aboutsummaryrefslogtreecommitdiff
path: root/sys/vm
Commit message (Expand)AuthorAgeFilesLines
* Introduce a new pmap function, pmap_extract_and_hold(). This functionAlan Cox2003-09-081-0/+1
* Revise the locking in mincore(2).Alan Cox2003-09-071-5/+5
* Don't open with exclusive bit, swapon(8) wants to trash our swapdev.Poul-Henning Kamp2003-09-021-2/+8
* Change clean_map from a global to an auto variableEivind Eklund2003-09-012-1/+1
* - Add vm object locking to the part of vm_pageout_scan() that laundersAlan Cox2003-08-311-20/+16
* Introduce MAP_ENTRY_GROWS_DOWN and MAP_ENTRY_GROWS_UP to allow forMarcel Moolenaar2003-08-302-80/+147
* Add a close() method to a swapdev.Poul-Henning Kamp2003-08-301-138/+254
* Protect the swapdevice tailq with a mutex.Poul-Henning Kamp2003-08-301-23/+50
* Continue the objectification of the swapdev backends:Poul-Henning Kamp2003-08-301-59/+106
* Make the strategy function a method of the individual swapdev.Poul-Henning Kamp2003-08-301-21/+30
* Consistent use modern function definitionsPoul-Henning Kamp2003-08-301-69/+23
* In vnode_pager_generic_putpages(), change the printf format specifierMarcel Moolenaar2003-08-291-2/+2
* Recent pmap changes permit the use of a more precise locking assertionAlan Cox2003-08-281-2/+1
* Assert that u_long is at least 64 bits if PAGE_SIZE is 32K.Marcel Moolenaar2003-08-251-0/+7
* Held pages, just like wired pages, should not be added to the cache queues.Alan Cox2003-08-231-1/+2
* Hold the page queues lock when performing vm_page_clear_dirty() andAlan Cox2003-08-232-2/+5
* To implement the sequential access optimization, vm_fault() may need toAlan Cox2003-08-231-8/+10
* Also define VM_PAGE_BITS_ALL for 16K and 32K pages. Make the constantMarcel Moolenaar2003-08-231-5/+7
* Add support for 16K and 32K page sizes. The valid and dirty mapsMarcel Moolenaar2003-08-231-0/+6
* Assert that the vm object's lock is held on entry to vm_page_grab(); removeAlan Cox2003-08-211-14/+6
* Assert that the vm object lock is held in vm_page_alloc().Alan Cox2003-08-201-0/+1
* In sysctl_vm_zone, do not calculate per-cpu cache stats onBosko Milekic2003-08-201-20/+17
* Replace a homegrown bdone()/bwait() implementation by the real thingPoul-Henning Kamp2003-08-181-27/+5
* Three unrelated changes to vm_proc_new(): (1) add vm object locking on theAlan Cox2003-08-181-10/+7
* Use NULL for 3rd argument of VOP_BMAP() rather than custom cast.Poul-Henning Kamp2003-08-171-4/+2
* In vm_thread_swap{in|out}(), remove the alpha specific conditionalMarcel Moolenaar2003-08-161-13/+2
* Eliminate unnecessary udev_t variable: we can derive it from the dev_tPoul-Henning Kamp2003-08-151-6/+4
* Make swaponvp() static to the swap_pager.Poul-Henning Kamp2003-08-152-2/+2
* Extend the scope of the page queues lock in vm_pageout_scan() to coverAlan Cox2003-08-151-14/+4
* Remove GIANT_REQUIRED from vmspace_alloc().Alan Cox2003-08-131-1/+0
* Reduce the size of the vm map (and by inclusion the vm space) on 64-bitAlan Cox2003-08-131-1/+1
* Expand inline the relevant parts of src/COPYRIGHT for Matt Dillon'sWarner Losh2003-08-122-5/+49
* Reduce the size of the vm object on 64-bit architectures by movingAlan Cox2003-08-121-1/+1
* - When deciding whether to init the zone with small_init or large_init,Bosko Milekic2003-08-112-6/+25
* Add the mlockall() and munlockall() system calls.Bruce M Simpson2003-08-117-27/+167
* More pipe changes:Mike Silbersack2003-08-113-0/+5
* Make the first two pages magic to protect the BSD labels rather thanPoul-Henning Kamp2003-08-061-2/+2
* Remove an unused variable.Poul-Henning Kamp2003-08-061-3/+0
* Staticize swap_pager_putpages()Poul-Henning Kamp2003-08-062-36/+4
* Access the swap_pagers' ->putpages() through swappagerops insteadPoul-Henning Kamp2003-08-061-1/+1
* Add XXX: comment to vm_pager_unswapped().Poul-Henning Kamp2003-08-061-0/+5
* Explicitly set B_PAGINGPoul-Henning Kamp2003-08-061-4/+2
* Rip out the totally bogos vnode swapdev_vp with extreeme prejudice.Poul-Henning Kamp2003-08-061-52/+11
* Use sparse struct initialization for struct pagerops.Poul-Henning Kamp2003-08-052-260/+12
* Use sparse struct initializations for struct pagerops.Poul-Henning Kamp2003-08-055-53/+28
* Put an uncovered page between the swap devices, that way we can be surePoul-Henning Kamp2003-08-041-32/+23
* Use kmem_alloc_nofault() instead of kmem_alloc_pageable() to allocateAlan Cox2003-08-041-1/+1
* Name swap_pager_find_dev() more correctly swp_pager_finde_dev().Poul-Henning Kamp2003-08-031-38/+21
* I accidentally hit undo before committing, fix the resulting off-by-one.Poul-Henning Kamp2003-08-031-1/+1
* Change the layout policy of the swap_pager from a hardcoded widthPoul-Henning Kamp2003-08-035-155/+133