[Intel-gfx] [PATCH 21/27] drm/i915/guc: Proper xarray usage for contexts_lookup

Daniele Ceraolo Spurio daniele.ceraolospurio at intel.com
Thu Aug 26 00:44:11 UTC 2021



On 8/18/2021 11:16 PM, Matthew Brost wrote:
> Lock the xarray and take ref to the context if needed.
>
> v2:
>   (Checkpatch)
>    - Add new line after declaration
>   (Daniel Vetter)
>    - Correct put / get accounting in xa_for_loops
>
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
> ---
>   .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 103 +++++++++++++++---
>   1 file changed, 88 insertions(+), 15 deletions(-)
>
> 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 509b298e7cf3..5f77f25322ca 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -606,8 +606,18 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
>   	unsigned long index, flags;
>   	bool pending_disable, pending_enable, deregister, destroyed, banned;
>   
> +	xa_lock_irqsave(&guc->context_lookup, flags);
>   	xa_for_each(&guc->context_lookup, index, ce) {
> -		spin_lock_irqsave(&ce->guc_state.lock, flags);
> +		/*
> +		 * Corner case where the ref count on the object is zero but and
> +		 * deregister G2H was lost. In this case we don't touch the ref
> +		 * count and finish the destroy of the context.
> +		 */
> +		bool do_put = kref_get_unless_zero(&ce->ref);
> +
> +		xa_unlock(&guc->context_lookup);
> +
> +		spin_lock(&ce->guc_state.lock);
>   
>   		/*
>   		 * Once we are at this point submission_disabled() is guaranteed
> @@ -623,7 +633,9 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
>   		banned = context_banned(ce);
>   		init_sched_state(ce);
>   
> -		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> +		spin_unlock(&ce->guc_state.lock);
> +
> +		GEM_BUG_ON(!do_put && !destroyed);
>   
>   		if (pending_enable || destroyed || deregister) {
>   			decr_outstanding_submission_g2h(guc);
> @@ -646,13 +658,19 @@ static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
>   			}
>   			intel_context_sched_disable_unpin(ce);
>   			decr_outstanding_submission_g2h(guc);
> -			spin_lock_irqsave(&ce->guc_state.lock, flags);
> +
> +			spin_lock(&ce->guc_state.lock);
>   			guc_blocked_fence_complete(ce);
> -			spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> +			spin_unlock(&ce->guc_state.lock);
>   
>   			intel_context_put(ce);
>   		}
> +
> +		if (do_put)
> +			intel_context_put(ce);

is it safe to do the put outside the xa_lock, in case the refcount goes 
to zero with this? I know it is unlikely because the refcount was > 0 if 
do_put is true, but it might've gone down between us checking earlier 
and now.

> +		xa_lock(&guc->context_lookup);
>   	}
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
>   }
>   
>   static inline bool
> @@ -873,16 +891,29 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
>   {
>   	struct intel_context *ce;
>   	unsigned long index;
> +	unsigned long flags;
>   
>   	if (unlikely(!guc_submission_initialized(guc))) {
>   		/* Reset called during driver load? GuC not yet initialised! */
>   		return;
>   	}
>   
> -	xa_for_each(&guc->context_lookup, index, ce)
> +	xa_lock_irqsave(&guc->context_lookup, flags);
> +	xa_for_each(&guc->context_lookup, index, ce) {
> +		if (!kref_get_unless_zero(&ce->ref))
> +			continue;
> +
> +		xa_unlock(&guc->context_lookup);
> +
>   		if (intel_context_is_pinned(ce))
>   			__guc_reset_context(ce, stalled);
>   
> +		intel_context_put(ce);
> +
> +		xa_lock(&guc->context_lookup);
> +	}
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
> +
>   	/* GuC is blown away, drop all references to contexts */
>   	xa_destroy(&guc->context_lookup);
>   }
> @@ -957,11 +988,24 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
>   {
>   	struct intel_context *ce;
>   	unsigned long index;
> +	unsigned long flags;
> +
> +	xa_lock_irqsave(&guc->context_lookup, flags);
> +	xa_for_each(&guc->context_lookup, index, ce) {
> +		if (!kref_get_unless_zero(&ce->ref))
> +			continue;
> +
> +		xa_unlock(&guc->context_lookup);
>   
> -	xa_for_each(&guc->context_lookup, index, ce)
>   		if (intel_context_is_pinned(ce))
>   			guc_cancel_context_requests(ce);
>   
> +		intel_context_put(ce);
> +
> +		xa_lock(&guc->context_lookup);
> +	}
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
> +
>   	guc_cancel_sched_engine_requests(guc->sched_engine);
>   
>   	/* GuC is blown away, drop all references to contexts */
> @@ -2850,21 +2894,28 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
>   	struct intel_context *ce;
>   	struct i915_request *rq;
>   	unsigned long index;
> +	unsigned long flags;
>   
>   	/* Reset called during driver load? GuC not yet initialised! */
>   	if (unlikely(!guc_submission_initialized(guc)))
>   		return;
>   
> +	xa_lock_irqsave(&guc->context_lookup, flags);
>   	xa_for_each(&guc->context_lookup, index, ce) {
> -		if (!intel_context_is_pinned(ce))
> +		if (!kref_get_unless_zero(&ce->ref))
>   			continue;
>   
> +		xa_unlock(&guc->context_lookup);
> +
> +		if (!intel_context_is_pinned(ce))
> +			goto next;
> +
>   		if (intel_engine_is_virtual(ce->engine)) {
>   			if (!(ce->engine->mask & engine->mask))
> -				continue;
> +				goto next;
>   		} else {
>   			if (ce->engine != engine)
> -				continue;
> +				goto next;
>   		}
>   
>   		list_for_each_entry(rq, &ce->guc_active.requests, sched.link) {
> @@ -2874,9 +2925,17 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
>   			intel_engine_set_hung_context(engine, ce);
>   
>   			/* Can only cope with one hang at a time... */
> -			return;
> +			intel_context_put(ce);
> +			xa_lock(&guc->context_lookup);
> +			goto done;
>   		}
> +next:
> +		intel_context_put(ce);
> +		xa_lock(&guc->context_lookup);
> +

nit: extra newline

Daniele

>   	}
> +done:
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
>   }
>   
>   void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
> @@ -2892,23 +2951,34 @@ void intel_guc_dump_active_requests(struct intel_engine_cs *engine,
>   	if (unlikely(!guc_submission_initialized(guc)))
>   		return;
>   
> +	xa_lock_irqsave(&guc->context_lookup, flags);
>   	xa_for_each(&guc->context_lookup, index, ce) {
> -		if (!intel_context_is_pinned(ce))
> +		if (!kref_get_unless_zero(&ce->ref))
>   			continue;
>   
> +		xa_unlock(&guc->context_lookup);
> +
> +		if (!intel_context_is_pinned(ce))
> +			goto next;
> +
>   		if (intel_engine_is_virtual(ce->engine)) {
>   			if (!(ce->engine->mask & engine->mask))
> -				continue;
> +				goto next;
>   		} else {
>   			if (ce->engine != engine)
> -				continue;
> +				goto next;
>   		}
>   
> -		spin_lock_irqsave(&ce->guc_active.lock, flags);
> +		spin_lock(&ce->guc_active.lock);
>   		intel_engine_dump_active_requests(&ce->guc_active.requests,
>   						  hung_rq, m);
> -		spin_unlock_irqrestore(&ce->guc_active.lock, flags);
> +		spin_unlock(&ce->guc_active.lock);
> +
> +next:
> +		intel_context_put(ce);
> +		xa_lock(&guc->context_lookup);
>   	}
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
>   }
>   
>   void intel_guc_submission_print_info(struct intel_guc *guc,
> @@ -2962,7 +3032,9 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
>   {
>   	struct intel_context *ce;
>   	unsigned long index;
> +	unsigned long flags;
>   
> +	xa_lock_irqsave(&guc->context_lookup, flags);
>   	xa_for_each(&guc->context_lookup, index, ce) {
>   		drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id);
>   		drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca);
> @@ -2981,6 +3053,7 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
>   
>   		guc_log_context_priority(p, ce);
>   	}
> +	xa_unlock_irqrestore(&guc->context_lookup, flags);
>   }
>   
>   static struct intel_context *



More information about the Intel-gfx mailing list