x86/spinlocks: Fix regression in spinlock contention detection

A spinlock is regarded as contended when there is at least one waiter.
Currently, the code that checks whether there are any waiters rely on
tail value being greater than head. However, this is not true if tail
reaches the max value and wraps back to zero, so arch_spin_is_contended()
incorrectly returns 0 (not contended) when tail is smaller than head.

The original code (before regression) handled this case by casting the
(tail - head) to an unsigned value. This change simply restores that
behavior.

Fixes: d6abfdb202 ("x86/spinlocks/paravirt: Fix memory corruption on unlock")
Signed-off-by: Tahsin Erdogan <tahsin@google.com>
Cc: peterz@infradead.org
Cc: Waiman.Long@hp.com
Cc: borntraeger@de.ibm.com
Cc: oleg@redhat.com
Cc: raghavendra.kt@linux.vnet.ibm.com
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1430799331-20445-1-git-send-email-tahsin@google.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This commit is contained in:
Tahsin Erdogan 2015-05-04 21:15:31 -07:00 committed by Thomas Gleixner
parent 94d4b4765b
commit e8a4a2696f

View File

@ -169,7 +169,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock)
struct __raw_tickets tmp = READ_ONCE(lock->tickets);
tmp.head &= ~TICKET_SLOWPATH_FLAG;
return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
}
#define arch_spin_is_contended arch_spin_is_contended