aboutsummaryrefslogtreecommitdiff
path: root/sys/net/netisr.c
Commit message (Expand)AuthorAgeFilesLines
* In case we cannot queue a packet reaching the queue limit, retain theBjoern A. Zeeb2009-06-301-0/+1
* In light of DPCPU use by netisr, revise various for loops from usingRobert Watson2009-06-261-17/+16
* Convert netisr to use dynamic per-CPU storage (DPCPU) instead of sizingRobert Watson2009-06-261-21/+40
* Add an optional callback function that will be invoked when a per-CPUBjoern A. Zeeb2009-06-141-0/+4
* Revert a recent netisr2 change: when billing packets to the currentRobert Watson2009-06-011-2/+0
* Garbage collect NETISR_POLL and NETISR_POLLMORE, which are no longerRobert Watson2009-06-011-6/+17
* Reimplement the netisr framework in order to support parallel netisrRobert Watson2009-06-011-157/+1029
* Garbage collect now-unused NETISR_FORCEQUEUE, which overrode the globalRobert Watson2009-05-131-10/+5
* Change the curvnet variable from a global const struct vnet *,Marko Zec2009-05-051-0/+4
* Remove NETISR_MPSAFE, which allows specific netisr handlers to be directlyRobert Watson2008-07-041-31/+15
* In keeping with style(9)'s recommendations on macros, use a ';'Robert Watson2008-03-161-1/+1
* Remove the now-unused NET_{LOCK,UNLOCK,ASSERT}_GIANT() macros, whichRobert Watson2007-08-061-1/+0
* First in a series of changes to remove the now-unused Giant compatibilityRobert Watson2007-07-271-92/+0
* Change net.isr.direct from defaulting to 0 to 1 in 7-CURRENT. ThisRobert Watson2006-11-281-1/+1
* - Don't pollute opt_global.h with DEVICE_POLLING and introduceGleb Smirnoff2005-10-051-0/+1
* Rename net.isr.enable to net.isr.dispatch.Robert Watson2005-10-041-5/+5
* Correctly unregister a netisr by clearing the ni->ni_queue field to NULL asAndre Oppermann2004-10-111-0/+1
* Correct a comment typo: s/Note/Not/.Robert Watson2004-09-031-1/+1
* Correct typo in printf() warning.Robert Watson2004-08-281-1/+1
* Change the default disposition of debug.mpsafenet from 0 to 1, whichRobert Watson2004-08-281-3/+84
* Apply error and success logic consistently to the function netisr_queue() andAndre Oppermann2004-08-271-3/+5
* Comment clarifying debug_mpsafenet.Robert Watson2004-07-181-4/+5
* o add a flags parameter to netisr_register that is used to specifySam Leffler2003-11-081-39/+45
* o make debug_mpsafenet globally visibleSam Leffler2003-11-051-0/+10
* When direct dispatching an netisr (net.isr.enable=1), if there are alreadyRobert Watson2003-10-031-13/+21
* Create a tunable for net.isr.enable so that it may be set fromRobert Watson2003-10-021-0/+1
* Temporarily turn net.isr.enable back off again until patches toRobert Watson2003-10-011-1/+1
* Enable net.isr.enable by default, causing "delivery to completion"Robert Watson2003-10-011-1/+1
* Discard the packet if the netisr queue is null instead of panicing, forJonathan Lemon2003-03-081-2/+8
* Update netisr handling; Each SWI now registers its queue, and all queueJonathan Lemon2003-03-041-58/+187
* Moved netisr code from kern/kern_intr.c to net/netisr.c as threatened in aJake Burkholder2002-09-221-0/+116