| Commit message (Expand) | Author | Age | Files | Lines |
* | dtrace sdt: remove the ugly sname parameter of SDT_PROBE_DEFINE | avg | 2013-11-26 | 1 | -4/+4 |
* | - For kernel compiled only with KDTRACE_HOOKS and not any lock debugging | attilio | 2013-11-25 | 1 | -1/+0 |
* | Make the callout arithmetic more robust adding checks for overflow. | davide | 2013-09-26 | 1 | -1/+6 |
* | Fix callout_init_rm() in the shared case, allocating storage for 'struct | davide | 2013-09-20 | 1 | -3/+11 |
* | Specify SDT probe argument types in the probe definition itself rather than | markj | 2013-08-15 | 1 | -4/+2 |
* | Cache the callout precision argument as part of the informations required | davide | 2013-03-25 | 1 | -2/+9 |
* | Bring back the comment on the sizing of the callout array that got | andre | 2013-03-10 | 1 | -0/+2 |
* | Fixup r248032: | davide | 2013-03-09 | 1 | -1/+1 |
* | Move the callout subsystem initialization to its own SYSINIT() | andre | 2013-03-08 | 1 | -34/+25 |
* | Move the auto-sizing of the callout array from init_param2() to | andre | 2013-03-08 | 1 | -0/+14 |
* | Complete r247813: | davide | 2013-03-04 | 1 | -8/+8 |
* | Use C99 'bool' rather than Machish 'boolean_t'. | davide | 2013-03-04 | 1 | -2/+2 |
* | Fix build with DIAGNOSTIC/CALLOUT_PROFILING options turned on. | davide | 2013-03-04 | 1 | -9/+9 |
* | - Make callout(9) tickless, relying on eventtimers(4) as backend for | davide | 2013-03-04 | 1 | -238/+522 |
* | callwheelmask and callwheelsize are always greater than zero. | davide | 2013-03-03 | 1 | -1/+1 |
* | Remove a couple of unused include. | davide | 2013-03-03 | 1 | -1/+0 |
* | MFcalloutng: | mav | 2013-03-03 | 1 | -2/+2 |
* | MFcalloutng: | davide | 2013-02-28 | 1 | -2/+2 |
* | Fixup r243901: | attilio | 2012-12-05 | 1 | -9/+12 |
* | The softclock_call_cc() is executing with the callout already removed | kib | 2012-12-05 | 1 | -29/+32 |
* | replace bit shifting loop with 1<<fls(n), improve comments. | alfred | 2012-12-04 | 1 | -6/+4 |
* | Rework the known mutexes to benefit about staying on their own | attilio | 2012-10-31 | 1 | -2/+2 |
* | Pad and align the callout_cpu mtx to its own cacheline to reduce false | jimharris | 2012-10-31 | 1 | -1/+1 |
* | Move the code to call the callout callback into the helper function | kib | 2012-05-03 | 1 | -198/+181 |
* | When callout_reset_on() cannot immediately migrate a callout since it | kib | 2012-05-03 | 1 | -0/+36 |
* | Mark MALLOC_DEFINEs static that have no corresponding MALLOC_DECLAREs. | ed | 2011-11-07 | 1 | -1/+1 |
* | callout_cpu_switch() allows preemption when dropping the outcoming | attilio | 2011-08-21 | 1 | -0/+7 |
* | Reintroduce the fix already discussed in r216805 (please check its history | attilio | 2011-04-08 | 1 | -24/+198 |
* | Revert r216805. | attilio | 2011-01-08 | 1 | -119/+23 |
* | Fix several callout migration races: | attilio | 2010-12-29 | 1 | -23/+119 |
* | Remove 'softclock_ih' as it is no longer used. | jhb | 2010-11-03 | 1 | -4/+1 |
* | Fix callout_tickstofirst() behavior after signed integer ticks overflow. | mav | 2010-10-31 | 1 | -2/+1 |
* | Fix panic on NULL dereference possible after r212541. | mav | 2010-09-14 | 1 | -1/+2 |
* | Make kern_tc.c provide minimum frequency of tc_ticktock() calls, required | mav | 2010-09-14 | 1 | -2/+2 |
* | Refactor timer management code with priority to one-shot operation mode. | mav | 2010-09-13 | 1 | -2/+37 |
* | Add an extra comment to the SDT probes definition. This allows us to get | rpaulo | 2010-08-22 | 1 | -2/+2 |
* | Update several places that iterate over CPUs to use CPU_FOREACH(). | jhb | 2010-06-11 | 1 | -3/+1 |
* | Properly fix callout handling by putting all the per-cpu info in | luigi | 2009-12-14 | 1 | -3/+22 |
* | Make sure callouts are not processed one tick late. | luigi | 2009-09-12 | 1 | -2/+2 |
* | Add explicit static DTrace tracing to the callout mechanism, capturing | rwatson | 2009-01-24 | 1 | -0/+15 |
* | Add a new KTR tracepoint in the KTR_CALLOUT class to note when a callout | jhb | 2009-01-13 | 1 | -0/+1 |
* | After a machine has been up for a bit more than 20 days with HZ=1000, | peter | 2008-10-28 | 1 | -1/+1 |
* | add callout_schedule; besides being useful it also improves | sam | 2008-08-02 | 1 | -0/+15 |
* | Fix a race which could result in some timeout buckets being skipped. | jeff | 2008-07-19 | 1 | -6/+11 |
* | - Correct a major error introduced in the per-cpu timeout commit. Sleep | jeff | 2008-04-06 | 1 | -5/+5 |
* | Implement per-cpu callout threads, wheels, and locks. | jeff | 2008-04-02 | 1 | -124/+246 |
* | Fix a race where timeout/untimeout could cause crashes for Giant locked | alfred | 2008-03-22 | 1 | -4/+19 |
* | - Pass the priority argument from *sleep() into sleepq and down into | jeff | 2008-03-12 | 1 | -1/+1 |
* | Really, no explicit checks against against lock_class_* object should be | attilio | 2008-02-06 | 1 | -2/+2 |
* | Cache the value of c_lock as it can change, in the struct, | attilio | 2007-11-22 | 1 | -5/+7 |