summary refs log tree commit diff stats
path: root/tcg
diff options
context:
space:
mode:
Diffstat (limited to 'tcg')
-rw-r--r--tcg/README22
-rw-r--r--tcg/aarch64/tcg-target.c.inc125
-rw-r--r--tcg/aarch64/tcg-target.h2
-rw-r--r--tcg/arm/tcg-target.c.inc295
-rw-r--r--tcg/arm/tcg-target.h2
-rw-r--r--tcg/i386/tcg-target.c.inc20
-rw-r--r--tcg/mips/tcg-target.c.inc102
-rw-r--r--tcg/optimize.c56
-rw-r--r--tcg/ppc/tcg-target.c.inc228
-rw-r--r--tcg/riscv/tcg-target.c.inc64
-rw-r--r--tcg/s390/tcg-target.c.inc34
-rw-r--r--tcg/tcg-op-gvec.c122
-rw-r--r--tcg/tcg-op.c145
-rw-r--r--tcg/tcg.c28
-rw-r--r--tcg/tci.c3
-rw-r--r--tcg/tci/tcg-target.c.inc23
16 files changed, 790 insertions, 481 deletions
diff --git a/tcg/README b/tcg/README
index 8510d823e3..c2e7762a37 100644
--- a/tcg/README
+++ b/tcg/README
@@ -295,19 +295,25 @@ ext32u_i64 t0, t1
 
 8, 16 or 32 bit sign/zero extension (both operands must have the same type)
 
-* bswap16_i32/i64 t0, t1
+* bswap16_i32/i64 t0, t1, flags
 
-16 bit byte swap on a 32/64 bit value. It assumes that the two/six high order
-bytes are set to zero.
+16 bit byte swap on the low bits of a 32/64 bit input.
+If flags & TCG_BSWAP_IZ, then t1 is known to be zero-extended from bit 15.
+If flags & TCG_BSWAP_OZ, then t0 will be zero-extended from bit 15.
+If flags & TCG_BSWAP_OS, then t0 will be sign-extended from bit 15.
+If neither TCG_BSWAP_OZ nor TCG_BSWAP_OS are set, then the bits of
+t0 above bit 15 may contain any value.
 
-* bswap32_i32/i64 t0, t1
+* bswap32_i64 t0, t1, flags
 
-32 bit byte swap on a 32/64 bit value. With a 64 bit value, it assumes that
-the four high order bytes are set to zero.
+32 bit byte swap on a 64-bit value.  The flags are the same as for bswap16,
+except they apply from bit 31 instead of bit 15.
 
-* bswap64_i64 t0, t1
+* bswap32_i32 t0, t1, flags
+* bswap64_i64 t0, t1, flags
 
-64 bit byte swap
+32/64 bit byte swap.  The flags are ignored, but still present
+for consistency with the other bswap opcodes.
 
 * discard_i32/i64 t0
 
diff --git a/tcg/aarch64/tcg-target.c.inc b/tcg/aarch64/tcg-target.c.inc
index 27cde314a9..5924977b42 100644
--- a/tcg/aarch64/tcg-target.c.inc
+++ b/tcg/aarch64/tcg-target.c.inc
@@ -475,9 +475,7 @@ typedef enum {
     /* Data-processing (1 source) instructions.  */
     I3507_CLZ       = 0x5ac01000,
     I3507_RBIT      = 0x5ac00000,
-    I3507_REV16     = 0x5ac00400,
-    I3507_REV32     = 0x5ac00800,
-    I3507_REV64     = 0x5ac00c00,
+    I3507_REV       = 0x5ac00000, /* + size << 10 */
 
     /* Data-processing (2 source) instructions.  */
     I3508_LSLV      = 0x1ac02000,
@@ -1417,19 +1415,11 @@ static void tcg_out_brcond(TCGContext *s, TCGType ext, TCGCond c, TCGArg a,
     }
 }
 
-static inline void tcg_out_rev64(TCGContext *s, TCGReg rd, TCGReg rn)
-{
-    tcg_out_insn(s, 3507, REV64, TCG_TYPE_I64, rd, rn);
-}
-
-static inline void tcg_out_rev32(TCGContext *s, TCGReg rd, TCGReg rn)
-{
-    tcg_out_insn(s, 3507, REV32, TCG_TYPE_I32, rd, rn);
-}
-
-static inline void tcg_out_rev16(TCGContext *s, TCGReg rd, TCGReg rn)
+static inline void tcg_out_rev(TCGContext *s, int ext, MemOp s_bits,
+                               TCGReg rd, TCGReg rn)
 {
-    tcg_out_insn(s, 3507, REV16, TCG_TYPE_I32, rd, rn);
+    /* REV, REV16, REV32 */
+    tcg_out_insn_3507(s, I3507_REV | (s_bits << 10), ext, rd, rn);
 }
 
 static inline void tcg_out_sxt(TCGContext *s, TCGType ext, MemOp s_bits,
@@ -1557,28 +1547,34 @@ static void tcg_out_cltz(TCGContext *s, TCGType ext, TCGReg d,
 /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
  *                                     TCGMemOpIdx oi, uintptr_t ra)
  */
-static void * const qemu_ld_helpers[16] = {
-    [MO_UB]   = helper_ret_ldub_mmu,
-    [MO_LEUW] = helper_le_lduw_mmu,
-    [MO_LEUL] = helper_le_ldul_mmu,
-    [MO_LEQ]  = helper_le_ldq_mmu,
-    [MO_BEUW] = helper_be_lduw_mmu,
-    [MO_BEUL] = helper_be_ldul_mmu,
-    [MO_BEQ]  = helper_be_ldq_mmu,
+static void * const qemu_ld_helpers[4] = {
+    [MO_8]  = helper_ret_ldub_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_16] = helper_be_lduw_mmu,
+    [MO_32] = helper_be_ldul_mmu,
+    [MO_64] = helper_be_ldq_mmu,
+#else
+    [MO_16] = helper_le_lduw_mmu,
+    [MO_32] = helper_le_ldul_mmu,
+    [MO_64] = helper_le_ldq_mmu,
+#endif
 };
 
 /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
  *                                     uintxx_t val, TCGMemOpIdx oi,
  *                                     uintptr_t ra)
  */
-static void * const qemu_st_helpers[16] = {
-    [MO_UB]   = helper_ret_stb_mmu,
-    [MO_LEUW] = helper_le_stw_mmu,
-    [MO_LEUL] = helper_le_stl_mmu,
-    [MO_LEQ]  = helper_le_stq_mmu,
-    [MO_BEUW] = helper_be_stw_mmu,
-    [MO_BEUL] = helper_be_stl_mmu,
-    [MO_BEQ]  = helper_be_stq_mmu,
+static void * const qemu_st_helpers[4] = {
+    [MO_8]  = helper_ret_stb_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_16] = helper_be_stw_mmu,
+    [MO_32] = helper_be_stl_mmu,
+    [MO_64] = helper_be_stq_mmu,
+#else
+    [MO_16] = helper_le_stw_mmu,
+    [MO_32] = helper_le_stl_mmu,
+    [MO_64] = helper_le_stq_mmu,
+#endif
 };
 
 static inline void tcg_out_adr(TCGContext *s, TCGReg rd, const void *target)
@@ -1602,7 +1598,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
     tcg_out_mov(s, TARGET_LONG_BITS == 64, TCG_REG_X1, lb->addrlo_reg);
     tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X2, oi);
     tcg_out_adr(s, TCG_REG_X3, lb->raddr);
-    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    tcg_out_call(s, qemu_ld_helpers[opc & MO_SIZE]);
     if (opc & MO_SIGN) {
         tcg_out_sxt(s, lb->type, size, lb->datalo_reg, TCG_REG_X0);
     } else {
@@ -1628,7 +1624,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
     tcg_out_mov(s, size == MO_64, TCG_REG_X2, lb->datalo_reg);
     tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_X3, oi);
     tcg_out_adr(s, TCG_REG_X4, lb->raddr);
-    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    tcg_out_call(s, qemu_st_helpers[opc & MO_SIZE]);
     tcg_out_goto(s, lb->raddr);
     return true;
 }
@@ -1724,7 +1720,8 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp memop, TCGType ext,
                                    TCGReg data_r, TCGReg addr_r,
                                    TCGType otype, TCGReg off_r)
 {
-    const MemOp bswap = memop & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((memop & MO_BSWAP) == 0);
 
     switch (memop & MO_SSIZE) {
     case MO_UB:
@@ -1736,40 +1733,19 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, MemOp memop, TCGType ext,
         break;
     case MO_UW:
         tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
-        if (bswap) {
-            tcg_out_rev16(s, data_r, data_r);
-        }
         break;
     case MO_SW:
-        if (bswap) {
-            tcg_out_ldst_r(s, I3312_LDRH, data_r, addr_r, otype, off_r);
-            tcg_out_rev16(s, data_r, data_r);
-            tcg_out_sxt(s, ext, MO_16, data_r, data_r);
-        } else {
-            tcg_out_ldst_r(s, (ext ? I3312_LDRSHX : I3312_LDRSHW),
-                           data_r, addr_r, otype, off_r);
-        }
+        tcg_out_ldst_r(s, (ext ? I3312_LDRSHX : I3312_LDRSHW),
+                       data_r, addr_r, otype, off_r);
         break;
     case MO_UL:
         tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
-        if (bswap) {
-            tcg_out_rev32(s, data_r, data_r);
-        }
         break;
     case MO_SL:
-        if (bswap) {
-            tcg_out_ldst_r(s, I3312_LDRW, data_r, addr_r, otype, off_r);
-            tcg_out_rev32(s, data_r, data_r);
-            tcg_out_sxt(s, TCG_TYPE_I64, MO_32, data_r, data_r);
-        } else {
-            tcg_out_ldst_r(s, I3312_LDRSWX, data_r, addr_r, otype, off_r);
-        }
+        tcg_out_ldst_r(s, I3312_LDRSWX, data_r, addr_r, otype, off_r);
         break;
     case MO_Q:
         tcg_out_ldst_r(s, I3312_LDRX, data_r, addr_r, otype, off_r);
-        if (bswap) {
-            tcg_out_rev64(s, data_r, data_r);
-        }
         break;
     default:
         tcg_abort();
@@ -1780,31 +1756,20 @@ static void tcg_out_qemu_st_direct(TCGContext *s, MemOp memop,
                                    TCGReg data_r, TCGReg addr_r,
                                    TCGType otype, TCGReg off_r)
 {
-    const MemOp bswap = memop & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((memop & MO_BSWAP) == 0);
 
     switch (memop & MO_SIZE) {
     case MO_8:
         tcg_out_ldst_r(s, I3312_STRB, data_r, addr_r, otype, off_r);
         break;
     case MO_16:
-        if (bswap && data_r != TCG_REG_XZR) {
-            tcg_out_rev16(s, TCG_REG_TMP, data_r);
-            data_r = TCG_REG_TMP;
-        }
         tcg_out_ldst_r(s, I3312_STRH, data_r, addr_r, otype, off_r);
         break;
     case MO_32:
-        if (bswap && data_r != TCG_REG_XZR) {
-            tcg_out_rev32(s, TCG_REG_TMP, data_r);
-            data_r = TCG_REG_TMP;
-        }
         tcg_out_ldst_r(s, I3312_STRW, data_r, addr_r, otype, off_r);
         break;
     case MO_64:
-        if (bswap && data_r != TCG_REG_XZR) {
-            tcg_out_rev64(s, TCG_REG_TMP, data_r);
-            data_r = TCG_REG_TMP;
-        }
         tcg_out_ldst_r(s, I3312_STRX, data_r, addr_r, otype, off_r);
         break;
     default:
@@ -2184,15 +2149,27 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
 
     case INDEX_op_bswap64_i64:
-        tcg_out_rev64(s, a0, a1);
+        tcg_out_rev(s, TCG_TYPE_I64, MO_64, a0, a1);
         break;
     case INDEX_op_bswap32_i64:
+        tcg_out_rev(s, TCG_TYPE_I32, MO_32, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tcg_out_sxt(s, TCG_TYPE_I64, MO_32, a0, a0);
+        }
+        break;
     case INDEX_op_bswap32_i32:
-        tcg_out_rev32(s, a0, a1);
+        tcg_out_rev(s, TCG_TYPE_I32, MO_32, a0, a1);
         break;
     case INDEX_op_bswap16_i64:
     case INDEX_op_bswap16_i32:
-        tcg_out_rev16(s, a0, a1);
+        tcg_out_rev(s, TCG_TYPE_I32, MO_16, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            /* Output must be sign-extended. */
+            tcg_out_sxt(s, ext, MO_16, a0, a0);
+        } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            /* Output must be zero-extended, but input isn't. */
+            tcg_out_uxt(s, MO_16, a0, a0);
+        }
         break;
 
     case INDEX_op_ext8s_i64:
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index ef55f7c185..551baf8da3 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -148,7 +148,7 @@ typedef enum {
 #define TCG_TARGET_HAS_cmpsel_vec       0
 
 #define TCG_TARGET_DEFAULT_MO (0)
-#define TCG_TARGET_HAS_MEMORY_BSWAP     1
+#define TCG_TARGET_HAS_MEMORY_BSWAP     0
 
 void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t, uintptr_t);
 
diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index 5157143246..7a761a602e 100644
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -1013,50 +1013,71 @@ static inline void tcg_out_ext16u(TCGContext *s, int cond,
     }
 }
 
-static inline void tcg_out_bswap16s(TCGContext *s, int cond, int rd, int rn)
+static void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn, int flags)
 {
     if (use_armv6_instructions) {
-        /* revsh */
-        tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn);
-    } else {
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_ASR(16));
-        tcg_out_dat_reg(s, cond, ARITH_ORR,
-                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
-    }
-}
+        if (flags & TCG_BSWAP_OS) {
+            /* revsh */
+            tcg_out32(s, 0x06ff0fb0 | (cond << 28) | (rd << 12) | rn);
+            return;
+        }
 
-static inline void tcg_out_bswap16(TCGContext *s, int cond, int rd, int rn)
-{
-    if (use_armv6_instructions) {
         /* rev16 */
         tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
-    } else {
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, rn, SHIFT_IMM_LSL(24));
-        tcg_out_dat_reg(s, cond, ARITH_MOV,
-                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSR(16));
-        tcg_out_dat_reg(s, cond, ARITH_ORR,
-                        rd, TCG_REG_TMP, rn, SHIFT_IMM_LSR(8));
+        if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            /* uxth */
+            tcg_out32(s, 0x06ff0070 | (cond << 28) | (rd << 12) | rd);
+        }
+        return;
     }
-}
 
-/* swap the two low bytes assuming that the two high input bytes and the
-   two high output bit can hold any value. */
-static inline void tcg_out_bswap16st(TCGContext *s, int cond, int rd, int rn)
-{
-    if (use_armv6_instructions) {
-        /* rev16 */
-        tcg_out32(s, 0x06bf0fb0 | (cond << 28) | (rd << 12) | rn);
-    } else {
+    if (flags == 0) {
+        /*
+         * For stores, no input or output extension:
+         *                              rn  = xxAB
+         * lsr tmp, rn, #8              tmp = 0xxA
+         * and tmp, tmp, #0xff          tmp = 000A
+         * orr rd, tmp, rn, lsl #8      rd  = xABA
+         */
         tcg_out_dat_reg(s, cond, ARITH_MOV,
                         TCG_REG_TMP, 0, rn, SHIFT_IMM_LSR(8));
         tcg_out_dat_imm(s, cond, ARITH_AND, TCG_REG_TMP, TCG_REG_TMP, 0xff);
         tcg_out_dat_reg(s, cond, ARITH_ORR,
                         rd, TCG_REG_TMP, rn, SHIFT_IMM_LSL(8));
+        return;
+    }
+
+    /*
+     * Byte swap, leaving the result at the top of the register.
+     * We will then shift down, zero or sign-extending.
+     */
+    if (flags & TCG_BSWAP_IZ) {
+        /*
+         *                              rn  = 00AB
+         * ror tmp, rn, #8              tmp = B00A
+         * orr tmp, tmp, tmp, lsl #16   tmp = BA00
+         */
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, rn, SHIFT_IMM_ROR(8));
+        tcg_out_dat_reg(s, cond, ARITH_ORR,
+                        TCG_REG_TMP, TCG_REG_TMP, TCG_REG_TMP,
+                        SHIFT_IMM_LSL(16));
+    } else {
+        /*
+         *                              rn  = xxAB
+         * and tmp, rn, #0xff00         tmp = 00A0
+         * lsl tmp, tmp, #8             tmp = 0A00
+         * orr tmp, tmp, rn, lsl #24    tmp = BA00
+         */
+        tcg_out_dat_rI(s, cond, ARITH_AND, TCG_REG_TMP, rn, 0xff00, 1);
+        tcg_out_dat_reg(s, cond, ARITH_MOV,
+                        TCG_REG_TMP, 0, TCG_REG_TMP, SHIFT_IMM_LSL(8));
+        tcg_out_dat_reg(s, cond, ARITH_ORR,
+                        TCG_REG_TMP, TCG_REG_TMP, rn, SHIFT_IMM_LSL(24));
     }
+    tcg_out_dat_reg(s, cond, ARITH_MOV, rd, 0, TCG_REG_TMP,
+                    (flags & TCG_BSWAP_OS
+                     ? SHIFT_IMM_ASR(8) : SHIFT_IMM_LSR(8)));
 }
 
 static inline void tcg_out_bswap32(TCGContext *s, int cond, int rd, int rn)
@@ -1372,34 +1393,38 @@ static void tcg_out_vldst(TCGContext *s, ARMInsn insn,
 /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
  *                                     int mmu_idx, uintptr_t ra)
  */
-static void * const qemu_ld_helpers[16] = {
+static void * const qemu_ld_helpers[8] = {
     [MO_UB]   = helper_ret_ldub_mmu,
     [MO_SB]   = helper_ret_ldsb_mmu,
-
-    [MO_LEUW] = helper_le_lduw_mmu,
-    [MO_LEUL] = helper_le_ldul_mmu,
-    [MO_LEQ]  = helper_le_ldq_mmu,
-    [MO_LESW] = helper_le_ldsw_mmu,
-    [MO_LESL] = helper_le_ldul_mmu,
-
-    [MO_BEUW] = helper_be_lduw_mmu,
-    [MO_BEUL] = helper_be_ldul_mmu,
-    [MO_BEQ]  = helper_be_ldq_mmu,
-    [MO_BESW] = helper_be_ldsw_mmu,
-    [MO_BESL] = helper_be_ldul_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_UW] = helper_be_lduw_mmu,
+    [MO_UL] = helper_be_ldul_mmu,
+    [MO_Q]  = helper_be_ldq_mmu,
+    [MO_SW] = helper_be_ldsw_mmu,
+    [MO_SL] = helper_be_ldul_mmu,
+#else
+    [MO_UW] = helper_le_lduw_mmu,
+    [MO_UL] = helper_le_ldul_mmu,
+    [MO_Q]  = helper_le_ldq_mmu,
+    [MO_SW] = helper_le_ldsw_mmu,
+    [MO_SL] = helper_le_ldul_mmu,
+#endif
 };
 
 /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
  *                                     uintxx_t val, int mmu_idx, uintptr_t ra)
  */
-static void * const qemu_st_helpers[16] = {
-    [MO_UB]   = helper_ret_stb_mmu,
-    [MO_LEUW] = helper_le_stw_mmu,
-    [MO_LEUL] = helper_le_stl_mmu,
-    [MO_LEQ]  = helper_le_stq_mmu,
-    [MO_BEUW] = helper_be_stw_mmu,
-    [MO_BEUL] = helper_be_stl_mmu,
-    [MO_BEQ]  = helper_be_stq_mmu,
+static void * const qemu_st_helpers[4] = {
+    [MO_8]   = helper_ret_stb_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_16] = helper_be_stw_mmu,
+    [MO_32] = helper_be_stl_mmu,
+    [MO_64] = helper_be_stq_mmu,
+#else
+    [MO_16] = helper_le_stw_mmu,
+    [MO_32] = helper_le_stl_mmu,
+    [MO_64] = helper_le_stq_mmu,
+#endif
 };
 
 /* Helper routines for marshalling helper function arguments into
@@ -1604,9 +1629,9 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
        icache usage.  For pre-armv6, use the signed helpers since we do
        not have a single insn sign-extend.  */
     if (use_armv6_instructions) {
-        func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)];
+        func = qemu_ld_helpers[opc & MO_SIZE];
     } else {
-        func = qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)];
+        func = qemu_ld_helpers[opc & MO_SSIZE];
         if (opc & MO_SIGN) {
             opc = MO_UL;
         }
@@ -1684,7 +1709,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *lb)
     argreg = tcg_out_arg_reg32(s, argreg, TCG_REG_R14);
 
     /* Tail-call to the helper, which will return to the fast path.  */
-    tcg_out_goto(s, COND_AL, qemu_st_helpers[opc & (MO_BSWAP | MO_SIZE)]);
+    tcg_out_goto(s, COND_AL, qemu_st_helpers[opc & MO_SIZE]);
     return true;
 }
 #endif /* SOFTMMU */
@@ -1693,7 +1718,8 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
                                          TCGReg datalo, TCGReg datahi,
                                          TCGReg addrlo, TCGReg addend)
 {
-    MemOp bswap = opc & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & MO_SSIZE) {
     case MO_UB:
@@ -1704,49 +1730,30 @@ static inline void tcg_out_qemu_ld_index(TCGContext *s, MemOp opc,
         break;
     case MO_UW:
         tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
-        if (bswap) {
-            tcg_out_bswap16(s, COND_AL, datalo, datalo);
-        }
         break;
     case MO_SW:
-        if (bswap) {
-            tcg_out_ld16u_r(s, COND_AL, datalo, addrlo, addend);
-            tcg_out_bswap16s(s, COND_AL, datalo, datalo);
-        } else {
-            tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
-        }
+        tcg_out_ld16s_r(s, COND_AL, datalo, addrlo, addend);
         break;
     case MO_UL:
-    default:
         tcg_out_ld32_r(s, COND_AL, datalo, addrlo, addend);
-        if (bswap) {
-            tcg_out_bswap32(s, COND_AL, datalo, datalo);
-        }
         break;
     case MO_Q:
-        {
-            TCGReg dl = (bswap ? datahi : datalo);
-            TCGReg dh = (bswap ? datalo : datahi);
-
-            /* Avoid ldrd for user-only emulation, to handle unaligned.  */
-            if (USING_SOFTMMU && use_armv6_instructions
-                && (dl & 1) == 0 && dh == dl + 1) {
-                tcg_out_ldrd_r(s, COND_AL, dl, addrlo, addend);
-            } else if (dl != addend) {
-                tcg_out_ld32_rwb(s, COND_AL, dl, addend, addrlo);
-                tcg_out_ld32_12(s, COND_AL, dh, addend, 4);
-            } else {
-                tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
-                                addend, addrlo, SHIFT_IMM_LSL(0));
-                tcg_out_ld32_12(s, COND_AL, dl, TCG_REG_TMP, 0);
-                tcg_out_ld32_12(s, COND_AL, dh, TCG_REG_TMP, 4);
-            }
-            if (bswap) {
-                tcg_out_bswap32(s, COND_AL, dl, dl);
-                tcg_out_bswap32(s, COND_AL, dh, dh);
-            }
+        /* Avoid ldrd for user-only emulation, to handle unaligned.  */
+        if (USING_SOFTMMU && use_armv6_instructions
+            && (datalo & 1) == 0 && datahi == datalo + 1) {
+            tcg_out_ldrd_r(s, COND_AL, datalo, addrlo, addend);
+        } else if (datalo != addend) {
+            tcg_out_ld32_rwb(s, COND_AL, datalo, addend, addrlo);
+            tcg_out_ld32_12(s, COND_AL, datahi, addend, 4);
+        } else {
+            tcg_out_dat_reg(s, COND_AL, ARITH_ADD, TCG_REG_TMP,
+                            addend, addrlo, SHIFT_IMM_LSL(0));
+            tcg_out_ld32_12(s, COND_AL, datalo, TCG_REG_TMP, 0);
+            tcg_out_ld32_12(s, COND_AL, datahi, TCG_REG_TMP, 4);
         }
         break;
+    default:
+        g_assert_not_reached();
     }
 }
 
@@ -1754,7 +1761,8 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc,
                                           TCGReg datalo, TCGReg datahi,
                                           TCGReg addrlo)
 {
-    MemOp bswap = opc & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & MO_SSIZE) {
     case MO_UB:
@@ -1765,47 +1773,28 @@ static inline void tcg_out_qemu_ld_direct(TCGContext *s, MemOp opc,
         break;
     case MO_UW:
         tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
-        if (bswap) {
-            tcg_out_bswap16(s, COND_AL, datalo, datalo);
-        }
         break;
     case MO_SW:
-        if (bswap) {
-            tcg_out_ld16u_8(s, COND_AL, datalo, addrlo, 0);
-            tcg_out_bswap16s(s, COND_AL, datalo, datalo);
-        } else {
-            tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
-        }
+        tcg_out_ld16s_8(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_UL:
-    default:
         tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
-        if (bswap) {
-            tcg_out_bswap32(s, COND_AL, datalo, datalo);
-        }
         break;
     case MO_Q:
-        {
-            TCGReg dl = (bswap ? datahi : datalo);
-            TCGReg dh = (bswap ? datalo : datahi);
-
-            /* Avoid ldrd for user-only emulation, to handle unaligned.  */
-            if (USING_SOFTMMU && use_armv6_instructions
-                && (dl & 1) == 0 && dh == dl + 1) {
-                tcg_out_ldrd_8(s, COND_AL, dl, addrlo, 0);
-            } else if (dl == addrlo) {
-                tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
-                tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
-            } else {
-                tcg_out_ld32_12(s, COND_AL, dl, addrlo, bswap ? 4 : 0);
-                tcg_out_ld32_12(s, COND_AL, dh, addrlo, bswap ? 0 : 4);
-            }
-            if (bswap) {
-                tcg_out_bswap32(s, COND_AL, dl, dl);
-                tcg_out_bswap32(s, COND_AL, dh, dh);
-            }
+        /* Avoid ldrd for user-only emulation, to handle unaligned.  */
+        if (USING_SOFTMMU && use_armv6_instructions
+            && (datalo & 1) == 0 && datahi == datalo + 1) {
+            tcg_out_ldrd_8(s, COND_AL, datalo, addrlo, 0);
+        } else if (datalo == addrlo) {
+            tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4);
+            tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
+        } else {
+            tcg_out_ld32_12(s, COND_AL, datalo, addrlo, 0);
+            tcg_out_ld32_12(s, COND_AL, datahi, addrlo, 4);
         }
         break;
+    default:
+        g_assert_not_reached();
     }
 }
 
@@ -1854,44 +1843,31 @@ static inline void tcg_out_qemu_st_index(TCGContext *s, int cond, MemOp opc,
                                          TCGReg datalo, TCGReg datahi,
                                          TCGReg addrlo, TCGReg addend)
 {
-    MemOp bswap = opc & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & MO_SIZE) {
     case MO_8:
         tcg_out_st8_r(s, cond, datalo, addrlo, addend);
         break;
     case MO_16:
-        if (bswap) {
-            tcg_out_bswap16st(s, cond, TCG_REG_R0, datalo);
-            tcg_out_st16_r(s, cond, TCG_REG_R0, addrlo, addend);
-        } else {
-            tcg_out_st16_r(s, cond, datalo, addrlo, addend);
-        }
+        tcg_out_st16_r(s, cond, datalo, addrlo, addend);
         break;
     case MO_32:
-    default:
-        if (bswap) {
-            tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
-            tcg_out_st32_r(s, cond, TCG_REG_R0, addrlo, addend);
-        } else {
-            tcg_out_st32_r(s, cond, datalo, addrlo, addend);
-        }
+        tcg_out_st32_r(s, cond, datalo, addrlo, addend);
         break;
     case MO_64:
         /* Avoid strd for user-only emulation, to handle unaligned.  */
-        if (bswap) {
-            tcg_out_bswap32(s, cond, TCG_REG_R0, datahi);
-            tcg_out_st32_rwb(s, cond, TCG_REG_R0, addend, addrlo);
-            tcg_out_bswap32(s, cond, TCG_REG_R0, datalo);
-            tcg_out_st32_12(s, cond, TCG_REG_R0, addend, 4);
-        } else if (USING_SOFTMMU && use_armv6_instructions
-                   && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (USING_SOFTMMU && use_armv6_instructions
+            && (datalo & 1) == 0 && datahi == datalo + 1) {
             tcg_out_strd_r(s, cond, datalo, addrlo, addend);
         } else {
             tcg_out_st32_rwb(s, cond, datalo, addend, addrlo);
             tcg_out_st32_12(s, cond, datahi, addend, 4);
         }
         break;
+    default:
+        g_assert_not_reached();
     }
 }
 
@@ -1899,44 +1875,31 @@ static inline void tcg_out_qemu_st_direct(TCGContext *s, MemOp opc,
                                           TCGReg datalo, TCGReg datahi,
                                           TCGReg addrlo)
 {
-    MemOp bswap = opc & MO_BSWAP;
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & MO_SIZE) {
     case MO_8:
         tcg_out_st8_12(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_16:
-        if (bswap) {
-            tcg_out_bswap16st(s, COND_AL, TCG_REG_R0, datalo);
-            tcg_out_st16_8(s, COND_AL, TCG_REG_R0, addrlo, 0);
-        } else {
-            tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
-        }
+        tcg_out_st16_8(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_32:
-    default:
-        if (bswap) {
-            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
-            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
-        } else {
-            tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
-        }
+        tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
         break;
     case MO_64:
         /* Avoid strd for user-only emulation, to handle unaligned.  */
-        if (bswap) {
-            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datahi);
-            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 0);
-            tcg_out_bswap32(s, COND_AL, TCG_REG_R0, datalo);
-            tcg_out_st32_12(s, COND_AL, TCG_REG_R0, addrlo, 4);
-        } else if (USING_SOFTMMU && use_armv6_instructions
-                   && (datalo & 1) == 0 && datahi == datalo + 1) {
+        if (USING_SOFTMMU && use_armv6_instructions
+            && (datalo & 1) == 0 && datahi == datalo + 1) {
             tcg_out_strd_8(s, COND_AL, datalo, addrlo, 0);
         } else {
             tcg_out_st32_12(s, COND_AL, datalo, addrlo, 0);
             tcg_out_st32_12(s, COND_AL, datahi, addrlo, 4);
         }
         break;
+    default:
+        g_assert_not_reached();
     }
 }
 
@@ -2245,7 +2208,7 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
 
     case INDEX_op_bswap16_i32:
-        tcg_out_bswap16(s, COND_AL, args[0], args[1]);
+        tcg_out_bswap16(s, COND_AL, args[0], args[1], args[2]);
         break;
     case INDEX_op_bswap32_i32:
         tcg_out_bswap32(s, COND_AL, args[0], args[1]);
diff --git a/tcg/arm/tcg-target.h b/tcg/arm/tcg-target.h
index 57fd0c0c74..95fcef33bc 100644
--- a/tcg/arm/tcg-target.h
+++ b/tcg/arm/tcg-target.h
@@ -174,7 +174,7 @@ extern bool use_neon_instructions;
 #define TCG_TARGET_HAS_cmpsel_vec       0
 
 #define TCG_TARGET_DEFAULT_MO (0)
-#define TCG_TARGET_HAS_MEMORY_BSWAP     1
+#define TCG_TARGET_HAS_MEMORY_BSWAP     0
 
 /* not defined -- call should be eliminated at compile time */
 void tb_target_set_jmp_target(uintptr_t, uintptr_t, uintptr_t, uintptr_t);
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 34113388ef..98d924b91a 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -2421,10 +2421,28 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
 
     OP_32_64(bswap16):
-        tcg_out_rolw_8(s, a0);
+        if (a2 & TCG_BSWAP_OS) {
+            /* Output must be sign-extended. */
+            if (rexw) {
+                tcg_out_bswap64(s, a0);
+                tcg_out_shifti(s, SHIFT_SAR + rexw, a0, 48);
+            } else {
+                tcg_out_bswap32(s, a0);
+                tcg_out_shifti(s, SHIFT_SAR, a0, 16);
+            }
+        } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            /* Output must be zero-extended, but input isn't. */
+            tcg_out_bswap32(s, a0);
+            tcg_out_shifti(s, SHIFT_SHR, a0, 16);
+        } else {
+            tcg_out_rolw_8(s, a0);
+        }
         break;
     OP_32_64(bswap32):
         tcg_out_bswap32(s, a0);
+        if (rexw && (a2 & TCG_BSWAP_OS)) {
+            tcg_out_ext32s(s, a0, a0);
+        }
         break;
 
     OP_32_64(neg):
diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index 5944448b2a..bf0eb84e2d 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -540,39 +540,37 @@ static void tcg_out_movi(TCGContext *s, TCGType type,
     }
 }
 
-static inline void tcg_out_bswap16(TCGContext *s, TCGReg ret, TCGReg arg)
+static void tcg_out_bswap16(TCGContext *s, TCGReg ret, TCGReg arg, int flags)
 {
+    /* ret and arg can't be register tmp0 */
+    tcg_debug_assert(ret != TCG_TMP0);
+    tcg_debug_assert(arg != TCG_TMP0);
+
+    /* With arg = abcd: */
     if (use_mips32r2_instructions) {
-        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
-    } else {
-        /* ret and arg can't be register at */
-        if (ret == TCG_TMP0 || arg == TCG_TMP0) {
-            tcg_abort();
+        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);                 /* badc */
+        if (flags & TCG_BSWAP_OS) {
+            tcg_out_opc_reg(s, OPC_SEH, ret, 0, ret);              /* ssdc */
+        } else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xffff);        /* 00dc */
         }
-
-        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);
-        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 8);
-        tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xff00);
-        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
+        return;
     }
-}
 
-static inline void tcg_out_bswap16s(TCGContext *s, TCGReg ret, TCGReg arg)
-{
-    if (use_mips32r2_instructions) {
-        tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
-        tcg_out_opc_reg(s, OPC_SEH, ret, 0, ret);
+    tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);                  /* 0abc */
+    if (!(flags & TCG_BSWAP_IZ)) {
+        tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP0, TCG_TMP0, 0x00ff);  /* 000c */
+    }
+    if (flags & TCG_BSWAP_OS) {
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);                  /* d000 */
+        tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16);                  /* ssd0 */
     } else {
-        /* ret and arg can't be register at */
-        if (ret == TCG_TMP0 || arg == TCG_TMP0) {
-            tcg_abort();
+        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 8);                   /* bcd0 */
+        if (flags & TCG_BSWAP_OZ) {
+            tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xff00);        /* 00d0 */
         }
-
-        tcg_out_opc_sa(s, OPC_SRL, TCG_TMP0, arg, 8);
-        tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);
-        tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16);
-        tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);
     }
+    tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_TMP0);                /* ssdc */
 }
 
 static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub)
@@ -581,27 +579,20 @@ static void tcg_out_bswap_subr(TCGContext *s, const tcg_insn_unit *sub)
     tcg_debug_assert(ok);
 }
 
-static void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg)
+static void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg, int flags)
 {
     if (use_mips32r2_instructions) {
         tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
         tcg_out_opc_sa(s, OPC_ROTR, ret, ret, 16);
+        if (flags & TCG_BSWAP_OZ) {
+            tcg_out_opc_bf(s, OPC_DEXT, ret, ret, 31, 0);
+        }
     } else {
-        tcg_out_bswap_subr(s, bswap32_addr);
-        /* delay slot -- never omit the insn, like tcg_out_mov might.  */
-        tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
-        tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
-    }
-}
-
-static void tcg_out_bswap32u(TCGContext *s, TCGReg ret, TCGReg arg)
-{
-    if (use_mips32r2_instructions) {
-        tcg_out_opc_reg(s, OPC_DSBH, ret, 0, arg);
-        tcg_out_opc_reg(s, OPC_DSHD, ret, 0, ret);
-        tcg_out_dsrl(s, ret, ret, 32);
-    } else {
-        tcg_out_bswap_subr(s, bswap32u_addr);
+        if (flags & TCG_BSWAP_OZ) {
+            tcg_out_bswap_subr(s, bswap32u_addr);
+        } else {
+            tcg_out_bswap_subr(s, bswap32_addr);
+        }
         /* delay slot -- never omit the insn, like tcg_out_mov might.  */
         tcg_out_opc_reg(s, OPC_OR, TCG_TMP0, arg, TCG_REG_ZERO);
         tcg_out_mov(s, TCG_TYPE_I32, ret, TCG_TMP3);
@@ -1367,14 +1358,14 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         break;
     case MO_UW | MO_BSWAP:
         tcg_out_opc_imm(s, OPC_LHU, TCG_TMP1, base, 0);
-        tcg_out_bswap16(s, lo, TCG_TMP1);
+        tcg_out_bswap16(s, lo, TCG_TMP1, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
         break;
     case MO_UW:
         tcg_out_opc_imm(s, OPC_LHU, lo, base, 0);
         break;
     case MO_SW | MO_BSWAP:
         tcg_out_opc_imm(s, OPC_LHU, TCG_TMP1, base, 0);
-        tcg_out_bswap16s(s, lo, TCG_TMP1);
+        tcg_out_bswap16(s, lo, TCG_TMP1, TCG_BSWAP_IZ | TCG_BSWAP_OS);
         break;
     case MO_SW:
         tcg_out_opc_imm(s, OPC_LH, lo, base, 0);
@@ -1383,7 +1374,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         if (TCG_TARGET_REG_BITS == 64 && is_64) {
             if (use_mips32r2_instructions) {
                 tcg_out_opc_imm(s, OPC_LWU, lo, base, 0);
-                tcg_out_bswap32u(s, lo, lo);
+                tcg_out_bswap32(s, lo, lo, TCG_BSWAP_IZ | TCG_BSWAP_OZ);
             } else {
                 tcg_out_bswap_subr(s, bswap32u_addr);
                 /* delay slot */
@@ -1396,7 +1387,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
     case MO_SL | MO_BSWAP:
         if (use_mips32r2_instructions) {
             tcg_out_opc_imm(s, OPC_LW, lo, base, 0);
-            tcg_out_bswap32(s, lo, lo);
+            tcg_out_bswap32(s, lo, lo, 0);
         } else {
             tcg_out_bswap_subr(s, bswap32_addr);
             /* delay slot */
@@ -1514,8 +1505,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         break;
 
     case MO_16 | MO_BSWAP:
-        tcg_out_opc_imm(s, OPC_ANDI, TCG_TMP1, lo, 0xffff);
-        tcg_out_bswap16(s, TCG_TMP1, TCG_TMP1);
+        tcg_out_bswap16(s, TCG_TMP1, lo, 0);
         lo = TCG_TMP1;
         /* FALLTHRU */
     case MO_16:
@@ -1523,7 +1513,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
         break;
 
     case MO_32 | MO_BSWAP:
-        tcg_out_bswap32(s, TCG_TMP3, lo);
+        tcg_out_bswap32(s, TCG_TMP3, lo, 0);
         lo = TCG_TMP3;
         /* FALLTHRU */
     case MO_32:
@@ -1542,9 +1532,9 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP0, base, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP1, base, 4);
         } else {
-            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? lo : hi);
+            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? lo : hi, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP3, base, 0);
-            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? hi : lo);
+            tcg_out_bswap32(s, TCG_TMP3, MIPS_BE ? hi : lo, 0);
             tcg_out_opc_imm(s, OPC_SW, TCG_TMP3, base, 4);
         }
         break;
@@ -1933,10 +1923,6 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_not_i64:
         i1 = OPC_NOR;
         goto do_unary;
-    case INDEX_op_bswap16_i32:
-    case INDEX_op_bswap16_i64:
-        i1 = OPC_WSBH;
-        goto do_unary;
     case INDEX_op_ext8s_i32:
     case INDEX_op_ext8s_i64:
         i1 = OPC_SEB;
@@ -1948,11 +1934,15 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_opc_reg(s, i1, a0, TCG_REG_ZERO, a1);
         break;
 
+    case INDEX_op_bswap16_i32:
+    case INDEX_op_bswap16_i64:
+        tcg_out_bswap16(s, a0, a1, a2);
+        break;
     case INDEX_op_bswap32_i32:
-        tcg_out_bswap32(s, a0, a1);
+        tcg_out_bswap32(s, a0, a1, 0);
         break;
     case INDEX_op_bswap32_i64:
-        tcg_out_bswap32u(s, a0, a1);
+        tcg_out_bswap32(s, a0, a1, a2);
         break;
     case INDEX_op_bswap64_i64:
         tcg_out_bswap64(s, a0, a1);
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 211a4209a0..9876ac52a8 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -355,10 +355,12 @@ static uint64_t do_constant_folding_2(TCGOpcode op, uint64_t x, uint64_t y)
         return (uint16_t)x;
 
     CASE_OP_32_64(bswap16):
-        return bswap16(x);
+        x = bswap16(x);
+        return y & TCG_BSWAP_OS ? (int16_t)x : x;
 
     CASE_OP_32_64(bswap32):
-        return bswap32(x);
+        x = bswap32(x);
+        return y & TCG_BSWAP_OS ? (int32_t)x : x;
 
     case INDEX_op_bswap64_i64:
         return bswap64(x);
@@ -1029,6 +1031,42 @@ void tcg_optimize(TCGContext *s)
             }
             break;
 
+        CASE_OP_32_64(bswap16):
+            mask = arg_info(op->args[1])->mask;
+            if (mask <= 0xffff) {
+                op->args[2] |= TCG_BSWAP_IZ;
+            }
+            mask = bswap16(mask);
+            switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) {
+            case TCG_BSWAP_OZ:
+                break;
+            case TCG_BSWAP_OS:
+                mask = (int16_t)mask;
+                break;
+            default: /* undefined high bits */
+                mask |= MAKE_64BIT_MASK(16, 48);
+                break;
+            }
+            break;
+
+        case INDEX_op_bswap32_i64:
+            mask = arg_info(op->args[1])->mask;
+            if (mask <= 0xffffffffu) {
+                op->args[2] |= TCG_BSWAP_IZ;
+            }
+            mask = bswap32(mask);
+            switch (op->args[2] & (TCG_BSWAP_OZ | TCG_BSWAP_OS)) {
+            case TCG_BSWAP_OZ:
+                break;
+            case TCG_BSWAP_OS:
+                mask = (int32_t)mask;
+                break;
+            default: /* undefined high bits */
+                mask |= MAKE_64BIT_MASK(32, 32);
+                break;
+            }
+            break;
+
         default:
             break;
         }
@@ -1135,9 +1173,6 @@ void tcg_optimize(TCGContext *s)
         CASE_OP_32_64(ext16s):
         CASE_OP_32_64(ext16u):
         CASE_OP_32_64(ctpop):
-        CASE_OP_32_64(bswap16):
-        CASE_OP_32_64(bswap32):
-        case INDEX_op_bswap64_i64:
         case INDEX_op_ext32s_i64:
         case INDEX_op_ext32u_i64:
         case INDEX_op_ext_i32_i64:
@@ -1151,6 +1186,17 @@ void tcg_optimize(TCGContext *s)
             }
             goto do_default;
 
+        CASE_OP_32_64(bswap16):
+        CASE_OP_32_64(bswap32):
+        case INDEX_op_bswap64_i64:
+            if (arg_is_const(op->args[1])) {
+                tmp = do_constant_folding(opc, arg_info(op->args[1])->val,
+                                          op->args[2]);
+                tcg_opt_gen_movi(s, &temps_used, op, op->args[0], tmp);
+                break;
+            }
+            goto do_default;
+
         CASE_OP_32_64(add):
         CASE_OP_32_64(sub):
         CASE_OP_32_64(mul):
diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 795701442b..e0f4665213 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -413,6 +413,10 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
 #define SRAD   XO31(794)
 #define SRADI  XO31(413<<1)
 
+#define BRH    XO31(219)
+#define BRW    XO31(155)
+#define BRD    XO31(187)
+
 #define TW     XO31( 4)
 #define TRAP   (TW | TO(31))
 
@@ -738,6 +742,26 @@ static inline void tcg_out_rlw(TCGContext *s, int op, TCGReg ra, TCGReg rs,
     tcg_out32(s, op | RA(ra) | RS(rs) | SH(sh) | MB(mb) | ME(me));
 }
 
+static inline void tcg_out_ext8s(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out32(s, EXTSB | RA(dst) | RS(src));
+}
+
+static inline void tcg_out_ext16s(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out32(s, EXTSH | RA(dst) | RS(src));
+}
+
+static inline void tcg_out_ext16u(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out32(s, ANDI | SAI(src, dst, 0xffff));
+}
+
+static inline void tcg_out_ext32s(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    tcg_out32(s, EXTSW | RA(dst) | RS(src));
+}
+
 static inline void tcg_out_ext32u(TCGContext *s, TCGReg dst, TCGReg src)
 {
     tcg_out_rld(s, RLDICL, dst, src, 0, 32);
@@ -753,6 +777,12 @@ static inline void tcg_out_shli64(TCGContext *s, TCGReg dst, TCGReg src, int c)
     tcg_out_rld(s, RLDICR, dst, src, c, 63 - c);
 }
 
+static inline void tcg_out_sari32(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    /* Limit immediate shift count lest we create an illegal insn.  */
+    tcg_out32(s, SRAWI | RA(dst) | RS(src) | SH(c & 31));
+}
+
 static inline void tcg_out_shri32(TCGContext *s, TCGReg dst, TCGReg src, int c)
 {
     tcg_out_rlw(s, RLWINM, dst, src, 32 - c, c, 31);
@@ -763,6 +793,116 @@ static inline void tcg_out_shri64(TCGContext *s, TCGReg dst, TCGReg src, int c)
     tcg_out_rld(s, RLDICL, dst, src, 64 - c, c);
 }
 
+static inline void tcg_out_sari64(TCGContext *s, TCGReg dst, TCGReg src, int c)
+{
+    tcg_out32(s, SRADI | RA(dst) | RS(src) | SH(c & 0x1f) | ((c >> 4) & 2));
+}
+
+static void tcg_out_bswap16(TCGContext *s, TCGReg dst, TCGReg src, int flags)
+{
+    TCGReg tmp = dst == src ? TCG_REG_R0 : dst;
+
+    if (have_isa_3_10) {
+        tcg_out32(s, BRH | RA(dst) | RS(src));
+        if (flags & TCG_BSWAP_OS) {
+            tcg_out_ext16s(s, dst, dst);
+        } else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext16u(s, dst, dst);
+        }
+        return;
+    }
+
+    /*
+     * In the following,
+     *   dep(a, b, m) -> (a & ~m) | (b & m)
+     *
+     * Begin with:                              src = xxxxabcd
+     */
+    /* tmp = rol32(src, 24) & 0x000000ff            = 0000000c */
+    tcg_out_rlw(s, RLWINM, tmp, src, 24, 24, 31);
+    /* tmp = dep(tmp, rol32(src, 8), 0x0000ff00)    = 000000dc */
+    tcg_out_rlw(s, RLWIMI, tmp, src, 8, 16, 23);
+
+    if (flags & TCG_BSWAP_OS) {
+        tcg_out_ext16s(s, dst, tmp);
+    } else {
+        tcg_out_mov(s, TCG_TYPE_REG, dst, tmp);
+    }
+}
+
+static void tcg_out_bswap32(TCGContext *s, TCGReg dst, TCGReg src, int flags)
+{
+    TCGReg tmp = dst == src ? TCG_REG_R0 : dst;
+
+    if (have_isa_3_10) {
+        tcg_out32(s, BRW | RA(dst) | RS(src));
+        if (flags & TCG_BSWAP_OS) {
+            tcg_out_ext32s(s, dst, dst);
+        } else if ((flags & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tcg_out_ext32u(s, dst, dst);
+        }
+        return;
+    }
+
+    /*
+     * Stolen from gcc's builtin_bswap32.
+     * In the following,
+     *   dep(a, b, m) -> (a & ~m) | (b & m)
+     *
+     * Begin with:                              src = xxxxabcd
+     */
+    /* tmp = rol32(src, 8) & 0xffffffff             = 0000bcda */
+    tcg_out_rlw(s, RLWINM, tmp, src, 8, 0, 31);
+    /* tmp = dep(tmp, rol32(src, 24), 0xff000000)   = 0000dcda */
+    tcg_out_rlw(s, RLWIMI, tmp, src, 24, 0, 7);
+    /* tmp = dep(tmp, rol32(src, 24), 0x0000ff00)   = 0000dcba */
+    tcg_out_rlw(s, RLWIMI, tmp, src, 24, 16, 23);
+
+    if (flags & TCG_BSWAP_OS) {
+        tcg_out_ext32s(s, dst, tmp);
+    } else {
+        tcg_out_mov(s, TCG_TYPE_REG, dst, tmp);
+    }
+}
+
+static void tcg_out_bswap64(TCGContext *s, TCGReg dst, TCGReg src)
+{
+    TCGReg t0 = dst == src ? TCG_REG_R0 : dst;
+    TCGReg t1 = dst == src ? dst : TCG_REG_R0;
+
+    if (have_isa_3_10) {
+        tcg_out32(s, BRD | RA(dst) | RS(src));
+        return;
+    }
+
+    /*
+     * In the following,
+     *   dep(a, b, m) -> (a & ~m) | (b & m)
+     *
+     * Begin with:                              src = abcdefgh
+     */
+    /* t0 = rol32(src, 8) & 0xffffffff              = 0000fghe */
+    tcg_out_rlw(s, RLWINM, t0, src, 8, 0, 31);
+    /* t0 = dep(t0, rol32(src, 24), 0xff000000)     = 0000hghe */
+    tcg_out_rlw(s, RLWIMI, t0, src, 24, 0, 7);
+    /* t0 = dep(t0, rol32(src, 24), 0x0000ff00)     = 0000hgfe */
+    tcg_out_rlw(s, RLWIMI, t0, src, 24, 16, 23);
+
+    /* t0 = rol64(t0, 32)                           = hgfe0000 */
+    tcg_out_rld(s, RLDICL, t0, t0, 32, 0);
+    /* t1 = rol64(src, 32)                          = efghabcd */
+    tcg_out_rld(s, RLDICL, t1, src, 32, 0);
+
+    /* t0 = dep(t0, rol32(t1, 24), 0xffffffff)      = hgfebcda */
+    tcg_out_rlw(s, RLWIMI, t0, t1, 8, 0, 31);
+    /* t0 = dep(t0, rol32(t1, 24), 0xff000000)      = hgfedcda */
+    tcg_out_rlw(s, RLWIMI, t0, t1, 24, 0, 7);
+    /* t0 = dep(t0, rol32(t1, 24), 0x0000ff00)      = hgfedcba */
+    tcg_out_rlw(s, RLWIMI, t0, t1, 24, 16, 23);
+
+    tcg_out_mov(s, TCG_TYPE_REG, dst, t0);
+}
+
 /* Emit a move into ret of arg, if it can be done in one insn.  */
 static bool tcg_out_movi_one(TCGContext *s, TCGReg ret, tcg_target_long arg)
 {
@@ -2322,7 +2462,6 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
                        const int const_args[TCG_MAX_OP_ARGS])
 {
     TCGArg a0, a1, a2;
-    int c;
 
     switch (opc) {
     case INDEX_op_exit_tb:
@@ -2390,7 +2529,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_ld8s_i32:
     case INDEX_op_ld8s_i64:
         tcg_out_mem_long(s, LBZ, LBZX, args[0], args[1], args[2]);
-        tcg_out32(s, EXTSB | RS(args[0]) | RA(args[0]));
+        tcg_out_ext8s(s, args[0], args[0]);
         break;
     case INDEX_op_ld16u_i32:
     case INDEX_op_ld16u_i64:
@@ -2587,8 +2726,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
     case INDEX_op_sar_i32:
         if (const_args[2]) {
-            /* Limit immediate shift count lest we create an illegal insn.  */
-            tcg_out32(s, SRAWI | RS(args[1]) | RA(args[0]) | SH(args[2] & 31));
+            tcg_out_sari32(s, args[0], args[1], args[2]);
         } else {
             tcg_out32(s, SRAW | SAB(args[1], args[0], args[2]));
         }
@@ -2676,8 +2814,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
     case INDEX_op_sar_i64:
         if (const_args[2]) {
-            int sh = SH(args[2] & 0x1f) | (((args[2] >> 5) & 1) << 1);
-            tcg_out32(s, SRADI | RA(args[0]) | RS(args[1]) | sh);
+            tcg_out_sari64(s, args[0], args[1], args[2]);
         } else {
             tcg_out32(s, SRAD | SAB(args[1], args[0], args[2]));
         }
@@ -2728,18 +2865,15 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_ext8s_i32:
     case INDEX_op_ext8s_i64:
-        c = EXTSB;
-        goto gen_ext;
+        tcg_out_ext8s(s, args[0], args[1]);
+        break;
     case INDEX_op_ext16s_i32:
     case INDEX_op_ext16s_i64:
-        c = EXTSH;
-        goto gen_ext;
+        tcg_out_ext16s(s, args[0], args[1]);
+        break;
     case INDEX_op_ext_i32_i64:
     case INDEX_op_ext32s_i64:
-        c = EXTSW;
-        goto gen_ext;
-    gen_ext:
-        tcg_out32(s, c | RS(args[1]) | RA(args[0]));
+        tcg_out_ext32s(s, args[0], args[1]);
         break;
     case INDEX_op_extu_i32_i64:
         tcg_out_ext32u(s, args[0], args[1]);
@@ -2759,72 +2893,16 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     case INDEX_op_bswap16_i32:
     case INDEX_op_bswap16_i64:
-        a0 = args[0], a1 = args[1];
-        /* a1 = abcd */
-        if (a0 != a1) {
-            /* a0 = (a1 r<< 24) & 0xff # 000c */
-            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
-            /* a0 = (a0 & ~0xff00) | (a1 r<< 8) & 0xff00 # 00dc */
-            tcg_out_rlw(s, RLWIMI, a0, a1, 8, 16, 23);
-        } else {
-            /* r0 = (a1 r<< 8) & 0xff00 # 00d0 */
-            tcg_out_rlw(s, RLWINM, TCG_REG_R0, a1, 8, 16, 23);
-            /* a0 = (a1 r<< 24) & 0xff # 000c */
-            tcg_out_rlw(s, RLWINM, a0, a1, 24, 24, 31);
-            /* a0 = a0 | r0 # 00dc */
-            tcg_out32(s, OR | SAB(TCG_REG_R0, a0, a0));
-        }
+        tcg_out_bswap16(s, args[0], args[1], args[2]);
         break;
-
     case INDEX_op_bswap32_i32:
+        tcg_out_bswap32(s, args[0], args[1], 0);
+        break;
     case INDEX_op_bswap32_i64:
-        /* Stolen from gcc's builtin_bswap32 */
-        a1 = args[1];
-        a0 = args[0] == a1 ? TCG_REG_R0 : args[0];
-
-        /* a1 = args[1] # abcd */
-        /* a0 = rotate_left (a1, 8) # bcda */
-        tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
-        /* a0 = (a0 & ~0xff000000) | ((a1 r<< 24) & 0xff000000) # dcda */
-        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
-        /* a0 = (a0 & ~0x0000ff00) | ((a1 r<< 24) & 0x0000ff00) # dcba */
-        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
-
-        if (a0 == TCG_REG_R0) {
-            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
-        }
+        tcg_out_bswap32(s, args[0], args[1], args[2]);
         break;
-
     case INDEX_op_bswap64_i64:
-        a0 = args[0], a1 = args[1], a2 = TCG_REG_R0;
-        if (a0 == a1) {
-            a0 = TCG_REG_R0;
-            a2 = a1;
-        }
-
-        /* a1 = # abcd efgh */
-        /* a0 = rl32(a1, 8) # 0000 fghe */
-        tcg_out_rlw(s, RLWINM, a0, a1, 8, 0, 31);
-        /* a0 = dep(a0, rl32(a1, 24), 0xff000000) # 0000 hghe */
-        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 0, 7);
-        /* a0 = dep(a0, rl32(a1, 24), 0x0000ff00) # 0000 hgfe */
-        tcg_out_rlw(s, RLWIMI, a0, a1, 24, 16, 23);
-
-        /* a0 = rl64(a0, 32) # hgfe 0000 */
-        /* a2 = rl64(a1, 32) # efgh abcd */
-        tcg_out_rld(s, RLDICL, a0, a0, 32, 0);
-        tcg_out_rld(s, RLDICL, a2, a1, 32, 0);
-
-        /* a0 = dep(a0, rl32(a2, 8), 0xffffffff)  # hgfe bcda */
-        tcg_out_rlw(s, RLWIMI, a0, a2, 8, 0, 31);
-        /* a0 = dep(a0, rl32(a2, 24), 0xff000000) # hgfe dcda */
-        tcg_out_rlw(s, RLWIMI, a0, a2, 24, 0, 7);
-        /* a0 = dep(a0, rl32(a2, 24), 0x0000ff00) # hgfe dcba */
-        tcg_out_rlw(s, RLWIMI, a0, a2, 24, 16, 23);
-
-        if (a0 == 0) {
-            tcg_out_mov(s, TCG_TYPE_REG, args[0], a0);
-        }
+        tcg_out_bswap64(s, args[0], args[1]);
         break;
 
     case INDEX_op_deposit_i32:
diff --git a/tcg/riscv/tcg-target.c.inc b/tcg/riscv/tcg-target.c.inc
index da7eecafc5..c16f96b401 100644
--- a/tcg/riscv/tcg-target.c.inc
+++ b/tcg/riscv/tcg-target.c.inc
@@ -852,37 +852,43 @@ static void tcg_out_mb(TCGContext *s, TCGArg a0)
 /* helper signature: helper_ret_ld_mmu(CPUState *env, target_ulong addr,
  *                                     TCGMemOpIdx oi, uintptr_t ra)
  */
-static void * const qemu_ld_helpers[16] = {
-    [MO_UB]   = helper_ret_ldub_mmu,
-    [MO_SB]   = helper_ret_ldsb_mmu,
-    [MO_LEUW] = helper_le_lduw_mmu,
-    [MO_LESW] = helper_le_ldsw_mmu,
-    [MO_LEUL] = helper_le_ldul_mmu,
+static void * const qemu_ld_helpers[8] = {
+    [MO_UB] = helper_ret_ldub_mmu,
+    [MO_SB] = helper_ret_ldsb_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_UW] = helper_be_lduw_mmu,
+    [MO_SW] = helper_be_ldsw_mmu,
+    [MO_UL] = helper_be_ldul_mmu,
 #if TCG_TARGET_REG_BITS == 64
-    [MO_LESL] = helper_le_ldsl_mmu,
+    [MO_SL] = helper_be_ldsl_mmu,
 #endif
-    [MO_LEQ]  = helper_le_ldq_mmu,
-    [MO_BEUW] = helper_be_lduw_mmu,
-    [MO_BESW] = helper_be_ldsw_mmu,
-    [MO_BEUL] = helper_be_ldul_mmu,
+    [MO_Q]  = helper_be_ldq_mmu,
+#else
+    [MO_UW] = helper_le_lduw_mmu,
+    [MO_SW] = helper_le_ldsw_mmu,
+    [MO_UL] = helper_le_ldul_mmu,
 #if TCG_TARGET_REG_BITS == 64
-    [MO_BESL] = helper_be_ldsl_mmu,
+    [MO_SL] = helper_le_ldsl_mmu,
+#endif
+    [MO_Q]  = helper_le_ldq_mmu,
 #endif
-    [MO_BEQ]  = helper_be_ldq_mmu,
 };
 
 /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
  *                                     uintxx_t val, TCGMemOpIdx oi,
  *                                     uintptr_t ra)
  */
-static void * const qemu_st_helpers[16] = {
-    [MO_UB]   = helper_ret_stb_mmu,
-    [MO_LEUW] = helper_le_stw_mmu,
-    [MO_LEUL] = helper_le_stl_mmu,
-    [MO_LEQ]  = helper_le_stq_mmu,
-    [MO_BEUW] = helper_be_stw_mmu,
-    [MO_BEUL] = helper_be_stl_mmu,
-    [MO_BEQ]  = helper_be_stq_mmu,
+static void * const qemu_st_helpers[4] = {
+    [MO_8]   = helper_ret_stb_mmu,
+#ifdef HOST_WORDS_BIGENDIAN
+    [MO_16] = helper_be_stw_mmu,
+    [MO_32] = helper_be_stl_mmu,
+    [MO_64] = helper_be_stq_mmu,
+#else
+    [MO_16] = helper_le_stw_mmu,
+    [MO_32] = helper_le_stl_mmu,
+    [MO_64] = helper_le_stq_mmu,
+#endif
 };
 
 /* We don't support oversize guests */
@@ -997,7 +1003,7 @@ static bool tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
     tcg_out_movi(s, TCG_TYPE_PTR, a2, oi);
     tcg_out_movi(s, TCG_TYPE_PTR, a3, (tcg_target_long)l->raddr);
 
-    tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SSIZE)]);
+    tcg_out_call(s, qemu_ld_helpers[opc & MO_SSIZE]);
     tcg_out_mov(s, (opc & MO_SIZE) == MO_64, l->datalo_reg, a0);
 
     tcg_out_goto(s, l->raddr);
@@ -1042,7 +1048,7 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
     tcg_out_movi(s, TCG_TYPE_PTR, a3, oi);
     tcg_out_movi(s, TCG_TYPE_PTR, a4, (tcg_target_long)l->raddr);
 
-    tcg_out_call(s, qemu_st_helpers[opc & (MO_BSWAP | MO_SSIZE)]);
+    tcg_out_call(s, qemu_st_helpers[opc & MO_SIZE]);
 
     tcg_out_goto(s, l->raddr);
     return true;
@@ -1052,10 +1058,8 @@ static bool tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
 static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
                                    TCGReg base, MemOp opc, bool is_64)
 {
-    const MemOp bswap = opc & MO_BSWAP;
-
-    /* We don't yet handle byteswapping, assert */
-    g_assert(!bswap);
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & (MO_SSIZE)) {
     case MO_UB:
@@ -1139,10 +1143,8 @@ static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
 static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
                                    TCGReg base, MemOp opc)
 {
-    const MemOp bswap = opc & MO_BSWAP;
-
-    /* We don't yet handle byteswapping, assert */
-    g_assert(!bswap);
+    /* Byte swapping is left to middle-end expansion. */
+    tcg_debug_assert((opc & MO_BSWAP) == 0);
 
     switch (opc & (MO_SSIZE)) {
     case MO_8:
diff --git a/tcg/s390/tcg-target.c.inc b/tcg/s390/tcg-target.c.inc
index 5fe073f09a..b82cf19f09 100644
--- a/tcg/s390/tcg-target.c.inc
+++ b/tcg/s390/tcg-target.c.inc
@@ -1951,15 +1951,37 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tgen_ext16u(s, TCG_TYPE_I32, args[0], args[1]);
         break;
 
-    OP_32_64(bswap16):
-        /* The TCG bswap definition requires bits 0-47 already be zero.
-           Thus we don't need the G-type insns to implement bswap16_i64.  */
-        tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
-        tcg_out_sh32(s, RS_SRL, args[0], TCG_REG_NONE, 16);
+    case INDEX_op_bswap16_i32:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        tcg_out_insn(s, RRE, LRVR, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tcg_out_sh32(s, RS_SRA, a0, TCG_REG_NONE, 16);
+        } else {
+            tcg_out_sh32(s, RS_SRL, a0, TCG_REG_NONE, 16);
+        }
+        break;
+    case INDEX_op_bswap16_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        tcg_out_insn(s, RRE, LRVGR, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tcg_out_sh64(s, RSY_SRAG, a0, a0, TCG_REG_NONE, 48);
+        } else {
+            tcg_out_sh64(s, RSY_SRLG, a0, a0, TCG_REG_NONE, 48);
+        }
         break;
-    OP_32_64(bswap32):
+
+    case INDEX_op_bswap32_i32:
         tcg_out_insn(s, RRE, LRVR, args[0], args[1]);
         break;
+    case INDEX_op_bswap32_i64:
+        a0 = args[0], a1 = args[1], a2 = args[2];
+        tcg_out_insn(s, RRE, LRVR, a0, a1);
+        if (a2 & TCG_BSWAP_OS) {
+            tgen_ext32s(s, a0, a0);
+        } else if ((a2 & (TCG_BSWAP_IZ | TCG_BSWAP_OZ)) == TCG_BSWAP_OZ) {
+            tgen_ext32u(s, a0, a0);
+        }
+        break;
 
     case INDEX_op_add2_i32:
         if (const_args[4]) {
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 515db120cc..ffe55e908f 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1736,12 +1736,45 @@ void tcg_gen_vec_add8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_addv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 m = tcg_constant_i32((int32_t)dup_const(MO_8, 0x80));
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+    TCGv_i32 t3 = tcg_temp_new_i32();
+
+    tcg_gen_andc_i32(t1, a, m);
+    tcg_gen_andc_i32(t2, b, m);
+    tcg_gen_xor_i32(t3, a, b);
+    tcg_gen_add_i32(d, t1, t2);
+    tcg_gen_and_i32(t3, t3, m);
+    tcg_gen_xor_i32(d, d, t3);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+    tcg_temp_free_i32(t3);
+}
+
 void tcg_gen_vec_add16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 m = tcg_constant_i64(dup_const(MO_16, 0x8000));
     gen_addv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    tcg_gen_andi_i32(t1, a, ~0xffff);
+    tcg_gen_add_i32(t2, a, b);
+    tcg_gen_add_i32(t1, t1, b);
+    tcg_gen_deposit_i32(d, t1, t2, 0, 16);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+}
+
 void tcg_gen_vec_add32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 t1 = tcg_temp_new_i64();
@@ -1886,12 +1919,45 @@ void tcg_gen_vec_sub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_subv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 m = tcg_constant_i32((int32_t)dup_const(MO_8, 0x80));
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+    TCGv_i32 t3 = tcg_temp_new_i32();
+
+    tcg_gen_or_i32(t1, a, m);
+    tcg_gen_andc_i32(t2, b, m);
+    tcg_gen_eqv_i32(t3, a, b);
+    tcg_gen_sub_i32(d, t1, t2);
+    tcg_gen_and_i32(t3, t3, m);
+    tcg_gen_xor_i32(d, d, t3);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+    tcg_temp_free_i32(t3);
+}
+
 void tcg_gen_vec_sub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 m = tcg_constant_i64(dup_const(MO_16, 0x8000));
     gen_subv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    tcg_gen_andi_i32(t1, b, ~0xffff);
+    tcg_gen_sub_i32(t2, a, b);
+    tcg_gen_sub_i32(t1, a, t1);
+    tcg_gen_deposit_i32(d, t1, t2, 0, 16);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+}
+
 void tcg_gen_vec_sub32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 t1 = tcg_temp_new_i64();
@@ -2612,6 +2678,20 @@ void tcg_gen_vec_shl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c)
     tcg_gen_andi_i64(d, d, mask);
 }
 
+void tcg_gen_vec_shl8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t mask = dup_const(MO_8, 0xff << c);
+    tcg_gen_shli_i32(d, a, c);
+    tcg_gen_andi_i32(d, d, mask);
+}
+
+void tcg_gen_vec_shl16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t mask = dup_const(MO_16, 0xffff << c);
+    tcg_gen_shli_i32(d, a, c);
+    tcg_gen_andi_i32(d, d, mask);
+}
+
 void tcg_gen_gvec_shli(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz)
 {
@@ -2663,6 +2743,20 @@ void tcg_gen_vec_shr16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c)
     tcg_gen_andi_i64(d, d, mask);
 }
 
+void tcg_gen_vec_shr8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t mask = dup_const(MO_8, 0xff >> c);
+    tcg_gen_shri_i32(d, a, c);
+    tcg_gen_andi_i32(d, d, mask);
+}
+
+void tcg_gen_vec_shr16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t mask = dup_const(MO_16, 0xffff >> c);
+    tcg_gen_shri_i32(d, a, c);
+    tcg_gen_andi_i32(d, d, mask);
+}
+
 void tcg_gen_gvec_shri(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz)
 {
@@ -2728,6 +2822,34 @@ void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c)
     tcg_temp_free_i64(s);
 }
 
+void tcg_gen_vec_sar8i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t s_mask = dup_const(MO_8, 0x80 >> c);
+    uint32_t c_mask = dup_const(MO_8, 0xff >> c);
+    TCGv_i32 s = tcg_temp_new_i32();
+
+    tcg_gen_shri_i32(d, a, c);
+    tcg_gen_andi_i32(s, d, s_mask);  /* isolate (shifted) sign bit */
+    tcg_gen_muli_i32(s, s, (2 << c) - 2); /* replicate isolated signs */
+    tcg_gen_andi_i32(d, d, c_mask);  /* clear out bits above sign  */
+    tcg_gen_or_i32(d, d, s);         /* include sign extension */
+    tcg_temp_free_i32(s);
+}
+
+void tcg_gen_vec_sar16i_i32(TCGv_i32 d, TCGv_i32 a, int32_t c)
+{
+    uint32_t s_mask = dup_const(MO_16, 0x8000 >> c);
+    uint32_t c_mask = dup_const(MO_16, 0xffff >> c);
+    TCGv_i32 s = tcg_temp_new_i32();
+
+    tcg_gen_shri_i32(d, a, c);
+    tcg_gen_andi_i32(s, d, s_mask);  /* isolate (shifted) sign bit */
+    tcg_gen_andi_i32(d, d, c_mask);  /* clear out bits above sign  */
+    tcg_gen_muli_i32(s, s, (2 << c) - 2); /* replicate isolated signs */
+    tcg_gen_or_i32(d, d, s);         /* include sign extension */
+    tcg_temp_free_i32(s);
+}
+
 void tcg_gen_gvec_sari(unsigned vece, uint32_t dofs, uint32_t aofs,
                        int64_t shift, uint32_t oprsz, uint32_t maxsz)
 {
diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index dcc2ed0bbc..44d711c0fc 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -1001,26 +1001,42 @@ void tcg_gen_ext16u_i32(TCGv_i32 ret, TCGv_i32 arg)
     }
 }
 
-/* Note: we assume the two high bytes are set to zero */
-void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg)
+void tcg_gen_bswap16_i32(TCGv_i32 ret, TCGv_i32 arg, int flags)
 {
+    /* Only one extension flag may be present. */
+    tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));
+
     if (TCG_TARGET_HAS_bswap16_i32) {
-        tcg_gen_op2_i32(INDEX_op_bswap16_i32, ret, arg);
+        tcg_gen_op3i_i32(INDEX_op_bswap16_i32, ret, arg, flags);
     } else {
         TCGv_i32 t0 = tcg_temp_new_i32();
+        TCGv_i32 t1 = tcg_temp_new_i32();
 
-        tcg_gen_ext8u_i32(t0, arg);
-        tcg_gen_shli_i32(t0, t0, 8);
-        tcg_gen_shri_i32(ret, arg, 8);
-        tcg_gen_or_i32(ret, ret, t0);
+        tcg_gen_shri_i32(t0, arg, 8);
+        if (!(flags & TCG_BSWAP_IZ)) {
+            tcg_gen_ext8u_i32(t0, t0);
+        }
+
+        if (flags & TCG_BSWAP_OS) {
+            tcg_gen_shli_i32(t1, arg, 24);
+            tcg_gen_sari_i32(t1, t1, 16);
+        } else if (flags & TCG_BSWAP_OZ) {
+            tcg_gen_ext8u_i32(t1, arg);
+            tcg_gen_shli_i32(t1, t1, 8);
+        } else {
+            tcg_gen_shli_i32(t1, arg, 8);
+        }
+
+        tcg_gen_or_i32(ret, t0, t1);
         tcg_temp_free_i32(t0);
+        tcg_temp_free_i32(t1);
     }
 }
 
 void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg)
 {
     if (TCG_TARGET_HAS_bswap32_i32) {
-        tcg_gen_op2_i32(INDEX_op_bswap32_i32, ret, arg);
+        tcg_gen_op3i_i32(INDEX_op_bswap32_i32, ret, arg, 0);
     } else {
         TCGv_i32 t0 = tcg_temp_new_i32();
         TCGv_i32 t1 = tcg_temp_new_i32();
@@ -1654,49 +1670,79 @@ void tcg_gen_ext32u_i64(TCGv_i64 ret, TCGv_i64 arg)
     }
 }
 
-/* Note: we assume the six high bytes are set to zero */
-void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg)
+void tcg_gen_bswap16_i64(TCGv_i64 ret, TCGv_i64 arg, int flags)
 {
+    /* Only one extension flag may be present. */
+    tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));
+
     if (TCG_TARGET_REG_BITS == 32) {
-        tcg_gen_bswap16_i32(TCGV_LOW(ret), TCGV_LOW(arg));
-        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+        tcg_gen_bswap16_i32(TCGV_LOW(ret), TCGV_LOW(arg), flags);
+        if (flags & TCG_BSWAP_OS) {
+            tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+        } else {
+            tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+        }
     } else if (TCG_TARGET_HAS_bswap16_i64) {
-        tcg_gen_op2_i64(INDEX_op_bswap16_i64, ret, arg);
+        tcg_gen_op3i_i64(INDEX_op_bswap16_i64, ret, arg, flags);
     } else {
         TCGv_i64 t0 = tcg_temp_new_i64();
+        TCGv_i64 t1 = tcg_temp_new_i64();
+
+        tcg_gen_shri_i64(t0, arg, 8);
+        if (!(flags & TCG_BSWAP_IZ)) {
+            tcg_gen_ext8u_i64(t0, t0);
+        }
 
-        tcg_gen_ext8u_i64(t0, arg);
-        tcg_gen_shli_i64(t0, t0, 8);
-        tcg_gen_shri_i64(ret, arg, 8);
-        tcg_gen_or_i64(ret, ret, t0);
+        if (flags & TCG_BSWAP_OS) {
+            tcg_gen_shli_i64(t1, arg, 56);
+            tcg_gen_sari_i64(t1, t1, 48);
+        } else if (flags & TCG_BSWAP_OZ) {
+            tcg_gen_ext8u_i64(t1, arg);
+            tcg_gen_shli_i64(t1, t1, 8);
+        } else {
+            tcg_gen_shli_i64(t1, arg, 8);
+        }
+
+        tcg_gen_or_i64(ret, t0, t1);
         tcg_temp_free_i64(t0);
+        tcg_temp_free_i64(t1);
     }
 }
 
-/* Note: we assume the four high bytes are set to zero */
-void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg)
+void tcg_gen_bswap32_i64(TCGv_i64 ret, TCGv_i64 arg, int flags)
 {
+    /* Only one extension flag may be present. */
+    tcg_debug_assert(!(flags & TCG_BSWAP_OS) || !(flags & TCG_BSWAP_OZ));
+
     if (TCG_TARGET_REG_BITS == 32) {
         tcg_gen_bswap32_i32(TCGV_LOW(ret), TCGV_LOW(arg));
-        tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+        if (flags & TCG_BSWAP_OS) {
+            tcg_gen_sari_i32(TCGV_HIGH(ret), TCGV_LOW(ret), 31);
+        } else {
+            tcg_gen_movi_i32(TCGV_HIGH(ret), 0);
+        }
     } else if (TCG_TARGET_HAS_bswap32_i64) {
-        tcg_gen_op2_i64(INDEX_op_bswap32_i64, ret, arg);
+        tcg_gen_op3i_i64(INDEX_op_bswap32_i64, ret, arg, flags);
     } else {
         TCGv_i64 t0 = tcg_temp_new_i64();
         TCGv_i64 t1 = tcg_temp_new_i64();
         TCGv_i64 t2 = tcg_constant_i64(0x00ff00ff);
 
-                                        /* arg = ....abcd */
-        tcg_gen_shri_i64(t0, arg, 8);   /*  t0 = .....abc */
-        tcg_gen_and_i64(t1, arg, t2);   /*  t1 = .....b.d */
-        tcg_gen_and_i64(t0, t0, t2);    /*  t0 = .....a.c */
-        tcg_gen_shli_i64(t1, t1, 8);    /*  t1 = ....b.d. */
-        tcg_gen_or_i64(ret, t0, t1);    /* ret = ....badc */
-
-        tcg_gen_shli_i64(t1, ret, 48);  /*  t1 = dc...... */
-        tcg_gen_shri_i64(t0, ret, 16);  /*  t0 = ......ba */
-        tcg_gen_shri_i64(t1, t1, 32);   /*  t1 = ....dc.. */
-        tcg_gen_or_i64(ret, t0, t1);    /* ret = ....dcba */
+                                            /* arg = xxxxabcd */
+        tcg_gen_shri_i64(t0, arg, 8);       /*  t0 = .xxxxabc */
+        tcg_gen_and_i64(t1, arg, t2);       /*  t1 = .....b.d */
+        tcg_gen_and_i64(t0, t0, t2);        /*  t0 = .....a.c */
+        tcg_gen_shli_i64(t1, t1, 8);        /*  t1 = ....b.d. */
+        tcg_gen_or_i64(ret, t0, t1);        /* ret = ....badc */
+
+        tcg_gen_shli_i64(t1, ret, 48);      /*  t1 = dc...... */
+        tcg_gen_shri_i64(t0, ret, 16);      /*  t0 = ......ba */
+        if (flags & TCG_BSWAP_OS) {
+            tcg_gen_sari_i64(t1, t1, 32);   /*  t1 = ssssdc.. */
+        } else {
+            tcg_gen_shri_i64(t1, t1, 32);   /*  t1 = ....dc.. */
+        }
+        tcg_gen_or_i64(ret, t0, t1);        /* ret = ssssdcba */
 
         tcg_temp_free_i64(t0);
         tcg_temp_free_i64(t1);
@@ -1717,7 +1763,7 @@ void tcg_gen_bswap64_i64(TCGv_i64 ret, TCGv_i64 arg)
         tcg_temp_free_i32(t0);
         tcg_temp_free_i32(t1);
     } else if (TCG_TARGET_HAS_bswap64_i64) {
-        tcg_gen_op2_i64(INDEX_op_bswap64_i64, ret, arg);
+        tcg_gen_op3i_i64(INDEX_op_bswap64_i64, ret, arg, 0);
     } else {
         TCGv_i64 t0 = tcg_temp_new_i64();
         TCGv_i64 t1 = tcg_temp_new_i64();
@@ -2830,7 +2876,7 @@ void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop)
     orig_memop = memop;
     if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) {
         memop &= ~MO_BSWAP;
-        /* The bswap primitive requires zero-extended input.  */
+        /* The bswap primitive benefits from zero-extended input.  */
         if ((memop & MO_SSIZE) == MO_SW) {
             memop &= ~MO_SIGN;
         }
@@ -2843,10 +2889,9 @@ void tcg_gen_qemu_ld_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop)
     if ((orig_memop ^ memop) & MO_BSWAP) {
         switch (orig_memop & MO_SIZE) {
         case MO_16:
-            tcg_gen_bswap16_i32(val, val);
-            if (orig_memop & MO_SIGN) {
-                tcg_gen_ext16s_i32(val, val);
-            }
+            tcg_gen_bswap16_i32(val, val, (orig_memop & MO_SIGN
+                                           ? TCG_BSWAP_IZ | TCG_BSWAP_OS
+                                           : TCG_BSWAP_IZ | TCG_BSWAP_OZ));
             break;
         case MO_32:
             tcg_gen_bswap32_i32(val, val);
@@ -2870,8 +2915,7 @@ void tcg_gen_qemu_st_i32(TCGv_i32 val, TCGv addr, TCGArg idx, MemOp memop)
         swap = tcg_temp_new_i32();
         switch (memop & MO_SIZE) {
         case MO_16:
-            tcg_gen_ext16u_i32(swap, val);
-            tcg_gen_bswap16_i32(swap, swap);
+            tcg_gen_bswap16_i32(swap, val, 0);
             break;
         case MO_32:
             tcg_gen_bswap32_i32(swap, val);
@@ -2919,7 +2963,7 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
     orig_memop = memop;
     if (!TCG_TARGET_HAS_MEMORY_BSWAP && (memop & MO_BSWAP)) {
         memop &= ~MO_BSWAP;
-        /* The bswap primitive requires zero-extended input.  */
+        /* The bswap primitive benefits from zero-extended input.  */
         if ((memop & MO_SIGN) && (memop & MO_SIZE) < MO_64) {
             memop &= ~MO_SIGN;
         }
@@ -2930,18 +2974,15 @@ void tcg_gen_qemu_ld_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
     plugin_gen_mem_callbacks(addr, info);
 
     if ((orig_memop ^ memop) & MO_BSWAP) {
+        int flags = (orig_memop & MO_SIGN
+                     ? TCG_BSWAP_IZ | TCG_BSWAP_OS
+                     : TCG_BSWAP_IZ | TCG_BSWAP_OZ);
         switch (orig_memop & MO_SIZE) {
         case MO_16:
-            tcg_gen_bswap16_i64(val, val);
-            if (orig_memop & MO_SIGN) {
-                tcg_gen_ext16s_i64(val, val);
-            }
+            tcg_gen_bswap16_i64(val, val, flags);
             break;
         case MO_32:
-            tcg_gen_bswap32_i64(val, val);
-            if (orig_memop & MO_SIGN) {
-                tcg_gen_ext32s_i64(val, val);
-            }
+            tcg_gen_bswap32_i64(val, val, flags);
             break;
         case MO_64:
             tcg_gen_bswap64_i64(val, val);
@@ -2971,12 +3012,10 @@ void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
         swap = tcg_temp_new_i64();
         switch (memop & MO_SIZE) {
         case MO_16:
-            tcg_gen_ext16u_i64(swap, val);
-            tcg_gen_bswap16_i64(swap, swap);
+            tcg_gen_bswap16_i64(swap, val, 0);
             break;
         case MO_32:
-            tcg_gen_ext32u_i64(swap, val);
-            tcg_gen_bswap32_i64(swap, swap);
+            tcg_gen_bswap32_i64(swap, val, 0);
             break;
         case MO_64:
             tcg_gen_bswap64_i64(swap, val);
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 5e53c3348f..5150ed700e 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -1778,6 +1778,14 @@ static const char * const alignment_name[(MO_AMASK >> MO_ASHIFT) + 1] = {
     [MO_ALIGN_64 >> MO_ASHIFT] = "al64+",
 };
 
+static const char bswap_flag_name[][6] = {
+    [TCG_BSWAP_IZ] = "iz",
+    [TCG_BSWAP_OZ] = "oz",
+    [TCG_BSWAP_OS] = "os",
+    [TCG_BSWAP_IZ | TCG_BSWAP_OZ] = "iz,oz",
+    [TCG_BSWAP_IZ | TCG_BSWAP_OS] = "iz,os",
+};
+
 static inline bool tcg_regset_single(TCGRegSet d)
 {
     return (d & (d - 1)) == 0;
@@ -1921,6 +1929,26 @@ static void tcg_dump_ops(TCGContext *s, bool have_prefs)
                     i = 1;
                 }
                 break;
+            case INDEX_op_bswap16_i32:
+            case INDEX_op_bswap16_i64:
+            case INDEX_op_bswap32_i32:
+            case INDEX_op_bswap32_i64:
+            case INDEX_op_bswap64_i64:
+                {
+                    TCGArg flags = op->args[k];
+                    const char *name = NULL;
+
+                    if (flags < ARRAY_SIZE(bswap_flag_name)) {
+                        name = bswap_flag_name[flags];
+                    }
+                    if (name) {
+                        col += qemu_log(",%s", name);
+                    } else {
+                        col += qemu_log(",$0x%" TCG_PRIlx, flags);
+                    }
+                    i = k = 1;
+                }
+                break;
             default:
                 i = 0;
                 break;
diff --git a/tcg/tci.c b/tcg/tci.c
index 71689d4a40..b672c7cae5 100644
--- a/tcg/tci.c
+++ b/tcg/tci.c
@@ -808,7 +808,8 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
             regs[r0] = (int8_t)regs[r1];
             break;
 #endif
-#if TCG_TARGET_HAS_ext16s_i32 || TCG_TARGET_HAS_ext16s_i64
+#if TCG_TARGET_HAS_ext16s_i32 || TCG_TARGET_HAS_ext16s_i64 || \
+    TCG_TARGET_HAS_bswap16_i32 || TCG_TARGET_HAS_bswap16_i64
         CASE_32_64(ext16s)
             tci_args_rr(insn, &r0, &r1);
             regs[r0] = (int16_t)regs[r1];
diff --git a/tcg/tci/tcg-target.c.inc b/tcg/tci/tcg-target.c.inc
index 9651e7a8f1..0cb16aaa81 100644
--- a/tcg/tci/tcg-target.c.inc
+++ b/tcg/tci/tcg-target.c.inc
@@ -597,6 +597,8 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
                        const TCGArg args[TCG_MAX_OP_ARGS],
                        const int const_args[TCG_MAX_OP_ARGS])
 {
+    TCGOpcode exts;
+
     switch (opc) {
     case INDEX_op_exit_tb:
         tcg_out_op_p(s, opc, (void *)args[0]);
@@ -710,13 +712,28 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     CASE_64(ext32u)      /* Optional (TCG_TARGET_HAS_ext32u_i64). */
     CASE_64(ext_i32)
     CASE_64(extu_i32)
-    CASE_32_64(bswap16)  /* Optional (TCG_TARGET_HAS_bswap16_*). */
-    CASE_32_64(bswap32)  /* Optional (TCG_TARGET_HAS_bswap32_*). */
-    CASE_64(bswap64)     /* Optional (TCG_TARGET_HAS_bswap64_i64). */
     CASE_32_64(ctpop)    /* Optional (TCG_TARGET_HAS_ctpop_*). */
+    case INDEX_op_bswap32_i32: /* Optional (TCG_TARGET_HAS_bswap32_i32). */
+    case INDEX_op_bswap64_i64: /* Optional (TCG_TARGET_HAS_bswap64_i64). */
         tcg_out_op_rr(s, opc, args[0], args[1]);
         break;
 
+    case INDEX_op_bswap16_i32: /* Optional (TCG_TARGET_HAS_bswap16_i32). */
+        exts = INDEX_op_ext16s_i32;
+        goto do_bswap;
+    case INDEX_op_bswap16_i64: /* Optional (TCG_TARGET_HAS_bswap16_i64). */
+        exts = INDEX_op_ext16s_i64;
+        goto do_bswap;
+    case INDEX_op_bswap32_i64: /* Optional (TCG_TARGET_HAS_bswap32_i64). */
+        exts = INDEX_op_ext32s_i64;
+    do_bswap:
+        /* The base tci bswaps zero-extend, and ignore high bits. */
+        tcg_out_op_rr(s, opc, args[0], args[1]);
+        if (args[2] & TCG_BSWAP_OS) {
+            tcg_out_op_rr(s, exts, args[0], args[0]);
+        }
+        break;
+
     CASE_32_64(add2)
     CASE_32_64(sub2)
         tcg_out_op_rrrrrr(s, opc, args[0], args[1], args[2],