Since x32 returns 32-bit long int and 64-bit long long int in the
same 64-bit register, we make the 32b-bit lround an alias of the
64-bit llround. Add -Wno-error for x32 build to silence the compiler.
On x86_64, memrchr (not a standard function) is defined as a strong
symbol, instead of a weak alias of __memrchr as on other
architectures. This results in linknamespace test failures from the
use of __memrchr from dirname. (Not a conformance issue because of
the mem* reservation, but contrary to glibc conventions.) This patch
makes x86_64 follow other architectures by defining memrchr as a weak
alias.
Tested for x86_64 (testsuite, and that disassembly of installed shared
libraries is unchanged by the patch).
[BZ #17719]
* sysdeps/x86_64/memrchr.S (memrchr): Rename to __memrchr and
define as weak alias of __memrchr.
(__memrchr): Do not define as strong alias of memrchr.
* conform/Makefile (test-xfail-XPG4/libgen.h/linknamespace):
Remove variable.
(test-xfail-UNIX98/libgen.h/linknamespace): Likewise.
(test-xfail-XOPEN2K/libgen.h/linknamespace): Likewise.
(test-xfail-XOPEN2K8/libgen.h/linknamespace): Likewise.
Use of strftime, a C90 function, ends up bringing in wcschr, which is
not a C90 function. Although not a conformance bug (C90 reserves
wcs*), this is still contrary to glibc practice of avoiding relying on
those reservations; this patch arranges for the internal uses to use
__wcschr instead, with wcschr being a weak alias. This is more
complicated than some such patches because of the various IFUNC
definitions of wcschr (which include code redefining libc_hidden_def
in a way that involves creating __GI_wcschr manually and so also needs
to create __GI___wcschr after the change of internal uses to use
__wcschr).
Tested for x86_64 and 32-bit x86 (testsuite, and that disassembly of
installed shared libraries is unchanged by the patch).
2014-12-10 Joseph Myers <joseph@codesourcery.com>
Adhemerval Zanella <azanella@linux.vnet.ibm.com>
[BZ #17634]
* wcsmbs/wcschr.c [!WCSCHR] (wcschr): Define as __wcschr.
Undefine after defining function. Define as weak alias of
__wcschr. Use libc_hidden_weak.
* include/wchar.h (__wcschr): Declare. Use libc_hidden_proto.
* sysdeps/i386/i686/multiarch/wcschr-c.c [IS_IN (libc) && SHARED]
(libc_hidden_def): Also define __GI___wcschr alias.
* sysdeps/i386/i686/multiarch/wcschr.S (wcschr): Rename to
__wcschr and define as weak alias of __wcschr.
* sysdeps/powerpc/power6/wcschr.c [!WCSCHR] (WCSCHR): Define as
__wcschr.
[!WCSCHR] (DEFAULT_WCSCHR): Define.
[DEFAULT_WCSCHR] (__wcschr): Use libc_hidden_def.
[DEFAULT_WCSCHR] (wcschr): Define as weak alias of __wcschr. Use
libc_hidden_weak. Do not use libc_hidden_def.
* sysdeps/powerpc/powerpc32/power4/multiarch/wcschr-ppc32.c
[IS_IN (libc) && SHARED] (libc_hidden_def): Also define
__GI___wcschr alias.
* sysdeps/powerpc/powerpc32/power4/multiarch/wcschr.c
[IS_IN (libc)] (wcschr): Define as macro expanding to
__redirect_wcschr.
[IS_IN (libc)] (__wcschr_ppc): Use __redirect_wcschr in typeof.
[IS_IN (libc)] (__wcschr_power6): Likewise.
[IS_IN (libc)] (__wcschr_power7): Likewise.
[IS_IN (libc)] (__libc_wcschr): New. Define with libc_ifunc
instead of wcschr.
[IS_IN (libc)] (wcschr): Undefine and define as weak alias of
__libc_wcschr.
[!IS_IN (libc)] (libc_hidden_def): Do not undefine and redefine.
* sysdeps/powerpc/powerpc64/multiarch/wcschr.c (wcschr): Rename to
__wcschr and define as weak alias of __wcschr. Use
libc_hidden_builtin_def.
* sysdeps/x86_64/wcschr.S (wcschr): Rename to __wcschr and define
as weak alias of __wcschr. Use libc_hidden_weak.
* time/alt_digit.c (_nl_get_walt_digit): Use __wcschr instead of
wcschr.
* time/era.c (_nl_init_era_entries): Likewise.
* conform/Makefile (test-xfail-ISO/time.h/linknamespace): Remove
variable.
(test-xfail-XPG3/time.h/linknamespace): Likewise.
(test-xfail-XPG4/time.h/linknamespace): Likewise.
This sets __HAVE_64B_ATOMICS if provided. It also sets
USE_ATOMIC_COMPILER_BUILTINS to true if the existing atomic ops use the
__atomic* builtins (aarch64, mips partially) or if this has been
tested (x86_64); otherwise, this is set to false so that C11 atomics will
be based on the existing atomic operations.
This patch removes a conditional on __GNUC_PREREQ (4, 6) in x86_64
code.
Tested for x86_64 that installed shared libraries are unchanged by
this patch. Committed (I think this file reasonably comes under math
maintainership).
* sysdeps/x86_64/fpu/dla.h [__FMA4__ && __GNUC_PREREQ (4, 6)]
(DLA_FMS): Make definition conditional only on [__FMA4__].
[__FMA4__ && !__GNUC_PREREQ (4, 6)] (DLA_FMS): Remove conditional
definition.
rawmemchr is not an ISO C function, but __rawmemchr is called from ISO
C functions, so rawmemchr should be a weak alias. On most
architecture it is, but x86_64 defines the function as rawmemchr with
__rawmemchr as a strong alias. This patch makes x86_64 follow the
same arrangements as other architectures.
Tested for x86_64 (testsuite, and that disassembly of installed shared
libraries is unchanged by the patch).
[BZ #17572]
* sysdeps/x86_64/rawmemchr.S (rawmemchr): Rename to __rawmemchr
and define as weak alias of __rawmemchr.
(__rawmemchr): Do not define as strong alias of rawmemchr.
Continuing the removal of the obsolete INTDEF / INTUSE mechanism, this
patch eliminates its use for _dl_init. Since _dl_init was already
declared with hidden visibility, creating a second hidden alias for it
was completely pointless, so this patch replaces all uses of
_dl_init_internal with plain _dl_init instead of using hidden_proto /
hidden_def (which are only needed when you want a hidden alias for a
non-hidden symbol; it's quite possible there are cases where they are
used but don't need to be because the symbol in question is not part
of the public ABI and is only used within a single library, so using
attributes_hidden instead would suffice).
Tested for x86_64 that installed stripped shared libraries are
unchanged by the patch.
[BZ #14132]
* elf/dl-init.c (_dl_init): Don't use INTDEF.
* sysdeps/aarch64/dl-machine.h (RTLD_START): Use _dl_init instead
of _dl_init_internal.
* sysdeps/alpha/dl-machine.h (RTLD_START): Likewise.
* sysdeps/arm/dl-machine.h (RTLD_START): Likewise.
* sysdeps/hppa/dl-machine.h (RTLD_START): Likewise.
* sysdeps/i386/dl-machine.h (RTLD_START): Likewise.
* sysdeps/ia64/dl-machine.h (RTLD_START): Likewise.
* sysdeps/m68k/dl-machine.h (RTLD_START): Likewise.
* sysdeps/microblaze/dl-machine.h (RTLD_START): Likewise.
* sysdeps/mips/dl-machine.h (RTLD_START): Likewise.
* sysdeps/powerpc/powerpc32/dl-start.S (_start): Likewise.
* sysdeps/s390/s390-32/dl-machine.h (RTLD_START): Likewise.
* sysdeps/s390/s390-64/dl-machine.h (RTLD_START): Likewise.
* sysdeps/sh/dl-machine.h (RTLD_START): Likewise.
* sysdeps/sparc/sparc32/dl-machine.h (RTLD_START): Likewise.
* sysdeps/sparc/sparc64/dl-machine.h (RTLD_START): Likewise.
* sysdeps/tile/dl-start.S (_start): Likewise.
* sysdeps/x86_64/dl-machine.h (RTLD_START): Likewise.
* sysdeps/x86_64/x32/dl-machine.h (RTLD_START): Likewise.
The compiler doesn't know that the cpuid asm statement in intel_check_word
will trash RBX. We are lucky that it doesn't cause any problems since
RBX is also used by compiler for other purposes so that RBX is saved and
restored. This patch replaces it with __cpuid_count.
[BZ #17259]
* sysdeps/x86_64/cacheinfo.c (intel_check_word): Replace cpuid
asm statement with __cpuid_count.
In this patch we take advantage of HSW memory bandwidth, manage to
reduce miss branch prediction by avoiding using branch instructions and
force destination to be aligned with avx instruction.
The CPU2006 403.gcc benchmark indicates this patch improves performance
from 2% to 10%.
Various architectures have files such as sysdeps/<arch>/shlib-versions
whose contents are in fact entirely Linux-specific, relating only to
the symbol / shared library versions for the port to Linux on that
architecture, when any future port to a different OS on that
architecture would use the symbol version of the glibc release it goes
in, as standard for new ports.
This patch moves such files under sysdeps/unix/sysv/linux/, merging in
the contents of sysdeps/<arch>/nptl/shlib-versions in the process.
The only bits not moved are those relating to libgcc_s versions, which
don't appear OS-specific in the same way that glibc's symbol versions
so. It deliberately does not change the regular expressions given for
matching configurations in each file; some match only Linux although
not Linux-specific, or match other OSes although Linux-specific. It
is with a view to at least the following further cleanups:
* Move architecture-specific content from the toplevel shlib-versions
and nptl/shlib-versions into sysdeps shlib-versions files, so
eliminating another difference between ex-ports and non-ex-ports
architectures.
* Likewise, for OS-specific content in shlib-versions files.
* At that point, the first field in shlib-versions files (the regular
expression matching a configuration triplet) should be redundant, so
eliminate that field and leave shlib-versions selection working
purely on a sysdeps basis (with limited use of %ifdef in
shlib-versions files when needed) rather than having its own
separate mechanism to select what configuration information is
relevant.
* Move the build of gnu/lib-names.h to a similar mechanism to that
used for gnu/stubs.h (each library build installing a version of the
header specifically for that build), so we can eliminate the
duplication of soname information in the makefiles and get it purely
from shlib-versions files again.
There may be other cleanups possible as well (in particular, I'm not
sure that all cases where the same "Earliest symbol set" information
is repeated for many different libraries actually should need to
repeat it rather than specifying it just once for DEFAULT for the
given configuration, and separately specifying any non-default choices
of soname).
Tested x86_64 that the installed shared libraries are unchanged by
this patch.
* sysdeps/aarch64/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/aarch64/shlib-versions: ... here.
* sysdeps/alpha/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/alpha/shlib-versions: ... here.
* sysdeps/arm/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/arm/shlib-versions: ... here.
* sysdeps/hppa/shlib-versions: Move all contents except for
libgcc_s entry to ...
* sysdeps/unix/sysv/linux/hppa/shlib-versions: ... here. Merge in
entry from ...
* sysdeps/hppa/nptl/shlib-versions: ... here. Remove file.
* sysdeps/ia64/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/ia64/shlib-versions: ... here. Merge in
entry from ...
* sysdeps/ia64/nptl/shlib-versions: ... here. Remove file.
* sysdeps/m68k/coldfire/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/m68k/coldfire/shlib-versions: ... here.
* sysdeps/microblaze/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/microblaze/shlib-versions: ... here.
* sysdeps/mips/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/mips/shlib-versions: ... here. Merge in
entry from ...
* sysdeps/mips/nptl/shlib-versions: ... here. Remove file.
* sysdeps/tile/shlib-versions: Move to ...
* sysdeps/unix/sysv/linux/tile/shlib-versions: ... here.
* sysdeps/unix/sysv/linux/x86_64/64/shlib-versions: Merge in entry
from ...
* sysdeps/x86_64/64/shlib-versions: ... here. Remove file.
* sysdeps/unix/sysv/linux/x86_64/x32/shlib-versions: Merge in
entry from ...
* sysdeps/x86_64/x32/shlib-versions: ... here. Remove file.
* config.h.in (HAVE_AVX2_SUPPORT): New #undef.
* sysdeps/i386/configure.ac: Set HAVE_AVX2_SUPPORT and
config-cflags-avx2.
* sysdeps/x86_64/configure.ac: Likewise.
* sysdeps/i386/configure: Regenerated.
* sysdeps/x86_64/configure: Likewise.
* sysdeps/x86_64/multiarch/Makefile (sysdep_routines): Add
memset-avx2 only if config-cflags-avx2 is yes.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list):
Tests for memset_chk and memset only if HAVE_AVX2_SUPPORT is
defined.
* sysdeps/x86_64/multiarch/memset.S: Define multiple versions
only if HAVE_AVX2_SUPPORT is defined.
* sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
The definition of SHARED is tested with #ifdef pretty much everywhere
apart from these few places. The tlsdesc.c code seems to be copy and
pasted to a few architectures and there is one instance in the hppa
startup code.
ChangeLog:
2014-07-09 Will Newton <will.newton@linaro.org>
* sysdeps/aarch64/tlsdesc.c (_dl_unmap): Test SHARED with #ifdef.
* sysdeps/arm/tlsdesc.c (_dl_unmap): Likewise.
* sysdeps/i386/tlsdesc.c (_dl_unmap): Likewise.
* sysdeps/x86_64/tlsdesc.c (_dl_unmap): Likewise.
* sysdeps/hppa/start.S (_start): Likewise.
shlib-versions files can contain ABI lines that map triplets to a
canonical ABI name. This name was once used for various purposes
where test baseline files for different ABIs went in a single
directory; now these purposes use sysdeps files, generation of headers
which have per-ABI variants uses abi-variants and related Makefile
variables and the shlib-versions ABI names are unused. This patch
duly removes those lines and associated build system support for them.
Tested for x86_64 (both a full testsuite run and confirming the
installed shared libraries are unchanged by the patch).
* Makeconfig ($(common-objpfx)soversions.mk): Do not generate
abi-name definition.
* scripts/soversions.awk: Do not handle or generate ABI lines.
* shlib-versions: Remove ABI entries.
* sysdeps/powerpc/nofpu/shlib-versions: Remove file.
* sysdeps/x86_64/x32/shlib-versions: Remove ABI entry.
This patch fixes bugs 16561 and 16562, bad results of yn in overflow
cases in non-default rounding modes, both because an intermediate
overflow in the recurrence does not get detected if the result is not
an infinity and because an overflowing result may occur in the wrong
sign. The fix is to set FE_TONEAREST mode internally for the parts of
the function where such overflows can occur (which includes the call
to y1 - where yn is used to compute a Bessel function of order -1,
negating the result of y1 isn't correct for overflowing results in
directed rounding modes) and then compute an overflowing value in the
original rounding mode if the to-nearest result was an infinity.
Tested x86_64 and x86 and ulps updated accordingly. Also tested for
mips64 and powerpc32 to test the ldbl-128 and ldbl-128ibm changes.
(The tests for these bugs were added in my previous y1 patch, so the
only thing this patch has to do with the testsuite is enable yn
testing in all rounding modes.)
[BZ #16561]
[BZ #16562]
* sysdeps/ieee754/dbl-64/e_jn.c: Include <float.h>.
(__ieee754_yn): Set FE_TONEAREST mode internally and then
recompute overflowing results in original rounding mode.
* sysdeps/ieee754/flt-32/e_jnf.c: Include <float.h>.
(__ieee754_ynf): Set FE_TONEAREST mode internally and then
recompute overflowing results in original rounding mode.
* sysdeps/ieee754/ldbl-128/e_jnl.c: Include <float.h>.
(__ieee754_ynl): Set FE_TONEAREST mode internally and then
recompute overflowing results in original rounding mode.
* sysdeps/ieee754/ldbl-128ibm/e_jnl.c: Include <float.h>.
(__ieee754_ynl): Set FE_TONEAREST mode internally and then
recompute overflowing results in original rounding mode.
* sysdeps/ieee754/ldbl-96/e_jnl.c: Include <float.h>.
(__ieee754_ynl): Set FE_TONEAREST mode internally and then
recompute overflowing results in original rounding mode.
* sysdeps/i386/fpu/fenv_private.h [!__SSE2_MATH__]
(libc_feholdsetround_ctx): New macro.
* math/libm-test.inc (yn_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps : Likewise.
This patch removes configure tests for assembler CFI support (and
thereby eliminates an architecture-specific case in the main
configure.ac), instead assuming that support is present
unconditionally.
The main test was added in 2003 around the time CFI support was added
to the assembler. cfi_personality and cfi_lsda support were added to
the assembler in 2006. cfi_sections support was added in 2009, a few
weeks before binutils 2.20 was released; it's in 2.20, the minimum
supported version, so even that configure test is obsolete.
Tested x86_64 that the installed shared libraries are unchanged by
this patch.
* configure.ac (libc_cv_asm_cfi_directives): Remove configure
test.
* configure: Regenerated.
* config.h.in (HAVE_ASM_CFI_DIRECTIVES): Remove macro undefine.
* sysdeps/arm/configure.ac (libc_cv_asm_cfi_directive_sections):
Remove configure test.
* sysdeps/arm/configure: Regenerated.
* sysdeps/nptl/configure.ac: Do not check
libc_cv_asm_cfi_directives.
* sysdeps/nptl/configure: Regenerated.
* sysdeps/x86_64/nptl/configure.ac: Remove file.
* sysdeps/x86_64/nptl/configure: Remove generated file.
* b/sysdeps/generic/sysdep.h [HAVE_ASM_CFI_DIRECTIVES]: Make code
unconditional.
[!HAVE_ASM_CFI_DIRECTIVES]: Remove conditional code.
This patch defines ELF_MACHINE_NO_RELA on all architectures. Tested
only on x86_64 to verify that the sources before and after are
identical except for two instructions that pass the current line
number in dl-machine.h to assert_fail.
This patch fixes spurious underflows from exp10 for arguments near 0
(part of bug 16560; that bug also includes spurious underflows from
exp2, which are not fixed by this patch). The problem is underflows
in the internal computation converting the exp10 argument to arguments
for exp (with extra precision), and the fix is simply to return 1
early for arguments near enough to 0 (just as arguments with large
enough magnitude have their own overflow / underflow logic at the
start of the function).
Tested x86_64 and x86 and ulps updated accordingly; also tested for
powerpc32 and mips64 to validate the ldbl-128ibm and ldbl-128 changes.
[BZ #16560]
* sysdeps/ieee754/dbl-64/e_exp10.c (__ieee754_exp10): Return 1 for
arguments close to 0.
* sysdeps/ieee754/ldbl-128/e_exp10l.c (__ieee754_exp10l):
Likewise.
* sysdeps/ieee754/ldbl-128ibm/e_exp10l.c (__ieee754_exp10l):
Likewise.
* math/auto-libm-test-in: Add more tests of exp10.
* math/auto-libm-test-out: Regenerated.
* sysdeps/x86_64/fpu/libm-test-ulps: Update.
This patch fixes bug 16539, spurious underflow exceptions from x86 /
x86-64 expm1l. The problem is that the computation of a base-2
exponent with extra precision involves spurious underflows for
arguments that are small but not subnormal, so a check is added to
just return the argument in those cases. (If the argument *is*
subnormal, underflowing is correct and the existing code will always
underflow, so it suffices to keep using the existing code in that
case; some expm1 implementations have a bug (bug 16353) with missing
underflow exceptions, but I don't think there's such a bug in this
particular version.)
Tested x86_64 and x86; no ulps updates needed.
(auto-libm-test-out diffs omitted below.)
[BZ #16539]
* sysdeps/i386/fpu/e_expl.S (IEEE754_EXPL) [USE_AS_EXPM1L]: Just
return the argument for normal arguments with exponent below -64.
* sysdeps/x86_64/fpu/e_expl.S (IEEE754_EXPL) [USE_AS_EXPM1L]:
Likewise.
* math/auto-libm-test-in: Add another test of expm1.
* math/auto-libm-test-out: Regenerated.
This patch enables testing of cpow in all rounding modes using
ALL_RM_TEST. There were two reasons this was previously deferred:
* MPC has complicated rounding-mode-dependent rules for the signs of
exact zero real or imaginary parts in the result of mpc_pow. Annex
G does not impose any such requirements and I don't think glibc
should try to implement any particular logic here. This patch adds
support for gen-auto-libm-tests passing the IGNORE_ZERO_INF_SIGN
flag to libm-test.inc.
* Error accumulations in some tests in non-default rounding modes
exceed the maximum error permitted in libm-test.inc. This patch
marks the problem tests with xfail-rounding. (It might be possible
to reduce the accumulations a bit by using round-to-nearest when
cpow calls clog, but I don't think there's much point; the
implementation approach for cpow is fundamentally deficient, as
discussed in the existing bug for cpow inaccuracy which can
reasonably be considered to cover these less-inaccurate cases as
well. It's possible that the test "cpow 2 0 10 0" will also need
xfail-rounding on some platforms.)
Tested x86_64 and x86 and ulps updated accordingly.
* math/gen-auto-libm-tests.c: Document use of
ignore-zero-inf-sign.
(input_flag_type): Add value flag_ignore_zero_inf_sign.
(input_flags): Add ignore-zero-inf-sign.
(output_for_one_input_case): Handle flag_ignore_zero_inf_sign.
* math/gen-libm-test.pl (generate_testfile): Handle
ignore-zero-inf-sign.
* math/auto-libm-test-in: Mark some cpow tests with
ignore-zero-inf-sign and some with xfail-rounding.
* math/auto-libm-test-out: Regenerated.
* math/libm-test.inc (cpow_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
This patch fixes bug 16315, bad pow handling of overflow/underflow in
non-default rounding modes. Tests of pow are duly converted to
ALL_RM_TEST to run all tests in all rounding modes.
There are two main issues here. First, various implementations
compute a negative result by negating a positive result, but this
yields inappropriate overflow / underflow values for directed
rounding, so either overflow / underflow results need recomputing in
the correct sign, or the relevant overflowing / underflowing operation
needs to be made to have a result of the correct sign. Second, the
dbl-64 implementation sets FE_TONEAREST internally; in the overflow /
underflow case, the result needs recomputing in the original rounding
mode.
Tested x86_64 and x86 and ulps updated accordingly.
[BZ #16315]
* sysdeps/i386/fpu/e_pow.S (__ieee754_pow): Ensure possibly
overflowing or underflowing operations take place with sign of
result.
* sysdeps/i386/fpu/e_powf.S (__ieee754_powf): Likewise.
* sysdeps/i386/fpu/e_powl.S (__ieee754_powl): Likewise.
* sysdeps/ieee754/dbl-64/e_pow.c: Include <math.h>.
(__ieee754_pow): Recompute overflowing and underflowing results in
original rounding mode.
* sysdeps/x86/fpu/powl_helper.c: Include <stdbool.h>.
(__powl_helper): Allow negative argument X and scale negated value
as needed. Avoid passing value outside [-1, 1] to f2xm1.
* sysdeps/x86_64/fpu/e_powl.S (__ieee754_powl): Ensure possibly
overflowing or underflowing operations take place with sign of
result.
* sysdeps/x86_64/fpu/multiarch/e_pow.c [HAVE_FMA4_SUPPORT]:
Include <math.h>.
* math/auto-libm-test-in: Add more tests of pow.
* math/auto-libm-test-out: Regenerated.
* math/libm-test.inc (pow_test): Use ALL_RM_TEST.
(pow_tonearest_test_data): Remove.
(pow_test_tonearest): Likewise.
(pow_towardzero_test_data): Likewise.
(pow_test_towardzero): Likewise.
(pow_downward_test_data): Likewise.
(pow_test_downward): Likewise.
(pow_upward_test_data): Likewise.
(pow_test_upward): Likewise.
(main): Don't call removed functions.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
This patch makes files using __ASSUME_* macros include
<kernel-features.h> explicitly, rather than relying on some other
header (such as tls.h, lowlevellock.h or pthreadP.h) to include it
implicitly. (I omitted cases where I've already posted or am testing
the patch that stops the file from needing __ASSUME_* at all.) This
accords with the general principle of making source files include the
headers for anything they use, and also helps make it safe to remove
<kernel-features.h> includes from any file that doesn't use
__ASSUME_* (some of those may be stray includes left behind after
increasing the minimum kernel version, others may never have been
needed or may have become obsolete after some other change).
Tested x86_64 that the disassembly of installed shared libraries is
unchanged by this patch.
* nptl/pthread_cond_wait.c: Include <kernel-features.h>.
* nptl/pthread_rwlock_timedrdlock.c: Likewise.
* nptl/pthread_rwlock_timedwrlock.c: Likewise.
* nptl/sysdeps/unix/sysv/linux/lowlevelrobustlock.c: Likewise.
* nscd/nscd.c: Likewise.
* sysdeps/i386/nptl/tcb-offsets.sym: Likewise.
* sysdeps/powerpc/nptl/tcb-offsets.sym: Likewise.
* sysdeps/sh/nptl/tcb-offsets.sym: Likewise.
* sysdeps/x86_64/nptl/tcb-offsets.sym: Likewise.
This patch adds ifunc tests for x86_64 memset_chk and memset. It also
defines HAS_AVX2 with AVX2_Usable since AVX2 may not be usable even if
processor has AVX2.
* sysdeps/x86_64/multiarch/ifunc-impl-list.c (__libc_ifunc_impl_list):
Add tests for memset_chk and memset.
* sysdeps/x86_64/multiarch/init-arch.h (HAS_AVX2): Defined
with AVX2_Usable.
In this patch we take advantage of HSW memory bandwidth, manage to
reduce miss branch prediction by avoiding using branch instructions and
force destination to be aligned with avx & avx2 instruction.
The CPU2006 403.gcc benchmark indicates this patch improves performance
from 26% to 59%.
* sysdeps/x86_64/multiarch/Makefile: Add memset-avx2.
* sysdeps/x86_64/multiarch/memset-avx2.S: New file.
* sysdeps/x86_64/multiarch/memset.S: Likewise.
* sysdeps/x86_64/multiarch/memset_chk.S: Likewise.
* sysdeps/x86_64/multiarch/rtld-memset.S: Likewise.
This patch fixes __ieee754_logl (-LDBL_MAX) on x86_64 and x86 not to
subtract 1 from its argument and so cause spurious overflow in
FE_DOWNWARD mode. (For any argument strictly less than -1, it doesn't
matter whether or not 1 is subtracted before computing log1p, as long
as the result doesn't overflow to -Inf.)
Tested x86_64 and x86. (This particular case lacks test coverage,
since the testsuite doesn't cover -lieee, but it will be covered by
tests after the following patch to test pow in all rounding modes,
which was the context in which this bug was found.)
[BZ #17022]
* sysdeps/i386/fpu/e_logl.S (__ieee754_logl): Do not subtract 1
from arguments -2 or below.
* sysdeps/i386/i686/fpu/e_logl.S (__ieee754_logl): Likewise.
* sysdeps/x86_64/fpu/e_logl.S (__ieee754_logl): Likewise.
As with other issues of this kind, bug 17042 is log2 (1) wrongly
returning -0 instead of +0 in round-downward mode because of
implementations effectively in terms of log1p (x - 1). This patch
fixes the issue in the same way used for log and log10.
Tested x86_64 and x86 and ulps updated accordingly. Also tested for
mips64 to confirm a fix was needed for ldbl-128 and to validate that
fix (also applied to ldbl-128ibm since that version of log2l is
essentially the same as the ldbl-128 one).
[BZ #17042]
* sysdeps/i386/fpu/e_log2.S (__ieee754_log2): Take absolete value
when x - 1 is zero.
* sysdeps/i386/fpu/e_log2f.S (__ieee754_log2f): Likewise.
* sysdeps/i386/fpu/e_log2l.S (__ieee754_log2l): Likewise.
* sysdeps/ieee754/ldbl-128/e_log2l.c (__ieee754_log2l): Return
0.0L for an argument of 1.0L.
* sysdeps/ieee754/ldbl-128ibm/e_log2l.c (__ieee754_log2l):
Likewise.
* sysdeps/x86_64/fpu/e_log2l.S (__ieee754_log2l): Take absolute
value when x - 1 is zero.
* math/libm-test.inc (log2_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
As with various other issues of this kind, bug 16977 is log10 (1)
wrongly returning -0 rather than +0 in round-downward mode because of
an implementation effectively in terms of log1p (x - 1). This patch
fixes the issue in the same way used for log.
Tested x86_64 and x86 and ulps updated accordingly. Also tested for
mips64 to confirm a fix was needed for ldbl-128 and to validate that
fix (also applied to ldbl-128ibm since that version of logl is
essentially the same as the ldbl-128 one).
[BZ #16977]
* sysdeps/i386/fpu/e_log10.S (__ieee754_log10): Take absolute
value when x - 1 is zero.
* sysdeps/i386/fpu/e_log10f.S (__ieee754_log10f): Likewise.
* sysdeps/i386/fpu/e_log10l.S (__ieee754_log10l): Likewise.
* sysdeps/ieee754/ldbl-128/e_log10l.c (__ieee754_log10l): Return
0.0L for an argument of 1.0L.
* sysdeps/ieee754/ldbl-128ibm/e_log10l.c (__ieee754_log10l):
Likewise.
* sysdeps/x86_64/fpu/e_log10l.S (__ieee754_log10l): Take absolute
value when x - 1 is zero.
* math/libm-test.inc (log10_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
Bug 16564 is spurious overflow of log1pl (LDBL_MAX) in FE_UPWARD mode,
resulting from log1pl adding 1 to its argument (for arguments not
close to 0), which overflows in that mode. This patch fixes this by
avoiding adding 1 to large arguments (precisely what counts as large
depends on the floating-point format).
Tested x86_64 and x86, and spot-checked log1pl tests on mips64 and
powerpc64.
[BZ #16564]
* sysdeps/i386/fpu/s_log1pl.S (__log1pl): Do not add 1 to positive
arguments with exponent 65 or above.
* sysdeps/ieee754/ldbl-128/s_log1pl.c (__log1pl): Do not add 1 to
arguments 0x1p113L or above.
* sysdeps/ieee754/ldbl-128ibm/s_log1pl.c (__log1pl): Do not add 1
to arguments 0x1p107L or above.
* sysdeps/x86_64/fpu/s_log1pl.S (__log1pl): Do not add 1 to
positive arguments with exponent 65 or above.
* math/auto-libm-test-in: Add more tests of log1p.
* math/auto-libm-test-out: Regenerated.
According to C99/C11 Annex G, cacos applied to a value with real part
+Inf and finite imaginary part should produce a result with real part
+0. glibc wrongly produces a result with real part -0 in FE_DOWNWARD
mode. This patch fixes this by checking for zero results in the
relevant case of non-finite arguments (where there should never be a
result with -0 real part), and converts the tests of cacos to
ALL_RM_TEST.
Tested x86_64 and x86 and ulps updated accordingly.
[BZ #16928]
* math/s_cacos.c (__cacos): Ensure zero real part of result from
non-finite arguments is +0.
* math/s_cacosf.c (__cacosf): Likewise.
* math/s_cacosl.c (__cacosl): Likewise.
* math/libm-test.inc (cacos_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
According to C99 and C11 Annex F, acosh (1) should be +0 in all
rounding modes. However, some implementations in glibc wrongly return
-0 in round-downward mode (which is what you get if you end up
computing log1p (-0), via 1 - 1 being -0 in round-downward mode).
This patch fixes the problem implementations, by correcting the test
for an exact 1 value in the ldbl-96 implementation to allow for the
explicit high bit of the mantissa, and by inserting fabs instructions
in the i386 implementations; tests of acosh are duly converted to
ALL_RM_TEST. I believe all the other sysdeps/ieee754 implementations
are already OK (I haven't checked the ia64 versions, but if buggy then
that will be obvious from the results of test runs after this patch is
in).
Tested x86_64 and x86 and ulps updated accordingly.
[BZ #16927]
* sysdeps/i386/fpu/e_acosh.S (__ieee754_acosh): Use fabs on x-1
value.
* sysdeps/i386/fpu/e_acoshf.S (__ieee754_acoshf): Likewise.
* sysdeps/i386/fpu/e_acoshl.S (__ieee754_acoshl): Likewise.
* sysdeps/ieee754/ldbl-96/e_acoshl.c (__ieee754_acoshl): Correct
for explicit high bit of mantissa when testing for argument equal
to 1.
* math/libm-test.inc (acosh_test): Use ALL_RM_TEST.
* sysdeps/i386/fpu/libm-test-ulps: Update.
* sysdeps/x86_64/fpu/libm-test-ulps: Likewise.
Define FEATURE_INDEX_1 and FEATURE_INDEX_MAX as macros
for use by both assembly and C code. This fixes the
-Wundef error for cases where FEATURE_INDEX_1 was not
defined but used the correct value of 0 for an undefined
macro.
