[RFC][PATCHv5 6/7] printk: use printk_safe buffers in printk

[Sergey Senozhatsky]

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().

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+0x1cd/0x438
 CPU: 0 PID: 366 Comm: bash
 Call Trace:
  [<ffffffff81045658>] warn_slowpath_null+0x1d/0x1f
  [<ffffffff81091527>] vprintk_emit+0x1cd/0x438
  [<ffffffff810918fe>] vprintk_default+0x1d/0x1f
  [<ffffffff810fdf6a>] printk+0x48/0x50
  [..]
  [<ffffffff813caaaa>] entry_SYSCALL_64_fastpath+0x18/0xad
 ---[ end trace ]---

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+0x3d/0x62
 CPU: 1 PID: 363 Comm: bash
 Call Trace:
  [<ffffffff81045658>] warn_slowpath_null+0x1d/0x1f
  [<ffffffff810838df>] down_trylock+0x3d/0x62
  [<ffffffff8109177e>] ? vprintk_emit+0x3f9/0x414
  [<ffffffff810905cb>] console_trylock+0x31/0xeb
  [<ffffffff8109177e>] vprintk_emit+0x3f9/0x414
  [<ffffffff81091905>] vprintk_default+0x1d/0x1f
  [<ffffffff810fdf71>] printk+0x48/0x50
  [..]
  [<ffffffff813caaaa>] entry_SYSCALL_64_fastpath+0x18/0xad
 ---[ end trace ]---

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+0x12d/0x559
 CPU: 1 PID: 329 Comm: bash
 Call Trace:
  [<ffffffff8103d6ca>] warn_slowpath_null+0x18/0x1a
  [<ffffffff8107f917>] console_unlock+0x12d/0x559
  [<ffffffff810772c4>] ? trace_hardirqs_on_caller+0x16d/0x189
  [<ffffffff810772ed>] ? trace_hardirqs_on+0xd/0xf
  [<ffffffff810800a6>] vprintk_emit+0x363/0x374
  [<ffffffff81080219>] vprintk_default+0x18/0x1a
  [<ffffffff810c7f77>] printk+0x43/0x4b
  [..]
  [<ffffffff814c2d6a>] entry_SYSCALL_64_fastpath+0x18/0xad
 ---[ end trace ]---

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+0x7f/0x4f7
 CPU: 3 PID: 363 Comm: bash
 Call Trace:
  [<ffffffff81045658>] warn_slowpath_null+0x1d/0x1f
  [<ffffffff8106c8d0>] try_to_wake_up+0x7f/0x4f7
  [<ffffffff8106cd5d>] wake_up_process+0x15/0x17
  [<ffffffff813c82c6>] __up.isra.0+0x56/0x63
  [<ffffffff810839a3>] up+0x32/0x42
  [<ffffffff8108f624>] __up_console_sem+0x37/0x55
  [<ffffffff810910ff>] console_unlock+0x21e/0x4c2
  [<ffffffff810917bf>] vprintk_emit+0x41c/0x462
  [<ffffffff81091971>] vprintk_default+0x1d/0x1f
  [<ffffffff810fdfdd>] printk+0x48/0x50
  [..]
  [<ffffffff813cab2a>] entry_SYSCALL_64_fastpath+0x18/0xad
 ---[ end trace ]---

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+0x3a/0xb0
 CPU: 2 PID: 305 Comm: bash
 Call Trace:
  [<ffffffff810399c0>] warn_slowpath_null+0x18/0x1a
  [<ffffffff8106b218>] call_console_drivers.isra.6.constprop.16+0x3a/0xb0
  [<ffffffff8106cc46>] console_unlock+0x471/0x48e
  [<ffffffff8106ce57>] vprintk_emit+0x1f4/0x206
  [<ffffffff8106cfcb>] vprintk_default+0x18/0x1a
  [<ffffffff8106af66>] vprintk_func+0x6e/0x70
  [<ffffffff810abbe3>] printk+0x3e/0x46
[..]
  [<ffffffff8145a860>] entry_SYSCALL_64_fastpath+0x13/0x94
 ---[ end trace ]---

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
---
 kernel/printk/printk.c | 50 ++++++++++++++++++++++++++++++++------------------
 1 file changed, 32 insertions(+), 18 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 6f7b217..80f0177 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -213,17 +213,31 @@ 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;
+
+	printk_safe_enter(flags);
+	lock_failed = down_trylock(&console_sem);
+	printk_safe_exit(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(flags);
+	up(&console_sem);
+	printk_safe_exit(flags);
+}
+#define up_console_sem() __up_console_sem(_RET_IP_)
 
 /*
  * This is used for debugging the mess that is the VT code by
@@ -1788,7 +1802,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 	boot_delay_msec(level);
 	printk_delay();
 
-	local_irq_save(flags);
+	printk_safe_enter(flags);
 	this_cpu = smp_processor_id();
 
 	/*
@@ -1804,13 +1818,12 @@ 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(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;
@@ -1870,12 +1883,10 @@ 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(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
@@ -1883,7 +1894,6 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (console_trylock())
 			console_unlock();
-		lockdep_on();
 	}
 
 	return printed_len;
@@ -2263,7 +2273,8 @@ static void console_cont_flush(char *text, size_t size)
 	unsigned long flags;
 	size_t len;
 
-	raw_spin_lock_irqsave(&logbuf_lock, flags);
+	printk_safe_enter(flags);
+	raw_spin_lock(&logbuf_lock);
 
 	if (!cont.len)
 		goto out;
@@ -2288,10 +2299,11 @@ static void console_cont_flush(char *text, size_t size)
 	stop_critical_timings();
 	call_console_drivers(cont.level, NULL, 0, text, len);
 	start_critical_timings();
-	local_irq_restore(flags);
+	printk_safe_exit(flags);
 	return;
 out:
-	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+	raw_spin_unlock(&logbuf_lock);
+	printk_safe_exit(flags);
 }
 
 /**
@@ -2356,7 +2368,8 @@ void console_unlock(void)
 		size_t len;
 		int level;
 
-		raw_spin_lock_irqsave(&logbuf_lock, flags);
+		printk_safe_enter(flags);
+		raw_spin_lock(&logbuf_lock);
 		if (seen_seq != log_next_seq) {
 			wake_klogd = true;
 			seen_seq = log_next_seq;
@@ -2417,7 +2430,7 @@ 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(flags);
 
 		if (do_cond_resched)
 			cond_resched();
@@ -2440,7 +2453,8 @@ 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(flags);
 
 	if (retry && console_trylock())
 		goto again;
-- 
2.10.2