summaryrefslogtreecommitdiff
path: root/shared-core/i915_dma.c
AgeCommit message (Collapse)Author
2008-06-06[intel] remove settable use_mi_batchbuffer_startKeith Packard
The driver can know what hardware requires MI_BATCH_BUFFER vs MI_BATCH_BUFFER_START; there's no reason to let user mode configure this.
2008-06-06[intel-gem] Use timers to retire requests periodically.Keith Packard
Without the user IRQ running constantly, there's no wakeup when the ring empties to go retire requests and free buffers. Use a 1 second timer to make that happen more often.
2008-06-06[intel] free the hardware status page at driver_unloadKeith Packard
This goes with the other hardware status page patch.
2008-06-06[intel-gem] Add explicit throttle ioctlKeith Packard
Instead of throttling and execbuffer time, have the application ask to throttle explicitly. This allows the throttle to happen less often, and without holding the DRM lock.
2008-06-06[intel] Allocate hardware status page at driver load timeKeith Packard
I couldn't get the re-allocated HWS to work on my 965GM, so I just gave up and made it persist across the lifetime of the driver instead.
2008-06-06Ignore X server provided mmio addressKeith Packard
2008-05-30Merge commit 'origin/master' into drm-gemEric Anholt
Conflicts: linux-core/Makefile.kernel shared-core/i915_drv.h shared-core/nouveau_state.c
2008-05-27[FreeBSD] Add vblank-rework support and get drivers building.Robert Noland
The i915 driver now works again.
2008-05-25[intel-gem] Add DRM_I915_GEM_BUSY ioctl to check for idle buffers.Keith Packard
This new ioctl returns whether re-using the buffer would force a wait.
2008-05-22[intel] Add debug code to verify the cached ring tail pointer.Keith Packard
Recording the tail pointer in a local variable improves performance, but if someone messes up and fails to reload at the right time, the driver will write commands to the wrong part of the ring and scramble execution badly. This change (available by setting I915_RING_VALIDATE to 1) checks to make sure the cached tail pointer matches the hardware tail pointer at each ring buffer addition, calling BUG_ON when that's not true.
2008-05-22[gem] Release GEM buffers from work task scheduled from IRQ.Eric Anholt
There are now 3 lists. Active is buffers currently in the ringbuffer. Flushing is not in the ringbuffer, but needs a flush before unbinding. Inactive is as before. This prevents object_free → unbind → wait_rendering → object_reference and a kernel oops about weird refcounting. This also avoids an synchronous extra flush and wait when freeing a buffer which had a write_domain set (such as a temporary rendered to and then from using the 2d engine). It will sit around on the flushing list until the appropriate flush gets emitted, or we need the GTT space for another operation.
2008-05-20[gem] Use a separate sequence number field from classic/ttmEric Anholt
This lets us get some qualities we desire, such as using the full 32-bit range (except zero), avoiding DRM_WAIT_ON, and a 1:1 mapping of active sequence numbers to request structs, which will be used soon for throttling and interrupt-driven list cleanup.
2008-05-15[gem] Rename the GTT LRU lists to active (executing) and inactive (idle).Eric Anholt
2008-05-12[intel] When polling for ring space, sleep for a lot longer (10ms)Keith Packard
If the ring is full, the engine will surely be running for more than 10ms.
2008-05-09GEM: Separate the LRU into execution list and LRU list.Eric Anholt
Now, the LRU list has objects that are completely done rendering and ready to kick out, while the execution list has things with active rendering, which have associated cookies and reference counts on them.
2008-05-06GEM: Use irq-based fencing rather than syncing and evicting every exec.Eric Anholt
2008-05-05Monitor ACTHD register while polling for idle ring.Keith Packard
When batch buffers are executing, the ring may be stuck for a long time. Monitor the ACTHD pointer which will show if the execution engine is actually hung.
2008-05-05Remove some debug messages.Keith Packard
2008-05-05Correct execbuffer offset. Add memory barrier and chipset flush.Keith Packard
2008-05-05Add i915_dispatch_gem_execbuffer (broken).Keith Packard
This function submits a gem-based execbuffer to the ring. It doesn't work yet.
2008-05-01Add pin/unpin object ioctls for gem.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
2008-04-22i915: gfx hw and i945gme fixes from upstreamDave Airlie
From Jesse and Zhenyu originally.
2008-03-24i915: fix oops on agp=offDave Airlie
Kernel bug 10289.
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.
2008-03-12Avoid large kmallocs.Thomas Hellstrom
2008-03-06drm: reorganise minor number handling using code from modesetting branchDave Airlie
Rip out the whole head thing and replace it with an idr and drm_minor structure.
2008-03-05i915: Evict if relocatee buffer is CACHED_MAPPED beforeXiang, Haihao
writting relocations, otherwise the GPU probably sees some inconsistent data. Fix fd.o bug#14656
2008-02-29More post-ioctl work.Thomas Hellstrom
2008-02-27Reinstate buffer idle before applying relocations.Thomas Hellstrom
2008-02-27Don't wait for buffer idle before applying relocations.Thomas Hellstrom
2008-02-26[i915] Relocation fixes.Thomas Hellstrom
2008-02-26Make the execbuffer code reasonably safe against errors.Thomas Hellstrom
In particular -EAGAINs, which should be common during Xserver operation. Also handle the fence creation failure case.
2008-02-22Fix one last occurance of struct _drm_i915_batchbuffer.Kristian Høgsberg
Thanks to Todd Merrill for pointing it out.
2008-02-13i915: Add a dri2 init path that gets the lock from the dri2 sarea.Kristian Høgsberg
2008-02-13i915: Only look up dev_priv->mmio_map if it's not already set upKristian Høgsberg
2008-02-13i915: Add I915_PARAM_CHIPSET_ID param to get chipset ID.Kristian Høgsberg
2008-02-13i915: Make sarea_priv setup optional.Kristian Høgsberg
2008-02-05i915: Re-report breadcrumbs on poll to the fence manager,Thomas Hellstrom
since a breadcrumb may actually turn up before a corresponding fence object has been placed on the fence ring.
2008-01-30i915: Avoid calling drm_fence_flush_old excessively.Thomas Hellstrom
2008-01-30Simplify the fencing code and differentiate between flushes andThomas Hellstrom
waiting types. Add a "command_stream_barrier" method to the bo driver.
2008-01-24i915: fix missing header when copying data from userspaceDave Airlie
2008-01-24i915 make relocs use copy from userDave Airlie
Switch relocs to using copy from user and remove index and pass buffer handles in instead.
2008-01-15Properly propagate the user-space fence flags.Thomas Hellstrom
This avoids a sync flush when user-space has already programmed and MI_FLUSH in the batchbuffer.
2008-01-03drm: cleanup DRM_DEBUG() parametersMárton Németh
As DRM_DEBUG macro already prints out the __FUNCTION__ string (see drivers/char/drm/drmP.h), it is not worth doing this again. At some other places the ending "\n" was added. airlied:- I cleaned up a few that this patch missed also
2007-12-15Document drm_bo_handle_validate. Match drm_bo_do_validate parameter order.Keith Packard
Document parameters and usage for drm_bo_handle_validate. Change parameter order to match drm_bo_do_validate (fence_class has been moved to after flags, hint and mask values). Existing users of this function have been changed, but out-of-tree users must be modified separately.
2007-12-11Make relocation validate client computed values when debuggingKeith Packard
2007-12-11i915: wait for buffer idle before writing relocationsKeith Packard
When writing a relocation entry, make sure the target buffer is idle, otherwise the GPU may see inconsistent data.
2007-12-11Allow relocation to be skipped when buffers don't move.Keith Packard
One of the costs of superioctl has been the need to perform relocations inside the kernel. The cost of mapping the buffers to the CPU and writing data is fairly high, especially if those buffers have been mapped and read by the GPU. If we assume that buffers don't move around very often, we can have the client compute the relocations itself using the previous GPU address. When that object doesn't move, the kernel can skip computing and writing the updated data. Here's a patch which adds a new field to struct drm_bo_info_req called 'presumed_offset', and a new DRM_BO_HINT_PRESUMED_OFFSET that is set when this field has been filled in by the client. There are two separate optimizations performed when the presumed_offset is correct: 1. i915_exec_reloc checks to see if all previous buffer offsets were guessed correctly. If so, there's no need for it to look at *any* of the relocations for a buffer. When this happens, it skips the whole relocation process, simply returning success. 2. i915_apply_reloc checks to see if the target buffer offset was guessed correctly. If so, it skips mapping the relocatee, computing the relocation and writing the value. If no relocations are needed, the relocatee should never be mapped to the CPU, and so the kernel shouldn't need to wait for any fences to pass.