The start of day context initialisation code in i915_gem_context_enable() loops
over each ring and calls the legacy switch context or the execlist init context
code as appropriate.
This patch moves the ring looping out of that function in to the top level
caller i915_gem_init_hw(). This means the a single pass can be made over all
rings doing the PPGTT, L3 remap and context initialisation of each ring
altogether.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The i915_gem_init_hw() function calls a bunch of smaller initialisation
functions. Multiple of which have generic sections and per ring sections. This
means multiple passes are done over the rings. Each pass writes data to the ring
which floats around in that ring's OLR until some random point in the future
when an add_request() is done by some random other piece of code.
This patch breaks i915_ppgtt_init_hw() in two with the per ring initialisation
now being done in i915_ppgtt_init_ring(). The ring looping is now done at the
top level in i915_gem_init_hw().
v2: Fix dumb loop variable re-use.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Added explicit request creation and submission to the GPU idle code path.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In order to explcitly track all GPU work (and completely remove the outstanding
lazy request), it is necessary to add extra i915_add_request() calls to various
places. Some of these do not need the implicit cache flush done as part of the
standard batch buffer submission process.
This patch adds a flag to _add_request() to specify whether the flush is
required or not.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The alloc_request() function does not actually return the newly allocated
request. Instead, it must be pulled from ring->outstanding_lazy_request. This
patch fixes this so that code can create a request and start using it knowing
exactly which request it actually owns.
v2: Updated for new i915_gem_request_alloc() scheme.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In execlist mode, the context object pointer is written in to the request
structure (and reference counted) at the point of request creation. In legacy
mode, this only happens inside i915_add_request().
This patch updates the legacy code path to match the execlist version. This
allows all the intermediate code between request creation and request submission
to get at the context object given only a request structure. Thus negating the
need to pass context pointers here, there and everywhere.
v2: Moved the context reference so it does not need to be undone if the
get_seqno() fails.
v3: Fixed execlist mode always hitting a warning about invalid last_contexts
(which don't exist in execlist mode).
v4: Updated for new i915_gem_request_alloc() scheme.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The i915_add_request() function is called to keep track of work that has been
written to the ring buffer. It adds epilogue commands to track progress (seqno
updates and such), moves the request structure onto the right list and other
such house keeping tasks. However, the work itself has already been written to
the ring and will get executed whether or not the add request call succeeds. So
no matter what goes wrong, there isn't a whole lot of point in failing the call.
At the moment, this is fine(ish). If the add request does bail early on and not
do the housekeeping, the request will still float around in the
ring->outstanding_lazy_request field and be picked up next time. It means
multiple pieces of work will be tagged as the same request and driver can't
actually wait for the first piece of work until something else has been
submitted. But it all sort of hangs together.
This patch series is all about removing the OLR and guaranteeing that each piece
of work gets its own personal request. That means that there is no more
'hoovering up of forgotten requests'. If the request does not get tracked then
it will be leaked. Thus the add request call _must_ not fail. The previous patch
should have already ensured that it _will_ not fail by removing the potential
for running out of ring space. This patch enforces the rule by actually removing
the early exit paths and the return code.
Note that if something does manage to fail and the epilogue commands don't get
written to the ring, the driver will still hang together. The request will be
added to the tracking lists. And as in the old case, any subsequent work will
generate a new seqno which will suffice for marking the old one as complete.
v2: Improved WARNings (Tomas Elf review request).
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It is a bad idea for i915_add_request() to fail. The work will already have been
send to the ring and will be processed, but there will not be any tracking or
management of that work.
The only way the add request call can fail is if it can't write its epilogue
commands to the ring (cache flushing, seqno updates, interrupt signalling). The
reasons for that are mostly down to running out of ring buffer space and the
problems associated with trying to get some more. This patch prevents that
situation from happening in the first place.
When a request is created, it marks sufficient space as reserved for the
epilogue commands. Thus guaranteeing that by the time the epilogue is written,
there will be plenty of space for it. Note that a ring_begin() call is required
to actually reserve the space (and do any potential waiting). However, that is
not currently done at request creation time. This is because the ring_begin()
code can allocate a request. Hence calling begin() from the request allocation
code would lead to infinite recursion! Later patches in this series remove the
need for begin() to do the allocate. At that point, it becomes safe for the
allocate to call begin() and really reserve the space.
Until then, there is a potential for insufficient space to be available at the
point of calling i915_add_request(). However, that would only be in the case
where the request was created and immediately submitted without ever calling
ring_begin() and adding any work to that request. Which should never happen. And
even if it does, and if that request happens to fall down the tiny window of
opportunity for failing due to being out of ring space then does it really
matter because the request wasn't doing anything in the first place?
v2: Updated the 'reserved space too small' warning to include the offending
sizes. Added a 'cancel' operation to clean up when a request is abandoned. Added
re-initialisation of tracking state after a buffer wrap to keep the sanity
checks accurate.
v3: Incremented the reserved size to accommodate Ironlake (after finally
managing to run on an ILK system). Also fixed missing wrap code in LRC mode.
v4: Added extra comment and removed duplicate WARN (feedback from Tomas).
For: VIZ-5115
CC: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Backmerge drm-next because the conflict between Ander's atomic fixes
for 4.2 and Maartens future work are getting to unwielding to handle.
Conflicts:
drivers/gpu/drm/i915/intel_display.c
drivers/gpu/drm/i915/intel_ringbuffer.h
Just always take ours, same as git merge -X ours, but done by hand
because I didn't trust git: It's confusing that it doesn't show any
conflicts in the merge diff at all.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
This patch doesn't have any functional change, but organize fruntbuffer
invalidate and busy by removing unecesarry signature argument for ring.
It was unsed on mark_fb_busy and only used on fb_obj_invalidate for the
same ORIGIN_CS usage. So let's clean it a bit
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Apparently we can have requests even if though the active list is empty,
so do the request retirement regardless of whether there's anything
on the active list.
The way it happened here is that during suspend intel_ring_idle()
notices the olr hanging around and then proceeds to get rid of it by
adding a request. However since there was nothing on the active lists
i915_gem_retire_requests() didn't clean those up, and so the idle work
never runs, and we leave the GPU "busy" during suspend resulting in a
WARN later.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
With the introduction of multiple views of an obj in the same vm, each
vma was taught to cache its copy of the pages (so that different views
could have different page arrangements). However, this missed decoupling
those vma->ggtt_view.pages when the vma released its reference on the
obj->pages. As we don't always free the vma, this leads to a possible
scenario (e.g. execbuffer interrupted by the shrinker) where the vma
points to a stale obj->pages, and explodes.
Fixes regression from commit fe14d5f4e5
Author: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Wed Dec 10 17:27:58 2014 +0000
drm/i915: Infrastructure for supporting different GGTT views per object
Tvrtko says, if someone else will be confused how this can happen, key
is the reservation execbuffer path. That puts the VMA on the exec_list
which prevents i915_vma_unbind and i915_gem_vma_destroy from fully
destroying the VMA. So the VMA is left existing as an empty object in
the list - unbound and disassociated with the backing store. Kind of a
cached memory object. And then re-using it needs to clear the cached
pages pointer which is fixed above.
Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1227892
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
[Jani: Added Tvrtko's explanation to commit message.]
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Apparently we can have requests even if though the active list is empty,
so do the request retirement regardless of whether there's anything
on the active list.
The way it happened here is that during suspend intel_ring_idle()
notices the olr hanging around and then proceeds to get rid of it by
adding a request. However since there was nothing on the active lists
i915_gem_retire_requests() didn't clean those up, and so the idle work
never runs, and we leave the GPU "busy" during suspend resulting in a
WARN later.
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
In commit 1854d5ca0d
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Apr 7 16:20:32 2015 +0100
drm/i915: Deminish contribution of wait-boosting from clients
we removed an atomic timer based check for allowing waitboosting and
moved it below the mutex taken during RPS. However, that mutex can be
held for long periods of time on Vallyview/Cherryview as communication
with the PCU is slow. As clients may frequently wait for results (e.g.
such as tranform feedback) we introduced contention between the client
and the RPS worker. We can take advantage of the RPS worker, by
switching the wait boost decision to use spin locks and defer the
actual reclocking to the worker.
Fixes a regression of up to 45% on Baytrail and Baswell!
v2 (Daniel):
- Use max_freq_softlimit instead of the not-yet-merged boost
frequency.
- Don't inject a fake irq into the boost work, instead treat
client_boost as just another legit waker.
v3: Drop the now unused mask (Chris).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90112
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
As Daniel commented on
commit b7ffe1362c5f468b853223acc9268804aa92afc8
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Apr 27 13:41:24 2015 +0100
drm/i915: Free RPS boosts for all laggards
it is better to be explicit when sharing hardcoded values such as
throttle/boost timeouts. Make it so!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
After allocating from the slab cache, we then need to free the request
back into the slab cache upon error (and not call kfree as that leads
to eventual memory corruption).
Fixes regression from
commit efab6d8dd1
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Apr 7 16:20:57 2015 +0100
drm/i915: Use a separate slab for requests
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If the client stalls on a congested request, chosen to be 20ms old to
match throttling, allow the client a free RPS boost.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: s/rq/req/]
[danvet: s/0/NULL/ reported by 0-day build]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that we have internal clients, rather than faking a whole
drm_i915_file_private just for tracking RPS boosts, create a new struct
intel_rps_client and pass it along when waiting.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: s/rq/req/]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Ring switches can occur many times per frame, and are often out of
control, causing frequent RPS boosting for no practical benefit. Treat
the sw semaphore synchronisation as a separate client and only allow it
to boost once per busy/idle cycle.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: s/rq/req/]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently, we only track the last request globally across all engines.
This prevents us from issuing concurrent read requests on e.g. the RCS
and BCS engines (or more likely the render and media engines). Without
semaphores, we incur costly stalls as we synchronise between rings -
greatly impacting the current performance of Broadwell versus Haswell in
certain workloads (like video decode). With the introduction of
reference counted requests, it is much easier to track the last request
per ring, as well as the last global write request so that we can
optimise inter-engine read read requests (as well as better optimise
certain CPU waits).
v2: Fix inverted readonly condition for nonblocking waits.
v3: Handle non-continguous engine array after waits
v4: Rebase, tidy, rewrite ring list debugging
v5: Use obj->active as a bitfield, it looks cool
v6: Micro-optimise, mostly involving moving code around
v7: Fix retire-requests-upto for execlists (and multiple rq->ringbuf)
v8: Rebase
v9: Refactor i915_gem_object_sync() to allow the compiler to better
optimise it.
Benchmark: igt/gem_read_read_speed
hsw:gt3e (with semaphores):
Before: Time to read-read 1024k: 275.794µs
After: Time to read-read 1024k: 123.260µs
hsw:gt3e (w/o semaphores):
Before: Time to read-read 1024k: 230.433µs
After: Time to read-read 1024k: 124.593µs
bdw-u (w/o semaphores): Before After
Time to read-read 1x1: 26.274µs 10.350µs
Time to read-read 128x128: 40.097µs 21.366µs
Time to read-read 256x256: 77.087µs 42.608µs
Time to read-read 512x512: 281.999µs 181.155µs
Time to read-read 1024x1024: 1196.141µs 1118.223µs
Time to read-read 2048x2048: 5639.072µs 5225.837µs
Time to read-read 4096x4096: 22401.662µs 21137.067µs
Time to read-read 8192x8192: 89617.735µs 85637.681µs
Testcase: igt/gem_concurrent_blit (read-read and friends)
Cc: Lionel Landwerlin <lionel.g.landwerlin@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> [v8]
[danvet: s/\<rq\>/req/g]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The merged seqno->request conversion from John called request
variables req, but some (not all) of Chris' recent patches changed
those to just rq. We've had a lenghty (and inconclusive) discussion on
irc which is the more meaningful name with maybe at most a slight bias
towards req.
Given that the "don't change names without good reason to avoid
conflicts" rule applies, so lets go back to a req everywhere for
consistency. I'll sed any patches for which this will cause conflicts
before applying.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
[danvet: s/origina/merged/ as pointed out by Chris - the first
mass-conversion patch was from Chris, the merged one from John.]
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
We no longer interpolate domains in the same manner, and even if we did,
we should trust setting either of the other write domains would trigger
an invalidation rather than force it. Remove the tweaking of the
read_domains since it serves no purpose and use
i915_gem_object_wait_rendering() directly.
Note that this goes back to
commit a8198eea15
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed Apr 13 22:04:09 2011 +0100
drm/i915: Introduce i915_gem_object_finish_gpu()
and gpu domain tracking died in
commit cc889e0f6c
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed Jun 13 20:45:19 2012 +0200
drm/i915: disable flushing_list/gpu_write_list
which is more than 1 year older.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add notes with information dug out of git history.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We do not yet support tiled objects bigger than the mappable
aperture size so reject them.
Reported-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[danvet: Rework the check a bit to avoid warnings.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Use partial view for huge BOs (bigger than half the mappable aperture)
in fault handler so that they can be accessed withough trying to make
room for them by evicting other objects.
v2:
- Only use partial views in the case where early rejection was
previously done.
- Account variable type changes from previous reroll.
v3:
- Add a comment about overwriting existing page entries.
(Tvrtko Ursulin)
- Whitespace fixes.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Do not skip special GGTT views when considering whether an object
is pinned or not.
Wrong behaviour was introduced in;
commit ec7adb6ee7
Author: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Date: Mon Mar 16 14:11:13 2015 +0200
drm/i915: Do not use ggtt_view with (aliasing) PPGTT
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
GGTT VMA sizes might be smaller than the whole object size due to
different GGTT views.
v2:
- Separate GGTT view constraint calculations from normal view
constraint calculations (Chris Wilson)
v3:
- Do not bother with debug wording. (Tvrtko Ursulin)
v4:
- Clearer logic for calculating map_and_fenceable (Tvrtko Ursulin)
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
[danvet: Drop BUG_ON, it's redudant.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reading a single value from the object, the locking only provides futile
protection against userspace races. The locking is useless so remove it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Unbinding doesn't always lead to unconditional destruction
of vma. This destruction avoidance happens if vma is part of
execbuffer relocation list or if vma is being considered for
eviction in i915_gem_evict_something().
For those other users, mark the vma unbound so that
the correct state of this vma is preserved.
Reported-by: Chris Wilson <chris@chris-wilson.co.ok>
Cc: Chris Wilson <chris@chris-wilson.co.ok>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drm-intel-next-2015-04-23:
- dither support for ns2501 dvo (Thomas Richter)
- some polish for the gtt code and fixes to finally enable the cmd parser on hsw
- first pile of bxt stage 1 enabling (too many different people to list ...)
- more psr fixes from Rodrigo
- skl rotation support from Chandra
- more atomic work from Ander and Matt
- pile of cleanups and micro-ops for execlist from Chris
drm-intel-next-2015-04-10:
- cdclk handling cleanup and fixes from Ville
- more prep patches for olr removal from John Harrison
- gmbus pin naming rework from Jani (prep for bxt)
- remove ->new_config from Ander (more atomic conversion work)
- rps (boost) tuning and unification with byt/bsw from Chris
- cmd parser batch bool tuning from Chris
- gen8 dynamic pte allocation (Michel Thierry, based on work from Ben Widawsky)
- execlist tuning (not yet all of it) from Chris
- add drm_plane_from_index (Chandra)
- various small things all over
* tag 'drm-intel-next-2015-04-23-fixed' of git://anongit.freedesktop.org/drm-intel: (204 commits)
drm/i915/gtt: Allocate va range only if vma is not bound
drm/i915: Enable cmd parser to do secure batch promotion for aliasing ppgtt
drm/i915: fix intel_prepare_ddi
drm/i915: factor out ddi_get_encoder_port
drm/i915/hdmi: check port in ibx_infoframe_enabled
drm/i915/hdmi: fix vlv infoframe port check
drm/i915: Silence compiler warning in dvo
drm/i915: Update DRIVER_DATE to 20150423
drm/i915: Enable dithering on NatSemi DVO2501 for Fujitsu S6010
rm/i915: Move i915_get_ggtt_vma_pages into ggtt_bind_vma
drm/i915: Don't try to outsmart gcc in i915_gem_gtt.c
drm/i915: Unduplicate i915_ggtt_unbind/bind_vma
drm/i915: Move ppgtt_bind/unbind around
drm/i915: move i915_gem_restore_gtt_mappings around
drm/i915: Fix up the vma aliasing ppgtt binding
drm/i915: Remove misleading comment around bind_to_vm
drm/i915: Don't use atomics for pg_dirty_rings
drm/i915: Don't look at pg_dirty_rings for aliasing ppgtt
drm/i915/skl: Support Y tiling in MMIO flips
drm/i915: Fixup kerneldoc for struct intel_context
...
Conflicts:
drivers/gpu/drm/i915/i915_drv.c
WaIdleLiteRestore is an execlists-only workaround, and requires the driver
to ensure that any context always has HEAD!=TAIL when attempting lite
restore.
Add two extra MI_NOOP instructions at the end of each request, but keep
the requests tail pointing before the MI_NOOPs. We may not need to
executed them, and this is why request->tail is sampled before adding
these extra instructions.
If we submit a context to the ELSP which has previously been submitted,
move the tail pointer past the MI_NOOPs. This ensures HEAD!=TAIL.
v2: Move overallocation to gen8_emit_request, and added note about
sampling request->tail in commit message (Chris).
v3: Remove redundant request->tail assignment in __i915_add_request, in
lrc mode this is already set in execlists_context_queue.
Do not add wa implementation details inside gem (Chris).
v4: Apply the wa whenever the req has been resubmitted and update
comment (Chris).
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Currently we have the problem that the decision whether ptes need to
be (re)written is splattered all over the codebase. Move all that into
i915_vma_bind. This needs a few changes:
- Just reuse the PIN_* flags for i915_vma_bind and do the conversion
to vma->bound in there to avoid duplicating the conversion code all
over.
- We need to make binding for EXECBUF (i.e. pick aliasing ppgtt if
around) explicit, add PIN_USER for that.
- Two callers want to update ptes, give them a PIN_UPDATE for that.
Of course we still want to avoid double-binding, but that should be
taken care of:
- A ppgtt vma will only ever see PIN_USER, so no issue with
double-binding.
- A ggtt vma with aliasing ppgtt needs both types of binding, and we
track that properly now.
- A ggtt vma without aliasing ppgtt could be bound twice. In the
lower-level ->bind_vma functions hence unconditionally set
GLOBAL_BIND when writing the ggtt ptes.
There's still a bit room for cleanup, but that's for follow-up
patches.
v2: Fixup fumbles.
v3: s/PIN_EXECBUF/PIN_USER/ for clearer meaning, suggested by Chris.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
It's true that we might need to context switch, but both the signalling
and implementation of the same are a few source files away. Remove it.
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
They change with the address space and not with each vma, so move them
into the right pile of vfuncs. Save 2 pointers per vma and clarifies
the code.
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Purpose of this tracking is to know when to flush the cache between
the CPU and the non-coherent display engine. Prior to:
commit 121920faf2
Author: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Mon Mar 23 11:10:37 2015 +0000
drm/i915/skl: Query display address through a wrapper
This worked by a mix of direct flag manipulation and checking for
existence of a pinned GGTT VMA.
With the introduction of rotated display mappings this approach is
no longer correct.
New simpler approach is to just keep this count over calls which pin
and unpin objects to and from display, at the slight cost of extra
space in every bo.
(Inspired and extracted code from a larger rework by Chris Wilson.)
v2: Remove the limit since it is not well defined. (Chris Wilson, Ville Syrjälä)
v3: Commit message corrections. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
One month passed between posting a patch and it getting merged, and
unfortunately even though it still applies, it needs fixing to account
for changes in function parameters since:
commit d385612e15b8b6eb3db328d83f1872ef8a381788
Author: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue Mar 17 14:45:29 2015 +0000
drm/i915: Log view type when printing warnings
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[danvet: Squash in fixup from Tvrtko to fix the rebase conflict.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The obj->pin_mappable flag only exists for debug purposes and is a
hindrance that is mistreated with rotated GGTT views. For debug
purposes, it suffices to mark objects with pin_display as being of note.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This provides a nice boost to mesa in swap bound scenarios (as mesa
throttles itself to the previous frame and given the scenario that will
complete shortly). It will also provide a good boost to systems running
with semaphores disabled and so frequently waiting on the GPU as it
switches rings. In the most favourable of microbenchmarks, this can
increase performance by around 15% - though in practice improvements
will be marginal and rarely noticeable.
v2: Account for user timeouts
v3: Limit the spinning to a single jiffie (~1us) at most. On an
otherwise idle system, there is no scheduler contention and so without a
limit we would spin until the GPU is ready.
v4: Drop forcewake - the lazy coherent access doesn't require it, and we
have no reason to believe that the forcewake itself improves seqno
coherency - it only adds delay.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Eero Tamminen <eero.t.tamminen@intel.com>
Cc: "Rantala, Valtteri" <valtteri.rantala@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move to i915_vma_bind as it is part of the binding.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We already assign a unique identifier to every request: seqno. That
someone felt like adding a second one without even mentioning why and
tweaking ABI smells very fishy.
Fixes regression from
commit b3a38998f0
Author: Nick Hoath <nicholas.hoath@intel.com>
Date: Thu Feb 19 16:30:47 2015 +0000
drm/i915: Fix a use after free, and unbalanced refcounting
v2: Rebase
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Nick Hoath <nicholas.hoath@intel.com>
Cc: Thomas Daniel <thomas.daniel@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Jani Nikula <jani.nikula@intel.com>
[danvet: Fixup because different merge order.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
vma are more frequently allocated than objects and so should equally
benefit from having a dedicated slab.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
requests are even more frequently allocated than objects and equally
benefit from having a dedicated slab.
v2: Rebase
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When we submit a request to the GPU, we first take the rpm wakelock, and
only release it once the GPU has been idle for a small period of time
after all requests have been complete. This means that we are sure no
new interrupt can arrive whilst we do not hold the rpm wakelock and so
can drop the individual get/put around every single request inside
execlists.
Note: to close one potential issue we should mark the GPU as busy
earlier in __i915_add_request.
To elaborate: The issue is that we emit the irq signalling sequence
before we grab the rpm reference, which means we could miss the
resulting interrupt (since that's not set up when suspended). The only
bad side effect is a missed interrupt, gt mmio writes automatically
wake up the hw itself. But otoh we have an umbrella rpm reference for
the entirety of execbuf, as long as that's there we're covered.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Explain a bit more about the add_request issue, which after
some irc chatting with Chris turns out to not be an issue really.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now with the trimmed memcpy before the command parser, we try to
allocate many different sizes of batches, predominantly one or two
pages. We can therefore speed up searching for a good sized batch by
keeping the objects of buckets of roughly the same size.
v2: Add a comment about bucket sizes
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
At runtime, this helps ensure that the batch pools are kept trim and
fast. Then at suspend, this releases memory that we do not need to
restore. It also ties into the oom-notifier to ensure that we recover as
much kernel memory as possible during OOM.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I woke up one morning and found 50k objects sitting in the batch pool
and every search seemed to iterate the entire list... Painting the
screen in oils would provide a more fluid display.
One issue with the current design is that we only check for retirements
on the current ring when preparing to submit a new batch. This means
that we can have thousands of "active" batches on another ring that we
have to walk over. The simplest way to avoid that is to split the pools
per ring and then our LRU execution ordering will also ensure that the
inactive buffers remain at the front.
v2: execlists still requires duplicate code.
v3: execlists requires more duplicate code
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This reverts commit ec5cc0f9b0
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu Jun 12 10:28:55 2014 +0100
drm/i915: Restrict GPU boost to the RCS engine
The premise that media/blitter workloads are not affected by boosting is
patently false with a trip through igt. The question that remains is
what exactly is going wrong with the media workload that prompted this?
Hopefully that would be fixed by the missing agressive downclocking, in
addition to the extra restrictions imposed on how frequent a process is
allowed to boost.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Deepak S <deepak.s@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll>
Acked-by: Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With boosting for missed pageflips, we have a much stronger indication
of when we need to (temporarily) boost GPU frequency to ensure smooth
delivery of frames. So now only allow each client to perform one RPS boost
in each period of GPU activity due to stalling on results.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Deepak S <deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The biggest user of i915_gem_object_get_page() is the relocation
processing during execbuffer. Typically userspace passes in a set of
relocations in sorted order. Sadly, we alternate between relocations
increasing from the start of the buffers, and relocations decreasing
from the end. However the majority of consecutive lookups will still be
in the same page. We could cache the start of the last sg chain, however
for most callers, the entire sgl is inside a single chain and so we see
no improve from the extra layer of caching.
v2: Avoid the double increment inside unlikely()
References: https://bugs.freedesktop.org/show_bug.cgi?id=88308
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The request allocation code is largely duplicated between legacy mode and
execlist mode. The actual difference between the two versions of the code is
pretty minimal.
This patch moves the common code out into a separate function. This is then
called by the execution specific version prior to setting up the one different
value.
For: VIZ-5190
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The submission portion of the execbuffer code path was abstracted into a
function pointer indirection as part of the legacy vs execlist work. The two
implementation functions are called 'i915_gem_ringbuffer_submission' and
'intel_execlists_submission' but the pointer was called 'do_execbuf'. There is
already a 'i915_gem_do_execbuffer' function (which is what calls the pointer
indirection). The name of the pointer is therefore considered to be backwards
and should be changed.
This patch renames it to 'execbuf_submit' which is hopefully a bit clearer.
For: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Tomas Elf <tomas.elf@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We were missing a convenience stub to aquire the right mutex whilst
dropping the request, so add it.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJVGHwjAAoJEHm+PkMAQRiG8rcIAJ6cEJ6mbqLpyz5XrGf4yNp0
+wG/QlEpT8rgrxe9wSjB3lfW3kR2Pe69b9fVVCdiklygdkmva5vfmDrVGGzYfe3M
QrFSSlMVBplvh6IiM/L1mVMtr3DSmCO23YZZ9R5b7FoEYatNHRpNWBCBpuXpd4aD
sLuIvO3L/S7LqeOAFkkYWv6AuL9umicmjR8u+nsmCSRJom7At/aJ6R66WIp9vxho
Rn7r6wcUk6B2Q/gYNjdSE8SIwdyKhuBGyvqQ9U9s6Btg9DQfM/b0vG5kw9hqeAq/
9445jqVDP1whA2vz6GjnvltidxrqRvuDPBwzOnFmY5U+KZz4lS3x2mnWAAJ3xWs=
=TqVJ
-----END PGP SIGNATURE-----
Merge tag 'v4.0-rc6' into drm-intel-next
Backmerge Linux 4.0-rc6 because conflicts are (again) getting out of
hand. To make sure we don't lose any bugfixes from the 4.0-rc5-rc6
flurry of patches we've applied them all to -next too.
Conflicts:
drivers/gpu/drm/i915/intel_display.c
Always take the version from -next, we've already handled all
conflicts with explicit cherrypicking.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
To allow for views where the view type is not defined by the view type only,
like it is in stereo or rotated 90 degree view, change the semantic to require
the whole view structure for comparison when we match a GGTT view.
This allows including parameters like offset to be included in the view which
is useful for eg. partial views.
v3:
- Rely on ggtt_view type being 0 for non-GGTT vma's, which equals to
I915_GGTT_VIEW_NORMAL. (Daniel Vetter)
- Do not use potentially slower comparison when we only want to know if
something is or is not a normal view.
- Rebase on top of rotated view patches. Add rotated view singleton.
- If one view is missing in comparison they're equal only if both are missing.
v4:
- Use comparison helper in obj_to_ggtt_view too. (Tvrtko Ursulin)
- Do WARN_ON if one view is NULL. (Tvrtko Ursulin)
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Traces for page directories and tables allocation and map.
v2: Removed references to teardown.
v3: bitmap_scnprintf has been deprecated.
v4: Replace bitmap_scnprintf with scnprintf correctly, and get right
range lengths. (Mika)
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we retire requests last, we may use a later seqno and so clear
the requests lists without clearing the active list, leading to
confusion. Hence we should retire requests first for consistency with
the early return. The order used to be important as the lifecycle for
the object on the active list was determined by request->seqno. However,
the requests themselves are now reference counted removing the
constraint from the order of retirement.
Fixes regression from
commit 1b5a433a4d
Author: John Harrison <John.C.Harrison@Intel.com>
Date: Mon Nov 24 18:49:42 2014 +0000
drm/i915: Convert 'i915_seqno_passed' calls into 'i915_gem_request_completed
'
and a
WARNING: CPU: 0 PID: 1383 at drivers/gpu/drm/i915/i915_gem_evict.c:279 i915_gem_evict_vm+0x10c/0x140()
WARN_ON(!list_empty(&vm->active_list))
Identified by updating WATCH_LISTS:
[drm:i915_verify_lists] *ERROR* blitter ring: active list not empty, but no requests
WARNING: CPU: 0 PID: 681 at drivers/gpu/drm/i915/i915_gem.c:2751 i915_gem_retire_requests_ring+0x149/0x230()
WARN_ON(i915_verify_lists(ring->dev))
Note that this is only a problem in evict_vm where the following happens
after a retire_request has cleaned out all requests, but not all active
bo:
- intel_ring_idle called from i915_gpu_idle notices that no requests are
outstanding and immediately returns.
- i915_gem_retire_requests_ring called from i915_gem_retire_requests also
immediately returns when there's no request, still leaving the bo on the
active list.
- evict_vm hits the WARN_ON(!list_empty(&vm->active_list)) after evicting
all active objects that there's still stuff left that shouldn't be
there.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
90/270 rotated scanout needs a rotated GTT view of the framebuffer.
This is put in a separate VMA with a dedicated ggtt view and wired such that
it is created when a framebuffer is pinned to a 90/270 rotated plane.
Rotation is only possible with Yb/Yf buffers and error is propagated to
user space in case of a mismatch.
Special rotated page view is constructed at the VMA creation time by
borrowing the DMA addresses from obj->pages.
v2:
* Do not bother with pages for rotated sg list, just populate the DMA
addresses. (Daniel Vetter)
* Checkpatch cleanup.
v3:
* Rebased on top of new plane handling (create rotated mapping when
setting the rotation property).
* Unpin rotated VMA on unpinning from display plane.
* Simplify rotation check using bitwise AND. (Chris Wilson)
v4:
* Fix unpinning of optional rotated mapping so it is really considered
to be optional.
v5:
* Rebased for fb modifier changes.
* Rebased for atomic commit.
* Only pin needed view for display. (Ville Syrjälä, Daniel Vetter)
v6:
* Rebased after preparatory work has been extracted out. (Daniel Vetter)
v7:
* Slightly simplified tiling geometry calculation.
* Moved rotated GGTT view implementation into i915_gem_gtt.c (Daniel Vetter)
v8:
* Do not use i915_gem_obj_size to get object size since that actually
returns the size of an VMA which may not exist.
* Rebased for ggtt view changes.
v9:
* Rebased after code review changes on the preceding patches.
* Tidy function definitions. (Joonas Lahtinen)
For: VIZ-4726
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com> (v4)
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
To support frame buffer rotation we need to be able to pass on the information
on what kind of GGTT view is required for display.
This patch just adds the parameter and makes all the callers default to the
normal view.
v2: Rebased for ggtt view changes.
v3: Don't limit PIN_MAPPABLE to normal views just yet. (Joonas Lahtinen)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> (v3)
[danvet: s/BUG/WARN/ in the patch hunk because. At least where the
BUG_ON isn't fatal right away.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch was formerly known as, "Force pd restore when PDEs change,
gen6-7." I had to change the name because it is needed for GEN8 too.
The real issue this is trying to solve is when a new object is mapped
into the current address space. The GPU does not snoop the new mapping
so we must do the gen specific action to reload the page tables.
GEN8 and GEN7 do differ in the way they load page tables for the RCS.
GEN8 does so with the context restore, while GEN7 requires the proper
load commands in the command streamer. Non-render is similar for both.
Caveat for GEN7
The docs say you cannot change the PDEs of a currently running context.
We never map new PDEs of a running context, and expect them to be
present - so I think this is okay. (We can unmap, but this should also
be okay since we only unmap unreferenced objects that the GPU shouldn't
be tryingto va->pa xlate.) The MI_SET_CONTEXT command does have a flag
to signal that even if the context is the same, force a reload. It's
unclear exactly what this does, but I have a hunch it's the right thing
to do.
The logic assumes that we always emit a context switch after mapping new
PDEs, and before we submit a batch. This is the case today, and has been
the case since the inception of hardware contexts. A note in the comment
let's the user know.
It's not just for gen8. If the current context has mappings change, we
need a context reload to switch
v2: Rebased after ppgtt clean up patches. Split the warning for aliasing
and true ppgtt options. And do not break aliasing ppgtt, where to->ppgtt
is always null.
v3: Invalidate PPGTT TLBs inside alloc_va_range.
v4: Rename ppgtt_invalidate_tlbs to mark_tlbs_dirty and move
pd_dirty_rings from i915_address_space to i915_hw_ppgtt. Fixes when
neither ctx->ppgtt and aliasing_ppgtt exist.
v5: Removed references to teardown_va_range.
v6: Updated needs_pd_load_pre/post.
v7: Fix pd_dirty_rings check in needs_pd_load_post, and update/move
comment about updated PDEs to object_pin/bind (Mika).
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v2+)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Instead of implementing the full tracking + dynamic allocation, this
patch does a bit less than half of the work, by tracking and warning on
unexpected conditions. The tracking itself follows which PTEs within a
page table are currently being used for objects. The next patch will
modify this to actually allocate the page tables only when necessary.
With the current patch there isn't much in the way of making a gen
agnostic range allocation function. However, in the next patch we'll add
more specificity which makes having separate functions a bit easier to
manage.
One important change introduced here is that DMA mappings are
created/destroyed at the same page directories/tables are
allocated/deallocated.
Notice that aliasing PPGTT is not managed here. The patch which actually
begins dynamic allocation/teardown explains the reasoning for this.
v2: s/pdp.page_directory/pdp.page_directories
Make a scratch page allocation helper
v3: Rebase and expand commit message.
v4: Allocate required pagetables only when it is needed, _bind_to_vm
instead of bind_vma (Daniel).
v5: Rebased to remove the unnecessary noise in the diff, also:
- PDE mask is GEN agnostic, renamed GEN6_PDE_MASK to I915_PDE_MASK.
- Removed unnecessary checks in gen6_alloc_va_range.
- Changed map/unmap_px_single macros to use dma functions directly and
be part of a static inline function instead.
- Moved drm_device plumbing through page tables operation to its own
patch.
- Moved allocate/teardown_va_range calls until they are fully
implemented (in subsequent patch).
- Merged pt and scratch_pt unmap_and_free path.
- Moved scratch page allocator helper to the patch that will use it.
v6: Reduce complexity by not tearing down pagetables dynamically, the
same can be achieved while freeing empty vms. (Daniel)
v7: s/i915_dma_map_px_single/i915_dma_map_single
s/gen6_write_pdes/gen6_write_pde
Prevent a NULL case when only GGTT is available. (Mika)
v8: Rebased after s/page_tables/page_table/.
v9: Reworked i915_pte_index and i915_pte_count.
Also exercise bitmap allocation here (gen6_alloc_va_range) and fix
incorrect write_page_range in i915_gem_restore_gtt_mappings (Mika).
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Michel Thierry <michel.thierry@intel.com> (v3+)
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Two code changes:
- Extract i915_gem_shrinker_init.
- Inline i915_gem_object_is_purgeable since we open-code it everywhere
else too.
This already has the benefit of pulling all the shrinker code
together, next patch adds a bit of kerneldoc.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This makes the interface consistent to old i915_gem_obj_ggtt_pin.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
GGTT views are only applicable when dealing with GGTT. Change the code to
reject ggtt_view where it should not be used and require it when it should
be.
v2:
- Dropped _ppgtt_ infixes, allow both types to be passed
- Disregard other but normal views when no view is specified
- More checks that valid parameters are passed
- More readable error checking
v3:
- Prefer WARN_ONCE over BUG_ON when there is code path for failure
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
[danvet: Drop unecessary forward decl from earlier patch iterations.]
[danvet: Remove unused variable spotted by Tvrtko.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Backmerge because of numerous and interleaving conflicts and git
rerere getting confused a bit too often.
Conflicts:
drivers/gpu/drm/i915/intel_display.c
All conflicts are because of -next patches backported to -fixes, so
just go with the code in -next.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
We need this for FBC, and possibly for PSR too.
v2: Don't only flush: invalidate too (Daniel).
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We want to port FBC to the frontbuffer tracking infrastructure, but
for that we need to know what caused the object invalidation so
we can react accordingly: CPU mmaps need manual, GTT mmaps and
flips don't need handling and ring rendering needs nukes.
v2: - s/ORIGIN_RENDER/ORIGIN_CS/ (Daniel, Rodrigo)
- Fix copy/pasted wrong documentation
- Rebase
v3: - Rebase
v4: - Don't pass the operation to flushes (Daniel).
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Long ago I found that I was getting sporadic errors when booting SNB,
with the symptom being that the first batch died with IPEHR != *ACTHD,
typically caused by the TLB being invalid. These magically disappeared
if I held the forcewake during the entire ring initialisation sequence.
(It can probably be shortened to a short critical section, but the whole
initialisation is full of register writes and so we would be taking and
releasing forcewake almost continually, and so holding it over the
entire sequence will probably be a net win!)
Note some of the kernels I encounted the issue already had the deferred
forcewake release, so it is still relevant.
I know that there have been a few other reports with similar failure
conditions on SNB, I think such as
References: https://bugs.freedesktop.org/show_bug.cgi?id=80913
v2: Wrap i915_gem_init_hw() with its own security blanket as we take
that path following resume and reset.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
This fixes a regression from
commit 5ed0bdf21a
Author: Thomas Gleixner <tglx@linutronix.de>
Date: Wed Jul 16 21:05:06 2014 +0000
drm: i915: Use nsec based interfaces
that made a negative timeout return immediately rather than the
previously defined behaviour of waiting indefinitely.
Testcase: igt/gem_wait
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=89494
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Kristian Høgsberg <krh@bitplanet.net>
Cc: stable@vger.kernel.org
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
[Jani: fixed a checkpatch complaint about whitespace.]
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJU/NacAAoJEHm+PkMAQRiGdUcIAJU5dHclwd9HRc7LX5iOwYN6
mN0aCsYjMD8Pjx2VcPCgJvkIoESQO5pkwYpFFWCwILup1bVEidqXfr8EPOdThzdh
kcaT0FwUvd19K+0jcKVNCX1RjKBtlUfUKONk6sS2x4RrYZpv0Ur8Gh+yXV8iMWtf
fAusNEYlxQJvEz5+NSKw86EZTr4VVcykKLNvj+/t/JrXEuue7IG8EyoAO/nLmNd2
V/TUKKttqpE6aUVBiBDmcMQl2SUVAfp5e+KJAHmizdDpSE80nU59UC1uyV8VCYdM
qwHXgttLhhKr8jBPOkvUxl4aSXW7S0QWO8TrMpNdEOeB3ZB8AKsiIuhe1JrK0ro=
=Xkue
-----END PGP SIGNATURE-----
Merge tag 'v4.0-rc3' into drm-next
Linux 4.0-rc3 backmerge to fix two i915 conflicts, and get
some mainline bug fixes needed for my testing box
Conflicts:
drivers/gpu/drm/i915/i915_drv.h
drivers/gpu/drm/i915/intel_display.c
- Y tiling support for scanout from Tvrtko&Damien
- Remove more UMS support
- some small prep patches for OLR removal from John Harrison
- first few patches for dynamic pagetable allocation from Ben Widawsky, rebased
by tons of other people
- DRRS support patches (Sonika&Vandana)
- fbc patches from Paulo
- make sure our vblank callbacks aren't called when the pipes are off
- various patches all over
* tag 'drm-intel-next-2015-02-27' of git://anongit.freedesktop.org/drm-intel: (61 commits)
drm/i915: Update DRIVER_DATE to 20150227
drm/i915: Clarify obj->map_and_fenceable
drm/i915/skl: Allow Y (and Yf) frame buffer creation
drm/i915/skl: Update watermarks for Y tiling
drm/i915/skl: Updated watermark programming
drm/i915/skl: Adjust get_plane_config() to support Yb/Yf tiling
drm/i915/skl: Teach pin_and_fence_fb_obj() about Y tiling constraints
drm/i915/skl: Adjust intel_fb_align_height() for Yb/Yf tiling
drm/i915/skl: Allow scanning out Y and Yf fbs
drm/i915/skl: Add new displayable tiling formats
drm/i915: Remove DRIVER_MODESET checks from modeset code
drm/i915: Remove regfile code&data for UMS suspend/resume
drm/i915: Remove DRIVER_MODESET checks from gem code
drm/i915: Remove DRIVER_MODESET checks in the gpu reset code
drm/i915: Remove DRIVER_MODESET checks from suspend/resume code
drm/i915: Remove DRIVER_MODESET checks in load/unload/close code
drm/i915: fix a printk format
drm/i915: Add media rc6 residency file to sysfs
drm/i915: Add missing description to parameter in alloc_pt_range
drm/i915: Removed the read of RP_STATE_CAP from sysfs/debugfs functions
...
- use the atomic helpers for plane_upate/disable hooks (Matt Roper)
- refactor the initial plane config code (Damien)
- ppgtt prep patches for dynamic pagetable alloc (Ben Widawsky, reworked and
rebased by a lot of other people)
- framebuffer modifier support from Tvrtko Ursulin, drm core code from Rob Clark
- piles of workaround patches for skl from Damien and Nick Hoath
- vGPU support for xengt on the client side (Yu Zhang)
- and the usual smaller things all over
* tag 'drm-intel-next-2015-02-14' of git://anongit.freedesktop.org/drm-intel: (88 commits)
drm/i915: Update DRIVER_DATE to 20150214
drm/i915: Remove references to previously removed UMS config option
drm/i915/skl: Use a LRI for WaDisableDgMirrorFixInHalfSliceChicken5
drm/i915/skl: Fix always true comparison in a revision id check
drm/i915/skl: Implement WaEnableLbsSlaRetryTimerDecrement
drm/i915/skl: Implement WaSetDisablePixMaskCammingAndRhwoInCommonSliceChicken
drm/i915: Add process identifier to requests
drm/i915/skl: Implement WaBarrierPerformanceFixDisable
drm/i915/skl: Implement WaCcsTlbPrefetchDisable:skl
drm/i915/skl: Implement WaDisableChickenBitTSGBarrierAckForFFSliceCS
drm/i915/skl: Implement WaDisableHDCInvalidation
drm/i915/skl: Implement WaDisableLSQCROPERFforOCL
drm/i915/skl: Implement WaDisablePartialResolveInVc
drm/i915/skl: Introduce a SKL specific init_workarounds()
drm/i915/skl: Document that we implement WaRsClearFWBitsAtReset
drm/i915/skl: Implement WaSetGAPSunitClckGateDisable
drm/i915/skl: Make the init clock gating function skylake specific
drm/i915/skl: Provide a gen9 specific init_render_ring()
drm/i915/skl: Document the WM read latency W/A with its name
drm/i915/skl: Also detect eDRAM on SKL
...
For an object right on the boundary of mappable space, as the fenceable
size is stricly greater than the actual size, its fence region may extend
out of mappable space.
Note that only pnv/g33 has fence_size > obj.size and an unmappable
range in the gtt, and there alignment constraints prevent bad things
from happening.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Clarify why this shouldn't change anything as per the
discussion on intel-gfx.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
In execlist mode, the ringbuf is a function of the ring and context whereas in
legacy mode, it is derived from the ring alone. Thus the calculation required to
determine the ringbuf pointer from the ring (and context) also needs to test
execlist mode or not. This is messy.
Further, the request structure holds a pointer to both the ring and the context
for which it was created. Thus, given a request, it is possible to derive the
ringbuf in either legacy or execlist mode. Hence it is necessary to pass just
the request in to all the low level functions rather than some combination of
request, ring, context and ringbuf. However, rather than recalculating it each
time, it is much simpler to just cache the ringbuf pointer in the request
structure itself.
Caching the pointer means the calculation is done once at request creation time
and all further code and simply read it directly from the request structure.
OTC-Jira: VIZ-5115
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
[danvet: Drop contentless comment in lrc alloc request entirely. And
spelling fix in the commit message.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When converting from implicitly tracked execlist queue items to ref counted
requests, not all frees of requests were replaced with unrefs, and extraneous
refs/unrefs of contexts were added.
Correct the unbalanced refcount & replace the frees.
Remove a noisy warning when hitting the request creation path.
drm_i915_gem_request and intel_context are both kref reference counted
structures. Upon allocation, drm_i915_gem_request's ref count should be
bumped using kref_init. When a context is assigned to the request,
the context's reference count should be bumped using i915_gem_context_reference.
i915_gem_request_reference will reduce the context reference count when
the request is freed.
Problem introduced in
commit 6d3d8274bc
Author: Nick Hoath <nicholas.hoath@intel.com>
AuthorDate: Thu Jan 15 13:10:39 2015 +0000
drm/i915: Subsume intel_ctx_submit_request in to drm_i915_gem_request
v2: Added comments explaining how the ctx pointer and the request object should
be ref-counted. Removed noisy warning.
v3: Cleaned up the language used in the commit & the header
description (Thanks David Gordon)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88652
Signed-off-by: Nick Hoath <nicholas.hoath@intel.com>
Reviewed-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Pull drm updates from Dave Airlie:
"This is the main drm pull, it has a shared branch with some alsa
crossover but everything should be acked by relevant people.
New drivers:
- ATMEL HLCDC driver
- designware HDMI core support (used in multiple SoCs).
core:
- lots more atomic modesetting work, properties and atomic ioctl
(hidden under option)
- bridge rework allows support for Samsung exynos chromebooks to
work finally.
- some more panels supported
i915:
- atomic plane update support
- DSI uses shared DSI infrastructure
- Skylake basic support is all merged now
- component framework used for i915/snd-hda interactions
- write-combine cpu memory mappings
- engine init code refactored
- full ppgtt enabled where execlists are enabled.
- cherryview rps/gpu turbo and pipe CRC support.
radeon:
- indirect draw support for evergreen/cayman
- SMC and manual fan control for SI/CI
- Displayport audio support
amdkfd:
- SDMA usermode queue support
- replace suballocator usage with more suitable one
- rework for allowing interfacing to more than radeon
nouveau:
- major renaming in prep for later splitting work
- merge arm platform driver into nouveau
- GK20A reclocking support
msm:
- conversion to atomic modesetting
- YUV support for mdp4/5
- eDP support
- hw cursor for mdp5
tegra:
- conversion to atomic modesetting
- better suspend/resume support for child devices
rcar-du:
- interlaced support
imx:
- move to using dw_hdmi shared support
- mode_fixup support
sti:
- DVO support
- HDMI infoframe support
exynos:
- refactoring and cleanup, removed lots of internal unnecessary
abstraction
- exynos7 DECON display controller support
Along with the usual bunch of fixes, cleanups etc"
* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (724 commits)
drm/radeon: fix voltage setup on hawaii
drm/radeon/dp: Set EDP_CONFIGURATION_SET for bridge chips if necessary
drm/radeon: only enable kv/kb dpm interrupts once v3
drm/radeon: workaround for CP HW bug on CIK
drm/radeon: Don't try to enable write-combining without PAT
drm/radeon: use 0-255 rather than 0-100 for pwm fan range
drm/i915: Clamp efficient frequency to valid range
drm/i915: Really ignore long HPD pulses on eDP
drm/exynos: Add DECON driver
drm/i915: Correct the base value while updating LP_OUTPUT_HOLD in MIPI_PORT_CTRL
drm/i915: Insert a command barrier on BLT/BSD cache flushes
drm/i915: Drop vblank wait from intel_dp_link_down
drm/exynos: fix NULL pointer reference
drm/exynos: remove exynos_plane_dpms
drm/exynos: remove mode property of exynos crtc
drm/exynos: Remove exynos_plane_dpms() call with no effect
drm/i915: Squelch overzealous uncore reset WARN_ON
drm/i915: Take runtime pm reference on hangcheck_info
drm/i915: Correct the IOSF Dev_FN field for IOSF transfers
drm/exynos: fix DMA_ATTR_NO_KERNEL_MAPPING usage
...
We use the pid of the process which opened our device when
we track which was the culprit of the gpu hang. But as that
file descriptor might get inherited, we might blame the
wrong process when we record the error state.
Track process identifiers in requests to always find
the correct offender.
v2: Track only user processes (Chris)
Cc: Kenneth Graunke <kenneth@whitecape.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
[danvet: drop NULL check before put_pid as suggested by Chris.]
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
With Intel GVT-g, the fence registers are partitioned by multiple
vGPU instances in different VMs. Routine i915_gem_load() is modified
to reset the num_fence_regs, when the driver detects it's running in
a VM. Accesses to the fence registers from vGPU will be trapped and
remapped by the host side. And the allocated fence number is provided
in PV INFO page structure. By now, the value of fence number is fixed,
but in the future we can relax this limitation, to allocate the fence
registers dynamically from host side.
Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Jike Song <jike.song@intel.com>
Signed-off-by: Eddie Dong <eddie.dong@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The core fix was applied in
commit a63b03e2d2
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Jan 6 10:29:35 2015 +0000
mutex: Always clear owner field upon mutex_unlock()
(note the absence of stable@ tag)
so we can now revert our band-aid commit 226e5ae9e5 for -next.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
When run as a timer, i915_hangcheck_elapsed() must adhere to all the
rules of running in a softirq context. This is advantageous to us as we
want to minimise the risk that a driver bug will prevent us from
detecting a hung GPU. However, that is irrelevant if the driver bug
prevents us from resetting and recovering. Still it is prudent not to
rely on mutexes inside the checker, but given the coarseness of
dev->struct_mutex doing so is extremely hard.
Give in and run from a work queue, i.e. outside of softirq.
v2: Use own workqueue to avoid deadlocks (Daniel)
Cleanup commit msg and add comment to i915_queue_hangcheck() (Chris)
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <dnaiel.vetter@ffwll.chm>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> (v1)
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
[danvet: Remove accidental kerneldoc comment starter, to appease the 0
day builder.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We can push down the decision whether to force flushing into the
implementation since in all places that matter obj->pin_display is
accurate already. The only place where the optimization really matters
is the sw_finish_ioctl, and that already checks for obj->pin_display
on its own.
I suspect that this was simply an artifact of how
commit 2c22569bba
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Aug 9 12:26:45 2013 +0100
drm/i915: Update rules for writing through the LLC with the cpu
evolved - only v2 added the pin_display tracking.
Note that we still retain the gist of this logic from the above commit
with the explicit force argument for the low-level clflush function.
Ville noted in his review that there's a slight behavioural change in
the set_to_gtt_domain function, which now also will flush display
plane data. This opens-open the potential for userspace to start doing
buggy things by omitting the sw_finish_ioctl, which is why I've
rejected a functional equivalent patch from Ville a while ago:
http://lists.freedesktop.org/archives/intel-gfx/2013-November/036421.html
But on second consideration it's not that evil, and in any case the
justification here is more clarity, not allowing crazy userspace.
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently we are hitting the WARN inside
i915_gem_object_set_cache_level() as we can now have an unbound object
in the GTT write domain (due to 43566dedde "drm/i915: Broaden
application of set-domain(GTT)"). To avoid the warning, we need to track
when we elided the clflush on a cacheable object and then evict the
cache for the object when we move the object out of a cacheable domain.
Reported-by: Jani Nikula <jani.nikula@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Jani Nikula <jani.nikula@intel.com>
Testcase: igt/gem_mmap_wc/set-cache-level
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=88607
Tested-by: huax.lu@intel.com
[danvet: Split if into nested if as discussion on the m-l.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We pin when we submit to execlist queue. Balance
the pinning when the submitted queue is cleaned on reset.
Cc: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Move all remaining elements that were unique to execlists queue items
in to the associated request.
Issue: VIZ-4274
v2: Rebase. Fixed issue of overzealous freeing of request.
v3: Removed re-addition of cleanup work queue (found by Daniel Vetter)
v4: Rebase.
v5: Actual removal of intel_ctx_submit_request. Update both tail and postfix
pointer in __i915_add_request (found by Thomas Daniel)
v6: Removed unrelated changes
Signed-off-by: Nick Hoath <nicholas.hoath@intel.com>
Reviewed-by: Thomas Daniel <thomas.daniel@intel.com>
[danvet: Reformat comment with strange linebreaks.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The first pass implementation of execlists required a backpointer to the context to be held
in the intel_ringbuffer. However the context pointer is available higher in the call stack.
Remove the backpointer from the ring buffer structure and instead pass it down through the
call stack.
v2: Integrate this changeset with the removal of duplicate request/execlist queue item members.
v3: Rebase
v4: Rebase. Remove passing of context when the request is passed.
Signed-off-by: Nick Hoath <nicholas.hoath@intel.com>
Reviewed-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Where there were duplicate variables for the tail, context and ring (engine)
in the gem request and the execlist queue item, use the one from the request
and remove the duplicate from the execlist queue item.
Issue: VIZ-4274
v1: Rebase
v2: Fixed build issues. Keep separate postfix & tail pointers as these are
used in different ways. Reinserted missing full tail pointer update.
Signed-off-by: Nick Hoath <nicholas.hoath@intel.com>
Reviewed-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
- refactor i915/snd-hda interaction to use the component framework (Imre)
- psr cleanups and small fixes (Rodrigo)
- a few perf w/a from Ken Graunke
- switch to atomic plane helpers (Matt Roper)
- wc mmap support (Chris Wilson & Akash Goel)
- smaller things all over
* tag 'drm-intel-next-2015-01-17' of git://anongit.freedesktop.org/drm-intel: (40 commits)
drm/i915: Update DRIVER_DATE to 20150117
i915: reuse %ph to dump small buffers
drm/i915: Ensure the HiZ RAW Stall Optimization is on for Cherryview.
drm/i915: Enable the HiZ RAW Stall Optimization on Broadwell.
drm/i915: PSR link standby at debugfs
drm/i915: group link_standby setup and let this info visible everywhere.
drm/i915: Add missing vbt check.
drm/i915: PSR HSW/BDW: Fix inverted logic at sink main_link_active bit.
drm/i915: PSR VLV/CHV: Remove condition checks that only applies to Haswell.
drm/i915: VLV/CHV PSR needs to exit PSR on every flush.
drm/i915: Fix kerneldoc for i915 atomic plane code
drm/i915: Don't pretend SDVO hotplug works on 915
drm/i915: Don't register HDMI connectors for eDP ports on VLV/CHV
drm/i915: Remove I915_HAS_HOTPLUG() check from i915_hpd_irq_setup()
drm/i915: Make hpd arrays big enough to avoid out of bounds access
Revert "drm/i915/chv: Use timeout mode for RC6 on chv"
drm/i915: Improve HiZ throughput on Cherryview.
drm/i915: Reset CSB read pointer in ring init
drm/i915: Drop unused position fields (v2)
drm/i915: Move to atomic plane helpers (v9)
...
When creating a fence for a tiled object, only fence the area that
makes up the actual tiles. The object may be larger than the tiled
area and if we allow those extra addresses to be fenced, they'll
get converted to addresses beyond where the object is mapped. This
opens up the possiblity of writes beyond the end of object.
To prevent this, we adjust the size of the fence to only encompass
the area that makes up the actual tiles. The extra space is considered
un-tiled and now behaves as if it was a linear object.
Testcase: igt/gem_tiled_fence_overflow
Reported-by: Dan Hettena <danh@ghs.com>
Signed-off-by: Bob Paauwe <bob.j.paauwe@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Commit 82460d972 ("drm/i915: Rework ppgtt init to no require an aliasing
ppgtt") introduced a regression on Broadwell, triggering the following
IOMMU fault at startup:
vgaarb: device changed decodes: PCI:0000:00:02.0,olddecodes=io+mem,decodes=io+mem:owns=io+mem
dmar: DRHD: handling fault status reg 2
dmar: DMAR:[DMA Write] Request device [00:02.0] fault addr 880000
DMAR:[fault reason 23] Unknown
fbcon: inteldrmfb (fb0) is primary device
Further commentary from Daniel:
I sugggested this change to David after staring at the offending patch
for a while. I have no idea and theory whatsoever why this would upset
the gpu less than the other way round. But it seems to work. David
promised to chase hw people a bit more to get a more meaningful answer.
Wrt the comment that this deletes: I've done some digging and afaict
loading context before ppgtt enable was once required before our recent
restructuring of the context/ppgtt init code: Before that context sw
setup (i.e. allocating the default context) and hw setup was smashed
together. Also the setup of the default context was the bit that
actually allocated the aliasing ppgtt structures. Which is the reason
for the context before ppgtt depency.
Or was, since with all the untangling there's no no real depency any
more (functional, who knows what the hw is doing), so the comment is
just stale.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Backmerge Linus tree after rc5 + drm-fixes went in.
There were a few amdkfd conflicts I wanted to avoid,
and Ben requested this for nouveau also.
Conflicts:
drivers/gpu/drm/amd/amdkfd/Makefile
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
drivers/gpu/drm/amd/amdkfd/kfd_priv.h
drivers/gpu/drm/amd/include/kgd_kfd_interface.h
drivers/gpu/drm/i915/intel_runtime_pm.c
drivers/gpu/drm/radeon/radeon_kfd.c
Conflicts:
drivers/gpu/drm/i915/intel_runtime_pm.c
Separate branch so that Takashi can also pull just this refactoring
into sound-next.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
If CONFIG_DEBUG_MUTEXES is set, the mutex->owner field is only cleared
if the mutex debugging is enabled which introduces a race in our
mutex_is_locked_by() - i.e. we may inspect the old owner value before it
is acquired by the new task.
This is the root cause of this error:
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 5cf6731..3ef3736 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -80,13 +80,13 @@ void debug_mutex_unlock(struct mutex *lock)
DEBUG_LOCKS_WARN_ON(lock->owner != current);
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
- mutex_clear_owner(lock);
}
/*
* __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
* mutexes so that we can do it here after we've verified state.
*/
+ mutex_clear_owner(lock);
atomic_set(&lock->count, 1);
}
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87955
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@vger.kernel.org
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
- plane handling refactoring from Matt Roper and Gustavo Padovan in prep for
atomic updates
- fixes and more patches for the seqno to request transformation from John
- docbook for fbc from Rodrigo
- prep work for dual-link dsi from Gaurav Signh
- crc fixes from Ville
- special ggtt views infrastructure from Tvrtko Ursulin
- shadow patch copying for the cmd parser from Brad Volkin
- execlist and full ppgtt by default on gen8, for testing for now
* tag 'drm-intel-next-2014-12-19' of git://anongit.freedesktop.org/drm-intel: (131 commits)
drm/i915: Update DRIVER_DATE to 20141219
drm/i915: Hold runtime PM during plane commit
drm/i915: Organize bind_vma funcs
drm/i915: Organize INSTDONE report for future.
drm/i915: Organize PDP regs report for future.
drm/i915: Organize PPGTT init
drm/i915: Organize Fence registers for future enablement.
drm/i915: tame the chattermouth (v2)
drm/i915: Warn about missing context state workarounds only once
drm/i915: Use true PPGTT in Gen8+ when execlists are enabled
drm/i915: Skip gunit save/restore for cherryview
drm/i915/chv: Use timeout mode for RC6 on chv
drm/i915: Add GPGPU_THREADS_DISPATCHED to the register whitelist
drm/i915: Tidy up execbuffer command parsing code
drm/i915: Mark shadow batch buffers as purgeable
drm/i915: Use batch length instead of object size in command parser
drm/i915: Use batch pools with the command parser
drm/i915: Implement a framework for batch buffer pools
drm/i915: fix use after free during eDP encoder destroying
drm/i915/skl: Skylake also supports DP MST
...
This will allow us to set per-file, or even per-context, periods in the
future.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch provides support to create write-combining virtual mappings of
GEM object. It intends to provide the same funtionality of 'mmap_gtt'
interface without the constraints and contention of a limited aperture
space, but requires clients handles the linear to tile conversion on their
own. This is for improving the CPU write operation performance, as with such
mapping, writes and reads are almost 50% faster than with mmap_gtt. Similar
to the GTT mmapping, unlike the regular CPU mmapping, it avoids the cache
flush after update from CPU side, when object is passed onto GPU. This
type of mapping is specially useful in case of sub-region update,
i.e. when only a portion of the object is to be updated. Using a CPU mmap
in such cases would normally incur a clflush of the whole object, and
using a GTT mmapping would likely require eviction of an active object or
fence and thus stall. The write-combining CPU mmap avoids both.
To ensure the cache coherency, before using this mapping, the GTT domain
has been reused here. This provides the required cache flush if the object
is in CPU domain or synchronization against the concurrent rendering.
Although the access through an uncached mmap should automatically
invalidate the cache lines, this may not be true for non-temporal write
instructions and also not all pages of the object may be updated at any
given point of time through this mapping. Having a call to get_pages in
set_to_gtt_domain function, as added in the earlier patch 'drm/i915:
Broaden application of set-domain(GTT)', would guarantee the clflush and
so there will be no cachelines holding the data for the object before it
is accessed through this map.
The drm_i915_gem_mmap structure (for the DRM_I915_GEM_MMAP_IOCTL) has been
extended with a new flags field (defaulting to 0 for existent users). In
order for userspace to detect the extended ioctl, a new parameter
I915_PARAM_MMAP_VERSION has been added for versioning the ioctl interface.
v2: Fix error handling, invalid flag detection, renaming (ickle)
v3: Rebase to latest drm-intel-nightly codebase
The new mmapping is exercised by igt/gem_mmap_wc,
igt/gem_concurrent_blit and igt/gem_gtt_speed.
Change-Id: Ie883942f9e689525f72fe9a8d3780c3a9faa769a
Signed-off-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Previously, this was restricted to only operate on bound objects - to
make pointer access through the GTT to the object coherent with writes
to and from the GPU. A second usecase is drm_intel_bo_wait_rendering()
which at present does not function unless the object also happens to
be bound into the GGTT (on current systems that is becoming increasingly
rare, especially for the typical requests from mesa). A third usecase is
a future patch wishing to extend the coverage of the GTT domain to
include objects not bound into the GGTT but still in its coherent cache
domain. For the latter pair of requests, we need to operate on the
object regardless of its bind state.
v2: After discussion with Akash, we came to the conclusion that the
get-pages was required in order for accurate domain tracking in the
corner cases (like the shrinker) and also useful for ensuring memory
coherency with earlier cached CPU mmaps in case userspace uses exotic
cache bypass (non-temporal) instructions.
v3: Fix the inactive object check.
v4: Rebase to latest drm-intel-nightly codebase
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
I've had these since before -rc1, but they missed my last pull
request. Real bug fixes and mostly cc: stable material.
* tag 'drm-intel-next-fixes-2014-12-30' of git://anongit.freedesktop.org/drm-intel:
drm/i915: add missing rpm ref to i915_gem_pwrite_ioctl
Revert "drm/i915: Preserve VGACNTR bits from the BIOS"
drm/i915: Don't call intel_prepare_page_flip() multiple times on gen2-4
drm/i915: Kill check_power_well() calls
This reverts commit 355a701838.
This had some bad side effects under normal operation, and should
have been dropped earlier.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Without this RPM ref we can hit the device suspended WARN via:
i915_gem_object_pin()->ggtt_bind_vma->gen6_ggtt_insert_entries(). I
noticed this on my BYT while keeping the i915 device in runtime
suspended state for a while. I chose this place to take the ref to
avoid the possible deadlock via the mutex_lock taken both later in this
function and in the runtime suspend handler. This can happen if an RPM
suspend event is queued and need to be flushed before taking the RPM
ref.
Testcase: igt/pm_rpm/gem-evict-pwrite
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=87363
Signed-off-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Let's be optimistic that for future platforms this will remain the same
and reorg a bit.
This reorg in if blocks instead of switch make life easier for future
platform support addition.
v2: Jani pointed out I was missing reg_830 for some gen3 platforms. So let's make
this platforms subcases of Gen checks.
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This patch sets up all of the tracking and copying necessary to
use batch pools with the command parser and dispatches the copied
(shadow) batch to the hardware.
After this patch, the parser is in 'enabling' mode.
Note that performance takes a hit from the copy in some cases
and will likely need some work. At a rough pass, the memcpy
appears to be the bottleneck. Without having done a deeper
analysis, two ideas that come to mind are:
1) Copy sections of the batch at a time, as they are reached
by parsing. Might improve cache locality.
2) Copy only up to the userspace-supplied batch length and
memset the rest of the buffer. Reduces the number of reads.
v2:
- Remove setting the capacity of the pool
- One global pool instead of per-ring pools
- Replace batch_obj with shadow_batch_obj and hook into eb->vmas
- Memset any space in the shadow batch beyond what gets copied
- Rebased on execlist prep refactoring
v3:
- Rebase on chained batch handling
- Squash in setting the secure dispatch flag
- Add a note about the interaction w/secure dispatch pinning
- Check for request->batch_obj == NULL in i915_gem_free_request
v4:
- Fix read domains for shadow_batch_obj
- Remove the set_to_gtt_domain call from i915_parse_cmds
- ggtt_pin/unpin in the parser block to simplify error handling
- Check USES_FULL_PPGTT before setting DISPATCH_SECURE flag
- Remove i915_gem_batch_pool_put calls
v5:
- Move 'pending_read_domains |= I915_GEM_DOMAIN_COMMAND' after
the parser (danvet, from v4 0/7 feedback)
Issue: VIZ-4719
Signed-off-by: Brad Volkin <bradley.d.volkin@intel.com>
Reviewed-By: Jon Bloomfield <jon.bloomfield@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
This adds a small module for managing a pool of batch buffers.
The only current use case is for the command parser, as described
in the kerneldoc in the patch. The code is simple, but separating
it out makes it easier to change the underlying algorithms and to
extend to future use cases should they arise.
The interface is simple: init to create an empty pool, fini to
clean it up, get to obtain a new buffer. Note that all buffers are
expected to be inactive before cleaning up the pool.
Locking is currently based on the caller holding the struct_mutex.
We already do that in the places where we will use the batch pool
for the command parser.
v2:
- s/BUG_ON/WARN_ON/ for locking assertions
- Remove the cap on pool size
- Switch from alloc/free to init/fini
v3:
- Idiomatic looping structure in _fini
- Correct handling of purged objects
- Don't return a buffer that's too much larger than needed
v4:
- Rebased to latest -nightly
v5:
- Remove _put() function and clean up comments to match
v6:
- Move purged check inside the loop (danvet, from v4 1/7 feedback)
v7:
- Use single list instead of two. (Chris W)
- s/active_list/cache_list
- Squashed in debug patches (Chris W)
drm/i915: Add a batch pool debugfs file
It provides some useful information about the buffers in
the global command parser batch pool.
v2: rebase on global pool instead of per-ring pools
v3: rebase
drm/i915: Add batch pool details to i915_gem_objects debugfs
To better account for the potentially large memory consumption
of the batch pool.
v8:
- Keep cache in LRU order (danvet, from v6 1/5 feedback)
Issue: VIZ-4719
Signed-off-by: Brad Volkin <bradley.d.volkin@intel.com>
Reviewed-By: Jon Bloomfield <jon.bloomfield@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Things like reliable GGTT mappings and mirrored 2d-on-3d display will need
to map objects into the same address space multiple times.
Added a GGTT view concept and linked it with the VMA to distinguish between
multiple instances per address space.
New objects and GEM functions which do not take this new view as a parameter
assume the default of zero (I915_GGTT_VIEW_NORMAL) which preserves the
previous behaviour.
This now means that objects can have multiple VMA entries so the code which
assumed there will only be one also had to be modified.
Alternative GGTT views are supposed to borrow DMA addresses from obj->pages
which is DMA mapped on first VMA instantiation and unmapped on the last one
going away.
v2:
* Removed per view special casing in i915_gem_ggtt_prepare /
finish_object in favour of creating and destroying DMA mappings
on first VMA instantiation and last VMA destruction. (Daniel Vetter)
* Simplified i915_vma_unbind which does not need to count the GGTT views.
(Daniel Vetter)
* Also moved obj->map_and_fenceable reset under the same check.
* Checkpatch cleanups.
v3:
* Only retire objects once the last VMA is unbound.
v4:
* Keep scatter-gather table for alternative views persistent for the
lifetime of the VMA.
* Propagate binding errors to callers and handle appropriately.
v5:
* Explicitly look for normal GGTT view in i915_gem_obj_bound to align
usage in i915_gem_object_ggtt_unpin. (Michel Thierry)
* Change to single if statement in i915_gem_obj_to_ggtt. (Michel Thierry)
* Removed stray semi-colon in i915_gem_object_set_cache_level.
For: VIZ-4544
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
[danvet: Drop hunk from i915_gem_shrink since it's just prettification
but upsets a __must_check warning.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Release struct_mutex if init_rings() fails.
This is a regression introduced in
commit 35a57ffbb1
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu Nov 20 00:33:07 2014 +0100
drm/i915: Only init engines once
Reported-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So apparently jiffies<->nsec<->ktime isn't accurate or something. At
elast if we timeout there's occasionally still a few hundred us left
(in a 2 second timeout).
Stuff I've tried and thrown out again:
- Sampling the before timestamp before jiffies. Doesn't improve test
path rate at all.
- Using jiffies. Way to inaccurate, which means way too much drift
with signals plus automatic ioctl restarting in userspace. In
hindsight we should have used an absolute timeout, but hey we need
something for v3 of the i915 gem wait interfaces ;-)
- Trying to figure out where accuracy gets lost. gl testcase really
don't care all that much about this (as long as isn't not massively
off), it's just that the testcase gets a bit upset if it receives an
EITME with timeout > 0.
So as long as we're in the ballbark it's good enough. So patch
everything up if we're at most one jiffies off. I get's me a solid
test again.
This regression is probably introduced in
commit 5ed0bdf21a
Author: Thomas Gleixner <tglx@linutronix.de>
Date: Wed Jul 16 21:05:06 2014 +0000
drm: i915: Use nsec based interfaces
Use ktime_get_raw_ns() and get rid of the back and forth timespec
conversions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Probably because I'm too lazy to confirm myself and still waiting for
QA ;-)
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=82749
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
We've lost the +1 required for correct timeouts in
commit 5ed0bdf21a
Author: Thomas Gleixner <tglx@linutronix.de>
Date: Wed Jul 16 21:05:06 2014 +0000
drm: i915: Use nsec based interfaces
Use ktime_get_raw_ns() and get rid of the back and forth timespec
conversions.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: John Stultz <john.stultz@linaro.org>
So fix this up by reinstating our handrolled _timeout function. While
at it bother with handling MAX_JIFFIES.
v2: Convert to usecs (we don't care about the accuracy anyway) first
to avoid overflow issues Dave Gordon spotted.
v3: Drop the explicit MAX_JIFFY_OFFSET check, usecs_to_jiffies should
take care of that already. It might be a bit too enthusiastic about it
though.
v4: Chris has a much nicer color, so use his implementation.
This requires to export nsec_to_jiffies from time.c.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dave Gordon <david.s.gordon@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=82749
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Acked-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Multiple GGTT VMAs per object will be introduced in the near future which will
make it impossible to guarantee normal GGTT view is at the head of the list.
Purpose of this patch is to break this assumption straight away so any
potential hidden assumptions in the code base can be bisected to this
simple patch.
For: VIZ-4544
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We need to do that every time we resume the rings, not just at load.
I've overlooked this in my untangling of the ring init code.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We can do this.
And now there's finally the clean split between software setup and
hardware setup I kinda wanted since multi-ring support was merged
aeons ago. It only took almost 5 years.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Updated the trace_irq code to use requests instead of seqnos. This includes
reference counting the request object to ensure it sticks around when required.
Note that getting access to the reference counting functions means moving the
inline i915_trace_irq_get() function from intel_ringbuffer.h to i915_drv.h.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
[danvet: Resolve conflict due to shuffled merge order.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The ring member of the object structure was always updated with the
last_read_seqno member. Thus with the conversion to last_read_req, obj->ring is
now a direct copy of obj->last_read_req->ring. This makes it somewhat redundant
and potentially misleading (especially as there was no comment to explain its
purpose).
This checkin removes the redundant field. Many uses were simply testing for
non-null to see if the object is active on the GPU. Some of these have been
converted to check 'obj->active' instead. Others (where the last_read_req is
about to be used anyway) have been changed to check obj->last_read_req. The rest
simply pull the ring out from the request structure and proceed as before.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Almost everywhere that caled i915_seqno_passed() was really asking 'has the
given seqno popped out of the hardware yet?'. Thus it had to query the current
hardware seqno and then do a signed delta comparison (which copes with wrapping
around zero but not with seqno values more than 2GB apart, although the latter
is unlikely!).
Now that the majority of seqno instances have been replaced with request
structures, it is possible to convert this test to be request based as well.
There is now a 'i915_gem_request_completed()' function which takes a request and
returns true or false as appropriate. Note that this currently just wraps up the
original _passed() test but a later patch in the series will reduce this to
simply returning a cached internal value, i.e.:
_completed(req) { return req->completed; }'
This checkin converts almost all _seqno_passed() calls. The only one left is in
the semaphore code which still requires seqnos not request structures.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
[danvet: Drop hunk touching the trace_irq code since I've dropped the
patch which converts that, and resolve resulting conflict.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
It makes a lot more sense (and makes future seqno -> request conversion patches
simpler) to fill in the 'ring' field of the request structure at the point of
creation rather than submission. Given that the request structure is assigned by
ring specific code and thus is locked to a ring from the start, there really is
no reason to defer this assignment.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
All the code above is now using requests not seqnos so it is possible to convert
the trace functions across. Note that rather than get into problematic reference
counting issues, the trace code only saves the seqno and ring values from the
request structure not the structure pointer itself.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
There is no longer any need to retrieve a seqno value from an i915_add_request()
call. The calling code already knows which request structure is being processed
(it can only be ring->OLR). And as the request itself is now used in preference
to the basic seqno value, the latter is now redundant in this situation.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Now that all code above is using request structures instead of seqno values, it
is possible to convert __wait_seqno() itself. Internally, it is still calling
i915_seqno_passed(), this will be updated later in the series. This step is just
changing the parameter list and function name.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Updated i915_wait_seqno() to take a request structure instead of a seqno value
and renamed it accordingly. Internally, it just pulls the seqno out of the
request and calls on to __wait_seqno() as before. However, all the code further
up the stack is now simplified as it can just pass the request object straight
through without having to peek inside.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
[danvet: Squash in hunk from an earlier patch which was rebased
wrongly.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Updated the _check_olr() function to actually take a request object and compare
it to the OLR rather than extracting seqnos and comparing those.
Note that there is one use case where the request object being processed is no
longer available at that point in the call stack. Hence a temporary copy of the
original function is still present (but called _check_ols() instead). This will
be removed in a subsequent patch.
Also, downgraded a BUG_ON to a WARN_ON as apparently the former is frowned upon
for shipping code.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The OLS value is now obsolete. Exactly the same value is guarateed to be always
available as PLR->seqno. Thus it is safe to remove the OLS completely. And also
to rename the PLR to OLR to keep the 'outstanding lazy ...' naming convention
valid.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Added reference counting of the request structure around __wait_seqno() calls.
This is a precursor to updating the wait code itself to take the request rather
than a seqno. At that point, it would be a Bad Idea for a request object to be
retired and freed while the wait code is still using it.
v3:
Note that even though the mutex lock is held during a call to i915_wait_seqno(),
it is still necessary to explicitly bump the reference count. It appears that
the shrinker can asynchronously retire items even though the mutex is locked.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
[danvet: Remove wrongly squashed hunk which breaks the build.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Convert the throttle code to use the request structure rather than extracting a
ring/seqno pair from it and using those. This is in preparation for
__wait_seqno() becoming __wait_request().
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The object structure contains the last read, write and fenced seqno values for
use in syncrhonisation operations. These have now been replaced with their
request structure counterparts.
Note that to ensure that objects do not end up with dangling pointers, the
assignments of last_*_req include reference count updates. Thus a request cannot
be freed if an object is still hanging on to it for any reason.
v2: Corrected 'last_rendering_' to 'last_read_' in a number of comments that did
not get updated when 'last_rendering_seqno' became 'last_read|write_seqno'
several millenia ago.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The plan is to use request structures everywhere that seqno values were
previously used. This means saving pointers to structures in places that used to
be simple integers. In turn, that means that the target structure now needs much
more stringent lifetime tracking. That is, it must not be freed while some other
random object still holds a pointer to it.
To achieve this tracking, a reference count needs to be added. Whenever a
pointer to the structure is saved away, the count must be incremented and the
free must only occur when all references have been released.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Thomas Daniel <Thomas.Daniel@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Before suspending, we wait upon the outstanding GPU requests and flush
our pending idle handlers. This should downclock the GPU to its lowest
power state. Add a WARN to check that the delayed tasks were run and did
their job properly.
Suggested-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Dynamic context pinning for LRCs introduced a leak in legacy mode.
Reinstate context unreference in i915_gem_free_request for legacy contexts.
Leak reported by i-g-t/drv_module_reload fixed by this patch.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=86507
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: John Harrison<John.C.Harrison@Intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The problem here is that SNA pins batchbuffers to etch out a bit more
performance. Iirc it started out as a w/a for i830M (which we've
implemented in the kernel since a long time already). The problem is
that the pin ioctl wasn't added in
commit d23db88c3a
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri May 23 08:48:08 2014 +0200
drm/i915: Prevent negative relocation deltas from wrapping
Fix this by simply disallowing pinning from userspace so that the
kernel is in full control of batch placement again. Especially since
distros are moving towards running X as non-root, so most users won't
even be able to see any benefits.
UMS support is dead now, but we need this minimal patch for
backporting. Follow-up patch will remove the pin ioctl code
completely.
Note to backporters: You must have both
commit b45305fce5
Author: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon Dec 17 16:21:27 2012 +0100
drm/i915: Implement workaround for broken CS tlb on i830/845
which laned in 3.8 and
commit c4d69da167
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon Sep 8 14:25:41 2014 +0100
drm/i915: Evict CS TLBs between batches
which is also marked cc: stable. Otherwise this could introduce a
regression by disabling the userspace w/a without the kernel w/a being
fully functional on i830/45.
References: https://bugs.freedesktop.org/show_bug.cgi?id=76554#c116
Cc: stable@vger.kernel.org # requires c4d69da167 and v3.8
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
drm-intel-next-2014-11-21:
- infoframe tracking (for fastboot) from Jesse
- start of the dri1/ums support removal
- vlv forcewake timeout fixes (Imre)
- bunch of patches to polish the rps code (Imre) and improve it on bdw (Tom
O'Rourke)
- on-demand pinning for execlist contexts
- vlv/chv backlight improvements (Ville)
- gen8+ render ctx w/a work from various people
- skl edp programming (Satheeshakrishna et al.)
- psr docbook (Rodrigo)
- piles of little fixes and improvements all over, as usual
* tag 'drm-intel-next-2014-11-21-fixed' of git://anongit.freedesktop.org/drm-intel: (117 commits)
drm/i915: Don't pin LRC in GGTT when dumping in debugfs
drm/i915: Update DRIVER_DATE to 20141121
drm/i915/g4x: fix g4x infoframe readout
drm/i915: Only call mod_timer() if not already pending
drm/i915: Don't rely upon encoder->type for infoframe hw state readout
drm/i915: remove the IRQs enabled WARN from intel_disable_gt_powersave
drm/i915: Use ggtt error obj capture helper for gen8 semaphores
drm/i915: vlv: increase timeout when setting idle GPU freq
drm/i915: vlv: fix cdclk setting during modeset while suspended
drm/i915: Dump hdmi pipe_config state
drm/i915: Gen9 shadowed registers
drm/i915/skl: Gen9 multi-engine forcewake
drm/i915: Read power well status before other registers for drpc info
drm/i915: Pin tiled objects for L-shaped configs
drm/i915: Update ring freq for full gpu freq range
drm/i915: change initial rps frequency for gen8
drm/i915: Keep min freq above floor on HSW/BDW
drm/i915: Use efficient frequency for HSW/BDW
drm/i915: Can i915_gem_init_ioctl
drm/i915: Sanitize ->lastclose
...
It happens on occasion that developers of generic user-space applications
abuse the dumb buffer API to get hold of drm buffers that they can both
mmap() and use for GPU acceleration, using the assumptions that dumb buffers
and buffers available for GPU are
a) The same type and can be aribtrarily type-casted.
b) fully coherent.
This patch makes the most widely used drivers warn nicely when that happens,
the next step will be to fail.
v2: Move drmP.h changes to drm_gem.h. Fix Radeon dumb mmap breakage.
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Let's just throw in the towel on this one and take the cheap way out.
Based on a patch from Chris Wilson, but checking for a different bit.
Chris' patch checked for even bank layout, this one here for a magic
bit. Given the evidence we've gathered (not much) both work I think,
but checking for the magic bit might be more accurate.
Anyway, works on my gm45 here.
For paranoi restrict to gen4 (and mobile), since we've only ever seen
this on gm45 and i965gm.
Also add some debugfs output so that we can skip the tiled swapping
tests properly in these cases.
v2: Clean up the quirk'ed pin count in free_object to avoid upsetting
the WARN_ON. Spotted by Chris.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=28813
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=45092
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Found one more!
With this we can clear up the ggtt init code a bit, yay!
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
With this all the ums nonsense around gem setup/teardown has
disappeared, yay!
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Again just complicates gem init functions and makes a general mess out
of everything.
Good riddance!
v2: In my enthusiasm to start removing dri1/ums crud I went overboard a
bit and killed parts of hangcheck. Resurrect it.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
We've killed ums support by now, it's time to reap the benefits. This
one here is getting in the way of doing some ring init cleanup.
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
With the deprecation of UMS, and by association DRI1, we have a tough
choice when updating the ring access routines. We either rewrite the
DRI1 routines blindly without testing (so likely to be broken) or take
the liberty of declaring them no longer supported and remove them
entirely. This takes the latter approach.
v2: Also remove the DRI1 sarea updates
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Fix rebase conflicts.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Up until now, we have pinned every logical ring context backing object
during creation, and left it pinned until destruction. This made my life
easier, but it's a harmful thing to do, because we cause fragmentation
of the GGTT (and, eventually, we would run out of space).
This patch makes the pinning on-demand: the backing objects of the two
contexts that are written to the ELSP are pinned right before submission
and unpinned once the hardware is done with them. The only context that
is still pinned regardless is the global default one, so that the HWS can
still be accessed in the same way (ring->status_page).
v2: In the early version of this patch, we were pinning the context as
we put it into the ELSP: on the one hand, this is very efficient because
only a maximum two contexts are pinned at any given time, but on the other
hand, we cannot really pin in interrupt time :(
v3: Use a mutex rather than atomic_t to protect pin count to avoid races.
Do not unpin default context in free_request.
v4: Break out pin and unpin into functions. Fix style problems reported
by checkpatch
v5: Remove unpin_lock as all pinning and unpinning is done with the struct
mutex already locked. Add WARN_ONs to make sure this is the case in future.
Issue: VIZ-4277
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Akash Goel <akash.goels@gmail.com>
Reviewed-by: Deepak S<deepak.s@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
No longer create a work item to clean each execlist queue item.
Instead, move retired execlist requests to a queue and clean up the
items during retire_requests.
v2: Fix legacy ring path broken during overzealous cleanup
v3: Update idle detection to take execlists queue into account
v4: Grab execlist lock when checking queue state
v5: Fix leaking requests by freeing in execlists_retire_requests.
Issue: VIZ-4274
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Reviewed-by: Deepak S <deepak.s@linux.intel.com>
Reviewed-by: Akash Goel <akash.goels@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Currently objects for which the hardware needs a contiguous physical
address are allocated a shadow backing storage to satisfy the contraint.
This shadow buffer is not wired into the normal obj->pages and so the
physical object is incoherent with accesses via the GPU, GTT and CPU. By
setting up the appropriate scatter-gather table, we can allow userspace
to access the physical object via either a GTT mmaping of or by rendering
into the GEM bo. However, keeping the CPU mmap of the shmemfs backing
storage coherent with the contiguous shadow is not yet possible.
Fortuituously, CPU mmaps of objects requiring physical addresses are not
expected to be coherent anyway.
This allows the physical constraint of the GEM object to be transparent
to userspace and allow it to efficiently render into or update them via
the GTT and GPU.
v2: Fix leak of pci handle spotted by Ville
v3: Remove the now duplicate call to detach_phys_object during free.
v4: Wait for rendering before pwrite. As this patch makes it possible to
render into the phys object, we should make it correct as well!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
So that it can be used by the flip code to wait for rendering without
holding any locks.
Signed-off-by: Ander Conselvan de Oliveira <ander.conselvan.de.oliveira@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Always require PIN_GLOBAL when we want a mappable offset (PIN_MAPPABLE).
This causes the pin to fixup the global binding in cases were the vma
was already bound (and due to the proceeding bug, we considered it to be
already mappable).
References: https://bugs.freedesktop.org/show_bug.cgi?id=85671
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add WARN_ON to check that PIN_MAP implies PIN_GLOBAL as
discussed on irc.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We use the obj->map_and_fenceable hint for when we already have a
valid mapping of this object in the aperture. This hint can only apply
to the GGTT and not to the aliasing-ppGTT. One user of the hint is
execbuffer relocation, which began to fail when it tried to follow the
hint and perform the relocate through the non-existent GGTT mapping.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=85671
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
An earlier commit (c8725f3dc0911d4354315a65150aecd8b7d0d74a: Do not call
retire_requests from wait_for_rendering) removed the use of the ring parameter
within wait_rendering__tail() but did not remove the parameter itself. As the
plan is to remove obj->ring which is where this parameter comes from, it is
simpler to just remove the parameter completely than to update it with a new
source.
For: VIZ-4377
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
CC: Chris Wilson <chris@chris-wilson.co.uk>
CC: Brad Volkin <bradley.d.volkin@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If these flags are on the object level it will be more difficult to allow
for multiple VMAs per object.
v2: Simplification and cleanup after code review comments (Chris Wilson).
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Not having checks for this isn't good.
I've checked igt and libdrm and they all already clear flags properly.
So we're lucky and should be able to sneak this ABI clarification in.
Testcase: igt/gem_wait/invalid-flags
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=85280
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Too many new drm driver writers seem to look at i915 for inspiration.
But we have two ways to do mmap, so discourage readers from the old,
ugly version. In a new driver we'd just expose two mmap offsets per
object, one for the gtt map and the other for the cpu map.
v2: Make it clear that i915 does cpu mmaps this way for past
cluelessness^W^W historical reasons. Asked for by Jani.
Cc: "Cheng, Yao" <yao.cheng@intel.com>
Cc: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If we are not able to free anything (the shrinker leaves nothing on the
global object lists), do not log anything. This is useful when other
subsystems are being stress-tested for their oom behaviour and i915.ko
is shouting into the logs about doing nothing.
Reported-by: Dave Jones <davej@redhat.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
The shrinker reports the number of pages freed, but we try to log the
number of bytes - which leads to some nonsense values being reportedly
freed during oom.
Reported-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
We can use the same logic to walk the different bound/unbound lists
during shrinker (as the unbound list is a degenerate case of the bound
list), slightly compacting the code.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
John Harrison