aboutsummaryrefslogtreecommitdiff
path: root/sys/vm/vnode_pager.c
Commit message (Expand)AuthorAgeFilesLines
* MFC r204205:Konstantin Belousov2010-02-251-3/+0
* MFC r202529:Konstantin Belousov2010-02-071-1/+6
* Change the type of uio_resid member of struct uio from int to ssize_t.Konstantin Belousov2009-06-251-1/+1
* Implement global and per-uid accounting of the anonymous memory. AddKonstantin Belousov2009-06-231-3/+4
* Correct a boundary case error in the management of a page's dirty bits byAlan Cox2009-06-021-10/+16
* Eliminate unnecessary clearing of the page's dirty mask from variousAlan Cox2009-05-151-5/+6
* Eliminate gratuitous clearing of the page's dirty mask.Alan Cox2009-05-121-1/+2
* Fix a race involving vnode_pager_input_smlfs(). Specifically, in the caseAlan Cox2009-05-091-23/+10
* Eliminate vnode_pager_input_smlfs()'s pointless call to pmap_clear_modify().Alan Cox2009-05-041-3/+0
* Eliminate unnecessary calls to pmap_clear_modify(). Specifically, callingAlan Cox2009-04-251-2/+6
* Adjust some variables (mostly related to the buffer cache) that holdJohn Baldwin2009-03-091-2/+2
* Comment out the assertion from r188321. It is not valid for nfs.Konstantin Belousov2009-02-091-1/+1
* Eliminate OBJ_NEEDGIANT. After r188331, OBJ_NEEDGIANT's only use is by aAlan Cox2009-02-081-2/+0
* Do not sleep for vnode lock while holding map lock in vm_fault. Try toKonstantin Belousov2009-02-081-53/+0
* Assert that vnode is exclusively locked when its vm object is resized.Konstantin Belousov2009-02-081-0/+1
* Decontextualize the couplet VOP_GETATTR / VOP_SETATTR as the passed threadAttilio Rao2008-08-281-1/+1
* A few more whitespace fixes.John Baldwin2008-07-301-1/+1
* The behaviour of the lockmgr going back at least to the 4.4BSD-Lite2 wasKonstantin Belousov2008-07-301-2/+9
* Fix vm object creation locking to allow SHARED vnode locking for vnode_create...Stephan Uphoff2008-06-121-6/+7
* Allow VM object creation in ufs_lookup. (If vfs.vmiodirenable is set)Stephan Uphoff2008-05-201-7/+15
* VOP_LOCK1() (and so VOP_LOCK()) and VOP_UNLOCK() are only used inAttilio Rao2008-01-131-1/+1
* vn_lock() is currently only used with the 'curthread' passed as argument.Attilio Rao2008-01-101-1/+1
* Remove an unnecessary call to pmap_remove_all() and the associated "XXX"Alan Cox2007-11-221-15/+1
* Correct an error of omission in the reimplementation of the pageAlan Cox2007-10-221-0/+4
* When we do open, we should lock the vnode exclusively. This fixes few races:Pawel Jakub Dawidek2007-07-261-3/+3
* Do proper "locking" for missing vmmeters part.Attilio Rao2007-06-041-8/+8
* Revert VMCNT_* operations introduction.Attilio Rao2007-05-311-10/+9
* - define and use VMCNT_{GET,SET,ADD,SUB,PTR} macros for manipulatingJeff Roberson2007-05-181-9/+10
* Long ago, revision 1.22 of vm/vm_pager.h introduced a bug. Specifically,Alan Cox2006-10-141-3/+1
* Change vnode_pager_addr() such that on returning it distinguishes betweenAlan Cox2006-10-141-19/+24
* Distinguish between two distinct kinds of errors from VOP_BMAP() inAlan Cox2006-10-101-2/+12
* Change vnode_pager_generic_getpages() so that it does not panic if theAlan Cox2006-10-081-2/+13
* Introduce a field to struct vm_page for storing flags that areAlan Cox2006-08-091-1/+1
* Eliminate a deadlock when creating snapshots. Blocking vn_start_write() mustTor Egge2006-03-021-2/+0
* - Fix silly VI locking that is used to check a single flag. The vnodeJeff Roberson2006-02-061-14/+6
* Use off_t for file size passed to vnode_create_vobject().Yaroslav Tykhiy2006-02-011-1/+1
* Rate limit vnode_pager_putpages printfs to once a second.Paul Saab2005-11-011-3/+8
* Do not use vm_pager_init() to initialize vnode_pbuf_freecnt variable.Alexander Kabaev2005-08-131-9/+0
* Use atomic operations on runningbufspace.Suleiman Souhlal2005-08-081-2/+4
* Remove a stale comment concerning spl* usage.Alan Cox2005-05-191-2/+0
* Correct 32 vs 64 bit signedness issues.Bjoern A. Zeeb2005-05-181-8/+9
* - Add a new object flag "OBJ_NEEDSGIANT". We set this flag if theJeff Roberson2005-05-031-0/+3
* - Don't NULL the vnode's v_object pointer until after the object is tornJeff Roberson2005-04-031-1/+1
* - LK_NOPAUSE is a nop now.Jeff Roberson2005-03-311-1/+1
* - Don't directly adjust v_usecount, use vref() instead.Jeff Roberson2005-03-141-3/+1
* - Retire OLOCK and OWANT. All callers hold the vnode lock when creatingJeff Roberson2005-03-141-17/+0
* - Don't acquire the vnode lock in destroy_vobject, assert that it hasJeff Roberson2005-03-131-2/+1
* Try to unbreak the vnode locking around vop_reclaim() (based mostly onPoul-Henning Kamp2005-02-191-0/+2
* Move the contents of vop_stddestroyvobject() to the new vnode_pagerPoul-Henning Kamp2005-01-281-0/+33
* Move the body of vop_stdcreatevobject() over to the vnode_pager underPoul-Henning Kamp2005-01-241-0/+50