@@ -186,6 +186,9 @@ struct intel_context {
/* GuC lrc descriptor reference count */
atomic_t guc_id_ref;
+ /* GuC number of requests not ready */
+ atomic_t guc_num_rq_not_ready;
+
/*
* GuC ID link - in list when unpinned but guc_id still valid in GuC
*/
@@ -22,6 +22,7 @@
#include "intel_reset.h"
#include "uc/intel_guc.h"
+#include "uc/intel_guc_submission.h"
#define RESET_MAX_RETRIES 3
@@ -776,6 +777,14 @@ static void nop_submit_request(struct i915_request *request)
{
RQ_TRACE(request, "-EIO\n");
+ /*
+ * XXX: Kinda ugly to check for GuC submission here but this function is
+ * going away once we switch to the DRM scheduler so we can live with
+ * this for now.
+ */
+ if (intel_engine_uses_guc(request->engine))
+ intel_guc_decr_num_rq_not_ready(request->context);
+
request = i915_request_mark_eio(request);
if (request) {
i915_request_submit(request);
@@ -76,6 +76,7 @@ struct intel_guc {
struct ida guc_ids;
u32 num_guc_ids;
u32 max_guc_ids;
+ atomic_t num_guc_ids_not_ready;
struct list_head guc_id_list_no_ref;
struct list_head guc_id_list_unpinned;
@@ -1323,6 +1323,41 @@ static inline void queue_request(struct i915_sched_engine *sched_engine,
kick_tasklet(&rq->engine->gt->uc.guc);
}
+/* Macro to tweak heuristic, using a simple over 50% not ready for now */
+#define TOO_MANY_GUC_IDS_NOT_READY(avail, consumed) \
+ (consumed > avail / 2)
+static bool too_many_guc_ids_not_ready(struct intel_guc *guc,
+ struct intel_context *ce)
+{
+ u32 available_guc_ids, guc_ids_consumed;
+
+ available_guc_ids = guc->num_guc_ids;
+ guc_ids_consumed = atomic_read(&guc->num_guc_ids_not_ready);
+
+ if (TOO_MANY_GUC_IDS_NOT_READY(available_guc_ids, guc_ids_consumed)) {
+ set_and_update_guc_ids_exhausted(guc);
+ return true;
+ }
+
+ return false;
+}
+
+static void incr_num_rq_not_ready(struct intel_context *ce)
+{
+ struct intel_guc *guc = ce_to_guc(ce);
+
+ if (!atomic_fetch_add(1, &ce->guc_num_rq_not_ready))
+ atomic_inc(&guc->num_guc_ids_not_ready);
+}
+
+void intel_guc_decr_num_rq_not_ready(struct intel_context *ce)
+{
+ struct intel_guc *guc = ce_to_guc(ce);
+
+ if (atomic_fetch_add(-1, &ce->guc_num_rq_not_ready) == 1)
+ atomic_dec(&guc->num_guc_ids_not_ready);
+}
+
static bool need_tasklet(struct intel_guc *guc, struct intel_context *ce)
{
struct i915_sched_engine * const sched_engine =
@@ -1369,6 +1404,8 @@ static void guc_submit_request(struct i915_request *rq)
kick_tasklet(guc);
spin_unlock_irqrestore(&sched_engine->lock, flags);
+
+ intel_guc_decr_num_rq_not_ready(rq->context);
}
#define GUC_ID_START 64 /* First 64 guc_ids reserved */
@@ -2240,10 +2277,13 @@ static int guc_request_alloc(struct i915_request *rq)
GEM_BUG_ON(!intel_context_is_pinned(rq->context));
/*
- * guc_ids are exhausted, don't allocate one here, defer to submission
- * in the tasklet.
+ * guc_ids are exhausted or a heuristic is met indicating too many
+ * guc_ids are waiting on requests with submission dependencies (not
+ * ready to submit). Don't allocate one here, defer to submission in the
+ * tasklet.
*/
- if (test_and_update_guc_ids_exhausted(guc)) {
+ if (test_and_update_guc_ids_exhausted(guc) ||
+ too_many_guc_ids_not_ready(guc, ce)) {
set_bit(I915_FENCE_FLAG_GUC_ID_NOT_PINNED, &rq->fence.flags);
goto out;
}
@@ -2299,6 +2339,7 @@ static int guc_request_alloc(struct i915_request *rq)
*/
set_bit(I915_FENCE_FLAG_GUC_ID_NOT_PINNED, &rq->fence.flags);
set_and_update_guc_ids_exhausted(guc);
+ incr_num_rq_not_ready(ce);
return 0;
} else if (unlikely(ret < 0)) {
@@ -2321,6 +2362,8 @@ static int guc_request_alloc(struct i915_request *rq)
clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);
out:
+ incr_num_rq_not_ready(ce);
+
/*
* We block all requests on this context if a G2H is pending for a
* schedule disable or context deregistration as the GuC will fail a
@@ -3088,6 +3131,8 @@ void intel_guc_log_submission_info(struct intel_guc *guc,
drm_printf(p, "GuC submit flags: 0x%04lx\n", guc->flags);
drm_printf(p, "GuC total number request without guc_id: %d\n",
guc->total_num_rq_with_no_guc_id);
+ drm_printf(p, "GuC Number GuC IDs not ready: %d\n",
+ atomic_read(&guc->num_guc_ids_not_ready));
drm_printf(p, "GuC stall reason: %d\n", guc->submission_stall_reason);
drm_printf(p, "GuC stalled request: %s\n",
yesno(guc->stalled_rq));
@@ -3127,6 +3172,8 @@ void intel_guc_log_context_info(struct intel_guc *guc,
atomic_read(&ce->pin_count));
drm_printf(p, "\t\tGuC ID Ref Count: %u\n",
atomic_read(&ce->guc_id_ref));
+ drm_printf(p, "\t\tNumber Requests Not Ready: %u\n",
+ atomic_read(&ce->guc_num_rq_not_ready));
drm_printf(p, "\t\tSchedule State: 0x%x, 0x%x\n\n",
ce->guc_state.sched_state,
atomic_read(&ce->guc_sched_state_no_lock));
@@ -51,4 +51,6 @@ static inline bool intel_guc_submission_is_used(struct intel_guc *guc)
return intel_guc_is_used(guc) && intel_guc_submission_is_wanted(guc);
}
+void intel_guc_decr_num_rq_not_ready(struct intel_context *ce);
+
#endif
Add a heuristic which checks if over half of the available guc_ids are currently consumed by requests not ready to be submitted. If this heuristic is true at request creation time (normal guc_id allocation location) force all submissions + guc_ids allocations to tasklet. Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/i915/gt/intel_context_types.h | 3 ++ drivers/gpu/drm/i915/gt/intel_reset.c | 9 ++++ drivers/gpu/drm/i915/gt/uc/intel_guc.h | 1 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 53 +++++++++++++++++-- .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 2 + 5 files changed, 65 insertions(+), 3 deletions(-)