From d2068da5c85697b5880483dd7beaba98e0b62e02 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Tue, 18 Aug 2020 06:23:40 +0800 Subject: soundwire: cadence: fix race condition between suspend and Slave device alerts In system suspend stress cases, the SOF CI reports timeouts. The root cause is that an alert is generated while the system suspends. The interrupt handling generates transactions on the bus that will never be handled because the interrupts are disabled in parallel. As a result, the transaction never completes and times out on resume. This error doesn't seem too problematic since it happens in a work queue, and the system recovers without issues. Nevertheless, this race condition should not happen. When doing a system suspend, or when disabling interrupts, we should make sure the current transaction can complete, and prevent new work from being queued. BugLink: https://github.com/thesofproject/linux/issues/2344 Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Reviewed-by: Rander Wang Signed-off-by: Bard Liao Acked-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20200817222340.18042-1-yung-chuan.liao@linux.intel.com Signed-off-by: Vinod Koul --- drivers/soundwire/cadence_master.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'drivers/soundwire/cadence_master.c') diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index ecf503fb23e1..8c354f946879 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -790,7 +790,16 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) CDNS_MCP_INT_SLAVE_MASK, 0); int_status &= ~CDNS_MCP_INT_SLAVE_MASK; - schedule_work(&cdns->work); + + /* + * Deal with possible race condition between interrupt + * handling and disabling interrupts on suspend. + * + * If the master is in the process of disabling + * interrupts, don't schedule a workqueue + */ + if (cdns->interrupt_enabled) + schedule_work(&cdns->work); } cdns_writel(cdns, CDNS_MCP_INTSTAT, int_status); @@ -923,6 +932,19 @@ update_masks: slave_state = cdns_readl(cdns, CDNS_MCP_SLAVE_INTSTAT1); cdns_writel(cdns, CDNS_MCP_SLAVE_INTSTAT1, slave_state); } + cdns->interrupt_enabled = state; + + /* + * Complete any on-going status updates before updating masks, + * and cancel queued status updates. + * + * There could be a race with a new interrupt thrown before + * the 3 mask updates below are complete, so in the interrupt + * we use the 'interrupt_enabled' status to prevent new work + * from being queued. + */ + if (!state) + cancel_work_sync(&cdns->work); cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK0, slave_intmask0); cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK1, slave_intmask1); -- cgit v1.2.3