Stefan Liebler [Thu, 28 Apr 2016 08:30:09 +0000 (10:30 +0200)]
S390: Fix "backtrace() returns infinitely deep stack frames with makecontext()" [BZ #18508].
On s390/s390x backtrace(buffer, size) returns the series of called functions until
"makecontext_ret" and additional entries (up to "size") with "makecontext_ret".
GDB-backtrace is also warning:
"Backtrace stopped: previous frame identical to this frame (corrupt stack?)"
To reproduce this scenario you have to setup a new context with makecontext()
and activate it with setcontext(). See e.g. cf() function in testcase stdlib/tst-makecontext.c.
Or see bug in libgo "Bug 66303 - runtime.Caller() returns infinitely deep stack frames
on s390x " (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66303).
This patch omits the cfi_startproc/cfi_endproc directives in ENTRY/END macro of
__makecontext_ret. Thus no frame information is generated in .eh_frame and backtrace
stops after __makecontext_ret. There is also no .eh_frame info for _start or
thread_start functions.
ChangeLog:
[BZ #18508]
* stdlib/Makefile ($(objpfx)tst-makecontext3):
Depend on $(libdl).
* stdlib/tst-makecontext.c (cf): Test if _Unwind_Backtrace
is not called infinitely times.
(backtrace_helper): New function.
(trace_arg): New struct.
(st1): Enlarge stack size.
* sysdeps/unix/sysv/linux/s390/s390-32/__makecontext_ret.S:
(__makecontext_ret): Omit cfi_startproc and cfi_endproc.
* sysdeps/unix/sysv/linux/s390/s390-64/__makecontext_ret.S:
Likewise.
Stefan Liebler [Mon, 4 Apr 2016 11:19:57 +0000 (13:19 +0200)]
S390: Extend structs La_s390_regs / La_s390_retval with vector-registers.
Starting with z13, vector registers can also occur as argument registers.
Thus the passed input/output register structs for
la_s390_[32|64]_gnu_plt[enter|exit] functions should reflect those new
registers. This patch extends these structs La_s390_regs and La_s390_retval
and adjusts _dl_runtime_profile() to handle those fields in case of
running on a z13 machine.
Stefan Liebler [Mon, 4 Apr 2016 11:19:57 +0000 (13:19 +0200)]
S390: Save and restore fprs/vrs while resolving symbols.
On s390, no fpr/vrs were saved while resolving a symbol
via _dl_runtime_resolve/_dl_runtime_profile.
According to the abi, the fpr-arguments are defined as call clobbered.
In leaf-functions, gcc 4.9 and newer can use fprs for saving/restoring gprs
instead of saving them to the stack.
If gcc do this in one of the resolver-functions, then the floating point
arguments of a library-function are invalid for the first library-function-call.
Thus, this patch saves/restores the fprs around the resolving code.
The same could occur for vector registers. Furthermore an ifunc-resolver
could also clobber the vector/floating point argument registers.
Thus this patch provides the further variants _dl_runtime_resolve_vx/
_dl_runtime_profile_vx, which are used if the kernel claims, that
we run on a machine with vector registers.
Furthermore, if _dl_runtime_profile calls _dl_call_pltexit,
the pointers to inregs-/outregs-structs were setup invalid.
Now they point to the correct location in the stack-frame.
Before branching back to the caller, the return values are now
restored instead of containing the return values of the
_dl_call_pltexit() call.
On s390-32, an endless loop occurs if _dl_call_pltexit() should be called.
Now, this code-path branches to this function instead of just after the
preceding basr-instruction.
ChangeLog:
* sysdeps/s390/s390-32/dl-trampoline.S: Include dl-trampoline.h twice
to create a non-vector/vector version for _dl_runtime_resolve and
_dl_runtime_profile. Move implementation to ...
* sysdeps/s390/s390-32/dl-trampoline.h: ... here.
(_dl_runtime_resolve) Save and restore fpr/vrs.
(_dl_runtime_profile) Save and restore vrs and fix some issues
if _dl_call_pltexit is called.
* sysdeps/s390/s390-32/dl-machine.h (elf_machine_runtime_setup):
Choose the correct resolver function if running on a machine with vx.
* sysdeps/s390/s390-64/dl-trampoline.S: Include dl-trampoline.h twice
to create a non-vector/vector version for _dl_runtime_resolve and
_dl_runtime_profile. Move implementation to ...
* sysdeps/s390/s390-64/dl-trampoline.h: ... here.
(_dl_runtime_resolve) Save and restore fpr/vrs.
(_dl_runtime_profile) Save and restore vrs and fix some issues
* sysdeps/s390/s390-64/dl-machine.h: (elf_machine_runtime_setup):
Choose the correct resolver function if running on a machine with vx.
Stefan Liebler [Mon, 4 Apr 2016 11:19:57 +0000 (13:19 +0200)]
S390: configure check for vector instruction support in assembler.
The S390 specific test checks if the assembler has support for the new z13
vector instructions by compiling a vector instruction. The .machine and
.machinemode directives are needed to compile the vector instruction without
-march=z13 option on 31/64 bit.
On success the macro HAVE_S390_VX_ASM_SUPPORT is defined. This macro is used
to determine if the optimized functions can be build without compile errors.
If the used assembler lacks vector support, then a warning is dumped while
configuring and only the common code functions are build.
The z13 instruction support was introduced in
"[Committed] S/390: Add support for IBM z13."
(https://sourceware.org/ml/binutils/2015-01/msg00197.html)
ChangeLog:
* config.h.in (HAVE_S390_VX_ASM_SUPPORT): New macro undefine.
* sysdeps/s390/configure.ac: Add test for S390 vector instruction
assembler support.
* sysdeps/s390/configure: Regenerated.
Stefan Liebler [Mon, 4 Apr 2016 11:19:57 +0000 (13:19 +0200)]
S390: Add new s390 platform.
The new IBM z13 is added to platform string array.
The macro _DL_PLATFORMS_COUNT is incremented to 8,
because it was not incremented by commit
"S/390: Sync AUXV capabilities and archs with kernel".
Stefan Liebler [Mon, 4 Apr 2016 11:19:57 +0000 (13:19 +0200)]
S390: Add hwcaps value for vector facility.
The HWCAP_S390_VX flag in hwcap field of auxiliary vector indicates
if the vector facility is available and the kernel is aware of it.
This can be tested with LD_SHOW_AUXV=1 <prog>.
Currently it does not show te, because it was not incremented
by commit "S/390: Add hwcap value for transactional execution.".
Thus _DL_HWCAP_COUNT is incremented by two.
Hongjiu Zhang [Mon, 7 Mar 2016 01:18:21 +0000 (20:18 -0500)]
sln: use stat64
When using sln on some filesystems which return 64-bit inodes,
the stat call might fail during install like so:
.../elf/sln .../elf/symlink.list
/lib32/libc.so.6: invalid destination: Value too large for defined data type
/lib32/ld-linux.so.2: invalid destination: Value too large for defined data type
Makefile:104: recipe for target 'install-symbolic-link' failed
Switch to using stat64 all the time to avoid this.
Stefan Liebler [Thu, 3 Mar 2016 07:22:43 +0000 (08:22 +0100)]
S390: Do not use direct socket syscalls if build on kernels >= 4.3. [BZ #19682]
Beginning with Linux 4.3, the kernel headers contain direct
system call numbers __NR_socket etc. on s390x. On older kernels,
the socket-multiplexer syscall __NR_socketcall was used.
To enable these new syscalls, the patch
"S390: Call direct system calls for socket operations."
(https://sourceware.org/git/?p=glibc.git;a=commit;h=016495b818cb61df7d0d10e6db54074271b3e3a5)
was applied upstream.
If glibc 2.23 is configured with --enable-kernel=4.3 and newer,
the direct socket syscalls are used.
For older kernels, the socket-multiplexer syscall is used instead.
In glibc 2.22 and earlier, this patch is not applied.
If you build glibc on a kernel < 4.3, the socket-multiplexer
syscall is used. But if you build glibc on kernel >= 4.3, the
direct socket-syscalls are used. If you install this glibc on a
kernel < 4.3, all socket operations will fail.
See "Bug 19682 - s390x: Incorrect syscall definitions cause
breakage with Linux 4.3 headers"
(https://sourceware.org/bugzilla/show_bug.cgi?id=19682)
The configure switch --enable-kernel does not influence this
behaviour on older glibc-releases.
The solution is to remove the direct socket-syscalls in
sysdeps/unix/sysv/linux/s390/s390-64/syscalls.list
(this patch) on older glibc-releases as it was done by the
upstream patch, too. These entries were never used on s390x,
but the c-files in sysdeps/unix/sysv/linux/.
After this removal, the behaviour of the socket functions are
not changed compared to the original glibc release version
and the socket-multiplexer-syscall is always used.
* A stack-based buffer overflow was found in libresolv when invoked from
libnss_dns, allowing specially crafted DNS responses to seize control
of execution flow in the DNS client. The buffer overflow occurs in
the functions send_dg (send datagram) and send_vc (send TCP) for the
NSS module libnss_dns.so.2 when calling getaddrinfo with AF_UNSPEC
family. The use of AF_UNSPEC triggers the low-level resolver code to
send out two parallel queries for A and AAAA. A mismanagement of the
buffers used for those queries could result in the response of a query
writing beyond the alloca allocated buffer created by
_nss_dns_gethostbyname4_r. Buffer management is simplified to remove
the overflow. Thanks to the Google Security Team and Red Hat for
reporting the security impact of this issue, and Robert Holiday of
Ciena for reporting the related bug 18665. (CVE-2015-7547)
See also:
https://sourceware.org/ml/libc-alpha/2016-02/msg00416.html
https://sourceware.org/ml/libc-alpha/2016-02/msg00418.html
As in bugzilla entry there is overflow in hsearch when looking for prime
number as SIZE_MAX - 1 is divisible by 5. We fix that by rejecting large
inputs before looking for prime.
Mike Frysinger [Sat, 30 May 2015 18:55:16 +0000 (14:55 -0400)]
nscd: drop selinux/flask.h include
Building nscd w/selinux enabled yields a warning which yields an error:
In file included from selinux.c:32:0:
/usr/include/selinux/flask.h:5:2: error:
#warning "Please remove any #include's of this header in your source code."
I've done just that and it builds cleanly with libselinux-2.4.
The lookup function implementation in
nss/nss_files/files-XXX.c:DB_LOOKUP has code to prevent that. It is
supposed skip closing the input file if it was already open.
/* Reset file pointer to beginning or open file. */ \
status = internal_setent (keep_stream); \
\
if (status == NSS_STATUS_SUCCESS) \
{ \
/* Tell getent function that we have repositioned the file pointer. */ \
last_use = getby; \
\
while ((status = internal_getent (result, buffer, buflen, errnop \
H_ERRNO_ARG EXTRA_ARGS_VALUE)) \
== NSS_STATUS_SUCCESS) \
{ break_if_match } \
\
if (! keep_stream) \
internal_endent (); \
} \
keep_stream is initialized from the stayopen flag in internal_setent.
internal_setent is called from the set*ent implementation as:
status = internal_setent (stayopen);
However, for non-host database, this flag is always 0, per the
STAYOPEN magic in nss/getXXent_r.c.
Thus, the fix is this:
- status = internal_setent (stayopen);
+ status = internal_setent (1);
This is not a behavioral change even for the hosts database (where the
application can specify the stayopen flag) because with a call to
sethostent(0), the file handle is still not closed in the
implementation of gethostent.
The fix for BZ #17273 introduced a single byte of memory corruption when
the line is entirely blank. It would walk back past the start of the
buffer if the heap happened to be 0x20 or 0x09 and then write a NUL byte.
buffer = '\n';
end_ptr = buffer;
while (end_ptr[-1] == ' ' || end_ptr[-1] == '\t')
end_ptr--;
*end_ptr = '\0';
Fix that and rework the tests. Adding the testcase for BZ #17273 to the
existing \040 parser does not really make sense as it's unrelated, and
leads to confusing behavior: it implicitly relies on the new entry being
longer than the previous entry (since it just rewinds the FILE*). Split
it out into its own dedicated testcase instead.
Way back in 2005 the atomic_exchange_and_add function was cleaned up to
avoid the explicit size checking and instead let gcc handle things itself.
Unfortunately that change ended up leaving beyond a cast to int, even when
the incoming value was a long. This has flown under the radar for a long
time due to the function not being heavily used in the tree (especially as
a full 64bit field), but a recent change to semaphores made some nptl tests
fail reliably. This is due to the code packing two 32bit values into one
64bit variable (where the high 32bits contained the number of waiters), and
then the whole variable being atomically updated between threads. On ia64,
that meant we never atomically updated the count, so sometimes the sem_post
would not wake up the waiters.
Mike Frysinger [Mon, 20 Jul 2015 11:29:15 +0000 (07:29 -0400)]
sparc: fix sigaction for 32bit builds [BZ #18694]
Commit a059d359d86130b5fa74e04a978c8523a0293f77 changed the sigaction
struct to pass conform tests, but it ended up also changing the ABI for
32 bit builds. For 64 bit builds, changing the long to two ints works,
but for 32 bit builds, it inserts 4 extra bytes. This leads to many
packages randomly failing like bash that spews things like:
configure: line 471: wait_for: No record of process 0
Bracket the new member by a wordsize check to fix the ABI for 32bit.
Carlos O'Donell [Fri, 6 Feb 2015 06:56:35 +0000 (01:56 -0500)]
hppa: Sync with pthread.h.
This reverts part of the previous commit to refactor pthread.h.
The refactoring must be done by having pthread.h include arch
bits headers, not the other way around. Then hppa provides the
arch bits header. For now we synchronzie again with pthread.h
and include the entire contents in the hppa copy.
Paul Pluzhnikov [Fri, 6 Feb 2015 05:30:42 +0000 (00:30 -0500)]
CVE-2015-1472: wscanf allocates too little memory
BZ #16618
Under certain conditions wscanf can allocate too little memory for the
to-be-scanned arguments and overflow the allocated buffer. The
implementation now correctly computes the required buffer size when
using malloc.
Carlos O'Donell [Fri, 6 Feb 2015 02:33:03 +0000 (21:33 -0500)]
hppa: Remove warnings and fix conformance errors.
(1) Fix warnings.
This is a bulk update to fix all the warnings that were causing
build failures with -Werror on hppa.
The most egregious problems are in dl-fptr.c which needs to be
entirely rewritten, thus I've used -Wno-error for that.
(2) Fix conformance errors.
The sysdep.c file had __syscall_error and syscall in one file
which caused conformance issues by including syscall when
__syscall_error was linked to. The fix is obviously to split
the file and use syscall.c to implement syscall.
David S. Miller [Sun, 1 Feb 2015 03:07:28 +0000 (19:07 -0800)]
Fix two bugs in sparc atomics.
* sysdeps/sparc/sparc32/bits/atomic.h
(__sparc32_atomic_do_unlock24): Put the memory barrier before the
unlock not after it.
(__v9_compare_and_exchange_val_32_acq): Use unions to avoid getting
volatile register usage warnings from the compiler.
H.J. Lu [Fri, 30 Jan 2015 14:50:20 +0000 (06:50 -0800)]
Use AVX unaligned memcpy only if AVX2 is available
memcpy with unaligned 256-bit AVX register loads/stores are slow on older
processorsl like Sandy Bridge. This patch adds bit_AVX_Fast_Unaligned_Load
and sets it only when AVX2 is available.
[BZ #17801]
* sysdeps/x86_64/multiarch/init-arch.c (__init_cpu_features):
Set the bit_AVX_Fast_Unaligned_Load bit for AVX2.
* sysdeps/x86_64/multiarch/init-arch.h (bit_AVX_Fast_Unaligned_Load):
New.
(index_AVX_Fast_Unaligned_Load): Likewise.
(HAS_AVX_FAST_UNALIGNED_LOAD): Likewise.
* sysdeps/x86_64/multiarch/memcpy.S (__new_memcpy): Check the
bit_AVX_Fast_Unaligned_Load bit instead of the bit_AVX_Usable bit.
* sysdeps/x86_64/multiarch/memcpy_chk.S (__memcpy_chk): Likewise.
* sysdeps/x86_64/multiarch/mempcpy.S (__mempcpy): Likewise.
* sysdeps/x86_64/multiarch/mempcpy_chk.S (__mempcpy_chk): Likewise.
* sysdeps/x86_64/multiarch/memmove.c (__libc_memmove): Replace
HAS_AVX with HAS_AVX_FAST_UNALIGNED_LOAD.
* sysdeps/x86_64/multiarch/memmove_chk.c (__memmove_chk): Likewise.
The padding bytes in the statsdata struct are not initialized, due to
which valgrind throws a warning:
==11384== Memcheck, a memory error detector
==11384== Copyright (C) 2002-2012, and GNU GPL'd, by Julian Seward et al.
==11384== Using Valgrind-3.8.1 and LibVEX; rerun with -h for copyright info
==11384== Command: nscd -d
==11384==
Fri 25 Apr 2014 10:34:53 AM CEST - 11384: handle_request: request received (Version = 2) from PID 11396
Fri 25 Apr 2014 10:34:53 AM CEST - 11384: GETSTAT
==11384== Thread 6:
==11384== Syscall param socketcall.sendto(msg) points to uninitialised byte(s)
==11384== at 0x4E4ACDC: send (in /lib64/libpthread-2.12.so)
==11384== by 0x11AF6B: send_stats (in /usr/sbin/nscd)
==11384== by 0x112F75: nscd_run_worker (in /usr/sbin/nscd)
==11384== by 0x4E439D0: start_thread (in /lib64/libpthread-2.12.so)
==11384== by 0x599AB6C: clone (in /lib64/libc-2.12.so)
==11384== Address 0x15708395 is on thread 6's stack
Chris Metcalf [Wed, 28 Jan 2015 19:51:21 +0000 (14:51 -0500)]
tilegx32: set __HAVE_64B_ATOMICS to 0
This is because of alignment issues in the sem_t support.
tilegx32 does in fact support 64-bit atomics and we will need
to revisit this after the 2.21 freeze.
Joseph Myers [Wed, 28 Jan 2015 18:40:35 +0000 (18:40 +0000)]
Disable 64-bit atomics for MIPS n32.
This patch disables use of 64-bit atomics for MIPS n32 to fix the
problems with unaligned semaphores.
Before 64-bit atomics are used for anything for which such alignment
issues do not arise, and before the addition of any new ILP32 ports
with 64-bit semaphores for which the ABI can be set to have the
greater alignment (AARCH64?), a better approach will need to be
established that allows architectures to declare their 64-bit atomics
availability accurately, without doing so causing inappropriate use of
such atomics on unaligned semaphores.
Tested for MIPS n32 that this fixes the nptl/tst-sem3 failure.
* sysdeps/mips/bits/atomic.h [_MIPS_SIM == _ABIN32]
(__HAVE_64B_ATOMICS): Define to 0.
This patch fixes a bug introduced by 18f2945ae9216cfc, where it optimizes
the FPSCR set by just issuing a mtfs instruction if new flag is different
from older one. The issue is a typo, where the new flag should the the
new value, instead of the old one.
Some powerpc64 processors (e5500 core for instance) does not provide the
fsqrt instruction, however current check to use in math_private.h is
__WORDSIZE and _ARCH_PWR4 (ISA 2.02). This is patch change it to use
the compiler flag _ARCH_PPCSQ (which is the same condition GCC uses to
decide whether to generate fsqrt instruction).
powerpc: Fix powerpc64 build failure with binutils 2.22
GLIBC memset optimization for POWER8 uses the '.machine power8'
directive, which is only supported officially on binutils 2.24+. This
causes a build failure on older binutils.
Since the requirement of .machine power8 is to correctly assembly the
'mtvsrd' instruction and it is already handled by the MTVSRD_V1_R4
macro, there is no really needed of using it.
The patch replaces the power8 with power7 for .machine directive.
This patch fix the elf/ifuncmain6pie failure when building with GCC
4.9+. For some reason, the compiler removes the branch taken code at
resolve_ifunc (sysdeps/powerpc/powerpc64/dl-machine.h) as dead-code
and thus the testcase fails because the ifunc resolves branches to an
invalid memory location. It fixes by explicit adding a dependency of
value based on odp variable to avoid compiler optimization.
H.J. Lu [Fri, 23 Jan 2015 22:48:40 +0000 (14:48 -0800)]
Use uint64_t and (uint64_t) 1 for 64-bit int
This patch replaces unsigned long int and 1UL with uint64_t and
(uint64_t) 1 to support ILP32 targets like x32.
[BZ #17870]
* nptl/sem_post.c (__new_sem_post): Replace unsigned long int
with uint64_t.
* nptl/sem_waitcommon.c (__sem_wait_cleanup): Replace 1UL with
(uint64_t) 1.
(__new_sem_wait_slow): Replace unsigned long int with uint64_t.
Replace 1UL with (uint64_t) 1.
* sysdeps/nptl/internaltypes.h (new_sem): Replace unsigned long
int with uint64_t.
Joseph Myers [Thu, 22 Jan 2015 22:39:26 +0000 (22:39 +0000)]
soft-fp: Use __label__ for all labels within macros.
soft-fp has various macros containing labels and goto statements.
Because label names are function-scoped, this is problematic for using
the same macro more than once within a function, which some
architectures do in the Linux kernel (the soft-fp version there
predates the addition of any of these labels and gotos). This patch
fixes this by using __label__ to make the labels local to the block
with the __label__ declaration.
Tested for powerpc-nofpu that installed stripped shared libraries are
unchanged by this patch.
This patch fix powerpc __get_clockfreq racy and cancel-safe issues by
dropping internal static cache and by using nocancel file operations.
The vDSO failure check is also removed, since kernel code does not
return an error (it cleans cr0.so bit on function return) and the static
code (to read value /proc) now uses non-cancellable calls.
Carlos O'Donell [Wed, 21 Jan 2015 15:08:18 +0000 (10:08 -0500)]
tst-getpw: Rewrite.
The test is rewritten to look for the testable conditions and
exit once they are all detected. This prevents the test from
iterating over 2000 UIDs and looking up each one. It speeds up
the test and prevents it from failing if the system under test
has an NSS-based passwd that is slower than the test timeout.
Carlos O'Donell [Wed, 21 Jan 2015 06:51:10 +0000 (01:51 -0500)]
Fix recursive dlopen.
The ability to recursively call dlopen is useful for malloc
implementations that wish to load other dynamic modules that
implement reentrant/AS-safe functions to use in their own
implementation.
Given that a user malloc implementation may be called by an
ongoing dlopen to allocate memory the user malloc
implementation interrupts dlopen and if it calls dlopen again
that's a reentrant call.
This patch fixes the issues with the ld.so.cache mapping
and the _r_debug assertion which prevent this from working
as expected.
Carlos O'Donell [Wed, 21 Jan 2015 05:46:16 +0000 (00:46 -0500)]
Fix semaphore destruction (bug 12674).
This commit fixes semaphore destruction by either using 64b atomic
operations (where available), or by using two separate fields when only
32b atomic operations are available. In the latter case, we keep a
conservative estimate of whether there are any waiting threads in one
bit of the field that counts the number of available tokens, thus
allowing sem_post to atomically both add a token and determine whether
it needs to call futex_wake.
[s390] Define a __tls_get_addr macro to avoid declaring it again
commit 050f7298e1ecc39887c329037575ccd972071255 added an extern
declaration for __tls_get_addr that conflicts with the one in s390
dl-tls.h, based on whether __tls_get_addr is defined as a macro. The
rationale seems to be based on the assumption that __tls_get_addr is
exported for every architecture and hence an internal non-plt alias is
needed. This is not true for s390 though, since it exports
__tls_get_offset and not __tls_get_addr. This results in tst-audit9
being stuck in an infinite loop.
This patch fixes this by defining a __tls_get_addr macro to itself so
as to not use the conflicting declaration.
powerpc: Fix POWER7/PPC64 performance regression on LE
This patch fixes a performance regression on the POWER7/PPC64 memcmp
porting for Little Endian. The LE code uses 'ldbrx' instruction to read
the memory on byte reversed form, however ISA 2.06 just provide the indexed
form which uses a register value as additional index, instead of a fixed value
enconded in the instruction.
And the port strategy for LE uses r0 index value and update the address
value on each compare loop interation. For large compare size values,
it adds 8 more instructions plus some more depending of trailing
size. This patch fixes it by adding pre-calculate indexes to remove the
address update on loops and tailing sizes.
For large sizes it shows a considerable gain, with double performance
pairing with BE.
This patch adds an optimized POWER8 strncmp. The implementation focus
on speeding up unaligned cases follwing the ideas of power8 strcmp.
The algorithm first check the initial 16 bytes, then align the first
function source and uses unaligned loads on second argument only.
Aditional checks for page boundaries are done for unaligned cases
(where sources alignment are different).
This patch optimized the POWER7 trailing check by avoiding using byte
read operations and instead use the doubleword already readed with
bitwise operations.
This patch adds an optimized POWER8 strcmp using unaligned accesses.
The algorithm first check the initial 16 bytes, then align the first
function source and uses unaligned loads on second argument only.
Aditional checks for page boundaries are done for unaligned cases
This patch adds an optimized POWER8 st{r,p}ncpy using unaligned accesses.
It shows 10%-80% improvement over the optimized POWER7 one that uses
only aligned accesses, specially on unaligned inputs.
The algorithm first read and check 16 bytes (if inputs do not cross a 4K
page size). The it realign source to 16-bytes and issue a 16 bytes read
and compare loop to speedup null byte checks for large strings. Also,
different from POWER7 optimization, the null pad is done inline in the
implementation using possible unaligned accesses, instead of realying on
a memset call. Special case is added for page cross reads.
With 3eb38795dbbbd816 (Simplify strncat) the generic algorithms uses
strlen, strnlen, and memcpy. This is faster than POWER7 current
implementation, especially for unaligned strings (where POWER7 code
uses byte-byte operations).
This patch removes the assembly implementation and uses a multiarch
specialization based on default algorithm calling optimized POWER7
symbols.
This patch adds an optimized POWER8 strcpy using unaligned accesses.
For strings up to 16 bytes the implementation first calculate the
string size, like strlen, and issues a memcpy. For larger strings,
source is first aligned to 16 bytes and then tested over a loop that
reads 16 bytes am combine the cmpb results for speedup. Special case is
added for page cross reads.
It shows 30%-60% improvement over the optimized POWER7 one that uses
only aligned accesses.
Leonhard Holz [Tue, 13 Jan 2015 06:03:56 +0000 (11:33 +0530)]
Fix memory handling in strxfrm_l [BZ #16009]
[Modified from the original email by Siddhesh Poyarekar]
This patch solves bug #16009 by implementing an additional path in
strxfrm that does not depend on caching the weight and rule indices.
In detail the following changed:
* The old main loop was factored out of strxfrm_l into the function
do_xfrm_cached to be able to alternativly use the non-caching version
do_xfrm.
* strxfrm_l allocates a a fixed size array on the stack. If this is not
sufficiant to store the weight and rule indices, the non-caching path is
taken. As the cache size is not dependent on the input there can be no
problems with integer overflows or stack allocations greater than
__MAX_ALLOCA_CUTOFF. Note that malloc-ing is not possible because the
definition of strxfrm does not allow an oom errorhandling.
* The uncached path determines the weight and rule index for every char
and for every pass again.
* Passing all the locale data array by array resulted in very long
parameter lists, so I introduced a structure that holds them.
* Checking for zero src string has been moved a bit upwards, it is
before the locale data initialization now.
* To verify that the non-caching path works correct I added a test run
to localedata/sort-test.sh & localedata/xfrm-test.c where all strings
are patched up with spaces so that they are too large for the caching path.
The ldbl-96 implementation of scalblnl (used for x86_64 and ia64) uses
a condition k <= -63 to determine when a standard underflowing result
tiny*__copysignl(tiny,x) should be returned. However, that condition
corresponds to values with exponent -16446 or less, and in the case of
-16446, the correct result for round-to-nearest depends on whether the
value is exactly 0x1p-16446 (half the least subnormal) or more than
that. This patch fixes the bug by changing the condition to k <= -64
and accordingly adjusting the exponent by 64 not 63 when converting to
a normal value.
Tested for x86_64.
[BZ #17803]
* sysdeps/ieee754/ldbl-96/s_scalblnl.c (twom63): Rename to
twom64. Adjust value to 0x1p-64L.
(__scalblnl): Only return standard underflowing result for K <=
-64 not K <= -63; adjust exponent for underflowing result by 64
not 63.
* math/libm-test.inc (scalbn_test_data): Add more tests.
(scalbln_test_data): Likewise.
Joseph Myers [Mon, 12 Jan 2015 22:34:58 +0000 (22:34 +0000)]
Fix ldbl-96 scalblnl for subnormal arguments (bug 17834).
The ldbl-96 implementation of scalblnl (used for x86_64 and ia64) is
incorrect for subnormal arguments (this is a separate bug from bug
17803, which is about underflowing results). There are two problems
with the adjustments of subnormal arguments: the "two63" variable
multiplied by is actually 0x1p52L not 0x1p63L, so is insufficient to
make values normal, and then GET_LDOUBLE_EXP(es,x), used to extract
the new exponent, extracts it into a variable that isn't used, while
the value taken to by the new exponent is wrongly taken from the high
part of the mantissa before the adjustment (hx). This patch fixes
both those problems and adds appropriate tests.
Tested for x86_64.
[BZ #17834]
* sysdeps/ieee754/ldbl-96/s_scalblnl.c (two63): Change value to
0x1p63L.
(__scalblnl): Get new exponent of adjusted subnormal value from ES
not HX.
* math/libm-test.inc (scalbn_test_data): Add more tests.
(scalbln_test_data): Likewise.
Linux 3.15 adds support for clock_gettime, gettimeofday, and time vDSO
(commit id 37c975545ec63320789962bf307f000f08fabd48). This patch adds
GLIBC supports to use such symbol when they are avaiable.
Along with x86 vDSO support, this patch cleanup x86_64 code by moving
all common code to x86 common folder. Only init-first.c is different
between implementations.
Linux kernel powerpc documentation states issuing a syscall inside a
transaction is not recommended and may lead to undefined behavior. It
also states syscalls does not abort transactoin neither they run in
transactional state.
To avoid side-effects being visible outside transactions, GLIBC with
lock elision enabled will issue a transaction abort instruction just
before all syscalls if hardware supports hardware transactions.
This patch adds support for lock elision using ISA 2.07 hardware
transactional memory for rwlocks. The logic is similar to the
one presented in pthread_mutex lock elision.
This patch adds support for lock elision using ISA 2.07 hardware
transactional memory instructions for pthread_mutex primitives.
Similar to s390 version, the for elision logic defined in
'force-elision.h' is only enabled if ENABLE_LOCK_ELISION is defined.
Also, the lock elision code should be able to be built even with
a compiler that does not provide HTM support with builtins.
However I have noted the performance is sub-optimal due scheduling
pressures.
Microblaze apparently has a variable page size (see thread below) and
should not hard-code any page-size related macros.
Also remove macros that are only used for BFD's trad-core support
which is not relavant for microblaze also according to the thread
starting here:
git://sourceware.org / glibc.git / log