target/arm: Use finalize_memop for aa64 fpr load/store

For 128-bit load/store, use 16-byte alignment.  This
requires that we perform the two operations in the
correct order so that we generate the alignment fault
before modifying memory.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210419202257.161730-27-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 26 insertions, 16 deletions

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index f2995d2b74..b90d6880e7 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -963,25 +963,33 @@ static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
 static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
 {
     /* This writes the bottom N bits of a 128 bit wide vector to memory */
-    TCGv_i64 tmp = tcg_temp_new_i64();
-    tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(s, srcidx, MO_64));
+    TCGv_i64 tmplo = tcg_temp_new_i64();
+    MemOp mop;
+
+    tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64));
+
     if (size < 4) {
-        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s),
-                            s->be_data + size);
+        mop = finalize_memop(s, size);
+        tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
         bool be = s->be_data == MO_BE;
         TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
+        TCGv_i64 tmphi = tcg_temp_new_i64();
+
+        tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx));
 
+        mop = s->be_data | MO_Q;
+        tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
+                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
         tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_st_i64(tmp, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
-                            s->be_data | MO_Q);
-        tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(s, srcidx));
-        tcg_gen_qemu_st_i64(tmp, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
-                            s->be_data | MO_Q);
+        tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr,
+                            get_mem_index(s), mop);
+
         tcg_temp_free_i64(tcg_hiaddr);
+        tcg_temp_free_i64(tmphi);
     }
 
-    tcg_temp_free_i64(tmp);
+    tcg_temp_free_i64(tmplo);
 }
 
 /*
@@ -992,10 +1000,11 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
     /* This always zero-extends and writes to a full 128 bit wide vector */
     TCGv_i64 tmplo = tcg_temp_new_i64();
     TCGv_i64 tmphi = NULL;
+    MemOp mop;
 
     if (size < 4) {
-        MemOp memop = s->be_data + size;
-        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
+        mop = finalize_memop(s, size);
+        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop);
     } else {
         bool be = s->be_data == MO_BE;
         TCGv_i64 tcg_hiaddr;
@@ -1003,11 +1012,12 @@ static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
         tmphi = tcg_temp_new_i64();
         tcg_hiaddr = tcg_temp_new_i64();
 
+        mop = s->be_data | MO_Q;
+        tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
+                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
         tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
-        tcg_gen_qemu_ld_i64(tmplo, be ? tcg_hiaddr : tcg_addr, get_mem_index(s),
-                            s->be_data | MO_Q);
-        tcg_gen_qemu_ld_i64(tmphi, be ? tcg_addr : tcg_hiaddr, get_mem_index(s),
-                            s->be_data | MO_Q);
+        tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr,
+                            get_mem_index(s), mop);
         tcg_temp_free_i64(tcg_hiaddr);
     }