summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
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
2008-08-01Revert "i915: Move all of the irq install/uninstall to load time."Dave Airlie
This reverts commit 965a72202b439068e62ac341990f51953457b202. Please re-do over properly
2008-07-31drm: add fault handler support so as to be more like possible upstreamDave Airlie
2008-07-30intel-gem: Replace version bump signalling GEM with I915_PARAM_HAS_GEM.Eric Anholt
2008-07-30intel-gem: Remove dead field from reverted changes.Eric Anholt
2008-07-30Revert "Rename drm_mm.c and its fuctions to drm_memrange."Eric Anholt
This reverts commit 3ad8db2071d30c198403e605f2726fc5c3e46bfd. We ended up not needing that namespace, and I'd rather not have the churn for producing diffs.
2008-07-30i915: more version checksDave Airlie
2008-07-30i915: add version checks for opregion on old kernelsDave Airlie
2008-07-29intel-gem: actually add i915_gem_debug.c.Eric Anholt
2008-07-29intel-gem: Check return value of pci_read_base.Eric Anholt
2008-07-29r300: Fix cliprect emitNicolai Haehnle
This makes our handling of cliprects sane. drm_clip_rect always has exclusive bottom-right corners, but the hardware expects inclusive bottom-right corners, so we adjust this here. This complements Michel Daenzer's commit 57aea290e1e0a26d1e74df6cff777eb9f038f1f8 to Mesa. See also http://bugs.freedesktop.org/show_bug.cgi?id=16123 .
2008-07-28intel: Fix typo in unused register definition name.Eric Anholt
2008-07-28intel-gem: checkpatch.pl on drm_proc.c new contents.Eric Anholt
2008-07-28Merge commit 'origin/master' into drm-gemEric Anholt
Conflicts: linux-core/Makefile.kernel shared-core/i915_dma.c shared-core/i915_drv.h shared-core/i915_irq.c
2008-07-29nouveau: fix nv04 fifo context save to save reg contents, not reg offsetStuart Bennett
clearly the function had never been used :)
2008-07-29nouveau: fix bad rename from 5a072f32c8f941d1ef301811881e8c89c8d8a5f1Stuart Bennett
2008-07-28intel-gem: Another checkpatch.pl pass.Eric Anholt
2008-07-28intel-gem: Fix regression tests.Eric Anholt
Main fix is an oops that was triggered by the gtt pwrite path when we don't have the gtt initialized. Also, settle on -EBADF for "bad object handle", and -EINVAL for "reading/writing beyond object boundary".
2008-07-28intel-gem: Speed up tiled readpixels by tracking which pages have been flushed.Eric Anholt
This is around 3x or so speedup, since we would read wide rows at a time, and clflush each tile 8 times as a result. We'll want code related to this anyway when we do fault-based per-page clflushing for sw fallbacks.
2008-07-26intel-gem: Move debug-only functions to a separate file.Eric Anholt
2008-07-26radeon: Add suspend/resume hooks for saving/clearing/restoring interrupts.Stefan Becker
Fixes http://bugs.freedesktop.org/show_bug.cgi?id=16799 .
2008-07-26r300_cmdbuf: Always emit INDX_BUFFER immediately after DRAW_INDEXNicolai Haehnle
DRAW_INDEX writes a vertex count to VAP_VF_CNTL. Docs say that behaviour is undefined (i.e. lockups happen) when this write is not followed by the right number of vertex indices. Thus we used to do the wrong thing when drawing across many cliprects was necessary, because we emitted a sequence DRAW_INDEX, DRAW_INDEX, INDX_BUFFER, INDX_BUFFER instead of DRAW_INDEX, INDX_BUFFER, DRAW_INDEX, INDX_BUFFER The latter is what we're doing now and which ought to be correct.
2008-07-25[FreeBSD] Duh, we need to actually define the drm_modeset_ctl...Robert Noland
2008-07-25drm: don't set the signal blocker on the master process.Dave Airlie
this lets us debug the X server through xkb startup. Not sure what the correct answer is, probably X needs to drop the lock when execing stuff, with input hotplug it can get xkb stuff at any time I believe.
2008-07-24[FreeBSD] Catch up to linux on vblank-reworkRobert Noland
2008-07-23i915: Move all of the irq install/uninstall to load time.Robert Noland
This resolves a panic on FreeBSD which was caused by trying to re-initialize the swap lock. It's just much easier to initialize all of the locks at load time. It should also ensure that the vblank structures are available earlier.
2008-07-23intel-gem: Fix pread math and logic errors.Eric Anholt
Fixes an oops in fbotexture from walking off the end of the page list.
2008-07-23intel-gem: Add a quick hack to reduce clflushing on pread.Eric Anholt
This increases overhead for the large-readpixels case due to the repeated page cache accessing, but greatly reduces overhead for the small-readpixels case.
2008-07-23intel-gem: Don't do the GTT-pwrite shortcut on tiled buffers.Eric Anholt
These will be covered by the fence, while pread/pwrite are supposed to be CPU-perspective writes, with manual detiling done by the client.
2008-07-23intel-gem: Move /proc debugging to a separate file.Eric Anholt
2008-07-22radeon: fix typo with a better typoDave Airlie
2008-07-22radeon: fix type DST vs Z cache flushDave Airlie
2008-07-21[FreeBSD] Improve upper_32_bits define.Robert Noland
Thanks to airlied.
2008-07-21intel-gem: Remove recently added pci_read_base prototype.Eric Anholt
This is in pci.h in the fixed patch to the kernel.
2008-07-21intel-gem: Set up HWS when it needs a vaddr during GEM init.Eric Anholt
This requires an updated 2D driver to not try to set it up as well.
2008-07-21Remove accidental leftover tests.Michel Dänzer
Thanks to Nicolai Haehnle for pointing this out on IRC.
2008-07-21Reinstate dev->vblank_enabled[].Michel Dänzer
I incorrectly thought it was obsolete.
2008-07-21Drop workaround for driver vblank counter going backwards.Michel Dänzer
The driver code that caused this is no longer necessary and has been dropped.
2008-07-21radeon: Post-vblank-rework-rework cleanups.Michel Dänzer
Thanks to the reworked vblank-rework, we can just use the hardware frame counter directly, and make the RADEON_PARAM_VBLANK_CRTC getparam just return what was set by the corresponding setparam.
2008-07-21vblank-rework rework cleanups.Michel Dänzer
Remove some dead/obsolete code and make drm_update_vblank_count() static.
2008-07-21Remove obsolete dev->vblank_suspend[crtc] tests.Michel Dänzer
Caused drm_update_vblank_count() not to do its thing when called from drm_modeset_ctl() -> drm_vblank_get(). The vblank functionality no longer needs to be suspended during a modeset, so rename the field to vblank_inmodeset.
2008-07-19i915: convert to using drm_vblank_get/put around vblank counter usageJesse Barnes
All interrupt off vblank count updates are done in drm_vblank_get/put now, so convert users of the vblank counter over to that interface.
2008-07-19Update vblank code to new APIJesse Barnes
In my last push I forgot to convert users of drm_update_vblank_count over to drm_vblank_get/put, since that's where any interrupt off->on update accounting is done now. Since the modeset ioctl did something similar (an open coded update of the counter) convert it over to using get/put too, which saves us from having to deal with every combination of interrupt off & on between calls.
2008-07-18drm-gem: Fix buildIan Romanick
On some distros missing prototypes cause kernel builds to fail. These are hack to make the code build.
2008-07-18intel-gem: Leave 8xx tiling on until we find any issues.Eric Anholt
2008-07-18radeon: remove microcode versionDave Airlie
2008-07-18drm/radeon: fixup 0 vs NULLDave Airlie
2008-07-17[FreeBSD] drm_irq.c updates for vblank fixes.Robert Noland
2008-07-17i915: remove old broken vblank codeJesse Barnes
Remove the unused (and broken) "in vblank" code now that the core has been fixed to use a counter while interrupts are enabled. Also make the vblank pipe get/set ioctls into dumb stub functions, since with the new code we can no longer let userspace control whether vblank interrupts are enabled, or the core code will misbehave.