aboutsummaryrefslogtreecommitdiff
path: root/sys/vm/vm_glue.c
Commit message (Expand)AuthorAgeFilesLines
* Use a single VM object for kernel stacks.Mark Johnston2020-04-261-48/+49
* Convert a few triviail consumers to the new unlocked grab API.Jeff Roberson2020-02-281-3/+1
* Don't release xbusy on kmem pages. After lockless page lookup we will notJeff Roberson2020-02-191-4/+2
* Consistently use busy and vm_page_valid() rather than touching page bitsJeff Roberson2020-01-231-4/+6
* vm: add missing CLTFLAG_MPSAFE annotationsMateusz Guzik2020-01-121-3/+3
* UMA NUMA flag day. UMA_ZONE_NUMA was a source of confusion. Make the namesJeff Roberson2020-01-041-1/+1
* vm: fix sysctl vm.kstack_cache_size change reportMateusz Guzik2019-12-071-5/+5
* Fix a few places that free a page from an object without busy held. This isJeff Roberson2019-12-021-0/+1
* Revise the page cache size policy.Mark Johnston2019-11-221-4/+5
* sys/vm/vm_glue.c: Incorrect function name in panic stringAllan Jude2019-09-191-2/+2
* Replace redundant code with a few new vm_page_grab facilities:Jeff Roberson2019-09-101-16/+3
* Change synchonization rules for vm_page reference counting.Mark Johnston2019-09-091-6/+0
* Wire pages in vm_page_grab() when appropriate.Mark Johnston2019-08-281-1/+1
* Handle UMA_ANYDOMAIN in kstack_import().Mark Johnston2019-08-251-2/+8
* Cache kernel stacks in UMA. This gives us NUMA support, better concurrency,Jeff Roberson2019-08-061-78/+97
* Merge the vm_page hold and wire mechanisms.Mark Johnston2019-07-081-6/+4
* Replace uses of vm_page_unwire(m, PQ_NONE) with vm_page_unwire_noq(m).Mark Johnston2019-06-071-1/+1
* Provide separate accounting for user-wired pages.Mark Johnston2019-05-131-14/+1
* Refactor domainset iterators for use by malloc(9) and UMA.Mark Johnston2018-10-231-1/+1
* Fix the build after r339601.Mark Johnston2018-10-221-2/+2
* Swap in processes unless there's a global memory shortage.Mark Johnston2018-10-221-1/+13
* vm: check for empty kstack cache before lockingMateusz Guzik2018-09-191-1/+1
* Avoid resource deadlocks when one domain has exhausted its memory. AttemptMark Johnston2018-09-061-3/+5
* Remove {max/min}_offset() macros, use vm_map_{max/min}() inlines.Konstantin Belousov2018-08-291-1/+1
* Account the size of the vslock-ed memory by the thread.Konstantin Belousov2018-03-241-1/+8
* Make v_wire_count a per-cpu counter(9) counter. This eliminates aJeff Roberson2018-02-121-1/+1
* Use per-domain locks for vm page queue free. Move paging control fromJeff Roberson2018-02-061-1/+1
* ANSIfy function definitions in sys/vm/Ed Maste2018-01-121-12/+4
* SPDX: Consider code from Carnegie-Mellon University.Pedro F. Giffuni2017-11-301-1/+1
* sys: further adoption of SPDX licensing ID tags.Pedro F. Giffuni2017-11-201-0/+2
* Move swapout code into vm/vm_swapout.c.Konstantin Belousov2017-10-201-501/+0
* Modify vm_page_grab_pages() to handle VM_ALLOC_NOWAIT.Mark Johnston2017-08-111-2/+2
* Introduce vm_page_grab_pages(), which is intended to replace loops callingAlan Cox2017-08-091-13/+7
* Renumber copyright clause 4Warner Losh2017-02-281-1/+1
* Eliminate unneeded vm_page_xbusy() and vm_page_xunbusy() operations whenAlan Cox2016-08-141-2/+3
* Fix a LOR between vnode locks and allproc_lock.Konstantin Belousov2016-06-221-10/+21
* Remove false claim. Giant is dropped by mi_startup() before passingKonstantin Belousov2016-05-221-2/+0
* sys/vm: minor spelling fixes in comments.Pedro F. Giffuni2016-05-021-2/+2
* A change to KPI of vm_pager_get_pages() and underlying VOP_GETPAGES().Gleb Smirnoff2015-12-161-25/+25
* Exploit r288122 to avoid pointlessly enqueueing a page that is about to beAlan Cox2015-10-091-1/+1
* Make kstack_pages a tunable on arm, x86, and powepc. On i386, theKonstantin Belousov2015-08-101-5/+5
* Make KPI of vm_pager_get_pages() more strict: if a pager changes a pageGleb Smirnoff2015-06-121-9/+8
* Add kernel option KSTACK_USAGE_PROF to sample the stack depth onKonstantin Belousov2014-10-041-0/+49
* If vm_page_grab() allocates a new page, the page is not inserted intoKonstantin Belousov2014-08-131-0/+1
* - Modify vm_page_unwire() and vm_page_enqueue() to directly acceptAttilio Rao2014-06-161-2/+2
* Rename global cnt to vm_cnt to avoid shadowing.Bryan Drewery2014-03-221-1/+1
* Remove the deprecated VM_ALLOC_RETRY flag for the vm_page_grab(9).Konstantin Belousov2013-08-221-3/+3
* The soft and hard busy mechanism rely on the vm object lock to work.Attilio Rao2013-08-091-12/+8
* Replace kernel virtual address space allocation with vmem. This providesJeff Roberson2013-08-071-5/+9
* Revert r253939:Attilio Rao2013-08-051-7/+9
generated by cgit v1.2.3 (git 2.25.1) at 2024-10-28 18:29:08 +0000