fs/dcache: Move wakeup out of i_seq_dir write held region.

__d_add() and __d_move() wake up waiters on dentry::d_wait from within
the i_seq_dir write held region.  This violates the PREEMPT_RT
constraints as the wake up acquires wait_queue_head::lock which is a
"sleeping" spinlock on RT.

There is no requirement to do so. __d_lookup_unhash() has cleared
DCACHE_PAR_LOOKUP and dentry::d_wait and returned the now unreachable wait
queue head pointer to the caller, so the actual wake up can be postponed
until the i_dir_seq write side critical section is left. The only
requirement is that dentry::lock is held across the whole sequence
including the wake up. The previous commit includes an analysis why this
is considered safe.

Move the wake up past end_dir_add() which leaves the i_dir_seq write side
critical section and enables preemption.

For non RT kernels there is no difference because preemption is still
disabled due to dentry::lock being held, but it shortens the time between
wake up and unlocking dentry::lock, which reduces the contention for the
woken up waiter.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

diff --git a/fs/dcache.c b/fs/dcache.c
index b6cdc0f..ea5cdec 100644 (file)
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2581,11 +2581,13 @@ static inline unsigned start_dir_add(struct inode *dir)
        }
 }
 
-static inline void end_dir_add(struct inode *dir, unsigned n)
+static inline void end_dir_add(struct inode *dir, unsigned int n,
+                              wait_queue_head_t *d_wait)
 {
        smp_store_release(&dir->i_dir_seq, n + 2);
        if (IS_ENABLED(CONFIG_PREEMPT_RT))
                preempt_enable();
+       wake_up_all(d_wait);
 }
 
 static void d_wait_lookup(struct dentry *dentry)
@@ -2756,7 +2758,6 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
                dir = dentry->d_parent->d_inode;
                n = start_dir_add(dir);
                d_wait = __d_lookup_unhash(dentry);
-               wake_up_all(d_wait);
        }
        if (inode) {
                unsigned add_flags = d_flags_for_inode(inode);
@@ -2768,7 +2769,7 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
        }
        __d_rehash(dentry);
        if (dir)
-               end_dir_add(dir, n);
+               end_dir_add(dir, n, d_wait);
        spin_unlock(&dentry->d_lock);
        if (inode)
                spin_unlock(&inode->i_lock);
@@ -2947,7 +2948,6 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
                dir = target->d_parent->d_inode;
                n = start_dir_add(dir);
                d_wait = __d_lookup_unhash(target);
-               wake_up_all(d_wait);
        }
 
        write_seqcount_begin(&dentry->d_seq);
@@ -2983,7 +2983,7 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
        write_seqcount_end(&dentry->d_seq);
 
        if (dir)
-               end_dir_add(dir, n);
+               end_dir_add(dir, n, d_wait);
 
        if (dentry->d_parent != old_parent)
                spin_unlock(&dentry->d_parent->d_lock);