| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | The page queues lock is no longer required by vm_page_wakeup(). | alc | 2006-10-23 | 1 | -3/+3 |
| * | Replace PG_BUSY with VPO_BUSY. In other words, changes to the page's | alc | 2006-10-22 | 1 | -7/+8 |
| * | Eliminate unnecessary PG_BUSY tests. They originally served a purpose | alc | 2006-10-21 | 1 | -1/+1 |
| * | Reimplement the page's NOSYNC flag as an object-synchronized instead of a | alc | 2006-08-13 | 1 | -5/+5 |
| * | Eliminate the acquisition and release of the page queues lock around a call | alc | 2006-08-06 | 1 | -4/+2 |
| * | Retire debug.mpsafevm. None of the architectures supported in CVS require | alc | 2006-07-21 | 1 | -7/+1 |
| * | Remove mpte optimization from pmap_enter_quick(). | ups | 2006-06-15 | 1 | -4/+2 |
| * | Simplify the implementation of vm_fault_additional_pages() based upon the | alc | 2006-05-13 | 1 | -12/+5 |
| * | Remove leading __ from __(inline|const|signed|volatile). They are | imp | 2006-03-08 | 1 | -2/+2 |
| * | Adjust old comment (present in rev 1.1) to match changes in rev 1.82. | tegge | 2006-02-02 | 1 | -1/+1 |
| * | Use the new macros abstracting the page coloring/queues implementation. | alc | 2006-01-27 | 1 | -2/+2 |
| * | MI changes: | netchild | 2005-12-31 | 1 | -2/+3 |
| * | Don't access fs->first_object after dropping reference to it. | tegge | 2005-12-20 | 1 | -1/+3 |
| * | Remove unneeded calls to pmap_remove_all(). The given page is not mapped. | alc | 2005-12-11 | 1 | -1/+0 |
| * | Eliminate an incorrect cast. | alc | 2005-09-07 | 1 | -1/+1 |
| * | Pass a value of type vm_prot_t to pmap_enter_quick() so that it determine | alc | 2005-09-03 | 1 | -1/+2 |
| * | Convert a remaining !fs.map->system_map to | jhb | 2005-07-14 | 1 | -1/+1 |
| * | The final test in unlock_and_deallocate() to determine if GIANT needs to be | grehan | 2005-05-12 | 1 | -1/+1 |
| * | - Add a new object flag "OBJ_NEEDSGIANT". We set this flag if the | jeff | 2005-05-03 | 1 | -4/+9 |
| * | - Remove GIANT_REQUIRED where giant is no longer required. | jeff | 2005-01-24 | 1 | -2/+6 |
| * | /* -> /*- for license, minor formatting changes | imp | 2005-01-07 | 1 | -1/+1 |
| * | Continue the transition from synchronizing access to the page's PG_BUSY | alc | 2004-12-24 | 1 | -11/+29 |
| * | Modify pmap_enter_quick() so that it expects the page queues to be locked | alc | 2004-12-23 | 1 | -4/+3 |
| * | In the common case, pmap_enter_quick() completes without sleeping. | alc | 2004-12-15 | 1 | -8/+2 |
| * | Remove unnecessary check for curthread == NULL. | alc | 2004-10-17 | 1 | -1/+1 |
| * | System maps are prohibited from mapping vnode-backed objects. Take | alc | 2004-09-11 | 1 | -8/+8 |
| * | Push Giant deep into vm_forkproc(), acquiring it only if the process has | alc | 2004-09-03 | 1 | -0/+4 |
| * | In vm_fault_unwire() eliminate the acquisition and release of Giant in the | alc | 2004-09-01 | 1 | -4/+0 |
| * | In the previous revision, I failed to condition an early release of Giant | alc | 2004-08-22 | 1 | -1/+2 |
| * | Further reduce the use of Giant by vm_fault(): Giant is held only when | alc | 2004-08-21 | 1 | -4/+3 |
| * | - Introduce and use a new tunable "debug.mpsafevm". At present, setting | alc | 2004-08-16 | 1 | -7/+11 |
| * | The vm map lock is needed in vm_fault() after the page has been found, | tegge | 2004-08-12 | 1 | -51/+37 |
| * | Make two changes to vm_fault(). | alc | 2004-08-09 | 1 | -16/+7 |
| * | Make two changes to vm_fault(). | alc | 2004-08-09 | 1 | -11/+6 |
| * | To date, unwiring a fictitious page has produced a panic. The reason | alc | 2004-05-22 | 1 | -11/+10 |
| * | Make vm_page's PG_ZERO flag immutable between the time of the page's | alc | 2004-05-06 | 1 | -1/+0 |
| * | - Make the acquisition of Giant in vm_fault_unwire() conditional on the | alc | 2004-03-10 | 1 | -2/+4 |
| * | Correct a long-standing race condition in vm_fault() that could result in a | alc | 2004-02-15 | 1 | -3/+1 |
| * | - Locking for the per-process resource limits structure has eliminated | alc | 2004-02-05 | 1 | -2/+0 |
| * | - Reduce Giant's scope in vm_fault(). | alc | 2003-12-26 | 1 | -14/+10 |
| * | NFC: Update stale comments. | mini | 2003-11-10 | 1 | -1/+1 |
| * | - vm_fault_copy_entry() should not assume that the source object contains | alc | 2003-10-15 | 1 | -5/+19 |
| * | Lock the destination object in vm_fault_copy_entry(). | alc | 2003-10-08 | 1 | -2/+7 |
| * | Retire vm_page_copy(). Its reason for being ended when peter@ modified | alc | 2003-10-08 | 1 | -2/+4 |
| * | Synchronize access to a vm page's valid field using the containing | alc | 2003-10-04 | 1 | -4/+8 |
| * | Migrate pmap_prefault() into the machine-independent virtual memory layer. | alc | 2003-10-03 | 1 | -1/+91 |
| * | Add vm object locking to vnode_pager_lock(). (This triggers the movement | alc | 2003-09-18 | 1 | -1/+1 |
| * | To implement the sequential access optimization, vm_fault() may need to | alc | 2003-08-23 | 1 | -8/+10 |
| * | Maintain a lock on the vm object of interest throughout vm_fault(), | alc | 2003-06-22 | 1 | -10/+9 |
| * | As vm_fault() descends the chain of backing objects, set paging-in- | alc | 2003-06-22 | 1 | -8/+8 |
