summaryrefslogtreecommitdiffstats
path: root/sys/vm
Commit message (Expand)AuthorAgeFilesLines
* make vm_page_select_cache staticassar2001-07-232-2/+1
* (vm_page_select_cache): add prototypeassar2001-07-211-0/+1
* The i386-specific includes in this file were "fixed" by bracketing them withbenno2001-07-151-3/+3
* Fix missing newline and terminator at the end of the vm.zone sysctl.des2001-07-091-2/+1
* Apply field bandages to the includes so compiles happen on alpha.mjacob2001-07-051-0/+6
* Move vm_page_zero_idle() from machine-dependant sections to adillon2001-07-051-0/+117
* Reorg vm_page.c into vm_page.c, vm_pageq.c, and vm_contig.c (for contigmalloc).dillon2001-07-046-465/+621
* Change inlines back into mainline code in preparation for mutexing. Also,dillon2001-07-046-840/+729
* whitespace / register cleanupdillon2001-07-0412-80/+81
* With Alfred's permission, remove vm_mtx in favor of a fine-grained approachdillon2001-07-0423-658/+294
* Fix a XXX comment by moving the initialization of the number of pbuf'sjhb2001-07-031-9/+9
* - Protect all accesses to nsw_[rw]count{,_{,a}sync} with the pbuf mutex.jhb2001-06-221-4/+4
* Introduce numerous SMP friendly changes to the mbuf allocator. Namely,bmilekic2001-06-224-17/+11
* Don't lock around swap_pager_swap_init() that is only called once duringjhb2001-06-201-0/+2
* Put the scheduler, vmdaemon, and pagedaemon kthreads back under Giant forjhb2001-06-202-19/+1
* Cleanup the tabbingdillon2001-06-111-17/+16
* Two fixes to the out-of-swap process termination code. First, start killingdillon2001-06-093-3/+44
* Change the way information about swap devices is exported to be moretmm2001-06-012-28/+46
* Clean up the code exporting interrupt statistics via sysctl a bit:tmm2001-06-011-30/+0
* Don't hold the VM lock across VOP's and other things that can sleep.jhb2001-05-291-2/+19
* Stick VM syscalls back under Giant if the BLEED option is not defined.jhb2001-05-242-0/+57
* This patch implements O_DIRECT about 80% of the way. It takes a patchsetdillon2001-05-242-0/+24
* - Assert Giant is held in the vnode pager methods.jhb2001-05-231-14/+18
* - Add in several asserts of vm_mtx.jhb2001-05-231-5/+42
* - Assert that the vm lock is held for all of _vm_object_allocate().jhb2001-05-231-31/+48
* - Add lots of vm_mtx assertions.jhb2001-05-231-2/+39
* - Lock the VM around the pmap_swapin_proc() call in faultin().jhb2001-05-231-15/+16
* - Fix the sw_alloc_interlock to actually lock itself when the lock isjhb2001-05-231-16/+20
* Assert Giant is held for the device pager alloc and getpages methods sincejhb2001-05-231-3/+3
* - Obtain Giant in mmap() syscall while messing with file descriptors andjhb2001-05-231-18/+32
* Acquire Giant around vm_map_remove() inside of the obreak() syscall forjhb2001-05-231-2/+7
* Take a more conservative approach and still lock Giant around VM faultsjhb2001-05-231-8/+6
* Set the phys_pager_alloc_lock to 1 when it is acquired so that it isjhb2001-05-231-1/+2
* aquire Giant when playing with the buffercache and doing IO.alfred2001-05-231-2/+5
* aquire vm mutex in swp_pager_async_iodone. Don't call swp_pager_async_iodonealfred2001-05-221-2/+3
* Remove duplicate include and sort includes.jhb2001-05-221-3/+2
* Sort includes.jhb2001-05-221-1/+1
* Unlock the VM lock at the end of munlock() instead of locking it again.jhb2001-05-221-1/+1
* Sort includes from previous commit.jhb2001-05-221-1/+1
* Sort includes.jhb2001-05-221-3/+3
* Introduce a global lock for the vm subsystem (vm_mtx).alfred2001-05-1922-171/+643
* - Use a timeout for the tsleep in scheduler() instead of having vmmeter()jhb2001-05-182-5/+22
* During the code to pick a process to kill when memory is exhausted, keepjhb2001-05-171-3/+18
* - Use PROC_LOCK_ASSERT instead of a direct mtx_assert.jhb2001-05-151-8/+6
* Actually biofinish(struct bio *, struct devstat *, int error) is more generalphk2001-05-061-3/+1
* Putting sys/lockmgr.h in here allows us to depollute userland includesmarkm2001-05-031-0/+2
* Undo part of the tangle of having sys/lock.h and sys/mutex.h included inmarkm2001-05-0114-18/+30
* Revert consequences of changes to mount.h, part 2.grog2001-04-292-4/+0
* Address a number of problems with sysctl_vm_zone().alfred2001-04-271-11/+29
* Correct #includes to work with fixed sys/mount.h.grog2001-04-232-0/+4
OpenPOWER on IntegriCloud