| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | - Close a race where a thread on another CPU could release a contested lock | jhb | 2003-11-12 | 1 | -4/+12 |
| * | Fix a typo in a comment. | jhb | 2003-11-12 | 1 | -1/+1 |
| * | Add an implementation of turnstiles and change the sleep mutex code to use | jhb | 2003-11-11 | 1 | -749/+462 |
| * | If a spin lock is held for too long and WITNESS is enabled, then call | jhb | 2003-07-31 | 1 | -3/+9 |
| * | When complaining about a sleeping thread owning a mutex, display the | jhb | 2003-07-30 | 1 | -1/+3 |
| * | - Add comments about the maintenance of the per-thread list of contested | jhb | 2003-07-02 | 1 | -4/+9 |
| * | Use __FBSDID(). | obrien | 2003-06-11 | 1 | -1/+3 |
| * | Add "" around mutex name to make message less confusing. | phk | 2003-05-31 | 1 | -1/+1 |
| * | Use TD_IS_RUNNING() instead of thread_running() in the adaptive mutex | jhb | 2003-04-17 | 1 | -7/+2 |
| * | Move the _oncpu entry from the KSE to the thread. | julian | 2003-04-10 | 1 | -1/+2 |
| * | Remove unused mtx_lock_giant(), mtx_unlock_giant(), related globals | tjr | 2003-03-23 | 1 | -43/+0 |
| * | Including <sys/stdint.h> is (almost?) universally only to be able to use | phk | 2003-03-18 | 1 | -1/+0 |
| * | Axe the useless MTX_SLEEPABLE flag. mutexes are not sleepable locks. | jhb | 2003-03-11 | 1 | -3/+1 |
| * | Remove safety belt: it is now ok to do a mtx_trylock() on a mutex you | jhb | 2003-03-04 | 1 | -5/+4 |
| * | Miscellaneous cleanups to _mtx_lock_sleep(): | jhb | 2003-03-04 | 1 | -4/+6 |
| * | Properly assert that mtx_trylock() is not called on a mutex we already | jhb | 2003-03-04 | 1 | -8/+4 |
| * | Unbreak mutex profiling (at least for me). | mtm | 2003-02-25 | 1 | -3/+15 |
| * | There's absolutely no need for a struct-within-a-struct, so move the | des | 2003-01-21 | 1 | -14/+12 |
| * | Disable the kernacc() check in mtx_validate() until such time that kernacc | phk | 2002-10-25 | 1 | -0/+5 |
| * | Whitespace cleanup. | des | 2002-10-23 | 1 | -10/+9 |
| * | Change the `mutex_prof' structure to use three variables contained | robert | 2002-10-22 | 1 | -18/+14 |
| * | Reduce the overhead of the mutex statistics gathering code, try to produce | des | 2002-10-21 | 1 | -19/+28 |
| * | - Create a new scheduler api that is defined in sys/sched.h | jeff | 2002-10-12 | 1 | -4/+2 |
| * | Rename the mutex thread and process states to use a more generic 'LOCK' | jhb | 2002-10-02 | 1 | -13/+13 |
| * | uh, commit all of the patch | julian | 2002-09-29 | 1 | -0/+1 |
| * | commit the version I actually tested.. | julian | 2002-09-29 | 1 | -2/+4 |
| * | Implement basic KSE loaning. This stops a hread that is blocked in BOUND mode | julian | 2002-09-29 | 1 | -1/+2 |
| * | Completely redo thread states. | julian | 2002-09-11 | 1 | -7/+6 |
| * | Add some KASSERT()'s to ensure that we don't perform spin mutex ops on | jhb | 2002-09-03 | 1 | -4/+16 |
| * | Add a new KTR type KTR_CONTENTION, and use it in the mutex code to | iedowse | 2002-08-26 | 1 | -0/+20 |
| * | Disable optimization of spinlocks on UP kernels w/o debugging for now | jhb | 2002-07-27 | 1 | -2/+2 |
| * | Add mtx_ prefixes to the fields used for mutex profiling, and fix a bug | des | 2002-07-03 | 1 | -11/+12 |
| * | Part 1 of KSE-III | julian | 2002-06-29 | 1 | -15/+16 |
| * | Replace thread_runnable() with thread_running() as the latter is more | jhb | 2002-06-04 | 1 | -6/+5 |
| * | Optimize the adaptive mutex spin a bit. Use a simple while loop with | jhb | 2002-06-04 | 1 | -1/+4 |
| * | Add a private thread_runnable() macro to make the code more readable and | jhb | 2002-06-04 | 1 | -3/+5 |
| * | Make the counters uintmax_ts, and use %ju rather than %llu. | des | 2002-05-23 | 1 | -2/+3 |
| * | Rename pause() to ia32_pause() so it doesn't conflict with the pause() | jhb | 2002-05-22 | 1 | -5/+5 |
| * | Rename cpu_pause() to pause(). Originally I was going to make this an | jhb | 2002-05-22 | 1 | -5/+5 |
| * | Add appropriate IA32 "pause" instructions to improve performanec on | jhb | 2002-05-21 | 1 | -1/+17 |
| * | Fix an old cut 'n' paste bug inherited from BSD/OS: don't increment 'i' | jhb | 2002-05-21 | 1 | -1/+1 |
| * | Whitespace fixup, properly indent the body of an else clause. | jhb | 2002-05-21 | 1 | -2/+2 |
| * | Add code to make default mutexes adaptive if the ADAPTIVE_MUTEXES kernel | jhb | 2002-05-21 | 1 | -0/+26 |
| * | Optimize spin mutexes for UP kernels without debugging to just enter and | jhb | 2002-05-21 | 1 | -0/+8 |
| * | Change mtx_init() to now take an extra argument. The third argument is | jhb | 2002-04-04 | 1 | -8/+11 |
| * | Revert to open hashing. It makes the code simpler, and works farily well | des | 2002-04-02 | 1 | -16/+10 |
| * | - Move the MI mutexes sched_lock and Giant from being declared in the | jhb | 2002-04-02 | 1 | -0/+27 |
| * | Spelling police. | jhb | 2002-04-02 | 1 | -1/+1 |
| * | - Add MTX_SYSINIT and SX_SYSINIT as macro glue for allowing sx and mtx | arr | 2002-04-02 | 1 | -0/+11 |
| * | Instead of get_cyclecount(9), use nanotime(9) to record acquisition and | des | 2002-04-02 | 1 | -19/+28 |
