target/arm: Split contiguous stores for endianness

We can choose the endianness at translation time, rather than
re-computing it at execution time.

Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20181005175350.30752-12-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 98 insertions, 37 deletions

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 526caec..1ad0431 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -1248,29 +1248,47 @@ DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_st3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_st4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 
-DEF_HELPER_FLAGS_4(sve_st1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-
-DEF_HELPER_FLAGS_4(sve_st1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-
-DEF_HELPER_FLAGS_4(sve_st1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4hh_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st1hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4hh_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st1ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4ss_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st1ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4ss_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st1dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4dd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+
+DEF_HELPER_FLAGS_4(sve_st1dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 
 DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 
-DEF_HELPER_FLAGS_4(sve_st1hs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
-DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1hs_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1hd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1hs_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 
-DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
+DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 
 DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG,
                    void, env, ptr, ptr, ptr, tl, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index d31988b..4263539 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -4836,12 +4836,17 @@ void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r)           \
 }
 
 #define DO_STN_2(N, NAME, ESIZE, MSIZE) \
-void __attribute__((flatten)) HELPER(sve_st##N##NAME##_r)             \
+void __attribute__((flatten)) HELPER(sve_st##N##NAME##_le_r)          \
     (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
 {                                                                     \
     sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE,         \
-                  arm_cpu_data_is_big_endian(env)                     \
-                  ? sve_st1##NAME##_be_tlb : sve_st1##NAME##_le_tlb); \
+                  sve_st1##NAME##_le_tlb);                            \
+}                                                                     \
+void __attribute__((flatten)) HELPER(sve_st##N##NAME##_be_r)          \
+    (CPUARMState *env, void *vg, target_ulong addr, uint32_t desc)    \
+{                                                                     \
+    sve_st##N##_r(env, vg, addr, desc, GETPC(), ESIZE, MSIZE,         \
+                  sve_st1##NAME##_be_tlb);                            \
 }
 
 DO_STN_1(1, bb, 1)
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 8d191df..05aba50 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -4953,32 +4953,70 @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn)
 static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr,
                       int msz, int esz, int nreg)
 {
-    static gen_helper_gvec_mem * const fn_single[4][4] = {
-        { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r,
-          gen_helper_sve_st1bs_r, gen_helper_sve_st1bd_r },
-        { NULL,                   gen_helper_sve_st1hh_r,
-          gen_helper_sve_st1hs_r, gen_helper_sve_st1hd_r },
-        { NULL, NULL,
-          gen_helper_sve_st1ss_r, gen_helper_sve_st1sd_r },
-        { NULL, NULL, NULL, gen_helper_sve_st1dd_r },
+    static gen_helper_gvec_mem * const fn_single[2][4][4] = {
+        { { gen_helper_sve_st1bb_r,
+            gen_helper_sve_st1bh_r,
+            gen_helper_sve_st1bs_r,
+            gen_helper_sve_st1bd_r },
+          { NULL,
+            gen_helper_sve_st1hh_le_r,
+            gen_helper_sve_st1hs_le_r,
+            gen_helper_sve_st1hd_le_r },
+          { NULL, NULL,
+            gen_helper_sve_st1ss_le_r,
+            gen_helper_sve_st1sd_le_r },
+          { NULL, NULL, NULL,
+            gen_helper_sve_st1dd_le_r } },
+        { { gen_helper_sve_st1bb_r,
+            gen_helper_sve_st1bh_r,
+            gen_helper_sve_st1bs_r,
+            gen_helper_sve_st1bd_r },
+          { NULL,
+            gen_helper_sve_st1hh_be_r,
+            gen_helper_sve_st1hs_be_r,
+            gen_helper_sve_st1hd_be_r },
+          { NULL, NULL,
+            gen_helper_sve_st1ss_be_r,
+            gen_helper_sve_st1sd_be_r },
+          { NULL, NULL, NULL,
+            gen_helper_sve_st1dd_be_r } },
     };
-    static gen_helper_gvec_mem * const fn_multiple[3][4] = {
-        { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_r,
-          gen_helper_sve_st2ss_r, gen_helper_sve_st2dd_r },
-        { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_r,
-          gen_helper_sve_st3ss_r, gen_helper_sve_st3dd_r },
-        { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_r,
-          gen_helper_sve_st4ss_r, gen_helper_sve_st4dd_r },
+    static gen_helper_gvec_mem * const fn_multiple[2][3][4] = {
+        { { gen_helper_sve_st2bb_r,
+            gen_helper_sve_st2hh_le_r,
+            gen_helper_sve_st2ss_le_r,
+            gen_helper_sve_st2dd_le_r },
+          { gen_helper_sve_st3bb_r,
+            gen_helper_sve_st3hh_le_r,
+            gen_helper_sve_st3ss_le_r,
+            gen_helper_sve_st3dd_le_r },
+          { gen_helper_sve_st4bb_r,
+            gen_helper_sve_st4hh_le_r,
+            gen_helper_sve_st4ss_le_r,
+            gen_helper_sve_st4dd_le_r } },
+        { { gen_helper_sve_st2bb_r,
+            gen_helper_sve_st2hh_be_r,
+            gen_helper_sve_st2ss_be_r,
+            gen_helper_sve_st2dd_be_r },
+          { gen_helper_sve_st3bb_r,
+            gen_helper_sve_st3hh_be_r,
+            gen_helper_sve_st3ss_be_r,
+            gen_helper_sve_st3dd_be_r },
+          { gen_helper_sve_st4bb_r,
+            gen_helper_sve_st4hh_be_r,
+            gen_helper_sve_st4ss_be_r,
+            gen_helper_sve_st4dd_be_r } },
     };
     gen_helper_gvec_mem *fn;
+    int be = s->be_data == MO_BE;
 
     if (nreg == 0) {
         /* ST1 */
-        fn = fn_single[msz][esz];
+        fn = fn_single[be][msz][esz];
     } else {
         /* ST2, ST3, ST4 -- msz == esz, enforced by encoding */
         assert(msz == esz);
-        fn = fn_multiple[nreg - 1][msz];
+        fn = fn_multiple[be][nreg - 1][msz];
     }
     assert(fn != NULL);
     do_mem_zpa(s, zt, pg, addr, fn);