Merge tag 'linux-can-fixes-for-6.10-20240621' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can

Marc Kleine-Budde says:

====================
pull-request: can 2024-06-21

The first patch is by Oleksij Rempel, it enhances the error handling
for tightly received RTS message in the j1939 protocol.

Shigeru Yoshida's patch fixes a kernel information leak in
j1939_send_one() in the j1939 protocol.

Followed by a patch by Oleksij Rempel for the j1939 protocol, to
properly recover from a CAN bus error during BAM transmission.

A patch by Chen Ni properly propagates errors in the kvaser_usb
driver.

The last patch is by Vitor Soares, that fixes an infinite loop in the
mcp251xfd driver is SPI async sending fails during xmit.

* tag 'linux-can-fixes-for-6.10-20240621' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can:
  can: mcp251xfd: fix infinite loop when xmit fails
  can: kvaser_usb: fix return value for hif_usb_send_regout
  net: can: j1939: recover socket queue on CAN bus error during BAM transmission
  net: can: j1939: Initialize unused data in j1939_send_one()
  net: can: j1939: enhanced error handling for tightly received RTS messages in xtp_rx_rts_session_new
====================

Link: https://patch.msgid.link/20240621121739.434355-1-mkl@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 86 insertions, 17 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);
 
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 8faf8a462c05..7292c81fc0cd 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -294,7 +294,7 @@ int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
 	}
 	usb_free_urb(urb);
 
-	return 0;
+	return err;
 }
 
 int kvaser_usb_can_rx_over_error(struct net_device *netdev)
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index a6fb89fa6278..7e8a20f2fc42 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -30,10 +30,6 @@ MODULE_ALIAS("can-proto-" __stringify(CAN_J1939));
 /* CAN_HDR: #bytes before can_frame data part */
 #define J1939_CAN_HDR (offsetof(struct can_frame, data))
 
-/* CAN_FTR: #bytes beyond data part */
-#define J1939_CAN_FTR (sizeof(struct can_frame) - J1939_CAN_HDR - \
-		 sizeof(((struct can_frame *)0)->data))
-
 /* lowest layer */
 static void j1939_can_recv(struct sk_buff *iskb, void *data)
 {
@@ -342,7 +338,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb)
 	memset(cf, 0, J1939_CAN_HDR);
 
 	/* make it a full can frame again */
-	skb_put(skb, J1939_CAN_FTR + (8 - dlc));
+	skb_put_zero(skb, 8 - dlc);
 
 	canid = CAN_EFF_FLAG |
 		(skcb->priority << 26) |
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index fe3df23a2595..4be73de5033c 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1593,8 +1593,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
 	struct j1939_sk_buff_cb skcb = *j1939_skb_to_cb(skb);
 	struct j1939_session *session;
 	const u8 *dat;
+	int len, ret;
 	pgn_t pgn;
-	int len;
 
 	netdev_dbg(priv->ndev, "%s\n", __func__);
 
@@ -1653,7 +1653,22 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
 	session->tskey = priv->rx_tskey++;
 	j1939_sk_errqueue(session, J1939_ERRQUEUE_RX_RTS);
 
-	WARN_ON_ONCE(j1939_session_activate(session));
+	ret = j1939_session_activate(session);
+	if (ret) {
+		/* Entering this scope indicates an issue with the J1939 bus.
+		 * Possible scenarios include:
+		 * - A time lapse occurred, and a new session was initiated
+		 *   due to another packet being sent correctly. This could
+		 *   have been caused by too long interrupt, debugger, or being
+		 *   out-scheduled by another task.
+		 * - The bus is receiving numerous erroneous packets, either
+		 *   from a malfunctioning device or during a test scenario.
+		 */
+		netdev_alert(priv->ndev, "%s: 0x%p: concurrent session with same addr (%02x %02x) is already active.\n",
+			     __func__, session, skcb.addr.sa, skcb.addr.da);
+		j1939_session_put(session);
+		return NULL;
+	}
 
 	return session;
 }
@@ -1681,6 +1696,8 @@ static int j1939_xtp_rx_rts_session_active(struct j1939_session *session,
 
 		j1939_session_timers_cancel(session);
 		j1939_session_cancel(session, J1939_XTP_ABORT_BUSY);
+		if (session->transmission)
+			j1939_session_deactivate_activate_next(session);
 
 		return -EBUSY;
 	}