[PATCH v6] can: mcp251xfd: fix infinite loop when xmit fails

[Vitor Soares]

From: Vitor Soares <vitor.soares@xxxxxxxxxxx>

When the mcp251xfd_start_xmit() function fails, the driver stops
processing messages, and the interrupt routine does not return,
running indefinitely even after killing the running application.

Error messages:
[  441.298819] mcp251xfd spi2.0 can0: ERROR in mcp251xfd_start_xmit: -16
[  441.306498] mcp251xfd spi2.0 can0: Transmit Event FIFO buffer not empty. (seq=0x000017c7, tef_tail=0x000017cf, tef_head=0x000017d0, tx_head=0x000017d3).
.. and repeat forever.

The issue can be triggered when multiple devices share the same
SPI interface. And there is concurrent access to the bus.

The problem occurs because tx_ring->head increments even if
mcp251xfd_start_xmit() fails. Consequently, the driver skips one
TX package while still expecting a response in
mcp251xfd_handle_tefif_one().

This patch resolves the issue by starting a workqueue to write
the tx obj synchronously if err = -EBUSY. In case of another error,
it decrements tx_ring->head, removes skb from the echo stack, and
drops the message.

Fixes: 55e5b97f003e ("can: mcp25xxfd: add driver for Microchip MCP25xxFD SPI CAN")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Vitor Soares <vitor.soares@xxxxxxxxxxx>
---

v5->v6
  - Move alloc/destroy workqueue to open()/stop() callbacks.
  - Change workqueue to workqueue ordered.
  - Return NETDEV_TX_BUSY if the worker is busy, replacing the previouse
    priv->tx_work_obj = NULL. With this change, setting priv->tx_work_obj = NULL
    is not necessary anymore.

V4->V5:
  - Start a workqueue to write tx obj with spi_sync() when spi_async() == -EBUSY.

V3->V4:
  - Leave can_put_echo_skb() and stop the queue if needed, before mcp251xfd_tx_obj_write().
  - Re-sync head and remove echo skb if mcp251xfd_tx_obj_write() fails.
  - Revert -> return NETDEV_TX_BUSY if mcp251xfd_tx_obj_write() == -EBUSY.

V2->V3:
  - Add tx_dropped stats.
  - netdev_sent_queue() only if can_put_echo_skb() succeed.

V1->V2:
  - Return NETDEV_TX_BUSY if mcp251xfd_tx_obj_write() == -EBUSY.
  - Rework the commit message to address the change above.
  - Change can_put_echo_skb() to be called after mcp251xfd_tx_obj_write() succeed.
    Otherwise, we get Kernel NULL pointer dereference error.

 .../net/can/spi/mcp251xfd/mcp251xfd-core.c    | 14 ++++-
 drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c  | 55 ++++++++++++++++---
 drivers/net/can/spi/mcp251xfd/mcp251xfd.h     |  5 ++
 3 files changed, 65 insertions(+), 9 deletions(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 1d9057dc44f2..bf1589aef1fc 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -1618,11 +1618,20 @@ static int mcp251xfd_open(struct net_device *ndev)
 	clear_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
 	can_rx_offload_enable(&priv->offload);
 
+	priv->wq = alloc_ordered_workqueue("%s-mcp251xfd_wq",
+					   WQ_FREEZABLE | WQ_MEM_RECLAIM,
+					   dev_name(&spi->dev));
+	if (!priv->wq) {
+		err = -ENOMEM;
+		goto out_can_rx_offload_disable;
+	}
+	INIT_WORK(&priv->tx_work, mcp251xfd_tx_obj_write_sync);
+
 	err = request_threaded_irq(spi->irq, NULL, mcp251xfd_irq,
 				   IRQF_SHARED | IRQF_ONESHOT,
 				   dev_name(&spi->dev), priv);
 	if (err)
-		goto out_can_rx_offload_disable;
+		goto out_destroy_workqueue;
 
 	err = mcp251xfd_chip_interrupts_enable(priv);
 	if (err)
@@ -1634,6 +1643,8 @@ static int mcp251xfd_open(struct net_device *ndev)
 
  out_free_irq:
 	free_irq(spi->irq, priv);
+ out_destroy_workqueue:
+	destroy_workqueue(priv->wq);
  out_can_rx_offload_disable:
 	can_rx_offload_disable(&priv->offload);
 	set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
@@ -1661,6 +1672,7 @@ static int mcp251xfd_stop(struct net_device *ndev)
 	hrtimer_cancel(&priv->tx_irq_timer);
 	mcp251xfd_chip_interrupts_disable(priv);
 	free_irq(ndev->irq, priv);
+	destroy_workqueue(priv->wq);
 	can_rx_offload_disable(&priv->offload);
 	mcp251xfd_timestamp_stop(priv);
 	mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
index 160528d3cc26..b1de8052a45c 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tx.c
@@ -131,6 +131,39 @@ mcp251xfd_tx_obj_from_skb(const struct mcp251xfd_priv *priv,
 	tx_obj->xfer[0].len = len;
 }
 
+static void mcp251xfd_tx_failure_drop(const struct mcp251xfd_priv *priv,
+				      struct mcp251xfd_tx_ring *tx_ring,
+				      int err)
+{
+	struct net_device *ndev = priv->ndev;
+	struct net_device_stats *stats = &ndev->stats;
+	unsigned int frame_len = 0;
+	u8 tx_head;
+
+	tx_ring->head--;
+	stats->tx_dropped++;
+	tx_head = mcp251xfd_get_tx_head(tx_ring);
+	can_free_echo_skb(ndev, tx_head, &frame_len);
+	netdev_completed_queue(ndev, 1, frame_len);
+	netif_wake_queue(ndev);
+
+	if (net_ratelimit())
+		netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err);
+}
+
+void mcp251xfd_tx_obj_write_sync(struct work_struct *work)
+{
+	struct mcp251xfd_priv *priv = container_of(work, struct mcp251xfd_priv,
+						   tx_work);
+	struct mcp251xfd_tx_obj *tx_obj = priv->tx_work_obj;
+	struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+	int err;
+
+	err = spi_sync(priv->spi, &tx_obj->msg);
+	if (err)
+		mcp251xfd_tx_failure_drop(priv, tx_ring, err);
+}
+
 static int mcp251xfd_tx_obj_write(const struct mcp251xfd_priv *priv,
 				  struct mcp251xfd_tx_obj *tx_obj)
 {
@@ -162,6 +195,11 @@ static bool mcp251xfd_tx_busy(const struct mcp251xfd_priv *priv,
 	return false;
 }
 
+static bool mcp251xfd_work_busy(struct work_struct *work)
+{
+	return work_busy(work);
+}
+
 netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 				 struct net_device *ndev)
 {
@@ -175,7 +213,8 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 	if (can_dev_dropped_skb(ndev, skb))
 		return NETDEV_TX_OK;
 
-	if (mcp251xfd_tx_busy(priv, tx_ring))
+	if (mcp251xfd_tx_busy(priv, tx_ring) ||
+	    mcp251xfd_work_busy(&priv->tx_work))
 		return NETDEV_TX_BUSY;
 
 	tx_obj = mcp251xfd_get_tx_obj_next(tx_ring);
@@ -193,13 +232,13 @@ netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 		netdev_sent_queue(priv->ndev, frame_len);
 
 	err = mcp251xfd_tx_obj_write(priv, tx_obj);
-	if (err)
-		goto out_err;
-
-	return NETDEV_TX_OK;
-
- out_err:
-	netdev_err(priv->ndev, "ERROR in %s: %d\n", __func__, err);
+	if (err == -EBUSY) {
+		netif_stop_queue(ndev);
+		priv->tx_work_obj = tx_obj;
+		queue_work(priv->wq, &priv->tx_work);
+	} else if (err) {
+		mcp251xfd_tx_failure_drop(priv, tx_ring, err);
+	}
 
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index 24510b3b8020..b35bfebd23f2 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -633,6 +633,10 @@ struct mcp251xfd_priv {
 	struct mcp251xfd_rx_ring *rx[MCP251XFD_FIFO_RX_NUM];
 	struct mcp251xfd_tx_ring tx[MCP251XFD_FIFO_TX_NUM];
 
+	struct workqueue_struct *wq;
+	struct work_struct tx_work;
+	struct mcp251xfd_tx_obj *tx_work_obj;
+
 	DECLARE_BITMAP(flags, __MCP251XFD_FLAGS_SIZE__);
 
 	u8 rx_ring_num;
@@ -952,6 +956,7 @@ void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
 void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv);
 void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv);
 
+void mcp251xfd_tx_obj_write_sync(struct work_struct *work);
 netdev_tx_t mcp251xfd_start_xmit(struct sk_buff *skb,
 				 struct net_device *ndev);
 
-- 
2.34.1