summaryrefslogtreecommitdiffstats
path: root/sys/vm
Commit message (Expand)AuthorAgeFilesLines
* Correct contigmalloc2()'s implementation of M_ZERO. Specifically,alc2007-04-191-1/+1
* Correct two comments.alc2007-04-191-2/+2
* Minor typo fix, noticed while I was going through *_pager.c files.keramida2007-04-101-1/+1
* When KVA is exhausted, try the vm_lowmem event for the last time beforepjd2007-04-051-4/+14
* Fix a problem for file systems that don't implement VOP_BMAP() operation.pjd2007-04-051-0/+2
* Prevent a race between vm_object_collapse() and vm_object_split() fromalc2007-03-271-0/+8
* Two small changes to vm_map_pmap_enter():alc2007-03-251-4/+3
* vm_page_busy() no longer requires the page queues lock to be held. Reducealc2007-03-231-2/+2
* Change the order of lock reacquisition in vm_object_split() in order toalc2007-03-221-2/+5
* Use PCPU_LAZY_INC() to update page fault statistics.alc2007-03-051-6/+6
* Use pause() in vm_object_deallocate() to yield the CPU to the lock holderjhb2007-02-271-1/+1
* Use pause() rather than tsleep() on stack variables and function pointers.jhb2007-02-271-2/+1
* Change the way that unmanaged pages are created. Specifically,alc2007-02-256-48/+11
* Change the page's CLEANCHK flag from being a page queue mutex synchronizedalc2007-02-222-16/+16
* Enable vm_page_free() and vm_page_free_zero() to be called on some pagesalc2007-02-181-2/+4
* Remove a stale comment. Add punctuation to a nearby comment.alc2007-02-171-6/+1
* Relax the page queue lock assertions in vm_page_remove() andalc2007-02-151-2/+3
* Avoid the unnecessary acquisition of the free page queues lock when a pagealc2007-02-141-4/+5
* Add uma_set_align() interface, which will be called at most once duringrwatson2007-02-112-2/+26
* Use the free page queue mutex instead of the page queue mutex toalc2007-02-112-7/+6
* - Move 'struct swdevt' back into swap_pager.h and expose it to userland.jhb2007-02-072-31/+32
* Change the pagedaemon, vm_wait(), and vm_waitpfault() to sleep on thealc2007-02-072-15/+21
* Change the free page queue lock from a spin mutex to a default (blocking)alc2007-02-054-22/+22
* Fix for problems that occur when all mbuf clusters migrate to the mbuf packetmohans2007-01-252-2/+10
* Fix for a bug where only one process (of multiple) blocked onmohans2007-01-241-2/+7
* - Remove setrunqueue and replace it with direct calls to sched_add().jeff2007-01-232-3/+3
* Use FOREACH_PROC_IN_SYSTEM instead of using its unrolled form.delphij2007-01-172-2/+2
* Remove uma_zalloc_arg() hack, which coerced M_WAITOK to M_NOWAIT whenrwatson2007-01-101-22/+3
* Declare the map entry created by kmem_init() for the range fromalc2007-01-071-1/+2
* - Add a new function uma_zone_exhausted() to see if a zone is full.jhb2007-01-053-0/+25
* Optimize vm_object_split(). Specifically, make the number of iterationsalc2006-12-171-9/+14
* Simplify the computation of the new object's size in vm_object_split().alc2006-12-161-3/+2
* Remove the requirement that phys_avail be sorted in ascending orderkmacy2006-12-081-2/+10
* Threading cleanup.. part 2 of several.julian2006-12-062-43/+3
* The clean_map has been made local to vm_init.c long ago.ru2006-11-201-1/+0
* Remove a redundant pointer-type variable.ru2006-11-201-19/+18
* When counting vm totals, skip unreferenced objects, includingru2006-11-201-0/+7
* There is no point in setting PG_REFERENCED on kmem_object pages becausealc2006-11-131-6/+1
* Make pmap_enter() responsible for setting PG_WRITEABLE insteadalc2006-11-122-8/+3
* I misplaced the assertion that was added to vm_page_startup() in thealc2006-11-081-6/+6
* Simplify the construction of the free queues in vm_page_startup(). Addalc2006-11-081-2/+12
* Ensure that the page's oflags field is initialized by contigmalloc().alc2006-11-081-0/+1
* Sweep kernel replacing suser(9) calls with priv(9) calls, assigningrwatson2006-11-062-10/+11
* Make KSE a kernel option, turned on by default in all GENERICjb2006-10-262-1/+36
* Better align output of "show uma" by moving from displaying the basicrwatson2006-10-261-5/+7
* The page queues lock is no longer required by vm_page_wakeup().alc2006-10-234-8/+8
* The page queues lock is no longer required by vm_page_busy() oralc2006-10-222-5/+4
* Complete break-out of sys/sys/mac.h into sys/security/mac/mac_framework.hrwatson2006-10-222-2/+4
* Replace PG_BUSY with VPO_BUSY. In other words, changes to the page'salc2006-10-228-51/+59
* Eliminate unnecessary PG_BUSY tests. They originally served a purposealc2006-10-212-2/+2
OpenPOWER on IntegriCloud