diff mbox series

[v2,2/5] powerpc: module_[32|64].c: replace swap function with built-in one

Message ID 14019281554057359@sas1-87f9feb8d943.qloud-c.yandex.net
State New
Headers show
Series simple sort swap function improvements | expand

Commit Message

Andrey Abramov March 31, 2019, 6:35 p.m. UTC 
Replace relaswap with built-in one, because relaswap
does a simple byte to byte swap.

Since Spectre mitigations have made indirect function calls more
expensive, and the default simple byte copies swap is implemented
without them, an "optimized" custom swap function is now
a waste of time as well as code.

Signed-off-by: Andrey Abramov <st5pub@yandex.ru>
Reviewed by: George Spelvin <lkml@sdf.org>
---
 arch/powerpc/kernel/module_32.c | 17 +----------------
 arch/powerpc/kernel/module_64.c | 17 +----------------
 2 files changed, 2 insertions(+), 32 deletions(-)

Comments

Michael Ellerman April 1, 2019, 11:08 a.m. UTC | #1 
Andrey Abramov <st5pub@yandex.ru> writes:
> Replace relaswap with built-in one, because relaswap
> does a simple byte to byte swap.

I replied to v1 with an ack, which stands, this is just a clarification.

> Since Spectre mitigations have made indirect function calls more
> expensive, and the default simple byte copies swap is implemented
> without them, an "optimized" custom swap function is now
> a waste of time as well as code.

Spectre mitigations don't necessarily slow down indirect function calls
on all arches or in all configurations on all arches, so that
justification is a bit dubious.

That's not really a problem for this patch, because the existing
overhead of the function call is probably already enough to rival the
cost of the 24 byte copy.

cheers
diff mbox series

Patch

diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 88d83771f462..c311e8575d10 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -79,21 +79,6 @@  static int relacmp(const void *_x, const void *_y)
 		return 0;
 }
 
-static void relaswap(void *_x, void *_y, int size)
-{
-	uint32_t *x, *y, tmp;
-	int i;
-
-	y = (uint32_t *)_x;
-	x = (uint32_t *)_y;
-
-	for (i = 0; i < sizeof(Elf32_Rela) / sizeof(uint32_t); i++) {
-		tmp = x[i];
-		x[i] = y[i];
-		y[i] = tmp;
-	}
-}
-
 /* Get the potential trampolines size required of the init and
    non-init sections */
 static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
@@ -130,7 +115,7 @@  static unsigned long get_plt_size(const Elf32_Ehdr *hdr,
 			 */
 			sort((void *)hdr + sechdrs[i].sh_offset,
 			     sechdrs[i].sh_size / sizeof(Elf32_Rela),
-			     sizeof(Elf32_Rela), relacmp, relaswap);
+			     sizeof(Elf32_Rela), relacmp, NULL);
 
 			ret += count_relocs((void *)hdr
 					     + sechdrs[i].sh_offset,
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 8661eea78503..0c833d7f36f1 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -231,21 +231,6 @@  static int relacmp(const void *_x, const void *_y)
 		return 0;
 }
 
-static void relaswap(void *_x, void *_y, int size)
-{
-	uint64_t *x, *y, tmp;
-	int i;
-
-	y = (uint64_t *)_x;
-	x = (uint64_t *)_y;
-
-	for (i = 0; i < sizeof(Elf64_Rela) / sizeof(uint64_t); i++) {
-		tmp = x[i];
-		x[i] = y[i];
-		y[i] = tmp;
-	}
-}
-
 /* Get size of potential trampolines required. */
 static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 				    const Elf64_Shdr *sechdrs)
@@ -269,7 +254,7 @@  static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 			 */
 			sort((void *)sechdrs[i].sh_addr,
 			     sechdrs[i].sh_size / sizeof(Elf64_Rela),
-			     sizeof(Elf64_Rela), relacmp, relaswap);
+			     sizeof(Elf64_Rela), relacmp, NULL);
 
 			relocs += count_relocs((void *)sechdrs[i].sh_addr,
 					       sechdrs[i].sh_size