Use IOMEM_ERR_PTR() instead of self defined IO_ERR_PTR().
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220503144937.679424-1-tvrtko.ursulin@linux.intel.com

Now that i915_vma_parked() is taking the object lock on vma destruction,
and the only user of the vma refcount, i915_gem_object_unbind()
also takes the object lock, remove the vma refcount.

v3: Documentation update.
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220304082641.308069-3-thomas.hellstrom@linux.intel.com

It's unclear what reference the initial vma kref reference refers to.
A vma can have multiple weak references, the object vma list,
the vm's bound list and the GT's closed_list, and the initial vma
reference can be put from lookups of all these lists.

With the current implementation this means
that any holder of yet another vma refcount (currently only
i915_gem_object_unbind()) needs to be holding two of either
*) An object refcount,
*) A vm open count
*) A vma open count

in order for us to not risk leaking a reference by having the
initial vma reference being put twice.

Address this by re-introducing i915_vma_destroy() which removes all
weak references of the vma and *then* puts the initial vma refcount.
This makes a strong vma reference hold on to the vma unconditionally.

Perhaps a better name would be i915_vma_revoke() or i915_vma_zombify(),
since other callers may still hold a refcount, but with the prospect of
being able to replace the vma refcount with the object lock in the near
future, let's stick with i915_vma_destroy().

Finally this commit fixes a race in that previously i915_vma_release() and
now i915_vma_destroy() could destroy a vma without taking the vm->mutex
after an advisory check that the vma mm_node was not allocated.
This would race with the ungrab_vma() function creating a trace similar
to the below one. This was fixed in one of the __i915_vma_put() callsites
in
commit bc1922e5 ("drm/i915: Fix a race between vma / object destruction and unbinding")
but although not seemingly triggered by CI, that
is not sufficient. This patch is needed to fix that properly.

[823.012188] Console: switching to colour dummy device 80x25
[823.012422] [IGT] gem_ppgtt: executing
[823.016667] [IGT] gem_ppgtt: starting subtest blt-vs-render-ctx0
[852.436465] stack segment: 0000 [#1] PREEMPT SMP NOPTI
[852.436480] CPU: 0 PID: 3200 Comm: gem_ppgtt Not tainted 5.16.0-CI-CI_DRM_11115+ #1
[852.436489] Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-P DDR5 RVP, BIOS ADLPFWI1.R00.2422.A00.2110131104 10/13/2021
[852.436499] RIP: 0010:ungrab_vma+0x9/0x80 [i915]
[852.436711] Code: ef e8 4b 85 cf e0 e8 36 a3 d6 e0 8b 83 f8 9c 00 00 85 c0 75 e1 5b 5d 41 5c 41 5d c3 e9 d6 fd 14 00 55 53 48 8b af c0 00 00 00 <8b> 45 00 85 c0 75 03 5b 5d c3 48 8b 85 a0 02 00 00 48 89 fb 48 8b
[852.436727] RSP: 0018:ffffc90006db7880 EFLAGS: 00010246
[852.436734] RAX: 0000000000000000 RBX: ffffc90006db7598 RCX: 0000000000000000
[852.436742] RDX: ffff88815349e898 RSI: ffff88815349e858 RDI: ffff88810a284140
[852.436748] RBP: 6b6b6b6b6b6b6b6b R08: ffff88815349e898 R09: ffff88815349e8e8
[852.436754] R10: 0000000000000001 R11: 0000000051ef1141 R12: ffff88810a284140
[852.436762] R13: 0000000000000000 R14: ffff88815349e868 R15: ffff88810a284458
[852.436770] FS:  00007f5c04b04e40(0000) GS:ffff88849f000000(0000) knlGS:0000000000000000
[852.436781] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[852.436788] CR2: 00007f5c04b38fe0 CR3: 000000010a6e8001 CR4: 0000000000770ef0
[852.436797] PKRU: 55555554
[852.436801] Call Trace:
[852.436806]  <TASK>
[852.436811]  i915_gem_evict_for_node+0x33c/0x3c0 [i915]
[852.437014]  i915_gem_gtt_reserve+0x106/0x130 [i915]
[852.437211]  i915_vma_pin_ww+0x8f4/0xb60 [i915]
[852.437412]  eb_validate_vmas+0x688/0x860 [i915]
[852.437596]  i915_gem_do_execbuffer+0xc0e/0x25b0 [i915]
[852.437770]  ? deactivate_slab+0x5f2/0x7d0
[852.437778]  ? _raw_spin_unlock_irqrestore+0x50/0x60
[852.437789]  ? i915_gem_execbuffer2_ioctl+0xc6/0x2c0 [i915]
[852.437944]  ? init_object+0x49/0x80
[852.437950]  ? __lock_acquire+0x5e6/0x2580
[852.437963]  i915_gem_execbuffer2_ioctl+0x116/0x2c0 [i915]
[852.438129]  ? i915_gem_do_execbuffer+0x25b0/0x25b0 [i915]
[852.438300]  drm_ioctl_kernel+0xac/0x140
[852.438310]  drm_ioctl+0x201/0x3d0
[852.438316]  ? i915_gem_do_execbuffer+0x25b0/0x25b0 [i915]
[852.438490]  __x64_sys_ioctl+0x6a/0xa0
[852.438498]  do_syscall_64+0x37/0xb0
[852.438507]  entry_SYSCALL_64_after_hwframe+0x44/0xae
[852.438515] RIP: 0033:0x7f5c0415b317
[852.438523] Code: b3 66 90 48 8b 05 71 4b 2d 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 41 4b 2d 00 f7 d8 64 89 01 48
[852.438542] RSP: 002b:00007ffd765039a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
[852.438553] RAX: ffffffffffffffda RBX: 000055e4d7829dd0 RCX: 00007f5c0415b317
[852.438562] RDX: 00007ffd76503a00 RSI: 00000000c0406469 RDI: 0000000000000017
[852.438571] RBP: 00007ffd76503a00 R08: 0000000000000000 R09: 0000000000000081
[852.438579] R10: 00000000ffffff7f R11: 0000000000000246 R12: 00000000c0406469
[852.438587] R13: 0000000000000017 R14: 00007ffd76503a00 R15: 0000000000000000
[852.438598]  </TASK>
[852.438602] Modules linked in: snd_hda_codec_hdmi i915 mei_hdcp x86_pkg_temp_thermal snd_hda_intel snd_intel_dspcfg drm_buddy coretemp crct10dif_pclmul crc32_pclmul snd_hda_codec ttm ghash_clmulni_intel snd_hwdep snd_hda_core e1000e drm_dp_helper ptp snd_pcm mei_me drm_kms_helper pps_core mei syscopyarea sysfillrect sysimgblt fb_sys_fops prime_numbers intel_lpss_pci smsc75xx usbnet mii
[852.440310] ---[ end trace e52cdd2fe4fd911c ]---

v2: Fix typos in the commit message.

Fixes: 7e00897b ("drm/i915: Add object locking to i915_gem_evict_for_node and i915_gem_evict_something, v2.")
Fixes: bc1922e5 ("drm/i915: Fix a race between vma / object destruction and unbinding")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220222133209.587978-1-thomas.hellstrom@linux.intel.com

We want to remove more members of i915_vma, which requires the locking to
be held more often.

Start requiring gem object lock for i915_vma_unbind, as it's one of the
callers that may unpin pages.

Some special care is needed when evicting, because the last reference to
the object may be held by the VMA, so after __i915_vma_unbind, vma may be
garbage, and we need to cache vma->obj before unlocking.

Changes since v1:
- Make trylock failing a WARN. (Matt)
- Remove double i915_vma_wait_for_bind() (Matt)
- Move atomic_set to right before mutex_unlock(), to make it more clear
  they belong together. (Matt)
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220114132320.109030-5-maarten.lankhorst@linux.intel.com

Implement async (non-blocking) unbinding by not syncing the vma before
calling unbind on the vma_resource.
Add the resulting unbind fence to the object's dma_resv from where it is
picked up by the ttm migration code.
Ideally these unbind fences should be coalesced with the migration blit
fence to avoid stalling the migration blit waiting for unbind, as they
can certainly go on in parallel, but since we don't yet have a
reasonable data structure to use to coalesce fences and attach the
resulting fence to a timeline, we defer that for now.

Note that with async unbinding, even while the unbind waits for the
preceding bind to complete before unbinding, the vma itself might have been
destroyed in the process, clearing the vma pages. Therefore we can
only allow async unbinding if we have a refcounted sg-list and keep a
refcount on that for the vma resource pages to stay intact until
binding occurs. If this condition is not met, a request for an async
unbind is diverted to a sync unbind.

v2:
- Use a separate kmem_cache for vma resources for now to isolate their
  memory allocation and aid debugging.
- Move the check for vm closed to the actual unbinding thread. Regardless
  of whether the vm is closed, we need the unbind fence to properly wait
  for capture.
- Clear vma_res::vm on unbind and update its documentation.
v4:
- Take cache coloring into account when searching for vma resources
  pending unbind. (Matthew Auld)
v5:
- Fix timeout and error check in i915_vma_resource_bind_dep_await().
- Avoid taking a reference on the object for async binding if
  async unbind capable.
- Fix braces around a single-line if statement.
v6:
- Fix up the cache coloring adjustment. (Kernel test robot <lkp@intel.com>)
- Don't allow async unbinding if the vma_res pages are not the same as
  the object pages. (Matthew Auld)
v7:
- s/unsigned long/u64/ in a number of places (Matthew Auld)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220110172219.107131-5-thomas.hellstrom@linux.intel.com

When introducing asynchronous unbinding, the vma itself may no longer
be alive when the actual binding or unbinding takes place.

Update the gtt i915_vma_ops accordingly to take a struct i915_vma_resource
instead of a struct i915_vma for the bind_vma() and unbind_vma() ops.
Similarly change the insert_entries() op for struct i915_address_space.

Replace a couple of i915_vma_snapshot members with their newly introduced
i915_vma_resource counterparts, since they have the same lifetime.

Also make sure to avoid changing the struct i915_vma_flags (in particular
the bind flags) async. That should now only be done sync under the
vm mutex.

v2:
- Update the vma_res::bound_flags when binding to the aliased ggtt
v6:
- Remove I915_VMA_ALLOC_BIT (Matthew Auld)
- Change some members of struct i915_vma_resource from unsigned long to u64
  (Matthew Auld)
v7:
- Fix vma resource size parameters to be u64 rather than unsigned long
  (Matthew Auld)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220110172219.107131-3-thomas.hellstrom@linux.intel.com

Introduce vma resources, sort of similar to TTM resources,  needed for
asynchronous bind management. Initially we will use them to hold
completion of unbinding when we capture data from a vma, but they will
be used extensively in upcoming patches for asynchronous vma unbinding.

v6:
- Some documentation updates
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220110172219.107131-2-thomas.hellstrom@linux.intel.com

Big delta, but boils down to moving set_pages to i915_vma.c, and removing
the special handling, all callers use the defaults anyway. We only remap
in ggtt, so default case will fall through.

Because we still don't require locking in i915_vma_unpin(), handle this by
using xchg in get_pages(), as it's locked with obj->mutex, and cmpxchg in
unpin, which only fails if we race a against a new pin.

Changes since v1:
- aliasing gtt sets ZERO_SIZE_PTR, not -ENODEV, remove special case
  from __i915_vma_get_pages(). (Matt)
Changes since v2:
- Free correct old pages in __i915_vma_get_pages(). (Matt)
  Remove race of clearing vma->pages accidentally from put,
  free it but leave it set, as only get has the lock.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211216142749.1966107-4-maarten.lankhorst@linux.intel.comReviewed-by: Matthew Auld <matthew.auld@intel.com>

When reworking the code to move the eviction fence to the object,
the best code is removed code.

Remove some functions that are unused, and change the function definition
if it's only used in 1 place.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
[mlankhorst: Remove new use of i915_active_has_exclusive]
Link: https://patchwork.freedesktop.org/patch/msgid/20211216142749.1966107-2-maarten.lankhorst@linux.intel.com

It's just an alias to vma->obj->base.resv, no need to duplicate it.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211117142024.1043017-5-matthew.auld@intel.com

vma->obj and vma->resv are now never NULL, and some checks can be removed.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211117142024.1043017-4-matthew.auld@intel.com

Allow multiple batch buffers to be submitted in a single execbuf IOCTL
after a context has been configured with the 'set_parallel' extension.
The number batches is implicit based on the contexts configuration.

This is implemented with a series of loops. First a loop is used to find
all the batches, a loop to pin all the HW contexts, a loop to create all
the requests, a loop to submit (emit BB start, etc...) all the requests,
a loop to tie the requests to the VMAs they touch, and finally a loop to
commit the requests to the backend.

A composite fence is also created for the generated requests to return
to the user and to stick in dma resv slots.

No behavior from the existing IOCTL should be changed aside from when
throttling because the ring for a context is full. In this situation,
i915 will now wait while holding the object locks. This change was done
because the code is much simpler to wait while holding the locks and we
believe there isn't a huge benefit of dropping these locks. If this
proves false we can restructure the code to drop the locks during the
wait.

IGT: https://patchwork.freedesktop.org/patch/447008/?series=93071&rev=1
media UMD: https://github.com/intel/media-driver/pull/1252

v2:
 (Matthew Brost)
  - Return proper error value if i915_request_create fails
v3:
 (John Harrison)
  - Add comment explaining create / add order loops + locking
  - Update commit message explaining different in IOCTL behavior
  - Line wrap some comments
  - eb_add_request returns void
  - Return -EINVAL rather triggering BUG_ON if cmd parser used
 (Checkpatch)
  - Check eb->batch_len[*current_batch]
v4:
 (CI)
  - Set batch len if passed if via execbuf args
  - Call __i915_request_skip after __i915_request_commit
 (Kernel test robot)
  - Initialize rq to NULL in eb_pin_timeline
v5:
 (John Harrison)
  - Fix typo in comments near bb order loops
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211014172005.27155-21-matthew.brost@intel.com

With the global kmem_cache shrink infrastructure gone there's nothing
special and we can convert them over.

I'm doing this split up into each patch because there's quite a bit of
noise with removing the static global.slab_vmas to just a
slab_vmas.

We have to keep i915_drv.h include in i915_globals otherwise there's
nothing anymore that pulls in GEM_BUG_ON.

v2: Make slab static (Jason, 0day)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-9-daniel.vetter@ffwll.ch

Generic helpers should be placed in i915_utils.h.
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210603051630.2635-9-matthew.brost@intel.com

Similarly to GGTT VMAs, DPT VMAs can be also a remapped or rotated view
of the mapped object, so make sure we debug print the details for these
views as well besides the normal view.

While at it also fix the debug print for the VMA type of DPT VMAs.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210524172703.2113058-3-imre.deak@intel.com

An object mapped via DPT can have remapped and rotated VMA instances
besides the normal VMA instance, similarly to GGTT VMA instances.
Adjust the corresponding VMA lookup asserts.

While at it also check if a DPT VM is passed incorrectly to
i915_vm_to_ppgtt().
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210524172703.2113058-2-imre.deak@intel.com

We previously complained when ww == NULL.

This function is now only used in selftests to pin an object,
and ww locking is now fixed.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
[danvet: Resolve conflict because we don't have a set-domain refactor,
see
https://lore.kernel.org/intel-gfx/20210203090205.25818-8-chris@chris-wilson.co.uk/

The really worrying thing here is that the above patch had a change in
arguments for i915_gem_object_set_to_gtt_domain(), without any
explanation. I decided to just faithfully apply Maarten's change but
not the argument change which was in Maarten's context diff.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210323155059.628690-26-maarten.lankhorst@linux.intel.com

As soon as we install fences, we should stop allocating memory
in order to prevent any potential deadlocks.

This is required later on, when we start adding support for
dma-fence annotations.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210323155059.628690-11-maarten.lankhorst@linux.intel.com

Currently we have a lot of places where we hold the gem object lock,
but haven't yet been converted to the ww dance. Complain loudly about
those places.

i915_vma_pin shouldn't have the obj lock held, so we can do a ww dance,
while i915_vma_pin_ww should.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com> #irc
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210323155059.628690-6-maarten.lankhorst@linux.intel.com

In the shrinker, we protect framebuffers from light reclaim as we
typically expect framebuffers to be reused in the near future (and with
low latency requirements). We can apply the same logic to the GGTT
eviction and defer framebuffers to the second pass only used if the
caller is desperate enough to wait for space to become available.
In most cases, the caller will use a smaller partial vma instead of
trying to force the object into the GGTT if doing so will cause other
users to be evicted.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210119214336.1463-5-chris@chris-wilson.co.uk

As a preparation step for full object locking and wait/wound handling
during pin and object mapping, ensure that we always pass the ww context
in i915_gem_execbuffer.c to i915_vma_pin, use lockdep to ensure this
happens.

This also requires changing the order of eb_parse slightly, to ensure
we pass ww at a point where we could still handle -EDEADLK safely.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-15-maarten.lankhorst@linux.intel.comSigned-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

Across suspend/resume, we clear the entire GGTT and rebuild from
scratch. In particular, we want to only preserve the global entries for
use by the HW, and delay reinstating the local binds until required by
the user. This means that we can evict any local binds in the global GTT,
saving any time in preserving their state, as they will be rebound on
demand.

References: https://gitlab.freedesktop.org/drm/intel/-/issues/1947Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200528082427.21402-2-chris@chris-wilson.co.uk

If we must revoke the fence because the VMA is no longer present, or
because the fence no longer applies, ensure that we do and convert it
into an error if we try but cannot.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200401210104.15907-3-chris@chris-wilson.co.uk

Since the number of fence regs can vary dramactically between platforms,
allocate the array on demand so we don't waste as much space.
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/20200316113846.4974-4-chris@chris-wilson.co.uk

Since the fence registers control HW detiling through the GGTT
aperture, make them a part of the intel_ggtt under gt/
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/20200316113846.4974-1-chris@chris-wilson.co.uk

On Braswell and Broxton (also known as Valleyview and Apollolake), we
need to serialise updates of the GGTT using the big stop_machine()
hammer. This has the side effect of appearing to lockdep as a possible
reclaim (since it uses the cpuhp mutex and that is tainted by per-cpu
allocations). However, we want to use vm->mutex (including ggtt->mutex)
from within the shrinker and so must avoid such possible taints. For this
purpose, we introduced the asynchronous vma binding and we can apply it
to the PIN_GLOBAL so long as take care to add the necessary waits for
the worker afterwards.

Closes: https://gitlab.freedesktop.org/drm/intel/issues/211Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200130181710.2030251-3-chris@chris-wilson.co.uk

Attempt to split i915_gem_gtt.[ch] into more manageable chunks.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Matthew Auld <matthew.auld@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/20200107134009.3255354-1-chris@chris-wilson.co.uk

Start introducing a kref on i915_vma in order to protect the vma unbind
(i915_gem_object_unbind) from a parallel destruction (i915_vma_parked).
Later, we will use the refcount to manage all access and turn i915_vma
into a first class container.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Acked-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191222210256.2066451-2-chris@chris-wilson.co.uk

It is not acceptable for context pinning to fail with -ENOSPC as we
should always be able to make space in the GGTT. The only reason we may
fail is that other "temporary" context pins are reserving their space
and we need to wait for an available slot.

Closes: https://gitlab.freedesktop.org/drm/intel/issues/676Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205113726.413351-2-chris@chris-wilson.co.uk

This is really just an alias of mmap_gtt. The 'mmap offset' nomenclature
comes from the value returned by this ioctl which is the offset into the
device fd which userpace uses with mmap(2).

mmap_gtt was our initial mmap_offset implementation, this extends
our CPU mmap support to allow additional fault handlers that depends on
the object's backing pages.

Note that we multiplex mmap_gtt and mmap_offset through the same ioctl,
and use the zero extending behaviour of drm to differentiate between
them, when we inspect the flags.

To support multiple mmap types on an object we need to support multiple
mmap_offsets for an object (each offset in the global device address
space corresponding to a unique instance of the object for a file + mmap
type). As we drop the simplified drm core idea of a single mmap_offset,
we need to provide replacement hooks for the dumb mmap interface as
well.

Link: https://gitlab.freedesktop.org/mesa/mesa/merge_requests/1675
Testcase: igt/gem_mmap_offset
Signed-off-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Signed-off-by: Matthew Auld <matthew.auld@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/20191204120032.3682839-1-chris@chris-wilson.co.uk

Currently even though i915_vma_parked() operates on a per-gt struct, it
is called from a global pm notify. This oddity was only because the long
term plan is to decouple the vma cache from the pm notification, but
right now the oddity stands out like a sore thumb!
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@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>
Link: https://patchwork.freedesktop.org/patch/msgid/20191021183236.21790-1-chris@chris-wilson.co.uk

Replace the struct_mutex requirement for pinning the i915_vma with the
local vm->mutex instead. Note that the vm->mutex is tainted by the
shrinker (we require unbinding from inside fs-reclaim) and so we cannot
allocate while holding that mutex. Instead we have to preallocate
workers to do allocate and apply the PTE updates after we have we
reserved their slot in the drm_mm (using fences to order the PTE writes
with the GPU work and with later unbind).

In adding the asynchronous vma binding, one subtle requirement is to
avoid coupling the binding fence into the backing object->resv. That is
the asynchronous binding only applies to the vma timeline itself and not
to the pages as that is a more global timeline (the binding of one vma
does not need to be ordered with another vma, nor does the implicit GEM
fencing depend on a vma, only on writes to the backing store). Keeping
the vma binding distinct from the backing store timelines is verified by
a number of async gem_exec_fence and gem_exec_schedule tests. The way we
do this is quite simple, we keep the fence for the vma binding separate
and only wait on it as required, and never add it to the obj->resv
itself.

Another consequence in reducing the locking around the vma is the
destruction of the vma is no longer globally serialised by struct_mutex.
A natural solution would be to add a kref to i915_vma, but that requires
decoupling the reference cycles, possibly by introducing a new
i915_mm_pages object that is own by both obj->mm and vma->pages.
However, we have not taken that route due to the overshadowing lmem/ttm
discussions, and instead play a series of complicated games with
trylocks to (hopefully) ensure that only one destruction path is called!

v2: Add some commentary, and some helpers to reduce patch churn.
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/20191004134015.13204-4-chris@chris-wilson.co.uk

A subset of 71724f70 ("drm/mm: Use helpers for drm_mm_node booleans")
in order to prepare drm-intel-next-queued for subsequent patches before
we can backmerge 71724f70 itself.
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/20191004142226.13711-1-chris@chris-wilson.co.uk

In preparation for rearranging the booleans into a flags field, ensure
all the current users are using the inline helpers and not directly
accessing the members.
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/20191003210100.22250-3-chris@chris-wilson.co.uk

In preparation for reducing struct_mutex stranglehold around the vm,
make the vma.flags atomic so that we can acquire a pin on the vma
atomically before deciding if we need to take the mutex.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190911090243.16786-1-chris@chris-wilson.co.uk

Try to tidy up the cache-coloring such that we rid the code of any
mm.color_adjust assumptions, this should hopefully make it more obvious
in the code when we need to actually use the cache-level as the color,
and as a bonus should make adding a different color-scheme simpler.
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>
Cc: Rodrigo Vivi <rodrigo.vivi@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/20190909124052.22900-3-matthew.auld@intel.com

Export color_differs so that we can use it elsewhere.
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>
Cc: Rodrigo Vivi <rodrigo.vivi@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/20190909124052.22900-1-matthew.auld@intel.com

Avoid calling i915_vma_put_fence() by using our alternate paths that
bind a secondary vma avoiding the original fenced vma. For the few
instances where we need to release the fence (i.e. on binding when the
GGTT range becomes invalid), replace the put_fence with a revoke_fence.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190822061557.18402-1-chris@chris-wilson.co.uk

We can reduce the locking for fence registers from the dev->struct_mutex
to a local mutex. We could introduce a mutex for the sole purpose of
tracking the fence acquisition, except there is a little bit of overlap
with the fault tracking, so use the i915_ggtt.mutex as it covers both.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190822060914.2671-1-chris@chris-wilson.co.uk

Before we acquire the vma for GPU activity, ensure that the underlying
object is not already in the process of being freed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190820100531.8430-1-chris@chris-wilson.co.uk