Rich Felker [Sat, 11 Apr 2015 14:38:57 +0000 (10:38 -0400)]
remove mismatched arguments from vmlock function definitions
commit
f08ab9e61a147630497198fe3239149275c0a3f4 introduced these
accidentally as remnants of some work I tried that did not work out.
Rich Felker [Fri, 10 Apr 2015 07:47:42 +0000 (03:47 -0400)]
apply vmlock wait to __unmapself in pthread_exit
Rich Felker [Fri, 10 Apr 2015 06:27:52 +0000 (02:27 -0400)]
redesign and simplify vmlock system
this global lock allows certain unlock-type primitives to exclude
mmap/munmap operations which could change the identity of virtual
addresses while references to them still exist.
the original design mistakenly assumed mmap/munmap would conversely
need to exclude the same operations which exclude mmap/munmap, so the
vmlock was implemented as a sort of 'symmetric recursive rwlock'. this
turned out to be unnecessary.
commit
25d12fc0fc51f1fae0f85b4649a6463eb805aa8f already shortened the
interval during which mmap/munmap held their side of the lock, but
left the inappropriate lock design and some inefficiency.
the new design uses a separate function, __vm_wait, which does not
hold any lock itself and only waits for lock users which were already
present when it was called to release the lock. this is sufficient
because of the way operations that need to be excluded are sequenced:
the "unlock-type" operations using the vmlock need only block
mmap/munmap operations that are precipitated by (and thus sequenced
after) the atomic-unlock they perform while holding the vmlock.
this allows for a spectacular lack of synchronization in the __vm_wait
function itself.
Rich Felker [Fri, 10 Apr 2015 04:54:48 +0000 (00:54 -0400)]
optimize out setting up robust list with kernel when not needed
as a result of commit
12e1e324683a1d381b7f15dd36c99b37dd44d940, kernel
processing of the robust list is only needed for process-shared
mutexes. previously the first attempt to lock any owner-tracked mutex
resulted in robust list initialization and a set_robust_list syscall.
this is no longer necessary, and since the kernel's record of the
robust list must now be cleared at thread exit time for detached
threads, optimizing it out is more worthwhile than before too.
Rich Felker [Fri, 10 Apr 2015 04:26:34 +0000 (00:26 -0400)]
process robust list in pthread_exit to fix detached thread use-after-unmap
the robust list head lies in the thread structure, which is unmapped
before exit for detached threads. this leaves the kernel unable to
process the exiting thread's robust list, and with a dangling pointer
which may happen to point to new unrelated data at the time the kernel
processes it.
userspace processing of the robust list was already needed for
non-pshared robust mutexes in order to perform private futex wakes
rather than the shared ones the kernel would do, but it was
conditional on linking pthread_mutexattr_setrobust and did not bother
processing the pshared mutexes in the list, which requires additional
logic for the robust list pending slot in case pthread_exit is
interrupted by asynchronous process termination.
the new robust list processing code is linked unconditionally (inlined
in pthread_exit), handles both private and shared mutexes, and also
removes the kernel's reference to the robust list before unmapping and
exit if the exiting thread is detached.
Rich Felker [Tue, 7 Apr 2015 16:47:19 +0000 (12:47 -0400)]
fix possible clobbering of syscall return values on mips
depending on the compiler's interpretation of __asm__ register names
for register class objects, it may be possible for the return value in
r2 to be clobbered by the function call to __stat_fix. I have not
observed any such breakage in normal builds and suspect it only
happens with -O0 or other unusual build options, but since there's an
ambiguity as to the semantics of this feature, it's best to use an
explicit temporary to avoid the issue.
based on reporting and patch by Eugene.
Szabolcs Nagy [Sat, 4 Apr 2015 11:27:06 +0000 (11:27 +0000)]
fix getdelim to set the error indicator on all failures
Rich Felker [Sat, 4 Apr 2015 04:15:19 +0000 (00:15 -0400)]
fix rpath string memory leak on failed dlopen
when dlopen fails, all partially-loaded libraries need to be unmapped
and freed. any of these libraries using an rpath with $ORIGIN
expansion may have an allocated string for the expanded rpath;
previously, this string was not freed when freeing the library data
structures.
Rich Felker [Fri, 3 Apr 2015 20:35:43 +0000 (16:35 -0400)]
halt dynamic linker library search on errors resolving $ORIGIN in rpath
this change hardens the dynamic linker against the possibility of
loading the wrong library due to inability to expand $ORIGIN in rpath.
hard failures such as excessively long paths or absence of /proc (when
resolving /proc/self/exe for the main executable's origin) do not stop
the path search, but memory allocation failures and any other
potentially transient failures do.
to implement this change, the meaning of the return value of
fixup_rpath function is changed. returning zero no longer indicates
that the dso's rpath string pointer is non-null; instead, the caller
needs to check. a return value of -1 indicates a failure that should
stop further path search.
Rich Felker [Thu, 2 Apr 2015 00:35:03 +0000 (20:35 -0400)]
remove macro definition of longjmp from setjmp.h
the C standard specifies that setjmp is a macro, but longjmp is a
normal function. a macro version of it would be permitted (albeit
useless) for C (not C++), but would have to be a function-like macro,
not an object-like one.
Rich Felker [Thu, 2 Apr 2015 00:27:29 +0000 (20:27 -0400)]
harden dynamic linker library path search
transient errors during the path search should not allow the search to
continue and possibly open the wrong file. this patch eliminates most
conditions where that could happen, but there is still a possibility
that $ORIGIN-based rpath processing will have an allocation failure,
causing the search to skip such a path. fixing this is left as a
separate task.
a small bug where overly-long path components caused an infinite loop
rather than being skipped/ignored is also fixed.
Rich Felker [Wed, 1 Apr 2015 23:31:06 +0000 (19:31 -0400)]
move O_PATH definition back to arch bits
while it's the same for all presently supported archs, it differs at
least on sparc, and conceptually it's no less arch-specific than the
other O_* macros. O_SEARCH and O_EXEC are still defined in terms of
O_PATH in the main fcntl.h.
Rich Felker [Wed, 1 Apr 2015 23:25:32 +0000 (19:25 -0400)]
aarch64: remove duplicate macro definitions in bits/fcntl.h
Rich Felker [Wed, 1 Apr 2015 23:12:18 +0000 (19:12 -0400)]
aarch64: fix definition of sem_nsems in semid_ds structure
POSIX requires the sem_nsems member to have type unsigned short. we
have to work around the incorrect kernel type using matching
endian-specific padding.
Szabolcs Nagy [Wed, 1 Apr 2015 20:21:50 +0000 (20:21 +0000)]
aarch64: fix namespace pollution in bits/shm.h
The shm_info struct is a gnu extension and some of its members do
not have shm* prefix. This is worked around in sys/shm.h by macros,
but aarch64 didn't use those.
Rich Felker [Mon, 30 Mar 2015 03:48:12 +0000 (23:48 -0400)]
release 1.1.8
Szabolcs Nagy [Wed, 25 Mar 2015 18:25:09 +0000 (18:25 +0000)]
regex: fix character class repetitions
Internally regcomp needs to copy some iteration nodes before
translating the AST into TNFA representation.
Literal nodes were not copied correctly: the class type and list
of negated class types were not copied so classes were ignored
(in the non-negated case an ignored char class caused the literal
to match everything).
This affects iterations when the upper bound is finite, larger
than one or the lower bound is larger than one. So eg. the EREs
[[:digit:]]{2}
[^[:space:]ab]{1,4}
were treated as
.{2}
[^ab]{1,4}
The fix is done with minimal source modification to copy the
necessary fields, but the AST preparation and node handling
code of tre will need to be cleaned up for clarity.
Szabolcs Nagy [Sun, 22 Mar 2015 18:32:55 +0000 (18:32 +0000)]
do not treat \0 as a backref in BRE
The valid BRE backref tokens are \1 .. \9, and 0 is not a special
character either so \0 is undefined by the standard.
Such undefined escaped characters are treated as literal characters
currently, following existing practice, so \0 is the same as 0.
Rich Felker [Mon, 23 Mar 2015 15:26:51 +0000 (11:26 -0400)]
fix FLT_ROUNDS regression in C++ applications
commit
559de8f5f06da9022cbba70e22e14a710eb74513 redefined FLT_ROUNDS
to use an external function that can report the actual current
rounding mode, rather than always reporting round-to-nearest. however,
float.h did not include 'extern "C"' wrapping for C++, so C++ programs
using FLT_ROUNDS ended up with an unresolved reference to a
name-mangled C++ function __flt_rounds.
Rich Felker [Mon, 23 Mar 2015 13:44:18 +0000 (09:44 -0400)]
fix internal buffer overrun in inet_pton
one stop condition for parsing abbreviated ipv6 addressed was missed,
allowing the internal ip[] buffer to overflow. this patch adds the
missing stop condition and masks the array index so that, in case
there are any remaining stop conditions missing, overflowing the
buffer is not possible.
Rich Felker [Fri, 20 Mar 2015 22:25:01 +0000 (18:25 -0400)]
suppress backref processing in ERE regcomp
one of the features of ERE is that it's actually a regular language
and does not admit expressions which cannot be matched in linear time.
introduction of \n backref support into regcomp's ERE parsing was
unintentional.
Rich Felker [Fri, 20 Mar 2015 22:06:04 +0000 (18:06 -0400)]
fix memory-corruption in regcomp with backslash followed by high byte
the regex parser handles the (undefined) case of an unexpected byte
following a backslash as a literal. however, instead of correctly
decoding a character, it was treating the byte value itself as a
character. this was not only semantically unjustified, but turned out
to be dangerous on archs where plain char is signed: bytes in the
range 252-255 alias the internal codes -4 through -1 used for special
types of literal nodes in the AST.
Rich Felker [Fri, 20 Mar 2015 05:21:37 +0000 (01:21 -0400)]
fix missing max_align_t definition on aarch64
Rich Felker [Thu, 19 Mar 2015 00:38:02 +0000 (20:38 -0400)]
release 1.1.7
Rich Felker [Wed, 18 Mar 2015 03:12:48 +0000 (23:12 -0400)]
fix MINSIGSTKSZ values for archs with large signal contexts
the previous values (2k min and 8k default) were too small for some
archs. aarch64 reserves 4k in the signal context for future extensions
and requires about 4.5k total, and powerpc reportedly uses over 2k.
the new minimums are chosen to fit the saved context and also allow a
minimal signal handler to run.
since the default (SIGSTKSZ) has always been 6k larger than the
minimum, it is also increased to maintain the 6k usable by the signal
handler. this happens to be able to store one pathname buffer and
should be sufficient for calling any function in libc that doesn't
involve conversion between floating point and decimal representations.
x86 (both 32-bit and 64-bit variants) may also need a larger minimum
(around 2.5k) in the future to support avx-512, but the values on
these archs are left alone for now pending further analysis.
the value for PTHREAD_STACK_MIN is not increased to match MINSIGSTKSZ
at this time. this is so as not to preclude applications from using
extremely small thread stacks when they know they will not be handling
signals. unfortunately cancellation and multi-threaded set*id() use
signals as an implementation detail and therefore require a stack
large enough for a signal context, so applications which use extremely
small thread stacks may still need to avoid using these features.
Rich Felker [Tue, 17 Mar 2015 00:12:49 +0000 (20:12 -0400)]
block all signals (even internal ones) in cancellation signal handler
previously the implementation-internal signal used for multithreaded
set*id operations was left unblocked during handling of the
cancellation signal. however, on some archs, signal contexts are huge
(up to 5k) and the possibility of nested signal handlers drastically
increases the minimum stack requirement. since the cancellation signal
handler will do its job and return in bounded time before possibly
passing execution to application code, there is no need to allow other
signals to interrupt it.
Rich Felker [Mon, 16 Mar 2015 22:43:54 +0000 (18:43 -0400)]
update authors/contributors list
these additions were made based on scanning commit authors since the
last update, at the time of the 1.1.4 release.
Rich Felker [Mon, 16 Mar 2015 03:46:22 +0000 (23:46 -0400)]
avoid sending huge names as nscd passwd/group queries
overly long user/group names are potentially a DoS vector and source
of other problems like partial writes by sendmsg, and not useful.
Rich Felker [Mon, 16 Mar 2015 03:33:59 +0000 (23:33 -0400)]
simplify nscd lookup code for alt passwd/group backends
previously, a sentinel value of (FILE *)-1 was used to inform the
caller of __nscd_query that nscd is not in use. aside from being an
ugly hack, this resulted in duplicate code paths for two logically
equivalent cases: no nscd, and "not found" result from nscd.
now, __nscd_query simply skips closing the socket and returns a valid
FILE pointer when nscd is not in use, and produces a fake "not found"
response header. the caller is then responsible for closing the socket
just like it would do if it had gotten a real "not found" response.
Josiah Worcester [Mon, 16 Mar 2015 00:20:53 +0000 (19:20 -0500)]
add alternate backend support for getgrouplist
This completes the alternate backend support that was previously added
to the getpw* and getgr* functions. Unlike those, though, it
unconditionally queries nscd. Any groups from nscd that aren't in the
/etc/groups file are added to the returned list, and any that are
present in the file are ignored. The purpose of this behavior is to
provide a view of the group database consistent with what is observed
by the getgr* functions. If group memberships reported by nscd were
honored when the corresponding group already has a definition in the
/etc/groups file, the user's getgrouplist-based membership in the
group would conflict with their non-membership in the reported
gr_mem[] for the group.
The changes made also make getgrouplist thread-safe and eliminate its
clobbering of the global getgrent state.
Szabolcs Nagy [Sat, 14 Mar 2015 19:43:43 +0000 (19:43 +0000)]
aarch64: fix typo in bits/ioctl.h
Szabolcs Nagy [Sat, 14 Mar 2015 17:40:09 +0000 (17:40 +0000)]
aarch64: add struct _aarch64_ctx to signal.h
The unwind code in libgcc uses this type for unwinding across signal
handlers. On aarch64 the kernel may place a sequence of structs on the
signal stack on top of the ucontext to provide additional information.
The unwinder only needs the header, but added all the types the kernel
currently defines for this mechanism because they are part of the uapi.
Rich Felker [Thu, 12 Mar 2015 18:43:36 +0000 (14:43 -0400)]
align x32 pthread type sizes to be common with 32-bit archs
previously, commit
e7b9887e8b65253087ab0b209dc8dd85c9f09614 aligned
the sizes with the glibc ABI. subsequent discussion during the merge
of the aarch64 port reached a conclusion that we should reject larger
arch-specific sizes, which have significant cost and no benefit, and
stick with the existing common 32-bit sizes for all 32-bit/ILP32 archs
and the x86_64 sizes for 64-bit archs.
one peculiarity of this change is that x32 pthread_attr_t is now
larger in musl than in the glibc x32 ABI, making it unsafe to call
pthread_attr_init from x32 code that was compiled against glibc. with
all the ABI issues of x32, it's not clear that ABI compatibility will
ever work, but if it's needed, pthread_attr_init and related functions
could be modified not to write to the last slot of the object.
this is not a regression versus previous releases, since on previous
releases the x32 pthread type sizes were all severely oversized
already (due to incorrectly using the x86_64 LP64 definitions).
moreover, x32 is still considered experimental and not ABI-stable.
Szabolcs Nagy [Tue, 10 Mar 2015 21:18:41 +0000 (21:18 +0000)]
add aarch64 port
This adds complete aarch64 target support including bigendian subarch.
Some of the long double math functions are known to be broken otherwise
interfaces should be fully functional, but at this point consider this
port experimental.
Initial work on this port was done by Sireesh Tripurari and Kevin Bortis.
Szabolcs Nagy [Tue, 10 Mar 2015 20:01:20 +0000 (20:01 +0000)]
math: add dummy implementations of 128 bit long double functions
This is in preparation for the aarch64 port only to have the long
double math symbols available on ld128 platforms. The implementations
should be fixed up later once we have proper tests for these functions.
Added bigendian handling for ld128 bit manipulations too.
Szabolcs Nagy [Mon, 9 Mar 2015 12:17:25 +0000 (12:17 +0000)]
math: add ld128 exp2l based on the freebsd implementation
Changed the special case handling and bit manipulation to better
match the double version.
Szabolcs Nagy [Wed, 11 Mar 2015 12:48:12 +0000 (12:48 +0000)]
copy the dtv pointer to the end of the pthread struct for TLS_ABOVE_TP archs
There are two main abi variants for thread local storage layout:
(1) TLS is above the thread pointer at a fixed offset and the pthread
struct is below that. So the end of the struct is at known offset.
(2) the thread pointer points to the pthread struct and TLS starts
below it. So the start of the struct is at known (zero) offset.
Assembly code for the dynamic TLSDESC callback needs to access the
dynamic thread vector (dtv) pointer which is currently at the front
of the pthread struct. So in case of (1) the asm code needs to hard
code the offset from the end of the struct which can easily break if
the struct changes.
This commit adds a copy of the dtv at the end of the struct. New members
must not be added after dtv_copy, only before it. The size of the struct
is increased a bit, but there is opportunity for size optimizations.
Rich Felker [Sat, 7 Mar 2015 19:11:01 +0000 (14:11 -0500)]
fix regression in pthread_cond_wait with cancellation disabled
due to a logic error in the use of masked cancellation mode,
pthread_cond_wait did not honor PTHREAD_CANCEL_DISABLE but instead
failed with ECANCELED when cancellation was pending.
Szabolcs Nagy [Sat, 7 Mar 2015 10:00:37 +0000 (11:00 +0100)]
fix FLT_ROUNDS to reflect the current rounding mode
Implemented as a wrapper around fegetround introducing a new function
to the ABI: __flt_rounds. (fegetround cannot be used directly from float.h)
Rich Felker [Fri, 6 Mar 2015 18:27:08 +0000 (13:27 -0500)]
fix over-alignment of TLS, insufficient builtin TLS on 64-bit archs
a conservative estimate of 4*sizeof(size_t) was used as the minimum
alignment for thread-local storage, despite the only requirements
being alignment suitable for struct pthread and void* (which struct
pthread already contains). additional alignment required by the
application or libraries is encoded in their headers and is already
applied.
over-alignment prevented the builtin_tls array from ever being used in
dynamic-linked programs on 64-bit archs, thereby requiring allocation
at startup even in programs with no TLS of their own.
Rich Felker [Thu, 5 Mar 2015 03:10:01 +0000 (22:10 -0500)]
add legacy functions from sysinfo.h duplicating sysconf functionality
Rich Felker [Thu, 5 Mar 2015 02:46:08 +0000 (21:46 -0500)]
fix signed left-shift overflow in pthread_condattr_setpshared
Szabolcs Nagy [Wed, 4 Mar 2015 19:37:33 +0000 (20:37 +0100)]
add new si_lower and si_upper siginfo_t members
new in linux v3.19 commit
ee1b58d36aa1b5a79eaba11f5c3633c88231da83
used to report intel mpx bound violation information.
Rich Felker [Wed, 4 Mar 2015 19:38:08 +0000 (14:38 -0500)]
declare incomplete type struct itimerspec in timerfd.h
normally time.h would provide a definition for this struct, but
depending on the feature test macros in use, it may not be exposed,
leading to warnings when it's used in the function prototypes.
Rich Felker [Wed, 4 Mar 2015 19:15:44 +0000 (14:15 -0500)]
fix preprocessor error introduced in poll.h in last commit
Trutz Behn [Fri, 13 Feb 2015 17:10:52 +0000 (18:10 +0100)]
fix POLLWRNORM and POLLWRBAND on mips
these macros have the same distinct definition on blackfin, frv, m68k,
mips, sparc and xtensa kernels. POLLMSG and POLLRDHUP additionally
differ on sparc.
Rich Felker [Wed, 4 Mar 2015 16:33:26 +0000 (11:33 -0500)]
fix x32 pthread type definitions
the previous definitions were copied from x86_64. not only did they
fail to match the ABI sizes; they also wrongly encoded an assumption
that long/pointer types are twice as large as int.
Rich Felker [Wed, 4 Mar 2015 15:48:00 +0000 (10:48 -0500)]
remove useless check of bin match in malloc
this re-check idiom seems to have been copied from the alloc_fwd and
alloc_rev functions, which guess a bin based on non-synchronized
memory access to adjacent chunk headers then need to confirm, after
locking the bin, that the chunk is actually in the bin they locked.
the check being removed, however, was being performed on a chunk
obtained from the already-locked bin. there is no race to account for
here; the check could only fail in the event of corrupt free lists,
and even then it would not catch them but simply continue running.
since the bin_index function is mildly expensive, it seems preferable
to remove the check rather than trying to convert it into a useful
consistency check. casual testing shows a 1-5% reduction in run time.
Rich Felker [Wed, 4 Mar 2015 14:44:43 +0000 (09:44 -0500)]
eliminate atomics in syslog setlogmask function
Rich Felker [Wed, 4 Mar 2015 14:29:39 +0000 (09:29 -0500)]
fix init race that could lead to deadlock in malloc init code
the malloc init code provided its own version of pthread_once type
logic, including the exact same bug that was fixed in pthread_once in
commit
0d0c2f40344640a2a6942dda156509593f51db5d.
since this code is called adjacent to expand_heap, which takes a lock,
there is no reason to have pthread_once-type initialization. simply
moving the init code into the interval where expand_heap already holds
its lock on the brk achieves the same result with much less
synchronization logic, and allows the buggy code to be eliminated
rather than just fixed.
Rich Felker [Wed, 4 Mar 2015 03:50:02 +0000 (22:50 -0500)]
make all objects used with atomic operations volatile
the memory model we use internally for atomics permits plain loads of
values which may be subject to concurrent modification without
requiring that a special load function be used. since a compiler is
free to make transformations that alter the number of loads or the way
in which loads are performed, the compiler is theoretically free to
break this usage. the most obvious concern is with atomic cas
constructs: something of the form tmp=*p;a_cas(p,tmp,f(tmp)); could be
transformed to a_cas(p,*p,f(*p)); where the latter is intended to show
multiple loads of *p whose resulting values might fail to be equal;
this would break the atomicity of the whole operation. but even more
fundamental breakage is possible.
with the changes being made now, objects that may be modified by
atomics are modeled as volatile, and the atomic operations performed
on them by other threads are modeled as asynchronous stores by
hardware which happens to be acting on the request of another thread.
such modeling of course does not itself address memory synchronization
between cores/cpus, but that aspect was already handled. this all
seems less than ideal, but it's the best we can do without mandating a
C11 compiler and using the C11 model for atomics.
in the case of pthread_once_t, the ABI type of the underlying object
is not volatile-qualified. so we are assuming that accessing the
object through a volatile-qualified lvalue via casts yields volatile
access semantics. the language of the C standard is somewhat unclear
on this matter, but this is an assumption the linux kernel also makes,
and seems to be the correct interpretation of the standard.
Rich Felker [Mon, 2 Mar 2015 23:52:31 +0000 (18:52 -0500)]
suppress masked cancellation in pthread_join
like close, pthread_join is a resource-deallocation function which is
also a cancellation point. the intent of masked cancellation mode is
to exempt such functions from failure with ECANCELED.
Rich Felker [Mon, 2 Mar 2015 23:48:58 +0000 (18:48 -0500)]
fix namespace issue in pthread_join affecting thrd_join
pthread_testcancel is not in the ISO C reserved namespace and thus
cannot be used here. use the namespace-protected version of the
function instead.
Rich Felker [Mon, 2 Mar 2015 23:11:28 +0000 (18:11 -0500)]
make aio_suspend a cancellation point and properly handle cancellation
Rich Felker [Mon, 2 Mar 2015 22:46:22 +0000 (17:46 -0500)]
factor cancellation cleanup push/pop out of futex __timedwait function
previously, the __timedwait function was optionally a cancellation
point depending on whether it was passed a pointer to a cleaup
function and context to register. as of now, only one caller actually
used such a cleanup function (and it may face removal soon); most
callers either passed a null pointer to disable cancellation or a
dummy cleanup function.
now, __timedwait is never a cancellation point, and __timedwait_cp is
the cancellable version. this makes the intent of the calling code
more obvious and avoids ugly dummy functions and long argument lists.
Rich Felker [Sat, 28 Feb 2015 04:25:45 +0000 (23:25 -0500)]
fix failure of internal futex __timedwait to report ECANCELED
as part of abstracting the futex wait, this function suppresses all
futex error values which callers should not see using a whitelist
approach. when the masked cancellation mode was added, the new
ECANCELED error was not whitelisted. this omission caused the new
pthread_cond_wait code using masked cancellation to exhibit a spurious
wake (rather than acting on cancellation) when the request arrived
after blocking on the cond var.
Rich Felker [Thu, 26 Feb 2015 07:07:08 +0000 (02:07 -0500)]
overhaul optimized x86_64 memset asm
on most cpu models, "rep stosq" has high overhead that makes it
undesirable for small memset sizes. the new code extends the
minimal-branch fast path for short memsets from size 15 up to size
126, and shrink-wraps this code path. in addition, "rep stosq" is
sensitive to misalignment. the cost varies with size and with cpu
model, but it has been observed performing 1.5 times slower when the
destination address is not aligned mod 16. the new code thus ensures
alignment mod 16, but also preserves any existing additional
alignment, in case there are cpu models where it is beneficial.
this version is based in part on changes proposed by Denys Vlasenko.
Rich Felker [Thu, 26 Feb 2015 06:51:39 +0000 (01:51 -0500)]
overhaul optimized i386 memset asm
on most cpu models, "rep stosl" has high overhead that makes it
undesirable for small memset sizes. the new code extends the
minimal-branch fast path for short memsets from size 15 up to size 62,
and shrink-wraps this code path. in addition, "rep stosl" is very
sensitive to misalignment. the cost varies with size and with cpu
model, but it has been observed performing 1.5 to 4 times slower when
the destination address is not aligned mod 16. the new code thus
ensures alignment mod 16, but also preserves any existing additional
alignment, in case there are cpu models where it is beneficial.
this version is based in part on changes to the x86_64 memset asm
proposed by Denys Vlasenko.
Alexander Monakov [Tue, 24 Feb 2015 18:44:07 +0000 (21:44 +0300)]
getloadavg: use sysinfo() instead of /proc/loadavg
Based on a patch by Szabolcs Nagy.
Rich Felker [Mon, 23 Feb 2015 23:53:01 +0000 (18:53 -0500)]
fix possible isatty false positives and unwanted device state changes
the equivalent checks for newly opened stdio output streams, used to
determine buffering mode, are also fixed.
on most archs, the TCGETS ioctl command shares a value with
SNDCTL_TMR_TIMEBASE, part of the OSS sound API which was apparently
used with certain MIDI and timer devices. for file descriptors
referring to such a device, TCGETS will not fail with ENOTTY as
expected; it may produce a different error, or may succeed, and if it
succeeds it changes the mode of the device. while it's unlikely that
such devices are in use, this is in principle very harmful behavior
for an operation which is supposed to do nothing but query whether the
fd refers to a tty.
TIOCGWINSZ, used to query logical window size for a terminal, was
chosen as an alternate ioctl to perform the isatty check. it does not
share a value with any other ioctl commands, and it succeeds on any
tty device.
this change also cleans up strace output to be less ugly and
misleading.
Rich Felker [Mon, 23 Feb 2015 17:41:16 +0000 (12:41 -0500)]
fix breakage in pthread_cond_wait due to typo
due to accidental use of = instead of ==, the error code was always
set to zero in the signaled wake case for non-shared cv waits.
suppressing ETIMEDOUT (the only possible wait error) is harmless and
actually permitted in this case, but suppressing mutex errors could
give the caller false information about the state of the mutex.
commit
8741ffe625363a553e8f509dc3ca7b071bdbab47 introduced this
regression and commit
d9da1fb8c592469431c764732d09f7756340190e
preserved it when reorganizing the code.
Josiah Worcester [Mon, 23 Feb 2015 02:58:10 +0000 (20:58 -0600)]
support alternate backends for the passwd and group dbs
when we fail to find the entry in the commonly accepted files, we
query a server over a Unix domain socket on /var/run/nscd/socket.
the protocol used here is compatible with glibc's nscd protocol on
most systems (all that use 32-bit numbers for all the protocol fields,
which appears to be everything but Alpha).
Rich Felker [Mon, 23 Feb 2015 05:42:40 +0000 (00:42 -0500)]
fix spurious errors in refactored passwd/group code
errno was treated as the error status when the return value of getline
was negative, but this condition can simply indicate EOF and is not
necessarily an error.
the spurious errors caused by this bug masked the bug which was fixed
in commit
fc5a96c9c8aa186effad7520d5df6b616bbfd29d.
Rich Felker [Mon, 23 Feb 2015 05:35:47 +0000 (00:35 -0500)]
fix crashes in refactored passwd/group code
the wrong condition was used in determining the presence of a result
that needs space/copying for the _r functions. a zero return value
does not necessarily mean success; it can also be a non-error negative
result: no such user/group.
Rich Felker [Mon, 23 Feb 2015 03:55:08 +0000 (22:55 -0500)]
simplify cond var code now that cleanup handler is not needed
Rich Felker [Mon, 23 Feb 2015 03:07:50 +0000 (22:07 -0500)]
fix pthread_cond_wait cancellation race
it's possible that signaling a waiter races with cancellation of that
same waiter. previously, cancellation was acted upon, causing the
signal to be consumed with no waiter returning. by using the new
masked cancellation state, it's possible to refuse to act on the
cancellation request and instead leave it pending.
to ease review and understanding of the changes made, this commit
leaves the unwait function, which was previously the cancellation
cleanup handler, in place. additional simplifications could be made by
removing it.
Rich Felker [Sun, 22 Feb 2015 03:05:15 +0000 (22:05 -0500)]
add new masked cancellation mode
this is a new extension which is presently intended only for
experimental and internal libc use. interface and behavior details may
change subject to feedback and experience from using it internally.
the basic concept for the new PTHREAD_CANCEL_MASKED state is that the
first cancellation point to observe the cancellation request fails
with an errno value of ECANCELED rather than acting on cancellation,
allowing the caller to process the status and choose whether/how to
act upon it.
Rich Felker [Sat, 21 Feb 2015 01:25:35 +0000 (20:25 -0500)]
prepare cancellation syscall asm for possibility of __cancel returning
Rich Felker [Fri, 20 Feb 2015 23:35:05 +0000 (18:35 -0500)]
map interruption of close by signal to success rather than EINPROGRESS
commit
82dc1e2e783815e00a90cd3f681436a80d54a314 addressed the
resolution of Austin Group issue 529, which requires close to leave
the fd open when failing with EINTR, by returning the newly defined
error code EINPROGRESS. this turns out to be a bad idea, though, since
legacy applications not aware of the new specification are likely to
interpret any error from close except EINTR as a hard failure.
Rich Felker [Tue, 17 Feb 2015 03:25:50 +0000 (22:25 -0500)]
make pthread_exit responsible for disabling cancellation
this requirement is tucked away in XSH 2.9.5 Thread Cancellation under
the heading Thread Cancellation Cleanup Handlers.
Rich Felker [Sat, 14 Feb 2015 19:05:35 +0000 (14:05 -0500)]
fix type error (arch-dependent) in new aio code
a_store is only valid for int, but ssize_t may be defined as long or
another type. since there is no valid way for another thread to acess
the return value without first checking the error/completion status of
the aiocb anyway, an atomic store is not necessary.
Josiah Worcester [Sat, 7 Feb 2015 21:40:46 +0000 (15:40 -0600)]
refactor group file access code
this allows getgrnam and getgrgid to share code with the _r versions
in preparation for alternate backend support.
Rich Felker [Fri, 13 Feb 2015 05:27:45 +0000 (00:27 -0500)]
overhaul aio implementation for correctness
previously, aio operations were not tracked by file descriptor; each
operation was completely independent. this resulted in non-conforming
behavior for non-seekable/append-mode writes (which are required to be
ordered) and made it impossible to implement aio_cancel, which in turn
made closing file descriptors with outstanding aio operations unsafe.
the new implementation is significantly heavier (roughly twice the
size, and seems to be slightly slower) and presently aims mainly at
correctness, not performance.
most of the public interfaces have been moved into a single file,
aio.c, because there is little benefit to be had from splitting them.
whenever any aio functions are used, aio_cancel and the internal
queue lifetime management and fd-to-queue mapping code must be linked,
and these functions make up the bulk of the code size.
the close function's interaction with aio is implemented with weak
alias magic, to avoid pulling in heavy aio cancellation code in
programs that don't use aio, and the expensive cancellation path
(which includes signal blocking) is optimized out when there are no
active aio queues.
Rich Felker [Wed, 11 Feb 2015 06:37:01 +0000 (01:37 -0500)]
fix bad character checking in wordexp
the character sequence '$((' was incorrectly interpreted as the
opening of arithmetic even within single-quoted contexts, thereby
suppressing the checks for bad characters after the closing quote.
presently bad character checking is only performed when the WRDE_NOCMD
is used; this patch only corrects checking in that case.
Josiah Worcester [Wed, 11 Feb 2015 00:32:55 +0000 (18:32 -0600)]
refactor passwd file access code
this allows getpwnam and getpwuid to share code with the _r versions
in preparation for alternate backend support.
Denys Vlasenko [Tue, 10 Feb 2015 17:30:57 +0000 (18:30 +0100)]
x86_64/memset: avoid performing final store twice
The code does a potentially misaligned 8-byte store to fill the tail
of the buffer. Then it fills the initial part of the buffer
which is a multiple of 8 bytes.
Therefore, if size is divisible by 8, we were storing last word twice.
This patch decrements byte count before dividing it by 8,
making one less store in "size is divisible by 8" case,
and not changing anything in all other cases.
All at the cost of replacing one MOV insn with LEA insn.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
Denys Vlasenko [Tue, 10 Feb 2015 17:30:56 +0000 (18:30 +0100)]
x86_64/memset: simple optimizations
"and $0xff,%esi" is a six-byte insn (81 e6 ff 00 00 00), can use
4-byte "movzbl %sil,%esi" (40 0f b6 f6) instead.
64-bit imul is slow, move it as far up as possible so that the result
(rax) has more time to be ready by the time we start using it
in mem stores.
There is no need to shuffle registers in preparation to "rep movs"
if we are not going to take that code path. Thus, patch moves
"jump if len < 16" instructions up, and changes alternate code path
to use rdx and rdi instead of rcx and r8.
Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
Timo Teräs [Mon, 9 Feb 2015 11:34:41 +0000 (13:34 +0200)]
make protocol table zero byte separated and add ipv6 protocols
Szabolcs Nagy [Mon, 9 Feb 2015 21:53:20 +0000 (22:53 +0100)]
add syscall numbers for the new execveat syscall
this syscall allows fexecve to be implemented without /proc, it is new
in linux v3.19, added in commit
51f39a1f0cea1cacf8c787f652f26dfee9611874
(sh and microblaze do not have allocated syscall numbers yet)
added a x32 fix as well: the io_setup and io_submit syscalls are no
longer common with x86_64, so use the x32 specific numbers.
Szabolcs Nagy [Mon, 9 Feb 2015 21:22:13 +0000 (22:22 +0100)]
add new socket options SO_INCOMING_CPU, SO_ATTACH_BPF, SO_DETACH_BPF
these socket options are new in linux v3.19, introduced in commit
2c8c56e15df3d4c2af3d656e44feb18789f75837 and commit
89aa075832b0da4402acebd698d0411dcc82d03e
with SO_INCOMING_CPU the cpu can be queried on which a socket is
managed inside the kernel and optimize polling of large number of
sockets accordingly.
SO_ATTACH_BPF lets eBPF programs (created by the bpf syscall) to
be attached to sockets.
Szabolcs Nagy [Mon, 9 Feb 2015 21:11:52 +0000 (22:11 +0100)]
use the internal macro name FUTEX_PRIVATE in __wait
the name was recently added for the setxid/synccall rework,
so use the name now that we have it.
Szabolcs Nagy [Mon, 9 Feb 2015 20:38:02 +0000 (21:38 +0100)]
add IEEE binary128 long double support to floatscan
just defining the necessary constants:
LD_B1B_MAX is 2^113 - 1 in base 10^9
KMAX is 2048 so the x array can hold up to 18432 decimal digits
(the worst case is converting 2^-16495 = 5^16495 * 10^-16495 to
binary, it requires the processing of int(log10(5)*16495)+1 = 11530
decimal digits after discarding the leading zeros, the conversion
requires some headroom in x, but KMAX is more than enough for that)
However this code is not optimal on archs with IEEE binary128
long double because the arithmetics is software emulated (on
all such platforms as far as i know) which means big and slow
strtod.
Szabolcs Nagy [Mon, 9 Feb 2015 00:16:35 +0000 (01:16 +0100)]
math: fix fmodl for IEEE binary128
This trivial copy-paste bug went unnoticed due to lack of testing.
No currently supported target archs are affected.
Szabolcs Nagy [Sun, 8 Feb 2015 18:13:09 +0000 (19:13 +0100)]
simplify armhf fesetenv
armhf fesetenv implementation did a useless read of the fpscr.
Szabolcs Nagy [Sun, 8 Feb 2015 17:56:52 +0000 (18:56 +0100)]
fix fesetenv(FE_DFL_ENV) on mips
mips fesetenv did not handle FE_DFL_ENV, now fcsr is cleared in that
case.
Szabolcs Nagy [Sun, 8 Feb 2015 16:41:56 +0000 (17:41 +0100)]
math: fix __fpclassifyl(-0.0) for IEEE binary128
The sign bit was not cleared before checking for 0 so -0.0
was misclassified as FP_SUBNORMAL instead of FP_ZERO.
Szabolcs Nagy [Sun, 8 Feb 2015 16:40:54 +0000 (17:40 +0100)]
add parenthesis in fma.c to clarify intent and silence warnings
Rich Felker [Sat, 7 Feb 2015 19:01:34 +0000 (14:01 -0500)]
make getaddrinfo support SOCK_RAW and other socket types
all socket types are accepted at this point, but that may be changed
at a later time if the behavior is not meaningful for other types. as
before, omitting type (a value of 0) gives both UDP and TCP results,
and SOCK_DGRAM or SOCK_STREAM restricts to UDP or TCP, respectively.
for other socket types, the service name argument is required to be a
null pointer, and the protocol number provided by the caller is used.
Szabolcs Nagy [Sat, 7 Feb 2015 16:25:58 +0000 (17:25 +0100)]
remove cruft from x86_64 syscall.h
x86_64 syscall.h defined some musl internal syscall names and made
them public. These defines were already moved to src/internal/syscall.h
(except for SYS_fadvise which is added now) so the cruft in x86_64
syscall.h is not needed.
Rich Felker [Fri, 6 Feb 2015 04:34:27 +0000 (23:34 -0500)]
fix failure of fchmodat to report EOPNOTSUPP in the race path
in the case where a non-symlink file was replaced by a symlink during
the fchmodat operation with AT_SYMLINK_NOFOLLOW, mode change on the
new symlink target was successfully suppressed, but the error was not
reported. instead, fchmodat simply returned 0.
Rich Felker [Thu, 5 Feb 2015 03:50:40 +0000 (22:50 -0500)]
fix fd leak race (missing O_CLOEXEC) in fchmodat
Rich Felker [Tue, 3 Feb 2015 05:31:35 +0000 (00:31 -0500)]
make execvp continue PATH search on EACCES rather than issuing an errror
the specification for execvp itself is unclear as to whether
encountering a file that cannot be executed due to EACCES during the
PATH search is a mandatory error condition; however, XBD 8.3's
specification of the PATH environment variable clarifies that the
search continues until a file with "appropriate execution permissions"
is found.
since it seems undesirable/erroneous to report ENOENT rather than
EACCES when an early path element has a non-executable file and all
later path elements lack any file by the requested name, the new code
stores a flag indicating that EACCES was seen and sets errno back to
EACCES in this case.
Rich Felker [Tue, 3 Feb 2015 05:16:55 +0000 (00:16 -0500)]
fix missing memory barrier in cancellation signal handler
in practice this was probably a non-issue, because the necessary
barrier almost certainly exists in kernel space -- implementing signal
delivery without such a barrier seems impossible -- but for the sake
of correctness, it should be done here too.
in principle, without a barrier, it is possible that the thread to be
cancelled does not see the store of its cancellation flag performed by
another thread. this affects both the case where the signal arrives
before entering the critical program counter range from __cp_begin to
__cp_end (in which case both the signal handler and the inline check
fail to see the value which was already stored) and the case where the
signal arrives during the critical range (in which case the signal
handler should be responsible for cancellation, but when it does not
see the cancellation flag, it assumes the signal is spurious and
refuses to act on it).
in the fix, the barrier is placed only in the signal handler, not in
the inline check at the beginning of the critical program counter
range. if the signal handler runs before the critical range is
entered, it will of course take no action, but its barrier will ensure
that the inline check subsequently sees the store. if on the other
hand the inline check runs first, it may miss seeing the store, but
the subsequent signal handler in the critical range will act upon the
cancellation request. this strategy avoids adding a memory barrier in
the common, non-cancellation code path.
Felix Janda [Sun, 1 Feb 2015 09:43:37 +0000 (10:43 +0100)]
fix typo in x86_64/x32 user_fpregs_struct
mxcs_mask should be mxcr_mask
Trutz Behn [Wed, 28 Jan 2015 17:46:54 +0000 (18:46 +0100)]
make fsync, fdatasync, and msync cancellation points
these are mandatory cancellation points per POSIX, so their omission
was a conformance bug.
Trutz Behn [Wed, 28 Jan 2015 17:46:52 +0000 (18:46 +0100)]
move MREMAP_MAYMOVE and MREMAP_FIXED out of bits
the definitions are generic for all kernel archs. exposure of these
macros now only occurs on the same feature test as for the function
accepting them, which is believed to be more correct.
Trutz Behn [Wed, 28 Jan 2015 17:46:49 +0000 (18:46 +0100)]
fix missing comma in sh setjmp asm
this typo did not result in an erroneous setjmp with at least binutils
2.22 but fix it for clarity and compatibility with potentially stricter
sh assemblers.
Trutz Behn [Wed, 28 Jan 2015 17:46:46 +0000 (18:46 +0100)]
remove mips-only EINIT and EREMDEV errnos
the errno values are unused by the kernel and the macro definitions were
never exposed by glibc.
Rich Felker [Sat, 31 Jan 2015 02:54:58 +0000 (21:54 -0500)]
fix failure of configure to detect gcc due to message translations
based on patch by Vadim Ushakov. in general overriding LC_ALL rather
than specific categories (here, LC_MESSAGES) is undesirable, but
LC_ALL is easier and in this case there is nothing else that depends
on the locale in this invocation of the compiler.
Rich Felker [Wed, 21 Jan 2015 19:26:05 +0000 (14:26 -0500)]
fix erroneous return of partial username matches by getspnam[_r]
when using /etc/shadow (rather than tcb) as its backend, getspnam_r
matched any username starting with the caller-provided string rather
than requiring an exact match. in practice this seems to have affected
only systems where one valid username is a prefix for another valid
username, and where the longer username appears first in the shadow
file.