aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2022-02-15 08:18:15 -0600
committerSunil K Pandey <skpgkp2@gmail.com>2022-05-25 15:07:28 -0700
commit69f16619e7119e26d70c00ac8b8750ed350147a3 (patch)
tree1738ded54d905fb4fdb94289f5d684301c85dbd3
parent7da0b8522b0498898f2b0d0b49f70869056e1e43 (diff)
downloadglibc-69f16619e7119e26d70c00ac8b8750ed350147a3.tar
glibc-69f16619e7119e26d70c00ac8b8750ed350147a3.tar.gz
glibc-69f16619e7119e26d70c00ac8b8750ed350147a3.tar.bz2
glibc-69f16619e7119e26d70c00ac8b8750ed350147a3.zip
x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ #29127]
Re-cherry-pick commit c627209832 for strcmp-avx2.S change which was omitted in intial cherry pick because at the time this bug was not present on release branch. Fixes BZ #29127. In the overflow fallback strncmp-avx2-rtm and wcsncmp-avx2-rtm would call strcmp-avx2 and wcscmp-avx2 respectively. This would have not checks around vzeroupper and would trigger spurious aborts. This commit fixes that. test-strcmp, test-strncmp, test-wcscmp, and test-wcsncmp all pass on AVX2 machines with and without RTM. Co-authored-by: H.J. Lu <hjl.tools@gmail.com> (cherry picked from commit c6272098323153db373f2986c67786ea8c85f1cf)
-rw-r--r--sysdeps/x86_64/multiarch/strcmp-avx2.S8
1 files changed, 2 insertions, 6 deletions
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S
index aa91f6e48a..a9806daadb 100644
--- a/sysdeps/x86_64/multiarch/strcmp-avx2.S
+++ b/sysdeps/x86_64/multiarch/strcmp-avx2.S
@@ -345,10 +345,10 @@ L(one_or_less):
movq %LOCALE_REG, %rdx
# endif
jb L(ret_zero)
-# ifdef USE_AS_WCSCMP
/* 'nbe' covers the case where length is negative (large
unsigned). */
- jnbe __wcscmp_avx2
+ jnbe OVERFLOW_STRCMP
+# ifdef USE_AS_WCSCMP
movl (%rdi), %edx
xorl %eax, %eax
cmpl (%rsi), %edx
@@ -357,10 +357,6 @@ L(one_or_less):
negl %eax
orl $1, %eax
# else
- /* 'nbe' covers the case where length is negative (large
- unsigned). */
-
- jnbe __strcmp_avx2
movzbl (%rdi), %eax
movzbl (%rsi), %ecx
TOLOWER_gpr (%rax, %eax)