locale: localdef input files are now encoded in UTF-8
Previously, they were assumed to be in ISO-8859-1, and that the output
charset overlapped with ISO-8859-1 for the characters actually used.
However, this did not work as intended on many architectures even for
an ISO-8859-1 output encoding because of the char signedness bug in
lr_getc. Therefore, this commit switches to UTF-8 without making
provisions for backwards compatibility.
The following Elisp code can be used to convert locale definition files
to UTF-8:
The array lr->buf contains characters, which can be signed. A 0xff
byte in the input could be incorrectly reported as EOF. More
importantly, get_string in linereader.c converts a signed input byte
to a Unicode code point using ADDWC ((uint32_t) ch), under the
assumption that this decodes the ISO-8859-1 input encoding. If char
is signed, this does not give the correct result. This means that
ISO-8859-1 input files for localedef are not actually supported,
contrary to the comment in get_string. This is a happy accident because
we can therefore change the file encoding to UTF-8 without impacting
backwards compatibility.
While at it, remove the \32 check for MS-DOS end-of-file character (^Z).
Reviewed-by: Carlos O'Donell <carlos@redhat.com> Tested-by: Carlos O'Donell <carlos@redhat.com>
Fangrui Song [Tue, 5 Jul 2022 04:15:51 +0000 (21:15 -0700)]
libc-symbols.h: remove unused macros
Beside weak_hidden_alias/declare_symbol_alias/hidden_data_ver, many
*_hidden_* macros are removed. If there is a rare need to use one, one
may write something like `#if IS_IN (libm)\nhidden_def (...)\n#endif`
instead.
The headers mempcpy.h, strcase.h, strchrnul.h, and strndup.h are
included if not building argp for glibc. Commit c5af724c0b214a517f8558887f7a70efcfa2c813 added them in 2003 for gnulib,
but gnulib's current master patches them out:
https://git.savannah.gnu.org/gitweb/?p=gnulib.git;a=blob;f=lib/argp-namefrob.h;h=9c82ac79c215540f986c3e04398edba3ba1b7234;hb=HEAD
The main drive is to optimize the internal usage and required size
when sigset_t is embedded in other data structures. On Linux, the
current supported signal set requires up to 8 bytes (16 on mips),
was lower than the user defined sigset_t (128 bytes).
A new internal type internal_sigset_t is added, along with the
functions to operate on it similar to the ones for sigset_t. The
internal-signals.h is also refactored to remove unused functions
Besides small stack usage on some functions (posix_spawn, abort)
it lower the struct pthread by about 120 bytes (112 on mips).
Kito Cheng [Tue, 28 Jun 2022 13:52:19 +0000 (21:52 +0800)]
riscv: Use memcpy to handle unaligned access when fixing R_RISCV_RELATIVE
Although RISC-V Linux will enable the unaligned memory access handler by
default, that is quite expensive in general, using memcpy will be much cheaper
- just break down that into several load/store byte instructions.
Tejas Belagod [Mon, 27 Jun 2022 18:00:50 +0000 (18:00 +0000)]
AArch64: Add asymmetric faulting mode for tag violations in mem.tagging tunable
The new asymmetric mode is available when HWCAP2_MTE3 is set (support is
available), bit2 is set in the tunable (user request per application),
and the system is configured such that the asymmetric mode is preferred over
sync or async (per-cpu system-wide setting).
Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
linux: Fix mq_timereceive check for 32 bit fallback code (BZ 29304)
On success, mq_receive() and mq_timedreceive() return the number of
bytes in the received message, so it requires to check if the value
is larger than 0.
Noah Goldstein [Tue, 28 Jun 2022 15:26:26 +0000 (08:26 -0700)]
x86-64: Small improvements to dl-trampoline.S
1. Remove sse2 instructions when using the avx512 or avx version.
2. Fixup some format nits in how the address offsets where aligned.
3. Use more space efficient instructions in the conditional AVX
restoral.
- vpcmpeqq -> vpcmpeqb
- cmp imm32, r; jz -> inc r; jz
4. Use `rep movsb` instead of `rep movsq`. The former is guranteed to
be fast with the ERMS flags, the latter is not. The latter also
wastes an instruction in size setup.
Noah Goldstein [Wed, 29 Jun 2022 23:07:15 +0000 (16:07 -0700)]
x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file
The primary memmove_{impl}_unaligned_erms implementations don't
interact with this function. Putting them in same file both
wastes space and unnecessarily bloats a hot code section.
Noah Goldstein [Wed, 29 Jun 2022 23:07:05 +0000 (16:07 -0700)]
x86: Move and slightly improve memset_erms
Implementation wise:
1. Remove the VZEROUPPER as memset_{impl}_unaligned_erms does not
use the L(stosb) label that was previously defined.
2. Don't give the hotpath (fallthrough) to zero size.
Code positioning wise:
Move memset_{chk}_erms to its own file. Leaving it in between the
memset_{impl}_unaligned both adds unnecessary complexity to the
file and wastes space in a relatively hot cache section.
Arjun Shankar [Wed, 29 Jun 2022 22:37:34 +0000 (00:37 +0200)]
linux: Remove unnecessary nice.c and signal.c
These files simply include the sysdeps/posix implementations which would
be used even in the absence of the files. They have been unnecessary
since 7b17aeda0c5e when nice and signal were removed from the
syscalls.list file.
Florian Weimer [Wed, 29 Jun 2022 11:50:50 +0000 (13:50 +0200)]
Linux: Forward declaration of struct iovec for process_madvise
This maintains compatibility between <sys/mman.h> and <linux/uio.h>.
Before that, the addition of process_madvise made those two header
files incompatible. This has been observed resulting in a build
failure in LLDB's Process/Linux/NativeRegisterContextLinux_s390x.cpp
source file.
H.J. Lu [Mon, 27 Jun 2022 18:36:28 +0000 (11:36 -0700)]
x86-64: Only define used SSE/AVX/AVX512 run-time resolvers
When glibc is built with x86-64 ISA level v3, SSE run-time resolvers
aren't used. For x86-64 ISA level v4 build, both SSE and AVX resolvers
are unused. Check the minimum x86-64 ISA level to exclude the unused
run-time resolvers.
Noah Goldstein [Fri, 24 Jun 2022 23:15:42 +0000 (16:15 -0700)]
x86: Fix backwards Prefer_No_VZEROUPPER check in ifunc-evex.h
Add third argument to X86_ISA_CPU_FEATURES_ARCH_P macro so the runtime
CPU_FEATURES_ARCH_P check can be inverted if the
MINIMUM_X86_ISA_LEVEL is not high enough to constantly evaluate
the check.
Use this new macro to correct the backwards check in ifunc-evex.h
Fangrui Song [Sun, 26 Jun 2022 22:31:19 +0000 (15:31 -0700)]
Makerules: Remove no-op -Wl,-d when linking libc_pic.os
In GNU ld, -d assigns space to common symbols for -r (i.e. change common
symbols to STB_GLOBAL definitions). This option was added in commit da2d1bc5adf49352232ad0514e79fbd5dcae08e8 (1998) perhaps because ld at
that time had a bug that common symbols did not override shared object
definitions. -d has been long unneeded and more so since -fno-common
was added to +cflags.
misc: Optimize internal usage of __libc_single_threaded
By adding an internal alias to avoid the GOT indirection.
On some architecture, __libc_single_thread may be accessed through
copy relocations and thus it requires to update also the copies
default copy.
This is done by adding a new internal macro,
libc_hidden_data_{proto,def}, which has an addition argument that
specifies the alias name (instead of default __GI_ one).
It was added on Linux 5.2 (2db154b3ea8e14b04fee23e3fdfd5e9d17fbc6ae)
as way t move a mount from one place to another and, in the next
commit, allow to attach an unattached mount tree.
Reviewed-by: Carlos O'Donell <carlos@redhat.com> Tested-by: Carlos O'Donell <carlos@redhat.com>
It was added on 5.2 (93766fbd2696c2c4453dd8e1070977e9cd4e6b6d) to
provide a way by which a filesystem opened with fsopen and configured
by a series of fsconfig calls can have a detached mount object
created for it.
Tested-by: Carlos O'Donell <carlos@redhat.com> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
It was added on Linux 5.2 (24dcb3d90a1f67fe08c68a004af37df059d74005)
to start the process of preparing to create a superblock that will
then be mountable, using an fd as a context handle.
Tested-by: Carlos O'Donell <carlos@redhat.com> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Fri, 24 Jun 2022 17:38:14 +0000 (19:38 +0200)]
resolv/tst-resolv-noaaaa: Support building for older C standards
This avoids a compilation error:
tst-resolv-noaaaa.c: In function 'response':
tst-resolv-noaaaa.c:74:11: error: a label can only be part of a statement and a declaration is not a statement
char ipv4[4] = {192, 0, 2, i + 1};
^~~~
tst-resolv-noaaaa.c:79:11: error: a label can only be part of a statement and a declaration is not a statement
char *name = xasprintf ("ptr-%d", i);
^~~~
Noah Goldstein [Thu, 23 Jun 2022 17:49:19 +0000 (10:49 -0700)]
x86: Remove faulty sanity tests for RTLD build with no multiarch
The sanity tests where meant to ensure that the default implementation
was only being built without multiarch with the exception of the
multiarch/rtld-*.S files.
The code used IS_IN (rtld) to check if the build for was for an
multiarch/rtld-*.S file which is incorrect as IS_IN (rtld) is set for
the non-multiarch build as well.
Noah Goldstein [Wed, 22 Jun 2022 23:51:20 +0000 (16:51 -0700)]
x86: Add support for compiling {raw|w}memchr with high ISA level
1. Refactor files so that all implementations for in the multiarch
directory.
- Essentially moved sse2 {raw|w}memchr.S implementation to
multiarch/{raw|w}memchr-sse2.S
- The non-multiarch {raw|w}memchr.S file now only includes one of
the implementations in the multiarch directory based on the
compiled ISA level (only used for non-multiarch builds.
Otherwise we go through the ifunc selector).
2. Add ISA level build guards to different implementations.
- I.e memchr-avx2.S which is ISA level 3 will only build if
compiled ISA level <= 3. Otherwise there is no reason to include
it as we will always use one of the ISA level 4
implementations (memchr-evex{-rtm}.S).
3. Add new multiarch/rtld-{raw}memchr.S that just include the
non-multiarch {raw}memchr.S which will in turn select the best
implementation based on the compiled ISA level.
4. Refactor the ifunc selector and ifunc implementation list to use
the ISA level aware wrapper macros that allow functions below the
compiled ISA level (with a guranteed replacement) to be skipped.
- Guranteed replacement essentially means that for any ISA level
build there must be a function that the baseline of the ISA
supports. So for {raw|w}memchr.S since there is not ISA level 2
function, the ISA level 2 build still includes the ISA level
1 (sse2) function. Once we reach the ISA level 3 build, however,
{raw|w}memchr-avx2{-rtm}.S will always be sufficient so the ISA
level 1 implementation ({raw|w}memchr-sse2.S) will not be built.
Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}
x86: Rename generic functions with unique postfix for clarity
Changed the names of the strspn-c, strcspn-c, and strpbrk-c files
in a general refactor. It didn't change the include paths for the
i386 files breaking the i386 build. This commit fixes that. Reviewed-by: Carlos O'Donell <carlos@redhat.com> Tested-by: Carlos O'Donell <carlos@redhat.com>
Noah Goldstein [Thu, 16 Jun 2022 22:07:12 +0000 (15:07 -0700)]
x86: Rename generic functions with unique postfix for clarity
No functions are changed. It just renames generic implementations from
'{func}_sse2' to '{func}_generic'. This is just because the postfix
"_sse2" was overloaded and was used for files that had hand-optimized
sse2 assembly implementations and files that just redirected back
to the generic implementation.
Fangrui Song [Thu, 16 Jun 2022 18:48:15 +0000 (11:48 -0700)]
x86-64: Handle fewer relocation types for RTLD_BOOTSTRAP
The RTLD_BOOTSTRAP branch is used to relocate ld.so itself. It only
needs to handle RELATIVE, GLOB_DAT, and JUMP_SLOT. RELATIVE has been
handled (by _ELF_DYNAMIC_DO_RELOC due to DT_RELACOUNT, or RELR), so the
switch statement only needs to handle GLOB_DAT and JUMP_SLOT.
We can drop these `#if[n]def RTLD_BOOTSTRAP` and add a large
`# ifndef RTLD_BOOTSTRAP` instead.
Fangrui Song [Thu, 16 Jun 2022 02:21:53 +0000 (19:21 -0700)]
aarch64: Handle fewer relocations for RTLD_BOOTSTRAP
The RTLD_BOOTSTRAP branch is used to relocate ld.so itself. It only
needs to handle RELATIVE, GLOB_DAT, and JUMP_SLOT.
TLSDESC/TLS_DTPMOD/TLS_DTPREL handling can be removed. Remove
`case AARCH64_R(RELATIVE)` as well as elf_machine_rela has checked it.
Fangrui Song [Thu, 16 Jun 2022 01:42:03 +0000 (18:42 -0700)]
riscv: Change the relocations handled for RTLD_BOOTSTRAP
The RTLD_BOOTSTRAP branch is used to relocate ld.so itself. It only
needs to handle RELATIVE, GLOB_DAT, and the symbolic relocation type
(R_RISCV_{32,64}). NONE and IRELATIVE can be removed.
The code relies on ld.so having DT_RELACOUNT so that the RTLD_BOOTSTRAP
branch does not need handle RELATIVE. Drop this minor size
optimization for clarity.
Noah Goldstein [Wed, 15 Jun 2022 17:41:28 +0000 (10:41 -0700)]
x86: Cleanup bounds checking in large memcpy case
1. Fix incorrect lower-bound threshold in L(large_memcpy_2x).
Previously was using `__x86_rep_movsb_threshold` and should
have been using `__x86_shared_non_temporal_threshold`.
2. Avoid reloading __x86_shared_non_temporal_threshold before
the L(large_memcpy_4x) bounds check.
3. Document the second bounds check for L(large_memcpy_4x)
more clearly.
Noah Goldstein [Wed, 15 Jun 2022 17:41:29 +0000 (10:41 -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.
Fangrui Song [Wed, 15 Jun 2022 18:29:55 +0000 (11:29 -0700)]
elf: Remove ELF_RTYPE_CLASS_EXTERN_PROTECTED_DATA
If an executable has copy relocations for extern protected data, that
can only work if the library containing the definition is built with
assumptions (a) the compiler emits GOT-generating relocations (b) the
linker produces R_*_GLOB_DAT instead of R_*_RELATIVE. Otherwise the
library uses its own definition directly and the executable accesses a
stale copy. Note: the GOT relocations defeat the purpose of protected
visibility as an optimization, but allow rtld to make the executable and
library use the same copy when copy relocations are present, but it
turns out this never worked perfectly.
Without ELF_RTYPE_CLASS_EXTERN_PROTECTED_DATA, b.so accesses the copy
relocated data like a.so.
There is now a warning for copy relocation on protected symbol since
commit 7374c02b683b7110b853a32496a619410364d70b. It's extremely
unlikely anyone relies on the ELF_RTYPE_CLASS_EXTERN_PROTECTED_DATA
behavior, so let's remove it: this removes a check in the symbol lookup
code.
Noah Goldstein [Tue, 14 Jun 2022 20:50:11 +0000 (13:50 -0700)]
x86: Fix misordered logic for setting `rep_movsb_stop_threshold`
Move the setting of `rep_movsb_stop_threshold` to after the tunables
have been collected so that the `rep_movsb_stop_threshold` (which
is used to redirect control flow to the non_temporal case) will
use any user value for `non_temporal_threshold` (set using
glibc.cpu.x86_non_temporal_threshold)
1. Copy relocations for extern protected data do not work properly,
regardless whether GNU_PROPERTY_1_NEEDED_INDIRECT_EXTERN_ACCESS is used.
It makes sense to produce a warning unconditionally.
2. Non-zero value of an undefined function symbol may break pointer
equality, but may be benign in many cases (many programs don't take the
address in the shared object then compare it with the address in the
executable). Reword the diagnostic to be clearer.
3. Remove the unneeded condition !(undef_map->l_1_needed &
GNU_PROPERTY_1_NEEDED_INDIRECT_EXTERN_ACCESS). If the executable does
not not have GNU_PROPERTY_1_NEEDED_INDIRECT_EXTERN_ACCESS (can only
occur in error cases), the diagnostic should be emitted as well.
When the defining shared object has
GNU_PROPERTY_1_NEEDED_INDIRECT_EXTERN_ACCESS, report an error to apply
the intended enforcement.
Stefan Liebler [Fri, 3 Jun 2022 12:52:51 +0000 (14:52 +0200)]
Avoid -Wstringop-overflow= warning in iconv module.
On s390x when compiling with GCC 12, I get this warning:
utf8-utf16-z9.c:
../iconv/loop.c: In function ‘__from_utf8_loop_etf3eh_single’:
../iconv/loop.c:445:22: error: writing 1 byte into a region of size 0 [-Werror=stringop-overflow=]
445 | bytebuf[inlen++] = *inptr++;
| ~~~~~~~~~~~~~~~~~^~~~~~~~~~
../iconv/loop.c:381:17: note: at offset 4 into destination object ‘bytebuf’ of size 4
381 | unsigned char bytebuf[MAX_NEEDED_INPUT];
| ^~~~~~~
../iconv/loop.c:445:22: error: writing 1 byte into a region of size 0 [-Werror=stringop-overflow=]
445 | bytebuf[inlen++] = *inptr++;
| ~~~~~~~~~~~~~~~~~^~~~~~~~~~
../iconv/loop.c:381:17: note: at offset 5 into destination object ‘bytebuf’ of size 4
381 | unsigned char bytebuf[MAX_NEEDED_INPUT];
| ^~~~~~~
This patch tells the compiler that inend is always behind inptr which
avoids the warning. Note that the SINGLE function is only used to
implement the mb*towc*() or wc*tomb*() functions. Those functions use
inptr and inend pointing to a variable on stack, compute the inend pointer
or explicitly check the arguments which always leads to inptr < inend.
Special notes for backporters (according to Siddhesh Poyarekar):
If someone wants to backport this patch to release branches, they should
also backport the following wcrtomb change. Otherwise the assumptions
assumed by this patch are not true.
Wilco Dijkstra [Fri, 10 Jun 2022 16:13:29 +0000 (17:13 +0100)]
Add bounds check to __libc_ifunc_impl_list
Add a proper bounds check to __libc_ifunc_impl_list. This makes MAX_IFUNC
redundant and fixes several targets that will write outside the array.
To avoid unnecessary large diffs, pass the maximum in the argument 'i' to
IFUNC_IMPL_ADD - 'max' can be used in new ifunc definitions and existing
ones can be updated if desired.
Wilco Dijkstra [Fri, 10 Jun 2022 12:33:26 +0000 (13:33 +0100)]
libio: Avoid RMW of flags2 outside lock (BZ #27842)
Remove an unconditional RMW on flags2 in flockfile - we don't need to change
_IO_FLAGS2_NEED_LOCK since it isn't used in flockfile or funlockfile.
This fixes BZ #27842.
Noah Goldstein [Thu, 9 Jun 2022 16:58:33 +0000 (09:58 -0700)]
x86: Add data file that can be shared by tanhf-avx2 and tanhf-sse4
tanhf-avx2 and tanhf-sse4 use the same data tables so we can save
over 4kb using a shared datatable. This does increase the memory
footprint of the sse4 version (as now all the targets are 32 bytes
instead of 16), generally it seems worth the code size save.
NB: This patch doesn't do anything itself, it is setup for future
patches.
Changed how the page cross case aligned string (rdi) in
rawmemchr. This was incompatible with how
`L(cross_page_continue)` expected the pointer to be aligned and
would cause rawmemchr to read data start started before the
beginning of the string. What it would read was in valid memory
but could count CHAR matches resulting in an incorrect return
value.
This commit fixes that issue by essentially reverting the changes to
the L(page_cross) case as they didn't really matter.
Test cases added and all pass with the new code (and where confirmed
to fail with the old code). Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Paul E. Murphy [Wed, 1 Jun 2022 16:19:49 +0000 (16:19 +0000)]
nptl_db: disable DT_RELR on libthread_db.so
Some nptl tests inadvertently use the host's gdb to verify
libthread_db.so, which is loaded with the host's runtime. This causes
a couple of test failures when the host glibc does not support DT_RELR.
The not correct, but simple, workaround is to build without DT_RELR
as this library is otherwise likely to load on glibc 2.17 and newer
today.
This allows tst-pthread-gdb-attach{,-static} to continue working
when testing on a gdb loaded with an older glibc.
This avoids a failure in tst-pthread-gdb-attach similar to:
Trying host libthread_db library: .../build/glibc/nptl_db/libthread_db.so.1.
dlopen failed: /lib64/libc.so.6: version `GLIBC_ABI_DT_RELR' not found (required by .../build/glibc/nptl_db/libthread_db.so.1).
Noah Goldstein [Fri, 3 Jun 2022 23:52:37 +0000 (18:52 -0500)]
x86: ZERO_UPPER_VEC_REGISTERS_RETURN_XTEST expect no transactions
Give fall-through path to `vzeroupper` and taken-path to `vzeroall`.
Generally even on machines with RTM the expectation is the
string-library functions will not be called in transactions. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Tue, 7 Jun 2022 04:11:32 +0000 (21:11 -0700)]
x86: Optimize memrchr-avx2.S
The new code:
1. prioritizes smaller user-arg lengths more.
2. optimizes target placement more carefully
3. reuses logic more
4. fixes up various inefficiencies in the logic. The biggest
case here is the `lzcnt` logic for checking returns which
saves either a branch or multiple instructions.
The total code size saving is: 306 bytes
Geometric Mean of all benchmarks New / Old: 0.760
Regressions:
There are some regressions. Particularly where the length (user arg
length) is large but the position of the match char is near the
beginning of the string (in first VEC). This case has roughly a
10-20% regression.
This is because the new logic gives the hot path for immediate matches
to shorter lengths (the more common input). This case has roughly
a 15-45% speedup.
Full xcheck passes on x86_64. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Tue, 7 Jun 2022 04:11:31 +0000 (21:11 -0700)]
x86: Optimize memrchr-evex.S
The new code:
1. prioritizes smaller user-arg lengths more.
2. optimizes target placement more carefully
3. reuses logic more
4. fixes up various inefficiencies in the logic. The biggest
case here is the `lzcnt` logic for checking returns which
saves either a branch or multiple instructions.
The total code size saving is: 263 bytes
Geometric Mean of all benchmarks New / Old: 0.755
Regressions:
There are some regressions. Particularly where the length (user arg
length) is large but the position of the match char is near the
beginning of the string (in first VEC). This case has roughly a
20% regression.
This is because the new logic gives the hot path for immediate matches
to shorter lengths (the more common input). This case has roughly
a 35% speedup.
Full xcheck passes on x86_64. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Tue, 7 Jun 2022 04:11:30 +0000 (21:11 -0700)]
x86: Optimize memrchr-sse2.S
The new code:
1. prioritizes smaller lengths more.
2. optimizes target placement more carefully.
3. reuses logic more.
4. fixes up various inefficiencies in the logic.
The total code size saving is: 394 bytes
Geometric Mean of all benchmarks New / Old: 0.874
Regressions:
1. The page cross case is now colder, especially re-entry from the
page cross case if a match is not found in the first VEC
(roughly 50%). My general opinion with this patch is this is
acceptable given the "coldness" of this case (less than 4%) and
generally performance improvement in the other far more common
cases.
2. There are some regressions 5-15% for medium/large user-arg
lengths that have a match in the first VEC. This is because the
logic was rewritten to optimize finds in the first VEC if the
user-arg length is shorter (where we see roughly 20-50%
performance improvements). It is not always the case this is a
regression. My intuition is some frontend quirk is partially
explaining the data although I haven't been able to find the
root cause.
Full xcheck passes on x86_64. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Tue, 7 Jun 2022 04:11:29 +0000 (21:11 -0700)]
Benchtests: Improve memrchr benchmarks
Add a second iteration for memrchr to set `pos` starting from the end
of the buffer.
Previously `pos` was only set relative to the beginning of the
buffer. This isn't really useful for memrchr because the beginning
of the search space is (buf + len). Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Tue, 7 Jun 2022 04:11:27 +0000 (21:11 -0700)]
x86: Create header for VEC classes in x86 strings library
This patch does not touch any existing code and is only meant to be a
tool for future patches so that simple source files can more easily be
maintained to target multiple VEC classes.
There is no difference in the objdump of libc.so before and after this
patch. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
powerpc: Fix VSX register number on __strncpy_power9 [BZ #29197]
__strncpy_power9 initializes VR 18 with zeroes to be used throughout the
code, including when zero-padding the destination string. However, the
v18 reference was mistakenly being used for stxv and stxvl, which take a
VSX vector as operand. The code ended up using the uninitialized VSR 18
register by mistake.
Both occurrences have been changed to use the proper VSX number for VR 18
(i.e. VSR 50).
Wilco Dijkstra [Tue, 7 Jun 2022 15:44:35 +0000 (16:44 +0100)]
AArch64: Add SVE memcpy
Add an initial SVE memcpy implementation. Copies up to 32 bytes use SVE
vectors which improves the random memcpy benchmark significantly.
Cleanup the memcpy and memmove ifunc selectors.
Adding a 512-bit EVEX version of strstr. The algorithm works as follows:
(1) We spend a few cycles at the begining to peek into the needle. We
locate an edge in the needle (first occurance of 2 consequent distinct
characters) and also store the first 64-bytes into a zmm register.
(2) We search for the edge in the haystack by looking into one cache
line of the haystack at a time. This avoids having to read past a page
boundary which can cause a seg fault.
(3) If an edge is found in the haystack we first compare the first
64-bytes of the needle (already stored in a zmm register) before we
proceed with a full string compare performed byte by byte.
Benchmarking results: (old = strstr_sse2_unaligned, new = strstr_avx512)
Geometric mean of all benchmarks: new / old = 0.66
Difficult skiptable(0) : new / old = 0.02
Difficult skiptable(1) : new / old = 0.01
Difficult 2-way : new / old = 0.25
Difficult testing first 2 : new / old = 1.26
Difficult skiptable(0) : new / old = 0.05
Difficult skiptable(1) : new / old = 0.06
Difficult 2-way : new / old = 0.26
Difficult testing first 2 : new / old = 1.05
Difficult skiptable(0) : new / old = 0.42
Difficult skiptable(1) : new / old = 0.24
Difficult 2-way : new / old = 0.21
Difficult testing first 2 : new / old = 1.04 Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
git://sourceware.org / glibc.git / log