KVM: emulate: do not initialize memopp

rip_relative is only set if decode_modrm runs, and if you have ModRM
you will also have a memopp.  We can then access memopp unconditionally.
Note that rip_relative cannot be hoisted up to decode_modrm, or you
break "mov $0, xyz(%rip)".

Also, move typecast on "out of range value" of mem.ea to decode_modrm.

Together, all these optimizations save about 50 cycles on each emulated
instructions (4-6%).

Signed-off-by: Bandan Das <bsd@redhat.com>
[Fix immediate operands with rip-relative addressing. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_emulate.h

@@ -295,6 +295,11 @@ struct x86_emulate_ctxt {
 	struct operand dst;
 	int (*execute)(struct x86_emulate_ctxt *ctxt);
 	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
+	/*
+	 * The following six fields are cleared together,
+	 * the rest are initialized unconditionally in x86_decode_insn
+	 * or elsewhere
+	 */
 	bool rip_relative;
 	u8 rex_prefix;
 	u8 lock_prefix;

arch/x86/kvm/emulate.c

@@ -1177,6 +1177,9 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 		}
 	}
 	op->addr.mem.ea = modrm_ea;
+	if (ctxt->ad_bytes != 8)
+		ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea;
+
 done:
 	return rc;
 }
@@ -4425,9 +4428,6 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 
 	ctxt->memop.addr.mem.seg = ctxt->seg_override;
 
-	if (ctxt->memop.type == OP_MEM && ctxt->ad_bytes != 8)
-		ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea;
-
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -4448,7 +4448,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
 
 done:
-	if (ctxt->memopp && ctxt->memopp->type == OP_MEM && ctxt->rip_relative)
+	if (ctxt->rip_relative)
 		ctxt->memopp->addr.mem.ea += ctxt->_eip;
 
 	return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;