From acc195bd2cc48445ea35d00036d8c0afcc4fcc9c Mon Sep 17 00:00:00 2001 From: Jerry Hoemann Date: Sun, 22 Nov 2020 19:08:39 -0700 Subject: watchdog/hpwdt: Disable NMI in Crash Kernel NMIs received during the crash path are problematic as hpwdt_pretimeout handling of the NMI would cause a reentry into kdump. The situation is complicated in that I/O errors can be signaled as NMI circumventing hpwdt_pretimeout's attempt to not claim NMI not associated with either the WDT or the iLO NMI switch. These NMI can additionally cause a secondary NMI which cause the system to hang. By disabling pretimeout and hpwdtimeout in crash path we both reduce the risk of receiving an NMI and simuletaneously leave the WDT running (if it was already in use) to allow the WDT to break the system out of hangs by the WDT reset. Signed-off-by: Jerry Hoemann Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/1606097320-56762-2-git-send-email-jerry.hoemann@hpe.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/hpwdt.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 7d34bcf1c45b..eeb4df24a7e7 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -21,6 +21,7 @@ #include #include #include +#include #define HPWDT_VERSION "2.0.3" #define SECS_TO_TICKS(secs) ((secs) * 1000 / 128) @@ -334,6 +335,11 @@ static int hpwdt_init_one(struct pci_dev *dev, watchdog_set_nowayout(&hpwdt_dev, nowayout); watchdog_init_timeout(&hpwdt_dev, soft_margin, NULL); + if (is_kdump_kernel()) { + pretimeout = 0; + kdumptimeout = 0; + } + if (pretimeout && hpwdt_dev.timeout <= PRETIMEOUT_SEC) { dev_warn(&dev->dev, "timeout <= pretimeout. Setting pretimeout to zero\n"); pretimeout = 0; -- cgit v1.2.3-59-g8ed1b