]> bbs.cooldavid.org Git - net-next-2.6.git/commit
drm/ttm: ttm_fault callback to allow driver to handle bo placement V6
authorJerome Glisse <jglisse@redhat.com>
Fri, 9 Apr 2010 12:39:23 +0000 (14:39 +0200)
committerDave Airlie <airlied@redhat.com>
Tue, 20 Apr 2010 04:12:05 +0000 (14:12 +1000)
commit82c5da6bf8b55a931b042fb531083863d26c8020
tree88168d32d7060598ac730c30967b2e62dc5da28d
parent9d87fa2138d06ff400551800d67d522625033e35
drm/ttm: ttm_fault callback to allow driver to handle bo placement V6

On fault the driver is given the opportunity to perform any operation
it sees fit in order to place the buffer into a CPU visible area of
memory. This patch doesn't break TTM users, nouveau, vmwgfx and radeon
should keep working properly. Future patch will take advantage of this
infrastructure and remove the old path from TTM once driver are
converted.

V2 return VM_FAULT_NOPAGE if callback return -EBUSY or -ERESTARTSYS
V3 balance io_mem_reserve and io_mem_free call, fault_reserve_notify
   is responsible to perform any necessary task for mapping to succeed
V4 minor cleanup, atomic_t -> bool as member is protected by reserve
   mecanism from concurent access
V5 the callback is now responsible for iomapping the bo and providing
   a virtual address this simplify TTM and will allow to get rid of
   TTM_MEMTYPE_FLAG_NEEDS_IOREMAP
V6 use the bus addr data to decide to ioremap or this isn't needed
   but we don't necesarily need to ioremap in the callback but still
   allow driver to use static mapping

Signed-off-by: Jerome Glisse <jglisse@redhat.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
drivers/gpu/drm/ttm/ttm_bo.c
drivers/gpu/drm/ttm/ttm_bo_util.c
drivers/gpu/drm/ttm/ttm_bo_vm.c
include/drm/ttm/ttm_bo_api.h
include/drm/ttm/ttm_bo_driver.h