summaryrefslogtreecommitdiff
path: root/kernel/watchdog.c
diff options
context:
space:
mode:
authorPetr Mladek <pmladek@suse.com>2021-05-23 03:41:59 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-05-23 04:09:07 +0300
commit0f90b88dbcd1143e0f408502eba0af97429c502a (patch)
treece6cec6574aa7a44f834bad3197e33635d95dd36 /kernel/watchdog.c
parentf70b00496f2a0669fdb19a783e613bdbdedcf901 (diff)
downloadlinux-0f90b88dbcd1143e0f408502eba0af97429c502a.tar.xz
watchdog: reliable handling of timestamps
Commit 9bf3bc949f8a ("watchdog: cleanup handling of false positives") tried to handle a virtual host stopped by the host a more straightforward and cleaner way. But it introduced a risk of false softlockup reports. The virtual host might be stopped at any time, for example between kvm_check_and_clear_guest_paused() and is_softlockup(). As a result, is_softlockup() might read the updated jiffies and detects a softlockup. A solution might be to put back kvm_check_and_clear_guest_paused() after is_softlockup() and detect it. But it would put back the cycle that complicates the logic. In fact, the handling of all the timestamps is not reliable. The code does not guarantee when and how many times the timestamps are read. For example, "period_ts" might be touched anytime also from NMI and re-read in is_softlockup(). It works just by chance. Fix all the problems by making the code even more explicit. 1. Make sure that "now" and "period_ts" timestamps are read only once. They might be changed at anytime by NMI or when the virtual guest is stopped by the host. Note that "now" timestamp does this implicitly because "jiffies" is marked volatile. 2. "now" time must be read first. The state of "period_ts" will decide whether it will be used or the period will get restarted. 3. kvm_check_and_clear_guest_paused() must be called before reading "period_ts". It touches the variable when the guest was stopped. As a result, "now" timestamp is used only when the watchdog was not touched and the guest not stopped in the meantime. "period_ts" is restarted in all other situations. Link: https://lkml.kernel.org/r/YKT55gw+RZfyoFf7@alley Fixes: 9bf3bc949f8aeefeacea4b ("watchdog: cleanup handling of false positives") Signed-off-by: Petr Mladek <pmladek@suse.com> Reported-by: Sergey Senozhatsky <senozhatsky@chromium.org> Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/watchdog.c')
-rw-r--r--kernel/watchdog.c34
1 files changed, 20 insertions, 14 deletions
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 7c397907d0e9..92d3bcc5a5e0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -302,10 +302,10 @@ void touch_softlockup_watchdog_sync(void)
__this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT);
}
-static int is_softlockup(unsigned long touch_ts, unsigned long period_ts)
+static int is_softlockup(unsigned long touch_ts,
+ unsigned long period_ts,
+ unsigned long now)
{
- unsigned long now = get_timestamp();
-
if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
/* Warn about unreasonable delays. */
if (time_after(now, period_ts + get_softlockup_thresh()))
@@ -353,8 +353,7 @@ static int softlockup_fn(void *data)
/* watchdog kicker functions */
static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
{
- unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts);
- unsigned long period_ts = __this_cpu_read(watchdog_report_ts);
+ unsigned long touch_ts, period_ts, now;
struct pt_regs *regs = get_irq_regs();
int duration;
int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
@@ -377,11 +376,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
/*
+ * Read the current timestamp first. It might become invalid anytime
+ * when a virtual machine is stopped by the host or when the watchog
+ * is touched from NMI.
+ */
+ now = get_timestamp();
+ /*
* If a virtual machine is stopped by the host it can look to
- * the watchdog like a soft lockup. Check to see if the host
- * stopped the vm before we process the timestamps.
+ * the watchdog like a soft lockup. This function touches the watchdog.
*/
kvm_check_and_clear_guest_paused();
+ /*
+ * The stored timestamp is comparable with @now only when not touched.
+ * It might get touched anytime from NMI. Make sure that is_softlockup()
+ * uses the same (valid) value.
+ */
+ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts));
/* Reset the interval when touched by known problematic code. */
if (period_ts == SOFTLOCKUP_DELAY_REPORT) {
@@ -398,13 +408,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
return HRTIMER_RESTART;
}
- /* check for a softlockup
- * This is done by making sure a high priority task is
- * being scheduled. The task touches the watchdog to
- * indicate it is getting cpu time. If it hasn't then
- * this is a good indication some task is hogging the cpu
- */
- duration = is_softlockup(touch_ts, period_ts);
+ /* Check for a softlockup. */
+ touch_ts = __this_cpu_read(watchdog_touch_ts);
+ duration = is_softlockup(touch_ts, period_ts, now);
if (unlikely(duration)) {
/*
* Prevent multiple soft-lockup reports if one cpu is already