octeon_ep: add heartbeat monitor

Monitor periodic heartbeat messages from device firmware.
Presence of heartbeat indicates the device is active and running.
If the heartbeat is missed for configured interval indicates
firmware has crashed and device is unusable; in this case, PF driver
stops and uninitialize the device.

Signed-off-by: Veerasenareddy Burru <[email protected]>
Signed-off-by: Abhijit Ayarekar <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: vburru

drivers/net/ethernet/marvell/octeon_ep/octep_cn9k_pf.c

@@ -16,6 +16,9 @@
 #define CTRL_MBOX_MAX_PF	128
 #define CTRL_MBOX_SZ		((size_t)(0x400000 / CTRL_MBOX_MAX_PF))
 
+#define FW_HB_INTERVAL_IN_SECS		1
+#define FW_HB_MISS_COUNT		10
+
 /* Names of Hardware non-queue generic interrupts */
 static char *cn93_non_ioq_msix_names[] = {
 	"epf_ire_rint",
@@ -249,6 +252,10 @@ static void octep_init_config_cn93_pf(struct octep_device *oct)
 	conf->ctrl_mbox_cfg.barmem_addr = (void __iomem *)oct->mmio[2].hw_addr +
 					   (0x400000ull * 7) +
 					   (link * CTRL_MBOX_SZ);
+
+	conf->hb_interval = FW_HB_INTERVAL_IN_SECS;
+	conf->max_hb_miss_cnt = FW_HB_MISS_COUNT;
+
 }
 
 /* Setup registers for a hardware Tx Queue  */
@@ -383,6 +390,8 @@ static bool octep_poll_non_ioq_interrupts_cn93_pf(struct octep_device *oct)
 		octep_write_csr64(oct, CN93_SDP_EPF_OEI_RINT, reg0);
 		if (reg0 & CN93_SDP_EPF_OEI_RINT_DATA_BIT_MBOX)
 			queue_work(octep_wq, &oct->ctrl_mbox_task);
+		else if (reg0 & CN93_SDP_EPF_OEI_RINT_DATA_BIT_HBEAT)
+			atomic_set(&oct->hb_miss_cnt, 0);
 
 		handled = true;
 	}

drivers/net/ethernet/marvell/octeon_ep/octep_config.h

@@ -200,5 +200,11 @@ struct octep_config {
 
 	/* ctrl mbox config */
 	struct octep_ctrl_mbox_config ctrl_mbox_cfg;
+
+	/* Configured maximum heartbeat miss count */
+	u32 max_hb_miss_cnt;
+
+	/* Configured firmware heartbeat interval in secs */
+	u32 hb_interval;
 };
 #endif /* _OCTEP_CONFIG_H_ */

drivers/net/ethernet/marvell/octeon_ep/octep_main.c

@@ -901,6 +901,37 @@ static void octep_intr_poll_task(struct work_struct *work)
 			   msecs_to_jiffies(OCTEP_INTR_POLL_TIME_MSECS));
 }
 
+/**
+ * octep_hb_timeout_task - work queue task to check firmware heartbeat.
+ *
+ * @work: pointer to hb work_struct
+ *
+ * Check for heartbeat miss count. Uninitialize oct device if miss count
+ * exceeds configured max heartbeat miss count.
+ *
+ **/
+static void octep_hb_timeout_task(struct work_struct *work)
+{
+	struct octep_device *oct = container_of(work, struct octep_device,
+						hb_task.work);
+
+	int miss_cnt;
+
+	miss_cnt = atomic_inc_return(&oct->hb_miss_cnt);
+	if (miss_cnt < oct->conf->max_hb_miss_cnt) {
+		queue_delayed_work(octep_wq, &oct->hb_task,
+				   msecs_to_jiffies(oct->conf->hb_interval * 1000));
+		return;
+	}
+
+	dev_err(&oct->pdev->dev, "Missed %u heartbeats. Uninitializing\n",
+		miss_cnt);
+	rtnl_lock();
+	if (netif_running(oct->netdev))
+		octep_stop(oct->netdev);
+	rtnl_unlock();
+}
+
 /**
  * octep_ctrl_mbox_task - work queue task to handle ctrl mbox messages.
  *
@@ -938,7 +969,7 @@ static const char *octep_devid_to_str(struct octep_device *oct)
 int octep_device_setup(struct octep_device *oct)
 {
 	struct pci_dev *pdev = oct->pdev;
-	int i;
+	int i, ret;
 
 	/* allocate memory for oct->conf */
 	oct->conf = kzalloc(sizeof(*oct->conf), GFP_KERNEL);
@@ -973,7 +1004,15 @@ int octep_device_setup(struct octep_device *oct)
 
 	oct->pkind = CFG_GET_IQ_PKIND(oct->conf);
 
-	return octep_ctrl_net_init(oct);
+	ret = octep_ctrl_net_init(oct);
+	if (ret)
+		return ret;
+
+	atomic_set(&oct->hb_miss_cnt, 0);
+	INIT_DELAYED_WORK(&oct->hb_task, octep_hb_timeout_task);
+	queue_delayed_work(octep_wq, &oct->hb_task,
+			   msecs_to_jiffies(oct->conf->hb_interval * 1000));
+	return 0;
 
 unsupported_dev:
 	for (i = 0; i < OCTEP_MMIO_REGIONS; i++)
@@ -1002,6 +1041,7 @@ static void octep_device_cleanup(struct octep_device *oct)
 	}
 
 	octep_ctrl_net_uninit(oct);
+	cancel_delayed_work_sync(&oct->hb_task);
 
 	oct->hw_ops.soft_reset(oct);
 	for (i = 0; i < OCTEP_MMIO_REGIONS; i++) {

drivers/net/ethernet/marvell/octeon_ep/octep_main.h

@@ -280,6 +280,13 @@ struct octep_device {
 	bool poll_non_ioq_intr;
 	/* Work entry to poll non-ioq interrupts */
 	struct delayed_work intr_poll_task;
+
+	/* Firmware heartbeat timer */
+	struct timer_list hb_timer;
+	/* Firmware heartbeat miss count tracked by timer */
+	atomic_t hb_miss_cnt;
+	/* Task to reset device on heartbeat miss */
+	struct delayed_work hb_task;
 };
 
 static inline u16 OCTEP_MAJOR_REV(struct octep_device *oct)

drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h

@@ -367,5 +367,7 @@
 
 /* bit 0 for control mbox interrupt */
 #define CN93_SDP_EPF_OEI_RINT_DATA_BIT_MBOX	BIT_ULL(0)
+/* bit 1 for firmware heartbeat interrupt */
+#define CN93_SDP_EPF_OEI_RINT_DATA_BIT_HBEAT	BIT_ULL(1)
 
 #endif /* _OCTEP_REGS_CN9K_PF_H_ */