linux-snps-arc.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] ARC: unwind: Use built-in sort swap to reduce code size and improve performance
@ 2025-04-09 17:11 Yu-Chun Lin
  2025-04-28  2:37 ` Vineet Gupta
  0 siblings, 1 reply; 2+ messages in thread
From: Yu-Chun Lin @ 2025-04-09 17:11 UTC (permalink / raw)
  To: vgupta; +Cc: linux-snps-arc, linux-kernel, jserv, visitorckw, Yu-Chun Lin

The custom swap function used in sort() was identical to the default
built-in sort swap. Remove the custom swap function and passes NULL to
sort(), allowing it to use the default swap function.

This change reduces code size and improves performance, particularly when
CONFIG_MITIGATION_RETPOLINE is enabled. With RETPOLINE mitigation, indirect
function calls incur significant overhead, and using the default swap
function avoids this cost.

$ ./scripts/bloat-o-meter ./unwind.o.old ./unwind.o.new
add/remove: 0/1 grow/shrink: 0/1 up/down: 0/-22 (-22)
Function                                     old     new   delta
init_unwind_hdr.constprop                    544     540      -4
swap_eh_frame_hdr_table_entries               18       -     -18
Total: Before=4410, After=4388, chg -0.50%

Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
---
Compile test only

 arch/arc/kernel/unwind.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index d8969dab12d4..789cfb9ea14e 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -241,15 +241,6 @@ static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2)
 	return (e1->start > e2->start) - (e1->start < e2->start);
 }
 
-static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
-{
-	struct eh_frame_hdr_table_entry *e1 = p1;
-	struct eh_frame_hdr_table_entry *e2 = p2;
-
-	swap(e1->start, e2->start);
-	swap(e1->fde, e2->fde);
-}
-
 static void init_unwind_hdr(struct unwind_table *table,
 			    void *(*alloc) (unsigned long))
 {
@@ -345,7 +336,7 @@ static void init_unwind_hdr(struct unwind_table *table,
 	sort(header->table,
 	     n,
 	     sizeof(*header->table),
-	     cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries);
+	     cmp_eh_frame_hdr_table_entries, NULL);
 
 	table->hdrsz = hdrSize;
 	smp_wmb();
-- 
2.43.0


_______________________________________________
linux-snps-arc mailing list
linux-snps-arc@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-snps-arc

^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH] ARC: unwind: Use built-in sort swap to reduce code size and improve performance
  2025-04-09 17:11 [PATCH] ARC: unwind: Use built-in sort swap to reduce code size and improve performance Yu-Chun Lin
@ 2025-04-28  2:37 ` Vineet Gupta
  0 siblings, 0 replies; 2+ messages in thread
From: Vineet Gupta @ 2025-04-28  2:37 UTC (permalink / raw)
  To: Yu-Chun Lin, vgupta; +Cc: linux-snps-arc, linux-kernel, jserv, visitorckw

On 4/9/25 10:11, Yu-Chun Lin wrote:
> The custom swap function used in sort() was identical to the default
> built-in sort swap. Remove the custom swap function and passes NULL to
> sort(), allowing it to use the default swap function.
>
> This change reduces code size and improves performance, particularly when
> CONFIG_MITIGATION_RETPOLINE is enabled. With RETPOLINE mitigation, indirect
> function calls incur significant overhead, and using the default swap
> function avoids this cost.
>
> $ ./scripts/bloat-o-meter ./unwind.o.old ./unwind.o.new
> add/remove: 0/1 grow/shrink: 0/1 up/down: 0/-22 (-22)
> Function                                     old     new   delta
> init_unwind_hdr.constprop                    544     540      -4
> swap_eh_frame_hdr_table_entries               18       -     -18
> Total: Before=4410, After=4388, chg -0.50%
>
> Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>

Acked-by: Vineet Gupta <vgupta@kernel.org>

Added to for-curr.

Thx,
-Vineet

> ---
> Compile test only
>
>  arch/arc/kernel/unwind.c | 11 +----------
>  1 file changed, 1 insertion(+), 10 deletions(-)
>
> diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
> index d8969dab12d4..789cfb9ea14e 100644
> --- a/arch/arc/kernel/unwind.c
> +++ b/arch/arc/kernel/unwind.c
> @@ -241,15 +241,6 @@ static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2)
>  	return (e1->start > e2->start) - (e1->start < e2->start);
>  }
>  
> -static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
> -{
> -	struct eh_frame_hdr_table_entry *e1 = p1;
> -	struct eh_frame_hdr_table_entry *e2 = p2;
> -
> -	swap(e1->start, e2->start);
> -	swap(e1->fde, e2->fde);
> -}
> -
>  static void init_unwind_hdr(struct unwind_table *table,
>  			    void *(*alloc) (unsigned long))
>  {
> @@ -345,7 +336,7 @@ static void init_unwind_hdr(struct unwind_table *table,
>  	sort(header->table,
>  	     n,
>  	     sizeof(*header->table),
> -	     cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries);
> +	     cmp_eh_frame_hdr_table_entries, NULL);
>  
>  	table->hdrsz = hdrSize;
>  	smp_wmb();


_______________________________________________
linux-snps-arc mailing list
linux-snps-arc@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-snps-arc

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2025-04-28  2:39 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-04-09 17:11 [PATCH] ARC: unwind: Use built-in sort swap to reduce code size and improve performance Yu-Chun Lin
2025-04-28  2:37 ` Vineet Gupta

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).