summaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_cpu.c
Commit message (Expand)AuthorAgeFilesLines
* Add an EARLY_AP_STARTUP option to start APs earlier during boot.jhb2016-05-141-0/+4
* Pull in r267961 and r267973 again. Fix for issues reported will follow.hselasky2014-06-281-4/+2
* Revert r267961, r267973:gjb2014-06-271-2/+4
* Extend the meaning of the CTLFLAG_TUN flag to automatically check ifhselasky2014-06-271-4/+2
* In cf_get_method, when we don't already know what clock speed the CPU iscperciva2014-05-111-5/+6
* Free resources in an error case.brueffer2014-05-021-0/+1
* Retire smp_active. It was racey and caused demonstrated problems withscottl2014-04-261-1/+1
* Revert r175376 and tune cpufreq(4) frequency comparison logic instead.mav2012-03-101-21/+10
* Mark all SYSCTL_NODEs static that have no corresponding SYSCTL_DECLs.ed2011-11-071-1/+2
* cpufreq: allocate long-lived buffer for handling of sysctl requestsavg2010-07-231-7/+6
* Free allocated sbufs before returning ENOMEM.brueffer2010-01-081-2/+6
* Provide a new CPU device driver ivar to report the nominal speed of thenwhitehorn2009-05-311-12/+21
* If possible, try to obtain max_mhz on cpufreq attach instead of first request.mav2008-12-161-1/+8
* Fix a few edge cases with error handling in cpufreq(4)'s CPUFREQ_GET()jhb2008-05-051-3/+3
* Remove duplicate cpufreq levels, i.e. ones that are within 25 Mhz of eachnjl2008-01-161-0/+11
* If we're on an SMP kernel and there is more than 1 CPU, reject any attemptsnjl2007-10-301-1/+17
* Always call sched_bind(), even if on the CPU in question. It is wrong tonjl2007-08-201-25/+15
* Use a different loop variable for the inner loop. This previous reuse couldnjl2007-08-191-4/+4
* Commit 14/14 of sched_lock decomposition.jeff2007-06-051-8/+8
* Add an interface for drivers to be notified of changes to CPU frequency.njl2007-03-261-26/+40
* - Print message about cpufreq and timecounter TSCmnag2006-03-031-1/+8
* make saved cpu level stackable.ume2005-10-031-30/+53
* Break out the checks for duplicates and absolute settings being too highnjl2005-09-021-8/+17
* Eliminate cpufreq levels for two cases that are less than optimal:njl2005-08-301-47/+48
* - don't forget to save freqency when priority is raised.ume2005-08-181-3/+2
* don't forget to update curr_priority. even when frequency isume2005-08-181-0/+1
* Save cpu level only when priority is greater than PRIO_USERume2005-08-161-1/+1
* The "lowest" sysctl setting makes more sense as the lowest one to use, sonjl2005-08-111-2/+2
* Add debugging prints to all the methods in case there are problems withnjl2005-04-101-7/+70
* Add a check for cpufreq_unregister() being called with no cpufreq devicenjl2005-03-311-0/+5
* Add locking to handle multiple threads getting/setting frequencies at thenjl2005-02-271-15/+62
* Allow users to reject levels below a given frequency (in MHz) via thenjl2005-02-261-1/+17
* Bump the maximum number of levels to 64 and add warning messages aboutnjl2005-02-241-5/+15
* Add the "freq_settings" sysctl to each device that registers with cpufreqnjl2005-02-201-0/+41
* Introduce a new method, cpufreq_drv_type(), that returns the type of thenjl2005-02-181-6/+7
* When dealing with systems with no absolute drivers attached, only calibratenjl2005-02-151-10/+22
* Bind to the driver's parent cpu before switching, for both absolute andnjl2005-02-151-18/+28
* Implement priorities. This allows a driver (say, for cooling purposes) tonjl2005-02-141-4/+38
* Add support for the CPUFREQ_FLAG_INFO_ONLY flag. Devices that report thisnjl2005-02-131-1/+8
* Set levels on all CPUs and attach a cpufreq device to each one. Sysctlnjl2005-02-131-22/+62
* Add support for relative cpufreq drivers. Such drivers modulate clocknjl2005-02-061-27/+192
* Add the cpufreq framework. This code manages multiple drivers and presentsnjl2005-02-041-0/+532
OpenPOWER on IntegriCloud