[PATCH v3 RESEND 2/2] arm: lib: xor-neon: move pragma options to makefile

Adrian Ratiu adrian.ratiu at collabora.com
Mon Jan 18 05:55:57 EST 2021


Using a pragma like GCC optimize is a bad idea because it tags
all functions with an __attribute__((optimize)) which replaces
optimization options rather than appending so could result in
dropping important flags. Not recommended for production use.

Because these options should always be enabled for this file,
it's better to set them via command line. tree-vectorize is on
by default in Clang, but it doesn't hurt to make it explicit.

Suggested-by: Arvind Sankar <nivedita at alum.mit.edu>
Suggested-by: Ard Biesheuvel <ardb at kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers at google.com>
Reviewed-by: Nathan Chancellor <natechancellor at gmail.com>
Signed-off-by: Adrian Ratiu <adrian.ratiu at collabora.com>
---
 arch/arm/lib/Makefile   |  2 +-
 arch/arm/lib/xor-neon.c | 10 ----------
 2 files changed, 1 insertion(+), 11 deletions(-)

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 6d2ba454f25b..12d31d1a7630 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -45,6 +45,6 @@ $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
   NEON_FLAGS			:= -march=armv7-a -mfloat-abi=softfp -mfpu=neon
-  CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
+  CFLAGS_xor-neon.o		+= $(NEON_FLAGS) -ftree-vectorize -Wno-unused-variable
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif
diff --git a/arch/arm/lib/xor-neon.c b/arch/arm/lib/xor-neon.c
index e1e76186ec23..62b493e386c4 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -14,16 +14,6 @@ MODULE_LICENSE("GPL");
 #error You should compile this file with '-march=armv7-a -mfloat-abi=softfp -mfpu=neon'
 #endif
 
-/*
- * Pull in the reference implementations while instructing GCC (through
- * -ftree-vectorize) to attempt to exploit implicit parallelism and emit
- * NEON instructions.
- */
-#ifdef CONFIG_CC_IS_GCC
-#pragma GCC optimize "tree-vectorize"
-#endif
-
-#pragma GCC diagnostic ignored "-Wunused-variable"
 #include <asm-generic/xor.h>
 
 struct xor_block_template const xor_block_neon_inner = {
-- 
2.30.0




More information about the linux-arm-kernel mailing list