[Qemu-devel] [PATCH 05/16] target-m68k: Inline addx, subx, negx

[Laurent Vivier <laurent@vivier.eu>]

From: Richard Henderson <rth@twiddle.net>

And add opcodes for 680x0

Signed-off-by: Laurent Vivier <laurent@vivier.eu>
---
 target-m68k/helper.c    |  40 ----------
 target-m68k/helper.h    |   2 -
 target-m68k/translate.c | 196 +++++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 178 insertions(+), 60 deletions(-)

diff --git a/target-m68k/helper.c b/target-m68k/helper.c
index 094a7e5..e838638 100644
--- a/target-m68k/helper.c
+++ b/target-m68k/helper.c
@@ -277,46 +277,6 @@ uint32_t HELPER(sats)(uint32_t val, uint32_t v)
     return val;
 }
 
-uint32_t HELPER(subx_cc)(CPUM68KState *env, uint32_t op1, uint32_t op2)
-{
-    uint32_t res, new_x;
-
-    if (env->cc_x) {
-        new_x = (op1 <= op2);
-        res = op1 - (op2 + 1);
-    } else {
-        new_x = (op1 < op2);
-        res = op1 - op2;
-    }
-    env->cc_x = new_x;
-    env->cc_c = new_x;
-    env->cc_n = res;
-    env->cc_z |= res; /* !Z is sticky */
-    env->cc_v = (res ^ op1) & (op1 ^ op2);
-
-    return res;
-}
-
-uint32_t HELPER(addx_cc)(CPUM68KState *env, uint32_t op1, uint32_t op2)
-{
-    uint32_t res, new_x;
-
-    if (env->cc_x) {
-        res = op1 + op2 + 1;
-        new_x = (res <= op2);
-    } else {
-        res = op1 + op2;
-        new_x = (res < op2);
-    }
-    env->cc_x = new_x;
-    env->cc_c = new_x;
-    env->cc_n = res;
-    env->cc_z |= res; /* !Z is sticky.  */
-    env->cc_v = (res ^ op1) & ~(op1 ^ op2);
-
-    return res;
-}
-
 void HELPER(set_sr)(CPUM68KState *env, uint32_t val)
 {
     env->sr = val & 0xffe0;
diff --git a/target-m68k/helper.h b/target-m68k/helper.h
index c868148..2697e32 100644
--- a/target-m68k/helper.h
+++ b/target-m68k/helper.h
@@ -3,8 +3,6 @@ DEF_HELPER_1(ff1, i32, i32)
 DEF_HELPER_FLAGS_2(sats, TCG_CALL_NO_RWG_SE, i32, i32, i32)
 DEF_HELPER_2(divu, void, env, i32)
 DEF_HELPER_2(divs, void, env, i32)
-DEF_HELPER_3(addx_cc, i32, env, i32, i32)
-DEF_HELPER_3(subx_cc, i32, env, i32, i32)
 DEF_HELPER_3(shl_cc, i32, env, i32, i32)
 DEF_HELPER_3(shr_cc, i32, env, i32, i32)
 DEF_HELPER_3(sar_cc, i32, env, i32, i32)
diff --git a/target-m68k/translate.c b/target-m68k/translate.c
index 05efd29..59d7017 100644
--- a/target-m68k/translate.c
+++ b/target-m68k/translate.c
@@ -1536,11 +1536,44 @@ DISAS_INSN(move)
 
 DISAS_INSN(negx)
 {
-    TCGv reg;
+    TCGv z;
+    TCGv src;
+    TCGv addr;
+    int opsize;
 
-    gen_flush_flags(s);
-    reg = DREG(insn, 0);
-    gen_helper_subx_cc(reg, cpu_env, tcg_const_i32(0), reg);
+    opsize = insn_opsize(insn);
+    SRC_EA(env, src, opsize, 1, &addr);
+
+    gen_flush_flags(s); /* compute old Z */
+
+    /* Perform substract with borrow.
+     * (X, N) =  -(src + X);
+     */
+
+    z = tcg_const_i32(0);
+    tcg_gen_add2_i32(QREG_CC_N, QREG_CC_X, src, z, QREG_CC_X, z);
+    tcg_gen_sub2_i32(QREG_CC_N, QREG_CC_X, z, z, QREG_CC_N, QREG_CC_X);
+    tcg_temp_free(z);
+    gen_ext(QREG_CC_N, QREG_CC_N, opsize, 1);
+
+    tcg_gen_andi_i32(QREG_CC_X, QREG_CC_X, 1);
+
+    /* Compute signed-overflow for negation.  The normal formula for
+     * subtraction is (res ^ src) & (src ^ dest), but with dest==0
+     * this simplies to res & src.
+     */
+
+    tcg_gen_and_i32(QREG_CC_V, QREG_CC_N, src);
+
+    /* Copy the rest of the results into place.  */
+    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_N); /* !Z is sticky */
+    tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);
+
+    set_cc_op(s, CC_OP_FLAGS);
+
+    /* result is in QREG_CC_N */
+
+    DEST_EA(env, insn, opsize, QREG_CC_N, &addr);
 }
 
 DISAS_INSN(lea)
@@ -1975,15 +2008,75 @@ DISAS_INSN(suba)
     tcg_gen_sub_i32(reg, reg, src);
 }
 
-DISAS_INSN(subx)
+static inline void gen_subx(DisasContext *s, TCGv src, TCGv dest, int opsize)
 {
-    TCGv reg;
+    TCGv tmp;
+
+    gen_flush_flags(s); /* compute old Z */
+
+    /* Perform substract with borrow.
+     * (X, N) = dest - (src + X);
+     */
+
+    tmp = tcg_const_i32(0);
+    tcg_gen_add2_i32(QREG_CC_N, QREG_CC_X, src, tmp, QREG_CC_X, tmp);
+    tcg_gen_sub2_i32(QREG_CC_N, QREG_CC_X, dest, tmp, QREG_CC_N, QREG_CC_X);
+    gen_ext(QREG_CC_N, QREG_CC_N, opsize, 1);
+    tcg_gen_andi_i32(QREG_CC_X, QREG_CC_X, 1);
+
+    /* Compute signed-overflow for substract.  */
+
+    tcg_gen_xor_i32(QREG_CC_V, QREG_CC_N, dest);
+    tcg_gen_xor_i32(tmp, dest, src);
+    tcg_gen_and_i32(QREG_CC_V, QREG_CC_V, tmp);
+    tcg_temp_free(tmp);
+
+    /* Copy the rest of the results into place.  */
+    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_N); /* !Z is sticky */
+    tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);
+
+    set_cc_op(s, CC_OP_FLAGS);
+
+    /* result is in QREG_CC_N */
+}
+
+DISAS_INSN(subx_reg)
+{
+    TCGv dest;
     TCGv src;
+    int opsize;
 
-    gen_flush_flags(s);
-    reg = DREG(insn, 9);
-    src = DREG(insn, 0);
-    gen_helper_subx_cc(reg, cpu_env, reg, src);
+    opsize = insn_opsize(insn);
+
+    src = gen_extend(DREG(insn, 0), opsize, 1);
+    dest = gen_extend(DREG(insn, 9), opsize, 1);
+
+    gen_subx(s, src, dest, opsize);
+
+    gen_partset_reg(opsize, DREG(insn, 9), QREG_CC_N);
+}
+
+DISAS_INSN(subx_mem)
+{
+    TCGv src;
+    TCGv addr_src;
+    TCGv dest;
+    TCGv addr_dest;
+    int opsize;
+
+    opsize = insn_opsize(insn);
+
+    addr_src = AREG(insn, 0);
+    tcg_gen_subi_i32(addr_src, addr_src, opsize);
+    src = gen_load(s, opsize, addr_src, 1);
+
+    addr_dest = AREG(insn, 9);
+    tcg_gen_subi_i32(addr_dest, addr_dest, opsize);
+    dest = gen_load(s, opsize, addr_dest, 1);
+
+    gen_subx(s, src, dest, opsize);
+
+    gen_store(s, opsize, addr_dest, QREG_CC_N);
 }
 
 DISAS_INSN(mov3q)
@@ -2110,15 +2203,74 @@ DISAS_INSN(adda)
     tcg_gen_add_i32(reg, reg, src);
 }
 
-DISAS_INSN(addx)
+static inline void gen_addx(DisasContext *s, TCGv src, TCGv dest, int opsize)
 {
-    TCGv reg;
+    TCGv tmp;
+
+    gen_flush_flags(s); /* compute old Z */
+
+    /* Perform addition with carry.
+     * (X, N) = src + dest + X;
+     */
+
+    tmp = tcg_const_i32(0);
+    tcg_gen_add2_i32(QREG_CC_N, QREG_CC_X, QREG_CC_X, tmp, dest, tmp);
+    tcg_gen_add2_i32(QREG_CC_N, QREG_CC_X, QREG_CC_N, QREG_CC_X, src, tmp);
+    gen_ext(QREG_CC_N, QREG_CC_N, opsize, 1);
+
+    /* Compute signed-overflow for addition.  */
+
+    tcg_gen_xor_i32(QREG_CC_V, QREG_CC_N, src);
+    tcg_gen_xor_i32(tmp, dest, src);
+    tcg_gen_andc_i32(QREG_CC_V, QREG_CC_V, tmp);
+    tcg_temp_free(tmp);
+
+    /* Copy the rest of the results into place.  */
+    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_N); /* !Z is sticky */
+    tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);
+
+    set_cc_op(s, CC_OP_FLAGS);
+
+    /* result is in QREG_CC_N */
+}
+
+DISAS_INSN(addx_reg)
+{
+    TCGv dest;
     TCGv src;
+    int opsize;
 
-    gen_flush_flags(s);
-    reg = DREG(insn, 9);
-    src = DREG(insn, 0);
-    gen_helper_addx_cc(reg, cpu_env, reg, src);
+    opsize = insn_opsize(insn);
+
+    dest = gen_extend(DREG(insn, 9), opsize, 1);
+    src = gen_extend(DREG(insn, 0), opsize, 1);
+
+    gen_addx(s, src, dest, opsize);
+
+    gen_partset_reg(opsize, DREG(insn, 9), QREG_CC_N);
+}
+
+DISAS_INSN(addx_mem)
+{
+    TCGv src;
+    TCGv addr_src;
+    TCGv dest;
+    TCGv addr_dest;
+    int opsize;
+
+    opsize = insn_opsize(insn);
+
+    addr_src = AREG(insn, 0);
+    tcg_gen_subi_i32(addr_src, addr_src, opsize_bytes(opsize));
+    src = gen_load(s, opsize, addr_src, 1);
+
+    addr_dest = AREG(insn, 9);
+    tcg_gen_subi_i32(addr_dest, addr_dest, opsize_bytes(opsize));
+    dest = gen_load(s, opsize, addr_dest, 1);
+
+    gen_addx(s, src, dest, opsize);
+
+    gen_store(s, opsize, addr_dest, QREG_CC_N);
 }
 
 /* TODO: This could be implemented without helper functions.  */
@@ -3117,6 +3269,8 @@ void register_m68k_insns (CPUM68KState *env)
     BASE(move,      3000, f000);
     INSN(strldsr,   40e7, ffff, CF_ISA_APLUSC);
     INSN(negx,      4080, fff8, CF_ISA_A);
+    INSN(negx,      4000, ff00, M68000);
+    INSN(undef,     40c0, ffc0, M68000);
     INSN(move_from_sr, 40c0, fff8, CF_ISA_A);
     INSN(move_from_sr, 40c0, ffc0, M68000);
     BASE(lea,       41c0, f1c0);
@@ -3187,7 +3341,10 @@ void register_m68k_insns (CPUM68KState *env)
     BASE(or,        8000, f000);
     BASE(divw,      80c0, f0c0);
     BASE(addsub,    9000, f000);
-    INSN(subx,      9180, f1f8, CF_ISA_A);
+    INSN(undef,     90c0, f0c0, CF_ISA_A);
+    INSN(subx_reg,  9180, f1f8, CF_ISA_A);
+    INSN(subx_reg,  9100, f138, M68000);
+    INSN(subx_mem,  9108, f138, M68000);
     INSN(suba,      91c0, f1c0, CF_ISA_A);
 
     BASE(undef_mac, a000, f000);
@@ -3222,7 +3379,10 @@ void register_m68k_insns (CPUM68KState *env)
     INSN(exg,       c188, f1f8, M68000);
     BASE(mulw,      c0c0, f0c0);
     BASE(addsub,    d000, f000);
-    INSN(addx,      d180, f1f8, CF_ISA_A);
+    INSN(undef,     d0c0, f0c0, CF_ISA_A);
+    INSN(addx_reg,      d180, f1f8, CF_ISA_A);
+    INSN(addx_reg,  d100, f138, M68000);
+    INSN(addx_mem,  d108, f138, M68000);
     INSN(adda,      d1c0, f1c0, CF_ISA_A);
     INSN(adda,      d0c0, f0c0, M68000);
     INSN(shift_im,  e080, f0f0, CF_ISA_A);
-- 
2.7.4