Crossing 2GB boundaries with indirect calls and jumps can use more
branch prediction resources on Intel Golden Cove CPU (see the
"Misprediction for Branches >2GB" section in Intel 64 and IA-32
Architectures Optimization Reference Manual.) There is visible
performance improvement on workloads with many PLT calls when executable
and shared libraries are mmapped below 2GB. Add the Prefer_MAP_32BIT_EXEC
bit so that mmap will try to map executable or denywrite pages in shared
libraries with MAP_32BIT first.
NB: Prefer_MAP_32BIT_EXEC reduces bits available for address space
layout randomization (ASLR), which is always disabled for SUID programs
and can only be enabled by the tunable, glibc.cpu.prefer_map_32bit_exec,
or the environment variable, LD_PREFER_MAP_32BIT_EXEC. This works only
between shared libraries or between shared libraries and executables with
addresses below 2GB. PIEs are usually loaded at a random address above
4GB by the kernel.
Simon Kissane [Fri, 10 Feb 2023 21:58:02 +0000 (08:58 +1100)]
gmon: fix memory corruption issues [BZ# 30101]
V2 of this patch fixes an issue in V1, where the state was changed to ON not
OFF at end of _mcleanup. I hadn't noticed that (counterintuitively) ON=0 and
OFF=3, hence zeroing the buffer turned it back on. So set the state to OFF
after the memset.
1. Prevent double free, and reads from unallocated memory, when
_mcleanup is (incorrectly) called two or more times in a row,
without an intervening call to __monstartup; with this patch, the
second and subsequent calls effectively become no-ops instead.
While setting tos=NULL is minimal fix, safest action is to zero the
whole gmonparam buffer.
2. Prevent memory leak when __monstartup is (incorrectly) called two
or more times in a row, without an intervening call to _mcleanup;
with this patch, the second and subsequent calls effectively become
no-ops instead.
3. After _mcleanup, treat __moncontrol(1) as __moncontrol(0) instead.
With zeroing of gmonparam buffer in _mcleanup, this stops the
state incorrectly being changed to GMON_PROF_ON despite profiling
actually being off. If we'd just done the minimal fix to _mcleanup
of setting tos=NULL, there is risk of far worse memory corruption:
kcount would point to deallocated memory, and the __profil syscall
would make the kernel write profiling data into that memory,
which could have since been reallocated to something unrelated.
4. Ensure __moncontrol(0) still turns off profiling even in error
state. Otherwise, if mcount overflows and sets state to
GMON_PROF_ERROR, when _mcleanup calls __moncontrol(0), the __profil
syscall to disable profiling will not be invoked. _mcleanup will
free the buffer, but the kernel will still be writing profiling
data into it, potentially corrupted arbitrary memory.
Also adds a test case for (1). Issues (2)-(4) are not feasible to test.
Signed-off-by: Simon Kissane <skissane@gmail.com> Reviewed-by: DJ Delorie <dj@redhat.com>
When mcount overflows, no gmon.out file is generated, but no message is printed
to the user, leaving the user with no idea why, and thinking maybe there is
some bug - which is how BZ 27576 ended up being logged. Print a message to
stderr in this case so the user knows what is going on.
As a comment in sys/gmon.h acknowledges, the hardcoded MAXARCS value is too
small for some large applications, including the test case in that BZ. Rather
than increase it, add tunables to enable MINARCS and MAXARCS to be overridden
at runtime (glibc.gmon.minarcs and glibc.gmon.maxarcs). So if a user gets the
mcount overflow error, they can try increasing maxarcs (they might need to
increase minarcs too if the heuristic is wrong in their case.)
Note setting minarcs/maxarcs too large can cause monstartup to fail with an
out of memory error. If you set them large enough, it can cause an integer
overflow in calculating the buffer size. I haven't done anything to defend
against that - it would not generally be a security vulnerability, since these
tunables will be ignored in suid/sgid programs (due to the SXID_ERASE default),
and if you can set GLIBC_TUNABLES in the environment of a process, you can take
it over anyway (LD_PRELOAD, LD_LIBRARY_PATH, etc). I thought about modifying
the code of monstartup to defend against integer overflows, but doing so is
complicated, and I realise the existing code is susceptible to them even prior
to this change (e.g. try passing a pathologically large highpc argument to
monstartup), so I decided just to leave that possibility in-place.
Add a test case which demonstrates mcount overflow and the tunables.
Document the new tunables in the manual.
Signed-off-by: Simon Kissane <skissane@gmail.com> Reviewed-by: DJ Delorie <dj@redhat.com>
The `__monstartup()` allocates a buffer used to store all the data
accumulated by the monitor.
The size of this buffer depends on the size of the internal structures
used and the address range for which the monitor is activated, as well
as on the maximum density of call instructions and/or callable functions
that could be potentially on a segment of executable code.
In particular a hash table of arcs is placed at the end of this buffer.
The size of this hash table is calculated in bytes as
p->fromssize = p->textsize / HASHFRACTION;
but actually should be
p->fromssize = ROUNDUP(p->textsize / HASHFRACTION, sizeof(*p->froms));
This results in writing beyond the end of the allocated buffer when an
added arc corresponds to a call near from the end of the monitored
address range, since `_mcount()` check the incoming caller address for
monitored range but not the intermediate result hash-like index that
uses to write into the table.
It should be noted that when the results are output to `gmon.out`, the
table is read to the last element calculated from the allocated size in
bytes, so the arcs stored outside the buffer boundary did not fall into
`gprof` for analysis. Thus this "feature" help me to found this bug
during working with https://sourceware.org/bugzilla/show_bug.cgi?id=29438
Just in case, I will explicitly note that the problem breaks the
`make test t=gmon/tst-gmon-dso` added for Bug 29438.
There, the arc of the `f3()` call disappears from the output, since in
the DSO case, the call to `f3` is located close to the end of the
monitored range.
Signed-off-by: Леонид Юрьев (Leonid Yuriev) <leo@yuriev.ru>
Another minor error seems a related typo in the calculation of
`kcountsize`, but since kcounts are smaller than froms, this is
actually to align the p->froms data.
Co-authored-by: DJ Delorie <dj@redhat.com> Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Joseph Myers [Wed, 22 Feb 2023 21:36:34 +0000 (21:36 +0000)]
Ignore MAP_VARIABLE in tst-mman-consts.py
Linux 6.2 removed the hppa compatibility MAP_VARIABLE define. That
means that, whether or not we remove it in glibc, it needs to be
ignored in tst-mman-consts.py (since this macro comparison
infrastructure expects that new kernel header versions only add new
macros, not remove old ones).
Tested with build-many-glibcs.py for hppa-linux-gnu (Linux 6.2
headers).
Fix the computation to allow for cntfrq_el0 being larger than 1GHz.
Assume cntfrq_el0 is a multiple of 1MHz to increase the maximum
interval (1024 seconds at 1GHz).
The default Linux implementation already handled the Linux generic
ABIs interface used on newer architectures, so there is no need to
Imply the generic any longer.
Reviewed-by: Carlos O'Donell <carlos@redhat.com> Tested-by: Carlos O'Donell <carlos@redhat.com>
And remove redundant entries on other architectures Version. The
version for fallocate64 was supposed to be 2.10, but it was then
added to 32-bit platforms in 2.11 because it mistakenly wasn't
exported for them in 2.10 (see the commit message for 1f3615a1c97a030bca59f728f998947f852679b9).
The linux/generic did not exist before 2.15, i.e. when the tile
ports were added (and microblaze did not exist before 2.18), which
explains those differences but also illustrates that "2.11 for 32-bit,
2.10 for 64-bit" should be sufficient since versions older than the
minimum for the architecture are automatically adjusted.
Reviewed-by: Carlos O'Donell <carlos@redhat.com> Tested-by: Carlos O'Donell <carlos@redhat.com>
While cleaning up old libc version support, the deprecated libc4 code was
accidentally kept in `implicit_soname`, instead of the libc6 code.
This causes additional symlinks to be created by `ldconfig` for libraries
without a soname, e.g. a library `libsomething.123.456.789` without a soname
will create a `libsomething.123` -> `libsomething.123.456.789` symlink.
As the libc6 version of the `implicit_soname` code is a trivial `xstrdup`,
just inline it and remove `implicit_soname` altogether.
Some further simplification looks possible (e.g. the call to `create_links`
looks like a no-op if `soname == NULL`, other than the verbose printfs), but
logic is kept as-is for now.
Fixes: BZ #30125 Fixes: 8ee878592c4a ("Assume only FLAG_ELF_LIBC6 suport") Signed-off-by: Joan Bruguera <joanbrugueram@gmail.com> Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Vitaly Buka [Sat, 18 Feb 2023 20:53:41 +0000 (12:53 -0800)]
stdlib: Undo post review change to 16adc58e73f3 [BZ #27749]
Post review removal of "goto restart" from
https://sourceware.org/pipermail/libc-alpha/2021-April/125470.html
introduced a bug when some atexit handers skipped.
Sergey Bugaev [Sat, 18 Feb 2023 20:37:14 +0000 (23:37 +0300)]
mach: Use PAGE_SIZE
The PAGE_SIZE from the Mach headers statically defines the machine's
page size. There's no need to query it dynamically; furthermore, the
implementation of the vm_statistics () RPC unconditionally fills in
pagesize = PAGE_SIZE;
Not doing the extra RPC shaves off 2 RPCs from the start-up of every
process!
Pavel Kozlov [Tue, 17 Jan 2023 12:12:23 +0000 (16:12 +0400)]
ARC:fpu: add extra capability check before use of sqrt and fma builtins
Add extra check for compiler definitions to ensure that compiler provides
sqrt and fma hw fpu instructions else use software implementation.
As divide/sqrt and FMA hw support from CPU side is optional,
the compiler can be configured by options to generate hw FPU instructions,
but without use of FDDIV, FDSQRT, FSDIV, FSSQRT, FDMADD and FSMADD
instructions. In this case __builtin_sqrt and __builtin_sqrtf provided by
compiler can't be used inside the glibc code, as these builtins are used
in implementations of sqrt() and sqrtf() functions but at the same time
these builtins unfold to sqrt() and sqrtf(). So it is possible to receive
code like that:
0001c4b4 <__ieee754_sqrtf>:
1c4b4: 0001 0000 b 0 ;1c4b4 <__ieee754_sqrtf>
The same is also true for __builtin_fma and __builtin_fmaf. Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Pavel Kozlov [Wed, 21 Dec 2022 16:19:46 +0000 (20:19 +0400)]
ARC: align child stack in clone
The ARCv2 ABI requires 4 byte stack pointer alignment. Don't allow to
use unaligned child stack in clone. As the stack grows down,
align it down.
This was pointed by misc/tst-misalign-clone-internal and
misc/tst-misalign-clone tests. Stack alignmet fixes these tests
fails. Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Use put/get macros __builtin_bswap32 instead. It allows to remove
the unaligned routines, the compiler will generate unaligned access
if the ABI allows it.
Joseph Myers [Fri, 17 Feb 2023 17:23:50 +0000 (17:23 +0000)]
Fix ifunc-impl-list.c build for s390
Builds for s390 recently started failing with:
../sysdeps/s390/multiarch/ifunc-impl-list.c: In function '__libc_ifunc_impl_list':
../sysdeps/s390/multiarch/ifunc-impl-list.c:83:21: error: unused variable 'dl_hwcap' [-Werror=unused-variable]
83 | unsigned long int dl_hwcap = features->hwcap;
| ^~~~~~~~
Joseph Myers [Thu, 16 Feb 2023 23:02:40 +0000 (23:02 +0000)]
C2x strtol binary constant handling
C2x adds binary integer constants starting with 0b or 0B, and supports
those constants in strtol-family functions when the base passed is 0
or 2. Implement that strtol support for glibc.
As discussed at
<https://sourceware.org/pipermail/libc-alpha/2020-December/120414.html>,
this is incompatible with previous C standard versions, in that such
an input string starting with 0b or 0B was previously required to be
parsed as 0 (with the rest of the string unprocessed). Thus, as
proposed there, this patch adds 20 new __isoc23_* functions with
appropriate header redirection support. This patch does *not* do
anything about scanf %i (which will need 12 new functions per long
double variant, so 12, 24 or 36 depending on the glibc configuration),
instead leaving that for a future patch. The function names would
remain as __isoc23_* even if C2x ends up published in 2024 rather than
2023.
Making this change leads to the question of what should happen to
internal uses of these functions in glibc and its tests. The header
redirection (which applies for _GNU_SOURCE or any other feature test
macros enabling C2x features) has the effect of redirecting internal
uses but without those uses then ending up at a hidden alias (see the
comment in include/stdio.h about interaction with libc_hidden_proto).
It seems desirable for the default for internal uses to be the same
versions used by normal code using _GNU_SOURCE, so rather than doing
anything to disable that redirection, similar macro definitions to
those in include/stdio.h are added to the include/ headers for the new
functions.
Given that the default for uses in glibc is for the redirections to
apply, the next question is whether the C2x semantics are correct for
all those uses. Uses with the base fixed to 10, 16 or any other value
other than 0 or 2 can be ignored. I think this leaves the following
internal uses to consider (an important consideration for review of
this patch will be both whether this list is complete and whether my
conclusions on all entries in it are correct):
I think all of these places are OK with the new semantics, except for
resolv/inet_addr.c, where the POSIX semantics of inet_addr do not
allow for binary constants; thus, I changed that file (to use
__strtoul_internal, whose semantics are unchanged) and added a test
for this case. In the case of posix/wordexp.c I think accepting
binary constants is OK since POSIX explicitly allows additional forms
of shell arithmetic expressions, and in stdlib/fmtmsg.c SEV_LEVEL is
not in POSIX so again I think accepting binary constants is OK.
Functions such as __strtol_internal, which are only exported for
compatibility with old binaries from when those were used in inline
functions in headers, have unchanged semantics; the __*_l_internal
versions (purely internal to libc and not exported) have a new
argument to specify whether to accept binary constants.
As well as for the standard functions, the header redirection also
applies to the *_l versions (GNU extensions), and to legacy functions
such as strtoq, to avoid confusing inconsistency (the *q functions
redirect to __isoc23_*ll rather than needing their own __isoc23_*
entry points). For the functions that are only declared with
_GNU_SOURCE, this means the old versions are no longer available for
normal user programs at all. An internal __GLIBC_USE_C2X_STRTOL macro
is used to control the redirections in the headers, and cases in glibc
that wish to avoid the redirections - the function implementations
themselves and the tests of the old versions of the GNU functions -
then undefine and redefine that macro to allow the old versions to be
accessed. (There would of course be greater complexity should we wish
to make any of the old versions into compat symbols / avoid them being
defined at all for new glibc ABIs.)
strtol_l.c has some similarity to strtol.c in gnulib, but has already
diverged some way (and isn't listed at all at
https://sourceware.org/glibc/wiki/SharedSourceFiles unlike strtoll.c
and strtoul.c); I haven't made any attempts at gnulib compatibility in
the changes to that file.
I note incidentally that inttypes.h and wchar.h are missing the
__nonnull present on declarations of this family of functions in
stdlib.h; I didn't make any changes in that regard for the new
declarations added.
Sergey Bugaev [Tue, 14 Feb 2023 17:37:20 +0000 (20:37 +0300)]
hurd: i386 TLS tweaks
* Micro-optimize TLS access using GCC's native support for gs-based
addressing when available;
* Just use THREAD_GETMEM and THREAD_SETMEM instead of more inline
assembly;
* Sync tcbhead_t layout with NPTL, in particular update/fix __private_ss
offset;
* Statically assert that the two offsets that are a part of ABI are what
we expect them to be.
See https://sourceware.org/pipermail/libc-alpha/2023-February/145432.html
and https://sourceware.org/pipermail/libc-alpha/2023-February/145442.html Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Mahesh Bodapati [Mon, 13 Feb 2023 17:23:19 +0000 (11:23 -0600)]
Naming the parameter of dummy_sa_handler
ISO C does not support omitting parameter names in function definitions
before C2X,the compiler is giving an error with older versions of gcc and
this commit will resolve the test failure "error: parameter name omitted"
Sergey Bugaev [Sun, 12 Feb 2023 11:10:34 +0000 (14:10 +0300)]
mach, hurd: Cast through uintptr_t
When casting between a pointer and an integer of a different size, GCC
emits a warning (which is escalated to a build failure by -Werror).
Indeed, if what you start with is a pointer, which you then cast to a
shorter integer and then back again, you're going to cut off some bits
of the pointer.
But if you start with an integer (such as mach_port_t), then cast it to
a longer pointer (void *), and then back to a shorter integer, you are
fine. To keep GCC happy, cast through an intermediary uintptr_t, which
is always the same size as a pointer.
Sergey Bugaev [Sun, 12 Feb 2023 11:10:33 +0000 (14:10 +0300)]
hurd: Use mach_msg_type_number_t where appropriate
It has been decided that on x86_64, mach_msg_type_number_t stays 32-bit.
Therefore, it's not possible to use mach_msg_type_number_t
interchangeably with size_t, in particular this breaks when a pointer to
a variable is passed to a MIG routine.
Sergey Bugaev [Sun, 12 Feb 2023 11:10:32 +0000 (14:10 +0300)]
hurd: Refactor readlinkat()
Make the code flow more linear using early returns where possible. This
makes it so much easier to reason about what runs on error / successful
code paths.
Paul Pluzhnikov [Fri, 10 Feb 2023 16:14:30 +0000 (16:14 +0000)]
Use __builtin_FILE instead of __FILE__ in assert in C++.
Likewise use __builtin_LINE instead of __LINE__.
When building C++, inline functions are required to have the exact same
sequence of tokens in every translation unit. But __FILE__ token, when
used in a header file, does not necessarily expand to the exact same
string literal, and that may cause compilation failure when C++ modules
are being used. (It would also cause unpredictable output on assertion
failure at runtime, but this rarely matters in practice.)
Samuel Thibault [Thu, 9 Feb 2023 18:58:43 +0000 (19:58 +0100)]
hurd: Fix unwinding over INTR_MSG_TRAP
We used to use .cfi_adjust_cfa_offset around %esp manipulation
asm instructions to fix unwinding, but when building glibc with
-fno-omit-frame-pointer this is bogus since in that case %ebp is the CFA and
does not move.
Instead, let's force -fno-omit-frame-pointer when building intr-msg.c so
that %ebp can always be used and no .cfi_adjust_cfa_offset is needed.
extern int clone3 (struct clone_args *__cl_args, size_t __size,
int (*__func) (void *__arg), void *__arg);
The powerpc64 ABI requires an initial stackframe so the child can
store/restore the TOC. It is create prior calling clone3 by
adjusting the stack size (since kernel will compute the stack as
stack plus size).
Checked on powerpc64-linux-gnu (power8, kernel 6.0) and
powerpc64le-linux-gnu (power9, kernel 4.18). Reviewed-by: Paul E. Murphy <murphyp@linux.ibm.com>
Florian Weimer [Wed, 8 Feb 2023 17:11:04 +0000 (18:11 +0100)]
elf: Smoke-test ldconfig -p against system /etc/ld.so.cache
The test is sufficient to detect the ldconfig bug fixed in
commit 9fe6f6363886aae6b2b210cae3ed1f5921299083 ("elf: Fix 64 time_t
support for installed statically binaries").
quxm [Wed, 25 Jan 2023 09:47:33 +0000 (17:47 +0800)]
C-SKY: Strip hard float abi from hard float feature.
The hard float abi and hard float are different,
Hard float abi: Use float register to pass float type arguments.
Hard float: Enable the hard float ISA feature.
So the with_fp_cond cannot represent these two features. When
-mfloat-abi=softfp, the float abi is soft and hard float is enabled.
So add 'with_hard_float_abi' in preconfigure and define 'CSKY_HARD_FLOAT_ABI'
if float abi is hard, and use 'CSKY_HARD_FLOAT_ABI' to determine
dynamic linker because it is what determines compatibility.
And with_fp_cond is still needed to tell glibc whether to enable
hard floating feature.
In addition, use AC_TRY_COMMAND to test gcc to ensure compatibility
between different versions of gcc. The original way has a problem
that __CSKY_HARD_FLOAT_FPU_SF__ means the target only has single
hard float-points ISA, so it's not defined in CPUs like ck810f.
Stefan Liebler [Thu, 2 Feb 2023 13:57:50 +0000 (14:57 +0100)]
S390: Influence hwcaps/stfle via GLIBC_TUNABLES.
This patch enables the option to influence hwcaps and stfle bits used
by the s390 specific ifunc-resolvers. The currently x86-specific
tunable glibc.cpu.hwcaps is also used on s390x to achieve the task. In
addition the user can also set a CPU arch-level like z13 instead of
single HWCAP and STFLE features.
Note that the tunable only handles the features which are really used
in the IFUNC-resolvers. All others are ignored as the values are only
used inside glibc. Thus we can influence:
- HWCAP_S390_VXRS (z13)
- HWCAP_S390_VXRS_EXT (z14)
- HWCAP_S390_VXRS_EXT2 (z15)
- STFLE_MIE3 (z15)
The influenced hwcap/stfle-bits are stored in the s390-specific
cpu_features struct which also contains reserved fields for future
usage.
The ifunc-resolvers and users of stfle bits are adjusted to use the
information from cpu_features struct.
On 31bit, the ELF_MACHINE_IRELATIVE macro is now also defined.
Otherwise the new ifunc-resolvers segfaults as they depend on
the not yet processed_rtld_global_ro@GLIBC_PRIVATE relocation.
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>
hppa: Add string-fza.h, string-fzc.h, and string-fzi.h
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.
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.
string: Improve generic strrchr with memrchr and strlen
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>
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>
- 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>
- 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>
- 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>
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>
Add string vectorized find and detection functions
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>
projects / thirdparty / glibc.git / log
