Previously we only accommodated having a vma pinned by a small number of
users, with the maximum being pinned for use by the display engine. As
such, we used a small bitfield only large enough to allow the vma to
be pinned twice (for back/front buffers) in each scanout plane. Keeping
the maximum permissible pin_count small allows us to quickly catch a
potential leak. However, as we want to split a 4096B page into 64
different cachelines and pin each cacheline for use by a different
timeline, we will exceed the current maximum permissible vma->pin_count
and so time has come to enlarge it.
Whilst we are here, try to pull together the similar bits:
Address/layout specification:
- bias, mappable, zone_4g: address limit specifiers
- fixed: address override, limits still apply though
- high: not strictly an address limit, but an address direction to search
Search controls:
- nonblock, nonfault, noevict
v2: Rewrite the guideline comment on bit consumption.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: John Harrison <john.C.Harrison@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190128181812.22804-2-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
Now that the submission backends are controlled via their own spinlocks,
with a wave of a magic wand we can lift the struct_mutex requirement
around GPU reset. That is we allow the submission frontend (userspace)
to keep on submitting while we process the GPU reset as we can suspend
the backend independently.
The major change is around the backoff/handoff strategy for performing
the reset. With no mutex deadlock, we no longer have to coordinate with
any waiter, and just perform the reset immediately.
Testcase: igt/gem_mmap_gtt/hang # regresses
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/20190125132230.22221-3-chris@chris-wilson.co.uk
So far we have been relying on vm->file pointer being NULL to declare
something GGTT.
This has the unfortunate consequence that the default kernel context is
also declared GGTT and interferes with the following patch which wants to
instantiate VMA's and execute requests against the kernel context.
Change the is_ggtt test to use an explicit flag in struct address_space to
solve this issue.
Note that the bit used is free since there is an alignment hole in the
struct.
v2:
* Mark mock ggtt.
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: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180831143643.12366-1-tvrtko.ursulin@linux.intel.com
Removing the pin bias from GuC allows us to not check for GuC every time
we pin a context, which fixes the assertion error on unresolved GuC
platform default in mock contexts selftest.
It also seems that we were using uninitialized WOPCM variables when
setting the GuC pin bias. The pin bias has to be set after the WOPCM,
but before the call to i915_gem_contexts_init where the first contexts
are pinned.
v2:
This also makes it so that there's no need to set GuC variables from
within the WOPCM init function or to move the WOPCM init, while keeping
the correct initialization order. Also for mock tests the pin bias is
left at 0 and we make sure that the pin bias with GuC will not be
smaller than without GuC.
v3:
Avoid unused i915 in intel_guc_ggtt_offset if debug is disabled.
v4:
Squash with WOPCM init reordering.
Moved the i915_ggtt_pin_bias helper to this patch, and made some
functions use it instead of directly dereferencing i915->ggtt.
v5:
Since we now don't use wopcm.guc.base for the pin bias there's no need to
validate it. It also has already been verified in WOPCM init.
v6:
Deleted the now unnecessarily introduced includes from previous versions.
Dropped naming changes from dev_priv to i915 for better patch readability.
v7:
Changed some comments to make more sense in the context they're in.
v8:
Moved and renamed the function which now returns the wopcm.guc.size to
intel_guc.c:intel_guc_reserved_gtt_size to avoid any possible confusion
with the pin_bias in ggtt, which should be used for pinning.
Fixed patch not applying or the most recent upstream.
Fixes: f7dc0157e4 ("drm/i915/uc: Fetch GuC/HuC firmwares from guc/huc specific init")
Testcase: igt/drv_selftest/mock_contexts #GuC
Signed-off-by: Jakub Bartmiński <jakub.bartminski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180727141148.30874-3-jakub.bartminski@intel.com
Add a mutex into struct i915_address_space to be used while operating on
the vma and their lists for a particular vm. As this may be called from
the shrinker, we taint the mutex with fs_reclaim so that from the start
lockdep warns us if we are caught holding the mutex across an
allocation. (With such small steps we will eventually rid ourselves of
struct_mutex recursion!)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711073608.20286-2-chris@chris-wilson.co.uk
Currently, the wc-stash used for providing flushed WC pages ready for
constructing the page directories is assumed to be protected by the
struct_mutex. However, we want to remove this global lock and so must
install a replacement global lock for accessing the global wc-stash (the
per-vm stash continues to be guarded by the vm).
We need to push ahead on this patch due to an oversight in hastily
removing the struct_mutex guard around the igt_ppgtt_alloc selftest. No
matter, it will prove very useful (i.e. will be required) in the near
future.
v2: Restore the onstack stash so that we can drop the vm->mutex in
future across the allocation.
v3: Restore the lost pagevec_init of the onstack allocation, and repaint
function names.
v4: Reorder init so that we don't try and use i915_address_space before
it is ininitialised.
Fixes: 1f6f00238a ("drm/i915/selftests: Drop struct_mutex around lowlevel pggtt allocation")
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/20180704185518.4193-1-chris@chris-wilson.co.uk
The discovery with trying to enable full-ppgtt was that we were
completely failing to the load both the mm and context following the
reset. Although we were performing mmio to set the PP_DIR (per-process
GTT) and CCID (context), these were taking no effect (the assumption was
that this would trigger reload of the context and restore the page
tables). It was not until we performed the LRI + MI_SET_CONTEXT in a
following context switch would anything occur.
Since we are then required to reset the context image and PP_DIR using
CS commands, we place those commands into every batch. The hardware
should recognise the no-ops and eliminate the expensive context loads,
but we still have to pay the cost of using cross-powerwell register
writes. In practice, this has no effect on actual context switch times,
and only adds a few hundred nanoseconds to no-op switches. We can improve
the latter by eliminating the w/a around known no-op switches, but there
is an ulterior motive to keeping them.
Always emitting the context switch at the beginning of the request (and
relying on HW to skip unneeded switches) does have one key advantage.
Should we implement request reordering on Haswell, we will not know in
advance what the previous executing context was on the GPU and so we
would not be able to elide the MI_SET_CONTEXT commands ourselves and
always have to emit them. Having our hand forced now actually prepares
us for later.
Now since that context and mm follow the request, we no longer (and not
for a long time since requests took over!) require a trace point to tell
when we write the switch into the ring, since it is always. (This is
even more important when you remember that simply writing into the ring
bears no relation to the current mm.)
v2: Sandybridge has to agree to use LRI as well.
Testcase: igt/drv_selftests/live_hangcheck
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: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611110845.31890-1-chris@chris-wilson.co.uk
We need to move to a more flexible timeline that doesn't assume one
fence context per engine, and so allow for a single timeline to be used
across a combination of engines. This means that preallocating a fence
context per engine is now a hindrance, and so we want to introduce the
singular timeline. From the code perspective, this has the notable
advantage of clearing up a lot of mirky semantics and some clumsy
pointer chasing.
By splitting the timeline up into a single entity rather than an array
of per-engine timelines, we can realise the goal of the previous patch
of tracking the timeline alongside the ring.
v2: Tweak wait_for_idle to stop the compiling thinking that ret may be
uninitialised.
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/20180502163839.3248-2-chris@chris-wilson.co.uk
In the future, we want to move a request between engines. To achieve
this, we first realise that we have two timelines in effect here. The
first runs through the GTT is required for ordering vma access, which is
tracked currently by engine. The second is implied by sequential
execution of commands inside the ringbuffer. This timeline is one that
maps to userspace's expectations when submitting requests (i.e. given the
same context, batch A is executed before batch B). As the rings's
timelines map to userspace and the GTT timeline an implementation
detail, move the timeline from the GTT into the ring itself (per-context
in logical-ring-contexts/execlists, or a global per-engine timeline for
the shared ringbuffers in legacy submission.
The two timelines are still assumed to be equivalent at the moment (no
migrating requests between engines yet) and so we can simply move from
one to the other without adding extra ordering.
v2: Reinforce that one isn't allowed to mix the engine execution
timeline with the client timeline from userspace (on the ring).
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/20180502163839.3248-1-chris@chris-wilson.co.uk
The private PAT management is to support PPAT entry manipulation. Two
APIs are introduced for dynamically managing PPAT entries: intel_ppat_get
and intel_ppat_put.
intel_ppat_get will search for an existing PPAT entry which perfectly
matches the required PPAT value. If not, it will try to allocate a new
entry if there is any available PPAT indexs, or return a partially
matched PPAT entry if there is no available PPAT indexes.
intel_ppat_put will put back the PPAT entry which comes from
intel_ppat_get. If it's dynamically allocated, the reference count will
be decreased. If the reference count turns into zero, the PPAT index is
freed again.
Besides, another two callbacks are introduced to support the private PAT
management framework. One is ppat->update_hw(), which writes the PPAT
configurations in ppat->entries into HW. Another one is ppat->match, which
will return a score to show how two PPAT values match with each other.
v17:
- Refine the comparision of score of BDW. (Joonas)
v16:
- Fix a bug in PPAT match function of BDW. (Joonas)
v15:
- Refine some code flow. (Joonas)
v12:
- Fix a problem "not returning the entry of best score". (Zhenyu)
v7:
- Keep all the register writes unchanged in this patch. (Joonas)
v6:
- Address all comments from Chris:
http://www.spinics.net/lists/intel-gfx/msg136850.html
- Address all comments from Joonas:
http://www.spinics.net/lists/intel-gfx/msg136845.html
v5:
- Add check and warnnings for those platforms which don't have PPAT.
v3:
- Introduce dirty bitmap for PPAT registers. (Chris)
- Change the name of the pointer "dev_priv" to "i915". (Chris)
- intel_ppat_{get, put} returns/takes a const intel_ppat_entry *. (Chris)
v2:
- API re-design. (Chris)
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@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> #v7
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[Joonas: Use BIT() in the enum in bdw_private_pat_match]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505392783-4084-1-git-send-email-zhi.a.wang@intel.com
When choosing a slot for an execbuffer, we ideally want to use the same
address as last time (so that we don't have to rebind it) and the same
address as expected by the user (so that we don't have to fixup any
relocations pointing to it). If we first try to bind the incoming
execbuffer->offset from the user, or the currently bound offset that
should hopefully achieve the goal of avoiding the rebind cost and the
relocation penalty. However, if the object is not currently bound there
we don't want to arbitrarily unbind an object in our chosen position and
so choose to rebind/relocate the incoming object instead. After we
report the new position back to the user, on the next pass the
relocations should have settled down.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtien@linux.intel.com>
I915_GEM_GET_APERTURE ioctl is used to probe aperture size from userspace.
In gvt environment, each vm only use the ballooned part of aperture, so we
should return the correct available aperture size exclude the reserved part
by balloon.
v2: add 'reserved' in struct i915_address_space to record the reserved size
in ggtt (Chris)
v3: remain aper_size as total, adjust aper_available_size exclude reserved
and pinned. UMD driver need to adjust the max allocation size according to
the available aperture size but not total size. KMD return the correct
usable aperture size any time (Chris, Joonas)
v4: decrease reserved in deballoon (Joonas)
v5: add onion teardown in balloon, add vgt_deballoon_space (Joonas)
v6: change title name (Zhenyu)
v7: code style refine (Joonas)
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Weinan Li <weinan.z.li@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1496198152-14175-1-git-send-email-weinan.z.li@intel.com
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
