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
  ...

1 files changed, 28 insertions, 23 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 437195f..2772208 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1427,16 +1427,19 @@ static int proc_exe_link(struct dentry *dentry, struct path *exe_path)
 static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
 {
 	struct inode *inode = dentry->d_inode;
+	struct path path;
 	int error = -EACCES;
 
-	/* We don't need a base pointer in the /proc filesystem */
-	path_put(&nd->path);
-
 	/* Are we allowed to snoop on the tasks file descriptors? */
 	if (!proc_fd_access_allowed(inode))
 		goto out;
 
-	error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path);
+	error = PROC_I(inode)->op.proc_get_link(dentry, &path);
+	if (error)
+		goto out;
+
+	nd_jump_link(nd, &path);
+	return NULL;
 out:
 	return ERR_PTR(error);
 }
@@ -1601,13 +1604,13 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
  * made this apply to all per process world readable and executable
  * directories.
  */
-int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
+int pid_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
 	const struct cred *cred;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = dentry->d_inode;
@@ -1781,7 +1784,7 @@ static int proc_fd_link(struct dentry *dentry, struct path *path)
 	return proc_fd_info(dentry->d_inode, path, NULL);
 }
 
-static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
@@ -1789,7 +1792,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct files_struct *files;
 	const struct cred *cred;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	inode = dentry->d_inode;
@@ -1868,7 +1871,7 @@ static struct dentry *proc_fd_instantiate(struct inode *dir,
 	d_set_d_op(dentry, &tid_fd_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, NULL))
+	if (tid_fd_revalidate(dentry, 0))
 		error = NULL;
 
  out:
@@ -1956,7 +1959,7 @@ out_no_task:
 }
 
 static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
-				    struct nameidata *nd)
+				    unsigned int flags)
 {
 	return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
 }
@@ -2003,7 +2006,7 @@ static int dname_to_vma_addr(struct dentry *dentry,
 	return 0;
 }
 
-static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	unsigned long vm_start, vm_end;
 	bool exact_vma_exists = false;
@@ -2013,7 +2016,7 @@ static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
 	struct inode *inode;
 	int status = 0;
 
-	if (nd && nd->flags & LOOKUP_RCU)
+	if (flags & LOOKUP_RCU)
 		return -ECHILD;
 
 	if (!capable(CAP_SYS_ADMIN)) {
@@ -2145,7 +2148,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 }
 
 static struct dentry *proc_map_files_lookup(struct inode *dir,
-		struct dentry *dentry, struct nameidata *nd)
+		struct dentry *dentry, unsigned int flags)
 {
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
@@ -2371,7 +2374,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
 	d_set_d_op(dentry, &tid_fd_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
-	if (tid_fd_revalidate(dentry, NULL))
+	if (tid_fd_revalidate(dentry, 0))
 		error = NULL;
 
  out:
@@ -2380,7 +2383,7 @@ static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
 
 static struct dentry *proc_lookupfdinfo(struct inode *dir,
 					struct dentry *dentry,
-					struct nameidata *nd)
+					unsigned int flags)
 {
 	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
 }
@@ -2430,7 +2433,7 @@ static struct dentry *proc_pident_instantiate(struct inode *dir,
 	d_set_d_op(dentry, &pid_dentry_operations);
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, NULL))
+	if (pid_revalidate(dentry, 0))
 		error = NULL;
 out:
 	return error;
@@ -2630,7 +2633,7 @@ static const struct file_operations proc_attr_dir_operations = {
 };
 
 static struct dentry *proc_attr_dir_lookup(struct inode *dir,
-				struct dentry *dentry, struct nameidata *nd)
+				struct dentry *dentry, unsigned int flags)
 {
 	return proc_pident_lookup(dir, dentry,
 				  attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
@@ -3114,7 +3117,8 @@ static const struct file_operations proc_tgid_base_operations = {
 	.llseek		= default_llseek,
 };
 
-static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
 	return proc_pident_lookup(dir, dentry,
 				  tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
 }
@@ -3237,13 +3241,13 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
 
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, NULL))
+	if (pid_revalidate(dentry, 0))
 		error = NULL;
 out:
 	return error;
 }
 
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *result;
 	struct task_struct *task;
@@ -3470,7 +3474,8 @@ static int proc_tid_base_readdir(struct file * filp,
 				   tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
 }
 
-static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
 	return proc_pident_lookup(dir, dentry,
 				  tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
 }
@@ -3508,13 +3513,13 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
 
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
-	if (pid_revalidate(dentry, NULL))
+	if (pid_revalidate(dentry, 0))
 		error = NULL;
 out:
 	return error;
 }
 
-static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
 	struct dentry *result = ERR_PTR(-ENOENT);
 	struct task_struct *task;