From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 16 Sep 2025 23:14:13 +0000 (-0700)
Subject: eth: fbnic: use fw uptime to detect fw crashes
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=7fd1f7bac2b878eb203fb316e03e1b87e8b86f6e;p=users%2Fhch%2Fmisc.git

eth: fbnic: use fw uptime to detect fw crashes

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 ownership and
heartbeat messages to detect that the watchdog has fired
(uptime went down).

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250916231420.1693955-3-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---

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.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 6e580654493c..9b39a73e4c35 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 until we receive the second uptime in a heartbeat resp.
+	 */
+	fbd->prev_firmware_time = 0;
+
 	/* Set heartbeat detection based on if we are taking ownership */
 	fbd->fw_heartbeat_enabled = take_ownership;
 
@@ -660,6 +665,7 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 }
 
 static const struct fbnic_tlv_index fbnic_ownership_resp_index[] = {
+	FBNIC_TLV_ATTR_U64(FBNIC_FW_OWNERSHIP_TIME),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -671,10 +677,14 @@ 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_OWNERSHIP_TIME);
+
 	return 0;
 }
 
 static const struct fbnic_tlv_index fbnic_heartbeat_resp_index[] = {
+	FBNIC_TLV_ATTR_U64(FBNIC_FW_HEARTBEAT_UPTIME),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -685,6 +695,9 @@ 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 +719,7 @@ 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 +780,8 @@ 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;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index ec67b80809b0..be7f2dc88698 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -198,9 +198,16 @@ enum {
 
 enum {
 	FBNIC_FW_OWNERSHIP_FLAG			= 0x0,
+	FBNIC_FW_OWNERSHIP_TIME			= 0x1,
 	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,