From 1161624f15f584096a0df3dda70403cd1d00721e Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 11 Feb 2010 14:43:14 +0200
Subject: KVM: inject #UD in 64bit mode from instruction that are not valid
 there

Some instruction are obsolete in a long mode. Inject #UD.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4dade6ac0827..96d4bef06e14 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1015,11 +1015,6 @@ done_prefixes:
 		}
 	}
 
-	if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
-		kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");
-		return -1;
-	}
-
 	if (c->d & Group) {
 		group = c->d & GroupMask;
 		c->modrm = insn_fetch(u8, 1, c->eip);
@@ -1828,6 +1823,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 	saved_eip = c->eip;
 
+	if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		goto done;
+	}
+
 	/* LOCK prefix is allowed only with some instructions */
 	if (c->lock_prefix && !(c->d & Lock)) {
 		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
-- 
cgit v1.2.3


From 3e2815e9fa6c06bcb8a9340e43008bbe48437d25 Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Date: Fri, 12 Feb 2010 15:53:59 +0900
Subject: KVM: x86 emulator: X86EMUL macro replacements: from
 do_fetch_insn_byte() to x86_decode_insn()

This patch just replaces the integer values used inside x86's
decode functions to X86EMUL_*.

By this patch, it becomes clearer that we are using X86EMUL_*
value propagated from ops->read_std() in do_fetch_insn_byte().

Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 96d4bef06e14..b8aed35ab5f9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -647,20 +647,20 @@ static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt,
 	if (linear < fc->start || linear >= fc->end) {
 		size = min(15UL, PAGE_SIZE - offset_in_page(linear));
 		rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL);
-		if (rc)
+		if (rc != X86EMUL_CONTINUE)
 			return rc;
 		fc->start = linear;
 		fc->end = linear + size;
 	}
 	*dest = fc->data[linear - fc->start];
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 			 struct x86_emulate_ops *ops,
 			 unsigned long eip, void *dest, unsigned size)
 {
-	int rc = 0;
+	int rc;
 
 	/* x86 instructions are limited to 15 bytes. */
 	if (eip + size - ctxt->decode.eip_orig > 15)
@@ -668,10 +668,10 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 	eip += ctxt->cs_base;
 	while (size--) {
 		rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++);
-		if (rc)
+		if (rc != X86EMUL_CONTINUE)
 			return rc;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 /*
@@ -782,7 +782,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	struct decode_cache *c = &ctxt->decode;
 	u8 sib;
 	int index_reg = 0, base_reg = 0, scale;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	if (c->rex_prefix) {
 		c->modrm_reg = (c->rex_prefix & 4) << 1;	/* REX.R */
@@ -895,7 +895,7 @@ static int decode_abs(struct x86_emulate_ctxt *ctxt,
 		      struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	switch (c->ad_bytes) {
 	case 2:
@@ -916,7 +916,7 @@ int
 x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 	int mode = ctxt->mode;
 	int def_op_bytes, def_ad_bytes, group;
 
@@ -1041,7 +1041,7 @@ done_prefixes:
 		rc = decode_modrm(ctxt, ops);
 	else if (c->d & MemAbs)
 		rc = decode_abs(ctxt, ops);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
 	if (!c->has_seg_override)
-- 
cgit v1.2.3


From 1b30eaa84609031c06e417eafd5b68f45e4266f7 Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Date: Fri, 12 Feb 2010 15:57:56 +0900
Subject: KVM: x86 emulator: X86EMUL macro replacements: x86_emulate_insn() and
 its helpers

This patch just replaces integer values used inside
x86_emulate_insn() and its helper functions to X86EMUL_*.

The purpose of this is to make it clear what will happen
when the variable rc is compared to X86EMUL_* at the end
of x86_emulate_insn().

Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 62 +++++++++++++++++++++++---------------------------
 1 file changed, 29 insertions(+), 33 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b8aed35ab5f9..ee1a2a2c12e9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -702,7 +702,7 @@ static int read_descriptor(struct x86_emulate_ctxt *ctxt,
 	*address = 0;
 	rc = ops->read_std((unsigned long)ptr, (unsigned long *)size, 2,
 			   ctxt->vcpu, NULL);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = ops->read_std((unsigned long)ptr + 2, address, op_bytes,
 			   ctxt->vcpu, NULL);
@@ -1301,7 +1301,7 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt,
 	int rc;
 
 	rc = emulate_pop(ctxt, ops, &selector, c->op_bytes);
-	if (rc != 0)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
 	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg);
@@ -1327,7 +1327,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt,
 			struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 	int reg = VCPU_REGS_RDI;
 
 	while (reg >= VCPU_REGS_RAX) {
@@ -1338,7 +1338,7 @@ static int emulate_popa(struct x86_emulate_ctxt *ctxt,
 		}
 
 		rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			break;
 		--reg;
 	}
@@ -1349,12 +1349,8 @@ static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
 				struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc;
 
-	rc = emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes);
-	if (rc != 0)
-		return rc;
-	return 0;
+	return emulate_pop(ctxt, ops, &c->dst.val, c->dst.bytes);
 }
 
 static inline void emulate_grp2(struct x86_emulate_ctxt *ctxt)
@@ -1390,7 +1386,7 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	switch (c->modrm_reg) {
 	case 0 ... 1:	/* test */
@@ -1437,7 +1433,7 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
 		emulate_push(ctxt);
 		break;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
@@ -1468,7 +1464,7 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 			return rc;
 		ctxt->eflags |= EFLG_ZF;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
@@ -1479,12 +1475,12 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
 	unsigned long cs;
 
 	rc = emulate_pop(ctxt, ops, &c->eip, c->op_bytes);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	if (c->op_bytes == 4)
 		c->eip = (u32)c->eip;
 	rc = emulate_pop(ctxt, ops, &cs, c->op_bytes);
-	if (rc)
+	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS);
 	return rc;
@@ -1539,7 +1535,7 @@ static inline int writeback(struct x86_emulate_ctxt *ctxt,
 	default:
 		break;
 	}
-	return 0;
+	return X86EMUL_CONTINUE;
 }
 
 static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
@@ -1811,7 +1807,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	struct decode_cache *c = &ctxt->decode;
 	unsigned int port;
 	int io_dir_in;
-	int rc = 0;
+	int rc = X86EMUL_CONTINUE;
 
 	ctxt->interruptibility = 0;
 
@@ -1926,7 +1922,7 @@ special_insn:
 		break;
 	case 0x07:		/* pop es */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x08 ... 0x0d:
@@ -1945,7 +1941,7 @@ special_insn:
 		break;
 	case 0x17:		/* pop ss */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x18 ... 0x1d:
@@ -1957,7 +1953,7 @@ special_insn:
 		break;
 	case 0x1f:		/* pop ds */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x20 ... 0x25:
@@ -1988,7 +1984,7 @@ special_insn:
 	case 0x58 ... 0x5f: /* pop reg */
 	pop_instruction:
 		rc = emulate_pop(ctxt, ops, &c->dst.val, c->op_bytes);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x60:	/* pusha */
@@ -1996,7 +1992,7 @@ special_insn:
 		break;
 	case 0x61:	/* popa */
 		rc = emulate_popa(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x63:		/* movsxd */
@@ -2141,7 +2137,7 @@ special_insn:
 	}
 	case 0x8f:		/* pop (sole member of Grp1a) */
 		rc = emulate_grp1a(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0x90: /* nop / xchg r8,rax */
@@ -2277,7 +2273,7 @@ special_insn:
 		break;
 	case 0xcb:		/* ret far */
 		rc = emulate_ret_far(ctxt, ops);
-		if (rc)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xd0 ... 0xd1:	/* Grp2 */
@@ -2351,7 +2347,7 @@ special_insn:
 		break;
 	case 0xf6 ... 0xf7:	/* Grp3 */
 		rc = emulate_grp3(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xf8: /* clc */
@@ -2385,14 +2381,14 @@ special_insn:
 		break;
 	case 0xfe ... 0xff:	/* Grp4/Grp5 */
 		rc = emulate_grp45(ctxt, ops);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	}
 
 writeback:
 	rc = writeback(ctxt, ops);
-	if (rc != 0)
+	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
 	/* Commit shadow register state. */
@@ -2418,7 +2414,7 @@ twobyte_insn:
 				goto cannot_emulate;
 
 			rc = kvm_fix_hypercall(ctxt->vcpu);
-			if (rc)
+			if (rc != X86EMUL_CONTINUE)
 				goto done;
 
 			/* Let the processor re-execute the fixed hypercall */
@@ -2429,7 +2425,7 @@ twobyte_insn:
 		case 2: /* lgdt */
 			rc = read_descriptor(ctxt, ops, c->src.ptr,
 					     &size, &address, c->op_bytes);
-			if (rc)
+			if (rc != X86EMUL_CONTINUE)
 				goto done;
 			realmode_lgdt(ctxt->vcpu, size, address);
 			/* Disable writeback. */
@@ -2440,7 +2436,7 @@ twobyte_insn:
 				switch (c->modrm_rm) {
 				case 1:
 					rc = kvm_fix_hypercall(ctxt->vcpu);
-					if (rc)
+					if (rc != X86EMUL_CONTINUE)
 						goto done;
 					break;
 				default:
@@ -2450,7 +2446,7 @@ twobyte_insn:
 				rc = read_descriptor(ctxt, ops, c->src.ptr,
 						     &size, &address,
 						     c->op_bytes);
-				if (rc)
+				if (rc != X86EMUL_CONTINUE)
 					goto done;
 				realmode_lidt(ctxt->vcpu, size, address);
 			}
@@ -2577,7 +2573,7 @@ twobyte_insn:
 		break;
 	case 0xa1:	 /* pop fs */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xa3:
@@ -2596,7 +2592,7 @@ twobyte_insn:
 		break;
 	case 0xa9:	/* pop gs */
 		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
 	case 0xab:
@@ -2669,7 +2665,7 @@ twobyte_insn:
 		break;
 	case 0xc7:		/* Grp9 (cmpxchg8b) */
 		rc = emulate_grp9(ctxt, ops, memop);
-		if (rc != 0)
+		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		c->dst.type = OP_NONE;
 		break;
-- 
cgit v1.2.3


From 0e4176a15f9af494ad098cb5a76bcfa17e14282b Mon Sep 17 00:00:00 2001
From: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Date: Fri, 12 Feb 2010 16:00:55 +0900
Subject: KVM: x86 emulator: Fix x86_emulate_insn() not to use the variable rc
 for non-X86EMUL values

This patch makes non-X86EMUL_* family functions not to use
the variable rc.

Be sure that this changes nothing but makes the purpose of
the variable rc clearer.

Signed-off-by: Takuya Yoshikawa <yoshikawa.takuya@oss.ntt.co.jp>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ee1a2a2c12e9..35f7acd4a91f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2498,9 +2498,9 @@ twobyte_insn:
 	case 0x21: /* mov from dr to reg */
 		if (c->modrm_mod != 3)
 			goto cannot_emulate;
-		rc = emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]);
-		if (rc)
+		if (emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]))
 			goto cannot_emulate;
+		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x22: /* mov reg, cr */
@@ -2513,18 +2513,16 @@ twobyte_insn:
 	case 0x23: /* mov from reg to dr */
 		if (c->modrm_mod != 3)
 			goto cannot_emulate;
-		rc = emulator_set_dr(ctxt, c->modrm_reg,
-				     c->regs[c->modrm_rm]);
-		if (rc)
+		if (emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]))
 			goto cannot_emulate;
+		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x30:
 		/* wrmsr */
 		msr_data = (u32)c->regs[VCPU_REGS_RAX]
 			| ((u64)c->regs[VCPU_REGS_RDX] << 32);
-		rc = kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data);
-		if (rc) {
+		if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			c->eip = kvm_rip_read(ctxt->vcpu);
 		}
@@ -2533,8 +2531,7 @@ twobyte_insn:
 		break;
 	case 0x32:
 		/* rdmsr */
-		rc = kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data);
-		if (rc) {
+		if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			c->eip = kvm_rip_read(ctxt->vcpu);
 		} else {
-- 
cgit v1.2.3


From 48005f64d0ea965d454e38b5181af4aba9bdef5b Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Fri, 19 Feb 2010 19:38:07 +0100
Subject: KVM: x86: Save&restore interrupt shadow mask

The interrupt shadow created by STI or MOV-SS-like operations is part of
the VCPU state and must be preserved across migration. Transfer it in
the spare padding field of kvm_vcpu_events.interrupt.

As a side effect we now have to make vmx_set_interrupt_shadow robust
against both shadow types being set. Give MOV SS a higher priority and
skip STI in that case to avoid that VMX throws a fault on next entry.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 Documentation/kvm/api.txt          | 11 ++++++++++-
 arch/x86/include/asm/kvm.h         |  7 ++++++-
 arch/x86/include/asm/kvm_emulate.h |  3 ---
 arch/x86/kvm/emulate.c             |  4 ++--
 arch/x86/kvm/svm.c                 |  2 +-
 arch/x86/kvm/vmx.c                 |  8 ++++----
 arch/x86/kvm/x86.c                 | 12 ++++++++++--
 include/linux/kvm.h                |  1 +
 8 files changed, 34 insertions(+), 14 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index beb444a95013..9e5de5a1c4ef 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -656,6 +656,7 @@ struct kvm_clock_data {
 4.29 KVM_GET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (out)
@@ -676,7 +677,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 soft;
-		__u8 pad;
+		__u8 shadow;
 	} interrupt;
 	struct {
 		__u8 injected;
@@ -688,9 +689,13 @@ struct kvm_vcpu_events {
 	__u32 flags;
 };
 
+KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+interrupt.shadow contains a valid state. Otherwise, this field is undefined.
+
 4.30 KVM_SET_VCPU_EVENTS
 
 Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
 Architectures: x86
 Type: vm ioctl
 Parameters: struct kvm_vcpu_event (in)
@@ -709,6 +714,10 @@ current in-kernel state. The bits are:
 KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
 KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
 
+If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
+the flags field to signal that interrupt.shadow contains a valid state and
+shall be written into the VCPU.
+
 
 5. The kvm_run structure
 
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index f46b79f6c16c..fb6117063ea3 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -257,6 +257,11 @@ struct kvm_reinject_control {
 /* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
 #define KVM_VCPUEVENT_VALID_NMI_PENDING	0x00000001
 #define KVM_VCPUEVENT_VALID_SIPI_VECTOR	0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS	0x01
+#define KVM_X86_SHADOW_INT_STI		0x02
 
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
@@ -271,7 +276,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 soft;
-		__u8 pad;
+		__u8 shadow;
 	} interrupt;
 	struct {
 		__u8 injected;
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7a6f54fa13ba..2666d7ac3229 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -153,9 +153,6 @@ struct decode_cache {
 	struct fetch_cache fetch;
 };
 
-#define X86_SHADOW_INT_MOV_SS  1
-#define X86_SHADOW_INT_STI     2
-
 struct x86_emulate_ctxt {
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 35f7acd4a91f..c9f604b0819c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2128,7 +2128,7 @@ special_insn:
 		}
 
 		if (c->modrm_reg == VCPU_SREG_SS)
-			toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS);
+			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_MOV_SS);
 
 		rc = kvm_load_segment_descriptor(ctxt->vcpu, sel, c->modrm_reg);
 
@@ -2366,7 +2366,7 @@ special_insn:
 		if (emulator_bad_iopl(ctxt))
 			kvm_inject_gp(ctxt->vcpu, 0);
 		else {
-			toggle_interruptibility(ctxt, X86_SHADOW_INT_STI);
+			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI);
 			ctxt->eflags |= X86_EFLAGS_IF;
 			c->dst.type = OP_NONE;	/* Disable writeback. */
 		}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 294bbca34173..bd8f52f0823f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -265,7 +265,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	u32 ret = 0;
 
 	if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
-		ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+		ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
 	return ret & mask;
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 68f895b00450..61f03980adae 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -846,9 +846,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 	int ret = 0;
 
 	if (interruptibility & GUEST_INTR_STATE_STI)
-		ret |= X86_SHADOW_INT_STI;
+		ret |= KVM_X86_SHADOW_INT_STI;
 	if (interruptibility & GUEST_INTR_STATE_MOV_SS)
-		ret |= X86_SHADOW_INT_MOV_SS;
+		ret |= KVM_X86_SHADOW_INT_MOV_SS;
 
 	return ret & mask;
 }
@@ -860,9 +860,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
 
 	interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
 
-	if (mask & X86_SHADOW_INT_MOV_SS)
+	if (mask & KVM_X86_SHADOW_INT_MOV_SS)
 		interruptibility |= GUEST_INTR_STATE_MOV_SS;
-	if (mask & X86_SHADOW_INT_STI)
+	else if (mask & KVM_X86_SHADOW_INT_STI)
 		interruptibility |= GUEST_INTR_STATE_STI;
 
 	if ((interruptibility != interruptibility_old))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2b1c9f2fb8dd..84ffd95ee198 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2111,6 +2111,9 @@ 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->nmi.injected = vcpu->arch.nmi_injected;
 	events->nmi.pending = vcpu->arch.nmi_pending;
@@ -2119,7 +2122,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	events->sipi_vector = vcpu->arch.sipi_vector;
 
 	events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
-			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
+			 | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+			 | KVM_VCPUEVENT_VALID_SHADOW);
 
 	vcpu_put(vcpu);
 }
@@ -2128,7 +2132,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
 {
 	if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
-			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
+			      | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+			      | KVM_VCPUEVENT_VALID_SHADOW))
 		return -EINVAL;
 
 	vcpu_load(vcpu);
@@ -2143,6 +2148,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 	vcpu->arch.interrupt.soft = events->interrupt.soft;
 	if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
 		kvm_pic_clear_isr_ack(vcpu->kvm);
+	if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
+		kvm_x86_ops->set_interrupt_shadow(vcpu,
+						  events->interrupt.shadow);
 
 	vcpu->arch.nmi_injected = events->nmi.injected;
 	if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 360f85e8c435..48516a2a0b84 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -502,6 +502,7 @@ struct kvm_ioeventfd {
 #define KVM_CAP_HYPERV_SPIN 46
 #define KVM_CAP_PCI_SEGMENT 47
 #define KVM_CAP_PPC_PAIRED_SINGLES 48
+#define KVM_CAP_INTR_SHADOW 49
 #define KVM_CAP_X86_ROBUST_SINGLESTEP 51
 
 #ifdef KVM_CAP_IRQ_ROUTING
-- 
cgit v1.2.3


From e35b7b9c9e7d8768ee34e5904fed4cb0f2c2cb5d Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 25 Feb 2010 16:36:42 +0200
Subject: KVM: x86 emulator: Add decoding of 16bit second in memory argument

Add decoding of Ep type of argument used by callf/jmpf.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c9f604b0819c..97a740368b30 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -85,6 +85,9 @@
 #define Src2ImmByte (2<<29)
 #define Src2One     (3<<29)
 #define Src2Imm16   (4<<29)
+#define Src2Mem16   (5<<29) /* Used for Ep encoding. First argument has to be
+			       in memory and second argument is located
+			       immediately after the first one in memory. */
 #define Src2Mask    (7<<29)
 
 enum {
@@ -1163,6 +1166,10 @@ done_prefixes:
 		c->src2.bytes = 1;
 		c->src2.val = 1;
 		break;
+	case Src2Mem16:
+		c->src2.bytes = 2;
+		c->src2.type = OP_MEM;
+		break;
 	}
 
 	/* Decode and fetch the destination operand: register or memory. */
@@ -1881,6 +1888,17 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		c->src.orig_val = c->src.val;
 	}
 
+	if (c->src2.type == OP_MEM) {
+		c->src2.ptr = (unsigned long *)(memop + c->src.bytes);
+		c->src2.val = 0;
+		rc = ops->read_emulated((unsigned long)c->src2.ptr,
+					&c->src2.val,
+					c->src2.bytes,
+					ctxt->vcpu);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
+	}
+
 	if ((c->d & DstMask) == ImplicitOps)
 		goto special_insn;
 
-- 
cgit v1.2.3


From ea79849d4c8461034b75acb19c8041b6fddee2a5 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 25 Feb 2010 16:36:43 +0200
Subject: KVM: x86 emulator: Implement jmp far opcode ff/5

Implement jmp far opcode ff/5. It is used by multiboot loader.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 97a740368b30..5b6794adaa2e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -346,7 +346,8 @@ static u32 group_table[] = {
 	[Group5*8] =
 	DstMem | SrcNone | ModRM, DstMem | SrcNone | ModRM,
 	SrcMem | ModRM | Stack, 0,
-	SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0,
+	SrcMem | ModRM | Stack, SrcMem | ModRM | Src2Mem16 | ImplicitOps,
+	SrcMem | ModRM | Stack, 0,
 	[Group7*8] =
 	0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv,
 	SrcNone | ModRM | DstMem | Mov, 0,
@@ -2322,6 +2323,7 @@ special_insn:
 	case 0xe9: /* jmp rel */
 		goto jmp;
 	case 0xea: /* jmp far */
+	jump_far:
 		if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val,
 						VCPU_SREG_CS))
 			goto done;
@@ -2397,11 +2399,16 @@ special_insn:
 		ctxt->eflags |= EFLG_DF;
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
-	case 0xfe ... 0xff:	/* Grp4/Grp5 */
+	case 0xfe: /* Grp4 */
+	grp45:
 		rc = emulate_grp45(ctxt, ops);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		break;
+	case 0xff: /* Grp5 */
+		if (c->modrm_reg == 5)
+			goto jump_far;
+		goto grp45;
 	}
 
 writeback:
-- 
cgit v1.2.3


From 835e6b80478e59820cff127adba3e518ae5a43f5 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Wed, 3 Mar 2010 17:53:05 +0200
Subject: KVM: x86 emulator mark VMMCALL and LMSW as privileged

LMSW is present in both group tables. It was marked privileged only in
one of them. Intel analog of VMMCALL is already marked privileged.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5b6794adaa2e..2832a8c07c6a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -362,9 +362,9 @@ static u32 group_table[] = {
 
 static u32 group2_table[] = {
 	[Group7*8] =
-	SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM,
+	SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM | Priv,
 	SrcNone | ModRM | DstMem | Mov, 0,
-	SrcMem16 | ModRM | Mov, 0,
+	SrcMem16 | ModRM | Mov | Priv, 0,
 	[Group9*8] =
 	0, 0, 0, 0, 0, 0, 0, 0,
 };
-- 
cgit v1.2.3


From d6d367d6783e38634377bc66b62bff3ffd717e5f Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Mon, 15 Mar 2010 16:38:28 +0200
Subject: KVM: x86 emulator: Fix DstAcc decoding.

Set correct operation length. Add RAX (64bit) handling.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2832a8c07c6a..0b70a364f0f4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1194,9 +1194,9 @@ done_prefixes:
 		break;
 	case DstAcc:
 		c->dst.type = OP_REG;
-		c->dst.bytes = c->op_bytes;
+		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 		c->dst.ptr = &c->regs[VCPU_REGS_RAX];
-		switch (c->op_bytes) {
+		switch (c->dst.bytes) {
 			case 1:
 				c->dst.val = *(u8 *)c->dst.ptr;
 				break;
@@ -1206,6 +1206,9 @@ done_prefixes:
 			case 4:
 				c->dst.val = *(u32 *)c->dst.ptr;
 				break;
+			case 8:
+				c->dst.val = *(u64 *)c->dst.ptr;
+				break;
 		}
 		c->dst.orig_val = c->dst.val;
 		break;
-- 
cgit v1.2.3


From c73e197bc525e67b71578126b679446f5b88b508 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Mon, 15 Mar 2010 16:38:29 +0200
Subject: KVM: x86 emulator: fix RCX access during rep emulation

During rep emulation access length to RCX depends on current address
mode.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0b70a364f0f4..4dce80560d26 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1852,7 +1852,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 
 	if (c->rep_prefix && (c->d & String)) {
 		/* All REP prefixes have the same first termination condition */
-		if (c->regs[VCPU_REGS_RCX] == 0) {
+		if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
 			kvm_rip_write(ctxt->vcpu, c->eip);
 			goto done;
 		}
@@ -1876,7 +1876,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				goto done;
 			}
 		}
-		c->regs[VCPU_REGS_RCX]--;
+		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
 		c->eip = kvm_rip_read(ctxt->vcpu);
 	}
 
-- 
cgit v1.2.3


From af5b4f7ff7ec76400b89db9538accd9aeb996da4 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Mon, 15 Mar 2010 16:38:30 +0200
Subject: KVM: x86 emulator: check return value against correct define

Check return value against correct define instead of open code
the value.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4dce80560d26..670ca8f151d2 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -566,7 +566,7 @@ static u32 group2_table[] = {
 #define insn_fetch(_type, _size, _eip)                                  \
 ({	unsigned long _x;						\
 	rc = do_insn_fetch(ctxt, ops, (_eip), &_x, (_size));		\
-	if (rc != 0)							\
+	if (rc != X86EMUL_CONTINUE)					\
 		goto done;						\
 	(_eip) += (_size);						\
 	(_type)_x;							\
-- 
cgit v1.2.3


From 49c6799a2ce3a6a4dd66021dabeb468901c7a700 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Mon, 15 Mar 2010 16:38:31 +0200
Subject: KVM: Remove pointer to rflags from realmode_set_cr parameters.

Mov reg, cr instruction doesn't change flags in any meaningful way, so
no need to update rflags after instruction execution.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 3 +--
 arch/x86/kvm/emulate.c          | 3 +--
 arch/x86/kvm/x86.c              | 4 +---
 3 files changed, 3 insertions(+), 7 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 28826c82d1e2..53f520259471 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -587,8 +587,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 		   unsigned long *rflags);
 
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
-		     unsigned long *rflags);
+void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value);
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 670ca8f151d2..91450b5cd49e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2534,8 +2534,7 @@ twobyte_insn:
 	case 0x22: /* mov reg, cr */
 		if (c->modrm_mod != 3)
 			goto cannot_emulate;
-		realmode_set_cr(ctxt->vcpu,
-				c->modrm_reg, c->modrm_val, &ctxt->eflags);
+		realmode_set_cr(ctxt->vcpu, c->modrm_reg, c->modrm_val);
 		c->dst.type = OP_NONE;
 		break;
 	case 0x23: /* mov from reg to dr */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index dd4a7ad63aff..35db4f0db4ea 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4080,13 +4080,11 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
 	return value;
 }
 
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
-		     unsigned long *rflags)
+void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val)
 {
 	switch (cr) {
 	case 0:
 		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
-		*rflags = kvm_get_rflags(vcpu);
 		break;
 	case 2:
 		vcpu->arch.cr2 = val;
-- 
cgit v1.2.3


From 52a4661737ecc918633f6b05c611a4af4b5eae5a Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:03 +0200
Subject: KVM: Provide callback to get/set control registers in emulator ops.

Use this callback instead of directly call kvm function. Also rename
realmode_(set|get)_cr to emulator_(set|get)_cr since function has nothing
to do with real mode.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |   3 +-
 arch/x86/include/asm/kvm_host.h    |   2 -
 arch/x86/kvm/emulate.c             |   7 +--
 arch/x86/kvm/x86.c                 | 114 +++++++++++++++++++------------------
 4 files changed, 63 insertions(+), 63 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 2666d7ac3229..0c5caa469eb8 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -108,7 +108,8 @@ struct x86_emulate_ops {
 				const void *new,
 				unsigned int bytes,
 				struct kvm_vcpu *vcpu);
-
+	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
+	void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 53f520259471..9d474c7ae261 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -586,8 +586,6 @@ void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 		   unsigned long *rflags);
 
-unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value);
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 91450b5cd49e..5b060e4be0e3 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2483,7 +2483,7 @@ twobyte_insn:
 			break;
 		case 4: /* smsw */
 			c->dst.bytes = 2;
-			c->dst.val = realmode_get_cr(ctxt->vcpu, 0);
+			c->dst.val = ops->get_cr(0, ctxt->vcpu);
 			break;
 		case 6: /* lmsw */
 			realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
@@ -2519,8 +2519,7 @@ twobyte_insn:
 	case 0x20: /* mov cr, reg */
 		if (c->modrm_mod != 3)
 			goto cannot_emulate;
-		c->regs[c->modrm_rm] =
-				realmode_get_cr(ctxt->vcpu, c->modrm_reg);
+		c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x21: /* mov from dr to reg */
@@ -2534,7 +2533,7 @@ twobyte_insn:
 	case 0x22: /* mov reg, cr */
 		if (c->modrm_mod != 3)
 			goto cannot_emulate;
-		realmode_set_cr(ctxt->vcpu, c->modrm_reg, c->modrm_val);
+		ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu);
 		c->dst.type = OP_NONE;
 		break;
 	case 0x23: /* mov from reg to dr */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 35db4f0db4ea..94a29759ab2c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3423,12 +3423,70 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
 }
 EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
 
+static u64 mk_cr_64(u64 curr_cr, u32 new_val)
+{
+	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
+}
+
+static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu)
+{
+	unsigned long value;
+
+	switch (cr) {
+	case 0:
+		value = kvm_read_cr0(vcpu);
+		break;
+	case 2:
+		value = vcpu->arch.cr2;
+		break;
+	case 3:
+		value = vcpu->arch.cr3;
+		break;
+	case 4:
+		value = kvm_read_cr4(vcpu);
+		break;
+	case 8:
+		value = kvm_get_cr8(vcpu);
+		break;
+	default:
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+		return 0;
+	}
+
+	return value;
+}
+
+static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu)
+{
+	switch (cr) {
+	case 0:
+		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
+		break;
+	case 2:
+		vcpu->arch.cr2 = val;
+		break;
+	case 3:
+		kvm_set_cr3(vcpu, val);
+		break;
+	case 4:
+		kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
+		break;
+	case 8:
+		kvm_set_cr8(vcpu, val & 0xfUL);
+		break;
+	default:
+		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
+	}
+}
+
 static struct x86_emulate_ops emulate_ops = {
 	.read_std            = kvm_read_guest_virt_system,
 	.fetch               = kvm_fetch_guest_virt,
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
+	.get_cr              = emulator_get_cr,
+	.set_cr              = emulator_set_cr,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
@@ -4026,11 +4084,6 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
 	return __emulator_write_emulated(rip, instruction, 3, vcpu, false);
 }
 
-static u64 mk_cr_64(u64 curr_cr, u32 new_val)
-{
-	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
-}
-
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 {
 	struct desc_ptr dt = { limit, base };
@@ -4052,57 +4105,6 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 	*rflags = kvm_get_rflags(vcpu);
 }
 
-unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
-{
-	unsigned long value;
-
-	switch (cr) {
-	case 0:
-		value = kvm_read_cr0(vcpu);
-		break;
-	case 2:
-		value = vcpu->arch.cr2;
-		break;
-	case 3:
-		value = vcpu->arch.cr3;
-		break;
-	case 4:
-		value = kvm_read_cr4(vcpu);
-		break;
-	case 8:
-		value = kvm_get_cr8(vcpu);
-		break;
-	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
-		return 0;
-	}
-
-	return value;
-}
-
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val)
-{
-	switch (cr) {
-	case 0:
-		kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
-		break;
-	case 2:
-		vcpu->arch.cr2 = val;
-		break;
-	case 3:
-		kvm_set_cr3(vcpu, val);
-		break;
-	case 4:
-		kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
-		break;
-	case 8:
-		kvm_set_cr8(vcpu, val & 0xfUL);
-		break;
-	default:
-		vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
-	}
-}
-
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-- 
cgit v1.2.3


From 93a152be5af3d651ff0ab5459f5e0f9662b22438 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:04 +0200
Subject: KVM: remove realmode_lmsw function.

Use (get|set)_cr callback to emulate lmsw inside emulator.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_host.h | 2 --
 arch/x86/kvm/emulate.c          | 4 ++--
 arch/x86/kvm/x86.c              | 7 -------
 3 files changed, 2 insertions(+), 11 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9d474c7ae261..b99cec1547c6 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -583,8 +583,6 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
-		   unsigned long *rflags);
 
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5b060e4be0e3..5e2fa61e8104 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2486,8 +2486,8 @@ twobyte_insn:
 			c->dst.val = ops->get_cr(0, ctxt->vcpu);
 			break;
 		case 6: /* lmsw */
-			realmode_lmsw(ctxt->vcpu, (u16)c->src.val,
-				      &ctxt->eflags);
+			ops->set_cr(0, (ops->get_cr(0, ctxt->vcpu) & ~0x0ful) |
+				    (c->src.val & 0x0f), ctxt->vcpu);
 			c->dst.type = OP_NONE;
 			break;
 		case 7: /* invlpg*/
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 94a29759ab2c..c382e9721099 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4098,13 +4098,6 @@ void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
 	kvm_x86_ops->set_idt(vcpu, &dt);
 }
 
-void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
-		   unsigned long *rflags)
-{
-	kvm_lmsw(vcpu, msw);
-	*rflags = kvm_get_rflags(vcpu);
-}
-
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-- 
cgit v1.2.3


From 9c5372445c1ad4fcdb4128957ec89334223b8113 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:05 +0200
Subject: KVM: Provide x86_emulate_ctxt callback to get current cpl

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |  1 +
 arch/x86/kvm/emulate.c             | 15 ++++++++-------
 arch/x86/kvm/x86.c                 |  6 ++++++
 3 files changed, 15 insertions(+), 7 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0c5caa469eb8..b048fd21c54e 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -110,6 +110,7 @@ struct x86_emulate_ops {
 				struct kvm_vcpu *vcpu);
 	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
 	void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
+	int (*cpl)(struct kvm_vcpu *vcpu);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5e2fa61e8104..8bd05571672c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1257,7 +1257,7 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt,
 	int rc;
 	unsigned long val, change_mask;
 	int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
-	int cpl = kvm_x86_ops->get_cpl(ctxt->vcpu);
+	int cpl = ops->cpl(ctxt->vcpu);
 
 	rc = emulate_pop(ctxt, ops, &val, len);
 	if (rc != X86EMUL_CONTINUE)
@@ -1758,7 +1758,8 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
-static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
+static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt,
+			      struct x86_emulate_ops *ops)
 {
 	int iopl;
 	if (ctxt->mode == X86EMUL_MODE_REAL)
@@ -1766,7 +1767,7 @@ static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_VM86)
 		return true;
 	iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
-	return kvm_x86_ops->get_cpl(ctxt->vcpu) > iopl;
+	return ops->cpl(ctxt->vcpu) > iopl;
 }
 
 static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt,
@@ -1803,7 +1804,7 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt,
 				 struct x86_emulate_ops *ops,
 				 u16 port, u16 len)
 {
-	if (emulator_bad_iopl(ctxt))
+	if (emulator_bad_iopl(ctxt, ops))
 		if (!emulator_io_port_access_allowed(ctxt, ops, port, len))
 			return false;
 	return true;
@@ -1842,7 +1843,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	/* Privileged instruction can be executed only in CPL=0 */
-	if ((c->d & Priv) && kvm_x86_ops->get_cpl(ctxt->vcpu)) {
+	if ((c->d & Priv) && ops->cpl(ctxt->vcpu)) {
 		kvm_inject_gp(ctxt->vcpu, 0);
 		goto done;
 	}
@@ -2378,7 +2379,7 @@ special_insn:
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xfa: /* cli */
-		if (emulator_bad_iopl(ctxt))
+		if (emulator_bad_iopl(ctxt, ops))
 			kvm_inject_gp(ctxt->vcpu, 0);
 		else {
 			ctxt->eflags &= ~X86_EFLAGS_IF;
@@ -2386,7 +2387,7 @@ special_insn:
 		}
 		break;
 	case 0xfb: /* sti */
-		if (emulator_bad_iopl(ctxt))
+		if (emulator_bad_iopl(ctxt, ops))
 			kvm_inject_gp(ctxt->vcpu, 0);
 		else {
 			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c382e9721099..9cb28a943c9a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3479,6 +3479,11 @@ static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu)
 	}
 }
 
+static int emulator_get_cpl(struct kvm_vcpu *vcpu)
+{
+	return kvm_x86_ops->get_cpl(vcpu);
+}
+
 static struct x86_emulate_ops emulate_ops = {
 	.read_std            = kvm_read_guest_virt_system,
 	.fetch               = kvm_fetch_guest_virt,
@@ -3487,6 +3492,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
+	.cpl                 = emulator_get_cpl,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
-- 
cgit v1.2.3


From 063db061b9b3472c925f09ae3a0a8359b80c2295 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:06 +0200
Subject: KVM: Provide current eip as part of emulator context.

Eliminate the need to call back into KVM to get it from emulator.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |  3 ++-
 arch/x86/kvm/emulate.c             | 12 ++++++------
 arch/x86/kvm/x86.c                 |  1 +
 3 files changed, 9 insertions(+), 7 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b048fd21c54e..07657258af8f 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -141,7 +141,7 @@ struct decode_cache {
 	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
-	unsigned long eip, eip_orig;
+	unsigned long eip;
 	/* modrm */
 	u8 modrm;
 	u8 modrm_mod;
@@ -160,6 +160,7 @@ struct x86_emulate_ctxt {
 	struct kvm_vcpu *vcpu;
 
 	unsigned long eflags;
+	unsigned long eip; /* eip before instruction emulation */
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
 	u32 cs_base;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8bd05571672c..2c27aa466cf4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -667,7 +667,7 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 	int rc;
 
 	/* x86 instructions are limited to 15 bytes. */
-	if (eip + size - ctxt->decode.eip_orig > 15)
+	if (eip + size - ctxt->eip > 15)
 		return X86EMUL_UNHANDLEABLE;
 	eip += ctxt->cs_base;
 	while (size--) {
@@ -927,7 +927,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	/* Shadow copy of register state. Committed on successful emulation. */
 
 	memset(c, 0, sizeof(struct decode_cache));
-	c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu);
+	c->eip = ctxt->eip;
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 
@@ -1878,7 +1878,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 			}
 		}
 		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
-		c->eip = kvm_rip_read(ctxt->vcpu);
+		c->eip = ctxt->eip;
 	}
 
 	if (c->src.type == OP_MEM) {
@@ -2447,7 +2447,7 @@ twobyte_insn:
 				goto done;
 
 			/* Let the processor re-execute the fixed hypercall */
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			c->eip = ctxt->eip;
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
@@ -2551,7 +2551,7 @@ twobyte_insn:
 			| ((u64)c->regs[VCPU_REGS_RDX] << 32);
 		if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			c->eip = ctxt->eip;
 		}
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;
@@ -2560,7 +2560,7 @@ twobyte_insn:
 		/* rdmsr */
 		if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = kvm_rip_read(ctxt->vcpu);
+			c->eip = ctxt->eip;
 		} else {
 			c->regs[VCPU_REGS_RAX] = (u32)msr_data;
 			c->regs[VCPU_REGS_RDX] = msr_data >> 32;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9cb28a943c9a..0ecd37ac9d39 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3531,6 +3531,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 		vcpu->arch.emulate_ctxt.vcpu = vcpu;
 		vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+		vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
 		vcpu->arch.emulate_ctxt.mode =
 			(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
 			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
-- 
cgit v1.2.3


From 5e3ae6c5407ffb23bc4d9871e09d1b222e1b31a4 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:07 +0200
Subject: KVM: x86 emulator: fix mov r/m, sreg emulation.

mov r/m, sreg generates #UD ins sreg is incorrect.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2c27aa466cf4..c3b9334eb248 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2126,12 +2126,11 @@ special_insn:
 	case 0x8c: { /* mov r/m, sreg */
 		struct kvm_segment segreg;
 
-		if (c->modrm_reg <= 5)
+		if (c->modrm_reg <= VCPU_SREG_GS)
 			kvm_get_segment(ctxt->vcpu, &segreg, c->modrm_reg);
 		else {
-			printk(KERN_INFO "0x8c: Invalid segreg in modrm byte 0x%02x\n",
-			       c->modrm);
-			goto cannot_emulate;
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
 		}
 		c->dst.val = segreg.selector;
 		break;
-- 
cgit v1.2.3


From 6e1e5ffee8d95f9bce71eaa029cb5247b0f2f673 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:08 +0200
Subject: KVM: x86 emulator: fix 0f 01 /5 emulation

It is undefined and should generate #UD.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c3b9334eb248..7c7debb424df 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2490,6 +2490,9 @@ twobyte_insn:
 				    (c->src.val & 0x0f), ctxt->vcpu);
 			c->dst.type = OP_NONE;
 			break;
+		case 5: /* not defined */
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
 		case 7: /* invlpg*/
 			emulate_invlpg(ctxt->vcpu, memop);
 			/* Disable writeback. */
-- 
cgit v1.2.3


From ab8557b2b361c8bb2e2421c791c8f6c4f6ba3d08 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:09 +0200
Subject: KVM: x86 emulator: 0f (20|21|22|23) ignore mod bits.

Resent spec says that for 0f (20|21|22|23) the 2 bits in the mod field
are ignored. Interestingly enough older spec says that 11 is only valid
encoding.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7c7debb424df..fa4604e03250 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2520,28 +2520,20 @@ twobyte_insn:
 		c->dst.type = OP_NONE;
 		break;
 	case 0x20: /* mov cr, reg */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
 		c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x21: /* mov from dr to reg */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
 		if (emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]))
 			goto cannot_emulate;
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x22: /* mov reg, cr */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
 		ops->set_cr(c->modrm_reg, c->modrm_val, ctxt->vcpu);
 		c->dst.type = OP_NONE;
 		break;
 	case 0x23: /* mov from reg to dr */
-		if (c->modrm_mod != 3)
-			goto cannot_emulate;
 		if (emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]))
 			goto cannot_emulate;
 		rc = X86EMUL_CONTINUE;
-- 
cgit v1.2.3


From 6aebfa6ea75f9a02a0339e733090dd40d6f2edfd Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:10 +0200
Subject: KVM: x86 emulator: inject #UD on access to non-existing CR

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index fa4604e03250..836e97ba45da 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2520,6 +2520,13 @@ twobyte_insn:
 		c->dst.type = OP_NONE;
 		break;
 	case 0x20: /* mov cr, reg */
+		switch (c->modrm_reg) {
+		case 1:
+		case 5 ... 7:
+		case 9 ... 15:
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
 		c->regs[c->modrm_rm] = ops->get_cr(c->modrm_reg, ctxt->vcpu);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
-- 
cgit v1.2.3


From 1e470be5a10801cb1c5c145f2cd9e0f5ebaf4f2e Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:11 +0200
Subject: KVM: x86 emulator: fix mov dr to inject #UD when needed.

If CR4.DE=1 access to registers DR4/DR5 cause #UD.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 836e97ba45da..5afddcfa1a7e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2531,9 +2531,12 @@ twobyte_insn:
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x21: /* mov from dr to reg */
-		if (emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]))
-			goto cannot_emulate;
-		rc = X86EMUL_CONTINUE;
+		if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) &&
+		    (c->modrm_reg == 4 || c->modrm_reg == 5)) {
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
+		emulator_get_dr(ctxt, c->modrm_reg, &c->regs[c->modrm_rm]);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x22: /* mov reg, cr */
@@ -2541,9 +2544,12 @@ twobyte_insn:
 		c->dst.type = OP_NONE;
 		break;
 	case 0x23: /* mov from reg to dr */
-		if (emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]))
-			goto cannot_emulate;
-		rc = X86EMUL_CONTINUE;
+		if ((ops->get_cr(4, ctxt->vcpu) & X86_CR4_DE) &&
+		    (c->modrm_reg == 4 || c->modrm_reg == 5)) {
+			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+			goto done;
+		}
+		emulator_set_dr(ctxt, c->modrm_reg, c->regs[c->modrm_rm]);
 		c->dst.type = OP_NONE;	/* no writeback */
 		break;
 	case 0x30:
-- 
cgit v1.2.3


From 2e901c4cf4b550ad37840870246e835889cf7322 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:12 +0200
Subject: KVM: x86 emulator: fix return values of syscall/sysenter/sysexit
 emulations

Return X86EMUL_PROPAGATE_FAULT is fault was injected. Also inject #UD
for those instruction when appropriate.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5afddcfa1a7e..1393bf034243 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1600,8 +1600,11 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt)
 	u64 msr_data;
 
 	/* syscall is not available in real mode */
-	if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86)
-		return X86EMUL_UNHANDLEABLE;
+	if (ctxt->mode == X86EMUL_MODE_REAL ||
+	    ctxt->mode == X86EMUL_MODE_VM86) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
@@ -1651,14 +1654,16 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt)
 	/* inject #GP if in real mode */
 	if (ctxt->mode == X86EMUL_MODE_REAL) {
 		kvm_inject_gp(ctxt->vcpu, 0);
-		return X86EMUL_UNHANDLEABLE;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 	/* XXX sysenter/sysexit have not been tested in 64bit mode.
 	* Therefore, we inject an #UD.
 	*/
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		return X86EMUL_UNHANDLEABLE;
+	if (ctxt->mode == X86EMUL_MODE_PROT64) {
+		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
 
@@ -1713,7 +1718,7 @@ emulate_sysexit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->mode == X86EMUL_MODE_REAL ||
 	    ctxt->mode == X86EMUL_MODE_VM86) {
 		kvm_inject_gp(ctxt->vcpu, 0);
-		return X86EMUL_UNHANDLEABLE;
+		return X86EMUL_PROPAGATE_FAULT;
 	}
 
 	setup_syscalls_segments(ctxt, &cs, &ss);
-- 
cgit v1.2.3


From fd5253658b403d51fc19e56ecb44c54a3071fded Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:13 +0200
Subject: KVM: x86 emulator: do not call writeback if msr access fails.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 1393bf034243..b89a8f217332 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2563,7 +2563,7 @@ twobyte_insn:
 			| ((u64)c->regs[VCPU_REGS_RDX] << 32);
 		if (kvm_set_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = ctxt->eip;
+			goto done;
 		}
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;
@@ -2572,7 +2572,7 @@ twobyte_insn:
 		/* rdmsr */
 		if (kvm_get_msr(ctxt->vcpu, c->regs[VCPU_REGS_RCX], &msr_data)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
-			c->eip = ctxt->eip;
+			goto done;
 		} else {
 			c->regs[VCPU_REGS_RAX] = (u32)msr_data;
 			c->regs[VCPU_REGS_RDX] = msr_data >> 32;
-- 
cgit v1.2.3


From a41ffb7540cb37426759e688083502d6463421b2 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:14 +0200
Subject: KVM: x86 emulator: If LOCK prefix is used dest arg should be memory.

If LOCK prefix is used dest arg should be memory, otherwise instruction
should generate #UD.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b89a8f217332..46a7ee3040a0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1842,7 +1842,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	/* LOCK prefix is allowed only with some instructions */
-	if (c->lock_prefix && !(c->d & Lock)) {
+	if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) {
 		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
 		goto done;
 	}
-- 
cgit v1.2.3


From aca06a83071e4e4c9150751db7ea6a46240734fc Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:15 +0200
Subject: KVM: x86 emulator: cleanup grp3 return value

When x86_emulate_insn() does not know how to emulate instruction it
exits via cannot_emulate label in all cases except when emulating
grp3. Fix that.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 46a7ee3040a0..d696cbd6ff7a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1397,7 +1397,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	int rc = X86EMUL_CONTINUE;
 
 	switch (c->modrm_reg) {
 	case 0 ... 1:	/* test */
@@ -1410,11 +1409,9 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
 		emulate_1op("neg", c->dst, ctxt->eflags);
 		break;
 	default:
-		DPRINTF("Cannot emulate %02x\n", c->b);
-		rc = X86EMUL_UNHANDLEABLE;
-		break;
+		return 0;
 	}
-	return rc;
+	return 1;
 }
 
 static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
@@ -2374,9 +2371,8 @@ special_insn:
 		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xf6 ... 0xf7:	/* Grp3 */
-		rc = emulate_grp3(ctxt, ops);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
+		if (!emulate_grp3(ctxt, ops))
+			goto cannot_emulate;
 		break;
 	case 0xf8: /* clc */
 		ctxt->eflags &= ~EFLG_CF;
-- 
cgit v1.2.3


From 38ba30ba51a003360f177d5b8349439fe44fc55b Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:17 +0200
Subject: KVM: x86 emulator: Emulate task switch in emulator.c

Implement emulation of 16/32 bit task switch in emulator.c

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |   5 +
 arch/x86/kvm/emulate.c             | 563 +++++++++++++++++++++++++++++++++++++
 2 files changed, 568 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index f901467a18b0..bd469296f5e5 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -11,6 +11,8 @@
 #ifndef _ASM_X86_KVM_X86_EMULATE_H
 #define _ASM_X86_KVM_X86_EMULATE_H
 
+#include <asm/desc_defs.h>
+
 struct x86_emulate_ctxt;
 
 /*
@@ -210,5 +212,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
 		    struct x86_emulate_ops *ops);
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
 		     struct x86_emulate_ops *ops);
+int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
+			 struct x86_emulate_ops *ops,
+			 u16 tss_selector, int reason);
 
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d696cbd6ff7a..db4776c6b500 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -33,6 +33,7 @@
 #include <asm/kvm_emulate.h>
 
 #include "x86.h"
+#include "tss.h"
 
 /*
  * Opcode effective-address decode tables.
@@ -1221,6 +1222,198 @@ done:
 	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 }
 
+static u32 desc_limit_scaled(struct desc_struct *desc)
+{
+	u32 limit = get_desc_limit(desc);
+
+	return desc->g ? (limit << 12) | 0xfff : limit;
+}
+
+static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt,
+				     struct x86_emulate_ops *ops,
+				     u16 selector, struct desc_ptr *dt)
+{
+	if (selector & 1 << 2) {
+		struct desc_struct desc;
+		memset (dt, 0, sizeof *dt);
+		if (!ops->get_cached_descriptor(&desc, VCPU_SREG_LDTR, ctxt->vcpu))
+			return;
+
+		dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */
+		dt->address = get_desc_base(&desc);
+	} else
+		ops->get_gdt(dt, ctxt->vcpu);
+}
+
+/* allowed just for 8 bytes segments */
+static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   struct x86_emulate_ops *ops,
+				   u16 selector, struct desc_struct *desc)
+{
+	struct desc_ptr dt;
+	u16 index = selector >> 3;
+	int ret;
+	u32 err;
+	ulong addr;
+
+	get_descriptor_table_ptr(ctxt, ops, selector, &dt);
+
+	if (dt.size < index * 8 + 7) {
+		kvm_inject_gp(ctxt->vcpu, selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+	addr = dt.address + index * 8;
+	ret = ops->read_std(addr, desc, sizeof *desc, ctxt->vcpu,  &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(ctxt->vcpu, addr, err);
+
+       return ret;
+}
+
+/* allowed just for 8 bytes segments */
+static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				    struct x86_emulate_ops *ops,
+				    u16 selector, struct desc_struct *desc)
+{
+	struct desc_ptr dt;
+	u16 index = selector >> 3;
+	u32 err;
+	ulong addr;
+	int ret;
+
+	get_descriptor_table_ptr(ctxt, ops, selector, &dt);
+
+	if (dt.size < index * 8 + 7) {
+		kvm_inject_gp(ctxt->vcpu, selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+
+	addr = dt.address + index * 8;
+	ret = ops->write_std(addr, desc, sizeof *desc, ctxt->vcpu, &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT)
+		kvm_inject_page_fault(ctxt->vcpu, addr, err);
+
+	return ret;
+}
+
+static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
+				   struct x86_emulate_ops *ops,
+				   u16 selector, int seg)
+{
+	struct desc_struct seg_desc;
+	u8 dpl, rpl, cpl;
+	unsigned err_vec = GP_VECTOR;
+	u32 err_code = 0;
+	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
+	int ret;
+
+	memset(&seg_desc, 0, sizeof seg_desc);
+
+	if ((seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86)
+	    || ctxt->mode == X86EMUL_MODE_REAL) {
+		/* set real mode segment descriptor */
+		set_desc_base(&seg_desc, selector << 4);
+		set_desc_limit(&seg_desc, 0xffff);
+		seg_desc.type = 3;
+		seg_desc.p = 1;
+		seg_desc.s = 1;
+		goto load;
+	}
+
+	/* NULL selector is not valid for TR, CS and SS */
+	if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || 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 */
+		goto load;
+
+	ret = read_segment_descriptor(ctxt, ops, selector, &seg_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	err_code = selector & 0xfffc;
+	err_vec = GP_VECTOR;
+
+	/* can't load system descriptor into segment selecor */
+	if (seg <= VCPU_SREG_GS && !seg_desc.s)
+		goto exception;
+
+	if (!seg_desc.p) {
+		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
+		goto exception;
+	}
+
+	rpl = selector & 3;
+	dpl = seg_desc.dpl;
+	cpl = ops->cpl(ctxt->vcpu);
+
+	switch (seg) {
+	case VCPU_SREG_SS:
+		/*
+		 * segment is not a writable data segment or segment
+		 * selector's RPL != CPL or segment selector's RPL != CPL
+		 */
+		if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl)
+			goto exception;
+		break;
+	case VCPU_SREG_CS:
+		if (!(seg_desc.type & 8))
+			goto exception;
+
+		if (seg_desc.type & 4) {
+			/* conforming */
+			if (dpl > cpl)
+				goto exception;
+		} else {
+			/* nonconforming */
+			if (rpl > cpl || dpl != cpl)
+				goto exception;
+		}
+		/* CS(RPL) <- CPL */
+		selector = (selector & 0xfffc) | cpl;
+		break;
+	case VCPU_SREG_TR:
+		if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9))
+			goto exception;
+		break;
+	case VCPU_SREG_LDTR:
+		if (seg_desc.s || seg_desc.type != 2)
+			goto exception;
+		break;
+	default: /*  DS, ES, FS, or GS */
+		/*
+		 * segment is not a data or readable code segment or
+		 * ((segment is a data or nonconforming code segment)
+		 * and (both RPL and CPL > DPL))
+		 */
+		if ((seg_desc.type & 0xa) == 0x8 ||
+		    (((seg_desc.type & 0xc) != 0xc) &&
+		     (rpl > dpl && cpl > dpl)))
+			goto exception;
+		break;
+	}
+
+	if (seg_desc.s) {
+		/* mark segment as accessed */
+		seg_desc.type |= 1;
+		ret = write_segment_descriptor(ctxt, ops, selector, &seg_desc);
+		if (ret != X86EMUL_CONTINUE)
+			return ret;
+	}
+load:
+	ops->set_segment_selector(selector, seg, ctxt->vcpu);
+	ops->set_cached_descriptor(&seg_desc, seg, ctxt->vcpu);
+	return X86EMUL_CONTINUE;
+exception:
+	kvm_queue_exception_e(ctxt->vcpu, err_vec, err_code);
+	return X86EMUL_PROPAGATE_FAULT;
+}
+
 static inline void emulate_push(struct x86_emulate_ctxt *ctxt)
 {
 	struct decode_cache *c = &ctxt->decode;
@@ -1812,6 +2005,376 @@ static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt,
 	return true;
 }
 
+static u32 get_cached_descriptor_base(struct x86_emulate_ctxt *ctxt,
+				      struct x86_emulate_ops *ops,
+				      int seg)
+{
+	struct desc_struct desc;
+	if (ops->get_cached_descriptor(&desc, seg, ctxt->vcpu))
+		return get_desc_base(&desc);
+	else
+		return ~0;
+}
+
+static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt,
+				struct x86_emulate_ops *ops,
+				struct tss_segment_16 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+
+	tss->ip = c->eip;
+	tss->flag = ctxt->eflags;
+	tss->ax = c->regs[VCPU_REGS_RAX];
+	tss->cx = c->regs[VCPU_REGS_RCX];
+	tss->dx = c->regs[VCPU_REGS_RDX];
+	tss->bx = c->regs[VCPU_REGS_RBX];
+	tss->sp = c->regs[VCPU_REGS_RSP];
+	tss->bp = c->regs[VCPU_REGS_RBP];
+	tss->si = c->regs[VCPU_REGS_RSI];
+	tss->di = c->regs[VCPU_REGS_RDI];
+
+	tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu);
+	tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
+	tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu);
+	tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu);
+	tss->ldt = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu);
+}
+
+static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
+				 struct x86_emulate_ops *ops,
+				 struct tss_segment_16 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int ret;
+
+	c->eip = tss->ip;
+	ctxt->eflags = tss->flag | 2;
+	c->regs[VCPU_REGS_RAX] = tss->ax;
+	c->regs[VCPU_REGS_RCX] = tss->cx;
+	c->regs[VCPU_REGS_RDX] = tss->dx;
+	c->regs[VCPU_REGS_RBX] = tss->bx;
+	c->regs[VCPU_REGS_RSP] = tss->sp;
+	c->regs[VCPU_REGS_RBP] = tss->bp;
+	c->regs[VCPU_REGS_RSI] = tss->si;
+	c->regs[VCPU_REGS_RDI] = tss->di;
+
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	ops->set_segment_selector(tss->ldt, VCPU_SREG_LDTR, ctxt->vcpu);
+	ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu);
+	ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	ret = load_segment_descriptor(ctxt, ops, tss->ldt, VCPU_SREG_LDTR);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int task_switch_16(struct x86_emulate_ctxt *ctxt,
+			  struct x86_emulate_ops *ops,
+			  u16 tss_selector, u16 old_tss_sel,
+			  ulong old_tss_base, struct desc_struct *new_desc)
+{
+	struct tss_segment_16 tss_seg;
+	int ret;
+	u32 err, new_tss_base = get_desc_base(new_desc);
+
+	ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	save_state_to_tss16(ctxt, ops, &tss_seg);
+
+	ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			     &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+		return ret;
+	}
+
+	if (old_tss_sel != 0xffff) {
+		tss_seg.prev_task_link = old_tss_sel;
+
+		ret = ops->write_std(new_tss_base,
+				     &tss_seg.prev_task_link,
+				     sizeof tss_seg.prev_task_link,
+				     ctxt->vcpu, &err);
+		if (ret == X86EMUL_PROPAGATE_FAULT) {
+			/* FIXME: need to provide precise fault address */
+			kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+			return ret;
+		}
+	}
+
+	return load_state_from_tss16(ctxt, ops, &tss_seg);
+}
+
+static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt,
+				struct x86_emulate_ops *ops,
+				struct tss_segment_32 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+
+	tss->cr3 = ops->get_cr(3, ctxt->vcpu);
+	tss->eip = c->eip;
+	tss->eflags = ctxt->eflags;
+	tss->eax = c->regs[VCPU_REGS_RAX];
+	tss->ecx = c->regs[VCPU_REGS_RCX];
+	tss->edx = c->regs[VCPU_REGS_RDX];
+	tss->ebx = c->regs[VCPU_REGS_RBX];
+	tss->esp = c->regs[VCPU_REGS_RSP];
+	tss->ebp = c->regs[VCPU_REGS_RBP];
+	tss->esi = c->regs[VCPU_REGS_RSI];
+	tss->edi = c->regs[VCPU_REGS_RDI];
+
+	tss->es = ops->get_segment_selector(VCPU_SREG_ES, ctxt->vcpu);
+	tss->cs = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
+	tss->ss = ops->get_segment_selector(VCPU_SREG_SS, ctxt->vcpu);
+	tss->ds = ops->get_segment_selector(VCPU_SREG_DS, ctxt->vcpu);
+	tss->fs = ops->get_segment_selector(VCPU_SREG_FS, ctxt->vcpu);
+	tss->gs = ops->get_segment_selector(VCPU_SREG_GS, ctxt->vcpu);
+	tss->ldt_selector = ops->get_segment_selector(VCPU_SREG_LDTR, ctxt->vcpu);
+}
+
+static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
+				 struct x86_emulate_ops *ops,
+				 struct tss_segment_32 *tss)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int ret;
+
+	ops->set_cr(3, tss->cr3, ctxt->vcpu);
+	c->eip = tss->eip;
+	ctxt->eflags = tss->eflags | 2;
+	c->regs[VCPU_REGS_RAX] = tss->eax;
+	c->regs[VCPU_REGS_RCX] = tss->ecx;
+	c->regs[VCPU_REGS_RDX] = tss->edx;
+	c->regs[VCPU_REGS_RBX] = tss->ebx;
+	c->regs[VCPU_REGS_RSP] = tss->esp;
+	c->regs[VCPU_REGS_RBP] = tss->ebp;
+	c->regs[VCPU_REGS_RSI] = tss->esi;
+	c->regs[VCPU_REGS_RDI] = tss->edi;
+
+	/*
+	 * SDM says that segment selectors are loaded before segment
+	 * descriptors
+	 */
+	ops->set_segment_selector(tss->ldt_selector, VCPU_SREG_LDTR, ctxt->vcpu);
+	ops->set_segment_selector(tss->es, VCPU_SREG_ES, ctxt->vcpu);
+	ops->set_segment_selector(tss->cs, VCPU_SREG_CS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ss, VCPU_SREG_SS, ctxt->vcpu);
+	ops->set_segment_selector(tss->ds, VCPU_SREG_DS, ctxt->vcpu);
+	ops->set_segment_selector(tss->fs, VCPU_SREG_FS, ctxt->vcpu);
+	ops->set_segment_selector(tss->gs, VCPU_SREG_GS, ctxt->vcpu);
+
+	/*
+	 * Now load segment descriptors. If fault happenes at this stage
+	 * it is handled in a context of new task
+	 */
+	ret = load_segment_descriptor(ctxt, ops, tss->ldt_selector, VCPU_SREG_LDTR);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->es, VCPU_SREG_ES);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->cs, VCPU_SREG_CS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ss, VCPU_SREG_SS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->ds, VCPU_SREG_DS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->fs, VCPU_SREG_FS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = load_segment_descriptor(ctxt, ops, tss->gs, VCPU_SREG_GS);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	return X86EMUL_CONTINUE;
+}
+
+static int task_switch_32(struct x86_emulate_ctxt *ctxt,
+			  struct x86_emulate_ops *ops,
+			  u16 tss_selector, u16 old_tss_sel,
+			  ulong old_tss_base, struct desc_struct *new_desc)
+{
+	struct tss_segment_32 tss_seg;
+	int ret;
+	u32 err, new_tss_base = get_desc_base(new_desc);
+
+	ret = ops->read_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	save_state_to_tss32(ctxt, ops, &tss_seg);
+
+	ret = ops->write_std(old_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			     &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, old_tss_base, err);
+		return ret;
+	}
+
+	ret = ops->read_std(new_tss_base, &tss_seg, sizeof tss_seg, ctxt->vcpu,
+			    &err);
+	if (ret == X86EMUL_PROPAGATE_FAULT) {
+		/* FIXME: need to provide precise fault address */
+		kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+		return ret;
+	}
+
+	if (old_tss_sel != 0xffff) {
+		tss_seg.prev_task_link = old_tss_sel;
+
+		ret = ops->write_std(new_tss_base,
+				     &tss_seg.prev_task_link,
+				     sizeof tss_seg.prev_task_link,
+				     ctxt->vcpu, &err);
+		if (ret == X86EMUL_PROPAGATE_FAULT) {
+			/* FIXME: need to provide precise fault address */
+			kvm_inject_page_fault(ctxt->vcpu, new_tss_base, err);
+			return ret;
+		}
+	}
+
+	return load_state_from_tss32(ctxt, ops, &tss_seg);
+}
+
+static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
+				    struct x86_emulate_ops *ops,
+				    u16 tss_selector, int reason)
+{
+	struct desc_struct curr_tss_desc, next_tss_desc;
+	int ret;
+	u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu);
+	ulong old_tss_base =
+		get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR);
+
+	/* FIXME: old_tss_base == ~0 ? */
+
+	ret = read_segment_descriptor(ctxt, ops, tss_selector, &next_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+	ret = read_segment_descriptor(ctxt, ops, old_tss_sel, &curr_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
+
+	/* FIXME: check that next_tss_desc is tss */
+
+	if (reason != TASK_SWITCH_IRET) {
+		if ((tss_selector & 3) > next_tss_desc.dpl ||
+		    ops->cpl(ctxt->vcpu) > next_tss_desc.dpl) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return X86EMUL_PROPAGATE_FAULT;
+		}
+	}
+
+	if (!next_tss_desc.p || desc_limit_scaled(&next_tss_desc) < 0x67) {
+		kvm_queue_exception_e(ctxt->vcpu, TS_VECTOR,
+				      tss_selector & 0xfffc);
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+
+	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
+		curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */
+		write_segment_descriptor(ctxt, ops, old_tss_sel,
+					 &curr_tss_desc);
+	}
+
+	if (reason == TASK_SWITCH_IRET)
+		ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT;
+
+	/* set back link to prev task only if NT bit is set in eflags
+	   note that old_tss_sel is not used afetr this point */
+	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
+		old_tss_sel = 0xffff;
+
+	if (next_tss_desc.type & 8)
+		ret = task_switch_32(ctxt, ops, tss_selector, old_tss_sel,
+				     old_tss_base, &next_tss_desc);
+	else
+		ret = task_switch_16(ctxt, ops, tss_selector, old_tss_sel,
+				     old_tss_base, &next_tss_desc);
+
+	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE)
+		ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT;
+
+	if (reason != TASK_SWITCH_IRET) {
+		next_tss_desc.type |= (1 << 1); /* set busy flag */
+		write_segment_descriptor(ctxt, ops, tss_selector,
+					 &next_tss_desc);
+	}
+
+	ops->set_cr(0,  ops->get_cr(0, ctxt->vcpu) | X86_CR0_TS, ctxt->vcpu);
+	ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu);
+	ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu);
+
+	return ret;
+}
+
+int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
+			 struct x86_emulate_ops *ops,
+			 u16 tss_selector, int reason)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int rc;
+
+	memset(c, 0, sizeof(struct decode_cache));
+	c->eip = ctxt->eip;
+	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
+
+	rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason);
+
+	if (rc == X86EMUL_CONTINUE) {
+		memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
+		kvm_rip_write(ctxt->vcpu, c->eip);
+	}
+
+	return rc;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
-- 
cgit v1.2.3


From 2e873022f511b82a5318c7af179f588f08d68cb9 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:18 +0200
Subject: KVM: x86 emulator: Use load_segment_descriptor() instead of
 kvm_load_segment_descriptor()

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index db4776c6b500..702bffffd27f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1508,7 +1508,7 @@ static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt,
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, seg);
+	rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg);
 	return rc;
 }
 
@@ -1683,7 +1683,7 @@ static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
 	rc = emulate_pop(ctxt, ops, &cs, c->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
-	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)cs, VCPU_SREG_CS);
+	rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS);
 	return rc;
 }
 
@@ -2717,7 +2717,7 @@ special_insn:
 		if (c->modrm_reg == VCPU_SREG_SS)
 			toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_MOV_SS);
 
-		rc = kvm_load_segment_descriptor(ctxt->vcpu, sel, c->modrm_reg);
+		rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg);
 
 		c->dst.type = OP_NONE;  /* Disable writeback. */
 		break;
@@ -2892,8 +2892,8 @@ special_insn:
 		goto jmp;
 	case 0xea: /* jmp far */
 	jump_far:
-		if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val,
-						VCPU_SREG_CS))
+		if (load_segment_descriptor(ctxt, ops, c->src2.val,
+					    VCPU_SREG_CS))
 			goto done;
 
 		c->eip = c->src.val;
-- 
cgit v1.2.3


From ceffb4597253b2420d2f171d8b1cdf2cd3137989 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:19 +0200
Subject: KVM: Use task switch from emulator.c

Remove old task switch code from x86.c

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c |   6 +-
 arch/x86/kvm/x86.c     | 561 ++-----------------------------------------------
 2 files changed, 22 insertions(+), 545 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 702bffffd27f..8225ec26efed 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2291,6 +2291,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	u16 old_tss_sel = ops->get_segment_selector(VCPU_SREG_TR, ctxt->vcpu);
 	ulong old_tss_base =
 		get_cached_descriptor_base(ctxt, ops, VCPU_SREG_TR);
+	u32 desc_limit;
 
 	/* FIXME: old_tss_base == ~0 ? */
 
@@ -2311,7 +2312,10 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 		}
 	}
 
-	if (!next_tss_desc.p || desc_limit_scaled(&next_tss_desc) < 0x67) {
+	desc_limit = desc_limit_scaled(&next_tss_desc);
+	if (!next_tss_desc.p ||
+	    ((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
+	     desc_limit < 0x2b)) {
 		kvm_queue_exception_e(ctxt->vcpu, TS_VECTOR,
 				      tss_selector & 0xfffc);
 		return X86EMUL_PROPAGATE_FAULT;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fbee8fbb33b5..f69854c8f339 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4832,557 +4832,30 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
-				   struct kvm_segment *kvm_desct)
-{
-	kvm_desct->base = get_desc_base(seg_desc);
-	kvm_desct->limit = get_desc_limit(seg_desc);
-	if (seg_desc->g) {
-		kvm_desct->limit <<= 12;
-		kvm_desct->limit |= 0xfff;
-	}
-	kvm_desct->selector = selector;
-	kvm_desct->type = seg_desc->type;
-	kvm_desct->present = seg_desc->p;
-	kvm_desct->dpl = seg_desc->dpl;
-	kvm_desct->db = seg_desc->d;
-	kvm_desct->s = seg_desc->s;
-	kvm_desct->l = seg_desc->l;
-	kvm_desct->g = seg_desc->g;
-	kvm_desct->avl = seg_desc->avl;
-	if (!selector)
-		kvm_desct->unusable = 1;
-	else
-		kvm_desct->unusable = 0;
-	kvm_desct->padding = 0;
-}
-
-static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu,
-					  u16 selector,
-					  struct desc_ptr *dtable)
-{
-	if (selector & 1 << 2) {
-		struct kvm_segment kvm_seg;
-
-		kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
-
-		if (kvm_seg.unusable)
-			dtable->size = 0;
-		else
-			dtable->size = kvm_seg.limit;
-		dtable->address = kvm_seg.base;
-	}
-	else
-		kvm_x86_ops->get_gdt(vcpu, dtable);
-}
-
-/* allowed just for 8 bytes segments */
-static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-					 struct desc_struct *seg_desc)
-{
-	struct desc_ptr dtable;
-	u16 index = selector >> 3;
-	int ret;
-	u32 err;
-	gva_t addr;
-
-	get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
-	if (dtable.size < index * 8 + 7) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
-		return X86EMUL_PROPAGATE_FAULT;
-	}
-	addr = dtable.base + index * 8;
-	ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc),
-					 vcpu,  &err);
-	if (ret == X86EMUL_PROPAGATE_FAULT)
-		kvm_inject_page_fault(vcpu, addr, err);
-
-       return ret;
-}
-
-/* allowed just for 8 bytes segments */
-static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-					 struct desc_struct *seg_desc)
-{
-	struct desc_ptr dtable;
-	u16 index = selector >> 3;
-
-	get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
-	if (dtable.size < index * 8 + 7)
-		return 1;
-	return kvm_write_guest_virt(dtable.address + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL);
-}
-
-static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu,
-			       struct desc_struct *seg_desc)
-{
-	u32 base_addr = get_desc_base(seg_desc);
-
-	return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL);
-}
-
-static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu,
-			     struct desc_struct *seg_desc)
-{
-	u32 base_addr = get_desc_base(seg_desc);
-
-	return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL);
-}
-
-static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
-{
-	struct kvm_segment kvm_seg;
-
-	kvm_get_segment(vcpu, &kvm_seg, seg);
-	return kvm_seg.selector;
-}
-
-static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg)
-{
-	struct kvm_segment segvar = {
-		.base = selector << 4,
-		.limit = 0xffff,
-		.selector = selector,
-		.type = 3,
-		.present = 1,
-		.dpl = 3,
-		.db = 0,
-		.s = 1,
-		.l = 0,
-		.g = 0,
-		.avl = 0,
-		.unusable = 0,
-	};
-	kvm_x86_ops->set_segment(vcpu, &segvar, seg);
-	return X86EMUL_CONTINUE;
-}
-
-static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
-{
-	return (seg != VCPU_SREG_LDTR) &&
-		(seg != VCPU_SREG_TR) &&
-		(kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
-}
-
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg)
-{
-	struct kvm_segment kvm_seg;
-	struct desc_struct seg_desc;
-	u8 dpl, rpl, cpl;
-	unsigned err_vec = GP_VECTOR;
-	u32 err_code = 0;
-	bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */
-	int ret;
-
-	if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
-		return kvm_load_realmode_segment(vcpu, selector, seg);
-
-	/* NULL selector is not valid for TR, CS and SS */
-	if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR)
-	    && null_selector)
-		goto exception;
-
-	/* TR should be in GDT only */
-	if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
-		goto exception;
-
-	ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc);
-	if (ret)
-		return ret;
-
-	seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg);
-
-	if (null_selector) { /* for NULL selector skip all following checks */
-		kvm_seg.unusable = 1;
-		goto load;
-	}
-
-	err_code = selector & 0xfffc;
-	err_vec = GP_VECTOR;
-
-	/* can't load system descriptor into segment selecor */
-	if (seg <= VCPU_SREG_GS && !kvm_seg.s)
-		goto exception;
-
-	if (!kvm_seg.present) {
-		err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR;
-		goto exception;
-	}
-
-	rpl = selector & 3;
-	dpl = kvm_seg.dpl;
-	cpl = kvm_x86_ops->get_cpl(vcpu);
-
-	switch (seg) {
-	case VCPU_SREG_SS:
-		/*
-		 * segment is not a writable data segment or segment
-		 * selector's RPL != CPL or segment selector's RPL != CPL
-		 */
-		if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl)
-			goto exception;
-		break;
-	case VCPU_SREG_CS:
-		if (!(kvm_seg.type & 8))
-			goto exception;
-
-		if (kvm_seg.type & 4) {
-			/* conforming */
-			if (dpl > cpl)
-				goto exception;
-		} else {
-			/* nonconforming */
-			if (rpl > cpl || dpl != cpl)
-				goto exception;
-		}
-		/* CS(RPL) <- CPL */
-		selector = (selector & 0xfffc) | cpl;
-            break;
-	case VCPU_SREG_TR:
-		if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9))
-			goto exception;
-		break;
-	case VCPU_SREG_LDTR:
-		if (kvm_seg.s || kvm_seg.type != 2)
-			goto exception;
-		break;
-	default: /*  DS, ES, FS, or GS */
-		/*
-		 * segment is not a data or readable code segment or
-		 * ((segment is a data or nonconforming code segment)
-		 * and (both RPL and CPL > DPL))
-		 */
-		if ((kvm_seg.type & 0xa) == 0x8 ||
-		    (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl)))
-			goto exception;
-		break;
-	}
-
-	if (!kvm_seg.unusable && kvm_seg.s) {
-		/* mark segment as accessed */
-		kvm_seg.type |= 1;
-		seg_desc.type |= 1;
-		save_guest_segment_descriptor(vcpu, selector, &seg_desc);
-	}
-load:
-	kvm_set_segment(vcpu, &kvm_seg, seg);
-	return X86EMUL_CONTINUE;
-exception:
-	kvm_queue_exception_e(vcpu, err_vec, err_code);
-	return X86EMUL_PROPAGATE_FAULT;
-}
-
-static void save_state_to_tss32(struct kvm_vcpu *vcpu,
-				struct tss_segment_32 *tss)
-{
-	tss->cr3 = vcpu->arch.cr3;
-	tss->eip = kvm_rip_read(vcpu);
-	tss->eflags = kvm_get_rflags(vcpu);
-	tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP);
-	tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI);
-	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
-	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
-	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
-	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
-	tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS);
-	tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS);
-	tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-}
-
-static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg)
-{
-	struct kvm_segment kvm_seg;
-	kvm_get_segment(vcpu, &kvm_seg, seg);
-	kvm_seg.selector = sel;
-	kvm_set_segment(vcpu, &kvm_seg, seg);
-}
-
-static int load_state_from_tss32(struct kvm_vcpu *vcpu,
-				  struct tss_segment_32 *tss)
-{
-	kvm_set_cr3(vcpu, tss->cr3);
-
-	kvm_rip_write(vcpu, tss->eip);
-	kvm_set_rflags(vcpu, tss->eflags | 2);
-
-	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx);
-	kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi);
-
-	/*
-	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
-	 */
-	kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR);
-	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
-	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
-	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
-	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
-	kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS);
-	kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS);
-
-	/*
-	 * Now load segment descriptors. If fault happenes at this stage
-	 * it is handled in a context of new task
-	 */
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS))
-		return 1;
-	return 0;
-}
-
-static void save_state_to_tss16(struct kvm_vcpu *vcpu,
-				struct tss_segment_16 *tss)
-{
-	tss->ip = kvm_rip_read(vcpu);
-	tss->flag = kvm_get_rflags(vcpu);
-	tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-	tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX);
-	tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX);
-	tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX);
-	tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-	tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP);
-	tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI);
-	tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI);
-
-	tss->es = get_segment_selector(vcpu, VCPU_SREG_ES);
-	tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS);
-	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
-	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
-	tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-}
-
-static int load_state_from_tss16(struct kvm_vcpu *vcpu,
-				 struct tss_segment_16 *tss)
-{
-	kvm_rip_write(vcpu, tss->ip);
-	kvm_set_rflags(vcpu, tss->flag | 2);
-	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax);
-	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx);
-	kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx);
-	kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx);
-	kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp);
-	kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp);
-	kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si);
-	kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di);
-
-	/*
-	 * SDM says that segment selectors are loaded before segment
-	 * descriptors
-	 */
-	kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR);
-	kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES);
-	kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS);
-	kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS);
-	kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS);
-
-	/*
-	 * Now load segment descriptors. If fault happenes at this stage
-	 * it is handled in a context of new task
-	 */
-	if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS))
-		return 1;
-
-	if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS))
-		return 1;
-	return 0;
-}
-
-static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
-			      u16 old_tss_sel, u32 old_tss_base,
-			      struct desc_struct *nseg_desc)
-{
-	struct tss_segment_16 tss_segment_16;
-	int ret = 0;
-
-	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
-			   sizeof tss_segment_16))
-		goto out;
-
-	save_state_to_tss16(vcpu, &tss_segment_16);
-
-	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
-			    sizeof tss_segment_16))
-		goto out;
-
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
-			   &tss_segment_16, sizeof tss_segment_16))
-		goto out;
-
-	if (old_tss_sel != 0xffff) {
-		tss_segment_16.prev_task_link = old_tss_sel;
-
-		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr_write(vcpu, nseg_desc),
-				    &tss_segment_16.prev_task_link,
-				    sizeof tss_segment_16.prev_task_link))
-			goto out;
-	}
-
-	if (load_state_from_tss16(vcpu, &tss_segment_16))
-		goto out;
-
-	ret = 1;
-out:
-	return ret;
-}
-
-static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       u16 old_tss_sel, u32 old_tss_base,
-		       struct desc_struct *nseg_desc)
-{
-	struct tss_segment_32 tss_segment_32;
-	int ret = 0;
-
-	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
-			   sizeof tss_segment_32))
-		goto out;
-
-	save_state_to_tss32(vcpu, &tss_segment_32);
-
-	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
-			    sizeof tss_segment_32))
-		goto out;
-
-	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc),
-			   &tss_segment_32, sizeof tss_segment_32))
-		goto out;
-
-	if (old_tss_sel != 0xffff) {
-		tss_segment_32.prev_task_link = old_tss_sel;
-
-		if (kvm_write_guest(vcpu->kvm,
-				    get_tss_base_addr_write(vcpu, nseg_desc),
-				    &tss_segment_32.prev_task_link,
-				    sizeof tss_segment_32.prev_task_link))
-			goto out;
-	}
-
-	if (load_state_from_tss32(vcpu, &tss_segment_32))
-		goto out;
-
-	ret = 1;
-out:
-	return ret;
-}
-
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 {
-	struct kvm_segment tr_seg;
-	struct desc_struct cseg_desc;
-	struct desc_struct nseg_desc;
-	int ret = 0;
-	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
-	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
-	u32 desc_limit;
-
-	old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
-
-	/* FIXME: Handle errors. Failure to read either TSS or their
-	 * descriptors should generate a pagefault.
-	 */
-	if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
-		goto out;
-
-	if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc))
-		goto out;
-
-	if (reason != TASK_SWITCH_IRET) {
-		int cpl;
-
-		cpl = kvm_x86_ops->get_cpl(vcpu);
-		if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) {
-			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-			return 1;
-		}
-	}
-
-	desc_limit = get_desc_limit(&nseg_desc);
-	if (!nseg_desc.p ||
-	    ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
-	     desc_limit < 0x2b)) {
-		kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
-		return 1;
-	}
-
-	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
-		cseg_desc.type &= ~(1 << 1); //clear the B flag
-		save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc);
-	}
-
-	if (reason == TASK_SWITCH_IRET) {
-		u32 eflags = kvm_get_rflags(vcpu);
-		kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
-	}
+	int cs_db, cs_l, ret;
+	cache_all_regs(vcpu);
 
-	/* set back link to prev task only if NT bit is set in eflags
-	   note that old_tss_sel is not used afetr this point */
-	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
-		old_tss_sel = 0xffff;
+	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
-	if (nseg_desc.type & 8)
-		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel,
-					 old_tss_base, &nseg_desc);
-	else
-		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel,
-					 old_tss_base, &nseg_desc);
+	vcpu->arch.emulate_ctxt.vcpu = vcpu;
+	vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+	vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu);
+	vcpu->arch.emulate_ctxt.mode =
+		(!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
+		(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
+		? X86EMUL_MODE_VM86 : cs_l
+		? X86EMUL_MODE_PROT64 :	cs_db
+		? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
-	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
-		u32 eflags = kvm_get_rflags(vcpu);
-		kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
-	}
+	ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops,
+				   tss_selector, reason);
 
-	if (reason != TASK_SWITCH_IRET) {
-		nseg_desc.type |= (1 << 1);
-		save_guest_segment_descriptor(vcpu, tss_selector,
-					      &nseg_desc);
-	}
+	if (ret == X86EMUL_CONTINUE)
+		kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
 
-	kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS);
-	seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg);
-	tr_seg.type = 11;
-	kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR);
-out:
-	return ret;
+	return (ret != X86EMUL_CONTINUE);
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
-- 
cgit v1.2.3


From 69f55cb11e8d789433d111ac3a0f60be37a1ae01 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:20 +0200
Subject: KVM: x86 emulator: populate OP_MEM operand during decoding.

All struct operand fields are initialized during decoding for all
operand types except OP_MEM, but there is no reason for that. Move
OP_MEM operand initialization into decoding stage for consistency.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 66 ++++++++++++++++++++++----------------------------
 1 file changed, 29 insertions(+), 37 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8225ec26efed..0eed6839619f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1057,6 +1057,10 @@ done_prefixes:
 
 	if (c->ad_bytes != 8)
 		c->modrm_ea = (u32)c->modrm_ea;
+
+	if (c->rip_relative)
+		c->modrm_ea += c->eip;
+
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -1091,6 +1095,8 @@ done_prefixes:
 			break;
 		}
 		c->src.type = OP_MEM;
+		c->src.ptr = (unsigned long *)c->modrm_ea;
+		c->src.val = 0;
 		break;
 	case SrcImm:
 	case SrcImmU:
@@ -1169,8 +1175,10 @@ done_prefixes:
 		c->src2.val = 1;
 		break;
 	case Src2Mem16:
-		c->src2.bytes = 2;
 		c->src2.type = OP_MEM;
+		c->src2.bytes = 2;
+		c->src2.ptr = (unsigned long *)(c->modrm_ea + c->src.bytes);
+		c->src2.val = 0;
 		break;
 	}
 
@@ -1192,6 +1200,15 @@ done_prefixes:
 			break;
 		}
 		c->dst.type = OP_MEM;
+		c->dst.ptr = (unsigned long *)c->modrm_ea;
+		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->dst.val = 0;
+		if (c->d & BitOp) {
+			unsigned long mask = ~(c->dst.bytes * 8 - 1);
+
+			c->dst.ptr = (void *)c->dst.ptr +
+						   (c->src.val & mask) / 8;
+		}
 		break;
 	case DstAcc:
 		c->dst.type = OP_REG;
@@ -1215,9 +1232,6 @@ done_prefixes:
 		break;
 	}
 
-	if (c->rip_relative)
-		c->modrm_ea += c->eip;
-
 done:
 	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 }
@@ -1638,14 +1652,13 @@ static inline int emulate_grp45(struct x86_emulate_ctxt *ctxt,
 }
 
 static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
-			       struct x86_emulate_ops *ops,
-			       unsigned long memop)
+			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
 	u64 old, new;
 	int rc;
 
-	rc = ops->read_emulated(memop, &old, 8, ctxt->vcpu);
+	rc = ops->read_emulated(c->modrm_ea, &old, 8, ctxt->vcpu);
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -1660,7 +1673,7 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 		new = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
 		       (u32) c->regs[VCPU_REGS_RBX];
 
-		rc = ops->cmpxchg_emulated(memop, &old, &new, 8, ctxt->vcpu);
+		rc = ops->cmpxchg_emulated(c->modrm_ea, &old, &new, 8, ctxt->vcpu);
 		if (rc != X86EMUL_CONTINUE)
 			return rc;
 		ctxt->eflags |= EFLG_ZF;
@@ -2382,7 +2395,6 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
-	unsigned long memop = 0;
 	u64 msr_data;
 	unsigned long saved_eip = 0;
 	struct decode_cache *c = &ctxt->decode;
@@ -2417,9 +2429,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		goto done;
 	}
 
-	if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs))
-		memop = c->modrm_ea;
-
 	if (c->rep_prefix && (c->d & String)) {
 		/* All REP prefixes have the same first termination condition */
 		if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
@@ -2451,8 +2460,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	if (c->src.type == OP_MEM) {
-		c->src.ptr = (unsigned long *)memop;
-		c->src.val = 0;
 		rc = ops->read_emulated((unsigned long)c->src.ptr,
 					&c->src.val,
 					c->src.bytes,
@@ -2463,8 +2470,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	if (c->src2.type == OP_MEM) {
-		c->src2.ptr = (unsigned long *)(memop + c->src.bytes);
-		c->src2.val = 0;
 		rc = ops->read_emulated((unsigned long)c->src2.ptr,
 					&c->src2.val,
 					c->src2.bytes,
@@ -2477,25 +2482,12 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		goto special_insn;
 
 
-	if (c->dst.type == OP_MEM) {
-		c->dst.ptr = (unsigned long *)memop;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.val = 0;
-		if (c->d & BitOp) {
-			unsigned long mask = ~(c->dst.bytes * 8 - 1);
-
-			c->dst.ptr = (void *)c->dst.ptr +
-						   (c->src.val & mask) / 8;
-		}
-		if (!(c->d & Mov)) {
-			/* optimisation - avoid slow emulated read */
-			rc = ops->read_emulated((unsigned long)c->dst.ptr,
-						&c->dst.val,
-						c->dst.bytes,
-						ctxt->vcpu);
-			if (rc != X86EMUL_CONTINUE)
-				goto done;
-		}
+	if ((c->dst.type == OP_MEM) && !(c->d & Mov)) {
+		/* optimisation - avoid slow emulated read if Mov */
+		rc = ops->read_emulated((unsigned long)c->dst.ptr, &c->dst.val,
+					c->dst.bytes, ctxt->vcpu);
+		if (rc != X86EMUL_CONTINUE)
+			goto done;
 	}
 	c->dst.orig_val = c->dst.val;
 
@@ -3062,7 +3054,7 @@ twobyte_insn:
 			kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
 			goto done;
 		case 7: /* invlpg*/
-			emulate_invlpg(ctxt->vcpu, memop);
+			emulate_invlpg(ctxt->vcpu, c->modrm_ea);
 			/* Disable writeback. */
 			c->dst.type = OP_NONE;
 			break;
@@ -3263,7 +3255,7 @@ twobyte_insn:
 							(u64) c->src.val;
 		break;
 	case 0xc7:		/* Grp9 (cmpxchg8b) */
-		rc = emulate_grp9(ctxt, ops, memop);
+		rc = emulate_grp9(ctxt, ops);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
 		c->dst.type = OP_NONE;
-- 
cgit v1.2.3


From a682e35449abc83d260a8219015c7cb4b25ecced Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:21 +0200
Subject: KVM: x86 emulator: add decoding of X,Y parameters from Intel SDM

Add decoding of X,Y parameters from Intel SDM which are used by string
instruction to specify source and destination. Use this new decoding
to implement movs, cmps, stos, lods in a generic way.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 125 +++++++++++++++++--------------------------------
 1 file changed, 44 insertions(+), 81 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0eed6839619f..3b32270a20db 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -51,6 +51,7 @@
 #define DstReg      (2<<1)	/* Register operand. */
 #define DstMem      (3<<1)	/* Memory operand. */
 #define DstAcc      (4<<1)      /* Destination Accumulator */
+#define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
 #define DstMask     (7<<1)
 /* Source operand type. */
 #define SrcNone     (0<<4)	/* No source operand. */
@@ -64,6 +65,7 @@
 #define SrcOne      (7<<4)	/* Implied '1' */
 #define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
 #define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
+#define SrcSI       (0xa<<4)	/* Source is in the DS:RSI */
 #define SrcMask     (0xf<<4)
 /* Generic ModRM decode. */
 #define ModRM       (1<<8)
@@ -177,12 +179,12 @@ static u32 opcode_table[256] = {
 	/* 0xA0 - 0xA7 */
 	ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs,
 	ByteOp | DstMem | SrcReg | Mov | MemAbs, DstMem | SrcReg | Mov | MemAbs,
-	ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | String, ImplicitOps | String,
+	ByteOp | SrcSI | DstDI | Mov | String, SrcSI | DstDI | Mov | String,
+	ByteOp | SrcSI | DstDI | String, SrcSI | DstDI | String,
 	/* 0xA8 - 0xAF */
-	0, 0, ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | Mov | String, ImplicitOps | Mov | String,
-	ByteOp | ImplicitOps | String, ImplicitOps | String,
+	0, 0, ByteOp | DstDI | Mov | String, DstDI | Mov | String,
+	ByteOp | SrcSI | DstAcc | Mov | String, SrcSI | DstAcc | Mov | String,
+	ByteOp | DstDI | String, DstDI | String,
 	/* 0xB0 - 0xB7 */
 	ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov,
 	ByteOp | DstReg | SrcImm | Mov, ByteOp | DstReg | SrcImm | Mov,
@@ -1145,6 +1147,14 @@ done_prefixes:
 		c->src.bytes = 1;
 		c->src.val = 1;
 		break;
+	case SrcSI:
+		c->src.type = OP_MEM;
+		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->src.ptr = (unsigned long *)
+			register_address(c,  seg_override_base(ctxt, c),
+					 c->regs[VCPU_REGS_RSI]);
+		c->src.val = 0;
+		break;
 	}
 
 	/*
@@ -1230,6 +1240,14 @@ done_prefixes:
 		}
 		c->dst.orig_val = c->dst.val;
 		break;
+	case DstDI:
+		c->dst.type = OP_MEM;
+		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		c->dst.ptr = (unsigned long *)
+			register_address(c, es_base(ctxt),
+					 c->regs[VCPU_REGS_RDI]);
+		c->dst.val = 0;
+		break;
 	}
 
 done:
@@ -2392,6 +2410,16 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
+static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base,
+			    int reg, unsigned long **ptr)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int df = (ctxt->eflags & EFLG_DF) ? -1 : 1;
+
+	register_address_increment(c, &c->regs[reg], df * c->src.bytes);
+	*ptr = (unsigned long *)register_address(c,  base, c->regs[reg]);
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
@@ -2754,89 +2782,16 @@ special_insn:
 		c->dst.val = (unsigned long)c->regs[VCPU_REGS_RAX];
 		break;
 	case 0xa4 ... 0xa5:	/* movs */
-		c->dst.type = OP_MEM;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
-		rc = ops->read_emulated(register_address(c,
-						seg_override_base(ctxt, c),
-						c->regs[VCPU_REGS_RSI]),
-					&c->dst.val,
-					c->dst.bytes, ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		break;
+		goto mov;
 	case 0xa6 ... 0xa7:	/* cmps */
-		c->src.type = OP_NONE; /* Disable writeback. */
-		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->src.ptr = (unsigned long *)register_address(c,
-				       seg_override_base(ctxt, c),
-						   c->regs[VCPU_REGS_RSI]);
-		rc = ops->read_emulated((unsigned long)c->src.ptr,
-					&c->src.val,
-					c->src.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-
 		c->dst.type = OP_NONE; /* Disable writeback. */
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
-		rc = ops->read_emulated((unsigned long)c->dst.ptr,
-					&c->dst.val,
-					c->dst.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-
 		DPRINTF("cmps: mem1=0x%p mem2=0x%p\n", c->src.ptr, c->dst.ptr);
-
-		emulate_2op_SrcV("cmp", c->src, c->dst, ctxt->eflags);
-
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->src.bytes
-								  : c->src.bytes);
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-								  : c->dst.bytes);
-
-		break;
+		goto cmp;
 	case 0xaa ... 0xab:	/* stos */
-		c->dst.type = OP_MEM;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)register_address(c,
-						   es_base(ctxt),
-						   c->regs[VCPU_REGS_RDI]);
 		c->dst.val = c->regs[VCPU_REGS_RAX];
-		register_address_increment(c, &c->regs[VCPU_REGS_RDI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
 		break;
 	case 0xac ... 0xad:	/* lods */
-		c->dst.type = OP_REG;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
-		c->dst.ptr = (unsigned long *)&c->regs[VCPU_REGS_RAX];
-		rc = ops->read_emulated(register_address(c,
-						seg_override_base(ctxt, c),
-						c->regs[VCPU_REGS_RSI]),
-					&c->dst.val,
-					c->dst.bytes,
-					ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			goto done;
-		register_address_increment(c, &c->regs[VCPU_REGS_RSI],
-				       (ctxt->eflags & EFLG_DF) ? -c->dst.bytes
-							   : c->dst.bytes);
-		break;
+		goto mov;
 	case 0xae ... 0xaf:	/* scas */
 		DPRINTF("Urk! I don't handle SCAS.\n");
 		goto cannot_emulate;
@@ -2979,6 +2934,14 @@ writeback:
 	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
+	if ((c->d & SrcMask) == SrcSI)
+		string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
+				&c->src.ptr);
+
+	if ((c->d & DstMask) == DstDI)
+		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI,
+				&c->dst.ptr);
+
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
 	kvm_rip_write(ctxt->vcpu, c->eip);
-- 
cgit v1.2.3


From d9271123a46011af26da680baeb7fdf67b498abf Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:22 +0200
Subject: KVM: x86 emulator: during rep emulation decrement ECX only if
 emulation succeeded

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 3b32270a20db..594574d8b9e9 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2411,13 +2411,13 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 }
 
 static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base,
-			    int reg, unsigned long **ptr)
+			    int reg, struct operand *op)
 {
 	struct decode_cache *c = &ctxt->decode;
 	int df = (ctxt->eflags & EFLG_DF) ? -1 : 1;
 
-	register_address_increment(c, &c->regs[reg], df * c->src.bytes);
-	*ptr = (unsigned long *)register_address(c,  base, c->regs[reg]);
+	register_address_increment(c, &c->regs[reg], df * op->bytes);
+	op->ptr = (unsigned long *)register_address(c,  base, c->regs[reg]);
 }
 
 int
@@ -2483,7 +2483,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 				goto done;
 			}
 		}
-		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
 		c->eip = ctxt->eip;
 	}
 
@@ -2936,11 +2935,13 @@ writeback:
 
 	if ((c->d & SrcMask) == SrcSI)
 		string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
-				&c->src.ptr);
+				&c->src);
 
 	if ((c->d & DstMask) == DstDI)
-		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI,
-				&c->dst.ptr);
+		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
+
+	if (c->rep_prefix && (c->d & String))
+		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
 
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
-- 
cgit v1.2.3


From cf8f70bfe38b326bb80b10f76d6544f571040229 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:23 +0200
Subject: KVM: x86 emulator: fix in/out emulation.

in/out emulation is broken now. The breakage is different depending
on where IO device resides. If it is in userspace emulator reports
emulation failure since it incorrectly interprets kvm_emulate_pio()
return value. If IO device is in the kernel emulation of 'in' will do
nothing since kvm_emulate_pio() stores result directly into vcpu
registers, so emulator will overwrite result of emulation during
commit of shadowed register.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |   7 ++
 arch/x86/include/asm/kvm_host.h    |   3 +-
 arch/x86/kvm/emulate.c             |  50 +++++----
 arch/x86/kvm/svm.c                 |  20 ++--
 arch/x86/kvm/vmx.c                 |  18 ++--
 arch/x86/kvm/x86.c                 | 213 +++++++++++++++++++++++--------------
 6 files changed, 178 insertions(+), 133 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index bd469296f5e5..679245c9a55f 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -119,6 +119,13 @@ struct x86_emulate_ops {
 				const void *new,
 				unsigned int bytes,
 				struct kvm_vcpu *vcpu);
+
+	int (*pio_in_emulated)(int size, unsigned short port, void *val,
+			       unsigned int count, struct kvm_vcpu *vcpu);
+
+	int (*pio_out_emulated)(int size, unsigned short port, const void *val,
+				unsigned int count, struct kvm_vcpu *vcpu);
+
 	bool (*get_cached_descriptor)(struct desc_struct *desc,
 				      int seg, struct kvm_vcpu *vcpu);
 	void (*set_cached_descriptor)(struct desc_struct *desc,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b99cec1547c6..776d3e202b56 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -590,8 +590,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
 struct x86_emulate_ctxt;
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
-		     int size, unsigned port);
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
 int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 			   int size, unsigned long count, int down,
 			    gva_t address, int rep, unsigned port);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 594574d8b9e9..2d095ce9dc87 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -210,13 +210,13 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xE0 - 0xE7 */
 	0, 0, 0, 0,
-	ByteOp | SrcImmUByte, SrcImmUByte,
-	ByteOp | SrcImmUByte, SrcImmUByte,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
 	SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
 	ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3,
@@ -2426,8 +2426,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	u64 msr_data;
 	unsigned long saved_eip = 0;
 	struct decode_cache *c = &ctxt->decode;
-	unsigned int port;
-	int io_dir_in;
 	int rc = X86EMUL_CONTINUE;
 
 	ctxt->interruptibility = 0;
@@ -2823,14 +2821,10 @@ special_insn:
 		break;
 	case 0xe4: 	/* inb */
 	case 0xe5: 	/* in */
-		port = c->src.val;
-		io_dir_in = 1;
-		goto do_io;
+		goto do_io_in;
 	case 0xe6: /* outb */
 	case 0xe7: /* out */
-		port = c->src.val;
-		io_dir_in = 0;
-		goto do_io;
+		goto do_io_out;
 	case 0xe8: /* call (near) */ {
 		long int rel = c->src.val;
 		c->src.val = (unsigned long) c->eip;
@@ -2855,25 +2849,29 @@ special_insn:
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 1;
-		goto do_io;
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_in:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			goto done;
+		}
+		if (!ops->pio_in_emulated(c->dst.bytes, c->src.val,
+					  &c->dst.val, 1, ctxt->vcpu))
+			goto done; /* IO is needed */
+		break;
 	case 0xee: /* out al,dx */
 	case 0xef: /* out (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 0;
-	do_io:
-		if (!emulator_io_permited(ctxt, ops, port,
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_out:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio(ctxt->vcpu, io_dir_in,
-				   (c->d & ByteOp) ? 1 : c->op_bytes,
-				   port) != 0) {
-			c->eip = saved_eip;
-			goto cannot_emulate;
-		}
+		ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1,
+				      ctxt->vcpu);
+		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
 		ctxt->vcpu->arch.halt_request = 1;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index abbc3f9d03b2..e9f79619e185 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1494,29 +1494,23 @@ static int shutdown_interception(struct vcpu_svm *svm)
 
 static int io_interception(struct vcpu_svm *svm)
 {
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
 	int size, in, string;
 	unsigned port;
 
 	++svm->vcpu.stat.io_exits;
-
-	svm->next_rip = svm->vmcb->control.exit_info_2;
-
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
-
-	if (string) {
-		if (emulate_instruction(&svm->vcpu,
-					0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
-
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-
+	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
-	return kvm_emulate_pio(&svm->vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 87b3c6843aac..1cceca1c59be 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2985,22 +2985,20 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	int size, in, string;
 	unsigned port;
 
-	++vcpu->stat.io_exits;
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	string = (exit_qualification & 16) != 0;
+	in = (exit_qualification & 8) != 0;
 
-	if (string) {
-		if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
+	++vcpu->stat.io_exits;
 
-	size = (exit_qualification & 7) + 1;
-	in = (exit_qualification & 8) != 0;
-	port = exit_qualification >> 16;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
 
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
 	skip_emulated_instruction(vcpu);
-	return kvm_emulate_pio(vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static void
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f69854c8f339..6624ad13ee99 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3404,6 +3404,86 @@ emul_write:
 	return emulator_write_emulated(addr, new, bytes, vcpu);
 }
 
+static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
+{
+	/* TODO: String I/O for in kernel device */
+	int r;
+
+	if (vcpu->arch.pio.in)
+		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
+				    vcpu->arch.pio.size, pd);
+	else
+		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
+				     vcpu->arch.pio.port, vcpu->arch.pio.size,
+				     pd);
+	return r;
+}
+
+
+static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
+			     unsigned int count, struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.pio.cur_count)
+		goto data_avail;
+
+	trace_kvm_pio(1, port, size, 1);
+
+	vcpu->arch.pio.port = port;
+	vcpu->arch.pio.in = 1;
+	vcpu->arch.pio.string = 0;
+	vcpu->arch.pio.down = 0;
+	vcpu->arch.pio.rep = 0;
+	vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
+	vcpu->arch.pio.size = size;
+
+	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+	data_avail:
+		memcpy(val, vcpu->arch.pio_data, size * count);
+		vcpu->arch.pio.cur_count = 0;
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_IO;
+	vcpu->run->io.direction = KVM_EXIT_IO_IN;
+	vcpu->run->io.size = size;
+	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+	vcpu->run->io.count = count;
+	vcpu->run->io.port = port;
+
+	return 0;
+}
+
+static int emulator_pio_out_emulated(int size, unsigned short port,
+			      const void *val, unsigned int count,
+			      struct kvm_vcpu *vcpu)
+{
+	trace_kvm_pio(0, port, size, 1);
+
+	vcpu->arch.pio.port = port;
+	vcpu->arch.pio.in = 0;
+	vcpu->arch.pio.string = 0;
+	vcpu->arch.pio.down = 0;
+	vcpu->arch.pio.rep = 0;
+	vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
+	vcpu->arch.pio.size = size;
+
+	memcpy(vcpu->arch.pio_data, val, size * count);
+
+	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+		vcpu->arch.pio.cur_count = 0;
+		return 1;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_IO;
+	vcpu->run->io.direction = KVM_EXIT_IO_OUT;
+	vcpu->run->io.size = size;
+	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
+	vcpu->run->io.count = count;
+	vcpu->run->io.port = port;
+
+	return 0;
+}
+
 static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	return kvm_x86_ops->get_segment_base(vcpu, seg);
@@ -3597,6 +3677,8 @@ static struct x86_emulate_ops emulate_ops = {
 	.read_emulated       = emulator_read_emulated,
 	.write_emulated      = emulator_write_emulated,
 	.cmpxchg_emulated    = emulator_cmpxchg_emulated,
+	.pio_in_emulated     = emulator_pio_in_emulated,
+	.pio_out_emulated    = emulator_pio_out_emulated,
 	.get_cached_descriptor = emulator_get_cached_descriptor,
 	.set_cached_descriptor = emulator_set_cached_descriptor,
 	.get_segment_selector = emulator_get_segment_selector,
@@ -3704,6 +3786,12 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 	if (vcpu->arch.pio.string)
 		return EMULATE_DO_MMIO;
 
+	if (vcpu->arch.pio.cur_count && !vcpu->arch.pio.string) {
+		if (!vcpu->arch.pio.in)
+			vcpu->arch.pio.cur_count = 0;
+		return EMULATE_DO_MMIO;
+	}
+
 	if (r || vcpu->mmio_is_write) {
 		run->exit_reason = KVM_EXIT_MMIO;
 		run->mmio.phys_addr = vcpu->mmio_phys_addr;
@@ -3760,43 +3848,36 @@ int complete_pio(struct kvm_vcpu *vcpu)
 	int r;
 	unsigned long val;
 
-	if (!io->string) {
-		if (io->in) {
-			val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-			memcpy(&val, vcpu->arch.pio_data, io->size);
-			kvm_register_write(vcpu, VCPU_REGS_RAX, val);
-		}
-	} else {
-		if (io->in) {
-			r = pio_copy_data(vcpu);
-			if (r)
-				goto out;
-		}
+	if (io->in) {
+		r = pio_copy_data(vcpu);
+		if (r)
+			goto out;
+	}
 
-		delta = 1;
-		if (io->rep) {
-			delta *= io->cur_count;
-			/*
-			 * The size of the register should really depend on
-			 * current address size.
-			 */
-			val = kvm_register_read(vcpu, VCPU_REGS_RCX);
-			val -= delta;
-			kvm_register_write(vcpu, VCPU_REGS_RCX, val);
-		}
-		if (io->down)
-			delta = -delta;
-		delta *= io->size;
-		if (io->in) {
-			val = kvm_register_read(vcpu, VCPU_REGS_RDI);
-			val += delta;
-			kvm_register_write(vcpu, VCPU_REGS_RDI, val);
-		} else {
-			val = kvm_register_read(vcpu, VCPU_REGS_RSI);
-			val += delta;
-			kvm_register_write(vcpu, VCPU_REGS_RSI, val);
-		}
+	delta = 1;
+	if (io->rep) {
+		delta *= io->cur_count;
+		/*
+		 * The size of the register should really depend on
+		 * current address size.
+		 */
+		val = kvm_register_read(vcpu, VCPU_REGS_RCX);
+		val -= delta;
+		kvm_register_write(vcpu, VCPU_REGS_RCX, val);
+	}
+	if (io->down)
+		delta = -delta;
+	delta *= io->size;
+	if (io->in) {
+		val = kvm_register_read(vcpu, VCPU_REGS_RDI);
+		val += delta;
+		kvm_register_write(vcpu, VCPU_REGS_RDI, val);
+	} else {
+		val = kvm_register_read(vcpu, VCPU_REGS_RSI);
+		val += delta;
+		kvm_register_write(vcpu, VCPU_REGS_RSI, val);
 	}
+
 out:
 	io->count -= io->cur_count;
 	io->cur_count = 0;
@@ -3804,21 +3885,6 @@ out:
 	return 0;
 }
 
-static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
-{
-	/* TODO: String I/O for in kernel device */
-	int r;
-
-	if (vcpu->arch.pio.in)
-		r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port,
-				    vcpu->arch.pio.size, pd);
-	else
-		r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
-				     vcpu->arch.pio.port, vcpu->arch.pio.size,
-				     pd);
-	return r;
-}
-
 static int pio_string_write(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pio_request *io = &vcpu->arch.pio;
@@ -3836,36 +3902,6 @@ static int pio_string_write(struct kvm_vcpu *vcpu)
 	return r;
 }
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
-{
-	unsigned long val;
-
-	trace_kvm_pio(!in, port, size, 1);
-
-	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
-	vcpu->run->io.size = vcpu->arch.pio.size = size;
-	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
-	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1;
-	vcpu->run->io.port = vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = in;
-	vcpu->arch.pio.string = 0;
-	vcpu->arch.pio.down = 0;
-	vcpu->arch.pio.rep = 0;
-
-	if (!vcpu->arch.pio.in) {
-		val = kvm_register_read(vcpu, VCPU_REGS_RAX);
-		memcpy(vcpu->arch.pio_data, &val, 4);
-	}
-
-	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
-		complete_pio(vcpu);
-		return 1;
-	}
-	return 0;
-}
-EXPORT_SYMBOL_GPL(kvm_emulate_pio);
-
 int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 		  int size, unsigned long count, int down,
 		  gva_t address, int rep, unsigned port)
@@ -3931,6 +3967,16 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
 
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
+	int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu);
+	/* do not return to emulator after return from userspace */
+	vcpu->arch.pio.cur_count = 0;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
+
 static void bounce_off(void *info)
 {
 	/* nothing */
@@ -4661,9 +4707,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	if (vcpu->arch.pio.cur_count) {
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = complete_pio(vcpu);
+		if (!vcpu->arch.pio.string)
+			r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+		else
+			r = complete_pio(vcpu);
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-		if (r)
+		if (r == EMULATE_DO_MMIO)
 			goto out;
 	}
 	if (vcpu->mmio_needed) {
-- 
cgit v1.2.3


From 7972995b0c346de76fe260ce0fd6bcc8ffab724a Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:24 +0200
Subject: KVM: x86 emulator: Move string pio emulation into emulator.c

Currently emulation is done outside of emulator so things like doing
ins/outs to/from mmio are broken it also makes it hard (if not impossible)
to implement single stepping in the future. The implementation in this
patch is not efficient since it exits to userspace for each IO while
previous implementation did 'ins' in batches. Further patch that
implements pio in string read ahead address this problem.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |   8 --
 arch/x86/kvm/emulate.c          |  48 +++-------
 arch/x86/kvm/x86.c              | 206 ++++------------------------------------
 3 files changed, 32 insertions(+), 230 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 776d3e202b56..26c629a062db 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -224,14 +224,9 @@ struct kvm_pv_mmu_op_buffer {
 
 struct kvm_pio_request {
 	unsigned long count;
-	int cur_count;
-	gva_t guest_gva;
 	int in;
 	int port;
 	int size;
-	int string;
-	int down;
-	int rep;
 };
 
 /*
@@ -591,9 +586,6 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 struct x86_emulate_ctxt;
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
-			   int size, unsigned long count, int down,
-			    gva_t address, int rep, unsigned port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2d095ce9dc87..2c66e097d916 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -153,8 +153,8 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0,
 	/* 0x68 - 0x6F */
 	SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0,
-	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* insb, insw/insd */
-	SrcNone  | ByteOp  | ImplicitOps, SrcNone  | ImplicitOps, /* outsb, outsw/outsd */
+	DstDI | ByteOp | Mov | String, DstDI | Mov | String, /* insb, insw/insd */
+	SrcSI | ByteOp | ImplicitOps | String, SrcSI | ImplicitOps | String, /* outsb, outsw/outsd */
 	/* 0x70 - 0x77 */
 	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
 	SrcImmByte, SrcImmByte, SrcImmByte, SrcImmByte,
@@ -2615,47 +2615,29 @@ special_insn:
 		break;
 	case 0x6c:		/* insb */
 	case 0x6d:		/* insw/insd */
+		c->dst.bytes = min(c->dst.bytes, 4u);
 		if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+					  c->dst.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio_string(ctxt->vcpu,
-				1,
-				(c->d & ByteOp) ? 1 : c->op_bytes,
-				c->rep_prefix ?
-				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
-				(ctxt->eflags & EFLG_DF),
-				register_address(c, es_base(ctxt),
-						 c->regs[VCPU_REGS_RDI]),
-				c->rep_prefix,
-				c->regs[VCPU_REGS_RDX]) == 0) {
-			c->eip = saved_eip;
-			return -1;
-		}
-		return 0;
+		if (!ops->pio_in_emulated(c->dst.bytes, c->regs[VCPU_REGS_RDX],
+					  &c->dst.val, 1, ctxt->vcpu))
+			goto done; /* IO is needed, skip writeback */
+		break;
 	case 0x6e:		/* outsb */
 	case 0x6f:		/* outsw/outsd */
+		c->src.bytes = min(c->src.bytes, 4u);
 		if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+					  c->src.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio_string(ctxt->vcpu,
-				0,
-				(c->d & ByteOp) ? 1 : c->op_bytes,
-				c->rep_prefix ?
-				address_mask(c, c->regs[VCPU_REGS_RCX]) : 1,
-				(ctxt->eflags & EFLG_DF),
-					 register_address(c,
-					  seg_override_base(ctxt, c),
-						 c->regs[VCPU_REGS_RSI]),
-				c->rep_prefix,
-				c->regs[VCPU_REGS_RDX]) == 0) {
-			c->eip = saved_eip;
-			return -1;
-		}
-		return 0;
+		ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX],
+				      &c->src.val, 1, ctxt->vcpu);
+
+		c->dst.type = OP_NONE; /* nothing to writeback */
+		break;
 	case 0x70 ... 0x7f: /* jcc (short) */
 		if (test_cc(c->b, ctxt->eflags))
 			jmp_rel(c, c->src.val);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6624ad13ee99..658e8e8155cb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3150,18 +3150,17 @@ static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
 }
 
-static int kvm_write_guest_virt_helper(gva_t addr, void *val,
+static int kvm_write_guest_virt_system(gva_t addr, void *val,
 				       unsigned int bytes,
-				       struct kvm_vcpu *vcpu, u32 access,
+				       struct kvm_vcpu *vcpu,
 				       u32 *error)
 {
 	void *data = val;
 	int r = X86EMUL_CONTINUE;
 
-	access |= PFERR_WRITE_MASK;
-
 	while (bytes) {
-		gpa_t gpa =  vcpu->arch.mmu.gva_to_gpa(vcpu, addr, access, error);
+		gpa_t gpa =  vcpu->arch.mmu.gva_to_gpa(vcpu, addr,
+						       PFERR_WRITE_MASK, error);
 		unsigned offset = addr & (PAGE_SIZE-1);
 		unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
 		int ret;
@@ -3184,20 +3183,6 @@ out:
 	return r;
 }
 
-static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes,
-				struct kvm_vcpu *vcpu, u32 *error)
-{
-	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
-	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, access, error);
-}
-
-static int kvm_write_guest_virt_system(gva_t addr, void *val,
-				       unsigned int bytes,
-				       struct kvm_vcpu *vcpu, u32 *error)
-{
-	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
-}
-
 static int emulator_read_emulated(unsigned long addr,
 				  void *val,
 				  unsigned int bytes,
@@ -3423,23 +3408,20 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
 static int emulator_pio_in_emulated(int size, unsigned short port, void *val,
 			     unsigned int count, struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.pio.cur_count)
+	if (vcpu->arch.pio.count)
 		goto data_avail;
 
 	trace_kvm_pio(1, port, size, 1);
 
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = 1;
-	vcpu->arch.pio.string = 0;
-	vcpu->arch.pio.down = 0;
-	vcpu->arch.pio.rep = 0;
-	vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
+	vcpu->arch.pio.count  = count;
 	vcpu->arch.pio.size = size;
 
 	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
 	data_avail:
 		memcpy(val, vcpu->arch.pio_data, size * count);
-		vcpu->arch.pio.cur_count = 0;
+		vcpu->arch.pio.count = 0;
 		return 1;
 	}
 
@@ -3461,16 +3443,13 @@ static int emulator_pio_out_emulated(int size, unsigned short port,
 
 	vcpu->arch.pio.port = port;
 	vcpu->arch.pio.in = 0;
-	vcpu->arch.pio.string = 0;
-	vcpu->arch.pio.down = 0;
-	vcpu->arch.pio.rep = 0;
-	vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
+	vcpu->arch.pio.count = count;
 	vcpu->arch.pio.size = size;
 
 	memcpy(vcpu->arch.pio_data, val, size * count);
 
 	if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
-		vcpu->arch.pio.cur_count = 0;
+		vcpu->arch.pio.count = 0;
 		return 1;
 	}
 
@@ -3717,7 +3696,6 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 	cache_all_regs(vcpu);
 
 	vcpu->mmio_is_write = 0;
-	vcpu->arch.pio.string = 0;
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		int cs_db, cs_l;
@@ -3783,12 +3761,9 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 	if (r == 0)
 		kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
 
-	if (vcpu->arch.pio.string)
-		return EMULATE_DO_MMIO;
-
-	if (vcpu->arch.pio.cur_count && !vcpu->arch.pio.string) {
+	if (vcpu->arch.pio.count) {
 		if (!vcpu->arch.pio.in)
-			vcpu->arch.pio.cur_count = 0;
+			vcpu->arch.pio.count = 0;
 		return EMULATE_DO_MMIO;
 	}
 
@@ -3821,158 +3796,12 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
 
-static int pio_copy_data(struct kvm_vcpu *vcpu)
-{
-	void *p = vcpu->arch.pio_data;
-	gva_t q = vcpu->arch.pio.guest_gva;
-	unsigned bytes;
-	int ret;
-	u32 error_code;
-
-	bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count;
-	if (vcpu->arch.pio.in)
-		ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code);
-	else
-		ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code);
-
-	if (ret == X86EMUL_PROPAGATE_FAULT)
-		kvm_inject_page_fault(vcpu, q, error_code);
-
-	return ret;
-}
-
-int complete_pio(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pio_request *io = &vcpu->arch.pio;
-	long delta;
-	int r;
-	unsigned long val;
-
-	if (io->in) {
-		r = pio_copy_data(vcpu);
-		if (r)
-			goto out;
-	}
-
-	delta = 1;
-	if (io->rep) {
-		delta *= io->cur_count;
-		/*
-		 * The size of the register should really depend on
-		 * current address size.
-		 */
-		val = kvm_register_read(vcpu, VCPU_REGS_RCX);
-		val -= delta;
-		kvm_register_write(vcpu, VCPU_REGS_RCX, val);
-	}
-	if (io->down)
-		delta = -delta;
-	delta *= io->size;
-	if (io->in) {
-		val = kvm_register_read(vcpu, VCPU_REGS_RDI);
-		val += delta;
-		kvm_register_write(vcpu, VCPU_REGS_RDI, val);
-	} else {
-		val = kvm_register_read(vcpu, VCPU_REGS_RSI);
-		val += delta;
-		kvm_register_write(vcpu, VCPU_REGS_RSI, val);
-	}
-
-out:
-	io->count -= io->cur_count;
-	io->cur_count = 0;
-
-	return 0;
-}
-
-static int pio_string_write(struct kvm_vcpu *vcpu)
-{
-	struct kvm_pio_request *io = &vcpu->arch.pio;
-	void *pd = vcpu->arch.pio_data;
-	int i, r = 0;
-
-	for (i = 0; i < io->cur_count; i++) {
-		if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS,
-				     io->port, io->size, pd)) {
-			r = -EOPNOTSUPP;
-			break;
-		}
-		pd += io->size;
-	}
-	return r;
-}
-
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
-		  int size, unsigned long count, int down,
-		  gva_t address, int rep, unsigned port)
-{
-	unsigned now, in_page;
-	int ret = 0;
-
-	trace_kvm_pio(!in, port, size, count);
-
-	vcpu->run->exit_reason = KVM_EXIT_IO;
-	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
-	vcpu->run->io.size = vcpu->arch.pio.size = size;
-	vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
-	vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count;
-	vcpu->run->io.port = vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = in;
-	vcpu->arch.pio.string = 1;
-	vcpu->arch.pio.down = down;
-	vcpu->arch.pio.rep = rep;
-
-	if (!count) {
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
-		return 1;
-	}
-
-	if (!down)
-		in_page = PAGE_SIZE - offset_in_page(address);
-	else
-		in_page = offset_in_page(address) + size;
-	now = min(count, (unsigned long)in_page / size);
-	if (!now)
-		now = 1;
-	if (down) {
-		/*
-		 * String I/O in reverse.  Yuck.  Kill the guest, fix later.
-		 */
-		pr_unimpl(vcpu, "guest string pio down\n");
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-	vcpu->run->io.count = now;
-	vcpu->arch.pio.cur_count = now;
-
-	if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count)
-		kvm_x86_ops->skip_emulated_instruction(vcpu);
-
-	vcpu->arch.pio.guest_gva = address;
-
-	if (!vcpu->arch.pio.in) {
-		/* string PIO write */
-		ret = pio_copy_data(vcpu);
-		if (ret == X86EMUL_PROPAGATE_FAULT)
-			return 1;
-		if (ret == 0 && !pio_string_write(vcpu)) {
-			complete_pio(vcpu);
-			if (vcpu->arch.pio.count == 0)
-				ret = 1;
-		}
-	}
-	/* no string PIO read support yet */
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
-
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 {
 	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu);
 	/* do not return to emulator after return from userspace */
-	vcpu->arch.pio.cur_count = 0;
+	vcpu->arch.pio.count = 0;
 	return ret;
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
@@ -4705,15 +4534,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (!irqchip_in_kernel(vcpu->kvm))
 		kvm_set_cr8(vcpu, kvm_run->cr8);
 
-	if (vcpu->arch.pio.cur_count) {
+	if (vcpu->arch.pio.count) {
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		if (!vcpu->arch.pio.string)
-			r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
-		else
-			r = complete_pio(vcpu);
+		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-		if (r == EMULATE_DO_MMIO)
+		if (r == EMULATE_DO_MMIO) {
+			r = 0;
 			goto out;
+		}
 	}
 	if (vcpu->mmio_needed) {
 		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
-- 
cgit v1.2.3


From cb404fe0898779ec5fe5e06e90aaddcf40aefad8 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:25 +0200
Subject: KVM: x86 emulator: remove saved_eip

c->eip is never written back in case of emulation failure, so no need to
set it to old value.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2c66e097d916..0579d9dd9aac 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2424,7 +2424,6 @@ int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {
 	u64 msr_data;
-	unsigned long saved_eip = 0;
 	struct decode_cache *c = &ctxt->decode;
 	int rc = X86EMUL_CONTINUE;
 
@@ -2436,7 +2435,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	 */
 
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
-	saved_eip = c->eip;
 
 	if (ctxt->mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
 		kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
@@ -2928,11 +2926,7 @@ writeback:
 	kvm_rip_write(ctxt->vcpu, c->eip);
 
 done:
-	if (rc == X86EMUL_UNHANDLEABLE) {
-		c->eip = saved_eip;
-		return -1;
-	}
-	return 0;
+	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 
 twobyte_insn:
 	switch (c->b) {
@@ -3209,6 +3203,5 @@ twobyte_insn:
 
 cannot_emulate:
 	DPRINTF("Cannot emulate %02x\n", c->b);
-	c->eip = saved_eip;
 	return -1;
 }
-- 
cgit v1.2.3


From 5cd21917da245fbe98bd443de2c7f519b3df6814 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:26 +0200
Subject: KVM: x86 emulator: restart string instruction without going back to a
 guest.

Currently when string instruction is only partially complete we go back
to a guest mode, guest tries to reexecute instruction and exits again
and at this point emulation continues. Avoid all of this by restarting
instruction without going back to a guest mode, but return to a guest
mode each 1024 iterations to allow interrupt injection. Pending
exception causes immediate guest entry too.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |  1 +
 arch/x86/kvm/emulate.c             | 34 +++++++++++++++++++++++-----------
 arch/x86/kvm/x86.c                 | 19 ++++++++++++++++++-
 3 files changed, 42 insertions(+), 12 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 679245c9a55f..7fda16f89cc8 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -193,6 +193,7 @@ struct x86_emulate_ctxt {
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
+	bool restart; /* restart string instruction after writeback */
 	/* decode cache */
 	struct decode_cache decode;
 };
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0579d9dd9aac..6de6ad1610d8 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -927,8 +927,11 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	int mode = ctxt->mode;
 	int def_op_bytes, def_ad_bytes, group;
 
-	/* Shadow copy of register state. Committed on successful emulation. */
 
+	/* we cannot decode insn before we complete previous rep insn */
+	WARN_ON(ctxt->restart);
+
+	/* Shadow copy of register state. Committed on successful emulation. */
 	memset(c, 0, sizeof(struct decode_cache));
 	c->eip = ctxt->eip;
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
@@ -2426,6 +2429,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	u64 msr_data;
 	struct decode_cache *c = &ctxt->decode;
 	int rc = X86EMUL_CONTINUE;
+	int saved_dst_type = c->dst.type;
 
 	ctxt->interruptibility = 0;
 
@@ -2454,8 +2458,11 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	}
 
 	if (c->rep_prefix && (c->d & String)) {
+		ctxt->restart = true;
 		/* All REP prefixes have the same first termination condition */
 		if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
+		string_done:
+			ctxt->restart = false;
 			kvm_rip_write(ctxt->vcpu, c->eip);
 			goto done;
 		}
@@ -2467,17 +2474,13 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		 * 	- if REPNE/REPNZ and ZF = 1 then done
 		 */
 		if ((c->b == 0xa6) || (c->b == 0xa7) ||
-				(c->b == 0xae) || (c->b == 0xaf)) {
+		    (c->b == 0xae) || (c->b == 0xaf)) {
 			if ((c->rep_prefix == REPE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == 0)) {
-					kvm_rip_write(ctxt->vcpu, c->eip);
-					goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == 0))
+				goto string_done;
 			if ((c->rep_prefix == REPNE_PREFIX) &&
-				((ctxt->eflags & EFLG_ZF) == EFLG_ZF)) {
-				kvm_rip_write(ctxt->vcpu, c->eip);
-				goto done;
-			}
+			    ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))
+				goto string_done;
 		}
 		c->eip = ctxt->eip;
 	}
@@ -2911,6 +2914,12 @@ writeback:
 	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
+	/*
+	 * restore dst type in case the decoding will be reused
+	 * (happens for string instruction )
+	 */
+	c->dst.type = saved_dst_type;
+
 	if ((c->d & SrcMask) == SrcSI)
 		string_addr_inc(ctxt, seg_override_base(ctxt, c), VCPU_REGS_RSI,
 				&c->src);
@@ -2918,8 +2927,11 @@ writeback:
 	if ((c->d & DstMask) == DstDI)
 		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
 
-	if (c->rep_prefix && (c->d & String))
+	if (c->rep_prefix && (c->d & String)) {
 		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+		if (!(c->regs[VCPU_REGS_RCX] & 0x3ff))
+			ctxt->restart = false;
+	}
 
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 658e8e8155cb..c88cb8145283 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3755,6 +3755,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DONE;
 	}
 
+restart:
 	r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
 	shadow_mask = vcpu->arch.emulate_ctxt.interruptibility;
 
@@ -3777,7 +3778,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (r) {
 		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
-			return EMULATE_DONE;
+			goto done;
 		if (!vcpu->mmio_needed) {
 			kvm_report_emulation_failure(vcpu, "mmio");
 			return EMULATE_FAIL;
@@ -3792,6 +3793,13 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DO_MMIO;
 	}
 
+done:
+	if (vcpu->arch.exception.pending)
+		vcpu->arch.emulate_ctxt.restart = false;
+
+	if (vcpu->arch.emulate_ctxt.restart)
+		goto restart;
+
 	return EMULATE_DONE;
 }
 EXPORT_SYMBOL_GPL(emulate_instruction);
@@ -4560,6 +4568,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			goto out;
 		}
 	}
+	if (vcpu->arch.emulate_ctxt.restart) {
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+		if (r == EMULATE_DO_MMIO) {
+			r = 0;
+			goto out;
+		}
+	}
 	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
 		kvm_register_write(vcpu, VCPU_REGS_RAX,
 				     kvm_run->hypercall.ret);
-- 
cgit v1.2.3


From 7b262e90fc20a49fddf3dad94c8cead1f0439751 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 18 Mar 2010 15:20:27 +0200
Subject: KVM: x86 emulator: introduce pio in string read ahead.

To optimize "rep ins" instruction do IO in big chunks ahead of time
instead of doing it only when required during instruction emulation.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |  7 ++++++
 arch/x86/kvm/emulate.c             | 46 +++++++++++++++++++++++++++++++++-----
 2 files changed, 48 insertions(+), 5 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7fda16f89cc8..b5e12c583860 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -151,6 +151,12 @@ struct fetch_cache {
 	unsigned long end;
 };
 
+struct read_cache {
+	u8 data[1024];
+	unsigned long pos;
+	unsigned long end;
+};
+
 struct decode_cache {
 	u8 twobyte;
 	u8 b;
@@ -178,6 +184,7 @@ struct decode_cache {
 	void *modrm_ptr;
 	unsigned long modrm_val;
 	struct fetch_cache fetch;
+	struct read_cache io_read;
 };
 
 struct x86_emulate_ctxt {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6de6ad1610d8..ab3fff5bf7c4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1257,6 +1257,36 @@ done:
 	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 }
 
+static int pio_in_emulated(struct x86_emulate_ctxt *ctxt,
+			   struct x86_emulate_ops *ops,
+			   unsigned int size, unsigned short port,
+			   void *dest)
+{
+	struct read_cache *rc = &ctxt->decode.io_read;
+
+	if (rc->pos == rc->end) { /* refill pio read ahead */
+		struct decode_cache *c = &ctxt->decode;
+		unsigned int in_page, n;
+		unsigned int count = c->rep_prefix ?
+			address_mask(c, c->regs[VCPU_REGS_RCX]) : 1;
+		in_page = (ctxt->eflags & EFLG_DF) ?
+			offset_in_page(c->regs[VCPU_REGS_RDI]) :
+			PAGE_SIZE - offset_in_page(c->regs[VCPU_REGS_RDI]);
+		n = min(min(in_page, (unsigned int)sizeof(rc->data)) / size,
+			count);
+		if (n == 0)
+			n = 1;
+		rc->pos = rc->end = 0;
+		if (!ops->pio_in_emulated(size, port, rc->data, n, ctxt->vcpu))
+			return 0;
+		rc->end = n * size;
+	}
+
+	memcpy(dest, rc->data + rc->pos, size);
+	rc->pos += size;
+	return 1;
+}
+
 static u32 desc_limit_scaled(struct desc_struct *desc)
 {
 	u32 limit = get_desc_limit(desc);
@@ -2622,8 +2652,8 @@ special_insn:
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (!ops->pio_in_emulated(c->dst.bytes, c->regs[VCPU_REGS_RDX],
-					  &c->dst.val, 1, ctxt->vcpu))
+		if (!pio_in_emulated(ctxt, ops, c->dst.bytes,
+				     c->regs[VCPU_REGS_RDX], &c->dst.val))
 			goto done; /* IO is needed, skip writeback */
 		break;
 	case 0x6e:		/* outsb */
@@ -2839,8 +2869,8 @@ special_insn:
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (!ops->pio_in_emulated(c->dst.bytes, c->src.val,
-					  &c->dst.val, 1, ctxt->vcpu))
+		if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
+				     &c->dst.val))
 			goto done; /* IO is needed */
 		break;
 	case 0xee: /* out al,dx */
@@ -2928,8 +2958,14 @@ writeback:
 		string_addr_inc(ctxt, es_base(ctxt), VCPU_REGS_RDI, &c->dst);
 
 	if (c->rep_prefix && (c->d & String)) {
+		struct read_cache *rc = &ctxt->decode.io_read;
 		register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
-		if (!(c->regs[VCPU_REGS_RCX] & 0x3ff))
+		/*
+		 * Re-enter guest when pio read ahead buffer is empty or,
+		 * if it is not used, after each 1024 iteration.
+		 */
+		if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) ||
+		    (rc->end != 0 && rc->end == rc->pos))
 			ctxt->restart = false;
 	}
 
-- 
cgit v1.2.3


From 482ac18ae293a3a0b1e1eea95c10dcc9ceeb4708 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Sun, 21 Mar 2010 13:08:20 +0200
Subject: KVM: x86 emulator: commit rflags as part of registers commit

Make sure that rflags is committed only after successful instruction
emulation.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h | 1 +
 arch/x86/kvm/emulate.c             | 1 +
 arch/x86/kvm/x86.c                 | 8 ++++++--
 3 files changed, 8 insertions(+), 2 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b5e12c583860..a1319c82050e 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -136,6 +136,7 @@ struct x86_emulate_ops {
 	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
 	void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
 	int (*cpl)(struct kvm_vcpu *vcpu);
+	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ab3fff5bf7c4..48de4b890055 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2972,6 +2972,7 @@ writeback:
 	/* Commit shadow register state. */
 	memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
 	kvm_rip_write(ctxt->vcpu, c->eip);
+	ops->set_rflags(ctxt->vcpu, ctxt->eflags);
 
 done:
 	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b4d3363b78e6..247e805a041e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3649,6 +3649,11 @@ static void emulator_set_segment_selector(u16 sel, int seg,
 	kvm_set_segment(vcpu, &kvm_seg, seg);
 }
 
+static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	kvm_x86_ops->set_rflags(vcpu, rflags);
+}
+
 static struct x86_emulate_ops emulate_ops = {
 	.read_std            = kvm_read_guest_virt_system,
 	.write_std           = kvm_write_guest_virt_system,
@@ -3666,6 +3671,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
 	.cpl                 = emulator_get_cpl,
+	.set_rflags          = emulator_set_rflags,
 };
 
 static void cache_all_regs(struct kvm_vcpu *vcpu)
@@ -3786,8 +3792,6 @@ restart:
 		return EMULATE_DO_MMIO;
 	}
 
-	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
-
 	if (vcpu->mmio_is_write) {
 		vcpu->mmio_needed = 0;
 		return EMULATE_DO_MMIO;
-- 
cgit v1.2.3


From 6550e1f165f384f3a46b60a1be9aba4bc3c2adad Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Sun, 21 Mar 2010 13:08:21 +0200
Subject: KVM: x86 emulator: add decoding of CMPXCHG8B dst operand

Decode CMPXCHG8B destination operand in decoding stage. Fixes regression
introduced by "If LOCK prefix is used dest arg should be memory" commit.
This commit relies on dst operand be decoded at the beginning of an
instruction emulation.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 24 ++++++++++--------------
 1 file changed, 10 insertions(+), 14 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 48de4b890055..b8ce53861f68 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -52,6 +52,7 @@
 #define DstMem      (3<<1)	/* Memory operand. */
 #define DstAcc      (4<<1)      /* Destination Accumulator */
 #define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
+#define DstMem64    (6<<1)	/* 64bit memory operand */
 #define DstMask     (7<<1)
 /* Source operand type. */
 #define SrcNone     (0<<4)	/* No source operand. */
@@ -360,7 +361,7 @@ static u32 group_table[] = {
 	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock,
 	DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock,
 	[Group9*8] =
-	0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0,
+	0, DstMem64 | ModRM | Lock, 0, 0, 0, 0, 0, 0,
 };
 
 static u32 group2_table[] = {
@@ -1205,6 +1206,7 @@ done_prefixes:
 			 c->twobyte && (c->b == 0xb6 || c->b == 0xb7));
 		break;
 	case DstMem:
+	case DstMem64:
 		if ((c->d & ModRM) && c->modrm_mod == 3) {
 			c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 			c->dst.type = OP_REG;
@@ -1214,7 +1216,10 @@ done_prefixes:
 		}
 		c->dst.type = OP_MEM;
 		c->dst.ptr = (unsigned long *)c->modrm_ea;
-		c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
+		if ((c->d & DstMask) == DstMem64)
+			c->dst.bytes = 8;
+		else
+			c->dst.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
 		c->dst.val = 0;
 		if (c->d & BitOp) {
 			unsigned long mask = ~(c->dst.bytes * 8 - 1);
@@ -1706,12 +1711,7 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	u64 old, new;
-	int rc;
-
-	rc = ops->read_emulated(c->modrm_ea, &old, 8, ctxt->vcpu);
-	if (rc != X86EMUL_CONTINUE)
-		return rc;
+	u64 old = c->dst.orig_val;
 
 	if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) ||
 	    ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) {
@@ -1719,15 +1719,12 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 		c->regs[VCPU_REGS_RAX] = (u32) (old >> 0);
 		c->regs[VCPU_REGS_RDX] = (u32) (old >> 32);
 		ctxt->eflags &= ~EFLG_ZF;
-
 	} else {
-		new = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
+		c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
 		       (u32) c->regs[VCPU_REGS_RBX];
 
-		rc = ops->cmpxchg_emulated(c->modrm_ea, &old, &new, 8, ctxt->vcpu);
-		if (rc != X86EMUL_CONTINUE)
-			return rc;
 		ctxt->eflags |= EFLG_ZF;
+		c->lock_prefix = 1;
 	}
 	return X86EMUL_CONTINUE;
 }
@@ -3245,7 +3242,6 @@ twobyte_insn:
 		rc = emulate_grp9(ctxt, ops);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
-		c->dst.type = OP_NONE;
 		break;
 	}
 	goto writeback;
-- 
cgit v1.2.3


From de3e6480f76804fe06d460ddb1920c7daa07f29b Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Sun, 21 Mar 2010 16:58:36 +0200
Subject: KVM: x86 emulator: fix unlocked CMPXCHG8B emulation

When CMPXCHG8B is executed without LOCK prefix it is racy. Preserve this
behaviour in emulator too.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/kvm/emulate.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index b8ce53861f68..64c9854f0458 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1724,7 +1724,6 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 		       (u32) c->regs[VCPU_REGS_RBX];
 
 		ctxt->eflags |= EFLG_ZF;
-		c->lock_prefix = 1;
 	}
 	return X86EMUL_CONTINUE;
 }
-- 
cgit v1.2.3


From 2fb53ad811e238d5dec8716b99986c3f234e3337 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Sun, 11 Apr 2010 13:05:15 +0300
Subject: KVM: x86 emulator: Don't overwrite decode cache

Currently if we an instruction spans a page boundary, when we fetch the
second half we overwrite the first half.  This prevents us from tracing
the full instruction opcodes.

Fix by appending the second half to the first.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 64c9854f0458..083b269a83ea 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -646,21 +646,22 @@ static unsigned long ss_base(struct x86_emulate_ctxt *ctxt)
 
 static int do_fetch_insn_byte(struct x86_emulate_ctxt *ctxt,
 			      struct x86_emulate_ops *ops,
-			      unsigned long linear, u8 *dest)
+			      unsigned long eip, u8 *dest)
 {
 	struct fetch_cache *fc = &ctxt->decode.fetch;
 	int rc;
-	int size;
+	int size, cur_size;
 
-	if (linear < fc->start || linear >= fc->end) {
-		size = min(15UL, PAGE_SIZE - offset_in_page(linear));
-		rc = ops->fetch(linear, fc->data, size, ctxt->vcpu, NULL);
+	if (eip == fc->end) {
+		cur_size = fc->end - fc->start;
+		size = min(15UL - cur_size, PAGE_SIZE - offset_in_page(eip));
+		rc = ops->fetch(ctxt->cs_base + eip, fc->data + cur_size,
+				size, ctxt->vcpu, NULL);
 		if (rc != X86EMUL_CONTINUE)
 			return rc;
-		fc->start = linear;
-		fc->end = linear + size;
+		fc->end += size;
 	}
-	*dest = fc->data[linear - fc->start];
+	*dest = fc->data[eip - fc->start];
 	return X86EMUL_CONTINUE;
 }
 
@@ -673,7 +674,6 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 	/* x86 instructions are limited to 15 bytes. */
 	if (eip + size - ctxt->eip > 15)
 		return X86EMUL_UNHANDLEABLE;
-	eip += ctxt->cs_base;
 	while (size--) {
 		rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++);
 		if (rc != X86EMUL_CONTINUE)
@@ -935,6 +935,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	/* Shadow copy of register state. Committed on successful emulation. */
 	memset(c, 0, sizeof(struct decode_cache));
 	c->eip = ctxt->eip;
+	c->fetch.start = c->fetch.end = c->eip;
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 
-- 
cgit v1.2.3


From 0760d44868f351ba30fc9a08cf1830e46aa72466 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Wed, 14 Apr 2010 15:50:57 +0200
Subject: KVM: x86: Terminate early if task_switch_16/32 failed

Stop the switch immediately if task_switch_16/32 returned an error. Only
if that step succeeded, the switch should actually take place and update
any register states.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 083b269a83ea..aace5659bbe0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2402,6 +2402,8 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	else
 		ret = task_switch_16(ctxt, ops, tss_selector, old_tss_sel,
 				     old_tss_base, &next_tss_desc);
+	if (ret != X86EMUL_CONTINUE)
+		return ret;
 
 	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE)
 		ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT;
-- 
cgit v1.2.3


From e269fb2189fb86d79d64c0ca74c6c1a549ad4aa3 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Wed, 14 Apr 2010 15:51:09 +0200
Subject: KVM: x86: Push potential exception error code on task switches

When a fault triggers a task switch, the error code, if existent, has to
be pushed on the new task's stack. Implement the missing bits.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/include/asm/kvm_emulate.h |  3 ++-
 arch/x86/include/asm/kvm_host.h    |  3 ++-
 arch/x86/include/asm/svm.h         |  1 +
 arch/x86/kvm/emulate.c             | 22 ++++++++++++++++++----
 arch/x86/kvm/svm.c                 | 11 ++++++++++-
 arch/x86/kvm/vmx.c                 | 12 +++++++++++-
 arch/x86/kvm/x86.c                 |  6 ++++--
 7 files changed, 48 insertions(+), 10 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index a1319c82050e..0b2729bf2070 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -230,6 +230,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
 		     struct x86_emulate_ops *ops);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 struct x86_emulate_ops *ops,
-			 u16 tss_selector, int reason);
+			 u16 tss_selector, int reason,
+			 bool has_error_code, u32 error_code);
 
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5d5e0a9afcf2..3602728d54de 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -595,7 +595,8 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+		    bool has_error_code, u32 error_code);
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1d91d05f9368..0e831059ac5a 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -244,6 +244,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXITINFOSHIFT_TS_REASON_IRET 36
 #define SVM_EXITINFOSHIFT_TS_REASON_JMP 38
+#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44
 
 #define	SVM_EXIT_READ_CR0 	0x000
 #define	SVM_EXIT_READ_CR3 	0x003
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index aace5659bbe0..585d0ef4a5f6 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2344,8 +2344,9 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt,
 }
 
 static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
-				    struct x86_emulate_ops *ops,
-				    u16 tss_selector, int reason)
+				   struct x86_emulate_ops *ops,
+				   u16 tss_selector, int reason,
+				   bool has_error_code, u32 error_code)
 {
 	struct desc_struct curr_tss_desc, next_tss_desc;
 	int ret;
@@ -2418,12 +2419,22 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
 	ops->set_cached_descriptor(&next_tss_desc, VCPU_SREG_TR, ctxt->vcpu);
 	ops->set_segment_selector(tss_selector, VCPU_SREG_TR, ctxt->vcpu);
 
+	if (has_error_code) {
+		struct decode_cache *c = &ctxt->decode;
+
+		c->op_bytes = c->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2;
+		c->lock_prefix = 0;
+		c->src.val = (unsigned long) error_code;
+		emulate_push(ctxt);
+	}
+
 	return ret;
 }
 
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 struct x86_emulate_ops *ops,
-			 u16 tss_selector, int reason)
+			 u16 tss_selector, int reason,
+			 bool has_error_code, u32 error_code)
 {
 	struct decode_cache *c = &ctxt->decode;
 	int rc;
@@ -2431,12 +2442,15 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 	memset(c, 0, sizeof(struct decode_cache));
 	c->eip = ctxt->eip;
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
+	c->dst.type = OP_NONE;
 
-	rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason);
+	rc = emulator_do_task_switch(ctxt, ops, tss_selector, reason,
+				     has_error_code, error_code);
 
 	if (rc == X86EMUL_CONTINUE) {
 		memcpy(ctxt->vcpu->arch.regs, c->regs, sizeof c->regs);
 		kvm_rip_write(ctxt->vcpu, c->eip);
+		rc = writeback(ctxt, ops);
 	}
 
 	return rc;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 87b36fbbfec8..78af52222fd2 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2222,6 +2222,8 @@ static int task_switch_interception(struct vcpu_svm *svm)
 		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK;
 	uint32_t idt_v =
 		svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_VALID;
+	bool has_error_code = false;
+	u32 error_code = 0;
 
 	tss_selector = (u16)svm->vmcb->control.exit_info_1;
 
@@ -2242,6 +2244,12 @@ static int task_switch_interception(struct vcpu_svm *svm)
 			svm->vcpu.arch.nmi_injected = false;
 			break;
 		case SVM_EXITINTINFO_TYPE_EXEPT:
+			if (svm->vmcb->control.exit_info_2 &
+			    (1ULL << SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE)) {
+				has_error_code = true;
+				error_code =
+					(u32)svm->vmcb->control.exit_info_2;
+			}
 			kvm_clear_exception_queue(&svm->vcpu);
 			break;
 		case SVM_EXITINTINFO_TYPE_INTR:
@@ -2258,7 +2266,8 @@ static int task_switch_interception(struct vcpu_svm *svm)
 	     (int_vec == OF_VECTOR || int_vec == BP_VECTOR)))
 		skip_emulated_instruction(&svm->vcpu);
 
-	return kvm_task_switch(&svm->vcpu, tss_selector, reason);
+	return kvm_task_switch(&svm->vcpu, tss_selector, reason,
+			       has_error_code, error_code);
 }
 
 static int cpuid_interception(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fb4a8869bb99..1b38d8a88cf7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3271,6 +3271,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qualification;
+	bool has_error_code = false;
+	u32 error_code = 0;
 	u16 tss_selector;
 	int reason, type, idt_v;
 
@@ -3293,6 +3295,13 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 			kvm_clear_interrupt_queue(vcpu);
 			break;
 		case INTR_TYPE_HARD_EXCEPTION:
+			if (vmx->idt_vectoring_info &
+			    VECTORING_INFO_DELIVER_CODE_MASK) {
+				has_error_code = true;
+				error_code =
+					vmcs_read32(IDT_VECTORING_ERROR_CODE);
+			}
+			/* fall through */
 		case INTR_TYPE_SOFT_EXCEPTION:
 			kvm_clear_exception_queue(vcpu);
 			break;
@@ -3307,7 +3316,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 		       type != INTR_TYPE_NMI_INTR))
 		skip_emulated_instruction(vcpu);
 
-	if (!kvm_task_switch(vcpu, tss_selector, reason))
+	if (!kvm_task_switch(vcpu, tss_selector, reason, has_error_code,
+			     error_code))
 		return 0;
 
 	/* clear all local breakpoint enable flags */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 40991527f54a..58a295c6bf62 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4778,7 +4778,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+		    bool has_error_code, u32 error_code)
 {
 	int cs_db, cs_l, ret;
 	cache_all_regs(vcpu);
@@ -4796,7 +4797,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 		? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
 
 	ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops,
-				   tss_selector, reason);
+				   tss_selector, reason, has_error_code,
+				   error_code);
 
 	if (ret == X86EMUL_CONTINUE)
 		kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
-- 
cgit v1.2.3


From 19d04437267f00c7b50343513693b7a3174ff908 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 15 Apr 2010 12:29:50 +0300
Subject: KVM: fix emulator_task_switch() return value.

emulator_task_switch() should return -1 for failure and 0 for success to
the caller, just like x86_emulate_insn() does.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/x86/kvm/emulate.c | 2 +-
 arch/x86/kvm/x86.c     | 7 ++++---
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'arch/x86/kvm/emulate.c')

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 585d0ef4a5f6..5ac0bb465ed6 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2453,7 +2453,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 		rc = writeback(ctxt, ops);
 	}
 
-	return rc;
+	return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
 }
 
 static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 58a295c6bf62..30efeead4511 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4800,10 +4800,11 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
 				   tss_selector, reason, has_error_code,
 				   error_code);
 
-	if (ret == X86EMUL_CONTINUE)
-		kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+	if (ret)
+		return EMULATE_FAIL;
 
-	return (ret != X86EMUL_CONTINUE);
+	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+	return EMULATE_DONE;
 }
 EXPORT_SYMBOL_GPL(kvm_task_switch);
 
-- 
cgit v1.2.3