summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/sha512-avx2-asm.S
diff options
context:
space:
mode:
authorDenys Vlasenko <dvlasenk@redhat.com>2017-01-19 22:33:04 +0100
committerHerbert Xu <herbert@gondor.apana.org.au>2017-01-23 22:50:29 +0800
commite183914af00e15eb41ae666d44e323bfa154be13 (patch)
tree177ded54a5bd45ec1ae6c544d28b0a45a31118f1 /arch/x86/crypto/sha512-avx2-asm.S
parent587d531b8f67ebe62f8326849a7a685a03cbc904 (diff)
crypto: x86 - make constants readonly, allow linker to merge them
A lot of asm-optimized routines in arch/x86/crypto/ keep its constants in .data. This is wrong, they should be on .rodata. Mnay of these constants are the same in different modules. For example, 128-bit shuffle mask 0x000102030405060708090A0B0C0D0E0F exists in at least half a dozen places. There is a way to let linker merge them and use just one copy. The rules are as follows: mergeable objects of different sizes should not share sections. You can't put them all in one .rodata section, they will lose "mergeability". GCC puts its mergeable constants in ".rodata.cstSIZE" sections, or ".rodata.cstSIZE.<object_name>" if -fdata-sections is used. This patch does the same: .section .rodata.cst16.SHUF_MASK, "aM", @progbits, 16 It is important that all data in such section consists of 16-byte elements, not larger ones, and there are no implicit use of one element from another. When this is not the case, use non-mergeable section: .section .rodata[.VAR_NAME], "a", @progbits This reduces .data by ~15 kbytes: text data bss dec hex filename 11097415 2705840 2630712 16433967 fac32f vmlinux-prev.o 11112095 2690672 2630712 16433479 fac147 vmlinux.o Merged objects are visible in System.map: ffffffff81a28810 r POLY ffffffff81a28810 r POLY ffffffff81a28820 r TWOONE ffffffff81a28820 r TWOONE ffffffff81a28830 r PSHUFFLE_BYTE_FLIP_MASK <- merged regardless of ffffffff81a28830 r SHUF_MASK <------------- the name difference ffffffff81a28830 r SHUF_MASK ffffffff81a28830 r SHUF_MASK .. ffffffff81a28d00 r K512 <- merged three identical 640-byte tables ffffffff81a28d00 r K512 ffffffff81a28d00 r K512 Use of object names in section name suffixes is not strictly necessary, but might help if someday link stage will use garbage collection to eliminate unused sections (ld --gc-sections). Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: Herbert Xu <herbert@gondor.apana.org.au> CC: Josh Poimboeuf <jpoimboe@redhat.com> CC: Xiaodong Liu <xiaodong.liu@intel.com> CC: Megha Dey <megha.dey@intel.com> CC: linux-crypto@vger.kernel.org CC: x86@kernel.org CC: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Diffstat (limited to 'arch/x86/crypto/sha512-avx2-asm.S')
-rw-r--r--arch/x86/crypto/sha512-avx2-asm.S10
1 files changed, 8 insertions, 2 deletions
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
index 1f20b35d8573..7f5f6c6ec72e 100644
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ b/arch/x86/crypto/sha512-avx2-asm.S
@@ -684,8 +684,11 @@ ENDPROC(sha512_transform_rorx)
########################################################################
### Binary Data
-.data
+# Mergeable 640-byte rodata section. This allows linker to merge the table
+# with other, exactly the same 640-byte fragment of another rodata section
+# (if such section exists).
+.section .rodata.cst640.K512, "aM", @progbits, 640
.align 64
# K[t] used in SHA512 hashing
K512:
@@ -730,14 +733,17 @@ K512:
.quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a
.quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817
+.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
.align 32
-
# Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb.
PSHUFFLE_BYTE_FLIP_MASK:
.octa 0x08090a0b0c0d0e0f0001020304050607
.octa 0x18191a1b1c1d1e1f1011121314151617
+.section .rodata.cst32.MASK_YMM_LO, "aM", @progbits, 32
+.align 32
MASK_YMM_LO:
.octa 0x00000000000000000000000000000000
.octa 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+
#endif