summaryrefslogtreecommitdiffstats
path: root/sys/amd64/amd64/busdma_machdep.c
Commit message (Expand)AuthorAgeFilesLines
* Introduce bus_dmamap_load_mbuf_sg(). Instead of taking a callback arg, thisscottl2005-01-071-13/+48
* Begin all license/copyright comments with /*-imp2005-01-051-1/+1
* Don't flag alignment constraints as a reason for bouncing. This fixes thescottl2004-11-291-1/+1
* Remove an extra #includescottl2004-11-211-1/+0
* Consolidate all of the bounce tests into the BUS_DMA_COULD_BOUNCE flag.scottl2004-11-211-29/+45
* Revert part of rev 1.56. Tag boundaries are handled by splitting segments,scottl2004-11-191-9/+5
* MFi386 rev 1.63-1.64:scottl2004-11-101-37/+142
* MFi386:peter2004-11-051-28/+79
* Fix a problem with tag->boundary inheritence that has existed since day onescottl2004-09-081-5/+5
* Sync with i386 - dont count needed bounce pages if loading a buffer thatpeter2004-08-161-1/+1
* MFi386: 1.57: transparently respect alignment/boundary tagspeter2004-07-081-11/+47
* Now that contigfree() does not require Giant, don't grab it in busdma.scottl2004-03-131-2/+0
* MFi386 rev 1.51 by scottl: make dflt_lock() always panic.peter2003-09-221-4/+0
* MFi386 rev 1.53 by scottl: Allocate the S/G list in the tag, not onpeter2003-09-221-27/+32
* MFi386 rev 1.55 by sam: remove unused #define BUS_DMAMAP_NSEGSpeter2003-09-221-2/+0
* In _bus_dmamap_load_buffer(), only count the number of bounce pages needed ifscottl2003-08-041-1/+2
* - Introduce a new busdma flag BUS_DMA_ZERO to request for zero'edmux2003-07-271-8/+11
* Sync more things with other backends.mux2003-07-011-12/+10
* Honor the boundary of the busdma tag when allocating bounce pages.mux2003-07-011-1/+1
* Mega busdma API commit.scottl2003-07-011-6/+55
* Catch amd64 up with the pending busdma async callback locking. Though thisscottl2003-06-281-0/+5
* Bring back bus_dmasync_op_t. It is now a typedef to an int, though thescottl2003-05-271-1/+1
* De-orbit bus_dmamem_alloc_size(). It's a hack and was never used anyways.scottl2003-05-261-26/+9
* style(9)mux2003-04-151-2/+2
* Restore delayed load support for the resource shortage case.simokawa2003-04-141-3/+27
* * Use _bus_dmamap_load_buffer() and respect maxsegsz in bus_dmamap_load().simokawa2003-04-141-119/+30
* Change the operation parameter of bus_dmamap_sync() from anmux2003-04-101-11/+4
* Add support for bounce buffers to _bus_dmamap_load_buffer, which is thejake2003-04-071-20/+63
* - Add vm_paddr_t, a physical address type. This is required for systemsjake2003-03-251-13/+17
* Use atomic operations to increment and decrement the refcountmux2003-03-201-4/+4
* - Lock down the bounce pages structures. We use the same locking schememux2003-03-171-26/+34
* Grab Giant around calls to contigmalloc() and contigfree() somux2003-03-131-1/+8
* Correctly set BUS_SPACE_MAXSIZE in all the busdma backends.mux2003-02-261-1/+1
* Back out M_* changes, per decision of the TRB.imp2003-02-191-2/+2
* Fix a problem in bus_dmamap_load_{mbuf,uio} when the first mbuf or the firstharti2003-02-041-11/+16
* Consolidate MIN/MAX macros into one place (param.h).alfred2003-02-021-2/+0
* Implement bus_dmamem_alloc_size() and bus_dmamem_free_size() asscottl2003-01-291-8/+26
* Remove M_TRYWAIT/M_WAITOK/M_WAIT. Callers should use 0.alfred2003-01-211-2/+2
* New bus_dma interfaces for use by crypto device drivers:sam2002-10-041-0/+206
* Don't use "NULL" when "0" is really meant.archie2002-08-211-1/+1
* Clean up:alfred2002-04-191-4/+10
* Change the preemption code for software interrupt thread schedules andjhb2002-01-051-1/+1
* Teach bus_dmamem_free() about contigfree(). This is a bit of a hack,wpaul2001-08-151-0/+3
* With Alfred's permission, remove vm_mtx in favor of a fine-grained approachdillon2001-07-041-0/+1
* Introduce a global lock for the vm subsystem (vm_mtx).alfred2001-05-191-0/+2
* - Catch up to the new swi API changes:jhb2001-02-091-1/+1
* Convert more malloc+bzero to malloc+M_ZERO.dwmalone2000-12-081-9/+7
* - Overhaul the software interrupt code to use interrupt threads for eachjhb2000-10-251-1/+3
* Back out the previous change to the queue(3) interface.jake2000-05-261-5/+5
* Change the way that the queue(3) structures are declared; don't assume thatjake2000-05-231-5/+5
OpenPOWER on IntegriCloud