This is a note to let you know that I've just added the patch titled
accel/habanalabs: fix EQ heartbeat mechanism
to the 6.7-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
accel-habanalabs-fix-eq-heartbeat-mechanism.patch
and it can be found in the queue-6.7 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit a171f44f33338be6fa6ef814a8f2735b0aa3bf04
Author: Farah Kassabri <fkassabri@xxxxxxxxx>
Date: Tue Oct 31 12:20:36 2023 +0200
accel/habanalabs: fix EQ heartbeat mechanism
[ Upstream commit d1958dce5ab6a3e089c60cf474e8c9b7e96e70ad ]
Stop rescheduling another heartbeat check when EQ heartbeat check fails
as it generates confusing logs in dmesg that the heartbeat fails.
Signed-off-by: Farah Kassabri <fkassabri@xxxxxxxxx>
Reviewed-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9e461c03e705..9290d4374551 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -1044,18 +1044,19 @@ static bool is_pci_link_healthy(struct hl_device *hdev)
return (vendor_id == PCI_VENDOR_ID_HABANALABS);
}
-static void hl_device_eq_heartbeat(struct hl_device *hdev)
+static int hl_device_eq_heartbeat_check(struct hl_device *hdev)
{
- u64 event_mask = HL_NOTIFIER_EVENT_DEVICE_RESET | HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE;
struct asic_fixed_properties *prop = &hdev->asic_prop;
if (!prop->cpucp_info.eq_health_check_supported)
- return;
+ return 0;
if (hdev->eq_heartbeat_received)
hdev->eq_heartbeat_received = false;
else
- hl_device_cond_reset(hdev, HL_DRV_RESET_HARD, event_mask);
+ return -EIO;
+
+ return 0;
}
static void hl_device_heartbeat(struct work_struct *work)
@@ -1072,10 +1073,9 @@ static void hl_device_heartbeat(struct work_struct *work)
/*
* For EQ health check need to check if driver received the heartbeat eq event
* in order to validate the eq is working.
+ * Only if both the EQ is healthy and we managed to send the next heartbeat reschedule.
*/
- hl_device_eq_heartbeat(hdev);
-
- if (!hdev->asic_funcs->send_heartbeat(hdev))
+ if ((!hl_device_eq_heartbeat_check(hdev)) && (!hdev->asic_funcs->send_heartbeat(hdev)))
goto reschedule;
if (hl_device_operational(hdev, NULL))
