The optimized i386 version is faster than the generic one, and
gcc implements it through the builtin. This optimization enables
us to migrate the implementation to a C version. The performance
on a Zen3 chip is similar to the SVID one.
The m68k provided an optimized version through __m81_u(remainderf)
(mathimpl.h), and gcc does not implement it through a builtin
(different than i386).
Performance improves a bit on x86_64 (Zen3, gcc 15.2.1):
reciprocal-throughput input master NO-SVID improvement
x86_64 subnormals 18.8522 16.2506 13.80%
x86_64 normal 421.8260 403.9270 4.24%
x86_64 close-exponent 21.0579 18.7642 10.89%
i686 subnormals 21.3443 21.4229 -0.37%
i686 normal 525.8380 538.807 -2.47%
i686 close-exponent 21.6589 21.7983 -0.64%
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
The optimized i386 version is faster than the generic one, and gcc
implements it through the builtin. This optimization enables us to
migrate the implementation to a C version. The performance on a Zen3
chip is similar to the SVID one.
The m68k provided an optimized version through __m81_u(remainderf)
(mathimpl.h), and gcc does not implement it through a builtin (different
than i386).
Performance improves a bit on x86_64 (Zen3, gcc 15.2.1):
reciprocal-throughput input master NO-SVID improvement
x86_64 subnormals 17.5349 15.6125 10.96%
x86_64 normal 53.8134 52.5754 2.30%
x86_64 close-exponent 20.0211 18.6656 6.77%
i686 subnormals 21.8105 20.1856 7.45%
i686 normal 73.1945 71.2199 2.70%
i686 close-exponent 22.2141 20.331 8.48%
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 3-10% and throughput for about 5-15%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 1-10% and throughput for about 5-10%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 3-7% and throughput for about 5-10%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 2% and throughput for about 5%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 2-10% and throughput for about 5-10%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
It improves latency for about 3-10% and throughput for about 5-10%.
Tested on x86_64-linux-gnu and i686-linux-gnu.
Reviewed-by: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
The C2y function uimaxabs has been renamed to umaxabs. Implement this
change in glibc, keeping a compat symbol under the old name, copying
the test to test the new name and changing the old test to test the
compat symbol. Jakub has done the corresponding change to the
built-in function in GCC.
Tested for x86_64 and x86.
Add the C23 memalignment function (query the alignment of a pointer)
to glibc.
Given how simple this operation is, it would make sense for compilers
to inline calls to this function, but I'm treating that as a compiler
matter (compilers should add it as a built-in function) rather than
adding an inline version to glibc headers (although such an inline
version would be reasonable as well). I've filed
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=122117 for this feature
in GCC.
Tested for x86_64 and x86.
Add the C23 memset_explicit function to glibc. Everything here is
closely based on the approach taken for explicit_bzero. This includes
the bits that relate to internal uses of explicit_bzero within glibc
(although we don't currently have any such internal uses of
memset_explicit), and also includes the nonnull attribute (when we
move to nonnull_if_nonzero for various functions following C2y, this
function should be included in that change).
The function is declared both for __USE_MISC and for __GLIBC_USE (ISOC23)
(so by default not just for compilers defaulting to C23 mode).
Tested for x86_64 and x86.
This reverts commit 3d3572f590.
Reason for revert: TCGETS etc. work to some extent on at least
a subset of architectures, so there is no pressing need to force
applications off them. Removal of the macros breaks building
the sanitizers, impacting both GCC and LLVM.
Reviewed-by: Sam James <sam@gentoo.org>
Undefine TCGETS, TCGETS2, and related ioctl constants in the installed
headers. Extract the correct constants (using the kernel type
definitions) automatically from the UAPI headers. The kernel
constants are available under KERNEL_* names during the glibc build,
computed using assembler constant extraction mechanism.
Alpha may have to use TCGETS instead of TCGETS2 because TCTGETS2
became available in Linux 4.20 only. Introduce ARCH_TCGETS to make
this choice explict.
To support emulation on powerpc, glibc versions of the termios
constants are added to the emulation code in internal-ioctl.h.
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
The use of the termios2 ioctl interface is an implementation detail which
should not bleed into public headers. Remove the PowerPC version of
<bits/ioctls.h> and define the termios2 ioctl numbers in <termios_arch.h>
instead. Also remove the include check from there which is unneeded in an
internal header.
Add an explicitly numeric interface for baudrate setting. For glibc,
this only announces what is a fair accompli, but this is a plausible
way forward for standardization, and may be possible to infill on
non-compliant systems. The POSIX committee has stated:
[https://www.austingroupbugs.net/view.php?id=1916#c7135]
A future version of this standard is expected to add at least
the following symbolic constants for use as values of objects
of type speed_t: B57600, B115200, B230400, B460800, and
B921600.
Implementations are encouraged to propose additional
interfaces which will make it possible to set and query a
wider range of speeds than just those enumerated by the
constants beginning with B. If a set of common interfaces
emerges between several implementations, a future version of
this standard will likely add those interfaces.
This is exactly that interface.
The use of the term "baud" is due to the need to have a term
contrasting "speed", and it is already well established as a legacy
term -- including in the names of the legacy Bxxx
constants. Futhermore, it *is* valid from the point of view that the
termios interface fundamentally emulates an RS-232 serial port as far
as the application software is concerned.
The documentation states that for the current version of glibc,
speed_t == baud_t, but explicitly declares that this may not be the
case in the future.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Linux has supported arbitrary speeds and split speeds in the kernel
since 2008 on all platforms except Alpha (fixed in 2020), but glibc
was never updated to match. This is further complicated by POSIX uses
of macros for the cf[gs]et[io]speed interfaces, rather than plain
numbers, as it really ought to have.
On most platforms, the glibc ABI includes the c_[io]speed fields in
struct termios, but they are incorrectly used. On MIPS and SPARC, they
are entirely missing.
For backwards compatibility, the kernel will still use the legacy
speed fields unless they are set to BOTHER, and will use the legacy
output speed as the input speed if the latter is 0 (== B0). However,
the specific encoding used is visible to user space applications,
including ones other than the one running.
- SPARC and MIPS get a new struct termios, and tc[gs]etattr() is
versioned accordingly. However, the new struct termios is set to be
a strict extension of the old one, which means that cf* interfaces
other than the speed-related ones do not need versioning.
- The Bxxx constants are redefined as equivalent to their integer
values and the legacy Bxxx constants are renamed __Bxxx.
- cf[gs]et[io]speed() and cfsetspeed() are versioned accordingly.
- tcgetattr() and cfset[io]speed() are adjusted to always keep the
c_[io]speed fields correct (unlike earlier versions), but to
canonicalize the representation to ALSO configure the legacy fields
if a valid legacy representation exists.
- tcsetattr(), too, canonicalizes the representation in this way
before passing it to the kernel, to maximize compatibility with
older applications/tools.
- The old IBAUD0 hack is removed; it is no longer necessary since
even the legacy c_cflag baud rate fields have had separate input
values for a long time.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
The powerpc architecture, only, emulates the termios ioctls using the
glibc termios structure. Export the real kernel ones as the termios2
interface; although the kernel doesn't call it termios2, it is exactly
the termios2 interface, and it avoids the namespace clash between the
emulated ioctls and the real kernel ioctls.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Linux 6.15 adds the new syscall open_tree_attr. Update
syscall-names.list and regenerate the arch-syscall.h headers with
build-many-glibcs.py update-syscalls.
Tested with build-many-glibcs.py.
Reviewed-by: Florian Weimer <fweimer@redhat.com>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the rootn functions, which compute the Yth root of X for
integer Y (with a domain error if Y is 0, even if X is a NaN). The
integer exponent has type long long int in C23; it was intmax_t in TS
18661-4, and as with other interfaces changed after their initial
appearance in the TS, I don't think we need to support the original
version of the interface.
As with pown and compoundn, I strongly encourage searching for worst
cases for ulps error for these implementations (necessarily
non-exhaustively, given the size of the input space). I also expect a
custom implementation for a given format could be much faster as well
as more accurate, although the implementation is simpler than those
for pown and compoundn.
This completes adding to glibc those TS 18661-4 functions (ignoring
DFP) that are included in C23. See
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=118592 regarding the C23
mathematical functions (not just the TS 18661-4 ones) missing built-in
functions in GCC, where such functions might usefully be added.
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the compoundn functions, which compute (1+X) to the
power Y for integer Y (and X at least -1). The integer exponent has
type long long int in C23; it was intmax_t in TS 18661-4, and as with
other interfaces changed after their initial appearance in the TS, I
don't think we need to support the original version of the interface.
Note that these functions are "compoundn" with a trailing "n", *not*
"compound" (CORE-MATH has the wrong name, for example).
As with pown, I strongly encourage searching for worst cases for ulps
error for these implementations (necessarily non-exhaustively, given
the size of the input space). I also expect a custom implementation
for a given format could be much faster as well as more accurate (I
haven't tested or benchmarked the CORE-MATH implementation for
binary32); this is one of the more complicated and less efficient
functions to implement in a type-generic way.
As with exp2m1 and exp10m1, this showed up places where the
powerpc64le IFUNC setup is not as self-contained as one might hope (in
this case, without the changes specific to powerpc64le, there were
undefined references to __GI___expf128).
Tested for x86_64 and x86, and with build-many-glibcs.py.
The <termio.h> interface is absolutely ancient: it was obsoleted by
<termios.h> already in the first version of POSIX (1988) and thus
predates the very first version of Linux. Unfortunately, some constant
macros are used both by <termio.h> and <termios.h>; particularly
problematic is the baud rate constants since the termio interface
*requires* that the baud rate is set via an enumeration as part of
c_cflag.
In preparation of revamping the termios interface to support the
arbitrary baud rate capability that the Linux kernel has supported
since 2008, remove <termio.h> in the hope that no one still uses this
archaic interface.
Note that there is no actual code in glibc to support termio: it is
purely an unabstracted ioctl() interface.
Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Reviewed-by: Florian Weimer <fweimer@redhat.com>
C2Y adds unsigned versions of the abs functions (see C2Y draft N3467 and
proposal N3349).
Tested for x86_64.
Signed-off-by: Lenard Mollenkopf <glibc@lenardmollenkopf.de>
We mistakenly dropped the check in 27b96e069aad17cefea9437542180bff448ac3a0;
there's some other checks which we *can* drop, but let's worry about that
later.
Fixes the build on ppc64le where GCC is configured with --with-long-double-format=ieee.
Reviewed-by: Andreas Schwab <schwab@suse.de>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the pown functions, which are like pow but with an
integer exponent. That exponent has type long long int in C23; it was
intmax_t in TS 18661-4, and as with other interfaces changed after
their initial appearance in the TS, I don't think we need to support
the original version of the interface. The test inputs are based on
the subset of test inputs for pow that use integer exponents that fit
in long long.
As the first such template implementation that saves and restores the
rounding mode internally (to avoid possible issues with directed
rounding and intermediate overflows or underflows in the wrong
rounding mode), support also needed to be added for using
SET_RESTORE_ROUND* in such template function implementations. This
required math-type-macros-float128.h to include <fenv_private.h>, so
it can tell whether SET_RESTORE_ROUNDF128 is defined. In turn, the
include order with <fenv_private.h> included before <math_private.h>
broke loongarch builds, showing up that
sysdeps/loongarch/math_private.h is really a fenv_private.h file
(maybe implemented internally before the consistent split of those
headers in 2018?) and needed to be renamed to fenv_private.h to avoid
errors with duplicate macro definitions if <math_private.h> is
included after <fenv_private.h>.
The underlying implementation uses __ieee754_pow functions (called
more than once in some cases, where the exponent does not fit in the
floating type). I expect a custom implementation for a given format,
that only handles integer exponents but handles larger exponents
directly, could be faster and more accurate in some cases.
I encourage searching for worst cases for ulps error for these
implementations (necessarily non-exhaustively, given the size of the
input space).
Tested for x86_64 and x86, and with build-many-glibcs.py.
Add function __inet_pton_chk which calls __chk_fail when the size of
argument dst is too small. inet_pton is redirected to __inet_pton_chk
or __inet_pton_warn when _FORTIFY_SOURCE is > 0.
Also add tests to debug/tst-fortify.c, update the abilist with
__inet_pton_chk and mention inet_pton fortification in maint.texi.
Co-authored-by: Frédéric Bérat <fberat@redhat.com>
Reviewed-by: Florian Weimer <fweimer@redhat.com>
- Create the __inet_ntop_chk routine that verifies that the builtin size
of the destination buffer is at least as big as the size given by the
user.
- Redirect calls from inet_ntop to __inet_ntop_chk or __inet_ntop_warn
- Update the abilist for this new routine
- Update the manual to mention the new fortification
Reviewed-by: Florian Weimer <fweimer@redhat.com>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the powr functions, which are like pow, but with simpler
handling of special cases (based on exp(y*log(x)), so negative x and
0^0 are domain errors, powers of -0 are always +0 or +Inf never -0 or
-Inf, and 1^+-Inf and Inf^0 are also domain errors, while NaN^0 and
1^NaN are NaN). The test inputs are taken from those for pow, with
appropriate adjustments (including removing all tests that would be
domain errors from those in auto-libm-test-in and adding some more
such tests in libm-test-powr.inc).
The underlying implementation uses __ieee754_pow functions after
dealing with all special cases that need to be handled differently.
It might be a little faster (avoiding a wrapper and redundant checks
for special cases) to have an underlying implementation built
separately for both pow and powr with compile-time conditionals for
special-case handling, but I expect the benefit of that would be
limited given that both functions will end up needing to use the same
logic for computing pow outside of special cases.
My understanding is that powr(negative, qNaN) should raise "invalid":
that the rule on "invalid" for an argument outside the domain of the
function takes precedence over a quiet NaN argument producing a quiet
NaN result with no exceptions raised (for rootn it's explicit that the
0th root of qNaN raises "invalid"). I've raised this on the WG14
reflector to confirm the intent.
Tested for x86_64 and x86, and with build-many-glibcs.py.
Linux 6.13 adds four new syscalls. Update syscall-names.list and
regenerate the arch-syscall.h headers with build-many-glibcs.py
update-syscalls.
Tested with build-many-glibcs.py.
Current Bionic has this function, with enhanced error checking
(the undefined case terminates the process).
Reviewed-by: Joseph Myers <josmyers@redhat.com>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the rsqrt functions (1/sqrt(x)). The test inputs are
taken from those for sqrt.
Tested for x86_64 and x86, and with build-many-glibcs.py.
powerpc was the only architecture with arch-specific hooks for
LD_SHOW_AUXV, and with the information moved to ld diagnostics there
is no need to keep the _dl_procinfo hook.
Checked with a build for all affected ABIs.
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
The _dl_string_platform is moved to hwcapinfo.h, since it is only used
by hwcapinfo.c and test-get_hwcap internal test.
Checked on powerpc64le-linux-gnu.
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
The ld.so diagnostics already prints AT_HWCAP values, but only in
hexadecimal. To avoid duplicating the strings, consolidate the
hwcap_names from cpu-features.h on a new file, dl-hwcap-info.h
(and it also improves the hwcap string description with more
values).
For future AT_HWCAP3/AT_HWCAP4 extensions, it is just a matter
to add them on dl-hwcap-info.c so both ld diagnostics and
tunable filtering will parse the new values.
Checked on powerpc64le-linux-gnu.
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the atan2pi functions (atan2(y,x)/pi).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the atanpi functions (atan(x)/pi).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the asinpi functions (asin(x)/pi).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the acospi functions (acos(x)/pi).
Tested for x86_64 and x86, and with build-many-glibcs.py.
Add ROP protection for the getcontext, setcontext, makecontext, swapcontext
and __sigsetjmp_symbol functions.
Reviewed-by: Peter Bergner <bergner@linux.ibm.com>
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the tanpi functions (tan(pi*x)).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the sinpi functions (sin(pi*x)).
Tested for x86_64 and x86, and with build-many-glibcs.py.
C23 adds various <math.h> function families originally defined in TS
18661-4. Add the cospi functions (cos(pi*x)).
Tested for x86_64 and x86, and with build-many-glibcs.py.
Update the inline asm syscall wrappers to match the newer register constraint
usage in INTERNAL_VSYSCALL_CALL_TYPE. Use the faster mfocrf instruction when
available, rather than the slower mfcr microcoded instruction.
Linux 6.11 has getrandom() in vDSO. It operates on a thread-local opaque
state allocated with mmap using flags specified by the vDSO.
Multiple states are allocated at once, as many as fit into a page, and
these are held in an array of available states to be doled out to each
thread upon first use, and recycled when a thread terminates. As these
states run low, more are allocated.
To make this procedure async-signal-safe, a simple guard is used in the
LSB of the opaque state address, falling back to the syscall if there's
reentrancy contention.
Also, _Fork() is handled by blocking signals on opaque state allocation
(so _Fork() always sees a consistent state even if it interrupts a
getrandom() call) and by iterating over the thread stack cache on
reclaim_stack. Each opaque state will be in the free states list
(grnd_alloc.states) or allocated to a running thread.
The cancellation is handled by always using GRND_NONBLOCK flags while
calling the vDSO, and falling back to the cancellable syscall if the
kernel returns EAGAIN (would block). Since getrandom is not defined by
POSIX and cancellation is supported as an extension, the cancellation is
handled as 'may occur' instead of 'shall occur' [1], meaning that if
vDSO does not block (the expected behavior) getrandom will not act as a
cancellation entrypoint. It avoids a pthread_testcancel call on the fast
path (different than 'shall occur' functions, like sem_wait()).
It is currently enabled for x86_64, which is available in Linux 6.11,
and aarch64, powerpc32, powerpc64, loongarch64, and s390x, which are
available in Linux 6.12.
Link: https://pubs.opengroup.org/onlinepubs/9799919799/nframe.html [1]
Co-developed-by: Jason A. Donenfeld <Jason@zx2c4.com>
Tested-by: Jason A. Donenfeld <Jason@zx2c4.com> # x86_64
Tested-by: Adhemerval Zanella <adhemerval.zanella@linaro.org> # x86_64, aarch64
Tested-by: Xi Ruoyao <xry111@xry111.site> # x86_64, aarch64, loongarch64
Tested-by: Stefan Liebler <stli@linux.ibm.com> # s390x
