It uses the bitmanip extension to optimize index_fist and index_last
with clz/ctz (using generic implementation that routes to compiler
builtin) and orc.b to check null bytes.
Checked the string test on riscv64 user mode.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
While ppc has the more important string functions in assembly,
there are still a few generic routines used.
Use the Power 6 CMPB insn for testing of zeros.
Checked on powerpc64le-linux-gnu.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
While arm has the more important string functions in assembly,
there are still a few generic routines used.
Use the UQSUB8 insn for testing of zeros.
Checked on armv7-linux-gnueabihf
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
While alpha has the more important string functions in assembly,
there are still a few for find the generic routines are used.
Use the CMPBGE insn, via the builtin, for testing of zeros. Use a
simplified expansion of __builtin_ctz when the insn isn't available.
Checked on alpha-linux-gnu.
Co-authored-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Use UXOR,SBZ to test for a zero byte within a word. While we can
get semi-decent code out of asm-goto, we would do slightly better
with a compiler builtin.
For index_zero et al, sequential testing of bytes is less expensive than
any tricks that involve a count-leading-zeros insn that we don't have.
Checked on hppa-linux-gnu.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
GCC's combine pass cannot merge (x >> c | y << (32 - c)) into a
double-word shift unless (1) the subtract is in the same basic block
and (2) the result of the subtract is used exactly once. Neither
condition is true for any use of MERGE.
By forcing the use of a double-word shift, we not only reduce
contention on SAR, but also allow the setting of SAR to be hoisted
outside of a loop.
Checked on hppa-linux-gnu.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Now that both strlen and memrchr have word vectorized implementation,
it should be faster to implement strrchr based on memrchr over the
string length instead of calling strchr on a loop.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powerpc64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
New algorithm read the lastaligned address and mask off the unwanted
bytes. The loop now read word-aligned address and check using the
has_eq macro.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powerpc64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
It also cleanups the multiple inclusion by leaving the ifunc
implementation to undef the weak_alias and libc_hidden_def.
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
New algorithm read the first aligned address and mask off the
unwanted bytes (this strategy is similar to arch-specific
implementations used on powerpc, sparc, and sh).
The loop now read word-aligned address and check using the has_eq
macro.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powerpc64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
Now that stpcpy is vectorized based on op_t, it should be better to
call it instead of strlen plus memcpy.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
It follows the strategy:
- Align the destination on word boundary using byte operations.
- If source is also word aligned, read a word per time, check for
null (using has_zero from string-fzb.h), and write the remaining
bytes.
- If source is not word aligned, loop by aligning the source, and
merging the result of two reads. Similar to aligned case,
check for null with has_zero, and write the remaining bytes if
null is found.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
It follows the strategy:
- Align the first input to word boundary using byte operations.
- If second input is also word aligned, read a word per time, check
for null (using has_zero), and check final words using byte
operation.
- If second input is not word aligned, loop by aligning the source,
and merge the result of two reads. Similar to aligned case, check
for null with has_zero, and check final words using byte operation.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
It follows the strategy:
- Align the first input to word boundary using byte operations.
- If second input is also word aligned, read a word per time, check for
null (using has_zero), and check final words using byte operation.
- If second input is not word aligned, loop by aligning the source, and
merging the result of two reads. Similar to aligned case, check for
null with has_zero, and check final words using byte operation.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
New algorithm now calls strchrnul.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powerpc64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
New algorithm read the first aligned address and mask off the unwanted
bytes (this strategy is similar to arch-specific implementations used
on powerpc, sparc, and sh).
The loop now read word-aligned address and check using the has_zero_eq
function.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc64-linux-gnu,
and powerpc-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
New algorithm read the first aligned address and mask off the
unwanted bytes (this strategy is similar to arch-specific
implementations used on powerpc, sparc, and sh).
The loop now read word-aligned address and check using the has_zero
macro.
Checked on x86_64-linux-gnu, i686-linux-gnu, powerpc-linux-gnu,
and powercp64-linux-gnu by removing the arch-specific assembly
implementation and disabling multi-arch (it covers both LE and BE
for 64 and 32 bits).
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
This patch adds generic string find and detection meant to be used in
generic vectorized string implementation. The idea is to decompose the
basic string operation so each architecture can reimplement if it
provides any specialized hardware instruction.
The 'string-misc.h' provides miscellaneous functions:
- extractbyte: extracts the byte from an specific index.
- repeat_bytes: setup an word by replicate the argument on each byte.
The 'string-fza.h' provides zero byte detection functions:
- find_zero_low, find_zero_all, find_eq_low, find_eq_all,
find_zero_eq_low, find_zero_eq_all, and find_zero_ne_all
The 'string-fzb.h' provides boolean zero byte detection functions:
- has_zero: determine if any byte within a word is zero.
- has_eq: determine byte equality between two words.
- has_zero_eq: determine if any byte within a word is zero along with
byte equality between two words.
The 'string-fzi.h' provides positions for string-fza.h results:
- index_first: return index of first zero byte within a word.
- index_last: return index of first byte different between two words.
The 'string-fzc.h' provides a combined version of fza and fzi:
- index_first_zero_eq: return index of first zero byte within a word or
first byte different between two words.
- index_first_zero_ne: return index of first zero byte within a word or
first byte equal between two words.
- index_last_zero: return index of last zero byte within a word.
- index_last_eq: return index of last byte different between two words.
The 'string-shift.h' provides a way to mask off parts of a work based on
some alignmnet (to handle unaligned arguments):
- shift_find, shift_find_last.
Co-authored-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
It moves OP_T_THRES out of memcopy.h to its own header and adjust
each architecture that redefines it.
Checked with a build and check with run-built-tests=no for all major
Linux ABIs.
Co-authored-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
It moves the op_t definition out to an specific header, adds
the attribute 'may-alias', and cleanup its duplicated definitions.
Checked with a build and check with run-built-tests=no for all major
Linux ABIs.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Almost all uses of rawmemchr find the end of a string. Since most targets use
a generic implementation, replacing it with strchr is better since that is
optimized by compilers into strlen (s) + s. Also fix the generic rawmemchr
implementation to use a cast to unsigned char in the if statement.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Improve SVE memcpy by copying 2 vectors if the size is small enough.
This improves performance of random memcpy by ~9% on Neoverse V1, and
33-64 byte copies are ~16% faster.
Reviewed-by: Szabolcs Nagy <szabolcs.nagy@arm.com>
This is a partial fix for mishandling of grouping when formatting
integers. It properly computes the width in the presence of grouping
characters when the width is larger than the number of significant
digits. The precision related issue is documented in bug 23432.
Co-authored-by: Andreas Schwab <schwab@suse.de>
If using -D_FORITFY_SOURCE=3 (in my case, I've patched GCC to add
=3 instead of =2 (we've done =2 for years in Gentoo)), building
glibc tests will fail on testmb like:
```
<command-line>: error: "_FORTIFY_SOURCE" redefined [-Werror]
<built-in>: note: this is the location of the previous definition
cc1: all warnings being treated as errors
make[2]: *** [../o-iterator.mk:9: /var/tmp/portage/sys-libs/glibc-2.36/work/build-x86-x86_64-pc-linux-gnu-nptl/stdlib/testmb.o] Error 1
make[2]: *** Waiting for unfinished jobs....
```
It's just because we're always setting -D_FORTIFY_SOURCE=2
rather than unsetting it first. If F_S is already 2, it's harmless,
but if it's another value (say, 1, or 3), the compiler will bawk.
(I'm not aware of a reason this couldn't be tested with =3,
but the toolchain support is limited for that (too new), and we want
to run the tests everywhere possible.)
Signed-off-by: Sam James <sam@gentoo.org>
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
This file is not used today since we end up using
sysdeps/i386/htl/machine-sp.h. Getting the stack pointer does not need
to be hurd specific and can go into sysdeps/<arch>.
Message-Id: <Y9tpWs2WOgE/Duiq@jupiter.tail36e24.ts.net>
Define the __glibc_fortify and other macros only when __FORTIFY_LEVEL >
0. This has the effect of not defining these macros on older C90
compilers that do not have support for variable length argument lists.
Also trim off the trailing backslashes from the definition of
__glibc_fortify and __glibc_fortify_n macros.
Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Reviewed-by: Florian Weimer <fweimer@redhat.com>
This adds a special SHM_ANON value that can be passed into shm_open ()
in place of a name. When called in this way, shm_open () will create a
new anonymous shared memory file. The file will be created in the same
way that other shared memory files are created (i.e., under /dev/shm/),
except that it is not given a name and therefore cannot be reached from
the file system, nor by other calls to shm_open (). This is accomplished
by utilizing O_TMPFILE.
This is intended to be compatible with FreeBSD's API of the same name.
Signed-off-by: Sergey Bugaev <bugaevc@gmail.com>
Message-Id: <20230130125216.6254-4-bugaevc@gmail.com>
This is a flag that causes open () to create a new, unnamed file in the
same filesystem as the given directory. The file descriptor can be
simply used in the creating process as a temporary file, or shared with
children processes via fork (), or sent over a Unix socket. The file can
be left anonymous, in which case it will be deleted from the backing
file system once all copies of the file descriptor are closed, or given
a permanent name with a linkat () call, such as the following:
int fd = open ("/tmp", O_TMPFILE | O_RDWR, 0700);
/* Do something with the file... */
linkat (fd, "", AT_FDCWD, "/tmp/filename", AT_EMPTY_PATH);
In between creating the file and linking it to the file system, it is
possible to set the file content, mode, ownership, author, and other
attributes, so that the file visibly appears in the file system (perhaps
replacing another file) atomically, with all of its attributes already
set up.
The Hurd support for O_TMPFILE directly exposes the dir_mkfile RPC to
user programs. Previously, dir_mkfile was used by glibc internally, in
particular for implementing tmpfile (), but not exposed to user programs
through a Unix-level API.
O_TMPFILE was initially introduced by Linux. This implementation is
intended to be compatible with the Linux implementation, except that the
O_EXCL flag is not given the special meaning when used together with
O_TMPFILE, unlike on Linux.
Signed-off-by: Sergey Bugaev <bugaevc@gmail.com>
Message-Id: <20230130125216.6254-3-bugaevc@gmail.com>
Instead of __file_name_lookup_at delegating to __file_name_lookup
in simple cases, make __file_name_lookup_at deal with both cases, and
have __file_name_lookup simply wrap __file_name_lookup_at.
This factorizes handling the empy name case.
Signed-off-by: Sergey Bugaev <bugaevc@gmail.com>
Message-Id: <20230130125216.6254-2-bugaevc@gmail.com>
Add an optimization to avoid calling clone3 when glibc detects that
there is no kernel support. It also adds __ASSUME_CLONE3, which allows
skipping this optimization and issuing the clone3 syscall directly.
It does not handle the the small window between 5.3 and 5.5 for
posix_spawn (CLONE_CLEAR_SIGHAND was added in 5.5).
Checked on x86_64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
It follow the internal signature:
extern int clone3 (struct clone_args *__cl_args, size_t __size,
int (*__func) (void *__arg), void *__arg);
Checked on aarch64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
The clone3 flag resets all signal handlers of the child not set to
SIG_IGN to SIG_DFL. It allows to skip most of the sigaction calls
to setup child signal handling, where previously a posix_spawn
had to issue 2 times NSIG sigaction calls (one to obtain the current
disposition and another to set either SIG_DFL or SIG_IGN).
With POSIX_SPAWN_SETSIGDEF the child will setup the signal for the case
where the disposition is SIG_IGN.
The code must handle the fallback where clone3 is not available. This is
done by splitting __clone_internal_fallback from __clone_internal.
Checked on x86_64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
All internal callers of __clone3 should provide an already aligned
stack. Removing the stack alignment in __clone3 is a net gain: it
simplifies the internal function contract (mask/unmask signals) along
with the arch-specific code.
Checked on x86_64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Different than kernel, clone3 returns EINVAL for NULL struct
clone_args or function pointer. This is similar to clone
interface that return EINVAL for NULL function argument.
It also clean up the Linux clone3.h interface, since it not
currently exported.
Checked on x86_64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
There is no need to issue another sigaction if the disposition is
already SIG_DFL.
Checked on x86_64-linux-gnu.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Occurs when `src` has no null-term.
Two cases:
1) Zero-length check is doing:
```
test %rdx, %rdx
jl L(zero_len)
```
which doesn't actually check zero (was at some point `decq` and the
flag never got updated).
The fix is just make the flag `jle` i.e:
```
test %rdx, %rdx
jle L(zero_len)
```
2) Length check in page-cross case checking if we should continue is
doing:
```
cmpq %r8, %rdx
jb L(page_cross_small)
```
which means we will continue searching for null-term if length ends at
the end of a page and there was no null-term in `src`.
The fix is to make the flag:
```
cmpq %r8, %rdx
jbe L(page_cross_small)
```
