summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/emulate.c1247
-rw-r--r--arch/x86/kvm/i8259.c53
-rw-r--r--arch/x86/kvm/irq.h1
-rw-r--r--arch/x86/kvm/kvm_timer.h4
-rw-r--r--arch/x86/kvm/mmu.c230
-rw-r--r--arch/x86/kvm/mmutrace.h84
-rw-r--r--arch/x86/kvm/paging_tmpl.h46
-rw-r--r--arch/x86/kvm/svm.c1040
-rw-r--r--arch/x86/kvm/timer.c3
-rw-r--r--arch/x86/kvm/trace.h165
-rw-r--r--arch/x86/kvm/vmx.c378
-rw-r--r--arch/x86/kvm/x86.c1599
-rw-r--r--arch/x86/kvm/x86.h7
13 files changed, 2892 insertions, 1965 deletions
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 4dade6ac0827..5ac0bb465ed6 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.
@@ -50,6 +51,8 @@
#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 DstMem64 (6<<1) /* 64bit memory operand */
#define DstMask (7<<1)
/* Source operand type. */
#define SrcNone (0<<4) /* No source operand. */
@@ -63,6 +66,7 @@
#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)
@@ -85,6 +89,9 @@
#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 {
@@ -147,8 +154,8 @@ 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,
@@ -173,12 +180,12 @@ 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,
@@ -204,13 +211,13 @@ 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,
@@ -343,7 +350,8 @@ 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,
@@ -353,14 +361,14 @@ 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[] = {
[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,
};
@@ -562,7 +570,7 @@ 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; \
@@ -638,40 +646,40 @@ 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 (rc)
+ 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];
- return 0;
+ *dest = fc->data[eip - fc->start];
+ 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)
+ 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)
+ if (rc != X86EMUL_CONTINUE)
return rc;
}
- return 0;
+ return X86EMUL_CONTINUE;
}
/*
@@ -702,7 +710,7 @@ 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);
@@ -782,7 +790,7 @@ 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 +903,7 @@ 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:
@@ -916,14 +924,18 @@ 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;
- /* 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 = c->eip_orig = kvm_rip_read(ctxt->vcpu);
+ 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);
@@ -1015,11 +1027,6 @@ 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);
@@ -1046,7 +1053,7 @@ 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)
@@ -1057,6 +1064,10 @@ 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 +1102,8 @@ 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:
@@ -1139,6 +1152,14 @@ 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;
}
/*
@@ -1168,6 +1189,12 @@ done_prefixes:
c->src2.bytes = 1;
c->src2.val = 1;
break;
+ case Src2Mem16:
+ 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;
}
/* Decode and fetch the destination operand: register or memory. */
@@ -1180,6 +1207,7 @@ 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;
@@ -1188,12 +1216,24 @@ done_prefixes:
break;
}
c->dst.type = OP_MEM;
+ c->dst.ptr = (unsigned long *)c->modrm_ea;
+ 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);
+
+ c->dst.ptr = (void *)c->dst.ptr +
+ (c->src.val & mask) / 8;
+ }
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;
@@ -1203,18 +1243,248 @@ 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;
+ 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;
}
- if (c->rip_relative)
- c->modrm_ea += c->eip;
-
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);
+
+ 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;
@@ -1251,7 +1521,7 @@ 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)
@@ -1306,10 +1576,10 @@ 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);
+ rc = load_segment_descriptor(ctxt, ops, (u16)selector, seg);
return rc;
}
@@ -1332,7 +1602,7 @@ 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) {
@@ -1343,7 +1613,7 @@ 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;
}
@@ -1354,12 +1624,8 @@ 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)
@@ -1395,7 +1661,6 @@ static inline int emulate_grp3(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops)
{
struct decode_cache *c = &ctxt->decode;
- int rc = 0;
switch (c->modrm_reg) {
case 0 ... 1: /* test */
@@ -1408,11 +1673,9 @@ 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,
@@ -1442,20 +1705,14 @@ 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,
- 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);
- 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])) {
@@ -1463,17 +1720,13 @@ 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(memop, &old, &new, 8, ctxt->vcpu);
- if (rc != X86EMUL_CONTINUE)
- return rc;
ctxt->eflags |= EFLG_ZF;
}
- return 0;
+ return X86EMUL_CONTINUE;
}
static int emulate_ret_far(struct x86_emulate_ctxt *ctxt,
@@ -1484,14 +1737,14 @@ 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);
+ rc = load_segment_descriptor(ctxt, ops, (u16)cs, VCPU_SREG_CS);
return rc;
}
@@ -1544,7 +1797,7 @@ 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)
@@ -1598,8 +1851,11 @@ 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);
@@ -1649,14 +1905,16 @@ 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);
@@ -1711,7 +1969,7 @@ 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);
@@ -1756,7 +2014,8 @@ 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)
@@ -1764,7 +2023,7 @@ 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,
@@ -1801,22 +2060,419 @@ 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;
}
+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,
+ bool has_error_code, u32 error_code)
+{
+ 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);
+ u32 desc_limit;
+
+ /* 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;
+ }
+ }
+
+ 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;
+ }
+
+ 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 (ret != X86EMUL_CONTINUE)
+ return ret;
+
+ 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);
+
+ 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,
+ bool has_error_code, u32 error_code)
+{
+ 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);
+ c->dst.type = OP_NONE;
+
+ 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 == X86EMUL_UNHANDLEABLE) ? -1 : 0;
+}
+
+static void string_addr_inc(struct x86_emulate_ctxt *ctxt, unsigned long base,
+ 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 * op->bytes);
+ op->ptr = (unsigned long *)register_address(c, base, c->regs[reg]);
+}
+
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;
- unsigned int port;
- int io_dir_in;
- int rc = 0;
+ int rc = X86EMUL_CONTINUE;
+ int saved_dst_type = c->dst.type;
ctxt->interruptibility = 0;
@@ -1826,26 +2482,30 @@ 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)) {
+ if (c->lock_prefix && (!(c->d & Lock) || c->dst.type != OP_MEM)) {
kvm_queue_exception(ctxt->vcpu, UD_VECTOR);
goto done;
}
/* 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;
}
- if (((c->d & ModRM) && (c->modrm_mod != 3)) || (c->d & MemAbs))
- memop = c->modrm_ea;
-
if (c->rep_prefix && (c->d & String)) {
+ ctxt->restart = true;
/* 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) {
+ string_done:
+ ctxt->restart = false;
kvm_rip_write(ctxt->vcpu, c->eip);
goto done;
}
@@ -1857,25 +2517,18 @@ 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->regs[VCPU_REGS_RCX]--;
- c->eip = kvm_rip_read(ctxt->vcpu);
+ c->eip = ctxt->eip;
}
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,
@@ -1885,29 +2538,25 @@ 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) {
+ 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;
- 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;
@@ -1926,7 +2575,7 @@ 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 +2594,7 @@ 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 +2606,7 @@ 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 +2637,7 @@ 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 +2645,7 @@ special_insn:
break;
case 0x61: /* popa */
rc = emulate_popa(ctxt, ops);
- if (rc != 0)
+ if (rc != X86EMUL_CONTINUE)
goto done;
break;
case 0x63: /* movsxd */
@@ -2010,47 +2659,29 @@ 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 (!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 */
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);
@@ -2107,12 +2738,11 @@ 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;
@@ -2132,16 +2762,16 @@ 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);
+ rc = load_segment_descriptor(ctxt, ops, sel, c->modrm_reg);
c->dst.type = OP_NONE; /* Disable writeback. */
break;
}
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 */
@@ -2175,89 +2805,16 @@ 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;
@@ -2277,7 +2834,7 @@ 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 */
@@ -2290,14 +2847,10 @@ 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;
@@ -2308,8 +2861,9 @@ special_insn:
case 0xe9: /* jmp rel */
goto jmp;
case 0xea: /* jmp far */
- if (kvm_load_segment_descriptor(ctxt->vcpu, c->src2.val,
- VCPU_SREG_CS))
+ jump_far:
+ if (load_segment_descriptor(ctxt, ops, c->src2.val,
+ VCPU_SREG_CS))
goto done;
c->eip = c->src.val;
@@ -2321,25 +2875,29 @@ 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 (!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 */
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;
@@ -2350,16 +2908,15 @@ special_insn:
c->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf6 ... 0xf7: /* Grp3 */
- rc = emulate_grp3(ctxt, ops);
- if (rc != 0)
- goto done;
+ if (!emulate_grp3(ctxt, ops))
+ goto cannot_emulate;
break;
case 0xf8: /* clc */
ctxt->eflags &= ~EFLG_CF;
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;
@@ -2367,10 +2924,10 @@ 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, X86_SHADOW_INT_STI);
+ toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI);
ctxt->eflags |= X86_EFLAGS_IF;
c->dst.type = OP_NONE; /* Disable writeback. */
}
@@ -2383,28 +2940,55 @@ 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 != 0)
+ if (rc != X86EMUL_CONTINUE)
goto done;
break;
+ case 0xff: /* Grp5 */
+ if (c->modrm_reg == 5)
+ goto jump_far;
+ goto grp45;
}
writeback:
rc = writeback(ctxt, ops);
- if (rc != 0)
+ 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);
+
+ if ((c->d & DstMask) == DstDI)
+ 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);
+ /*
+ * 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;
+ }
+
/* 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:
- if (rc == X86EMUL_UNHANDLEABLE) {
- c->eip = saved_eip;
- return -1;
- }
- return 0;
+ return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
twobyte_insn:
switch (c->b) {
@@ -2418,18 +3002,18 @@ 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 */
- c->eip = kvm_rip_read(ctxt->vcpu);
+ c->eip = ctxt->eip;
/* Disable writeback. */
c->dst.type = OP_NONE;
break;
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 +3024,7 @@ 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 +3034,7 @@ 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);
}
@@ -2459,15 +3043,18 @@ 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,
- &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 5: /* not defined */
+ 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;
@@ -2493,54 +3080,54 @@ 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] =
- realmode_get_cr(ctxt->vcpu, c->modrm_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;
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)
- goto cannot_emulate;
+ 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 */
- if (c->modrm_mod != 3)
- goto cannot_emulate;
- realmode_set_cr(ctxt->vcpu,
- c->modrm_reg, c->modrm_val, &ctxt->eflags);
+ 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;
- rc = emulator_set_dr(ctxt, c->modrm_reg,
- c->regs[c->modrm_rm]);
- if (rc)
- goto cannot_emulate;
+ 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:
/* 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);
+ goto done;
}
rc = X86EMUL_CONTINUE;
c->dst.type = OP_NONE;
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);
+ goto done;
} else {
c->regs[VCPU_REGS_RAX] = (u32)msr_data;
c->regs[VCPU_REGS_RDX] = msr_data >> 32;
@@ -2577,7 +3164,7 @@ 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 +3183,7 @@ 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:
@@ -2668,16 +3255,14 @@ twobyte_insn:
(u64) c->src.val;
break;
case 0xc7: /* Grp9 (cmpxchg8b) */
- rc = emulate_grp9(ctxt, ops, memop);
- if (rc != 0)
+ rc = emulate_grp9(ctxt, ops);
+ if (rc != X86EMUL_CONTINUE)
goto done;
- c->dst.type = OP_NONE;
break;
}
goto writeback;
cannot_emulate:
DPRINTF("Cannot emulate %02x\n", c->b);
- c->eip = saved_eip;
return -1;
}
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index a790fa128a9f..93825ff3338f 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -33,6 +33,29 @@
#include <linux/kvm_host.h>
#include "trace.h"
+static void pic_lock(struct kvm_pic *s)
+ __acquires(&s->lock)
+{
+ raw_spin_lock(&s->lock);
+}
+
+static void pic_unlock(struct kvm_pic *s)
+ __releases(&s->lock)
+{
+ bool wakeup = s->wakeup_needed;
+ struct kvm_vcpu *vcpu;
+
+ s->wakeup_needed = false;
+
+ raw_spin_unlock(&s->lock);
+
+ if (wakeup) {
+ vcpu = s->kvm->bsp_vcpu;
+ if (vcpu)
+ kvm_vcpu_kick(vcpu);
+ }
+}
+
static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
{
s->isr &= ~(1 << irq);
@@ -45,19 +68,19 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
* Other interrupt may be delivered to PIC while lock is dropped but
* it should be safe since PIC state is already updated at this stage.
*/
- raw_spin_unlock(&s->pics_state->lock);
+ pic_unlock(s->pics_state);
kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
- raw_spin_lock(&s->pics_state->lock);
+ pic_lock(s->pics_state);
}
void kvm_pic_clear_isr_ack(struct kvm *kvm)
{
struct kvm_pic *s = pic_irqchip(kvm);
- raw_spin_lock(&s->lock);
+ pic_lock(s);
s->pics[0].isr_ack = 0xff;
s->pics[1].isr_ack = 0xff;
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
}
/*
@@ -158,9 +181,9 @@ static void pic_update_irq(struct kvm_pic *s)
void kvm_pic_update_irq(struct kvm_pic *s)
{
- raw_spin_lock(&s->lock);
+ pic_lock(s);
pic_update_irq(s);
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
}
int kvm_pic_set_irq(void *opaque, int irq, int level)
@@ -168,14 +191,14 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
struct kvm_pic *s = opaque;
int ret = -1;
- raw_spin_lock(&s->lock);
+ pic_lock(s);
if (irq >= 0 && irq < PIC_NUM_PINS) {
ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, level);
pic_update_irq(s);
trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
s->pics[irq >> 3].imr, ret == 0);
}
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
return ret;
}
@@ -205,7 +228,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
int irq, irq2, intno;
struct kvm_pic *s = pic_irqchip(kvm);
- raw_spin_lock(&s->lock);
+ pic_lock(s);
irq = pic_get_irq(&s->pics[0]);
if (irq >= 0) {
pic_intack(&s->pics[0], irq);
@@ -230,7 +253,7 @@ int kvm_pic_read_irq(struct kvm *kvm)
intno = s->pics[0].irq_base + irq;
}
pic_update_irq(s);
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
return intno;
}
@@ -444,7 +467,7 @@ static int picdev_write(struct kvm_io_device *this,
printk(KERN_ERR "PIC: non byte write\n");
return 0;
}
- raw_spin_lock(&s->lock);
+ pic_lock(s);
switch (addr) {
case 0x20:
case 0x21:
@@ -457,7 +480,7 @@ static int picdev_write(struct kvm_io_device *this,
elcr_ioport_write(&s->pics[addr & 1], addr, data);
break;
}
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
return 0;
}
@@ -474,7 +497,7 @@ static int picdev_read(struct kvm_io_device *this,
printk(KERN_ERR "PIC: non byte read\n");
return 0;
}
- raw_spin_lock(&s->lock);
+ pic_lock(s);
switch (addr) {
case 0x20:
case 0x21:
@@ -488,7 +511,7 @@ static int picdev_read(struct kvm_io_device *this,
break;
}
*(unsigned char *)val = data;
- raw_spin_unlock(&s->lock);
+ pic_unlock(s);
return 0;
}
@@ -505,7 +528,7 @@ static void pic_irq_request(void *opaque, int level)
s->output = level;
if (vcpu && level && (s->pics[0].isr_ack & (1 << irq))) {
s->pics[0].isr_ack &= ~(1 << irq);
- kvm_vcpu_kick(vcpu);
+ s->wakeup_needed = true;
}
}
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 34b15915754d..cd1f362f413d 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -63,6 +63,7 @@ struct kvm_kpic_state {
struct kvm_pic {
raw_spinlock_t lock;
+ bool wakeup_needed;
unsigned pending_acks;
struct kvm *kvm;
struct kvm_kpic_state pics[2]; /* 0 is master pic, 1 is slave pic */
diff --git a/arch/x86/kvm/kvm_timer.h b/arch/x86/kvm/kvm_timer.h
index 55c7524dda54..64bc6ea78d90 100644
--- a/arch/x86/kvm/kvm_timer.h
+++ b/arch/x86/kvm/kvm_timer.h
@@ -10,9 +10,7 @@ struct kvm_timer {
};
struct kvm_timer_ops {
- bool (*is_periodic)(struct kvm_timer *);
+ bool (*is_periodic)(struct kvm_timer *);
};
-
enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);
-
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 19a8906bcaa2..a6f695d76928 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -148,7 +148,6 @@ module_param(oos_shadow, bool, 0644);
#include <trace/events/kvm.h>
-#undef TRACE_INCLUDE_FILE
#define CREATE_TRACE_POINTS
#include "mmutrace.h"
@@ -174,12 +173,7 @@ struct kvm_shadow_walk_iterator {
shadow_walk_okay(&(_walker)); \
shadow_walk_next(&(_walker)))
-
-struct kvm_unsync_walk {
- int (*entry) (struct kvm_mmu_page *sp, struct kvm_unsync_walk *walk);
-};
-
-typedef int (*mmu_parent_walk_fn) (struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp);
+typedef int (*mmu_parent_walk_fn) (struct kvm_mmu_page *sp);
static struct kmem_cache *pte_chain_cache;
static struct kmem_cache *rmap_desc_cache;
@@ -223,7 +217,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
-static int is_write_protection(struct kvm_vcpu *vcpu)
+static bool is_write_protection(struct kvm_vcpu *vcpu)
{
return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
}
@@ -327,7 +321,6 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
page = alloc_page(GFP_KERNEL);
if (!page)
return -ENOMEM;
- set_page_private(page, 0);
cache->objects[cache->nobjs++] = page_address(page);
}
return 0;
@@ -438,9 +431,9 @@ static void unaccount_shadowed(struct kvm *kvm, gfn_t gfn)
int i;
gfn = unalias_gfn(kvm, gfn);
+ slot = gfn_to_memslot_unaliased(kvm, gfn);
for (i = PT_DIRECTORY_LEVEL;
i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- slot = gfn_to_memslot_unaliased(kvm, gfn);
write_count = slot_largepage_idx(gfn, slot, i);
*write_count -= 1;
WARN_ON(*write_count < 0);
@@ -654,7 +647,6 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
{
struct kvm_rmap_desc *desc;
- struct kvm_rmap_desc *prev_desc;
u64 *prev_spte;
int i;
@@ -666,7 +658,6 @@ static u64 *rmap_next(struct kvm *kvm, unsigned long *rmapp, u64 *spte)
return NULL;
}
desc = (struct kvm_rmap_desc *)(*rmapp & ~1ul);
- prev_desc = NULL;
prev_spte = NULL;
while (desc) {
for (i = 0; i < RMAP_EXT && desc->sptes[i]; ++i) {
@@ -794,7 +785,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
int retval = 0;
struct kvm_memslots *slots;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
for (i = 0; i < slots->nmemslots; i++) {
struct kvm_memory_slot *memslot = &slots->memslots[i];
@@ -925,7 +916,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache, PAGE_SIZE);
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
- INIT_LIST_HEAD(&sp->oos_link);
bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
sp->multimapped = 0;
sp->parent_pte = parent_pte;
@@ -1009,8 +999,7 @@ static void mmu_page_remove_parent_pte(struct kvm_mmu_page *sp,
}
-static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
- mmu_parent_walk_fn fn)
+static void mmu_parent_walk(struct kvm_mmu_page *sp, mmu_parent_walk_fn fn)
{
struct kvm_pte_chain *pte_chain;
struct hlist_node *node;
@@ -1019,8 +1008,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (!sp->multimapped && sp->parent_pte) {
parent_sp = page_header(__pa(sp->parent_pte));
- fn(vcpu, parent_sp);
- mmu_parent_walk(vcpu, parent_sp, fn);
+ fn(parent_sp);
+ mmu_parent_walk(parent_sp, fn);
return;
}
hlist_for_each_entry(pte_chain, node, &sp->parent_ptes, link)
@@ -1028,8 +1017,8 @@ static void mmu_parent_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (!pte_chain->parent_ptes[i])
break;
parent_sp = page_header(__pa(pte_chain->parent_ptes[i]));
- fn(vcpu, parent_sp);
- mmu_parent_walk(vcpu, parent_sp, fn);
+ fn(parent_sp);
+ mmu_parent_walk(parent_sp, fn);
}
}
@@ -1066,16 +1055,15 @@ static void kvm_mmu_update_parents_unsync(struct kvm_mmu_page *sp)
}
}
-static int unsync_walk_fn(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
+static int unsync_walk_fn(struct kvm_mmu_page *sp)
{
kvm_mmu_update_parents_unsync(sp);
return 1;
}
-static void kvm_mmu_mark_parents_unsync(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp)
+static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp)
{
- mmu_parent_walk(vcpu, sp, unsync_walk_fn);
+ mmu_parent_walk(sp, unsync_walk_fn);
kvm_mmu_update_parents_unsync(sp);
}
@@ -1201,6 +1189,7 @@ static struct kvm_mmu_page *kvm_mmu_lookup_page(struct kvm *kvm, gfn_t gfn)
static void kvm_unlink_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
WARN_ON(!sp->unsync);
+ trace_kvm_mmu_sync_page(sp);
sp->unsync = 0;
--kvm->stat.mmu_unsync;
}
@@ -1209,12 +1198,11 @@ static int kvm_mmu_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp);
static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
- if (sp->role.glevels != vcpu->arch.mmu.root_level) {
+ if (sp->role.cr4_pae != !!is_pae(vcpu)) {
kvm_mmu_zap_page(vcpu->kvm, sp);
return 1;
}
- trace_kvm_mmu_sync_page(sp);
if (rmap_write_protect(vcpu->kvm, sp->gfn))
kvm_flush_remote_tlbs(vcpu->kvm);
kvm_unlink_unsync_page(vcpu->kvm, sp);
@@ -1331,6 +1319,8 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
role = vcpu->arch.mmu.base_role;
role.level = level;
role.direct = direct;
+ if (role.direct)
+ role.cr4_pae = 0;
role.access = access;
if (vcpu->arch.mmu.root_level <= PT32_ROOT_LEVEL) {
quadrant = gaddr >> (PAGE_SHIFT + (PT64_PT_BITS * level));
@@ -1351,7 +1341,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
mmu_page_add_parent_pte(vcpu, sp, parent_pte);
if (sp->unsync_children) {
set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
- kvm_mmu_mark_parents_unsync(vcpu, sp);
+ kvm_mmu_mark_parents_unsync(sp);
}
trace_kvm_mmu_get_page(sp, false);
return sp;
@@ -1573,13 +1563,14 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
r = 0;
index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
+restart:
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link)
if (sp->gfn == gfn && !sp->role.direct) {
pgprintk("%s: gfn %lx role %x\n", __func__, gfn,
sp->role.word);
r = 1;
if (kvm_mmu_zap_page(kvm, sp))
- n = bucket->first;
+ goto restart;
}
return r;
}
@@ -1593,13 +1584,14 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
index = kvm_page_table_hashfn(gfn);
bucket = &kvm->arch.mmu_page_hash[index];
+restart:
hlist_for_each_entry_safe(sp, node, nn, bucket, hash_link) {
if (sp->gfn == gfn && !sp->role.direct
&& !sp->role.invalid) {
pgprintk("%s: zap %lx %x\n",
__func__, gfn, sp->role.word);
if (kvm_mmu_zap_page(kvm, sp))
- nn = bucket->first;
+ goto restart;
}
}
}
@@ -1626,20 +1618,6 @@ static void mmu_convert_notrap(struct kvm_mmu_page *sp)
}
}
-struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva)
-{
- struct page *page;
-
- gpa_t gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL);
-
- if (gpa == UNMAPPED_GVA)
- return NULL;
-
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-
- return page;
-}
-
/*
* The function is based on mtrr_type_lookup() in
* arch/x86/kernel/cpu/mtrr/generic.c
@@ -1752,7 +1730,6 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
struct kvm_mmu_page *s;
struct hlist_node *node, *n;
- trace_kvm_mmu_unsync_page(sp);
index = kvm_page_table_hashfn(sp->gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
/* don't unsync if pagetable is shadowed with multiple roles */
@@ -1762,10 +1739,11 @@ static int kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
if (s->role.word != sp->role.word)
return 1;
}
+ trace_kvm_mmu_unsync_page(sp);
++vcpu->kvm->stat.mmu_unsync;
sp->unsync = 1;
- kvm_mmu_mark_parents_unsync(vcpu, sp);
+ kvm_mmu_mark_parents_unsync(sp);
mmu_convert_notrap(sp);
return 0;
@@ -1837,6 +1815,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= PT_WRITABLE_MASK;
+ if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK))
+ spte &= ~PT_USER_MASK;
+
/*
* Optimization: for pte sync, if spte was writable the hash
* lookup is unnecessary (and expensive). Write protection
@@ -1892,6 +1873,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
child = page_header(pte & PT64_BASE_ADDR_MASK);
mmu_page_remove_parent_pte(child, sptep);
+ __set_spte(sptep, shadow_trap_nonpresent_pte);
+ kvm_flush_remote_tlbs(vcpu->kvm);
} else if (pfn != spte_to_pfn(*sptep)) {
pgprintk("hfn old %lx new %lx\n",
spte_to_pfn(*sptep), pfn);
@@ -2081,21 +2064,23 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
hpa_t root = vcpu->arch.mmu.root_hpa;
ASSERT(!VALID_PAGE(root));
- if (tdp_enabled)
- direct = 1;
if (mmu_check_root(vcpu, root_gfn))
return 1;
+ if (tdp_enabled) {
+ direct = 1;
+ root_gfn = 0;
+ }
+ spin_lock(&vcpu->kvm->mmu_lock);
sp = kvm_mmu_get_page(vcpu, root_gfn, 0,
PT64_ROOT_LEVEL, direct,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
+ spin_unlock(&vcpu->kvm->mmu_lock);
vcpu->arch.mmu.root_hpa = root;
return 0;
}
direct = !is_paging(vcpu);
- if (tdp_enabled)
- direct = 1;
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
@@ -2111,11 +2096,18 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
root_gfn = 0;
if (mmu_check_root(vcpu, root_gfn))
return 1;
+ if (tdp_enabled) {
+ direct = 1;
+ root_gfn = i << 30;
+ }
+ spin_lock(&vcpu->kvm->mmu_lock);
sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30,
PT32_ROOT_LEVEL, direct,
ACC_ALL, NULL);
root = __pa(sp->spt);
++sp->root_count;
+ spin_unlock(&vcpu->kvm->mmu_lock);
+
vcpu->arch.mmu.pae_root[i] = root | PT_PRESENT_MASK;
}
vcpu->arch.mmu.root_hpa = __pa(vcpu->arch.mmu.pae_root);
@@ -2299,13 +2291,19 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
/* no rsvd bits for 2 level 4K page table entries */
context->rsvd_bits_mask[0][1] = 0;
context->rsvd_bits_mask[0][0] = 0;
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+ if (!is_pse(vcpu)) {
+ context->rsvd_bits_mask[1][1] = 0;
+ break;
+ }
+
if (is_cpuid_PSE36())
/* 36bits PSE 4MB page */
context->rsvd_bits_mask[1][1] = rsvd_bits(17, 21);
else
/* 32 bits PSE 4MB page */
context->rsvd_bits_mask[1][1] = rsvd_bits(13, 21);
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
break;
case PT32E_ROOT_LEVEL:
context->rsvd_bits_mask[0][2] =
@@ -2318,7 +2316,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 62) |
rsvd_bits(13, 20); /* large page */
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
break;
case PT64_ROOT_LEVEL:
context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
@@ -2336,7 +2334,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int level)
context->rsvd_bits_mask[1][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51) |
rsvd_bits(13, 20); /* large page */
- context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[1][0];
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
break;
}
}
@@ -2438,7 +2436,8 @@ static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
else
r = paging32_init_context(vcpu);
- vcpu->arch.mmu.base_role.glevels = vcpu->arch.mmu.root_level;
+ vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
+ vcpu->arch.mmu.base_role.cr0_wp = is_write_protection(vcpu);
return r;
}
@@ -2478,7 +2477,9 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
goto out;
spin_lock(&vcpu->kvm->mmu_lock);
kvm_mmu_free_some_pages(vcpu);
+ spin_unlock(&vcpu->kvm->mmu_lock);
r = mmu_alloc_roots(vcpu);
+ spin_lock(&vcpu->kvm->mmu_lock);
mmu_sync_roots(vcpu);
spin_unlock(&vcpu->kvm->mmu_lock);
if (r)
@@ -2527,7 +2528,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
}
++vcpu->kvm->stat.mmu_pte_updated;
- if (sp->role.glevels == PT32_ROOT_LEVEL)
+ if (!sp->role.cr4_pae)
paging32_update_pte(vcpu, sp, spte, new);
else
paging64_update_pte(vcpu, sp, spte, new);
@@ -2562,36 +2563,11 @@ static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu)
}
static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes)
+ u64 gpte)
{
gfn_t gfn;
- int r;
- u64 gpte = 0;
pfn_t pfn;
- if (bytes != 4 && bytes != 8)
- return;
-
- /*
- * Assume that the pte write on a page table of the same type
- * as the current vcpu paging mode. This is nearly always true
- * (might be false while changing modes). Note it is verified later
- * by update_pte().
- */
- if (is_pae(vcpu)) {
- /* Handle a 32-bit guest writing two halves of a 64-bit gpte */
- if ((bytes == 4) && (gpa % 4 == 0)) {
- r = kvm_read_guest(vcpu->kvm, gpa & ~(u64)7, &gpte, 8);
- if (r)
- return;
- memcpy((void *)&gpte + (gpa % 8), new, 4);
- } else if ((bytes == 8) && (gpa % 8 == 0)) {
- memcpy((void *)&gpte, new, 8);
- }
- } else {
- if ((bytes == 4) && (gpa % 4 == 0))
- memcpy((void *)&gpte, new, 4);
- }
if (!is_present_gpte(gpte))
return;
gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
@@ -2640,10 +2616,46 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
int flooded = 0;
int npte;
int r;
+ int invlpg_counter;
pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes);
- mmu_guess_page_from_pte_write(vcpu, gpa, new, bytes);
+
+ invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter);
+
+ /*
+ * Assume that the pte write on a page table of the same type
+ * as the current vcpu paging mode. This is nearly always true
+ * (might be false while changing modes). Note it is verified later
+ * by update_pte().
+ */
+ if ((is_pae(vcpu) && bytes == 4) || !new) {
+ /* Handle a 32-bit guest writing two halves of a 64-bit gpte */
+ if (is_pae(vcpu)) {
+ gpa &= ~(gpa_t)7;
+ bytes = 8;
+ }
+ r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8));
+ if (r)
+ gentry = 0;
+ new = (const u8 *)&gentry;
+ }
+
+ switch (bytes) {
+ case 4:
+ gentry = *(const u32 *)new;
+ break;
+ case 8:
+ gentry = *(const u64 *)new;
+ break;
+ default:
+ gentry = 0;
+ break;
+ }
+
+ mmu_guess_page_from_pte_write(vcpu, gpa, gentry);
spin_lock(&vcpu->kvm->mmu_lock);
+ if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
+ gentry = 0;
kvm_mmu_access_page(vcpu, gfn);
kvm_mmu_free_some_pages(vcpu);
++vcpu->kvm->stat.mmu_pte_write;
@@ -2662,10 +2674,12 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
}
index = kvm_page_table_hashfn(gfn);
bucket = &vcpu->kvm->arch.mmu_page_hash[index];
+
+restart:
hlist_for_each_entry_safe(sp, node, n, bucket, hash_link) {
if (sp->gfn != gfn || sp->role.direct || sp->role.invalid)
continue;
- pte_size = sp->role.glevels == PT32_ROOT_LEVEL ? 4 : 8;
+ pte_size = sp->role.cr4_pae ? 8 : 4;
misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1);
misaligned |= bytes < 4;
if (misaligned || flooded) {
@@ -2682,14 +2696,14 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
pgprintk("misaligned: gpa %llx bytes %d role %x\n",
gpa, bytes, sp->role.word);
if (kvm_mmu_zap_page(vcpu->kvm, sp))
- n = bucket->first;
+ goto restart;
++vcpu->kvm->stat.mmu_flooded;
continue;
}
page_offset = offset;
level = sp->role.level;
npte = 1;
- if (sp->role.glevels == PT32_ROOT_LEVEL) {
+ if (!sp->role.cr4_pae) {
page_offset <<= 1; /* 32->64 */
/*
* A 32-bit pde maps 4MB while the shadow pdes map
@@ -2707,20 +2721,11 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
continue;
}
spte = &sp->spt[page_offset / sizeof(*spte)];
- if ((gpa & (pte_size - 1)) || (bytes < pte_size)) {
- gentry = 0;
- r = kvm_read_guest_atomic(vcpu->kvm,
- gpa & ~(u64)(pte_size - 1),
- &gentry, pte_size);
- new = (const void *)&gentry;
- if (r < 0)
- new = NULL;
- }
while (npte--) {
entry = *spte;
mmu_pte_write_zap_pte(vcpu, sp, spte);
- if (new)
- mmu_pte_write_new_pte(vcpu, sp, spte, new);
+ if (gentry)
+ mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
mmu_pte_write_flush_tlb(vcpu, entry, *spte);
++spte;
}
@@ -2900,22 +2905,23 @@ void kvm_mmu_zap_all(struct kvm *kvm)
struct kvm_mmu_page *sp, *node;
spin_lock(&kvm->mmu_lock);
+restart:
list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link)
if (kvm_mmu_zap_page(kvm, sp))
- node = container_of(kvm->arch.active_mmu_pages.next,
- struct kvm_mmu_page, link);
+ goto restart;
+
spin_unlock(&kvm->mmu_lock);
kvm_flush_remote_tlbs(kvm);
}
-static void kvm_mmu_remove_one_alloc_mmu_page(struct kvm *kvm)
+static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm)
{
struct kvm_mmu_page *page;
page = container_of(kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
- kvm_mmu_zap_page(kvm, page);
+ return kvm_mmu_zap_page(kvm, page) + 1;
}
static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
@@ -2927,7 +2933,7 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
- int npages, idx;
+ int npages, idx, freed_pages;
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
@@ -2935,8 +2941,8 @@ static int mmu_shrink(int nr_to_scan, gfp_t gfp_mask)
kvm->arch.n_free_mmu_pages;
cache_count += npages;
if (!kvm_freed && nr_to_scan > 0 && npages > 0) {
- kvm_mmu_remove_one_alloc_mmu_page(kvm);
- cache_count--;
+ freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm);
+ cache_count -= freed_pages;
kvm_freed = kvm;
}
nr_to_scan--;
@@ -3011,7 +3017,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
unsigned int nr_pages = 0;
struct kvm_memslots *slots;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
+
for (i = 0; i < slots->nmemslots; i++)
nr_pages += slots->memslots[i].npages;
@@ -3174,8 +3181,7 @@ static gva_t canonicalize(gva_t gva)
}
-typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp,
- u64 *sptep);
+typedef void (*inspect_spte_fn) (struct kvm *kvm, u64 *sptep);
static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
inspect_spte_fn fn)
@@ -3191,7 +3197,7 @@ static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
child = page_header(ent & PT64_BASE_ADDR_MASK);
__mmu_spte_walk(kvm, child, fn);
} else
- fn(kvm, sp, &sp->spt[i]);
+ fn(kvm, &sp->spt[i]);
}
}
}
@@ -3282,11 +3288,13 @@ static void audit_mappings(struct kvm_vcpu *vcpu)
static int count_rmaps(struct kvm_vcpu *vcpu)
{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_memslots *slots;
int nmaps = 0;
int i, j, k, idx;
idx = srcu_read_lock(&kvm->srcu);
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
struct kvm_memory_slot *m = &slots->memslots[i];
struct kvm_rmap_desc *d;
@@ -3315,7 +3323,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
return nmaps;
}
-void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
+void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
{
unsigned long *rmapp;
struct kvm_mmu_page *rev_sp;
@@ -3331,14 +3339,14 @@ void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
printk(KERN_ERR "%s: no memslot for gfn %ld\n",
audit_msg, gfn);
printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n",
- audit_msg, sptep - rev_sp->spt,
+ audit_msg, (long int)(sptep - rev_sp->spt),
rev_sp->gfn);
dump_stack();
return;
}
rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt],
- is_large_pte(*sptep));
+ rev_sp->role.level);
if (!*rmapp) {
if (!printk_ratelimit())
return;
@@ -3373,7 +3381,7 @@ static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu)
continue;
if (!(ent & PT_WRITABLE_MASK))
continue;
- inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]);
+ inspect_spte_has_rmap(vcpu->kvm, &pt[i]);
}
}
return;
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 3e4a5c6ca2a9..42f07b1bfbc9 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -6,14 +6,12 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvmmmu
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE mmutrace
#define KVM_MMU_PAGE_FIELDS \
__field(__u64, gfn) \
__field(__u32, role) \
__field(__u32, root_count) \
- __field(__u32, unsync)
+ __field(bool, unsync)
#define KVM_MMU_PAGE_ASSIGN(sp) \
__entry->gfn = sp->gfn; \
@@ -30,14 +28,14 @@
\
role.word = __entry->role; \
\
- trace_seq_printf(p, "sp gfn %llx %u/%u q%u%s %s%s %spge" \
+ trace_seq_printf(p, "sp gfn %llx %u%s q%u%s %s%s" \
" %snxe root %u %s%c", \
- __entry->gfn, role.level, role.glevels, \
+ __entry->gfn, role.level, \
+ role.cr4_pae ? " pae" : "", \
role.quadrant, \
role.direct ? " direct" : "", \
access_str[role.access], \
role.invalid ? " invalid" : "", \
- role.cr4_pge ? "" : "!", \
role.nxe ? "" : "!", \
__entry->root_count, \
__entry->unsync ? "unsync" : "sync", 0); \
@@ -94,15 +92,15 @@ TRACE_EVENT(
TP_printk("pte %llx level %u", __entry->pte, __entry->level)
);
-/* We set a pte accessed bit */
-TRACE_EVENT(
- kvm_mmu_set_accessed_bit,
+DECLARE_EVENT_CLASS(kvm_mmu_set_bit_class,
+
TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
TP_ARGS(table_gfn, index, size),
TP_STRUCT__entry(
__field(__u64, gpa)
- ),
+ ),
TP_fast_assign(
__entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
@@ -112,22 +110,20 @@ TRACE_EVENT(
TP_printk("gpa %llx", __entry->gpa)
);
-/* We set a pte dirty bit */
-TRACE_EVENT(
- kvm_mmu_set_dirty_bit,
+/* We set a pte accessed bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_accessed_bit,
+
TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
- TP_ARGS(table_gfn, index, size),
- TP_STRUCT__entry(
- __field(__u64, gpa)
- ),
+ TP_ARGS(table_gfn, index, size)
+);
- TP_fast_assign(
- __entry->gpa = ((u64)table_gfn << PAGE_SHIFT)
- + index * size;
- ),
+/* We set a pte dirty bit */
+DEFINE_EVENT(kvm_mmu_set_bit_class, kvm_mmu_set_dirty_bit,
- TP_printk("gpa %llx", __entry->gpa)
+ TP_PROTO(unsigned long table_gfn, unsigned index, unsigned size),
+
+ TP_ARGS(table_gfn, index, size)
);
TRACE_EVENT(
@@ -166,55 +162,45 @@ TRACE_EVENT(
__entry->created ? "new" : "existing")
);
-TRACE_EVENT(
- kvm_mmu_sync_page,
+DECLARE_EVENT_CLASS(kvm_mmu_page_class,
+
TP_PROTO(struct kvm_mmu_page *sp),
TP_ARGS(sp),
TP_STRUCT__entry(
KVM_MMU_PAGE_FIELDS
- ),
+ ),
TP_fast_assign(
KVM_MMU_PAGE_ASSIGN(sp)
- ),
+ ),
TP_printk("%s", KVM_MMU_PAGE_PRINTK())
);
-TRACE_EVENT(
- kvm_mmu_unsync_page,
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_sync_page,
TP_PROTO(struct kvm_mmu_page *sp),
- TP_ARGS(sp),
-
- TP_STRUCT__entry(
- KVM_MMU_PAGE_FIELDS
- ),
- TP_fast_assign(
- KVM_MMU_PAGE_ASSIGN(sp)
- ),
-
- TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+ TP_ARGS(sp)
);
-TRACE_EVENT(
- kvm_mmu_zap_page,
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_unsync_page,
TP_PROTO(struct kvm_mmu_page *sp),
- TP_ARGS(sp),
- TP_STRUCT__entry(
- KVM_MMU_PAGE_FIELDS
- ),
+ TP_ARGS(sp)
+);
- TP_fast_assign(
- KVM_MMU_PAGE_ASSIGN(sp)
- ),
+DEFINE_EVENT(kvm_mmu_page_class, kvm_mmu_zap_page,
+ TP_PROTO(struct kvm_mmu_page *sp),
- TP_printk("%s", KVM_MMU_PAGE_PRINTK())
+ TP_ARGS(sp)
);
-
#endif /* _TRACE_KVMMMU_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE mmutrace
+
/* This part must be outside protection */
#include <trace/define_trace.h>
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 81eab9a50e6a..89d66ca4d87c 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -170,7 +170,7 @@ walk:
goto access_error;
#if PTTYPE == 64
- if (fetch_fault && is_nx(vcpu) && (pte & PT64_NX_MASK))
+ if (fetch_fault && (pte & PT64_NX_MASK))
goto access_error;
#endif
@@ -190,10 +190,10 @@ walk:
if ((walker->level == PT_PAGE_TABLE_LEVEL) ||
((walker->level == PT_DIRECTORY_LEVEL) &&
- (pte & PT_PAGE_SIZE_MASK) &&
+ is_large_pte(pte) &&
(PTTYPE == 64 || is_pse(vcpu))) ||
((walker->level == PT_PDPE_LEVEL) &&
- (pte & PT_PAGE_SIZE_MASK) &&
+ is_large_pte(pte) &&
is_long_mode(vcpu))) {
int lvl = walker->level;
@@ -258,11 +258,17 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page,
pt_element_t gpte;
unsigned pte_access;
pfn_t pfn;
+ u64 new_spte;
gpte = *(const pt_element_t *)pte;
if (~gpte & (PT_PRESENT_MASK | PT_ACCESSED_MASK)) {
- if (!is_present_gpte(gpte))
- __set_spte(spte, shadow_notrap_nonpresent_pte);
+ if (!is_present_gpte(gpte)) {
+ if (page->unsync)
+ new_spte = shadow_trap_nonpresent_pte;
+ else
+ new_spte = shadow_notrap_nonpresent_pte;
+ __set_spte(spte, new_spte);
+ }
return;
}
pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
@@ -457,6 +463,7 @@ out_unlock:
static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
{
struct kvm_shadow_walk_iterator iterator;
+ gpa_t pte_gpa = -1;
int level;
u64 *sptep;
int need_flush = 0;
@@ -467,9 +474,16 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
level = iterator.level;
sptep = iterator.sptep;
- if (level == PT_PAGE_TABLE_LEVEL ||
- ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
- ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {
+ if (is_last_spte(*sptep, level)) {
+ struct kvm_mmu_page *sp = page_header(__pa(sptep));
+ int offset, shift;
+
+ shift = PAGE_SHIFT -
+ (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level;
+ offset = sp->role.quadrant << shift;
+
+ pte_gpa = (sp->gfn << PAGE_SHIFT) + offset;
+ pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
if (is_shadow_present_pte(*sptep)) {
rmap_remove(vcpu->kvm, sptep);
@@ -487,7 +501,17 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
if (need_flush)
kvm_flush_remote_tlbs(vcpu->kvm);
+
+ atomic_inc(&vcpu->kvm->arch.invlpg_counter);
+
spin_unlock(&vcpu->kvm->mmu_lock);
+
+ if (pte_gpa == -1)
+ return;
+
+ if (mmu_topup_memory_caches(vcpu))
+ return;
+ kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0);
}
static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
@@ -551,12 +575,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
{
int i, offset, nr_present;
bool reset_host_protection;
+ gpa_t first_pte_gpa;
offset = nr_present = 0;
if (PTTYPE == 32)
offset = sp->role.quadrant << PT64_LEVEL_BITS;
+ first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t);
+
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
unsigned pte_access;
pt_element_t gpte;
@@ -566,8 +593,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
if (!is_shadow_present_pte(sp->spt[i]))
continue;
- pte_gpa = gfn_to_gpa(sp->gfn);
- pte_gpa += (i+offset) * sizeof(pt_element_t);
+ pte_gpa = first_pte_gpa + i * sizeof(pt_element_t);
if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte,
sizeof(pt_element_t)))
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 737361fcd503..ce438e0fdd26 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -28,6 +28,7 @@
#include <linux/ftrace_event.h>
#include <linux/slab.h>
+#include <asm/tlbflush.h>
#include <asm/desc.h>
#include <asm/virtext.h>
@@ -44,10 +45,11 @@ MODULE_LICENSE("GPL");
#define SEG_TYPE_LDT 2
#define SEG_TYPE_BUSY_TSS16 3
-#define SVM_FEATURE_NPT (1 << 0)
-#define SVM_FEATURE_LBRV (1 << 1)
-#define SVM_FEATURE_SVML (1 << 2)
-#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
+#define SVM_FEATURE_NPT (1 << 0)
+#define SVM_FEATURE_LBRV (1 << 1)
+#define SVM_FEATURE_SVML (1 << 2)
+#define SVM_FEATURE_NRIP (1 << 3)
+#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
@@ -55,6 +57,8 @@ MODULE_LICENSE("GPL");
#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+static bool erratum_383_found __read_mostly;
+
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
@@ -70,6 +74,7 @@ struct kvm_vcpu;
struct nested_state {
struct vmcb *hsave;
u64 hsave_msr;
+ u64 vm_cr_msr;
u64 vmcb;
/* These are the merged vectors */
@@ -77,6 +82,7 @@ struct nested_state {
/* gpa pointers to the real vectors */
u64 vmcb_msrpm;
+ u64 vmcb_iopm;
/* A VMEXIT is required but not yet emulated */
bool exit_required;
@@ -91,6 +97,9 @@ struct nested_state {
};
+#define MSRPM_OFFSETS 16
+static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
+
struct vcpu_svm {
struct kvm_vcpu vcpu;
struct vmcb *vmcb;
@@ -110,13 +119,39 @@ struct vcpu_svm {
struct nested_state nested;
bool nmi_singlestep;
+
+ unsigned int3_injected;
+ unsigned long int3_rip;
+};
+
+#define MSR_INVALID 0xffffffffU
+
+static struct svm_direct_access_msrs {
+ u32 index; /* Index of the MSR */
+ bool always; /* True if intercept is always on */
+} direct_access_msrs[] = {
+ { .index = MSR_K6_STAR, .always = true },
+ { .index = MSR_IA32_SYSENTER_CS, .always = true },
+#ifdef CONFIG_X86_64
+ { .index = MSR_GS_BASE, .always = true },
+ { .index = MSR_FS_BASE, .always = true },
+ { .index = MSR_KERNEL_GS_BASE, .always = true },
+ { .index = MSR_LSTAR, .always = true },
+ { .index = MSR_CSTAR, .always = true },
+ { .index = MSR_SYSCALL_MASK, .always = true },
+#endif
+ { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
+ { .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
+ { .index = MSR_IA32_LASTINTFROMIP, .always = false },
+ { .index = MSR_IA32_LASTINTTOIP, .always = false },
+ { .index = MSR_INVALID, .always = false },
};
/* enable NPT for AMD64 and X86 with PAE */
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
static bool npt_enabled = true;
#else
-static bool npt_enabled = false;
+static bool npt_enabled;
#endif
static int npt = 1;
@@ -129,6 +164,7 @@ static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
static int nested_svm_exit_handled(struct vcpu_svm *svm);
+static int nested_svm_intercept(struct vcpu_svm *svm);
static int nested_svm_vmexit(struct vcpu_svm *svm);
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
@@ -163,8 +199,8 @@ static unsigned long iopm_base;
struct kvm_ldttss_desc {
u16 limit0;
u16 base0;
- unsigned base1 : 8, type : 5, dpl : 2, p : 1;
- unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+ unsigned base1:8, type:5, dpl:2, p:1;
+ unsigned limit1:4, zero0:3, g:1, base2:8;
u32 base3;
u32 zero1;
} __attribute__((packed));
@@ -194,6 +230,27 @@ static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
#define MSRS_RANGE_SIZE 2048
#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
+static u32 svm_msrpm_offset(u32 msr)
+{
+ u32 offset;
+ int i;
+
+ for (i = 0; i < NUM_MSR_MAPS; i++) {
+ if (msr < msrpm_ranges[i] ||
+ msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
+ continue;
+
+ offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
+ offset += (i * MSRS_RANGE_SIZE); /* add range offset */
+
+ /* Now we have the u8 offset - but need the u32 offset */
+ return offset / 4;
+ }
+
+ /* MSR not in any range */
+ return MSR_INVALID;
+}
+
#define MAX_INST_SIZE 15
static inline u32 svm_has(u32 feat)
@@ -213,7 +270,7 @@ static inline void stgi(void)
static inline void invlpga(unsigned long addr, u32 asid)
{
- asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
+ asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid));
}
static inline void force_new_asid(struct kvm_vcpu *vcpu)
@@ -235,23 +292,6 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
vcpu->arch.efer = efer;
}
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- /* If we are within a nested VM we'd better #VMEXIT and let the
- guest handle the exception */
- if (nested_svm_check_exception(svm, nr, has_error_code, error_code))
- return;
-
- svm->vmcb->control.event_inj = nr
- | SVM_EVTINJ_VALID
- | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
- | SVM_EVTINJ_TYPE_EXEPT;
- svm->vmcb->control.event_inj_err = error_code;
-}
-
static int is_external_interrupt(u32 info)
{
info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
@@ -264,7 +304,7 @@ 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;
}
@@ -283,6 +323,9 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (svm->vmcb->control.next_rip != 0)
+ svm->next_rip = svm->vmcb->control.next_rip;
+
if (!svm->next_rip) {
if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
@@ -297,6 +340,68 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
svm_set_interrupt_shadow(vcpu, 0);
}
+static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
+ bool has_error_code, u32 error_code,
+ bool reinject)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ /*
+ * If we are within a nested VM we'd better #VMEXIT and let the guest
+ * handle the exception
+ */
+ if (!reinject &&
+ nested_svm_check_exception(svm, nr, has_error_code, error_code))
+ return;
+
+ if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) {
+ unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu);
+
+ /*
+ * For guest debugging where we have to reinject #BP if some
+ * INT3 is guest-owned:
+ * Emulate nRIP by moving RIP forward. Will fail if injection
+ * raises a fault that is not intercepted. Still better than
+ * failing in all cases.
+ */
+ skip_emulated_instruction(&svm->vcpu);
+ rip = kvm_rip_read(&svm->vcpu);
+ svm->int3_rip = rip + svm->vmcb->save.cs.base;
+ svm->int3_injected = rip - old_rip;
+ }
+
+ svm->vmcb->control.event_inj = nr
+ | SVM_EVTINJ_VALID
+ | (has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
+ | SVM_EVTINJ_TYPE_EXEPT;
+ svm->vmcb->control.event_inj_err = error_code;
+}
+
+static void svm_init_erratum_383(void)
+{
+ u32 low, high;
+ int err;
+ u64 val;
+
+ /* Only Fam10h is affected */
+ if (boot_cpu_data.x86 != 0x10)
+ return;
+
+ /* Use _safe variants to not break nested virtualization */
+ val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
+ if (err)
+ return;
+
+ val |= (1ULL << 47);
+
+ low = lower_32_bits(val);
+ high = upper_32_bits(val);
+
+ native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+
+ erratum_383_found = true;
+}
+
static int has_svm(void)
{
const char *msg;
@@ -319,7 +424,7 @@ static int svm_hardware_enable(void *garbage)
struct svm_cpu_data *sd;
uint64_t efer;
- struct descriptor_table gdt_descr;
+ struct desc_ptr gdt_descr;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
@@ -344,14 +449,16 @@ static int svm_hardware_enable(void *garbage)
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
- kvm_get_gdt(&gdt_descr);
- gdt = (struct desc_struct *)gdt_descr.base;
+ native_store_gdt(&gdt_descr);
+ gdt = (struct desc_struct *)gdt_descr.address;
sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
wrmsrl(MSR_EFER, efer | EFER_SVME);
wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+ svm_init_erratum_383();
+
return 0;
}
@@ -391,42 +498,98 @@ err_1:
}
+static bool valid_msr_intercept(u32 index)
+{
+ int i;
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
+ if (direct_access_msrs[i].index == index)
+ return true;
+
+ return false;
+}
+
static void set_msr_interception(u32 *msrpm, unsigned msr,
int read, int write)
{
+ u8 bit_read, bit_write;
+ unsigned long tmp;
+ u32 offset;
+
+ /*
+ * If this warning triggers extend the direct_access_msrs list at the
+ * beginning of the file
+ */
+ WARN_ON(!valid_msr_intercept(msr));
+
+ offset = svm_msrpm_offset(msr);
+ bit_read = 2 * (msr & 0x0f);
+ bit_write = 2 * (msr & 0x0f) + 1;
+ tmp = msrpm[offset];
+
+ BUG_ON(offset == MSR_INVALID);
+
+ read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp);
+ write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+
+ msrpm[offset] = tmp;
+}
+
+static void svm_vcpu_init_msrpm(u32 *msrpm)
+{
int i;
- for (i = 0; i < NUM_MSR_MAPS; i++) {
- if (msr >= msrpm_ranges[i] &&
- msr < msrpm_ranges[i] + MSRS_IN_RANGE) {
- u32 msr_offset = (i * MSRS_IN_RANGE + msr -
- msrpm_ranges[i]) * 2;
-
- u32 *base = msrpm + (msr_offset / 32);
- u32 msr_shift = msr_offset % 32;
- u32 mask = ((write) ? 0 : 2) | ((read) ? 0 : 1);
- *base = (*base & ~(0x3 << msr_shift)) |
- (mask << msr_shift);
+ memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ if (!direct_access_msrs[i].always)
+ continue;
+
+ set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+ }
+}
+
+static void add_msr_offset(u32 offset)
+{
+ int i;
+
+ for (i = 0; i < MSRPM_OFFSETS; ++i) {
+
+ /* Offset already in list? */
+ if (msrpm_offsets[i] == offset)
return;
- }
+
+ /* Slot used by another offset? */
+ if (msrpm_offsets[i] != MSR_INVALID)
+ continue;
+
+ /* Add offset to list */
+ msrpm_offsets[i] = offset;
+
+ return;
}
+
+ /*
+ * If this BUG triggers the msrpm_offsets table has an overflow. Just
+ * increase MSRPM_OFFSETS in this case.
+ */
BUG();
}
-static void svm_vcpu_init_msrpm(u32 *msrpm)
+static void init_msrpm_offsets(void)
{
- memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+ int i;
-#ifdef CONFIG_X86_64
- set_msr_interception(msrpm, MSR_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_FS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_KERNEL_GS_BASE, 1, 1);
- set_msr_interception(msrpm, MSR_LSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_CSTAR, 1, 1);
- set_msr_interception(msrpm, MSR_SYSCALL_MASK, 1, 1);
-#endif
- set_msr_interception(msrpm, MSR_K6_STAR, 1, 1);
- set_msr_interception(msrpm, MSR_IA32_SYSENTER_CS, 1, 1);
+ memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+
+ for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+ u32 offset;
+
+ offset = svm_msrpm_offset(direct_access_msrs[i].index);
+ BUG_ON(offset == MSR_INVALID);
+
+ add_msr_offset(offset);
+ }
}
static void svm_enable_lbrv(struct vcpu_svm *svm)
@@ -467,6 +630,8 @@ static __init int svm_hardware_setup(void)
memset(iopm_va, 0xff, PAGE_SIZE * (1 << IOPM_ALLOC_ORDER));
iopm_base = page_to_pfn(iopm_pages) << PAGE_SHIFT;
+ init_msrpm_offsets();
+
if (boot_cpu_has(X86_FEATURE_NX))
kvm_enable_efer_bits(EFER_NX);
@@ -523,7 +688,7 @@ static void init_seg(struct vmcb_seg *seg)
{
seg->selector = 0;
seg->attrib = SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK |
- SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
+ SVM_SELECTOR_WRITE_MASK; /* Read/Write Data Segment */
seg->limit = 0xffff;
seg->base = 0;
}
@@ -543,16 +708,16 @@ static void init_vmcb(struct vcpu_svm *svm)
svm->vcpu.fpu_active = 1;
- control->intercept_cr_read = INTERCEPT_CR0_MASK |
+ control->intercept_cr_read = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK;
- control->intercept_cr_write = INTERCEPT_CR0_MASK |
+ control->intercept_cr_write = INTERCEPT_CR0_MASK |
INTERCEPT_CR3_MASK |
INTERCEPT_CR4_MASK |
INTERCEPT_CR8_MASK;
- control->intercept_dr_read = INTERCEPT_DR0_MASK |
+ control->intercept_dr_read = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
@@ -561,7 +726,7 @@ static void init_vmcb(struct vcpu_svm *svm)
INTERCEPT_DR6_MASK |
INTERCEPT_DR7_MASK;
- control->intercept_dr_write = INTERCEPT_DR0_MASK |
+ control->intercept_dr_write = INTERCEPT_DR0_MASK |
INTERCEPT_DR1_MASK |
INTERCEPT_DR2_MASK |
INTERCEPT_DR3_MASK |
@@ -575,7 +740,7 @@ static void init_vmcb(struct vcpu_svm *svm)
(1 << MC_VECTOR);
- control->intercept = (1ULL << INTERCEPT_INTR) |
+ control->intercept = (1ULL << INTERCEPT_INTR) |
(1ULL << INTERCEPT_NMI) |
(1ULL << INTERCEPT_SMI) |
(1ULL << INTERCEPT_SELECTIVE_CR0) |
@@ -636,7 +801,8 @@ static void init_vmcb(struct vcpu_svm *svm)
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
- /* This is the guest-visible cr0 value.
+ /*
+ * This is the guest-visible cr0 value.
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
@@ -729,6 +895,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
svm_vcpu_init_msrpm(svm->msrpm);
svm->nested.msrpm = page_address(nested_msrpm_pages);
+ svm_vcpu_init_msrpm(svm->nested.msrpm);
svm->vmcb = page_address(page);
clear_page(svm->vmcb);
@@ -882,7 +1049,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
var->db = (s->attrib >> SVM_SELECTOR_DB_SHIFT) & 1;
var->g = (s->attrib >> SVM_SELECTOR_G_SHIFT) & 1;
- /* AMD's VMCB does not have an explicit unusable field, so emulate it
+ /*
+ * AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
var->unusable = !var->present || (var->type == 0);
@@ -918,7 +1086,8 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
var->type |= 0x1;
break;
case VCPU_SREG_SS:
- /* On AMD CPUs sometimes the DB bit in the segment
+ /*
+ * On AMD CPUs sometimes the DB bit in the segment
* descriptor is left as 1, although the whole segment has
* been made unusable. Clear it here to pass an Intel VMX
* entry check when cross vendor migrating.
@@ -936,36 +1105,36 @@ static int svm_get_cpl(struct kvm_vcpu *vcpu)
return save->cpl;
}
-static void svm_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.idtr.limit;
- dt->base = svm->vmcb->save.idtr.base;
+ dt->size = svm->vmcb->save.idtr.limit;
+ dt->address = svm->vmcb->save.idtr.base;
}
-static void svm_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.idtr.limit = dt->limit;
- svm->vmcb->save.idtr.base = dt->base ;
+ svm->vmcb->save.idtr.limit = dt->size;
+ svm->vmcb->save.idtr.base = dt->address ;
}
-static void svm_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- dt->limit = svm->vmcb->save.gdtr.limit;
- dt->base = svm->vmcb->save.gdtr.base;
+ dt->size = svm->vmcb->save.gdtr.limit;
+ dt->address = svm->vmcb->save.gdtr.base;
}
-static void svm_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->save.gdtr.limit = dt->limit;
- svm->vmcb->save.gdtr.base = dt->base ;
+ svm->vmcb->save.gdtr.limit = dt->size;
+ svm->vmcb->save.gdtr.base = dt->address ;
}
static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
@@ -978,6 +1147,7 @@ static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
static void update_cr0_intercept(struct vcpu_svm *svm)
{
+ struct vmcb *vmcb = svm->vmcb;
ulong gcr0 = svm->vcpu.arch.cr0;
u64 *hcr0 = &svm->vmcb->save.cr0;
@@ -989,11 +1159,25 @@ static void update_cr0_intercept(struct vcpu_svm *svm)
if (gcr0 == *hcr0 && svm->vcpu.fpu_active) {
- svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
- svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK;
+ vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read;
+ vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write;
+ }
} else {
svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ if (is_nested(svm)) {
+ struct vmcb *hsave = svm->nested.hsave;
+
+ hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK;
+ hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK;
+ }
}
}
@@ -1001,6 +1185,27 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm)) {
+ /*
+ * We are here because we run in nested mode, the host kvm
+ * intercepts cr0 writes but the l1 hypervisor does not.
+ * But the L1 hypervisor may intercept selective cr0 writes.
+ * This needs to be checked here.
+ */
+ unsigned long old, new;
+
+ /* Remove bits that would trigger a real cr0 write intercept */
+ old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK;
+ new = cr0 & SVM_CR0_SELECTIVE_MASK;
+
+ if (old == new) {
+ /* cr0 write with ts and mp unchanged */
+ svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+ if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE)
+ return;
+ }
+ }
+
#ifdef CONFIG_X86_64
if (vcpu->arch.efer & EFER_LME) {
if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
@@ -1134,70 +1339,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
svm->vmcb->control.asid = sd->next_asid++;
}
-static int svm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *dest)
+static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value)
{
struct vcpu_svm *svm = to_svm(vcpu);
- switch (dr) {
- case 0 ... 3:
- *dest = vcpu->arch.db[dr];
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr6;
- else
- *dest = svm->vmcb->save.dr6;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
- *dest = vcpu->arch.dr7;
- else
- *dest = svm->vmcb->save.dr7;
- break;
- }
-
- return EMULATE_DONE;
-}
-
-static int svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- switch (dr) {
- case 0 ... 3:
- vcpu->arch.db[dr] = value;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- vcpu->arch.eff_db[dr] = value;
- break;
- case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 6:
- vcpu->arch.dr6 = (value & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return EMULATE_FAIL; /* will re-inject UD */
- /* fall through */
- case 7:
- vcpu->arch.dr7 = (value & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- svm->vmcb->save.dr7 = vcpu->arch.dr7;
- vcpu->arch.switch_db_regs = (value & DR7_BP_EN_MASK);
- }
- break;
- }
-
- return EMULATE_DONE;
+ svm->vmcb->save.dr7 = value;
}
static int pf_interception(struct vcpu_svm *svm)
@@ -1234,7 +1380,7 @@ static int db_interception(struct vcpu_svm *svm)
}
if (svm->vcpu.guest_debug &
- (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)){
+ (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) {
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc =
svm->vmcb->save.cs.base + svm->vmcb->save.rip;
@@ -1268,7 +1414,22 @@ static int ud_interception(struct vcpu_svm *svm)
static void svm_fpu_activate(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
+ u32 excp;
+
+ if (is_nested(svm)) {
+ u32 h_excp, n_excp;
+
+ h_excp = svm->nested.hsave->control.intercept_exceptions;
+ n_excp = svm->nested.intercept_exceptions;
+ h_excp &= ~(1 << NM_VECTOR);
+ excp = h_excp | n_excp;
+ } else {
+ excp = svm->vmcb->control.intercept_exceptions;
+ excp &= ~(1 << NM_VECTOR);
+ }
+
+ svm->vmcb->control.intercept_exceptions = excp;
+
svm->vcpu.fpu_active = 1;
update_cr0_intercept(svm);
}
@@ -1279,8 +1440,59 @@ static int nm_interception(struct vcpu_svm *svm)
return 1;
}
-static int mc_interception(struct vcpu_svm *svm)
+static bool is_erratum_383(void)
{
+ int err, i;
+ u64 value;
+
+ if (!erratum_383_found)
+ return false;
+
+ value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
+ if (err)
+ return false;
+
+ /* Bit 62 may or may not be set for this mce */
+ value &= ~(1ULL << 62);
+
+ if (value != 0xb600000000010015ULL)
+ return false;
+
+ /* Clear MCi_STATUS registers */
+ for (i = 0; i < 6; ++i)
+ native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
+
+ value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
+ if (!err) {
+ u32 low, high;
+
+ value &= ~(1ULL << 2);
+ low = lower_32_bits(value);
+ high = upper_32_bits(value);
+
+ native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+ }
+
+ /* Flush tlb to evict multi-match entries */
+ __flush_tlb_all();
+
+ return true;
+}
+
+static void svm_handle_mce(struct vcpu_svm *svm)
+{
+ if (is_erratum_383()) {
+ /*
+ * Erratum 383 triggered. Guest state is corrupt so kill the
+ * guest.
+ */
+ pr_err("KVM: Guest triggered AMD Erratum 383\n");
+
+ set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests);
+
+ return;
+ }
+
/*
* On an #MC intercept the MCE handler is not called automatically in
* the host. So do it by hand here.
@@ -1289,6 +1501,11 @@ static int mc_interception(struct vcpu_svm *svm)
"int $0x12\n");
/* not sure if we ever come back to this point */
+ return;
+}
+
+static int mc_interception(struct vcpu_svm *svm)
+{
return 1;
}
@@ -1309,29 +1526,23 @@ 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)
@@ -1384,6 +1595,8 @@ static int nested_svm_check_permissions(struct vcpu_svm *svm)
static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code)
{
+ int vmexit;
+
if (!is_nested(svm))
return 0;
@@ -1392,21 +1605,28 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
svm->vmcb->control.exit_info_1 = error_code;
svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
- return nested_svm_exit_handled(svm);
+ vmexit = nested_svm_intercept(svm);
+ if (vmexit == NESTED_EXIT_DONE)
+ svm->nested.exit_required = true;
+
+ return vmexit;
}
-static inline int nested_svm_intr(struct vcpu_svm *svm)
+/* This function returns true if it is save to enable the irq window */
+static inline bool nested_svm_intr(struct vcpu_svm *svm)
{
if (!is_nested(svm))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
- return 0;
+ return true;
if (!(svm->vcpu.arch.hflags & HF_HIF_MASK))
- return 0;
+ return false;
- svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_code = SVM_EXIT_INTR;
+ svm->vmcb->control.exit_info_1 = 0;
+ svm->vmcb->control.exit_info_2 = 0;
if (svm->nested.intercept & 1ULL) {
/*
@@ -1417,21 +1637,40 @@ static inline int nested_svm_intr(struct vcpu_svm *svm)
*/
svm->nested.exit_required = true;
trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
- return 1;
+ return false;
}
- return 0;
+ return true;
}
-static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
+/* This function returns true if it is save to enable the nmi window */
+static inline bool nested_svm_nmi(struct vcpu_svm *svm)
+{
+ if (!is_nested(svm))
+ return true;
+
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI)))
+ return true;
+
+ svm->vmcb->control.exit_code = SVM_EXIT_NMI;
+ svm->nested.exit_required = true;
+
+ return false;
+}
+
+static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
{
struct page *page;
+ might_sleep();
+
page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
if (is_error_page(page))
goto error;
- return kmap_atomic(page, idx);
+ *_page = page;
+
+ return kmap(page);
error:
kvm_release_page_clean(page);
@@ -1440,61 +1679,55 @@ error:
return NULL;
}
-static void nested_svm_unmap(void *addr, enum km_type idx)
+static void nested_svm_unmap(struct page *page)
{
- struct page *page;
+ kunmap(page);
+ kvm_release_page_dirty(page);
+}
- if (!addr)
- return;
+static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
+{
+ unsigned port;
+ u8 val, bit;
+ u64 gpa;
- page = kmap_atomic_to_page(addr);
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+ return NESTED_EXIT_HOST;
- kunmap_atomic(addr, idx);
- kvm_release_page_dirty(page);
+ port = svm->vmcb->control.exit_info_1 >> 16;
+ gpa = svm->nested.vmcb_iopm + (port / 8);
+ bit = port % 8;
+ val = 0;
+
+ if (kvm_read_guest(svm->vcpu.kvm, gpa, &val, 1))
+ val &= (1 << bit);
+
+ return val ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
-static bool nested_svm_exit_handled_msr(struct vcpu_svm *svm)
+static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
{
- u32 param = svm->vmcb->control.exit_info_1 & 1;
- u32 msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- bool ret = false;
- u32 t0, t1;
- u8 *msrpm;
+ u32 offset, msr, value;
+ int write, mask;
if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
- return false;
+ return NESTED_EXIT_HOST;
- msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
+ msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+ offset = svm_msrpm_offset(msr);
+ write = svm->vmcb->control.exit_info_1 & 1;
+ mask = 1 << ((2 * (msr & 0xf)) + write);
- if (!msrpm)
- goto out;
+ if (offset == MSR_INVALID)
+ return NESTED_EXIT_DONE;
- switch (msr) {
- case 0 ... 0x1fff:
- t0 = (msr * 2) % 8;
- t1 = msr / 8;
- break;
- case 0xc0000000 ... 0xc0001fff:
- t0 = (8192 + msr - 0xc0000000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- case 0xc0010000 ... 0xc0011fff:
- t0 = (16384 + msr - 0xc0010000) * 2;
- t1 = (t0 / 8);
- t0 %= 8;
- break;
- default:
- ret = true;
- goto out;
- }
-
- ret = msrpm[t1] & ((1 << param) << t0);
+ /* Offset is in 32 bit units but need in 8 bit units */
+ offset *= 4;
-out:
- nested_svm_unmap(msrpm, KM_USER0);
+ if (kvm_read_guest(svm->vcpu.kvm, svm->nested.vmcb_msrpm + offset, &value, 4))
+ return NESTED_EXIT_DONE;
- return ret;
+ return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
static int nested_svm_exit_special(struct vcpu_svm *svm)
@@ -1504,17 +1737,21 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
switch (exit_code) {
case SVM_EXIT_INTR:
case SVM_EXIT_NMI:
+ case SVM_EXIT_EXCP_BASE + MC_VECTOR:
return NESTED_EXIT_HOST;
- /* For now we are always handling NPFs when using them */
case SVM_EXIT_NPF:
+ /* For now we are always handling NPFs when using them */
if (npt_enabled)
return NESTED_EXIT_HOST;
break;
- /* When we're shadowing, trap PFs */
case SVM_EXIT_EXCP_BASE + PF_VECTOR:
+ /* When we're shadowing, trap PFs */
if (!npt_enabled)
return NESTED_EXIT_HOST;
break;
+ case SVM_EXIT_EXCP_BASE + NM_VECTOR:
+ nm_interception(svm);
+ break;
default:
break;
}
@@ -1525,7 +1762,7 @@ static int nested_svm_exit_special(struct vcpu_svm *svm)
/*
* If this function returns true, this #vmexit was already handled
*/
-static int nested_svm_exit_handled(struct vcpu_svm *svm)
+static int nested_svm_intercept(struct vcpu_svm *svm)
{
u32 exit_code = svm->vmcb->control.exit_code;
int vmexit = NESTED_EXIT_HOST;
@@ -1534,6 +1771,9 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
case SVM_EXIT_MSR:
vmexit = nested_svm_exit_handled_msr(svm);
break;
+ case SVM_EXIT_IOIO:
+ vmexit = nested_svm_intercept_ioio(svm);
+ break;
case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: {
u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0);
if (svm->nested.intercept_cr_read & cr_bits)
@@ -1564,6 +1804,10 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
vmexit = NESTED_EXIT_DONE;
break;
}
+ case SVM_EXIT_ERR: {
+ vmexit = NESTED_EXIT_DONE;
+ break;
+ }
default: {
u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
if (svm->nested.intercept & exit_bits)
@@ -1571,9 +1815,17 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
}
}
- if (vmexit == NESTED_EXIT_DONE) {
+ return vmexit;
+}
+
+static int nested_svm_exit_handled(struct vcpu_svm *svm)
+{
+ int vmexit;
+
+ vmexit = nested_svm_intercept(svm);
+
+ if (vmexit == NESTED_EXIT_DONE)
nested_svm_vmexit(svm);
- }
return vmexit;
}
@@ -1615,6 +1867,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
vmcb->control.exit_info_1,
@@ -1622,10 +1875,13 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
vmcb->control.exit_int_info,
vmcb->control.exit_int_info_err);
- nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page);
if (!nested_vmcb)
return 1;
+ /* Exit nested SVM mode */
+ svm->nested.vmcb = 0;
+
/* Give the current vmcb to the guest */
disable_gif(svm);
@@ -1635,9 +1891,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
nested_vmcb->save.ds = vmcb->save.ds;
nested_vmcb->save.gdtr = vmcb->save.gdtr;
nested_vmcb->save.idtr = vmcb->save.idtr;
- if (npt_enabled)
- nested_vmcb->save.cr3 = vmcb->save.cr3;
+ nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu);
+ nested_vmcb->save.cr3 = svm->vcpu.arch.cr3;
nested_vmcb->save.cr2 = vmcb->save.cr2;
+ nested_vmcb->save.cr4 = svm->vcpu.arch.cr4;
nested_vmcb->save.rflags = vmcb->save.rflags;
nested_vmcb->save.rip = vmcb->save.rip;
nested_vmcb->save.rsp = vmcb->save.rsp;
@@ -1709,10 +1966,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
svm->vmcb->save.cpl = 0;
svm->vmcb->control.exit_int_info = 0;
- /* Exit nested SVM mode */
- svm->nested.vmcb = 0;
-
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
kvm_mmu_reset_context(&svm->vcpu);
kvm_mmu_load(&svm->vcpu);
@@ -1722,19 +1976,33 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
- u32 *nested_msrpm;
+ /*
+ * This function merges the msr permission bitmaps of kvm and the
+ * nested vmcb. It is omptimized in that it only merges the parts where
+ * the kvm msr permission bitmap may contain zero bits
+ */
int i;
- nested_msrpm = nested_svm_map(svm, svm->nested.vmcb_msrpm, KM_USER0);
- if (!nested_msrpm)
- return false;
+ if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+ return true;
- for (i=0; i< PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER) / 4; i++)
- svm->nested.msrpm[i] = svm->msrpm[i] | nested_msrpm[i];
+ for (i = 0; i < MSRPM_OFFSETS; i++) {
+ u32 value, p;
+ u64 offset;
- svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+ if (msrpm_offsets[i] == 0xffffffff)
+ break;
+
+ p = msrpm_offsets[i];
+ offset = svm->nested.vmcb_msrpm + (p * 4);
- nested_svm_unmap(nested_msrpm, KM_USER0);
+ if (kvm_read_guest(svm->vcpu.kvm, offset, &value, 4))
+ return false;
+
+ svm->nested.msrpm[p] = svm->msrpm[p] | value;
+ }
+
+ svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
return true;
}
@@ -1744,26 +2012,34 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
struct vmcb *nested_vmcb;
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ struct page *page;
+ u64 vmcb_gpa;
+
+ vmcb_gpa = svm->vmcb->save.rax;
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return false;
- /* nested_vmcb is our indicator if nested SVM is activated */
- svm->nested.vmcb = svm->vmcb->save.rax;
-
- trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+ trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, vmcb_gpa,
nested_vmcb->save.rip,
nested_vmcb->control.int_ctl,
nested_vmcb->control.event_inj,
nested_vmcb->control.nested_ctl);
+ trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read,
+ nested_vmcb->control.intercept_cr_write,
+ nested_vmcb->control.intercept_exceptions,
+ nested_vmcb->control.intercept);
+
/* Clear internal status */
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
- /* Save the old vmcb, so we don't need to pick what we save, but
- can restore everything when a VMEXIT occurs */
+ /*
+ * Save the old vmcb, so we don't need to pick what we save, but can
+ * restore everything when a VMEXIT occurs
+ */
hsave->save.es = vmcb->save.es;
hsave->save.cs = vmcb->save.cs;
hsave->save.ss = vmcb->save.ss;
@@ -1803,14 +2079,17 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
if (npt_enabled) {
svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
- } else {
+ } else
kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
- kvm_mmu_reset_context(&svm->vcpu);
- }
+
+ /* Guest paging mode is active - reset mmu */
+ kvm_mmu_reset_context(&svm->vcpu);
+
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
kvm_register_write(&svm->vcpu, VCPU_REGS_RAX, nested_vmcb->save.rax);
kvm_register_write(&svm->vcpu, VCPU_REGS_RSP, nested_vmcb->save.rsp);
kvm_register_write(&svm->vcpu, VCPU_REGS_RIP, nested_vmcb->save.rip);
+
/* In case we don't even reach vcpu_run, the fields are not updated */
svm->vmcb->save.rax = nested_vmcb->save.rax;
svm->vmcb->save.rsp = nested_vmcb->save.rsp;
@@ -1819,22 +2098,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
svm->vmcb->save.cpl = nested_vmcb->save.cpl;
- /* We don't want a nested guest to be more powerful than the guest,
- so all intercepts are ORed */
- svm->vmcb->control.intercept_cr_read |=
- nested_vmcb->control.intercept_cr_read;
- svm->vmcb->control.intercept_cr_write |=
- nested_vmcb->control.intercept_cr_write;
- svm->vmcb->control.intercept_dr_read |=
- nested_vmcb->control.intercept_dr_read;
- svm->vmcb->control.intercept_dr_write |=
- nested_vmcb->control.intercept_dr_write;
- svm->vmcb->control.intercept_exceptions |=
- nested_vmcb->control.intercept_exceptions;
-
- svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
-
- svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa;
+ svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
+ svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL;
/* cache intercepts */
svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read;
@@ -1851,13 +2116,43 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
else
svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+ if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+ /* We only want the cr8 intercept bits of the guest */
+ svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK;
+ svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
+ }
+
+ /* We don't want to see VMMCALLs from a nested guest */
+ svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL);
+
+ /*
+ * We don't want a nested guest to be more powerful than the guest, so
+ * all intercepts are ORed
+ */
+ svm->vmcb->control.intercept_cr_read |=
+ nested_vmcb->control.intercept_cr_read;
+ svm->vmcb->control.intercept_cr_write |=
+ nested_vmcb->control.intercept_cr_write;
+ svm->vmcb->control.intercept_dr_read |=
+ nested_vmcb->control.intercept_dr_read;
+ svm->vmcb->control.intercept_dr_write |=
+ nested_vmcb->control.intercept_dr_write;
+ svm->vmcb->control.intercept_exceptions |=
+ nested_vmcb->control.intercept_exceptions;
+
+ svm->vmcb->control.intercept |= nested_vmcb->control.intercept;
+
+ svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
+
+ /* nested_vmcb is our indicator if nested SVM is activated */
+ svm->nested.vmcb = vmcb_gpa;
enable_gif(svm);
@@ -1883,6 +2178,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
static int vmload_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
@@ -1890,12 +2186,12 @@ static int vmload_interception(struct vcpu_svm *svm)
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
@@ -1903,6 +2199,7 @@ static int vmload_interception(struct vcpu_svm *svm)
static int vmsave_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
+ struct page *page;
if (nested_svm_check_permissions(svm))
return 1;
@@ -1910,12 +2207,12 @@ static int vmsave_interception(struct vcpu_svm *svm)
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
- nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, KM_USER0);
+ nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
if (!nested_vmcb)
return 1;
nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
- nested_svm_unmap(nested_vmcb, KM_USER0);
+ nested_svm_unmap(page);
return 1;
}
@@ -2018,6 +2315,8 @@ 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;
@@ -2038,6 +2337,12 @@ 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:
@@ -2054,7 +2359,14 @@ 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);
+ if (kvm_task_switch(&svm->vcpu, tss_selector, reason,
+ has_error_code, error_code) == EMULATE_FAIL) {
+ svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ svm->vcpu.run->internal.ndata = 0;
+ return 0;
+ }
+ return 1;
}
static int cpuid_interception(struct vcpu_svm *svm)
@@ -2145,9 +2457,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
case MSR_IA32_SYSENTER_ESP:
*data = svm->sysenter_esp;
break;
- /* Nobody will change the following 5 values in the VMCB so
- we can safely return them on rdmsr. They will always be 0
- until LBRV is implemented. */
+ /*
+ * Nobody will change the following 5 values in the VMCB so we can
+ * safely return them on rdmsr. They will always be 0 until LBRV is
+ * implemented.
+ */
case MSR_IA32_DEBUGCTLMSR:
*data = svm->vmcb->save.dbgctl;
break;
@@ -2167,7 +2481,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
*data = svm->nested.hsave_msr;
break;
case MSR_VM_CR:
- *data = 0;
+ *data = svm->nested.vm_cr_msr;
break;
case MSR_IA32_UCODE_REV:
*data = 0x01000065;
@@ -2197,6 +2511,31 @@ static int rdmsr_interception(struct vcpu_svm *svm)
return 1;
}
+static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int svm_dis, chg_mask;
+
+ if (data & ~SVM_VM_CR_VALID_MASK)
+ return 1;
+
+ chg_mask = SVM_VM_CR_VALID_MASK;
+
+ if (svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK)
+ chg_mask &= ~(SVM_VM_CR_SVM_LOCK_MASK | SVM_VM_CR_SVM_DIS_MASK);
+
+ svm->nested.vm_cr_msr &= ~chg_mask;
+ svm->nested.vm_cr_msr |= (data & chg_mask);
+
+ svm_dis = svm->nested.vm_cr_msr & SVM_VM_CR_SVM_DIS_MASK;
+
+ /* check for svm_disable while efer.svme is set */
+ if (svm_dis && (vcpu->arch.efer & EFER_SVME))
+ return 1;
+
+ return 0;
+}
+
static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -2263,6 +2602,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
svm->nested.hsave_msr = data;
break;
case MSR_VM_CR:
+ return svm_set_vm_cr(vcpu, data);
case MSR_VM_IGNNE:
pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
@@ -2326,16 +2666,16 @@ static int pause_interception(struct vcpu_svm *svm)
}
static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
- [SVM_EXIT_READ_CR0] = emulate_on_interception,
- [SVM_EXIT_READ_CR3] = emulate_on_interception,
- [SVM_EXIT_READ_CR4] = emulate_on_interception,
- [SVM_EXIT_READ_CR8] = emulate_on_interception,
+ [SVM_EXIT_READ_CR0] = emulate_on_interception,
+ [SVM_EXIT_READ_CR3] = emulate_on_interception,
+ [SVM_EXIT_READ_CR4] = emulate_on_interception,
+ [SVM_EXIT_READ_CR8] = emulate_on_interception,
[SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
- [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
- [SVM_EXIT_READ_DR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR0] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR3] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR4] = emulate_on_interception,
+ [SVM_EXIT_WRITE_CR8] = cr8_write_interception,
+ [SVM_EXIT_READ_DR0] = emulate_on_interception,
[SVM_EXIT_READ_DR1] = emulate_on_interception,
[SVM_EXIT_READ_DR2] = emulate_on_interception,
[SVM_EXIT_READ_DR3] = emulate_on_interception,
@@ -2354,15 +2694,14 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception,
[SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception,
[SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception,
- [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
- [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
- [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
- [SVM_EXIT_INTR] = intr_interception,
+ [SVM_EXIT_EXCP_BASE + PF_VECTOR] = pf_interception,
+ [SVM_EXIT_EXCP_BASE + NM_VECTOR] = nm_interception,
+ [SVM_EXIT_EXCP_BASE + MC_VECTOR] = mc_interception,
+ [SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
[SVM_EXIT_SMI] = nop_on_interception,
[SVM_EXIT_INIT] = nop_on_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
- /* [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, */
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = emulate_on_interception,
@@ -2370,7 +2709,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
- [SVM_EXIT_IOIO] = io_interception,
+ [SVM_EXIT_IOIO] = io_interception,
[SVM_EXIT_MSR] = msr_interception,
[SVM_EXIT_TASK_SWITCH] = task_switch_interception,
[SVM_EXIT_SHUTDOWN] = shutdown_interception,
@@ -2393,7 +2732,12 @@ static int handle_exit(struct kvm_vcpu *vcpu)
struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
- trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+ trace_kvm_exit(exit_code, vcpu);
+
+ if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
+ vcpu->arch.cr0 = svm->vmcb->save.cr0;
+ if (npt_enabled)
+ vcpu->arch.cr3 = svm->vmcb->save.cr3;
if (unlikely(svm->nested.exit_required)) {
nested_svm_vmexit(svm);
@@ -2422,11 +2766,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
svm_complete_interrupts(svm);
- if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK))
- vcpu->arch.cr0 = svm->vmcb->save.cr0;
- if (npt_enabled)
- vcpu->arch.cr3 = svm->vmcb->save.cr3;
-
if (svm->vmcb->control.exit_code == SVM_EXIT_ERR) {
kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
kvm_run->fail_entry.hardware_entry_failure_reason
@@ -2511,6 +2850,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (irr == -1)
return;
@@ -2522,8 +2864,12 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- return !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
- !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ int ret;
+ ret = !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
+ !(svm->vcpu.arch.hflags & HF_NMI_MASK);
+ ret = ret && gif_set(svm) && nested_svm_nmi(svm);
+
+ return ret;
}
static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
@@ -2568,13 +2914,13 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- nested_svm_intr(svm);
-
- /* In case GIF=0 we can't rely on the CPU to tell us when
- * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
- * The next time we get that intercept, this function will be
- * called again though and we'll get the vintr intercept. */
- if (gif_set(svm)) {
+ /*
+ * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
+ * 1, because that's a separate STGI/VMRUN intercept. The next time we
+ * get that intercept, this function will be called again though and
+ * we'll get the vintr intercept.
+ */
+ if (gif_set(svm) && nested_svm_intr(svm)) {
svm_set_vintr(svm);
svm_inject_irq(svm, 0x0);
}
@@ -2588,9 +2934,10 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
== HF_NMI_MASK)
return; /* IRET will cause a vm exit */
- /* Something prevents NMI from been injected. Single step over
- possible problem (IRET or exception injection or interrupt
- shadow) */
+ /*
+ * Something prevents NMI from been injected. Single step over possible
+ * problem (IRET or exception injection or interrupt shadow)
+ */
svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
update_db_intercept(vcpu);
@@ -2614,6 +2961,9 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) {
int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
kvm_set_cr8(vcpu, cr8);
@@ -2625,6 +2975,9 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
u64 cr8;
+ if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK))
+ return;
+
cr8 = kvm_get_cr8(vcpu);
svm->vmcb->control.int_ctl &= ~V_TPR_MASK;
svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK;
@@ -2635,6 +2988,9 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
u8 vector;
int type;
u32 exitintinfo = svm->vmcb->control.exit_int_info;
+ unsigned int3_injected = svm->int3_injected;
+
+ svm->int3_injected = 0;
if (svm->vcpu.arch.hflags & HF_IRET_MASK)
svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK);
@@ -2654,18 +3010,25 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
svm->vcpu.arch.nmi_injected = true;
break;
case SVM_EXITINTINFO_TYPE_EXEPT:
- /* In case of software exception do not reinject an exception
- vector, but re-execute and instruction instead */
- if (is_nested(svm))
- break;
- if (kvm_exception_is_soft(vector))
+ /*
+ * In case of software exceptions, do not reinject the vector,
+ * but re-execute the instruction instead. Rewind RIP first
+ * if we emulated INT3 before.
+ */
+ if (kvm_exception_is_soft(vector)) {
+ if (vector == BP_VECTOR && int3_injected &&
+ kvm_is_linear_rip(&svm->vcpu, svm->int3_rip))
+ kvm_rip_write(&svm->vcpu,
+ kvm_rip_read(&svm->vcpu) -
+ int3_injected);
break;
+ }
if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {
u32 err = svm->vmcb->control.exit_int_info_err;
- kvm_queue_exception_e(&svm->vcpu, vector, err);
+ kvm_requeue_exception_e(&svm->vcpu, vector, err);
} else
- kvm_queue_exception(&svm->vcpu, vector);
+ kvm_requeue_exception(&svm->vcpu, vector);
break;
case SVM_EXITINTINFO_TYPE_INTR:
kvm_queue_interrupt(&svm->vcpu, vector, false);
@@ -2688,6 +3051,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
u16 gs_selector;
u16 ldt_selector;
+ svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+
/*
* A vmexit emulation is required before the vcpu can be executed
* again.
@@ -2695,10 +3062,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(svm->nested.exit_required))
return;
- svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
- svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
- svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
-
pre_svm_run(svm);
sync_lapic_to_cr8(vcpu);
@@ -2811,6 +3174,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
}
+
+ /*
+ * We need to handle MC intercepts here before the vcpu has a chance to
+ * change the physical cpu
+ */
+ if (unlikely(svm->vmcb->control.exit_code ==
+ SVM_EXIT_EXCP_BASE + MC_VECTOR))
+ svm_handle_mce(svm);
}
#undef R
@@ -2879,25 +3250,39 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
}
+static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+ switch (func) {
+ case 0x8000000A:
+ entry->eax = 1; /* SVM revision 1 */
+ entry->ebx = 8; /* Lets support 8 ASIDs in case we add proper
+ ASID emulation to nested SVM */
+ entry->ecx = 0; /* Reserved */
+ entry->edx = 0; /* Do not support any additional features */
+
+ break;
+ }
+}
+
static const struct trace_print_flags svm_exit_reasons_str[] = {
- { SVM_EXIT_READ_CR0, "read_cr0" },
- { SVM_EXIT_READ_CR3, "read_cr3" },
- { SVM_EXIT_READ_CR4, "read_cr4" },
- { SVM_EXIT_READ_CR8, "read_cr8" },
- { SVM_EXIT_WRITE_CR0, "write_cr0" },
- { SVM_EXIT_WRITE_CR3, "write_cr3" },
- { SVM_EXIT_WRITE_CR4, "write_cr4" },
- { SVM_EXIT_WRITE_CR8, "write_cr8" },
- { SVM_EXIT_READ_DR0, "read_dr0" },
- { SVM_EXIT_READ_DR1, "read_dr1" },
- { SVM_EXIT_READ_DR2, "read_dr2" },
- { SVM_EXIT_READ_DR3, "read_dr3" },
- { SVM_EXIT_WRITE_DR0, "write_dr0" },
- { SVM_EXIT_WRITE_DR1, "write_dr1" },
- { SVM_EXIT_WRITE_DR2, "write_dr2" },
- { SVM_EXIT_WRITE_DR3, "write_dr3" },
- { SVM_EXIT_WRITE_DR5, "write_dr5" },
- { SVM_EXIT_WRITE_DR7, "write_dr7" },
+ { SVM_EXIT_READ_CR0, "read_cr0" },
+ { SVM_EXIT_READ_CR3, "read_cr3" },
+ { SVM_EXIT_READ_CR4, "read_cr4" },
+ { SVM_EXIT_READ_CR8, "read_cr8" },
+ { SVM_EXIT_WRITE_CR0, "write_cr0" },
+ { SVM_EXIT_WRITE_CR3, "write_cr3" },
+ { SVM_EXIT_WRITE_CR4, "write_cr4" },
+ { SVM_EXIT_WRITE_CR8, "write_cr8" },
+ { SVM_EXIT_READ_DR0, "read_dr0" },
+ { SVM_EXIT_READ_DR1, "read_dr1" },
+ { SVM_EXIT_READ_DR2, "read_dr2" },
+ { SVM_EXIT_READ_DR3, "read_dr3" },
+ { SVM_EXIT_WRITE_DR0, "write_dr0" },
+ { SVM_EXIT_WRITE_DR1, "write_dr1" },
+ { SVM_EXIT_WRITE_DR2, "write_dr2" },
+ { SVM_EXIT_WRITE_DR3, "write_dr3" },
+ { SVM_EXIT_WRITE_DR5, "write_dr5" },
+ { SVM_EXIT_WRITE_DR7, "write_dr7" },
{ SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" },
{ SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" },
{ SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" },
@@ -2946,8 +3331,10 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- update_cr0_intercept(svm);
svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR;
+ if (is_nested(svm))
+ svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR;
+ update_cr0_intercept(svm);
}
static struct kvm_x86_ops svm_x86_ops = {
@@ -2986,8 +3373,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
- .get_dr = svm_get_dr,
- .set_dr = svm_set_dr,
+ .set_dr7 = svm_set_dr7,
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
@@ -3023,12 +3409,14 @@ static struct kvm_x86_ops svm_x86_ops = {
.cpuid_update = svm_cpuid_update,
.rdtscp_supported = svm_rdtscp_supported,
+
+ .set_supported_cpuid = svm_set_supported_cpuid,
};
static int __init svm_init(void)
{
return kvm_init(&svm_x86_ops, sizeof(struct vcpu_svm),
- THIS_MODULE);
+ __alignof__(struct vcpu_svm), THIS_MODULE);
}
static void __exit svm_exit(void)
diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c
index eea40439066c..4ddadb1a5ffe 100644
--- a/arch/x86/kvm/timer.c
+++ b/arch/x86/kvm/timer.c
@@ -12,7 +12,8 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
/*
* There is a race window between reading and incrementing, but we do
* not care about potentially loosing timer events in the !reinject
- * case anyway.
+ * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+ * in vcpu_enter_guest.
*/
if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
atomic_inc(&ktimer->pending);
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 6ad30a29f044..a6544b8e7c0f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -5,8 +5,6 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_PATH arch/x86/kvm
-#define TRACE_INCLUDE_FILE trace
/*
* Tracepoint for guest mode entry.
@@ -184,8 +182,8 @@ TRACE_EVENT(kvm_apic,
* Tracepoint for kvm guest exit:
*/
TRACE_EVENT(kvm_exit,
- TP_PROTO(unsigned int exit_reason, unsigned long guest_rip),
- TP_ARGS(exit_reason, guest_rip),
+ TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu),
+ TP_ARGS(exit_reason, vcpu),
TP_STRUCT__entry(
__field( unsigned int, exit_reason )
@@ -194,7 +192,7 @@ TRACE_EVENT(kvm_exit,
TP_fast_assign(
__entry->exit_reason = exit_reason;
- __entry->guest_rip = guest_rip;
+ __entry->guest_rip = kvm_rip_read(vcpu);
),
TP_printk("reason %s rip 0x%lx",
@@ -221,6 +219,38 @@ TRACE_EVENT(kvm_inj_virq,
TP_printk("irq %u", __entry->irq)
);
+#define EXS(x) { x##_VECTOR, "#" #x }
+
+#define kvm_trace_sym_exc \
+ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \
+ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \
+ EXS(MF), EXS(MC)
+
+/*
+ * Tracepoint for kvm interrupt injection:
+ */
+TRACE_EVENT(kvm_inj_exception,
+ TP_PROTO(unsigned exception, bool has_error, unsigned error_code),
+ TP_ARGS(exception, has_error, error_code),
+
+ TP_STRUCT__entry(
+ __field( u8, exception )
+ __field( u8, has_error )
+ __field( u32, error_code )
+ ),
+
+ TP_fast_assign(
+ __entry->exception = exception;
+ __entry->has_error = has_error;
+ __entry->error_code = error_code;
+ ),
+
+ TP_printk("%s (0x%x)",
+ __print_symbolic(__entry->exception, kvm_trace_sym_exc),
+ /* FIXME: don't print error_code if not present */
+ __entry->has_error ? __entry->error_code : 0)
+);
+
/*
* Tracepoint for page fault.
*/
@@ -413,12 +443,34 @@ TRACE_EVENT(kvm_nested_vmrun,
),
TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x "
- "event_inj: 0x%08x npt: %s\n",
+ "event_inj: 0x%08x npt: %s",
__entry->rip, __entry->vmcb, __entry->nested_rip,
__entry->int_ctl, __entry->event_inj,
__entry->npt ? "on" : "off")
);
+TRACE_EVENT(kvm_nested_intercepts,
+ TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept),
+ TP_ARGS(cr_read, cr_write, exceptions, intercept),
+
+ TP_STRUCT__entry(
+ __field( __u16, cr_read )
+ __field( __u16, cr_write )
+ __field( __u32, exceptions )
+ __field( __u64, intercept )
+ ),
+
+ TP_fast_assign(
+ __entry->cr_read = cr_read;
+ __entry->cr_write = cr_write;
+ __entry->exceptions = exceptions;
+ __entry->intercept = intercept;
+ ),
+
+ TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx",
+ __entry->cr_read, __entry->cr_write, __entry->exceptions,
+ __entry->intercept)
+);
/*
* Tracepoint for #VMEXIT while nested
*/
@@ -447,7 +499,7 @@ TRACE_EVENT(kvm_nested_vmexit,
__entry->exit_int_info_err = exit_int_info_err;
),
TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx "
- "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+ "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x",
__entry->rip,
ftrace_print_symbols_seq(p, __entry->exit_code,
kvm_x86_ops->exit_reasons_str),
@@ -482,7 +534,7 @@ TRACE_EVENT(kvm_nested_vmexit_inject,
),
TP_printk("reason: %s ext_inf1: 0x%016llx "
- "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+ "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x",
ftrace_print_symbols_seq(p, __entry->exit_code,
kvm_x86_ops->exit_reasons_str),
__entry->exit_info1, __entry->exit_info2,
@@ -504,7 +556,7 @@ TRACE_EVENT(kvm_nested_intr_vmexit,
__entry->rip = rip
),
- TP_printk("rip: 0x%016llx\n", __entry->rip)
+ TP_printk("rip: 0x%016llx", __entry->rip)
);
/*
@@ -526,7 +578,7 @@ TRACE_EVENT(kvm_invlpga,
__entry->address = address;
),
- TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n",
+ TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx",
__entry->rip, __entry->asid, __entry->address)
);
@@ -547,11 +599,102 @@ TRACE_EVENT(kvm_skinit,
__entry->slb = slb;
),
- TP_printk("rip: 0x%016llx slb: 0x%08x\n",
+ TP_printk("rip: 0x%016llx slb: 0x%08x",
__entry->rip, __entry->slb)
);
+#define __print_insn(insn, ilen) ({ \
+ int i; \
+ const char *ret = p->buffer + p->len; \
+ \
+ for (i = 0; i < ilen; ++i) \
+ trace_seq_printf(p, " %02x", insn[i]); \
+ trace_seq_printf(p, "%c", 0); \
+ ret; \
+ })
+
+#define KVM_EMUL_INSN_F_CR0_PE (1 << 0)
+#define KVM_EMUL_INSN_F_EFL_VM (1 << 1)
+#define KVM_EMUL_INSN_F_CS_D (1 << 2)
+#define KVM_EMUL_INSN_F_CS_L (1 << 3)
+
+#define kvm_trace_symbol_emul_flags \
+ { 0, "real" }, \
+ { KVM_EMUL_INSN_F_CR0_PE \
+ | KVM_EMUL_INSN_F_EFL_VM, "vm16" }, \
+ { KVM_EMUL_INSN_F_CR0_PE, "prot16" }, \
+ { KVM_EMUL_INSN_F_CR0_PE \
+ | KVM_EMUL_INSN_F_CS_D, "prot32" }, \
+ { KVM_EMUL_INSN_F_CR0_PE \
+ | KVM_EMUL_INSN_F_CS_L, "prot64" }
+
+#define kei_decode_mode(mode) ({ \
+ u8 flags = 0xff; \
+ switch (mode) { \
+ case X86EMUL_MODE_REAL: \
+ flags = 0; \
+ break; \
+ case X86EMUL_MODE_VM86: \
+ flags = KVM_EMUL_INSN_F_EFL_VM; \
+ break; \
+ case X86EMUL_MODE_PROT16: \
+ flags = KVM_EMUL_INSN_F_CR0_PE; \
+ break; \
+ case X86EMUL_MODE_PROT32: \
+ flags = KVM_EMUL_INSN_F_CR0_PE \
+ | KVM_EMUL_INSN_F_CS_D; \
+ break; \
+ case X86EMUL_MODE_PROT64: \
+ flags = KVM_EMUL_INSN_F_CR0_PE \
+ | KVM_EMUL_INSN_F_CS_L; \
+ break; \
+ } \
+ flags; \
+ })
+
+TRACE_EVENT(kvm_emulate_insn,
+ TP_PROTO(struct kvm_vcpu *vcpu, __u8 failed),
+ TP_ARGS(vcpu, failed),
+
+ TP_STRUCT__entry(
+ __field( __u64, rip )
+ __field( __u32, csbase )
+ __field( __u8, len )
+ __array( __u8, insn, 15 )
+ __field( __u8, flags )
+ __field( __u8, failed )
+ ),
+
+ TP_fast_assign(
+ __entry->rip = vcpu->arch.emulate_ctxt.decode.fetch.start;
+ __entry->csbase = kvm_x86_ops->get_segment_base(vcpu, VCPU_SREG_CS);
+ __entry->len = vcpu->arch.emulate_ctxt.decode.eip
+ - vcpu->arch.emulate_ctxt.decode.fetch.start;
+ memcpy(__entry->insn,
+ vcpu->arch.emulate_ctxt.decode.fetch.data,
+ 15);
+ __entry->flags = kei_decode_mode(vcpu->arch.emulate_ctxt.mode);
+ __entry->failed = failed;
+ ),
+
+ TP_printk("%x:%llx:%s (%s)%s",
+ __entry->csbase, __entry->rip,
+ __print_insn(__entry->insn, __entry->len),
+ __print_symbolic(__entry->flags,
+ kvm_trace_symbol_emul_flags),
+ __entry->failed ? " failed" : ""
+ )
+ );
+
+#define trace_kvm_emulate_insn_start(vcpu) trace_kvm_emulate_insn(vcpu, 0)
+#define trace_kvm_emulate_insn_failed(vcpu) trace_kvm_emulate_insn(vcpu, 1)
+
#endif /* _TRACE_KVM_H */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH arch/x86/kvm
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
/* This part must be outside protection */
#include <trace/define_trace.h>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index edca080407a5..859a01a07dbf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -27,6 +27,7 @@
#include <linux/moduleparam.h>
#include <linux/ftrace_event.h>
#include <linux/slab.h>
+#include <linux/tboot.h>
#include "kvm_cache_regs.h"
#include "x86.h"
@@ -98,6 +99,8 @@ module_param(ple_gap, int, S_IRUGO);
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
+#define NR_AUTOLOAD_MSRS 1
+
struct vmcs {
u32 revision_id;
u32 abort;
@@ -125,6 +128,11 @@ struct vcpu_vmx {
u64 msr_guest_kernel_gs_base;
#endif
struct vmcs *vmcs;
+ struct msr_autoload {
+ unsigned nr;
+ struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
+ struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+ } msr_autoload;
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
@@ -234,56 +242,56 @@ static const u32 vmx_msr_index[] = {
};
#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
-static inline int is_page_fault(u32 intr_info)
+static inline bool is_page_fault(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_no_device(u32 intr_info)
+static inline bool is_no_device(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_invalid_opcode(u32 intr_info)
+static inline bool is_invalid_opcode(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int is_external_interrupt(u32 intr_info)
+static inline bool is_external_interrupt(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
== (INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
-static inline int is_machine_check(u32 intr_info)
+static inline bool is_machine_check(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
INTR_INFO_VALID_MASK)) ==
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
-static inline int cpu_has_vmx_msr_bitmap(void)
+static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
}
-static inline int cpu_has_vmx_tpr_shadow(void)
+static inline bool cpu_has_vmx_tpr_shadow(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW;
}
-static inline int vm_need_tpr_shadow(struct kvm *kvm)
+static inline bool vm_need_tpr_shadow(struct kvm *kvm)
{
return (cpu_has_vmx_tpr_shadow()) && (irqchip_in_kernel(kvm));
}
-static inline int cpu_has_secondary_exec_ctrls(void)
+static inline bool cpu_has_secondary_exec_ctrls(void)
{
return vmcs_config.cpu_based_exec_ctrl &
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
@@ -303,80 +311,80 @@ static inline bool cpu_has_vmx_flexpriority(void)
static inline bool cpu_has_vmx_ept_execute_only(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+ return vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT;
}
static inline bool cpu_has_vmx_eptp_uncacheable(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+ return vmx_capability.ept & VMX_EPTP_UC_BIT;
}
static inline bool cpu_has_vmx_eptp_writeback(void)
{
- return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+ return vmx_capability.ept & VMX_EPTP_WB_BIT;
}
static inline bool cpu_has_vmx_ept_2m_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT;
}
static inline bool cpu_has_vmx_ept_1g_page(void)
{
- return !!(vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT);
+ return vmx_capability.ept & VMX_EPT_1GB_PAGE_BIT;
}
-static inline int cpu_has_vmx_invept_individual_addr(void)
+static inline bool cpu_has_vmx_invept_individual_addr(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT;
}
-static inline int cpu_has_vmx_invept_context(void)
+static inline bool cpu_has_vmx_invept_context(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_CONTEXT_BIT;
}
-static inline int cpu_has_vmx_invept_global(void)
+static inline bool cpu_has_vmx_invept_global(void)
{
- return !!(vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT);
+ return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT;
}
-static inline int cpu_has_vmx_ept(void)
+static inline bool cpu_has_vmx_ept(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_EPT;
}
-static inline int cpu_has_vmx_unrestricted_guest(void)
+static inline bool cpu_has_vmx_unrestricted_guest(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_UNRESTRICTED_GUEST;
}
-static inline int cpu_has_vmx_ple(void)
+static inline bool cpu_has_vmx_ple(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_PAUSE_LOOP_EXITING;
}
-static inline int vm_need_virtualize_apic_accesses(struct kvm *kvm)
+static inline bool vm_need_virtualize_apic_accesses(struct kvm *kvm)
{
return flexpriority_enabled && irqchip_in_kernel(kvm);
}
-static inline int cpu_has_vmx_vpid(void)
+static inline bool cpu_has_vmx_vpid(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_ENABLE_VPID;
}
-static inline int cpu_has_vmx_rdtscp(void)
+static inline bool cpu_has_vmx_rdtscp(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
SECONDARY_EXEC_RDTSCP;
}
-static inline int cpu_has_virtual_nmis(void)
+static inline bool cpu_has_virtual_nmis(void)
{
return vmcs_config.pin_based_exec_ctrl & PIN_BASED_VIRTUAL_NMIS;
}
@@ -595,16 +603,56 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
vmcs_write32(EXCEPTION_BITMAP, eb);
}
+static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
+{
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr)
+ return;
+ --m->nr;
+ m->guest[i] = m->guest[m->nr];
+ m->host[i] = m->host[m->nr];
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+}
+
+static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
+ u64 guest_val, u64 host_val)
+{
+ unsigned i;
+ struct msr_autoload *m = &vmx->msr_autoload;
+
+ for (i = 0; i < m->nr; ++i)
+ if (m->guest[i].index == msr)
+ break;
+
+ if (i == m->nr) {
+ ++m->nr;
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+ }
+
+ m->guest[i].index = msr;
+ m->guest[i].value = guest_val;
+ m->host[i].index = msr;
+ m->host[i].value = host_val;
+}
+
static void reload_tss(void)
{
/*
* VT restores TR but not its size. Useless.
*/
- struct descriptor_table gdt;
+ struct desc_ptr gdt;
struct desc_struct *descs;
- kvm_get_gdt(&gdt);
- descs = (void *)gdt.base;
+ native_store_gdt(&gdt);
+ descs = (void *)gdt.address;
descs[GDT_ENTRY_TSS].type = 9; /* available TSS */
load_TR_desc();
}
@@ -631,9 +679,57 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
guest_efer |= host_efer & ignore_bits;
vmx->guest_msrs[efer_offset].data = guest_efer;
vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+ clear_atomic_switch_msr(vmx, MSR_EFER);
+ /* On ept, can't emulate nx, and must switch nx atomically */
+ if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
+ guest_efer = vmx->vcpu.arch.efer;
+ if (!(guest_efer & EFER_LMA))
+ guest_efer &= ~EFER_LME;
+ add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
+ return false;
+ }
+
return true;
}
+static unsigned long segment_base(u16 selector)
+{
+ struct desc_ptr gdt;
+ struct desc_struct *d;
+ unsigned long table_base;
+ unsigned long v;
+
+ if (!(selector & ~3))
+ return 0;
+
+ native_store_gdt(&gdt);
+ table_base = gdt.address;
+
+ if (selector & 4) { /* from ldt */
+ u16 ldt_selector = kvm_read_ldt();
+
+ if (!(ldt_selector & ~3))
+ return 0;
+
+ table_base = segment_base(ldt_selector);
+ }
+ d = (struct desc_struct *)(table_base + (selector & ~7));
+ v = get_desc_base(d);
+#ifdef CONFIG_X86_64
+ if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
+#endif
+ return v;
+}
+
+static inline unsigned long kvm_read_tr_base(void)
+{
+ u16 tr;
+ asm("str %0" : "=g"(tr));
+ return segment_base(tr);
+}
+
static void vmx_save_host_state(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -758,7 +854,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
if (vcpu->cpu != cpu) {
- struct descriptor_table dt;
+ struct desc_ptr dt;
unsigned long sysenter_esp;
vcpu->cpu = cpu;
@@ -767,8 +863,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
* processors.
*/
vmcs_writel(HOST_TR_BASE, kvm_read_tr_base()); /* 22.2.4 */
- kvm_get_gdt(&dt);
- vmcs_writel(HOST_GDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_gdt(&dt);
+ vmcs_writel(HOST_GDTR_BASE, dt.address); /* 22.2.4 */
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
@@ -846,9 +942,9 @@ 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 +956,9 @@ 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))
@@ -882,7 +978,8 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
}
static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
- bool has_error_code, u32 error_code)
+ bool has_error_code, u32 error_code,
+ bool reinject)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 intr_info = nr | INTR_INFO_VALID_MASK;
@@ -1176,9 +1273,16 @@ static __init int vmx_disabled_by_bios(void)
u64 msr;
rdmsrl(MSR_IA32_FEATURE_CONTROL, msr);
- return (msr & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- == FEATURE_CONTROL_LOCKED;
+ if (msr & FEATURE_CONTROL_LOCKED) {
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX)
+ && tboot_enabled())
+ return 1;
+ if (!(msr & FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX)
+ && !tboot_enabled())
+ return 1;
+ }
+
+ return 0;
/* locked but not enabled */
}
@@ -1186,21 +1290,23 @@ static int hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
- u64 old;
+ u64 old, test_bits;
if (read_cr4() & X86_CR4_VMXE)
return -EBUSY;
INIT_LIST_HEAD(&per_cpu(vcpus_on_cpu, cpu));
rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
- if ((old & (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
- != (FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED))
+
+ test_bits = FEATURE_CONTROL_LOCKED;
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ if (tboot_enabled())
+ test_bits |= FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX;
+
+ if ((old & test_bits) != test_bits) {
/* enable and lock */
- wrmsrl(MSR_IA32_FEATURE_CONTROL, old |
- FEATURE_CONTROL_LOCKED |
- FEATURE_CONTROL_VMXON_ENABLED);
+ wrmsrl(MSR_IA32_FEATURE_CONTROL, old | test_bits);
+ }
write_cr4(read_cr4() | X86_CR4_VMXE); /* FIXME: not cpu hotplug safe */
asm volatile (ASM_VMX_VMXON_RAX
: : "a"(&phys_addr), "m"(phys_addr)
@@ -1521,7 +1627,7 @@ static gva_t rmode_tss_base(struct kvm *kvm)
struct kvm_memslots *slots;
gfn_t base_gfn;
- slots = rcu_dereference(kvm->memslots);
+ slots = kvm_memslots(kvm);
base_gfn = kvm->memslots->memslots[0].base_gfn +
kvm->memslots->memslots[0].npages - 3;
return base_gfn << PAGE_SHIFT;
@@ -1649,6 +1755,7 @@ static void exit_lmode(struct kvm_vcpu *vcpu)
vmcs_write32(VM_ENTRY_CONTROLS,
vmcs_read32(VM_ENTRY_CONTROLS)
& ~VM_ENTRY_IA32E_MODE);
+ vmx_set_efer(vcpu, vcpu->arch.efer);
}
#endif
@@ -1934,28 +2041,28 @@ static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
*l = (ar >> 13) & 1;
}
-static void vmx_get_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_IDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_IDTR_BASE);
+ dt->size = vmcs_read32(GUEST_IDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_IDTR_BASE);
}
-static void vmx_set_idt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_IDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_IDTR_BASE, dt->base);
+ vmcs_write32(GUEST_IDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_IDTR_BASE, dt->address);
}
-static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- dt->limit = vmcs_read32(GUEST_GDTR_LIMIT);
- dt->base = vmcs_readl(GUEST_GDTR_BASE);
+ dt->size = vmcs_read32(GUEST_GDTR_LIMIT);
+ dt->address = vmcs_readl(GUEST_GDTR_BASE);
}
-static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct descriptor_table *dt)
+static void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
{
- vmcs_write32(GUEST_GDTR_LIMIT, dt->limit);
- vmcs_writel(GUEST_GDTR_BASE, dt->base);
+ vmcs_write32(GUEST_GDTR_LIMIT, dt->size);
+ vmcs_writel(GUEST_GDTR_BASE, dt->address);
}
static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
@@ -2296,6 +2403,16 @@ static void allocate_vpid(struct vcpu_vmx *vmx)
spin_unlock(&vmx_vpid_lock);
}
+static void free_vpid(struct vcpu_vmx *vmx)
+{
+ if (!enable_vpid)
+ return;
+ spin_lock(&vmx_vpid_lock);
+ if (vmx->vpid != 0)
+ __clear_bit(vmx->vpid, vmx_vpid_bitmap);
+ spin_unlock(&vmx_vpid_lock);
+}
+
static void __vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr)
{
int f = sizeof(unsigned long);
@@ -2334,7 +2451,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
u32 junk;
u64 host_pat, tsc_this, tsc_base;
unsigned long a;
- struct descriptor_table dt;
+ struct desc_ptr dt;
int i;
unsigned long kvm_vmx_return;
u32 exec_control;
@@ -2415,14 +2532,16 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
- kvm_get_idt(&dt);
- vmcs_writel(HOST_IDTR_BASE, dt.base); /* 22.2.4 */
+ native_store_idt(&dt);
+ vmcs_writel(HOST_IDTR_BASE, dt.address); /* 22.2.4 */
asm("mov $.Lkvm_vmx_return, %0" : "=r"(kvm_vmx_return));
vmcs_writel(HOST_RIP, kvm_vmx_return); /* 22.2.5 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
rdmsr(MSR_IA32_SYSENTER_CS, host_sysenter_cs, junk);
vmcs_write32(HOST_IA32_SYSENTER_CS, host_sysenter_cs);
@@ -2947,22 +3066,20 @@ 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
@@ -3053,19 +3170,9 @@ static int handle_cr(struct kvm_vcpu *vcpu)
return 0;
}
-static int check_dr_alias(struct kvm_vcpu *vcpu)
-{
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return -1;
- }
- return 0;
-}
-
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
- unsigned long val;
int dr, reg;
/* Do not handle if the CPL > 0, will trigger GP on re-entry */
@@ -3100,67 +3207,20 @@ static int handle_dr(struct kvm_vcpu *vcpu)
dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
reg = DEBUG_REG_ACCESS_REG(exit_qualification);
if (exit_qualification & TYPE_MOV_FROM_DR) {
- switch (dr) {
- case 0 ... 3:
- val = vcpu->arch.db[dr];
- break;
- case 4:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- val = vcpu->arch.dr6;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- val = vcpu->arch.dr7;
- break;
- }
- kvm_register_write(vcpu, reg, val);
- } else {
- val = vcpu->arch.regs[reg];
- switch (dr) {
- case 0 ... 3:
- vcpu->arch.db[dr] = val;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
- vcpu->arch.eff_db[dr] = val;
- break;
- case 4:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- case 6:
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
- break;
- case 5:
- if (check_dr_alias(vcpu) < 0)
- return 1;
- /* fall through */
- default: /* 7 */
- if (val & 0xffffffff00000000ULL) {
- kvm_inject_gp(vcpu, 0);
- return 1;
- }
- vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
- if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
- vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
- vcpu->arch.switch_db_regs =
- (val & DR7_BP_EN_MASK);
- }
- break;
- }
- }
+ unsigned long val;
+ if (!kvm_get_dr(vcpu, dr, &val))
+ kvm_register_write(vcpu, reg, val);
+ } else
+ kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg]);
skip_emulated_instruction(vcpu);
return 1;
}
+static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ vmcs_writel(GUEST_DR7, val);
+}
+
static int handle_cpuid(struct kvm_vcpu *vcpu)
{
kvm_emulate_cpuid(vcpu);
@@ -3292,6 +3352,8 @@ 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;
@@ -3314,6 +3376,13 @@ 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;
@@ -3328,8 +3397,13 @@ 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) == EMULATE_FAIL) {
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
return 0;
+ }
/* clear all local breakpoint enable flags */
vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
@@ -3574,7 +3648,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
u32 exit_reason = vmx->exit_reason;
u32 vectoring_info = vmx->idt_vectoring_info;
- trace_kvm_exit(exit_reason, kvm_rip_read(vcpu));
+ trace_kvm_exit(exit_reason, vcpu);
/* If guest state is invalid, start emulating */
if (vmx->emulation_required && emulate_invalid_guest_state)
@@ -3923,10 +3997,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- spin_lock(&vmx_vpid_lock);
- if (vmx->vpid != 0)
- __clear_bit(vmx->vpid, vmx_vpid_bitmap);
- spin_unlock(&vmx_vpid_lock);
+ free_vpid(vmx);
vmx_free_vmcs(vcpu);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
@@ -3988,6 +4059,7 @@ free_msrs:
uninit_vcpu:
kvm_vcpu_uninit(&vmx->vcpu);
free_vcpu:
+ free_vpid(vmx);
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
}
@@ -4118,6 +4190,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
}
}
+static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
+{
+}
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
@@ -4154,6 +4230,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.set_idt = vmx_set_idt,
.get_gdt = vmx_get_gdt,
.set_gdt = vmx_set_gdt,
+ .set_dr7 = vmx_set_dr7,
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
@@ -4189,6 +4266,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
.cpuid_update = vmx_cpuid_update,
.rdtscp_supported = vmx_rdtscp_supported,
+
+ .set_supported_cpuid = vmx_set_supported_cpuid,
};
static int __init vmx_init(void)
@@ -4236,7 +4315,8 @@ static int __init vmx_init(void)
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx), THIS_MODULE);
+ r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
if (r)
goto out3;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index dd9bc8fb81ab..05d571f6f196 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -42,7 +42,7 @@
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <trace/events/kvm.h>
-#undef TRACE_INCLUDE_FILE
+
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -224,34 +224,6 @@ static void drop_user_return_notifiers(void *ignore)
kvm_on_user_return(&smsr->urn);
}
-unsigned long segment_base(u16 selector)
-{
- struct descriptor_table gdt;
- struct desc_struct *d;
- unsigned long table_base;
- unsigned long v;
-
- if (selector == 0)
- return 0;
-
- kvm_get_gdt(&gdt);
- table_base = gdt.base;
-
- if (selector & 4) { /* from ldt */
- u16 ldt_selector = kvm_read_ldt();
-
- table_base = segment_base(ldt_selector);
- }
- d = (struct desc_struct *)(table_base + (selector & ~7));
- v = get_desc_base(d);
-#ifdef CONFIG_X86_64
- if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
- v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
-#endif
- return v;
-}
-EXPORT_SYMBOL_GPL(segment_base);
-
u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
{
if (irqchip_in_kernel(vcpu->kvm))
@@ -293,7 +265,8 @@ static int exception_class(int vector)
}
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
- unsigned nr, bool has_error, u32 error_code)
+ unsigned nr, bool has_error, u32 error_code,
+ bool reinject)
{
u32 prev_nr;
int class1, class2;
@@ -304,6 +277,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
vcpu->arch.exception.error_code = error_code;
+ vcpu->arch.exception.reinject = reinject;
return;
}
@@ -332,10 +306,16 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr)
{
- kvm_multiple_exception(vcpu, nr, false, 0);
+ kvm_multiple_exception(vcpu, nr, false, 0, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception);
+void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr)
+{
+ kvm_multiple_exception(vcpu, nr, false, 0, true);
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception);
+
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
u32 error_code)
{
@@ -352,10 +332,16 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
{
- kvm_multiple_exception(vcpu, nr, true, error_code);
+ kvm_multiple_exception(vcpu, nr, true, error_code, false);
}
EXPORT_SYMBOL_GPL(kvm_queue_exception_e);
+void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code)
+{
+ kvm_multiple_exception(vcpu, nr, true, error_code, true);
+}
+EXPORT_SYMBOL_GPL(kvm_requeue_exception_e);
+
/*
* Checks if cpl <= required_cpl; if true, return true. Otherwise queue
* a #GP and return false.
@@ -476,7 +462,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
kvm_x86_ops->set_cr0(vcpu, cr0);
- vcpu->arch.cr0 = cr0;
kvm_mmu_reset_context(vcpu);
return;
@@ -485,7 +470,7 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
- kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f));
+ kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
@@ -517,7 +502,6 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
}
kvm_x86_ops->set_cr4(vcpu, cr4);
vcpu->arch.cr4 = cr4;
- vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled;
kvm_mmu_reset_context(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);
@@ -592,6 +576,80 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_get_cr8);
+int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
+{
+ switch (dr) {
+ case 0 ... 3:
+ vcpu->arch.db[dr] = val;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+ vcpu->arch.eff_db[dr] = val;
+ break;
+ case 4:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ case 6:
+ if (val & 0xffffffff00000000ULL) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+ break;
+ case 5:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ default: /* 7 */
+ if (val & 0xffffffff00000000ULL) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+ if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+ kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
+ vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
+ }
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_set_dr);
+
+int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
+{
+ switch (dr) {
+ case 0 ... 3:
+ *val = vcpu->arch.db[dr];
+ break;
+ case 4:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ case 6:
+ *val = vcpu->arch.dr6;
+ break;
+ case 5:
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+ /* fall through */
+ default: /* 7 */
+ *val = vcpu->arch.dr7;
+ break;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_get_dr);
+
static inline u32 bit(int bitno)
{
return 1 << (bitno & 31);
@@ -606,9 +664,10 @@ static inline u32 bit(int bitno)
* kvm-specific. Those are put in the beginning of the list.
*/
-#define KVM_SAVE_MSRS_BEGIN 5
+#define KVM_SAVE_MSRS_BEGIN 7
static u32 msrs_to_save[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
HV_X64_MSR_APIC_ASSIST_PAGE,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
@@ -625,48 +684,42 @@ static u32 emulated_msrs[] = {
MSR_IA32_MISC_ENABLE,
};
-static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (efer & efer_reserved_bits) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (efer & efer_reserved_bits)
+ return 1;
if (is_paging(vcpu)
- && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+ return 1;
if (efer & EFER_FFXSR) {
struct kvm_cpuid_entry2 *feat;
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT)))
+ return 1;
}
if (efer & EFER_SVME) {
struct kvm_cpuid_entry2 *feat;
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
- if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
- kvm_inject_gp(vcpu, 0);
- return;
- }
+ if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM)))
+ return 1;
}
- kvm_x86_ops->set_efer(vcpu, efer);
-
efer &= ~EFER_LMA;
efer |= vcpu->arch.efer & EFER_LMA;
+ kvm_x86_ops->set_efer(vcpu, efer);
+
vcpu->arch.efer = efer;
vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
kvm_mmu_reset_context(vcpu);
+
+ return 0;
}
void kvm_enable_efer_bits(u64 mask)
@@ -696,14 +749,22 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
{
- static int version;
+ int version;
+ int r;
struct pvclock_wall_clock wc;
struct timespec boot;
if (!wall_clock)
return;
- version++;
+ r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version));
+ if (r)
+ return;
+
+ if (version & 1)
+ ++version; /* first time write, random junk */
+
+ ++version;
kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
@@ -796,6 +857,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
vcpu->hv_clock.system_time = ts.tv_nsec +
(NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+ vcpu->hv_clock.flags = 0;
+
/*
* The interface expects us to write an even number signaling that the
* update is finished. Since the guest won't see the intermediate
@@ -1087,10 +1150,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
switch (msr) {
case MSR_EFER:
- set_efer(vcpu, data);
- break;
+ return set_efer(vcpu, data);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
+ data &= ~(u64)0x100; /* ignore ignne emulation enable */
if (data != 0) {
pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
data);
@@ -1133,10 +1196,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
+ case MSR_KVM_WALL_CLOCK_NEW:
case MSR_KVM_WALL_CLOCK:
vcpu->kvm->arch.wall_clock = data;
kvm_write_wall_clock(vcpu->kvm, data);
break;
+ case MSR_KVM_SYSTEM_TIME_NEW:
case MSR_KVM_SYSTEM_TIME: {
if (vcpu->arch.time_page) {
kvm_release_page_dirty(vcpu->arch.time_page);
@@ -1408,9 +1473,11 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
data = vcpu->arch.efer;
break;
case MSR_KVM_WALL_CLOCK:
+ case MSR_KVM_WALL_CLOCK_NEW:
data = vcpu->kvm->arch.wall_clock;
break;
case MSR_KVM_SYSTEM_TIME:
+ case MSR_KVM_SYSTEM_TIME_NEW:
data = vcpu->arch.time;
break;
case MSR_IA32_P5_MC_ADDR:
@@ -1549,6 +1616,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_HYPERV_VAPIC:
case KVM_CAP_HYPERV_SPIN:
case KVM_CAP_PCI_SEGMENT:
+ case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
r = 1;
break;
@@ -1769,6 +1837,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
{
int r;
+ vcpu_load(vcpu);
r = -E2BIG;
if (cpuid->nent < vcpu->arch.cpuid_nent)
goto out;
@@ -1780,6 +1849,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
out:
cpuid->nent = vcpu->arch.cpuid_nent;
+ vcpu_put(vcpu);
return r;
}
@@ -1910,6 +1980,24 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
}
break;
}
+ case KVM_CPUID_SIGNATURE: {
+ char signature[12] = "KVMKVMKVM\0\0";
+ u32 *sigptr = (u32 *)signature;
+ entry->eax = 0;
+ entry->ebx = sigptr[0];
+ entry->ecx = sigptr[1];
+ entry->edx = sigptr[2];
+ break;
+ }
+ case KVM_CPUID_FEATURES:
+ entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
+ (1 << KVM_FEATURE_NOP_IO_DELAY) |
+ (1 << KVM_FEATURE_CLOCKSOURCE2) |
+ (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+ entry->ebx = 0;
+ entry->ecx = 0;
+ entry->edx = 0;
+ break;
case 0x80000000:
entry->eax = min(entry->eax, 0x8000001a);
break;
@@ -1918,6 +2006,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->ecx &= kvm_supported_word6_x86_features;
break;
}
+
+ kvm_x86_ops->set_supported_cpuid(function, entry);
+
put_cpu();
}
@@ -1953,6 +2044,23 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
do_cpuid_ent(&cpuid_entries[nent], func, 0,
&nent, cpuid->nent);
+
+
+
+ r = -E2BIG;
+ if (nent >= cpuid->nent)
+ goto out_free;
+
+ do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
+ cpuid->nent);
+
+ r = -E2BIG;
+ if (nent >= cpuid->nent)
+ goto out_free;
+
+ do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
+ cpuid->nent);
+
r = -E2BIG;
if (nent >= cpuid->nent)
goto out_free;
@@ -2032,6 +2140,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
int r;
unsigned bank_num = mcg_cap & 0xff, bank;
+ vcpu_load(vcpu);
r = -EINVAL;
if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS)
goto out;
@@ -2046,6 +2155,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu,
for (bank = 0; bank < bank_num; bank++)
vcpu->arch.mce_banks[bank*4] = ~(u64)0;
out:
+ vcpu_put(vcpu);
return r;
}
@@ -2105,14 +2215,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
{
vcpu_load(vcpu);
- events->exception.injected = vcpu->arch.exception.pending;
+ events->exception.injected =
+ vcpu->arch.exception.pending &&
+ !kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
events->exception.error_code = vcpu->arch.exception.error_code;
- events->interrupt.injected = vcpu->arch.interrupt.pending;
+ events->interrupt.injected =
+ vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
- events->interrupt.soft = vcpu->arch.interrupt.soft;
+ 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;
@@ -2121,7 +2237,8 @@ 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);
}
@@ -2130,7 +2247,8 @@ 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);
@@ -2145,6 +2263,9 @@ 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)
@@ -2159,6 +2280,36 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return 0;
}
+static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *dbgregs)
+{
+ vcpu_load(vcpu);
+
+ memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
+ dbgregs->dr6 = vcpu->arch.dr6;
+ dbgregs->dr7 = vcpu->arch.dr7;
+ dbgregs->flags = 0;
+
+ vcpu_put(vcpu);
+}
+
+static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
+ struct kvm_debugregs *dbgregs)
+{
+ if (dbgregs->flags)
+ return -EINVAL;
+
+ vcpu_load(vcpu);
+
+ memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
+ vcpu->arch.dr6 = dbgregs->dr6;
+ vcpu->arch.dr7 = dbgregs->dr7;
+
+ vcpu_put(vcpu);
+
+ return 0;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2313,7 +2464,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&mce, argp, sizeof mce))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
+ vcpu_put(vcpu);
break;
}
case KVM_GET_VCPU_EVENTS: {
@@ -2337,6 +2490,29 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
break;
}
+ case KVM_GET_DEBUGREGS: {
+ struct kvm_debugregs dbgregs;
+
+ kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs);
+
+ r = -EFAULT;
+ if (copy_to_user(argp, &dbgregs,
+ sizeof(struct kvm_debugregs)))
+ break;
+ r = 0;
+ break;
+ }
+ case KVM_SET_DEBUGREGS: {
+ struct kvm_debugregs dbgregs;
+
+ r = -EFAULT;
+ if (copy_from_user(&dbgregs, argp,
+ sizeof(struct kvm_debugregs)))
+ break;
+
+ r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
+ break;
+ }
default:
r = -EINVAL;
}
@@ -2390,7 +2566,7 @@ gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn)
struct kvm_mem_alias *alias;
struct kvm_mem_aliases *aliases;
- aliases = rcu_dereference(kvm->arch.aliases);
+ aliases = kvm_aliases(kvm);
for (i = 0; i < aliases->naliases; ++i) {
alias = &aliases->aliases[i];
@@ -2409,7 +2585,7 @@ gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
struct kvm_mem_alias *alias;
struct kvm_mem_aliases *aliases;
- aliases = rcu_dereference(kvm->arch.aliases);
+ aliases = kvm_aliases(kvm);
for (i = 0; i < aliases->naliases; ++i) {
alias = &aliases->aliases[i];
@@ -2804,11 +2980,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
if (copy_from_user(&irq_event, argp, sizeof irq_event))
goto out;
+ r = -ENXIO;
if (irqchip_in_kernel(kvm)) {
__s32 status;
status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
irq_event.irq, irq_event.level);
if (ioctl == KVM_IRQ_LINE_STATUS) {
+ r = -EFAULT;
irq_event.status = status;
if (copy_to_user(argp, &irq_event,
sizeof irq_event))
@@ -3024,6 +3202,18 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v);
}
+static void kvm_set_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
+{
+ kvm_x86_ops->set_segment(vcpu, var, seg);
+}
+
+void kvm_get_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
+{
+ kvm_x86_ops->get_segment(vcpu, var, seg);
+}
+
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
@@ -3104,14 +3294,17 @@ 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(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 *error)
+static int kvm_write_guest_virt_system(gva_t addr, void *val,
+ unsigned int bytes,
+ struct kvm_vcpu *vcpu,
+ u32 *error)
{
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
- gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, 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;
@@ -3134,7 +3327,6 @@ out:
return r;
}
-
static int emulator_read_emulated(unsigned long addr,
void *val,
unsigned int bytes,
@@ -3237,9 +3429,9 @@ mmio:
}
int emulator_write_emulated(unsigned long addr,
- const void *val,
- unsigned int bytes,
- struct kvm_vcpu *vcpu)
+ const void *val,
+ unsigned int bytes,
+ struct kvm_vcpu *vcpu)
{
/* Crossing a page boundary? */
if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
@@ -3257,45 +3449,150 @@ int emulator_write_emulated(unsigned long addr,
}
EXPORT_SYMBOL_GPL(emulator_write_emulated);
+#define CMPXCHG_TYPE(t, ptr, old, new) \
+ (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old))
+
+#ifdef CONFIG_X86_64
+# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new)
+#else
+# define CMPXCHG64(ptr, old, new) \
+ (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old))
+#endif
+
static int emulator_cmpxchg_emulated(unsigned long addr,
const void *old,
const void *new,
unsigned int bytes,
struct kvm_vcpu *vcpu)
{
- printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
-#ifndef CONFIG_X86_64
- /* guests cmpxchg8b have to be emulated atomically */
- if (bytes == 8) {
- gpa_t gpa;
- struct page *page;
- char *kaddr;
- u64 val;
+ gpa_t gpa;
+ struct page *page;
+ char *kaddr;
+ bool exchanged;
- gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
+ /* guests cmpxchg8b have to be emulated atomically */
+ if (bytes > 8 || (bytes & (bytes - 1)))
+ goto emul_write;
- if (gpa == UNMAPPED_GVA ||
- (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
- goto emul_write;
+ gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL);
- if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
- goto emul_write;
+ if (gpa == UNMAPPED_GVA ||
+ (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
+ goto emul_write;
- val = *(u64 *)new;
+ if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK))
+ goto emul_write;
- page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
- kaddr = kmap_atomic(page, KM_USER0);
- set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
- kunmap_atomic(kaddr, KM_USER0);
- kvm_release_page_dirty(page);
+ kaddr = kmap_atomic(page, KM_USER0);
+ kaddr += offset_in_page(gpa);
+ switch (bytes) {
+ case 1:
+ exchanged = CMPXCHG_TYPE(u8, kaddr, old, new);
+ break;
+ case 2:
+ exchanged = CMPXCHG_TYPE(u16, kaddr, old, new);
+ break;
+ case 4:
+ exchanged = CMPXCHG_TYPE(u32, kaddr, old, new);
+ break;
+ case 8:
+ exchanged = CMPXCHG64(kaddr, old, new);
+ break;
+ default:
+ BUG();
}
+ kunmap_atomic(kaddr, KM_USER0);
+ kvm_release_page_dirty(page);
+
+ if (!exchanged)
+ return X86EMUL_CMPXCHG_FAILED;
+
+ kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);
+
+ return X86EMUL_CONTINUE;
+
emul_write:
-#endif
+ printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
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.count)
+ goto data_avail;
+
+ trace_kvm_pio(1, port, size, 1);
+
+ vcpu->arch.pio.port = port;
+ vcpu->arch.pio.in = 1;
+ 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.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.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.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);
@@ -3316,14 +3613,14 @@ int emulate_clts(struct kvm_vcpu *vcpu)
int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
- return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest);
+ return kvm_get_dr(ctxt->vcpu, dr, dest);
}
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
{
unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U;
- return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask);
+ return kvm_set_dr(ctxt->vcpu, dr, value & mask);
}
void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
@@ -3344,12 +3641,167 @@ 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 int emulator_get_cpl(struct kvm_vcpu *vcpu)
+{
+ return kvm_x86_ops->get_cpl(vcpu);
+}
+
+static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops->get_gdt(vcpu, dt);
+}
+
+static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg,
+ struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment var;
+
+ kvm_get_segment(vcpu, &var, seg);
+
+ if (var.unusable)
+ return false;
+
+ if (var.g)
+ var.limit >>= 12;
+ set_desc_limit(desc, var.limit);
+ set_desc_base(desc, (unsigned long)var.base);
+ desc->type = var.type;
+ desc->s = var.s;
+ desc->dpl = var.dpl;
+ desc->p = var.present;
+ desc->avl = var.avl;
+ desc->l = var.l;
+ desc->d = var.db;
+ desc->g = var.g;
+
+ return true;
+}
+
+static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg,
+ struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment var;
+
+ /* needed to preserve selector */
+ kvm_get_segment(vcpu, &var, seg);
+
+ var.base = get_desc_base(desc);
+ var.limit = get_desc_limit(desc);
+ if (desc->g)
+ var.limit = (var.limit << 12) | 0xfff;
+ var.type = desc->type;
+ var.present = desc->p;
+ var.dpl = desc->dpl;
+ var.db = desc->d;
+ var.s = desc->s;
+ var.l = desc->l;
+ var.g = desc->g;
+ var.avl = desc->avl;
+ var.present = desc->p;
+ var.unusable = !var.present;
+ var.padding = 0;
+
+ kvm_set_segment(vcpu, &var, seg);
+ return;
+}
+
+static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment kvm_seg;
+
+ kvm_get_segment(vcpu, &kvm_seg, seg);
+ return kvm_seg.selector;
+}
+
+static void emulator_set_segment_selector(u16 sel, int seg,
+ struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment kvm_seg;
+
+ kvm_get_segment(vcpu, &kvm_seg, seg);
+ kvm_seg.selector = sel;
+ 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,
.fetch = kvm_fetch_guest_virt,
.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,
+ .set_segment_selector = emulator_set_segment_selector,
+ .get_gdt = emulator_get_gdt,
+ .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)
@@ -3380,14 +3832,14 @@ 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;
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
vcpu->arch.emulate_ctxt.vcpu = vcpu;
- vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(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)
@@ -3396,6 +3848,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
+ trace_kvm_emulate_insn_start(vcpu);
/* Only allow emulation of specific instructions on #UD
* (namely VMMCALL, sysenter, sysexit, syscall)*/
@@ -3428,6 +3881,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
++vcpu->stat.insn_emulation;
if (r) {
++vcpu->stat.insn_emulation_fail;
+ trace_kvm_emulate_insn_failed(vcpu);
if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
return EMULATE_DONE;
return EMULATE_FAIL;
@@ -3439,16 +3893,20 @@ 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;
if (r == 0)
kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask);
- if (vcpu->arch.pio.string)
+ if (vcpu->arch.pio.count) {
+ if (!vcpu->arch.pio.in)
+ vcpu->arch.pio.count = 0;
return EMULATE_DO_MMIO;
+ }
- if ((r || vcpu->mmio_is_write) && run) {
+ if (r || vcpu->mmio_is_write) {
run->exit_reason = KVM_EXIT_MMIO;
run->mmio.phys_addr = vcpu->mmio_phys_addr;
memcpy(run->mmio.data, vcpu->mmio_data, 8);
@@ -3458,222 +3916,41 @@ 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) {
+ ++vcpu->stat.insn_emulation_fail;
+ trace_kvm_emulate_insn_failed(vcpu);
kvm_report_emulation_failure(vcpu, "mmio");
return EMULATE_FAIL;
}
return EMULATE_DO_MMIO;
}
- kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
-
if (vcpu->mmio_is_write) {
vcpu->mmio_needed = 0;
return EMULATE_DO_MMIO;
}
- return EMULATE_DONE;
-}
-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->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;
- }
-
- 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 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;
-}
+done:
+ if (vcpu->arch.exception.pending)
+ vcpu->arch.emulate_ctxt.restart = false;
-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;
+ if (vcpu->arch.emulate_ctxt.restart)
+ goto restart;
- 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(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;
+ return EMULATE_DONE;
}
-EXPORT_SYMBOL_GPL(kvm_emulate_pio);
+EXPORT_SYMBOL_GPL(emulate_instruction);
-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)
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short 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 */
-
+ 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.count = 0;
return ret;
}
-EXPORT_SYMBOL_GPL(kvm_emulate_pio_string);
+EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
static void bounce_off(void *info)
{
@@ -3996,85 +4273,20 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu)
return emulator_write_emulated(rip, instruction, 3, vcpu);
}
-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 descriptor_table dt = { limit, base };
+ struct desc_ptr dt = { limit, base };
kvm_x86_ops->set_gdt(vcpu, &dt);
}
void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base)
{
- struct descriptor_table dt = { limit, base };
+ struct desc_ptr dt = { limit, 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);
-}
-
-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,
- unsigned long *rflags)
-{
- 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;
- 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];
@@ -4138,9 +4350,13 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
+ best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
+ if (!best || best->eax < 0x80000008)
+ goto not_found;
best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
if (best)
return best->eax & 0xff;
+not_found:
return 36;
}
@@ -4254,9 +4470,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu)
{
/* try to reinject previous events if any */
if (vcpu->arch.exception.pending) {
+ trace_kvm_inj_exception(vcpu->arch.exception.nr,
+ vcpu->arch.exception.has_error_code,
+ vcpu->arch.exception.error_code);
kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
vcpu->arch.exception.has_error_code,
- vcpu->arch.exception.error_code);
+ vcpu->arch.exception.error_code,
+ vcpu->arch.exception.reinject);
return;
}
@@ -4486,7 +4706,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
}
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
- post_kvm_run_save(vcpu);
vapic_exit(vcpu);
@@ -4514,26 +4733,17 @@ 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) {
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = complete_pio(vcpu);
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
- if (r)
- goto out;
- }
- if (vcpu->mmio_needed) {
- memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
- vcpu->mmio_read_completed = 1;
- vcpu->mmio_needed = 0;
-
+ if (vcpu->arch.pio.count || vcpu->mmio_needed ||
+ vcpu->arch.emulate_ctxt.restart) {
+ if (vcpu->mmio_needed) {
+ memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
+ vcpu->mmio_read_completed = 1;
+ vcpu->mmio_needed = 0;
+ }
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
- EMULTYPE_NO_DECODE);
+ r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (r == EMULATE_DO_MMIO) {
- /*
- * Read-modify-write. Back to userspace.
- */
r = 0;
goto out;
}
@@ -4545,6 +4755,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
r = __vcpu_run(vcpu);
out:
+ post_kvm_run_save(vcpu);
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
@@ -4616,12 +4827,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
return 0;
}
-void kvm_get_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
-{
- kvm_x86_ops->get_segment(vcpu, var, seg);
-}
-
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
struct kvm_segment cs;
@@ -4635,7 +4840,7 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits);
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
struct kvm_sregs *sregs)
{
- struct descriptor_table dt;
+ struct desc_ptr dt;
vcpu_load(vcpu);
@@ -4650,11 +4855,11 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR);
kvm_x86_ops->get_idt(vcpu, &dt);
- sregs->idt.limit = dt.limit;
- sregs->idt.base = dt.base;
+ sregs->idt.limit = dt.size;
+ sregs->idt.base = dt.address;
kvm_x86_ops->get_gdt(vcpu, &dt);
- sregs->gdt.limit = dt.limit;
- sregs->gdt.base = dt.base;
+ sregs->gdt.limit = dt.size;
+ sregs->gdt.base = dt.address;
sregs->cr0 = kvm_read_cr0(vcpu);
sregs->cr2 = vcpu->arch.cr2;
@@ -4693,563 +4898,33 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
return 0;
}
-static void kvm_set_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
-{
- kvm_x86_ops->set_segment(vcpu, var, seg);
-}
-
-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 descriptor_table *dtable)
-{
- if (selector & 1 << 2) {
- struct kvm_segment kvm_seg;
-
- kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR);
-
- if (kvm_seg.unusable)
- dtable->limit = 0;
- else
- dtable->limit = kvm_seg.limit;
- dtable->base = 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 descriptor_table dtable;
- u16 index = selector >> 3;
- int ret;
- u32 err;
- gva_t addr;
-
- get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
- if (dtable.limit < 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 descriptor_table dtable;
- u16 index = selector >> 3;
-
- get_segment_descriptor_dtable(vcpu, selector, &dtable);
-
- if (dtable.limit < index * 8 + 7)
- return 1;
- return kvm_write_guest_virt(dtable.base + 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)
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
+ bool has_error_code, u32 error_code)
{
- 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;
+ int cs_db, cs_l, ret;
+ cache_all_regs(vcpu);
- if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu))
- return kvm_load_realmode_segment(vcpu, selector, seg);
+ kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
- /* 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;
+ 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;
- /* TR should be in GDT only */
- if (seg == VCPU_SREG_TR && (selector & (1 << 2)))
- goto exception;
+ ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops,
+ tss_selector, reason, has_error_code,
+ error_code);
- 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;
+ return EMULATE_FAIL;
- 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);
- }
-
- /* 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 (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);
-
- if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
- u32 eflags = kvm_get_rflags(vcpu);
- kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
- }
-
- if (reason != TASK_SWITCH_IRET) {
- nseg_desc.type |= (1 << 1);
- save_guest_segment_descriptor(vcpu, tss_selector,
- &nseg_desc);
- }
-
- 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;
+ kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);
@@ -5258,15 +4933,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
{
int mmu_reset_needed = 0;
int pending_vec, max_bits;
- struct descriptor_table dt;
+ struct desc_ptr dt;
vcpu_load(vcpu);
- dt.limit = sregs->idt.limit;
- dt.base = sregs->idt.base;
+ dt.size = sregs->idt.limit;
+ dt.address = sregs->idt.base;
kvm_x86_ops->set_idt(vcpu, &dt);
- dt.limit = sregs->gdt.limit;
- dt.base = sregs->gdt.base;
+ dt.size = sregs->gdt.limit;
+ dt.address = sregs->gdt.base;
kvm_x86_ops->set_gdt(vcpu, &dt);
vcpu->arch.cr2 = sregs->cr2;
@@ -5365,11 +5040,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
}
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
- vcpu->arch.singlestep_cs =
- get_segment_selector(vcpu, VCPU_SREG_CS);
- vcpu->arch.singlestep_rip = kvm_rip_read(vcpu);
- }
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+ vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
+ get_segment_base(vcpu, VCPU_SREG_CS);
/*
* Trigger an rflags update that will inject or remove the trace
@@ -5860,13 +5533,22 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
return kvm_x86_ops->interrupt_allowed(vcpu);
}
+bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
+{
+ unsigned long current_rip = kvm_rip_read(vcpu) +
+ get_segment_base(vcpu, VCPU_SREG_CS);
+
+ return current_rip == linear_rip;
+}
+EXPORT_SYMBOL_GPL(kvm_is_linear_rip);
+
unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
{
unsigned long rflags;
rflags = kvm_x86_ops->get_rflags(vcpu);
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF);
+ rflags &= ~X86_EFLAGS_TF;
return rflags;
}
EXPORT_SYMBOL_GPL(kvm_get_rflags);
@@ -5874,10 +5556,8 @@ EXPORT_SYMBOL_GPL(kvm_get_rflags);
void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
- vcpu->arch.singlestep_cs ==
- get_segment_selector(vcpu, VCPU_SREG_CS) &&
- vcpu->arch.singlestep_rip == kvm_rip_read(vcpu))
- rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+ kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
+ rflags |= X86_EFLAGS_TF;
kvm_x86_ops->set_rflags(vcpu, rflags);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);
@@ -5893,3 +5573,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index b7a404722d2b..f4b54458285b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -65,6 +65,13 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
}
+static inline struct kvm_mem_aliases *kvm_aliases(struct kvm *kvm)
+{
+ return rcu_dereference_check(kvm->arch.aliases,
+ srcu_read_lock_held(&kvm->srcu)
+ || lockdep_is_held(&kvm->slots_lock));
+}
+
void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
OpenPOWER on IntegriCloud