| Commit message (Expand) | Author | Age | Files | Lines |
* | Since breakage of malloc(9)/uma_zalloc(9) is totally non-optional in | green | 2004-07-19 | 1 | -0/+6 |
* | Introduce debug.nosleepwithlocks sysctl, 0 by default. If set to 1 | bmilekic | 2004-07-04 | 1 | -11/+9 |
* | Reextend the M_WAITOK-disabling-hack to all three of the mbuf-related | green | 2004-07-04 | 1 | -2/+4 |
* | Limit mbuma damage. Suddenly ALL allocations with M_WAITOK are subject | green | 2004-07-03 | 1 | -4/+8 |
* | Make uma_mtx MTX_RECURSE. Here's why: | bmilekic | 2004-06-23 | 1 | -1/+11 |
* | Backout previous change, I think Julian has a better solution which | bmilekic | 2004-06-09 | 1 | -1/+1 |
* | Make the slabrefzone, the zone from which we allocated slabs with | bmilekic | 2004-06-09 | 1 | -1/+2 |
* | Bring in mbuma to replace mballoc. | bmilekic | 2004-05-31 | 1 | -272/+618 |
* | - Make the acquisition of Giant in vm_fault_unwire() conditional on the | alc | 2004-03-10 | 1 | -11/+1 |
* | Mark uma_callout as CALLOUT_MPSAFE, as uma_timeout can run MPSAFE. | rwatson | 2004-03-07 | 1 | -1/+1 |
* | - Fix a problem where we did not drain the cache of buckets in the zone | jeff | 2004-02-01 | 1 | -8/+21 |
* | Mechanical whitespace cleanup. | des | 2004-01-30 | 1 | -41/+41 |
* | Fix all users of mp_maxid to use the same semantics, namely: | jhb | 2003-12-03 | 1 | -16/+8 |
* | - Unbreak UP. mp_maxid is not defined on uni-processor machines, although | jeff | 2003-11-30 | 1 | -0/+8 |
* | - Replace the local maxcpu with mp_maxid. Previously, if mp_maxid | jeff | 2003-11-30 | 1 | -20/+48 |
* | - Remove use of Giant from uma_zone_set_obj(). | alc | 2003-11-14 | 1 | -7/+1 |
* | - Fix MD_SMALL_ALLOC on architectures that support it. Define a new alloc | jeff | 2003-09-21 | 1 | -21/+46 |
* | Bad Jeffr! No cookie! | peter | 2003-09-20 | 1 | -2/+2 |
* | - Remove the working-set algorithm. Instead, use the per cpu buckets as the | jeff | 2003-09-19 | 1 | -75/+28 |
* | - Remove the cache colorization code. We can't use it due to all of the | jeff | 2003-09-19 | 1 | -50/+0 |
* | - There are an endless stream of style(9) errors in this file. Fix a few. | jeff | 2003-09-19 | 1 | -44/+18 |
* | - Don't inspect the zone in page_alloc(). It may be NULL. | jeff | 2003-09-19 | 1 | -5/+6 |
* | - Move the logic for dealing with the uma_boot_pages cache into the | jeff | 2003-09-19 | 1 | -21/+22 |
* | - Fix the silly flag situation in UMA. Remove redundant ZFLAG/ZONE flags | jeff | 2003-09-19 | 1 | -40/+31 |
* | - Don't abuse M_DEVBUF, define a tag for UMA hashes. | jeff | 2003-09-19 | 1 | -3/+4 |
* | - Eliminate a pair of unnecessary variables. | jeff | 2003-09-19 | 1 | -9/+4 |
* | - Initialize a pool of bucket zones so that we waste less space on zones that | jeff | 2003-09-19 | 1 | -75/+139 |
* | In sysctl_vm_zone, do not calculate per-cpu cache stats on | bmilekic | 2003-08-20 | 1 | -20/+17 |
* | - When deciding whether to init the zone with small_init or large_init, | bmilekic | 2003-08-11 | 1 | -5/+24 |
* | Revise obj_alloc(). Most notably, use the object's lock to prevent two | alc | 2003-08-03 | 1 | -17/+30 |
* | When INVARIANTS is on and we're in uma_zalloc_free(), we need to make | bmilekic | 2003-08-02 | 1 | -0/+15 |
* | Only free the pcpu cache buckets if they are non-NULL. | bmilekic | 2003-08-01 | 1 | -4/+6 |
* | Plug a race and a leak in UMA. | bmilekic | 2003-07-30 | 1 | -13/+29 |
* | When generating the zone stats make sure to handle the master zone | bmilekic | 2003-07-30 | 1 | -0/+7 |
* | Remove the disabling of buckets workaround. | phk | 2003-07-30 | 1 | -1/+0 |
* | - Get rid of the ill-conceived uz_cachefree member of uma_zone. | jeff | 2003-07-30 | 1 | -15/+24 |
* | - Check to see if we need a slab prior to allocating one. Failure to do | jeff | 2003-07-30 | 1 | -2/+2 |
* | Temporary workaround: Always disable buckets, there is a bug there | phk | 2003-07-29 | 1 | -0/+1 |
* | None of the "alloc" functions used by UMA assume that Giant is held any | alc | 2003-07-28 | 1 | -9/+2 |
* | Gulp ... call kmem_malloc() without Giant. | alc | 2003-07-26 | 1 | -7/+1 |
* | When INVARIANTS is defined make sure that uma_zalloc_arg (and hence | harti | 2003-07-18 | 1 | -0/+20 |
* | Move the pcpu lock out of the uma_cache and instead have a single set | bmilekic | 2003-06-25 | 1 | -28/+18 |
* | Make sure that the zone destructor doesn't get called twice in | bmilekic | 2003-06-25 | 1 | -2/+6 |
* | Use __FBSDID(). | obrien | 2003-06-11 | 1 | -4/+3 |
* | Revert last commit, I have no idea what happened. | phk | 2003-06-09 | 1 | -1/+1 |
* | A white-space nit I noticed. | phk | 2003-06-09 | 1 | -1/+1 |
* | uma_zone_set_obj() must perform VM_OBJECT_LOCK_INIT() if the caller | alc | 2003-04-28 | 1 | -2/+3 |
* | Remove an XXX comment. It is no longer a problem. | alc | 2003-04-26 | 1 | -4/+1 |
* | Lock the vm_object in obj_alloc(). | alc | 2003-04-19 | 1 | -0/+2 |
* | Don't grab Giant in slab_zalloc() if M_NOWAIT is specified. This | gallatin | 2003-04-18 | 1 | -4/+9 |