2014-09-04 06:57:13 +08:00
|
|
|
/*
|
|
|
|
|
* 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>
|
2016-10-08 08:02:55 +08:00
|
|
|
#include <linux/cpu.h>
|
2017-02-09 01:51:35 +08:00
|
|
|
#include <linux/sched/debug.h>
|
2014-09-04 06:57:13 +08:00
|
|
|
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
#ifdef arch_trigger_cpumask_backtrace
|
2014-09-04 06:57:13 +08:00
|
|
|
/* For reliability, we're prepared to waste bits here. */
|
|
|
|
|
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
|
|
|
|
|
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
/* "in progress" flag of arch_trigger_cpumask_backtrace */
|
2014-09-04 06:57:13 +08:00
|
|
|
static unsigned long backtrace_flag;
|
|
|
|
|
|
2015-09-23 00:12:10 +08:00
|
|
|
/*
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
* When raise() is called it will be passed a pointer to the
|
2015-09-23 00:12:10 +08:00
|
|
|
* 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.
|
|
|
|
|
*/
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
|
|
|
|
|
bool exclude_self,
|
2014-09-04 06:57:13 +08:00
|
|
|
void (*raise)(cpumask_t *mask))
|
|
|
|
|
{
|
2016-05-21 08:00:33 +08:00
|
|
|
int i, this_cpu = get_cpu();
|
2014-09-04 06:57:13 +08:00
|
|
|
|
|
|
|
|
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;
|
|
|
|
|
}
|
|
|
|
|
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
cpumask_copy(to_cpumask(backtrace_mask), mask);
|
|
|
|
|
if (exclude_self)
|
2014-09-04 06:57:13 +08:00
|
|
|
cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
|
|
|
|
|
|
2016-10-08 08:02:49 +08:00
|
|
|
/*
|
|
|
|
|
* 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);
|
|
|
|
|
|
2014-09-04 06:57:13 +08:00
|
|
|
if (!cpumask_empty(to_cpumask(backtrace_mask))) {
|
nmi_backtrace: add more trigger_*_cpu_backtrace() methods
Patch series "improvements to the nmi_backtrace code" v9.
This patch series modifies the trigger_xxx_backtrace() NMI-based remote
backtracing code to make it more flexible, and makes a few small
improvements along the way.
The motivation comes from the task isolation code, where there are
scenarios where we want to be able to diagnose a case where some cpu is
about to interrupt a task-isolated cpu. It can be helpful to see both
where the interrupting cpu is, and also an approximation of where the
cpu that is being interrupted is. The nmi_backtrace framework allows us
to discover the stack of the interrupted cpu.
I've tested that the change works as desired on tile, and build-tested
x86, arm, mips, and sparc64. For x86 I confirmed that the generic
cpuidle stuff as well as the architecture-specific routines are in the
new cpuidle section. For arm, mips, and sparc I just build-tested it
and made sure the generic cpuidle routines were in the new cpuidle
section, but I didn't attempt to figure out which the platform-specific
idle routines might be. That might be more usefully done by someone
with platform experience in follow-up patches.
This patch (of 4):
Currently you can only request a backtrace of either all cpus, or all
cpus but yourself. It can also be helpful to request a remote backtrace
of a single cpu, and since we want that, the logical extension is to
support a cpumask as the underlying primitive.
This change modifies the existing lib/nmi_backtrace.c code to take a
cpumask as its basic primitive, and modifies the linux/nmi.h code to use
the new "cpumask" method instead.
The existing clients of nmi_backtrace (arm and x86) are converted to
using the new cpumask approach in this change.
The other users of the backtracing API (sparc64 and mips) are converted
to use the cpumask approach rather than the all/allbutself approach.
The mips code ignored the "include_self" boolean but with this change it
will now also dump a local backtrace if requested.
Link: http://lkml.kernel.org/r/1472487169-14923-2-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: Aaron Tomlin <atomlin@redhat.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-08 08:02:45 +08:00
|
|
|
pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n",
|
|
|
|
|
this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask));
|
2014-09-04 06:57:13 +08:00
|
|
|
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();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2016-05-21 08:00:33 +08:00
|
|
|
* Force flush any remote buffers that might be stuck in IRQ context
|
|
|
|
|
* and therefore could not run their irq_work.
|
2014-09-04 06:57:13 +08:00
|
|
|
*/
|
2016-12-27 22:16:05 +08:00
|
|
|
printk_safe_flush();
|
2014-09-04 06:57:13 +08:00
|
|
|
|
2016-05-21 08:00:33 +08:00
|
|
|
clear_bit_unlock(0, &backtrace_flag);
|
2014-09-04 06:57:13 +08:00
|
|
|
put_cpu();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
bool nmi_cpu_backtrace(struct pt_regs *regs)
|
|
|
|
|
{
|
2017-04-20 16:52:31 +08:00
|
|
|
static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
|
2014-09-04 06:57:13 +08:00
|
|
|
int cpu = smp_processor_id();
|
|
|
|
|
|
|
|
|
|
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
|
2017-04-20 16:52:31 +08:00
|
|
|
arch_spin_lock(&lock);
|
2016-10-08 08:02:55 +08:00
|
|
|
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();
|
|
|
|
|
}
|
2017-04-20 16:52:31 +08:00
|
|
|
arch_spin_unlock(&lock);
|
2014-09-04 06:57:13 +08:00
|
|
|
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
|
|
|
|
|
return true;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return false;
|
|
|
|
|
}
|
|
|
|
|
NOKPROBE_SYMBOL(nmi_cpu_backtrace);
|
|
|
|
|
#endif
|