lkml.org 
[lkml]   [2021]   [Feb]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v2] printk: fix deadlock when kernel panic
Date
We found a deadlock bug on our server when the kernel panic. It can be
described in the following diagram.

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)

The register_nmi_handler() can be called in the __crash_kexec() or the
crash_smp_send_stop() on the x86-64. Because CPU1 is interrupted by the
NMI with holding the read_lock and crash_nmi_callback() never returns,
CPU0 can deadlock when printk_safe_flush_on_panic() is called.

When we hold the read_lock and then interrupted by the NMI, if the NMI
handler call nmi_panic(), it is also can lead to deadlock.

In order to fix it, we make read_lock global and rename it to
safe_read_lock. And we handle safe_read_lock the same way in
printk_safe_flush_on_panic() as we handle logbuf_lock there.

Fixes: cf9b1106c81c ("printk/nmi: flush NMI messages on the system panic")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
v2:
- handle read_lock the same way as we handle logbuf_lock there.

Thanks Petr.

kernel/printk/printk_safe.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index a0e6f746de6c..2e9e3ed7d63e 100644
--- 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 printk_safe_seq_buf *s)
*/
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 irq_work *work)
* 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 @@ static void __printk_safe_flush(struct irq_work *work)

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();
}

--
2.11.0
\
 
 \ /
  Last update: 2021-02-06 06:43    [W:0.201 / U:3.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site