summaryrefslogtreecommitdiff
path: root/linux-core/i915_gem.c
AgeCommit message (Collapse)Author
2008-12-10Revert "Merge branch 'modesetting-gem'"Jesse Barnes
This reverts commit 6656db10551bbb8770dd945b6d81d5138521f208. We really just want the libdrm and ioctl bits, not all the driver stuff.
2008-08-16i915: set domain properly on fb mapping, flush out changesJesse Barnes
The user visible ioctl does this, but since we call into GEM internals directly, we have to flush things ourselves. Fixes initial fb console corruption.
2008-08-07Merge branch 'drm-gem' into modesetting-gemJesse Barnes
2008-08-06Switch from shmem_getpage to read_mapping_pageKeith Packard
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.
2008-08-01Merge 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
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.
2008-07-28Merge 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
2008-07-28intel-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
2008-07-23intel-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
2008-07-21intel-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.
2008-07-18drm-gem: Fix buildIan Romanick
On some distros missing prototypes cause kernel builds to fail. These are hack to make the code build.
2008-07-11intel-gem: Add two new ioctls for managing tiling on objects.Eric Anholt
Various chips have exciting interactions between the CPU and the GPU's different ways of accessing interleaved memory, so we need some kernel assistance in determining how it works. Only fully tested on GM965 so far.
2008-07-07[intel-gem] typo fix in DRM_ERROREric Anholt
2008-07-07Merge commit 'origin/drm-gem' into ms-gemKristian Høgsberg
Conflicts: linux-core/drmP.h linux-core/drm_drv.c linux-core/drm_stub.c linux-core/i915_drv.c linux-core/i915_gem.c shared-core/i915_drv.h shared-core/i915_irq.c
2008-06-24[intel-gem] Include drm_compat.h to get kmap_atomic_prot_pfnKeith Packard
2008-06-24[intel-gem] Recover resources from wedged hardware.Keith Packard
Clean up queues, free objects. On the next entervt, unmark the hardware to let the user try again (presumably after resetting the chip). Someday we'll automatically recover...
2008-06-24[intel-gem] pwrite through GTTKeith Packard
Pin/copy_from_user/unpin through the GTT to eliminate clflush costs. Benchmarks say this helps quite a bit.
2008-06-21[intel-gem] Add /proc/dri/*/i915_gem_interruptKeith Packard
This tracks most of the interrupt-related status, including the interrupt registers in the chip and the sequence number variables.
2008-06-21[intel-gem] Remove unused variable.Keith Packard
2008-06-20[intel-gem] Use polling in i915_gem_idle instead of interrupts.Keith Packard
While waiting for the hardware to idle on leavevt or lastclose, poll for the sync sequence number instead of waiting for an interrupt. This allows the code to bail if the hardware hangs for some reason. Also, this avoids issues with signals as the exisiting wait function is interruptible.
2008-06-20[intel-gem] Add intel-specific /proc entries to help monitor gem operationKeith Packard
This adds gem_active, gem_flushing, gem_inactive, gem_request and gem_seqno entries to monitor gem operation and help debug issues.
2008-06-20[intel-gem] Use shmem_getpage instead of find_or_create_pageKeith Packard
find_or_create_page doesn't quite set up pages correctly; any newly created pages aren't hooked into the shmem object quite right; user space mmaps of those pages end up mapping pages full of zeros which then get written to the real pages inappropriately. This patch requires that the kernel export shmem_getpage.
2008-06-20[intel-gem] Add DRM_IOCTL_I915_GEM_SW_FINISH to flag CPU writesKeith Packard
When a software fallback has completed, usermode must notify the kernel so that any scanout buffers can be synchronized. This ioctl should be called whenever a fallback completes to flush CPU and chipset caches.
2008-06-18Merge commit 'origin/drm-gem' into modesetting-gemJesse Barnes
Lots of conflicts, seems to load ok, but I'm sure some bugs snuck in. Conflicts: linux-core/drmP.h linux-core/drm_lock.c linux-core/i915_gem.c shared-core/drm.h shared-core/i915_dma.c shared-core/i915_drv.h shared-core/i915_irq.c
2008-06-13[intel-gem] Execute MI_FLUSH in leavevt_ioctlKeith Packard
In leavevt_ioctl, queue an MI_FLUSH and then block waiting for it to complete. This will empty the active and flushing lists. That leaves only the inactive list to evict.
2008-06-13[intel-gem] inactive list may contain objects in CPU write domainKeith Packard
Pin/unpin need to know whether to remove/add objects from the inactive list, inactive objects cannot be in any GPU write domain as those would be on the flushing list instead. However, inactive objects may be in the CPU write domain.
2008-06-13[intel-gem] BUG_ON active objects in gem_object_unbindKeith Packard
Now that gem_object_unbind waits for rendering to complete, objects should not be active when they are being pulled from the GTT. BUG_ON if this is broken.
2008-06-13[intel-gem] Debugging -- verify inactive list invariantsKeith Packard
Inactive list elements may not be pinned, active or have non-CPU write domains.
2008-06-13[intel-gem] whitespace fixesKeith Packard
2008-06-13[intel-gem] show total GTT space in /proc/dri/*/gem_objectsKeith Packard
2008-06-13[intel-gem] Wait for rendering to complete before unbinding.Keith Packard
Moving to the CPU domain doesn't ensure that rendering is finished, the buffer may still be in use as a texture or other data source.
2008-06-13[intel-gem] add gtt and pin counts to /proc/dri/*/gem_objectsKeith Packard
Not quite portable, but these are useful for intel. Some more general mechanism could be done...
2008-06-13[intel-gem] Left the last exec buffer pinned. oops.Keith Packard
Loop end variable 'pinned' was set one too low.
2008-06-13[intel-gem] Pin objects during execbufferKeith Packard
Pinning the objects avoids accidentally evicting them while binding other objects.
2008-06-13[intel-gem] throttle based on frames rather than time. Reduces jitter.Keith Packard
Record the last execbuffer sequence for each client. Record that sequence in the throttle ioctl as the 'throttle sequence'. Wait for the last throttle sequence in the throttle ioctl.
2008-06-13[intel-gem] evict_something was failing when wait_request freed objectsKeith Packard
When i915_wait_request clears object from the active list, it may end up freeing them and not moving them to the inactive list. This ends up unbinding objects from the GTT without there ever being new objects visible to i915_gem_evict_something on the inactive list. As the only success condition required the presence of objects on the inactive list, this would falsely assume that no GTT space had been made available, and end up returning -ENOMEM to the application.
2008-06-13[intel-gem] Use a delayed_work instead of a timer + work_structKeith Packard
We want request retirement to occur about once a second when the request queue is non-empty. This was done with a timer that queued a work_struct, using a delayed_work instead makes a lot more sense.
2008-06-13[intel-gem] Reorder i915_add_request to schedule work lastKeith Packard
i915_add_request was calling schedule_delayed_work before adding the request to the list; it makes more sense to do that last.
2008-06-13[gem] Don't require the lock in execbuf now that it's not needed for the ring.Eric Anholt
2008-06-11[gem] Remove the drm_client_lock_take in set_domain.Eric Anholt
We no longer need to use it to protect against shared ringbuffer access.
2008-06-11Use GEM in modesettingJesse Barnes
Use GEM for ring buffer setup and framebuffer allocation. This means reworking the hardware status page stuff a bit (just use the basic range allocator for vram for now) and #ifdef'ing out the TTM & DRI2 code. Works well enough to load/unload several times and display fbcon on my T61 (though there's still some unexplained console corruption).
2008-06-11[gem] Another round of cleanups from checkpatch.plEric Anholt