Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_unlink into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
A small adjust to the sem_unlink implementation is necessary to avoid
a check-localplt failure.
A placeholder symbol to keep the GLIBC_2.1.1 version alive in
libpthread is added with this commit.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_timedwait into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_post into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_init into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_getvalue into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_destroy into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_close, sem_open into libc
The symbols were moved using move-symbol-to-libc.py.
Both functions are moved at the same time because they depend
on internal functions in sysdeps/pthread/sem_routines.c, which
are moved in this commit as well. Additional hidden prototypes
are required to avoid check-localplt failures.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move sem_clockwait into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
A new placeholder version is added at version GLIBC_2.30, to
preserve that version in libpthread.so.0.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Consolidate async cancel enable/disable implementation in libc
Previously, the source file nptl/cancellation.c was compiled multiple
times, for libc, libpthread, librt. This commit switches to a single
implementation, with new __pthread_enable_asynccancel@@GLIBC_PRIVATE,
__pthread_disable_asynccancel@@GLIBC_PRIVATE exports.
The almost-unused CANCEL_ASYNC and CANCEL_RESET macros are replaced
by LIBC_CANCEL_ASYNC and LIBC_CANCEL_ASYNC macros. They call the
__pthread_* functions unconditionally now. The macros are still
needed because shared code uses them; Hurd has different definitions.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 15:15:57 +0000 (17:15 +0200)]
nptl: Move pthread_testcancel into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
A temporary __pthread_testcancel@@GLIBC_PRIVATE export is created
because it is needed by the semaphore implementation.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Florian Weimer [Wed, 5 May 2021 04:20:31 +0000 (06:20 +0200)]
elf, nptl: Initialize static TLS directly in ld.so
The stack list is available in ld.so since commit
1daccf403b1bd86370eb94edca794dc106d02039 ("nptl: Move stack list
variables into _rtld_global"), so it's possible to walk the stack
list directly in ld.so and perform the initialization there.
This eliminates an unprotected function pointer from _rtld_global
and reduces the libpthread initialization code.
Florian Weimer [Tue, 4 May 2021 13:52:58 +0000 (15:52 +0200)]
posix: Fix Hurd build failure in tst-execveat
This avoids a -Werror compilation failure due to unused local
variables.
Noah Goldstein [Mon, 3 May 2021 07:03:19 +0000 (03:03 -0400)]
x86: Optimize memchr-evex.S
No bug. This commit optimizes memchr-evex.S. The optimizations include
replacing some branches with cmovcc, avoiding some branches entirely
in the less_4x_vec case, making the page cross logic less strict,
saving some ALU in the alignment process, and most importantly
increasing ILP in the 4x loop. test-memchr, test-rawmemchr, and
test-wmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Noah Goldstein [Mon, 3 May 2021 07:01:58 +0000 (03:01 -0400)]
x86: Optimize memchr-avx2.S
No bug. This commit optimizes memchr-avx2.S. The optimizations include
replacing some branches with cmovcc, avoiding some branches entirely
in the less_4x_vec case, making the page cross logic less strict,
asaving a few instructions the in loop return loop. test-memchr,
test-rawmemchr, and test-wmemchr are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>
Érico Nogueira [Tue, 27 Apr 2021 13:09:45 +0000 (10:09 -0300)]
linux: use __fd_to_filename helper function instead of snprintf.
Change made to fchmodat and fexecve. There are tests using xasprintf
instead of this helper as well, but this commit doesn't touch them.
Alexandra Hájková [Mon, 3 May 2021 16:35:10 +0000 (16:35 +0000)]
linux: Add execveat system call wrapper
It operates similar to execve and it is is already used to implement
fexecve without requiring /proc to be mounted. However, different
than fexecve, if the syscall is not supported by the kernel an error
is returned instead of trying a fallback.
Checked on x86_64-linux-gnu and powerpc64le-linux-gnu.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Noah Goldstein [Mon, 3 May 2021 08:44:35 +0000 (04:44 -0400)]
Bench: Expand bench-memchr.c
No bug. This commit adds some additional cases for bench-memchr.c
including testing medium sizes and testing short length with both an
inbound match and out of bound match.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Lirong Yuan [Thu, 1 Apr 2021 19:37:23 +0000 (12:37 -0700)]
locale: Align _nl_C_LC_CTYPE_class and _nl_C_LC_CTYPE_class32
Otherwise, programs that use character classification macros such as
isspace may observe unaligned pointers.
Florian Weimer [Mon, 3 May 2021 12:12:55 +0000 (14:12 +0200)]
nptl: Re-sort Versions file
Due to an incorrect conflict resolution, libc/GLIBC_2.2 section was no
longer sorted lexicographically.
H.J. Lu [Fri, 30 Apr 2021 12:58:59 +0000 (05:58 -0700)]
x86: Set rep_movsb_threshold to 2112 on processors with FSRM
The glibc memcpy benchmark on Intel Core i7-1065G7 (Ice Lake) showed
that REP MOVSB became faster after 2112 bytes:
Vector Move REP MOVSB
length=2112, align1=0, align2=0: 24.20 24.40
length=2112, align1=1, align2=0: 26.07 23.13
length=2112, align1=0, align2=1: 27.18 28.13
length=2112, align1=1, align2=1: 26.23 25.16
length=2176, align1=0, align2=0: 23.18 22.52
length=2176, align1=2, align2=0: 25.45 22.52
length=2176, align1=0, align2=2: 27.14 27.82
length=2176, align1=2, align2=2: 22.73 25.56
length=2240, align1=0, align2=0: 24.62 24.25
length=2240, align1=3, align2=0: 29.77 27.15
length=2240, align1=0, align2=3: 35.55 29.93
length=2240, align1=3, align2=3: 34.49 25.15
length=2304, align1=0, align2=0: 34.75 26.64
length=2304, align1=4, align2=0: 32.09 22.63
length=2304, align1=0, align2=4: 28.43 31.24
Use REP MOVSB for data size > 2112 bytes in memcpy on processors with
fast short REP MOVSB (FSRM).
* sysdeps/x86/dl-cacheinfo.h (dl_init_cacheinfo): Set
rep_movsb_threshold to 2112 on processors with fast short REP
MOVSB (FSRM).
H.J. Lu [Fri, 30 Apr 2021 17:10:47 +0000 (10:10 -0700)]
bench-memcpy: Collect data from 2KB to 4KB
Collect data on memcpy from 2KB to 4KB with the 64-byte increment value.
Alyssa Ross [Mon, 3 May 2021 08:34:11 +0000 (10:34 +0200)]
stdio: fix vfscanf with matches longer than INT_MAX (bug 27650)
Patterns like %*[ can safely be used to match a great many characters,
and it's quite realisitic to use them for more than INT_MAX characters
from an IO stream.
With the previous approach, after INT_MAX characters (v)fscanf would
return successfully, indicating an end to the match, even though there
wasn't one.
Florian Weimer [Mon, 3 May 2021 07:23:17 +0000 (09:23 +0200)]
nptl: Move pthread_yield into libc, as a compatibility symbol
And deprecate it in <pthread.h>, redirecting it to sched_yield
for the time being.
The symbol was moved using scripts/move-symbol-to-libc.py.
No GLIBC_2.34 symbol version is added because of the compatibility
symbol status.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_setpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_setkind_np into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_init into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_getpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_getkind_np into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlockattr_destroy into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_trywrlock into libc
And __pthread_rwlock_trywrlock as a compatibility symbol.
Remove the unused __libc_rwlock_trywrlock macro.
The symbols were moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_tryrdlock into libc
And __pthread_rwlock_tryrdlock as a compatibility symbol.
Remove the unused __libc_rwlock_tryrdlock macro.
The symbols were moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_timedwrlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_timedrdlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_init into libc
And __pthread_rwlock_init as a compatibility symbol.
__libc_rwlock_init is changed to call __pthread_rwlock_init directly.
The symbols were moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_destroy into libc
And __pthread_rwlock_destroy as a compatibility symbol.
rwlocks do not need finalization, so change __libc_rwlock_fini to do
nothing.
The symbols were moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_clockwrlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 07:10:57 +0000 (09:10 +0200)]
nptl: Move pthread_rwlock_clockrdlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move tss_set into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_setspecific@@GLIBC_2.34 is no longer needed after the move,
so it is removed with this commit, too.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move tss_get into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_getspecific@@GLIBC_2.34 is no longer needed after the move,
so it is removed with this commit, too.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move tss_delete into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_key_delete@@GLIBC_PRIVATE is no longer needed after that,
so it is removed as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move tss_create into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_key_create@@GLIBC_2.34 is no longer needed by glibc
itself with this change, but __pthread_key_create is used by
libstdc++, so it still has to be exported as a public symbol.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move thrd_exit into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_exit@@GLIBC_PRIVATE symbol is no longer needed
after this change, so remove it.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:12 +0000 (08:12 +0200)]
nptl: Move mtx_unlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_mutex_unlock@GLIBC_2.34 is not removed in this commit
because it is still used from nptl/nptl-init.c.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move mtx_trylock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_mutex_trylock@@GLIBC_2.34 symbol version is no longer
needed because the call is now internal to libc, so remove it with
this commit.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move mtx_timedlock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_mutex_timedlock@@GLIBC_PRIVATE export is no longer
needed, so it is removed with this commit.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move mtx_lock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
__pthread_mutex_lock@GLIBC_2.34 is not removed in this commit
because it is still used from nptl/nptl-init.c.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move mtx_init into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The calls to __pthread_mutex_init, __pthread_mutexattr_init,
__pthread_mutexattr_settype are now private and no longer need
to be exported. This allows the removal of the newly added
GLIBC_2.34 symbol versions for those functions.
Also clean up some weak declarations in <libc-lockP.h> for
these functions. They are not needed and potentially incorrect
for static linking of mtx_init.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move mtx_destroy into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_mutex_destroy@@GLIBC_2.34 symbol is no longer
neded because this commit makes __pthread_mutex_destroy@GLIBC_2.0
a compatibility symbol, so remove the new symbol version.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_wait into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_wait@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_timedwait into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_timedwait@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_signal into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_signal@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_init into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_init@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_destroy into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_destroy@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move cnd_broadcast into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
The __pthread_cond_broadcast@@GLIBC_PRIVATE symbol is no longer
neded, so remove that as well.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
nptl: Move call_once into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
This change also turns __pthread_once into a compatibility symbol
because after the call_once move, an internal call to __pthread_once
can be used. This an adjustment to __libc_once: Outside libc (e.g.,
in nscd), it has to call pthread_once. With __pthread_once as a
compatibility symbol, it is no longer to add a new GLIBC_2.34
version after the move from libpthread, and this commit removes
the new __pthread_once@@GLIBC_2.34 version.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Florian Weimer [Mon, 3 May 2021 06:12:11 +0000 (08:12 +0200)]
Add pthread-in-libc, libpthread-routines-var, librt-routines-var
These make variables can be used to add routines to different
libraries for the Hurd and Linux builds.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Tested-by: Carlos O'Donell <carlos@redhat.com>
Raoni Fassina Firmino [Fri, 30 Apr 2021 21:12:08 +0000 (18:12 -0300)]
powerpc64le: Optimize memset for POWER10
This implementation is based on __memset_power8 and integrates a lot
of suggestions from Anton Blanchard.
The biggest difference is that it makes extensive use of stxvl to
alignment and tail code to avoid branches and small stores. It has
three main execution paths:
a) "Short lengths" for lengths up to 64 bytes, avoiding as many
branches as possible.
b) "General case" for larger lengths, it has an alignment section
using stxvl to avoid branches, a 128 bytes loop and then a tail
code, again using stxvl with few branches.
c) "Zeroing cache blocks" for lengths from 256 bytes upwards and set
value being zero. It is mostly the __memset_power8 code but the
alignment phase was simplified because, at this point, address is
already 16-bytes aligned and also changed to use vector stores.
The tail code was also simplified to reuse the general case tail.
All unaligned stores use stxvl instructions that do not generate
alignment interrupts on POWER10, making it safe to use on
caching-inhibited memory.
On average, this implementation provides something around 30%
improvement when compared to __memset_power8.
Reviewed-by: Matheus Castanho <msc@linux.ibm.com>
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
Tulio Magno Quites Machado Filho [Fri, 30 Apr 2021 21:12:08 +0000 (18:12 -0300)]
powerpc64le: Optimize memcpy for POWER10
This implementation is based on __memcpy_power8_cached and integrates
suggestions from Anton Blanchard.
It benefits from loads and stores with length for short lengths and for
tail code, simplifying the code.
All unaligned memory accesses use instructions that do not generate
alignment interrupts on POWER10, making it safe to use on
caching-inhibited memory.
The main loop has also been modified in order to increase instruction
throughput by reducing the dependency on updates from previous iterations.
On average, this implementation provides around 30% improvement when
compared to __memcpy_power7 and 10% improvement in comparison to
__memcpy_power8_cached.
Lucas A. M. Magalhaes [Fri, 30 Apr 2021 21:12:08 +0000 (18:12 -0300)]
powerpc64le: Optimized memmove for POWER10
This patch was initially based on the __memmove_power7 with some ideas
from strncpy implementation for Power 9.
Improvements from __memmove_power7:
1. Use lxvl/stxvl for alignment code.
The code for Power 7 uses branches when the input is not naturally
aligned to the width of a vector. The new implementation uses
lxvl/stxvl instead which reduces pressure on GPRs. It also allows
the removal of branch instructions, implicitly removing branch stalls
and mispredictions.
2. Use of lxv/stxv and lxvl/stxvl pair is safe to use on Cache Inhibited
memory.
On Power 10 vector load and stores are safe to use on CI memory for
addresses unaligned to 16B. This code takes advantage of this to
do unaligned loads.
The unaligned loads don't have a significant performance impact by
themselves. However doing so decreases register pressure on GPRs
and interdependence stalls on load/store pairs. This also improved
readability as there are now less code paths for different alignments.
Finally this reduces the overall code size.
3. Improved performance.
This version runs on average about 30% better than memmove_power7
for lengths larger than 8KB. For input lengths shorter than 8KB
the improvement is smaller, it has on average about 17% better
performance.
This version has a degradation of about 50% for input lengths
in the 0 to 31 bytes range when dest is unaligned.
Reviewed-by: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>
Joseph Myers [Thu, 29 Apr 2021 10:50:11 +0000 (10:50 +0000)]
Update kernel version to 5.12 in tst-mman-consts.py.
This patch updates the kernel version in the test tst-mman-consts.py
to 5.12. (There are no new MAP_* constants covered by this test in
5.12 that need any other header changes.)
Tested with build-many-glibcs.py.
Joseph Myers [Wed, 28 Apr 2021 17:19:24 +0000 (17:19 +0000)]
Update syscall lists for Linux 5.12.
Linux 5.12 has one new syscall, mount_setattr. Update
syscall-names.list and regenerate the arch-syscall.h headers with
build-many-glibcs.py update-syscalls.
Tested with build-many-glibcs.py.
Paul Zimmermann [Wed, 28 Apr 2021 09:02:00 +0000 (11:02 +0200)]
regenerate ulps on x86_64 with -march=native
On x86_64, when configuring glibc with CFLAGS="-O2 -g -march=native",
some tests fail. After this patch, "make check" succeeds.
Tested on Intel Core i5-4590 with gcc 10.2.1.
Martin Sebor [Wed, 28 Apr 2021 01:05:30 +0000 (19:05 -0600)]
Pass a valid pointer to pthread_setspecific to avoid GCC 11 warning.
Martin Sebor [Tue, 27 Apr 2021 19:01:55 +0000 (13:01 -0600)]
Add __attribute_access_none to disable GCC warnings [BZ #27714]
GCC 11 warns when a pointer to an uninitialized object is passed
to a function that takes a const-qualified argument. This is done
on the assumption that most such functions read from the object.
For the rare case of a function that doesn't, GCC 11 extends
attribute access to add a new mode called none.
POSIX pthread_setspecific() is one such rare function that takes
a const void* argument but that doesn't read from the object it
points to. To suppress the -Wmaybe-uninitialized issued by GCC
11 when the address of an uninitialized object is passed to it
(e.g., the result of malloc()), this change #defines
__attr_access_none in cdefs.h and uses the macro on the function
in sysdeps/htl/pthread.h and sysdeps/nptl/pthread.h.
Joseph Myers [Tue, 27 Apr 2021 15:19:08 +0000 (15:19 +0000)]
Use Linux 5.12 and GCC 11 branch in build-many-glibcs.py.
This patch makes build-many-glibcs.py use Linux 5.12 and GCC 11
branch.
Tested with build-many-glibcs.py (host-libraries, compilers and glibcs
builds).
Raphael Moreira Zinsly [Thu, 25 Feb 2021 13:42:27 +0000 (10:42 -0300)]
powerpc: Add log IFUNC multiarch support for POWER10
Checked on ppc64le built without --with-cpu, with --with-cpu=power9
and with --disable-multi-arch.
Reviewed-by: Matheus Castanho <msc@linux.ibm.com>
Hanataka Shinya [Thu, 18 Feb 2021 04:00:48 +0000 (23:00 -0500)]
LC_COLLATE: Fix last character ellipsis handling (Bug 22668)
During ellipsis processing the collation cursor was not correctly
moved to the end of the ellipsis after processing.
The code inserted the new entry after the cursor, but before the
real end of the ellipsis:
[cursor]
... element_t <-> element_t <-> element_t <-> element_t
"<U0000>" "<U0001>" "<U007F>"
startp endp
At the end of the function we have:
[cursor]
... element_t <-> element_t <-> element_t
"<U007E>" "<U007F>"
endp
The cursor should be pointing at endp, the last element in the
doubly-linked list, otherwise when execution returns to the
caller we will start inserting the next line after <U007E>.
Subsequent operations end up unlinking the ellipsis end entry or
just leaving it in the list dangling from the end. This kind of
dangling is immediately visible in C.UTF-8 with the following
sorting from strcoll:
<U0010FFFF>
<U0000FFFF>
<U000007FF>
<U0000007F>
With the cursor correctly adjusted the end entry is correctly given
the right location and thus the right weight.
Retested and no regressions on x86_64 and i686.
Co-authored-by: Carlos O'Donell <carlos@redhat.com>
Noah Goldstein [Fri, 23 Apr 2021 19:56:25 +0000 (15:56 -0400)]
x86: Optimize strchr-evex.S
No bug. This commit optimizes strchr-evex.S. The optimizations are
mostly small things such as save an ALU in the alignment process,
saving a few instructions in the loop return. The one significant
change is saving 2 instructions in the 4x loop. test-strchr,
test-strchrnul, test-wcschr, and test-wcschrnul are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Noah Goldstein [Fri, 23 Apr 2021 19:56:24 +0000 (15:56 -0400)]
x86: Optimize strchr-avx2.S
No bug. This commit optimizes strchr-avx2.S. The optimizations are all
small things such as save an ALU in the alignment process, saving a
few instructions in the loop return, saving some bytes in the main
loop, and increasing the ILP in the return cases. test-strchr,
test-strchrnul, test-wcschr, and test-wcschrnul are all passing.
Signed-off-by: Noah Goldstein <goldstein.w.n@gmail.com>
Florian Weimer [Fri, 23 Apr 2021 16:08:38 +0000 (18:08 +0200)]
nptl: Remove __h_errno_location from libpthread
The existing definition in libc will be used instead.
The symbol was moved (that is, removed) using
scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 16:08:37 +0000 (18:08 +0200)]
nptl: Remove __res_state from libpthread
The existing definition in libc will be used instead.
The symbol was moved (that is, removed) using
scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 08:23:24 +0000 (10:23 +0200)]
nptl: Move pthread_spin_trylock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 08:11:51 +0000 (10:11 +0200)]
nptl: Move pthread_spin_lock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Thu, 22 Apr 2021 13:18:12 +0000 (15:18 +0200)]
nptl: Move pthread_spin_init, Move pthread_spin_unlock into libc
For some architectures, the two functions are aliased, so these
symbols need to be moved at the same time.
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Thu, 22 Apr 2021 13:12:09 +0000 (15:12 +0200)]
nptl: Move pthread_spin_destroy into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 09:17:10 +0000 (11:17 +0200)]
nptl: Move pthread_condattr_setpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 09:02:54 +0000 (11:02 +0200)]
nptl: Move pthread_condattr_setclock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 09:00:53 +0000 (11:00 +0200)]
nptl: Move pthread_condattr_getpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 08:55:07 +0000 (10:55 +0200)]
nptl: Move pthread_condattr_getclock into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:49:00 +0000 (09:49 +0200)]
nptl: Move pthread_mutexattr_settype, __pthread_mutexattr_settype into libc
And pthread_mutexattr_setkind_np as a compatibility symbol.
__pthread_mutexattr_settype is used in mtx_init from libpthread,
so this commit adds a GLIBC_2.34 symbol version for it.
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:48:36 +0000 (09:48 +0200)]
nptl: Move pthread_mutexattr_setrobust into libc
And pthread_mutexattr_getrobust_np as a compat symbol.
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:48:10 +0000 (09:48 +0200)]
pthread: Use pthread_mutexattr_setrobust in tests
pthread_mutexattr_setrobust_np is about to be deprecated.
Florian Weimer [Fri, 23 Apr 2021 07:48:09 +0000 (09:48 +0200)]
nptl: Move pthread_mutexattr_setpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:47:37 +0000 (09:47 +0200)]
nptl: Move pthread_mutexattr_setprotocol into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:47:15 +0000 (09:47 +0200)]
nptl: Move pthread_mutexattr_setprioceiling into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:46:57 +0000 (09:46 +0200)]
nptl: Move pthread_mutexattr_init, __pthread_mutexattr_init into libc
__pthread_mutexattr_init cannot be be made a compat symbol because
it is used in mtx_init, which is still in libpthread.
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:46:15 +0000 (09:46 +0200)]
nptl: Move pthread_mutexattr_gettype into libc
And pthread_mutexattr_getkind_np as a compatibility symbol.
(There is no declaration in <pthread.h>, so there is no need
to add an alias or a deprecation warning there.)
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:46:03 +0000 (09:46 +0200)]
nptl: Move pthread_mutexattr_getrobust into libc
And pthread_mutexattr_getrobust_np as a compat symbol.
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:45:48 +0000 (09:45 +0200)]
nptl: Move pthread_mutexattr_getpshared into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:45:29 +0000 (09:45 +0200)]
nptl: Move pthread_mutexattr_getprotocol into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:45:09 +0000 (09:45 +0200)]
nptl: Move pthread_mutexattr_getprioceiling into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:44:49 +0000 (09:44 +0200)]
nptl: Move pthread_mutexattr_destroy into libc
And __pthread_mutexattr_destroy as a compat symbol (so no
GLIBC_2.34 symbol version is added for it).
The symbols were moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:44:23 +0000 (09:44 +0200)]
nptl: Move pthread_mutex_trylock, __pthread_mutex_trylock into libc
The symbols were moved using scripts/move-symbol-to-libc.py.
__pthread_mutex_trylock is used to implement mtx_timedlock,
which still resides in libpthread, so add a GLIBC_2.34 version
for it, to match the existing GLIBC_2.0 version.
Florian Weimer [Fri, 23 Apr 2021 07:43:24 +0000 (09:43 +0200)]
nptl: Move pthread_mutex_timedlock, pthread_mutex_clocklock to libc
The symbols were moved using scripts/move-symbol-to-libc.py.
The symbol aliasing follows pthread_cond_timedwait et al.
Missing hidden prototypes had to be added to nptl/pthreadP.h
for consistency.
Florian Weimer [Fri, 23 Apr 2021 07:43:08 +0000 (09:43 +0200)]
nptl: Move pthread_mutex_setprioceiling into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Florian Weimer [Fri, 23 Apr 2021 07:42:51 +0000 (09:42 +0200)]
nptl: Move pthread_mutex_getprioceiling into libc
The symbol was moved using scripts/move-symbol-to-libc.py.
Matheus Castanho [Tue, 29 Sep 2020 18:40:08 +0000 (15:40 -0300)]
powerpc: Add optimized strlen for POWER10
Improvements compared to POWER9 version:
1. Take into account first 16B comparison for aligned strings
The previous version compares the first 16B and increments r4 by the number
of bytes until the address is 16B-aligned, then starts doing aligned loads at
that address. For aligned strings, this causes the first 16B to be compared
twice, because the increment is 0. Here we calculate the next 16B-aligned
address differently, which avoids that issue.
2. Use simple comparisons for the first ~192 bytes
The main loop is good for big strings, but comparing 16B each time is better
for smaller strings. So after aligning the address to 16 Bytes, we check
more 176B in 16B chunks. There may be some overlaps with the main loop for
unaligned strings, but we avoid using the more aggressive strategy too soon,
and also allow the loop to start at a 64B-aligned address. This greatly
benefits smaller strings and avoids overlapping checks if the string is
already aligned at a 64B boundary.
3. Reduce dependencies between load blocks caused by address calculation on loop
Doing a precise time tracing on the code showed many loads in the loop were
stalled waiting for updates to r4 from previous code blocks. This
implementation avoids that as much as possible by using 2 registers (r4 and
r5) to hold addresses to be used by different parts of the code.
Also, the previous code aligned the address to 16B, then to 64B by doing a
few 48B loops (if needed) until the address was aligned. The main loop could
not start until that 48B loop had finished and r4 was updated with the
current address. Here we calculate the address used by the loop very early,
so it can start sooner.
The main loop now uses 2 pointers 128B apart to make pointer updates less
frequent, and also unrolls 1 iteration to guarantee there is enough time
between iterations to update the pointers, reducing stalled cycles.
4. Use new P10 instructions
lxvp is used to load 32B with a single instruction, reducing contention in
the load queue.
vextractbm allows simplifying the tail code for the loop, replacing
vbpermq and avoiding having to generate a permute control vector.
Reviewed-by: Paul E Murphy <murphyp@linux.ibm.com>
Reviewed-by: Raphael M Zinsly <rzinsly@linux.ibm.com>
Reviewed-by: Lucas A. M. Magalhaes <lamm@linux.ibm.com>
Florian Weimer [Thu, 22 Apr 2021 17:53:15 +0000 (19:53 +0200)]
nptl: Do not build nptl/tst-pthread-gdb-attach as PIE
Florian Weimer [Thu, 22 Apr 2021 17:50:16 +0000 (19:50 +0200)]
nptl: Move pthread_kill_other_threads_np compatibility symbol into libc
And stop including the function for new architectures.
H.J. Lu [Thu, 22 Apr 2021 01:40:08 +0000 (18:40 -0700)]
x86: tst-cpu-features-supports.c: Update AMX check
Pass "amx-bf16", "amx-int8" and "amx-tile", instead of "amx_bf16",
"amx_int8" and "amx_tile", to __builtin_cpu_supports for GCC 11.