RDMA/bnxt_re: Add firmware stall check detection

Every completion will update last_seen value in the unit of jiffies.
last_seen field will be used to know if firmware is alive and
is useful to detect firmware stall.

Non blocking interface __wait_for_resp will have logic to detect
firmware stall. After every 10 second interval if __wait_for_resp
has not received completion for a given command it will check for
firmware stall condition.

If current jiffies is greater than last_seen
jiffies + RCFW_FW_STALL_TIMEOUT_SEC * HZ, it is a firmware stall.

Signed-off-by: Kashyap Desai <[email protected]>
Signed-off-by: Selvin Xavier <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Leon Romanovsky <[email protected]>

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -112,11 +112,13 @@ static int __wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie, u8 opcode)
 	do {
 		if (test_bit(ERR_DEVICE_DETACHED, &cmdq->flags))
 			return bnxt_qplib_map_rc(opcode);
+		if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
+			return -ETIMEDOUT;
 
-		/* Non zero means command completed */
 		wait_event_timeout(cmdq->waitq,
 				   !test_bit(cbit, cmdq->cmdq_bitmap),
-				   msecs_to_jiffies(10000));
+				   msecs_to_jiffies(RCFW_FW_STALL_TIMEOUT_SEC
+						    * 1000));
 
 		if (!test_bit(cbit, cmdq->cmdq_bitmap))
 			return 0;
@@ -126,6 +128,11 @@ static int __wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie, u8 opcode)
 		if (!test_bit(cbit, cmdq->cmdq_bitmap))
 			return 0;
 
+		/* Firmware stall is detected */
+		if (time_after(jiffies, cmdq->last_seen +
+			      (RCFW_FW_STALL_TIMEOUT_SEC * HZ)))
+			return -ENODEV;
+
 	} while (true);
 };
 
@@ -154,6 +161,8 @@ static int __block_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie, u8 opcode)
 	do {
 		if (test_bit(ERR_DEVICE_DETACHED, &cmdq->flags))
 			return bnxt_qplib_map_rc(opcode);
+		if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
+			return -ETIMEDOUT;
 
 		udelay(1);
 
@@ -184,9 +193,6 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw,
 	hwq = &cmdq->hwq;
 	pdev = rcfw->pdev;
 
-	if (test_bit(FIRMWARE_TIMED_OUT, &cmdq->flags))
-		return -ETIMEDOUT;
-
 	/* Cmdq are in 16-byte units, each request can consume 1 or more
 	 * cmdqe
 	 */
@@ -285,14 +291,21 @@ static int __poll_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie,
 	do {
 		if (test_bit(ERR_DEVICE_DETACHED, &cmdq->flags))
 			return bnxt_qplib_map_rc(opcode);
+		if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
+			return -ETIMEDOUT;
 
 		usleep_range(1000, 1001);
 
 		bnxt_qplib_service_creq(&rcfw->creq.creq_tasklet);
 		if (!test_bit(cbit, cmdq->cmdq_bitmap))
 			return 0;
-		if (jiffies_to_msecs(jiffies - issue_time) > 10000)
-			return -ETIMEDOUT;
+		if (jiffies_to_msecs(jiffies - issue_time) >
+		    (RCFW_FW_STALL_TIMEOUT_SEC * 1000)) {
+			/* Firmware stall is detected */
+			if (time_after(jiffies, cmdq->last_seen +
+				      (RCFW_FW_STALL_TIMEOUT_SEC * HZ)))
+				return -ENODEV;
+		}
 	} while (true);
 };
 
@@ -308,6 +321,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw,
 	/* Prevent posting if f/w is not in a state to process */
 	if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
 		return -ENXIO;
+	if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
+		return -ETIMEDOUT;
 
 	if (test_bit(FIRMWARE_INITIALIZED_FLAG, &cmdq->flags) &&
 	    opcode == CMDQ_BASE_OPCODE_INITIALIZE_FW) {
@@ -375,14 +390,15 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 		/* timed out */
 		dev_err(&rcfw->pdev->dev, "cmdq[%#x]=%#x timedout (%d)msec\n",
 			cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
-		set_bit(FIRMWARE_TIMED_OUT, &rcfw->cmdq.flags);
 		return rc;
 	}
 
 	if (rc) {
 		spin_lock_irqsave(&rcfw->cmdq.hwq.lock, flags);
 		crsqe = &rcfw->crsqe_tbl[cbit];
 		crsqe->is_waiter_alive = false;
+		if (rc == -ENODEV)
+			set_bit(FIRMWARE_STALL_DETECTED, &rcfw->cmdq.flags);
 		spin_unlock_irqrestore(&rcfw->cmdq.hwq.lock, flags);
 		return -ETIMEDOUT;
 	}
@@ -533,6 +549,17 @@ static int bnxt_qplib_process_qp_event(struct bnxt_qplib_rcfw *rcfw,
 		cookie &= RCFW_MAX_COOKIE_VALUE;
 		cbit = cookie % rcfw->cmdq_depth;
 		crsqe = &rcfw->crsqe_tbl[cbit];
+
+		if (WARN_ONCE(test_bit(FIRMWARE_STALL_DETECTED,
+				       &rcfw->cmdq.flags),
+		    "QPLIB: Unreponsive rcfw channel detected.!!")) {
+			dev_info(&pdev->dev,
+				 "rcfw timedout: cookie = %#x, free_slots = %d",
+				 cookie, crsqe->free_slots);
+			spin_unlock_irqrestore(&hwq->lock, flags);
+			return rc;
+		}
+
 		if (!test_and_clear_bit(cbit, rcfw->cmdq.cmdq_bitmap))
 			dev_warn(&pdev->dev,
 				 "CMD bit %d was not requested\n", cbit);
@@ -582,6 +609,7 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t)
 		 * reading any further.
 		 */
 		dma_rmb();
+		rcfw->cmdq.last_seen = jiffies;
 
 		type = creqe->type & CREQ_BASE_TYPE_MASK;
 		switch (type) {

drivers/infiniband/hw/bnxt_re/qplib_rcfw.h

@@ -51,6 +51,7 @@
 
 #define RCFW_DBR_PCI_BAR_REGION		2
 #define RCFW_DBR_BASE_PAGE_SHIFT	12
+#define RCFW_FW_STALL_TIMEOUT_SEC	40
 
 /* Cmdq contains a fix number of a 16-Byte slots */
 struct bnxt_qplib_cmdqe {
@@ -128,7 +129,6 @@ static inline u32 bnxt_qplib_set_cmd_slots(struct cmdq_base *req)
 
 #define RCFW_MAX_COOKIE_VALUE		(BNXT_QPLIB_CMDQE_MAX_CNT - 1)
 #define RCFW_CMD_IS_BLOCKING		0x8000
-#define RCFW_BLOCKED_CMD_WAIT_COUNT	20000000UL /* 20 sec */
 
 /* Crsq buf is 1024-Byte */
 struct bnxt_qplib_crsbe {
@@ -170,7 +170,7 @@ struct bnxt_qplib_qp_node {
 
 #define FIRMWARE_INITIALIZED_FLAG	(0)
 #define FIRMWARE_FIRST_FLAG		(31)
-#define FIRMWARE_TIMED_OUT		(3)
+#define FIRMWARE_STALL_DETECTED		(3)
 #define ERR_DEVICE_DETACHED             (4)
 
 struct bnxt_qplib_cmdq_mbox {
@@ -185,6 +185,7 @@ struct bnxt_qplib_cmdq_ctx {
 	wait_queue_head_t		waitq;
 	unsigned long			flags;
 	unsigned long			*cmdq_bitmap;
+	unsigned long			last_seen;
 	u32				seq_num;
 };