drm/i915: Mark up the calling context for intel_wakeref_put()

Previously, we assumed we could use mutex_trylock() within an atomic
context, falling back to a worker if contended. However, such trickery
is illegal inside interrupt context, and so we need to always use a
worker under such circumstances. As we normally are in process context,
we can typically use a plain mutex, and only defer to a work when we
know we are being called from an interrupt path.

Fixes: 51fbd8de87 ("drm/i915/pmu: Atomically acquire the gt_pm wakeref")
References: a0855d24fc ("locking/mutex: Complain upon mutex API misuse in IRQ contexts")
References: https://bugs.freedesktop.org/show_bug.cgi?id=111626
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/20191120125433.3767149-1-chris@chris-wilson.co.uk
This commit is contained in:
Chris Wilson
2019-11-20 12:54:33 +00:00
parent 8a126392b7
commit 07779a76ee
11 changed files with 54 additions and 25 deletions

View File

@@ -54,7 +54,8 @@ int __intel_wakeref_get_first(struct intel_wakeref *wf)
static void ____intel_wakeref_put_last(struct intel_wakeref *wf)
{
if (!atomic_dec_and_test(&wf->count))
INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
if (unlikely(!atomic_dec_and_test(&wf->count)))
goto unlock;
/* ops->put() must reschedule its own release on error/deferral */
@@ -67,13 +68,12 @@ unlock:
mutex_unlock(&wf->mutex);
}
void __intel_wakeref_put_last(struct intel_wakeref *wf)
void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
{
INTEL_WAKEREF_BUG_ON(work_pending(&wf->work));
/* Assume we are not in process context and so cannot sleep. */
if (wf->ops->flags & INTEL_WAKEREF_PUT_ASYNC ||
!mutex_trylock(&wf->mutex)) {
if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) {
schedule_work(&wf->work);
return;
}