Re: ??????[PATCH 1/3 v3] dcache: Don't take unnecessary lock in d_count update

2013-05-23 Thread Waiman Long
On 05/23/2013 05:09 AM, remaper wrote: maybe you can use the atomic_dec_and_lock(&dentry->d_count,&dentry->d_lock) here, right ? -- Origin -- The current code takes the dentry's d_lock lock whenever the d_count reference count is being updated. In reality, nothi

??????[PATCH 1/3 v3] dcache: Don't take unnecessary lock in d_count update

2013-05-23 Thread remaper
maybe you can use the atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock) here, right ? -- Origin -- >The current code takes the dentry's d_lock lock whenever the d_count >reference count is being updated. In reality, nothing big really > happens until d_count g

[PATCH 1/3 v3] dcache: Don't take unnecessary lock in d_count update

2013-05-22 Thread Waiman Long
The current code takes the dentry's d_lock lock whenever the d_count reference count is being updated. In reality, nothing big really happens until d_count goes to 0 in dput(). So it is not necessary to take the lock if the reference count won't go to 0. Without using a lock, multiple threads may