2023-09-28 09:42:53

by Oded Gabbay

[permalink] [raw]
Subject: [PATCH 2/3] accel/habanalabs: fix bug in decoder wait for cs completion

From: farah kassabri <[email protected]>

The decoder interrupts are handled in the interrupt context
same as all user interrupts.
In such case, the wait list should be protected by
spin_lock_irqsave in order to avoid deadlock that might happen
with the user submission flow.

Signed-off-by: farah kassabri <[email protected]>
Reviewed-by: Oded Gabbay <[email protected]>
Signed-off-by: Oded Gabbay <[email protected]>
---
.../accel/habanalabs/common/command_submission.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/accel/habanalabs/common/command_submission.c b/drivers/accel/habanalabs/common/command_submission.c
index 4f7b70d9754c..3aa6eeef443b 100644
--- a/drivers/accel/habanalabs/common/command_submission.c
+++ b/drivers/accel/habanalabs/common/command_submission.c
@@ -3526,7 +3526,7 @@ static int _hl_interrupt_wait_ioctl_user_addr(struct hl_device *hdev, struct hl_
u64 *timestamp)
{
struct hl_user_pending_interrupt *pend;
- unsigned long timeout;
+ unsigned long timeout, flags;
u64 completion_value;
long completion_rc;
int rc = 0;
@@ -3546,9 +3546,9 @@ static int _hl_interrupt_wait_ioctl_user_addr(struct hl_device *hdev, struct hl_
/* Add pending user interrupt to relevant list for the interrupt
* handler to monitor
*/
- spin_lock(&interrupt->wait_list_lock);
+ spin_lock_irqsave(&interrupt->wait_list_lock, flags);
list_add_tail(&pend->list_node, &interrupt->wait_list_head);
- spin_unlock(&interrupt->wait_list_lock);
+ spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);

/* We check for completion value as interrupt could have been received
* before we added the node to the wait list
@@ -3579,14 +3579,14 @@ static int _hl_interrupt_wait_ioctl_user_addr(struct hl_device *hdev, struct hl_
* If comparison fails, keep waiting until timeout expires
*/
if (completion_rc > 0) {
- spin_lock(&interrupt->wait_list_lock);
+ spin_lock_irqsave(&interrupt->wait_list_lock, flags);
/* reinit_completion must be called before we check for user
* completion value, otherwise, if interrupt is received after
* the comparison and before the next wait_for_completion,
* we will reach timeout and fail
*/
reinit_completion(&pend->fence.completion);
- spin_unlock(&interrupt->wait_list_lock);
+ spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);

if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 8)) {
dev_err(hdev->dev, "Failed to copy completion value from user\n");
@@ -3623,9 +3623,9 @@ static int _hl_interrupt_wait_ioctl_user_addr(struct hl_device *hdev, struct hl_
}

remove_pending_user_interrupt:
- spin_lock(&interrupt->wait_list_lock);
+ spin_lock_irqsave(&interrupt->wait_list_lock, flags);
list_del(&pend->list_node);
- spin_unlock(&interrupt->wait_list_lock);
+ spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);

*timestamp = ktime_to_ns(pend->fence.timestamp);

--
2.34.1