linux/lib/nmi_backtrace.c
Petr Mladek 719f6a7040 printk: Use the main logbuf in NMI when logbuf_lock is available
The commit 42a0bb3f71 ("printk/nmi: generic solution for safe
printk in NMI") caused that printk stores messages into a temporary
buffer in NMI context.

The buffer is per-CPU and therefore the size is rather limited.
It works quite well for NMI backtraces. But there are longer logs
that might get printed in NMI context, for example, lockdep
warnings, ftrace_dump_on_oops.

The temporary buffer is used to avoid deadlocks caused by
logbuf_lock. Also it is needed to avoid races with the other
temporary buffer that is used when PRINTK_SAFE_CONTEXT is entered.
But the main buffer can be used in NMI if the lock is available
and we did not interrupt PRINTK_SAFE_CONTEXT.

The lock is checked using raw_spin_is_locked(). It might cause
false negatives when the lock is taken on another CPU and
this CPU is in the safe context from other reasons. Note that
the safe context is used also to get console semaphore or when
calling console drivers. For this reason, we do the check in
printk_nmi_enter(). It makes the handling consistent for
the entire NMI handler and avoids reshuffling of the messages.

The patch also defines special printk context that allows
to use printk_deferred() in NMI. Note that we could not flush
the messages to the consoles because console drivers might use
many other internal locks.

The newly created vprintk_deferred() disables the preemption
only around the irq work handling. It is needed there to keep
the consistency between the two per-CPU variables. But there
is no reason to disable preemption around vprintk_emit().

Finally, the patch puts back explicit serialization of the NMI
backtraces from different CPUs. It was removed by the
commit a9edc88093 ("x86/nmi: Perform a safe
NMI stack trace on all CPUs"). It was not needed because
the flushing of the temporary per-CPU buffers was serialized.

Link: http://lkml.kernel.org/r/1493912763-24873-1-git-send-email-pmladek@suse.com
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <rack+kernel@arm.linux.org.uk>
Cc: Daniel Thompson <daniel.thompson@linaro.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: x86@kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Suggested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
2017-05-19 14:42:19 +02:00

113 lines
3.1 KiB
C

/*
* NMI backtrace support
*
* Gratuitously copied from arch/x86/kernel/apic/hw_nmi.c by Russell King,
* with the following header:
*
* HW NMI watchdog support
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
* Arch specific calls to support NMI watchdog
*
* Bits copied from original nmi.c file
*/
#include <linux/cpumask.h>
#include <linux/delay.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
#include <linux/cpu.h>
#include <linux/sched/debug.h>
#ifdef arch_trigger_cpumask_backtrace
/* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
/* "in progress" flag of arch_trigger_cpumask_backtrace */
static unsigned long backtrace_flag;
/*
* When raise() is called it will be passed a pointer to the
* backtrace_mask. Architectures that call nmi_cpu_backtrace()
* directly from their raise() functions may rely on the mask
* they are passed being updated as a side effect of this call.
*/
void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self,
void (*raise)(cpumask_t *mask))
{
int i, this_cpu = get_cpu();
if (test_and_set_bit(0, &backtrace_flag)) {
/*
* If there is already a trigger_all_cpu_backtrace() in progress
* (backtrace_flag == 1), don't output double cpu dump infos.
*/
put_cpu();
return;
}
cpumask_copy(to_cpumask(backtrace_mask), mask);
if (exclude_self)
cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
/*
* Don't try to send an NMI to this cpu; it may work on some
* architectures, but on others it may not, and we'll get
* information at least as useful just by doing a dump_stack() here.
* Note that nmi_cpu_backtrace(NULL) will clear the cpu bit.
*/
if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask)))
nmi_cpu_backtrace(NULL);
if (!cpumask_empty(to_cpumask(backtrace_mask))) {
pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n",
this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask));
raise(to_cpumask(backtrace_mask));
}
/* Wait for up to 10 seconds for all CPUs to do the backtrace */
for (i = 0; i < 10 * 1000; i++) {
if (cpumask_empty(to_cpumask(backtrace_mask)))
break;
mdelay(1);
touch_softlockup_watchdog();
}
/*
* Force flush any remote buffers that might be stuck in IRQ context
* and therefore could not run their irq_work.
*/
printk_safe_flush();
clear_bit_unlock(0, &backtrace_flag);
put_cpu();
}
bool nmi_cpu_backtrace(struct pt_regs *regs)
{
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
int cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
arch_spin_lock(&lock);
if (regs && cpu_in_idle(instruction_pointer(regs))) {
pr_warn("NMI backtrace for cpu %d skipped: idling at pc %#lx\n",
cpu, instruction_pointer(regs));
} else {
pr_warn("NMI backtrace for cpu %d\n", cpu);
if (regs)
show_regs(regs);
else
dump_stack();
}
arch_spin_unlock(&lock);
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return true;
}
return false;
}
NOKPROBE_SYMBOL(nmi_cpu_backtrace);
#endif