For an uncontended rwsem, count and owner are the only fields a task needs to touch when acquiring the rwsem. So they are put next to each other to increase the chance that they will share the same cacheline.
Suggested-by: Linus Torvalds <[email protected]> Signed-off-by: Waiman Long <[email protected]> --- include/linux/rwsem.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index b44e533..be0b926 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -20,21 +20,30 @@ #include <linux/osq_lock.h> #endif -struct rw_semaphore; - -/* All arch specific implementations share the same struct */ +/* + * For an uncontended rwsem, count and owner are the only fields a task + * needs to touch when acquiring the rwsem. So they are put next to each + * other to increase the chance that they will share the same cacheline. + * + * In a contended rwsem, the owner is likely the most frequently accessed + * field in the structure as the optimistic waiter that holds the osq lock + * will spin on owner. For an embedded rwsem, other hot fields in the + * containing structure should be moved further away from the rwsem to + * reduce the chance that they will share the same cacheline causing + * cacheline bouncing problem. + */ struct rw_semaphore { atomic_long_t count; - struct list_head wait_list; - raw_spinlock_t wait_lock; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; + struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif + raw_spinlock_t wait_lock; + struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif -- 1.8.3.1
