Commit 9a01c3ed authored by Chris Metcalf's avatar Chris Metcalf Committed by Linus Torvalds

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.comSigned-off-by: default avatarChris Metcalf <cmetcalf@mellanox.com>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Reviewed-by: default avatarAaron Tomlin <atomlin@redhat.com>
Reviewed-by: default avatarPetr 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 589a9785
...@@ -36,8 +36,9 @@ extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); ...@@ -36,8 +36,9 @@ extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
#endif #endif
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
extern void arch_trigger_all_cpu_backtrace(bool); extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
#define arch_trigger_all_cpu_backtrace(x) arch_trigger_all_cpu_backtrace(x) bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
#endif #endif
static inline int nr_legacy_irqs(void) static inline int nr_legacy_irqs(void)
......
...@@ -760,7 +760,7 @@ static void raise_nmi(cpumask_t *mask) ...@@ -760,7 +760,7 @@ static void raise_nmi(cpumask_t *mask)
smp_cross_call(mask, IPI_CPU_BACKTRACE); smp_cross_call(mask, IPI_CPU_BACKTRACE);
} }
void arch_trigger_all_cpu_backtrace(bool include_self) void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{ {
nmi_trigger_all_cpu_backtrace(include_self, raise_nmi); nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_nmi);
} }
...@@ -51,7 +51,8 @@ extern int cp0_fdc_irq; ...@@ -51,7 +51,8 @@ extern int cp0_fdc_irq;
extern int get_c0_fdc_int(void); extern int get_c0_fdc_int(void);
void arch_trigger_all_cpu_backtrace(bool); void arch_trigger_cpumask_backtrace(const struct cpumask *mask,
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
#endif /* _ASM_IRQ_H */ #endif /* _ASM_IRQ_H */
...@@ -569,9 +569,16 @@ static void arch_dump_stack(void *info) ...@@ -569,9 +569,16 @@ static void arch_dump_stack(void *info)
dump_stack(); dump_stack();
} }
void arch_trigger_all_cpu_backtrace(bool include_self) void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{ {
smp_call_function(arch_dump_stack, NULL, 1); long this_cpu = get_cpu();
if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
dump_stack();
smp_call_function_many(mask, arch_dump_stack, NULL, 1);
put_cpu();
} }
int mips_get_process_fp_mode(struct task_struct *task) int mips_get_process_fp_mode(struct task_struct *task)
......
...@@ -86,8 +86,9 @@ static inline unsigned long get_softint(void) ...@@ -86,8 +86,9 @@ static inline unsigned long get_softint(void)
return retval; return retval;
} }
void arch_trigger_all_cpu_backtrace(bool); void arch_trigger_cpumask_backtrace(const struct cpumask *mask,
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
extern void *hardirq_stack[NR_CPUS]; extern void *hardirq_stack[NR_CPUS];
extern void *softirq_stack[NR_CPUS]; extern void *softirq_stack[NR_CPUS];
......
...@@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) ...@@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp)
} }
} }
void arch_trigger_all_cpu_backtrace(bool include_self) void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{ {
struct thread_info *tp = current_thread_info(); struct thread_info *tp = current_thread_info();
struct pt_regs *regs = get_irq_regs(); struct pt_regs *regs = get_irq_regs();
...@@ -255,15 +255,15 @@ void arch_trigger_all_cpu_backtrace(bool include_self) ...@@ -255,15 +255,15 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot));
if (include_self) if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
__global_reg_self(tp, regs, this_cpu); __global_reg_self(tp, regs, this_cpu);
smp_fetch_global_regs(); smp_fetch_global_regs();
for_each_online_cpu(cpu) { for_each_cpu(cpu, mask) {
struct global_reg_snapshot *gp; struct global_reg_snapshot *gp;
if (!include_self && cpu == this_cpu) if (exclude_self && cpu == this_cpu)
continue; continue;
gp = &global_cpu_snapshot[cpu].reg; gp = &global_cpu_snapshot[cpu].reg;
...@@ -300,7 +300,7 @@ void arch_trigger_all_cpu_backtrace(bool include_self) ...@@ -300,7 +300,7 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
static void sysrq_handle_globreg(int key) static void sysrq_handle_globreg(int key)
{ {
arch_trigger_all_cpu_backtrace(true); trigger_all_cpu_backtrace();
} }
static struct sysrq_key_op sparc_globalreg_op = { static struct sysrq_key_op sparc_globalreg_op = {
......
...@@ -50,8 +50,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector); ...@@ -50,8 +50,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
extern void init_ISA_irqs(void); extern void init_ISA_irqs(void);
#ifdef CONFIG_X86_LOCAL_APIC #ifdef CONFIG_X86_LOCAL_APIC
void arch_trigger_all_cpu_backtrace(bool); void arch_trigger_cpumask_backtrace(const struct cpumask *mask,
#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace bool exclude_self);
#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
#endif #endif
#endif /* _ASM_X86_IRQ_H */ #endif /* _ASM_X86_IRQ_H */
...@@ -26,32 +26,32 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh) ...@@ -26,32 +26,32 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh)
} }
#endif #endif
#ifdef arch_trigger_all_cpu_backtrace #ifdef arch_trigger_cpumask_backtrace
static void nmi_raise_cpu_backtrace(cpumask_t *mask) static void nmi_raise_cpu_backtrace(cpumask_t *mask)
{ {
apic->send_IPI_mask(mask, NMI_VECTOR); apic->send_IPI_mask(mask, NMI_VECTOR);
} }
void arch_trigger_all_cpu_backtrace(bool include_self) void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
{ {
nmi_trigger_all_cpu_backtrace(include_self, nmi_raise_cpu_backtrace); nmi_trigger_cpumask_backtrace(mask, exclude_self,
nmi_raise_cpu_backtrace);
} }
static int static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
{ {
if (nmi_cpu_backtrace(regs)) if (nmi_cpu_backtrace(regs))
return NMI_HANDLED; return NMI_HANDLED;
return NMI_DONE; return NMI_DONE;
} }
NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); NOKPROBE_SYMBOL(nmi_cpu_backtrace_handler);
static int __init register_trigger_all_cpu_backtrace(void) static int __init register_nmi_cpu_backtrace_handler(void)
{ {
register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler, register_nmi_handler(NMI_LOCAL, nmi_cpu_backtrace_handler,
0, "arch_bt"); 0, "arch_bt");
return 0; return 0;
} }
early_initcall(register_trigger_all_cpu_backtrace); early_initcall(register_nmi_cpu_backtrace_handler);
#endif #endif
...@@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {} ...@@ -35,21 +35,34 @@ static inline void hardlockup_detector_disable(void) {}
* base function. Return whether such support was available, * base function. Return whether such support was available,
* to allow calling code to fall back to some other mechanism: * to allow calling code to fall back to some other mechanism:
*/ */
#ifdef arch_trigger_all_cpu_backtrace #ifdef arch_trigger_cpumask_backtrace
static inline bool trigger_all_cpu_backtrace(void) static inline bool trigger_all_cpu_backtrace(void)
{ {
arch_trigger_all_cpu_backtrace(true); arch_trigger_cpumask_backtrace(cpu_online_mask, false);
return true; return true;
} }
static inline bool trigger_allbutself_cpu_backtrace(void) static inline bool trigger_allbutself_cpu_backtrace(void)
{ {
arch_trigger_all_cpu_backtrace(false); arch_trigger_cpumask_backtrace(cpu_online_mask, true);
return true;
}
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
arch_trigger_cpumask_backtrace(mask, false);
return true;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
arch_trigger_cpumask_backtrace(cpumask_of(cpu), false);
return true; return true;
} }
/* generic implementation */ /* generic implementation */
void nmi_trigger_all_cpu_backtrace(bool include_self, void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self,
void (*raise)(cpumask_t *mask)); void (*raise)(cpumask_t *mask));
bool nmi_cpu_backtrace(struct pt_regs *regs); bool nmi_cpu_backtrace(struct pt_regs *regs);
...@@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void) ...@@ -62,6 +75,14 @@ static inline bool trigger_allbutself_cpu_backtrace(void)
{ {
return false; return false;
} }
static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
{
return false;
}
static inline bool trigger_single_cpu_backtrace(int cpu)
{
return false;
}
#endif #endif
#ifdef CONFIG_LOCKUP_DETECTOR #ifdef CONFIG_LOCKUP_DETECTOR
......
...@@ -17,20 +17,21 @@ ...@@ -17,20 +17,21 @@
#include <linux/kprobes.h> #include <linux/kprobes.h>
#include <linux/nmi.h> #include <linux/nmi.h>
#ifdef arch_trigger_all_cpu_backtrace #ifdef arch_trigger_cpumask_backtrace
/* For reliability, we're prepared to waste bits here. */ /* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
/* "in progress" flag of arch_trigger_all_cpu_backtrace */ /* "in progress" flag of arch_trigger_cpumask_backtrace */
static unsigned long backtrace_flag; static unsigned long backtrace_flag;
/* /*
* When raise() is called it will be is passed a pointer to the * When raise() is called it will be passed a pointer to the
* backtrace_mask. Architectures that call nmi_cpu_backtrace() * backtrace_mask. Architectures that call nmi_cpu_backtrace()
* directly from their raise() functions may rely on the mask * directly from their raise() functions may rely on the mask
* they are passed being updated as a side effect of this call. * they are passed being updated as a side effect of this call.
*/ */
void nmi_trigger_all_cpu_backtrace(bool include_self, void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
bool exclude_self,
void (*raise)(cpumask_t *mask)) void (*raise)(cpumask_t *mask))
{ {
int i, this_cpu = get_cpu(); int i, this_cpu = get_cpu();
...@@ -44,13 +45,13 @@ void nmi_trigger_all_cpu_backtrace(bool include_self, ...@@ -44,13 +45,13 @@ void nmi_trigger_all_cpu_backtrace(bool include_self,
return; return;
} }
cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); cpumask_copy(to_cpumask(backtrace_mask), mask);
if (!include_self) if (exclude_self)
cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
if (!cpumask_empty(to_cpumask(backtrace_mask))) { if (!cpumask_empty(to_cpumask(backtrace_mask))) {
pr_info("Sending NMI to %s CPUs:\n", pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n",
(include_self ? "all" : "other")); this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask));
raise(to_cpumask(backtrace_mask)); raise(to_cpumask(backtrace_mask));
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment