KVM: emulate: protect checks on ctxt->d by a common "if (unlikely())"

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.
Make this more effective by adding two more flag bits that say whether the
.intercept and .check_perm fields are valid.  We will reuse these
flags later to avoid initializing fields of the emulate_ctxt struct.

This skims about 30 cycles for each emulated instructions, which is
approximately a 3% improvement.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/emulate.c

@@ -162,6 +162,8 @@
 #define NoWrite     ((u64)1 << 45)  /* No writeback */
 #define SrcWrite    ((u64)1 << 46)  /* Write back src operand */
 #define NoMod	    ((u64)1 << 47)  /* Mod field is ignored */
+#define Intercept   ((u64)1 << 48)  /* Has valid intercept field */
+#define CheckPerm   ((u64)1 << 49)  /* Has valid check_perm field */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -3546,9 +3548,9 @@ 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) }
@@ -3557,10 +3559,10 @@ 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)
@@ -4393,6 +4395,13 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 		return EMULATION_FAILED;
 
 	ctxt->execute = opcode.u.execute;
+
+	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;
 
@@ -4416,6 +4425,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 			ctxt->op_bytes = 16;
 		else if (ctxt->d & Mmx)
 			ctxt->op_bytes = 8;
+	}
 
 	/* ModRM and SIB bytes. */
 	if (ctxt->d & ModRM) {
@@ -4549,6 +4559,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *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);
@@ -4620,6 +4632,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 			}
 		}
+	}
 
 	if ((ctxt->src.type == OP_MEM) && !(ctxt->d & NoAccess)) {
 		rc = segmented_read(ctxt, ctxt->src.addr.mem,