56 lines
1.6 KiB
Diff
56 lines
1.6 KiB
Diff
|
From c6272098323153db373f2986c67786ea8c85f1cf Mon Sep 17 00:00:00 2001
|
||
|
|
From: Noah Goldstein <goldstein.w.n@gmail.com>
|
||
|
|
Date: Tue, 15 Feb 2022 08:18:15 -0600
|
||
|
|
Subject: [PATCH] x86: Fallback {str|wcs}cmp RTM in the ncmp overflow case [BZ
|
||
|
|
#28896]
|
||
|
|
Content-type: text/plain; charset=UTF-8
|
||
|
|
|
||
|
|
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>
|
||
|
|
---
|
||
|
|
sysdeps/x86_64/multiarch/strcmp-avx2.S | 8 ++------
|
||
|
|
1 file changed, 2 insertions(+), 6 deletions(-)
|
||
|
|
|
||
|
|
Conflicts:
|
||
|
|
sysdeps/x86_64/multiarch/strcmp-avx2.S
|
||
|
|
(split into two patches due to upstream bug differences)
|
||
|
|
|
||
|
|
diff --git a/sysdeps/x86_64/multiarch/strcmp-avx2.S b/sysdeps/x86_64/multiarch/strcmp-avx2.S
|
||
|
|
index 28cc98b6..e267c6cb 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)
|
||
|
|
--
|
||
|
|
GitLab
|
||
|
|
|