panic, x86: Fix re-entrance problem due to panic on NMI

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

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

For that, introduce nmi_panic() macro to reduce code duplication. In
the case of panic on NMI, don't return from NMI handlers if another CPU
already panicked.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Baoquan He <bhe@redhat.com>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: David Hildenbrand <dahi@linux.vnet.ibm.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Gobinda Charan Maji <gobinda.cemk07@gmail.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Javi Merino <javi.merino@arm.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: kexec@lists.infradead.org
Cc: linux-doc@vger.kernel.org
Cc: lkml <linux-kernel@vger.kernel.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Nicolas Iooss <nicolas.iooss_linux@m4x.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/20151210014626.25437.13302.stgit@softrs
[ Cleanup comments, fixup formatting. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This commit is contained in:
Hidehiro Kawai 2015-12-14 11:19:09 +01:00 committed by Thomas Gleixner
parent d267b8d6c6
commit 1717f2096b
4 changed files with 46 additions and 8 deletions

View file

@ -231,7 +231,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
#endif
if (panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
nmi_panic("NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
@ -255,8 +255,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
reason, smp_processor_id());
show_regs(regs);
if (panic_on_io_nmi)
panic("NMI IOCK error: Not continuing");
if (panic_on_io_nmi) {
nmi_panic("NMI IOCK error: Not continuing");
/*
* If we end up here, it means we have received an NMI while
* processing panic(). Simply return without delaying and
* re-enabling NMIs.
*/
return;
}
/* Re-enable the IOCK line, wait for a few seconds */
reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
@ -297,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
pr_emerg("Do you have a strange power saving mode enabled?\n");
if (unknown_nmi_panic || panic_on_unrecovered_nmi)
panic("NMI: Not continuing");
nmi_panic("NMI: Not continuing");
pr_emerg("Dazed and confused, but trying to continue\n");
}

View file

@ -445,6 +445,26 @@ extern int sysctl_panic_on_stackoverflow;
extern bool crash_kexec_post_notifiers;
/*
* panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
* holds a CPU number which is executing panic() currently. A value of
* PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
*/
extern atomic_t panic_cpu;
#define PANIC_CPU_INVALID -1
/*
* A variant of panic() called from NMI context. We return if we've already
* panicked on this CPU.
*/
#define nmi_panic(fmt, ...) \
do { \
int cpu = raw_smp_processor_id(); \
\
if (atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu) != cpu) \
panic(fmt, ##__VA_ARGS__); \
} while (0)
/*
* Only to be used by arch init code. If the user over-wrote the default
* CONFIG_PANIC_TIMEOUT, honor it.

View file

@ -61,6 +61,8 @@ void __weak panic_smp_self_stop(void)
cpu_relax();
}
atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
/**
* panic - halt the system
* @fmt: The text string to print
@ -71,17 +73,17 @@ 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 panic_cpu) from invoking panic() again.
*/
local_irq_disable();
@ -94,8 +96,16 @@ 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 == PANIC_CPU_INVALID' means this is the 1st CPU which
* comes here, so go ahead.
* `old_cpu == this_cpu' means we came from nmi_panic() which sets
* panic_cpu to this CPU. In this case, this is also the 1st CPU.
*/
if (!spin_trylock(&panic_lock))
this_cpu = raw_smp_processor_id();
old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
if (old_cpu != PANIC_CPU_INVALID && old_cpu != this_cpu)
panic_smp_self_stop();
console_verbose();

View file

@ -351,7 +351,7 @@ static void watchdog_overflow_callback(struct perf_event *event,
trigger_allbutself_cpu_backtrace();
if (hardlockup_panic)
panic("Hard LOCKUP");
nmi_panic("Hard LOCKUP");
__this_cpu_write(hard_watchdog_warn, true);
return;