linux-kernel - [PATCH 5.10 617/663] printk: fix deadlock when kernel panic

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210301161212.371954534@linuxfoundation.org>
Date:   Mon,  1 Mar 2021 17:14:25 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Muchun Song <songmuchun@...edance.com>,
        Petr Mladek <pmladek@...e.com>,
        Sergey Senozhatsky <sergey.senozhatsky@...il.com>
Subject: [PATCH 5.10 617/663] printk: fix deadlock when kernel panic

From: Muchun Song <songmuchun@...edance.com>

commit 8a8109f303e25a27f92c1d8edd67d7cbbc60a4eb upstream.

printk_safe_flush_on_panic() caused the following deadlock on our
server:

CPU0:                                         CPU1:
panic                                         rcu_dump_cpu_stacks
  kdump_nmi_shootdown_cpus                      nmi_trigger_cpumask_backtrace
    register_nmi_handler(crash_nmi_callback)      printk_safe_flush
                                                    __printk_safe_flush
                                                      raw_spin_lock_irqsave(&read_lock)
    // send NMI to other processors
    apic_send_IPI_allbutself(NMI_VECTOR)
                                                        // NMI interrupt, dead loop
                                                        crash_nmi_callback
  printk_safe_flush_on_panic
    printk_safe_flush
      __printk_safe_flush
        // deadlock
        raw_spin_lock_irqsave(&read_lock)

DEADLOCK: read_lock is taken on CPU1 and will never get released.

It happens when panic() stops a CPU by NMI while it has been in
the middle of printk_safe_flush().

Handle the lock the same way as logbuf_lock. The printk_safe buffers
are flushed only when both locks can be safely taken. It can avoid
the deadlock _in this particular case_ at expense of losing contents
of printk_safe buffers.

Note: It would actually be safe to re-init the locks when all CPUs were
      stopped by NMI. But it would require passing this information
      from arch-specific code. It is not worth the complexity.
      Especially because logbuf_lock and printk_safe buffers have been
      obsoleted by the lockless ring buffer.

Fixes: cf9b1106c81c ("printk/nmi: flush NMI messages on the system panic")
Signed-off-by: Muchun Song <songmuchun@...edance.com>
Reviewed-by: Petr Mladek <pmladek@...e.com>
Cc: <stable@...r.kernel.org>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@...il.com>
Signed-off-by: Petr Mladek <pmladek@...e.com>
Link: https://lore.kernel.org/r/20210210034823.64867-1-songmuchun@bytedance.com
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 kernel/printk/printk_safe.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -45,6 +45,8 @@ struct printk_safe_seq_buf {
 static DEFINE_PER_CPU(struct printk_safe_seq_buf, safe_print_seq);
 static DEFINE_PER_CPU(int, printk_context);
 
+static DEFINE_RAW_SPINLOCK(safe_read_lock);
+
 #ifdef CONFIG_PRINTK_NMI
 static DEFINE_PER_CPU(struct printk_safe_seq_buf, nmi_print_seq);
 #endif
@@ -180,8 +182,6 @@ static void report_message_lost(struct p
  */
 static void __printk_safe_flush(struct irq_work *work)
 {
-	static raw_spinlock_t read_lock =
-		__RAW_SPIN_LOCK_INITIALIZER(read_lock);
 	struct printk_safe_seq_buf *s =
 		container_of(work, struct printk_safe_seq_buf, work);
 	unsigned long flags;
@@ -195,7 +195,7 @@ static void __printk_safe_flush(struct i
 	 * different CPUs. This is especially important when printing
 	 * a backtrace.
 	 */
-	raw_spin_lock_irqsave(&read_lock, flags);
+	raw_spin_lock_irqsave(&safe_read_lock, flags);
 
 	i = 0;
 more:
@@ -232,7 +232,7 @@ more:
 
 out:
 	report_message_lost(s);
-	raw_spin_unlock_irqrestore(&read_lock, flags);
+	raw_spin_unlock_irqrestore(&safe_read_lock, flags);
 }
 
 /**
@@ -278,6 +278,14 @@ void printk_safe_flush_on_panic(void)
 		raw_spin_lock_init(&logbuf_lock);
 	}
 
+	if (raw_spin_is_locked(&safe_read_lock)) {
+		if (num_online_cpus() > 1)
+			return;
+
+		debug_locks_off();
+		raw_spin_lock_init(&safe_read_lock);
+	}
+
 	printk_safe_flush();
 }