Merge tag 'linux-can-fixes-for-6.11-20240830' of...

Merge tag 'linux-can-fixes-for-6.11-20240830' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can

Marc Kleine-Budde says:

====================
pull-request: can 2024-08-30

The first patch is by Kuniyuki Iwashima for the CAN BCM protocol that
adds a missing proc entry removal when a device unregistered.

Simon Horman fixes the cleanup in the error cleanup path of the m_can
driver's open function.

Markus Schneider-Pargmann contributes 7 fixes for the m_can driver,
all related to the recently added IRQ coalescing support.

The next 2 patches are by me, target the mcp251xfd driver and fix ring
and coalescing configuration problems when switching from CAN-CC to
CAN-FD mode.

Simon Arlott's patch fixes a possible deadlock in the mcp251x driver.

The last patch is by Martin Jocic for the kvaser_pciefd driver and
fixes a problem with lost IRQs, which result in starvation, under high
load situations.

* tag 'linux-can-fixes-for-6.11-20240830' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can:
  can: kvaser_pciefd: Use a single write when releasing RX buffers
  can: mcp251x: fix deadlock if an interrupt occurs during mcp251x_open
  can: mcp251xfd: mcp251xfd_ring_init(): check TX-coalescing configuration
  can: mcp251xfd: fix ring configuration when switching from CAN-CC to CAN-FD mode
  can: m_can: Limit coalescing to peripheral instances
  can: m_can: Reset cached active_interrupts on start
  can: m_can: disable_all_interrupts, not clear active_interrupts
  can: m_can: Do not cancel timer from within timer
  can: m_can: Remove m_can_rx_peripheral indirection
  can: m_can: Remove coalesing disable in isr during suspend
  can: m_can: Reset coalescing during suspend/resume
  can: m_can: Release irq on error in m_can_open
  can: bcm: Remove proc entry when dev is unregistered.
====================

Link: https://patch.msgid.link/20240830215914.1610393-1-mkl@pengutronix.deSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/can/kvaser_pciefd.c

@@ -1686,6 +1686,7 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *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))
@@ -1699,17 +1700,14 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
 			kvaser_pciefd_transmit_irq(pcie->can[i]);
 	}
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
-		/* Reset DMA buffer 0, may trigger new interrupt */
-		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
-			  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
-	}
+	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
+		srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
 
-	if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
-		/* Reset DMA buffer 1, may trigger new interrupt */
-		iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1,
-			  KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
-	}
+	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);
 
 	return IRQ_HANDLED;
 }

drivers/net/can/m_can/m_can.c

@@ -483,11 +483,10 @@ static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev)
 {
 	m_can_coalescing_disable(cdev);
 	m_can_write(cdev, M_CAN_ILE, 0x0);
-	cdev->active_interrupts = 0x0;
 
 	if (!cdev->net->irq) {
 		dev_dbg(cdev->dev, "Stop hrtimer\n");
-		hrtimer_cancel(&cdev->hrtimer);
+		hrtimer_try_to_cancel(&cdev->hrtimer);
 	}
 }
 
@@ -1037,22 +1036,6 @@ static int m_can_rx_handler(struct net_device *dev, int quota, u32 irqstatus)
 	return work_done;
 }
 
-static int m_can_rx_peripheral(struct net_device *dev, u32 irqstatus)
-{
-	struct m_can_classdev *cdev = netdev_priv(dev);
-	int work_done;
-
-	work_done = m_can_rx_handler(dev, NAPI_POLL_WEIGHT, irqstatus);
-
-	/* Don't re-enable interrupts if the driver had a fatal error
-	 * (e.g., FIFO read failure).
-	 */
-	if (work_done < 0)
-		m_can_disable_all_interrupts(cdev);
-
-	return work_done;
-}
-
 static int m_can_poll(struct napi_struct *napi, int quota)
 {
 	struct net_device *dev = napi->dev;
@@ -1217,16 +1200,18 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir)
 			      HRTIMER_MODE_REL);
 }
 
-static irqreturn_t m_can_isr(int irq, void *dev_id)
+/* This interrupt handler is called either from the interrupt thread or a
+ * hrtimer. This has implications like cancelling a timer won't be possible
+ * blocking.
+ */
+static int m_can_interrupt_handler(struct m_can_classdev *cdev)
 {
-	struct net_device *dev = (struct net_device *)dev_id;
-	struct m_can_classdev *cdev = netdev_priv(dev);
+	struct net_device *dev = cdev->net;
 	u32 ir;
+	int ret;
 
-	if (pm_runtime_suspended(cdev->dev)) {
-		m_can_coalescing_disable(cdev);
+	if (pm_runtime_suspended(cdev->dev))
 		return IRQ_NONE;
-	}
 
 	ir = m_can_read(cdev, M_CAN_IR);
 	m_can_coalescing_update(cdev, ir);
@@ -1250,11 +1235,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 			m_can_disable_all_interrupts(cdev);
 			napi_schedule(&cdev->napi);
 		} else {
-			int pkts;
-
-			pkts = m_can_rx_peripheral(dev, ir);
-			if (pkts < 0)
-				goto out_fail;
+			ret = m_can_rx_handler(dev, NAPI_POLL_WEIGHT, ir);
+			if (ret < 0)
+				return ret;
 		}
 	}
 
@@ -1272,8 +1255,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 	} else  {
 		if (ir & (IR_TEFN | IR_TEFW)) {
 			/* New TX FIFO Element arrived */
-			if (m_can_echo_tx_event(dev) != 0)
-				goto out_fail;
+			ret = m_can_echo_tx_event(dev);
+			if (ret != 0)
+				return ret;
 		}
 	}
 
@@ -1281,16 +1265,31 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
 		can_rx_offload_threaded_irq_finish(&cdev->offload);
 
 	return IRQ_HANDLED;
+}
 
-out_fail:
-	m_can_disable_all_interrupts(cdev);
-	return IRQ_HANDLED;
+static irqreturn_t m_can_isr(int irq, void *dev_id)
+{
+	struct net_device *dev = (struct net_device *)dev_id;
+	struct m_can_classdev *cdev = netdev_priv(dev);
+	int ret;
+
+	ret =  m_can_interrupt_handler(cdev);
+	if (ret < 0) {
+		m_can_disable_all_interrupts(cdev);
+		return IRQ_HANDLED;
+	}
+
+	return ret;
 }
 
 static enum hrtimer_restart m_can_coalescing_timer(struct hrtimer *timer)
 {
 	struct m_can_classdev *cdev = container_of(timer, struct m_can_classdev, hrtimer);
 
+	if (cdev->can.state == CAN_STATE_BUS_OFF ||
+	    cdev->can.state == CAN_STATE_STOPPED)
+		return HRTIMER_NORESTART;
+
 	irq_wake_thread(cdev->net->irq, cdev->net);
 
 	return HRTIMER_NORESTART;
@@ -1542,6 +1541,7 @@ static int m_can_chip_config(struct net_device *dev)
 		else
 			interrupts &= ~(IR_ERR_LEC_31X);
 	}
+	cdev->active_interrupts = 0;
 	m_can_interrupt_enable(cdev, interrupts);
 
 	/* route all interrupts to INT0 */
@@ -1991,8 +1991,17 @@ static enum hrtimer_restart hrtimer_callback(struct hrtimer *timer)
 {
 	struct m_can_classdev *cdev = container_of(timer, struct
 						   m_can_classdev, hrtimer);
+	int ret;
+
+	if (cdev->can.state == CAN_STATE_BUS_OFF ||
+	    cdev->can.state == CAN_STATE_STOPPED)
+		return HRTIMER_NORESTART;
 
-	m_can_isr(0, cdev->net);
+	ret = m_can_interrupt_handler(cdev);
+
+	/* On error or if napi is scheduled to read, stop the timer */
+	if (ret < 0 || napi_is_scheduled(&cdev->napi))
+		return HRTIMER_NORESTART;
 
 	hrtimer_forward_now(timer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS));
 
@@ -2052,7 +2061,7 @@ static int m_can_open(struct net_device *dev)
 	/* start the m_can controller */
 	err = m_can_start(dev);
 	if (err)
-		goto exit_irq_fail;
+		goto exit_start_fail;
 
 	if (!cdev->is_peripheral)
 		napi_enable(&cdev->napi);
@@ -2061,6 +2070,9 @@ static int m_can_open(struct net_device *dev)
 
 	return 0;
 
+exit_start_fail:
+	if (cdev->is_peripheral || dev->irq)
+		free_irq(dev->irq, dev);
 exit_irq_fail:
 	if (cdev->is_peripheral)
 		destroy_workqueue(cdev->tx_wq);
@@ -2172,7 +2184,7 @@ static int m_can_set_coalesce(struct net_device *dev,
 	return 0;
 }
 
-static const struct ethtool_ops m_can_ethtool_ops = {
+static const struct ethtool_ops m_can_ethtool_ops_coalescing = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS_IRQ |
 		ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ |
 		ETHTOOL_COALESCE_TX_USECS_IRQ |
@@ -2183,18 +2195,20 @@ static const struct ethtool_ops m_can_ethtool_ops = {
 	.set_coalesce = m_can_set_coalesce,
 };
 
-static const struct ethtool_ops m_can_ethtool_ops_polling = {
+static const struct ethtool_ops m_can_ethtool_ops = {
 	.get_ts_info = ethtool_op_get_ts_info,
 };
 
-static int register_m_can_dev(struct net_device *dev)
+static int register_m_can_dev(struct m_can_classdev *cdev)
 {
+	struct net_device *dev = cdev->net;
+
 	dev->flags |= IFF_ECHO;	/* we support local echo */
 	dev->netdev_ops = &m_can_netdev_ops;
-	if (dev->irq)
-		dev->ethtool_ops = &m_can_ethtool_ops;
+	if (dev->irq && cdev->is_peripheral)
+		dev->ethtool_ops = &m_can_ethtool_ops_coalescing;
 	else
-		dev->ethtool_ops = &m_can_ethtool_ops_polling;
+		dev->ethtool_ops = &m_can_ethtool_ops;
 
 	return register_candev(dev);
 }
@@ -2380,7 +2394,7 @@ int m_can_class_register(struct m_can_classdev *cdev)
 	if (ret)
 		goto rx_offload_del;
 
-	ret = register_m_can_dev(cdev->net);
+	ret = register_m_can_dev(cdev);
 	if (ret) {
 		dev_err(cdev->dev, "registering %s failed (err=%d)\n",
 			cdev->net->name, ret);
@@ -2427,12 +2441,15 @@ int m_can_class_suspend(struct device *dev)
 		netif_device_detach(ndev);
 
 		/* leave the chip running with rx interrupt enabled if it is
-		 * used as a wake-up source.
+		 * used as a wake-up source. Coalescing needs to be reset then,
+		 * the timer is cancelled here, interrupts are done in resume.
 		 */
-		if (cdev->pm_wake_source)
+		if (cdev->pm_wake_source) {
+			hrtimer_cancel(&cdev->hrtimer);
 			m_can_write(cdev, M_CAN_IE, IR_RF0N);
-		else
+		} else {
 			m_can_stop(ndev);
+		}
 
 		m_can_clk_stop(cdev);
 	}
@@ -2462,6 +2479,13 @@ int m_can_class_resume(struct device *dev)
 			return ret;
 
 		if (cdev->pm_wake_source) {
+			/* Restore active interrupts but disable coalescing as
+			 * we may have missed important waterlevel interrupts
+			 * between suspend and resume. Timers are already
+			 * stopped in suspend. Here we enable all interrupts
+			 * again.
+			 */
+			cdev->active_interrupts |= IR_RF0N | IR_TEFN;
 			m_can_write(cdev, M_CAN_IE, cdev->active_interrupts);
 		} else {
 			ret  = m_can_start(ndev);

drivers/net/can/spi/mcp251x.c

@@ -752,7 +752,7 @@ static int mcp251x_hw_wake(struct spi_device *spi)
 	int ret;
 
 	/* Force wakeup interrupt to wake device, but don't execute IST */
-	disable_irq(spi->irq);
+	disable_irq_nosync(spi->irq);
 	mcp251x_write_2regs(spi, CANINTE, CANINTE_WAKIE, CANINTF_WAKIF);
 
 	/* Wait for oscillator startup timer after wake up */

drivers/net/can/spi/mcp251xfd/mcp251xfd-ram.c

@@ -97,7 +97,16 @@ void can_ram_get_layout(struct can_ram_layout *layout,
 	if (ring) {
 		u8 num_rx_coalesce = 0, num_tx_coalesce = 0;
 
-		num_rx = can_ram_rounddown_pow_of_two(config, &config->rx, 0, ring->rx_pending);
+		/* If the ring parameters have been configured in
+		 * CAN-CC mode, but and we are in CAN-FD mode now,
+		 * they might be to big. Use the default CAN-FD values
+		 * in this case.
+		 */
+		num_rx = ring->rx_pending;
+		if (num_rx > layout->max_rx)
+			num_rx = layout->default_rx;
+
+		num_rx = can_ram_rounddown_pow_of_two(config, &config->rx, 0, num_rx);
 
 		/* The ethtool doc says:
 		 * To disable coalescing, set usecs = 0 and max_frames = 1.

drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c

@@ -290,7 +290,7 @@ int mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
 	const struct mcp251xfd_rx_ring *rx_ring;
 	u16 base = 0, ram_used;
 	u8 fifo_nr = 1;
-	int i;
+	int err = 0, i;
 
 	netdev_reset_queue(priv->ndev);
 
@@ -386,10 +386,18 @@ int mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
 		netdev_err(priv->ndev,
 			   "Error during ring configuration, using more RAM (%u bytes) than available (%u bytes).\n",
 			   ram_used, MCP251XFD_RAM_SIZE);
-		return -ENOMEM;
+		err = -ENOMEM;
 	}
 
-	return 0;
+	if (priv->tx_obj_num_coalesce_irq &&
+	    priv->tx_obj_num_coalesce_irq * 2 != priv->tx->obj_num) {
+		netdev_err(priv->ndev,
+			   "Error during ring configuration, number of TEF coalescing buffers (%u) must be half of TEF buffers (%u).\n",
+			   priv->tx_obj_num_coalesce_irq, priv->tx->obj_num);
+		err = -EINVAL;
+	}
+
+	return err;
 }
 
 void mcp251xfd_ring_free(struct mcp251xfd_priv *priv)
@@ -469,11 +477,25 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
 
 	/* switching from CAN-2.0 to CAN-FD mode or vice versa */
 	if (fd_mode != test_bit(MCP251XFD_FLAGS_FD_MODE, priv->flags)) {
+		const struct ethtool_ringparam ring = {
+			.rx_pending = priv->rx_obj_num,
+			.tx_pending = priv->tx->obj_num,
+		};
+		const struct ethtool_coalesce ec = {
+			.rx_coalesce_usecs_irq = priv->rx_coalesce_usecs_irq,
+			.rx_max_coalesced_frames_irq = priv->rx_obj_num_coalesce_irq,
+			.tx_coalesce_usecs_irq = priv->tx_coalesce_usecs_irq,
+			.tx_max_coalesced_frames_irq = priv->tx_obj_num_coalesce_irq,
+		};
 		struct can_ram_layout layout;
 
-		can_ram_get_layout(&layout, &mcp251xfd_ram_config, NULL, NULL, fd_mode);
-		priv->rx_obj_num = layout.default_rx;
-		tx_ring->obj_num = layout.default_tx;
+		can_ram_get_layout(&layout, &mcp251xfd_ram_config, &ring, &ec, fd_mode);
+
+		priv->rx_obj_num = layout.cur_rx;
+		priv->rx_obj_num_coalesce_irq = layout.rx_coalesce;
+
+		tx_ring->obj_num = layout.cur_tx;
+		priv->tx_obj_num_coalesce_irq = layout.tx_coalesce;
 	}
 
 	if (fd_mode) {

net/can/bcm.c

@@ -1470,6 +1470,10 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
 
 		/* remove device reference, if this is our bound device */
 		if (bo->bound && bo->ifindex == dev->ifindex) {
+#if IS_ENABLED(CONFIG_PROC_FS)
+			if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read)
+				remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir);
+#endif
 			bo->bound   = 0;
 			bo->ifindex = 0;
 			notify_enodev = 1;