android_kernel_motorola_sm6225/include/linux/cpu.h
Ingo Molnar a263898f62 CPU hotplug: fix cpu_is_offline() on !CONFIG_HOTPLUG_CPU
make randconfig bootup testing found that the cpufreq code
crashes on bootup, if the powernow-k8 driver is enabled and
if maxcpus=1 passed on the boot line to a !CONFIG_HOTPLUG_CPU
kernel.

First lockdep found out that there's an inconsistent unlock
sequence:

 =====================================
 [ BUG: bad unlock balance detected! ]
 -------------------------------------
 swapper/1 is trying to release lock (&per_cpu(cpu_policy_rwsem, cpu)) at:
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 but there are no more locks to release!

Call Trace:
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 [<ffffffff80251c29>] print_unlock_inbalance_bug+0x104/0x12c
 [<ffffffff80252f3a>] mark_held_locks+0x56/0x94
 [<ffffffff806ffd8e>] unlock_policy_rwsem_write+0x3c/0x42
 [<ffffffff807008b6>] cpufreq_add_dev+0x2a8/0x5c4
 ...

then shortly afterwards the cpufreq code crashed on an assert:

 ------------[ cut here ]------------
 kernel BUG at drivers/cpufreq/cpufreq.c:1068!
 invalid opcode: 0000 [1] SMP
 [...]
 Call Trace:
  [<ffffffff805145d6>] sysdev_driver_unregister+0x5b/0x91
  [<ffffffff806ff520>] cpufreq_register_driver+0x15d/0x1a2
  [<ffffffff80cc0596>] powernowk8_init+0x86/0x94
 [...]
 ---[ end trace 1e9219be2b4431de ]---

the bug was caused by maxcpus=1 bootup, which brought up the
secondary core as !cpu_online() but !cpu_is_offline() either,
which on on !CONFIG_HOTPLUG_CPU is always 0 (include/linux/cpu.h):

  /* CPUs don't go offline once they're online w/o CONFIG_HOTPLUG_CPU */
  static inline int cpu_is_offline(int cpu) { return 0; }

but the cpufreq code uses cpu_online() and cpu_is_offline() in
a mixed way - the low-level drivers use cpu_online(), while
the cpufreq core uses cpu_is_offline(). This opened up the
possibility to add the non-initialized sysdev device of the
secondary core:

 cpufreq-core: trying to register driver powernow-k8
 cpufreq-core: adding CPU 0
 powernow-k8: BIOS error - no PSB or ACPI _PSS objects
 cpufreq-core: initialization failed
 cpufreq-core: adding CPU 1
 cpufreq-core: initialization failed

which then blew up. The fix is to make cpu_is_offline() always
the negation of cpu_online(). With that fix applied the kernel
boots up fine without crashing:

 Calling initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94()
 powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 3800+ processors (1 cpu cores) (version 2.20.00)
 powernow-k8: BIOS error - no PSB or ACPI _PSS objects
 initcall 0xffffffff80cc0510: powernowk8_init+0x0/0x94() returned -19.
 initcall 0xffffffff80cc0510 ran for 19 msecs: powernowk8_init+0x0/0x94()
 Calling initcall 0xffffffff80cc328f: init_lapic_nmi_sysfs+0x0/0x39()

We could fix this by making CPU enumeration aware of max_cpus, but that
would be more fragile IMO, and the cpu_online(cpu) != cpu_is_offline(cpu)
possibility was quite confusing and a continuous source of bugs too.

Most distributions have kernels with CPU hotplug enabled, so this bug
remained hidden for a long time.

Bug forensics:

The broken cpu_is_offline() API variant was introduced via:

 commit a59d2e4e6977e7b94e003c96a41f07e96cddc340
 Author: Rusty Russell <rusty@rustcorp.com.au>
 Date:   Mon Mar 8 06:06:03 2004 -0800

     [PATCH] minor cleanups for hotplug CPUs

( this predates linux-2.6.git, this commit is available from Thomas's
  historic git tree. )

Then 1.5 years later the cpufreq code made use of it:

 commit c32b6b8e52
 Author: Ashok Raj <ashok.raj@intel.com>
 Date:   Sun Oct 30 14:59:54 2005 -0800

     [PATCH] create and destroy cpufreq sysfs entries based on cpu notifiers

 +       if (cpu_is_offline(cpu))
 +               return 0;

which is a correct use of the subtly broken new API. v2.6.15 then
shipped with this bug included.

then it took two more years for random-kernel qa to hit it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-06 12:39:42 -08:00

138 lines
3.8 KiB
C

/*
* include/linux/cpu.h - generic cpu definition
*
* This is mainly for topological representation. We define the
* basic 'struct cpu' here, which can be embedded in per-arch
* definitions of processors.
*
* Basic handling of the devices is done in drivers/base/cpu.c
* and system devices are handled in drivers/base/sys.c.
*
* CPUs are exported via sysfs in the class/cpu/devices/
* directory.
*
* Per-cpu interfaces can be implemented using a struct device_interface.
* See the following for how to do this:
* - drivers/base/intf.c
* - Documentation/driver-model/interface.txt
*/
#ifndef _LINUX_CPU_H_
#define _LINUX_CPU_H_
#include <linux/sysdev.h>
#include <linux/node.h>
#include <linux/compiler.h>
#include <linux/cpumask.h>
#include <asm/semaphore.h>
#include <linux/mutex.h>
struct cpu {
int node_id; /* The node which contains the CPU */
int hotpluggable; /* creates sysfs control file if hotpluggable */
struct sys_device sysdev;
};
extern int register_cpu(struct cpu *cpu, int num);
extern struct sys_device *get_cpu_sysdev(unsigned cpu);
extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr);
extern void cpu_remove_sysdev_attr(struct sysdev_attribute *attr);
extern int cpu_add_sysdev_attr_group(struct attribute_group *attrs);
extern void cpu_remove_sysdev_attr_group(struct attribute_group *attrs);
extern int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls);
#ifdef CONFIG_HOTPLUG_CPU
extern void unregister_cpu(struct cpu *cpu);
#endif
struct notifier_block;
#ifdef CONFIG_SMP
/* Need to know about CPUs going up/down? */
#ifdef CONFIG_HOTPLUG_CPU
extern int register_cpu_notifier(struct notifier_block *nb);
extern void unregister_cpu_notifier(struct notifier_block *nb);
#else
#ifndef MODULE
extern int register_cpu_notifier(struct notifier_block *nb);
#else
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
#endif
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
#endif
int cpu_up(unsigned int cpu);
#else
static inline int register_cpu_notifier(struct notifier_block *nb)
{
return 0;
}
static inline void unregister_cpu_notifier(struct notifier_block *nb)
{
}
#endif /* CONFIG_SMP */
extern struct sysdev_class cpu_sysdev_class;
#ifdef CONFIG_HOTPLUG_CPU
/* Stop CPUs going up and down. */
static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
{
mutex_lock(cpu_hp_mutex);
}
static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
{
mutex_unlock(cpu_hp_mutex);
}
extern void lock_cpu_hotplug(void);
extern void unlock_cpu_hotplug(void);
#define hotcpu_notifier(fn, pri) { \
static struct notifier_block fn##_nb = \
{ .notifier_call = fn, .priority = pri }; \
register_cpu_notifier(&fn##_nb); \
}
#define register_hotcpu_notifier(nb) register_cpu_notifier(nb)
#define unregister_hotcpu_notifier(nb) unregister_cpu_notifier(nb)
int cpu_down(unsigned int cpu);
#else /* CONFIG_HOTPLUG_CPU */
static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
{ }
static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
{ }
#define lock_cpu_hotplug() do { } while (0)
#define unlock_cpu_hotplug() do { } while (0)
#define hotcpu_notifier(fn, pri) do { (void)(fn); } while (0)
/* These aren't inline functions due to a GCC bug. */
#define register_hotcpu_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotcpu_notifier(nb) ({ (void)(nb); })
#endif /* CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM_SLEEP_SMP
extern int suspend_cpu_hotplug;
extern int disable_nonboot_cpus(void);
extern void enable_nonboot_cpus(void);
#else /* !CONFIG_PM_SLEEP_SMP */
#define suspend_cpu_hotplug 0
static inline int disable_nonboot_cpus(void) { return 0; }
static inline void enable_nonboot_cpus(void) {}
#endif /* !CONFIG_PM_SLEEP_SMP */
#endif /* _LINUX_CPU_H_ */