target/riscv: Relax fld alignment requirement

According to the risc-v specification:
"FLD and FSD are only guaranteed to execute atomically if the effective
address is naturally aligned and XLEN≥64."

We currently implement fld as MO_ATOM_IFALIGN when XLEN < 64, which does
not violate the rules. But it will hide some problems. So relax it to
MO_ATOM_NONE.

Signed-off-by: LIU Zhiwei <zhiwei_liu@linux.alibaba.com>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20240802072417.659-4-zhiwei_liu@linux.alibaba.com>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

diff --git a/target/riscv/insn_trans/trans_rvd.c.inc b/target/riscv/insn_trans/trans_rvd.c.inc
index 49682292b8a0951d78ec68ae21e2947d67e8f456..8a46124f98293f3231b9418ef16e7cfa5e2a6f8e 100644 (file)
--- a/target/riscv/insn_trans/trans_rvd.c.inc
+++ b/target/riscv/insn_trans/trans_rvd.c.inc
@@ -48,11 +48,17 @@ static bool trans_fld(DisasContext *ctx, arg_fld *a)
     REQUIRE_EXT(ctx, RVD);
 
     /*
-     * Zama16b applies to loads and stores of no more than MXLEN bits defined
-     * in the F, D, and Q extensions.
+     * FLD and FSD are only guaranteed to execute atomically if the effective
+     * address is naturally aligned and XLEN≥64. Also, zama16b applies to
+     * loads and stores of no more than MXLEN bits defined in the F, D, and
+     * Q extensions.
      */
-    if ((get_xl_max(ctx) >= MXL_RV64) && ctx->cfg_ptr->ext_zama16b) {
+    if (get_xl_max(ctx) == MXL_RV32) {
+        memop |= MO_ATOM_NONE;
+    } else if (ctx->cfg_ptr->ext_zama16b) {
         memop |= MO_ATOM_WITHIN16;
+    } else {
+        memop |= MO_ATOM_IFALIGN;
     }
 
     decode_save_opc(ctx);
@@ -71,8 +77,12 @@ static bool trans_fsd(DisasContext *ctx, arg_fsd *a)
     REQUIRE_FPU;
     REQUIRE_EXT(ctx, RVD);
 
-    if ((get_xl_max(ctx) >= MXL_RV64) && ctx->cfg_ptr->ext_zama16b) {
+    if (get_xl_max(ctx) == MXL_RV32) {
+        memop |= MO_ATOM_NONE;
+    } else if (ctx->cfg_ptr->ext_zama16b) {
         memop |= MO_ATOM_WITHIN16;
+    } else {
+        memop |= MO_ATOM_IFALIGN;
     }
 
     decode_save_opc(ctx);