target/arm: Use tcg_gen_qemu_ld_i128 for LDXP

While we don't require 16-byte atomicity here, using a single larger
load simplifies the code, and makes it a closer match to STXP.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20230530191438.411344-5-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 20 insertions, 11 deletions

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 1d34c5a703..1fff74c73a 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -2386,14 +2386,14 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                                TCGv_i64 addr, int size, bool is_pair)
 {
     int idx = get_mem_index(s);
-    MemOp memop = s->be_data;
+    MemOp memop;
 
     g_assert(size <= 3);
     if (is_pair) {
         g_assert(size >= 2);
         if (size == 2) {
             /* The pair must be single-copy atomic for the doubleword.  */
-            memop |= MO_64 | MO_ALIGN;
+            memop = finalize_memop(s, MO_64 | MO_ALIGN);
             tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
             if (s->be_data == MO_LE) {
                 tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32);
@@ -2403,21 +2403,30 @@ static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                 tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 0, 32);
             }
         } else {
-            /* The pair must be single-copy atomic for *each* doubleword, not
-               the entire quadword, however it must be quadword aligned.  */
-            memop |= MO_64;
-            tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx,
-                                memop | MO_ALIGN_16);
+            /*
+             * The pair must be single-copy atomic for *each* doubleword, not
+             * the entire quadword, however it must be quadword aligned.
+             * Expose the complete load to tcg, for ease of tlb lookup,
+             * but indicate that only 8-byte atomicity is required.
+             */
+            TCGv_i128 t16 = tcg_temp_new_i128();
 
-            TCGv_i64 addr2 = tcg_temp_new_i64();
-            tcg_gen_addi_i64(addr2, addr, 8);
-            tcg_gen_qemu_ld_i64(cpu_exclusive_high, addr2, idx, memop);
+            memop = finalize_memop_atom(s, MO_128 | MO_ALIGN_16,
+                                        MO_ATOM_IFALIGN_PAIR);
+            tcg_gen_qemu_ld_i128(t16, addr, idx, memop);
 
+            if (s->be_data == MO_LE) {
+                tcg_gen_extr_i128_i64(cpu_exclusive_val,
+                                      cpu_exclusive_high, t16);
+            } else {
+                tcg_gen_extr_i128_i64(cpu_exclusive_high,
+                                      cpu_exclusive_val, t16);
+            }
             tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val);
             tcg_gen_mov_i64(cpu_reg(s, rt2), cpu_exclusive_high);
         }
     } else {
-        memop |= size | MO_ALIGN;
+        memop = finalize_memop(s, size | MO_ALIGN);
         tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
         tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val);
     }