Merge remote-tracking branch 'torvalds/master' into perf/core

To pick up the fixes sent for v5.12 and continue development based on
v5.12-rc2, i.e. without the swap on file bug.

This also gets a slightly newer and better tools/perf/arch/arm/util/cs-etm.c
patch version, using the BIT() macro, that had already been slated to
v5.13 but ended up going to v5.12-rc1 on an older version.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 46 insertions, 5 deletions

diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index 76217258780a..0f335182267f 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -38,7 +38,7 @@ static inline int queue_free_slots(struct hl_hw_queue *q, u32 queue_len)
 		return (abs(delta) - queue_len);
 }
 
-void hl_int_hw_queue_update_ci(struct hl_cs *cs)
+void hl_hw_queue_update_ci(struct hl_cs *cs)
 {
 	struct hl_device *hdev = cs->ctx->hdev;
 	struct hl_hw_queue *q;
@@ -53,8 +53,13 @@ void hl_int_hw_queue_update_ci(struct hl_cs *cs)
 	if (!hdev->asic_prop.max_queues || q->queue_type == QUEUE_TYPE_HW)
 		return;
 
+	/* We must increment CI for every queue that will never get a
+	 * completion, there are 2 scenarios this can happen:
+	 * 1. All queues of a non completion CS will never get a completion.
+	 * 2. Internal queues never gets completion.
+	 */
 	for (i = 0 ; i < hdev->asic_prop.max_queues ; i++, q++) {
-		if (q->queue_type == QUEUE_TYPE_INT)
+		if (!cs_needs_completion(cs) || q->queue_type == QUEUE_TYPE_INT)
 			atomic_add(cs->jobs_in_queue_cnt[i], &q->ci);
 	}
 }
@@ -292,6 +297,10 @@ static void ext_queue_schedule_job(struct hl_cs_job *job)
 	len = job->job_cb_size;
 	ptr = cb->bus_address;
 
+	/* Skip completion flow in case this is a non completion CS */
+	if (!cs_needs_completion(job->cs))
+		goto submit_bd;
+
 	cq_pkt.data = cpu_to_le32(
 			((q->pi << CQ_ENTRY_SHADOW_INDEX_SHIFT)
 				& CQ_ENTRY_SHADOW_INDEX_MASK) |
@@ -318,6 +327,7 @@ static void ext_queue_schedule_job(struct hl_cs_job *job)
 
 	cq->pi = hl_cq_inc_ptr(cq->pi);
 
+submit_bd:
 	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
 }
 
@@ -525,6 +535,7 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 	struct hl_cs_job *job, *tmp;
 	struct hl_hw_queue *q;
 	int rc = 0, i, cq_cnt;
+	bool first_entry;
 	u32 max_queues;
 
 	cntr = &hdev->aggregated_cs_counters;
@@ -548,7 +559,9 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 			switch (q->queue_type) {
 			case QUEUE_TYPE_EXT:
 				rc = ext_queue_sanity_checks(hdev, q,
-						cs->jobs_in_queue_cnt[i], true);
+						cs->jobs_in_queue_cnt[i],
+						cs_needs_completion(cs) ?
+								true : false);
 				break;
 			case QUEUE_TYPE_INT:
 				rc = int_queue_sanity_checks(hdev, q,
@@ -583,12 +596,38 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 		hdev->asic_funcs->collective_wait_init_cs(cs);
 
 	spin_lock(&hdev->cs_mirror_lock);
+
+	/* Verify staged CS exists and add to the staged list */
+	if (cs->staged_cs && !cs->staged_first) {
+		struct hl_cs *staged_cs;
+
+		staged_cs = hl_staged_cs_find_first(hdev, cs->staged_sequence);
+		if (!staged_cs) {
+			dev_err(hdev->dev,
+				"Cannot find staged submission sequence %llu",
+				cs->staged_sequence);
+			rc = -EINVAL;
+			goto unlock_cs_mirror;
+		}
+
+		if (is_staged_cs_last_exists(hdev, staged_cs)) {
+			dev_err(hdev->dev,
+				"Staged submission sequence %llu already submitted",
+				cs->staged_sequence);
+			rc = -EINVAL;
+			goto unlock_cs_mirror;
+		}
+
+		list_add_tail(&cs->staged_cs_node, &staged_cs->staged_cs_node);
+	}
+
 	list_add_tail(&cs->mirror_node, &hdev->cs_mirror_list);
 
 	/* Queue TDR if the CS is the first entry and if timeout is wanted */
+	first_entry = list_first_entry(&hdev->cs_mirror_list,
+					struct hl_cs, mirror_node) == cs;
 	if ((hdev->timeout_jiffies != MAX_SCHEDULE_TIMEOUT) &&
-			(list_first_entry(&hdev->cs_mirror_list,
-					struct hl_cs, mirror_node) == cs)) {
+				first_entry && cs_needs_timeout(cs)) {
 		cs->tdr_active = true;
 		schedule_delayed_work(&cs->work_tdr, hdev->timeout_jiffies);
 
@@ -623,6 +662,8 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 
 	goto out;
 
+unlock_cs_mirror:
+	spin_unlock(&hdev->cs_mirror_lock);
 unroll_cq_resv:
 	q = &hdev->kernel_queues[0];
 	for (i = 0 ; (i < max_queues) && (cq_cnt > 0) ; i++, q++) {