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
55 lines
2.7 KiB
Diff
55 lines
2.7 KiB
Diff
commit 94b0dc9419bd038cb85b364a7556569386c31741
|
|
Author: Noah Goldstein <goldstein.w.n@gmail.com>
|
|
Date: Wed Jun 15 10:41:29 2022 -0700
|
|
|
|
x86: Add bounds `x86_non_temporal_threshold`
|
|
|
|
The lower-bound (16448) and upper-bound (SIZE_MAX / 16) are assumed
|
|
by memmove-vec-unaligned-erms.
|
|
|
|
The lower-bound is needed because memmove-vec-unaligned-erms unrolls
|
|
the loop aggressively in the L(large_memset_4x) case.
|
|
|
|
The upper-bound is needed because memmove-vec-unaligned-erms
|
|
right-shifts the value of `x86_non_temporal_threshold` by
|
|
LOG_4X_MEMCPY_THRESH (4) which without a bound may overflow.
|
|
|
|
The lack of lower-bound can be a correctness issue. The lack of
|
|
upper-bound cannot.
|
|
|
|
(cherry picked from commit b446822b6ae4e8149902a78cdd4a886634ad6321)
|
|
|
|
diff --git a/manual/tunables.texi b/manual/tunables.texi
|
|
index 28ff502990c2a10f..5ab3212f34e3dc37 100644
|
|
--- a/manual/tunables.texi
|
|
+++ b/manual/tunables.texi
|
|
@@ -47,7 +47,7 @@ glibc.malloc.mxfast: 0x0 (min: 0x0, max: 0xffffffffffffffff)
|
|
glibc.elision.skip_lock_busy: 3 (min: -2147483648, max: 2147483647)
|
|
glibc.malloc.top_pad: 0x0 (min: 0x0, max: 0xffffffffffffffff)
|
|
glibc.cpu.x86_rep_stosb_threshold: 0x800 (min: 0x1, max: 0xffffffffffffffff)
|
|
-glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x0, max: 0xffffffffffffffff)
|
|
+glibc.cpu.x86_non_temporal_threshold: 0xc0000 (min: 0x4040, max: 0x0fffffffffffffff)
|
|
glibc.cpu.x86_shstk:
|
|
glibc.cpu.hwcap_mask: 0x6 (min: 0x0, max: 0xffffffffffffffff)
|
|
glibc.malloc.mmap_max: 0 (min: -2147483648, max: 2147483647)
|
|
diff --git a/sysdeps/x86/dl-cacheinfo.h b/sysdeps/x86/dl-cacheinfo.h
|
|
index 560bf260e8fbd7bf..8f85f70858413ebe 100644
|
|
--- a/sysdeps/x86/dl-cacheinfo.h
|
|
+++ b/sysdeps/x86/dl-cacheinfo.h
|
|
@@ -931,8 +931,14 @@ dl_init_cacheinfo (struct cpu_features *cpu_features)
|
|
|
|
TUNABLE_SET_WITH_BOUNDS (x86_data_cache_size, data, 0, SIZE_MAX);
|
|
TUNABLE_SET_WITH_BOUNDS (x86_shared_cache_size, shared, 0, SIZE_MAX);
|
|
+ /* SIZE_MAX >> 4 because memmove-vec-unaligned-erms right-shifts the value of
|
|
+ 'x86_non_temporal_threshold' by `LOG_4X_MEMCPY_THRESH` (4) and it is best
|
|
+ if that operation cannot overflow. Minimum of 0x4040 (16448) because the
|
|
+ L(large_memset_4x) loops need 64-byte to cache align and enough space for
|
|
+ at least 1 iteration of 4x PAGE_SIZE unrolled loop. Both values are
|
|
+ reflected in the manual. */
|
|
TUNABLE_SET_WITH_BOUNDS (x86_non_temporal_threshold, non_temporal_threshold,
|
|
- 0, SIZE_MAX);
|
|
+ 0x4040, SIZE_MAX >> 4);
|
|
TUNABLE_SET_WITH_BOUNDS (x86_rep_movsb_threshold, rep_movsb_threshold,
|
|
minimum_rep_movsb_threshold, SIZE_MAX);
|
|
TUNABLE_SET_WITH_BOUNDS (x86_rep_stosb_threshold, rep_stosb_threshold, 1,
|