target-arm: Fix garbage collection of temporaries in Neon emulation.

Fix garbage collection of temporaries in Neon emulation.

Signed-off-by: Christophe Lyon <christophe.lyon@st.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

diff --git a/target-arm/translate.c b/target-arm/translate.c
index f445c871105a0df0030d8bf8926967ee035489bc..41cbb96ab03d92c293d4ce56ba4a83c5c10d6faa 100644 (file)
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -4183,6 +4183,13 @@ static inline void gen_neon_mull(TCGv_i64 dest, TCGv a, TCGv b, int size, int u)
         break;
     default: abort();
     }
+
+    /* gen_helper_neon_mull_[su]{8|16} do not free their parameters.
+       Don't forget to clean them now.  */
+    if (size < 2) {
+      dead_tmp(a);
+      dead_tmp(b);
+    }
 }
 
 /* Translate a NEON data processing instruction.  Return nonzero if the
@@ -4847,7 +4854,7 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                 if (size == 3) {
                     tcg_temp_free_i64(tmp64);
                 } else {
-                    dead_tmp(tmp2);
+                    tcg_temp_free_i32(tmp2);
                 }
             } else if (op == 10) {
                 /* VSHLL */
@@ -5083,8 +5090,6 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                     case 8: case 9: case 10: case 11: case 12: case 13:
                         /* VMLAL, VQDMLAL, VMLSL, VQDMLSL, VMULL, VQDMULL */
                         gen_neon_mull(cpu_V0, tmp, tmp2, size, u);
-                        dead_tmp(tmp2);
-                        dead_tmp(tmp);
                         break;
                     case 14: /* Polynomial VMULL */
                         cpu_abort(env, "Polynomial VMULL not implemented");
@@ -5235,6 +5240,10 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                         return 1;
 
                     tmp2 = neon_get_scalar(size, rm);
+                    /* We need a copy of tmp2 because gen_neon_mull
+                     * deletes it during pass 0.  */
+                    tmp4 = new_tmp();
+                    tcg_gen_mov_i32(tmp4, tmp2);
                     tmp3 = neon_load_reg(rn, 1);
 
                     for (pass = 0; pass < 2; pass++) {
@@ -5242,9 +5251,9 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                             tmp = neon_load_reg(rn, 0);
                         } else {
                             tmp = tmp3;
+                            tmp2 = tmp4;
                         }
                         gen_neon_mull(cpu_V0, tmp, tmp2, size, u);
-                        dead_tmp(tmp);
                         if (op == 6 || op == 7) {
                             gen_neon_negl(cpu_V0, size);
                         }
@@ -5271,7 +5280,6 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                         neon_store_reg64(cpu_V0, rd + pass);
                     }
 
-                    dead_tmp(tmp2);
 
                     break;
                 default: /* 14 and 15 are RESERVED */