[v3,20/30] target/s390x: improve MOVE LONG and MOVE LONG EXTENDED

diff --git a/target/s390x/mem_helper.c b/target/s390x/mem_helper.c
index 6dfa087ff1..cb0ec3eebf 100644
--- a/target/s390x/mem_helper.c
+++ b/target/s390x/mem_helper.c
@@ -576,49 +576,60 @@  void HELPER(stam)(CPUS390XState *env, uint32_t r1, uint64_t a2, uint32_t r3)
     }
 }
 
-/* move long */
-uint32_t HELPER(mvcl)(CPUS390XState *env, uint32_t r1, uint32_t r2)
+/* move long helper */
+static inline uint32_t do_mvcl(CPUS390XState *env,
+                               uint64_t *dest, uint64_t *destlen,
+                               uint64_t *src, uint64_t *srclen,
+                               uint8_t pad, uintptr_t ra)
 {
-    uintptr_t ra = GETPC();
-    uint64_t destlen = env->regs[r1 + 1] & 0xffffff;
-    uint64_t dest = get_address(env, r1);
-    uint64_t srclen = env->regs[r2 + 1] & 0xffffff;
-    uint64_t src = get_address(env, r2);
-    uint8_t pad = env->regs[r2 + 1] >> 24;
-    uint8_t v;
+    uint64_t len = MIN(*srclen, *destlen);
     uint32_t cc;
 
-    if (destlen == srclen) {
+    if (*destlen == *srclen) {
         cc = 0;
-    } else if (destlen < srclen) {
+    } else if (*destlen < *srclen) {
         cc = 1;
     } else {
         cc = 2;
     }
 
-    if (srclen > destlen) {
-        srclen = destlen;
-    }
+    /* Copy the src array */
+    fast_memmove(env, *dest, *src, len, ra);
+    *src += len;
+    *srclen -= len;
+    *dest += len;
+    *destlen -= len;
 
-    for (; destlen && srclen; src++, dest++, destlen--, srclen--) {
-        v = cpu_ldub_data_ra(env, src, ra);
-        cpu_stb_data_ra(env, dest, v, ra);
-    }
+    /* Pad the remaining area */
+    fast_memset(env, *dest, pad, *destlen, ra);
+    *dest += *destlen;
+    *destlen = 0;
 
-    for (; destlen; dest++, destlen--) {
-        cpu_stb_data_ra(env, dest, pad, ra);
-    }
+    return cc;
+}
 
-    env->regs[r1 + 1] = destlen;
-    /* can't use srclen here, we trunc'ed it */
-    env->regs[r2 + 1] -= src - env->regs[r2];
+/* move long */
+uint32_t HELPER(mvcl)(CPUS390XState *env, uint32_t r1, uint32_t r2)
+{
+    uintptr_t ra = GETPC();
+    uint64_t destlen = env->regs[r1 + 1] & 0xffffff;
+    uint64_t dest = get_address(env, r1);
+    uint64_t srclen = env->regs[r2 + 1] & 0xffffff;
+    uint64_t src = get_address(env, r2);
+    uint8_t pad = env->regs[r2 + 1] >> 24;
+    uint32_t cc;
+
+    cc = do_mvcl(env, &dest, &destlen, &src, &srclen, pad, ra);
+
+    env->regs[r1 + 1] = deposit64(env->regs[r1 + 1], 0, 24, destlen);
+    env->regs[r2 + 1] = deposit64(env->regs[r2 + 1], 0, 24, srclen);
     set_address(env, r1, dest);
     set_address(env, r2, src);
 
     return cc;
 }
 
-/* move long extended another memcopy insn with more bells and whistles */
+/* move long extended */
 uint32_t HELPER(mvcle)(CPUS390XState *env, uint32_t r1, uint64_t a2,
                        uint32_t r3)
 {
@@ -627,34 +638,13 @@  uint32_t HELPER(mvcle)(CPUS390XState *env, uint32_t r1, uint64_t a2,
     uint64_t dest = get_address(env, r1);
     uint64_t srclen = get_length(env, r3 + 1);
     uint64_t src = get_address(env, r3);
-    uint8_t pad = a2 & 0xff;
-    uint8_t v;
+    uint8_t pad = a2;
     uint32_t cc;
 
-    if (destlen == srclen) {
-        cc = 0;
-    } else if (destlen < srclen) {
-        cc = 1;
-    } else {
-        cc = 2;
-    }
-
-    if (srclen > destlen) {
-        srclen = destlen;
-    }
-
-    for (; destlen && srclen; src++, dest++, destlen--, srclen--) {
-        v = cpu_ldub_data_ra(env, src, ra);
-        cpu_stb_data_ra(env, dest, v, ra);
-    }
-
-    for (; destlen; dest++, destlen--) {
-        cpu_stb_data_ra(env, dest, pad, ra);
-    }
+    cc = do_mvcl(env, &dest, &destlen, &src, &srclen, pad, ra);
 
-    set_length(env, r1 + 1 , destlen);
-    /* can't use srclen here, we trunc'ed it */
-    set_length(env, r3 + 1, env->regs[r3 + 1] - src - env->regs[r3]);
+    set_length(env, r1 + 1, destlen);
+    set_length(env, r3 + 1, srclen);
     set_address(env, r1, dest);
     set_address(env, r3, src);
 
diff --git a/target/s390x/translate.c b/target/s390x/translate.c
index 999d716f61..729d25d8f8 100644
--- a/target/s390x/translate.c
+++ b/target/s390x/translate.c
@@ -2981,22 +2981,42 @@  static ExitStatus op_mvcin(DisasContext *s, DisasOps *o)
 
 static ExitStatus op_mvcl(DisasContext *s, DisasOps *o)
 {
-    TCGv_i32 r1 = tcg_const_i32(get_field(s->fields, r1));
-    TCGv_i32 r2 = tcg_const_i32(get_field(s->fields, r2));
-    gen_helper_mvcl(cc_op, cpu_env, r1, r2);
-    tcg_temp_free_i32(r1);
-    tcg_temp_free_i32(r2);
+    int r1 = get_field(s->fields, r1);
+    int r2 = get_field(s->fields, r2);
+    TCGv_i32 t1, t2;
+
+    /* r1 and r2 must be even.  */
+    if (r1 & 1 || r2 & 1) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return EXIT_NORETURN;
+    }
+
+    t1 = tcg_const_i32(r1);
+    t2 = tcg_const_i32(r2);
+    gen_helper_mvcl(cc_op, cpu_env, t1, t2);
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
     set_cc_static(s);
     return NO_EXIT;
 }
 
 static ExitStatus op_mvcle(DisasContext *s, DisasOps *o)
 {
-    TCGv_i32 r1 = tcg_const_i32(get_field(s->fields, r1));
-    TCGv_i32 r3 = tcg_const_i32(get_field(s->fields, r3));
-    gen_helper_mvcle(cc_op, cpu_env, r1, o->in2, r3);
-    tcg_temp_free_i32(r1);
-    tcg_temp_free_i32(r3);
+    int r1 = get_field(s->fields, r1);
+    int r3 = get_field(s->fields, r3);
+    TCGv_i32 t1, t3;
+
+    /* r1 and r3 must be even.  */
+    if (r1 & 1 || r3 & 1) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return EXIT_NORETURN;
+    }
+
+    t1 = tcg_const_i32(r1);
+    t3 = tcg_const_i32(r3);
+    gen_helper_mvcle(cc_op, cpu_env, t1, o->in2, t3);
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t3);
     set_cc_static(s);
     return NO_EXIT;
 }