leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity

habanalabs: fix race between wait and irq

Browse Source 
There is a race in the user interrupts code, where between checking
the target value and adding the new pend to the list, there is a chance
the interrupt happened.

In that case, no one will complete the node, and we will get a timeout
on it.

Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
This commit is contained in:
Oded Gabbay 2022-01-19 00:10:43 +02:00
parent 54faa5607b
commit 7a78d4d481
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
drivers/misc/habanalabs/common/command_submission.c
View File

@ -2892,16 +2892,21 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
pend->cq_kernel_addr = (u64 *) cb->kernel_address + cq_counters_offset;
pend->cq_target_value = target_value;
spin_lock_irqsave(&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
*/
if (*pend->cq_kernel_addr >= target_value) {
spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
*status = HL_WAIT_CS_STATUS_COMPLETED;
/* There was no interrupt, we assume the completion is now. */
pend->fence.timestamp = ktime_get();
goto set_timestamp;
} else if (!timeout_us) {
spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
*status = HL_WAIT_CS_STATUS_BUSY;
pend->fence.timestamp = ktime_get();
goto set_timestamp;
@ -2910,7 +2915,6 @@ static int _hl_interrupt_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
/* Add pending user interrupt to relevant list for the interrupt
* handler to monitor
*/
spin_lock_irqsave(&interrupt->wait_list_lock, flags);
list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head);
spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);