[ Upstream commit
86d8ddc74124c3fdfc139f246ba6da15e45e86e3 ]
When GuC support was added to error capture, the reference counting
around the request object was broken. Fix it up.
The context based search manages the spinlocking around the search
internally. So it needs to grab the reference count internally as
well. The execlist only request based search relies on external
locking, so it needs an external reference count but within the
spinlock not outside it.
The only other caller of the context based search is the code for
dumping engine state to debugfs. That code wasn't previously getting
an explicit reference at all as it does everything while holding the
execlist specific spinlock. So, that needs updaing as well as that
spinlock doesn't help when using GuC submission. Rather than trying to
conditionally get/put depending on submission model, just change it to
always do the get/put.
v2: Explicitly document adding an extra blank line in some dense code
(Andy Shevchenko). Fix multiple potential null pointer derefs in case
of no request found (some spotted by Tvrtko, but there was more!).
Also fix a leaked request in case of !started and another in
__guc_reset_context now that intel_context_find_active_request is
actually reference counting the returned request.
v3: Add a _get suffix to intel_context_find_active_request now that it
grabs a reference (Daniele).
v4: Split the intel_guc_find_hung_context change to a separate patch
and rename intel_context_find_active_request_get to
intel_context_get_active_request (Tvrtko).
v5: s/locking/reference counting/ in commit message (Tvrtko)
Fixes:
dc0dad365c5e ("drm/i915/guc: Fix for error capture after full GPU reset with GuC")
Fixes:
573ba126aef3 ("drm/i915/guc: Capture error state on context reset")
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Michael Cheng <michael.cheng@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Tejas Upadhyay <tejaskumarx.surendrakumar.upadhyay@intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230127002842.3169194-3-John.C.Harrison@Intel.com
(cherry picked from commit
3700e353781e27f1bc7222f51f2cc36cbeb9b4ec)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
return rq;
}
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
{
struct intel_context *parent = intel_context_to_parent(ce);
struct i915_request *rq, *active = NULL;
active = rq;
}
+ if (active)
+ active = i915_request_get_rcu(active);
spin_unlock_irqrestore(&parent->guc_state.lock, flags);
return active;
struct i915_request *intel_context_create_request(struct intel_context *ce);
-struct i915_request *
-intel_context_find_active_request(struct intel_context *ce);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
static inline bool intel_context_is_barrier(const struct intel_context *ce)
{
if (guc) {
ce = intel_engine_get_hung_context(engine);
if (ce)
- hung_rq = intel_context_find_active_request(ce);
+ hung_rq = intel_context_get_active_request(ce);
} else {
hung_rq = intel_engine_execlist_find_hung_request(engine);
+ if (hung_rq)
+ hung_rq = i915_request_get_rcu(hung_rq);
}
if (hung_rq)
else
intel_engine_dump_active_requests(&engine->sched_engine->requests,
hung_rq, m);
+ if (hung_rq)
+ i915_request_put(hung_rq);
}
void intel_engine_dump(struct intel_engine_cs *engine,
goto next_context;
guilty = false;
- rq = intel_context_find_active_request(ce);
+ rq = intel_context_get_active_request(ce);
if (!rq) {
head = ce->ring->tail;
goto out_replay;
head = intel_ring_wrap(ce->ring, rq->head);
__i915_request_reset(rq, guilty);
+ i915_request_put(rq);
out_replay:
guc_reset_state(ce, head, guilty);
next_context:
ce = intel_engine_get_hung_context(engine);
if (ce) {
intel_engine_clear_hung_context(engine);
- rq = intel_context_find_active_request(ce);
+ rq = intel_context_get_active_request(ce);
if (!rq || !i915_request_started(rq))
goto no_request_capture;
} else {
if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
spin_lock_irqsave(&engine->sched_engine->lock, flags);
rq = intel_engine_execlist_find_hung_request(engine);
+ if (rq)
+ rq = i915_request_get_rcu(rq);
spin_unlock_irqrestore(&engine->sched_engine->lock,
flags);
}
}
- if (rq)
- rq = i915_request_get_rcu(rq);
-
if (!rq)
goto no_request_capture;
capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
- if (!capture) {
- i915_request_put(rq);
+ if (!capture)
goto no_request_capture;
- }
if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
intel_guc_capture_get_matching_node(engine->gt, ee, ce);
return ee;
no_request_capture:
+ if (rq)
+ i915_request_put(rq);
kfree(ee);
return NULL;
}
projects / platform / kernel / linux-starfive.git / commitdiff