There are several checks for "peculiar" aspects of instructions in both
x86_decode_insn and x86_emulate_insn. Group them together, and guard
them with a single "if" that lets the processor quickly skip them all.
To do this effectively, add two more flag bits that say whether the
.intercept and .check_perm fields are valid.
This skims about 10 cycles for each emulated instructions, which is
a 2 to 6% improvement.
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
To review, use -b.
arch/x86/kvm/emulate.c | 175 ++++++++++++++++++++++++++-----------------------
1 file changed, 94 insertions(+), 81 deletions(-)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9e40fbf94dcd..94974055d906 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -161,6 +161,8 @@
#define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */
#define NoWrite ((u64)1 << 45) /* No writeback */
#define SrcWrite ((u64)1 << 46) /* Write back src operand */
+#define Intercept ((u64)1 << 47) /* Has intercept field */
+#define CheckPerm ((u64)1 << 48) /* Has intercept field */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
@@ -3514,9 +3516,9 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
}
#define D(_y) { .flags = (_y) }
-#define DI(_y, _i) { .flags = (_y), .intercept = x86_intercept_##_i }
-#define DIP(_y, _i, _p) { .flags = (_y), .intercept = x86_intercept_##_i, \
- .check_perm = (_p) }
+#define DI(_y, _i) { .flags = (_y)|Intercept, .intercept = x86_intercept_##_i }
+#define DIP(_y, _i, _p) { .flags = (_y)|Intercept|CheckPerm, \
+ .intercept = x86_intercept_##_i, .check_perm = (_p) }
#define N D(NotImpl)
#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
@@ -3525,10 +3527,10 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
#define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
#define II(_f, _e, _i) \
- { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
+ { .flags = (_f)|Intercept, .u.execute = (_e), .intercept = x86_intercept_##_i }
#define IIP(_f, _e, _i, _p) \
- { .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i, \
- .check_perm = (_p) }
+ { .flags = (_f)|Intercept|CheckPerm, .u.execute = (_e), \
+ .intercept = x86_intercept_##_i, .check_perm = (_p) }
#define GP(_f, _g) { .flags = ((_f) | Prefix), .u.gprefix = (_g) }
#define D2bv(_f) D((_f) | ByteOp), D(_f)
@@ -4352,29 +4354,37 @@ done_prefixes:
return EMULATION_FAILED;
ctxt->execute = opcode.u.execute;
- ctxt->check_perm = opcode.check_perm;
- ctxt->intercept = opcode.intercept;
- if (ctxt->d & NotImpl)
- return EMULATION_FAILED;
+ if (unlikely(ctxt->d &
+ (NotImpl|EmulateOnUD|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+ /*
+ * These are copied unconditionally here, and checked unconditionally
+ * in x86_emulate_insn.
+ */
+ ctxt->check_perm = opcode.check_perm;
+ ctxt->intercept = opcode.intercept;
- if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
- return EMULATION_FAILED;
+ if (ctxt->d & NotImpl)
+ return EMULATION_FAILED;
- if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
- ctxt->op_bytes = 8;
+ if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
+ return EMULATION_FAILED;
- if (ctxt->d & Op3264) {
- if (mode == X86EMUL_MODE_PROT64)
+ if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
ctxt->op_bytes = 8;
- else
- ctxt->op_bytes = 4;
- }
- if (ctxt->d & Sse)
- ctxt->op_bytes = 16;
- else if (ctxt->d & Mmx)
- ctxt->op_bytes = 8;
+ if (ctxt->d & Op3264) {
+ if (mode == X86EMUL_MODE_PROT64)
+ ctxt->op_bytes = 8;
+ else
+ ctxt->op_bytes = 4;
+ }
+
+ if (ctxt->d & Sse)
+ ctxt->op_bytes = 16;
+ else if (ctxt->d & Mmx)
+ ctxt->op_bytes = 8;
+ }
/* ModRM and SIB bytes. */
if (ctxt->d & ModRM) {
@@ -4508,75 +4518,78 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
- if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
- (ctxt->d & Undefined)) {
- rc = emulate_ud(ctxt);
- goto done;
- }
-
- if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
- || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
- rc = emulate_ud(ctxt);
- goto done;
- }
-
- if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
- rc = emulate_nm(ctxt);
- goto done;
- }
+ if (unlikely(ctxt->d &
+ (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) {
+ if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) ||
+ (ctxt->d & Undefined)) {
+ rc = emulate_ud(ctxt);
+ goto done;
+ }
- if (ctxt->d & Mmx) {
- rc = flush_pending_x87_faults(ctxt);
- if (rc != X86EMUL_CONTINUE)
+ if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
+ || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
+ rc = emulate_ud(ctxt);
goto done;
- /*
- * Now that we know the fpu is exception safe, we can fetch
- * operands from it.
- */
- fetch_possible_mmx_operand(ctxt, &ctxt->src);
- fetch_possible_mmx_operand(ctxt, &ctxt->src2);
- if (!(ctxt->d & Mov))
- fetch_possible_mmx_operand(ctxt, &ctxt->dst);
- }
+ }
- if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
- rc = emulator_check_intercept(ctxt, ctxt->intercept,
- X86_ICPT_PRE_EXCEPT);
- if (rc != X86EMUL_CONTINUE)
+ if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
+ rc = emulate_nm(ctxt);
goto done;
- }
+ }
- /* Privileged instruction can be executed only in CPL=0 */
- if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
- rc = emulate_gp(ctxt, 0);
- goto done;
- }
+ if (ctxt->d & Mmx) {
+ rc = flush_pending_x87_faults(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ /*
+ * Now that we know the fpu is exception safe, we can fetch
+ * operands from it.
+ */
+ fetch_possible_mmx_operand(ctxt, &ctxt->src);
+ fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+ if (!(ctxt->d & Mov))
+ fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+ }
- /* Instruction can only be executed in protected mode */
- if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
- rc = emulate_ud(ctxt);
- goto done;
- }
+ if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
+ rc = emulator_check_intercept(ctxt, ctxt->intercept,
+ X86_ICPT_PRE_EXCEPT);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ }
- /* Do instruction specific permission checks */
- if (ctxt->check_perm) {
- rc = ctxt->check_perm(ctxt);
- if (rc != X86EMUL_CONTINUE)
+ /* Privileged instruction can be executed only in CPL=0 */
+ if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
+ rc = emulate_gp(ctxt, 0);
goto done;
- }
+ }
- if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
- rc = emulator_check_intercept(ctxt, ctxt->intercept,
- X86_ICPT_POST_EXCEPT);
- if (rc != X86EMUL_CONTINUE)
+ /* Instruction can only be executed in protected mode */
+ if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
+ rc = emulate_ud(ctxt);
goto done;
- }
+ }
- if (ctxt->rep_prefix && (ctxt->d & String)) {
- /* All REP prefixes have the same first termination condition */
- if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
- ctxt->eip = ctxt->_eip;
- goto done;
+ /* Do instruction specific permission checks */
+ if (ctxt->check_perm) {
+ rc = ctxt->check_perm(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ }
+
+ if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
+ rc = emulator_check_intercept(ctxt, ctxt->intercept,
+ X86_ICPT_POST_EXCEPT);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ }
+
+ if (ctxt->rep_prefix && (ctxt->d & String)) {
+ /* All REP prefixes have the same first termination condition */
+ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) {
+ ctxt->eip = ctxt->_eip;
+ goto done;
+ }
}
}
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
