| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Ensure that deactivated pages that are not expected to be reused are | markj | 2015-11-08 | 3 | -9/+16 |
| * | Reduce the amount of calls to VOP_BMAP() made from the local vnode | kib | 2015-10-24 | 1 | -81/+39 |
| * | Fix capitalization | jah | 2015-10-23 | 1 | -1/+1 |
| * | Remove unclear comment about address truncation in busdma. Add (hopefully mu... | jah | 2015-10-23 | 1 | -0/+5 |
| * | Only marker is guaranteed to be present on the queue after the relock | kib | 2015-10-18 | 1 | -5/+17 |
| * | Revert r289302, invalid pages can be queued, e.g. by vfs_vmio_unwire(). | kib | 2015-10-15 | 1 | -5/+5 |
| * | Invalid pages should not appear on the inactive queue. Change the | kib | 2015-10-14 | 1 | -5/+5 |
| * | Parallelize the buffer cache and rewrite getnewbuf(). This results in a | jeff | 2015-10-14 | 1 | -1/+5 |
| * | Exploit r288122 to avoid pointlessly enqueueing a page that is about to be | alc | 2015-10-09 | 1 | -1/+1 |
| * | Exploit r288122 to address a cosmetic issue. Pages belonging to either | alc | 2015-10-06 | 1 | -1/+1 |
| * | Mark swap_pager_putpages static at its definition. It was already | imp | 2015-10-05 | 1 | -3/+1 |
| * | Reduce the scope of a variable to the only file where it is used. | alc | 2015-10-03 | 3 | -2/+2 |
| * | As a step towards the elimination of PG_CACHED pages, rework the handling | markj | 2015-09-30 | 4 | -15/+28 |
| * | The conversion of kmem_alloc_attr() from operating on a vm map to a vmem | alc | 2015-09-26 | 1 | -28/+13 |
| * | Exploit r288122 to address a cosmetic issue. Since the pages allocated | alc | 2015-09-26 | 1 | -1/+1 |
| * | Change vm_page_unwire() such that it (1) accepts PQ_NONE as the specified | alc | 2015-09-22 | 2 | -17/+21 |
| * | Correct a non-fatal error in vm_pageout_worker(). vm_pageout_worker() | alc | 2015-09-20 | 1 | -6/+11 |
| * | Eliminate (many) unnecessary calls to pmap_remove_all(). Pages from objects | alc | 2015-09-17 | 1 | -1/+2 |
| * | Remove the v_cache_min and v_cache_max sysctls. They are unused and have | markj | 2015-09-11 | 3 | -9/+2 |
| * | Remove a check which caused spurious SIGSEGV on usermode access to the | kib | 2015-09-09 | 1 | -10/+4 |
| * | The swap pager is compatible with direct dispatch. It does its own | imp | 2015-09-08 | 1 | -11/+42 |
| * | To simplify upcoming changes to the inactive queue scan, change the code | alc | 2015-09-08 | 1 | -18/+8 |
| * | Eliminate pointless requeueing of pages from terminated objects. These | alc | 2015-09-05 | 1 | -23/+25 |
| * | Don't trash memory from UMA_ZONE_NOFREE zones. | mjg | 2015-09-02 | 1 | -2/+2 |
| * | Handle held pages earlier in the inactive queue scan. | alc | 2015-09-01 | 1 | -31/+33 |
| * | Remove weighted page handling from vm_page_advise(). | markj | 2015-08-28 | 1 | -54/+25 |
| * | In vm_pageout_scan(), simplify the logic for determining if a page can be | alc | 2015-08-27 | 1 | -15/+15 |
| * | Testing whether a page is dirty does not require the page lock. Moreover, | alc | 2015-08-25 | 1 | -6/+10 |
| * | Make the UMA harvesting go away completely if not wanted. Default to "not wan... | markm | 2015-08-22 | 1 | -4/+4 |
| * | Eliminate pointless assignments to rtvals[] in swap_pager_putpages(). | alc | 2015-08-21 | 1 | -12/+12 |
| * | Prevent ticks rollover from preventing vm_lowmem event | rstone | 2015-08-20 | 1 | -3/+4 |
| * | Add the kernel support for minidumps on arm64. | andrew | 2015-08-20 | 1 | -7/+7 |
| * | As another piece of PG_CACHE page elimination, remove an LRU-defeating call | alc | 2015-08-16 | 1 | -5/+0 |
| * | Make kstack_pages a tunable on arm, x86, and powepc. On i386, the | kib | 2015-08-10 | 1 | -5/+5 |
| * | Avoid sign extension of value passed to kva_alloc from uma_zone_reserve_kva | zbb | 2015-08-10 | 1 | -2/+2 |
| * | Introduce a sysctl for reporting the number of fully populated reservations. | alc | 2015-08-06 | 1 | -0/+32 |
| * | Properly sort the function declarations added in r286296 | jah | 2015-08-05 | 1 | -2/+2 |
| * | Add two new pmap functions: | jah | 2015-08-04 | 1 | -0/+2 |
| * | Refinements to r281079's sequential access optimization: Prefetched pages, | alc | 2015-08-03 | 1 | -2/+12 |
| * | Do not pretend that vm_fault(9) supports unwiring the address. Rename | kib | 2015-07-30 | 3 | -26/+21 |
| * | - Make 'struct buf *buf' private to vfs_bio.c. Having a global variable | jeff | 2015-07-29 | 1 | -0/+2 |
| * | Revert r173708's modifications to vm_object_page_remove(). | kib | 2015-07-25 | 2 | -24/+5 |
| * | Refactor unmapped buffer address handling. | jeff | 2015-07-23 | 3 | -29/+18 |
| * | Add an initial NUMA affinity/policy configuration for threads and processes. | adrian | 2015-07-11 | 4 | -11/+596 |
| * | The intention of r254304 was to scan the active queue continuously. | alc | 2015-07-08 | 2 | -15/+20 |
| * | Add a local variable initialization needed in the OBJT_DEFAULT case. | markj | 2015-07-05 | 1 | -0/+1 |
| * | vm: don't lock proc around accesses to vm_{t,d}addr and RLIMIT_DATA in sys_mmap | mjg | 2015-07-02 | 1 | -4/+2 |
| * | Account for the main process stack being one page below the highest | kib | 2015-07-02 | 1 | -1/+2 |
| * | Huge cleanup of random(4) code. | markm | 2015-06-30 | 1 | -32/+4 |
| * | If INVARIANTS is specified, add ctor/dtor to junk memory if they are | jmg | 2015-06-25 | 2 | -0/+19 |
