summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2008-08-14on_each_cpu() compat fixup from krhAlex Deucher
2008-08-14radeon: fix kernel_mm properlyDave Airlie
2008-08-14radeon: FEDORA: patch to make 3D driver workDave Airlie
set gart buffers start
2008-08-14radeon: remove debuggingDave Airlie
2008-08-14radeon: use mm_enabled variable to denote memory manager runningDave Airlie
2008-08-14radeon: make buffer swap for older drivers work again on GEMDave Airlie
2008-08-14radeon: add userspace call for mm support checkDave Airlie
2008-08-14radeon: FEDORA: add old DMA buffers on top of GEMDave Airlie
This really shouldn't go upstream, it just lets me run the old 3D driver on GEM setup system
2008-08-13i915: setup hardware status page if physical addrs are requiredJesse Barnes
Needed for the modesetting case where we initialize the ring at load time.
2008-08-13Merge branch 'modesetting-101' into modesetting-gemJesse Barnes
2008-08-13Merge branch 'master' into modesetting-gemJesse Barnes
Conflicts: libdrm/Makefile.am libdrm/xf86drm.h shared-core/i915_dma.c shared-core/i915_irq.c
2008-08-13Don't call the vblank tasklet with irqs disabled.Thomas Hellstrom
If a specific tasklet shares data with irq context, it needs to take a private irq-blocking spinlock within the tasklet itself.
2008-08-12[intel_bufmgr_gem] Fix flink buffer name caching (#17085, #17092).Kristian Høgsberg
Store the global name in global_name, don't overwrite the gem_handle.
2008-08-12Add error checking to framebuffer creationJesse Barnes
Make the Intel routine return an error if needed and make the core check for it.
2008-08-12Export a generic dri_bo handle for use by clientsJesse Barnes
We'll need something like this (either a handle field or a dri_bo_get_handle function) for kernel mode setting to get at the handles.
2008-08-11libdrm: Allow build outside of source tree.Matthieu Herrb
2008-08-11drm_vm: fix for build on 2.6.22Dave Airlie
thanks to malc0 for pointing it out
2008-08-11drm: add OS_HAS_GEM option.Dave Airlie
To build i915 driver pass OS_HAS_GEM=1 to make for now
2008-08-09NV50: minor changesMaarten Maathuis
2008-08-09NV50: enable hotplug irqMaarten Maathuis
2008-08-09NV50: call drm_sysfs_hotplug_event when appropriateMaarten Maathuis
2008-08-09drm: TRUE/trueDave Airlie
2008-08-08Drop TTM interfaces from the userland library.Eric Anholt
2008-08-08Fix compile warning from check_aperture change.Eric Anholt
2008-08-08Merge branch 'drm-gem'Eric Anholt
Conflicts: shared-core/i915_dma.c This brings in kernel support and userland interface for intel GEM.
2008-08-08Replace the check_aperture API with one we can make thread-safe.Eric Anholt
While the bufmgr isn't thread-safe at the moment, we need it to be for shared objects between contexts.
2008-08-08nouveau: wait for pgraph idle after loading or saving a contextStuart Bennett
the nvidia driver does this, and it stops the error message appearing on nv40
2008-08-08radeon: add initial support for legacy crtc/encoders.Dave Airlie
not all there yet
2008-08-07Make modesetting-gem build with recent kernelsJesse Barnes
Needed to merge in VM fault changes & pci_read_base API update.
2008-08-07Make flink save the kernel-assigned name and return it instead of creating ↵Keith Packard
another name
2008-08-07Merge branch 'drm-gem' into modesetting-gemJesse Barnes
2008-08-06Switch from shmem_getpage to read_mapping_pageKeith Packard
2008-08-06radeon: fixup PCI GART table with GEM enabledDave Airlie
2008-08-06radeon: just evict to TT not cachedDave Airlie
2008-08-06drm: don't teardown things in modeset pathsDave Airlie
2008-08-06pcigart: fixup memset + remove wbinvdDave Airlie
2008-08-06radeon: fix setting new memmap in right placeDave Airlie
2008-08-05[gem-intel] Retiring flush requests should clear flushed write_domainsKeith Packard
When i915_gem_retire_request has a flush which matches an object write domain, clear the write domain. This will move the object to the inactive list rather than the flushing list, avoiding trouble with objects left stuck on the flushing list.
2008-08-05[gem-intel] Don't clear write_domain until flush completesKeith Packard
In i915_gem_object_wait_rendering, if the object write domain is being written by the GPU, the appropriate flushing commands are written to the device and an additional request queued to mark that flush. Finally, the function blocks on that new request. The bug was that the write_domain in the object was cleared before the function blocked. If the wait is interrupted by a signal, the flushing commands may still be pending. With the current write_domain information lost, the restarted syscall will drop right through the write_domain test as that value was lost, and so the function will not block at all. Oops. Fixed by simply moving the write_domain clear until after the wait_request succeeds. Note that the restarted system call will generate an additional flush sequence and request, but that should be 'harmless', aside from a slight performance impact. Someday we'll track flushing more accurately and clear write_domains more efficiently, but for now, this should suffice. This bug was discovered in the 2d gem development by running x11perf -copypixwin500 and noticing that the window got cleared accidentally.
2008-08-04Expose pin/unpin/set_tiling/flink APIsKeith Packard
2008-08-05radeon: fix blit due to registers wrongDave Airlie
2008-08-04drm: finish bo after lastcloseDave Airlie
2008-08-04radeon: add userspace mm enable switchDave Airlie
2008-08-04radeon: don't use ring if cp not goingDave Airlie
2008-08-04drm: remove unused typesDave Airlie
2008-08-04drm: fixup master code to use krefsDave Airlie
2008-08-04i915/radeon: use rmmap lockedDave Airlie
2008-08-04modesetting: pick_crtcs can't be staticDave Airlie
2008-08-04drm: remove unneeded debuggingDave Airlie
2008-08-01Merge commit 'origin/drm-gem' into modesetting-gemKristian Høgsberg
Conflicts: linux-core/Makefile.kernel linux-core/drmP.h linux-core/drm_mm.c linux-core/drm_stub.c linux-core/i915_gem.c linux-core/i915_opregion.c shared-core/i915_dma.c shared-core/i915_drv.h shared-core/i915_irq.c