| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Handle lock recursion differenty by always checking against LO_RECURSABLE | attilio | 2009-06-02 | 1 | -6/+6 |
| * | Remove extra cpu_spinwait() invocations. This should really only be used | jhb | 2009-05-29 | 1 | -8/+0 |
| * | Tweak a few comments on adaptive spinning. | jhb | 2009-05-29 | 1 | -4/+10 |
| * | Add the OpenSolaris dtrace lockstat provider. The lockstat provider | sson | 2009-05-26 | 1 | -7/+90 |
| * | - Wrap lock profiling state variables in #ifdef LOCK_PROFILING blocks. | jeff | 2009-03-15 | 1 | -1/+5 |
| * | Remove even more unneeded variable assignments. | ed | 2009-02-26 | 1 | -1/+0 |
| * | add RW_SYSINIT_FLAGS macro and rw_sysinit_flags initialization function | kmacy | 2008-12-08 | 1 | -0/+8 |
| * | Teach WITNESS about the interlocks used with lockmgr. This removes a bunch | jhb | 2008-09-10 | 1 | -2/+2 |
| * | Various whitespace fixes. | jhb | 2008-09-10 | 1 | -1/+0 |
| * | Improve a comment which, in the actual CVS stock, doesn't completely | attilio | 2008-05-27 | 1 | -2/+5 |
| * | - Add sysctls at debug.rwlock to control the behavior of the speculative | jeff | 2008-04-04 | 1 | -3/+26 |
| * | Add rw_try_rlock() and rw_try_wlock() to rwlocks. | attilio | 2008-04-01 | 1 | -0/+49 |
| * | - In rw_wunlock_hard prefer to wakeup writers if there are both readers | jeff | 2008-02-07 | 1 | -4/+4 |
| * | Adaptive spinning in write path with readers and writer starvation avoidance. | jeff | 2008-02-06 | 1 | -154/+170 |
| * | Remove a conditional that is always true. | jhb | 2008-01-17 | 1 | -1/+1 |
| * | - Re-implement lock profiling in such a way that it no longer breaks | jeff | 2007-12-15 | 1 | -24/+7 |
| * | Simplify the adaptive spinning algorithm in rwlock and mutex: | attilio | 2007-11-26 | 1 | -112/+72 |
| * | Expand lock class with the "virtual" function lc_assert which will offer | attilio | 2007-11-18 | 1 | -0/+9 |
| * | Remove a bogus KASSERT which will prevent rwlock to be acquired | attilio | 2007-11-14 | 1 | -3/+0 |
| * | generally we are interested in what thread did something as | julian | 2007-11-14 | 1 | -1/+1 |
| * | Fix some problems with lock profiling in rw locks: | attilio | 2007-07-20 | 1 | -8/+28 |
| * | Introduce a new rwlocks initialization function: rw_init_flags. | attilio | 2007-06-26 | 1 | -9/+85 |
| * | Commit 3/14 of sched_lock decomposition. | jeff | 2007-06-04 | 1 | -26/+28 |
| * | Move lock_profile_object_{init,destroy}() into lock_{init,destroy}(). | jhb | 2007-05-18 | 1 | -2/+0 |
| * | Add destroyed cookie values for sx locks and rwlocks as well as extra | jhb | 2007-05-08 | 1 | -1/+17 |
| * | - Drop memory barriers in rw_try_upgrade(). We don't need an 'acq' memory | jhb | 2007-03-30 | 1 | -4/+4 |
| * | - Simplify the #ifdef's for adaptive mutexes and rwlocks by conditionally | jhb | 2007-03-22 | 1 | -23/+29 |
| * | Rename the 'mtx_object', 'rw_object', and 'sx_object' members of mutexes, | jhb | 2007-03-21 | 1 | -72/+72 |
| * | Print readers count as unsigned in ddb 'show lock'. | jhb | 2007-03-13 | 1 | -2/+2 |
| * | Fix a typo. | jhb | 2007-03-12 | 1 | -1/+1 |
| * | Add two new function pointers 'lc_lock' and 'lc_unlock' to lock classes. | jhb | 2007-03-09 | 1 | -0/+33 |
| * | Use C99-style struct member initialization for lock classes. | jhb | 2007-03-09 | 1 | -3/+3 |
| * | Fix some nits in lock profiling for rwlocks: | jhb | 2007-03-07 | 1 | -6/+9 |
| * | Further improvements to LOCK_PROFILING: | kmacy | 2007-02-27 | 1 | -2/+2 |
| * | Add rw_wowned() interface to rwlock(9), allowing a kernel thread to | rwatson | 2007-02-26 | 1 | -0/+7 |
| * | general LOCK_PROFILING cleanup | kmacy | 2007-02-26 | 1 | -11/+3 |
| * | track lock class name in a way that doesn't break WITNESS | kmacy | 2006-11-13 | 1 | -1/+1 |
| * | MUTEX_PROFILING has been generalized to LOCK_PROFILING. We now profile | kmacy | 2006-11-11 | 1 | -2/+20 |
| * | Adjust td_locks for non-spin mutexes, rwlocks, and sx locks so that it is | jhb | 2006-07-27 | 1 | -0/+4 |
| * | Implement rw_try_upgrade() and rw_downgrade(). rw_try_upgrade() makes a | jhb | 2006-04-19 | 1 | -2/+133 |
| * | 'owner' is not used without SMP. Fix kernel build for such kernel | wkoszek | 2006-04-18 | 1 | -0/+4 |
| * | Adaptively spin before blocking on the turnstile if an rwlock is write | jhb | 2006-04-18 | 1 | -7/+88 |
| * | - Add a rw_wowner() macro that just returns the owner of a write lock and | jhb | 2006-04-17 | 1 | -26/+38 |
| * | Fix another compile problem. If I find any more, this file is going in the | scottl | 2006-02-01 | 1 | -1/+1 |
| * | Regroup order of operations to better reflect what was probably intended. | scottl | 2006-01-30 | 1 | -3/+3 |
| * | Take a stab at making this compile when WITNESS is not defined. gcc can't | scottl | 2006-01-29 | 1 | -4/+4 |
| * | Unbreak on archs where %d doesn't print uintptr_t arithmetic. | mlaier | 2006-01-29 | 1 | -1/+2 |
| * | Add a basic reader/writer lock implementation to the kernel. This | jhb | 2006-01-27 | 1 | -0/+587 |
