softlockup: make detector be aware of task switch of processes hogging cpu

For now, soft lockup detector warns once for each case of process
softlockup.  But the thread 'watchdog/n' may not always get the cpu at the
time slot between the task switch of two processes hogging that cpu to
reset soft_watchdog_warn.

An example would be two processes hogging the cpu.  Process A causes the
softlockup warning and is killed manually by a user.  Process B
immediately becomes the new process hogging the cpu preventing the
softlockup code from resetting the soft_watchdog_warn variable.

This case is a false negative of "warn only once for a process", as there
may be a different process that is going to hog the cpu.  Resolve this by
saving/checking the task pointer of the hogging process and use that to
reset soft_watchdog_warn too.

[dzickus@redhat.com: update comment]
Signed-off-by: chai wen <chaiw.fnst@cn.fujitsu.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index a8d6914030fe6ec5aa9e08154ce29b480d2c0745..7b223b212683202e2e50ee83153eb8df7dbbe3de 100644 (file)
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -47,6 +47,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
 static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt);
+static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
@@ -333,8 +334,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
                        return HRTIMER_RESTART;
 
                /* only warn once */
-               if (__this_cpu_read(soft_watchdog_warn) == true)
+               if (__this_cpu_read(soft_watchdog_warn) == true) {
+                       /*
+                        * When multiple processes are causing softlockups the
+                        * softlockup detector only warns on the first one
+                        * because the code relies on a full quiet cycle to
+                        * re-arm.  The second process prevents the quiet cycle
+                        * and never gets reported.  Use task pointers to detect
+                        * this.
+                        */
+                       if (__this_cpu_read(softlockup_task_ptr_saved) !=
+                           current) {
+                               __this_cpu_write(soft_watchdog_warn, false);
+                               __touch_watchdog();
+                       }
                        return HRTIMER_RESTART;
+               }
 
                if (softlockup_all_cpu_backtrace) {
                        /* Prevent multiple soft-lockup reports if one cpu is already
@@ -350,6 +365,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
                pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
                        smp_processor_id(), duration,
                        current->comm, task_pid_nr(current));
+               __this_cpu_write(softlockup_task_ptr_saved, current);
                print_modules();
                print_irqtrace_events(current);
                if (regs)