summaryrefslogtreecommitdiff
path: root/sys/vm
Commit message (Expand)AuthorAgeFilesLines
* After the object lock was dropped, the object' reference count couldKonstantin Belousov2013-05-301-5/+5
* Remove the capitalization in the assertion message. Print the addressKonstantin Belousov2013-05-301-1/+1
* o Change the locking scheme for swp_bcount.Attilio Rao2013-05-281-5/+7
* Acquire read lock on the src object for vm_fault_copy_entry().Attilio Rao2013-05-221-4/+4
* o Relax locking assertions for vm_page_find_least()Attilio Rao2013-05-213-8/+18
* Add ddb command 'show pginfo' which provides useful information aboutKonstantin Belousov2013-05-211-0/+23
* Relax the object locking in vm_fault_prefault(). A read lock suffices.Alan Cox2013-05-171-5/+5
* Relax the object locking assertion in vm_page_lookup(). Now that a radixAlan Cox2013-05-171-1/+1
* o Add accessor functions to add and remove pages from a specificAttilio Rao2013-05-132-198/+139
* Bandaid for compiling with gcc, which happens to be the default compilerPeter Wemm2013-05-131-0/+1
* Refactor vm_page_alloc()'s interactions with vm_reserv_alloc_page() andAlan Cox2013-05-123-25/+63
* To reduce the amount of arithmetic performed in the various radix treeAlan Cox2013-05-111-13/+12
* Fix-up r250338 by completing the removal of VM_NDOMAIN in favor ofAttilio Rao2013-05-081-2/+2
* Rename VM_NDOMAIN into MAXMEMDOM and move it into machine/param.h inAttilio Rao2013-05-071-10/+10
* Remove a redundant call to panic() from vm_radix_keydiff(). The assertionAlan Cox2013-05-071-4/+2
* Optimize vm_radix_lookup_ge() and vm_radix_lookup_le(). Specifically,Alan Cox2013-05-041-103/+75
* Fix two bugs in the current NUMA-aware allocation code:John Baldwin2013-05-031-6/+48
* Add a hint suggesting why tmpfs does not need a special case there.Konstantin Belousov2013-05-021-1/+1
* Rework the handling of the tmpfs node backing swap object and tmpfsKonstantin Belousov2013-04-282-1/+34
* Make vm_object_page_clean() and vm_mmap_vnode() tolerate the vnode'Konstantin Belousov2013-04-282-3/+15
* Assert that the object type for the vnode' non-NULL v_object, passedKonstantin Belousov2013-04-281-0/+6
* Convert panic() into KASSERT().Konstantin Belousov2013-04-281-2/+1
* Eliminate an unneeded call to vm_radix_trimkey() from vm_radix_lookup_le().Alan Cox2013-04-281-1/+0
* Avoid some lookup restarts in vm_radix_lookup_{ge,le}().Alan Cox2013-04-271-22/+24
* Panic if UMA_ZONE_PCPU is created at early stages of boot, when mp_ncpusGleb Smirnoff2013-04-221-0/+1
* Simplify vm_radix_{add,dec}lev().Alan Cox2013-04-221-8/+13
* When calculating the number of reserved nodes, discount the pages that willAlan Cox2013-04-181-2/+9
* Although we perform path compression to reduce the height of the trie andAlan Cox2013-04-151-26/+32
* Although we perform path compression to reduce the height of the trie andAlan Cox2013-04-121-20/+33
* Convert UMA code to C99 uintXX_t types.Gleb Smirnoff2013-04-094-97/+97
* Swap us_freecount and us_flags, achieving same structure sizeGleb Smirnoff2013-04-091-2/+2
* Since now we support 256 items per slab, we need more bitsGleb Smirnoff2013-04-091-1/+1
* Fix KASSERTs: maximum number of items per slab is 256.Gleb Smirnoff2013-04-091-3/+3
* Fix the assertions for the state of the object under the map entryKonstantin Belousov2013-04-091-6/+16
* The per-page act_count can be made very-easily protected by theAttilio Rao2013-04-082-5/+5
* Merge from projects/counters: UMA_ZONE_PCPU zones.Gleb Smirnoff2013-04-083-38/+68
* Micro-optimize the order of struct vm_radix_node's fields. Specifically,Alan Cox2013-04-071-2/+2
* Prepare to replace the buf splay with a trie:Jeff Roberson2013-04-061-20/+4
* Simplify vm_radix_keybarr().Alan Cox2013-04-061-3/+1
* Simplify vm_radix_insert().Alan Cox2013-04-061-29/+8
* Replace the remaining uses of vm_radix_node_page() by vm_radix_isleaf() andAlan Cox2013-04-031-65/+67
* Release the v_writecount reference on the vnode in case of error,Konstantin Belousov2013-03-281-0/+4
* Introduce vm_radix_isleaf() and use it in a couple places. As compared toAlan Cox2013-03-261-2/+12
* Micro-optimize the control flow in a few places. Eliminate a panic callAlan Cox2013-03-241-8/+6
* Only size and create the bio_transient_map when unmapped buffers areKonstantin Belousov2013-03-211-4/+6
* Fix the logic inversion in the r248512.Konstantin Belousov2013-03-201-1/+1
* Do not map the swap i/o pbufs if the geom provider for the swapKonstantin Belousov2013-03-192-13/+34
* Pass unmapped buffers for page in requests if the filesystem indicated supportKonstantin Belousov2013-03-191-6/+30
* Implement the concept of the unmapped VMIO buffers, i.e. buffers whichKonstantin Belousov2013-03-193-1/+9
* Sync back vmcontention branch into HEAD:Attilio Rao2013-03-188-344/+957