Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull the big VFS changes from Al Viro:
 "This one is *big* and changes quite a few things around VFS.  What's in there:

   - the first of two really major architecture changes - death to open
     intents.

     The former is finally there; it was very long in making, but with
     Miklos getting through really hard and messy final push in
     fs/namei.c, we finally have it.  Unlike his variant, this one
     doesn't introduce struct opendata; what we have instead is
     ->atomic_open() taking preallocated struct file * and passing
     everything via its fields.

     Instead of returning struct file *, it returns -E...  on error, 0
     on success and 1 in "deal with it yourself" case (e.g.  symlink
     found on server, etc.).

     See comments before fs/namei.c:atomic_open().  That made a lot of
     goodies finally possible and quite a few are in that pile:
     ->lookup(), ->d_revalidate() and ->create() do not get struct
     nameidata * anymore; ->lookup() and ->d_revalidate() get lookup
     flags instead, ->create() gets "do we want it exclusive" flag.

     With the introduction of new helper (kern_path_locked()) we are rid
     of all struct nameidata instances outside of fs/namei.c; it's still
     visible in namei.h, but not for long.  Come the next cycle,
     declaration will move either to fs/internal.h or to fs/namei.c
     itself.  [me, miklos, hch]

   - The second major change: behaviour of final fput().  Now we have
     __fput() done without any locks held by caller *and* not from deep
     in call stack.

     That obviously lifts a lot of constraints on the locking in there.
     Moreover, it's legal now to call fput() from atomic contexts (which
     has immediately simplified life for aio.c).  We also don't need
     anti-recursion logics in __scm_destroy() anymore.

     There is a price, though - the damn thing has become partially
     asynchronous.  For fput() from normal process we are guaranteed
     that pending __fput() will be done before the caller returns to
     userland, exits or gets stopped for ptrace.

     For kernel threads and atomic contexts it's done via
     schedule_work(), so theoretically we might need a way to make sure
     it's finished; so far only one such place had been found, but there
     might be more.

     There's flush_delayed_fput() (do all pending __fput()) and there's
     __fput_sync() (fput() analog doing __fput() immediately).  I hope
     we won't need them often; see warnings in fs/file_table.c for
     details.  [me, based on task_work series from Oleg merged last
     cycle]

   - sync series from Jan

   - large part of "death to sync_supers()" work from Artem; the only
     bits missing here are exofs and ext4 ones.  As far as I understand,
     those are going via the exofs and ext4 trees resp.; once they are
     in, we can put ->write_super() to the rest, along with the thread
     calling it.

   - preparatory bits from unionmount series (from dhowells).

   - assorted cleanups and fixes all over the place, as usual.

  This is not the last pile for this cycle; there's at least jlayton's
  ESTALE work and fsfreeze series (the latter - in dire need of fixes,
  so I'm not sure it'll make the cut this cycle).  I'll probably throw
  symlink/hardlink restrictions stuff from Kees into the next pile, too.
  Plus there's a lot of misc patches I hadn't thrown into that one -
  it's large enough as it is..."

* 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits)
  ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file()
  btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file()
  switch dentry_open() to struct path, make it grab references itself
  spufs: shift dget/mntget towards dentry_open()
  zoran: don't bother with struct file * in zoran_map
  ecryptfs: don't reinvent the wheels, please - use struct completion
  don't expose I_NEW inodes via dentry->d_inode
  tidy up namei.c a bit
  unobfuscate follow_up() a bit
  ext3: pass custom EOF to generic_file_llseek_size()
  ext4: use core vfs llseek code for dir seeks
  vfs: allow custom EOF in generic_file_llseek code
  vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes
  vfs: Remove unnecessary flushing of block devices
  vfs: Make sys_sync writeout also block device inodes
  vfs: Create function for iterating over block devices
  vfs: Reorder operations during sys_sync
  quota: Move quota syncing to ->sync_fs method
  quota: Split dquot_quota_sync() to writeback and cache flushing part
  vfs: Move noop_backing_dev_info check from sync into writeback
  ...

5 files changed, 33 insertions, 91 deletions

diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 534c1d46e69e..1b5d9af937df 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -32,7 +32,7 @@
 /**
  * ecryptfs_d_revalidate - revalidate an ecryptfs dentry
  * @dentry: The ecryptfs dentry
- * @nd: The associated nameidata
+ * @flags: lookup flags
  *
  * Called when the VFS needs to revalidate a dentry. This
  * is called whenever a name lookup finds a dentry in the
@@ -42,32 +42,20 @@
  * Returns 1 if valid, 0 otherwise.
  *
  */
-static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *lower_dentry;
 	struct vfsmount *lower_mnt;
-	struct dentry *dentry_save = NULL;
-	struct vfsmount *vfsmount_save = NULL;
 	int rc = 1;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
 	if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
 		goto out;
-	if (nd) {
-		dentry_save = nd->path.dentry;
-		vfsmount_save = nd->path.mnt;
-		nd->path.dentry = lower_dentry;
-		nd->path.mnt = lower_mnt;
-	}
-	rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
-	if (nd) {
-		nd->path.dentry = dentry_save;
-		nd->path.mnt = vfsmount_save;
-	}
+	rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
 	if (dentry->d_inode) {
 		struct inode *lower_inode =
 			ecryptfs_inode_to_lower(dentry->d_inode);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 867b64c5d84f..989e034f02bd 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -550,20 +550,6 @@ extern struct kmem_cache *ecryptfs_key_record_cache;
 extern struct kmem_cache *ecryptfs_key_sig_cache;
 extern struct kmem_cache *ecryptfs_global_auth_tok_cache;
 extern struct kmem_cache *ecryptfs_key_tfm_cache;
-extern struct kmem_cache *ecryptfs_open_req_cache;
-
-struct ecryptfs_open_req {
-#define ECRYPTFS_REQ_PROCESSED 0x00000001
-#define ECRYPTFS_REQ_DROPPED   0x00000002
-#define ECRYPTFS_REQ_ZOMBIE    0x00000004
-	u32 flags;
-	struct file **lower_file;
-	struct dentry *lower_dentry;
-	struct vfsmount *lower_mnt;
-	wait_queue_head_t wait;
-	struct mutex mux;
-	struct list_head kthread_ctl_list;
-};
 
 struct inode *ecryptfs_get_inode(struct inode *lower_inode,
 				 struct super_block *sb);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a07441a0a878..ffa2be57804d 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -173,7 +173,7 @@ ecryptfs_do_create(struct inode *directory_inode,
 		inode = ERR_CAST(lower_dir_dentry);
 		goto out;
 	}
-	rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL);
+	rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
 		       "rc = [%d]\n", __func__, rc);
@@ -240,7 +240,6 @@ out:
  * @dir: The inode of the directory in which to create the file.
  * @dentry: The eCryptfs dentry
  * @mode: The mode of the new file.
- * @nd: nameidata
  *
  * Creates a new file.
  *
@@ -248,7 +247,7 @@ out:
  */
 static int
 ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
-		umode_t mode, struct nameidata *nd)
+		umode_t mode, bool excl)
 {
 	struct inode *ecryptfs_inode;
 	int rc;
@@ -270,8 +269,8 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		iput(ecryptfs_inode);
 		goto out;
 	}
-	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
 	unlock_new_inode(ecryptfs_inode);
+	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
 out:
 	return rc;
 }
@@ -374,7 +373,7 @@ static int ecryptfs_lookup_interpose(struct dentry *dentry,
  */
 static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
 				      struct dentry *ecryptfs_dentry,
-				      struct nameidata *ecryptfs_nd)
+				      unsigned int flags)
 {
 	char *encrypted_and_encoded_name = NULL;
 	size_t encrypted_and_encoded_name_size;
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 0dbe58a8b172..809e67d05ca3 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -27,7 +27,12 @@
 #include <linux/mount.h>
 #include "ecryptfs_kernel.h"
 
-struct kmem_cache *ecryptfs_open_req_cache;
+struct ecryptfs_open_req {
+	struct file **lower_file;
+	struct path path;
+	struct completion done;
+	struct list_head kthread_ctl_list;
+};
 
 static struct ecryptfs_kthread_ctl {
 #define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
@@ -67,18 +72,10 @@ static int ecryptfs_threadfn(void *ignored)
 			req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
 					       struct ecryptfs_open_req,
 					       kthread_ctl_list);
-			mutex_lock(&req->mux);
 			list_del(&req->kthread_ctl_list);
-			if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) {
-				dget(req->lower_dentry);
-				mntget(req->lower_mnt);
-				(*req->lower_file) = dentry_open(
-					req->lower_dentry, req->lower_mnt,
-					(O_RDWR | O_LARGEFILE), current_cred());
-				req->flags |= ECRYPTFS_REQ_PROCESSED;
-			}
-			wake_up(&req->wait);
-			mutex_unlock(&req->mux);
+			*req->lower_file = dentry_open(&req->path,
+				(O_RDWR | O_LARGEFILE), current_cred());
+			complete(&req->done);
 		}
 		mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	}
@@ -111,10 +108,9 @@ void ecryptfs_destroy_kthread(void)
 	ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
 	list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list,
 			    kthread_ctl_list) {
-		mutex_lock(&req->mux);
-		req->flags |= ECRYPTFS_REQ_ZOMBIE;
-		wake_up(&req->wait);
-		mutex_unlock(&req->mux);
+		list_del(&req->kthread_ctl_list);
+		*req->lower_file = ERR_PTR(-EIO);
+		complete(&req->done);
 	}
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	kthread_stop(ecryptfs_kthread);
@@ -136,34 +132,26 @@ int ecryptfs_privileged_open(struct file **lower_file,
 			     struct vfsmount *lower_mnt,
 			     const struct cred *cred)
 {
-	struct ecryptfs_open_req *req;
+	struct ecryptfs_open_req req;
 	int flags = O_LARGEFILE;
 	int rc = 0;
 
+	init_completion(&req.done);
+	req.lower_file = lower_file;
+	req.path.dentry = lower_dentry;
+	req.path.mnt = lower_mnt;
+
 	/* Corresponding dput() and mntput() are done when the
 	 * lower file is fput() when all eCryptfs files for the inode are
 	 * released. */
-	dget(lower_dentry);
-	mntget(lower_mnt);
 	flags |= IS_RDONLY(lower_dentry->d_inode) ? O_RDONLY : O_RDWR;
-	(*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred);
+	(*lower_file) = dentry_open(&req.path, flags, cred);
 	if (!IS_ERR(*lower_file))
 		goto out;
 	if ((flags & O_ACCMODE) == O_RDONLY) {
 		rc = PTR_ERR((*lower_file));
 		goto out;
 	}
-	req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL);
-	if (!req) {
-		rc = -ENOMEM;
-		goto out;
-	}
-	mutex_init(&req->mux);
-	req->lower_file = lower_file;
-	req->lower_dentry = lower_dentry;
-	req->lower_mnt = lower_mnt;
-	init_waitqueue_head(&req->wait);
-	req->flags = 0;
 	mutex_lock(&ecryptfs_kthread_ctl.mux);
 	if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
 		rc = -EIO;
@@ -171,27 +159,14 @@ int ecryptfs_privileged_open(struct file **lower_file,
 		printk(KERN_ERR "%s: We are in the middle of shutting down; "
 		       "aborting privileged request to open lower file\n",
 			__func__);
-		goto out_free;
+		goto out;
 	}
-	list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+	list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
 	mutex_unlock(&ecryptfs_kthread_ctl.mux);
 	wake_up(&ecryptfs_kthread_ctl.wait);
-	wait_event(req->wait, (req->flags != 0));
-	mutex_lock(&req->mux);
-	BUG_ON(req->flags == 0);
-	if (req->flags & ECRYPTFS_REQ_DROPPED
-	    || req->flags & ECRYPTFS_REQ_ZOMBIE) {
-		rc = -EIO;
-		printk(KERN_WARNING "%s: Privileged open request dropped\n",
-		       __func__);
-		goto out_unlock;
-	}
-	if (IS_ERR(*req->lower_file))
-		rc = PTR_ERR(*req->lower_file);
-out_unlock:
-	mutex_unlock(&req->mux);
-out_free:
-	kmem_cache_free(ecryptfs_open_req_cache, req);
+	wait_for_completion(&req.done);
+	if (IS_ERR(*lower_file))
+		rc = PTR_ERR(*lower_file);
 out:
 	return rc;
 }
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 68954937a071..1c0b3b6b75c6 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -499,13 +499,12 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	s = sget(fs_type, NULL, set_anon_super, NULL);
+	s = sget(fs_type, NULL, set_anon_super, flags, NULL);
 	if (IS_ERR(s)) {
 		rc = PTR_ERR(s);
 		goto out;
 	}
 
-	s->s_flags = flags;
 	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
 	if (rc)
 		goto out1;
@@ -682,11 +681,6 @@ static struct ecryptfs_cache_info {
 		.name = "ecryptfs_key_tfm_cache",
 		.size = sizeof(struct ecryptfs_key_tfm),
 	},
-	{
-		.cache = &ecryptfs_open_req_cache,
-		.name = "ecryptfs_open_req_cache",
-		.size = sizeof(struct ecryptfs_open_req),
-	},
 };
 
 static void ecryptfs_free_kmem_caches(void)