target/s390x: Improve ADD LOGICAL WITH CARRY

Now that ADD LOGICAL outputs carry, we can use that as input directly.
It also means we can re-use CC_OP_ADDU and produce an output carry
directly from ADD LOGICAL WITH CARRY.

Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20201214221356.68039-3-richard.henderson@linaro.org>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>

target/s390x/cc_helper.c

@@ -144,16 +144,6 @@ static uint32_t cc_calc_add_64(int64_t a1, int64_t a2, int64_t ar)
     }
 }
 
-static uint32_t cc_calc_addc_64(uint64_t a1, uint64_t a2, uint64_t ar)
-{
-    /* Recover a2 + carry_in.  */
-    uint64_t a2c = ar - a1;
-    /* Check for a2+carry_in overflow, then a1+a2c overflow.  */
-    int carry_out = (a2c < a2) || (ar < a1);
-
-    return (ar != 0) + 2 * carry_out;
-}
-
 static uint32_t cc_calc_sub_64(int64_t a1, int64_t a2, int64_t ar)
 {
     if ((a1 > 0 && a2 < 0 && ar < 0) || (a1 < 0 && a2 > 0 && ar > 0)) {
@@ -240,16 +230,6 @@ static uint32_t cc_calc_add_32(int32_t a1, int32_t a2, int32_t ar)
     }
 }
 
-static uint32_t cc_calc_addc_32(uint32_t a1, uint32_t a2, uint32_t ar)
-{
-    /* Recover a2 + carry_in.  */
-    uint32_t a2c = ar - a1;
-    /* Check for a2+carry_in overflow, then a1+a2c overflow.  */
-    int carry_out = (a2c < a2) || (ar < a1);
-
-    return (ar != 0) + 2 * carry_out;
-}
-
 static uint32_t cc_calc_sub_32(int32_t a1, int32_t a2, int32_t ar)
 {
     if ((a1 > 0 && a2 < 0 && ar < 0) || (a1 < 0 && a2 > 0 && ar > 0)) {
@@ -485,9 +465,6 @@ static uint32_t do_calc_cc(CPUS390XState *env, uint32_t cc_op,
     case CC_OP_ADD_64:
         r =  cc_calc_add_64(src, dst, vr);
         break;
-    case CC_OP_ADDC_64:
-        r =  cc_calc_addc_64(src, dst, vr);
-        break;
     case CC_OP_SUB_64:
         r =  cc_calc_sub_64(src, dst, vr);
         break;
@@ -513,9 +490,6 @@ static uint32_t do_calc_cc(CPUS390XState *env, uint32_t cc_op,
     case CC_OP_ADD_32:
         r =  cc_calc_add_32(src, dst, vr);
         break;
-    case CC_OP_ADDC_32:
-        r =  cc_calc_addc_32(src, dst, vr);
-        break;
     case CC_OP_SUB_32:
         r =  cc_calc_sub_32(src, dst, vr);
         break;

target/s390x/helper.c

@@ -403,14 +403,12 @@ const char *cc_name(enum cc_op cc_op)
         [CC_OP_LTGT0_32]  = "CC_OP_LTGT0_32",
         [CC_OP_LTGT0_64]  = "CC_OP_LTGT0_64",
         [CC_OP_ADD_64]    = "CC_OP_ADD_64",
-        [CC_OP_ADDC_64]   = "CC_OP_ADDC_64",
         [CC_OP_SUB_64]    = "CC_OP_SUB_64",
         [CC_OP_SUBU_64]   = "CC_OP_SUBU_64",
         [CC_OP_SUBB_64]   = "CC_OP_SUBB_64",
         [CC_OP_ABS_64]    = "CC_OP_ABS_64",
         [CC_OP_NABS_64]   = "CC_OP_NABS_64",
         [CC_OP_ADD_32]    = "CC_OP_ADD_32",
-        [CC_OP_ADDC_32]   = "CC_OP_ADDC_32",
         [CC_OP_SUB_32]    = "CC_OP_SUB_32",
         [CC_OP_SUBU_32]   = "CC_OP_SUBU_32",
         [CC_OP_SUBB_32]   = "CC_OP_SUBB_32",

target/s390x/insn-data.def

@@ -82,10 +82,10 @@
     C(0xcc0a, ALSIH,   RIL_a, HW,  r1_sr32, i2_32u, new, r1_32h, add, addu32)
     C(0xcc0b, ALSIHN,  RIL_a, HW,  r1_sr32, i2_32u, new, r1_32h, add, 0)
 /* ADD LOGICAL WITH CARRY */
-    C(0xb998, ALCR,    RRE,   Z,   r1, r2, new, r1_32, addc, addc32)
+    C(0xb998, ALCR,    RRE,   Z,   r1_32u, r2_32u, new, r1_32, addc32, addu32)
-    C(0xb988, ALCGR,   RRE,   Z,   r1, r2, r1, 0, addc, addc64)
+    C(0xb988, ALCGR,   RRE,   Z,   r1, r2, r1, 0, addc64, addu64)
-    C(0xe398, ALC,     RXY_a, Z,   r1, m2_32u, new, r1_32, addc, addc32)
+    C(0xe398, ALC,     RXY_a, Z,   r1_32u, m2_32u, new, r1_32, addc32, addu32)
-    C(0xe388, ALCG,    RXY_a, Z,   r1, m2_64, r1, 0, addc, addc64)
+    C(0xe388, ALCG,    RXY_a, Z,   r1, m2_64, r1, 0, addc64, addu64)
 
 /* AND */
     C(0x1400, NR,      RR_a,  Z,   r1, r2, new, r1_32, and, nz32)

target/s390x/internal.h

@@ -170,7 +170,6 @@ enum cc_op {
     CC_OP_LTGT0_64,             /* signed less/greater than 0 (64bit) */
 
     CC_OP_ADD_64,               /* overflow on add (64bit) */
-    CC_OP_ADDC_64,              /* overflow on unsigned add-carry (64bit) */
     CC_OP_SUB_64,               /* overflow on subtraction (64bit) */
     CC_OP_SUBU_64,              /* overflow on unsigned subtraction (64bit) */
     CC_OP_SUBB_64,              /* overflow on unsigned sub-borrow (64bit) */
@@ -179,7 +178,6 @@ enum cc_op {
     CC_OP_MULS_64,              /* overflow on signed multiply (64bit) */
 
     CC_OP_ADD_32,               /* overflow on add (32bit) */
-    CC_OP_ADDC_32,              /* overflow on unsigned add-carry (32bit) */
     CC_OP_SUB_32,               /* overflow on subtraction (32bit) */
     CC_OP_SUBU_32,              /* overflow on unsigned subtraction (32bit) */
     CC_OP_SUBB_32,              /* overflow on unsigned sub-borrow (32bit) */

target/s390x/translate.c

@@ -600,12 +600,10 @@ static void gen_op_calc_cc(DisasContext *s)
         dummy = tcg_const_i64(0);
         /* FALLTHRU */
     case CC_OP_ADD_64:
-    case CC_OP_ADDC_64:
     case CC_OP_SUB_64:
     case CC_OP_SUBU_64:
     case CC_OP_SUBB_64:
     case CC_OP_ADD_32:
-    case CC_OP_ADDC_32:
     case CC_OP_SUB_32:
     case CC_OP_SUBU_32:
     case CC_OP_SUBB_32:
@@ -665,12 +663,10 @@ static void gen_op_calc_cc(DisasContext *s)
         gen_helper_calc_cc(cc_op, cpu_env, local_cc_op, cc_src, cc_dst, dummy);
         break;
     case CC_OP_ADD_64:
-    case CC_OP_ADDC_64:
     case CC_OP_SUB_64:
     case CC_OP_SUBU_64:
     case CC_OP_SUBB_64:
     case CC_OP_ADD_32:
-    case CC_OP_ADDC_32:
     case CC_OP_SUB_32:
     case CC_OP_SUBU_32:
     case CC_OP_SUBB_32:
@@ -1443,30 +1439,41 @@ static DisasJumpType op_addu64(DisasContext *s, DisasOps *o)
     return DISAS_NEXT;
 }
 
-static DisasJumpType op_addc(DisasContext *s, DisasOps *o)
+/* Compute carry into cc_src. */
+static void compute_carry(DisasContext *s)
 {
-    DisasCompare cmp;
+    switch (s->cc_op) {
-    TCGv_i64 carry;
+    case CC_OP_ADDU:
-
+        /* The carry value is already in cc_src (1,0). */
-    tcg_gen_add_i64(o->out, o->in1, o->in2);
+        break;
-
+    default:
-    /* The carry flag is the msb of CC, therefore the branch mask that would
+        gen_op_calc_cc(s);
-       create that comparison is 3.  Feeding the generated comparison to
+        /* fall through */
-       setcond produces the carry flag that we desire.  */
+    case CC_OP_STATIC:
-    disas_jcc(s, &cmp, 3);
+        /* The carry flag is the msb of CC; compute into cc_src. */
-    carry = tcg_temp_new_i64();
+        tcg_gen_extu_i32_i64(cc_src, cc_op);
-    if (cmp.is_64) {
+        tcg_gen_shri_i64(cc_src, cc_src, 1);
-        tcg_gen_setcond_i64(cmp.cond, carry, cmp.u.s64.a, cmp.u.s64.b);
+        break;
-    } else {
-        TCGv_i32 t = tcg_temp_new_i32();
-        tcg_gen_setcond_i32(cmp.cond, t, cmp.u.s32.a, cmp.u.s32.b);
-        tcg_gen_extu_i32_i64(carry, t);
-        tcg_temp_free_i32(t);
     }
-    free_compare(&cmp);
+}
+
+static DisasJumpType op_addc32(DisasContext *s, DisasOps *o)
+{
+    compute_carry(s);
+    tcg_gen_add_i64(o->out, o->in1, o->in2);
+    tcg_gen_add_i64(o->out, o->out, cc_src);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_addc64(DisasContext *s, DisasOps *o)
+{
+    compute_carry(s);
+
+    TCGv_i64 zero = tcg_const_i64(0);
+    tcg_gen_add2_i64(o->out, cc_src, o->in1, zero, cc_src, zero);
+    tcg_gen_add2_i64(o->out, cc_src, o->out, cc_src, o->in2, zero);
+    tcg_temp_free_i64(zero);
 
-    tcg_gen_add_i64(o->out, o->out, carry);
-    tcg_temp_free_i64(carry);
     return DISAS_NEXT;
 }
 
@@ -5217,16 +5224,6 @@ static void cout_addu64(DisasContext *s, DisasOps *o)
     gen_op_update2_cc_i64(s, CC_OP_ADDU, cc_src, o->out);
 }
 
-static void cout_addc32(DisasContext *s, DisasOps *o)
-{
-    gen_op_update3_cc_i64(s, CC_OP_ADDC_32, o->in1, o->in2, o->out);
-}
-
-static void cout_addc64(DisasContext *s, DisasOps *o)
-{
-    gen_op_update3_cc_i64(s, CC_OP_ADDC_64, o->in1, o->in2, o->out);
-}
-
 static void cout_cmps32(DisasContext *s, DisasOps *o)
 {
     gen_op_update2_cc_i64(s, CC_OP_LTGT_32, o->in1, o->in2);