iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

printk: fix deadlock when kernel panic

Browse Source 
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@bytedance.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: <stable@vger.kernel.org>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20210210034823.64867-1-songmuchun@bytedance.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Muchun Song 2021-02-10 11:48:23 +08:00 committed by Greg Kroah-Hartman
parent 02a5c25073
commit beb25678ff
1 changed files with 12 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
kernel/printk/nmi.c
View File

@ -52,6 +52,8 @@ struct nmi_seq_buf {
};
static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
static DEFINE_RAW_SPINLOCK(nmi_read_lock);
/*
* Safe printk() for NMI context. It uses a per-CPU buffer to
* store the message. NMIs are not nested, so there is always only
@ -134,8 +136,6 @@ static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
*/
static void __printk_nmi_flush(struct irq_work *work)
{
static raw_spinlock_t read_lock =
__RAW_SPIN_LOCK_INITIALIZER(read_lock);
struct nmi_seq_buf *s = container_of(work, struct nmi_seq_buf, work);
unsigned long flags;
size_t len, size;
@ -148,7 +148,7 @@ static void __printk_nmi_flush(struct irq_work *work)
* different CPUs. This is especially important when printing
* a backtrace.
*/
raw_spin_lock_irqsave(&read_lock, flags);
raw_spin_lock_irqsave(&nmi_read_lock, flags);
i = 0;
more:
@ -197,7 +197,7 @@ more:
goto more;
out:
raw_spin_unlock_irqrestore(&read_lock, flags);
raw_spin_unlock_irqrestore(&nmi_read_lock, flags);
}
/**
@ -239,6 +239,14 @@ void printk_nmi_flush_on_panic(void)
raw_spin_lock_init(&logbuf_lock);
}
if (in_nmi() && raw_spin_is_locked(&nmi_read_lock)) {
if (num_online_cpus() > 1)
return;
debug_locks_off();
raw_spin_lock_init(&nmi_read_lock);
}
printk_nmi_flush();
}