[Intel-gfx] [PATCH 14/25] drm/i915/guc: Implement multi-lrc reset
John Harrison
john.c.harrison at intel.com
Thu Oct 14 00:28:05 UTC 2021
On 10/13/2021 13:42, Matthew Brost wrote:
> Update context and full GPU reset to work with multi-lrc. The idea is
> parent context tracks all the active requests inflight for itself and
> its children. The parent context owns the reset replaying / canceling
> requests as needed.
>
> v2:
> (John Harrison)
> - Simply loop in find active request
> - Add comments to find ative request / reset loop
> v3:
> (John Harrison)
> - s/its'/its/g
> - Fix comment when searching for active request
> - Reorder if state in __guc_reset_context
>
> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
Reviewed-by: John Harrison <John.C.Harrison at Intel.com>
> ---
> drivers/gpu/drm/i915/gt/intel_context.c | 15 +++-
> .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 69 ++++++++++++++-----
> 2 files changed, 63 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
> index 79f321c6c008..6aab60584ee5 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context.c
> +++ b/drivers/gpu/drm/i915/gt/intel_context.c
> @@ -529,20 +529,29 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
>
> struct i915_request *intel_context_find_active_request(struct intel_context *ce)
> {
> + struct intel_context *parent = intel_context_to_parent(ce);
> struct i915_request *rq, *active = NULL;
> unsigned long flags;
>
> GEM_BUG_ON(!intel_engine_uses_guc(ce->engine));
>
> - spin_lock_irqsave(&ce->guc_state.lock, flags);
> - list_for_each_entry_reverse(rq, &ce->guc_state.requests,
> + /*
> + * We search the parent list to find an active request on the submitted
> + * context. The parent list contains the requests for all the contexts
> + * in the relationship so we have to do a compare of each request's
> + * context.
> + */
> + spin_lock_irqsave(&parent->guc_state.lock, flags);
> + list_for_each_entry_reverse(rq, &parent->guc_state.requests,
> sched.link) {
> + if (rq->context != ce)
> + continue;
> if (i915_request_completed(rq))
> break;
>
> active = rq;
> }
> - spin_unlock_irqrestore(&ce->guc_state.lock, flags);
> + spin_unlock_irqrestore(&parent->guc_state.lock, flags);
>
> return active;
> }
> 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 f690b7c2b295..bc052d206861 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -683,6 +683,11 @@ static inline int rq_prio(const struct i915_request *rq)
> return rq->sched.attr.priority;
> }
>
> +static inline bool is_multi_lrc(struct intel_context *ce)
> +{
> + return intel_context_is_parallel(ce);
> +}
> +
> static bool is_multi_lrc_rq(struct i915_request *rq)
> {
> return intel_context_is_parallel(rq->context);
> @@ -1218,10 +1223,15 @@ __unwind_incomplete_requests(struct intel_context *ce)
>
> static void __guc_reset_context(struct intel_context *ce, bool stalled)
> {
> + bool local_stalled;
> struct i915_request *rq;
> unsigned long flags;
> u32 head;
> + int i, number_children = ce->parallel.number_children;
> bool skip = false;
> + struct intel_context *parent = ce;
> +
> + GEM_BUG_ON(intel_context_is_child(ce));
>
> intel_context_get(ce);
>
> @@ -1247,25 +1257,38 @@ static void __guc_reset_context(struct intel_context *ce, bool stalled)
> if (unlikely(skip))
> goto out_put;
>
> - rq = intel_context_find_active_request(ce);
> - if (!rq) {
> - head = ce->ring->tail;
> - stalled = false;
> - goto out_replay;
> - }
> + /*
> + * For each context in the relationship find the hanging request
> + * resetting each context / request as needed
> + */
> + for (i = 0; i < number_children + 1; ++i) {
> + if (!intel_context_is_pinned(ce))
> + goto next_context;
> +
> + local_stalled = false;
> + rq = intel_context_find_active_request(ce);
> + if (!rq) {
> + head = ce->ring->tail;
> + goto out_replay;
> + }
>
> - if (!i915_request_started(rq))
> - stalled = false;
> + if (i915_request_started(rq))
> + local_stalled = true;
>
> - GEM_BUG_ON(i915_active_is_idle(&ce->active));
> - head = intel_ring_wrap(ce->ring, rq->head);
> - __i915_request_reset(rq, stalled);
> + GEM_BUG_ON(i915_active_is_idle(&ce->active));
> + head = intel_ring_wrap(ce->ring, rq->head);
>
> + __i915_request_reset(rq, local_stalled && stalled);
> out_replay:
> - guc_reset_state(ce, head, stalled);
> - __unwind_incomplete_requests(ce);
> + guc_reset_state(ce, head, local_stalled && stalled);
> +next_context:
> + if (i != number_children)
> + ce = list_next_entry(ce, parallel.child_link);
> + }
> +
> + __unwind_incomplete_requests(parent);
> out_put:
> - intel_context_put(ce);
> + intel_context_put(parent);
> }
>
> void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
> @@ -1286,7 +1309,8 @@ void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
>
> xa_unlock(&guc->context_lookup);
>
> - if (intel_context_is_pinned(ce))
> + if (intel_context_is_pinned(ce) &&
> + !intel_context_is_child(ce))
> __guc_reset_context(ce, stalled);
>
> intel_context_put(ce);
> @@ -1378,7 +1402,8 @@ void intel_guc_submission_cancel_requests(struct intel_guc *guc)
>
> xa_unlock(&guc->context_lookup);
>
> - if (intel_context_is_pinned(ce))
> + if (intel_context_is_pinned(ce) &&
> + !intel_context_is_child(ce))
> guc_cancel_context_requests(ce);
>
> intel_context_put(ce);
> @@ -2071,6 +2096,8 @@ static struct i915_sw_fence *guc_context_block(struct intel_context *ce)
> u16 guc_id;
> bool enabled;
>
> + GEM_BUG_ON(intel_context_is_child(ce));
> +
> spin_lock_irqsave(&ce->guc_state.lock, flags);
>
> incr_context_blocked(ce);
> @@ -2125,6 +2152,7 @@ static void guc_context_unblock(struct intel_context *ce)
> bool enable;
>
> GEM_BUG_ON(context_enabled(ce));
> + GEM_BUG_ON(intel_context_is_child(ce));
>
> spin_lock_irqsave(&ce->guc_state.lock, flags);
>
> @@ -2151,11 +2179,14 @@ static void guc_context_unblock(struct intel_context *ce)
> static void guc_context_cancel_request(struct intel_context *ce,
> struct i915_request *rq)
> {
> + struct intel_context *block_context =
> + request_to_scheduling_context(rq);
> +
> if (i915_sw_fence_signaled(&rq->submit)) {
> struct i915_sw_fence *fence;
>
> intel_context_get(ce);
> - fence = guc_context_block(ce);
> + fence = guc_context_block(block_context);
> i915_sw_fence_wait(fence);
> if (!i915_request_completed(rq)) {
> __i915_request_skip(rq);
> @@ -2169,7 +2200,7 @@ static void guc_context_cancel_request(struct intel_context *ce,
> */
> flush_work(&ce_to_guc(ce)->ct.requests.worker);
>
> - guc_context_unblock(ce);
> + guc_context_unblock(block_context);
> intel_context_put(ce);
> }
> }
> @@ -2195,6 +2226,8 @@ static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
> intel_wakeref_t wakeref;
> unsigned long flags;
>
> + GEM_BUG_ON(intel_context_is_child(ce));
> +
> guc_flush_submissions(guc);
>
> spin_lock_irqsave(&ce->guc_state.lock, flags);
More information about the Intel-gfx
mailing list