diff options
| author |   Chris Wilson <chris@chris-wilson.co.uk> | 2019-07-15 09:09:28 +0100 |
|---|---|---|
| committer |   Jani Nikula <jani.nikula@intel.com> | 2019-07-29 15:49:54 +0300 |
| commit | 982b1d002f16c2695871e005c4132060c836db56 (patch) | |
| tree | c34fede876d0f26993c767e3945802d4bfeff717 /drivers/gpu/drm/i915/gt/intel_engine_cs.c | |
| parent | drm/i915/perf: add missing delay for OA muxes configuration (diff) | |
| download | linux-dev-982b1d002f16c2695871e005c4132060c836db56.tar.xz linux-dev-982b1d002f16c2695871e005c4132060c836db56.zip | |
drm/i915: Lock the engine while dumping the active request
We cannot let the request be retired and freed while we are trying to
dump it during error capture. It is not sufficient just to grab a
reference to the request, as during retirement we may free the ring
which we are also dumping. So take the engine lock to prevent retiring
and freeing of the request.
Reported-by: Alex Shumsky <alexthreed@gmail.com>
Fixes: 83c317832eb1 ("drm/i915: Dump the ringbuffer of the active request for debugging")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Alex Shumsky <alexthreed@gmail.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190715080946.15593-6-chris@chris-wilson.co.uk
(cherry picked from commit cfe7288c276e359eebf057699fe86c2f8af14224)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Diffstat (limited to 'drivers/gpu/drm/i915/gt/intel_engine_cs.c')
| -rw-r--r-- | drivers/gpu/drm/i915/gt/intel_engine_cs.c | 11 |
1 files changed, 4 insertions, 7 deletions
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 7fd33e81c2d9..aa5a1f11a91b 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1471,6 +1471,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; + unsigned long flags; if (header) { va_list ap; @@ -1490,10 +1491,9 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_engine_count(error, engine), i915_reset_count(error)); - rcu_read_lock(); - drm_printf(m, "\tRequests:\n"); + spin_lock_irqsave(&engine->active.lock, flags); rq = intel_engine_find_active_request(engine); if (rq) { print_request(m, rq, "\t\tactive "); @@ -1513,8 +1513,7 @@ void intel_engine_dump(struct intel_engine_cs *engine, print_request_ring(m, rq); } - - rcu_read_unlock(); + spin_unlock_irqrestore(&engine->active.lock, flags); wakeref = intel_runtime_pm_get_if_in_use(&engine->i915->runtime_pm); if (wakeref) { @@ -1672,7 +1671,6 @@ struct i915_request * intel_engine_find_active_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; - unsigned long flags; /* * We are called by the error capture, reset and to dump engine @@ -1685,7 +1683,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) * At all other times, we must assume the GPU is still running, but * we only care about the snapshot of this moment. */ - spin_lock_irqsave(&engine->active.lock, flags); + lockdep_assert_held(&engine->active.lock); list_for_each_entry(request, &engine->active.requests, sched.link) { if (i915_request_completed(request)) continue; @@ -1700,7 +1698,6 @@ intel_engine_find_active_request(struct intel_engine_cs *engine) active = request; break; } - spin_unlock_irqrestore(&engine->active.lock, flags); return active; } |