160c7ba346
Currently, the nmi_cpu_backtrace() declines to produce backtraces for idle CPUs. This is a good choice in the common case in which problems are caused only by non-idle CPUs. However, there are occasionally situations in which idle CPUs are helping to cause problems. This commit therefore adds an nmi_backtrace.backtrace_idle kernel boot parameter that causes nmi_cpu_backtrace() to dump stacks even of idle CPUs. Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: <linux-doc@vger.kernel.org>
115 lines
3.1 KiB
C
115 lines
3.1 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* 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();
|
|
}
|
|
|
|
// Dump stacks even for idle CPUs.
|
|
static bool backtrace_idle;
|
|
module_param(backtrace_idle, bool, 0644);
|
|
|
|
bool nmi_cpu_backtrace(struct pt_regs *regs)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
|
|
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
|
|
if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
|
|
pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
|
|
cpu, (void *)instruction_pointer(regs));
|
|
} else {
|
|
pr_warn("NMI backtrace for cpu %d\n", cpu);
|
|
if (regs)
|
|
show_regs(regs);
|
|
else
|
|
dump_stack();
|
|
}
|
|
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
NOKPROBE_SYMBOL(nmi_cpu_backtrace);
|
|
#endif
|