Re: [PATCH V2] x86 spinlock: Fix memory corruption on completing completions

From: Raghavendra K T
Date: Mon Feb 09 2015 - 12:02:17 EST

Ccing Davidlohr, (sorry that I got confused with similar address in cc

On 02/09/2015 08:44 PM, Oleg Nesterov wrote:
On 02/09, Raghavendra K T wrote:

+static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock)
+ arch_spinlock_t old, new;
+ __ticket_t diff;
+ = READ_ONCE(lock->tickets);
+ diff = ( & ~TICKET_SLOWPATH_FLAG) -;
+ /* try to clear slowpath flag when there are no contenders */
+ (diff == TICKET_LOCK_INC)) {
+ new = old;
+ cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
+ }

Can't we simplify it? We own .head, and we already know it. We only need
to clear TICKET_SLOWPATH_FLAG in .tail atomically?


static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock, __ticket_t head)
__ticket_t old_tail, new_tail;

new_tail = head + TICKET_LOCK_INC;
old_tail = new_tail | TICKET_SLOWPATH_FLAG;

if (READ_ONCE(lock->tickets.tail) == old_tail)
cmpxchg(&lock->tickets.tail, old_tail, new_tail);


- __ticket_check_and_clear_slowpath(lock);
+ __ticket_check_and_clear_slowpath(lock, inc.tail);

Or I missed something?

Thanks.. Perfect, 'll update with this change. (Jeremy had hinted

And I think it would be better to avoid ifdef(CONFIG_PARAVIRT_SPINLOCKS),
ww can just do


While at it, I think current arch_spin_unlock() has similar structure
and wanted to clean it up. considering we define
TICKET_SLOWPATH_FLAG 0 or 1, I think compiler would be smart enough
to generate appropriate code and we could avoid #ifdef.

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at