| Commit message (Expand) | Author | Age | Files | Lines |
* | MFC r285706,r303562,r303563,r303584,r303643,r303652,r303655,r303707: | mjg | 2016-12-31 | 1 | -0/+29 |
* | MFC 261517,261520: | jhb | 2014-02-18 | 1 | -3/+0 |
* | Several improvements to rmlock(9). Many of these are based on patches | jhb | 2013-06-25 | 1 | -0/+1 |
* | - Implement run-time expansion of the KTR buffer via sysctl. | jeff | 2012-11-15 | 1 | -25/+4 |
* | panic: add a switch and infrastructure for stopping other CPUs in SMP case | avg | 2011-12-11 | 1 | -0/+5 |
* | Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs. | ed | 2011-11-07 | 1 | -2/+3 |
* | Explicitly wire the user buffer rather than doing it implicitly in | mdf | 2011-01-27 | 1 | -0/+3 |
* | Remove unneeded includes of <sys/linker_set.h>. Other headers that use | jhb | 2011-01-11 | 1 | -1/+0 |
* | Fix typos. | brucec | 2010-11-09 | 1 | -1/+1 |
* | Re-add r212370 now that the LOR in powerpc64 has been resolved: | mdf | 2010-09-16 | 1 | -14/+6 |
* | Revert r212370, as it causes a LOR on powerpc. powerpc does a few | mdf | 2010-09-13 | 1 | -6/+14 |
* | Add a drain function for struct sysctl_req, and use it for a variety of | mdf | 2010-09-09 | 1 | -14/+6 |
* | Use ISO C99 integer types in sys/kern where possible. | ed | 2010-06-21 | 1 | -6/+6 |
* | lock_profile_release_lock: do not compare unsigned with zero | avg | 2010-06-17 | 1 | -3/+5 |
* | Update several places that iterate over CPUs to use CPU_FOREACH(). | jhb | 2010-06-11 | 1 | -3/+1 |
* | - Implement a new mechanism for resetting lock profiling. We now | jeff | 2009-03-15 | 1 | -9/+101 |
* | - track maximum wait time | kmacy | 2008-07-27 | 1 | -4/+9 |
* | - Embed the recursion counter for any locking primitive directly in the | attilio | 2008-05-15 | 1 | -4/+1 |
* | Really, no explicit checks against against lock_class_* object should be | attilio | 2008-02-06 | 1 | -2/+2 |
* | Fix logic in skipcount handling (used to sample every 1/N lock operations | kris | 2008-01-08 | 1 | -1/+1 |
* | - Pause a while after disabling lock profiling and before resetting it | jeff | 2007-12-31 | 1 | -5/+11 |
* | - Re-implement lock profiling in such a way that it no longer breaks | jeff | 2007-12-15 | 1 | -222/+434 |
* | Initial checkin for rmlock (read mostly lock) a multi reader single writer | ups | 2007-11-08 | 1 | -0/+1 |
* | Currently the LO_NOPROFILE flag (which is masked on upper level code by | attilio | 2007-09-14 | 1 | -1/+1 |
* | Revert some debugging KTRs that were added during development. | kris | 2007-06-03 | 1 | -4/+0 |
* | Move lock_profile_object_{init,destroy}() into lock_{init,destroy}(). | jhb | 2007-05-18 | 1 | -0/+2 |
* | skip call to _lock_profile_obtain_lock_success entirely if acquisition time i... | kmacy | 2007-04-03 | 1 | -14/+11 |
* | general LOCK_PROFILING cleanup | kmacy | 2007-02-26 | 1 | -55/+6 |
* | Bug fix for obscenely large wait times on uncontested locks | kmacy | 2006-12-04 | 1 | -4/+4 |
* | track lock class name in a way that doesn't break WITNESS | kmacy | 2006-11-13 | 1 | -3/+4 |
* | Unbreak witness | kmacy | 2006-11-12 | 1 | -1/+1 |
* | show lock class in profiling output for default case where type is not specif... | kmacy | 2006-11-12 | 1 | -19/+22 |
* | tinderbox fix | kmacy | 2006-11-11 | 1 | -1/+1 |
* | remove lingering call to rd(tick) | kmacy | 2006-11-11 | 1 | -1/+1 |
* | missed nits replacing mutex with lock | kmacy | 2006-11-11 | 1 | -4/+4 |
* | MUTEX_PROFILING has been generalized to LOCK_PROFILING. We now profile | kmacy | 2006-11-11 | 1 | -0/+291 |
* | Add a basic reader/writer lock implementation to the kernel. This | jhb | 2006-01-27 | 1 | -0/+1 |
* | Always include the lock_classes[] array in the kernel. The | jhb | 2006-01-18 | 1 | -2/+0 |
* | Bah. Fix 'show lock' to actually be compiled in. I had just fixed this in | jhb | 2006-01-17 | 1 | -0/+3 |
* | Add a new file (kern/subr_lock.c) for holding code related to struct | jhb | 2006-01-17 | 1 | -0/+113 |