qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: richard.henderson@linaro.org, paul@nowt.org
Subject: [PATCH v2 37/37] target/i386: remove old SSE decoder
Date: Tue, 20 Sep 2022 19:25:07 +0200	[thread overview]
Message-ID: <20220920172507.95568-38-pbonzini@redhat.com> (raw)
In-Reply-To: <20220920172507.95568-1-pbonzini@redhat.com>

With all SSE (and AVX!) instructions now implemented in disas_insn_new,
it's possible to remove gen_sse, as well as the helpers for instructions
that now use gvec.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/ops_sse.h            |  124 ---
 target/i386/ops_sse_header.h     |   61 --
 target/i386/tcg/decode-new.c.inc |    3 -
 target/i386/tcg/emit.c.inc       |   17 +
 target/i386/tcg/translate.c      | 1722 +-----------------------------
 5 files changed, 19 insertions(+), 1908 deletions(-)

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 43b32edbfc..76bf20b878 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -297,17 +297,6 @@ static inline int satsw(int x)
 #define FMAXUB(a, b) ((a) > (b)) ? (a) : (b)
 #define FMAXSW(a, b) ((int16_t)(a) > (int16_t)(b)) ? (a) : (b)
 
-#define FAND(a, b) ((a) & (b))
-#define FANDN(a, b) ((~(a)) & (b))
-#define FOR(a, b) ((a) | (b))
-#define FXOR(a, b) ((a) ^ (b))
-
-#define FCMPGTB(a, b) ((int8_t)(a) > (int8_t)(b) ? -1 : 0)
-#define FCMPGTW(a, b) ((int16_t)(a) > (int16_t)(b) ? -1 : 0)
-#define FCMPGTL(a, b) ((int32_t)(a) > (int32_t)(b) ? -1 : 0)
-#define FCMPEQ(a, b) ((a) == (b) ? -1 : 0)
-
-#define FMULLW(a, b) ((a) * (b))
 #define FMULHRW(a, b) (((int16_t)(a) * (int16_t)(b) + 0x8000) >> 16)
 #define FMULHUW(a, b) ((a) * (b) >> 16)
 #define FMULHW(a, b) ((int16_t)(a) * (int16_t)(b) >> 16)
@@ -315,46 +304,6 @@ static inline int satsw(int x)
 #define FAVG(a, b) (((a) + (b) + 1) >> 1)
 #endif
 
-SSE_HELPER_B(helper_paddb, FADD)
-SSE_HELPER_W(helper_paddw, FADD)
-SSE_HELPER_L(helper_paddl, FADD)
-SSE_HELPER_Q(helper_paddq, FADD)
-
-SSE_HELPER_B(helper_psubb, FSUB)
-SSE_HELPER_W(helper_psubw, FSUB)
-SSE_HELPER_L(helper_psubl, FSUB)
-SSE_HELPER_Q(helper_psubq, FSUB)
-
-SSE_HELPER_B(helper_paddusb, FADDUB)
-SSE_HELPER_B(helper_paddsb, FADDSB)
-SSE_HELPER_B(helper_psubusb, FSUBUB)
-SSE_HELPER_B(helper_psubsb, FSUBSB)
-
-SSE_HELPER_W(helper_paddusw, FADDUW)
-SSE_HELPER_W(helper_paddsw, FADDSW)
-SSE_HELPER_W(helper_psubusw, FSUBUW)
-SSE_HELPER_W(helper_psubsw, FSUBSW)
-
-SSE_HELPER_B(helper_pminub, FMINUB)
-SSE_HELPER_B(helper_pmaxub, FMAXUB)
-
-SSE_HELPER_W(helper_pminsw, FMINSW)
-SSE_HELPER_W(helper_pmaxsw, FMAXSW)
-
-SSE_HELPER_Q(helper_pand, FAND)
-SSE_HELPER_Q(helper_pandn, FANDN)
-SSE_HELPER_Q(helper_por, FOR)
-SSE_HELPER_Q(helper_pxor, FXOR)
-
-SSE_HELPER_B(helper_pcmpgtb, FCMPGTB)
-SSE_HELPER_W(helper_pcmpgtw, FCMPGTW)
-SSE_HELPER_L(helper_pcmpgtl, FCMPGTL)
-
-SSE_HELPER_B(helper_pcmpeqb, FCMPEQ)
-SSE_HELPER_W(helper_pcmpeqw, FCMPEQ)
-SSE_HELPER_L(helper_pcmpeql, FCMPEQ)
-
-SSE_HELPER_W(helper_pmullw, FMULLW)
 SSE_HELPER_W(helper_pmulhuw, FMULHUW)
 SSE_HELPER_W(helper_pmulhw, FMULHW)
 
@@ -432,29 +381,6 @@ void glue(helper_maskmov, SUFFIX)(CPUX86State *env, Reg *d, Reg *s,
 }
 #endif
 
-void glue(helper_movl_mm_T0, SUFFIX)(Reg *d, uint32_t val)
-{
-    int i;
-
-    d->L(0) = val;
-    d->L(1) = 0;
-    for (i = 1; i < (1 << SHIFT); i++) {
-        d->Q(i) = 0;
-    }
-}
-
-#ifdef TARGET_X86_64
-void glue(helper_movq_mm_T0, SUFFIX)(Reg *d, uint64_t val)
-{
-    int i;
-
-    d->Q(0) = val;
-    for (i = 1; i < (1 << SHIFT); i++) {
-        d->Q(i) = 0;
-    }
-}
-#endif
-
 #define SHUFFLE4(F, a, b, offset) do {      \
     r0 = a->F((order & 3) + offset);        \
     r1 = a->F(((order >> 2) & 3) + offset); \
@@ -1216,27 +1142,6 @@ uint32_t glue(helper_movmskpd, SUFFIX)(CPUX86State *env, Reg *s)
 
 #endif
 
-uint32_t glue(helper_pmovmskb, SUFFIX)(CPUX86State *env, Reg *s)
-{
-    uint32_t val;
-    int i;
-
-    val = 0;
-    for (i = 0; i < (1 << SHIFT); i++) {
-        uint8_t byte = 0;
-        byte |= (s->B(8 * i + 0) >> 7);
-        byte |= (s->B(8 * i + 1) >> 6) & 0x02;
-        byte |= (s->B(8 * i + 2) >> 5) & 0x04;
-        byte |= (s->B(8 * i + 3) >> 4) & 0x08;
-        byte |= (s->B(8 * i + 4) >> 3) & 0x10;
-        byte |= (s->B(8 * i + 5) >> 2) & 0x20;
-        byte |= (s->B(8 * i + 6) >> 1) & 0x40;
-        byte |= (s->B(8 * i + 7)) & 0x80;
-        val |= byte << (8 * i);
-    }
-    return val;
-}
-
 #define PACK_HELPER_B(name, F) \
 void glue(helper_pack ## name, SUFFIX)(CPUX86State *env,      \
         Reg *d, Reg *v, Reg *s)                               \
@@ -1587,13 +1492,6 @@ void glue(helper_pmaddubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s)
     }
 }
 
-#define FABSB(x) (x > INT8_MAX  ? -(int8_t)x : x)
-#define FABSW(x) (x > INT16_MAX ? -(int16_t)x : x)
-#define FABSL(x) (x > INT32_MAX ? -(int32_t)x : x)
-SSE_HELPER_1(helper_pabsb, B, 8 << SHIFT, FABSB)
-SSE_HELPER_1(helper_pabsw, W, 4 << SHIFT, FABSW)
-SSE_HELPER_1(helper_pabsd, L, 2 << SHIFT, FABSL)
-
 #define FMULHRSW(d, s) (((int16_t) d * (int16_t)s + 0x4000) >> 15)
 SSE_HELPER_W(helper_pmulhrsw, FMULHRSW)
 
@@ -1723,9 +1621,6 @@ void glue(helper_pmuldq, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s)
     }
 }
 
-#define FCMPEQQ(d, s) (d == s ? -1 : 0)
-SSE_HELPER_Q(helper_pcmpeqq, FCMPEQQ)
-
 void glue(helper_packusdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s)
 {
     uint16_t r[8];
@@ -1746,22 +1641,6 @@ void glue(helper_packusdw, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s)
     }
 }
 
-#define FMINSB(d, s) MIN((int8_t)d, (int8_t)s)
-#define FMINSD(d, s) MIN((int32_t)d, (int32_t)s)
-#define FMAXSB(d, s) MAX((int8_t)d, (int8_t)s)
-#define FMAXSD(d, s) MAX((int32_t)d, (int32_t)s)
-SSE_HELPER_B(helper_pminsb, FMINSB)
-SSE_HELPER_L(helper_pminsd, FMINSD)
-SSE_HELPER_W(helper_pminuw, MIN)
-SSE_HELPER_L(helper_pminud, MIN)
-SSE_HELPER_B(helper_pmaxsb, FMAXSB)
-SSE_HELPER_L(helper_pmaxsd, FMAXSD)
-SSE_HELPER_W(helper_pmaxuw, MAX)
-SSE_HELPER_L(helper_pmaxud, MAX)
-
-#define FMULLD(d, s) ((int32_t)d * (int32_t)s)
-SSE_HELPER_L(helper_pmulld, FMULLD)
-
 #if SHIFT == 1
 void glue(helper_phminposuw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
@@ -2042,9 +1921,6 @@ void glue(helper_mpsadbw, SUFFIX)(CPUX86State *env, Reg *d, Reg *v, Reg *s,
 }
 
 /* SSE4.2 op helpers */
-#define FCMPGTQ(d, s) ((int64_t)d > (int64_t)s ? -1 : 0)
-SSE_HELPER_Q(helper_pcmpgtq, FCMPGTQ)
-
 #if SHIFT == 1
 static inline int pcmp_elen(CPUX86State *env, int reg, uint32_t ctrl)
 {
diff --git a/target/i386/ops_sse_header.h b/target/i386/ops_sse_header.h
index 00de6d69f1..2f1f811f9f 100644
--- a/target/i386/ops_sse_header.h
+++ b/target/i386/ops_sse_header.h
@@ -64,46 +64,6 @@ DEF_HELPER_4(glue(pslldq, SUFFIX), void, env, Reg, Reg, Reg)
 #define SSE_HELPER_Q(name, F)\
     DEF_HELPER_4(glue(name, SUFFIX), void, env, Reg, Reg, Reg)
 
-SSE_HELPER_B(paddb, FADD)
-SSE_HELPER_W(paddw, FADD)
-SSE_HELPER_L(paddl, FADD)
-SSE_HELPER_Q(paddq, FADD)
-
-SSE_HELPER_B(psubb, FSUB)
-SSE_HELPER_W(psubw, FSUB)
-SSE_HELPER_L(psubl, FSUB)
-SSE_HELPER_Q(psubq, FSUB)
-
-SSE_HELPER_B(paddusb, FADDUB)
-SSE_HELPER_B(paddsb, FADDSB)
-SSE_HELPER_B(psubusb, FSUBUB)
-SSE_HELPER_B(psubsb, FSUBSB)
-
-SSE_HELPER_W(paddusw, FADDUW)
-SSE_HELPER_W(paddsw, FADDSW)
-SSE_HELPER_W(psubusw, FSUBUW)
-SSE_HELPER_W(psubsw, FSUBSW)
-
-SSE_HELPER_B(pminub, FMINUB)
-SSE_HELPER_B(pmaxub, FMAXUB)
-
-SSE_HELPER_W(pminsw, FMINSW)
-SSE_HELPER_W(pmaxsw, FMAXSW)
-
-SSE_HELPER_Q(pand, FAND)
-SSE_HELPER_Q(pandn, FANDN)
-SSE_HELPER_Q(por, FOR)
-SSE_HELPER_Q(pxor, FXOR)
-
-SSE_HELPER_B(pcmpgtb, FCMPGTB)
-SSE_HELPER_W(pcmpgtw, FCMPGTW)
-SSE_HELPER_L(pcmpgtl, FCMPGTL)
-
-SSE_HELPER_B(pcmpeqb, FCMPEQ)
-SSE_HELPER_W(pcmpeqw, FCMPEQ)
-SSE_HELPER_L(pcmpeql, FCMPEQ)
-
-SSE_HELPER_W(pmullw, FMULLW)
 #if SHIFT == 0
 DEF_HELPER_3(glue(pmulhrw, SUFFIX), void, env, Reg, Reg)
 #endif
@@ -120,10 +80,6 @@ DEF_HELPER_4(glue(psadbw, SUFFIX), void, env, Reg, Reg, Reg)
 #if SHIFT < 2
 DEF_HELPER_4(glue(maskmov, SUFFIX), void, env, Reg, Reg, tl)
 #endif
-DEF_HELPER_2(glue(movl_mm_T0, SUFFIX), void, Reg, i32)
-#ifdef TARGET_X86_64
-DEF_HELPER_2(glue(movq_mm_T0, SUFFIX), void, Reg, i64)
-#endif
 
 #if SHIFT == 0
 DEF_HELPER_3(glue(pshufw, SUFFIX), void, Reg, Reg, int)
@@ -279,7 +235,6 @@ DEF_HELPER_2(glue(movmskps, SUFFIX), i32, env, Reg)
 DEF_HELPER_2(glue(movmskpd, SUFFIX), i32, env, Reg)
 #endif
 
-DEF_HELPER_2(glue(pmovmskb, SUFFIX), i32, env, Reg)
 DEF_HELPER_4(glue(packsswb, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(packuswb, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(packssdw, SUFFIX), void, env, Reg, Reg, Reg)
@@ -326,9 +281,6 @@ DEF_HELPER_4(glue(phaddsw, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(phsubw, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(phsubd, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(phsubsw, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_3(glue(pabsb, SUFFIX), void, env, Reg, Reg)
-DEF_HELPER_3(glue(pabsw, SUFFIX), void, env, Reg, Reg)
-DEF_HELPER_3(glue(pabsd, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_4(glue(pmaddubsw, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(pmulhrsw, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(pshufb, SUFFIX), void, env, Reg, Reg, Reg)
@@ -359,17 +311,7 @@ DEF_HELPER_3(glue(pmovsldup, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_3(glue(pmovshdup, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_3(glue(pmovdldup, SUFFIX), void, env, Reg, Reg)
 DEF_HELPER_4(glue(pmuldq, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pcmpeqq, SUFFIX), void, env, Reg, Reg, Reg)
 DEF_HELPER_4(glue(packusdw, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pminsb, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pminsd, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pminuw, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pminud, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pmaxsb, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pmaxsd, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pmaxuw, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pmaxud, SUFFIX), void, env, Reg, Reg, Reg)
-DEF_HELPER_4(glue(pmulld, SUFFIX), void, env, Reg, Reg, Reg)
 #if SHIFT == 1
 DEF_HELPER_3(glue(phminposuw, SUFFIX), void, env, Reg, Reg)
 #endif
@@ -390,9 +332,6 @@ DEF_HELPER_5(glue(mpsadbw, SUFFIX), void, env, Reg, Reg, Reg, i32)
 #endif
 
 /* SSE4.2 op helpers */
-#if SHIFT >= 1
-DEF_HELPER_4(glue(pcmpgtq, SUFFIX), void, env, Reg, Reg, Reg)
-#endif
 #if SHIFT == 1
 DEF_HELPER_4(glue(pcmpestri, SUFFIX), void, env, Reg, Reg, i32)
 DEF_HELPER_4(glue(pcmpestrm, SUFFIX), void, env, Reg, Reg, i32)
diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc
index e4de3bac0a..64876696f5 100644
--- a/target/i386/tcg/decode-new.c.inc
+++ b/target/i386/tcg/decode-new.c.inc
@@ -1538,9 +1538,6 @@ static void disas_insn_new(DisasContext *s, CPUState *cpu, int b)
     X86DecodedInsn decode;
     X86DecodeFunc decode_func = decode_root;
 
-#ifdef CONFIG_USER_ONLY
-    if (limit) { --limit; }
-#endif
     s->has_modrm = false;
 
  next_byte:
diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc
index ef4e3478fa..31186545c8 100644
--- a/target/i386/tcg/emit.c.inc
+++ b/target/i386/tcg/emit.c.inc
@@ -19,7 +19,24 @@
  * License along with this library; if not, see <http://www.gnu.org/licenses/>.
  */
 
+#define ZMM_OFFSET(reg) offsetof(CPUX86State, xmm_regs[reg])
+
+typedef void (*SSEFunc_i_ep)(TCGv_i32 val, TCGv_ptr env, TCGv_ptr reg);
+typedef void (*SSEFunc_l_ep)(TCGv_i64 val, TCGv_ptr env, TCGv_ptr reg);
 typedef void (*SSEFunc_0_epp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b);
+typedef void (*SSEFunc_0_eppp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
+                               TCGv_ptr reg_c);
+typedef void (*SSEFunc_0_epppp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
+                                TCGv_ptr reg_c, TCGv_ptr reg_d);
+typedef void (*SSEFunc_0_eppi)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
+                               TCGv_i32 val);
+typedef void (*SSEFunc_0_epppi)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
+                                TCGv_ptr reg_c, TCGv_i32 val);
+typedef void (*SSEFunc_0_ppi)(TCGv_ptr reg_a, TCGv_ptr reg_b, TCGv_i32 val);
+typedef void (*SSEFunc_0_pppi)(TCGv_ptr reg_a, TCGv_ptr reg_b, TCGv_ptr reg_c,
+                               TCGv_i32 val);
+typedef void (*SSEFunc_0_eppt)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
+                               TCGv val);
 typedef void (*SSEFunc_0_epppti)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
                                  TCGv_ptr reg_c, TCGv a0, TCGv_i32 scale);
 
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 627d321f00..c00cf0c682 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -128,9 +128,6 @@ typedef struct DisasContext {
     /* TCG local register indexes (only used inside old micro ops) */
     TCGv tmp0;
     TCGv tmp4;
-    TCGv_ptr ptr0;
-    TCGv_ptr ptr1;
-    TCGv_ptr ptr2;
     TCGv_i32 tmp2_i32;
     TCGv_i32 tmp3_i32;
     TCGv_i64 tmp1_i64;
@@ -2871,57 +2868,6 @@ static void gen_sty_env_A0(DisasContext *s, int offset, bool align)
     tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
 }
 
-static inline void gen_op_movo(DisasContext *s, int d_offset, int s_offset)
-{
-    tcg_gen_ld_i64(s->tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_st_i64(s->tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(0)));
-    tcg_gen_ld_i64(s->tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(1)));
-    tcg_gen_st_i64(s->tmp1_i64, cpu_env, d_offset + offsetof(XMMReg, XMM_Q(1)));
-}
-
-static inline void gen_op_movq(DisasContext *s, int d_offset, int s_offset)
-{
-    tcg_gen_ld_i64(s->tmp1_i64, cpu_env, s_offset);
-    tcg_gen_st_i64(s->tmp1_i64, cpu_env, d_offset);
-}
-
-static inline void gen_op_movl(DisasContext *s, int d_offset, int s_offset)
-{
-    tcg_gen_ld_i32(s->tmp2_i32, cpu_env, s_offset);
-    tcg_gen_st_i32(s->tmp2_i32, cpu_env, d_offset);
-}
-
-static inline void gen_op_movq_env_0(DisasContext *s, int d_offset)
-{
-    tcg_gen_movi_i64(s->tmp1_i64, 0);
-    tcg_gen_st_i64(s->tmp1_i64, cpu_env, d_offset);
-}
-
-#define ZMM_OFFSET(reg) offsetof(CPUX86State, xmm_regs[reg])
-#define XMM_OFFSET(reg) offsetof(CPUX86State, xmm_regs[reg].ZMM_X(0))
-
-typedef void (*SSEFunc_i_ep)(TCGv_i32 val, TCGv_ptr env, TCGv_ptr reg);
-typedef void (*SSEFunc_l_ep)(TCGv_i64 val, TCGv_ptr env, TCGv_ptr reg);
-typedef void (*SSEFunc_0_epi)(TCGv_ptr env, TCGv_ptr reg, TCGv_i32 val);
-typedef void (*SSEFunc_0_epl)(TCGv_ptr env, TCGv_ptr reg, TCGv_i64 val);
-typedef void (*SSEFunc_0_epp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b);
-typedef void (*SSEFunc_0_eppp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                               TCGv_ptr reg_c);
-typedef void (*SSEFunc_0_epppp)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                                TCGv_ptr reg_c, TCGv_ptr reg_d);
-typedef void (*SSEFunc_0_eppi)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                               TCGv_i32 val);
-typedef void (*SSEFunc_0_epppi)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                                TCGv_ptr reg_c, TCGv_i32 val);
-typedef void (*SSEFunc_0_ppi)(TCGv_ptr reg_a, TCGv_ptr reg_b, TCGv_i32 val);
-typedef void (*SSEFunc_0_pppi)(TCGv_ptr reg_a, TCGv_ptr reg_b, TCGv_ptr reg_c,
-                               TCGv_i32 val);
-typedef void (*SSEFunc_0_eppt)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                               TCGv val);
-typedef void (*SSEFunc_0_epppt)(TCGv_ptr env, TCGv_ptr reg_a, TCGv_ptr reg_b,
-                                TCGv_ptr reg_c, TCGv val);
-
-static bool first = true; static unsigned long limit;
 #include "decode-new.h"
 #include "emit.c.inc"
 #include "decode-new.c.inc"
@@ -4607,40 +2917,15 @@ static target_ulong disas_insn(DisasContext *s, CPUState *cpu)
 
     prefixes = 0;
 
-    if (first) first = false, limit = getenv("LIMIT") ? atol(getenv("LIMIT")) : -1;
-    bool use_new = true;
-#ifdef CONFIG_USER_ONLY
-    use_new &= limit > 0;
-#endif
  next_byte:
     s->prefix = prefixes;
     b = x86_ldub_code(env, s);
     /* Collect prefixes.  */
     switch (b) {
     default:
-#ifndef CONFIG_USER_ONLY
-        use_new &= b <= limit;
-#endif
-        if (use_new && 0) {
-            disas_insn_new(s, cpu, b);
-            return s->pc;
-        }
         break;
     case 0x0f:
         b = x86_ldub_code(env, s) + 0x100;
-#ifndef CONFIG_USER_ONLY
-        use_new &= b <= limit;
-#endif
-        if (use_new &&
-            (b == 0x138 || b == 0x13a ||
-             (b >= 0x10e && b <= 0x117) ||
-             (b >= 0x128 && b <= 0x12f) ||
-             (b >= 0x150 && b <= 0x17f) ||
-             b == 0x1c2 || (b >= 0x1c4 && b <= 0x1c6) ||
-             (b >= 0x1d0 && b <= 0x1ff))) {
-            disas_insn_new(s, cpu, b + 0x100);
-            return s->pc;
-        }
         break;
     case 0xf3:
         prefixes |= PREFIX_REPZ;
@@ -8470,7 +6755,7 @@ static target_ulong disas_insn(DisasContext *s, CPUState *cpu)
 
         set_cc_op(s, CC_OP_POPCNT);
         break;
-    case 0x110 ... 0x117:
+    case 0x10e ... 0x117:
     case 0x128 ... 0x12f:
     case 0x138 ... 0x13a:
     case 0x150 ... 0x179:
@@ -8478,7 +6763,7 @@ static target_ulong disas_insn(DisasContext *s, CPUState *cpu)
     case 0x1c2:
     case 0x1c4 ... 0x1c6:
     case 0x1d0 ... 0x1fe:
-        gen_sse(env, s, b, pc_start);
+        disas_insn_new(s, cpu, b);
         break;
     default:
         goto unknown_op;
@@ -8635,9 +6920,6 @@ static void i386_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cpu)
     dc->tmp2_i32 = tcg_temp_new_i32();
     dc->tmp3_i32 = tcg_temp_new_i32();
     dc->tmp4 = tcg_temp_new();
-    dc->ptr0 = tcg_temp_new_ptr();
-    dc->ptr1 = tcg_temp_new_ptr();
-    dc->ptr2 = tcg_temp_new_ptr();
     dc->cc_srcT = tcg_temp_local_new();
 }
 
-- 
2.37.2



      parent reply	other threads:[~2022-09-20 23:04 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-20 17:24 [PATCH v2 00/37] target/i386: new decoder + AVX implementation Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 01/37] target/i386: Define XMMReg and access macros, align ZMM registers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 02/37] target/i386: make ldo/sto operations consistent with ldq Paolo Bonzini
2022-09-24 15:00   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 03/37] target/i386: REPZ and REPNZ are mutually exclusive Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 04/37] target/i386: introduce insn_get_addr Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 05/37] target/i386: add core of new i386 decoder Paolo Bonzini
2022-09-24 15:09   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 06/37] target/i386: add ALU load/writeback core Paolo Bonzini
2022-09-24 15:13   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 07/37] target/i386: add CPUID[EAX=7, ECX=0].ECX to DisasContext Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 08/37] target/i386: add CPUID feature checks to new decoder Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 09/37] target/i386: add AVX_EN hflag Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 10/37] target/i386: validate VEX prefixes via the instructions' exception classes Paolo Bonzini
2022-09-24 20:19   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 11/37] target/i386: validate SSE prefixes directly in the decoding table Paolo Bonzini
2022-09-24 20:23   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 12/37] target/i386: move scalar 0F 38 and 0F 3A instruction to new decoder Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 13/37] target/i386: Prepare ops_sse_header.h for 256 bit AVX Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 14/37] target/i386: extend helpers to support VEX.V 3- and 4- operand encodings Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 15/37] target/i386: support operand merging in binary scalar helpers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 16/37] target/i386: provide 3-operand versions of unary " Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 17/37] target/i386: implement additional AVX comparison operators Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 18/37] target/i386: Introduce 256-bit vector helpers Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 19/37] target/i386: reimplement 0x0f 0x60-0x6f, add AVX Paolo Bonzini
2022-09-24 20:31   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 20/37] target/i386: reimplement 0x0f 0xd8-0xdf, 0xe8-0xef, 0xf8-0xff, " Paolo Bonzini
2022-09-24 20:32   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 21/37] target/i386: reimplement 0x0f 0x50-0x5f, " Paolo Bonzini
2022-09-24 20:37   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 22/37] target/i386: reimplement 0x0f 0x78-0x7f, " Paolo Bonzini
2022-09-24 20:43   ` Richard Henderson
2022-09-26  7:24     ` Paolo Bonzini
2022-09-26  7:46       ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 23/37] target/i386: reimplement 0x0f 0x70-0x77, " Paolo Bonzini
2022-09-24 20:53   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 24/37] target/i386: reimplement 0x0f 0xd0-0xd7, 0xe0-0xe7, 0xf0-0xf7, " Paolo Bonzini
2022-09-24 20:56   ` Richard Henderson
2022-09-26  7:56     ` Paolo Bonzini
2022-09-20 17:24 ` [PATCH v2 25/37] target/i386: clarify (un)signedness of immediates from 0F3Ah opcodes Paolo Bonzini
2022-09-24 20:57   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 26/37] target/i386: reimplement 0x0f 0x3a, add AVX Paolo Bonzini
2022-09-24 21:02   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 27/37] target/i386: Use tcg gvec ops for pmovmskb Paolo Bonzini
2022-09-24 21:08   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 28/37] target/i386: reimplement 0x0f 0x38, add AVX Paolo Bonzini
2022-09-24 21:14   ` Richard Henderson
2022-09-20 17:24 ` [PATCH v2 29/37] target/i386: reimplement 0x0f 0xc2, 0xc4-0xc6, " Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 30/37] target/i386: reimplement 0x0f 0x10-0x17, " Paolo Bonzini
2022-09-24 21:16   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 31/37] target/i386: reimplement 0x0f 0x28-0x2f, " Paolo Bonzini
2022-09-24 21:18   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 32/37] target/i386: implement XSAVE and XRSTOR of AVX registers Paolo Bonzini
2022-09-24 21:19   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 33/37] target/i386: implement VLDMXCSR/VSTMXCSR Paolo Bonzini
2022-09-24 21:20   ` Richard Henderson
2022-09-20 17:25 ` [PATCH v2 34/37] target/i386: Enable AVX cpuid bits when using TCG Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 35/37] tests/tcg: extend SSE tests to AVX Paolo Bonzini
2022-09-20 17:25 ` [PATCH v2 36/37] target/i386: move 3DNow to the new decoder Paolo Bonzini
2022-09-24 21:24   ` Richard Henderson
2022-09-20 17:25 ` Paolo Bonzini [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220920172507.95568-38-pbonzini@redhat.com \
    --to=pbonzini@redhat.com \
    --cc=paul@nowt.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).