For updates to implicit registers (RCX in LOOP instructions, RSI or RDI
in string instructions, or the stack pointer) do the add directly using
the registers (with no temporary) if 32-bit or 64-bit, or use a temporary
created for the occasion if 16-bit.  This is more efficient and removes
move instructions for the MO_TL case.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Link: https://lore.kernel.org/r/20241215090613.89588-14-pbonzini@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/tcg/translate.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 9b2fde5eb28..a8935f487aa 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -505,17 +505,24 @@ static inline void gen_op_jmp_v(DisasContext *s, TCGv dest)
     s->pc_save = -1;
 }
 
+static inline void gen_op_add_reg(DisasContext *s, MemOp size, int reg, TCGv val)
+{
+    /* Using cpu_regs[reg] does not work for xH registers.  */
+    assert(size >= MO_16);
+    if (size == MO_16) {
+        TCGv temp = tcg_temp_new();
+        tcg_gen_add_tl(temp, cpu_regs[reg], val);
+        gen_op_mov_reg_v(s, size, reg, temp);
+    } else {
+        tcg_gen_add_tl(cpu_regs[reg], cpu_regs[reg], val);
+        tcg_gen_ext_tl(cpu_regs[reg], cpu_regs[reg], size);
+    }
+}
+
 static inline
 void gen_op_add_reg_im(DisasContext *s, MemOp size, int reg, int32_t val)
 {
-    tcg_gen_addi_tl(s->tmp0, cpu_regs[reg], val);
-    gen_op_mov_reg_v(s, size, reg, s->tmp0);
-}
-
-static inline void gen_op_add_reg(DisasContext *s, MemOp size, int reg, TCGv val)
-{
-    tcg_gen_add_tl(s->tmp0, cpu_regs[reg], val);
-    gen_op_mov_reg_v(s, size, reg, s->tmp0);
+    gen_op_add_reg(s, size, reg, tcg_constant_tl(val));
 }
 
 static inline void gen_op_ld_v(DisasContext *s, int idx, TCGv t0, TCGv a0)
-- 
2.48.1