printk: do cond_resched() between lines while outputting to consoles

commit 8d91f8b15361dfb438ab6eb3b319e2ded43458ff upstream.

@console_may_schedule tracks whether console_sem was acquired through
lock or trylock.  If the former, we're inside a sleepable context and
console_conditional_schedule() performs cond_resched().  This allows
console drivers which use console_lock for synchronization to yield
while performing time-consuming operations such as scrolling.

However, the actual console outputting is performed while holding
irq-safe logbuf_lock, so console_unlock() clears @console_may_schedule
before starting outputting lines.  Also, only a few drivers call
console_conditional_schedule() to begin with.  This means that when a
lot of lines need to be output by console_unlock(), for example on a
console registration, the task doing console_unlock() may not yield for
a long time on a non-preemptible kernel.

If this happens with a slow console devices, for example a serial
console, the outputting task may occupy the cpu for a very long time.
Long enough to trigger softlockup and/or RCU stall warnings, which in
turn pile more messages, sometimes enough to trigger the next cycle of
warnings incapacitating the system.

Fix it by making console_unlock() insert cond_resched() between lines if
@console_may_schedule.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Calvin Owens <calvinowens@fb.com>
Acked-by: Jan Kara <jack@suse.com>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Kyle McMartin <kyle@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/console.h b/include/linux/console.h
index bd194343c3460d85730e53ef340ca8337e5827a1..ea731af2451ee3607c16fda14d50fa684a54f03b 100644 (file)
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -150,6 +150,7 @@ extern int console_trylock(void);
 extern void console_unlock(void);
 extern void console_conditional_schedule(void);
 extern void console_unblank(void);
+extern void console_flush_on_panic(void);
 extern struct tty_driver *console_device(int *);
 extern void console_stop(struct console *);
 extern void console_start(struct console *);

diff --git a/kernel/panic.c b/kernel/panic.c
index 4b150bc0c6c111ee09f783eaa6aa101339f6ceec..41e2b54f36b5cdc73ecbda53a246662ba541ba57 100644 (file)
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -157,8 +157,7 @@ void panic(const char *fmt, ...)
         * panic() is not being callled from OOPS.
         */
        debug_locks_off();
-       console_trylock();
-       console_unlock();
+       console_flush_on_panic();
 
        if (!panic_blink)
                panic_blink = no_blink;

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 2ce8826f1053d801f0b003f5a3e67de0fdfe8e30..c048e34b177f2a5e63557f672e9827330c1b34cf 100644 (file)
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2233,13 +2233,24 @@ void console_unlock(void)
        static u64 seen_seq;
        unsigned long flags;
        bool wake_klogd = false;
-       bool retry;
+       bool do_cond_resched, retry;
 
        if (console_suspended) {
                up_console_sem();
                return;
        }
 
+       /*
+        * Console drivers are called under logbuf_lock, so
+        * @console_may_schedule should be cleared before; however, we may
+        * end up dumping a lot of lines, for example, if called from
+        * console registration path, and should invoke cond_resched()
+        * between lines if allowable.  Not doing so can cause a very long
+        * scheduling stall on a slow console leading to RCU stall and
+        * softlockup warnings which exacerbate the issue with more
+        * messages practically incapacitating the system.
+        */
+       do_cond_resched = console_may_schedule;
        console_may_schedule = 0;
 
        /* flush buffered message fragment immediately to console */
@@ -2311,6 +2322,9 @@ skip:
                call_console_drivers(level, ext_text, ext_len, text, len);
                start_critical_timings();
                local_irq_restore(flags);
+
+               if (do_cond_resched)
+                       cond_resched();
        }
        console_locked = 0;
 
@@ -2378,6 +2392,25 @@ void console_unblank(void)
        console_unlock();
 }
 
+/**
+ * console_flush_on_panic - flush console content on panic
+ *
+ * Immediately output all pending messages no matter what.
+ */
+void console_flush_on_panic(void)
+{
+       /*
+        * If someone else is holding the console lock, trylock will fail
+        * and may_schedule may be set.  Ignore and proceed to unlock so
+        * that messages are flushed out.  As this can be called from any
+        * context and we don't want to get preempted while flushing,
+        * ensure may_schedule is cleared.
+        */
+       console_trylock();
+       console_may_schedule = 0;
+       console_unlock();
+}
+
 /*
  * Return the console tty driver structure and its associated index
  */