diff options
| author | Chris Wilson | 2019-02-13 19:27:37 +0100 |
|---|---|---|
| committer | Chris Wilson | 2019-02-15 13:59:26 +0100 |
| commit | d9e61b66a5d305bbf052a70a853b3be680d911ba (patch) | |
| tree | 844fd1334d53b561bb00b687167f31467b4af698 /drivers/gpu/drm/i915/i915_request.c | |
| parent | drm/i915/selftests: Always use an active engine while resetting (diff) | |
| download | kernel-qcow2-linux-d9e61b66a5d305bbf052a70a853b3be680d911ba.tar.gz kernel-qcow2-linux-d9e61b66a5d305bbf052a70a853b3be680d911ba.tar.xz kernel-qcow2-linux-d9e61b66a5d305bbf052a70a853b3be680d911ba.zip | |
drm/i915: Defer application of request banning to submission
As we currently do not check on submission whether the context is banned
in a timely manner it is possible for some requests to escape
cancellation after their parent context is banned. By moving the ban
into the request submission under the engine->timeline.lock, we
serialise it with the reset and setting of the context ban.
References: eb8d0f5af4ec ("drm/i915: Remove GPU reset dependence on struct_mutex")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190213182737.12695-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915/i915_request.c')
| -rw-r--r-- | drivers/gpu/drm/i915/i915_request.c | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 0acd6baa3c88..5ab4e1c01618 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -366,6 +366,9 @@ void __i915_request_submit(struct i915_request *request) GEM_BUG_ON(!irqs_disabled()); lockdep_assert_held(&engine->timeline.lock); + if (i915_gem_context_is_banned(request->gem_context)) + i915_request_skip(request, -EIO); + GEM_BUG_ON(request->global_seqno); seqno = next_global_seqno(&engine->timeline); |