| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Now that interrupt-safe uvm maps are porperly locked, the interrupt-safe |   kettenis | 2015-09-11 | 1 | -5/+1 |
| * | Give the pool page allocator backends more sensible names. We now have: | kettenis | 2015-09-08 | 1 | -20/+19 |
| * | Now that msleep(9) no longer requires the kernel lock (as long as PCATCH | kettenis | 2015-09-08 | 1 | -15/+2 |
| * | We no longer need to grab the kernel lock for allocating and freeing pages | kettenis | 2015-09-06 | 1 | -5/+11 |
| * | Push down the KERNEL_LOCK/KERNEL_UNLOCK calls into the back-end allocator | kettenis | 2015-09-01 | 1 | -7/+21 |
| * | re-enable *8. |   dlg | 2015-08-21 | 1 | -2/+2 |
| * | remove the POOL_NEEDS_CATCHUP macro, it isnt used. | dlg | 2015-07-23 | 1 | -4/+1 |
| * | Move `ticks' declaration to sys/kernel.h. |   uebayasi | 2015-07-20 | 1 | -3/+1 |
| * | disable *8 again for now. incoherent archs arent having much fun with it. | dlg | 2015-04-21 | 1 | -2/+2 |
| * | nothing uses pool_sleep, so get rid of it | dlg | 2015-04-07 | 1 | -3/+1 |
| * | introduce a garbage collector for (very) idle pool pages. | dlg | 2015-04-07 | 1 | -2/+53 |
| * | reintroduce r1.173: | dlg | 2015-03-20 | 1 | -2/+2 |
| * | Remove some includes include-what-you-use claims don't |   jsg | 2015-03-14 | 1 | -2/+1 |
| * | reintroduce page item cache colouring. | dlg | 2015-02-10 | 1 | -7/+20 |
| * | pool_chk_page iterates over a pages free item lists and checks that | dlg | 2015-01-22 | 1 | -11/+10 |
| * | white space fixes. no binary change. | dlg | 2015-01-19 | 1 | -7/+7 |
| * | splassert on some archs (or just sparc64) check that you're not in | dlg | 2015-01-05 | 1 | -1/+7 |
| * | back out r1.173, aka the "* 8" diff. it tickles a problem on some | dlg | 2015-01-04 | 1 | -2/+2 |
| * | avoid the use of an uninitialised variable in one of the codepaths in | jsg | 2015-01-04 | 1 | -2/+2 |
| * | remove some unused fields from pool. ok dlg |   tedu | 2014-12-22 | 1 | -7/+2 |
| * | if we're able to use large page allocators, try and place at least | dlg | 2014-12-22 | 1 | -2/+2 |
| * | timestamp empty pages, and only free them if theyve been idle for at least | dlg | 2014-12-19 | 1 | -2/+8 |
| * | the last commit changed LIST_INSERT_HEAD to TAILQ_INSERT_TAIL cos the | dlg | 2014-12-19 | 1 | -3/+3 |
| * | replace the page LISTS with page TAILQs. this will let me pull pages from | dlg | 2014-12-19 | 1 | -41/+41 |
| * | init the mutex used in sleeping pool_gets with the right ipl if the | dlg | 2014-12-04 | 1 | -3/+4 |
| * | move arc4random prototype to systm.h. more appropriate for most code | tedu | 2014-11-18 | 1 | -2/+1 |
| * | hoist the slowdown handling up to the pool_do_get callers. this lets | dlg | 2014-11-15 | 1 | -19/+16 |
| * | move the slowdown back up. it needs to take place after the allocated page | tedu | 2014-11-14 | 1 | -10/+18 |
| * | Grab the pool mutex in sysctl_dopool(), but only for pools for which | kettenis | 2014-11-10 | 1 | -4/+5 |
| * | remove color support. discussed with dlg and mikeb | tedu | 2014-11-01 | 1 | -14/+4 |
| * | take the pool_item pi_magic touching out from under #ifdef DIAGNOSTIC. | dlg | 2014-10-13 | 1 | -16/+4 |
| * | massage the pool item header and pool item magic words. | dlg | 2014-10-10 | 1 | -31/+55 |
| * | in pool_destroy, enter and leave mutex as necessary to satisfy assertions. | tedu | 2014-09-28 | 1 | -1/+3 |
| * | fix the calculation of the number of items to prime the pool with | dlg | 2014-09-26 | 1 | -2/+3 |
| * | Only compile poison-related code if DIAGNOSTIC instead of if !SMALL_KERNEL, |   miod | 2014-09-23 | 1 | -11/+7 |
| * | rework the pool code to make the locking more obvious (to me at | dlg | 2014-09-22 | 1 | -444/+334 |
| * | if userland asks for an unknown sysctl, return EOPNOTSUPP instead | dlg | 2014-09-17 | 1 | -2/+2 |
| * | disable taking the mutex to read pool stats. | dlg | 2014-09-16 | 1 | -3/+4 |
| * | tweak panics so they use __func__ consistently. | dlg | 2014-09-16 | 1 | -41/+37 |
| * | deprecate PR_DEBUG and MALLOC_DEBUG in pools. | dlg | 2014-09-16 | 1 | -24/+1 |
| * | remove uneeded proc.h includes | jsg | 2014-09-14 | 1 | -2/+1 |
| * | change some (flags & PR_WAITOK) to ISSET(flags, PR_WAITOK) | dlg | 2014-09-08 | 1 | -5/+5 |
| * | deprecate the use of the PR_PHINPAGE flag by replacing it with a test | dlg | 2014-09-08 | 1 | -26/+23 |
| * | KASSERT that the page header pool will use in page headers. | dlg | 2014-09-05 | 1 | -1/+4 |
| * | rework how pools with large pages (>PAGE_SIZE) are implemented. | dlg | 2014-09-04 | 1 | -122/+102 |
| * | deprecate the "item offset" handling. nothing uses it, so we can | dlg | 2014-08-27 | 1 | -21/+6 |
| * | bring back r1.130: | dlg | 2014-08-20 | 1 | -22/+32 |
| * | external page headers use an RB tree to find the page header | dlg | 2014-08-18 | 1 | -30/+25 |
| * | sigh. when returning ENOENT in the sysctl path, unlock on the way out. | dlg | 2014-08-12 | 1 | -2/+2 |
| * | i accidentally removed the check for whether the requested pool in | dlg | 2014-08-12 | 1 | -2/+6 |
