[PATCH net-next v2 4/7] gve: Recover from queue stall due to missed IRQ

[Jeroen de Borst <jeroendb@google.com>]

From: John Fraker <jfraker@google.com>

Don't always reset the driver on a TX timeout. Attempt to
recover by kicking the queue in case an IRQ was missed.

Fixes: 9e5f7d26a4c08 ("gve: Add workqueue and reset support")
Signed-off-by: John Fraker <jfraker@google.com>
Signed-off-by: David Awogbemila <awogbemila@google.com>
---
 drivers/net/ethernet/google/gve/gve.h        |  4 +-
 drivers/net/ethernet/google/gve/gve_adminq.h |  1 +
 drivers/net/ethernet/google/gve/gve_main.c   | 48 +++++++++++++++++++-
 3 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 3de561e22659..51ed8fe71d2d 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -30,7 +30,7 @@
 #define GVE_MIN_MSIX 3
 
 /* Numbers of gve tx/rx stats in stats report. */
-#define GVE_TX_STATS_REPORT_NUM	5
+#define GVE_TX_STATS_REPORT_NUM	6
 #define GVE_RX_STATS_REPORT_NUM	2
 
 /* Interval to schedule a stats report update, 20000ms. */
@@ -413,7 +413,9 @@ struct gve_tx_ring {
 	u32 q_num ____cacheline_aligned; /* queue idx */
 	u32 stop_queue; /* count of queue stops */
 	u32 wake_queue; /* count of queue wakes */
+	u32 queue_timeout; /* count of queue timeouts */
 	u32 ntfy_id; /* notification block index */
+	u32 last_kick_msec; /* Last time the queue was kicked */
 	dma_addr_t bus; /* dma address of the descr ring */
 	dma_addr_t q_resources_bus; /* dma address of the queue resources */
 	dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 47c3d8f313fc..3953f6f7a427 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -270,6 +270,7 @@ enum gve_stat_names {
 	TX_LAST_COMPLETION_PROCESSED	= 5,
 	RX_NEXT_EXPECTED_SEQUENCE	= 6,
 	RX_BUFFERS_POSTED		= 7,
+	TX_TIMEOUT_CNT			= 8,
 	// stats from NIC
 	RX_QUEUE_DROP_CNT		= 65,
 	RX_NO_BUFFERS_POSTED		= 66,
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index b6805ad2011b..7647cd05b1d2 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -24,6 +24,9 @@
 #define GVE_VERSION		"1.0.0"
 #define GVE_VERSION_PREFIX	"GVE-"
 
+// Minimum amount of time between queue kicks in msec (10 seconds)
+#define MIN_TX_TIMEOUT_GAP (1000 * 10)
+
 const char gve_version_str[] = GVE_VERSION;
 static const char gve_version_prefix[] = GVE_VERSION_PREFIX;
 
@@ -1121,9 +1124,47 @@ static void gve_turnup(struct gve_priv *priv)
 
 static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue)
 {
-	struct gve_priv *priv = netdev_priv(dev);
+	struct gve_notify_block *block;
+	struct gve_tx_ring *tx = NULL;
+	struct gve_priv *priv;
+	u32 last_nic_done;
+	u32 current_time;
+	u32 ntfy_idx;
+
+	netdev_info(dev, "Timeout on tx queue, %d", txqueue);
+	priv = netdev_priv(dev);
+	if (txqueue > priv->tx_cfg.num_queues)
+		goto reset;
+
+	ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue);
+	if (ntfy_idx > priv->num_ntfy_blks)
+		goto reset;
+
+	block = &priv->ntfy_blocks[ntfy_idx];
+	tx = block->tx;
 
+	current_time = jiffies_to_msecs(jiffies);
+	if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time)
+		goto reset;
+
+	/* Check to see if there are missed completions, which will allow us to
+	 * kick the queue.
+	 */
+	last_nic_done = gve_tx_load_event_counter(priv, tx);
+	if (last_nic_done - tx->done) {
+		netdev_info(dev, "Kicking queue %d", txqueue);
+		iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block));
+		napi_schedule(&block->napi);
+		tx->last_kick_msec = current_time;
+		goto out;
+	} // Else reset.
+
+reset:
 	gve_schedule_reset(priv);
+
+out:
+	if (tx)
+		tx->queue_timeout++;
 	priv->tx_timeo_cnt++;
 }
 
@@ -1252,6 +1293,11 @@ void gve_handle_report_stats(struct gve_priv *priv)
 				.value = cpu_to_be64(last_completion),
 				.queue_id = cpu_to_be32(idx),
 			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(TX_TIMEOUT_CNT),
+				.value = cpu_to_be64(priv->tx[idx].queue_timeout),
+				.queue_id = cpu_to_be32(idx),
+			};
 		}
 	}
 	/* rx stats */
-- 
2.33.0.882.g93a45727a2-goog

v2: Unchanged