In the current scheme, on submitting a request we take a single global
GEM wakeref, which trickles down to wake up all GT power domains. This
is undesirable as we would like to be able to localise our power
management to the available power domains and to remove the global GEM
operations from the heart of the driver. (The intent there is to push
global GEM decisions to the boundary as used by the GEM user interface.)
Now during request construction, each request is responsible via its
logical context to acquire a wakeref on each power domain it intends to
utilize. Currently, each request takes a wakeref on the engine(s) and
the engines themselves take a chipset wakeref. This gives us a
transition on each engine which we can extend if we want to insert more
powermangement control (such as soft rc6). The global GEM operations
that currently require a struct_mutex are reduced to listening to pm
events from the chipset GT wakeref. As we reduce the struct_mutex
requirement, these listeners should evaporate.
Perhaps the biggest immediate change is that this removes the
struct_mutex requirement around GT power management, allowing us greater
flexibility in request construction. Another important knock-on effect,
is that by tracking engine usage, we can insert a switch back to the
kernel context on that engine immediately, avoiding any extra delay or
inserting global synchronisation barriers. This makes tracking when an
engine and its associated contexts are idle much easier -- important for
when we forgo our assumed execution ordering and need idle barriers to
unpin used contexts. In the process, it means we remove a large chunk of
code whose only purpose was to switch back to the kernel context.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190424200717.1686-5-chris@chris-wilson.co.uk
We can no longer assume execution ordering, and in particular we cannot
assume which context will execute last. One side-effect of this is that
we cannot determine if the kernel-context is resident on the GPU, so
remove the routines that claimed to do so.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308093657.8640-4-chris@chris-wilson.co.uk
Currently we assume that we know the order in which requests run and so
can determine if we need to reissue a switch-to-kernel-context prior to
idling. That assumption does not hold for the future, so instead of
tracking which barriers have been used, simply determine if we have ever
switched away from the kernel context by using the engine and before
idling ensure that all engines that have been used since the last idle
are synchronously switched back to the kernel context for safety (and
else of shrinking memory while idle).
v2: Use intel_engine_mask_t and ALL_ENGINES
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308093657.8640-3-chris@chris-wilson.co.uk
A starting point to counter the pervasive struct_mutex. For the goal of
avoiding (or at least blocking under them!) global locks during user
request submission, a simple but important step is being able to manage
each clients GTT separately. For which, we want to replace using the
struct_mutex as the guard for all things GTT/VM and switch instead to a
specific mutex inside i915_address_space.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190128102356.15037-2-chris@chris-wilson.co.uk
Our goal is to remove struct_mutex and replace it with fine grained
locking. One of the thorny issues is our eviction logic for reclaiming
space for an execbuffer (or GTT mmaping, among a few other examples).
While eviction itself is easy to move under a per-VM mutex, performing
the activity tracking is less agreeable. One solution is not to do any
MRU tracking and do a simple coarse evaluation during eviction of
active/inactive, with a loose temporal ordering of last
insertion/evaluation. That keeps all the locking constrained to when we
are manipulating the VM itself, neatly avoiding the tricky handling of
possible recursive locking during execbuf and elsewhere.
Note that discarding the MRU (currently implemented as a pair of lists,
to avoid scanning the active list for a NONBLOCKING search) is unlikely
to impact upon our efficiency to reclaim VM space (where we think a LRU
model is best) as our current strategy is to use random idle replacement
first before doing a search, and over time the use of softpinned 48b
per-ppGTT is growing (thereby eliminating any need to perform any eviction
searches, in theory at least) with the remaining users being found on
much older devices (gen2-gen6).
v2: Changelog and commentary rewritten to elaborate on the duality of a
single list being both an inactive and active list.
v3: Consolidate bool parameters into a single set of flags; don't
comment on the duality of a single variable being a multiplicity of
bits.
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>
Link: https://patchwork.freedesktop.org/patch/msgid/20190128102356.15037-1-chris@chris-wilson.co.uk
Needs just a few additional includes here and there.
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190108082709.3748-1-jani.nikula@intel.com
Usually we have no idea about the upper bound we need to wait to catch
up with userspace when idling the device, but in a few situations we
know the system was idle beforehand and can provide a short timeout in
order to very quickly catch a failure, long before hangcheck kicks in.
In the following patches, we will use the timeout to curtain two overly
long waits, where we know we can expect the GPU to complete within a
reasonable time or declare it broken.
In particular, with a broken GPU we expect it to fail during the initial
GPU setup where do a couple of context switches to record the defaults.
This is a task that takes a few milliseconds even on the slowest of
devices, but we may have to wait 60s for hangcheck to give in and
declare the machine inoperable. In this a case where any gpu hang is
unacceptable, both from a timeliness and practical standpoint.
The other improvement is that in selftests, we do not need to arm an
independent timer to inject a wedge, as we can just limit the timeout on
the wait directly.
v2: Include the timeout parameter in the trace.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709122044.7028-1-chris@chris-wilson.co.uk
We want to de-emphasize the link between the request (dependency,
execution and fence tracking) from GEM and so rename the struct from
drm_i915_gem_request to i915_request. That is we may implement the GEM
user interface on top of requests, but they are an abstraction for
tracking execution rather than an implementation detail of GEM. (Since
they are not tied to HW, we keep the i915 prefix as opposed to intel.)
In short, the spatch:
@@
@@
- struct drm_i915_gem_request
+ struct i915_request
A corollary to contracting the type name, we also harmonise on using
'rq' shorthand for local variables where space if of the essence and
repetition makes 'request' unwieldy. For globals and struct members,
'request' is still much preferred for its clarity.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180221095636.6649-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
During evict, we wish to idle the GPU if we see that the GGTT is full.
However, our test for idle in i915_gem_evict_something() and in
i915_gem_switch_to_kernel_context() do not match leading to
disappointment - we never believe that we are idle and keep trying to
flush the GGTT ad infinitum.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103438
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024220855.30155-2-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Insert a breakpoint, a chance to escape back to the scheduler and run
something else for a bit, if we find that the GGTT is full and needs to
be idled in order to make some room. In practice, this should only be an
issue in stress tests as the wait itself will normally give the chance
for the scheduler to intervene and make progress.
References: https://bugs.freedesktop.org/show_bug.cgi?id=103438
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171024205053.7845-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
A bug recently encountered involved the issue where are we were
submitting requests to different ppGTT, each would pin a segment of the
GGTT for its logical context and ring. However, this is invisible to
eviction as we do not tie the context/ring VMA to a request and so do
not automatically wait upon it them (instead they are marked as pinned,
preventing eviction entirely). Instead the eviction code must flush those
contexts by switching to the kernel context. This selftest tries to
fill the GGTT with contexts to exercise a path where the
switch-to-kernel-context failed to make forward progress and we fail
with ENOSPC.
v2: Make the hole in the filled GGTT explicit.
v3: Swap out the arbitrary timeout for a private notification from
i915_gem_evict_something()
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171012125726.14736-3-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
In the full-ppgtt world, we can fill the GGTT full of context objects.
These context objects are currently implicitly tracked by the requests
that pin them i.e. they are only unpinned when the request is completed
and retired, but we do not have the link from the vma to the request
(anymore). In order to unpin those contexts, we have to issue another
request and wait upon the switch to the kernel context.
The bug during eviction was that we assumed that a full GGTT meant we
would have requests on the GGTT timeline, and so we missed situations
where those requests where merely in flight (and when even they have not
yet been submitted to hw yet). The fix employed here is to change the
already-is-idle test to no look at the execution timeline, but count the
outstanding requests and then check that we have switched to the kernel
context. Erring on the side of overkill here just means that we stall a
little longer than may be strictly required, but we only expect to hit
this path in extreme corner cases where returning an erroneous error is
worse than the delay.
v2: Logical inversion when swapping over branches.
Fixes: 80b204bce8 ("drm/i915: Enable multiple timelines")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171012125726.14736-1-chris@chris-wilson.co.uk
If the caller says that he doesn't want to evict any other faulting
vma, honour that flag. The logic was used in evict_something, but not
the more specific evict_for_node, now being used as a preliminary probe
since commit 606fec956c ("drm/i915: Prefer random replacement before
eviction search").
Fixes: 606fec956c ("drm/i915: Prefer random replacement before eviction search")
Fixes: 821188778b ("drm/i915: Choose not to evict faultable objects from the GGTT")
References: https://bugs.freedesktop.org/show_bug.cgi?id=102490
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009084401.29090-4-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
We don't wish to refault the entire object (other vma) when unbinding
one partial vma. To do this track which vma have been faulted into the
user's address space.
v2: Use a local vma_offset to tidy up a multiline unmap_mapping_range().
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009084401.29090-3-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
When userspace is doing most of the work, avoiding relocs (using
NO_RELOC) and opting out of implicit synchronisation (using ASYNC), we
still spend a lot of time processing the arrays in execbuf, even though
we now should have nothing to do most of the time. One issue that
becomes readily apparent in profiling anv is that iterating over the
large execobj[] is unfriendly to the loop prefetchers of the CPU and it
much prefers iterating over a pair of arrays rather than one big array.
v2: Clear vma[] on construction to handle errors during vma lookup
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170816085210.4199-3-chris@chris-wilson.co.uk
The major scaling bottleneck in execbuffer is the processing of the
execobjects. Creating an auxiliary list is inefficient when compared to
using the execobject array we already have allocated.
Reservation is then split into phases. As we lookup up the VMA, we
try and bind it back into active location. Only if that fails, do we add
it to the unbound list for phase 2. In phase 2, we try and add all those
objects that could not fit into their previous location, with fallback
to retrying all objects and evicting the VM in case of severe
fragmentation. (This is the same as before, except that phase 1 is now
done inline with looking up the VMA to avoid an iteration over the
execobject array. In the ideal case, we eliminate the separate reservation
phase). During the reservation phase, we only evict from the VM between
passes (rather than currently as we try to fit every new VMA). In
testing with Unreal Engine's Atlantis demo which stresses the eviction
logic on gen7 class hardware, this speed up the framerate by a factor of
2.
The second loop amalgamation is between move_to_gpu and move_to_active.
As we always submit the request, even if incomplete, we can use the
current request to track active VMA as we perform the flushes and
synchronisation required.
The next big advancement is to avoid copying back to the user any
execobjects and relocations that are not changed.
v2: Add a Theory of Operation spiel.
v3: Fall back to slow relocations in preparation for flushing userptrs.
v4: Document struct members, factor out eb_validate_vma(), add a few
more comments to explain some magic and hide other magic behind macros.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Currently the vma has one link member that is used for both holding its
place in the execbuf reservation list, and in any eviction list. This
dual property is quite tricky and error prone.
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/20170615081435.17699-3-chris@chris-wilson.co.uk
This has the benefit of not requiring us to manipulate the
vma->exec_link list when tearing down the execbuffer, and is a
marginally cheaper test to detect the user error.
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/20170615081435.17699-2-chris@chris-wilson.co.uk
As we now distinguish everywhere that can call
i915_gem_retire_requests() following a successful wait_for_idle, we can
remove the duplication by moving that call into i915_gem_wait_for_idle()
itself.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170330145041.9005-3-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
It looks like we were incorrectly comparing vma->node against itself
instead of the target node, when evicting for a node on systems where we
need guard pages between regions with different cache domains. As a
consequence we can end up trying to needlessly evict neighbouring nodes,
even if they have the same cache domain, and if they were pinned we
would fail the eviction.
Fixes: 625d988acc ("drm/i915: Extract reserving space in the GTT to a helper")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170306235414.23407-3-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Once upon a time, back in the UMS days, we supported userspace
initialising the GTT and sharing portions of the GTT with other users.
Now, we own the GTT (both global and per-process) and the tables always
start at 0 - so we can remove i915_address_space.start and forget about
this old complication.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170215084357.19977-20-chris@chris-wilson.co.uk
Chris Wilson needs the new drm_driver->release callback to make sure
the shiny new dma-buf testcases don't oops the driver on unload.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
As we now mark the reserved hole (drm_mm.head_node) with the special
UNEVICTABLE color, we can use the page coloring to avoid prefetching of
the CS beyond the end of the GTT.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170206084547.27921-3-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
The drm_mm range manager claimed to support top-down insertion, but it
was neither searching for the top-most hole that could fit the
allocation request nor fitting the request to the hole correctly.
In order to search the range efficiently, we create a secondary index
for the holes using either their size or their address. This index
allows us to find the smallest hole or the hole at the bottom or top of
the range efficiently, whilst keeping the hole stack to rapidly service
evictions.
v2: Search for holes both high and low. Rename flags to mode.
v3: Discover rb_entry_safe() and use it!
v4: Kerneldoc for enum drm_mm_insert_mode.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Christian Gmeiner <christian.gmeiner@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Stephen Warren <swarren@wwwdotorg.org>
Cc: Alexandre Courbot <gnurou@gmail.com>
Cc: Eric Anholt <eric@anholt.net>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com> # vmwgfx
Reviewed-by: Lucas Stach <l.stach@pengutronix.de> #etnaviv
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/20170202210438.28702-1-chris@chris-wilson.co.uk
Start converting over from the byte count to its semantic macro, either
we want to allocate the size of a physical page in main memory or we
want the size of a virtual page in the GTT. 4096 could mean either, but
PAGE_SIZE and I915_GTT_PAGE_SIZE are explicit and should help improve
code comprehension and future changes. In the future, we may want to use
variable GTT page sizes and so have the challenge of knowing which
hardcoded values were used to represent a physical page vs the virtual
page.
v2: Look for a few more 4096s to convert, discover IS_ALIGNED().
v3: 4096ul paranoia, make fence alignment a distinct value of 4096, keep
bdw stolen w/a as 4096 until we know better.
v4: Add asserts that i915_vma_insert() start/end are aligned to GTT page
sizes.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170110144734.26052-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Missed when rebasing patches, I failed to set ret to zero before
starting the unbind loop (which depends upon ret being zero).
Reported-by: Matthew Auld <matthew.william.auld@gmail.com>
Fixes: 9332f3b1b9 ("drm/i915: Combine loops within i915_gem_evict_something")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170105155940.10033-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Cc: <stable@vger.kernel.org> # v4.9+
Directly merge drm-misc into drm-intel since Dave is on vacation and
we need the various drm-misc patches (fb format rework, drm mm fixes,
selftest framework and others). Also pulled back -rc2 in first to
resync with drm-intel-fixes and make sure I can reuse the exact rerere
solutions from drm-tip for safety, and because I'm lazy.
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Using mm->color_adjust makes the eviction scanner much tricker since we
don't know the actual neighbours of the target hole until after it is
created (after scanning is complete). To work out whether we need to
evict the neighbours because they impact upon the hole, we have to then
check the hole afterwards - requiring an extra step in the user of the
eviction scanner when they apply color_adjust.
v2: Massage kerneldoc.
Signed-off-by: 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>
Link: http://patchwork.freedesktop.org/patch/msgid/20161222083641.2691-34-chris@chris-wilson.co.uk
Compute the minimal required hole during scan and only evict those nodes
that overlap. This enables us to reduce the number of nodes we need to
evict to the bare minimum.
Signed-off-by: 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>
Link: http://patchwork.freedesktop.org/patch/msgid/20161222083641.2691-31-chris@chris-wilson.co.uk
Doing the check is trivial (low cost in comparison to overall eviction)
and helps simplify the code.
Signed-off-by: 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>
Link: http://patchwork.freedesktop.org/patch/msgid/20161222083641.2691-29-chris@chris-wilson.co.uk
The scan state occupies a large proportion of the struct drm_mm and is
rarely used and only contains temporary state. That makes it suitable to
moving to its struct and onto the stack of the callers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[danvet: Fix up etnaviv to compile, was missing a BUG_ON.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Some object retain an extra pin whilst they are active (e.g. contexts).
This excludes them from being considered for eviction unless we idle the
GPU. If before we look at the active list, we retire beforehand we can
hopefully remove a few excess pins and reduce the amount of searching
required.
v2: Similar principle applies to evict_for_vma
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20161209150555.602-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Soft-pinning depends upon being able to check for availabilty of an
interval and evict overlapping object from a drm_mm range manager very
quickly. Currently it uses a linear list, and so performance is dire and
not suitable as a general replacement. Worse, the current code will oops
if it tries to evict an active buffer.
It also helps if the routine reports the correct error codes as expected
by its callers and emits a tracepoint upon use.
For posterity since the wrong patch was pushed (i.e. that missed these
key points and had known bugs), this is the changelog that should have
been on commit 506a8e87d8 ("drm/i915: Add soft-pinning API for
execbuffer"):
Userspace can pass in an offset that it presumes the object is located
at. The kernel will then do its utmost to fit the object into that
location. The assumption is that userspace is handling its own object
locations (for example along with full-ppgtt) and that the kernel will
rarely have to make space for the user's requests.
This extends the DRM_IOCTL_I915_GEM_EXECBUFFER2 to do the following:
* if the user supplies a virtual address via the execobject->offset
*and* sets the EXEC_OBJECT_PINNED flag in execobject->flags, then
that object is placed at that offset in the address space selected
by the context specifier in execbuffer.
* the location must be aligned to the GTT page size, 4096 bytes
* as the object is placed exactly as specified, it may be used by this
execbuffer call without relocations pointing to it
It may fail to do so if:
* EINVAL is returned if the object does not have a 4096 byte aligned
address
* the object conflicts with another pinned object (either pinned by
hardware in that address space, e.g. scanouts in the aliasing ppgtt)
or within the same batch.
EBUSY is returned if the location is pinned by hardware
EINVAL is returned if the location is already in use by the batch
* EINVAL is returned if the object conflicts with its own alignment (as meets
the hardware requirements) or if the placement of the object does not fit
within the address space
All other execbuffer errors apply.
Presence of this execbuf extension may be queried by passing
I915_PARAM_HAS_EXEC_SOFTPIN to DRM_IOCTL_I915_GETPARAM and checking for
a reported value of 1 (or greater).
v2: Combine the hole/adjusted-hole ENOSPC checks
v3: More color, more splitting, more blurb.
Fixes: 506a8e87d8 ("drm/i915: Add soft-pinning API for execbuffer")
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/20161205142941.21965-2-chris@chris-wilson.co.uk
99% of the time we access i915_address_space->dev we want the i915
device and not the drm device, so let's store the drm_i915_private
backpointer instead. The only real complication here are the inlines
in i915_vma.h where drm_i915_private is not yet defined and so we have
to choose an alternate path for our asserts.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161129095008.32622-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
With the infrastructure converted over to tracking multiple timelines in
the GEM API whilst preserving the efficiency of using a single execution
timeline internally, we can now assign a separate timeline to every
context with full-ppgtt.
v2: Add a comment to indicate the xfer between timelines upon submission.
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/20161028125858.23563-35-chris@chris-wilson.co.uk
We want to decouple RPM and struct_mutex, but currently RPM has to walk
the list of bound objects and remove userspace mmapping before we
suspend (otherwise userspace may continue to access the GTT whilst it is
powered down). This currently requires the struct_mutex to walk the
bound_list, but if we move that to a separate list and lock we can take
the first step towards removing the struct_mutex.
v2: Split runtime suspend unmapping vs regular unmapping, to make the
locking (and barriers) clearer. Add the object to the userfault_list
prior to inserting the first PTE, the race between add/revoke depends
upon struct_mutex for regular unmappings and rpm for runtime-suspend.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> #v1
Link: http://patchwork.freedesktop.org/patch/msgid/20161024124218.18252-1-chris@chris-wilson.co.uk
With the possibility of addition of many more number of rings in future,
the drm_i915_private structure could bloat as an array, of type
intel_engine_cs, is embedded inside it.
struct intel_engine_cs engine[I915_NUM_ENGINES];
Though this is still fine as generally there is only a single instance of
drm_i915_private structure used, but not all of the possible rings would be
enabled or active on most of the platforms. Some memory can be saved by
allocating intel_engine_cs structure only for the enabled/active engines.
Currently the engine/ring ID is kept static and dev_priv->engine[] is simply
indexed using the enums defined in intel_engine_id.
To save memory and continue using the static engine/ring IDs, 'engine' is
defined as an array of pointers.
struct intel_engine_cs *engine[I915_NUM_ENGINES];
dev_priv->engine[engine_ID] will be NULL for disabled engine instances.
There is a text size reduction of 928 bytes, from 1028200 to 1027272, for
i915.o file (but for i915.ko file text size remain same as 1193131 bytes).
v2:
- Remove the engine iterator field added in drm_i915_private structure,
instead pass a local iterator variable to the for_each_engine**
macros. (Chris)
- Do away with intel_engine_initialized() and instead directly use the
NULL pointer check on engine pointer. (Chris)
v3:
- Remove for_each_engine_id() macro, as the updated macro for_each_engine()
can be used in place of it. (Chris)
- Protect the access to Render engine Fault register with a NULL check, as
engine specific init is done later in Driver load sequence.
v4:
- Use !!dev_priv->engine[VCS] style for the engine check in getparam. (Chris)
- Kill the superfluous init_engine_lists().
v5:
- Cleanup the intel_engines_init() & intel_engines_setup(), with respect to
allocation of intel_engine_cs structure. (Chris)
v6:
- Rebase.
v7:
- Optimize the for_each_engine_masked() macro. (Chris)
- Change the type of 'iter' local variable to enum intel_engine_id. (Chris)
- Rebase.
v8: Rebase.
v9: Rebase.
v10:
- For index calculation use engine ID instead of pointer based arithmetic in
intel_engine_sync_index() as engine pointers are not contiguous now (Chris)
- For appropriateness, rename local enum variable 'iter' to 'id'. (Joonas)
- Use for_each_engine macro for cleanup in intel_engines_init() and remove
check for NULL engine pointer in cleanup() routines. (Joonas)
v11: Rebase.
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Akash Goel <akash.goel@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1476378888-7372-1-git-send-email-akash.goel@intel.com
In the next patch we want to handle reset directly by a locked waiter in
order to avoid issues with returning before the reset is handled. To
handle the reset, we must first know whether we hold the struct_mutex.
If we do not hold the struct_mtuex we can not perform the reset, but we do
not block the reset worker either (and so we can just continue to wait for
request completion) - otherwise we must relinquish the mutex.
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/20160909131201.16673-10-chris@chris-wilson.co.uk
Often times we do not want to evict mapped objects from the GGTT as
these are quite expensive to teardown and frequently reused (causing an
equally, if not more so, expensive setup). In particular, when faulting
in a new object we want to avoid evicting an active object, or else we
may trigger a page-fault-of-doom as we ping-pong between evicting two
objects.
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/20160818161718.27187-26-chris@chris-wilson.co.uk
The principal motivation for this was to try and eliminate the
struct_mutex from i915_gem_suspend - but we still need to hold the mutex
current for the i915_gem_context_lost(). (The issue there is that there
may be an indirect lockdep cycle between cpu_hotplug (i.e. suspend) and
struct_mutex via the stop_machine().) For the moment, enabling last
request tracking for the engine, allows us to do busyness checking and
waiting without requiring the struct_mutex - which is useful in its own
right.
As a side-effect of having a robust means for tracking engine busyness,
we can replace our other busyness heuristic, that of comparing against
the last submitted seqno. For paranoid reasons, we have a semi-ordered
check of that seqno inside the hangchecker, which we can now improve to
an ordered check of the engine's busyness (removing a locked xchg in the
process).
v2: Pass along "bool interruptible" as being unlocked we cannot rely on
i915->mm.interruptible being stable or even under our control.
v3: Replace check Ironlake i915_gpu_busy() with the common precalculated value
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/1470388464-28458-6-git-send-email-chris@chris-wilson.co.uk
This is not the full fix, as we are required to percolate the u64 nature
down through the drm_mm stack, but this is required now to prevent
explosions due to mismatch between execbuf (eb_vma_misplaced) and vma
binding (i915_vma_misplaced) - and reduces the risk of spurious changes
as we adjust the vma interface in the next patches.
v2: long long casts not required for u64 printk (%llx)
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/1470324762-2545-6-git-send-email-chris@chris-wilson.co.uk
Slight micro-optimise to produce combine loops so that gcc is able to
optimise the inner-loops concisely. Since we are reviewing the loops, we
can update the comments to describe the current state of affairs, in
particular the distinction between evicting from the global GTT (which
may contain untracked items and transient global pins) and the
per-process GTT.
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/1470324762-2545-1-git-send-email-chris@chris-wilson.co.uk
Chris Wilson