Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/viro/vfs

Pull vfs updates from Al Viro:

 - Preparations of parallel lookups (the remaining main obstacle is the
   need to move security_d_instantiate(); once that becomes safe, the
   rest will be a matter of rather short series local to fs/*.c

 - preadv2/pwritev2 series from Christoph

 - assorted fixes

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (32 commits)
  splice: handle zero nr_pages in splice_to_pipe()
  vfs: show_vfsstat: do not ignore errors from show_devname method
  dcache.c: new helper: __d_add()
  don't bother with __d_instantiate(dentry, NULL)
  untangle fsnotify_d_instantiate() a bit
  uninline d_add()
  replace d_add_unique() with saner primitive
  quota: use lookup_one_len_unlocked()
  cifs_get_root(): use lookup_one_len_unlocked()
  nfs_lookup: don't bother with d_instantiate(dentry, NULL)
  kill dentry_unhash()
  ceph_fill_trace(): don't bother with d_instantiate(dn, NULL)
  autofs4: don't bother with d_instantiate(dentry, NULL) in ->lookup()
  configfs: move d_rehash() into configfs_create() for regular files
  ceph: don't bother with d_rehash() in splice_dentry()
  namei: teach lookup_slow() to skip revalidate
  namei: massage lookup_slow() to be usable by lookup_one_len_unlocked()
  lookup_one_len_unlocked(): use lookup_dcache()
  namei: simplify invalidation logics in lookup_dcache()
  namei: change calling conventions for lookup_{fast,slow} and follow_managed()
  ...

arch/x86/entry/syscalls/syscall_32.tbl

@@ -384,3 +384,5 @@
 375	i386	membarrier		sys_membarrier
 376	i386	mlock2			sys_mlock2
 377	i386	copy_file_range		sys_copy_file_range
+378	i386	preadv2			sys_preadv2
+379	i386	pwritev2		sys_pwritev2

arch/x86/entry/syscalls/syscall_64.tbl

@@ -333,6 +333,8 @@
 324	common	membarrier		sys_membarrier
 325	common	mlock2			sys_mlock2
 326	common	copy_file_range		sys_copy_file_range
+327	64	preadv2			sys_preadv2
+328	64	pwritev2		sys_pwritev2
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact

fs/autofs4/root.c

@@ -542,8 +542,6 @@ static struct dentry *autofs4_lookup(struct inode *dir,
 		ino->dentry = dentry;
 
 		autofs4_add_active(dentry);
-
-		d_instantiate(dentry, NULL);
 	}
 	return NULL;
 }

fs/cachefiles/daemon.c

@@ -162,6 +162,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 				      size_t buflen, loff_t *pos)
 {
 	struct cachefiles_cache *cache = file->private_data;
+	unsigned long long b_released;
+	unsigned f_released;
 	char buffer[256];
 	int n;
 
@@ -174,6 +176,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 	cachefiles_has_space(cache, 0, 0);
 
 	/* summarise */
+	f_released = atomic_xchg(&cache->f_released, 0);
+	b_released = atomic_long_xchg(&cache->b_released, 0);
 	clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
 
 	n = snprintf(buffer, sizeof(buffer),
@@ -183,15 +187,18 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
 		     " fstop=%llx"
 		     " brun=%llx"
 		     " bcull=%llx"
-		     " bstop=%llx",
+		     " bstop=%llx"
+		     " freleased=%x"
+		     " breleased=%llx",
 		     test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
 		     (unsigned long long) cache->frun,
 		     (unsigned long long) cache->fcull,
 		     (unsigned long long) cache->fstop,
 		     (unsigned long long) cache->brun,
 		     (unsigned long long) cache->bcull,
-		     (unsigned long long) cache->bstop
-		     );
+		     (unsigned long long) cache->bstop,
+		     f_released,
+		     b_released);
 
 	if (n > buflen)
 		return -EMSGSIZE;

fs/cachefiles/interface.c

@@ -291,15 +291,8 @@ static void cachefiles_drop_object(struct fscache_object *_object)
 	}
 
 	/* note that the object is now inactive */
-	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
-		write_lock(&cache->active_lock);
-		if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
-					&object->flags))
-			BUG();
-		rb_erase(&object->active_node, &cache->active_nodes);
-		wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-		write_unlock(&cache->active_lock);
-	}
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+		cachefiles_mark_object_inactive(cache, object);
 
 	dput(object->dentry);
 	object->dentry = NULL;

fs/cachefiles/internal.h

@@ -66,6 +66,8 @@ struct cachefiles_cache {
 	struct rb_root			active_nodes;	/* active nodes (can't be culled) */
 	rwlock_t			active_lock;	/* lock for active_nodes */
 	atomic_t			gravecounter;	/* graveyard uniquifier */
+	atomic_t			f_released;	/* number of objects released lately */
+	atomic_long_t			b_released;	/* number of blocks released lately */
 	unsigned			frun_percent;	/* when to stop culling (% files) */
 	unsigned			fcull_percent;	/* when to start culling (% files) */
 	unsigned			fstop_percent;	/* when to stop allocating (% files) */
@@ -157,6 +159,8 @@ extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
 /*
  * namei.c
  */
+extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+					    struct cachefiles_object *object);
 extern int cachefiles_delete_object(struct cachefiles_cache *cache,
 				    struct cachefiles_object *object);
 extern int cachefiles_walk_to_object(struct cachefiles_object *parent,

fs/cachefiles/namei.c

@@ -257,6 +257,28 @@ static int cachefiles_mark_object_active(struct cachefiles_cache *cache,
 	return -ETIMEDOUT;
 }
 
+/*
+ * Mark an object as being inactive.
+ */
+void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+				     struct cachefiles_object *object)
+{
+	write_lock(&cache->active_lock);
+	rb_erase(&object->active_node, &cache->active_nodes);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	write_unlock(&cache->active_lock);
+
+	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+
+	/* This object can now be culled, so we need to let the daemon know
+	 * that there is something it can remove if it needs to.
+	 */
+	atomic_long_add(d_backing_inode(object->dentry)->i_blocks,
+			&cache->b_released);
+	if (atomic_inc_return(&cache->f_released))
+		cachefiles_state_changed(cache);
+}
+
 /*
  * delete an object representation from the cache
  * - file backed objects are unlinked
@@ -684,11 +706,7 @@ int cachefiles_walk_to_object(struct cachefiles_object *parent,
 
 check_error:
 	_debug("check error %d", ret);
-	write_lock(&cache->active_lock);
-	rb_erase(&object->active_node, &cache->active_nodes);
-	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
-	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
-	write_unlock(&cache->active_lock);
+	cachefiles_mark_object_inactive(cache, object);
 release_dentry:
 	dput(object->dentry);
 	object->dentry = NULL;

fs/ceph/inode.c

@@ -977,13 +977,8 @@ static void update_dentry_lease(struct dentry *dentry,
 /*
  * splice a dentry to an inode.
  * caller must hold directory i_mutex for this to be safe.
- *
- * we will only rehash the resulting dentry if @prehash is
- * true; @prehash will be set to false (for the benefit of
- * the caller) if we fail.
  */
-static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
-				    bool *prehash)
+static struct dentry *splice_dentry(struct dentry *dn, struct inode *in)
 {
 	struct dentry *realdn;
 
@@ -996,8 +991,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
-		if (prehash)
-			*prehash = false; /* don't rehash on error */
 		dn = realdn; /* note realdn contains the error */
 		goto out;
 	} else if (realdn) {
@@ -1013,8 +1006,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in,
 		dout("dn %p attached to %p ino %llx.%llx\n",
 		     dn, d_inode(dn), ceph_vinop(d_inode(dn)));
 	}
-	if ((!prehash || *prehash) && d_unhashed(dn))
-		d_rehash(dn);
 out:
 	return dn;
 }
@@ -1247,10 +1238,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
 			} else {
-				dout("d_instantiate %p NULL\n", dn);
-				d_instantiate(dn, NULL);
 				if (have_lease && d_unhashed(dn))
-					d_rehash(dn);
+					d_add(dn, NULL);
 				update_dentry_lease(dn, rinfo->dlease,
 						    session,
 						    req->r_request_started);
@@ -1262,7 +1251,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		if (d_really_is_negative(dn)) {
 			ceph_dir_clear_ordered(dir);
 			ihold(in);
-			dn = splice_dentry(dn, in, &have_lease);
+			dn = splice_dentry(dn, in);
 			if (IS_ERR(dn)) {
 				err = PTR_ERR(dn);
 				goto done;
@@ -1292,7 +1281,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 		dout(" linking snapped dir %p to dn %p\n", in, dn);
 		ceph_dir_clear_ordered(dir);
 		ihold(in);
-		dn = splice_dentry(dn, in, NULL);
+		dn = splice_dentry(dn, in);
 		if (IS_ERR(dn)) {
 			err = PTR_ERR(dn);
 			goto done;
@@ -1503,7 +1492,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 		}
 
 		if (d_really_is_negative(dn)) {
-			struct dentry *realdn = splice_dentry(dn, in, NULL);
+			struct dentry *realdn = splice_dentry(dn, in);
 			if (IS_ERR(realdn)) {
 				err = PTR_ERR(realdn);
 				d_drop(dn);

fs/cifs/cifsfs.c

@@ -642,9 +642,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 		while (*s && *s != sep)
 			s++;
 
-		inode_lock(dir);
-		child = lookup_one_len(p, dentry, s - p);
-		inode_unlock(dir);
+		child = lookup_one_len_unlocked(p, dentry, s - p);
 		dput(dentry);
 		dentry = child;
 	} while (!IS_ERR(dentry));

fs/configfs/dir.c

@@ -432,14 +432,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den
 				(sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ?
 					configfs_init_bin_file :
 					configfs_init_file);
-	if (error) {
+	if (error)
 		configfs_put(sd);
-		return error;
-	}
-
-	d_rehash(dentry);
-
-	return 0;
+	return error;
 }
 
 static struct dentry * configfs_lookup(struct inode *dir,

fs/configfs/inode.c

@@ -201,9 +201,17 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in
 	configfs_set_inode_lock_class(sd, inode);
 
 	init(inode);
-	d_instantiate(dentry, inode);
-	if (S_ISDIR(mode) || S_ISLNK(mode))
+	if (S_ISDIR(mode) || S_ISLNK(mode)) {
+		/*
+		 * ->symlink(), ->mkdir(), configfs_register_subsystem() or
+		 * create_default_group() - already hashed.
+		 */
+		d_instantiate(dentry, inode);
 		dget(dentry);  /* pin link and directory dentries in core */
+	} else {
+		/* ->lookup() */
+		d_add(dentry, inode);
+	}
 	return error;
 }