| Commit message (Expand) | Author | Age | Files | Lines |
* | Remove some, but not all, assumptions that the BSP is CPU 0 and that CPUs | Nathan Whitehorn | 2017-11-25 | 1 | -1/+3 |
* | sys: further adoption of SPDX licensing ID tags. | Pedro F. Giffuni | 2017-11-20 | 1 | -0/+2 |
* | Remove register keyword from sys/ and ANSIfy prototypes | Ed Maste | 2017-05-17 | 1 | -11/+7 |
* | Initialize 'ticks' earlier in boot after 'hz' is set. | John Baldwin | 2016-11-22 | 1 | -38/+0 |
* | Renumber license clauses in sys/kern to avoid skipping #3 | Ed Maste | 2016-09-15 | 1 | -1/+1 |
* | Prevent parallel tc_windup() calls, both parallel top-level calls from | Konstantin Belousov | 2016-07-27 | 1 | -6/+8 |
* | Do not acquire the thread lock in hardclock_cnt() unless needed. | Mark Johnston | 2016-05-18 | 1 | -3/+5 |
* | Add an EARLY_AP_STARTUP option to start APs earlier during boot. | John Baldwin | 2016-05-14 | 1 | -0/+33 |
* | sys: extend use of the howmany() macro when available. | Pedro F. Giffuni | 2016-04-26 | 1 | -3/+2 |
* | The struct thread td_estcpu member is only used by the 4BSD scheduler. | Konstantin Belousov | 2016-04-17 | 1 | -2/+0 |
* | Initialize ticks so that it wraps 10 minutes after boot to increase the | Peter Wemm | 2015-02-05 | 1 | -0/+5 |
* | The process spin lock currently has the following distinct uses: | Konstantin Belousov | 2014-11-26 | 1 | -8/+8 |
* | When sleeping waiting for the profiling stop, always set P_STOPPROF | Konstantin Belousov | 2014-11-10 | 1 | -3/+3 |
* | dtrace sdt: remove the ugly sname parameter of SDT_PROBE_DEFINE | Andriy Gapon | 2013-11-26 | 1 | -1/+1 |
* | - For kernel compiled only with KDTRACE_HOOKS and not any lock debugging | Attilio Rao | 2013-11-25 | 1 | -1/+0 |
* | Correct a bug that prevented deadlkres from (almost) ever firing. | Ryan Stone | 2013-06-28 | 1 | -8/+2 |
* | Add a generic way to call per event allocate / release function. | Fabien Thomas | 2013-03-05 | 1 | -1/+2 |
* | - Make callout(9) tickless, relying on eventtimers(4) as backend for | Davide Italiano | 2013-03-04 | 1 | -2/+1 |
* | Add support for good old 8192Hz profiling clock to software PMC. | Alexander Motin | 2013-02-26 | 1 | -0/+5 |
* | Mark 'ticks', 'time_second', and 'time_uptime' as volatile to prevent the | John Baldwin | 2013-01-28 | 1 | -2/+2 |
* | Implement the DTrace sched provider. This implementation aims to be | Ryan Stone | 2012-05-15 | 1 | -0/+6 |
* | Add software PMC support. | Fabien Thomas | 2012-03-28 | 1 | -1/+11 |
* | Idle ticks optimization: | Alexander Motin | 2012-03-10 | 1 | -16/+31 |
* | Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs. | Ed Schouten | 2011-11-07 | 1 | -1/+2 |
* | Fix interrupt counters dumping on SW_WATCHDOG fire. | Alexander Motin | 2011-09-27 | 1 | -1/+1 |
* | - Remove the eintrcnt/eintrnames usage and introduce the concept of | Attilio Rao | 2011-07-18 | 1 | -1/+1 |
* | Fix several places to ignore processes that are not yet fully constructed. | John Baldwin | 2011-04-06 | 1 | -0/+4 |
* | After some off-list discussion, revert a number of changes to the | Dimitry Andric | 2010-11-22 | 1 | -1/+1 |
* | Apply the STATIC_VNET_DEFINE and STATIC_DPCPU_DEFINE macros throughout | Dimitry Andric | 2010-11-14 | 1 | -1/+1 |
* | Tweak the waitchannel messages for the dead lock detection kthread. Use | John Baldwin | 2010-11-02 | 1 | -2/+2 |
* | Make kern_tc.c provide minimum frequency of tc_ticktock() calls, required | Alexander Motin | 2010-09-14 | 1 | -2/+2 |
* | Replace spin lock with the set of atomics. It is impractical for one | Alexander Motin | 2010-09-14 | 1 | -10/+14 |
* | Refactor timer management code with priority to one-shot operation mode. | Alexander Motin | 2010-09-13 | 1 | -52/+88 |
* | - Simplify logic in handling ticks wrap-up | Attilio Rao | 2010-07-07 | 1 | -13/+10 |
* | Fix a lock leak in the deadlock resolver in case the ticks counter | Attilio Rao | 2010-06-28 | 1 | -2/+6 |
* | Use ISO C99 integer types in sys/kern where possible. | Ed Schouten | 2010-06-21 | 1 | -1/+1 |
* | Implement new event timers infrastructure. It provides unified APIs for | Alexander Motin | 2010-06-20 | 1 | -6/+6 |
* | Update several places that iterate over CPUs to use CPU_FOREACH(). | John Baldwin | 2010-06-11 | 1 | -3/+1 |
* | - Implement MI helper functions, dividing one or two timer interrupts with | Alexander Motin | 2010-05-24 | 1 | -0/+52 |
* | getblk lockmgr is mostly used as a msleep() and may lead too easilly to | Attilio Rao | 2010-04-19 | 1 | -0/+1 |
* | - Introduce a blessed list for sxlocks that prevents the deadlkres to | Attilio Rao | 2010-04-11 | 1 | -1/+31 |
* | Introduce the new kernel thread called "deadlock resolver". | Attilio Rao | 2010-01-09 | 1 | -1/+121 |
* | Mark the clock sysctls as MPSAFE. | Ed Schouten | 2009-05-18 | 1 | -3/+4 |
* | - Implement generic macros for producing KTR records that are compatible | Jeff Roberson | 2009-01-17 | 1 | -2/+2 |
* | Implement per-cpu callout threads, wheels, and locks. | Jeff Roberson | 2008-04-02 | 1 | -23/+2 |
* | In keeping with style(9)'s recommendations on macros, use a ';' | Robert Watson | 2008-03-16 | 1 | -1/+1 |
* | Remove kernel support for M:N threading. | Jeff Roberson | 2008-03-12 | 1 | -8/+0 |
* | Add a new 'why' argument to kdb_enter(), and a set of constants to use | Robert Watson | 2007-12-25 | 1 | -1/+1 |
* | Move use of 'i' in cp_time sysctl under SCTL_MASK32 so that it compiles | Robert Watson | 2007-11-29 | 1 | -1/+2 |
* | Move the shared cp_time array (counts %sys, %user, %idle etc) to the | Peter Wemm | 2007-11-29 | 1 | -9/+72 |