From 760d37adc6e25ce61865a9b3dd403597001b2884 Mon Sep 17 00:00:00 2001 From: Arvind Sankar Date: Tue, 4 Aug 2020 19:48:17 -0400 Subject: [PATCH] x86/boot/compressed: Use builtin mem functions for decompressor Since commits 19a122c5db4a ("x86, boot: Create a separate string.h file to provide standard string functions") 09ea54df991e ("x86, boot: Move memcmp() into string.h and string.c") the decompressor stub has been using the compiler's builtin memcpy, memset and memcmp functions, _except_ where it would likely have the largest impact, in the decompression code itself. Remove the #undef's of memcpy and memset in misc.c so that the decompressor code also uses the compiler builtins. The rationale given in the comment doesn't really apply: just because some functions use the out-of-line version is no reason to not use the builtin version in the rest. Replace the comment with an explanation of why memzero and memmove are being #define'd. Drop the suggestion to #undef in boot/string.h as well: the out-of-line versions are not really optimized versions, they're generic code that's good enough for the preboot environment. The compiler will likely generate better code for constant-size memcpy/memset/memcmp if it is allowed to. Most decompressors' performance is unchanged, with the exception of LZ4 and 64-bit ZSTD. Before After ARCH LZ4 73ms 10ms 32 LZ4 120ms 10ms 64 ZSTD 90ms 74ms 64 Measurements on QEMU on 2.2GHz Broadwell Xeon, using defconfig kernels. Decompressor code size has small differences, with the largest being that 64-bit ZSTD decreases just over 2k. The largest code size increase was on 64-bit XZ, of about 400 bytes. Signed-off-by: Arvind Sankar Suggested-by: Nick Terrell Tested-by: Nick Terrell Acked-by: Kees Cook Signed-off-by: Linus Torvalds --- arch/x86/boot/compressed/misc.c | 7 ++----- arch/x86/boot/string.h | 5 +---- 2 files changed, 3 insertions(+), 9 deletions(-) diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b41..e478e40fbe5a9 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512e..a232da487cd20 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp -- 2.39.5