| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | o Replace the vm_map's hint by the root of a splay tree. By design, | alc | 2002-05-24 | 2 | -81/+106 |
| * | o Make contigmalloc1() static. | alc | 2002-05-22 | 2 | -5/+1 |
| * | In uma_zalloc_arg(), if we are performing a M_WAITOK allocation, ensure | jhb | 2002-05-20 | 1 | -0/+7 |
| * | o Eliminate the acquisition and release of Giant from minherit(2). | alc | 2002-05-18 | 1 | -7/+2 |
| * | o Remove GIANT_REQUIRED from vm_map_madvise(). Instead, acquire and | alc | 2002-05-18 | 3 | -8/+9 |
| * | o Remove the acquisition and release of Giant from mprotect(). | alc | 2002-05-18 | 1 | -6/+2 |
| * | More s/file system/filesystem/g | trhodes | 2002-05-16 | 1 | -1/+1 |
| * | Make daddr_t and u_daddr_t 64bits wide. | phk | 2002-05-14 | 1 | -2/+2 |
| * | Don't call the uz free function while the zone lock is held. This can lead | jeff | 2002-05-13 | 1 | -14/+21 |
| * | Remove the hash_free() lock order reversal. This could have happened for | jeff | 2002-05-13 | 1 | -69/+72 |
| * | o Remove GIANT_REQUIRED and an excessive number of blank lines | alc | 2002-05-12 | 1 | -10/+0 |
| * | o Acquire and release Giant in vm_object_reference() and | alc | 2002-05-12 | 2 | -11/+9 |
| * | o Header files shouldn't depend on options: Provide prototypes | alc | 2002-05-06 | 1 | -3/+0 |
| * | o Condition the compilation and use of vm_freeze_copyopts() | alc | 2002-05-06 | 3 | -2/+14 |
| * | o Some improvements to the page coloring of vm objects, particularly, | alc | 2002-05-06 | 1 | -9/+17 |
| * | o Move vm_freeze_copyopts() from vm_map.{c.h} to vm_object.{c,h}. It's plainly | alc | 2002-05-06 | 4 | -78/+78 |
| * | o Condition the compilation of uiomoveco() and vm_uiomove() | alc | 2002-05-05 | 2 | -1/+7 |
| * | Expand the one-line function pbreassignbuf() the only place it is or could | phk | 2002-05-05 | 1 | -1/+1 |
| * | o Remove GIANT_REQUIRED from vm_map_lookup() and vm_map_lookup_done(). | alc | 2002-05-05 | 1 | -2/+2 |
| * | Use pages instead of uz_maxpages, which has not been initialized yet, when | jeff | 2002-05-04 | 1 | -2/+2 |
| * | o Make _vm_object_allocate() and vm_object_allocate() callable | alc | 2002-05-04 | 2 | -22/+21 |
| * | o Remove GIANT_REQUIRED from vm_map_lookup_entry() and | alc | 2002-05-04 | 2 | -7/+3 |
| * | o Change the implementation of vm_map locking to use exclusive locks | alc | 2002-05-02 | 1 | -26/+24 |
| * | Hide a pointer to the malloc_type bucket at the end of the freed memory. If | jeff | 2002-05-02 | 2 | -2/+84 |
| * | Move around the dbg code a bit so it's always under a lock. This stops a | jeff | 2002-05-02 | 1 | -8/+7 |
| * | - Changed the size element of uma_zctor_args to be size_t instead of int. | arr | 2002-05-02 | 2 | -4/+4 |
| * | malloc/free(9) no longer require Giant. Use the malloc_mtx to protect the | jeff | 2002-05-02 | 2 | -8/+19 |
| * | o Remove dead and lockmgr()-specific debugging code. | alc | 2002-05-02 | 2 | -23/+0 |
| * | Remove the temporary alignment check in free(). | jeff | 2002-05-02 | 3 | -19/+118 |
| * | o Convert the vm_page buckets mutex to a spin lock. (This resolves | alc | 2002-04-30 | 1 | -14/+11 |
| * | Add a new UMA debugging facility. This will overwrite freed memory with | jeff | 2002-04-30 | 2 | -0/+159 |
| * | Move the implementation of M_ZERO into UMA so that it can be passed to | jeff | 2002-04-30 | 2 | -16/+21 |
| * | o Revert vm_fault1() to its original name vm_fault(), eliminating the wrapper | alc | 2002-04-30 | 1 | -16/+11 |
| * | Add a new zone flag UMA_ZONE_MTXCLASS. This puts the zone in it's own | jeff | 2002-04-29 | 4 | -10/+34 |
| * | Tidy up some loose ends. | peter | 2002-04-29 | 2 | -3/+0 |
| * | Document three synchronization issues in vm_fault(). | alc | 2002-04-29 | 1 | -0/+8 |
| * | Pass the caller's file name and line number to the vm_map locking functions. | alc | 2002-04-28 | 2 | -20/+35 |
| * | o Introduce and use vm_map_trylock() to replace several direct uses | alc | 2002-04-28 | 5 | -8/+14 |
| * | We do not necessarily need to map/unmap pages to zero parts of them. | peter | 2002-04-28 | 3 | -4/+14 |
| * | o Begin documenting the (existing) locking protocol on the vm_map | alc | 2002-04-27 | 2 | -25/+26 |
| * | o Control access to the vm_page_buckets with a mutex. | alc | 2002-04-26 | 1 | -33/+17 |
| * | - Fix a round down bogon in uma_zone_set_max(). | arr | 2002-04-25 | 1 | -0/+2 |
| * | Reintroduce locking on accesses to vm_object_list. | alc | 2002-04-20 | 3 | -1/+10 |
| * | o Move the acquisition of Giant from vm_fault() to the point | alc | 2002-04-19 | 1 | -12/+8 |
| * | Add a comment documenting a race condition in vm_fault(): Specifically, a | alc | 2002-04-18 | 1 | -0/+3 |
| * | o Call vm_map_growstack() from vm_fault() if vm_map_lookup() has failed | alc | 2002-04-18 | 1 | -1/+10 |
| * | Do not free the vmspace until p->p_vmspace is set to null. Otherwise | peter | 2002-04-17 | 1 | -3/+7 |
| * | Remove an unused option, VM_FAULT_HOLD, to vm_fault(). | alc | 2002-04-17 | 2 | -3/+0 |
| * | Pass vm_page_t instead of physical addresses to pmap_zero_page[_area]() | peter | 2002-04-15 | 4 | -28/+14 |
| * | Fix a witness warning when expanding a hash table. We were allocating the new | jeff | 2002-04-14 | 1 | -38/+79 |
