Assign contexts in parent-child relationship consecutive guc_ids. This
is accomplished by partitioning guc_id space between ones that need to
be consecutive (1/16 available guc_ids) and ones that do not (15/16 of
available guc_ids). The consecutive search is implemented via the bitmap
API.
This is a precursor to the full GuC multi-lrc implementation but aligns
to how GuC mutli-lrc interface is defined - guc_ids must be consecutive
when using the GuC multi-lrc interface.
v2:
(Daniel Vetter)
- Explicitly state why we assign consecutive guc_ids
v3:
(John Harrison)
- Bring back in spin lock
Signed-off-by: Matthew Brost <matthew.brost@xxxxxxxxx>
---
drivers/gpu/drm/i915/gt/uc/intel_guc.h | 6 +-
.../gpu/drm/i915/gt/uc/intel_guc_submission.c | 104 ++++++++++++++----
2 files changed, 86 insertions(+), 24 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 25a598e2b6e8..a9f4ec972bfb 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -76,9 +76,13 @@ struct intel_guc {
*/
spinlock_t lock;
/**
- * @guc_ids: used to allocate new guc_ids
+ * @guc_ids: used to allocate new guc_ids, single-lrc
*/
struct ida guc_ids;
+ /**
+ * @guc_ids_bitmap: used to allocate new guc_ids, multi-lrc
+ */
+ unsigned long *guc_ids_bitmap;
/**
* @guc_id_list: list of intel_context with valid guc_ids but no
* refs
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 1f2809187513..79e7732e83b2 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -128,6 +128,16 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
#define GUC_REQUEST_SIZE 64 /* bytes */
+/*
+ * We reserve 1/16 of the guc_ids for multi-lrc as these need to be contiguous
+ * per the GuC submission interface. A different allocation algorithm is used
+ * (bitmap vs. ida) between multi-lrc and single-lrc hence the reason to
+ * partition the guc_id space. We believe the number of multi-lrc contexts in
+ * use should be low and 1/16 should be sufficient. Minimum of 32 guc_ids for
+ * multi-lrc.
+ */
+#define NUMBER_MULTI_LRC_GUC_ID (GUC_MAX_LRC_DESCRIPTORS / 16)
+
/*
* Below is a set of functions which control the GuC scheduling state which
* require a lock.
@@ -1206,6 +1216,11 @@ int intel_guc_submission_init(struct intel_guc *guc)
INIT_WORK(&guc->submission_state.destroyed_worker,
destroyed_worker_func);
+ guc->submission_state.guc_ids_bitmap =
+ bitmap_zalloc(NUMBER_MULTI_LRC_GUC_ID, GFP_KERNEL);
+ if (!guc->submission_state.guc_ids_bitmap)
+ return -ENOMEM;
+
return 0;
}
@@ -1217,6 +1232,7 @@ void intel_guc_submission_fini(struct intel_guc *guc)
guc_lrc_desc_pool_destroy(guc);
guc_flush_destroyed_contexts(guc);
i915_sched_engine_put(guc->sched_engine);
+ bitmap_free(guc->submission_state.guc_ids_bitmap);
}
static inline void queue_request(struct i915_sched_engine *sched_engine,
@@ -1268,18 +1284,43 @@ static void guc_submit_request(struct i915_request *rq)
spin_unlock_irqrestore(&sched_engine->lock, flags);
}
-static int new_guc_id(struct intel_guc *guc)
+static int new_guc_id(struct intel_guc *guc, struct intel_context *ce)
{
- return ida_simple_get(&guc->submission_state.guc_ids, 0,
- GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL |
- __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
+ int ret;
+
+ GEM_BUG_ON(intel_context_is_child(ce));
+
+ if (intel_context_is_parent(ce))
+ ret = bitmap_find_free_region(guc->submission_state.guc_ids_bitmap,
+ NUMBER_MULTI_LRC_GUC_ID,
+ order_base_2(ce->parallel.number_children
+ + 1));
+ else
+ ret = ida_simple_get(&guc->submission_state.guc_ids,
+ NUMBER_MULTI_LRC_GUC_ID,
+ GUC_MAX_LRC_DESCRIPTORS,
+ GFP_KERNEL | __GFP_RETRY_MAYFAIL |
+ __GFP_NOWARN);
+ if (unlikely(ret < 0))
+ return ret;
+
+ ce->guc_id.id = ret;
+ return 0;
}
static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce)
{
+ GEM_BUG_ON(intel_context_is_child(ce));
+
if (!context_guc_id_invalid(ce)) {
- ida_simple_remove(&guc->submission_state.guc_ids,
- ce->guc_id.id);
+ if (intel_context_is_parent(ce))
+ bitmap_release_region(guc->submission_state.guc_ids_bitmap,
+ ce->guc_id.id,
+ order_base_2(ce->parallel.number_children
+ + 1));
