[PATCH 2/3] accel/habanalabs: fix wait_for_interrupt abortion flow

Oded Gabbay ogabbay at kernel.org
Mon Jun 12 10:59:20 UTC 2023


From: farah kassabri <fkassabri at habana.ai>

When the driver needs to abort waiters for interrupts, for cases
such as critical events that occur and driver need to do hard reset,
in such scenario the driver will complete the fence to wake up the
waiting thread, and will set the fence error indication.
The return value of the completion API will be greater than 0
since it will return the timeout, but as this indicates successful
completion, the driver should mark it as aborted.

Signed-off-by: farah kassabri <fkassabri at habana.ai>
Reviewed-by: Oded Gabbay <ogabbay at kernel.org>
Signed-off-by: Oded Gabbay <ogabbay at kernel.org>
---
 .../habanalabs/common/command_submission.c    | 32 +++++++++----------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/accel/habanalabs/common/command_submission.c b/drivers/accel/habanalabs/common/command_submission.c
index 02ac6d754fba..396bbf8652b7 100644
--- a/drivers/accel/habanalabs/common/command_submission.c
+++ b/drivers/accel/habanalabs/common/command_submission.c
@@ -3449,7 +3449,15 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
 	completion_rc = wait_for_completion_interruptible_timeout(&pend->fence.completion,
 								timeout);
 	if (completion_rc > 0) {
-		*status = HL_WAIT_CS_STATUS_COMPLETED;
+		if (pend->fence.error == -EIO) {
+			dev_err_ratelimited(hdev->dev,
+					"interrupt based wait ioctl aborted(error:%d) due to a reset cycle initiated\n",
+					pend->fence.error);
+			rc = -EIO;
+			*status = HL_WAIT_CS_STATUS_ABORTED;
+		} else {
+			*status = HL_WAIT_CS_STATUS_COMPLETED;
+		}
 	} else {
 		if (completion_rc == -ERESTARTSYS) {
 			dev_err_ratelimited(hdev->dev,
@@ -3458,21 +3466,13 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
 			rc = -EINTR;
 			*status = HL_WAIT_CS_STATUS_ABORTED;
 		} else {
-			if (pend->fence.error == -EIO) {
-				dev_err_ratelimited(hdev->dev,
-						"interrupt based wait ioctl aborted(error:%d) due to a reset cycle initiated\n",
-						pend->fence.error);
-				rc = -EIO;
-				*status = HL_WAIT_CS_STATUS_ABORTED;
-			} else {
-				/* The wait has timed-out. We don't know anything beyond that
-				 * because the workload wasn't submitted through the driver.
-				 * Therefore, from driver's perspective, the workload is still
-				 * executing.
-				 */
-				rc = 0;
-				*status = HL_WAIT_CS_STATUS_BUSY;
-			}
+			/* The wait has timed-out. We don't know anything beyond that
+			 * because the workload was not submitted through the driver.
+			 * Therefore, from driver's perspective, the workload is still
+			 * executing.
+			 */
+			rc = 0;
+			*status = HL_WAIT_CS_STATUS_BUSY;
 		}
 	}
 
-- 
2.40.1



More information about the dri-devel mailing list