[PATCH v2 0/2] tcg/arm: Expand epilogue inline

[PATCH v2 0/2] tcg/arm: Expand epilogue inline

[Richard Henderson]

From: Richard Henderson <rth@twiddle.net>

v1: http://patchwork.ozlabs.org/patch/1176721/
v2 splits the patch in half, as requested by Phil.


r~


Richard Henderson (2):
  tcg/arm: Split out tcg_out_epilogue
  tcg/arm: Expand epilogue inline

 tcg/arm/tcg-target.inc.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

-- 
2.23.0

[PATCH v2 1/2] tcg/arm: Split out tcg_out_epilogue

[Richard Henderson]

From: Richard Henderson <rth@twiddle.net>

We will shortly use this function from tcg_out_op as well.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/arm/tcg-target.inc.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index fffb6611e2..e1aa740ba4 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -1746,6 +1746,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64)
 }
 
 static tcg_insn_unit *tb_ret_addr;
+static void tcg_out_epilogue(TCGContext *s);
 
 static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
                 const TCGArg *args, const int *const_args)
@@ -2284,19 +2285,17 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count)
       + TCG_TARGET_STACK_ALIGN - 1) \
      & -TCG_TARGET_STACK_ALIGN)
 
+#define STACK_ADDEND  (FRAME_SIZE - PUSH_SIZE)
+
 static void tcg_target_qemu_prologue(TCGContext *s)
 {
-    int stack_addend;
-
     /* Calling convention requires us to save r4-r11 and lr.  */
     /* stmdb sp!, { r4 - r11, lr } */
     tcg_out32(s, (COND_AL << 28) | 0x092d4ff0);
 
     /* Reserve callee argument and tcg temp space.  */
-    stack_addend = FRAME_SIZE - PUSH_SIZE;
-
     tcg_out_dat_rI(s, COND_AL, ARITH_SUB, TCG_REG_CALL_STACK,
-                   TCG_REG_CALL_STACK, stack_addend, 1);
+                   TCG_REG_CALL_STACK, STACK_ADDEND, 1);
     tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
                   CPU_TEMP_BUF_NLONGS * sizeof(long));
 
@@ -2310,11 +2309,15 @@ static void tcg_target_qemu_prologue(TCGContext *s)
      */
     s->code_gen_epilogue = s->code_ptr;
     tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, 0);
-
-    /* TB epilogue */
     tb_ret_addr = s->code_ptr;
+    tcg_out_epilogue(s);
+}
+
+static void tcg_out_epilogue(TCGContext *s)
+{
+    /* Release local stack frame.  */
     tcg_out_dat_rI(s, COND_AL, ARITH_ADD, TCG_REG_CALL_STACK,
-                   TCG_REG_CALL_STACK, stack_addend, 1);
+                   TCG_REG_CALL_STACK, STACK_ADDEND, 1);
 
     /* ldmia sp!, { r4 - r11, pc } */
     tcg_out32(s, (COND_AL << 28) | 0x08bd8ff0);
-- 
2.23.0

[PATCH v2 2/2] tcg/arm: Expand epilogue inline

[Richard Henderson]

From: Richard Henderson <rth@twiddle.net>

It is, after all, just two instructions.

Profiling on a cortex-a15, using -d nochain to increase the number
of exit_tb that are executed, shows a minor improvement of 0.5%.

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 tcg/arm/tcg-target.inc.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
index e1aa740ba4..6aa7757aac 100644
--- a/tcg/arm/tcg-target.inc.c
+++ b/tcg/arm/tcg-target.inc.c
@@ -1745,7 +1745,6 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64)
 #endif
 }
 
-static tcg_insn_unit *tb_ret_addr;
 static void tcg_out_epilogue(TCGContext *s);
 
 static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
@@ -1756,14 +1755,8 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
 
     switch (opc) {
     case INDEX_op_exit_tb:
-        /* Reuse the zeroing that exists for goto_ptr.  */
-        a0 = args[0];
-        if (a0 == 0) {
-            tcg_out_goto(s, COND_AL, s->code_gen_epilogue);
-        } else {
-            tcg_out_movi32(s, COND_AL, TCG_REG_R0, args[0]);
-            tcg_out_goto(s, COND_AL, tb_ret_addr);
-        }
+        tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, args[0]);
+        tcg_out_epilogue(s);
         break;
     case INDEX_op_goto_tb:
         {
@@ -2309,7 +2302,6 @@ static void tcg_target_qemu_prologue(TCGContext *s)
      */
     s->code_gen_epilogue = s->code_ptr;
     tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, 0);
-    tb_ret_addr = s->code_ptr;
     tcg_out_epilogue(s);
 }
 
-- 
2.23.0

Re: [PATCH v2 1/2] tcg/arm: Split out tcg_out_epilogue

[Philippe Mathieu-Daudé]

On 2/16/20 10:41 AM, Richard Henderson wrote:
> From: Richard Henderson <rth@twiddle.net>
> 
> We will shortly use this function from tcg_out_op as well.
> 
> Signed-off-by: Richard Henderson <rth@twiddle.net>
> ---
>   tcg/arm/tcg-target.inc.c | 19 +++++++++++--------
>   1 file changed, 11 insertions(+), 8 deletions(-)
> 
> diff --git a/tcg/arm/tcg-target.inc.c b/tcg/arm/tcg-target.inc.c
> index fffb6611e2..e1aa740ba4 100644
> --- a/tcg/arm/tcg-target.inc.c
> +++ b/tcg/arm/tcg-target.inc.c
> @@ -1746,6 +1746,7 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args, bool is64)
>   }
>   
>   static tcg_insn_unit *tb_ret_addr;
> +static void tcg_out_epilogue(TCGContext *s);
>   
>   static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
>                   const TCGArg *args, const int *const_args)
> @@ -2284,19 +2285,17 @@ static void tcg_out_nop_fill(tcg_insn_unit *p, int count)
>         + TCG_TARGET_STACK_ALIGN - 1) \
>        & -TCG_TARGET_STACK_ALIGN)
>   
> +#define STACK_ADDEND  (FRAME_SIZE - PUSH_SIZE)
> +
>   static void tcg_target_qemu_prologue(TCGContext *s)
>   {
> -    int stack_addend;
> -
>       /* Calling convention requires us to save r4-r11 and lr.  */
>       /* stmdb sp!, { r4 - r11, lr } */
>       tcg_out32(s, (COND_AL << 28) | 0x092d4ff0);
>   
>       /* Reserve callee argument and tcg temp space.  */
> -    stack_addend = FRAME_SIZE - PUSH_SIZE;
> -
>       tcg_out_dat_rI(s, COND_AL, ARITH_SUB, TCG_REG_CALL_STACK,
> -                   TCG_REG_CALL_STACK, stack_addend, 1);
> +                   TCG_REG_CALL_STACK, STACK_ADDEND, 1);
>       tcg_set_frame(s, TCG_REG_CALL_STACK, TCG_STATIC_CALL_ARGS_SIZE,
>                     CPU_TEMP_BUF_NLONGS * sizeof(long));
>   
> @@ -2310,11 +2309,15 @@ static void tcg_target_qemu_prologue(TCGContext *s)
>        */
>       s->code_gen_epilogue = s->code_ptr;
>       tcg_out_movi(s, TCG_TYPE_PTR, TCG_REG_R0, 0);
> -
> -    /* TB epilogue */
>       tb_ret_addr = s->code_ptr;
> +    tcg_out_epilogue(s);
> +}
> +
> +static void tcg_out_epilogue(TCGContext *s)
> +{
> +    /* Release local stack frame.  */
>       tcg_out_dat_rI(s, COND_AL, ARITH_ADD, TCG_REG_CALL_STACK,
> -                   TCG_REG_CALL_STACK, stack_addend, 1);
> +                   TCG_REG_CALL_STACK, STACK_ADDEND, 1);
>   
>       /* ldmia sp!, { r4 - r11, pc } */
>       tcg_out32(s, (COND_AL << 28) | 0x08bd8ff0);
> 

Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>

Thanks for splitting v1 :)