summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_mutex.c
Commit message (Expand)AuthorAgeFilesLines
* Unbreak mutex profiling (at least for me).mtm2003-02-251-3/+15
* There's absolutely no need for a struct-within-a-struct, so move thedes2003-01-211-14/+12
* Disable the kernacc() check in mtx_validate() until such time that kernaccphk2002-10-251-0/+5
* Whitespace cleanup.des2002-10-231-10/+9
* Change the `mutex_prof' structure to use three variables containedrobert2002-10-221-18/+14
* Reduce the overhead of the mutex statistics gathering code, try to producedes2002-10-211-19/+28
* - Create a new scheduler api that is defined in sys/sched.hjeff2002-10-121-4/+2
* Rename the mutex thread and process states to use a more generic 'LOCK'jhb2002-10-021-13/+13
* uh, commit all of the patchjulian2002-09-291-0/+1
* commit the version I actually tested..julian2002-09-291-2/+4
* Implement basic KSE loaning. This stops a hread that is blocked in BOUND modejulian2002-09-291-1/+2
* Completely redo thread states.julian2002-09-111-7/+6
* Add some KASSERT()'s to ensure that we don't perform spin mutex ops onjhb2002-09-031-4/+16
* Add a new KTR type KTR_CONTENTION, and use it in the mutex code toiedowse2002-08-261-0/+20
* Disable optimization of spinlocks on UP kernels w/o debugging for nowjhb2002-07-271-2/+2
* Add mtx_ prefixes to the fields used for mutex profiling, and fix a bugdes2002-07-031-11/+12
* Part 1 of KSE-IIIjulian2002-06-291-15/+16
* Replace thread_runnable() with thread_running() as the latter is morejhb2002-06-041-6/+5
* Optimize the adaptive mutex spin a bit. Use a simple while loop withjhb2002-06-041-1/+4
* Add a private thread_runnable() macro to make the code more readable andjhb2002-06-041-3/+5
* Make the counters uintmax_ts, and use %ju rather than %llu.des2002-05-231-2/+3
* Rename pause() to ia32_pause() so it doesn't conflict with the pause()jhb2002-05-221-5/+5
* Rename cpu_pause() to pause(). Originally I was going to make this anjhb2002-05-221-5/+5
* Add appropriate IA32 "pause" instructions to improve performanec onjhb2002-05-211-1/+17
* Fix an old cut 'n' paste bug inherited from BSD/OS: don't increment 'i'jhb2002-05-211-1/+1
* Whitespace fixup, properly indent the body of an else clause.jhb2002-05-211-2/+2
* Add code to make default mutexes adaptive if the ADAPTIVE_MUTEXES kerneljhb2002-05-211-0/+26
* Optimize spin mutexes for UP kernels without debugging to just enter andjhb2002-05-211-0/+8
* Change mtx_init() to now take an extra argument. The third argument isjhb2002-04-041-8/+11
* Revert to open hashing. It makes the code simpler, and works farily welldes2002-04-021-16/+10
* - Move the MI mutexes sched_lock and Giant from being declared in thejhb2002-04-021-0/+27
* Spelling police.jhb2002-04-021-1/+1
* - Add MTX_SYSINIT and SX_SYSINIT as macro glue for allowing sx and mtxarr2002-04-021-0/+11
* Instead of get_cyclecount(9), use nanotime(9) to record acquisition anddes2002-04-021-19/+28
* Mutex profiling code, conditional on the MUTEX_PROFILING option. Adds thedes2002-04-021-2/+159
* Add a new mtx_init option "MTX_DUPOK" which allows duplicate acquires of locksjeff2002-03-271-1/+3
* Remove __P.alfred2002-03-191-1/+1
* Tidy up some unused variablespeter2002-02-201-5/+0
* Add kern_giant_ucred to instrument Giant around ucred related operationsdillon2002-02-181-0/+2
* In a threaded world, differnt priorirites become properties ofjulian2002-02-111-15/+13
* Use the mtx_owner() macro in one spot in _mtx_lock_sleep() to make thejhb2002-02-091-1/+1
* Bump the limits for determining if we've held a spinlock too long as theyjhb2002-01-151-2/+2
* Change the preemption code for software interrupt thread schedules andjhb2002-01-051-11/+3
* Modify the critical section API as follows:jhb2001-12-181-5/+3
* Remove definition of witness and comment stating that this file implementsjhb2001-11-151-22/+1
* Add mtx_lock_giant() and mtx_unlock_giant() wrappers for sysctl managementdillon2001-10-261-0/+42
* The mtx_init() and sx_init() functions bzero'd locks before handing themjhb2001-10-201-1/+3
* Remove superflous parens after de-macroizing.jhb2001-09-261-2/+2
* Since we no longer inline any debugging code in the mutex operations, movejhb2001-09-221-4/+24
* Fix a bug in propagate priority: the kse group pointer wasn't beingjhb2001-09-191-0/+1
OpenPOWER on IntegriCloud