index
:
wireguard-openbsd
jd/histogram
jd/queueboosts
jd/simplify-queueing
master
WireGuard implementation for the OpenBSD kernel
Matt Dunwoodie
summary
refs
log
tree
commit
diff
stats
log msg
author
committer
range
path:
root
/
sys
/
kern
/
vfs_biomem.c
(
follow
)
Commit message (
Expand
)
Author
Age
Files
Lines
*
clean up buffer cache statistics somewhat to
beck
2011-09-19
1
-4
/
+12
*
Revert previous diff decrementing bcstats.numbufpages here. This function
beck
2011-04-07
1
-3
/
+9
*
fix nasty buffer cache bug where we could forget about pages shrunk off of a
beck
2011-04-05
1
-1
/
+2
*
Constrain the buffer cache to use only the dma reachable region of memory.
beck
2011-04-02
1
-19
/
+5
*
Right now, if anything internal changes with a uvm object, diverse
oga
2010-04-30
1
-5
/
+2
*
the atomic primitives are still impossible to get at without using proc.h
deraadt
2010-04-21
1
-1
/
+2
*
buf_dealloc_mem can be called without B_BUSY. Don't decrement busymapped in that case.
art
2009-08-09
1
-2
/
+3
*
Keep track of number of currently mapped and B_BUSY buffers. beck@ ok
art
2009-08-09
1
-1
/
+5
*
reintroduce the uvm_tree commit.
oga
2009-08-06
1
-2
/
+2
*
backout the buf_acquire() does the bremfree() since all callers
thib
2009-06-25
1
-3
/
+1
*
Backout all changes to uvm after pmemrange (which will be backed out
oga
2009-06-16
1
-2
/
+2
*
All caller of buf_acquire were doing bremfree before the call.
art
2009-06-06
1
-1
/
+3
*
Instead of the global hash table with the terrible hashfunction and a
oga
2009-06-02
1
-2
/
+2
*
Make the interactions in allocating buffers less confusing.
art
2009-04-22
1
-17
/
+40
*
Use atop() and ptoa() in buf_free_pages() to make it consistent with
pedro
2008-11-08
1
-3
/
+3
*
Make buf_dealloc_mem() remove the mapping even if b_pobj is NULL. Otherwise
kettenis
2008-08-03
1
-8
/
+9
*
add $OpenBSD$ tag.
thib
2008-06-11
1
-0
/
+1
*
Buffer cache revamp
beck
2008-06-10
1
-0
/
+305