summaryrefslogtreecommitdiffstats
path: root/kernel/watchdog.c
diff options
context:
space:
mode:
authorDouglas Anderson <dianders@chromium.org>2023-05-19 19:18:32 +0200
committerAndrew Morton <akpm@linux-foundation.org>2023-06-10 02:44:19 +0200
commit81972551df9d168a8183b786ff4de06008469c2e (patch)
treec38cb9943a7e2037a4d3ec85ba3f0ea3691263ba /kernel/watchdog.c
parentwatchdog/perf: rename watchdog_hld.c to watchdog_perf.c (diff)
downloadlinux-81972551df9d168a8183b786ff4de06008469c2e.tar.xz
linux-81972551df9d168a8183b786ff4de06008469c2e.zip
watchdog/hardlockup: move perf hardlockup checking/panic to common watchdog.c
The perf hardlockup detector works by looking at interrupt counts and seeing if they change from run to run. The interrupt counts are managed by the common watchdog code via its watchdog_timer_fn(). Currently the API between the perf detector and the common code is a function: is_hardlockup(). When the hard lockup detector sees that function return true then it handles printing out debug info and inducing a panic if necessary. Let's change the API a little bit in preparation for the buddy hardlockup detector. The buddy hardlockup detector wants to print nearly the same debug info and have nearly the same panic behavior. That means we want to move all that code to the common file. For now, the code in the common file will only be there if the perf hardlockup detector is enabled, but eventually it will be selected by a common config. Right now, this _just_ moves the code from the perf detector file to the common file and changes the names. It doesn't make the changes that the buddy hardlockup detector will need and doesn't do any style cleanups. A future patch will do cleanup to make it more obvious what changed. With the above, we no longer have any callers of is_hardlockup() outside of the "watchdog.c" file, so we can remove it from the header, make it static, and move it to the same "#ifdef" block as our new watchdog_hardlockup_check(). While doing this, it can be noted that even if no hardlockup detectors were configured the existing code used to still have the code for counting/checking "hrtimer_interrupts" even if the perf hardlockup detector wasn't configured. We didn't need to do that, so move all the "hrtimer_interrupts" counting to only be there if the perf hardlockup detector is configured as well. This change is expected to be a no-op. Link: https://lkml.kernel.org/r/20230519101840.v5.8.Id4133d3183e798122dc3b6205e7852601f289071@changeid Signed-off-by: Douglas Anderson <dianders@chromium.org> Reviewed-by: Petr Mladek <pmladek@suse.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen-Yu Tsai <wens@csie.org> Cc: Christophe Leroy <christophe.leroy@csgroup.eu> Cc: Colin Cross <ccross@android.com> Cc: Daniel Thompson <daniel.thompson@linaro.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guenter Roeck <groeck@chromium.org> Cc: Ian Rogers <irogers@google.com> Cc: Lecopzer Chen <lecopzer.chen@mediatek.com> Cc: Marc Zyngier <maz@kernel.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masayoshi Mizuma <msys.mizuma@gmail.com> Cc: Matthias Kaehlcke <mka@chromium.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Pingfan Liu <kernelfans@gmail.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: "Ravi V. Shankar" <ravi.v.shankar@intel.com> Cc: Ricardo Neri <ricardo.neri@intel.com> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Boyd <swboyd@chromium.org> Cc: Sumit Garg <sumit.garg@linaro.org> Cc: Tzung-Bi Shih <tzungbi@chromium.org> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'kernel/watchdog.c')
-rw-r--r--kernel/watchdog.c93
1 files changed, 73 insertions, 20 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index c705a18b26bf..12ce37d76e7d 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -85,6 +85,78 @@ __setup("nmi_watchdog=", hardlockup_panic_setup);
#endif /* CONFIG_HARDLOCKUP_DETECTOR */
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
+
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
+static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
+static DEFINE_PER_CPU(bool, hard_watchdog_warn);
+static unsigned long hardlockup_allcpu_dumped;
+
+static bool is_hardlockup(void)
+{
+ unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
+
+ if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
+ return true;
+
+ __this_cpu_write(hrtimer_interrupts_saved, hrint);
+ return false;
+}
+
+static void watchdog_hardlockup_kick(void)
+{
+ __this_cpu_inc(hrtimer_interrupts);
+}
+
+void watchdog_hardlockup_check(struct pt_regs *regs)
+{
+ /* check for a hardlockup
+ * This is done by making sure our timer interrupt
+ * is incrementing. The timer interrupt should have
+ * fired multiple times before we overflow'd. If it hasn't
+ * then this is a good indication the cpu is stuck
+ */
+ if (is_hardlockup()) {
+ int this_cpu = smp_processor_id();
+
+ /* only print hardlockups once */
+ if (__this_cpu_read(hard_watchdog_warn) == true)
+ return;
+
+ pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
+ this_cpu);
+ print_modules();
+ print_irqtrace_events(current);
+ if (regs)
+ show_regs(regs);
+ else
+ dump_stack();
+
+ /*
+ * Perform all-CPU dump only once to avoid multiple hardlockups
+ * generating interleaving traces
+ */
+ if (sysctl_hardlockup_all_cpu_backtrace &&
+ !test_and_set_bit(0, &hardlockup_allcpu_dumped))
+ trigger_allbutself_cpu_backtrace();
+
+ if (hardlockup_panic)
+ nmi_panic(regs, "Hard LOCKUP");
+
+ __this_cpu_write(hard_watchdog_warn, true);
+ return;
+ }
+
+ __this_cpu_write(hard_watchdog_warn, false);
+ return;
+}
+
+#else /* CONFIG_HARDLOCKUP_DETECTOR_PERF */
+
+static inline void watchdog_hardlockup_kick(void) { }
+
+#endif /* !CONFIG_HARDLOCKUP_DETECTOR_PERF */
+
/*
* These functions can be overridden if an architecture implements its
* own hardlockup detector.
@@ -176,8 +248,6 @@ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
static DEFINE_PER_CPU(unsigned long, watchdog_report_ts);
static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
static DEFINE_PER_CPU(bool, softlockup_touch_sync);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
static unsigned long soft_lockup_nmi_warn;
static int __init nowatchdog_setup(char *str)
@@ -312,22 +382,6 @@ static int is_softlockup(unsigned long touch_ts,
}
/* watchdog detector functions */
-bool is_hardlockup(void)
-{
- unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
- if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
- return true;
-
- __this_cpu_write(hrtimer_interrupts_saved, hrint);
- return false;
-}
-
-static void watchdog_interrupt_count(void)
-{
- __this_cpu_inc(hrtimer_interrupts);
-}
-
static DEFINE_PER_CPU(struct completion, softlockup_completion);
static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
@@ -358,8 +412,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
if (!watchdog_enabled)
return HRTIMER_NORESTART;
- /* kick the hardlockup detector */
- watchdog_interrupt_count();
+ watchdog_hardlockup_kick();
/* kick the softlockup detector */
if (completion_done(this_cpu_ptr(&softlockup_completion))) {