summaryrefslogtreecommitdiff
path: root/sys/kern/subr_pool.c
AgeCommit message (Expand)Author
2004-01-09Add a new pool initialization flag, PR_IMMEDRELEASE. This flag causesthorpej
2003-12-29pool_prime_page: initialize ph_time to mono_time instead of zeroyamt
2003-11-13two changes in improve scalability:chs
2003-04-09Add the ability for pool caches to cache the physical address ofthorpej
2003-03-16Only define POOL_LOGSIZE/pool_size if POOL_DIAGNOSTIC is defined.matt
2003-02-23Use splvm() instead of splhigh() when accessing the internal page header pool.pk
2003-01-18Merge the nathanw_sa branch.thorpej
2002-11-24Quell uninitialised variable warnings.scw
2002-11-09Fix signed/unsigned comparison warnings.thorpej
2002-11-08Parse the modifier of ddb command as documented.enami
2002-09-27remove trailing \n in panic(). approved perry.provos
2002-08-25Fix signed/unsigned comparison warnings from GCC 3.3.thorpej
2002-07-30Bring down a fix from the "newlock" branch, slightly modified:thorpej
2002-07-11Add wchan to a panic (must have NOWAIT).matt
2002-03-13Move 'struct pool_cache_group' definition into <sys/pool.h>simonb
2002-03-13Remove two instances of an "error" variable that is only ever assigned tosimonb
2002-03-09Put back pool_prime(); the i386 mp pmap uses it.thorpej
2002-03-09Fix a couple of typos in simple_{,un}lock()'s.thorpej
2002-03-09Remove pool_prime(). Nothing uses it, and how it should be used it notthorpej
2002-03-09If, when a page becomes idle, the backend allocator is waiting forthorpej
2002-03-09Remove PR_MALLOCOK and PR_STATIC. The former wasn't actually used,thorpej
2002-03-08Add a missing simple_unlock.thorpej
2002-03-08Add an optional "drain" client callback, which can be set by the newthorpej
2002-03-08Remove PR_FREEHEADER; nothing uses it anymore.thorpej
2002-03-08Pool deals fairly well with physical memory shortage, but it doesn'tthorpej
2001-11-20Call pr_log(PRLOG_GET) when POOL_DIAGNOSTIC is defined instead of DIAGNOSTICenami
2001-11-12add RCSIDslukem
2001-10-21in pool_drain(), call pool_reclaim() while we still have interrupts blockedchs
2001-10-07Add support for allocating pool memory in units smaller than a whole page.bjh21
2001-09-26jump through hoops to avoid calling uvm_km_free_poolpage() while holdingchs
2001-07-01Protect the `pool cache group' pool with splvm(), so that pool cachesthorpej
2001-06-05Do the reentrancy checking if POOL_DIAGNOSTIC, not DIAGNOSTIC. Preventsthorpej
2001-06-05Assert that no locks are held if we're called with PR_WAITOK.thorpej
2001-05-13Make this build again ifdef DIAGNOSTIC (oops)sommerfeld
2001-05-13Remove pool reentrancy testing overhead unless DIAGNOSTIC is defined.sommerfeld
2001-05-10Rearrange the code that adds pages of objects to the pool; requirethorpej
2001-05-10Use POOL_NEEDS_CATCHUP() in one more place.thorpej
2001-05-10Encapsulate the test for a pool needing a pool_catchup() in a macro.thorpej
2001-05-09Remove pool_create() and pool_prime(). Nothing except pool_create()thorpej
2001-05-04Add pool_cache_destruct_object(), used to force destruction ofthorpej
2001-01-29Don't use PR_URGENT to allocate page header. We don't want to just panicenami
2001-01-14Change some low-hanging splimp() calls to splvm().thorpej
2000-12-11Add some basic statistics to pool_cache.thorpej
2000-12-10Don't hold a pool cache lock across any call to pool_get() or pool_put().thorpej
2000-12-07...and when freeing cache groups, clear `freeto' if that's the onethorpej
2000-12-07When we invalidate a pool cache, make sure to clear `allocfrom' ifthorpej
2000-12-07Add a /c modifier to "show pool" to display pool caches.thorpej
2000-12-07This is a first-cut implementation of support for caching ofthorpej
2000-12-06ANSI'ify.thorpej
2000-11-19In pool_setlowat(), only call pool_catchup() if the pool is under thesommerfeld