diff mbox series

[v3,02/16] tcg/mips: Support unaligned access for softmmu

Message ID 20210818201931.393394-3-richard.henderson@linaro.org
State Superseded
Headers show
Series tcg/mips: Unaligned access and other cleanup | expand

Commit Message

Richard Henderson Aug. 18, 2021, 8:19 p.m. UTC
We can use the routines just added for user-only to emit
unaligned accesses in softmmu mode too.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/mips/tcg-target.c.inc | 91 ++++++++++++++++++++++-----------------
 1 file changed, 51 insertions(+), 40 deletions(-)

-- 
2.25.1

Comments

Jiaxun Yang Aug. 21, 2021, 6:39 a.m. UTC | #1
在2021年8月19日八月 上午4:19,Richard Henderson写道:
> We can use the routines just added for user-only to emit

> unaligned accesses in softmmu mode too.

> 

> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Jiaxun Yang <jiaxun.yang@flygoat.com>


Thanks!

> ---

>  tcg/mips/tcg-target.c.inc | 91 ++++++++++++++++++++++-----------------

>  1 file changed, 51 insertions(+), 40 deletions(-)

> 

> diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc

> index 7ed0de9dae..3d6a0ba39e 100644

> --- a/tcg/mips/tcg-target.c.inc

> +++ b/tcg/mips/tcg-target.c.inc

> @@ -1154,8 +1154,10 @@ static void tcg_out_tlb_load(TCGContext *s, 

> TCGReg base, TCGReg addrl,

>                               tcg_insn_unit *label_ptr[2], bool is_load)

>  {

>      MemOp opc = get_memop(oi);

> -    unsigned s_bits = opc & MO_SIZE;

>      unsigned a_bits = get_alignment_bits(opc);

> +    unsigned s_bits = opc & MO_SIZE;

> +    unsigned a_mask = (1 << a_bits) - 1;

> +    unsigned s_mask = (1 << s_bits) - 1;

>      int mem_index = get_mmuidx(oi);

>      int fast_off = TLB_MASK_TABLE_OFS(mem_index);

>      int mask_off = fast_off + offsetof(CPUTLBDescFast, mask);

> @@ -1163,7 +1165,7 @@ static void tcg_out_tlb_load(TCGContext *s, 

> TCGReg base, TCGReg addrl,

>      int add_off = offsetof(CPUTLBEntry, addend);

>      int cmp_off = (is_load ? offsetof(CPUTLBEntry, addr_read)

>                     : offsetof(CPUTLBEntry, addr_write));

> -    target_ulong mask;

> +    target_ulong tlb_mask;

>  

>      /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx].  */

>      tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_AREG0, mask_off);

> @@ -1177,27 +1179,13 @@ static void tcg_out_tlb_load(TCGContext *s, 

> TCGReg base, TCGReg addrl,

>      /* Add the tlb_table pointer, creating the CPUTLBEntry address in 

> TMP3.  */

>      tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP3, TCG_TMP3, TCG_TMP1);

>  

> -    /* We don't currently support unaligned accesses.

> -       We could do so with mips32r6.  */

> -    if (a_bits < s_bits) {

> -        a_bits = s_bits;

> -    }

> -

> -    /* Mask the page bits, keeping the alignment bits to compare against.  */

> -    mask = (target_ulong)TARGET_PAGE_MASK | ((1 << a_bits) - 1);

> -

>      /* Load the (low-half) tlb comparator.  */

>      if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {

> -        tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);

> -        tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, mask);

> +        tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);

>      } else {

>          tcg_out_ldst(s, (TARGET_LONG_BITS == 64 ? OPC_LD

>                           : TCG_TARGET_REG_BITS == 64 ? OPC_LWU : OPC_LW),

>                       TCG_TMP0, TCG_TMP3, cmp_off);

> -        tcg_out_movi(s, TCG_TYPE_TL, TCG_TMP1, mask);

> -        /* No second compare is required here;

> -           load the tlb addend for the fast path.  */

> -        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);

>      }

>  

>      /* Zero extend a 32-bit guest address for a 64-bit host. */

> @@ -1205,7 +1193,25 @@ static void tcg_out_tlb_load(TCGContext *s, 

> TCGReg base, TCGReg addrl,

>          tcg_out_ext32u(s, base, addrl);

>          addrl = base;

>      }

> -    tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);

> +

> +    /*

> +     * Mask the page bits, keeping the alignment bits to compare 

> against.

> +     * For unaligned accesses, compare against the end of the access to

> +     * verify that it does not cross a page boundary.

> +     */

> +    tlb_mask = (target_ulong)TARGET_PAGE_MASK | a_mask;

> +    tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, tlb_mask);

> +    if (a_mask >= s_mask) {

> +        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);

> +    } else {

> +        tcg_out_opc_imm(s, ALIAS_PADDI, TCG_TMP2, addrl, s_mask - 

> a_mask);

> +        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, TCG_TMP2);

> +    }

> +

> +    if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) {

> +        /* Load the tlb addend for the fast path.  */

> +        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);

> +    }

>  

>      label_ptr[0] = s->code_ptr;

>      tcg_out_opc_br(s, OPC_BNE, TCG_TMP1, TCG_TMP0);

> @@ -1213,7 +1219,7 @@ static void tcg_out_tlb_load(TCGContext *s, 

> TCGReg base, TCGReg addrl,

>      /* Load and test the high half tlb comparator.  */

>      if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {

>          /* delay slot */

> -        tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3, cmp_off + 

> HI_OFF);

> +        tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + HI_OFF);

>  

>          /* Load the tlb addend for the fast path.  */

>          tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);

> @@ -1535,8 +1541,7 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, 

> TCGReg lo, TCGReg hi,

>      }

>  }

>  

> -static void __attribute__((unused))

> -tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi,

> +static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg 

> hi,

>                                      TCGReg base, MemOp opc, bool is_64)

>  {

>      const MIPSInsn lw1 = MIPS_BE ? OPC_LWL : OPC_LWR;

> @@ -1655,8 +1660,8 @@ static void tcg_out_qemu_ld(TCGContext *s, const 

> TCGArg *args, bool is_64)

>  #if defined(CONFIG_SOFTMMU)

>      tcg_insn_unit *label_ptr[2];

>  #else

> -    unsigned a_bits, s_bits;

>  #endif

> +    unsigned a_bits, s_bits;

>      TCGReg base = TCG_REG_A0;

>  

>      data_regl = *args++;

> @@ -1665,10 +1670,20 @@ static void tcg_out_qemu_ld(TCGContext *s, 

> const TCGArg *args, bool is_64)

>      addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);

>      oi = *args++;

>      opc = get_memop(oi);

> +    a_bits = get_alignment_bits(opc);

> +    s_bits = opc & MO_SIZE;

>  

> +    /*

> +     * R6 removes the left/right instructions but requires the

> +     * system to support misaligned memory accesses.

> +     */

>  #if defined(CONFIG_SOFTMMU)

>      tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 1);

> -    tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);

> +    if (use_mips32r6_instructions || a_bits >= s_bits) {

> +        tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, 

> is_64);

> +    } else {

> +        tcg_out_qemu_ld_unalign(s, data_regl, data_regh, base, opc, 

> is_64);

> +    }

>      add_qemu_ldst_label(s, 1, oi,

>                          (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),

>                          data_regl, data_regh, addr_regl, addr_regh,

> @@ -1685,12 +1700,6 @@ static void tcg_out_qemu_ld(TCGContext *s, const 

> TCGArg *args, bool is_64)

>      } else {

>          tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, 

> addr_regl);

>      }

> -    a_bits = get_alignment_bits(opc);

> -    s_bits = opc & MO_SIZE;

> -    /*

> -     * R6 removes the left/right instructions but requires the

> -     * system to support misaligned memory accesses.

> -     */

>      if (use_mips32r6_instructions) {

>          if (a_bits) {

>              tcg_out_test_alignment(s, true, addr_regl, addr_regh, 

> a_bits);

> @@ -1770,8 +1779,7 @@ static void tcg_out_qemu_st_direct(TCGContext *s, 

> TCGReg lo, TCGReg hi,

>      }

>  }

>  

> -static void __attribute__((unused))

> -tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg hi,

> +static void tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg 

> hi,

>                                      TCGReg base, MemOp opc)

>  {

>      const MIPSInsn sw1 = MIPS_BE ? OPC_SWL : OPC_SWR;

> @@ -1851,9 +1859,8 @@ static void tcg_out_qemu_st(TCGContext *s, const 

> TCGArg *args, bool is_64)

>      MemOp opc;

>  #if defined(CONFIG_SOFTMMU)

>      tcg_insn_unit *label_ptr[2];

> -#else

> -    unsigned a_bits, s_bits;

>  #endif

> +    unsigned a_bits, s_bits;

>      TCGReg base = TCG_REG_A0;

>  

>      data_regl = *args++;

> @@ -1862,10 +1869,20 @@ static void tcg_out_qemu_st(TCGContext *s, 

> const TCGArg *args, bool is_64)

>      addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);

>      oi = *args++;

>      opc = get_memop(oi);

> +    a_bits = get_alignment_bits(opc);

> +    s_bits = opc & MO_SIZE;

>  

> +    /*

> +     * R6 removes the left/right instructions but requires the

> +     * system to support misaligned memory accesses.

> +     */

>  #if defined(CONFIG_SOFTMMU)

>      tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 0);

> -    tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);

> +    if (use_mips32r6_instructions || a_bits >= s_bits) {

> +        tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);

> +    } else {

> +        tcg_out_qemu_st_unalign(s, data_regl, data_regh, base, opc);

> +    }

>      add_qemu_ldst_label(s, 0, oi,

>                          (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),

>                          data_regl, data_regh, addr_regl, addr_regh,

> @@ -1882,12 +1899,6 @@ static void tcg_out_qemu_st(TCGContext *s, const 

> TCGArg *args, bool is_64)

>      } else {

>          tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, 

> addr_regl);

>      }

> -    a_bits = get_alignment_bits(opc);

> -    s_bits = opc & MO_SIZE;

> -    /*

> -     * R6 removes the left/right instructions but requires the

> -     * system to support misaligned memory accesses.

> -     */

>      if (use_mips32r6_instructions) {

>          if (a_bits) {

>              tcg_out_test_alignment(s, true, addr_regl, addr_regh, 

> a_bits);

> -- 

> 2.25.1

> 

> 

> 



-- 
- Jiaxun
diff mbox series

Patch

diff --git a/tcg/mips/tcg-target.c.inc b/tcg/mips/tcg-target.c.inc
index 7ed0de9dae..3d6a0ba39e 100644
--- a/tcg/mips/tcg-target.c.inc
+++ b/tcg/mips/tcg-target.c.inc
@@ -1154,8 +1154,10 @@  static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
                              tcg_insn_unit *label_ptr[2], bool is_load)
 {
     MemOp opc = get_memop(oi);
-    unsigned s_bits = opc & MO_SIZE;
     unsigned a_bits = get_alignment_bits(opc);
+    unsigned s_bits = opc & MO_SIZE;
+    unsigned a_mask = (1 << a_bits) - 1;
+    unsigned s_mask = (1 << s_bits) - 1;
     int mem_index = get_mmuidx(oi);
     int fast_off = TLB_MASK_TABLE_OFS(mem_index);
     int mask_off = fast_off + offsetof(CPUTLBDescFast, mask);
@@ -1163,7 +1165,7 @@  static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
     int add_off = offsetof(CPUTLBEntry, addend);
     int cmp_off = (is_load ? offsetof(CPUTLBEntry, addr_read)
                    : offsetof(CPUTLBEntry, addr_write));
-    target_ulong mask;
+    target_ulong tlb_mask;
 
     /* Load tlb_mask[mmu_idx] and tlb_table[mmu_idx].  */
     tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP0, TCG_AREG0, mask_off);
@@ -1177,27 +1179,13 @@  static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
     /* Add the tlb_table pointer, creating the CPUTLBEntry address in TMP3.  */
     tcg_out_opc_reg(s, ALIAS_PADD, TCG_TMP3, TCG_TMP3, TCG_TMP1);
 
-    /* We don't currently support unaligned accesses.
-       We could do so with mips32r6.  */
-    if (a_bits < s_bits) {
-        a_bits = s_bits;
-    }
-
-    /* Mask the page bits, keeping the alignment bits to compare against.  */
-    mask = (target_ulong)TARGET_PAGE_MASK | ((1 << a_bits) - 1);
-
     /* Load the (low-half) tlb comparator.  */
     if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
-        tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);
-        tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, mask);
+        tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + LO_OFF);
     } else {
         tcg_out_ldst(s, (TARGET_LONG_BITS == 64 ? OPC_LD
                          : TCG_TARGET_REG_BITS == 64 ? OPC_LWU : OPC_LW),
                      TCG_TMP0, TCG_TMP3, cmp_off);
-        tcg_out_movi(s, TCG_TYPE_TL, TCG_TMP1, mask);
-        /* No second compare is required here;
-           load the tlb addend for the fast path.  */
-        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);
     }
 
     /* Zero extend a 32-bit guest address for a 64-bit host. */
@@ -1205,7 +1193,25 @@  static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
         tcg_out_ext32u(s, base, addrl);
         addrl = base;
     }
-    tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);
+
+    /*
+     * Mask the page bits, keeping the alignment bits to compare against.
+     * For unaligned accesses, compare against the end of the access to
+     * verify that it does not cross a page boundary.
+     */
+    tlb_mask = (target_ulong)TARGET_PAGE_MASK | a_mask;
+    tcg_out_movi(s, TCG_TYPE_I32, TCG_TMP1, tlb_mask);
+    if (a_mask >= s_mask) {
+        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, addrl);
+    } else {
+        tcg_out_opc_imm(s, ALIAS_PADDI, TCG_TMP2, addrl, s_mask - a_mask);
+        tcg_out_opc_reg(s, OPC_AND, TCG_TMP1, TCG_TMP1, TCG_TMP2);
+    }
+
+    if (TCG_TARGET_REG_BITS >= TARGET_LONG_BITS) {
+        /* Load the tlb addend for the fast path.  */
+        tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);
+    }
 
     label_ptr[0] = s->code_ptr;
     tcg_out_opc_br(s, OPC_BNE, TCG_TMP1, TCG_TMP0);
@@ -1213,7 +1219,7 @@  static void tcg_out_tlb_load(TCGContext *s, TCGReg base, TCGReg addrl,
     /* Load and test the high half tlb comparator.  */
     if (TCG_TARGET_REG_BITS < TARGET_LONG_BITS) {
         /* delay slot */
-        tcg_out_ld(s, TCG_TYPE_I32, TCG_TMP0, TCG_TMP3, cmp_off + HI_OFF);
+        tcg_out_ldst(s, OPC_LW, TCG_TMP0, TCG_TMP3, cmp_off + HI_OFF);
 
         /* Load the tlb addend for the fast path.  */
         tcg_out_ld(s, TCG_TYPE_PTR, TCG_TMP2, TCG_TMP3, add_off);
@@ -1535,8 +1541,7 @@  static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg lo, TCGReg hi,
     }
 }
 
-static void __attribute__((unused))
-tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
+static void tcg_out_qemu_ld_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
                                     TCGReg base, MemOp opc, bool is_64)
 {
     const MIPSInsn lw1 = MIPS_BE ? OPC_LWL : OPC_LWR;
@@ -1655,8 +1660,8 @@  static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
 #if defined(CONFIG_SOFTMMU)
     tcg_insn_unit *label_ptr[2];
 #else
-    unsigned a_bits, s_bits;
 #endif
+    unsigned a_bits, s_bits;
     TCGReg base = TCG_REG_A0;
 
     data_regl = *args++;
@@ -1665,10 +1670,20 @@  static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
     addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
     oi = *args++;
     opc = get_memop(oi);
+    a_bits = get_alignment_bits(opc);
+    s_bits = opc & MO_SIZE;
 
+    /*
+     * R6 removes the left/right instructions but requires the
+     * system to support misaligned memory accesses.
+     */
 #if defined(CONFIG_SOFTMMU)
     tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 1);
-    tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);
+    if (use_mips32r6_instructions || a_bits >= s_bits) {
+        tcg_out_qemu_ld_direct(s, data_regl, data_regh, base, opc, is_64);
+    } else {
+        tcg_out_qemu_ld_unalign(s, data_regl, data_regh, base, opc, is_64);
+    }
     add_qemu_ldst_label(s, 1, oi,
                         (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
                         data_regl, data_regh, addr_regl, addr_regh,
@@ -1685,12 +1700,6 @@  static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args, bool is_64)
     } else {
         tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
     }
-    a_bits = get_alignment_bits(opc);
-    s_bits = opc & MO_SIZE;
-    /*
-     * R6 removes the left/right instructions but requires the
-     * system to support misaligned memory accesses.
-     */
     if (use_mips32r6_instructions) {
         if (a_bits) {
             tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits);
@@ -1770,8 +1779,7 @@  static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg lo, TCGReg hi,
     }
 }
 
-static void __attribute__((unused))
-tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
+static void tcg_out_qemu_st_unalign(TCGContext *s, TCGReg lo, TCGReg hi,
                                     TCGReg base, MemOp opc)
 {
     const MIPSInsn sw1 = MIPS_BE ? OPC_SWL : OPC_SWR;
@@ -1851,9 +1859,8 @@  static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
     MemOp opc;
 #if defined(CONFIG_SOFTMMU)
     tcg_insn_unit *label_ptr[2];
-#else
-    unsigned a_bits, s_bits;
 #endif
+    unsigned a_bits, s_bits;
     TCGReg base = TCG_REG_A0;
 
     data_regl = *args++;
@@ -1862,10 +1869,20 @@  static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
     addr_regh = (TCG_TARGET_REG_BITS < TARGET_LONG_BITS ? *args++ : 0);
     oi = *args++;
     opc = get_memop(oi);
+    a_bits = get_alignment_bits(opc);
+    s_bits = opc & MO_SIZE;
 
+    /*
+     * R6 removes the left/right instructions but requires the
+     * system to support misaligned memory accesses.
+     */
 #if defined(CONFIG_SOFTMMU)
     tcg_out_tlb_load(s, base, addr_regl, addr_regh, oi, label_ptr, 0);
-    tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
+    if (use_mips32r6_instructions || a_bits >= s_bits) {
+        tcg_out_qemu_st_direct(s, data_regl, data_regh, base, opc);
+    } else {
+        tcg_out_qemu_st_unalign(s, data_regl, data_regh, base, opc);
+    }
     add_qemu_ldst_label(s, 0, oi,
                         (is_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
                         data_regl, data_regh, addr_regl, addr_regh,
@@ -1882,12 +1899,6 @@  static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is_64)
     } else {
         tcg_out_opc_reg(s, ALIAS_PADD, base, TCG_GUEST_BASE_REG, addr_regl);
     }
-    a_bits = get_alignment_bits(opc);
-    s_bits = opc & MO_SIZE;
-    /*
-     * R6 removes the left/right instructions but requires the
-     * system to support misaligned memory accesses.
-     */
     if (use_mips32r6_instructions) {
         if (a_bits) {
             tcg_out_test_alignment(s, true, addr_regl, addr_regh, a_bits);