about summary refs log tree commit diff
path: root/nptl
Commit message (Collapse)AuthorAgeFilesLines
* Add a configure option to enable lock elision and disable by defaultAndi Kleen2013-07-022-0/+8
| | | | Can be enabled with --enable-lock-elision=yes at configure time.
* Disable elision for any pthread_mutexattr_settype callAndi Kleen2013-07-022-0/+10
| | | | | | | | | | PTHREAD_MUTEX_NORMAL requires deadlock for nesting, DEFAULT does not. Since glibc uses the same value (0) disable elision for any call to pthread_mutexattr_settype() with a 0 value. This implies that a program can disable elision by doing pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_NORMAL) Based on a original proposal by Rich Felker.
* Add elision to pthread_mutex_{try,timed,un}lockAndi Kleen2013-07-0214-24/+267
| | | | | | | | | | | | | | | | | | | | | | | Add elision paths to the basic mutex locks. The normal path has a check for RTM and upgrades the lock to RTM when available. Trylocks cannot automatically upgrade, so they check for elision every time. We use a 4 byte value in the mutex to store the lock elision adaptation state. This is separate from the adaptive spin state and uses a separate field. Condition variables currently do not support elision. Recursive mutexes and condition variables may be supported at some point, but are not in the current implementation. Also "trylock" will not automatically enable elision unless some other lock call has been already called on the lock. This version does not use IFUNC, so it means every lock has one additional check for elision. Benchmarking showed the overhead to be negligible.
* Add minimal test suite changes for elision enabled kernelsAndi Kleen2013-07-023-1/+28
| | | | | | tst-mutex5 and 8 test some behaviour not required by POSIX, that elision changes. This changes these tests to not check this when elision is enabled at configure time.
* Add new internal mutex type flags for elision.Andi Kleen2013-07-023-9/+43
| | | | | | | | | | Add Enable/disable flags used internally Extend the mutex initializers to have the fields needed for elision. The layout stays the same, and this is not visible to programs. These changes are not exposed outside pthread
* Add the low level infrastructure for pthreads lock elision with TSXAndi Kleen2013-07-0212-0/+502
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Lock elision using TSX is a technique to optimize lock scaling It allows to run locks in parallel using hardware support for a transactional execution mode in 4th generation Intel Core CPUs. See http://www.intel.com/software/tsx for more Information. This patch implements a simple adaptive lock elision algorithm based on RTM. It enables elision for the pthread mutexes and rwlocks. The algorithm keeps track whether a mutex successfully elides or not, and stops eliding for some time when it is not. When the CPU supports RTM the elision path is automatically tried, otherwise any elision is disabled. The adaptation algorithm and its tuning is currently preliminary. The code adds some checks to the lock fast paths. Micro-benchmarks show little to no difference without RTM. This patch implements the low level "lll_" code for lock elision. Followon patches hook this into the pthread implementation Changes with the RTM mutexes: ----------------------------- Lock elision in pthreads is generally compatible with existing programs. There are some obscure exceptions, which are expected to be uncommon. See the manual for more details. - A broken program that unlocks a free lock will crash. There are ways around this with some tradeoffs (more code in hot paths) I'm still undecided on what approach to take here; have to wait for testing reports. - pthread_mutex_destroy of a lock mutex will not return EBUSY but 0. - There's also a similar situation with trylock outside the mutex, "knowing" that the mutex must be held due to some other condition. In this case an assert failure cannot be recovered. This situation is usually an existing bug in the program. - Same applies to the rwlocks. Some of the return values changes (for example there is no EDEADLK for an elided lock, unless it aborts. However when elided it will also never deadlock of course) - Timing changes, so broken programs that make assumptions about specific timing may expose already existing latent problems. Note that these broken programs will break in other situations too (loaded system, new faster hardware, compiler optimizations etc.) - Programs with non recursive mutexes that take them recursively in a thread and which would always deadlock without elision may not always see a deadlock. The deadlock will only happen on an early or delayed abort (which typically happens at some point) This only happens for mutexes not explicitely set to PTHREAD_MUTEX_NORMAL or PTHREAD_MUTEX_ADAPTIVE_NP. PTHREAD_MUTEX_NORMAL mutexes do not elide. The elision default can be set at configure time. This patch implements the basic infrastructure for elision.
* BZ #12310: pthread_exit in static app. segfaultsVladimir Nikulichev2013-06-242-0/+9
| | | | | | | | | | | | | | | | Static applications that call pthread_exit on the main thread segfault. This is because after a thread terminates __libc_start_main decrements __nptl_nthreads which is only defined in pthread_create. Therefore the right solution is to add a requirement to pthread_create from pthread_exit. ~~~ nptl/ 2013-06-24 Vladimir Nikulichev <v.nikulichev@gmail.com> [BZ #12310] * pthread_exit.c: Add reference to pthread_create.
* Include <string.h> in nptl/pthread_setattr_default_np.c.Joseph Myers2013-06-222-0/+5
|
* PowerPC: Reserve TCB space for EBB frameworkAdhemerval Zanella2013-06-171-0/+5
| | | | | This patch reserves four pointer to be used in future Event-Based Branch framework for PowerPC.
* New API to set default thread attributesSiddhesh Poyarekar2013-06-1513-13/+643
| | | | | | | This patch introduces two new convenience functions to set the default thread attributes used for creating threads. This allows a programmer to set the default thread attributes just once in a process and then run pthread_create without additional attributes.
* Avoid access beyond memory bounds in pthread_attr_getaffinity_npSiddhesh Poyarekar2013-06-144-1/+80
| | | | | | | | | Resolves BZ #15618. pthread_attr_getaffinity_np may write beyond bounds of the input cpuset buffer if the size of the input buffer is smaller than the buffer present in the input pthread attributes. Fix is to copy to the extent of the minimum of the source and the destination.
* x86*: Return syscall error for lll_futex_wake.Carlos O'Donell2013-06-103-8/+17
| | | | | | | | | | | | | | | | | | | | | | It is very very possible that the futex syscall returns an error and that the caller of lll_futex_wake may want to look at that error and propagate the failure. This patch allows a caller to see the syscall error. There are no users of the syscall error at present, but future cleanups are now be able to check for the error. -- nplt/ 2013-06-10 Carlos O'Donell <carlos@redhat.com> * sysdeps/unix/sysv/linux/i386/lowlevellock.h (lll_futex_wake): Return syscall error. * sysdeps/unix/sysv/linux/x86_64/lowlevellock.h (lll_futex_wake): Return syscall error.
* Fix previous commit.Ondrej Bilka2013-06-081-2/+2
|
* Silence warning: __inline is not at beginning of declaration.Ondrej Bilka2013-06-082-1/+5
|
* Fix leading whitespaces.Ondrej Bilka2013-06-063-3/+8
|
* Remove trailing whitespace in nptl.Joseph Myers2013-06-0615-49/+67
|
* Link extra-libs consistently with libc and ld.so.Joseph Myers2013-05-312-8/+5
|
* Add #include <stdint.h> for uint[32|64]_t usage (except installed headers).Ryan S. Arnold2013-05-163-0/+8
|
* Reserve new TLS field for x86 and x86_64Andreas Jaeger2013-05-153-2/+12
| | | | | | | [BZ #10686] * sysdeps/x86_64/tls.h (struct tcbhead_t): Add __private_ss field. * sysdeps/i386/tls.h (struct tcbhead_t): Likewise.
* Fix tst-mutexpi8Andi Kleen2013-05-092-0/+18
| | | | | | 2013-05-09 Andi Kleen <ak@linux.intel.com> * tst-mutex8.c (do_test): Check for ENABLE_PI.
* Consolidate pthread_attr value validationSiddhesh Poyarekar2013-04-227-29/+98
| | | | | Define inline functions that wrap around validation for each of the pthread attributes to reduce duplication in code.
* Extend i486 pthread_cond_timedwait to use futex syscall with absolute timeoutAndreas Schwab2013-04-112-66/+321
|
* sem_post.c: Include atomic.h.Carlos O'Donell2013-04-072-0/+5
| | | | | | | | | | | | | | The sem_post.c file uses atomic functions without including atomic.h. Add `#include <atomic.h>' to the file to prevent any compile time warnings when other headers change and atomic.h isn't implicitly included. --- nptl/ 2013-04-07 Carlos O'Donell <carlos@redhat.com> * sysdeps/unix/sysv/linux/sem_post.c: Include atomic.h.
* Fix static build when configured with --disable-hidden-pltSiddhesh Poyarekar2013-04-042-1/+9
| | | | | | | | | | | | | | | Fixes BZ #15337. Static builds fail with the following warning: /home/tools/glibc/glibc/nptl/../nptl/sysdeps/unix/sysv/linux/x86_64/cancellation.S:80: undefined reference to `__GI___pthread_unwind' When the source is configured with --disable-hidden-plt. This is because the preprocessor conditional in cancellation.S only checks if the build is for SHARED, whereas hidden_def is defined appropriately only for a SHARED build that will have symbol versioning *and* hidden defs are enabled. The last case is false here.
* Avoid unconditional __call_tls_dtors calls in static linking.Roland McGrath2013-03-282-1/+9
|
* Fix up ChangeLogSiddhesh Poyarekar2013-03-191-6/+6
| | | | | I forgot to fix up the ChangeLog after renaming __default_attr to __default_pthread_attr in code.
* Move __default_stacksize into __default_pthread_attrSiddhesh Poyarekar2013-03-197-22/+26
| | | | | Make __default_pthread_attr object to store default attribute values for threads.
* Rename some static variablesSiddhesh Poyarekar2013-03-184-6/+19
| | | | Rename some static variables to give them unique names.
* Include atomic.h in generic lowlevellock.c.Carlos O'Donell2013-03-122-1/+5
|
* Rejigger i386 dl-sysdep.h files.Roland McGrath2013-03-043-50/+44
|
* Revert GLIBC_PTHREAD_DEFAULT_STACKSIZE changes.Carlos O'Donell2013-03-014-133/+31
| | | | | | | This reverts the change that allows the POSIX Thread default stack size to be changed by the environment variable GLIBC_PTHREAD_DEFAULT_STACKSIZE. It has been requested that more discussion happen before this change goes into 2.18.
* Fix build warningSiddhesh Poyarekar2013-03-012-0/+3
|
* Set default stack size from program environmentSiddhesh Poyarekar2013-03-014-23/+142
| | | | New environment variable GLIBC_PTHREAD_DEFAULT_STACKSIZE to do this.
* Add priority inheritance futex support on sparc.David S. Miller2013-02-212-0/+39
| | | | | | | | | * sysdeps/unix/sysv/linux/sparc/lowlevellock.h (FUTEX_WAIT_REQUEUE_PI): Define. (FUTEX_CMP_REQUEUE_PI): Likewise. (lll_futex_wait_requeue_pi): Likewise. (lll_futex_timed_wait_requeue_pi): Likewise. (lll_futex_cmp_requeue_pi): Likewise.
* nptl: Fix comment typo in fork.c.Carlos O'Donell2013-02-212-1/+5
|
* Fix ChangeLogsSiddhesh Poyarekar2013-02-181-0/+5
|
* C++11 thread_local destructors supportSiddhesh Poyarekar2013-02-181-0/+3
| | | | | | | | | | | This feature is specifically for the C++ compiler to offload calling thread_local object destructors on thread program exit, to glibc. This is to overcome the possible complication of destructors of thread_local objects getting called after the DSO in which they're defined is unloaded by the dynamic linker. The DSO is marked as 'unloadable' if it has a constructed thread_local object and marked as 'unloadable' again when all the constructed thread_local objects defined in it are destroyed.
* Fix build warnings in some test casesSiddhesh Poyarekar2013-02-183-0/+3
| | | | Include stdlib.h to get declaration of exit(3)
* FUTEX_*_REQUEUE_PI support for non-x86 codeSiddhesh Poyarekar2013-02-188-42/+252
| | | | | Add FUTEX_*_REQUEUE_PI support for the default C code and also add implementations for s-390 and ppc.
* Remove bounded-pointers build system support.Joseph Myers2013-02-151-1/+0
|
* Remove bp-sym.h and BP_SYM uses from C code.Joseph Myers2013-02-141-23/+22
|
* Don't use GLIBC_PRIVATE errno outside of librariesAndreas Schwab2013-02-045-0/+14
|
* Hide reference to mktemp in libpthreadAndreas Schwab2013-01-162-1/+6
|
* Remove unnecessary assert on attr in allocate_stack().Carlos O'Donell2013-01-112-1/+9
|
* Add --enable-hardcoded-path-in-tests configure optionH.J. Lu2013-01-113-12/+23
|
* Revert "Extend i486 pthread_cond_timedwait to use futex syscall with ↵Andreas Schwab2013-01-101-315/+66
| | | | | | absolute timeout" This reverts commit 1bd57044e963abb886cb912beadea714815a3d5c.
* Extend i486 pthread_cond_timedwait to use futex syscall with absolute timeoutAndreas Schwab2013-01-101-66/+315
| | | | | | * sysdeps/unix/sysv/linux/i386/i486/pthread_cond_timedwait.S (__pthread_cond_timedwait): If possible use FUTEX_WAIT_BITSET to directly use absolute timeout.
* Update copyright notices with scripts/update-copyrights.Joseph Myers2013-01-02649-653/+653
|
* Add script to update copyright notices and reformat some to facilitate its use.Joseph Myers2013-01-012-1/+6
|
* Convert pthread_rwlock_try(rd/wr)lock to prototypesAndi Kleen2012-12-283-6/+11
| | | | | | | | | | 2012-12-28 Andi Kleen <ak@linux.intel.com> * pthread_rwlock_tryrdlock.c (__pthread_rwlock_tryrdlock): * Convert to prototype. * pthread_rwlock_trywrlock.c (__pthread_rwlock_trywrlock): Likewise.