fs: dcache scale dentry refcount

Make d_count non-atomic and protect it with d_lock. This allows us to ensure a
0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when
we start protecting many other dentry members with d_lock.

Signed-off-by: Nick Piggin <npiggin@kernel.dk>

1 files changed, 82 insertions, 24 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 3d3c843c36ed..81e91502b294 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -45,6 +45,7 @@
  *   - d_flags
  *   - d_name
  *   - d_lru
+ *   - d_count
  *
  * Ordering:
  * dcache_lock
@@ -125,6 +126,7 @@ static void __d_free(struct rcu_head *head)
  */
 static void d_free(struct dentry *dentry)
 {
+        BUG_ON(dentry->d_count);
         this_cpu_dec(nr_dentry);
         if (dentry->d_op && dentry->d_op->d_release)
                 dentry->d_op->d_release(dentry);
@@ -222,8 +224,11 @@ static struct dentry *d_kill(struct dentry *dentry)
         struct dentry *parent;
 
         list_del(&dentry->d_u.d_child);
-        /*drops the locks, at that point nobody can reach this dentry */
         dentry_iput(dentry);
+        /*
+         * dentry_iput drops the locks, at which point nobody (except
+         * transient RCU lookups) can reach this dentry.
+         */
         if (IS_ROOT(dentry))
                 parent = NULL;
         else
@@ -303,13 +308,23 @@ void dput(struct dentry *dentry)
                 return;
 
 repeat:
-        if (atomic_read(&dentry->d_count) == 1)
+        if (dentry->d_count == 1)
                 might_sleep();
-        if (!atomic_dec_and_lock(&dentry->d_count, &dcache_lock))
-                return;
-
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count)) {
+        if (dentry->d_count == 1) {
+                if (!spin_trylock(&dcache_lock)) {
+                        /*
+                         * Something of a livelock possibility we could avoid
+                         * by taking dcache_lock and trying again, but we
+                         * want to reduce dcache_lock anyway so this will
+                         * get improved.
+                         */
+                        spin_unlock(&dentry->d_lock);
+                        goto repeat;
+                }
+        }
+        dentry->d_count--;
+        if (dentry->d_count) {
                 spin_unlock(&dentry->d_lock);
                 spin_unlock(&dcache_lock);
                 return;
@@ -389,7 +404,7 @@ int d_invalidate(struct dentry * dentry)
          * working directory or similar).
          */
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) > 1) {
+        if (dentry->d_count > 1) {
                 if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
                         spin_unlock(&dentry->d_lock);
                         spin_unlock(&dcache_lock);
@@ -404,29 +419,61 @@ int d_invalidate(struct dentry * dentry)
 }
 EXPORT_SYMBOL(d_invalidate);
 
-/* This should be called _only_ with dcache_lock held */
+/* This must be called with dcache_lock and d_lock held */
 static inline struct dentry * __dget_locked_dlock(struct dentry *dentry)
 {
-        atomic_inc(&dentry->d_count);
+        dentry->d_count++;
         dentry_lru_del(dentry);
         return dentry;
 }
 
+/* This should be called _only_ with dcache_lock held */
 static inline struct dentry * __dget_locked(struct dentry *dentry)
 {
-        atomic_inc(&dentry->d_count);
         spin_lock(&dentry->d_lock);
-        dentry_lru_del(dentry);
+        __dget_locked_dlock(dentry);
         spin_unlock(&dentry->d_lock);
         return dentry;
 }
 
+struct dentry * dget_locked_dlock(struct dentry *dentry)
+{
+        return __dget_locked_dlock(dentry);
+}
+
 struct dentry * dget_locked(struct dentry *dentry)
 {
         return __dget_locked(dentry);
 }
 EXPORT_SYMBOL(dget_locked);
 
+struct dentry *dget_parent(struct dentry *dentry)
+{
+        struct dentry *ret;
+
+repeat:
+        spin_lock(&dentry->d_lock);
+        ret = dentry->d_parent;
+        if (!ret)
+                goto out;
+        if (dentry == ret) {
+                ret->d_count++;
+                goto out;
+        }
+        if (!spin_trylock(&ret->d_lock)) {
+                spin_unlock(&dentry->d_lock);
+                cpu_relax();
+                goto repeat;
+        }
+        BUG_ON(!ret->d_count);
+        ret->d_count++;
+        spin_unlock(&ret->d_lock);
+out:
+        spin_unlock(&dentry->d_lock);
+        return ret;
+}
+EXPORT_SYMBOL(dget_parent);
+
 /**
  * d_find_alias - grab a hashed alias of inode
  * @inode: inode in question
@@ -495,7 +542,7 @@ restart:
         spin_lock(&dcache_lock);
         list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
                 spin_lock(&dentry->d_lock);
-                if (!atomic_read(&dentry->d_count)) {
+                if (!dentry->d_count) {
                         __dget_locked_dlock(dentry);
                         __d_drop(dentry);
                         spin_unlock(&dentry->d_lock);
@@ -530,7 +577,10 @@ static void prune_one_dentry(struct dentry * dentry)
          */
         while (dentry) {
                 spin_lock(&dcache_lock);
-                if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock)) {
+                spin_lock(&dentry->d_lock);
+                dentry->d_count--;
+                if (dentry->d_count) {
+                        spin_unlock(&dentry->d_lock);
                         spin_unlock(&dcache_lock);
                         return;
                 }
@@ -562,7 +612,7 @@ static void shrink_dentry_list(struct list_head *list)
                  * the LRU because of laziness during lookup.  Do not free
                  * it - just keep it off the LRU list.
                  */
-                if (atomic_read(&dentry->d_count)) {
+                if (dentry->d_count) {
                         spin_unlock(&dentry->d_lock);
                         continue;
                 }
@@ -783,7 +833,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                 do {
                         struct inode *inode;
 
-                        if (atomic_read(&dentry->d_count) != 0) {
+                        if (dentry->d_count != 0) {
                                 printk(KERN_ERR
                                        "BUG: Dentry %p{i=%lx,n=%s}"
                                        " still in use (%d)"
@@ -792,7 +842,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                                        dentry->d_inode ?
                                        dentry->d_inode->i_ino : 0UL,
                                        dentry->d_name.name,
-                                       atomic_read(&dentry->d_count),
+                                       dentry->d_count,
                                        dentry->d_sb->s_type->name,
                                        dentry->d_sb->s_id);
                                 BUG();
@@ -802,7 +852,9 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                                 parent = NULL;
                         else {
                                 parent = dentry->d_parent;
-                                atomic_dec(&parent->d_count);
+                                spin_lock(&parent->d_lock);
+                                parent->d_count--;
+                                spin_unlock(&parent->d_lock);
                         }
 
                         list_del(&dentry->d_u.d_child);
@@ -853,7 +905,9 @@ void shrink_dcache_for_umount(struct super_block *sb)
 
         dentry = sb->s_root;
         sb->s_root = NULL;
-        atomic_dec(&dentry->d_count);
+        spin_lock(&dentry->d_lock);
+        dentry->d_count--;
+        spin_unlock(&dentry->d_lock);
         shrink_dcache_for_umount_subtree(dentry);
 
         while (!hlist_empty(&sb->s_anon)) {
@@ -950,7 +1004,7 @@ resume:
                  * move only zero ref count dentries to the end 
                  * of the unused list for prune_dcache
                  */
-                if (!atomic_read(&dentry->d_count)) {
+                if (!dentry->d_count) {
                         dentry_lru_move_tail(dentry);
                         found++;
                 } else {
@@ -1068,7 +1122,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
         memcpy(dname, name->name, name->len);
         dname[name->len] = 0;
 
-        atomic_set(&dentry->d_count, 1);
+        dentry->d_count = 1;
         dentry->d_flags = DCACHE_UNHASHED;
         spin_lock_init(&dentry->d_lock);
         dentry->d_inode = NULL;
@@ -1556,7 +1610,7 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
                                 goto next;
                 }
 
-                atomic_inc(&dentry->d_count);
+                dentry->d_count++;
                 found = dentry;
                 spin_unlock(&dentry->d_lock);
                 break;
@@ -1653,7 +1707,7 @@ void d_delete(struct dentry * dentry)
         spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
         isdir = S_ISDIR(dentry->d_inode->i_mode);
-        if (atomic_read(&dentry->d_count) == 1) {
+        if (dentry->d_count == 1) {
                 dentry->d_flags &= ~DCACHE_CANT_MOUNT;
                 dentry_iput(dentry);
                 fsnotify_nameremove(dentry, isdir);
@@ -2494,11 +2548,15 @@ resume:
                         this_parent = dentry;
                         goto repeat;
                 }
-                atomic_dec(&dentry->d_count);
+                spin_lock(&dentry->d_lock);
+                dentry->d_count--;
+                spin_unlock(&dentry->d_lock);
         }
         if (this_parent != root) {
                 next = this_parent->d_u.d_child.next;
-                atomic_dec(&this_parent->d_count);
+                spin_lock(&this_parent->d_lock);
+                this_parent->d_count--;
+                spin_unlock(&this_parent->d_lock);
                 this_parent = this_parent->d_parent;
                 goto resume;
         }