diff options
| author | Sunil K Pandey <skpgkp1@gmail.com> | 2020-06-12 08:57:16 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2020-07-04 10:05:03 -0700 |
| commit | 23db5555eb914c6a0228ecf5dc13c13be5d8dbd7 (patch) | |
| tree | 25bc74d71ad5954385951cb39ed83995fa42c107 | |
| parent | 21344a3d62a29406fddeec069ee4eb3c341369f9 (diff) | |
| download | glibc-23db5555eb914c6a0228ecf5dc13c13be5d8dbd7.tar glibc-23db5555eb914c6a0228ecf5dc13c13be5d8dbd7.tar.gz glibc-23db5555eb914c6a0228ecf5dc13c13be5d8dbd7.tar.bz2 glibc-23db5555eb914c6a0228ecf5dc13c13be5d8dbd7.zip | |
Fix avx2 strncmp offset compare condition check [BZ #25933]
strcmp-avx2.S: In avx2 strncmp function, strings are compared in
chunks of 4 vector size(i.e. 32x4=128 byte for avx2). After first 4
vector size comparison, code must check whether it already passed
the given offset. This patch implement avx2 offset check condition
for strncmp function, if both string compare same for first 4 vector
size.
(cherry picked from commit 75870237ff3bb363447b03f4b0af100227570910)
| -rw-r--r-- | sysdeps/x86_64/multiarch/strcmp-avx2.S | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S index 78fc116877..156c19496a 100644 --- a/sysdeps/x86_64/multiarch/strcmp-avx2.S +++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S @@ -591,7 +591,14 @@ L(loop_cross_page_2_vec): movl $(PAGE_SIZE / (VEC_SIZE * 4) - 1), %esi testq %rdi, %rdi +# ifdef USE_AS_STRNCMP + /* At this point, if %rdi value is 0, it already tested + VEC_SIZE*4+%r10 byte starting from %rax. This label + checks whether strncmp maximum offset reached or not. */ + je L(string_nbyte_offset_check) +# else je L(back_to_loop) +# endif tzcntq %rdi, %rcx addq %r10, %rcx /* Adjust for number of bytes skipped. */ @@ -627,6 +634,14 @@ L(loop_cross_page_2_vec): VZEROUPPER ret +# ifdef USE_AS_STRNCMP +L(string_nbyte_offset_check): + leaq (VEC_SIZE * 4)(%r10), %r10 + cmpq %r10, %r11 + jbe L(zero) + jmp L(back_to_loop) +# endif + .p2align 4 L(cross_page_loop): /* Check one byte/dword at a time. */ |