Merge branch 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull misc vfs updates from Al Viro:
 "All kinds of stuff.  That probably should've been 5 or 6 separate
  branches, but by the time I'd realized how large and mixed that bag
  had become it had been too close to -final to play with rebasing.

  Some fs/namei.c cleanups there, memdup_user_nul() introduction and
  switching open-coded instances, burying long-dead code, whack-a-mole
  of various kinds, several new helpers for ->llseek(), assorted
  cleanups and fixes from various people, etc.

  One piece probably deserves special mention - Neil's
  lookup_one_len_unlocked().  Similar to lookup_one_len(), but gets
  called without ->i_mutex and tries to avoid ever taking it.  That, of
  course, means that it's not useful for any directory modifications,
  but things like getting inode attributes in nfds readdirplus are fine
  with that.  I really should've asked for moratorium on lookup-related
  changes this cycle, but since I hadn't done that early enough...  I
  *am* asking for that for the coming cycle, though - I'm going to try
  and get conversion of i_mutex to rwsem with ->lookup() done under lock
  taken shared.

  There will be a patch closer to the end of the window, along the lines
  of the one Linus had posted last May - mechanical conversion of
  ->i_mutex accesses to inode_lock()/inode_unlock()/inode_trylock()/
  inode_is_locked()/inode_lock_nested().  To quote Linus back then:

    -----
    |    This is an automated patch using
    |
    |        sed 's/mutex_lock(&\(.*\)->i_mutex)/inode_lock(\1)/'
    |        sed 's/mutex_unlock(&\(.*\)->i_mutex)/inode_unlock(\1)/'
    |        sed 's/mutex_lock_nested(&\(.*\)->i_mutex,[     ]*I_MUTEX_\([A-Z0-9_]*\))/inode_lock_nested(\1, I_MUTEX_\2)/'
    |        sed 's/mutex_is_locked(&\(.*\)->i_mutex)/inode_is_locked(\1)/'
    |        sed 's/mutex_trylock(&\(.*\)->i_mutex)/inode_trylock(\1)/'
    |
    |    with a very few manual fixups
    -----

  I'm going to send that once the ->i_mutex-affecting stuff in -next
  gets mostly merged (or when Linus says he's about to stop taking
  merges)"

* 'work.misc' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (63 commits)
  nfsd: don't hold i_mutex over userspace upcalls
  fs:affs:Replace time_t with time64_t
  fs/9p: use fscache mutex rather than spinlock
  proc: add a reschedule point in proc_readfd_common()
  logfs: constify logfs_block_ops structures
  fcntl: allow to set O_DIRECT flag on pipe
  fs: __generic_file_splice_read retry lookup on AOP_TRUNCATED_PAGE
  fs: xattr: Use kvfree()
  [s390] page_to_phys() always returns a multiple of PAGE_SIZE
  nbd: use ->compat_ioctl()
  fs: use block_device name vsprintf helper
  lib/vsprintf: add %*pg format specifier
  fs: use gendisk->disk_name where possible
  poll: plug an unused argument to do_poll
  amdkfd: don't open-code memdup_user()
  cdrom: don't open-code memdup_user()
  rsxx: don't open-code memdup_user()
  mtip32xx: don't open-code memdup_user()
  [um] mconsole: don't open-code memdup_user_nul()
  [um] hostaudio: don't open-code memdup_user()
  ...

3 files changed, 14 insertions, 19 deletions

diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 00575d776d91..2246454dec76 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -823,7 +823,7 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
 		} else
 			dchild = dget(dparent);
 	} else
-		dchild = lookup_one_len(name, dparent, namlen);
+		dchild = lookup_one_len_unlocked(name, dparent, namlen);
 	if (IS_ERR(dchild))
 		return rv;
 	if (d_mountpoint(dchild))
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 924416f91fdd..d6ef0955a979 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2858,14 +2858,14 @@ nfsd4_encode_dirent_fattr(struct xdr_stream *xdr, struct nfsd4_readdir *cd,
 	__be32 nfserr;
 	int ignore_crossmnt = 0;
 
-	dentry = lookup_one_len(name, cd->rd_fhp->fh_dentry, namlen);
+	dentry = lookup_one_len_unlocked(name, cd->rd_fhp->fh_dentry, namlen);
 	if (IS_ERR(dentry))
 		return nfserrno(PTR_ERR(dentry));
 	if (d_really_is_negative(dentry)) {
 		/*
-		 * nfsd_buffered_readdir drops the i_mutex between
-		 * readdir and calling this callback, leaving a window
-		 * where this directory entry could have gone away.
+		 * we're not holding the i_mutex here, so there's
+		 * a window where this directory entry could have gone
+		 * away.
 		 */
 		dput(dentry);
 		return nfserr_noent;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5411bf09b810..d41c149fae75 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -218,10 +218,16 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		host_err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
 			goto out_nfserr;
-		/*
-		 * check if we have crossed a mount point ...
-		 */
 		if (nfsd_mountpoint(dentry, exp)) {
+			/*
+			 * We don't need the i_mutex after all.  It's
+			 * still possible we could open this (regular
+			 * files can be mountpoints too), but the
+			 * i_mutex is just there to prevent renames of
+			 * something that we might be about to delegate,
+			 * and a mountpoint won't be renamed:
+			 */
+			fh_unlock(fhp);
 			if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
 				dput(dentry);
 				goto out_nfserr;
@@ -1817,7 +1823,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 	offset = *offsetp;
 
 	while (1) {
-		struct inode *dir_inode = file_inode(file);
 		unsigned int reclen;
 
 		cdp->err = nfserr_eof; /* will be cleared on successful read */
@@ -1836,15 +1841,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 		if (!size)
 			break;
 
-		/*
-		 * Various filldir functions may end up calling back into
-		 * lookup_one_len() and the file system's ->lookup() method.
-		 * These expect i_mutex to be held, as it would within readdir.
-		 */
-		host_err = mutex_lock_killable(&dir_inode->i_mutex);
-		if (host_err)
-			break;
-
 		de = (struct buffered_dirent *)buf.dirent;
 		while (size > 0) {
 			offset = de->offset;
@@ -1861,7 +1857,6 @@ static __be32 nfsd_buffered_readdir(struct file *file, nfsd_filldir_t func,
 			size -= reclen;
 			de = (struct buffered_dirent *)((char *)de + reclen);
 		}
-		mutex_unlock(&dir_inode->i_mutex);
 		if (size > 0) /* We bailed out early */
 			break;