search for: old_tail

Paravirt spinlock clears slowpath flag after doing unlock. As explained by Linus currently it does: prev = *lock; add_smp(&lock->tickets.head, TICKET_LOCK_INC); /* add_smp() is a full mb() */ if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) __ticket_unlock_slowpath(lock, prev); which

Paravirt spinlock clears slowpath flag after doing unlock. As explained by Linus currently it does: prev = *lock; add_smp(&lock->tickets.head, TICKET_LOCK_INC); /* add_smp() is a full mb() */ if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) __ticket_unlock_slowpath(lock, prev); which

...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? IOW, 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); } Plus - __ticket_check_and_clear_slowpath(lock); + __ticket_check_and_clear_slowpath(...

...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? IOW, 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); } Plus - __ticket_check_and_clear_slowpath(lock); + __ticket_check_and_clear_slowpath(...

This version fixes three bugs in the 2nd patch of this series that caused kernel BUG when the system was under race. We weren't accounting with t_oustanding_credits correctly, and there were race conditions caused by the fact the I had overlooked the fact that __jbd2_log_wait_for_space() and jbd2_get_transaction() requires j_state_lock to be write locked. Theodore Ts'o (3): jbd2: Use