[PATCH] x86/crc32: improve crc32c_arch() code generation with clang

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Eric Biggers <ebiggers@xxxxxxxxxx>

crc32c_arch() is affected by
https://github.com/llvm/llvm-project/issues/20571 where clang
unnecessarily spills the inputs to "rm"-constrained operands to the
stack.  Replace "rm" with ASM_INPUT_RM which partially works around this
by expanding to "r" when the compiler is clang.  This results in better
code generation with clang, though still not optimal.

Signed-off-by: Eric Biggers <ebiggers@xxxxxxxxxx>
---

This applies to
https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git/log/?h=crc-next

 arch/x86/lib/crc32-glue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/lib/crc32-glue.c b/arch/x86/lib/crc32-glue.c
index 9c3f9c1b7bb9..4b4721176799 100644
--- a/arch/x86/lib/crc32-glue.c
+++ b/arch/x86/lib/crc32-glue.c
@@ -53,14 +53,14 @@ u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
 		return crc;
 	}
 
 	for (num_longs = len / sizeof(unsigned long);
 	     num_longs != 0; num_longs--, p += sizeof(unsigned long))
-		asm(CRC32_INST : "+r" (crc) : "rm" (*(unsigned long *)p));
+		asm(CRC32_INST : "+r" (crc) : ASM_INPUT_RM (*(unsigned long *)p));
 
 	for (len %= sizeof(unsigned long); len; len--, p++)
-		asm("crc32b %1, %0" : "+r" (crc) : "rm" (*p));
+		asm("crc32b %1, %0" : "+r" (crc) : ASM_INPUT_RM (*p));
 
 	return crc;
 }
 EXPORT_SYMBOL(crc32c_arch);
 

base-commit: 4ffd50862d41e5aaf2e749efa354afaa1317c309
-- 
2.48.1





[Index of Archives]     [Kernel]     [Gnu Classpath]     [Gnu Crypto]     [DM Crypt]     [Netfilter]     [Bugtraq]
  Powered by Linux