[V2 PATCH 1/3] x86/panic: Fix re-entrance problem due to panic on NMI

[Hidehiro Kawai]

If panic on NMI happens just after panic() on the same CPU, panic()
is recursively called.  As the result, it stalls after failing to
acquire panic_lock.

To avoid this problem, don't call panic() in NMI context if
we've already entered panic().

V2:
- Use atomic_cmpxchg() instead of current spin_trylock() to
  exclude concurrent accesses to the panic routines
- Don't introduce no-lock version of panic()

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@xxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
 arch/x86/kernel/nmi.c  |   15 +++++++++++----
 include/linux/kernel.h |    1 +
 kernel/panic.c         |   13 ++++++++++---
 3 files changed, 22 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index d05bd2e..5b32d81 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -230,7 +230,8 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 	}
 #endif
 
-	if (panic_on_unrecovered_nmi)
+	if (panic_on_unrecovered_nmi &&
+	    atomic_cmpxchg(&panicking_cpu, -1, raw_smp_processor_id()) == -1)
 		panic("NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
@@ -255,8 +256,13 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 		 reason, smp_processor_id());
 	show_regs(regs);
 
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
+	if (panic_on_io_nmi) {
+		if (atomic_cmpxchg(&panicking_cpu, -1, raw_smp_processor_id())
+		    == -1)
+			panic("NMI IOCK error: Not continuing");
+		else
+			return; /* We don't want to wait and re-enable NMI */
+	}
 
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
@@ -296,7 +302,8 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 		 reason, smp_processor_id());
 
 	pr_emerg("Do you have a strange power saving mode enabled?\n");
-	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
+	if ((unknown_nmi_panic || panic_on_unrecovered_nmi) &&
+	    atomic_cmpxchg(&panicking_cpu, -1, raw_smp_processor_id()) == -1)
 		panic("NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5582410..8ca199b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -442,6 +442,7 @@ extern __scanf(2, 0)
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;
+extern atomic_t panicking_cpu;
 
 /*
  * Only to be used by arch init code. If the user over-wrote the default
diff --git a/kernel/panic.c b/kernel/panic.c
index 04e91ff..7e6b568 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -60,6 +60,8 @@ void __weak panic_smp_self_stop(void)
 		cpu_relax();
 }
 
+atomic_t panicking_cpu = ATOMIC_INIT(-1);
+
 /**
  *	panic - halt the system
  *	@fmt: The text string to print
@@ -70,17 +72,17 @@ void __weak panic_smp_self_stop(void)
  */
 void panic(const char *fmt, ...)
 {
-	static DEFINE_SPINLOCK(panic_lock);
 	static char buf[1024];
 	va_list args;
 	long i, i_next = 0;
 	int state = 0;
+	int old_cpu, this_cpu;
 
 	/*
 	 * Disable local interrupts. This will prevent panic_smp_self_stop
 	 * from deadlocking the first cpu that invokes the panic, since
 	 * there is nothing to prevent an interrupt handler (that runs
-	 * after the panic_lock is acquired) from invoking panic again.
+	 * after setting panicking_cpu) from invoking panic again.
 	 */
 	local_irq_disable();
 
@@ -93,8 +95,13 @@ void panic(const char *fmt, ...)
 	 * multiple parallel invocations of panic, all other CPUs either
 	 * stop themself or will wait until they are stopped by the 1st CPU
 	 * with smp_send_stop().
+	 *
+	 * `old_cpu == -1' means we are the first comer.
+	 * `old_cpu == this_cpu' means we came here due to panic on NMI.
 	 */
-	if (!spin_trylock(&panic_lock))
+	this_cpu = raw_smp_processor_id();
+	old_cpu = atomic_cmpxchg(&panicking_cpu, -1, this_cpu);
+	if (old_cpu != -1 && old_cpu != this_cpu)
 		panic_smp_self_stop();
 
 	console_verbose();


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/