[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 14/46] target/i386: do not clobber T0 on string operations
From: |
Paolo Bonzini |
Subject: |
[PULL 14/46] target/i386: do not clobber T0 on string operations |
Date: |
Sun, 31 Dec 2023 09:44:30 +0100 |
The new decoder would rather have the operand in T0 when expanding SCAS, rather
than use R_EAX directly as gen_scas currently does. This makes SCAS more
similar
to CMP and SUB, in that CC_DST = T0 - T1.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
target/i386/tcg/translate.c | 45 ++++++++++++++++++++-----------------
1 file changed, 24 insertions(+), 21 deletions(-)
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index efef4e74d4c..00ed0cc9a31 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -522,9 +522,9 @@ void gen_op_add_reg_im(DisasContext *s, MemOp size, int
reg, int32_t val)
gen_op_mov_reg_v(s, size, reg, s->tmp0);
}
-static inline void gen_op_add_reg_T0(DisasContext *s, MemOp size, int reg)
+static inline void gen_op_add_reg(DisasContext *s, MemOp size, int reg, TCGv
val)
{
- tcg_gen_add_tl(s->tmp0, cpu_regs[reg], s->T0);
+ tcg_gen_add_tl(s->tmp0, cpu_regs[reg], val);
gen_op_mov_reg_v(s, size, reg, s->tmp0);
}
@@ -707,10 +707,12 @@ static inline void gen_string_movl_A0_EDI(DisasContext *s)
gen_lea_v_seg(s, s->aflag, cpu_regs[R_EDI], R_ES, -1);
}
-static inline void gen_op_movl_T0_Dshift(DisasContext *s, MemOp ot)
+static inline TCGv gen_compute_Dshift(DisasContext *s, MemOp ot)
{
- tcg_gen_ld32s_tl(s->T0, tcg_env, offsetof(CPUX86State, df));
- tcg_gen_shli_tl(s->T0, s->T0, ot);
+ TCGv dshift = tcg_temp_new();
+ tcg_gen_ld32s_tl(dshift, tcg_env, offsetof(CPUX86State, df));
+ tcg_gen_shli_tl(dshift, dshift, ot);
+ return dshift;
};
static TCGv gen_ext_tl(TCGv dst, TCGv src, MemOp size, bool sign)
@@ -818,13 +820,16 @@ static bool gen_check_io(DisasContext *s, MemOp ot,
TCGv_i32 port,
static void gen_movs(DisasContext *s, MemOp ot)
{
+ TCGv dshift;
+
gen_string_movl_A0_ESI(s);
gen_op_ld_v(s, ot, s->T0, s->A0);
gen_string_movl_A0_EDI(s);
gen_op_st_v(s, ot, s->T0, s->A0);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_ESI);
- gen_op_add_reg_T0(s, s->aflag, R_EDI);
+
+ dshift = gen_compute_Dshift(s, ot);
+ gen_op_add_reg(s, s->aflag, R_ESI, dshift);
+ gen_op_add_reg(s, s->aflag, R_EDI, dshift);
}
static void gen_op_update1_cc(DisasContext *s)
@@ -1249,8 +1254,7 @@ static void gen_stos(DisasContext *s, MemOp ot)
gen_op_mov_v_reg(s, MO_32, s->T0, R_EAX);
gen_string_movl_A0_EDI(s);
gen_op_st_v(s, ot, s->T0, s->A0);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_EDI);
+ gen_op_add_reg(s, s->aflag, R_EDI, gen_compute_Dshift(s, ot));
}
static void gen_lods(DisasContext *s, MemOp ot)
@@ -1258,8 +1262,7 @@ static void gen_lods(DisasContext *s, MemOp ot)
gen_string_movl_A0_ESI(s);
gen_op_ld_v(s, ot, s->T0, s->A0);
gen_op_mov_reg_v(s, ot, R_EAX, s->T0);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_ESI);
+ gen_op_add_reg(s, s->aflag, R_ESI, gen_compute_Dshift(s, ot));
}
static void gen_scas(DisasContext *s, MemOp ot)
@@ -1267,19 +1270,21 @@ static void gen_scas(DisasContext *s, MemOp ot)
gen_string_movl_A0_EDI(s);
gen_op_ld_v(s, ot, s->T1, s->A0);
gen_op(s, OP_CMPL, ot, R_EAX);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_EDI);
+ gen_op_add_reg(s, s->aflag, R_EDI, gen_compute_Dshift(s, ot));
}
static void gen_cmps(DisasContext *s, MemOp ot)
{
+ TCGv dshift;
+
gen_string_movl_A0_EDI(s);
gen_op_ld_v(s, ot, s->T1, s->A0);
gen_string_movl_A0_ESI(s);
gen_op(s, OP_CMPL, ot, OR_TMP0);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_ESI);
- gen_op_add_reg_T0(s, s->aflag, R_EDI);
+
+ dshift = gen_compute_Dshift(s, ot);
+ gen_op_add_reg(s, s->aflag, R_ESI, dshift);
+ gen_op_add_reg(s, s->aflag, R_EDI, dshift);
}
static void gen_bpt_io(DisasContext *s, TCGv_i32 t_port, int ot)
@@ -1307,8 +1312,7 @@ static void gen_ins(DisasContext *s, MemOp ot)
tcg_gen_andi_i32(s->tmp2_i32, s->tmp2_i32, 0xffff);
gen_helper_in_func(ot, s->T0, s->tmp2_i32);
gen_op_st_v(s, ot, s->T0, s->A0);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_EDI);
+ gen_op_add_reg(s, s->aflag, R_EDI, gen_compute_Dshift(s, ot));
gen_bpt_io(s, s->tmp2_i32, ot);
}
@@ -1321,8 +1325,7 @@ static void gen_outs(DisasContext *s, MemOp ot)
tcg_gen_andi_i32(s->tmp2_i32, s->tmp2_i32, 0xffff);
tcg_gen_trunc_tl_i32(s->tmp3_i32, s->T0);
gen_helper_out_func(ot, s->tmp2_i32, s->tmp3_i32);
- gen_op_movl_T0_Dshift(s, ot);
- gen_op_add_reg_T0(s, s->aflag, R_ESI);
+ gen_op_add_reg(s, s->aflag, R_ESI, gen_compute_Dshift(s, ot));
gen_bpt_io(s, s->tmp2_i32, ot);
}
--
2.43.0
- [PULL 02/46] target/i386: optimize computation of JL and JLE from flags, (continued)
- [PULL 02/46] target/i386: optimize computation of JL and JLE from flags, Paolo Bonzini, 2023/12/31
- [PULL 05/46] target/i386: remove unnecessary truncations, Paolo Bonzini, 2023/12/31
- [PULL 07/46] target/i386: document more deviations from the manual, Paolo Bonzini, 2023/12/31
- [PULL 03/46] target/i386: speedup JO/SETO after MUL or IMUL, Paolo Bonzini, 2023/12/31
- [PULL 04/46] target/i386: remove unnecessary arguments from raise_interrupt, Paolo Bonzini, 2023/12/31
- [PULL 06/46] target/i386: clean up cpu_cc_compute_all, Paolo Bonzini, 2023/12/31
- [PULL 08/46] target/i386: reimplement check for validity of LOCK prefix, Paolo Bonzini, 2023/12/31
- [PULL 09/46] target/i386: avoid trunc and ext for MULX and RORX, Paolo Bonzini, 2023/12/31
- [PULL 10/46] target/i386: rename zext0/zext2 and make them closer to the manual, Paolo Bonzini, 2023/12/31
- [PULL 11/46] target/i386: add X86_SPECIALs for MOVSX and MOVZX, Paolo Bonzini, 2023/12/31
- [PULL 14/46] target/i386: do not clobber T0 on string operations,
Paolo Bonzini <=
- [PULL 16/46] target/i386: do not use s->tmp4 for push, Paolo Bonzini, 2023/12/31
- [PULL 15/46] target/i386: split eflags computation out of gen_compute_eflags, Paolo Bonzini, 2023/12/31
- [PULL 12/46] target/i386: do not decode string source/destination into decode->mem, Paolo Bonzini, 2023/12/31
- [PULL 13/46] target/i386: do not clobber A0 in POP translation, Paolo Bonzini, 2023/12/31
- [PULL 18/46] target/i386: prepare for implementation of STOS/SCAS in new decoder, Paolo Bonzini, 2023/12/31
- [PULL 17/46] target/i386: do not use s->tmp0 for jumps on ECX ==/!= 0, Paolo Bonzini, 2023/12/31
- [PULL 19/46] target/i386: move operand load and writeback out of gen_cmovcc1, Paolo Bonzini, 2023/12/31
- [PULL 21/46] target/i386: introduce flags writeback mechanism, Paolo Bonzini, 2023/12/31
- [PULL 20/46] target/i386: adjust decoding of J operand, Paolo Bonzini, 2023/12/31
- [PULL 34/46] meson: move accelerator dependency checks together, Paolo Bonzini, 2023/12/31