summaryrefslogtreecommitdiff
path: root/linux-core
AgeCommit message (Collapse)Author
2008-05-01Use krefs for refcounting.Keith Packard
krefs are way easier than a custom-coded spinlock+int combo.
2008-05-01Unbind objects when freeing, fix some error paths, and warn in others.Eric Anholt
2008-05-01Fix offset passed to AGP to be pages instead of bytes.Eric Anholt
Fix some utterly bonged loop while we were staring at it.
2008-05-01Fix missing member settings in obj/obj_priv, and some error paths.Eric Anholt
2008-05-01Make GEM object handles be nonzero.Eric Anholt
2008-05-01Remove _args from gem ioctl argument structure tags.Eric Anholt
2008-05-01Add pin/unpin object ioctls for gem.Eric Anholt
2008-05-01checkpoint: relocations support.Eric Anholt
2008-05-01checkpoint: gtt binding written.Eric Anholt
2008-05-01checkpoint: rename to GEM and a few more i915 bits.Eric Anholt
2008-04-30Hacking towards hooking up execbuffer.Eric Anholt
2008-04-29Remove the remainder of the mmfs device.Eric Anholt
2008-04-29Move mmfs ioctls into the DRM. Untested.Eric Anholt
2008-04-28Rename drm_mm.c and its fuctions to drm_memrange.Eric Anholt
It's not really a graphics memory allocator, just something to track ranges of address space. It doesn't involve actual allocation, and was consuming some desired namespace.
2008-04-23Add mmap ioctl to mmfs.Eric Anholt
2008-04-23Add pread/pwrite ioctls to mmfs.Eric Anholt
2008-04-23Move mmfs.h userland interface to shared-core.Eric Anholt
2008-04-23Initial add of mmfs module.Eric Anholt
2008-04-23Clarify that drm_agp_ttm_backend is associated with a drm_ttm.Eric Anholt
On first looking at it I assumed it was an aspect of the ttm backend as a whole rather than specific allocations from a backend.
2008-04-22linux-core Makefile: add GIT_REVISIONPekka Paalanen
This tries to automatically fetch a git revision string and if succeeds, it #defines GIT_REVISION string macro. Packagers can override it by 'make GIT_REVISION=foo'. Update Nouveau to use GIT_REVISION, if defined, instead of DRIVER_DATE in struct drm_driver. Signed-off-by: Pekka Paalanen <pq@iki.fi>
2008-04-14Fix buffer object map wait error.Thomas Hellstrom
Add some branch prediction hints.
2008-04-14Fix buffer object creation validation.Thomas Hellstrom
BO lock fixes.
2008-04-14Unlock the BO mutex while waiting for idle, unmapped, unfenced.Thomas Hellstrom
Move unfenced checking into idle checking. Never time out while waiting for software events like unmapped or unfenced.
2008-04-14Fix up buffer manager locking.Thomas Hellstrom
2008-04-11Save and restore dsparb and d_state regsKeith Packard
2008-04-07Missing KERNEL_VERSION macroPatrice Mandin
2008-04-07nouveau: enable accelerated move to sysmemBen Skeggs
2008-04-07nouveau: enable m2mf for tt<->vram moves, fix fence_pollBen Skeggs
2008-04-06Place highmem pages last in the ttm page array.Thomas Hellstrom
2008-04-06Use clflush() when available for cache flushing.Thomas Hellstrom
2008-04-06[I915] Fix VRAM eviction.Thomas Hellstrom
2008-04-06Fix emergency allocation accounting.Thomas Hellstrom
2008-03-30Initialize the fence::error member.Thomas Hellstrom
2008-03-30[i915] Report buffer state _after_ fence submission to user-space.Thomas Hellstrom
This fixes a problem where the wrong bo->fence_type was reported, and also saves some memory space. [bo core] export the drm_bo_fill_rep_arg function.
2008-03-30Don't call fence::poll during irq if there are no waiters.Thomas Hellström
2008-03-24nouveau: silence warningBen Skeggs
2008-03-17Evict cached_mapped relocatee before applying reloc.Thomas Hellstrom
Fix that got left out after the intel-post-reloc merge.
2008-03-17drm/pcigart: fix the pci gart to use the drm_pci wrapper.Dave Airlie
This is the correct fix for the RS690 and hopefully the dma coherent work. For now we limit everybody to a 32-bit DMA mask but it is possible for RS690 to use a 40-bit DMA mask for the GART table itself, and the PCIE cards can use 40-bits for the table entries. Signed-off-by: Dave Airlie <airlied@redhat.com>
2008-03-16[via] Allow a little larger stride for SG DMA DownloadFromScreen.Thomas Hellstrom
2008-03-16ati: fix rs690 igp gart by allocating the page table in 32-bit memoryDave Airlie
2008-03-16drm: this u32 should be a dma_addr_tDave Airlie
doesn't fix anything but just making it consistent
2008-03-14fix build problemsAlan Hourihane
2008-03-14drm: Fix race that can lockup the kernelMike Isely
The i915_vblank_swap() function schedules an automatic buffer swap upon receipt of the vertical sync interrupt. Such an operation is lengthy so it can't be allowed to happen in normal interrupt context, thus the DRM implements this by scheduling the work in a kernel softirq-scheduled tasklet. In order for the buffer swap to work safely, the DRM's central lock must be taken, via a call to drm_lock_take() located in drivers/char/drm/drm_irq.c within the function drm_locked_tasklet_func(). The lock-taking logic uses a non-interrupt-blocking spinlock to implement the manipulations needed to take the lock. This semantic would be safe if all attempts to use the spinlock only happen from process context. However this buffer swap happens from softirq context which is really a form of interrupt context. Thus we have an unsafe situation, in that drm_locked_tasklet_func() can block on a spinlock already taken by a thread in process context which will never get scheduled again because of the blocked softirq tasklet. This wedges the kernel hard. To trigger this bug, run a dual-head cloned mode configuration which uses the i915 drm, then execute an opengl application which synchronizes buffer swaps against the vertical sync interrupt. In my testing, a lockup always results after running anywhere from 5 minutes to an hour and a half. I believe dual-head is needed to really trigger the problem because then the vertical sync interrupt handling is no longer predictable (due to being interrupt-sourced from two different heads running at different speeds). This raises the probability of the tasklet trying to run while the userspace DRI is doing things to the GPU (and manipulating the DRM lock). The fix is to change the relevant spinlock semantics to be the interrupt-blocking form. After this change I am no longer able to trigger the lockup; the longest test run so far was 20 hours (test stopped after that point). Note: I have examined the places where this spinlock is being employed; all are reasonably short bounded sequences and should be suitable for interrupts being blocked without impacting overall kernel interrupt response latency. Signed-off-by: Mike Isely <isely@pobox.com>
2008-03-12Merge branch 'intel-post-reloc'Thomas Hellstrom
Conflicts: linux-core/drm_compat.c linux-core/drm_compat.h linux-core/drm_ttm.c shared-core/i915_dma.c Bump driver minor to 13 due to introduction of new relocation type.
2008-03-12Bug # 14712Thomas Hellstrom
Disable page saving for GPU read-only TTMs.
2008-03-12Dont allow !sysadmin clients to alter the memory type ofThomas Hellstrom
NO_EVICT buffers.
2008-03-12Fix for debug memory routinesAlan Hourihane
2008-03-12Add error messageAlan Hourihane
2008-03-12Add an emergency pinnable memory quota for root-only processes.Thomas Hellstrom
2008-03-12Fix kernel crash when we hit OOM conditions.Thomas Hellstrom
(Alan Hourihane)