When doing an nmi backtrace of many cores, most of which are idle, the
output is a little overwhelming and very uninformative. Suppress
messages for cpus that are idling when they are interrupted and just
emit one line, "NMI backtrace for N skipped: idling at pc 0xNNN".
We do this by grouping all the cpuidle code together into a new
.cpuidle.text section, and then checking the address of the interrupted
PC to see if it lies within that section.
This commit suitably tags x86 and tile idle routines, and only adds in
the minimal framework for other architectures.
Link: http://lkml.kernel.org/r/1472487169-14923-5-git-send-email-cmetcalf@mellanox.com
Signed-off-by: Chris Metcalf <cmetcalf@mellanox.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Thompson <daniel.thompson@linaro.org> [arm]
Tested-by: Petr Mladek <pmladek@suse.com>
Cc: Aaron Tomlin <atomlin@redhat.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.gnu.warning)
_text = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.fixup)
IRQENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.gnu.warning)
SOFTIRQENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
HYPERVISOR_TEXT
KPROBES_TEXT
ENTRY_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
HYPERVISOR_TEXT
KPROBES_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.gnu.warning)
#ifndef CONFIG_SCHEDULE_L1
SCHED_TEXT
#endif
+ CPUIDLE_TEXT
LOCK_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
_stext = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.text.__*)
*(.text..tlbmiss)
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
#ifdef CONFIG_DEBUG_INFO
INIT_TEXT
_stext = . ;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
#if defined(CONFIG_ROMKERNEL)
*(.int_redirect)
_text = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.fixup)
__end_ivt_text = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.gnu.linkonce.t*)
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.gnu.warning)
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
. = ALIGN(16);
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.gnu.warning)
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.gnu.warning)
.text : {
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
EXIT_TEXT
EXIT_CALL
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
.text : {
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.fixup)
.text : {
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
IRQENTRY_TEXT
SOFTIRQENTRY_TEXT
_stext = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
.text ALIGN(PAGE_SIZE) : {
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
/* careful! __ftr_alt_* sections need to be close to .text */
*(.text .fixup __ftr_alt_* .ref.text)
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
_text = .; /* Text and read-only data */
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
*(.text.*)
TEXT_TEXT
EXTRA_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
HEAD_TEXT
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
* When interrupted at _cpu_idle_nap, we bump the PC forward 8, and
* as a result return to the function that called _cpu_idle().
*/
-STD_ENTRY(_cpu_idle)
+STD_ENTRY_SECTION(_cpu_idle, .cpuidle.text)
movei r1, 1
IRQ_ENABLE_LOAD(r2, r3)
mtspr INTERRUPT_CRITICAL_SECTION, r1
.text : AT (ADDR(.text) - LOAD_OFFSET) {
HEAD_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
IRQENTRY_TEXT
_stext = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
*(.stub .text.* .gnu.linkonce.t.*)
_stext = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
/* .gnu.warning sections are handled specially by elf32.em. */
.text : { /* Real text segment */
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
*(.fixup)
#include <asm/processor-flags.h>
#ifndef __ASSEMBLY__
+
+/* Provide __cpuidle; we can't safely include <linux/cpu.h> */
+#define __cpuidle __attribute__((__section__(".cpuidle.text")))
+
/*
* Interrupt control:
*/
asm volatile("sti": : :"memory");
}
-static inline void native_safe_halt(void)
+static inline __cpuidle void native_safe_halt(void)
{
asm volatile("sti; hlt": : :"memory");
}
-static inline void native_halt(void)
+static inline __cpuidle void native_halt(void)
{
asm volatile("hlt": : :"memory");
}
* Used in the idle loop; sti takes one instruction cycle
* to complete:
*/
-static inline void arch_safe_halt(void)
+static inline __cpuidle void arch_safe_halt(void)
{
native_safe_halt();
}
* Used when interrupts are already enabled or to
* shutdown the processor:
*/
-static inline void halt(void)
+static inline __cpuidle void halt(void)
{
native_halt();
}
}
EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
-void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
+void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
{
unsigned int cpu = smp_processor_id();
struct cstate_entry *percpu_entry;
/*
* We use this if we don't have any better idle routine..
*/
-void default_idle(void)
+void __cpuidle default_idle(void)
{
trace_cpu_idle_rcuidle(1, smp_processor_id());
safe_halt();
* with interrupts enabled and no flags, which is backwards compatible with the
* original MWAIT implementation.
*/
-static void mwait_idle(void)
+static __cpuidle void mwait_idle(void)
{
if (!current_set_polling_and_test()) {
trace_cpu_idle_rcuidle(1, smp_processor_id());
_stext = .;
TEXT_TEXT
SCHED_TEXT
+ CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
ENTRY_TEXT
VMLINUX_SYMBOL(__sched_text_start) = .;
*(.sched.literal .sched.text)
VMLINUX_SYMBOL(__sched_text_end) = .;
+ VMLINUX_SYMBOL(__cpuidle_text_start) = .;
+ *(.cpuidle.literal .cpuidle.text)
+ VMLINUX_SYMBOL(__cpuidle_text_end) = .;
VMLINUX_SYMBOL(__lock_text_start) = .;
*(.spinlock.literal .spinlock.text)
VMLINUX_SYMBOL(__lock_text_end) = .;
#include <linux/sched.h> /* need_resched() */
#include <linux/tick.h>
#include <linux/cpuidle.h>
+#include <linux/cpu.h>
#include <acpi/processor.h>
/*
* Callers should disable interrupts before the call and enable
* interrupts after return.
*/
-static void acpi_safe_halt(void)
+static void __cpuidle acpi_safe_halt(void)
{
if (!tif_need_resched()) {
safe_halt();
*
* Caller disables interrupt before call and enables interrupt after return.
*/
-static void acpi_idle_do_entry(struct acpi_processor_cx *cx)
+static void __cpuidle acpi_idle_do_entry(struct acpi_processor_cx *cx)
{
if (cx->entry_method == ACPI_CSTATE_FFH) {
/* Call into architectural FFH based C-state */
#include <linux/cpuidle.h>
#include <linux/cpumask.h>
#include <linux/tick.h>
+#include <linux/cpu.h>
#include "cpuidle.h"
}
#ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev,
- struct cpuidle_driver *drv, int index)
+static int __cpuidle poll_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
local_irq_enable();
if (!current_set_polling_and_test()) {
*
* Must be called under local_irq_disable().
*/
-static int intel_idle(struct cpuidle_device *dev,
- struct cpuidle_driver *drv, int index)
+static __cpuidle int intel_idle(struct cpuidle_device *dev,
+ struct cpuidle_driver *drv, int index)
{
unsigned long ecx = 1; /* break on interrupt flag */
struct cpuidle_state *state = &drv->states[index];
*(.spinlock.text) \
VMLINUX_SYMBOL(__lock_text_end) = .;
+#define CPUIDLE_TEXT \
+ ALIGN_FUNCTION(); \
+ VMLINUX_SYMBOL(__cpuidle_text_start) = .; \
+ *(.cpuidle.text) \
+ VMLINUX_SYMBOL(__cpuidle_text_end) = .;
+
#define KPROBES_TEXT \
ALIGN_FUNCTION(); \
VMLINUX_SYMBOL(__kprobes_text_start) = .; \
void cpu_idle_poll_ctrl(bool enable);
+/* Attach to any functions which should be considered cpuidle. */
+#define __cpuidle __attribute__((__section__(".cpuidle.text")))
+
+bool cpu_in_idle(unsigned long pc);
+
void arch_cpu_idle(void);
void arch_cpu_idle_prepare(void);
void arch_cpu_idle_enter(void);
#include "sched.h"
+/* Linker adds these: start and end of __cpuidle functions */
+extern char __cpuidle_text_start[], __cpuidle_text_end[];
+
/**
* sched_idle_set_state - Record idle state for the current CPU.
* @idle_state: State to record.
__setup("hlt", cpu_idle_nopoll_setup);
#endif
-static inline int cpu_idle_poll(void)
+static noinline int __cpuidle cpu_idle_poll(void)
{
rcu_idle_enter();
trace_cpu_idle_rcuidle(0, smp_processor_id());
*
* To use when the cpuidle framework cannot be used.
*/
-void default_idle_call(void)
+void __cpuidle default_idle_call(void)
{
if (current_clr_polling_and_test()) {
local_irq_enable();
}
}
+bool cpu_in_idle(unsigned long pc)
+{
+ return pc >= (unsigned long)__cpuidle_text_start &&
+ pc < (unsigned long)__cpuidle_text_end;
+}
+
void cpu_startup_entry(enum cpuhp_state state)
{
/*
#include <linux/delay.h>
#include <linux/kprobes.h>
#include <linux/nmi.h>
+#include <linux/cpu.h>
#ifdef arch_trigger_cpumask_backtrace
/* For reliability, we're prepared to waste bits here. */
int cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
- pr_warn("NMI backtrace for cpu %d\n", cpu);
- if (regs)
- show_regs(regs);
- else
- dump_stack();
+ 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();
+ }
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return true;
}
#define DATA_SECTIONS ".data", ".data.rel"
#define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \
- ".kprobes.text"
+ ".kprobes.text", ".cpuidle.text"
#define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
".fixup", ".entry.text", ".exception.text", ".text.*", \
".coldtext"
strcmp(".irqentry.text", txtname) == 0 ||
strcmp(".softirqentry.text", txtname) == 0 ||
strcmp(".kprobes.text", txtname) == 0 ||
+ strcmp(".cpuidle.text", txtname) == 0 ||
strcmp(".text.unlikely", txtname) == 0;
}
".irqentry.text" => 1,
".softirqentry.text" => 1,
".kprobes.text" => 1,
+ ".cpuidle.text" => 1,
".text.unlikely" => 1,
);
projects / kernel.git / commitdiff