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>

16 files changed, 108 insertions, 50 deletions

diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index a796c9417fb1..413b5642e6cf 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -198,7 +198,7 @@ static int autofs4_tree_busy(struct vfsmount *mnt,
                         else
                                 ino_count++;
 
-                        if (atomic_read(&p->d_count) > ino_count) {
+                        if (p->d_count > ino_count) {
                                 top_ino->last_used = jiffies;
                                 dput(p);
                                 return 1;
@@ -347,7 +347,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 2;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         /* Can we umount this guy */
@@ -369,7 +369,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 if (!exp_leaves) {
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 1;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
@@ -383,7 +383,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
                 } else {
                         /* Path walk currently on this dentry? */
                         ino_count = atomic_read(&ino->count) + 1;
-                        if (atomic_read(&dentry->d_count) > ino_count)
+                        if (dentry->d_count > ino_count)
                                 goto next;
 
                         expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index d34896cfb19f..7922509b5b2b 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -436,7 +436,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
                 spin_lock(&active->d_lock);
 
                 /* Already gone? */
-                if (atomic_read(&active->d_count) == 0)
+                if (active->d_count == 0)
                         goto next;
 
                 qstr = &active->d_name;
@@ -452,7 +452,7 @@ static struct dentry *autofs4_lookup_active(struct dentry *dentry)
                         goto next;
 
                 if (d_unhashed(active)) {
-                        dget(active);
+                        dget_dlock(active);
                         spin_unlock(&active->d_lock);
                         spin_unlock(&sbi->lookup_lock);
                         spin_unlock(&dcache_lock);
@@ -507,7 +507,7 @@ static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
                         goto next;
 
                 if (d_unhashed(expiring)) {
-                        dget(expiring);
+                        dget_dlock(expiring);
                         spin_unlock(&expiring->d_lock);
                         spin_unlock(&sbi->lookup_lock);
                         spin_unlock(&dcache_lock);
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index d902948a90d8..3ecf915a4550 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -150,7 +150,9 @@ more:
                 di = ceph_dentry(dentry);
         }
 
-        atomic_inc(&dentry->d_count);
+        spin_lock(&dentry->d_lock);
+        dentry->d_count++;
+        spin_unlock(&dentry->d_lock);
         spin_unlock(&dcache_lock);
 
         dout(" %llu (%llu) dentry %p %.*s %p\n", di->offset, filp->f_pos,
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index bf1286588f26..bb68c799074d 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -879,8 +879,8 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
         } else if (realdn) {
                 dout("dn %p (%d) spliced with %p (%d) "
                      "inode %p ino %llx.%llx\n",
-                     dn, atomic_read(&dn->d_count),
-                     realdn, atomic_read(&realdn->d_count),
+                     dn, dn->d_count,
+                     realdn, realdn->d_count,
                      realdn->d_inode, ceph_vinop(realdn->d_inode));
                 dput(dn);
                 dn = realdn;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 38800eaa81d0..a50fca1e03be 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1486,7 +1486,7 @@ retry:
         *base = ceph_ino(temp->d_inode);
         *plen = len;
         dout("build_path on %p %d built %llx '%.*s'\n",
-             dentry, atomic_read(&dentry->d_count), *base, len, path);
+             dentry, dentry->d_count, *base, len, path);
         return path;
 }
 
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 4cce3b07d9d7..9e37e8bc9b89 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -559,7 +559,7 @@ static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
         if (cii->c_flags & C_FLUSH) 
                 coda_flag_inode_children(inode, C_FLUSH);
 
-        if (atomic_read(&de->d_count) > 1)
+        if (de->d_count > 1)
                 /* pretend it's valid, but don't change the flags */
                 goto out;
 
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 20024a9ef5a7..e9acea440ffc 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -394,8 +394,7 @@ static void remove_dir(struct dentry * d)
         if (d->d_inode)
                 simple_rmdir(parent->d_inode,d);
 
-        pr_debug(" o %s removing done (%d)\n",d->d_name.name,
-                 atomic_read(&d->d_count));
+        pr_debug(" o %s removing done (%d)\n",d->d_name.name, d->d_count);
 
         dput(parent);
 }
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 253476d78ed8..79b37765d8ff 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -253,7 +253,7 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
                 spin_lock(&dcache_lock);
                 spin_lock(&dentry->d_lock);
                 if (!(d_unhashed(dentry) && dentry->d_inode)) {
-                        dget_locked(dentry);
+                        dget_locked_dlock(dentry);
                         __d_drop(dentry);
                         spin_unlock(&dentry->d_lock);
                         spin_unlock(&dcache_lock);
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;
         }
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a1ed7a7cb173..5e5c7ec1fc98 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -260,7 +260,7 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
                                    ecryptfs_dentry->d_parent));
         lower_inode = lower_dentry->d_inode;
         fsstack_copy_attr_atime(ecryptfs_dir_inode, lower_dir_dentry->d_inode);
-        BUG_ON(!atomic_read(&lower_dentry->d_count));
+        BUG_ON(!lower_dentry->d_count);
         ecryptfs_set_dentry_private(ecryptfs_dentry,
                                     kmem_cache_alloc(ecryptfs_dentry_info_cache,
                                                      GFP_KERNEL));
diff --git a/fs/locks.c b/fs/locks.c
index 8729347bcd1a..08415b2a6d36 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1389,7 +1389,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
                 if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
                         goto out;
                 if ((arg == F_WRLCK)
-                    && ((atomic_read(&dentry->d_count) > 1)
+                    && ((dentry->d_count > 1)
                         || (atomic_read(&inode->i_count) > 1)))
                         goto out;
         }
diff --git a/fs/namei.c b/fs/namei.c
index f3b5ca404659..cbfa5fb31072 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2133,7 +2133,7 @@ void dentry_unhash(struct dentry *dentry)
         shrink_dcache_parent(dentry);
         spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) == 2)
+        if (dentry->d_count == 2)
                 __d_drop(dentry);
         spin_unlock(&dentry->d_lock);
         spin_unlock(&dcache_lock);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9184c7c80f78..12de824edb5c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1720,7 +1720,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 
         spin_lock(&dcache_lock);
         spin_lock(&dentry->d_lock);
-        if (atomic_read(&dentry->d_count) > 1) {
+        if (dentry->d_count > 1) {
                 spin_unlock(&dentry->d_lock);
                 spin_unlock(&dcache_lock);
                 /* Start asynchronous writeout of the inode */
@@ -1868,7 +1868,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
         dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n",
                  old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
                  new_dentry->d_parent->d_name.name, new_dentry->d_name.name,
-                 atomic_read(&new_dentry->d_count));
+                 new_dentry->d_count);
 
         /*
          * For non-directories, check whether the target is busy and if so,
@@ -1886,7 +1886,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                         rehash = new_dentry;
                 }
 
-                if (atomic_read(&new_dentry->d_count) > 2) {
+                if (new_dentry->d_count > 2) {
                         int err;
 
                         /* copy the target dentry's name */
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 7bdec8531400..8fe9eb47a97f 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -496,7 +496,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
 
         dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n",
                 dentry->d_parent->d_name.name, dentry->d_name.name,
-                atomic_read(&dentry->d_count));
+                dentry->d_count);
         nfs_inc_stats(dir, NFSIOS_SILLYRENAME);
 
         /*
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 184938fcff04..3a359023c9f7 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1756,8 +1756,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
                 goto out_dput_new;
 
         if (svc_msnfs(ffhp) &&
-                ((atomic_read(&odentry->d_count) > 1)
-                 || (atomic_read(&ndentry->d_count) > 1))) {
+                ((odentry->d_count > 1) || (ndentry->d_count > 1))) {
                         host_err = -EPERM;
                         goto out_dput_new;
         }
@@ -1843,7 +1842,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
         if (type != S_IFDIR) { /* It's UNLINK */
 #ifdef MSNFS
                 if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
-                        (atomic_read(&rdentry->d_count) > 1)) {
+                        (rdentry->d_count > 1)) {
                         host_err = -EPERM;
                 } else
 #endif
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index f804d41ec9d3..d36fc7ee615f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -838,7 +838,7 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
 
 static int nilfs_tree_was_touched(struct dentry *root_dentry)
 {
-        return atomic_read(&root_dentry->d_count) > 1;
+        return root_dentry->d_count > 1;
 }
 
 /**