summary refs log tree commit diff stats
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/alpha/translate.c38
-rw-r--r--target/avr/translate.c16
-rw-r--r--target/cris/translate_v10.c.inc18
-rw-r--r--target/hexagon/genptr.c8
-rw-r--r--target/hexagon/idef-parser/parser-helpers.c28
-rw-r--r--target/hexagon/macros.h14
-rw-r--r--target/hexagon/translate.c32
-rw-r--r--target/hppa/translate.c2
-rw-r--r--target/m68k/translate.c76
-rw-r--r--target/mips/tcg/nanomips_translate.c.inc2
-rw-r--r--target/mips/tcg/translate.c8
-rw-r--r--target/s390x/tcg/translate.c152
-rw-r--r--target/sparc/ldst_helper.c10
-rw-r--r--target/sparc/translate.c85
-rw-r--r--target/xtensa/translate.c4
15 files changed, 233 insertions, 260 deletions
diff --git a/target/alpha/translate.c b/target/alpha/translate.c
index 9d25e21164..be8adb2526 100644
--- a/target/alpha/translate.c
+++ b/target/alpha/translate.c
@@ -72,7 +72,7 @@ struct DisasContext {
 #ifdef CONFIG_USER_ONLY
 #define UNALIGN(C)  (C)->unalign
 #else
-#define UNALIGN(C)  0
+#define UNALIGN(C)  MO_ALIGN
 #endif
 
 /* Target-specific return values from translate_one, indicating the
@@ -2399,21 +2399,21 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
             switch ((insn >> 12) & 0xF) {
             case 0x0:
                 /* Longword physical access (hw_ldl/p) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL | MO_ALIGN);
                 break;
             case 0x1:
                 /* Quadword physical access (hw_ldq/p) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN);
                 break;
             case 0x2:
                 /* Longword physical access with lock (hw_ldl_l/p) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LESL | MO_ALIGN);
                 tcg_gen_mov_i64(cpu_lock_addr, addr);
                 tcg_gen_mov_i64(cpu_lock_value, va);
                 break;
             case 0x3:
                 /* Quadword physical access with lock (hw_ldq_l/p) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN);
                 tcg_gen_mov_i64(cpu_lock_addr, addr);
                 tcg_gen_mov_i64(cpu_lock_value, va);
                 break;
@@ -2438,11 +2438,13 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
                 goto invalid_opc;
             case 0xA:
                 /* Longword virtual access with protection check (hw_ldl/w) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, MO_LESL);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX,
+                                    MO_LESL | MO_ALIGN);
                 break;
             case 0xB:
                 /* Quadword virtual access with protection check (hw_ldq/w) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX, MO_LEUQ);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_KERNEL_IDX,
+                                    MO_LEUQ | MO_ALIGN);
                 break;
             case 0xC:
                 /* Longword virtual access with alt access mode (hw_ldl/a)*/
@@ -2453,12 +2455,14 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
             case 0xE:
                 /* Longword virtual access with alternate access mode and
                    protection checks (hw_ldl/wa) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, MO_LESL);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX,
+                                    MO_LESL | MO_ALIGN);
                 break;
             case 0xF:
                 /* Quadword virtual access with alternate access mode and
                    protection checks (hw_ldq/wa) */
-                tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX, MO_LEUQ);
+                tcg_gen_qemu_ld_i64(va, addr, MMU_USER_IDX,
+                                    MO_LEUQ | MO_ALIGN);
                 break;
             }
             break;
@@ -2659,7 +2663,7 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
                 vb = load_gpr(ctx, rb);
                 tmp = tcg_temp_new();
                 tcg_gen_addi_i64(tmp, vb, disp12);
-                tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LESL);
+                tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LESL | MO_ALIGN);
                 break;
             case 0x1:
                 /* Quadword physical access */
@@ -2667,17 +2671,17 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
                 vb = load_gpr(ctx, rb);
                 tmp = tcg_temp_new();
                 tcg_gen_addi_i64(tmp, vb, disp12);
-                tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LEUQ);
+                tcg_gen_qemu_st_i64(va, tmp, MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN);
                 break;
             case 0x2:
                 /* Longword physical access with lock */
                 ret = gen_store_conditional(ctx, ra, rb, disp12,
-                                            MMU_PHYS_IDX, MO_LESL);
+                                            MMU_PHYS_IDX, MO_LESL | MO_ALIGN);
                 break;
             case 0x3:
                 /* Quadword physical access with lock */
                 ret = gen_store_conditional(ctx, ra, rb, disp12,
-                                            MMU_PHYS_IDX, MO_LEUQ);
+                                            MMU_PHYS_IDX, MO_LEUQ | MO_ALIGN);
                 break;
             case 0x4:
                 /* Longword virtual access */
@@ -2771,11 +2775,11 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
         break;
     case 0x2A:
         /* LDL_L */
-        gen_load_int(ctx, ra, rb, disp16, MO_LESL, 0, 1);
+        gen_load_int(ctx, ra, rb, disp16, MO_LESL | MO_ALIGN, 0, 1);
         break;
     case 0x2B:
         /* LDQ_L */
-        gen_load_int(ctx, ra, rb, disp16, MO_LEUQ, 0, 1);
+        gen_load_int(ctx, ra, rb, disp16, MO_LEUQ | MO_ALIGN, 0, 1);
         break;
     case 0x2C:
         /* STL */
@@ -2788,12 +2792,12 @@ static DisasJumpType translate_one(DisasContext *ctx, uint32_t insn)
     case 0x2E:
         /* STL_C */
         ret = gen_store_conditional(ctx, ra, rb, disp16,
-                                    ctx->mem_idx, MO_LESL);
+                                    ctx->mem_idx, MO_LESL | MO_ALIGN);
         break;
     case 0x2F:
         /* STQ_C */
         ret = gen_store_conditional(ctx, ra, rb, disp16,
-                                    ctx->mem_idx, MO_LEUQ);
+                                    ctx->mem_idx, MO_LEUQ | MO_ALIGN);
         break;
     case 0x30:
         /* BR */
diff --git a/target/avr/translate.c b/target/avr/translate.c
index a6aeae6dfa..cd82f5d591 100644
--- a/target/avr/translate.c
+++ b/target/avr/translate.c
@@ -1492,7 +1492,7 @@ static void gen_data_store(DisasContext *ctx, TCGv data, TCGv addr)
     if (ctx->base.tb->flags & TB_FLAGS_FULL_ACCESS) {
         gen_helper_fullwr(cpu_env, data, addr);
     } else {
-        tcg_gen_qemu_st8(data, addr, MMU_DATA_IDX); /* mem[addr] = data */
+        tcg_gen_qemu_st_tl(data, addr, MMU_DATA_IDX, MO_UB);
     }
 }
 
@@ -1501,7 +1501,7 @@ static void gen_data_load(DisasContext *ctx, TCGv data, TCGv addr)
     if (ctx->base.tb->flags & TB_FLAGS_FULL_ACCESS) {
         gen_helper_fullrd(data, cpu_env, addr);
     } else {
-        tcg_gen_qemu_ld8u(data, addr, MMU_DATA_IDX); /* data = mem[addr] */
+        tcg_gen_qemu_ld_tl(data, addr, MMU_DATA_IDX, MO_UB);
     }
 }
 
@@ -1979,7 +1979,7 @@ static bool trans_LPM1(DisasContext *ctx, arg_LPM1 *a)
 
     tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */
     tcg_gen_or_tl(addr, addr, L);
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     return true;
 }
 
@@ -1996,7 +1996,7 @@ static bool trans_LPM2(DisasContext *ctx, arg_LPM2 *a)
 
     tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */
     tcg_gen_or_tl(addr, addr, L);
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     return true;
 }
 
@@ -2013,7 +2013,7 @@ static bool trans_LPMX(DisasContext *ctx, arg_LPMX *a)
 
     tcg_gen_shli_tl(addr, H, 8); /* addr = H:L */
     tcg_gen_or_tl(addr, addr, L);
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     tcg_gen_addi_tl(addr, addr, 1); /* addr = addr + 1 */
     tcg_gen_andi_tl(L, addr, 0xff);
     tcg_gen_shri_tl(addr, addr, 8);
@@ -2045,7 +2045,7 @@ static bool trans_ELPM1(DisasContext *ctx, arg_ELPM1 *a)
     TCGv Rd = cpu_r[0];
     TCGv addr = gen_get_zaddr();
 
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     return true;
 }
 
@@ -2058,7 +2058,7 @@ static bool trans_ELPM2(DisasContext *ctx, arg_ELPM2 *a)
     TCGv Rd = cpu_r[a->rd];
     TCGv addr = gen_get_zaddr();
 
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     return true;
 }
 
@@ -2071,7 +2071,7 @@ static bool trans_ELPMX(DisasContext *ctx, arg_ELPMX *a)
     TCGv Rd = cpu_r[a->rd];
     TCGv addr = gen_get_zaddr();
 
-    tcg_gen_qemu_ld8u(Rd, addr, MMU_CODE_IDX); /* Rd = mem[addr] */
+    tcg_gen_qemu_ld_tl(Rd, addr, MMU_CODE_IDX, MO_UB);
     tcg_gen_addi_tl(addr, addr, 1); /* addr = addr + 1 */
     gen_set_zaddr(addr);
     return true;
diff --git a/target/cris/translate_v10.c.inc b/target/cris/translate_v10.c.inc
index 32338bb69b..b7b0517982 100644
--- a/target/cris/translate_v10.c.inc
+++ b/target/cris/translate_v10.c.inc
@@ -80,13 +80,9 @@ static void gen_store_v10_conditional(DisasContext *dc, TCGv addr, TCGv val,
     /* Store only if F flag isn't set */
     tcg_gen_andi_tl(t1, cpu_PR[PR_CCS], F_FLAG_V10);
     tcg_gen_brcondi_tl(TCG_COND_NE, t1, 0, l1);
-    if (size == 1) {
-        tcg_gen_qemu_st8(tval, taddr, mem_index);
-    } else if (size == 2) {
-        tcg_gen_qemu_st16(tval, taddr, mem_index);
-    } else {
-        tcg_gen_qemu_st32(tval, taddr, mem_index);
-    }
+
+    tcg_gen_qemu_st_tl(tval, taddr, mem_index, ctz32(size) | MO_TE);
+
     gen_set_label(l1);
     tcg_gen_shri_tl(t1, t1, 1);  /* shift F to P position */
     tcg_gen_or_tl(cpu_PR[PR_CCS], cpu_PR[PR_CCS], t1); /*P=F*/
@@ -109,13 +105,7 @@ static void gen_store_v10(DisasContext *dc, TCGv addr, TCGv val,
         return;
     }
 
-    if (size == 1) {
-        tcg_gen_qemu_st8(val, addr, mem_index);
-    } else if (size == 2) {
-        tcg_gen_qemu_st16(val, addr, mem_index);
-    } else {
-        tcg_gen_qemu_st32(val, addr, mem_index);
-    }
+    tcg_gen_qemu_st_tl(val, addr, mem_index, ctz32(size) | MO_TE);
 }
 
 
diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c
index 502c85ae35..244063b1d2 100644
--- a/target/hexagon/genptr.c
+++ b/target/hexagon/genptr.c
@@ -320,14 +320,14 @@ void gen_set_byte_i64(int N, TCGv_i64 result, TCGv src)
 
 static inline void gen_load_locked4u(TCGv dest, TCGv vaddr, int mem_index)
 {
-    tcg_gen_qemu_ld32u(dest, vaddr, mem_index);
+    tcg_gen_qemu_ld_tl(dest, vaddr, mem_index, MO_TEUL);
     tcg_gen_mov_tl(hex_llsc_addr, vaddr);
     tcg_gen_mov_tl(hex_llsc_val, dest);
 }
 
 static inline void gen_load_locked8u(TCGv_i64 dest, TCGv vaddr, int mem_index)
 {
-    tcg_gen_qemu_ld64(dest, vaddr, mem_index);
+    tcg_gen_qemu_ld_i64(dest, vaddr, mem_index, MO_TEUQ);
     tcg_gen_mov_tl(hex_llsc_addr, vaddr);
     tcg_gen_mov_i64(hex_llsc_val_i64, dest);
 }
@@ -678,7 +678,7 @@ static void gen_load_frame(DisasContext *ctx, TCGv_i64 frame, TCGv EA)
 {
     Insn *insn = ctx->insn;  /* Needed for CHECK_NOSHUF */
     CHECK_NOSHUF(EA, 8);
-    tcg_gen_qemu_ld64(frame, EA, ctx->mem_idx);
+    tcg_gen_qemu_ld_i64(frame, EA, ctx->mem_idx, MO_TEUQ);
 }
 
 static void gen_return(DisasContext *ctx, TCGv_i64 dst, TCGv src)
@@ -1019,7 +1019,7 @@ static void gen_vreg_load(DisasContext *ctx, intptr_t dstoff, TCGv src,
         tcg_gen_andi_tl(src, src, ~((int32_t)sizeof(MMVector) - 1));
     }
     for (int i = 0; i < sizeof(MMVector) / 8; i++) {
-        tcg_gen_qemu_ld64(tmp, src, ctx->mem_idx);
+        tcg_gen_qemu_ld_i64(tmp, src, ctx->mem_idx, MO_TEUQ);
         tcg_gen_addi_tl(src, src, 8);
         tcg_gen_st_i64(tmp, cpu_env, dstoff + i * 8);
     }
diff --git a/target/hexagon/idef-parser/parser-helpers.c b/target/hexagon/idef-parser/parser-helpers.c
index 86511efb62..8734218e51 100644
--- a/target/hexagon/idef-parser/parser-helpers.c
+++ b/target/hexagon/idef-parser/parser-helpers.c
@@ -1737,36 +1737,34 @@ void gen_load_cancel(Context *c, YYLTYPE *locp)
 void gen_load(Context *c, YYLTYPE *locp, HexValue *width,
               HexSignedness signedness, HexValue *ea, HexValue *dst)
 {
-    char size_suffix[4] = {0};
-    const char *sign_suffix;
+    unsigned dst_bit_width;
+    unsigned src_bit_width;
+
     /* Memop width is specified in the load macro */
     assert_signedness(c, locp, signedness);
-    sign_suffix = (width->imm.value > 4)
-                   ? ""
-                   : ((signedness == UNSIGNED) ? "u" : "s");
+
     /* If dst is a variable, assert that is declared and load the type info */
     if (dst->type == VARID) {
         find_variable(c, locp, dst, dst);
     }
 
-    snprintf(size_suffix, 4, "%" PRIu64, width->imm.value * 8);
+    src_bit_width = width->imm.value * 8;
+    dst_bit_width = MAX(dst->bit_width, 32);
+
     /* Lookup the effective address EA */
     find_variable(c, locp, ea, ea);
     OUT(c, locp, "if (insn->slot == 0 && pkt->pkt_has_store_s1) {\n");
     OUT(c, locp, "probe_noshuf_load(", ea, ", ", width, ", ctx->mem_idx);\n");
     OUT(c, locp, "process_store(ctx, 1);\n");
     OUT(c, locp, "}\n");
-    OUT(c, locp, "tcg_gen_qemu_ld", size_suffix, sign_suffix);
+
+    OUT(c, locp, "tcg_gen_qemu_ld_i", &dst_bit_width);
     OUT(c, locp, "(");
-    if (dst->bit_width > width->imm.value * 8) {
-        /*
-         * Cast to the correct TCG type if necessary, to avoid implict cast
-         * warnings. This is needed when the width of the destination var is
-         * larger than the size of the requested load.
-         */
-        OUT(c, locp, "(TCGv) ");
+    OUT(c, locp, dst, ", ", ea, ", ctx->mem_idx, MO_", &src_bit_width);
+    if (signedness == SIGNED) {
+        OUT(c, locp, " | MO_SIGN");
     }
-    OUT(c, locp, dst, ", ", ea, ", ctx->mem_idx);\n");
+    OUT(c, locp, " | MO_TE);\n");
 }
 
 void gen_store(Context *c, YYLTYPE *locp, HexValue *width, HexValue *ea,
diff --git a/target/hexagon/macros.h b/target/hexagon/macros.h
index 3e162de3a7..760630de8f 100644
--- a/target/hexagon/macros.h
+++ b/target/hexagon/macros.h
@@ -99,37 +99,37 @@
 #define MEM_LOAD1s(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 1); \
-        tcg_gen_qemu_ld8s(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_SB); \
     } while (0)
 #define MEM_LOAD1u(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 1); \
-        tcg_gen_qemu_ld8u(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_UB); \
     } while (0)
 #define MEM_LOAD2s(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 2); \
-        tcg_gen_qemu_ld16s(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TESW); \
     } while (0)
 #define MEM_LOAD2u(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 2); \
-        tcg_gen_qemu_ld16u(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TEUW); \
     } while (0)
 #define MEM_LOAD4s(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 4); \
-        tcg_gen_qemu_ld32s(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TESL); \
     } while (0)
 #define MEM_LOAD4u(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 4); \
-        tcg_gen_qemu_ld32s(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_tl(DST, VA, ctx->mem_idx, MO_TEUL); \
     } while (0)
 #define MEM_LOAD8u(DST, VA) \
     do { \
         CHECK_NOSHUF(VA, 8); \
-        tcg_gen_qemu_ld64(DST, VA, ctx->mem_idx); \
+        tcg_gen_qemu_ld_i64(DST, VA, ctx->mem_idx, MO_TEUQ); \
     } while (0)
 
 #define MEM_STORE1_FUNC(X) \
diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c
index c087f183d0..cddd7c5db4 100644
--- a/target/hexagon/translate.c
+++ b/target/hexagon/translate.c
@@ -627,27 +627,27 @@ void process_store(DisasContext *ctx, int slot_num)
         switch (ctx->store_width[slot_num]) {
         case 1:
             gen_check_store_width(ctx, slot_num);
-            tcg_gen_qemu_st8(hex_store_val32[slot_num],
-                             hex_store_addr[slot_num],
-                             ctx->mem_idx);
+            tcg_gen_qemu_st_tl(hex_store_val32[slot_num],
+                               hex_store_addr[slot_num],
+                               ctx->mem_idx, MO_UB);
             break;
         case 2:
             gen_check_store_width(ctx, slot_num);
-            tcg_gen_qemu_st16(hex_store_val32[slot_num],
-                              hex_store_addr[slot_num],
-                              ctx->mem_idx);
+            tcg_gen_qemu_st_tl(hex_store_val32[slot_num],
+                               hex_store_addr[slot_num],
+                               ctx->mem_idx, MO_TEUW);
             break;
         case 4:
             gen_check_store_width(ctx, slot_num);
-            tcg_gen_qemu_st32(hex_store_val32[slot_num],
-                              hex_store_addr[slot_num],
-                              ctx->mem_idx);
+            tcg_gen_qemu_st_tl(hex_store_val32[slot_num],
+                               hex_store_addr[slot_num],
+                               ctx->mem_idx, MO_TEUL);
             break;
         case 8:
             gen_check_store_width(ctx, slot_num);
-            tcg_gen_qemu_st64(hex_store_val64[slot_num],
-                              hex_store_addr[slot_num],
-                              ctx->mem_idx);
+            tcg_gen_qemu_st_i64(hex_store_val64[slot_num],
+                                hex_store_addr[slot_num],
+                                ctx->mem_idx, MO_TEUQ);
             break;
         default:
             {
@@ -693,13 +693,13 @@ static void process_dczeroa(DisasContext *ctx)
         TCGv_i64 zero = tcg_constant_i64(0);
 
         tcg_gen_andi_tl(addr, hex_dczero_addr, ~0x1f);
-        tcg_gen_qemu_st64(zero, addr, ctx->mem_idx);
+        tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ);
         tcg_gen_addi_tl(addr, addr, 8);
-        tcg_gen_qemu_st64(zero, addr, ctx->mem_idx);
+        tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ);
         tcg_gen_addi_tl(addr, addr, 8);
-        tcg_gen_qemu_st64(zero, addr, ctx->mem_idx);
+        tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ);
         tcg_gen_addi_tl(addr, addr, 8);
-        tcg_gen_qemu_st64(zero, addr, ctx->mem_idx);
+        tcg_gen_qemu_st_i64(zero, addr, ctx->mem_idx, MO_UQ);
     }
 }
 
diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index 6a3154ebc6..59e4688bfa 100644
--- a/target/hppa/translate.c
+++ b/target/hppa/translate.c
@@ -271,7 +271,7 @@ typedef struct DisasContext {
 #ifdef CONFIG_USER_ONLY
 #define UNALIGN(C)  (C)->unalign
 #else
-#define UNALIGN(C)  0
+#define UNALIGN(C)  MO_ALIGN
 #endif
 
 /* Note that ssm/rsm instructions number PSW_W and PSW_E differently.  */
diff --git a/target/m68k/translate.c b/target/m68k/translate.c
index 422f4652f1..744eb3748b 100644
--- a/target/m68k/translate.c
+++ b/target/m68k/translate.c
@@ -304,23 +304,14 @@ static inline void gen_addr_fault(DisasContext *s)
 static inline TCGv gen_load(DisasContext *s, int opsize, TCGv addr,
                             int sign, int index)
 {
-    TCGv tmp;
-    tmp = tcg_temp_new_i32();
-    switch(opsize) {
+    TCGv tmp = tcg_temp_new_i32();
+
+    switch (opsize) {
     case OS_BYTE:
-        if (sign)
-            tcg_gen_qemu_ld8s(tmp, addr, index);
-        else
-            tcg_gen_qemu_ld8u(tmp, addr, index);
-        break;
     case OS_WORD:
-        if (sign)
-            tcg_gen_qemu_ld16s(tmp, addr, index);
-        else
-            tcg_gen_qemu_ld16u(tmp, addr, index);
-        break;
     case OS_LONG:
-        tcg_gen_qemu_ld32u(tmp, addr, index);
+        tcg_gen_qemu_ld_tl(tmp, addr, index,
+                           opsize | (sign ? MO_SIGN : 0) | MO_TE);
         break;
     default:
         g_assert_not_reached();
@@ -332,15 +323,11 @@ static inline TCGv gen_load(DisasContext *s, int opsize, TCGv addr,
 static inline void gen_store(DisasContext *s, int opsize, TCGv addr, TCGv val,
                              int index)
 {
-    switch(opsize) {
+    switch (opsize) {
     case OS_BYTE:
-        tcg_gen_qemu_st8(val, addr, index);
-        break;
     case OS_WORD:
-        tcg_gen_qemu_st16(val, addr, index);
-        break;
     case OS_LONG:
-        tcg_gen_qemu_st32(val, addr, index);
+        tcg_gen_qemu_st_tl(val, addr, index, opsize | MO_TE);
         break;
     default:
         g_assert_not_reached();
@@ -971,23 +958,16 @@ static void gen_load_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
     tmp = tcg_temp_new();
     switch (opsize) {
     case OS_BYTE:
-        tcg_gen_qemu_ld8s(tmp, addr, index);
-        gen_helper_exts32(cpu_env, fp, tmp);
-        break;
     case OS_WORD:
-        tcg_gen_qemu_ld16s(tmp, addr, index);
-        gen_helper_exts32(cpu_env, fp, tmp);
-        break;
-    case OS_LONG:
-        tcg_gen_qemu_ld32u(tmp, addr, index);
+        tcg_gen_qemu_ld_tl(tmp, addr, index, opsize | MO_SIGN | MO_TE);
         gen_helper_exts32(cpu_env, fp, tmp);
         break;
     case OS_SINGLE:
-        tcg_gen_qemu_ld32u(tmp, addr, index);
+        tcg_gen_qemu_ld_tl(tmp, addr, index, MO_TEUL);
         gen_helper_extf32(cpu_env, fp, tmp);
         break;
     case OS_DOUBLE:
-        tcg_gen_qemu_ld64(t64, addr, index);
+        tcg_gen_qemu_ld_i64(t64, addr, index, MO_TEUQ);
         gen_helper_extf64(cpu_env, fp, t64);
         break;
     case OS_EXTENDED:
@@ -995,11 +975,11 @@ static void gen_load_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
             gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
             break;
         }
-        tcg_gen_qemu_ld32u(tmp, addr, index);
+        tcg_gen_qemu_ld_i32(tmp, addr, index, MO_TEUL);
         tcg_gen_shri_i32(tmp, tmp, 16);
         tcg_gen_st16_i32(tmp, fp, offsetof(FPReg, l.upper));
         tcg_gen_addi_i32(tmp, addr, 4);
-        tcg_gen_qemu_ld64(t64, tmp, index);
+        tcg_gen_qemu_ld_i64(t64, tmp, index, MO_TEUQ);
         tcg_gen_st_i64(t64, fp, offsetof(FPReg, l.lower));
         break;
     case OS_PACKED:
@@ -1024,24 +1004,18 @@ static void gen_store_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
     tmp = tcg_temp_new();
     switch (opsize) {
     case OS_BYTE:
-        gen_helper_reds32(tmp, cpu_env, fp);
-        tcg_gen_qemu_st8(tmp, addr, index);
-        break;
     case OS_WORD:
-        gen_helper_reds32(tmp, cpu_env, fp);
-        tcg_gen_qemu_st16(tmp, addr, index);
-        break;
     case OS_LONG:
         gen_helper_reds32(tmp, cpu_env, fp);
-        tcg_gen_qemu_st32(tmp, addr, index);
+        tcg_gen_qemu_st_tl(tmp, addr, index, opsize | MO_TE);
         break;
     case OS_SINGLE:
         gen_helper_redf32(tmp, cpu_env, fp);
-        tcg_gen_qemu_st32(tmp, addr, index);
+        tcg_gen_qemu_st_tl(tmp, addr, index, MO_TEUL);
         break;
     case OS_DOUBLE:
         gen_helper_redf64(t64, cpu_env, fp);
-        tcg_gen_qemu_st64(t64, addr, index);
+        tcg_gen_qemu_st_i64(t64, addr, index, MO_TEUQ);
         break;
     case OS_EXTENDED:
         if (m68k_feature(s->env, M68K_FEATURE_CF_FPU)) {
@@ -1050,10 +1024,10 @@ static void gen_store_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
         }
         tcg_gen_ld16u_i32(tmp, fp, offsetof(FPReg, l.upper));
         tcg_gen_shli_i32(tmp, tmp, 16);
-        tcg_gen_qemu_st32(tmp, addr, index);
+        tcg_gen_qemu_st_i32(tmp, addr, index, MO_TEUL);
         tcg_gen_addi_i32(tmp, addr, 4);
         tcg_gen_ld_i64(t64, fp, offsetof(FPReg, l.lower));
-        tcg_gen_qemu_st64(t64, tmp, index);
+        tcg_gen_qemu_st_i64(t64, tmp, index, MO_TEUQ);
         break;
     case OS_PACKED:
         /*
@@ -2079,14 +2053,14 @@ DISAS_INSN(movep)
     if (insn & 0x80) {
         for ( ; i > 0 ; i--) {
             tcg_gen_shri_i32(dbuf, reg, (i - 1) * 8);
-            tcg_gen_qemu_st8(dbuf, abuf, IS_USER(s));
+            tcg_gen_qemu_st_i32(dbuf, abuf, IS_USER(s), MO_UB);
             if (i > 1) {
                 tcg_gen_addi_i32(abuf, abuf, 2);
             }
         }
     } else {
         for ( ; i > 0 ; i--) {
-            tcg_gen_qemu_ld8u(dbuf, abuf, IS_USER(s));
+            tcg_gen_qemu_ld_tl(dbuf, abuf, IS_USER(s), MO_UB);
             tcg_gen_deposit_i32(reg, reg, dbuf, (i - 1) * 8, 8);
             if (i > 1) {
                 tcg_gen_addi_i32(abuf, abuf, 2);
@@ -4337,14 +4311,14 @@ static void m68k_copy_line(TCGv dst, TCGv src, int index)
     t1 = tcg_temp_new_i64();
 
     tcg_gen_andi_i32(addr, src, ~15);
-    tcg_gen_qemu_ld64(t0, addr, index);
+    tcg_gen_qemu_ld_i64(t0, addr, index, MO_TEUQ);
     tcg_gen_addi_i32(addr, addr, 8);
-    tcg_gen_qemu_ld64(t1, addr, index);
+    tcg_gen_qemu_ld_i64(t1, addr, index, MO_TEUQ);
 
     tcg_gen_andi_i32(addr, dst, ~15);
-    tcg_gen_qemu_st64(t0, addr, index);
+    tcg_gen_qemu_st_i64(t0, addr, index, MO_TEUQ);
     tcg_gen_addi_i32(addr, addr, 8);
-    tcg_gen_qemu_st64(t1, addr, index);
+    tcg_gen_qemu_st_i64(t1, addr, index, MO_TEUQ);
 }
 
 DISAS_INSN(move16_reg)
@@ -4767,7 +4741,7 @@ static void gen_qemu_store_fcr(DisasContext *s, TCGv addr, int reg)
 
     tmp = tcg_temp_new();
     gen_load_fcr(s, tmp, reg);
-    tcg_gen_qemu_st32(tmp, addr, index);
+    tcg_gen_qemu_st_tl(tmp, addr, index, MO_TEUL);
 }
 
 static void gen_qemu_load_fcr(DisasContext *s, TCGv addr, int reg)
@@ -4776,7 +4750,7 @@ static void gen_qemu_load_fcr(DisasContext *s, TCGv addr, int reg)
     TCGv tmp;
 
     tmp = tcg_temp_new();
-    tcg_gen_qemu_ld32u(tmp, addr, index);
+    tcg_gen_qemu_ld_tl(tmp, addr, index, MO_TEUL);
     gen_store_fcr(s, tmp, reg);
 }
 
diff --git a/target/mips/tcg/nanomips_translate.c.inc b/target/mips/tcg/nanomips_translate.c.inc
index 9398e28000..97b9572caa 100644
--- a/target/mips/tcg/nanomips_translate.c.inc
+++ b/target/mips/tcg/nanomips_translate.c.inc
@@ -998,7 +998,7 @@ static void gen_llwp(DisasContext *ctx, uint32_t base, int16_t offset,
     TCGv tmp2 = tcg_temp_new();
 
     gen_base_offset_addr(ctx, taddr, base, offset);
-    tcg_gen_qemu_ld64(tval, taddr, ctx->mem_idx);
+    tcg_gen_qemu_ld_i64(tval, taddr, ctx->mem_idx, MO_TEUQ);
     if (cpu_is_bigendian(ctx)) {
         tcg_gen_extr_i64_tl(tmp2, tmp1, tval);
     } else {
diff --git a/target/mips/tcg/translate.c b/target/mips/tcg/translate.c
index 999fbb7cc1..a6ca2e5a3b 100644
--- a/target/mips/tcg/translate.c
+++ b/target/mips/tcg/translate.c
@@ -1949,13 +1949,13 @@ FOP_CONDNS(s, FMT_S, 32, gen_store_fpr32(ctx, fp0, fd))
 
 /* load/store instructions. */
 #ifdef CONFIG_USER_ONLY
-#define OP_LD_ATOMIC(insn, fname)                                          \
+#define OP_LD_ATOMIC(insn, memop)                                          \
 static inline void op_ld_##insn(TCGv ret, TCGv arg1, int mem_idx,          \
                                 DisasContext *ctx)                         \
 {                                                                          \
     TCGv t0 = tcg_temp_new();                                              \
     tcg_gen_mov_tl(t0, arg1);                                              \
-    tcg_gen_qemu_##fname(ret, arg1, ctx->mem_idx);                         \
+    tcg_gen_qemu_ld_tl(ret, arg1, ctx->mem_idx, memop);                    \
     tcg_gen_st_tl(t0, cpu_env, offsetof(CPUMIPSState, lladdr));            \
     tcg_gen_st_tl(ret, cpu_env, offsetof(CPUMIPSState, llval));            \
 }
@@ -1967,9 +1967,9 @@ static inline void op_ld_##insn(TCGv ret, TCGv arg1, int mem_idx,          \
     gen_helper_##insn(ret, cpu_env, arg1, tcg_constant_i32(mem_idx));      \
 }
 #endif
-OP_LD_ATOMIC(ll, ld32s);
+OP_LD_ATOMIC(ll, MO_TESL);
 #if defined(TARGET_MIPS64)
-OP_LD_ATOMIC(lld, ld64);
+OP_LD_ATOMIC(lld, MO_TEUQ);
 #endif
 #undef OP_LD_ATOMIC
 
diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c
index 46b874e94d..a05205beb1 100644
--- a/target/s390x/tcg/translate.c
+++ b/target/s390x/tcg/translate.c
@@ -1973,32 +1973,24 @@ static DisasJumpType op_clc(DisasContext *s, DisasOps *o)
 {
     int l = get_field(s, l1);
     TCGv_i32 vl;
+    MemOp mop;
 
     switch (l + 1) {
     case 1:
-        tcg_gen_qemu_ld8u(cc_src, o->addr1, get_mem_index(s));
-        tcg_gen_qemu_ld8u(cc_dst, o->in2, get_mem_index(s));
-        break;
     case 2:
-        tcg_gen_qemu_ld16u(cc_src, o->addr1, get_mem_index(s));
-        tcg_gen_qemu_ld16u(cc_dst, o->in2, get_mem_index(s));
-        break;
     case 4:
-        tcg_gen_qemu_ld32u(cc_src, o->addr1, get_mem_index(s));
-        tcg_gen_qemu_ld32u(cc_dst, o->in2, get_mem_index(s));
-        break;
     case 8:
-        tcg_gen_qemu_ld64(cc_src, o->addr1, get_mem_index(s));
-        tcg_gen_qemu_ld64(cc_dst, o->in2, get_mem_index(s));
-        break;
+        mop = ctz32(l + 1) | MO_TE;
+        tcg_gen_qemu_ld_tl(cc_src, o->addr1, get_mem_index(s), mop);
+        tcg_gen_qemu_ld_tl(cc_dst, o->in2, get_mem_index(s), mop);
+        gen_op_update2_cc_i64(s, CC_OP_LTUGTU_64, cc_src, cc_dst);
+        return DISAS_NEXT;
     default:
         vl = tcg_constant_i32(l);
         gen_helper_clc(cc_op, cpu_env, vl, o->addr1, o->in2);
         set_cc_static(s);
         return DISAS_NEXT;
     }
-    gen_op_update2_cc_i64(s, CC_OP_LTUGTU_64, cc_src, cc_dst);
-    return DISAS_NEXT;
 }
 
 static DisasJumpType op_clcl(DisasContext *s, DisasOps *o)
@@ -2199,7 +2191,7 @@ static DisasJumpType op_cvd(DisasContext *s, DisasOps *o)
     TCGv_i32 t2 = tcg_temp_new_i32();
     tcg_gen_extrl_i64_i32(t2, o->in1);
     gen_helper_cvd(t1, t2);
-    tcg_gen_qemu_st64(t1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(t1, o->in2, get_mem_index(s), MO_TEUQ);
     return DISAS_NEXT;
 }
 
@@ -2457,7 +2449,7 @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o)
     switch (m3) {
     case 0xf:
         /* Effectively a 32-bit load.  */
-        tcg_gen_qemu_ld32u(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_TEUL);
         len = 32;
         goto one_insert;
 
@@ -2465,7 +2457,7 @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o)
     case 0x6:
     case 0x3:
         /* Effectively a 16-bit load.  */
-        tcg_gen_qemu_ld16u(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_TEUW);
         len = 16;
         goto one_insert;
 
@@ -2474,7 +2466,7 @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o)
     case 0x2:
     case 0x1:
         /* Effectively an 8-bit load.  */
-        tcg_gen_qemu_ld8u(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_UB);
         len = 8;
         goto one_insert;
 
@@ -2490,7 +2482,7 @@ static DisasJumpType op_icm(DisasContext *s, DisasOps *o)
         ccm = 0;
         while (m3) {
             if (m3 & 0x8) {
-                tcg_gen_qemu_ld8u(tmp, o->in2, get_mem_index(s));
+                tcg_gen_qemu_ld_i64(tmp, o->in2, get_mem_index(s), MO_UB);
                 tcg_gen_addi_i64(o->in2, o->in2, 1);
                 tcg_gen_deposit_i64(o->out, o->out, tmp, pos, 8);
                 ccm |= 0xffull << pos;
@@ -2746,25 +2738,25 @@ static DisasJumpType op_llgt(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_ld8s(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_ld8s(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_SB);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_ld8u(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_ld8u(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_UB);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_ld16s(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_ld16s(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TESW);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_ld16u(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_ld16u(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUW);
     return DISAS_NEXT;
 }
 
@@ -2803,7 +2795,7 @@ static DisasJumpType op_lat(DisasContext *s, DisasOps *o)
 static DisasJumpType op_lgat(DisasContext *s, DisasOps *o)
 {
     TCGLabel *lab = gen_new_label();
-    tcg_gen_qemu_ld64(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUQ);
     /* The value is stored even in case of trap. */
     tcg_gen_brcondi_i64(TCG_COND_NE, o->out, 0, lab);
     gen_trap(s);
@@ -2825,7 +2817,8 @@ static DisasJumpType op_lfhat(DisasContext *s, DisasOps *o)
 static DisasJumpType op_llgfat(DisasContext *s, DisasOps *o)
 {
     TCGLabel *lab = gen_new_label();
-    tcg_gen_qemu_ld32u(o->out, o->in2, get_mem_index(s));
+
+    tcg_gen_qemu_ld_i64(o->out, o->in2, get_mem_index(s), MO_TEUL);
     /* The value is stored even in case of trap. */
     tcg_gen_brcondi_i64(TCG_COND_NE, o->out, 0, lab);
     gen_trap(s);
@@ -2942,7 +2935,7 @@ static DisasJumpType op_lpswe(DisasContext *s, DisasOps *o)
     tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s),
                         MO_TEUQ | MO_ALIGN_8);
     tcg_gen_addi_i64(o->in2, o->in2, 8);
-    tcg_gen_qemu_ld64(t2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t2, o->in2, get_mem_index(s), MO_TEUQ);
     gen_helper_load_psw(cpu_env, t1, t2);
     return DISAS_NORETURN;
 }
@@ -2966,7 +2959,7 @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o)
     /* Only one register to read. */
     t1 = tcg_temp_new_i64();
     if (unlikely(r1 == r3)) {
-        tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
         store_reg32_i64(r1, t1);
         return DISAS_NEXT;
     }
@@ -2974,9 +2967,9 @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o)
     /* First load the values of the first and last registers to trigger
        possible page faults. */
     t2 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
     tcg_gen_addi_i64(t2, o->in2, 4 * ((r3 - r1) & 15));
-    tcg_gen_qemu_ld32u(t2, t2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t2, t2, get_mem_index(s), MO_TEUL);
     store_reg32_i64(r1, t1);
     store_reg32_i64(r3, t2);
 
@@ -2991,7 +2984,7 @@ static DisasJumpType op_lm32(DisasContext *s, DisasOps *o)
     while (r1 != r3) {
         r1 = (r1 + 1) & 15;
         tcg_gen_add_i64(o->in2, o->in2, t2);
-        tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
         store_reg32_i64(r1, t1);
     }
     return DISAS_NEXT;
@@ -3006,7 +2999,7 @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o)
     /* Only one register to read. */
     t1 = tcg_temp_new_i64();
     if (unlikely(r1 == r3)) {
-        tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
         store_reg32h_i64(r1, t1);
         return DISAS_NEXT;
     }
@@ -3014,9 +3007,9 @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o)
     /* First load the values of the first and last registers to trigger
        possible page faults. */
     t2 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
     tcg_gen_addi_i64(t2, o->in2, 4 * ((r3 - r1) & 15));
-    tcg_gen_qemu_ld32u(t2, t2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t2, t2, get_mem_index(s), MO_TEUL);
     store_reg32h_i64(r1, t1);
     store_reg32h_i64(r3, t2);
 
@@ -3031,7 +3024,7 @@ static DisasJumpType op_lmh(DisasContext *s, DisasOps *o)
     while (r1 != r3) {
         r1 = (r1 + 1) & 15;
         tcg_gen_add_i64(o->in2, o->in2, t2);
-        tcg_gen_qemu_ld32u(t1, o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUL);
         store_reg32h_i64(r1, t1);
     }
     return DISAS_NEXT;
@@ -3045,7 +3038,7 @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o)
 
     /* Only one register to read. */
     if (unlikely(r1 == r3)) {
-        tcg_gen_qemu_ld64(regs[r1], o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(regs[r1], o->in2, get_mem_index(s), MO_TEUQ);
         return DISAS_NEXT;
     }
 
@@ -3053,9 +3046,9 @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o)
        possible page faults. */
     t1 = tcg_temp_new_i64();
     t2 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld64(t1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(t1, o->in2, get_mem_index(s), MO_TEUQ);
     tcg_gen_addi_i64(t2, o->in2, 8 * ((r3 - r1) & 15));
-    tcg_gen_qemu_ld64(regs[r3], t2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(regs[r3], t2, get_mem_index(s), MO_TEUQ);
     tcg_gen_mov_i64(regs[r1], t1);
 
     /* Only two registers to read. */
@@ -3069,7 +3062,7 @@ static DisasJumpType op_lm64(DisasContext *s, DisasOps *o)
     while (r1 != r3) {
         r1 = (r1 + 1) & 15;
         tcg_gen_add_i64(o->in2, o->in2, t1);
-        tcg_gen_qemu_ld64(regs[r1], o->in2, get_mem_index(s));
+        tcg_gen_qemu_ld_i64(regs[r1], o->in2, get_mem_index(s), MO_TEUQ);
     }
     return DISAS_NEXT;
 }
@@ -3923,15 +3916,15 @@ static DisasJumpType op_soc(DisasContext *s, DisasOps *o)
     a = get_address(s, 0, get_field(s, b2), get_field(s, d2));
     switch (s->insn->data) {
     case 1: /* STOCG */
-        tcg_gen_qemu_st64(regs[r1], a, get_mem_index(s));
+        tcg_gen_qemu_st_i64(regs[r1], a, get_mem_index(s), MO_TEUQ);
         break;
     case 0: /* STOC */
-        tcg_gen_qemu_st32(regs[r1], a, get_mem_index(s));
+        tcg_gen_qemu_st_i64(regs[r1], a, get_mem_index(s), MO_TEUL);
         break;
     case 2: /* STOCFH */
         h = tcg_temp_new_i64();
         tcg_gen_shri_i64(h, regs[r1], 32);
-        tcg_gen_qemu_st32(h, a, get_mem_index(s));
+        tcg_gen_qemu_st_i64(h, a, get_mem_index(s), MO_TEUL);
         break;
     default:
         g_assert_not_reached();
@@ -4050,7 +4043,7 @@ static DisasJumpType op_ectg(DisasContext *s, DisasOps *o)
     gen_addi_and_wrap_i64(s, o->addr1, regs[r3], 0);
 
     /* load the third operand into r3 before modifying anything */
-    tcg_gen_qemu_ld64(regs[r3], o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(regs[r3], o->addr1, get_mem_index(s), MO_TEUQ);
 
     /* subtract CPU timer from first operand and store in GR0 */
     gen_helper_stpt(tmp, cpu_env);
@@ -4128,9 +4121,9 @@ static DisasJumpType op_stcke(DisasContext *s, DisasOps *o)
     tcg_gen_shri_i64(c1, c1, 8);
     tcg_gen_ori_i64(c2, c2, 0x10000);
     tcg_gen_or_i64(c2, c2, todpr);
-    tcg_gen_qemu_st64(c1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(c1, o->in2, get_mem_index(s), MO_TEUQ);
     tcg_gen_addi_i64(o->in2, o->in2, 8);
-    tcg_gen_qemu_st64(c2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(c2, o->in2, get_mem_index(s), MO_TEUQ);
     /* ??? We don't implement clock states.  */
     gen_op_movi_cc(s, 0);
     return DISAS_NEXT;
@@ -4343,7 +4336,7 @@ static DisasJumpType op_stnosm(DisasContext *s, DisasOps *o)
        restart, we'll have the wrong SYSTEM MASK in place.  */
     t = tcg_temp_new_i64();
     tcg_gen_shri_i64(t, psw_mask, 56);
-    tcg_gen_qemu_st8(t, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_st_i64(t, o->addr1, get_mem_index(s), MO_UB);
 
     if (s->fields.op == 0xac) {
         tcg_gen_andi_i64(psw_mask, psw_mask,
@@ -4380,13 +4373,13 @@ static DisasJumpType op_stfle(DisasContext *s, DisasOps *o)
 
 static DisasJumpType op_st8(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st8(o->in1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->in1, o->in2, get_mem_index(s), MO_UB);
     return DISAS_NEXT;
 }
 
 static DisasJumpType op_st16(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st16(o->in1, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->in1, o->in2, get_mem_index(s), MO_TEUW);
     return DISAS_NEXT;
 }
 
@@ -4424,7 +4417,7 @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o)
     case 0xf:
         /* Effectively a 32-bit store.  */
         tcg_gen_shri_i64(tmp, o->in1, pos);
-        tcg_gen_qemu_st32(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_TEUL);
         break;
 
     case 0xc:
@@ -4432,7 +4425,7 @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o)
     case 0x3:
         /* Effectively a 16-bit store.  */
         tcg_gen_shri_i64(tmp, o->in1, pos);
-        tcg_gen_qemu_st16(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_TEUW);
         break;
 
     case 0x8:
@@ -4441,7 +4434,7 @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o)
     case 0x1:
         /* Effectively an 8-bit store.  */
         tcg_gen_shri_i64(tmp, o->in1, pos);
-        tcg_gen_qemu_st8(tmp, o->in2, get_mem_index(s));
+        tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_UB);
         break;
 
     default:
@@ -4450,7 +4443,7 @@ static DisasJumpType op_stcm(DisasContext *s, DisasOps *o)
         while (m3) {
             if (m3 & 0x8) {
                 tcg_gen_shri_i64(tmp, o->in1, pos);
-                tcg_gen_qemu_st8(tmp, o->in2, get_mem_index(s));
+                tcg_gen_qemu_st_i64(tmp, o->in2, get_mem_index(s), MO_UB);
                 tcg_gen_addi_i64(o->in2, o->in2, 1);
             }
             m3 = (m3 << 1) & 0xf;
@@ -4469,11 +4462,8 @@ static DisasJumpType op_stm(DisasContext *s, DisasOps *o)
     TCGv_i64 tsize = tcg_constant_i64(size);
 
     while (1) {
-        if (size == 8) {
-            tcg_gen_qemu_st64(regs[r1], o->in2, get_mem_index(s));
-        } else {
-            tcg_gen_qemu_st32(regs[r1], o->in2, get_mem_index(s));
-        }
+        tcg_gen_qemu_st_i64(regs[r1], o->in2, get_mem_index(s),
+                            size == 8 ? MO_TEUQ : MO_TEUL);
         if (r1 == r3) {
             break;
         }
@@ -4494,7 +4484,7 @@ static DisasJumpType op_stmh(DisasContext *s, DisasOps *o)
 
     while (1) {
         tcg_gen_shl_i64(t, regs[r1], t32);
-        tcg_gen_qemu_st32(t, o->in2, get_mem_index(s));
+        tcg_gen_qemu_st_i64(t, o->in2, get_mem_index(s), MO_TEUL);
         if (r1 == r3) {
             break;
         }
@@ -4804,28 +4794,28 @@ static DisasJumpType op_xc(DisasContext *s, DisasOps *o)
 
         l++;
         while (l >= 8) {
-            tcg_gen_qemu_st64(o->in2, o->addr1, get_mem_index(s));
+            tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UQ);
             l -= 8;
             if (l > 0) {
                 tcg_gen_addi_i64(o->addr1, o->addr1, 8);
             }
         }
         if (l >= 4) {
-            tcg_gen_qemu_st32(o->in2, o->addr1, get_mem_index(s));
+            tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UL);
             l -= 4;
             if (l > 0) {
                 tcg_gen_addi_i64(o->addr1, o->addr1, 4);
             }
         }
         if (l >= 2) {
-            tcg_gen_qemu_st16(o->in2, o->addr1, get_mem_index(s));
+            tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UW);
             l -= 2;
             if (l > 0) {
                 tcg_gen_addi_i64(o->addr1, o->addr1, 2);
             }
         }
         if (l) {
-            tcg_gen_qemu_st8(o->in2, o->addr1, get_mem_index(s));
+            tcg_gen_qemu_st_i64(o->in2, o->addr1, get_mem_index(s), MO_UB);
         }
         gen_op_movi_cc(s, 0);
         return DISAS_NEXT;
@@ -5314,13 +5304,13 @@ static void wout_cond_e1e2(DisasContext *s, DisasOps *o)
 
 static void wout_m1_8(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st8(o->out, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_UB);
 }
 #define SPEC_wout_m1_8 0
 
 static void wout_m1_16(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st16(o->out, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUW);
 }
 #define SPEC_wout_m1_16 0
 
@@ -5334,7 +5324,7 @@ static void wout_m1_16a(DisasContext *s, DisasOps *o)
 
 static void wout_m1_32(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st32(o->out, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUL);
 }
 #define SPEC_wout_m1_32 0
 
@@ -5348,7 +5338,7 @@ static void wout_m1_32a(DisasContext *s, DisasOps *o)
 
 static void wout_m1_64(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st64(o->out, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->out, o->addr1, get_mem_index(s), MO_TEUQ);
 }
 #define SPEC_wout_m1_64 0
 
@@ -5362,7 +5352,7 @@ static void wout_m1_64a(DisasContext *s, DisasOps *o)
 
 static void wout_m2_32(DisasContext *s, DisasOps *o)
 {
-    tcg_gen_qemu_st32(o->out, o->in2, get_mem_index(s));
+    tcg_gen_qemu_st_i64(o->out, o->in2, get_mem_index(s), MO_TEUL);
 }
 #define SPEC_wout_m2_32 0
 
@@ -5557,7 +5547,7 @@ static void in1_m1_8u(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld8u(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_UB);
 }
 #define SPEC_in1_m1_8u 0
 
@@ -5565,7 +5555,7 @@ static void in1_m1_16s(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld16s(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TESW);
 }
 #define SPEC_in1_m1_16s 0
 
@@ -5573,7 +5563,7 @@ static void in1_m1_16u(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld16u(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUW);
 }
 #define SPEC_in1_m1_16u 0
 
@@ -5581,7 +5571,7 @@ static void in1_m1_32s(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld32s(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TESL);
 }
 #define SPEC_in1_m1_32s 0
 
@@ -5589,7 +5579,7 @@ static void in1_m1_32u(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld32u(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUL);
 }
 #define SPEC_in1_m1_32u 0
 
@@ -5597,7 +5587,7 @@ static void in1_m1_64(DisasContext *s, DisasOps *o)
 {
     in1_la1(s, o);
     o->in1 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld64(o->in1, o->addr1, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in1, o->addr1, get_mem_index(s), MO_TEUQ);
 }
 #define SPEC_in1_m1_64 0
 
@@ -5811,35 +5801,35 @@ static void in2_sh(DisasContext *s, DisasOps *o)
 static void in2_m2_8u(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld8u(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_UB);
 }
 #define SPEC_in2_m2_8u 0
 
 static void in2_m2_16s(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld16s(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TESW);
 }
 #define SPEC_in2_m2_16s 0
 
 static void in2_m2_16u(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld16u(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUW);
 }
 #define SPEC_in2_m2_16u 0
 
 static void in2_m2_32s(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld32s(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TESL);
 }
 #define SPEC_in2_m2_32s 0
 
 static void in2_m2_32u(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld32u(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUL);
 }
 #define SPEC_in2_m2_32u 0
 
@@ -5855,14 +5845,14 @@ static void in2_m2_32ua(DisasContext *s, DisasOps *o)
 static void in2_m2_64(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld64(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUQ);
 }
 #define SPEC_in2_m2_64 0
 
 static void in2_m2_64w(DisasContext *s, DisasOps *o)
 {
     in2_a2(s, o);
-    tcg_gen_qemu_ld64(o->in2, o->in2, get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, o->in2, get_mem_index(s), MO_TEUQ);
     gen_addi_and_wrap_i64(s, o->in2, o->in2, 0);
 }
 #define SPEC_in2_m2_64w 0
@@ -5879,14 +5869,14 @@ static void in2_m2_64a(DisasContext *s, DisasOps *o)
 static void in2_mri2_16s(DisasContext *s, DisasOps *o)
 {
     o->in2 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld16s(o->in2, gen_ri2(s), get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, gen_ri2(s), get_mem_index(s), MO_TESW);
 }
 #define SPEC_in2_mri2_16s 0
 
 static void in2_mri2_16u(DisasContext *s, DisasOps *o)
 {
     o->in2 = tcg_temp_new_i64();
-    tcg_gen_qemu_ld16u(o->in2, gen_ri2(s), get_mem_index(s));
+    tcg_gen_qemu_ld_i64(o->in2, gen_ri2(s), get_mem_index(s), MO_TEUW);
 }
 #define SPEC_in2_mri2_16u 0
 
diff --git a/target/sparc/ldst_helper.c b/target/sparc/ldst_helper.c
index a53580d9e4..7972d56a72 100644
--- a/target/sparc/ldst_helper.c
+++ b/target/sparc/ldst_helper.c
@@ -593,6 +593,7 @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr,
 #if defined(DEBUG_MXCC) || defined(DEBUG_ASI)
     uint32_t last_addr = addr;
 #endif
+    MemOpIdx oi;
 
     do_check_align(env, addr, size - 1, GETPC());
     switch (asi) {
@@ -692,19 +693,20 @@ uint64_t helper_ld_asi(CPUSPARCState *env, target_ulong addr,
     case ASI_M_IODIAG:  /* Turbosparc IOTLB Diagnostic */
         break;
     case ASI_KERNELTXT: /* Supervisor code access */
+        oi = make_memop_idx(memop, cpu_mmu_index(env, true));
         switch (size) {
         case 1:
-            ret = cpu_ldub_code(env, addr);
+            ret = cpu_ldb_code_mmu(env, addr, oi, GETPC());
             break;
         case 2:
-            ret = cpu_lduw_code(env, addr);
+            ret = cpu_ldw_code_mmu(env, addr, oi, GETPC());
             break;
         default:
         case 4:
-            ret = cpu_ldl_code(env, addr);
+            ret = cpu_ldl_code_mmu(env, addr, oi, GETPC());
             break;
         case 8:
-            ret = cpu_ldq_code(env, addr);
+            ret = cpu_ldq_code_mmu(env, addr, oi, GETPC());
             break;
         }
         break;
diff --git a/target/sparc/translate.c b/target/sparc/translate.c
index 137bdc5159..414e014b11 100644
--- a/target/sparc/translate.c
+++ b/target/sparc/translate.c
@@ -1899,7 +1899,7 @@ static void gen_swap(DisasContext *dc, TCGv dst, TCGv src,
                      TCGv addr, int mmu_idx, MemOp memop)
 {
     gen_address_mask(dc, addr);
-    tcg_gen_atomic_xchg_tl(dst, addr, src, mmu_idx, memop);
+    tcg_gen_atomic_xchg_tl(dst, addr, src, mmu_idx, memop | MO_ALIGN);
 }
 
 static void gen_ldstub(DisasContext *dc, TCGv dst, TCGv addr, int mmu_idx)
@@ -2155,12 +2155,12 @@ static void gen_ld_asi(DisasContext *dc, TCGv dst, TCGv addr,
         break;
     case GET_ASI_DIRECT:
         gen_address_mask(dc, addr);
-        tcg_gen_qemu_ld_tl(dst, addr, da.mem_idx, da.memop);
+        tcg_gen_qemu_ld_tl(dst, addr, da.mem_idx, da.memop | MO_ALIGN);
         break;
     default:
         {
             TCGv_i32 r_asi = tcg_constant_i32(da.asi);
-            TCGv_i32 r_mop = tcg_constant_i32(memop);
+            TCGv_i32 r_mop = tcg_constant_i32(memop | MO_ALIGN);
 
             save_state(dc);
 #ifdef TARGET_SPARC64
@@ -2201,7 +2201,7 @@ static void gen_st_asi(DisasContext *dc, TCGv src, TCGv addr,
         /* fall through */
     case GET_ASI_DIRECT:
         gen_address_mask(dc, addr);
-        tcg_gen_qemu_st_tl(src, addr, da.mem_idx, da.memop);
+        tcg_gen_qemu_st_tl(src, addr, da.mem_idx, da.memop | MO_ALIGN);
         break;
 #if !defined(TARGET_SPARC64) && !defined(CONFIG_USER_ONLY)
     case GET_ASI_BCOPY:
@@ -2233,7 +2233,7 @@ static void gen_st_asi(DisasContext *dc, TCGv src, TCGv addr,
     default:
         {
             TCGv_i32 r_asi = tcg_constant_i32(da.asi);
-            TCGv_i32 r_mop = tcg_constant_i32(memop & MO_SIZE);
+            TCGv_i32 r_mop = tcg_constant_i32(memop | MO_ALIGN);
 
             save_state(dc);
 #ifdef TARGET_SPARC64
@@ -2283,7 +2283,7 @@ static void gen_cas_asi(DisasContext *dc, TCGv addr, TCGv cmpv,
     case GET_ASI_DIRECT:
         oldv = tcg_temp_new();
         tcg_gen_atomic_cmpxchg_tl(oldv, addr, cmpv, gen_load_gpr(dc, rd),
-                                  da.mem_idx, da.memop);
+                                  da.mem_idx, da.memop | MO_ALIGN);
         gen_store_gpr(dc, rd, oldv);
         break;
     default:
@@ -2347,7 +2347,7 @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr,
         switch (size) {
         case 4:
             d32 = gen_dest_fpr_F(dc);
-            tcg_gen_qemu_ld_i32(d32, addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_ld_i32(d32, addr, da.mem_idx, da.memop | MO_ALIGN);
             gen_store_fpr_F(dc, rd, d32);
             break;
         case 8:
@@ -2397,7 +2397,8 @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr,
         /* Valid for lddfa only.  */
         if (size == 8) {
             gen_address_mask(dc, addr);
-            tcg_gen_qemu_ld_i64(cpu_fpr[rd / 2], addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_ld_i64(cpu_fpr[rd / 2], addr, da.mem_idx,
+                                da.memop | MO_ALIGN);
         } else {
             gen_exception(dc, TT_ILL_INSN);
         }
@@ -2406,7 +2407,7 @@ static void gen_ldf_asi(DisasContext *dc, TCGv addr,
     default:
         {
             TCGv_i32 r_asi = tcg_constant_i32(da.asi);
-            TCGv_i32 r_mop = tcg_constant_i32(da.memop);
+            TCGv_i32 r_mop = tcg_constant_i32(da.memop | MO_ALIGN);
 
             save_state(dc);
             /* According to the table in the UA2011 manual, the only
@@ -2454,7 +2455,7 @@ static void gen_stf_asi(DisasContext *dc, TCGv addr,
         switch (size) {
         case 4:
             d32 = gen_load_fpr_F(dc, rd);
-            tcg_gen_qemu_st_i32(d32, addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_st_i32(d32, addr, da.mem_idx, da.memop | MO_ALIGN);
             break;
         case 8:
             tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx,
@@ -2506,7 +2507,8 @@ static void gen_stf_asi(DisasContext *dc, TCGv addr,
         /* Valid for stdfa only.  */
         if (size == 8) {
             gen_address_mask(dc, addr);
-            tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_st_i64(cpu_fpr[rd / 2], addr, da.mem_idx,
+                                da.memop | MO_ALIGN);
         } else {
             gen_exception(dc, TT_ILL_INSN);
         }
@@ -2543,7 +2545,7 @@ static void gen_ldda_asi(DisasContext *dc, TCGv addr, int insn, int rd)
             TCGv_i64 tmp = tcg_temp_new_i64();
 
             gen_address_mask(dc, addr);
-            tcg_gen_qemu_ld_i64(tmp, addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_ld_i64(tmp, addr, da.mem_idx, da.memop | MO_ALIGN);
 
             /* Note that LE ldda acts as if each 32-bit register
                result is byte swapped.  Having just performed one
@@ -2613,7 +2615,7 @@ static void gen_stda_asi(DisasContext *dc, TCGv hi, TCGv addr,
                 tcg_gen_concat32_i64(t64, hi, lo);
             }
             gen_address_mask(dc, addr);
-            tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop);
+            tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN);
         }
         break;
 
@@ -2651,7 +2653,7 @@ static void gen_casx_asi(DisasContext *dc, TCGv addr, TCGv cmpv,
     case GET_ASI_DIRECT:
         oldv = tcg_temp_new();
         tcg_gen_atomic_cmpxchg_tl(oldv, addr, cmpv, gen_load_gpr(dc, rd),
-                                  da.mem_idx, da.memop);
+                                  da.mem_idx, da.memop | MO_ALIGN);
         gen_store_gpr(dc, rd, oldv);
         break;
     default:
@@ -2678,7 +2680,7 @@ static void gen_ldda_asi(DisasContext *dc, TCGv addr, int insn, int rd)
         return;
     case GET_ASI_DIRECT:
         gen_address_mask(dc, addr);
-        tcg_gen_qemu_ld_i64(t64, addr, da.mem_idx, da.memop);
+        tcg_gen_qemu_ld_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN);
         break;
     default:
         {
@@ -2710,7 +2712,7 @@ static void gen_stda_asi(DisasContext *dc, TCGv hi, TCGv addr,
         break;
     case GET_ASI_DIRECT:
         gen_address_mask(dc, addr);
-        tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop);
+        tcg_gen_qemu_st_i64(t64, addr, da.mem_idx, da.memop | MO_ALIGN);
         break;
     case GET_ASI_BFILL:
         /* Store 32 bytes of T64 to ADDR.  */
@@ -5179,15 +5181,18 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                 switch (xop) {
                 case 0x0:       /* ld, V9 lduw, load unsigned word */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld32u(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUL | MO_ALIGN);
                     break;
                 case 0x1:       /* ldub, load unsigned byte */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld8u(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_UB);
                     break;
                 case 0x2:       /* lduh, load unsigned halfword */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld16u(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUW | MO_ALIGN);
                     break;
                 case 0x3:       /* ldd, load double word */
                     if (rd & 1)
@@ -5197,7 +5202,8 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
 
                         gen_address_mask(dc, cpu_addr);
                         t64 = tcg_temp_new_i64();
-                        tcg_gen_qemu_ld64(t64, cpu_addr, dc->mem_idx);
+                        tcg_gen_qemu_ld_i64(t64, cpu_addr,
+                                            dc->mem_idx, MO_TEUQ | MO_ALIGN);
                         tcg_gen_trunc_i64_tl(cpu_val, t64);
                         tcg_gen_ext32u_tl(cpu_val, cpu_val);
                         gen_store_gpr(dc, rd + 1, cpu_val);
@@ -5208,11 +5214,12 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                     break;
                 case 0x9:       /* ldsb, load signed byte */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld8s(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr, dc->mem_idx, MO_SB);
                     break;
                 case 0xa:       /* ldsh, load signed halfword */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld16s(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TESW | MO_ALIGN);
                     break;
                 case 0xd:       /* ldstub */
                     gen_ldstub(dc, cpu_val, cpu_addr, dc->mem_idx);
@@ -5266,11 +5273,13 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
 #ifdef TARGET_SPARC64
                 case 0x08: /* V9 ldsw */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld32s(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TESL | MO_ALIGN);
                     break;
                 case 0x0b: /* V9 ldx */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_ld64(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_ld_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUQ | MO_ALIGN);
                     break;
                 case 0x18: /* V9 ldswa */
                     gen_ld_asi(dc, cpu_val, cpu_addr, insn, MO_TESL);
@@ -5321,7 +5330,7 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                     gen_address_mask(dc, cpu_addr);
                     cpu_dst_32 = gen_dest_fpr_F(dc);
                     tcg_gen_qemu_ld_i32(cpu_dst_32, cpu_addr,
-                                        dc->mem_idx, MO_TEUL);
+                                        dc->mem_idx, MO_TEUL | MO_ALIGN);
                     gen_store_fpr_F(dc, rd, cpu_dst_32);
                     break;
                 case 0x21:      /* ldfsr, V9 ldxfsr */
@@ -5330,14 +5339,14 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                     if (rd == 1) {
                         TCGv_i64 t64 = tcg_temp_new_i64();
                         tcg_gen_qemu_ld_i64(t64, cpu_addr,
-                                            dc->mem_idx, MO_TEUQ);
+                                            dc->mem_idx, MO_TEUQ | MO_ALIGN);
                         gen_helper_ldxfsr(cpu_fsr, cpu_env, cpu_fsr, t64);
                         break;
                     }
 #endif
                     cpu_dst_32 = tcg_temp_new_i32();
                     tcg_gen_qemu_ld_i32(cpu_dst_32, cpu_addr,
-                                        dc->mem_idx, MO_TEUL);
+                                        dc->mem_idx, MO_TEUL | MO_ALIGN);
                     gen_helper_ldfsr(cpu_fsr, cpu_env, cpu_fsr, cpu_dst_32);
                     break;
                 case 0x22:      /* ldqf, load quad fpreg */
@@ -5369,15 +5378,17 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                 switch (xop) {
                 case 0x4: /* st, store word */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_st32(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_st_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUL | MO_ALIGN);
                     break;
                 case 0x5: /* stb, store byte */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_st8(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_st_tl(cpu_val, cpu_addr, dc->mem_idx, MO_UB);
                     break;
                 case 0x6: /* sth, store halfword */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_st16(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_st_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUW | MO_ALIGN);
                     break;
                 case 0x7: /* std, store double word */
                     if (rd & 1)
@@ -5390,7 +5401,8 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                         lo = gen_load_gpr(dc, rd + 1);
                         t64 = tcg_temp_new_i64();
                         tcg_gen_concat_tl_i64(t64, lo, cpu_val);
-                        tcg_gen_qemu_st64(t64, cpu_addr, dc->mem_idx);
+                        tcg_gen_qemu_st_i64(t64, cpu_addr,
+                                            dc->mem_idx, MO_TEUQ | MO_ALIGN);
                     }
                     break;
 #if !defined(CONFIG_USER_ONLY) || defined(TARGET_SPARC64)
@@ -5413,7 +5425,8 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
 #ifdef TARGET_SPARC64
                 case 0x0e: /* V9 stx */
                     gen_address_mask(dc, cpu_addr);
-                    tcg_gen_qemu_st64(cpu_val, cpu_addr, dc->mem_idx);
+                    tcg_gen_qemu_st_tl(cpu_val, cpu_addr,
+                                       dc->mem_idx, MO_TEUQ | MO_ALIGN);
                     break;
                 case 0x1e: /* V9 stxa */
                     gen_st_asi(dc, cpu_val, cpu_addr, insn, MO_TEUQ);
@@ -5431,18 +5444,20 @@ static void disas_sparc_insn(DisasContext * dc, unsigned int insn)
                     gen_address_mask(dc, cpu_addr);
                     cpu_src1_32 = gen_load_fpr_F(dc, rd);
                     tcg_gen_qemu_st_i32(cpu_src1_32, cpu_addr,
-                                        dc->mem_idx, MO_TEUL);
+                                        dc->mem_idx, MO_TEUL | MO_ALIGN);
                     break;
                 case 0x25: /* stfsr, V9 stxfsr */
                     {
 #ifdef TARGET_SPARC64
                         gen_address_mask(dc, cpu_addr);
                         if (rd == 1) {
-                            tcg_gen_qemu_st64(cpu_fsr, cpu_addr, dc->mem_idx);
+                            tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr,
+                                               dc->mem_idx, MO_TEUQ | MO_ALIGN);
                             break;
                         }
 #endif
-                        tcg_gen_qemu_st32(cpu_fsr, cpu_addr, dc->mem_idx);
+                        tcg_gen_qemu_st_tl(cpu_fsr, cpu_addr,
+                                           dc->mem_idx, MO_TEUL | MO_ALIGN);
                     }
                     break;
                 case 0x26:
diff --git a/target/xtensa/translate.c b/target/xtensa/translate.c
index 0cf3075649..728aeebebf 100644
--- a/target/xtensa/translate.c
+++ b/target/xtensa/translate.c
@@ -1549,7 +1549,7 @@ static void translate_dcache(DisasContext *dc, const OpcodeArg arg[],
     TCGv_i32 res = tcg_temp_new_i32();
 
     tcg_gen_addi_i32(addr, arg[0].in, arg[1].imm);
-    tcg_gen_qemu_ld8u(res, addr, dc->cring);
+    tcg_gen_qemu_ld_i32(res, addr, dc->cring, MO_UB);
 }
 
 static void translate_depbits(DisasContext *dc, const OpcodeArg arg[],
@@ -1726,7 +1726,7 @@ static void translate_l32r(DisasContext *dc, const OpcodeArg arg[],
     } else {
         tmp = tcg_constant_i32(arg[1].imm);
     }
-    tcg_gen_qemu_ld32u(arg[0].out, tmp, dc->cring);
+    tcg_gen_qemu_ld_i32(arg[0].out, tmp, dc->cring, MO_TEUL);
 }
 
 static void translate_loop(DisasContext *dc, const OpcodeArg arg[],