Age | Commit message (Expand) | Author |
2016-03-17 | - add realloc_pages to move a buffer's physmem from one range to another. | Bob Beck |
2015-07-19 | Change uvm_page[re]alloc_multi to actually use the flags passed in, and return | Bob Beck |
2014-12-17 | Prefer MADV_* over POSIX_MADV_* in kernel for consistency: the latter | Philip Guenther |
2014-12-15 | Use MAP_INHERIT_* for the 'inh' argument to the UMV_MAPFLAG() macro, | Philip Guenther |
2014-11-16 | Replace a plethora of historical protection options with just | Theo de Raadt |
2014-08-11 | Do not pmap_update(pmap_kernel()) within the `create mappings' loop, but only | Miod Vallat |
2014-03-28 | Reduce uvm include madness. Use <uvm/uvm_extern.h> instead of | Martin Pieuchot |
2013-07-09 | back out the cache flipper temporarily to work out of tree. | Bob Beck |
2013-06-27 | B_WANTED is set when we want a B_BUSY buffer - Therefore we should always | Bob Beck |
2013-06-13 | beck would prefer to keep things just as they were for a while longer. | Ted Unangst |
2013-06-11 | sprinkle knf fairy dust over new buf code | Ted Unangst |
2013-06-11 | High memory page flipping for the buffer cache. | Bob Beck |
2013-01-18 | oops. this kassert should have gone with the B_NOTMAPPED commit | Bob Beck |
2013-01-18 | Give buf_acquire_unmapped and B_NOTMAPPED a viking funeral as they should | Bob Beck |
2012-12-02 | Fix kva reserve - ensure that kva reserve is checked for, as well | Bob Beck |
2012-11-18 | These functions all should be called with splbio, so splassert(IPL_BIO) | Bob Beck |
2012-11-17 | Don't map a buffer (and potentially sleep) when invalidating it in vinvalbuf. | Bob Beck |
2011-09-19 | clean up buffer cache statistics somewhat to | Bob Beck |
2011-04-07 | Revert previous diff decrementing bcstats.numbufpages here. This function | Bob Beck |
2011-04-05 | fix nasty buffer cache bug where we could forget about pages shrunk off of a | Bob Beck |
2011-04-02 | Constrain the buffer cache to use only the dma reachable region of memory. | Bob Beck |
2010-04-30 | Right now, if anything internal changes with a uvm object, diverse | Owain Ainsworth |
2010-04-21 | the atomic primitives are still impossible to get at without using proc.h | Theo de Raadt |
2009-08-09 | buf_dealloc_mem can be called without B_BUSY. Don't decrement busymapped in t... | Artur Grabowski |
2009-08-09 | Keep track of number of currently mapped and B_BUSY buffers. beck@ ok | Artur Grabowski |
2009-08-06 | reintroduce the uvm_tree commit. | Owain Ainsworth |
2009-06-25 | backout the buf_acquire() does the bremfree() since all callers | Thordur I. Bjornsson |
2009-06-16 | Backout all changes to uvm after pmemrange (which will be backed out | Owain Ainsworth |
2009-06-06 | All caller of buf_acquire were doing bremfree before the call. | Artur Grabowski |
2009-06-02 | Instead of the global hash table with the terrible hashfunction and a | Owain Ainsworth |
2009-04-22 | Make the interactions in allocating buffers less confusing. | Artur Grabowski |
2008-11-08 | Use atop() and ptoa() in buf_free_pages() to make it consistent with | Pedro Martelletto |
2008-08-03 | Make buf_dealloc_mem() remove the mapping even if b_pobj is NULL. Otherwise | Mark Kettenis |
2008-06-11 | add $OpenBSD$ tag. | Thordur I. Bjornsson |
2008-06-10 | Buffer cache revamp | Bob Beck |