mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-04-27 11:38:12 -04:00
Code Issues Packages Projects Releases Wiki Activity

drm/i915/gt: Harden the heartbeat against a stuck driver

Browse Source 
If the driver gets stuck holding the kernel timeline, we cannot issue a
heartbeat and so fail to discover that the driver is indeed stuck and do
not issue a GPU reset (which would hopefully unstick the driver!).
Switch to using a trylock so that we can query if the heartbeat's
timeline mutex is locked elsewhere, and then use the timer to probe if it
remains stuck at the same spot for consecutive heartbeats, indicating
that the mutex has not been released and the engine has not progressed.

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/20200702095219.963-1-chris@chris-wilson.co.uk
This commit is contained in:
Chris Wilson
2020-07-02 10:52:18 +01:00
parent 680c45c767
commit aab4707fdd
2 changed files with 13 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
View File

@@ -65,6 +65,7 @@ static void heartbeat(struct work_struct *wrk)
container_of(wrk, typeof(*engine), heartbeat.work.work);
struct intel_context *ce = engine->kernel_context;
struct i915_request *rq;
unsigned long serial;
/* Just in case everything has gone horribly wrong, give it a kick */
intel_engine_flush_submission(engine);
@@ -122,10 +123,19 @@ static void heartbeat(struct work_struct *wrk)
goto out;
}
if (engine->wakeref_serial == engine->serial)
serial = READ_ONCE(engine->serial);
if (engine->wakeref_serial == serial)
goto out;
mutex_lock(&ce->timeline->mutex);
if (!mutex_trylock(&ce->timeline->mutex)) {
/* Unable to lock the kernel timeline, is the engine stuck? */
if (xchg(&engine->heartbeat.blocked, serial) == serial)
intel_gt_handle_error(engine->gt, engine->mask,
I915_ERROR_CAPTURE,
"no heartbeat on %s",
engine->name);
goto out;
}
intel_context_enter(ce);
rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN);

1
drivers/gpu/drm/i915/gt/intel_engine_types.h
View File

@@ -348,6 +348,7 @@ struct intel_engine_cs {
struct {
struct delayed_work work;
struct i915_request *systole;
unsigned long blocked;
} heartbeat;
unsigned long serial;