From e862d7b786f566e69d604e461410e786666d6148 Mon Sep 17 00:00:00 2001 From: Matthias Schiffer Date: Fri, 14 Mar 2025 12:03:09 +0900 Subject: [PATCH] can: m_can: fix missed interrupts with m_can_pci BugLink: https://bugs.launchpad.net/bugs/2102266 [ Upstream commit 743375f8deee360b0e902074bab99b0c9368d42f ] The interrupt line of PCI devices is interpreted as edge-triggered, however the interrupt signal of the m_can controller integrated in Intel Elkhart Lake CPUs appears to be generated level-triggered. Consider the following sequence of events: - IR register is read, interrupt X is set - A new interrupt Y is triggered in the m_can controller - IR register is written to acknowledge interrupt X. Y remains set in IR As at no point in this sequence no interrupt flag is set in IR, the m_can interrupt line will never become deasserted, and no edge will ever be observed to trigger another run of the ISR. This was observed to result in the TX queue of the EHL m_can to get stuck under high load, because frames were queued to the hardware in m_can_start_xmit(), but m_can_finish_tx() was never run to account for their successful transmission. On an Elkhart Lake based board with the two CAN interfaces connected to each other, the following script can reproduce the issue: ip link set can0 up type can bitrate 1000000 ip link set can1 up type can bitrate 1000000 cangen can0 -g 2 -I 000 -L 8 & cangen can0 -g 2 -I 001 -L 8 & cangen can0 -g 2 -I 002 -L 8 & cangen can0 -g 2 -I 003 -L 8 & cangen can0 -g 2 -I 004 -L 8 & cangen can0 -g 2 -I 005 -L 8 & cangen can0 -g 2 -I 006 -L 8 & cangen can0 -g 2 -I 007 -L 8 & cangen can1 -g 2 -I 100 -L 8 & cangen can1 -g 2 -I 101 -L 8 & cangen can1 -g 2 -I 102 -L 8 & cangen can1 -g 2 -I 103 -L 8 & cangen can1 -g 2 -I 104 -L 8 & cangen can1 -g 2 -I 105 -L 8 & cangen can1 -g 2 -I 106 -L 8 & cangen can1 -g 2 -I 107 -L 8 & stress-ng --matrix 0 & To fix the issue, repeatedly read and acknowledge interrupts at the start of the ISR until no interrupt flags are set, so the next incoming interrupt will also result in an edge on the interrupt line. While we have received a report that even with this patch, the TX queue can become stuck under certain (currently unknown) circumstances on the Elkhart Lake, this patch completely fixes the issue with the above reproducer, and it is unclear whether the remaining issue has a similar cause at all. Fixes: cab7ffc0324f ("can: m_can: add PCI glue driver for Intel Elkhart Lake") Signed-off-by: Matthias Schiffer Reviewed-by: Markus Schneider-Pargmann Link: https://patch.msgid.link/fdf0439c51bcb3a46c21e9fb21c7f1d06363be84.1728288535.git.matthias.schiffer@ew.tq-group.com Signed-off-by: Marc Kleine-Budde Signed-off-by: Sasha Levin [koichiroden: adjusted context due to multiple missing commits related to rx coalescing] Signed-off-by: Koichiro Den Signed-off-by: Mehmet Basaran --- drivers/net/can/m_can/m_can.c | 23 ++++++++++++++++++----- drivers/net/can/m_can/m_can.h | 1 + drivers/net/can/m_can/m_can_pci.c | 1 + 3 files changed, 20 insertions(+), 5 deletions(-) diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index d58bb3640450..e5dccde765e6 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1089,18 +1089,31 @@ static int m_can_echo_tx_event(struct net_device *dev) static int m_can_interrupt_handler(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - u32 ir; + u32 ir = 0, ir_read; int ret; if (pm_runtime_suspended(cdev->dev)) return IRQ_NONE; - ir = m_can_read(cdev, M_CAN_IR); + + /* The m_can controller signals its interrupt status as a level, but + * depending in the integration the CPU may interpret the signal as + * edge-triggered (for example with m_can_pci). For these + * edge-triggered integrations, we must observe that IR is 0 at least + * once to be sure that the next interrupt will generate an edge. + */ + while ((ir_read = m_can_read(cdev, M_CAN_IR)) != 0) { + ir |= ir_read; + + /* ACK all irqs */ + m_can_write(cdev, M_CAN_IR, ir); + + if (!cdev->irq_edge_triggered) + break; + } + if (!ir) return IRQ_NONE; - /* ACK all irqs */ - m_can_write(cdev, M_CAN_IR, ir); - if (cdev->ops->clear_interrupts) cdev->ops->clear_interrupts(cdev); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index 520e14277dff..0a0953206054 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -91,6 +91,7 @@ struct m_can_classdev { int pm_clock_support; int is_peripheral; + bool irq_edge_triggered; struct mram_cfg mcfg[MRAM_CFG_NUM]; diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index f2219aa2824b..0363edd1773f 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -126,6 +126,7 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class->net->irq = pci_irq_vector(pci, 0); mcan_class->pm_clock_support = 1; mcan_class->can.clock.freq = id->driver_data; + mcan_class->irq_edge_triggered = true; mcan_class->ops = &m_can_pci_ops; pci_set_drvdata(pci, mcan_class);