The legacy context switch for ringbuffer submission is multistaged,
where each of those stages may fail. However, we were updating global
state after some stages, and so we had to force the incomplete request
to be submitted because we could not unwind. Save the global state
before performing the switches, and so enable us to unwind back to the
previous global state should any phase fail. We then must cancel the
request instead of submitting it should the construction fail.
v2: s/saved_ctx/from_ctx/; s/ctx/to_ctx/ etc.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171123152631.31385-1-chris@chris-wilson.co.uk
Since removing the module parameter to force selection of ringbuffer
emission for gen8, the code is defunct. Remove it.
To put the difference into perspective, a couple of microbenchmarks
(bdw i7-5557u, 20170324):
ring execlists
exec continuous nops on all rings: 1.491us 2.223us
exec sequential nops on each ring: 12.508us 53.682us
single nop + sync: 9.272us 30.291us
vblank_mode=0 glxgears: ~11000fps ~9000fps
Since the earlier submission, gen8 ringbuffer submission has fallen
further and further behind in features. So while ringbuffer may hold the
throughput crown, in terms of interactive latency, execlists is much
better. Alas, we have no convenient metrics for such, other than
demonstrating things we can do with execlists but can not using
legacy ringbuffer submission.
We have made a few improvements to lowlevel execlists throughput,
and ringbuffer currently panics on boot! (bdw i7-5557u, 20171026):
ring execlists
exec continuous nops on all rings: n/a 1.921us
exec sequential nops on each ring: n/a 44.621us
single nop + sync: n/a 21.953us
vblank_mode=0 glxgears: n/a ~18500fps
References: https://bugs.freedesktop.org/show_bug.cgi?id=87725
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Once-upon-a-time-Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171120205504.21892-2-chris@chris-wilson.co.uk
At the start of building a request, we would wait for roughly enough
space to fit the average request (to reduce the likelihood of having to
wait and abort partway through request construction). To achieve we
would try to begin a 0-length command packet, this just adds extra
confusion so make the wait-for-space explicit, as in the next patch we
want to move it from the backend to the i915_gem_request_alloc() so it
can ensure that the wait-for-space is the first operation in building a
new request.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171115151204.8105-2-chris@chris-wilson.co.uk
Take a copy of the HW state after a reset upon module loading by
executing a context switch from a blank context to the kernel context,
thus saving the default hw state over the blank context image.
We can then use the default hw state to initialise any future context,
ensuring that each starts with the default view of hw state.
v2: Unmap our default state from the GTT after stealing it from the
context. This should stop us from accidentally overwriting it via the
GTT (and frees up some precious GTT space).
Testcase: igt/gem_ctx_isolation
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110142634.10551-7-chris@chris-wilson.co.uk
In the next few patches, we will want to both copy out of the context
image and write a valid image into a new context. To be completely safe,
we should then couple in our domain tracking to ensure that we don't
have any issues with stale data remaining in unwanted cachelines.
Historically, we omitted the .write=true from the call to set-gtt-domain
in i915_switch_context() in order to avoid a stall between every request
as we would want to wait for the previous context write from the gpu.
Since then, we limit the set-gtt-domain to only occur when we first bind
the vma, so once in use we will never stall, and we are sure to flush
the context following a load from swap.
Equally we never applied the lessons learnt from ringbuffer submission
to execlists; so time to apply the flush of the lrc after load as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171110142634.10551-6-chris@chris-wilson.co.uk
In the next patch, we want to reduce the lock coverage within the
shrinker, and one of the dangerous walks we have is over obj->vma_list.
We are only walking the obj->vma_list in order to check whether it has
been permanently pinned by HW access, typically via use on the scanout.
But we have a couple of other long term pins, the context objects for
which we currently have to check the individual vma pin_count. If we
instead mark these using obj->pin_display, we can forgo the dangerous
and sometimes slow list iteration.
v2: Rearrange code to try and avoid confusion from false associations
due to arrangement of whitespace along with rebasing on obj->pin_global.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171013202621.7276-4-chris@chris-wilson.co.uk
Typically, there is space available within the ring and if not we have
to wait (by definition a slow path). Rearrange the code to reduce the
number of branches and stack size for the hotpath, accomodating a slight
growth for the wait.
v2: Fix the new assert that packets are not larger than the actual ring.
v3: Make the parameters unsigned as well to make usage.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170504130846.4807-3-chris@chris-wilson.co.uk
Since unifying ringbuffer/execlist submission to use
engine->pin_context, we ensure that the intel_ring is available before
we start constructing the request. We can therefore move the assignment
of the request->ring to the central i915_gem_request_alloc() and not
require it in every engine->request_alloc() callback. Another small step
towards simplification (of the core, but at a cost of handling error
pointers in less important callers of engine->pin_context).
v2: Rearrange a few branches to reduce impact of PTR_ERR() on gcc's code
generation.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170504093308.4137-1-chris@chris-wilson.co.uk
The contents of a ring are only valid between HEAD and TAIL, when the
ring is idle (HEAD == TAIL) we can simply let the pages go under memory
pressure if they are not pinned by an active context. Any new content
will be written after HEAD and so the ring will again be valid between
HEAD and TAIL, everything outside can be discarded.
Note that we take care of ensuring that we do not reset the HEAD
backwards following a GPU hang on an idle ring.
The same precautions are what enable us to use stolen memory for rings.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170420101709.27250-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Or rather it is used only by intel_ring_pin() to extract the
drm_i915_private which we can easily pass in. As this is a relatively
rare operation, save the space in the struct, and as such it is even
break even in the extra code for passing around the parameter:
add/remove: 0/0 grow/shrink: 2/3 up/down: 15/-15 (0)
function old new delta
intel_init_ring_buffer 906 918 +12
execlists_context_pin 1308 1311 +3
mock_engine 407 403 -4
intel_engine_create_ring 367 363 -4
intel_ring_pin 326 319 -7
Total: Before=1261794, After=1261794, chg +0.00%
v2: Reorder intel_init_ring_buffer to keep the ring setup together:
add/remove: 0/0 grow/shrink: 2/3 up/down: 9/-15 (-6)
function old new delta
intel_init_ring_buffer 906 912 +6
execlists_context_pin 1308 1311 +3
mock_engine 407 403 -4
intel_engine_create_ring 367 363 -4
intel_ring_pin 326 319 -7
Total: Before=1261794, After=1261788, chg -0.00%
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170403113426.25707-1-chris@chris-wilson.co.uk
This removes the usage of intel_ring_emit in favour of
directly writing to the ring buffer.
intel_ring_emit was preventing the compiler for optimising
fetch and increment of the current ring buffer pointer and
therefore generating very verbose code for every write.
It had no useful purpose since all ringbuffer operations
are started and ended with intel_ring_begin and
intel_ring_advance respectively, with no bail out in the
middle possible, so it is fine to increment the tail in
intel_ring_begin and let the code manage the pointer
itself.
Useless instruction removal amounts to approximately
two and half kilobytes of saved text on my build.
Not sure if this has any measurable performance
implications but executing a ton of useless instructions
on fast paths cannot be good.
v2:
* Change return from intel_ring_begin to error pointer by
popular demand.
* Move tail increment to intel_ring_advance to enable some
error checking.
v3:
* Move tail advance back into intel_ring_begin.
* Rebase and tidy.
v4:
* Complete rebase after a few months since v3.
v5:
* Remove unecessary cast and fix !debug compile. (Chris Wilson)
v6:
* Make intel_ring_offset take request as well.
* Fix recording of request postfix plus a sprinkle of asserts.
(Chris Wilson)
v7:
* Use intel_ring_offset to get the postfix. (Chris Wilson)
* Convert GVT code as well.
v8:
* Rename *out++ to *cs++.
v9:
* Fix GVT out to cs conversion in GVT.
v10:
* Rebase for new intel_ring_begin in selftests.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170214113242.29241-1-tvrtko.ursulin@linux.intel.com
