diff mbox series

[v2,2/2] drm/i915/guc: Don't deadlock busyness stats vs reset

Message ID 20221102192109.2492625-3-John.C.Harrison@Intel.com (mailing list archive)
State New, archived
Headers show
Series Fix for two GuC issues | expand

Commit Message

John Harrison Nov. 2, 2022, 7:21 p.m. UTC
From: John Harrison <John.C.Harrison@Intel.com>

The engine busyness stats has a worker function to do things like
64bit extend the 32bit hardware counters. The GuC's reset prepare
function flushes out this worker function to ensure no corruption
happens during the reset. Unforunately, the worker function has an
infinite wait for active resets to finish before doing its work. Thus
a deadlock would occur if the worker function had actually started
just as the reset starts.

The function being used to lock the reset-in-progress mutex is called
intel_gt_reset_trylock(). However, as noted it does not follow
standard 'trylock' conventions and exit if already locked. So rename
the current _trylock function to intel_gt_reset_lock_interruptible(),
which is the behaviour it actually provides. In addition, add a new
implementation of _trylock and call that from the busyness stats
worker instead.

v2: Rename existing trylock to interruptible rather than trying to
preserve the existing (confusing) naming scheme (review comments from
Tvrtko).

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c       |  2 +-
 drivers/gpu/drm/i915/gt/intel_reset.c          | 18 ++++++++++++++++--
 drivers/gpu/drm/i915/gt/intel_reset.h          |  1 +
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c  |  4 +++-
 4 files changed, 21 insertions(+), 4 deletions(-)

Comments

Tvrtko Ursulin Nov. 3, 2022, 11:31 a.m. UTC | #1
On 02/11/2022 19:21, John.C.Harrison@Intel.com wrote:
> From: John Harrison <John.C.Harrison@Intel.com>
> 
> The engine busyness stats has a worker function to do things like
> 64bit extend the 32bit hardware counters. The GuC's reset prepare
> function flushes out this worker function to ensure no corruption
> happens during the reset. Unforunately, the worker function has an
> infinite wait for active resets to finish before doing its work. Thus
> a deadlock would occur if the worker function had actually started
> just as the reset starts.
> 
> The function being used to lock the reset-in-progress mutex is called
> intel_gt_reset_trylock(). However, as noted it does not follow
> standard 'trylock' conventions and exit if already locked. So rename
> the current _trylock function to intel_gt_reset_lock_interruptible(),
> which is the behaviour it actually provides. In addition, add a new
> implementation of _trylock and call that from the busyness stats
> worker instead.
> 
> v2: Rename existing trylock to interruptible rather than trying to
> preserve the existing (confusing) naming scheme (review comments from
> Tvrtko).
> 
> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
> ---
>   drivers/gpu/drm/i915/gem/i915_gem_mman.c       |  2 +-
>   drivers/gpu/drm/i915/gt/intel_reset.c          | 18 ++++++++++++++++--
>   drivers/gpu/drm/i915/gt/intel_reset.h          |  1 +
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c  |  4 +++-
>   4 files changed, 21 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> index e63329bc80659..c29efdef8313a 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
> @@ -330,7 +330,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
>   	if (ret)
>   		goto err_rpm;
>   
> -	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
> +	ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu);
>   	if (ret)
>   		goto err_pages;
>   
> diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
> index 3159df6cdd492..24736ebee17c2 100644
> --- a/drivers/gpu/drm/i915/gt/intel_reset.c
> +++ b/drivers/gpu/drm/i915/gt/intel_reset.c
> @@ -1407,15 +1407,19 @@ void intel_gt_handle_error(struct intel_gt *gt,
>   	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
>   }
>   
> -int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
> +static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, bool retry)
>   {
>   	might_lock(&gt->reset.backoff_srcu);
> -	might_sleep();
> +	if (retry)
> +		might_sleep();
>   
>   	rcu_read_lock();
>   	while (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
>   		rcu_read_unlock();
>   
> +		if (!retry)
> +			return -EBUSY;
> +
>   		if (wait_event_interruptible(gt->reset.queue,
>   					     !test_bit(I915_RESET_BACKOFF,
>   						       &gt->reset.flags)))
> @@ -1429,6 +1433,16 @@ int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
>   	return 0;
>   }
>   
> +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
> +{
> +	return _intel_gt_reset_lock(gt, srcu, false);
> +}
> +
> +int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu)
> +{
> +	return _intel_gt_reset_lock(gt, srcu, true);
> +}
> +
>   void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
>   __releases(&gt->reset.backoff_srcu)
>   {
> diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
> index adc734e673870..25c975b6e8fc0 100644
> --- a/drivers/gpu/drm/i915/gt/intel_reset.h
> +++ b/drivers/gpu/drm/i915/gt/intel_reset.h
> @@ -39,6 +39,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs *engine,
>   void __i915_request_reset(struct i915_request *rq, bool guilty);
>   
>   int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
> +int __must_check intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu);
>   void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
>   
>   void intel_gt_set_wedged(struct intel_gt *gt);
> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> index 941613be3b9dd..92e514061d20b 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -1401,7 +1401,9 @@ static void guc_timestamp_ping(struct work_struct *wrk)
>   
>   	/*
>   	 * Synchronize with gt reset to make sure the worker does not
> -	 * corrupt the engine/guc stats.
> +	 * corrupt the engine/guc stats. NB: can't actually block waiting
> +	 * for a reset to complete as the reset requires flushing out
> +	 * this worker thread if started. So waiting would deadlock.
>   	 */
>   	ret = intel_gt_reset_trylock(gt, &srcu);
>   	if (ret)

LGTM but I don't remember fully how ping worker and reset interact so 
I'll let Umesh r-b. Like is it okay to skip the ping or we'd need to 
re-schedule it ASAP due wrap issues? Maybe reset makes that pointless, I 
don't remember.

Regards,

Tvrtko
John Harrison Nov. 3, 2022, 6:45 p.m. UTC | #2
On 11/3/2022 04:31, Tvrtko Ursulin wrote:
> On 02/11/2022 19:21, John.C.Harrison@Intel.com wrote:
>> From: John Harrison <John.C.Harrison@Intel.com>
>>
>> The engine busyness stats has a worker function to do things like
>> 64bit extend the 32bit hardware counters. The GuC's reset prepare
>> function flushes out this worker function to ensure no corruption
>> happens during the reset. Unforunately, the worker function has an
>> infinite wait for active resets to finish before doing its work. Thus
>> a deadlock would occur if the worker function had actually started
>> just as the reset starts.
>>
>> The function being used to lock the reset-in-progress mutex is called
>> intel_gt_reset_trylock(). However, as noted it does not follow
>> standard 'trylock' conventions and exit if already locked. So rename
>> the current _trylock function to intel_gt_reset_lock_interruptible(),
>> which is the behaviour it actually provides. In addition, add a new
>> implementation of _trylock and call that from the busyness stats
>> worker instead.
>>
>> v2: Rename existing trylock to interruptible rather than trying to
>> preserve the existing (confusing) naming scheme (review comments from
>> Tvrtko).
>>
>> Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>> ---
>>   drivers/gpu/drm/i915/gem/i915_gem_mman.c       |  2 +-
>>   drivers/gpu/drm/i915/gt/intel_reset.c          | 18 ++++++++++++++++--
>>   drivers/gpu/drm/i915/gt/intel_reset.h          |  1 +
>>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c  |  4 +++-
>>   4 files changed, 21 insertions(+), 4 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c 
>> b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>> index e63329bc80659..c29efdef8313a 100644
>> --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>> @@ -330,7 +330,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
>>       if (ret)
>>           goto err_rpm;
>>   -    ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
>> +    ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu);
>>       if (ret)
>>           goto err_pages;
>>   diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c 
>> b/drivers/gpu/drm/i915/gt/intel_reset.c
>> index 3159df6cdd492..24736ebee17c2 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_reset.c
>> +++ b/drivers/gpu/drm/i915/gt/intel_reset.c
>> @@ -1407,15 +1407,19 @@ void intel_gt_handle_error(struct intel_gt *gt,
>>       intel_runtime_pm_put(gt->uncore->rpm, wakeref);
>>   }
>>   -int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
>> +static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, bool 
>> retry)
>>   {
>>       might_lock(&gt->reset.backoff_srcu);
>> -    might_sleep();
>> +    if (retry)
>> +        might_sleep();
>>         rcu_read_lock();
>>       while (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
>>           rcu_read_unlock();
>>   +        if (!retry)
>> +            return -EBUSY;
>> +
>>           if (wait_event_interruptible(gt->reset.queue,
>>                            !test_bit(I915_RESET_BACKOFF,
>>                                  &gt->reset.flags)))
>> @@ -1429,6 +1433,16 @@ int intel_gt_reset_trylock(struct intel_gt 
>> *gt, int *srcu)
>>       return 0;
>>   }
>>   +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
>> +{
>> +    return _intel_gt_reset_lock(gt, srcu, false);
>> +}
>> +
>> +int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu)
>> +{
>> +    return _intel_gt_reset_lock(gt, srcu, true);
>> +}
>> +
>>   void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
>>   __releases(&gt->reset.backoff_srcu)
>>   {
>> diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h 
>> b/drivers/gpu/drm/i915/gt/intel_reset.h
>> index adc734e673870..25c975b6e8fc0 100644
>> --- a/drivers/gpu/drm/i915/gt/intel_reset.h
>> +++ b/drivers/gpu/drm/i915/gt/intel_reset.h
>> @@ -39,6 +39,7 @@ int __intel_engine_reset_bh(struct intel_engine_cs 
>> *engine,
>>   void __i915_request_reset(struct i915_request *rq, bool guilty);
>>     int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int 
>> *srcu);
>> +int __must_check intel_gt_reset_lock_interruptible(struct intel_gt 
>> *gt, int *srcu);
>>   void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
>>     void intel_gt_set_wedged(struct intel_gt *gt);
>> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c 
>> b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>> index 941613be3b9dd..92e514061d20b 100644
>> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>> @@ -1401,7 +1401,9 @@ static void guc_timestamp_ping(struct 
>> work_struct *wrk)
>>         /*
>>        * Synchronize with gt reset to make sure the worker does not
>> -     * corrupt the engine/guc stats.
>> +     * corrupt the engine/guc stats. NB: can't actually block waiting
>> +     * for a reset to complete as the reset requires flushing out
>> +     * this worker thread if started. So waiting would deadlock.
>>        */
>>       ret = intel_gt_reset_trylock(gt, &srcu);
>>       if (ret)
>
> LGTM but I don't remember fully how ping worker and reset interact so 
> I'll let Umesh r-b. Like is it okay to skip the ping or we'd need to 
> re-schedule it ASAP due wrap issues? Maybe reset makes that pointless, 
> I don't remember.
The reset is cancelling the worker anyway. And it will then be 
rescheduled once the reset is done. And the ping time is defined as 
1/8th the wrap time (being approx 223 seconds on current platforms). So 
as long as the reset doesn't take longer than about 200s, there is no 
issue. And if the reset did take longer than that then we have bigger 
issues than the busyness stats (which can't actually be counting anyway 
because nothing is running if the GT is in reset) being slightly off.

John.

>
> Regards,
>
> Tvrtko
Umesh Nerlige Ramappa Nov. 3, 2022, 6:54 p.m. UTC | #3
On Thu, Nov 03, 2022 at 11:45:57AM -0700, John Harrison wrote:
>On 11/3/2022 04:31, Tvrtko Ursulin wrote:
>>On 02/11/2022 19:21, John.C.Harrison@Intel.com wrote:
>>>From: John Harrison <John.C.Harrison@Intel.com>
>>>
>>>The engine busyness stats has a worker function to do things like
>>>64bit extend the 32bit hardware counters. The GuC's reset prepare
>>>function flushes out this worker function to ensure no corruption
>>>happens during the reset. Unforunately, the worker function has an
>>>infinite wait for active resets to finish before doing its work. Thus
>>>a deadlock would occur if the worker function had actually started
>>>just as the reset starts.
>>>
>>>The function being used to lock the reset-in-progress mutex is called
>>>intel_gt_reset_trylock(). However, as noted it does not follow
>>>standard 'trylock' conventions and exit if already locked. So rename
>>>the current _trylock function to intel_gt_reset_lock_interruptible(),
>>>which is the behaviour it actually provides. In addition, add a new
>>>implementation of _trylock and call that from the busyness stats
>>>worker instead.
>>>
>>>v2: Rename existing trylock to interruptible rather than trying to
>>>preserve the existing (confusing) naming scheme (review comments from
>>>Tvrtko).
>>>
>>>Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
>>>---
>>>  drivers/gpu/drm/i915/gem/i915_gem_mman.c       |  2 +-
>>>  drivers/gpu/drm/i915/gt/intel_reset.c          | 18 ++++++++++++++++--
>>>  drivers/gpu/drm/i915/gt/intel_reset.h          |  1 +
>>>  .../gpu/drm/i915/gt/uc/intel_guc_submission.c  |  4 +++-
>>>  4 files changed, 21 insertions(+), 4 deletions(-)
>>>
>>>diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c 
>>>b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>>>index e63329bc80659..c29efdef8313a 100644
>>>--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>>>+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
>>>@@ -330,7 +330,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
>>>      if (ret)
>>>          goto err_rpm;
>>>  -    ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
>>>+    ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu);
>>>      if (ret)
>>>          goto err_pages;
>>>  diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c 
>>>b/drivers/gpu/drm/i915/gt/intel_reset.c
>>>index 3159df6cdd492..24736ebee17c2 100644
>>>--- a/drivers/gpu/drm/i915/gt/intel_reset.c
>>>+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
>>>@@ -1407,15 +1407,19 @@ void intel_gt_handle_error(struct intel_gt *gt,
>>>      intel_runtime_pm_put(gt->uncore->rpm, wakeref);
>>>  }
>>>  -int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
>>>+static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, 
>>>bool retry)
>>>  {
>>>      might_lock(&gt->reset.backoff_srcu);
>>>-    might_sleep();
>>>+    if (retry)
>>>+        might_sleep();
>>>        rcu_read_lock();
>>>      while (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
>>>          rcu_read_unlock();
>>>  +        if (!retry)
>>>+            return -EBUSY;
>>>+
>>>          if (wait_event_interruptible(gt->reset.queue,
>>>                           !test_bit(I915_RESET_BACKOFF,
>>>                                 &gt->reset.flags)))
>>>@@ -1429,6 +1433,16 @@ int intel_gt_reset_trylock(struct intel_gt 
>>>*gt, int *srcu)
>>>      return 0;
>>>  }
>>>  +int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
>>>+{
>>>+    return _intel_gt_reset_lock(gt, srcu, false);
>>>+}
>>>+
>>>+int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu)
>>>+{
>>>+    return _intel_gt_reset_lock(gt, srcu, true);
>>>+}
>>>+
>>>  void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
>>>  __releases(&gt->reset.backoff_srcu)
>>>  {
>>>diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h 
>>>b/drivers/gpu/drm/i915/gt/intel_reset.h
>>>index adc734e673870..25c975b6e8fc0 100644
>>>--- a/drivers/gpu/drm/i915/gt/intel_reset.h
>>>+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
>>>@@ -39,6 +39,7 @@ int __intel_engine_reset_bh(struct 
>>>intel_engine_cs *engine,
>>>  void __i915_request_reset(struct i915_request *rq, bool guilty);
>>>    int __must_check intel_gt_reset_trylock(struct intel_gt *gt, 
>>>int *srcu);
>>>+int __must_check intel_gt_reset_lock_interruptible(struct 
>>>intel_gt *gt, int *srcu);
>>>  void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
>>>    void intel_gt_set_wedged(struct intel_gt *gt);
>>>diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c 
>>>b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>>>index 941613be3b9dd..92e514061d20b 100644
>>>--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>>>+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
>>>@@ -1401,7 +1401,9 @@ static void guc_timestamp_ping(struct 
>>>work_struct *wrk)
>>>        /*
>>>       * Synchronize with gt reset to make sure the worker does not
>>>-     * corrupt the engine/guc stats.
>>>+     * corrupt the engine/guc stats. NB: can't actually block waiting
>>>+     * for a reset to complete as the reset requires flushing out
>>>+     * this worker thread if started. So waiting would deadlock.
>>>       */
>>>      ret = intel_gt_reset_trylock(gt, &srcu);
>>>      if (ret)
>>
>>LGTM but I don't remember fully how ping worker and reset interact 
>>so I'll let Umesh r-b. Like is it okay to skip the ping or we'd need 
>>to re-schedule it ASAP due wrap issues? Maybe reset makes that 
>>pointless, I don't remember.
>The reset is cancelling the worker anyway. And it will then be 
>rescheduled once the reset is done. And the ping time is defined as 
>1/8th the wrap time (being approx 223 seconds on current platforms). 
>So as long as the reset doesn't take longer than about 200s, there is 
>no issue. And if the reset did take longer than that then we have 
>bigger issues than the busyness stats (which can't actually be 
>counting anyway because nothing is running if the GT is in reset) 
>being slightly off.

In addition to canceling the ping worker, __reset_guc_busyness_stats is 
performing the same activities that the ping-worker would do if it were 
to run, so we should be safe to skip the worker when a reset is in 
progress, so lgtm,

Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>

Thanks,
Umesh

>
>John.
>
>>
>>Regards,
>>
>>Tvrtko
>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index e63329bc80659..c29efdef8313a 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -330,7 +330,7 @@  static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 	if (ret)
 		goto err_rpm;
 
-	ret = intel_gt_reset_trylock(ggtt->vm.gt, &srcu);
+	ret = intel_gt_reset_lock_interruptible(ggtt->vm.gt, &srcu);
 	if (ret)
 		goto err_pages;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 3159df6cdd492..24736ebee17c2 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1407,15 +1407,19 @@  void intel_gt_handle_error(struct intel_gt *gt,
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 }
 
-int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
+static int _intel_gt_reset_lock(struct intel_gt *gt, int *srcu, bool retry)
 {
 	might_lock(&gt->reset.backoff_srcu);
-	might_sleep();
+	if (retry)
+		might_sleep();
 
 	rcu_read_lock();
 	while (test_bit(I915_RESET_BACKOFF, &gt->reset.flags)) {
 		rcu_read_unlock();
 
+		if (!retry)
+			return -EBUSY;
+
 		if (wait_event_interruptible(gt->reset.queue,
 					     !test_bit(I915_RESET_BACKOFF,
 						       &gt->reset.flags)))
@@ -1429,6 +1433,16 @@  int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
 	return 0;
 }
 
+int intel_gt_reset_trylock(struct intel_gt *gt, int *srcu)
+{
+	return _intel_gt_reset_lock(gt, srcu, false);
+}
+
+int intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu)
+{
+	return _intel_gt_reset_lock(gt, srcu, true);
+}
+
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag)
 __releases(&gt->reset.backoff_srcu)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h
index adc734e673870..25c975b6e8fc0 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.h
+++ b/drivers/gpu/drm/i915/gt/intel_reset.h
@@ -39,6 +39,7 @@  int __intel_engine_reset_bh(struct intel_engine_cs *engine,
 void __i915_request_reset(struct i915_request *rq, bool guilty);
 
 int __must_check intel_gt_reset_trylock(struct intel_gt *gt, int *srcu);
+int __must_check intel_gt_reset_lock_interruptible(struct intel_gt *gt, int *srcu);
 void intel_gt_reset_unlock(struct intel_gt *gt, int tag);
 
 void intel_gt_set_wedged(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 941613be3b9dd..92e514061d20b 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1401,7 +1401,9 @@  static void guc_timestamp_ping(struct work_struct *wrk)
 
 	/*
 	 * Synchronize with gt reset to make sure the worker does not
-	 * corrupt the engine/guc stats.
+	 * corrupt the engine/guc stats. NB: can't actually block waiting
+	 * for a reset to complete as the reset requires flushing out
+	 * this worker thread if started. So waiting would deadlock.
 	 */
 	ret = intel_gt_reset_trylock(gt, &srcu);
 	if (ret)