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 <[email protected]>
Suggested-by: Ard Biesheuvel <[email protected]>
Reviewed-by: Nick Desaulniers <[email protected]>
Reviewed-by: Nathan Chancellor <[email protected]>
Signed-off-by: Adrian Ratiu <[email protected]>
---
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 f9f3601cc2d1..65125ce69044 100644
--- a/arch/arm/lib/xor-neon.c
+++ b/arch/arm/lib/xor-neon.c
@@ -23,16 +23,6 @@ MODULE_LICENSE("GPL");
#warning Clang does not vectorize code in this file.
#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