target/s390x: Use tcg_gen_qemu_{ld,st}_i128 for LPQ, STPQ

No need to roll our own, as this is now provided by tcg.
This was the last use of retxl, so remove that too.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

5 files changed, 9 insertions, 91 deletions

diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h
index c47e7adcb1..f130c29f83 100644
--- a/target/s390x/cpu.h
+++ b/target/s390x/cpu.h
@@ -76,9 +76,6 @@ struct CPUArchState {
 
     float_status fpu_status; /* passed to softfloat lib */
 
-    /* The low part of a 128-bit return, or remainder of a divide.  */
-    uint64_t retxl;
-
     PSW psw;
 
     S390CrashReason crash_reason;
diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 341bc51ec2..7529e725f2 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -108,10 +108,6 @@ DEF_HELPER_FLAGS_2(sfas, TCG_CALL_NO_WG, void, env, i64)
 DEF_HELPER_FLAGS_2(srnm, TCG_CALL_NO_WG, void, env, i64)
 DEF_HELPER_FLAGS_1(popcnt, TCG_CALL_NO_RWG_SE, i64, i64)
 DEF_HELPER_2(stfle, i32, env, i64)
-DEF_HELPER_FLAGS_2(lpq, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_2(lpq_parallel, TCG_CALL_NO_WG, i64, env, i64)
-DEF_HELPER_FLAGS_4(stpq, TCG_CALL_NO_WG, void, env, i64, i64, i64)
-DEF_HELPER_FLAGS_4(stpq_parallel, TCG_CALL_NO_WG, void, env, i64, i64, i64)
 DEF_HELPER_4(mvcos, i32, env, i64, i64, i64)
 DEF_HELPER_4(cu12, i32, env, i32, i32, i32)
 DEF_HELPER_4(cu14, i32, env, i32, i32, i32)
diff --git a/target/s390x/tcg/insn-data.h.inc b/target/s390x/tcg/insn-data.h.inc
index 1f1ac742a9..bcc70d99ba 100644
--- a/target/s390x/tcg/insn-data.h.inc
+++ b/target/s390x/tcg/insn-data.h.inc
@@ -570,7 +570,7 @@
     D(0xc804, LPD,     SSF,   ILA, 0, 0, new_P, r3_P32, lpd, 0, MO_TEUL)
     D(0xc805, LPDG,    SSF,   ILA, 0, 0, new_P, r3_P64, lpd, 0, MO_TEUQ)
 /* LOAD PAIR FROM QUADWORD */
-    C(0xe38f, LPQ,     RXY_a, Z,   0, a2, r1_P, 0, lpq, 0)
+    C(0xe38f, LPQ,     RXY_a, Z,   0, a2, 0, r1_D64, lpq, 0)
 /* LOAD POSITIVE */
     C(0x1000, LPR,     RR_a,  Z,   0, r2_32s, new, r1_32, abs, abs32)
     C(0xb900, LPGR,    RRE,   Z,   0, r2, r1, 0, abs, abs64)
diff --git a/target/s390x/tcg/mem_helper.c b/target/s390x/tcg/mem_helper.c
index 8b58b8d88d..0e0d66b3b6 100644
--- a/target/s390x/tcg/mem_helper.c
+++ b/target/s390x/tcg/mem_helper.c
@@ -2398,67 +2398,6 @@ uint64_t HELPER(lra)(CPUS390XState *env, uint64_t addr)
 }
 #endif
 
-/* load pair from quadword */
-uint64_t HELPER(lpq)(CPUS390XState *env, uint64_t addr)
-{
-    uintptr_t ra = GETPC();
-    uint64_t hi, lo;
-
-    check_alignment(env, addr, 16, ra);
-    hi = cpu_ldq_data_ra(env, addr + 0, ra);
-    lo = cpu_ldq_data_ra(env, addr + 8, ra);
-
-    env->retxl = lo;
-    return hi;
-}
-
-uint64_t HELPER(lpq_parallel)(CPUS390XState *env, uint64_t addr)
-{
-    uintptr_t ra = GETPC();
-    uint64_t hi, lo;
-    int mem_idx;
-    MemOpIdx oi;
-    Int128 v;
-
-    assert(HAVE_ATOMIC128);
-
-    mem_idx = cpu_mmu_index(env, false);
-    oi = make_memop_idx(MO_TEUQ | MO_ALIGN_16, mem_idx);
-    v = cpu_atomic_ldo_be_mmu(env, addr, oi, ra);
-    hi = int128_gethi(v);
-    lo = int128_getlo(v);
-
-    env->retxl = lo;
-    return hi;
-}
-
-/* store pair to quadword */
-void HELPER(stpq)(CPUS390XState *env, uint64_t addr,
-                  uint64_t low, uint64_t high)
-{
-    uintptr_t ra = GETPC();
-
-    check_alignment(env, addr, 16, ra);
-    cpu_stq_data_ra(env, addr + 0, high, ra);
-    cpu_stq_data_ra(env, addr + 8, low, ra);
-}
-
-void HELPER(stpq_parallel)(CPUS390XState *env, uint64_t addr,
-                           uint64_t low, uint64_t high)
-{
-    uintptr_t ra = GETPC();
-    int mem_idx;
-    MemOpIdx oi;
-    Int128 v;
-
-    assert(HAVE_ATOMIC128);
-
-    mem_idx = cpu_mmu_index(env, false);
-    oi = make_memop_idx(MO_TEUQ | MO_ALIGN_16, mem_idx);
-    v = int128_make128(low, high);
-    cpu_atomic_sto_be_mmu(env, addr, v, oi, ra);
-}
-
 /* Execute instruction.  This instruction executes an insn modified with
    the contents of r1.  It does not change the executed instruction in memory;
    it does not change the program counter.
diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c
index d6670e6a87..3eb3708d55 100644
--- a/target/s390x/tcg/translate.c
+++ b/target/s390x/tcg/translate.c
@@ -335,11 +335,6 @@ static void store_freg32_i64(int reg, TCGv_i64 v)
     tcg_gen_st32_i64(v, cpu_env, freg32_offset(reg));
 }
 
-static void return_low128(TCGv_i64 dest)
-{
-    tcg_gen_ld_i64(dest, cpu_env, offsetof(CPUS390XState, retxl));
-}
-
 static void update_psw_addr(DisasContext *s)
 {
     /* psw.addr */
@@ -3130,15 +3125,9 @@ static DisasJumpType op_lpd(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_lpq(DisasContext *s, DisasOps *o)
 {
-    if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) {
-        gen_helper_lpq(o->out, cpu_env, o->in2);
-    } else if (HAVE_ATOMIC128) {
-        gen_helper_lpq_parallel(o->out, cpu_env, o->in2);
-    } else {
-        gen_helper_exit_atomic(cpu_env);
-        return DISAS_NORETURN;
-    }
-    return_low128(o->out2);
+    o->out_128 = tcg_temp_new_i128();
+    tcg_gen_qemu_ld_i128(o->out_128, o->in2, get_mem_index(s),
+                         MO_TE | MO_128 | MO_ALIGN);
     return DISAS_NEXT;
 }
 
@@ -4533,14 +4522,11 @@ static DisasJumpType op_stmh(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_stpq(DisasContext *s, DisasOps *o)
 {
-    if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) {
-        gen_helper_stpq(cpu_env, o->in2, o->out2, o->out);
-    } else if (HAVE_ATOMIC128) {
-        gen_helper_stpq_parallel(cpu_env, o->in2, o->out2, o->out);
-    } else {
-        gen_helper_exit_atomic(cpu_env);
-        return DISAS_NORETURN;
-    }
+    TCGv_i128 t16 = tcg_temp_new_i128();
+
+    tcg_gen_concat_i64_i128(t16, o->out2, o->out);
+    tcg_gen_qemu_st_i128(t16, o->in2, get_mem_index(s),
+                         MO_TE | MO_128 | MO_ALIGN);
     return DISAS_NEXT;
 }