From 801ad2f87b0c6d0c34a75a4efd6bfd3a2d9f9298 Mon Sep 17 00:00:00 2001 From: Jake Hamby Date: Fri, 6 Sep 2024 23:19:51 +0000 Subject: [PATCH 1/2] can: m_can: enable NAPI before enabling interrupts If an interrupt (RX-complete or error flag) is set when bringing up the CAN device, e.g. due to CAN bus traffic before initializing the device, when m_can_start() is called and interrupts are enabled, m_can_isr() is called immediately, which disables all CAN interrupts and calls napi_schedule(). Because napi_enable() isn't called until later in m_can_open(), the call to napi_schedule() never schedules the m_can_poll() callback and the device is left with interrupts disabled and can't receive any CAN packets until rebooted. This can be verified by running "cansend" from another device before setting the bitrate and calling "ip link set up can0" on the test device. Adding debug lines to m_can_isr() shows it's called with flags (IR_EP | IR_EW | IR_CRCE), which calls m_can_disable_all_interrupts() and napi_schedule(), and then m_can_poll() is never called. Move the call to napi_enable() above the call to m_can_start() to enable any initial interrupt flags to be handled by m_can_poll() so that interrupts are reenabled. Add a call to napi_disable() in the error handling section of m_can_open(), to handle the case where later functions return errors. Also, in m_can_close(), move the call to napi_disable() below the call to m_can_stop() to ensure all interrupts are handled when bringing down the device. This race condition is much less likely to occur. Tested on a Microchip SAMA7G54 MPU. The fix should be applicable to any SoC with a Bosch M_CAN controller. Signed-off-by: Jake Hamby Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Link: https://patch.msgid.link/20240910-can-m_can-fix-ifup-v3-1-6c1720ba45ce@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 012c3d22b01d..c1a07013433e 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1763,9 +1763,6 @@ static int m_can_close(struct net_device *dev) netif_stop_queue(dev); - if (!cdev->is_peripheral) - napi_disable(&cdev->napi); - m_can_stop(dev); m_can_clk_stop(cdev); free_irq(dev->irq, dev); @@ -1776,6 +1773,8 @@ static int m_can_close(struct net_device *dev) destroy_workqueue(cdev->tx_wq); cdev->tx_wq = NULL; can_rx_offload_disable(&cdev->offload); + } else { + napi_disable(&cdev->napi); } close_candev(dev); @@ -2030,6 +2029,8 @@ static int m_can_open(struct net_device *dev) if (cdev->is_peripheral) can_rx_offload_enable(&cdev->offload); + else + napi_enable(&cdev->napi); /* register interrupt handler */ if (cdev->is_peripheral) { @@ -2063,9 +2064,6 @@ static int m_can_open(struct net_device *dev) if (err) goto exit_start_fail; - if (!cdev->is_peripheral) - napi_enable(&cdev->napi); - netif_start_queue(dev); return 0; @@ -2079,6 +2077,8 @@ static int m_can_open(struct net_device *dev) out_wq_fail: if (cdev->is_peripheral) can_rx_offload_disable(&cdev->offload); + else + napi_disable(&cdev->napi); close_candev(dev); exit_disable_clks: m_can_clk_stop(cdev); From 2c09b50efcad985cf920ca88baa9aa52b1999dcc Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Mon, 9 Sep 2024 15:07:41 +0200 Subject: [PATCH 2/2] can: m_can: m_can_close(): stop clocks after device has been shut down After calling m_can_stop() an interrupt may be pending or NAPI might still be executed. This means the driver might still touch registers of the IP core after the clocks have been disabled. This is not good practice and might lead to aborts depending on the SoC integration. To avoid these potential problems, make m_can_close() symmetric to m_can_open(), i.e. stop the clocks at the end, right before shutting down the transceiver. Fixes: e0d1f4816f2a ("can: m_can: add Bosch M_CAN controller support") Link: https://patch.msgid.link/20240910-can-m_can-fix-ifup-v3-2-6c1720ba45ce@pengutronix.de Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index c1a07013433e..7fec04b024d5 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1764,7 +1764,6 @@ static int m_can_close(struct net_device *dev) netif_stop_queue(dev); m_can_stop(dev); - m_can_clk_stop(cdev); free_irq(dev->irq, dev); m_can_clean(dev); @@ -1779,6 +1778,7 @@ static int m_can_close(struct net_device *dev) close_candev(dev); + m_can_clk_stop(cdev); phy_power_off(cdev->transceiver); return 0;