accel/habanalabs: split user interrupts pending list

Currently driver maintain one list for both pending user interrupts
which seeks to wait till CQ reaches it's target value and also the ones
that seeks to get timestamp records when the CQ reaches it's target
value.
This causes delay in handling the waiters which gets higher priority
than the timestamp records.
In order to solve this, let's split the list into two,
one for each case and each one is protected by it's own spinlock.
Waiters will be handled within the interrupt context first,
then the timestamp records will be set.
Freeing the timestamp related memory will be handled in a workqueue.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

drivers/accel/habanalabs/common/habanalabs.h

@@ -1128,7 +1128,9 @@ struct hl_ts_free_jobs {
  * @ts_free_jobs_data: timestamp free jobs related data
  * @type: user interrupt type
  * @wait_list_head: head to the list of user threads pending on this interrupt
+ * @ts_list_head: head to the list of timestamp records
  * @wait_list_lock: protects wait_list_head
+ * @ts_list_lock: protects ts_list_head
  * @timestamp: last timestamp taken upon interrupt
  * @interrupt_id: msix interrupt id
  */
@@ -1137,7 +1139,9 @@ struct hl_user_interrupt {
 	struct hl_ts_free_jobs		ts_free_jobs_data;
 	enum hl_user_interrupt_type	type;
 	struct list_head		wait_list_head;
+	struct list_head		ts_list_head;
 	spinlock_t			wait_list_lock;
+	spinlock_t			ts_list_lock;
 	ktime_t				timestamp;
 	u32				interrupt_id;
 };
@@ -1199,7 +1203,7 @@ struct timestamp_reg_info {
  * struct hl_user_pending_interrupt - holds a context to a user thread
  *                                    pending on an interrupt
  * @ts_reg_info: holds the timestamps registration nodes info
- * @wait_list_node: node in the list of user threads pending on an interrupt
+ * @list_node: node in the list of user threads pending on an interrupt or timestamp
  * @fence: hl fence object for interrupt completion
  * @cq_target_value: CQ target value
  * @cq_kernel_addr: CQ kernel address, to be used in the cq interrupt
@@ -1207,7 +1211,7 @@ struct timestamp_reg_info {
  */
 struct hl_user_pending_interrupt {
 	struct timestamp_reg_info	ts_reg_info;
-	struct list_head		wait_list_node;
+	struct list_head		list_node;
 	struct hl_fence			fence;
 	u64				cq_target_value;
 	u64				*cq_kernel_addr;
@@ -2742,6 +2746,8 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 	usr_intr.type = intr_type; \
 	INIT_LIST_HEAD(&usr_intr.wait_list_head); \
 	spin_lock_init(&usr_intr.wait_list_lock); \
+	INIT_LIST_HEAD(&usr_intr.ts_list_head); \
+	spin_lock_init(&usr_intr.ts_list_lock); \
 })
 
 struct hwmon_chip_info;
@@ -3712,7 +3718,7 @@ void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q);
 irqreturn_t hl_irq_handler_cq(int irq, void *arg);
 irqreturn_t hl_irq_handler_eq(int irq, void *arg);
 irqreturn_t hl_irq_handler_dec_abnrm(int irq, void *arg);
-irqreturn_t hl_irq_handler_user_interrupt(int irq, void *arg);
+irqreturn_t hl_irq_user_interrupt_handler(int irq, void *arg);
 irqreturn_t hl_irq_user_interrupt_thread_handler(int irq, void *arg);
 irqreturn_t hl_irq_eq_error_interrupt_thread_handler(int irq, void *arg);
 u32 hl_cq_inc_ptr(u32 ptr);

drivers/accel/habanalabs/common/irq.c

@@ -304,7 +304,7 @@ static int handle_registration_node(struct hl_device *hdev, struct hl_user_pendi
 	dev_dbg(hdev->dev, "Irq handle: Timestamp record (%p) ts cb address (%p), interrupt_id: %u\n",
 			pend, pend->ts_reg_info.timestamp_kernel_addr, intr->interrupt_id);
 
-	list_del(&pend->wait_list_node);
+	list_del(&pend->list_node);
 
 	/* Putting the refcount for ts_buff and cq_cb objects will be handled
 	 * in workqueue context, just add job to free_list.
@@ -326,12 +326,13 @@ static int handle_registration_node(struct hl_device *hdev, struct hl_user_pendi
 	return 0;
 }
 
-static void handle_user_interrupt(struct hl_device *hdev, struct hl_user_interrupt *intr)
+static void handle_user_interrupt_ts_list(struct hl_device *hdev, struct hl_user_interrupt *intr)
 {
 	struct list_head *ts_reg_free_list_head = NULL, *dynamic_alloc_list_head = NULL;
 	struct hl_user_pending_interrupt *pend, *temp_pend;
 	struct timestamp_reg_work_obj *job;
 	bool reg_node_handle_fail = false;
+	unsigned long flags;
 	int rc;
 
 	/* For registration nodes:
@@ -340,34 +341,27 @@ static void handle_user_interrupt(struct hl_device *hdev, struct hl_user_interru
 	 * or in irq handler context at all (since release functions are long and
 	 * might sleep), so we will need to handle that part in workqueue context.
 	 * To avoid handling kmalloc failure which compels us rolling back actions
-	 * and move nodes hanged on the free list back to the interrupt wait list
+	 * and move nodes hanged on the free list back to the interrupt ts list
 	 * we always alloc the job of the WQ at the beginning.
 	 */
 	job = kmalloc(sizeof(*job), GFP_ATOMIC);
 	if (!job)
 		return;
 
-	spin_lock(&intr->wait_list_lock);
-
-	list_for_each_entry_safe(pend, temp_pend, &intr->wait_list_head, wait_list_node) {
+	spin_lock_irqsave(&intr->ts_list_lock, flags);
+	list_for_each_entry_safe(pend, temp_pend, &intr->ts_list_head, list_node) {
 		if ((pend->cq_kernel_addr && *(pend->cq_kernel_addr) >= pend->cq_target_value) ||
 				!pend->cq_kernel_addr) {
-			if (pend->ts_reg_info.buf) {
-				if (!reg_node_handle_fail) {
-					rc = handle_registration_node(hdev, pend,
-							&ts_reg_free_list_head,
-							&dynamic_alloc_list_head, intr);
-					if (rc)
-						reg_node_handle_fail = true;
-				}
-			} else {
-				/* Handle wait target value node */
-				pend->fence.timestamp = intr->timestamp;
-				complete_all(&pend->fence.completion);
+			if (!reg_node_handle_fail) {
+				rc = handle_registration_node(hdev, pend,
+						&ts_reg_free_list_head,
+						&dynamic_alloc_list_head, intr);
+				if (rc)
+					reg_node_handle_fail = true;
 			}
 		}
 	}
-	spin_unlock(&intr->wait_list_lock);
+	spin_unlock_irqrestore(&intr->ts_list_lock, flags);
 
 	if (ts_reg_free_list_head) {
 		INIT_WORK(&job->free_obj, hl_ts_free_objects);
@@ -380,6 +374,23 @@ static void handle_user_interrupt(struct hl_device *hdev, struct hl_user_interru
 	}
 }
 
+static void handle_user_interrupt_wait_list(struct hl_device *hdev, struct hl_user_interrupt *intr)
+{
+	struct hl_user_pending_interrupt *pend, *temp_pend;
+	unsigned long flags;
+
+	spin_lock_irqsave(&intr->wait_list_lock, flags);
+	list_for_each_entry_safe(pend, temp_pend, &intr->wait_list_head, list_node) {
+		if ((pend->cq_kernel_addr && *(pend->cq_kernel_addr) >= pend->cq_target_value) ||
+				!pend->cq_kernel_addr) {
+			/* Handle wait target value node */
+			pend->fence.timestamp = intr->timestamp;
+			complete_all(&pend->fence.completion);
+		}
+	}
+	spin_unlock_irqrestore(&intr->wait_list_lock, flags);
+}
+
 static void handle_tpc_interrupt(struct hl_device *hdev)
 {
 	u64 event_mask;
@@ -401,19 +412,38 @@ static void handle_unexpected_user_interrupt(struct hl_device *hdev)
 }
 
 /**
- * hl_irq_handler_user_interrupt - irq handler for user interrupts
+ * hl_irq_user_interrupt_handler - irq handler for user interrupts.
  *
  * @irq: irq number
  * @arg: pointer to user interrupt structure
- *
  */
-irqreturn_t hl_irq_handler_user_interrupt(int irq, void *arg)
+irqreturn_t hl_irq_user_interrupt_handler(int irq, void *arg)
 {
 	struct hl_user_interrupt *user_int = arg;
+	struct hl_device *hdev = user_int->hdev;
 
 	user_int->timestamp = ktime_get();
+	switch (user_int->type) {
+	case HL_USR_INTERRUPT_CQ:
+		/* First handle user waiters threads */
+		handle_user_interrupt_wait_list(hdev, &hdev->common_user_cq_interrupt);
+		handle_user_interrupt_wait_list(hdev, user_int);
+
+		/* Second handle user timestamp registrations */
+		handle_user_interrupt_ts_list(hdev,  &hdev->common_user_cq_interrupt);
+		handle_user_interrupt_ts_list(hdev, user_int);
+		break;
+	case HL_USR_INTERRUPT_DECODER:
+		handle_user_interrupt_wait_list(hdev, &hdev->common_decoder_interrupt);
+
+		/* Handle decoder interrupt registered on this specific irq */
+		handle_user_interrupt_wait_list(hdev, user_int);
+		break;
+	default:
+		break;
+	}
 
-	return IRQ_WAKE_THREAD;
+	return IRQ_HANDLED;
 }
 
 /**
@@ -429,19 +459,8 @@ irqreturn_t hl_irq_user_interrupt_thread_handler(int irq, void *arg)
 	struct hl_user_interrupt *user_int = arg;
 	struct hl_device *hdev = user_int->hdev;
 
+	user_int->timestamp = ktime_get();
 	switch (user_int->type) {
-	case HL_USR_INTERRUPT_CQ:
-		handle_user_interrupt(hdev, &hdev->common_user_cq_interrupt);
-
-		/* Handle user cq interrupt registered on this specific irq */
-		handle_user_interrupt(hdev, user_int);
-		break;
-	case HL_USR_INTERRUPT_DECODER:
-		handle_user_interrupt(hdev, &hdev->common_decoder_interrupt);
-
-		/* Handle decoder interrupt registered on this specific irq */
-		handle_user_interrupt(hdev, user_int);
-		break;
 	case HL_USR_INTERRUPT_TPC:
 		handle_tpc_interrupt(hdev);
 		break;

drivers/accel/habanalabs/gaudi2/gaudi2.c

@@ -4227,9 +4227,7 @@ static int gaudi2_dec_enable_msix(struct hl_device *hdev)
 			rc = request_irq(irq, hl_irq_handler_dec_abnrm, 0,
 						gaudi2_irq_name(i), (void *) dec);
 		} else {
-			rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
-					hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
-					gaudi2_irq_name(i),
+			rc = request_irq(irq, hl_irq_user_interrupt_handler, 0, gaudi2_irq_name(i),
 					(void *) &hdev->user_interrupt[dec->core_id]);
 		}
 
@@ -4287,17 +4285,17 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
 	}
 
 	irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_TPC_ASSERT);
-	rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
-			hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
-			gaudi2_irq_name(GAUDI2_IRQ_NUM_TPC_ASSERT), &hdev->tpc_interrupt);
+	rc = request_threaded_irq(irq, NULL, hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
+					gaudi2_irq_name(GAUDI2_IRQ_NUM_TPC_ASSERT),
+					&hdev->tpc_interrupt);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to request IRQ %d", irq);
 		goto free_dec_irq;
 	}
 
 	irq = pci_irq_vector(hdev->pdev, GAUDI2_IRQ_NUM_UNEXPECTED_ERROR);
-	rc = request_irq(irq, hl_irq_handler_user_interrupt, 0,
-			gaudi2_irq_name(GAUDI2_IRQ_NUM_UNEXPECTED_ERROR),
+	rc = request_threaded_irq(irq, NULL, hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
+					gaudi2_irq_name(GAUDI2_IRQ_NUM_UNEXPECTED_ERROR),
 					&hdev->unexpected_error_interrupt);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to request IRQ %d", irq);
@@ -4309,10 +4307,8 @@ static int gaudi2_enable_msix(struct hl_device *hdev)
 			i++, j++, user_irq_init_cnt++) {
 
 		irq = pci_irq_vector(hdev->pdev, i);
-		rc = request_threaded_irq(irq, hl_irq_handler_user_interrupt,
-						hl_irq_user_interrupt_thread_handler, IRQF_ONESHOT,
-						gaudi2_irq_name(i), &hdev->user_interrupt[j]);
-
+		rc = request_irq(irq, hl_irq_user_interrupt_handler, 0, gaudi2_irq_name(i),
+				&hdev->user_interrupt[j]);
 		if (rc) {
 			dev_err(hdev->dev, "Failed to request IRQ %d", irq);
 			goto free_user_irq;