about summary refs log tree commit diff
Commit message (Collapse)AuthorAgeFilesLines
...
* Add HWCAP2_AFP, HWCAP2_RPRES from Linux 5.17 to AArch64 bits/hwcap.hJoseph Myers2022-03-281-0/+2
| | | | | Add the new HWCAP2_AFP and HWCAP2_RPRES constants from Linux 5.17. Tested with build-many-glibcs.py for aarch64-linux-gnu.
* x86: Remove AVX str{n}casecmpNoah Goldstein2022-03-256-197/+105
| | | | | | | | | | | | | | | | | The rational is: 1. SSE42 has nearly identical logic so any benefit is minimal (3.4% regression on Tigerlake using SSE42 versus AVX across the benchtest suite). 2. AVX2 version covers the majority of targets that previously prefered it. 3. The targets where AVX would still be best (SnB and IVB) are becoming outdated. All in all the saving the code size is worth it. All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Add EVEX optimized str{n}casecmpNoah Goldstein2022-03-256-40/+321
| | | | | | | geometric_mean(N=40) of all benchmarks EVEX / SSE42: .621 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Add AVX2 optimized str{n}casecmpNoah Goldstein2022-03-258-31/+331
| | | | | | | geometric_mean(N=40) of all benchmarks AVX2 / SSE42: .702 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* string: Expand page cross test cases in test-strncmp.cNoah Goldstein2022-03-251-1/+26
| | | | | | Test cases for when both `s1` and `s2` are near the end of a page where previously missing. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* string: Expand page cross test cases in test-strcmp.cNoah Goldstein2022-03-251-1/+14
| | | | | | Test cases for when both `s1` and `s2` are near the end of a page where previously missing. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Optimize str{n}casecmp TOLOWER logic in strcmp-sse42.SNoah Goldstein2022-03-251-48/+35
| | | | | | | | | | | | | Slightly faster method of doing TOLOWER that saves an instruction. Also replace the hard coded 5-byte no with .p2align 4. On builds with CET enabled this misaligned entry to strcasecmp. geometric_mean(N=40) of all benchmarks New / Original: .920 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Optimize str{n}casecmp TOLOWER logic in strcmp.SNoah Goldstein2022-03-251-35/+29
| | | | | | | | | | | | | Slightly faster method of doing TOLOWER that saves an instruction. Also replace the hard coded 5-byte no with .p2align 4. On builds with CET enabled this misaligned entry to strcasecmp. geometric_mean(N=40) of all benchmarks New / Original: .894 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* string: Expand page cross tests in test-strncasecmp.cNoah Goldstein2022-03-251-12/+154
| | | | | Add more robust tests that cover all the page cross edge cases. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* string: Expand page cross tests in test-strcasecmp.cNoah Goldstein2022-03-251-12/+100
| | | | | Add more robust tests that cover all the page cross edge cases. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Use json-lib in bench-strncasecmp.cNoah Goldstein2022-03-251-44/+69
| | | | | | Just QOL change to make parsing the output of the benchtests more consistent. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Use json-lib in bench-strcasecmp.cNoah Goldstein2022-03-251-26/+51
| | | | | | Just QOL change to make parsing the output of the benchtests more consistent. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Fix fallback for wcsncmp_avx2 in strcmp-avx2.S [BZ #28896]Noah Goldstein2022-03-252-1/+16
| | | | | | | | | | | | | | | | | | | | Overflow case for __wcsncmp_avx2_rtm should be __wcscmp_avx2_rtm not __wcscmp_avx2. commit ddf0992cf57a93200e0c782e2a94d0733a5a0b87 Author: Noah Goldstein <goldstein.w.n@gmail.com> Date: Sun Jan 9 16:02:21 2022 -0600 x86: Fix __wcsncmp_avx2 in strcmp-avx2.S [BZ# 28755] Set the wrong fallback function for `__wcsncmp_avx2_rtm`. It was set to fallback on to `__wcscmp_avx2` instead of `__wcscmp_avx2_rtm` which can cause spurious aborts. This change will need to be backported. All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Remove strspn-sse2.S and use the generic implementationNoah Goldstein2022-03-252-116/+4
| | | | | | | | | The generic implementation is faster. geometric_mean(N=20) of all benchmarks New / Original: .710 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Remove strpbrk-sse2.S and use the generic implementationNoah Goldstein2022-03-252-8/+4
| | | | | | | The generic implementation is faster (see strcspn commit). All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Remove strcspn-sse2.S and use the generic implementationNoah Goldstein2022-03-252-123/+4
| | | | | | | | | The generic implementation is faster. geometric_mean(N=20) of all benchmarks New / Original: .678 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Optimize strspn in strspn-c.cNoah Goldstein2022-03-251-47/+39
| | | | | | | | | | | | Use _mm_cmpeq_epi8 and _mm_movemask_epi8 to get strlen instead of _mm_cmpistri. Also change offset to unsigned to avoid unnecessary sign extensions. geometric_mean(N=20) of all benchmarks that dont fallback on sse2; New / Original: .901 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Optimize strcspn and strpbrk in strcspn-c.cNoah Goldstein2022-03-251-46/+37
| | | | | | | | | | | | Use _mm_cmpeq_epi8 and _mm_movemask_epi8 to get strlen instead of _mm_cmpistri. Also change offset to unsigned to avoid unnecessary sign extensions. geometric_mean(N=20) of all benchmarks that dont fallback on sse2/strlen; New / Original: .928 All string/memory tests pass. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Use json-lib in bench-strspn.cNoah Goldstein2022-03-251-20/+58
| | | | | | Just QOL change to make parsing the output of the benchtests more consistent. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Use json-lib in bench-strpbrk.cNoah Goldstein2022-03-251-20/+61
| | | | | | Just QOL change to make parsing the output of the benchtests more consistent. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Code cleanup in strchr-evex and comment justifying branchNoah Goldstein2022-03-251-66/+80
| | | | | | | | | | | Small code cleanup for size: -81 bytes. Add comment justifying using a branch to do NULL/non-null return. All string/memory tests pass and no regressions in benchtests. geometric_mean(N=20) of all benchmarks New / Original: .985 Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* x86: Code cleanup in strchr-avx2 and comment justifying branchNoah Goldstein2022-03-251-97/+107
| | | | | | | | | | | Small code cleanup for size: -53 bytes. Add comment justifying using a branch to do NULL/non-null return. All string/memory tests pass and no regressions in benchtests. geometric_mean(N=20) of all benchmarks Original / New: 1.00 Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Add random benchmark in bench-strchr.cNoah Goldstein2022-03-251-0/+143
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Add benchmark that randomizes whether return should be NULL or pointer to CHAR. The rationale is on many architectures there is a choice between a predicate execution option (i.e cmovcc on x86) or a branch. On x86 the results for cmovcc vs branch are something along the lines of the following: perc-zero, Br On Result, Time Br / Time cmov 0.10, 1, ,0.983 0.10, 0, ,1.246 0.25, 1, ,1.035 0.25, 0, ,1.49 0.33, 1, ,1.016 0.33, 0, ,1.579 0.50, 1, ,1.228 0.50, 0, ,1.739 0.66, 1, ,1.039 0.66, 0, ,1.764 0.75, 1, ,0.996 0.75, 0, ,1.642 0.90, 1, ,1.071 0.90, 0, ,1.409 1.00, 1, ,0.937 1.00, 0, ,0.999 Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* benchtests: Use json-lib in bench-strchr.cNoah Goldstein2022-03-251-30/+64
| | | | | | Just QOL change to make parsing the output of the benchtests more consistent. Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
* Update kernel version to 5.17 in tst-mman-consts.pyJoseph Myers2022-03-241-1/+1
| | | | | | | | This patch updates the kernel version in the test tst-mman-consts.py to 5.17. (There are no new MAP_* constants covered by this test in 5.17 that need any other header changes.) Tested with build-many-glibcs.py.
* iconvdata: Fix enum type on UTF-7Adhemerval Zanella2022-03-231-1/+1
| | | | Checked on x86_64-linux-gnu.
* nscd: Remove unused variableAdhemerval Zanella2022-03-231-5/+1
|
* support: Fix support_process_state_wait path size calculationAdhemerval Zanella2022-03-231-1/+2
| | | | | | | Use INT_STRLEN_BOUND to proper get the maximum pid_t size. Also fix the wrong calculation (the 3 should multiply the sizeof (pid_t)). Checked on x86_64-linux-gnu.
* support: Remove unused extract_8 functionAdhemerval Zanella2022-03-231-11/+0
|
* locale: Remove ununsed wctype_table_get functionAdhemerval Zanella2022-03-231-27/+0
|
* gmon: Remove unused sprofil.c functionsAdhemerval Zanella2022-03-231-12/+0
|
* Update syscall lists for Linux 5.17Joseph Myers2022-03-2327-2/+29
| | | | | | | | Linux 5.17 has one new syscall, set_mempolicy_home_node. Update syscall-names.list and regenerate the arch-syscall.h headers with build-many-glibcs.py update-syscalls. Tested with build-many-glibcs.py.
* Fix ununsed fstatat64_time64_statxAdhemerval Zanella2022-03-231-5/+5
| | | | It is only called for legacy ABIs.
* malloc: Fix duplicate inline for do_set_mxfastAdhemerval Zanella2022-03-231-2/+1
|
* elf: Remove inline _dl_dprintfAdhemerval Zanella2022-03-231-11/+0
| | | | | | It is not used on rtld and ldsodef interfaces are meant to be used solely on loader. It also removes the only usage of gcc extension __builtin_va_arg_pack.
* configure.ac: fix bashisms in configure.acSam James2022-03-226-6/+6
| | | | | | | | | | | | | | | | | | | configure scripts need to be runnable with a POSIX-compliant /bin/sh. On many (but not all!) systems, /bin/sh is provided by Bash, so errors like this aren't spotted. Notably Debian defaults to /bin/sh provided by dash which doesn't tolerate such bashisms as '=='. This retains compatibility with bash. Fixes configure warnings/errors like: ``` checking if compiler warns about alias for function with incompatible types... yes /var/tmp/portage/sys-libs/glibc-2.34-r10/work/glibc-2.34/configure: 4209: test: xyes: unexpected operator ``` Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org> Signed-off-by: Sam James <sam@gentoo.org>
* getaddrinfo: Refactor code for readabilitySiddhesh Poyarekar2022-03-231-12/+33
| | | | | | | | The close_retry goto jump is confusing and clumsy to read, so refactor the code a bit to make it easier to follow. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* Use Linux 5.17 in build-many-glibcs.pyJoseph Myers2022-03-221-1/+1
| | | | | | | This patch makes build-many-glibcs.py use Linux 5.17. Tested with build-many-glibcs.py (host-libraries, compilers and glibcs builds).
* resolv: Fix unaligned accesses to fields in HEADER structJohn David Anglin2022-03-223-14/+21
| | | | | | | | | | | | | | | | The structure HEADER is normally aligned to a word boundary but sometimes it needs to be accessed when aligned on a byte boundary. This change defines a new typedef, UHEADER, with alignment 1. It is used to ensure the fields are accessed with byte loads and stores when necessary. V4: Change to res_mkquery.c deleted. Small whitespace fix. V5: Move UHEADER typedef to resolv/resolv-internal.h. Replace all HEADER usage with UHEADER in resolv/res_send.c. Signed-off-by: John David Anglin <dave.anglin@bell.net> Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
* gai_init: Avoid jumping from if condition to its else counterpartSiddhesh Poyarekar2022-03-221-250/+248
| | | | | | | | | | | Clean up another antipattern where code flows from an if condition to its else counterpart with a goto. Most of the change in this patch is whitespace-only; a `git diff -b` ought to show the actual logic changes. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaiconf_init: Refactor some bits for readabilitySiddhesh Poyarekar2022-03-221-65/+84
| | | | | | | | Split out line processing for `label`, `precedence` and `scopev4` into separate functions instead of the gotos. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gethosts: Return EAI_MEMORY on allocation failureSiddhesh Poyarekar2022-03-221-2/+2
| | | | | | | | | All other cases of failures due to lack of memory return EAI_MEMORY, so it seems wrong to return EAI_SYSTEM here. The only reason convert_hostent_to_gaih_addrtuple could fail is on calloc failure. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: Split result generation into its own functionSiddhesh Poyarekar2022-03-221-90/+86
| | | | | | | Simplify the loop a wee bit and clean up variable names too. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: split loopback lookup into its own functionSiddhesh Poyarekar2022-03-221-65/+62
| | | | | | | | | | | | Flatten the condition nesting and replace the alloca for RET.AT/ATR with a single array LOCAL_AT[2]. This gets rid of alloca and alloca accounting. `git diff -b` is probably the best way to view this change since much of the diff is whitespace changes. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: make gethosts into a functionSiddhesh Poyarekar2022-03-221-58/+59
| | | | | | | | The macro is quite a pain to debug, so make gethosts into a function to make it easier to maintain. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: separate nss lookup loop into its own functionSiddhesh Poyarekar2022-03-221-277/+286
| | | | | Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: Split nscd lookup code into its own function.Siddhesh Poyarekar2022-03-221-114/+134
| | | | | | | | Add a new member got_ipv6 to indicate if the results have an IPv6 result and use it instead of the local got_ipv6. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: Split simple gethostbyname into its own functionSiddhesh Poyarekar2022-03-221-63/+64
| | | | | | | | Add a free_at flag in gaih_result to indicate if res.at needs to be freed by the caller. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: make numeric lookup a separate routineSiddhesh Poyarekar2022-03-221-439/+452
| | | | | | | | | | | | | Introduce the gaih_result structure and general paradigm for cleanups that follow to process the lookup request and return a result. A lookup function (like text_to_binary_address), should return an integer error code and set members of gaih_result based on what it finds. If the function does not have a result and no errors have occurred during the lookup, it should return 0 and res.at should be set to NULL, allowing a subsequent function to do the lookup until we run out of options. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
* gaih_inet: Simplify service resolutionSiddhesh Poyarekar2022-03-221-100/+78
| | | | | | | | | | Refactor the code to split out the service resolution code into a separate function. Allocate the service tuples array just once to the size of the typeproto array, thus avoiding the unnecessary pointer chasing and stack allocations. Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org> Reviewed-by: DJ Delorie <dj@redhat.com>
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-11-02 03:43:12 +0000