its' -> itsUpdate 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
Should this not check the parent as well/instead?requests as needed. Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx> --- drivers/gpu/drm/i915/gt/intel_context.c | 11 ++-- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 63 +++++++++++++------ 2 files changed, 51 insertions(+), 23 deletions(-) diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 00d1aee6d199..5615be32879c 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -528,20 +528,21 @@ 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));
And to be clear, this can be called on regular contexts (where ce == parent) and on both the parent or child contexts of multi-LRC contexts (where ce may or may not match parent)?
- spin_lock_irqsave(&ce->guc_state.lock, flags);
- list_for_each_entry_reverse(rq, &ce->guc_state.requests,
+ spin_lock_irqsave(&parent->guc_state.lock, flags);
+ list_for_each_entry_reverse(rq, &parent->guc_state.requests,
sched.link) {
- if (i915_request_completed(rq))
+ if (i915_request_completed(rq) && rq->context == ce)
'rq->context == ce' means:- single-LRC context, rq is owned by ce
- multi-LRC context, ce is child, rq really belongs to ce but is being tracked by parent
- multi-LRC context, ce is parent, rq really is owned by ce
Would be clearer to say 'if(rq->ce != ce) continue;' and leave 'active = rq;' alone?break; - active = rq; + active = (rq->context == ce) ? rq : active;
And again, the intention is to ignore requests that are owned by other members of the same multi-LRC group?
Would be good to add some documentation to this function to explain the above (assuming my description is correct?).
}
- 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 f0b60fecf253..e34e0ea9136a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -670,6 +670,11 @@ static 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);
@@ -1179,10 +1184,13 @@ __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->guc_number_children;
If this is a child context, does it not need to pull the child count
from the parent? Likewise the list/link pointers below? Or does each
child context have a full list of its siblings + parent?
bool skip = false;
+ struct intel_context *parent = ce;
intel_context_get(ce);
@@ -1209,25 +1217,34 @@ 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 (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;
+ GEM_BUG_ON(i915_active_is_idle(&ce->active));
+ head = intel_ring_wrap(ce->ring, rq->head);
- GEM_BUG_ON(i915_active_is_idle(&ce->active));
- head = intel_ring_wrap(ce->ring, rq->head);
- __i915_request_reset(rq, stalled);
+ if (i915_request_started(rq))
Why change the ordering of the started test versus the wrap/reset
call? Is it significant? Why is it now important to be reversed?Can this not be put in to the step clause of the for statement?+ local_stalled = true; + __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, guc_child_link);
As above, I think this function would benefit from some comments to explain exactly what is being done and why.+ } + + __unwind_incomplete_requests(parent); out_put: - intel_context_put(ce); + intel_context_put(parent);
John.
}
void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
@@ -1248,7 +1265,8 @@ 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);
@@ -1340,7 +1358,8 @@ 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);
@@ -2031,6 +2050,8 @@ 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);
@@ -2068,6 +2089,7 @@ 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);
@@ -2099,11 +2121,14 @@ 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);
@@ -2117,7 +2142,7 @@ 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);
}
}
@@ -2143,6 +2168,8 @@ 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);
