forked from rpms/glibc
668eaab0c7
* Fri Jul 22 2022 Arjun Shankar <arjun@redhat.com> - 2.34-40
- Sync with upstream branch release/2.34/master,
commit b2f32e746492615a6eb3e66fac1e766e32e8deb1:
- malloc: Simplify implementation of __malloc_assert
- Update syscall-names.list for Linux 5.18
- x86: Add missing IS_IN (libc) check to strncmp-sse4_2.S
- x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file
- x86: Move and slightly improve memset_erms
- x86: Add definition for __wmemset_chk AVX2 RTM in ifunc impl list
- x86: Put wcs{n}len-sse4.1 in the sse4.1 text section
- x86: Align entry for memrchr to 64-bytes.
- x86: Add BMI1/BMI2 checks for ISA_V3 check
- x86: Cleanup bounds checking in large memcpy case
- x86: Add bounds `x86_non_temporal_threshold`
- x86: Add sse42 implementation to strcmp's ifunc
- x86: Fix misordered logic for setting `rep_movsb_stop_threshold`
- x86: Align varshift table to 32-bytes
- x86: ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST expect no transactions
- x86: Shrink code size of memchr-evex.S
- x86: Shrink code size of memchr-avx2.S
- x86: Optimize memrchr-avx2.S
- x86: Optimize memrchr-evex.S
- x86: Optimize memrchr-sse2.S
- x86: Add COND_VZEROUPPER that can replace vzeroupper if no `ret`
- x86: Create header for VEC classes in x86 strings library
- x86_64: Add strstr function with 512-bit EVEX
- x86-64: Ignore r_addend for R_X86_64_GLOB_DAT/R_X86_64_JUMP_SLOT
- x86_64: Implement evex512 version of strlen, strnlen, wcslen and wcsnlen
- x86_64: Remove bzero optimization
- x86_64: Remove end of line trailing spaces
- nptl: Fix ___pthread_unregister_cancel_restore asynchronous restore
- linux: Fix mq_timereceive check for 32 bit fallback code (BZ 29304)
Resolves: #2109505
91 lines
2.5 KiB
Diff
91 lines
2.5 KiB
Diff
commit e805606193e1a39956ca5ef73cb44a8796730686
|
|
Author: Noah Goldstein <goldstein.w.n@gmail.com>
|
|
Date: Mon Jun 6 21:11:28 2022 -0700
|
|
|
|
x86: Add COND_VZEROUPPER that can replace vzeroupper if no `ret`
|
|
|
|
The RTM vzeroupper mitigation has no way of replacing inline
|
|
vzeroupper not before a return.
|
|
|
|
This can be useful when hoisting a vzeroupper to save code size
|
|
for example:
|
|
|
|
```
|
|
L(foo):
|
|
cmpl %eax, %edx
|
|
jz L(bar)
|
|
tzcntl %eax, %eax
|
|
addq %rdi, %rax
|
|
VZEROUPPER_RETURN
|
|
|
|
L(bar):
|
|
xorl %eax, %eax
|
|
VZEROUPPER_RETURN
|
|
```
|
|
|
|
Can become:
|
|
|
|
```
|
|
L(foo):
|
|
COND_VZEROUPPER
|
|
cmpl %eax, %edx
|
|
jz L(bar)
|
|
tzcntl %eax, %eax
|
|
addq %rdi, %rax
|
|
ret
|
|
|
|
L(bar):
|
|
xorl %eax, %eax
|
|
ret
|
|
```
|
|
|
|
This code does not change any existing functionality.
|
|
|
|
There is no difference in the objdump of libc.so before and after this
|
|
patch.
|
|
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
|
|
|
|
(cherry picked from commit dd5c483b2598f411428df4d8864c15c4b8a3cd68)
|
|
|
|
diff --git a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
|
|
index 3f531dd47fceefe9..6ca9f5e6bae7ba72 100644
|
|
--- a/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
|
|
+++ b/sysdeps/x86_64/multiarch/avx-rtm-vecs.h
|
|
@@ -20,6 +20,7 @@
|
|
#ifndef _AVX_RTM_VECS_H
|
|
#define _AVX_RTM_VECS_H 1
|
|
|
|
+#define COND_VZEROUPPER COND_VZEROUPPER_XTEST
|
|
#define ZERO_UPPER_VEC_REGISTERS_RETURN \
|
|
ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST
|
|
|
|
diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
|
|
index 7bebdeb21095eda0..93e44be22e2275f1 100644
|
|
--- a/sysdeps/x86_64/sysdep.h
|
|
+++ b/sysdeps/x86_64/sysdep.h
|
|
@@ -106,6 +106,24 @@ lose: \
|
|
vzeroupper; \
|
|
ret
|
|
|
|
+/* Can be used to replace vzeroupper that is not directly before a
|
|
+ return. This is useful when hoisting a vzeroupper from multiple
|
|
+ return paths to decrease the total number of vzerouppers and code
|
|
+ size. */
|
|
+#define COND_VZEROUPPER_XTEST \
|
|
+ xtest; \
|
|
+ jz 1f; \
|
|
+ vzeroall; \
|
|
+ jmp 2f; \
|
|
+1: \
|
|
+ vzeroupper; \
|
|
+2:
|
|
+
|
|
+/* In RTM define this as COND_VZEROUPPER_XTEST. */
|
|
+#ifndef COND_VZEROUPPER
|
|
+# define COND_VZEROUPPER vzeroupper
|
|
+#endif
|
|
+
|
|
/* Zero upper vector registers and return. */
|
|
#ifndef ZERO_UPPER_VEC_REGISTERS_RETURN
|
|
# define ZERO_UPPER_VEC_REGISTERS_RETURN \
|