mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-09-04 18:09:57 +00:00
Code Issues Releases Wiki Activity

accel/habanalabs: fix wait_for_interrupt abortion flow

Browse source 
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@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
farah kassabri 2023-06-12 13:58:11 +03:00 committed by Oded Gabbay
parent eaa43a06b7
commit 2da9f8d805
1 changed files with 16 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
drivers/accel/habanalabs/common/command_submission.c
View file

@ -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;
}
}