diff options
| author | Oded Gabbay <ogabbay@kernel.org> | 2022-01-18 23:10:43 +0100 |
|---|---|---|
| committer | Oded Gabbay <ogabbay@kernel.org> | 2022-02-28 13:22:03 +0100 |
| commit | 7a78d4d4819ec75c749d591c432d50cf7003448b (patch) | |
| tree | 06c73fd87cff2b899afcf61f8b1508540522a4be /drivers | |
| parent | habanalabs: fix user interrupt wait when timeout is 0 (diff) | |
| download | linux-7a78d4d4819ec75c749d591c432d50cf7003448b.tar.xz linux-7a78d4d4819ec75c749d591c432d50cf7003448b.zip | |
habanalabs: fix race between wait and irq
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>
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/misc/habanalabs/common/command_submission.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c index 8dd2f399d1c4..307a95a039e0 100644 --- a/drivers/misc/habanalabs/common/command_submission.c +++ b/drivers/misc/habanalabs/common/command_submission.c @@ -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); |