summaryrefslogtreecommitdiffstats
path: root/sys/vm/uma_core.c
Commit message (Expand)AuthorAgeFilesLines
* Remove UMA_ZONE_REFCNT feature, now unused.glebius2016-03-011-83/+4
* Redo r292484. Embed task(9) into zone, so that uz_maxaction is calledglebius2016-02-031-4/+5
* Move uma_dbg_alloc() and uma_dbg_free() into uma_core.c, which allowsglebius2016-02-031-1/+102
* Add a safety net to reclaim mbufs when one of the mbuf zones becomejtl2015-12-201-0/+20
* Don't make assertions about td_critnest when the scheduler is stopped.markj2015-12-111-3/+2
* Consistently enforce the restriction against calling malloc/free when in ajtl2015-11-191-0/+7
* Exploit r288122 to address a cosmetic issue. Since the pages allocatedalc2015-09-261-1/+1
* Don't trash memory from UMA_ZONE_NOFREE zones.mjg2015-09-021-2/+2
* Make the UMA harvesting go away completely if not wanted. Default to "not wan...markm2015-08-221-4/+4
* Avoid sign extension of value passed to kva_alloc from uma_zone_reserve_kvazbb2015-08-101-2/+2
* Huge cleanup of random(4) code.markm2015-06-301-32/+4
* If INVARIANTS is specified, add ctor/dtor to junk memory if they arejmg2015-06-251-0/+14
* CALLOUT_MPSAFE has lost its meaning since r141428, i.e., for more than tenjkim2015-05-221-1/+1
* The vmem callback to reclaim kmem arena address space on low orkib2015-05-091-4/+38
* Eliminate an unused variable.alc2015-04-201-2/+1
* Rework r281162. Indeed, the flexible array member is preferable here.dchagin2015-04-121-1/+1
* UMA zone limit can be lowered, so remove protection against fromglebius2015-04-101-5/+2
* Properly calculate "UMA Zones" per cpu cache size. Avoid allocatingdchagin2015-04-061-1/+1
* Fix wrong kassert msg in uma.dchagin2015-04-051-2/+2
* Fix integer truncation bug in malloc(9)rstone2015-04-011-9/+9
* Set the SBUF_INCLUDENUL flag in sbuf_new_for_sysctl() so that sysctlian2015-03-141-0/+1
* Eliminate a stale debug message. The per-CPU cache locks were replacedalc2014-12-311-3/+0
* Provide mutual exclusion between zone allocation/destruction andkib2014-11-301-2/+31
* This is the much-discussed major upgrade to the random(4) device, known to yo...markm2014-10-301-0/+35
* Change the UMA mutex into a rwlockbryanv2014-10-051-20/+20
* Remove stray uma_mtx lock/unlock in zone_drain_wait()bryanv2014-10-051-2/+0
* Pull in r267961 and r267973 again. Fix for issues reported will follow.hselasky2014-06-281-2/+1
* Revert r267961, r267973:gjb2014-06-271-1/+2
* Extend the meaning of the CTLFLAG_TUN flag to automatically check ifhselasky2014-06-271-2/+1
* - Modify vm_page_unwire() and vm_page_enqueue() to directly acceptattilio2014-06-161-1/+1
* Introduce new "256 Bucket" zone to split requests and reduce congestionmav2014-06-121-1/+2
* Allocating new bucket for bucket zone, never take it from the zone itself,mav2014-06-121-0/+2
* After r251709, avoid a clang 3.4 warning about an unused static constdim2014-02-141-4/+1
* Make M_ZERO flag work correctly on UMA_ZONE_PCPU zones.glebius2014-02-101-2/+14
* Provide macros that allow easily export uma(9) zone limits andglebius2014-02-071-0/+29
* In keg_dtor(), print out the keg name in the "Freed UMA keg was not empty"rodrigc2013-11-291-1/+2
* - Add bucket size column to `show uma` DDB command.mav2013-11-281-5/+34
* Make UMA to not blindly force offpage slab header allocation for largemav2013-11-271-2/+16
* Don't count bucket allocation failures for UMA zones as their own failures.mav2013-11-271-5/+3
* Fix bug introduced at r252226, when udata argument passed to bucket_alloc()mav2013-11-271-3/+4
* When purging per-CPU UMA caches do not return empty buckets into the globalmav2013-11-231-4/+16
* Implement mechanism to safely but slowly purge UMA per-CPU caches.mav2013-11-191-0/+77
* Grow UMA zone bucket size also on lock congestion during item free.mav2013-11-191-2/+13
* Add two new UMA bucket zones to store 3 and 9 items per bucket.mav2013-11-191-0/+2
* Implement soft pressure on UMA cache bucket sizes.mav2013-11-191-0/+9
* Fix bug introduced in rewrite of keg_free_slab in -r251894.mckusick2013-08-311-1/+1
* Different consumers of the struct vm_page abuse pageq member to keepkib2013-08-101-13/+1
* Replace kernel virtual address space allocation with vmem. This providesjeff2013-08-071-6/+6
* Revert r249590 and in case if mp_ncpus isn't initialized use MAXCPU. Thisglebius2013-07-231-2/+3
* Remove a spurious keg lock acquisition.davide2013-06-281-1/+1
OpenPOWER on IntegriCloud