summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_switch.c
Commit message (Expand)AuthorAgeFilesLines
* - Use DPCPU for SCHED_STATS. This is somewhat awkward because thejeff2009-06-251-18/+37
* fix typo in runz_fuzzjulian2008-05-121-1/+1
* - Make SCHED_STATS more generic by adding a wrapper to create thejeff2008-04-171-25/+41
* - Restore runq to manipulating threads directly by putting runq links andjeff2008-03-201-64/+49
* - Remove the unused and redundant sched_newproc() function.jeff2008-03-201-34/+0
* - Move maybe_preempt() from kern_switch.c to sched_4bsd.c. This is functionjeff2008-03-201-113/+26
* In keeping with style(9)'s recommendations on macros, use a ';'rwatson2008-03-161-1/+1
* Remove kernel support for M:N threading.jeff2008-03-121-1/+1
* generally we are interested in what thread did something asjulian2007-11-141-3/+3
* - Fix ULE in kernels without PREEMPTION compiled in by always enabling thejeff2007-10-081-12/+1
* Fix some entries in the locks static table of witness.attilio2007-09-201-1/+0
* - Move all of the PS_ flags into either p_flag or td_flags.jeff2007-09-171-2/+2
* - Improve runq_findbit_from() which is used by ULE's circular queue. Maskjeff2007-08-201-32/+22
* - Set SW_PREEMPT when we preempt in critical_exit().jeff2007-08-031-1/+1
* - Remove explicit references to sched_lock. A simpler assert will do.jeff2007-07-191-2/+1
* - Garbage collect unused concurrency functions.jeff2007-06-121-23/+0
* Commit 1/14 of sched_lock decomposition.jeff2007-06-041-21/+71
* - Change types for necent runq additions to u_char rather than int.jeff2007-02-081-5/+5
* - Remove setrunqueue and replace it with direct calls to sched_add().jeff2007-01-231-82/+3
* - Don't pass a pointer into runq_choose_from(). The caller can adjust thejeff2007-01-041-3/+2
* - Add three new functions to support circular run queues.jeff2007-01-041-4/+93
* Prefer a more traditional spelling of inhibited in comments and panicrwatson2006-12-311-2/+2
* Threading cleanup.. part 2 of several.julian2006-12-061-573/+62
* Make KSE a kernel option, turned on by default in all GENERICjb2006-10-261-0/+68
* Add scheduler CORE, the work I have done half a year ago, recent,davidxu2006-06-131-1/+6
* sched_rem() already sets ke->ke_state to KES_THREAD, so there's no needcognet2006-06-011-2/+0
* Trim trailing whitespace.kan2005-12-281-46/+45
* Restore KTR_CRITICAL but conditionally compile it in as KTR_SCHED.njl2005-12-181-2/+9
* Clean up unused or poorly utilized KTR values. Remove KTR_FS, KTR_KGDB,njl2005-12-171-2/+2
* In adjustrunqueue(), add code to handle thread migrating case fordavidxu2005-08-031-1/+6
* Restore preemption of idle threads.ups2005-06-101-3/+1
* Lots of whitespace cleanup.ups2005-06-091-5/+6
* Fix some race conditions for pinned threads that may cause them to runups2005-06-091-18/+30
* Use low level constructs borrowed from interrupt threads to wait forups2005-05-231-11/+4
* Fix a bug that caused preemption to happen for a thread in the sameups2005-05-191-2/+2
* Sprinkle some volatile magic and rearrange things a bit to avoid raceups2005-04-081-5/+11
* Divorce critical sections from spinlocks. Critical sections as denoted byjhb2005-04-041-4/+0
* Add a read-only kern.sched.preemption sysctl so that user space can tellrwatson2005-03-201-0/+13
* A further step on the journey of meaking panics and debugging more reliable:rwatson2005-03-171-2/+3
* /* -> /*- for copyright notices, minor format tweaks as necessaryimp2005-01-061-1/+1
* - Define KTR points for KTR_SCHED.jeff2004-12-261-0/+3
* - Garbage collect several unused members of struct kse and struce ksegrp.jeff2004-12-141-6/+0
* Remove local definitions of RANGEOF() and use __rangeof() instead.das2004-11-201-2/+0
* Add basic critical section tracing to KTR using event type KTR_CRITICAL.rwatson2004-11-071-0/+4
* If a process needs to be swapped in, wakeup the swapper from withinscottl2004-10-161-0/+4
* Fix maybe_preempt_in_ksegrp for !SMP.ups2004-10-131-7/+33
* Make !SMP kernels compile, and as far as I can tell, work again.phk2004-10-121-1/+2
* Prevent preemption in slot_fill.ups2004-10-121-1/+110
* Don't release the slot twice.. sched_rem() has already done it.julian2004-10-101-1/+0
* When preempting a thread, put it back on the HEAD of its run queue.julian2004-10-051-6/+8
OpenPOWER on IntegriCloud