From bcfba4f4bf3c9c7c72b459d52a9e826dfd72855e Mon Sep 17 00:00:00 2001 From: Ulrich Obergfell Date: Tue, 14 Apr 2015 15:44:10 -0700 Subject: watchdog: implement error handling for failure to set up hardware perf events If watchdog_nmi_enable() fails to set up the hardware perf event of one CPU, the entire hard lockup detector is deemed unreliable. Hence, disable the hard lockup detector and shut down the hardware perf events on all CPUs. [dzickus@redhat.com: update comments to explain some code] Signed-off-by: Ulrich Obergfell Signed-off-by: Don Zickus Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 26002ed..fd2b6dc 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -502,6 +502,21 @@ static void watchdog(unsigned int cpu) __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); + + /* + * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the + * failure path. Check for failures that can occur asynchronously - + * for example, when CPUs are on-lined - and shut down the hardware + * perf event on each CPU accordingly. + * + * The only non-obvious place this bit can be cleared is through + * watchdog_nmi_enable(), so a pr_info() is placed there. Placing a + * pr_info here would be too noisy as it would result in a message + * every few seconds if the hardlockup was disabled but the softlockup + * enabled. + */ + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) + watchdog_nmi_disable(cpu); } #ifdef CONFIG_HARDLOCKUP_DETECTOR @@ -552,6 +567,18 @@ handle_err: goto out_save; } + /* + * Disable the hard lockup detector if _any_ CPU fails to set up + * set up the hardware perf event. The watchdog() function checks + * the NMI_WATCHDOG_ENABLED bit periodically. + * + * The barriers are for syncing up watchdog_enabled across all the + * cpus, as clear_bit() does not use barriers. + */ + smp_mb__before_atomic(); + clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); + smp_mb__after_atomic(); + /* skip displaying the same error again */ if (cpu > 0 && (PTR_ERR(event) == cpu0_err)) return PTR_ERR(event); @@ -565,6 +592,9 @@ handle_err: else pr_err("disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event)); + + pr_info("Shutting down hard lockup detector on all cpus\n"); + return PTR_ERR(event); /* success path */ -- cgit v0.10.2