Improve performance of recursive IO locks by adding a fast path for
the single-threaded case. To reduce the number of memory accesses for
locking/unlocking, only increment the recursion counter if the lock
is already taken.
On Neoverse V1, a microbenchmark with many small freads improved by
2.9x. Multithreaded performance improved by 2%.
Reviewed-by: Cristian Rodríguez <crrodriguez@opensuse.org>
So far this test checks if pidfd_open-syscall is supported,
which was introduced with linux 5.3.
The process_madvise-syscall was introduced with linux 5.10.
Thus you'll get FAILs if you are running a kernel in between.
This patch adds a check if the first process_madvise-syscall
returns ENOSYS and in this case will fail with UNSUPPORTED.
Reviewed-by: Florian Weimer <fweimer@redhat.com>
`#ifndef STPCPY` is incorrect for checking if `STRCPY` is already
defined. It doesn't end up mattering as the whole check is
guarded by `#if IS_IN (libc)` but is incorrect none the less.
Similar to 6720d36b66 for x86-64.
Clang cannot assemble movzx in the AT&T dialect mode. Change movzx to
movzbl, which follows the AT&T dialect and is used elsewhere in the
file.
The older libc versions are obsolete for over twenty years now.
This patch removes the special flags for libc5 and libc4 and assumes
that all libraries cached are libc6 compatible and use FLAG_ELF_LIBC6.
Checked with a build for all affected architectures.
Co-authored-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
exit only terminates the current thread, not the whole process, so it
is the wrong fallback system call in this context. All supported
Linux versions implement the exit_group system call anyway.
This patch updates the kernel version in the tests tst-mman-consts.py,
tst-mount-consts.py and tst-pidfd-consts.py to 5.18. (There are no
new constants covered by these tests in 5.19, or in 5.17 or 5.18 in
the case of tst-mount-consts.py that previously used version 5.16,
that need any other header changes.)
Tested with build-many-glibcs.py.
__pthread_sigmask cannot actually fail with valid pointer arguments
(it would need a really broken seccomp filter), and we do not check
for errors elsewhere.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Since commit ec2c1fcefb ("malloc:
Abort on heap corruption, without a backtrace [BZ #21754]"),
__libc_message always terminates the process. Since commit
a289ea09ea ("Do not print backtraces
on fatal glibc errors"), the backtrace facility has been removed.
Therefore, remove enum __libc_message_action and the action
argument of __libc_message, and mark __libc_message as _No_return.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Linux 5.19 has no new syscalls, but enables memfd_secret in the uapi
headers for RISC-V. Update the version number in syscall-names.list
to reflect that it is still current for 5.19 and regenerate the
arch-syscall.h headers with build-many-glibcs.py update-syscalls.
Tested with build-many-glibcs.py.
The inline and library functions that the CMSG_NXTHDR macro may expand
to increment the pointer to the header before checking the stride of
the increment against available space. Since C only allows incrementing
pointers to one past the end of an array, the increment must be done
after a length check. This commit fixes that and includes a regression
test for CMSG_FIRSTHDR and CMSG_NXTHDR.
The Linux, Hurd, and generic headers are all changed.
Tested on Linux on armv7hl, i686, x86_64, aarch64, ppc64le, and s390x.
[BZ #28846]
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
pidfd_getfd can fail for a valid pidfd with errno EPERM for various
reasons in a restricted environment. Use FAIL_UNSUPPORTED in that case.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
Rather than buffering 16 MiB of entropy in userspace (by way of
chacha20), simply call getrandom() every time.
This approach is doubtlessly slower, for now, but trying to prematurely
optimize arc4random appears to be leading toward all sorts of nasty
properties and gotchas. Instead, this patch takes a much more
conservative approach. The interface is added as a basic loop wrapper
around getrandom(), and then later, the kernel and libc together can
work together on optimizing that.
This prevents numerous issues in which userspace is unaware of when it
really must throw away its buffer, since we avoid buffering all
together. Future improvements may include userspace learning more from
the kernel about when to do that, which might make these sorts of
chacha20-based optimizations more possible. The current heuristic of 16
MiB is meaningless garbage that doesn't correspond to anything the
kernel might know about. So for now, let's just do something
conservative that we know is correct and won't lead to cryptographic
issues for users of this function.
This patch might be considered along the lines of, "optimization is the
root of all evil," in that the much more complex implementation it
replaces moves too fast without considering security implications,
whereas the incremental approach done here is a much safer way of going
about things. Once this lands, we can take our time in optimizing this
properly using new interplay between the kernel and userspace.
getrandom(0) is used, since that's the one that ensures the bytes
returned are cryptographically secure. But on systems without it, we
fallback to using /dev/urandom. This is unfortunate because it means
opening a file descriptor, but there's not much of a choice. Secondly,
as part of the fallback, in order to get more or less the same
properties of getrandom(0), we poll on /dev/random, and if the poll
succeeds at least once, then we assume the RNG is initialized. This is a
rough approximation, as the ancient "non-blocking pool" initialized
after the "blocking pool", not before, and it may not port back to all
ancient kernels, though it does to all kernels supported by glibc
(≥3.2), so generally it's the best approximation we can do.
The motivation for including arc4random, in the first place, is to have
source-level compatibility with existing code. That means this patch
doesn't attempt to litigate the interface itself. It does, however,
choose a conservative approach for implementing it.
Cc: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Cristian Rodríguez <crrodriguez@opensuse.org>
Cc: Paul Eggert <eggert@cs.ucla.edu>
Cc: Mark Harris <mark.hsj@gmail.com>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: linux-crypto@vger.kernel.org
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Commit a06b40cdf5 updated stat.h to use
__USE_XOPEN2K8 instead of __USE_MISC to add the st_atim, st_mtim and
st_ctim members to struct stat. However, for microblaze, there are two
definitions of struct stat, depending on the __USE_FILE_OFFSET64 macro.
The second one was not updated.
Change __USE_MISC to __USE_XOPEN2K8 in the __USE_FILE_OFFSET64 version
of struct stat for microblaze.
The hppa port starts libc at GLIBC_2.2, but has earlier symbol
versions in other shared objects. This means that the compat
symbol for readdir64 is not actually present in libc even though
have-GLIBC_2.1.3 is defined as yes at the make level.
Fixes commit 15e50e6c96 ("Linux:
dirent/tst-readdir64-compat can be a regular test") by mostly
reverting it.
It adds vectorized ChaCha20 implementation based on libgcrypt
cipher/chacha20-amd64-avx2.S. It is used only if AVX2 is supported
and enabled by the architecture.
As for generic implementation, the last step that XOR with the
input is omited. The final state register clearing is also
omitted.
On a Ryzen 9 5900X it shows the following improvements (using
formatted bench-arc4random data):
SSE MB/s
-----------------------------------------------
arc4random [single-thread] 704.25
arc4random_buf(16) [single-thread] 1018.17
arc4random_buf(32) [single-thread] 1315.27
arc4random_buf(48) [single-thread] 1449.36
arc4random_buf(64) [single-thread] 1511.16
arc4random_buf(80) [single-thread] 1539.48
arc4random_buf(96) [single-thread] 1571.06
arc4random_buf(112) [single-thread] 1596.16
arc4random_buf(128) [single-thread] 1613.48
-----------------------------------------------
AVX2 MB/s
-----------------------------------------------
arc4random [single-thread] 922.61
arc4random_buf(16) [single-thread] 1478.70
arc4random_buf(32) [single-thread] 2241.80
arc4random_buf(48) [single-thread] 2681.28
arc4random_buf(64) [single-thread] 2913.43
arc4random_buf(80) [single-thread] 3009.73
arc4random_buf(96) [single-thread] 3141.16
arc4random_buf(112) [single-thread] 3254.46
arc4random_buf(128) [single-thread] 3305.02
-----------------------------------------------
Checked on x86_64-linux-gnu.
It adds vectorized ChaCha20 implementation based on libgcrypt
cipher/chacha20-amd64-ssse3.S. It replaces the ROTATE_SHUF_2 (which
uses pshufb) by ROTATE2 and thus making the original implementation
SSE2.
As for generic implementation, the last step that XOR with the
input is omited. The final state register clearing is also
omitted.
On a Ryzen 9 5900X it shows the following improvements (using
formatted bench-arc4random data):
GENERIC MB/s
-----------------------------------------------
arc4random [single-thread] 443.11
arc4random_buf(16) [single-thread] 552.27
arc4random_buf(32) [single-thread] 626.86
arc4random_buf(48) [single-thread] 649.81
arc4random_buf(64) [single-thread] 663.95
arc4random_buf(80) [single-thread] 674.78
arc4random_buf(96) [single-thread] 675.17
arc4random_buf(112) [single-thread] 680.69
arc4random_buf(128) [single-thread] 683.20
-----------------------------------------------
SSE MB/s
-----------------------------------------------
arc4random [single-thread] 704.25
arc4random_buf(16) [single-thread] 1018.17
arc4random_buf(32) [single-thread] 1315.27
arc4random_buf(48) [single-thread] 1449.36
arc4random_buf(64) [single-thread] 1511.16
arc4random_buf(80) [single-thread] 1539.48
arc4random_buf(96) [single-thread] 1571.06
arc4random_buf(112) [single-thread] 1596.16
arc4random_buf(128) [single-thread] 1613.48
-----------------------------------------------
Checked on x86_64-linux-gnu.
It adds vectorized ChaCha20 implementation based on libgcrypt
cipher/chacha20-aarch64.S. It is used as default and only
little-endian is supported (BE uses generic code).
As for generic implementation, the last step that XOR with the
input is omited. The final state register clearing is also
omitted.
On a virtualized Linux on Apple M1 it shows the following
improvements (using formatted bench-arc4random data):
GENERIC MB/s
-----------------------------------------------
arc4random [single-thread] 380.89
arc4random_buf(16) [single-thread] 500.73
arc4random_buf(32) [single-thread] 552.61
arc4random_buf(48) [single-thread] 566.82
arc4random_buf(64) [single-thread] 574.01
arc4random_buf(80) [single-thread] 581.02
arc4random_buf(96) [single-thread] 591.19
arc4random_buf(112) [single-thread] 592.29
arc4random_buf(128) [single-thread] 596.43
-----------------------------------------------
OPTIMIZED MB/s
-----------------------------------------------
arc4random [single-thread] 569.60
arc4random_buf(16) [single-thread] 825.78
arc4random_buf(32) [single-thread] 987.03
arc4random_buf(48) [single-thread] 1042.39
arc4random_buf(64) [single-thread] 1075.50
arc4random_buf(80) [single-thread] 1094.68
arc4random_buf(96) [single-thread] 1130.16
arc4random_buf(112) [single-thread] 1129.58
arc4random_buf(128) [single-thread] 1137.91
-----------------------------------------------
Checked on aarch64-linux-gnu.
The implementation is based on scalar Chacha20 with per-thread cache.
It uses getrandom or /dev/urandom as fallback to get the initial entropy,
and reseeds the internal state on every 16MB of consumed buffer.
To improve performance and lower memory consumption the per-thread cache
is allocated lazily on first arc4random functions call, and if the
memory allocation fails getentropy or /dev/urandom is used as fallback.
The cache is also cleared on thread exit iff it was initialized (so if
arc4random is not called it is not touched).
Although it is lock-free, arc4random is still not async-signal-safe
(the per thread state is not updated atomically).
The ChaCha20 implementation is based on RFC8439 [1], omitting the final
XOR of the keystream with the plaintext because the plaintext is a
stream of zeros. This strategy is similar to what OpenBSD arc4random
does.
The arc4random_uniform is based on previous work by Florian Weimer,
where the algorithm is based on Jérémie Lumbroso paper Optimal Discrete
Uniform Generation from Coin Flips, and Applications (2013) [2], who
credits Donald E. Knuth and Andrew C. Yao, The complexity of nonuniform
random number generation (1976), for solving the general case.
The main advantage of this method is the that the unit of randomness is not
the uniform random variable (uint32_t), but a random bit. It optimizes the
internal buffer sampling by initially consuming a 32-bit random variable
and then sampling byte per byte. Depending of the upper bound requested,
it might lead to better CPU utilization.
Checked on x86_64-linux-gnu, aarch64-linux, and powerpc64le-linux-gnu.
Co-authored-by: Florian Weimer <fweimer@redhat.com>
Reviewed-by: Yann Droneaud <ydroneaud@opteya.com>
[1] https://datatracker.ietf.org/doc/html/rfc8439
[2] https://arxiv.org/pdf/1304.1916.pdf
Before this the test fails if run in a chroot by a non-root user:
warning: could not become root outside namespace (Operation not permitted)
../sysdeps/unix/sysv/linux/tst-mount.c:36: numeric comparison failure
left: 1 (0x1); from: errno
right: 19 (0x13); from: ENODEV
error: ../sysdeps/unix/sysv/linux/tst-mount.c:39: not true: fd != -1
error: ../sysdeps/unix/sysv/linux/tst-mount.c:46: not true: r != -1
error: ../sysdeps/unix/sysv/linux/tst-mount.c:48: not true: r != -1
../sysdeps/unix/sysv/linux/tst-mount.c:52: numeric comparison failure
left: 1 (0x1); from: errno
right: 9 (0x9); from: EBADF
error: ../sysdeps/unix/sysv/linux/tst-mount.c:55: not true: mfd != -1
../sysdeps/unix/sysv/linux/tst-mount.c:58: numeric comparison failure
left: 1 (0x1); from: errno
right: 2 (0x2); from: ENOENT
error: ../sysdeps/unix/sysv/linux/tst-mount.c:61: not true: r != -1
../sysdeps/unix/sysv/linux/tst-mount.c:65: numeric comparison failure
left: 1 (0x1); from: errno
right: 2 (0x2); from: ENOENT
error: ../sysdeps/unix/sysv/linux/tst-mount.c:68: not true: pfd != -1
error: ../sysdeps/unix/sysv/linux/tst-mount.c:75: not true: fd_tree != -1
../sysdeps/unix/sysv/linux/tst-mount.c:88: numeric comparison failure
left: 1 (0x1); from: errno
right: 38 (0x26); from: ENOSYS
error: 12 test failures
Checking that the test can enter a new mount namespace is more correct
than just checking the return value of support_become_root() as the test
code changes the mount namespace it runs in so running it as root on a
system that does not support mount namespaces should still skip.
Also change the test to remove the unnecessary fork.
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
1. Add default ISA level selection in non-multiarch/rtld
implementations.
2. Add ISA level build guards to different implementations.
- I.e strcpy-avx2.S which is ISA level 3 will only build if
compiled ISA level <= 3. Otherwise there is no reason to
include it as we will always use one of the ISA level 4
implementations (strcpy-evex.S).
3. Refactor the ifunc selector and ifunc implementation list to use
the ISA level aware wrapper macros that allow functions below the
compiled ISA level (with a guranteed replacement) to be skipped.
Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}
And m32 with and without multiarch.
1. Add ISA level build guards to different implementations.
- wcscpy-ssse3.S is used as ISA level 2/3/4.
- wcscpy-generic.c is only used at ISA level 1 and will
only build if compiled with ISA level == 1. Otherwise
there is no reason to include it as we will always use
wcscpy-ssse3.S
2. Refactor the ifunc selector and ifunc implementation list to use
the ISA level aware wrapper macros that allow functions below the
compiled ISA level (with a guranteed replacement) to be skipped.
Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}
And m32 with and without multiarch.
1. Add default ISA level selection in non-multiarch/rtld
implementations.
2. Add ISA level build guards to different implementations.
- I.e strcmp-avx2.S which is ISA level 3 will only build if
compiled ISA level <= 3. Otherwise there is no reason to
include it as we will always use one of the ISA level 4
implementations (strcmp-evex.S).
3. Refactor the ifunc selector and ifunc implementation list to use
the ISA level aware wrapper macros that allow functions below the
compiled ISA level (with a guranteed replacement) to be skipped.
Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}
And m32 with and without multiarch.
Starting with commit e070501d12
"Replace __libc_multiple_threads with __libc_single_threaded"
the testcases nptl/tst-cancel-self and
nptl/tst-cancel-self-cancelstate are failing.
This is fixed by only defining SINGLE_THREAD_BY_GLOBAL on s390x,
but not on s390.
Starting with commit 09c76a7409
"Linux: Consolidate {RTLD_}SINGLE_THREAD_P definition",
SINGLE_THREAD_BY_GLOBAL was defined in
sysdeps/unix/sysv/linux/s390/s390-64/sysdep.h.
Lateron the commit 9a973da617
"s390: Consolidate Linux syscall definition" consolidates the sysdep.h files
from s390-32/s390-64 subdirectories. Unfortunately the macro is now always
defined instead of only on s390-64.
As information:
TLS_MULTIPLE_THREADS_IN_TCB is also only defined for s390.
See: sysdeps/s390/nptl/tls.h
