target/arm: Pass single_memop to gen_mte_checkN

Pass the individual memop to gen_mte_checkN.
For the moment, do nothing with it.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230530191438.411344-14-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

3 files changed, 22 insertions, 15 deletions

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 85d896e..0b60069 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -285,7 +285,7 @@ TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write,
  * For MTE, check multiple logical sequential accesses.
  */
 TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write,
-                        bool tag_checked, int size)
+                        bool tag_checked, int total_size, MemOp single_mop)
 {
     if (tag_checked && s->mte_active[0]) {
         TCGv_i64 ret;
@@ -295,7 +295,7 @@ TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write,
         desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
         desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
         desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write);
-        desc = FIELD_DP32(desc, MTEDESC, SIZEM1, size - 1);
+        desc = FIELD_DP32(desc, MTEDESC, SIZEM1, total_size - 1);
 
         ret = tcg_temp_new_i64();
         gen_helper_mte_check(ret, cpu_env, tcg_constant_i32(desc), addr);
@@ -2841,14 +2841,12 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
     bool is_vector = extract32(insn, 26, 1);
     bool is_load = extract32(insn, 22, 1);
     int opc = extract32(insn, 30, 2);
-
     bool is_signed = false;
     bool postindex = false;
     bool wback = false;
     bool set_tag = false;
-
     TCGv_i64 clean_addr, dirty_addr;
-
+    MemOp mop;
     int size;
 
     if (opc == 3) {
@@ -2931,12 +2929,17 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
         }
     }
 
+    if (is_vector) {
+        mop = finalize_memop_asimd(s, size);
+    } else {
+        mop = finalize_memop(s, size);
+    }
     clean_addr = gen_mte_checkN(s, dirty_addr, !is_load,
-                                (wback || rn != 31) && !set_tag, 2 << size);
+                                (wback || rn != 31) && !set_tag,
+                                2 << size, mop);
 
     if (is_vector) {
-        MemOp mop = finalize_memop_asimd(s, size);
-
+        /* LSE2 does not merge FP pairs; leave these as separate operations. */
         if (is_load) {
             do_fp_ld(s, rt, clean_addr, mop);
         } else {
@@ -2951,9 +2954,11 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
     } else {
         TCGv_i64 tcg_rt = cpu_reg(s, rt);
         TCGv_i64 tcg_rt2 = cpu_reg(s, rt2);
-        MemOp mop = size + 1;
 
         /*
+         * We built mop above for the single logical access -- rebuild it
+         * now for the paired operation.
+         *
          * With LSE2, non-sign-extending pairs are treated atomically if
          * aligned, and if unaligned one of the pair will be completely
          * within a 16-byte block and that element will be atomic.
@@ -2963,6 +2968,7 @@ static void disas_ldst_pair(DisasContext *s, uint32_t insn)
          * This treats sign-extending loads like zero-extending loads,
          * since that reuses the most code below.
          */
+        mop = size + 1;
         if (s->align_mem) {
             mop |= (size == 2 ? MO_ALIGN_4 : MO_ALIGN_8);
         }
@@ -3741,7 +3747,7 @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn)
      * promote consecutive little-endian elements below.
      */
     clean_addr = gen_mte_checkN(s, tcg_rn, is_store, is_postidx || rn != 31,
-                                total);
+                                total, finalize_memop(s, size));
 
     /*
      * Consecutive little-endian elements from a single register
@@ -3899,10 +3905,11 @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
     total = selem << scale;
     tcg_rn = cpu_reg_sp(s, rn);
 
-    clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31,
-                                total);
     mop = finalize_memop(s, scale);
 
+    clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31,
+                                total, mop);
+
     tcg_ebytes = tcg_constant_i64(1 << scale);
     for (xs = 0; xs < selem; xs++) {
         if (replicate) {
diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h
index cecf2ba..b55dc43 100644
--- a/target/arm/tcg/translate-a64.h
+++ b/target/arm/tcg/translate-a64.h
@@ -51,7 +51,7 @@ TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr);
 TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write,
                         bool tag_checked, MemOp memop);
 TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write,
-                        bool tag_checked, int size);
+                        bool tag_checked, int total_size, MemOp memop);
 
 /* We should have at some point before trying to access an FP register
  * done the necessary access check, so assert that
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 671d2ef..ff05062 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -4176,7 +4176,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs,
 
     dirty_addr = tcg_temp_new_i64();
     tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm);
-    clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len);
+    clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8);
 
     /*
      * Note that unpredicated load/store of vector/predicate registers
@@ -4278,7 +4278,7 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs,
 
     dirty_addr = tcg_temp_new_i64();
     tcg_gen_addi_i64(dirty_addr, cpu_reg_sp(s, rn), imm);
-    clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len);
+    clean_addr = gen_mte_checkN(s, dirty_addr, false, rn != 31, len, MO_8);
 
     /* Note that unpredicated load/store of vector/predicate registers
      * are defined as a stream of bytes, which equates to little-endian