[PATCH v3 0/3] can: kvaser_pciefd: Fix ISR race conditions

[PATCH v3 0/3] can: kvaser_pciefd: Fix ISR race conditions

[Axel Forsman]

This patch series fixes a couple of race conditions in the
kvaser_pciefd driver surfaced by enabling MSI interrupts and the new
Kvaser PCIe 8xCAN.

Changes since version 2:
* Rebase onto linux-can/main to resolve del_timer()/timer_delete()
  merge conflict.
* Reword 2nd commit message slightly.

Changes since version 1:
* Change type of srb_cmd_reg from "__le32 __iomem *" to
  "void __iomem *".
* Maintain TX FIFO count in driver instead of querying HW.
* Stop queue at end of .start_xmit() if full.

Axel Forsman (3):
  can: kvaser_pciefd: Force IRQ edge in case of nested IRQ
  can: kvaser_pciefd: Fix echo_skb race
  can: kvaser_pciefd: Continue parsing DMA buf after dropped RX

 drivers/net/can/kvaser_pciefd.c | 184 ++++++++++++++++++--------------
 1 file changed, 103 insertions(+), 81 deletions(-)

-- 
2.47.2

[PATCH v3 1/3] can: kvaser_pciefd: Force IRQ edge in case of nested IRQ

[Axel Forsman]

Avoid the driver missing IRQs by temporarily masking IRQs in the ISR
to enforce an edge even if a different IRQ is signalled before handled
IRQs are cleared.

Fixes: 48f827d4f48f ("can: kvaser_pciefd: Move reset of DMA RX buffers to the end of the ISR")
Cc: stable@vger.kernel.org
Signed-off-by: Axel Forsman <axfo@kvaser.com>
Tested-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Jimmy Assarsson <extja@kvaser.com>
---
 drivers/net/can/kvaser_pciefd.c | 83 ++++++++++++++++-----------------
 1 file changed, 39 insertions(+), 44 deletions(-)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index cf0d51805272..9cc9176c2058 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1646,24 +1646,28 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 	return res;
 }
 
-static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
 {
+	void __iomem *srb_cmd_reg = KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG;
 	u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
-		kvaser_pciefd_read_buffer(pcie, 0);
+	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
 
-	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
+		kvaser_pciefd_read_buffer(pcie, 0);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0, srb_cmd_reg); /* Rearm buffer */
+	}
+
+	if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
 		kvaser_pciefd_read_buffer(pcie, 1);
+		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1, srb_cmd_reg); /* Rearm buffer */
+	}
 
 	if (unlikely(irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF0 ||
 		     irq & KVASER_PCIEFD_SRB_IRQ_DUF1))
 		dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
-
-	iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
-	return irq;
 }
 
 static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
@@ -1691,29 +1695,22 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 	struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
 	const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
 	u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
-	u32 srb_irq = 0;
-	u32 srb_release = 0;
 	int i;
 
 	if (!(pci_irq & irq_mask->all))
 		return IRQ_NONE;
 
+	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+
 	if (pci_irq & irq_mask->kcan_rx0)
-		srb_irq = kvaser_pciefd_receive_irq(pcie);
+		kvaser_pciefd_receive_irq(pcie);
 
 	for (i = 0; i < pcie->nr_channels; i++) {
 		if (pci_irq & irq_mask->kcan_tx[i])
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
-
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
-		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
-
-	if (srb_release)
-		iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 
 	return IRQ_HANDLED;
 }
@@ -1733,13 +1730,22 @@ static void kvaser_pciefd_teardown_can_ctrls(struct kvaser_pciefd *pcie)
 	}
 }
 
+static void kvaser_pciefd_disable_irq_srcs(struct kvaser_pciefd *pcie)
+{
+	unsigned int i;
+
+	/* Masking PCI_IRQ is insufficient as running ISR will unmask it */
+	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
+	for (i = 0; i < pcie->nr_channels; ++i)
+		iowrite32(0, pcie->can[i]->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
+}
+
 static int kvaser_pciefd_probe(struct pci_dev *pdev,
 			       const struct pci_device_id *id)
 {
 	int ret;
 	struct kvaser_pciefd *pcie;
 	const struct kvaser_pciefd_irq_mask *irq_mask;
-	void __iomem *irq_en_base;
 
 	pcie = devm_kzalloc(&pdev->dev, sizeof(*pcie), GFP_KERNEL);
 	if (!pcie)
@@ -1805,8 +1811,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IEN_REG);
 
 	/* Enable PCI interrupts */
-	irq_en_base = KVASER_PCIEFD_PCI_IEN_ADDR(pcie);
-	iowrite32(irq_mask->all, irq_en_base);
+	iowrite32(irq_mask->all, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
 	/* Ready the DMA buffers */
 	iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
 		  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
@@ -1820,8 +1825,7 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
-	/* Disable PCI interrupts */
-	iowrite32(0, irq_en_base);
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 
 err_pci_free_irq_vectors:
@@ -1844,35 +1848,26 @@ static int kvaser_pciefd_probe(struct pci_dev *pdev,
 	return ret;
 }
 
-static void kvaser_pciefd_remove_all_ctrls(struct kvaser_pciefd *pcie)
-{
-	int i;
-
-	for (i = 0; i < pcie->nr_channels; i++) {
-		struct kvaser_pciefd_can *can = pcie->can[i];
-
-		if (can) {
-			iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_IEN_REG);
-			unregister_candev(can->can.dev);
-			timer_delete(&can->bec_poll_timer);
-			kvaser_pciefd_pwm_stop(can);
-			free_candev(can->can.dev);
-		}
-	}
-}
-
 static void kvaser_pciefd_remove(struct pci_dev *pdev)
 {
 	struct kvaser_pciefd *pcie = pci_get_drvdata(pdev);
+	unsigned int i;
 
-	kvaser_pciefd_remove_all_ctrls(pcie);
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
 
-	/* Disable interrupts */
-	iowrite32(0, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CTRL_REG);
-	iowrite32(0, KVASER_PCIEFD_PCI_IEN_ADDR(pcie));
+		unregister_candev(can->can.dev);
+		timer_delete(&can->bec_poll_timer);
+		kvaser_pciefd_pwm_stop(can);
+	}
 
+	kvaser_pciefd_disable_irq_srcs(pcie);
 	free_irq(pcie->pci->irq, pcie);
 	pci_free_irq_vectors(pcie->pci);
+
+	for (i = 0; i < pcie->nr_channels; ++i)
+		free_candev(pcie->can[i]->can.dev);
+
 	pci_iounmap(pdev, pcie->reg_base);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
-- 
2.47.2

[PATCH v3 2/3] can: kvaser_pciefd: Fix echo_skb race

[Axel Forsman]

The functions kvaser_pciefd_start_xmit() and
kvaser_pciefd_handle_ack_packet() raced to stop/wake TX queues and
get/put echo skbs, as kvaser_pciefd_can->echo_lock was only ever taken
when transmitting and KCAN_TX_NR_PACKETS_CURRENT gets decremented
prior to handling of ACKs. E.g., this caused the following error:

    can_put_echo_skb: BUG! echo_skb 5 is occupied!

Instead, use the synchronization helpers in netdev_queues.h. As those
piggyback on BQL barriers, start updating in-flight packets and bytes
counts as well.

Cc: stable@vger.kernel.org
Signed-off-by: Axel Forsman <axfo@kvaser.com>
Tested-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Jimmy Assarsson <extja@kvaser.com>
---
 drivers/net/can/kvaser_pciefd.c | 93 +++++++++++++++++++++------------
 1 file changed, 59 insertions(+), 34 deletions(-)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index 9cc9176c2058..a61cbade96d9 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -16,6 +16,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/timer.h>
+#include <net/netdev_queues.h>
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
@@ -410,10 +411,13 @@ struct kvaser_pciefd_can {
 	void __iomem *reg_base;
 	struct can_berr_counter bec;
 	u8 cmd_seq;
+	u8 tx_max_count;
+	u8 tx_idx;
+	u8 ack_idx;
 	int err_rep_cnt;
-	int echo_idx;
+	unsigned int completed_tx_pkts;
+	unsigned int completed_tx_bytes;
 	spinlock_t lock; /* Locks sensitive registers (e.g. MODE) */
-	spinlock_t echo_lock; /* Locks the message echo buffer */
 	struct timer_list bec_poll_timer;
 	struct completion start_comp, flush_comp;
 };
@@ -714,6 +718,9 @@ static int kvaser_pciefd_open(struct net_device *netdev)
 	int ret;
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
 
+	can->tx_idx = 0;
+	can->ack_idx = 0;
+
 	ret = open_candev(netdev);
 	if (ret)
 		return ret;
@@ -745,21 +752,26 @@ static int kvaser_pciefd_stop(struct net_device *netdev)
 		timer_delete(&can->bec_poll_timer);
 	}
 	can->can.state = CAN_STATE_STOPPED;
+	netdev_reset_queue(netdev);
 	close_candev(netdev);
 
 	return ret;
 }
 
+static unsigned int kvaser_pciefd_tx_avail(const struct kvaser_pciefd_can *can)
+{
+	return can->tx_max_count - (READ_ONCE(can->tx_idx) - READ_ONCE(can->ack_idx));
+}
+
 static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
-					   struct kvaser_pciefd_can *can,
+					   struct can_priv *can, u8 seq,
 					   struct sk_buff *skb)
 {
 	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
 	int packet_size;
-	int seq = can->echo_idx;
 
 	memset(p, 0, sizeof(*p));
-	if (can->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+	if (can->ctrlmode & CAN_CTRLMODE_ONE_SHOT)
 		p->header[1] |= KVASER_PCIEFD_TPACKET_SMS;
 
 	if (cf->can_id & CAN_RTR_FLAG)
@@ -782,7 +794,7 @@ static int kvaser_pciefd_prepare_tx_packet(struct kvaser_pciefd_tx_packet *p,
 	} else {
 		p->header[1] |=
 			FIELD_PREP(KVASER_PCIEFD_RPACKET_DLC_MASK,
-				   can_get_cc_dlc((struct can_frame *)cf, can->can.ctrlmode));
+				   can_get_cc_dlc((struct can_frame *)cf, can->ctrlmode));
 	}
 
 	p->header[1] |= FIELD_PREP(KVASER_PCIEFD_PACKET_SEQ_MASK, seq);
@@ -797,22 +809,24 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 					    struct net_device *netdev)
 {
 	struct kvaser_pciefd_can *can = netdev_priv(netdev);
-	unsigned long irq_flags;
 	struct kvaser_pciefd_tx_packet packet;
+	unsigned int seq = can->tx_idx & (can->can.echo_skb_max - 1);
+	unsigned int frame_len;
 	int nr_words;
-	u8 count;
 
 	if (can_dev_dropped_skb(netdev, skb))
 		return NETDEV_TX_OK;
+	if (!netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1))
+		return NETDEV_TX_BUSY;
 
-	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, can, skb);
+	nr_words = kvaser_pciefd_prepare_tx_packet(&packet, &can->can, seq, skb);
 
-	spin_lock_irqsave(&can->echo_lock, irq_flags);
 	/* Prepare and save echo skb in internal slot */
-	can_put_echo_skb(skb, netdev, can->echo_idx, 0);
-
-	/* Move echo index to the next slot */
-	can->echo_idx = (can->echo_idx + 1) % can->can.echo_skb_max;
+	WRITE_ONCE(can->can.echo_skb[seq], NULL);
+	frame_len = can_skb_get_frame_len(skb);
+	can_put_echo_skb(skb, netdev, seq, frame_len);
+	netdev_sent_queue(netdev, frame_len);
+	WRITE_ONCE(can->tx_idx, can->tx_idx + 1);
 
 	/* Write header to fifo */
 	iowrite32(packet.header[0],
@@ -836,14 +850,7 @@ static netdev_tx_t kvaser_pciefd_start_xmit(struct sk_buff *skb,
 			     KVASER_PCIEFD_KCAN_FIFO_LAST_REG);
 	}
 
-	count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-			  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
-	/* No room for a new message, stop the queue until at least one
-	 * successful transmit
-	 */
-	if (count >= can->can.echo_skb_max || can->can.echo_skb[can->echo_idx])
-		netif_stop_queue(netdev);
-	spin_unlock_irqrestore(&can->echo_lock, irq_flags);
+	netif_subqueue_maybe_stop(netdev, 0, kvaser_pciefd_tx_avail(can), 1, 1);
 
 	return NETDEV_TX_OK;
 }
@@ -970,6 +977,8 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		can->kv_pcie = pcie;
 		can->cmd_seq = 0;
 		can->err_rep_cnt = 0;
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
 		can->bec.txerr = 0;
 		can->bec.rxerr = 0;
 
@@ -983,11 +992,10 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie)
 		tx_nr_packets_max =
 			FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_MAX_MASK,
 				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		can->tx_max_count = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
 
 		can->can.clock.freq = pcie->freq;
-		can->can.echo_skb_max = min(KVASER_PCIEFD_CAN_TX_MAX_COUNT, tx_nr_packets_max - 1);
-		can->echo_idx = 0;
-		spin_lock_init(&can->echo_lock);
+		can->can.echo_skb_max = roundup_pow_of_two(can->tx_max_count);
 		spin_lock_init(&can->lock);
 
 		can->can.bittiming_const = &kvaser_pciefd_bittiming_const;
@@ -1510,19 +1518,21 @@ static int kvaser_pciefd_handle_ack_packet(struct kvaser_pciefd *pcie,
 		netdev_dbg(can->can.dev, "Packet was flushed\n");
 	} else {
 		int echo_idx = FIELD_GET(KVASER_PCIEFD_PACKET_SEQ_MASK, p->header[0]);
-		int len;
-		u8 count;
+		unsigned int len, frame_len = 0;
 		struct sk_buff *skb;
 
+		if (echo_idx != (can->ack_idx & (can->can.echo_skb_max - 1)))
+			return 0;
 		skb = can->can.echo_skb[echo_idx];
-		if (skb)
-			kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
-		len = can_get_echo_skb(can->can.dev, echo_idx, NULL);
-		count = FIELD_GET(KVASER_PCIEFD_KCAN_TX_NR_PACKETS_CURRENT_MASK,
-				  ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NR_PACKETS_REG));
+		if (!skb)
+			return 0;
+		kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
+		len = can_get_echo_skb(can->can.dev, echo_idx, &frame_len);
 
-		if (count < can->can.echo_skb_max && netif_queue_stopped(can->can.dev))
-			netif_wake_queue(can->can.dev);
+		/* Pairs with barrier in kvaser_pciefd_start_xmit() */
+		smp_store_release(&can->ack_idx, can->ack_idx + 1);
+		can->completed_tx_pkts++;
+		can->completed_tx_bytes += frame_len;
 
 		if (!one_shot_fail) {
 			can->can.dev->stats.tx_bytes += len;
@@ -1638,11 +1648,26 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
 {
 	int pos = 0;
 	int res = 0;
+	unsigned int i;
 
 	do {
 		res = kvaser_pciefd_read_packet(pcie, &pos, dma_buf);
 	} while (!res && pos > 0 && pos < KVASER_PCIEFD_DMA_SIZE);
 
+	/* Report ACKs in this buffer to BQL en masse for correct periods */
+	for (i = 0; i < pcie->nr_channels; ++i) {
+		struct kvaser_pciefd_can *can = pcie->can[i];
+
+		if (!can->completed_tx_pkts)
+			continue;
+		netif_subqueue_completed_wake(can->can.dev, 0,
+					      can->completed_tx_pkts,
+					      can->completed_tx_bytes,
+					      kvaser_pciefd_tx_avail(can), 1);
+		can->completed_tx_pkts = 0;
+		can->completed_tx_bytes = 0;
+	}
+
 	return res;
 }
 
-- 
2.47.2

[PATCH v3 3/3] can: kvaser_pciefd: Continue parsing DMA buf after dropped RX

[Axel Forsman]

Going bus-off on a channel doing RX could result in dropped packets.

As netif_running() gets cleared before the channel abort procedure,
the handling of any last RDATA packets would see netif_rx() return
non-zero to signal a dropped packet. kvaser_pciefd_read_buffer() dealt
with this "error" by breaking out of processing the remaining DMA RX
buffer.

Only return an error from kvaser_pciefd_read_buffer() due to packet
corruption, otherwise handle it internally.

Cc: stable@vger.kernel.org
Signed-off-by: Axel Forsman <axfo@kvaser.com>
Tested-by: Jimmy Assarsson <extja@kvaser.com>
Reviewed-by: Jimmy Assarsson <extja@kvaser.com>
---
 drivers/net/can/kvaser_pciefd.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
index a61cbade96d9..f6921368cd14 100644
--- a/drivers/net/can/kvaser_pciefd.c
+++ b/drivers/net/can/kvaser_pciefd.c
@@ -1209,7 +1209,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_canfd_skb(priv->dev, &cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 
 		cf->len = can_fd_dlc2len(dlc);
@@ -1221,7 +1221,7 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 		skb = alloc_can_skb(priv->dev, (struct can_frame **)&cf);
 		if (!skb) {
 			priv->dev->stats.rx_dropped++;
-			return -ENOMEM;
+			return 0;
 		}
 		can_frame_set_cc_len((struct can_frame *)cf, dlc, priv->ctrlmode);
 	}
@@ -1239,7 +1239,9 @@ static int kvaser_pciefd_handle_data_packet(struct kvaser_pciefd *pcie,
 	priv->dev->stats.rx_packets++;
 	kvaser_pciefd_set_skb_timestamp(pcie, skb, p->timestamp);
 
-	return netif_rx(skb);
+	netif_rx(skb);
+
+	return 0;
 }
 
 static void kvaser_pciefd_change_state(struct kvaser_pciefd_can *can,
-- 
2.47.2