diff options
author | Dave Airlie <airlied@redhat.com> | 2016-02-09 10:27:41 +1000 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2016-02-09 10:27:41 +1000 |
commit | b039d6d02500ba8fe22e545b55b4961c1ef0f32d (patch) | |
tree | a8e5b387d79a21afa42e6bb905ea1b188f91f5c8 /include/uapi | |
parent | 388f7b1d6e8ca06762e2454d28d6c3c55ad0fe95 (diff) | |
parent | 947eaebc318d63ada82901cea86c586ac3d854f0 (diff) | |
download | linux-b039d6d02500ba8fe22e545b55b4961c1ef0f32d.tar.gz linux-b039d6d02500ba8fe22e545b55b4961c1ef0f32d.tar.bz2 linux-b039d6d02500ba8fe22e545b55b4961c1ef0f32d.zip |
Merge tag 'drm-intel-next-2016-01-24' of git://anongit.freedesktop.org/drm-intel into drm-next
- support for v3 vbt dsi blocks (Jani)
- improve mmio debug checks (Mika Kuoppala)
- reorg the ddi port translation table entries and related code (Ville)
- reorg gen8 interrupt handling for future platforms (Tvrtko)
- refactor tile width/height computations for framebuffers (Ville)
- kerneldoc integration for intel_pm.c (Jani)
- move default context from engines to device-global dev_priv (Dave Gordon)
- make seqno/irq ordering coherent with execlist (Chris)
- decouple internal engine number from UABI (Chris&Tvrtko)
- tons of small fixes all over, as usual
* tag 'drm-intel-next-2016-01-24' of git://anongit.freedesktop.org/drm-intel: (148 commits)
drm/i915: Update DRIVER_DATE to 20160124
drm/i915: Seal busy-ioctl uABI and prevent leaking of internal ids
drm/i915: Decouple execbuf uAPI from internal implementation
drm/i915: Use ordered seqno write interrupt generation on gen8+ execlists
drm/i915: Limit the auto arming of mmio debugs on vlv/chv
drm/i915: Tune down "GT register while GT waking disabled" message
drm/i915: tidy up a few leftovers
drm/i915: abolish separate per-ring default_context pointers
drm/i915: simplify allocation of driver-internal requests
drm/i915: Fix NULL plane->fb oops on SKL
drm/i915: Do not put big intel_crtc_state on the stack
Revert "drm/i915: Add two-stage ILK-style watermark programming (v10)"
drm/i915: add DOC: headline to RC6 kernel-doc
drm/i915: turn some bogus kernel-doc comments to normal comments
drm/i915/sdvo: revert bogus kernel-doc comments to normal comments
drm/i915/gen9: Correct max save/restore register count during gpu reset with GuC
drm/i915: Demote user facing DMC firmware load failure message
drm/i915: use hlist_for_each_entry
drm/i915: skl_update_scaler() wants a rotation bitmask instead of bit number
drm/i915: Don't reject primary plane windowing with color keying enabled on SKL+
...
Diffstat (limited to 'include/uapi')
-rw-r--r-- | include/uapi/drm/i915_drm.h | 33 |
1 files changed, 29 insertions, 4 deletions
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index acf21026c78a..6a19371391fa 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -812,10 +812,35 @@ struct drm_i915_gem_busy { /** Handle of the buffer to check for busy */ __u32 handle; - /** Return busy status (1 if busy, 0 if idle). - * The high word is used to indicate on which rings the object - * currently resides: - * 16:31 - busy (r or r/w) rings (16 render, 17 bsd, 18 blt, etc) + /** Return busy status + * + * A return of 0 implies that the object is idle (after + * having flushed any pending activity), and a non-zero return that + * the object is still in-flight on the GPU. (The GPU has not yet + * signaled completion for all pending requests that reference the + * object.) + * + * The returned dword is split into two fields to indicate both + * the engines on which the object is being read, and the + * engine on which it is currently being written (if any). + * + * The low word (bits 0:15) indicate if the object is being written + * to by any engine (there can only be one, as the GEM implicit + * synchronisation rules force writes to be serialised). Only the + * engine for the last write is reported. + * + * The high word (bits 16:31) are a bitmask of which engines are + * currently reading from the object. Multiple engines may be + * reading from the object simultaneously. + * + * The value of each engine is the same as specified in the + * EXECBUFFER2 ioctl, i.e. I915_EXEC_RENDER, I915_EXEC_BSD etc. + * Note I915_EXEC_DEFAULT is a symbolic value and is mapped to + * the I915_EXEC_RENDER engine for execution, and so it is never + * reported as active itself. Some hardware may have parallel + * execution engines, e.g. multiple media engines, which are + * mapped to the same identifier in the EXECBUFFER2 ioctl and + * so are not separately reported for busyness. */ __u32 busy; }; |