alistair23-linux/lib/spinlock_debug.c
Vikram Mulukutla 214f766ea0 lib/spinlock_debug: avoid livelock in do_raw_spin_lock()
The logic in do_raw_spin_lock() attempts to acquire a spinlock by invoking
arch_spin_trylock() in a loop with a delay between each attempt.  Now
consider the following situation in a 2 CPU system:

1. CPU-0 continually acquires and releases a spinlock in a
   tight loop; it stays in this loop until some condition X
   is satisfied. X can only be satisfied by another CPU.

2. CPU-1 tries to acquire the same spinlock, in an attempt
   to satisfy the aforementioned condition X. However, it
   never sees the unlocked value of the lock because the
   debug spinlock code uses trylock instead of just lock;
   it checks at all the wrong moments - whenever CPU-0 has
   locked the lock.

Now in the absence of debug spinlocks, the architecture specific spinlock
code can correctly allow CPU-1 to wait in a "queue" (e.g., ticket
spinlocks), ensuring that it acquires the lock at some point.  However,
with the debug spinlock code, livelock can easily occur due to the use of
try_lock, which obviously cannot put the CPU in that "queue".  This
queueing mechanism is implemented in both x86 and ARM spinlock code.

Note that the situation mentioned above is not hypothetical.  A real
problem was encountered where CPU-0 was running hrtimer_cancel with
interrupts disabled, and CPU-1 was attempting to run the hrtimer that
CPU-0 was trying to cancel.

Address this by actually attempting arch_spin_lock once it is suspected
that there is a spinlock lockup.  If we're in a situation that is
described above, the arch_spin_lock should succeed; otherwise other
timeout mechanisms (e.g., watchdog) should alert the system of a lockup.
Therefore, if there is a genuine system problem and the spinlock can't be
acquired, the end result (irrespective of this change being present) is
the same.  If there is a livelock caused by the debug code, this change
will allow the lock to be acquired, depending on the implementation of the
lower level arch specific spinlock code.

[akpm@linux-foundation.org: tweak comment]
Signed-off-by: Vikram Mulukutla <markivx@codeaurora.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-06 03:04:57 +09:00

303 lines
7.1 KiB
C

/*
* Copyright 2005, Red Hat, Inc., Ingo Molnar
* Released under the General Public License (GPL).
*
* This file contains the spinlock/rwlock implementations for
* DEBUG_SPINLOCK.
*/
#include <linux/spinlock.h>
#include <linux/nmi.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
#include <linux/delay.h>
#include <linux/export.h>
void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Make sure we are not reinitializing a held lock:
*/
debug_check_no_locks_freed((void *)lock, sizeof(*lock));
lockdep_init_map(&lock->dep_map, name, key, 0);
#endif
lock->raw_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
lock->magic = SPINLOCK_MAGIC;
lock->owner = SPINLOCK_OWNER_INIT;
lock->owner_cpu = -1;
}
EXPORT_SYMBOL(__raw_spin_lock_init);
void __rwlock_init(rwlock_t *lock, const char *name,
struct lock_class_key *key)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
* Make sure we are not reinitializing a held lock:
*/
debug_check_no_locks_freed((void *)lock, sizeof(*lock));
lockdep_init_map(&lock->dep_map, name, key, 0);
#endif
lock->raw_lock = (arch_rwlock_t) __ARCH_RW_LOCK_UNLOCKED;
lock->magic = RWLOCK_MAGIC;
lock->owner = SPINLOCK_OWNER_INIT;
lock->owner_cpu = -1;
}
EXPORT_SYMBOL(__rwlock_init);
static void spin_dump(raw_spinlock_t *lock, const char *msg)
{
struct task_struct *owner = NULL;
if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
owner = lock->owner;
printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
msg, raw_smp_processor_id(),
current->comm, task_pid_nr(current));
printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
".owner_cpu: %d\n",
lock, lock->magic,
owner ? owner->comm : "<none>",
owner ? task_pid_nr(owner) : -1,
lock->owner_cpu);
dump_stack();
}
static void spin_bug(raw_spinlock_t *lock, const char *msg)
{
if (!debug_locks_off())
return;
spin_dump(lock, msg);
}
#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
static inline void
debug_spin_lock_before(raw_spinlock_t *lock)
{
SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
SPIN_BUG_ON(lock->owner == current, lock, "recursion");
SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
lock, "cpu recursion");
}
static inline void debug_spin_lock_after(raw_spinlock_t *lock)
{
lock->owner_cpu = raw_smp_processor_id();
lock->owner = current;
}
static inline void debug_spin_unlock(raw_spinlock_t *lock)
{
SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
SPIN_BUG_ON(!raw_spin_is_locked(lock), lock, "already unlocked");
SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
lock->owner = SPINLOCK_OWNER_INIT;
lock->owner_cpu = -1;
}
static void __spin_lock_debug(raw_spinlock_t *lock)
{
u64 i;
u64 loops = loops_per_jiffy * HZ;
for (i = 0; i < loops; i++) {
if (arch_spin_trylock(&lock->raw_lock))
return;
__delay(1);
}
/* lockup suspected: */
spin_dump(lock, "lockup suspected");
#ifdef CONFIG_SMP
trigger_all_cpu_backtrace();
#endif
/*
* The trylock above was causing a livelock. Give the lower level arch
* specific lock code a chance to acquire the lock. We have already
* printed a warning/backtrace at this point. The non-debug arch
* specific code might actually succeed in acquiring the lock. If it is
* not successful, the end-result is the same - there is no forward
* progress.
*/
arch_spin_lock(&lock->raw_lock);
}
void do_raw_spin_lock(raw_spinlock_t *lock)
{
debug_spin_lock_before(lock);
if (unlikely(!arch_spin_trylock(&lock->raw_lock)))
__spin_lock_debug(lock);
debug_spin_lock_after(lock);
}
int do_raw_spin_trylock(raw_spinlock_t *lock)
{
int ret = arch_spin_trylock(&lock->raw_lock);
if (ret)
debug_spin_lock_after(lock);
#ifndef CONFIG_SMP
/*
* Must not happen on UP:
*/
SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
#endif
return ret;
}
void do_raw_spin_unlock(raw_spinlock_t *lock)
{
debug_spin_unlock(lock);
arch_spin_unlock(&lock->raw_lock);
}
static void rwlock_bug(rwlock_t *lock, const char *msg)
{
if (!debug_locks_off())
return;
printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n",
msg, raw_smp_processor_id(), current->comm,
task_pid_nr(current), lock);
dump_stack();
}
#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
#if 0 /* __write_lock_debug() can lock up - maybe this can too? */
static void __read_lock_debug(rwlock_t *lock)
{
u64 i;
u64 loops = loops_per_jiffy * HZ;
int print_once = 1;
for (;;) {
for (i = 0; i < loops; i++) {
if (arch_read_trylock(&lock->raw_lock))
return;
__delay(1);
}
/* lockup suspected: */
if (print_once) {
print_once = 0;
printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
"%s/%d, %p\n",
raw_smp_processor_id(), current->comm,
current->pid, lock);
dump_stack();
}
}
}
#endif
void do_raw_read_lock(rwlock_t *lock)
{
RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
arch_read_lock(&lock->raw_lock);
}
int do_raw_read_trylock(rwlock_t *lock)
{
int ret = arch_read_trylock(&lock->raw_lock);
#ifndef CONFIG_SMP
/*
* Must not happen on UP:
*/
RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
#endif
return ret;
}
void do_raw_read_unlock(rwlock_t *lock)
{
RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
arch_read_unlock(&lock->raw_lock);
}
static inline void debug_write_lock_before(rwlock_t *lock)
{
RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
lock, "cpu recursion");
}
static inline void debug_write_lock_after(rwlock_t *lock)
{
lock->owner_cpu = raw_smp_processor_id();
lock->owner = current;
}
static inline void debug_write_unlock(rwlock_t *lock)
{
RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
lock, "wrong CPU");
lock->owner = SPINLOCK_OWNER_INIT;
lock->owner_cpu = -1;
}
#if 0 /* This can cause lockups */
static void __write_lock_debug(rwlock_t *lock)
{
u64 i;
u64 loops = loops_per_jiffy * HZ;
int print_once = 1;
for (;;) {
for (i = 0; i < loops; i++) {
if (arch_write_trylock(&lock->raw_lock))
return;
__delay(1);
}
/* lockup suspected: */
if (print_once) {
print_once = 0;
printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
"%s/%d, %p\n",
raw_smp_processor_id(), current->comm,
current->pid, lock);
dump_stack();
}
}
}
#endif
void do_raw_write_lock(rwlock_t *lock)
{
debug_write_lock_before(lock);
arch_write_lock(&lock->raw_lock);
debug_write_lock_after(lock);
}
int do_raw_write_trylock(rwlock_t *lock)
{
int ret = arch_write_trylock(&lock->raw_lock);
if (ret)
debug_write_lock_after(lock);
#ifndef CONFIG_SMP
/*
* Must not happen on UP:
*/
RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
#endif
return ret;
}
void do_raw_write_unlock(rwlock_t *lock)
{
debug_write_unlock(lock);
arch_write_unlock(&lock->raw_lock);
}