[PATCH net-next 2/9] eth: fbnic: use fw uptime to detect fw crashes

[Jakub Kicinski <kuba@kernel.org>]

Currently we only detect FW crashes when it stops responding
to heartbeat messages. FW has a watchdog which will reset it
in case of crashes. Use FW uptime sent in the heartbeat messages
to detect that the watchdog has fired.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic.h    |  4 ++++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.h |  6 ++++++
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 15 ++++++++++++++-
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 311c7dda911a..09058d847729 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -84,6 +84,10 @@ struct fbnic_dev {
 	/* Local copy of hardware statistics */
 	struct fbnic_hw_stats hw_stats;
 
+	/* Firmware time since boot in milliseconds */
+	u64 firmware_time;
+	u64 prev_firmware_time;
+
 	struct fbnic_fw_log fw_log;
 };
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index ec67b80809b0..c1de2793fa3d 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -201,6 +201,12 @@ enum {
 	FBNIC_FW_OWNERSHIP_MSG_MAX
 };
 
+enum {
+	FBNIC_FW_HEARTBEAT_UPTIME               = 0x0,
+	FBNIC_FW_HEARTBEAT_NUMBER_OF_MESSAGES   = 0x1,
+	FBNIC_FW_HEARTBEAT_MSG_MAX
+};
+
 enum {
 	FBNIC_FW_START_UPGRADE_ERROR		= 0x0,
 	FBNIC_FW_START_UPGRADE_SECTION		= 0x1,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 6e580654493c..72f750eea055 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -495,6 +495,11 @@ int fbnic_fw_xmit_ownership_msg(struct fbnic_dev *fbd, bool take_ownership)
 
 	fbd->last_heartbeat_request = req_time;
 
+	/* Set prev_firmware_time to 0 to avoid triggering firmware crash
+	 * detection now that we received a response from firmware.
+	 */
+	fbd->prev_firmware_time = 0;
+
 	/* Set heartbeat detection based on if we are taking ownership */
 	fbd->fw_heartbeat_enabled = take_ownership;
 
@@ -671,6 +676,9 @@ static int fbnic_fw_parse_ownership_resp(void *opaque,
 	/* Count the ownership response as a heartbeat reply */
 	fbd->last_heartbeat_response = jiffies;
 
+	/* Capture firmware time for logging and firmware crash check */
+	fbd->firmware_time = fta_get_uint(results, FBNIC_FW_HEARTBEAT_UPTIME);
+
 	return 0;
 }
 
@@ -685,6 +693,9 @@ static int fbnic_fw_parse_heartbeat_resp(void *opaque,
 
 	fbd->last_heartbeat_response = jiffies;
 
+	/* Capture firmware time for logging and firmware crash check */
+	fbd->firmware_time = fta_get_uint(results, FBNIC_FW_HEARTBEAT_UPTIME);
+
 	return 0;
 }
 
@@ -706,6 +717,7 @@ static int fbnic_fw_xmit_heartbeat_message(struct fbnic_dev *fbd)
 		goto free_message;
 
 	fbd->last_heartbeat_request = req_time;
+	fbd->prev_firmware_time = fbd->firmware_time;
 
 	return err;
 
@@ -766,7 +778,8 @@ void fbnic_fw_check_heartbeat(struct fbnic_dev *fbd)
 		return;
 
 	/* Was the last heartbeat response long time ago? */
-	if (!fbnic_fw_heartbeat_current(fbd)) {
+	if (!fbnic_fw_heartbeat_current(fbd) ||
+	    fbd->firmware_time < fbd->prev_firmware_time) {
 		dev_warn(fbd->dev,
 			 "Firmware did not respond to heartbeat message\n");
 		fbd->fw_heartbeat_enabled = false;
-- 
2.51.0