| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | When waiting for the busy page, do not unlock the object unless unlock | kib | 2010-05-20 | 1 | -3/+6 |
| * | The page queues lock is no longer required by vm_page_set_invalid(), so | alc | 2010-05-18 | 1 | -3/+7 |
| * | On entry to pmap_enter(), assert that the page is busy. While I'm | alc | 2010-05-16 | 2 | -3/+5 |
| * | Correct an error of omission in r202897: Now that amd64 uses the direct map | alc | 2010-05-16 | 1 | -0/+14 |
| * | Add a comment about the proper use of vm_object_page_remove(). | alc | 2010-05-16 | 1 | -1/+2 |
| * | Update synchronization annotations for struct vm_page. Add a comment | alc | 2010-05-11 | 1 | -5/+8 |
| * | Continue cleaning the queue instead of moving to the next queue or | kib | 2010-05-10 | 1 | -4/+2 |
| * | Push down the acquisition of the page queues lock into vm_pageq_remove(). | alc | 2010-05-09 | 2 | -27/+41 |
| * | Call vm_page_deactivate() rather than vm_page_dontneed() in | alc | 2010-05-09 | 1 | -4/+2 |
| * | Remove the page queues lock around a call to vm_page_activate(). Make the | alc | 2010-05-09 | 1 | -3/+1 |
| * | Minimize the scope of the page queues lock in vm_fault(). | alc | 2010-05-08 | 2 | -5/+3 |
| * | Push down the page queues into vm_page_cache(), vm_page_try_to_cache(), and | alc | 2010-05-08 | 5 | -66/+34 |
| * | Fix a typo in the previous commit. | jkim | 2010-05-07 | 1 | -1/+1 |
| * | One more use for vm_pageout_init_marker(). | kib | 2010-05-07 | 1 | -8/+1 |
| * | Eliminate unnecessary page queues locking. | alc | 2010-05-07 | 1 | -4/+0 |
| * | Push down the page queues lock into vm_page_activate(). | alc | 2010-05-07 | 3 | -16/+17 |
| * | Update the synchronization requirements for the page usage count. | alc | 2010-05-07 | 1 | -1/+1 |
| * | Eliminate acquisitions of the page queues lock that are no longer needed. | alc | 2010-05-07 | 1 | -9/+2 |
| * | Push down the page queues lock into vm_page_deactivate(). Eliminate an | alc | 2010-05-07 | 2 | -7/+10 |
| * | Eliminate page queues locking around most calls to vm_page_free(). | alc | 2010-05-06 | 6 | -41/+1 |
| * | Update a comment to say that access to a page's wire count is now | alc | 2010-05-06 | 1 | -1/+1 |
| * | Push down the page queues lock inside of vm_page_free_toq() and | alc | 2010-05-06 | 2 | -11/+14 |
| * | Add a helper function vm_pageout_page_lock(), similar to tegge' | kib | 2010-05-06 | 3 | -14/+65 |
| * | Acquire the page lock around all remaining calls to vm_page_free() on | alc | 2010-05-05 | 4 | -11/+9 |
| * | Push down the acquisition of the page queues lock into vm_page_unwire(). | alc | 2010-05-05 | 3 | -19/+13 |
| * | Add page locking to the vm_page_cow* functions. | alc | 2010-05-04 | 2 | -13/+13 |
| * | Add lock assertions. | alc | 2010-05-04 | 1 | -1/+7 |
| * | Handle busy status of the page in a way expected for pager_getpage(). | kib | 2010-05-03 | 1 | -4/+4 |
| * | Acquire the page lock around vm_page_wire() in vm_page_grab(). | alc | 2010-05-03 | 1 | -0/+3 |
| * | It makes more sense for the object-based backend allocator to use OBJT_PHYS | alc | 2010-05-03 | 1 | -10/+4 |
| * | The pages allocated by kmem_alloc_attr() and kmem_malloc() are unmanaged. | alc | 2010-05-03 | 2 | -8/+0 |
| * | Assert that the page queues lock is held in vm_page_remove() and | alc | 2010-05-03 | 1 | -2/+4 |
| * | Add page lock assertions where we access the page's hold_count. | alc | 2010-05-02 | 1 | -0/+3 |
| * | Eliminate an assignment that was made redundant by r207410. | alc | 2010-05-02 | 1 | -2/+0 |
| * | Defer the acquisition of the page and page queues locks in | alc | 2010-05-02 | 1 | -8/+8 |
| * | Simplify vm_fault(). The introduction of the new page lock renders a bit of | alc | 2010-05-02 | 1 | -13/+5 |
| * | Correct an error in r207410: Remove an unlock of a lock that is no longer | alc | 2010-05-02 | 1 | -1/+0 |
| * | It makes no sense for vm_page_sleep_if_busy()'s helper, vm_page_sleep(), | alc | 2010-05-02 | 2 | -9/+22 |
| * | This change addresses the race condition that was introduced by the previous | alc | 2010-05-02 | 1 | -14/+16 |
| * | Correct an error of omission in r206819. If VMFS_TLB_ALIGNED_SPACE is | alc | 2010-05-02 | 1 | -1/+5 |
| * | Update locking comment above vm_page: | kmacy | 2010-05-01 | 1 | -9/+10 |
| * | push up dropping of the page queue lock to avoid holding it in vm_pageout_flush | kmacy | 2010-04-30 | 2 | -29/+19 |
| * | don't call vm_pageout_flush with the page queue mutex held | kmacy | 2010-04-30 | 1 | -0/+2 |
| * | - acquire the page lock in vm_contig_launder_page before checking page fields | kmacy | 2010-04-30 | 1 | -6/+15 |
| * | - don't check hold_count without the page lock held | kmacy | 2010-04-30 | 1 | -6/+7 |
| * | Unlock page lock instead of recursively locking it. | kib | 2010-04-30 | 1 | -3/+3 |
| * | don't allow unsynchronized free in vm_page_unhold | kmacy | 2010-04-30 | 1 | -1/+4 |
| * | On Alan's advice, rather than do a wholesale conversion on a single | kmacy | 2010-04-30 | 15 | -75/+433 |
| * | Simplify the inner loop of vm_pageout_object_deactivate_pages(). Rather | alc | 2010-04-29 | 1 | -7/+4 |
| * | When doing kstack swapin, read as much pages in one run as possible. | kib | 2010-04-29 | 1 | -11/+25 |
