about summary refs log tree commit diff
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* fix rare but nasty under-allocation bug in malloc with large requestsRich Felker2011-04-041-1/+1
| | | | | | | | | the bug appeared only with requests roughly 2*sizeof(size_t) to 4*sizeof(size_t) bytes smaller than a multiple of the page size, and only for requests large enough to be serviced by mmap instead of the normal heap. it was only ever observed on 64-bit machines but presumably could also affect 32-bit (albeit with a smaller window of opportunity).
* simplify vdprintf implementation greatly based on recent vfprintf changesRich Felker2011-04-041-5/+2
| | | | | | | since vfprintf will provide a temporary buffer in the case where the target FILE has a zero buffer size, don't bother setting up a real buffer for vdprintf. this also allows us to skip the call to fflush since we know everything will be written out before vfprintf returns.
* use a local temp buffer for unbuffered streams in vfprintfRich Felker2011-04-042-0/+14
| | | | | | | | | this change makes it so most calls to fprintf(stderr, ...) will result in a single writev syscall, as opposed to roughly 2*N syscalls (and possibly more) where N is the number of format specifiers. in principle we could use a much larger buffer, but it's best not to increase the stack requirements too much. most messages are under 80 chars.
* fix nl_langinfo to actually use the existing, correct internal versionRich Felker2011-04-032-15/+5
|
* make ualarm actually work (obsolete function removed from SUS)Rich Felker2011-04-031-4/+9
|
* fix various bugs in strtold:Rich Felker2011-04-031-10/+13
| | | | | | | | | | | 0e10000000000000000000000000000000 was setting ERANGE exponent char e/p was considered part of the match even if not followed by a valid decimal value "1e +10" was parsed as "1e+10" hex digits were misinterpreted as 0..5 instead of 10..15
* fix serious bug in strchr - char signednessRich Felker2011-04-031-9/+11
| | | | | | search for bytes with high bit set was giving (potentially dangerous) wrong results. i've tested, cleaned up, and hopefully sped up this function now.
* add setresuid/setresgid functions (nonstandard)Rich Felker2011-04-032-0/+20
|
* pthread_create need not set errnoRich Felker2011-04-031-1/+1
|
* fix statvfs syscalls (missing size argument)Rich Felker2011-04-032-2/+2
|
* block all signals during rsyscallRich Felker2011-04-031-4/+9
| | | | | otherwise a signal handler could see an inconsistent and nonconformant program state where different threads have different uids/gids.
* fix race condition in rsyscall handlerRich Felker2011-04-031-1/+1
| | | | | | | | | | | | | | | | | | the problem: there is a (single-instruction) race condition window between a thread flagging itself dead and decrementing itself from the thread count. if it receives the rsyscall signal at this exact moment, the rsyscall caller will never succeed in signalling enough flags to succeed, and will deadlock forever. in previous versions of musl, the about-to-terminate thread masked all signals prior to decrementing the thread count, but this cost a whole syscall just to account for extremely rare races. the solution is a huge hack: rather than blocking in the signal handler if the thread is dead, modify the signal mask of the saved context and return in order to prevent further signal handling by the dead thread. this allows the dead thread to continue decrementing the thread count (if it had not yet done so) and exiting, even while the live part of the program blocks for rsyscall.
* don't trust siginfo in rsyscall handlerRich Felker2011-04-031-3/+2
| | | | | | | | for some inexplicable reason, linux allows the sender of realtime signals to spoof its identity. permission checks for sending signals should limit the impact to same-user processes, but just to be safe, we avoid trusting the siginfo structure and instead simply examine the program state to see if we're in the middle of a legitimate rsyscall.
* timer threads should sleep and stay asleep... a long timeRich Felker2011-04-031-1/+1
|
* revert to deleting kernel-level timer from cancellation handlerRich Felker2011-04-032-7/+11
| | | | | this is necessary in order to avoid breaking timer_getoverrun in the last run of the timer event handler, if it has not yet finished.
* simplify calling of timer signal handlerRich Felker2011-04-033-12/+6
|
* simplify pthread tsd key handlingRich Felker2011-04-033-10/+7
|
* omit pthread tsd dtor code if tsd is not usedRich Felker2011-04-032-14/+24
|
* don't disable seeking after first seek failureRich Felker2011-04-021-8/+0
| | | | | this could cause problems if the application uses dup2(fd,fileno(f)) to redirect, and the old fd was not seekable but the new fd is.
* apparently fseek should not set the error flag on failed seekRich Felker2011-04-021-4/+1
|
* avoid over-allocation of brk on first mallocRich Felker2011-04-011-4/+4
| | | | | | | if init_malloc returns positive (successful first init), malloc will retry getting a chunk from the free bins rather than expanding the heap again. also pass init_malloc a hint for the size of the initial allocation.
* reorganize the __libc structure for threaded performance issuesRich Felker2011-04-011-6/+6
| | | | | | | we want to keep atomically updated fields (locks and thread count) and really anything writable far away from frequently-needed function pointers. stuff some rarely-needed function pointers in between to pad, hopefully up to a cache line boundary.
* simplify setting result on thread cancellationRich Felker2011-04-011-1/+1
|
* use bss instead of mmap for main thread's pthread thread-specific dataRich Felker2011-04-012-9/+4
| | | | this simplifies code and removes a failure case
* remove obsolete and useless useconds_t typeRich Felker2011-04-012-2/+2
|
* fix misspelled PTHREAD_CANCELED constantRich Felker2011-04-011-1/+1
|
* use a_store to set cancel flag in pthread_cancel, to ensure a barrierRich Felker2011-04-011-1/+1
|
* simplify pthread_key_deleteRich Felker2011-03-311-1/+1
| | | | | calling this function on an uninitialized key value is UB, so there is no need to check that the table pointer was initialized.
* greatly simplify pthread_key_create (~20% size reduction)Rich Felker2011-03-311-10/+9
|
* avoid all malloc/free in timer creation/destructionRich Felker2011-03-305-29/+20
| | | | | | | | | | instead of allocating a userspace structure for signal-based timers, simply use the kernel timer id. we use the fact that thread pointers will always be zero in the low bit (actually more) to encode integer timerid values as pointers. also, this change ensures that the timer_destroy syscall has completed before the library timer_destroy function returns, in case it matters.
* optimize timer creation and possibly protect against some minor racesRich Felker2011-03-302-16/+19
| | | | | | | | | the major idea of this patch is not to depend on having the timer pointer delivered to the signal handler, and instead use the thread pointer to get the callback function address and argument. this way, the parent thread can make the timer_create syscall while the child thread is starting, and it should never have to block waiting for the barrier.
* avoid crash on stupid but allowable usage of pthread_mutex_unlockRich Felker2011-03-301-1/+3
| | | | | | | unlocking an unlocked mutex is not UB for robust or error-checking mutexes, so we must avoid calling __pthread_self (which might crash due to lack of thread-register initialization) until after checking that the mutex is locked.
* rename __simple_malloc.c to lite_malloc.c - yes this affects behavior!Rich Felker2011-03-301-0/+0
| | | | | | | | | | | | | | | why does this affect behavior? well, the linker seems to traverse archive files starting from its current position when resolving symbols. since calloc.c comes alphabetically (and thus in sequence in the archive file) between __simple_malloc.c and malloc.c, attempts to resolve the "malloc" symbol for use by calloc.c were pulling in the full malloc.c implementation rather than the __simple_malloc.c implementation. as of now, lite_malloc.c and malloc.c are adjacent in the archive and in the correct order, so malloc.c should never be used to resolve "malloc" unless it's already needed to resolve another symbol ("free" or "realloc").
* streamline mutex unlock to remove a useless branch, use a_store to unlockRich Felker2011-03-301-2/+6
| | | | | | | | | this roughly halves the cost of pthread_mutex_unlock, at least for non-robust, normal-type mutexes. the a_store change is in preparation for future support of archs which require a memory barrier or special atomic store operation, and also should prevent the possibility of the compiler misordering writes.
* cheap special-case optimization for normal mutexesRich Felker2011-03-301-0/+4
| | | | | | | cycle-level benchmark on atom cpu showed typical pthread_mutex_lock call dropping from ~120 cycles to ~90 cycles with this change. benefit may vary with compiler options and version, but this optimization is very cheap to make and should always help some.
* reorder timer initialization so that timer_create does not depend on freeRich Felker2011-03-292-9/+17
| | | | | this allows small programs which only create times, but never delete them, to use simple_malloc instead of the full malloc.
* revert mutex "optimization" that turned out to be worseRich Felker2011-03-291-1/+1
|
* implement POSIX timersRich Felker2011-03-295-0/+143
| | | | | | | | this implementation is superior to the glibc/nptl implementation, in that it gives true realtime behavior. there is no risk of timer expiration events being lost due to failed thread creation or failed malloc, because the thread is created as time creation time, and reused until the timer is deleted.
* major improvements to cancellation handlingRich Felker2011-03-294-8/+19
| | | | | | | | | | | | | - there is no longer any risk of spoofing cancellation requests, since the cancel flag is set in pthread_cancel rather than in the signal handler. - cancellation signal is no longer unblocked when running the cancellation handlers. instead, pthread_create will cause any new threads created from a cancellation handler to unblock their own cancellation signal. - various tweaks in preparation for POSIX timer support.
* some preliminaries for adding POSIX timersRich Felker2011-03-291-0/+4
|
* fix tempnam name generation, and a small bug in tmpnam on retry limitRich Felker2011-03-292-21/+20
|
* make tmpfile fail after exceeding max tries.Rich Felker2011-03-291-2/+6
|
* fix tmpnam to generate better names, not depend on non-ISO-C symbolsRich Felker2011-03-291-25/+17
|
* fix messed-up errno if remove fails for a non-EISDIR reasonRich Felker2011-03-291-2/+2
|
* learned something new - remove is supposed to support directories on POSIXRich Felker2011-03-291-1/+3
|
* revert some more spin optimizations that turned out to be pessimizationsRich Felker2011-03-283-4/+3
|
* fix broken spinlock due to miscompilationRich Felker2011-03-281-1/+1
| | | | actually this trick also seems to have made the uncontended case slower.
* remove useless field in pthread struct (wasted a good bit of space)Rich Felker2011-03-281-1/+0
|
* fix getc - the classic error of trying to store EOF+0-255 in a char type..Rich Felker2011-03-281-3/+3
|
* major stdio overhaul, using readv/writev, plus other changesRich Felker2011-03-2837-281/+258
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | the biggest change in this commit is that stdio now uses readv to fill the caller's buffer and the FILE buffer with a single syscall, and likewise writev to flush the FILE buffer and write out the caller's buffer in a single syscall. making this change required fundamental architectural changes to stdio, so i also made a number of other improvements in the process: - the implementation no longer assumes that further io will fail following errors, and no longer blocks io when the error flag is set (though the latter could easily be changed back if desired) - unbuffered mode is no longer implemented as a one-byte buffer. as a consequence, scanf unreading has to use ungetc, to the unget buffer has been enlarged to hold at least 2 wide characters. - the FILE structure has been rearranged to maintain the locations of the fields that might be used in glibc getc/putc type macros, while shrinking the structure to save some space. - error cases for fflush, fseek, etc. should be more correct. - library-internal macros are used for getc_unlocked and putc_unlocked now, eliminating some ugly code duplication. __uflow and __overflow are no longer used anywhere but these macros. switch to read or write mode is also separated so the code can be better shared, e.g. with ungetc. - lots of other small things.