| Age | Commit message (Collapse) | Author |
|---|
|
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.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Now that we changed execbuf submission slightly to allow us to do all
pinning in one place, we can now simply add ww versions on top of
struct_mutex. All we have to do is a separate path for -EDEADLK
handling, which needs to unpin all gem bo's before dropping the lock,
then starting over.
This finally allows us to do parallel submission, but because not
all of the pinning code uses the ww ctx yet, we cannot completely
drop struct_mutex yet.
Changes since v1:
- Keep struct_mutex for now. :(
Changes since v2:
- Make sure we always lock the ww context in slowpath.
Changes since v3:
- Don't call __eb_unreserve_vma in eb_move_to_gpu now; this can be
done on normal unlock path.
- Unconditionally release vmas and context.
Changes since v4:
- Rebased on top of struct_mutex reduction.
Changes since v5:
- Remove training wheels.
Changes since v6:
- Fix accidentally broken -ENOSPC handling.
Changes since v7:
- Handle gt buffer pool better.
Changes since v8:
- Properly clear variables, to make -EDEADLK handling not BUG.
Change since v9:
- Fix unpinning fence on pnv and below.
Changes since v10:
- Make relocation gpu chaining working again.
Changes since v11:
- Remove relocation chaining, pain to make it work.
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/20200819140904.1708856-9-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Execbuffer submission will perform its own WW locking, and we
cannot rely on the implicit lock there.
This also makes it clear that the GVT code will get a lockdep splat when
multiple batchbuffer shadows need to be performed in the same instance,
fix that up.
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-7-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
i915_gem_ww_ctx is used to lock all gem bo's for pinning and memory
eviction. We don't use it yet, but lets start adding the definition
first.
To use it, we have to pass a non-NULL ww to gem_object_lock, and don't
unlock directly. It is done in i915_gem_ww_ctx_fini.
Changes since v1:
- Change ww_ctx and obj order in locking functions (Jonas Lahtinen)
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/20200819140904.1708856-6-maarten.lankhorst@linux.intel.com
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
I915_GEM_THROTTLE dates back to the time before contexts where there was
just a single engine, and therefore a single timeline and request list
globally. That request list was in execution/retirement order, and so
walking it to find a particular aged request made sense and could be
split per file.
That is no more. We now have many timelines with a file, as many as the
user wants to construct (essentially per-engine, per-context). Each of
those run independently and so make the single list futile. Remove the
disordered list, and iterate over all the timelines to find a request to
wait on in each to satisfy the criteria that the CPU is no more than 20ms
ahead of its oldest request.
It should go without saying that the I915_GEM_THROTTLE ioctl is no
longer used as the primary means of throttling, so it makes sense to push
the complication into the ioctl where it only impacts upon its few
irregular users, rather than the execbuf/retire where everybody has to
pay the cost. Fortunately, the few users do not create vast amount of
contexts, so the loops over contexts/engines should be concise.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200728152010.30701-1-chris@chris-wilson.co.uk
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
If we find ourselves trying to reuse a misplaced but active vma, we
currently try to discard it to avoid having to wait to unbind it
(upsetting the current user fo the vma). An alternative to marking it as
a dicarded vma and keeping it in both the obj->vma.list and
obj->vma.tree, is to simply remove it from the lookup rbtree.
While it remains in the list of vma, it will be unbound under eviction
pressure and freed along with the object. We will never reuse it again
for new instances. As before, with no pruning, the list may continually
grow, but eventually we will have the most constrained version of the
ggtt view that meets all requirements -- so the list of vma should not
grow without bound.
Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/2012
Fixes: 9bdcaa5e3a2f ("drm/i915: Discard a misplaced GGTT vma")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200611180421.23262-1-chris@chris-wilson.co.uk
|
|
As a last minute addition, I added an assertion to make sure that the
new i915_vma view would be equal to the discard. However, the positive
encouragement from CI only goes to show that we rarely take this path,
and it wasn't until the post-merge run did we hit the assert -- because
it compared the wrong view. Fixup the copy'n'paste error and compare
against both the old view and the expected new view.
Fixes: 9bdcaa5e3a2f ("drm/i915: Discard a misplaced GGTT vma")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200605184844.24644-1-chris@chris-wilson.co.uk
|
|
Across the many users of the GGTT vma (internal objects, mmapings,
display etc), we may end up with conflicting requirements for the
placement. Currently, we try to resolve the conflict by unbinding the
vma and rebinding it to match the new constraints; over time we will end
up with a GGTT that matches the most strict constraints over all
concurrent users. However, this causes a problem if the vma is currently
in use as we must wait until it is idle before moving it. But there is
no restriction on the number of views we may use (apart from the limited
size of the GGTT itself), and so if the active vma does not meet our
requirements, try and build a new one!
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/20200605165258.1483-1-chris@chris-wilson.co.uk
|
|
We cached the number of vma bound to the object in order to speed up
shrinker decisions. This has been superseded by being more proactive in
removing objects we cannot shrink from the shrinker lists, and so we can
drop the clumsy attempt at atomically counting the bind count and
comparing it to the number of pinned mappings of the object. This will
only get more clumsier with asynchronous binding and unbinding.
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/20200401223924.16667-1-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
|
|
Make the GT responsible for restoring its fence when it wakes up from
suspend.
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/20200316113846.4974-2-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
|
|
The #include has been splattered all over the place, but there are
precious few places, all .c files, that actually need it.
v2: remove leftover double newlines
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200225133131.3301-1-jani.nikula@intel.com
|
|
Commit 4f2a572eda67 ("drm/i915/userptr: Never allow userptr into the
mappable GGTT") made I915_GEM_MMAP_GTT IOCTLs to fail when attempted
on a userptr object in order to protect from a lockdep splat. Later
on, new mapping types were introduced by commit cc662126b413
("drm/i915: Introduce DRM_I915_GEM_MMAP_OFFSET"). Those new mapping
types suffer from the same lockdep splat issue but they now succeed
when tried on top of a userptr object. Fix it.
v2: Don't play with the -ENODEV driver response (Chris)
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Abdiel Janulgue <abdiel.janulgue@linux.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/20200204162302.1299516-1-chris@chris-wilson.co.uk
|
|
drm_pci_alloc and drm_pci_free are just very thin wrappers around
dma_alloc_coherent, with a note that we should be removing them.
Furthermore since
commit de09d31dd38a50fdce106c15abd68432eebbd014
Author: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Date: Fri Jan 15 16:51:42 2016 -0800
page-flags: define PG_reserved behavior on compound pages
As far as I can see there's no users of PG_reserved on compound pages.
Let's use PF_NO_COMPOUND here.
drm_pci_alloc has been declared broken since it mixes GFP_COMP and
SetPageReserved. Avoid this conflict by weaning ourselves off using the
abstraction and using the dma functions directly.
Reported-by: Taketo Kabe
Closes: https://gitlab.freedesktop.org/drm/intel/issues/1027
Fixes: de09d31dd38a ("page-flags: define PG_reserved behavior on compound pages")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: <stable@vger.kernel.org> # v4.5+
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200202153934.3899472-1-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/211
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/20200130181710.2030251-3-chris@chris-wilson.co.uk
|
|
The i915_ggtt now sits beneath gt/ outside of the auspices of gem/ and
should be given a fresh name to reflect that. We also want to give it a
name that reflects its role in the system suspend/resume, with the
intention of pulling together all the GGTT operations (e.g. restoring
the fence registers once they are pulled under gt/intel_ggtt_detiler.c)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Rreviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200130181710.2030251-2-chris@chris-wilson.co.uk
|
|
To multiply 2 u32 numbers to generate a u64 in C requires a bit of
forewarning for the compiler.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ramalingam C <ramalingam.c@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200123125934.1401755-1-chris@chris-wilson.co.uk
|
|
drm specific WARN* calls include device information in the
backtrace, so we know what device the warnings originate from.
Covert all the calls of WARN* with device specific drm_WARN*
variants in functions where drm_i915_private struct pointer is readily
available.
The conversion was done automatically with below coccinelle semantic
patch. checkpatch errors/warnings are fixed manually.
@rule1@
identifier func, T;
@@
func(...) {
...
struct drm_i915_private *T = ...;
<+...
(
-WARN(
+drm_WARN(&T->drm,
...)
|
-WARN_ON(
+drm_WARN_ON(&T->drm,
...)
|
-WARN_ONCE(
+drm_WARN_ONCE(&T->drm,
...)
|
-WARN_ON_ONCE(
+drm_WARN_ON_ONCE(&T->drm,
...)
)
...+>
}
@rule2@
identifier func, T;
@@
func(struct drm_i915_private *T,...) {
<+...
(
-WARN(
+drm_WARN(&T->drm,
...)
|
-WARN_ON(
+drm_WARN_ON(&T->drm,
...)
|
-WARN_ONCE(
+drm_WARN_ONCE(&T->drm,
...)
|
-WARN_ON_ONCE(
+drm_WARN_ON_ONCE(&T->drm,
...)
)
...+>
}
command: ls drivers/gpu/drm/i915/*.c | xargs spatch --sp-file \
<script> --linux-spacing --in-place
Signed-off-by: Pankaj Bharadiya <pankaj.laxminarayan.bharadiya@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200115034455.17658-10-pankaj.laxminarayan.bharadiya@intel.com
|
|
When LMEM is supported, dumb buffer preferred to be created from LMEM.
v2:
Parameters are reshuffled. [Chris]
v3:
s/region_id/mem_type
v4:
use the i915_gem_object_create_region [chris]
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200104191043.2207314-2-chris@chris-wilson.co.uk
|
|
When cleaning up the mock device, remember to flush the context worker
to free the residual GEM contexts before shutting down the device.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/802
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191230165821.3840449-1-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
|
|
Only acquire the various atomic references required to unbind the vma if
we do need to unbind the vma.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191222210256.2066451-1-chris@chris-wilson.co.uk
|
|
Begin pulling the GT setup underneath a single GT umbrella; let intel_gt
take ownership of its engines! As hinted, the complication is the
lifetime of the probed engine versus the active lifetime of the GT
backends. We need to detect the engine layout early and keep it until
the end so that we can sanitize state on takeover and release.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Acked-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191222120752.1368352-1-chris@chris-wilson.co.uk
|
|
As the GEM global context setup is now independent of the GT state
(although GT does currently still depend upon the global
i915->kernel_context), we can move its init earlier, leaving the gt init
ready to be extracted.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191221200109.1202310-1-chris@chris-wilson.co.uk
|
|
Allocate only an internal intel_context for the kernel_context, forgoing
a global GEM context for internal use as we only require a separate
address space (for our own protection).
Now having weaned GT from requiring ce->gem_context, we can stop
referencing it entirely. This also means we no longer have to create random
and unnecessary GEM contexts for internal use.
GEM contexts are now entirely for tracking GEM clients, and intel_context
the execution environment on the GPU.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Acked-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
|
|
Keep the intel_context as being the primary state for i915_request, with
the GEM context a backpointer from the low level state for the rarer
cases we need client information. Our goal is to remove such references
to clients from the backend, and leave the HW submission agnostic to
client interfaces and self-contained.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-1-chris@chris-wilson.co.uk
|
|
Since obj->frontbuffer is no longer protected by the struct_mutex, as we
are processing the execbuf, it may be removed. Mark the
intel_frontbuffer as rcu protected, and so acquire a reference to
the struct as we track activity upon it.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/827
Fixes: 8e7cb1799b4f ("drm/i915: Extract intel_frontbuffer active tracking")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v5.4+
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191218104043.3539458-1-chris@chris-wilson.co.uk
|
|
As i915_gem_object_unbind() waits on an rcu_barrier() to flush vm
releases (and destruction of their bound vma), we have to be careful not
to invoke that barrier from beneath the shrinker:
<4> [430.222671] WARNING: possible circular locking dependency detected
<4> [430.222673] 5.4.0-rc8-CI-CI_DRM_7508+ #1 Tainted: G U
<4> [430.222675] ------------------------------------------------------
<4> [430.222677] gem_pwrite/2317 is trying to acquire lock:
<4> [430.222678] ffffffff82248218 (rcu_state.barrier_mutex){+.+.}, at: rcu_barrier+0x23/0x190
<4> [430.222685]
but task is already holding lock:
<4> [430.222687] ffffffff82263a40 (fs_reclaim){+.+.}, at: fs_reclaim_acquire.part.117+0x0/0x30
<4> [430.222691]
which lock already depends on the new lock.
<4> [430.222693]
the existing dependency chain (in reverse order) is:
<4> [430.222695]
-> #2 (fs_reclaim){+.+.}:
<4> [430.222698] fs_reclaim_acquire.part.117+0x24/0x30
<4> [430.222702] kmem_cache_alloc_trace+0x2a/0x2c0
<4> [430.222705] intel_cpuc_prepare+0x37/0x1a0
<4> [430.222709] cpuhp_invoke_callback+0x9b/0x9d0
<4> [430.222712] _cpu_up+0xa2/0x140
<4> [430.222714] do_cpu_up+0x61/0xa0
<4> [430.222718] smp_init+0x57/0x96
<4> [430.222722] kernel_init_freeable+0xac/0x1c7
<4> [430.222725] kernel_init+0x5/0x100
<4> [430.222728] ret_from_fork+0x24/0x50
<4> [430.222729]
-> #1 (cpu_hotplug_lock.rw_sem){++++}:
<4> [430.222733] cpus_read_lock+0x34/0xd0
<4> [430.222734] rcu_barrier+0xaa/0x190
<4> [430.222736] kernel_init+0x21/0x100
<4> [430.222737] ret_from_fork+0x24/0x50
<4> [430.222739]
-> #0 (rcu_state.barrier_mutex){+.+.}:
<4> [430.222742] __lock_acquire+0x1328/0x15d0
<4> [430.222743] lock_acquire+0xa7/0x1c0
<4> [430.222746] __mutex_lock+0x9a/0x9d0
<4> [430.222747] rcu_barrier+0x23/0x190
<4> [430.222850] i915_gem_object_unbind+0x264/0x3d0 [i915]
<4> [430.222882] i915_gem_shrink+0x297/0x5f0 [i915]
<4> [430.222912] i915_gem_shrink_all+0x38/0x60 [i915]
<4> [430.222934] i915_drop_caches_set+0x1f0/0x240 [i915]
<4> [430.222938] simple_attr_write+0xb0/0xd0
<4> [430.222941] full_proxy_write+0x51/0x80
<4> [430.222943] vfs_write+0xb9/0x1d0
<4> [430.222944] ksys_write+0x9f/0xe0
<4> [430.222946] do_syscall_64+0x4f/0x210
<4> [430.222948] entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [430.222950]
other info that might help us debug this:
<4> [430.222952] Chain exists of:
rcu_state.barrier_mutex --> cpu_hotplug_lock.rw_sem --> fs_reclaim
<4> [430.222955] Possible unsafe locking scenario:
<4> [430.222957] CPU0 CPU1
<4> [430.222958] ---- ----
<4> [430.222960] lock(fs_reclaim);
<4> [430.222961] lock(cpu_hotplug_lock.rw_sem);
<4> [430.222963] lock(fs_reclaim);
<4> [430.222964] lock(rcu_state.barrier_mutex);
<4> [430.222966]
*** DEADLOCK ***
<4> [430.222968] 3 locks held by gem_pwrite/2317:
<4> [430.222969] #0: ffff88849e2d9408 (sb_writers#14){.+.+}, at: vfs_write+0x1a4/0x1d0
<4> [430.222973] #1: ffff888496976db0 (&attr->mutex){+.+.}, at: simple_attr_write+0x36/0xd0
<4> [430.222976] #2: ffffffff82263a40 (fs_reclaim){+.+.}, at: fs_reclaim_acquire.part.117+0x0/0x30
<4> [430.222980]
stack backtrace:
<4> [430.222982] CPU: 1 PID: 2317 Comm: gem_pwrite Tainted: G U 5.4.0-rc8-CI-CI_DRM_7508+ #1
<4> [430.222985] Hardware name: Intel Corporation Tiger Lake Client Platform/TigerLake U DDR4 SODIMM RVP, BIOS TGLSFWI1.R00.2321.A08.1909162051 09/16/2019
<4> [430.222989] Call Trace:
<4> [430.222992] dump_stack+0x71/0x9b
<4> [430.222995] check_noncircular+0x19b/0x1c0
<4> [430.222998] ? __lock_acquire+0x1328/0x15d0
<4> [430.222999] __lock_acquire+0x1328/0x15d0
<4> [430.223001] ? mark_held_locks+0x49/0x70
<4> [430.223003] lock_acquire+0xa7/0x1c0
<4> [430.223005] ? rcu_barrier+0x23/0x190
<4> [430.223008] __mutex_lock+0x9a/0x9d0
<4> [430.223009] ? rcu_barrier+0x23/0x190
<4> [430.223011] ? rcu_barrier+0x23/0x190
<4> [430.223013] ? find_held_lock+0x2d/0x90
<4> [430.223045] ? i915_gem_object_unbind+0x24a/0x3d0 [i915]
<4> [430.223048] ? rcu_barrier+0x23/0x190
<4> [430.223049] rcu_barrier+0x23/0x190
<4> [430.223081] i915_gem_object_unbind+0x264/0x3d0 [i915]
<4> [430.223119] i915_gem_shrink+0x297/0x5f0 [i915]
Closes: https://gitlab.freedesktop.org/drm/intel/issues/743
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/20191208161252.3015727-1-chris@chris-wilson.co.uk
|
|
Before we signal the fence to indicate completion, ensure the pwrite
through the indirect GGTT is coherent (as best as we know) in memory.
Any listeners to the fence may start immediately and sample from the
backing store prior to the writes being posted, thus seeing stale data.
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/20191206105527.1130413-1-chris@chris-wilson.co.uk
|
|
As we may start the loop again, we require our local list of i915_vma
we've processed to be reinitialised.
Fixes: aa5e4453dc05 ("drm/i915/gem: Try to flush pending unbind events")
Closes: https://gitlab.freedesktop.org/drm/intel/issues/731
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191205132912.606868-1-chris@chris-wilson.co.uk
|
|
If we cannot handle a vma within the unbind loop, try to flush the
pending events (i915_vma_parked, i915_vm_release) and try again. This
avoids a round trip to userspace that is not guaranteed to make forward
progress, as the events we wait upon require being idle.
References: cb6c3d45f948 ("drm/i915/gem: Avoid parking the vma as we unbind")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191204123556.3740002-1-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
|
|
In order to avoid keeping a reference on the i915_vma (which is long
overdue!) we have to coordinate all the possible lifetimes and only use
the vma while we know it is alive. In this episode, we are reminded that
while idle, the closed vma are destroyed. So if the GT idles while we are
working with the vma, the vma itself becomes invalid.
First class i915_vma here we come, but in the meantime keep piling on
the straw.
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/20191203155032.3137263-1-chris@chris-wilson.co.uk
|
|
Once inside a request, inside the timeline->mutex, pinning is verboten.
<4> [896.032829] ======================================================
<4> [896.032831] WARNING: possible circular locking dependency detected
<4> [896.032835] 5.4.0-rc8-CI-Patchwork_15533+ #1 Tainted: G U
<4> [896.032838] ------------------------------------------------------
<4> [896.032841] gem_exec_parall/3720 is trying to acquire lock:
<4> [896.032844] ffff888401863270 (&kernel#2){+.+.}, at: i915_request_create+0x16/0x1c0 [i915]
<4> [896.032915]
but task is already holding lock:
<4> [896.032917] ffff8883ec1c93c0 (&vm->mutex){+.+.}, at: i915_vma_pin+0xf3/0x11c0 [i915]
<4> [896.032952]
which lock already depends on the new lock.
<4> [896.032954]
the existing dependency chain (in reverse order) is:
<4> [896.032956]
-> #1 (&vm->mutex){+.+.}:
<4> [896.032961] __mutex_lock+0x9a/0x9d0
<4> [896.032995] i915_vma_pin+0xf3/0x11c0 [i915]
<4> [896.033033] intel_renderstate_emit+0xb9/0x9e0 [i915]
<4> [896.033081] i915_gem_init+0x5a9/0xa50 [i915]
<4> [896.033112] i915_driver_probe+0xb00/0x15f0 [i915]
<4> [896.033144] i915_pci_probe+0x43/0x1c0 [i915]
<4> [896.033149] pci_device_probe+0x9e/0x120
<4> [896.033154] really_probe+0xea/0x420
<4> [896.033158] driver_probe_device+0x10b/0x120
<4> [896.033161] device_driver_attach+0x4a/0x50
<4> [896.033164] __driver_attach+0x97/0x130
<4> [896.033168] bus_for_each_dev+0x74/0xc0
<4> [896.033171] bus_add_driver+0x142/0x220
<4> [896.033174] driver_register+0x56/0xf0
<4> [896.033178] do_one_initcall+0x58/0x2ff
<4> [896.033183] do_init_module+0x56/0x1f8
<4> [896.033187] load_module+0x243e/0x29f0
<4> [896.033190] __do_sys_finit_module+0xe9/0x110
<4> [896.033194] do_syscall_64+0x4f/0x210
<4> [896.033197] entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [896.033200]
-> #0 (&kernel#2){+.+.}:
<4> [896.033206] __lock_acquire+0x1328/0x15d0
<4> [896.033209] lock_acquire+0xa7/0x1c0
<4> [896.033213] __mutex_lock+0x9a/0x9d0
<4> [896.033255] i915_request_create+0x16/0x1c0 [i915]
<4> [896.033287] intel_engine_flush_barriers+0x4c/0x100 [i915]
<4> [896.033327] ggtt_flush+0x37/0x60 [i915]
<4> [896.033366] i915_gem_evict_something+0x46b/0x5a0 [i915]
<4> [896.033407] i915_gem_gtt_insert+0x21d/0x6a0 [i915]
<4> [896.033449] i915_vma_pin+0xb36/0x11c0 [i915]
<4> [896.033488] gen6_ppgtt_pin+0xd5/0x170 [i915]
<4> [896.033523] ring_context_pin+0x2e/0xc0 [i915]
<4> [896.033554] __intel_context_do_pin+0x6b/0x190 [i915]
<4> [896.033591] i915_gem_do_execbuffer+0x1814/0x26c0 [i915]
<4> [896.033627] i915_gem_execbuffer2_ioctl+0x11b/0x460 [i915]
<4> [896.033632] drm_ioctl_kernel+0xa7/0xf0
<4> [896.033635] drm_ioctl+0x2e1/0x390
<4> [896.033638] do_vfs_ioctl+0xa0/0x6f0
<4> [896.033641] ksys_ioctl+0x35/0x60
<4> [896.033644] __x64_sys_ioctl+0x11/0x20
<4> [896.033647] do_syscall_64+0x4f/0x210
<4> [896.033650] entry_SYSCALL_64_after_hwframe+0x49/0xbe
Lift the object allocation and pin prior to the request construction.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191202204316.2665847-1-chris@chris-wilson.co.uk
|
|
Some machines require ACPI for runtime resume, and ACPI is quite kmalloc
happy. We cannot handle kmalloc from inside the vm->mutex, as they are
used by the shrinker, and so we must ensure the global runtime-pm is
awake prior to unbinding to avoid the potential inversion.
<4> [57.121748] ======================================================
<4> [57.121750] WARNING: possible circular locking dependency detected
<4> [57.121753] 5.4.0-rc8-CI-CI_DRM_7466+ #1 Tainted: G U
<4> [57.121754] ------------------------------------------------------
<4> [57.121756] i915_pm_rpm/1105 is trying to acquire lock:
<4> [57.121758] ffffffff82263a40 (fs_reclaim){+.+.}, at: fs_reclaim_acquire.part.117+0x0/0x30
<4> [57.121766]
but task is already holding lock:
<4> [57.121768] ffff888475a593c0 (&vm->mutex){+.+.}, at: i915_vma_unbind+0x21/0x50 [i915]
<4> [57.121868]
which lock already depends on the new lock.
<4> [57.121869]
the existing dependency chain (in reverse order) is:
<4> [57.121871]
-> #1 (&vm->mutex){+.+.}:
<4> [57.121951] i915_gem_shrinker_taints_mutex+0xa2/0xd0 [i915]
<4> [57.122028] i915_address_space_init+0xa9/0x170 [i915]
<4> [57.122104] i915_ggtt_init_hw+0x47/0x130 [i915]
<4> [57.122150] i915_driver_probe+0xbb4/0x15f0 [i915]
<4> [57.122197] i915_pci_probe+0x43/0x1c0 [i915]
<4> [57.122202] pci_device_probe+0x9e/0x120
<4> [57.122206] really_probe+0xea/0x420
<4> [57.122209] driver_probe_device+0x10b/0x120
<4> [57.122212] device_driver_attach+0x4a/0x50
<4> [57.122214] __driver_attach+0x97/0x130
<4> [57.122217] bus_for_each_dev+0x74/0xc0
<4> [57.122220] bus_add_driver+0x142/0x220
<4> [57.122222] driver_register+0x56/0xf0
<4> [57.122226] do_one_initcall+0x58/0x2ff
<4> [57.122230] do_init_module+0x56/0x1f8
<4> [57.122233] load_module+0x243e/0x29f0
<4> [57.122236] __do_sys_finit_module+0xe9/0x110
<4> [57.122239] do_syscall_64+0x4f/0x210
<4> [57.122242] entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [57.122244]
-> #0 (fs_reclaim){+.+.}:
<4> [57.122249] __lock_acquire+0x1328/0x15d0
<4> [57.122251] lock_acquire+0xa7/0x1c0
<4> [57.122254] fs_reclaim_acquire.part.117+0x24/0x30
<4> [57.122257] __kmalloc+0x48/0x320
<4> [57.122261] acpi_ns_internalize_name+0x44/0x9b
<4> [57.122264] acpi_ns_get_node_unlocked+0x6b/0xd3
<4> [57.122267] acpi_ns_get_node+0x3b/0x50
<4> [57.122271] acpi_get_handle+0x8a/0xb4
<4> [57.122274] acpi_has_method+0x1c/0x40
<4> [57.122278] acpi_pci_set_power_state+0x40/0xe0
<4> [57.122281] pci_platform_power_transition+0x3e/0x90
<4> [57.122284] pci_set_power_state+0x83/0xf0
<4> [57.122287] pci_restore_standard_config+0x22/0x40
<4> [57.122289] pci_pm_runtime_resume+0x23/0xc0
<4> [57.122293] __rpm_callback+0xb1/0x110
<4> [57.122296] rpm_callback+0x1a/0x70
<4> [57.122299] rpm_resume+0x50e/0x790
<4> [57.122302] __pm_runtime_resume+0x42/0x80
<4> [57.122357] __intel_runtime_pm_get+0x15/0x60 [i915]
<4> [57.122435] ggtt_unbind_vma+0x24/0x60 [i915]
<4> [57.122514] __i915_vma_unbind.part.39+0xb5/0x500 [i915]
<4> [57.122593] i915_vma_unbind+0x2d/0x50 [i915]
<4> [57.122668] i915_gem_object_unbind+0x11c/0x260 [i915]
<4> [57.122740] i915_gem_object_set_cache_level+0x32/0x90 [i915]
<4> [57.122810] i915_gem_set_caching_ioctl+0x1f7/0x2f0 [i915]
<4> [57.122815] drm_ioctl_kernel+0xa7/0xf0
<4> [57.122818] drm_ioctl+0x2e1/0x390
<4> [57.122822] do_vfs_ioctl+0xa0/0x6f0
<4> [57.122825] ksys_ioctl+0x35/0x60
<4> [57.122828] __x64_sys_ioctl+0x11/0x20
<4> [57.122830] do_syscall_64+0x4f/0x210
<4> [57.122833] entry_SYSCALL_64_after_hwframe+0x49/0xbe
Closes: https://gitlab.freedesktop.org/drm/intel/issues/711
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/20191203101347.2836057-1-chris@chris-wilson.co.uk
|
|
Since retirement may be running in a worker on another CPU, it may be
skipped in the local intel_gt_wait_for_idle(). To ensure the state is
consistent for our sanity checks upon load, serialise with the remote
retirer by waiting on the timeline->mutex.
Outside of this use case, e.g. on suspend or module unload, we expect the
slack to be picked up by intel_gt_pm_wait_for_idle() and so prefer to
put the special case serialisation with retirement in its single user,
for now at least.
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/20191121071044.97798-2-chris@chris-wilson.co.uk
|
|
This died many years ago as we now use i915_vma first and foremost.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191115170835.1367869-1-chris@chris-wilson.co.uk
|
|
Backmerge to get dfce90259d74 ("Backmerge i915 security patches from
commit 'ea0b163b13ff' into drm-next") and thus 100d46bd72ec ("Merge
Intel Gen8/Gen9 graphics fixes from Jon Bloomfield.").
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
|
|
This backmerges the branch that ended up in Linus' tree. It removes
all the changes for the rc6 patches from Linus' tree in favour of
a patch that is based on a large refactor that occured.
Otherwise it all looks good.
Signed-off-by: Dave Airlie <airlied@redhat.com>
|
|
For Gen7, the original cmdparser motive was to permit limited
use of register read/write instructions in unprivileged BB's.
This worked by copying the user supplied bb to a kmd owned
bb, and running it in secure mode, from the ggtt, only if
the scanner finds no unsafe commands or registers.
For Gen8+ we can't use this same technique because running bb's
from the ggtt also disables access to ppgtt space. But we also
do not actually require 'secure' execution since we are only
trying to reduce the available command/register set. Instead we
will copy the user buffer to a kmd owned read-only bb in ppgtt,
and run in the usual non-secure mode.
Note that ro pages are only supported by ppgtt (not ggtt), but
luckily that's exactly what we need.
Add the required paths to map the shadow buffer to ppgtt ro for Gen8+
v2: IS_GEN7/IS_GEN (Mika)
v3: rebase
v4: rebase
v5: rebase
Signed-off-by: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris.p.wilson@intel.com>
|
|
Assume all responsibility for operating on the HW to sanitize the GT
state upon load/resume in intel_gt_sanitize() itself.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101141009.15581-1-chris@chris-wilson.co.uk
(cherry picked from commit 797a615357ac0feb79c9ce41f5eaac3eb738a51f)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Assume all responsibility for operating on the HW to sanitize the GT
state upon load/resume in intel_gt_sanitize() itself.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Andi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191101141009.15581-1-chris@chris-wilson.co.uk
|
|
Our timelines are currently contained within an intel_gt, and we only
need to perform list/spinlock initialisation, so we can pull the
intel_timelines_init() into our intel_gt_init_early().
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/20191101130406.4142-1-chris@chris-wilson.co.uk
|
|
Commit 50d84418f586 ("drm/i915: Add i915 to i915_inject_probe_failure")
introduced new functions unfortunately named incompatibly with rules
established by commit f2db53f14d3d ("drm/i915: Replace "_load" with
"_probe" consequently"). Fix it for consistency.
Suggested-by: Michał Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Cc: Michał Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.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/20191029102036.6326-2-janusz.krzysztofik@linux.intel.com
|
|
i915_irq.c is large. One reason for this is that has a large chunk of
the GT render power management stashed away in it. Extract that logic
out of i915_irq.c and intel_pm.c and put it under one roof.
Based on a patch by Chris Wilson.
Signed-off-by: Andi Shyti <andi.shyti@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20191024211642.7688-1-chris@chris-wilson.co.uk
|
|
Again we wish to operate on the engines, which are owned by the
intel_gt. As such it is easier, and much more consistent, to pass the
intel_gt parameter.
v2: Unexport i915_gem_load_power_context()
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/20191022141935.15733-1-chris@chris-wilson.co.uk
|
|
Engines belong to the GT so make it indicative in the API.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191022094726.3001-7-tvrtko.ursulin@linux.intel.com
|
|
Engines belong to the GT so make it indicative in the API.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191022094726.3001-6-tvrtko.ursulin@linux.intel.com
|
|
Engines belong to the GT so make it indicative in the API.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191022094726.3001-5-tvrtko.ursulin@linux.intel.com
|
