[PATCH v5 1/3] can: rockchip_canfd: prevent TX stall on echo skb failure

[PATCH v5 1/3] can: rockchip_canfd: prevent TX stall on echo skb failure

[Cunhao Lu]

rkcanfd_start_xmit() advances tx_head and requests transmission even when
can_put_echo_skb() fails. This creates a pending TX entry without the echo
skb that the RXSTX completion path needs to match the self-received frame.
The entry cannot be completed, and the netdev TX queue can remain stopped
after the two-entry software FIFO fills.

Install the echo skb before loading the hardware TX buffer. If installation
fails, account the frame as dropped and leave both the hardware FIFO and
software TX state unchanged. After the echo skb is installed, use the
stored echo skb as the source for the hardware frame data.

This depends on the standalone can_put_echo_skb() ownership fix. It makes
the remaining -EINVAL path consume the skb and was posted at:

Link: https://lore.kernel.org/linux-can/tencent_944DADCC4B42C8484EC01DA2B15F42132906@qq.com
Fixes: b6661d73290c ("can: rockchip_canfd: add TX PATH")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 12200dcfd338..86fa8f2e1c8b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -88,7 +88,16 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_BUSY;
 	}
 
-	cfd = (struct canfd_frame *)skb->data;
+	tx_head = rkcanfd_get_tx_head(priv);
+	frame_len = can_skb_get_frame_len(skb);
+	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
+	if (err) {
+		ndev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	skb = priv->can.echo_skb[tx_head];
+	cfd = (const struct canfd_frame *)skb->data;
 
 	if (cfd->can_id & CAN_EFF_FLAG) {
 		reg_frameinfo = RKCANFD_REG_FD_FRAMEINFO_FRAME_FORMAT;
@@ -114,7 +123,6 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 					    cfd->len);
 	}
 
-	tx_head = rkcanfd_get_tx_head(priv);
 	reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
 
 	rkcanfd_write(priv, RKCANFD_REG_FD_TXFRAMEINFO, reg_frameinfo);
@@ -123,10 +131,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		rkcanfd_write(priv, RKCANFD_REG_FD_TXDATA0 + i,
 			      *(u32 *)(cfd->data + i));
 
-	frame_len = can_skb_get_frame_len(skb);
-	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
-	if (!err)
-		netdev_sent_queue(priv->ndev, frame_len);
+	netdev_sent_queue(priv->ndev, frame_len);
 
 	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);
 

-- 
2.34.1

[PATCH v5 1/3] can: rockchip_canfd: prevent TX stall on echo skb failure

[Cunhao Lu]

rkcanfd_start_xmit() advances tx_head and requests transmission even when
can_put_echo_skb() fails. This creates a pending TX entry without the echo
skb that the RXSTX completion path needs to match the self-received frame.
The entry cannot be completed, and the netdev TX queue can remain stopped
after the two-entry software FIFO fills.

Install the echo skb before loading the hardware TX buffer. If installation
fails, account the frame as dropped and leave both the hardware FIFO and
software TX state unchanged. After the echo skb is installed, use the
stored echo skb as the source for the hardware frame data.

This depends on the standalone can_put_echo_skb() ownership fix. It makes
the remaining -EINVAL path consume the skb and was posted at:

Link: https://lore.kernel.org/linux-can/tencent_944DADCC4B42C8484EC01DA2B15F42132906@qq.com
Fixes: b6661d73290c ("can: rockchip_canfd: add TX PATH")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 12200dcfd338..86fa8f2e1c8b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -88,7 +88,16 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_BUSY;
 	}
 
-	cfd = (struct canfd_frame *)skb->data;
+	tx_head = rkcanfd_get_tx_head(priv);
+	frame_len = can_skb_get_frame_len(skb);
+	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
+	if (err) {
+		ndev->stats.tx_dropped++;
+		return NETDEV_TX_OK;
+	}
+
+	skb = priv->can.echo_skb[tx_head];
+	cfd = (const struct canfd_frame *)skb->data;
 
 	if (cfd->can_id & CAN_EFF_FLAG) {
 		reg_frameinfo = RKCANFD_REG_FD_FRAMEINFO_FRAME_FORMAT;
@@ -114,7 +123,6 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 					    cfd->len);
 	}
 
-	tx_head = rkcanfd_get_tx_head(priv);
 	reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
 
 	rkcanfd_write(priv, RKCANFD_REG_FD_TXFRAMEINFO, reg_frameinfo);
@@ -123,10 +131,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		rkcanfd_write(priv, RKCANFD_REG_FD_TXDATA0 + i,
 			      *(u32 *)(cfd->data + i));
 
-	frame_len = can_skb_get_frame_len(skb);
-	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
-	if (!err)
-		netdev_sent_queue(priv->ndev, frame_len);
+	netdev_sent_queue(priv->ndev, frame_len);
 
 	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);
 

-- 
2.34.1


_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip

[PATCH v5 2/3] can: rockchip_canfd: retry the outstanding TX buffer

[Cunhao Lu]

rkcanfd_xmit_retry() originally operated with a TX FIFO depth of one. At
that depth, the masked head and tail indices both select buffer 0, so using
tx_head happened to select the correct buffer.

After the FIFO depth was increased to two, tx_head instead identifies the
next free buffer when one frame is outstanding. The erratum 6 workaround
therefore requests transmission from the wrong buffer, leaving the
outstanding echo entry incomplete and the netdev TX queue stopped.

Use tx_tail to select the outstanding buffer for retransmission.

Fixes: a5605d61c7dd ("can: rockchip_canfd: enable full TX-FIFO depth of 2")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 86fa8f2e1c8b..fc338ea865fe 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -57,8 +57,8 @@ static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
 
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
 {
-	const unsigned int tx_head = rkcanfd_get_tx_head(priv);
-	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
+	const unsigned int tx_tail = rkcanfd_get_tx_tail(priv);
+	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_tail);
 
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 }

-- 
2.34.1

[PATCH v5 2/3] can: rockchip_canfd: retry the outstanding TX buffer

[Cunhao Lu]

rkcanfd_xmit_retry() originally operated with a TX FIFO depth of one. At
that depth, the masked head and tail indices both select buffer 0, so using
tx_head happened to select the correct buffer.

After the FIFO depth was increased to two, tx_head instead identifies the
next free buffer when one frame is outstanding. The erratum 6 workaround
therefore requests transmission from the wrong buffer, leaving the
outstanding echo entry incomplete and the netdev TX queue stopped.

Use tx_tail to select the outstanding buffer for retransmission.

Fixes: a5605d61c7dd ("can: rockchip_canfd: enable full TX-FIFO depth of 2")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index 86fa8f2e1c8b..fc338ea865fe 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -57,8 +57,8 @@ static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
 
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
 {
-	const unsigned int tx_head = rkcanfd_get_tx_head(priv);
-	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
+	const unsigned int tx_tail = rkcanfd_get_tx_tail(priv);
+	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_tail);
 
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 }

-- 
2.34.1


_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip

[PATCH v5 3/3] can: rockchip_canfd: serialize TX state and command writes

[Cunhao Lu]

The TX completion path removes an echo skb before advancing tx_tail. In
parallel, the transmit path reads tx_head, tx_tail and the tail echo slot
when applying the erratum 6 queue restriction. There is no synchronization
between these operations.

On SMP, the transmit path can consequently observe a pending frame with
an empty echo slot. It can also keep a pointer to an echo skb while the
completion path removes and queues it for NAPI, where it can be freed on
another CPU. The inconsistent snapshot can stop the netdev TX queue when
there is no later completion to wake it.

There is a second race in the command submission sequence.
rkcanfd_start_xmit() runs in softirq context.
rkcanfd_xmit_retry() runs from the RX interrupt handler. On controllers
affected by erratum 12, both execute a MODE/CMD/MODE register sequence. The
interrupt handler can restore the default MODE between the softirq writes.
The resumed softirq then issues CMD without SPACE_RX_MODE and bypasses the
erratum 12 workaround.

Add a TX state lock and use it to protect tx_head, tx_tail and the echo skb
ring as one state. The same lock serializes the MODE/CMD/MODE sequence
between the transmit and interrupt paths. Keep completion and wakeup
outside the lock to avoid nesting the TX state lock with the netdev TX
queue lock. Install the echo skb before loading the hardware TX buffer so
an echo setup failure cannot desynchronize the hardware and software TX
state.

Tested on an RK3588 rev2.2 at 1 Mbit/s with 100,000 extended CAN frames.
The run triggered 138 erratum 6 retries and completed without drops, queue
stalls or driver warnings. RK3588 does not enable erratum 12, so this test
does not exercise that hardware workaround.

Fixes: ae002cc32ec4 ("can: rockchip_canfd: prepare to use full TX-FIFO depth")
Fixes: 83f9bd6bf39d ("can: rockchip_canfd: implement workaround for erratum 12")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c |  1 +
 drivers/net/can/rockchip/rockchip_canfd-rx.c   | 31 +++++++++++++++++++-------
 drivers/net/can/rockchip/rockchip_canfd-tx.c   | 26 ++++++++++++++++++---
 drivers/net/can/rockchip/rockchip_canfd.h      |  4 +++-
 4 files changed, 50 insertions(+), 12 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 29de0c01e4ed..c8257858b452 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -904,6 +904,7 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
+	spin_lock_init(&priv->tx_lock);
 
 	match = device_get_match_data(&pdev->dev);
 	if (match) {
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 475c0409e215..02efc8c0cddc 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -100,14 +100,25 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	const struct canfd_frame *cfd_nominal;
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	if (!rkcanfd_get_tx_pending(priv))
+		goto out_unlock;
 
 	tx_tail = rkcanfd_get_tx_tail(priv);
 	skb = priv->can.echo_skb[tx_tail];
 	if (!skb) {
+		const unsigned int tx_head_unmasked = priv->tx_head;
+		const unsigned int tx_tail_unmasked = priv->tx_tail;
+
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 		netdev_err(priv->ndev,
 			   "%s: echo_skb[%u]=NULL tx_head=0x%08x tx_tail=0x%08x\n",
 			   __func__, tx_tail,
-			   priv->tx_head, priv->tx_tail);
+			   tx_head_unmasked, tx_tail_unmasked);
 
 		return -ENOMSG;
 	}
@@ -123,17 +134,18 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 		rkcanfd_handle_tx_done_one(priv, ts, &frame_len);
 
 		WRITE_ONCE(priv->tx_tail, priv->tx_tail + 1);
+		*tx_done = true;
+
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
 		netif_subqueue_completed_wake(priv->ndev, 0, 1, frame_len,
 					      rkcanfd_get_effective_tx_free(priv),
 					      RKCANFD_TX_START_THRESHOLD);
 
-		*tx_done = true;
-
 		return 0;
 	}
 
 	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6))
-		return 0;
+		goto out_unlock;
 
 	/* Erratum 6: Extended frames may be send as standard frames.
 	 *
@@ -143,7 +155,7 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	 */
 	if (!(cfd_nominal->can_id & CAN_EFF_FLAG) ||
 	    (cfd_rx->can_id & CAN_EFF_FLAG))
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - standard part and RTR flag of the TX'ed frame
@@ -151,20 +163,20 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	 */
 	if ((cfd_nominal->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)) !=
 	    (cfd_rx->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)))
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - length is not the same
 	 */
 	if (cfd_nominal->len != cfd_rx->len)
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - the data of non RTR frames is different
 	 */
 	if (!(cfd_nominal->can_id & CAN_RTR_FLAG) &&
 	    memcmp(cfd_nominal->data, cfd_rx->data, cfd_nominal->len))
-		return 0;
+		goto out_unlock;
 
 	/* Affected by Erratum 6 */
 	u64_stats_update_begin(&rkcanfd_stats->syncp);
@@ -185,6 +197,9 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 
 	rkcanfd_xmit_retry(priv);
 
+out_unlock:
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 	return 0;
 }
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index fc338ea865fe..b367341dd0ae 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -14,6 +14,8 @@ static bool rkcanfd_tx_tail_is_eff(const struct rkcanfd_priv *priv)
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	if (!rkcanfd_get_tx_pending(priv))
 		return false;
 
@@ -33,13 +35,22 @@ static bool rkcanfd_tx_tail_is_eff(const struct rkcanfd_priv *priv)
 	return cfd->can_id & CAN_EFF_FLAG;
 }
 
-unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv)
+unsigned int rkcanfd_get_effective_tx_free(struct rkcanfd_priv *priv)
 {
+	unsigned int tx_free;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
 	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6 &&
 	    rkcanfd_tx_tail_is_eff(priv))
-		return 0;
+		tx_free = 0;
+	else
+		tx_free = rkcanfd_get_tx_free(priv);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
-	return rkcanfd_get_tx_free(priv);
+	return tx_free;
 }
 
 static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
@@ -60,6 +71,8 @@ void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
 	const unsigned int tx_tail = rkcanfd_get_tx_tail(priv);
 	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_tail);
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 }
 
@@ -69,6 +82,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	u32 reg_frameinfo, reg_id, reg_cmd;
 	unsigned int tx_head, frame_len;
 	const struct canfd_frame *cfd;
+	unsigned long flags;
 	int err;
 	u8 i;
 
@@ -88,10 +102,13 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_BUSY;
 	}
 
+	spin_lock_irqsave(&priv->tx_lock, flags);
 	tx_head = rkcanfd_get_tx_head(priv);
 	frame_len = can_skb_get_frame_len(skb);
 	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
 	if (err) {
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 		ndev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
@@ -136,6 +153,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);
 
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
 	netif_subqueue_maybe_stop(priv->ndev, 0,
 				  rkcanfd_get_effective_tx_free(priv),
@@ -152,6 +170,8 @@ void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 	unsigned int tx_tail;
 	struct sk_buff *skb;
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	tx_tail = rkcanfd_get_tx_tail(priv);
 	skb = priv->can.echo_skb[tx_tail];
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 93131c7d7f54..3cf283a7b380 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -15,6 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/reset.h>
 #include <linux/skbuff.h>
+#include <linux/spinlock.h>
 #include <linux/timecounter.h>
 #include <linux/types.h>
 #include <linux/u64_stats_sync.h>
@@ -462,6 +463,7 @@ struct rkcanfd_priv {
 	struct can_rx_offload offload;
 	struct net_device *ndev;
 
+	spinlock_t tx_lock; /* protects tx_head, tx_tail and echo_skb */
 	void __iomem *regs;
 	unsigned int tx_head;
 	unsigned int tx_tail;
@@ -544,7 +546,7 @@ void rkcanfd_timestamp_start(struct rkcanfd_priv *priv);
 void rkcanfd_timestamp_stop(struct rkcanfd_priv *priv);
 void rkcanfd_timestamp_stop_sync(struct rkcanfd_priv *priv);
 
-unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv);
+unsigned int rkcanfd_get_effective_tx_free(struct rkcanfd_priv *priv);
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
 netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,

-- 
2.34.1

[PATCH v5 3/3] can: rockchip_canfd: serialize TX state and command writes

[Cunhao Lu]

The TX completion path removes an echo skb before advancing tx_tail. In
parallel, the transmit path reads tx_head, tx_tail and the tail echo slot
when applying the erratum 6 queue restriction. There is no synchronization
between these operations.

On SMP, the transmit path can consequently observe a pending frame with
an empty echo slot. It can also keep a pointer to an echo skb while the
completion path removes and queues it for NAPI, where it can be freed on
another CPU. The inconsistent snapshot can stop the netdev TX queue when
there is no later completion to wake it.

There is a second race in the command submission sequence.
rkcanfd_start_xmit() runs in softirq context.
rkcanfd_xmit_retry() runs from the RX interrupt handler. On controllers
affected by erratum 12, both execute a MODE/CMD/MODE register sequence. The
interrupt handler can restore the default MODE between the softirq writes.
The resumed softirq then issues CMD without SPACE_RX_MODE and bypasses the
erratum 12 workaround.

Add a TX state lock and use it to protect tx_head, tx_tail and the echo skb
ring as one state. The same lock serializes the MODE/CMD/MODE sequence
between the transmit and interrupt paths. Keep completion and wakeup
outside the lock to avoid nesting the TX state lock with the netdev TX
queue lock. Install the echo skb before loading the hardware TX buffer so
an echo setup failure cannot desynchronize the hardware and software TX
state.

Tested on an RK3588 rev2.2 at 1 Mbit/s with 100,000 extended CAN frames.
The run triggered 138 erratum 6 retries and completed without drops, queue
stalls or driver warnings. RK3588 does not enable erratum 12, so this test
does not exercise that hardware workaround.

Fixes: ae002cc32ec4 ("can: rockchip_canfd: prepare to use full TX-FIFO depth")
Fixes: 83f9bd6bf39d ("can: rockchip_canfd: implement workaround for erratum 12")
Cc: stable@vger.kernel.org
Signed-off-by: Cunhao Lu <1579567540@qq.com>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c |  1 +
 drivers/net/can/rockchip/rockchip_canfd-rx.c   | 31 +++++++++++++++++++-------
 drivers/net/can/rockchip/rockchip_canfd-tx.c   | 26 ++++++++++++++++++---
 drivers/net/can/rockchip/rockchip_canfd.h      |  4 +++-
 4 files changed, 50 insertions(+), 12 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index 29de0c01e4ed..c8257858b452 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -904,6 +904,7 @@ static int rkcanfd_probe(struct platform_device *pdev)
 	priv->can.do_set_mode = rkcanfd_set_mode;
 	priv->can.do_get_berr_counter = rkcanfd_get_berr_counter;
 	priv->ndev = ndev;
+	spin_lock_init(&priv->tx_lock);
 
 	match = device_get_match_data(&pdev->dev);
 	if (match) {
diff --git a/drivers/net/can/rockchip/rockchip_canfd-rx.c b/drivers/net/can/rockchip/rockchip_canfd-rx.c
index 475c0409e215..02efc8c0cddc 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-rx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-rx.c
@@ -100,14 +100,25 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	const struct canfd_frame *cfd_nominal;
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	if (!rkcanfd_get_tx_pending(priv))
+		goto out_unlock;
 
 	tx_tail = rkcanfd_get_tx_tail(priv);
 	skb = priv->can.echo_skb[tx_tail];
 	if (!skb) {
+		const unsigned int tx_head_unmasked = priv->tx_head;
+		const unsigned int tx_tail_unmasked = priv->tx_tail;
+
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 		netdev_err(priv->ndev,
 			   "%s: echo_skb[%u]=NULL tx_head=0x%08x tx_tail=0x%08x\n",
 			   __func__, tx_tail,
-			   priv->tx_head, priv->tx_tail);
+			   tx_head_unmasked, tx_tail_unmasked);
 
 		return -ENOMSG;
 	}
@@ -123,17 +134,18 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 		rkcanfd_handle_tx_done_one(priv, ts, &frame_len);
 
 		WRITE_ONCE(priv->tx_tail, priv->tx_tail + 1);
+		*tx_done = true;
+
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
 		netif_subqueue_completed_wake(priv->ndev, 0, 1, frame_len,
 					      rkcanfd_get_effective_tx_free(priv),
 					      RKCANFD_TX_START_THRESHOLD);
 
-		*tx_done = true;
-
 		return 0;
 	}
 
 	if (!(priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6))
-		return 0;
+		goto out_unlock;
 
 	/* Erratum 6: Extended frames may be send as standard frames.
 	 *
@@ -143,7 +155,7 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	 */
 	if (!(cfd_nominal->can_id & CAN_EFF_FLAG) ||
 	    (cfd_rx->can_id & CAN_EFF_FLAG))
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - standard part and RTR flag of the TX'ed frame
@@ -151,20 +163,20 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 	 */
 	if ((cfd_nominal->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)) !=
 	    (cfd_rx->can_id & (CAN_RTR_FLAG | CAN_SFF_MASK)))
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - length is not the same
 	 */
 	if (cfd_nominal->len != cfd_rx->len)
-		return 0;
+		goto out_unlock;
 
 	/* Not affected if:
 	 * - the data of non RTR frames is different
 	 */
 	if (!(cfd_nominal->can_id & CAN_RTR_FLAG) &&
 	    memcmp(cfd_nominal->data, cfd_rx->data, cfd_nominal->len))
-		return 0;
+		goto out_unlock;
 
 	/* Affected by Erratum 6 */
 	u64_stats_update_begin(&rkcanfd_stats->syncp);
@@ -185,6 +197,9 @@ static int rkcanfd_rxstx_filter(struct rkcanfd_priv *priv,
 
 	rkcanfd_xmit_retry(priv);
 
+out_unlock:
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 	return 0;
 }
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
index fc338ea865fe..b367341dd0ae 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
@@ -14,6 +14,8 @@ static bool rkcanfd_tx_tail_is_eff(const struct rkcanfd_priv *priv)
 	const struct sk_buff *skb;
 	unsigned int tx_tail;
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	if (!rkcanfd_get_tx_pending(priv))
 		return false;
 
@@ -33,13 +35,22 @@ static bool rkcanfd_tx_tail_is_eff(const struct rkcanfd_priv *priv)
 	return cfd->can_id & CAN_EFF_FLAG;
 }
 
-unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv)
+unsigned int rkcanfd_get_effective_tx_free(struct rkcanfd_priv *priv)
 {
+	unsigned int tx_free;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
 	if (priv->devtype_data.quirks & RKCANFD_QUIRK_RK3568_ERRATUM_6 &&
 	    rkcanfd_tx_tail_is_eff(priv))
-		return 0;
+		tx_free = 0;
+	else
+		tx_free = rkcanfd_get_tx_free(priv);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
-	return rkcanfd_get_tx_free(priv);
+	return tx_free;
 }
 
 static void rkcanfd_start_xmit_write_cmd(const struct rkcanfd_priv *priv,
@@ -60,6 +71,8 @@ void rkcanfd_xmit_retry(struct rkcanfd_priv *priv)
 	const unsigned int tx_tail = rkcanfd_get_tx_tail(priv);
 	const u32 reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_tail);
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
 }
 
@@ -69,6 +82,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	u32 reg_frameinfo, reg_id, reg_cmd;
 	unsigned int tx_head, frame_len;
 	const struct canfd_frame *cfd;
+	unsigned long flags;
 	int err;
 	u8 i;
 
@@ -88,10 +102,13 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		return NETDEV_TX_BUSY;
 	}
 
+	spin_lock_irqsave(&priv->tx_lock, flags);
 	tx_head = rkcanfd_get_tx_head(priv);
 	frame_len = can_skb_get_frame_len(skb);
 	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
 	if (err) {
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 		ndev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
@@ -136,6 +153,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);
 
 	rkcanfd_start_xmit_write_cmd(priv, reg_cmd);
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
 	netif_subqueue_maybe_stop(priv->ndev, 0,
 				  rkcanfd_get_effective_tx_free(priv),
@@ -152,6 +170,8 @@ void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,
 	unsigned int tx_tail;
 	struct sk_buff *skb;
 
+	lockdep_assert_held(&priv->tx_lock);
+
 	tx_tail = rkcanfd_get_tx_tail(priv);
 	skb = priv->can.echo_skb[tx_tail];
 
diff --git a/drivers/net/can/rockchip/rockchip_canfd.h b/drivers/net/can/rockchip/rockchip_canfd.h
index 93131c7d7f54..3cf283a7b380 100644
--- a/drivers/net/can/rockchip/rockchip_canfd.h
+++ b/drivers/net/can/rockchip/rockchip_canfd.h
@@ -15,6 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/reset.h>
 #include <linux/skbuff.h>
+#include <linux/spinlock.h>
 #include <linux/timecounter.h>
 #include <linux/types.h>
 #include <linux/u64_stats_sync.h>
@@ -462,6 +463,7 @@ struct rkcanfd_priv {
 	struct can_rx_offload offload;
 	struct net_device *ndev;
 
+	spinlock_t tx_lock; /* protects tx_head, tx_tail and echo_skb */
 	void __iomem *regs;
 	unsigned int tx_head;
 	unsigned int tx_tail;
@@ -544,7 +546,7 @@ void rkcanfd_timestamp_start(struct rkcanfd_priv *priv);
 void rkcanfd_timestamp_stop(struct rkcanfd_priv *priv);
 void rkcanfd_timestamp_stop_sync(struct rkcanfd_priv *priv);
 
-unsigned int rkcanfd_get_effective_tx_free(const struct rkcanfd_priv *priv);
+unsigned int rkcanfd_get_effective_tx_free(struct rkcanfd_priv *priv);
 void rkcanfd_xmit_retry(struct rkcanfd_priv *priv);
 netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 void rkcanfd_handle_tx_done_one(struct rkcanfd_priv *priv, const u32 ts,

-- 
2.34.1


_______________________________________________
Linux-rockchip mailing list
Linux-rockchip@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-rockchip

Re: [PATCH v5 1/3] can: rockchip_canfd: prevent TX stall on echo skb failure

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Out-of-bounds read and hardware register out-of-bounds write due to CAN XL frame mishandling.
--

--- Patch [1]: [PATCH v5 1/3] can: rockchip_canfd: prevent TX stall on echo skb failure ---
commit 8df8ef3a7e1e7414d8117605f2f14ed295ef9ad1
Author: Cunhao Lu <1579567540@qq.com>

can: rockchip_canfd: prevent TX stall on echo skb failure

This patch prevents a TX stall by installing the echo skb before loading
the hardware TX buffer. If installation fails, it drops the frame and leaves
the hardware FIFO and software TX state unchanged. It correctly relies on the
echo skb as the source for hardware frame data after it is installed.

Link: https://lore.kernel.org/linux-can/tencent_944DADCC4B42C8484EC01DA2B15F42132906@qq.com

> diff --git a/drivers/net/can/rockchip/rockchip_canfd-tx.c b/drivers/net/can/rockchip/rockchip_canfd-tx.c
> index 12200dcfd3389..86fa8f2e1c8ba 100644
> --- a/drivers/net/can/rockchip/rockchip_canfd-tx.c
> +++ b/drivers/net/can/rockchip/rockchip_canfd-tx.c
[ ... ]
> @@ -114,7 +123,6 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
>  					    cfd->len);
>  	}
>  
> -	tx_head = rkcanfd_get_tx_head(priv);
>  	reg_cmd = RKCANFD_REG_CMD_TX_REQ(tx_head);
>  
>  	rkcanfd_write(priv, RKCANFD_REG_FD_TXFRAMEINFO, reg_frameinfo);
> @@ -123,10 +131,7 @@ netdev_tx_t rkcanfd_start_xmit(struct sk_buff *skb, struct net_device *ndev)
>  		rkcanfd_write(priv, RKCANFD_REG_FD_TXDATA0 + i,
>  			      *(u32 *)(cfd->data + i));
>  

[Severity: High]
This is a pre-existing issue, but does this code properly handle CAN XL frames?

If an ETH_P_CANXL frame is sent via AF_PACKET, can_dev_dropped_skb() currently
lacks a check to drop CAN XL frames for devices that don't support CAN XL.
When such a frame enters rkcanfd_start_xmit(), can_is_canfd_skb() returns
false, causing the driver to treat it as a Classic CAN frame.

The driver reads cfd->len from offset 4, which in a canxl_frame corresponds to
the user-controlled flags field. Because valid CAN XL frames require CANXL_XLF
(0x80) to be set, cfd->len is evaluated as at least 128.

Could a minimally sized CAN XL frame trigger a loop of 32 iterations here,
leading to an out-of-bounds read from cfd->data and an out-of-bounds write
to device memory at RKCANFD_REG_FD_TXDATA0 + i?

> -	frame_len = can_skb_get_frame_len(skb);
> -	err = can_put_echo_skb(skb, ndev, tx_head, frame_len);
> -	if (!err)
> -		netdev_sent_queue(priv->ndev, frame_len);
> +	netdev_sent_queue(priv->ndev, frame_len);
>  
>  	WRITE_ONCE(priv->tx_head, priv->tx_head + 1);

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260731-master-v5-0-5b27029dee20@qq.com?part=1