aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/i915/intel_pm.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-07-26 17:38:50 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2013-07-26 17:38:50 -0400
commit2408c2e5294144b7af34636ce0ac894b3195a136 (patch)
tree1d8500a23165cd5a0152010f71544b01b8f31c7d /drivers/gpu/drm/i915/intel_pm.c
parent0f746650258187664a7afa1f708618f6599f6d76 (diff)
parent8002db6336dd361fc13214e9515fe5d52ff294ee (diff)
Merge branch 'qxl-fixes' of git://people.freedesktop.org/~airlied/linux
Pull qxl drm fixes from Dave Airlie: "Okay as I warned, the qxl driver was running a bit free and loose with its ttm object reservations and the new lockdep enabled reservation tracking shone a bright light into it, it also with the new reservations mutexes hits a possible deadlock during boot. The first patch is a real fix to render the console correctly as the driver used to just drop irq renderering as too hard, this also fixes a sleeping while atomic warning. The other two patches are the big ugly ones that redo how the driver allocates objects and reserves them and makes things all work properly, I've tested this in a VM, and compared to the current code which hits a lockdep warning and the sleep while atomic warning before failing. So sorry this is coming in late, I should have tested qxl before merging the mutex code, but I'd rather just fix qxl with this than revert the reservations code at this point" * 'qxl-fixes' of git://people.freedesktop.org/~airlied/linux: qxl: convert qxl driver to proper use for reservations qxl: allow creation of pre-pinned objects and use for releases. drm/qxl: add delayed fb operations
Diffstat (limited to 'drivers/gpu/drm/i915/intel_pm.c')
0 files changed, 0 insertions, 0 deletions