printk: use printk_safe buffers in printk

Use printk_safe per-CPU buffers in printk recursion-prone blocks:
-- around logbuf_lock protected sections in vprintk_emit() and
   console_unlock()
-- around down_trylock_console_sem() and up_console_sem()

Note that this solution addresses deadlocks caused by printk()
recursive calls only. That is vprintk_emit() and console_unlock().
The rest will be converted in a followup patch.

Another thing to note is that we now keep lockdep enabled in printk,
because we are protected against the printk recursion caused by
lockdep in vprintk_emit() by the printk-safe mechanism - we first
switch to per-CPU buffers and only then access the deadlock-prone
locks.

Examples:

1) printk() from logbuf_lock spin_lock section

Assume the following code:
  printk()
    raw_spin_lock(&logbuf_lock);
    WARN_ON(1);
    raw_spin_unlock(&logbuf_lock);

which now produces:

 ------------[ cut here ]------------
 WARNING: CPU: 0 PID: 366 at kernel/printk/printk.c:1811 vprintk_emit
 CPU: 0 PID: 366 Comm: bash
 Call Trace:
   warn_slowpath_null+0x1d/0x1f
   vprintk_emit+0x1cd/0x438
   vprintk_default+0x1d/0x1f
   printk+0x48/0x50
  [..]

2) printk() from semaphore sem->lock spin_lock section

Assume the following code

  printk()
    console_trylock()
      down_trylock()
        raw_spin_lock_irqsave(&sem->lock, flags);
        WARN_ON(1);
        raw_spin_unlock_irqrestore(&sem->lock, flags);

which now produces:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 363 at kernel/locking/semaphore.c:141 down_trylock
 CPU: 1 PID: 363 Comm: bash
 Call Trace:
   warn_slowpath_null+0x1d/0x1f
   down_trylock+0x3d/0x62
   ? vprintk_emit+0x3f9/0x414
   console_trylock+0x31/0xeb
   vprintk_emit+0x3f9/0x414
   vprintk_default+0x1d/0x1f
   printk+0x48/0x50
  [..]

3) printk() from console_unlock()

Assume the following code:

  printk()
    console_unlock()
      raw_spin_lock(&logbuf_lock);
      WARN_ON(1);
      raw_spin_unlock(&logbuf_lock);

which now produces:

 ------------[ cut here ]------------
 WARNING: CPU: 1 PID: 329 at kernel/printk/printk.c:2384 console_unlock
 CPU: 1 PID: 329 Comm: bash
 Call Trace:
   warn_slowpath_null+0x18/0x1a
   console_unlock+0x12d/0x559
   ? trace_hardirqs_on_caller+0x16d/0x189
   ? trace_hardirqs_on+0xd/0xf
   vprintk_emit+0x363/0x374
   vprintk_default+0x18/0x1a
   printk+0x43/0x4b
  [..]

4) printk() from try_to_wake_up()

Assume the following code:

  printk()
    console_unlock()
      up()
        try_to_wake_up()
          raw_spin_lock_irqsave(&p->pi_lock, flags);
          WARN_ON(1);
          raw_spin_unlock_irqrestore(&p->pi_lock, flags);

which now produces:

 ------------[ cut here ]------------
 WARNING: CPU: 3 PID: 363 at kernel/sched/core.c:2028 try_to_wake_up
 CPU: 3 PID: 363 Comm: bash
 Call Trace:
   warn_slowpath_null+0x1d/0x1f
   try_to_wake_up+0x7f/0x4f7
   wake_up_process+0x15/0x17
   __up.isra.0+0x56/0x63
   up+0x32/0x42
   __up_console_sem+0x37/0x55
   console_unlock+0x21e/0x4c2
   vprintk_emit+0x41c/0x462
   vprintk_default+0x1d/0x1f
   printk+0x48/0x50
  [..]

5) printk() from call_console_drivers()

Assume the following code:
  printk()
    console_unlock()
      call_console_drivers()
      ...
          WARN_ON(1);

which now produces:

 ------------[ cut here ]------------
 WARNING: CPU: 2 PID: 305 at kernel/printk/printk.c:1604 call_console_drivers
 CPU: 2 PID: 305 Comm: bash
 Call Trace:
   warn_slowpath_null+0x18/0x1a
   call_console_drivers.isra.6.constprop.16+0x3a/0xb0
   console_unlock+0x471/0x48e
   vprintk_emit+0x1f4/0x206
   vprintk_default+0x18/0x1a
   vprintk_func+0x6e/0x70
   printk+0x3e/0x46
  [..]

6) unsupported placeholder in printk() format now prints an actual
   warning from vscnprintf(), instead of
   	'BUG: recent printk recursion!'.

 ------------[ cut here ]------------
 WARNING: CPU: 5 PID: 337 at lib/vsprintf.c:1900 format_decode
 Please remove unsupported %
  in format string
 CPU: 5 PID: 337 Comm: bash
 Call Trace:
   dump_stack+0x4f/0x65
   __warn+0xc2/0xdd
   warn_slowpath_fmt+0x4b/0x53
   format_decode+0x22c/0x308
   vsnprintf+0x89/0x3b7
   vscnprintf+0xd/0x26
   vprintk_emit+0xb4/0x238
   vprintk_default+0x1d/0x1f
   vprintk_func+0x6c/0x73
   printk+0x43/0x4b
  [..]

Link: http://lkml.kernel.org/r/[email protected]
Cc: Andrew Morton <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Jan Kara <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Calvin Owens <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Peter Hurley <[email protected]>
Cc: [email protected]
Signed-off-by: Sergey Senozhatsky <[email protected]>
Signed-off-by: Petr Mladek <[email protected]>
Reviewed-by: Steven Rostedt (VMware) <[email protected]>

Author: sergey-senozhatsky

kernel/printk/printk.c

@@ -213,17 +213,36 @@ static int nr_ext_console_drivers;
 
 static int __down_trylock_console_sem(unsigned long ip)
 {
-	if (down_trylock(&console_sem))
+	int lock_failed;
+	unsigned long flags;
+
+	/*
+	 * Here and in __up_console_sem() we need to be in safe mode,
+	 * because spindump/WARN/etc from under console ->lock will
+	 * deadlock in printk()->down_trylock_console_sem() otherwise.
+	 */
+	printk_safe_enter_irqsave(flags);
+	lock_failed = down_trylock(&console_sem);
+	printk_safe_exit_irqrestore(flags);
+
+	if (lock_failed)
 		return 1;
 	mutex_acquire(&console_lock_dep_map, 0, 1, ip);
 	return 0;
 }
 #define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_)
 
-#define up_console_sem() do { \
-	mutex_release(&console_lock_dep_map, 1, _RET_IP_);\
-	up(&console_sem);\
-} while (0)
+static void __up_console_sem(unsigned long ip)
+{
+	unsigned long flags;
+
+	mutex_release(&console_lock_dep_map, 1, ip);
+
+	printk_safe_enter_irqsave(flags);
+	up(&console_sem);
+	printk_safe_exit_irqrestore(flags);
+}
+#define up_console_sem() __up_console_sem(_RET_IP_)
 
 /*
  * This is used for debugging the mess that is the VT code by
@@ -1689,7 +1708,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	boot_delay_msec(level);
 	printk_delay();
 
-	local_irq_save(flags);
+	printk_safe_enter_irqsave(flags);
 	this_cpu = smp_processor_id();
 
 	/*
@@ -1705,13 +1724,12 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (!oops_in_progress && !lockdep_recursing(current)) {
 			recursion_bug = true;
-			local_irq_restore(flags);
+			printk_safe_exit_irqrestore(flags);
 			return 0;
 		}
 		zap_locks();
 	}
 
-	lockdep_off();
 	/* This stops the holder of console_sem just where we want him */
 	raw_spin_lock(&logbuf_lock);
 	logbuf_cpu = this_cpu;
@@ -1771,20 +1789,17 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
-	lockdep_on();
-	local_irq_restore(flags);
+	printk_safe_exit_irqrestore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
 	if (!in_sched) {
-		lockdep_off();
 		/*
 		 * Try to acquire and then immediately release the console
 		 * semaphore.  The release will print out buffers and wake up
 		 * /dev/kmsg and syslog() users.
 		 */
 		if (console_trylock())
 			console_unlock();
-		lockdep_on();
 	}
 
 	return printed_len;
@@ -2209,7 +2224,8 @@ void console_unlock(void)
 		size_t len;
 		int level;
 
-		raw_spin_lock_irqsave(&logbuf_lock, flags);
+		printk_safe_enter_irqsave(flags);
+		raw_spin_lock(&logbuf_lock);
 		if (seen_seq != log_next_seq) {
 			wake_klogd = true;
 			seen_seq = log_next_seq;
@@ -2259,7 +2275,7 @@ void console_unlock(void)
 		stop_critical_timings();	/* don't trace print latency */
 		call_console_drivers(level, ext_text, ext_len, text, len);
 		start_critical_timings();
-		local_irq_restore(flags);
+		printk_safe_exit_irqrestore(flags);
 
 		if (do_cond_resched)
 			cond_resched();
@@ -2282,7 +2298,8 @@ void console_unlock(void)
 	 */
 	raw_spin_lock(&logbuf_lock);
 	retry = console_seq != log_next_seq;
-	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+	raw_spin_unlock(&logbuf_lock);
+	printk_safe_exit_irqrestore(flags);
 
 	if (retry && console_trylock())
 		goto again;