Re: [PATCH v2 14/35] tcg/i386: Support TCG_COND_TST{EQ,NE}

2023-11-08 Thread Philippe Mathieu-Daudé

On 28/10/23 21:45, Richard Henderson wrote:

Merge tcg_out_testi into tcg_out_cmp and adjust the two uses.

Signed-off-by: Richard Henderson 
---
  tcg/i386/tcg-target.c.inc | 83 ++-
  1 file changed, 47 insertions(+), 36 deletions(-)




  #if TCG_TARGET_REG_BITS == 64
@@ -1422,15 +1424,35 @@ static void tcg_out_jxx(TCGContext *s, int opc, 
TCGLabel *l, bool small)
  static int tcg_out_cmp(TCGContext *s, TCGCond cond, TCGArg arg1,
 TCGArg arg2, int const_arg2, int rexw)
  {
-if (const_arg2) {
-if (arg2 == 0) {
-/* test r, r */
-tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg1);
+if (is_tst_cond(cond)) {
+if (!const_arg2) {
+tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg2);
+} else if (arg2 <= 0xff && (TCG_TARGET_REG_BITS == 64 || arg1 < 4)) {
+tcg_out_modrm(s, OPC_GRP3_Eb | P_REXB_RM, EXT3_TESTi, arg1);
+tcg_out8(s, arg2);
+} else if ((arg2 & ~0xff00) == 0 && arg1 < 4) {
+tcg_out_modrm(s, OPC_GRP3_Eb, EXT3_TESTi, arg1 + 4);
+tcg_out8(s, arg2 >> 8);
  } else {


For this part, a double-review from x86 developer is welcomed,


-tgen_arithi(s, ARITH_CMP + rexw, arg1, arg2, 0);
+if (rexw) {
+if (arg2 == (uint32_t)arg2) {
+rexw = 0;
+} else {
+tcg_debug_assert(arg2 == (int32_t)arg2);
+}
+}
+tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_TESTi, arg1);
+tcg_out32(s, arg2);
  }
  } else {


then the rest is OK.

Reviewed-by: Philippe Mathieu-Daudé 




[PATCH v2 14/35] tcg/i386: Support TCG_COND_TST{EQ,NE}

2023-10-28 Thread Richard Henderson
Merge tcg_out_testi into tcg_out_cmp and adjust the two uses.

Signed-off-by: Richard Henderson 
---
 tcg/i386/tcg-target.c.inc | 83 ++-
 1 file changed, 47 insertions(+), 36 deletions(-)

diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 7d5ed0d045..17b250f16f 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -505,6 +505,8 @@ static const uint8_t tcg_cond_to_jcc[] = {
 [TCG_COND_GEU] = JCC_JAE,
 [TCG_COND_LEU] = JCC_JBE,
 [TCG_COND_GTU] = JCC_JA,
+[TCG_COND_TSTEQ] = JCC_JE,
+[TCG_COND_TSTNE] = JCC_JNE,
 };
 
 #if TCG_TARGET_REG_BITS == 64
@@ -1422,15 +1424,35 @@ static void tcg_out_jxx(TCGContext *s, int opc, 
TCGLabel *l, bool small)
 static int tcg_out_cmp(TCGContext *s, TCGCond cond, TCGArg arg1,
TCGArg arg2, int const_arg2, int rexw)
 {
-if (const_arg2) {
-if (arg2 == 0) {
-/* test r, r */
-tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg1);
+if (is_tst_cond(cond)) {
+if (!const_arg2) {
+tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg2);
+} else if (arg2 <= 0xff && (TCG_TARGET_REG_BITS == 64 || arg1 < 4)) {
+tcg_out_modrm(s, OPC_GRP3_Eb | P_REXB_RM, EXT3_TESTi, arg1);
+tcg_out8(s, arg2);
+} else if ((arg2 & ~0xff00) == 0 && arg1 < 4) {
+tcg_out_modrm(s, OPC_GRP3_Eb, EXT3_TESTi, arg1 + 4);
+tcg_out8(s, arg2 >> 8);
 } else {
-tgen_arithi(s, ARITH_CMP + rexw, arg1, arg2, 0);
+if (rexw) {
+if (arg2 == (uint32_t)arg2) {
+rexw = 0;
+} else {
+tcg_debug_assert(arg2 == (int32_t)arg2);
+}
+}
+tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_TESTi, arg1);
+tcg_out32(s, arg2);
 }
 } else {
-tgen_arithr(s, ARITH_CMP + rexw, arg1, arg2);
+if (!const_arg2) {
+tgen_arithr(s, ARITH_CMP + rexw, arg1, arg2);
+} else if (arg2 == 0) {
+tcg_out_modrm(s, OPC_TESTL + rexw, arg1, arg1);
+} else {
+tcg_debug_assert(!rexw || arg2 == (int32_t)arg2);
+tgen_arithi(s, ARITH_CMP + rexw, arg1, arg2, 0);
+}
 }
 return tcg_cond_to_jcc[cond];
 }
@@ -1449,18 +1471,21 @@ static void tcg_out_brcond2(TCGContext *s, const TCGArg 
*args,
 {
 TCGLabel *label_next = gen_new_label();
 TCGLabel *label_this = arg_label(args[5]);
+TCGCond cond = args[4];
 
-switch(args[4]) {
+switch (cond) {
 case TCG_COND_EQ:
-tcg_out_brcond(s, 0, TCG_COND_NE, args[0], args[2], const_args[2],
-   label_next, 1);
-tcg_out_brcond(s, 0, TCG_COND_EQ, args[1], args[3], const_args[3],
+case TCG_COND_TSTEQ:
+tcg_out_brcond(s, 0, tcg_invert_cond(cond),
+   args[0], args[2], const_args[2], label_next, 1);
+tcg_out_brcond(s, 0, cond, args[1], args[3], const_args[3],
label_this, small);
 break;
 case TCG_COND_NE:
-tcg_out_brcond(s, 0, TCG_COND_NE, args[0], args[2], const_args[2],
+case TCG_COND_TSTNE:
+tcg_out_brcond(s, 0, cond, args[0], args[2], const_args[2],
label_this, small);
-tcg_out_brcond(s, 0, TCG_COND_NE, args[1], args[3], const_args[3],
+tcg_out_brcond(s, 0, cond, args[1], args[3], const_args[3],
label_this, small);
 break;
 case TCG_COND_LT:
@@ -1797,23 +1822,6 @@ static void tcg_out_nopn(TCGContext *s, int n)
 tcg_out8(s, 0x90);
 }
 
-/* Test register R vs immediate bits I, setting Z flag for EQ/NE. */
-static void __attribute__((unused))
-tcg_out_testi(TCGContext *s, TCGReg r, uint32_t i)
-{
-/*
- * This is used for testing alignment, so we can usually use testb.
- * For i686, we have to use testl for %esi/%edi.
- */
-if (i <= 0xff && (TCG_TARGET_REG_BITS == 64 || r < 4)) {
-tcg_out_modrm(s, OPC_GRP3_Eb | P_REXB_RM, EXT3_TESTi, r);
-tcg_out8(s, i);
-} else {
-tcg_out_modrm(s, OPC_GRP3_Ev, EXT3_TESTi, r);
-tcg_out32(s, i);
-}
-}
-
 typedef struct {
 TCGReg base;
 int index;
@@ -2074,16 +2082,17 @@ static TCGLabelQemuLdst *prepare_host_addr(TCGContext 
*s, HostAddress *h,
 tcg_out_ld(s, TCG_TYPE_PTR, TCG_REG_L0, TCG_REG_L0,
offsetof(CPUTLBEntry, addend));
 } else if (a_mask) {
-ldst = new_ldst_label(s);
+int jcc;
 
+ldst = new_ldst_label(s);
 ldst->is_ld = is_ld;
 ldst->oi = oi;
 ldst->addrlo_reg = addrlo;
 ldst->addrhi_reg = addrhi;
 
-tcg_out_testi(s, addrlo, a_mask);
 /* jne slow_path */
-tcg_out_opc(s, OPC_JCC_long + JCC_JNE, 0, 0, 0);
+jcc = tcg_out_cmp(s, TCG_COND_TSTNE, addrlo, a_mask, true, false);
+tcg_out_opc(s, OPC_JCC_long + jcc, 0,