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

Pull more vfs updates from Al Viro:
 "Assorted VFS fixes and related cleanups (IMO the most interesting in
  that part are f_path-related things and Eric's descriptor-related
  stuff).  UFS regression fixes (it got broken last cycle).  9P fixes.
  fs-cache series, DAX patches, Jan's file_remove_suid() work"

[ I'd say this is much more than "fixes and related cleanups".  The
  file_table locking rule change by Eric Dumazet is a rather big and
  fundamental update even if the patch isn't huge.   - Linus ]

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (49 commits)
  9p: cope with bogus responses from server in p9_client_{read,write}
  p9_client_write(): avoid double p9_free_req()
  9p: forgetting to cancel request on interrupted zero-copy RPC
  dax: bdev_direct_access() may sleep
  block: Add support for DAX reads/writes to block devices
  dax: Use copy_from_iter_nocache
  dax: Add block size note to documentation
  fs/file.c: __fget() and dup2() atomicity rules
  fs/file.c: don't acquire files->file_lock in fd_install()
  fs:super:get_anon_bdev: fix race condition could cause dev exceed its upper limitation
  vfs: avoid creation of inode number 0 in get_next_ino
  namei: make set_root_rcu() return void
  make simple_positive() public
  ufs: use dir_pages instead of ufs_dir_pages()
  pagemap.h: move dir_pages() over there
  remove the pointless include of lglock.h
  fs: cleanup slight list_entry abuse
  xfs: Correctly lock inode when removing suid and file capabilities
  fs: Call security_ops->inode_killpriv on truncate
  fs: Provide function telling whether file_remove_privs() will do anything
  ...

69 files changed, 657 insertions, 467 deletions

diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index cffe8370fb44..c69a87eaf57d 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -64,7 +64,7 @@ struct affs_inode_info {
 /* short cut to get to the affs specific inode data */
 static inline struct affs_inode_info *AFFS_I(struct inode *inode)
 {
-	return list_entry(inode, struct affs_inode_info, vfs_inode);
+	return container_of(inode, struct affs_inode_info, vfs_inode);
 }
 
 /*
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 5b700ef1e59d..c37149b929be 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -238,11 +238,6 @@ static inline u64 autofs4_get_ino(struct autofs_sb_info *sbi)
 	return d_inode(sbi->sb->s_root)->i_ino;
 }
 
-static inline int simple_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static inline void __autofs4_add_expiring(struct dentry *dentry)
 {
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
diff --git a/fs/befs/befs.h b/fs/befs/befs.h
index 1fead8d56a98..35d19e8731e3 100644
--- a/fs/befs/befs.h
+++ b/fs/befs/befs.h
@@ -112,7 +112,7 @@ BEFS_SB(const struct super_block *super)
 static inline struct befs_inode_info *
 BEFS_I(const struct inode *inode)
 {
-	return list_entry(inode, struct befs_inode_info, vfs_inode);
+	return container_of(inode, struct befs_inode_info, vfs_inode);
 }
 
 static inline befs_blocknr_t
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index cd46e4158830..6b659967898e 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1530,7 +1530,7 @@ static int fill_files_note(struct memelfnote *note)
 		file = vma->vm_file;
 		if (!file)
 			continue;
-		filename = d_path(&file->f_path, name_curpos, remaining);
+		filename = file_path(file, name_curpos, remaining);
 		if (IS_ERR(filename)) {
 			if (PTR_ERR(filename) == -ENAMETOOLONG) {
 				vfree(data);
@@ -1540,7 +1540,7 @@ static int fill_files_note(struct memelfnote *note)
 			continue;
 		}
 
-		/* d_path() fills at the end, move name down */
+		/* file_path() fills at the end, move name down */
 		/* n = strlen(filename) + 1: */
 		n = (name_curpos + remaining) - filename;
 		remaining = filename - name_curpos;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4fe10f93db8a..198243717da5 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -152,6 +152,9 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
 
+	if (IS_DAX(inode))
+		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
+				NULL, DIO_SKIP_DIO_COUNT);
 	return __blockdev_direct_IO(iocb, inode, I_BDEV(inode), iter, offset,
 				    blkdev_get_block, NULL, NULL,
 				    DIO_SKIP_DIO_COUNT);
@@ -443,6 +446,12 @@ long bdev_direct_access(struct block_device *bdev, sector_t sector,
 	long avail;
 	const struct block_device_operations *ops = bdev->bd_disk->fops;
 
+	/*
+	 * The device driver is allowed to sleep, in order to make the
+	 * memory directly accessible.
+	 */
+	might_sleep();
+
 	if (size < 0)
 		return size;
 	if (!ops->direct_access)
@@ -1170,6 +1179,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
+		bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0;
 		if (!partno) {
 			ret = -ENXIO;
 			bdev->bd_part = disk_get_part(disk, partno);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 795d754327a7..b823fac91c92 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1748,7 +1748,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	}
 
 	current->backing_dev_info = inode_to_bdi(inode);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err) {
 		mutex_unlock(&inode->i_mutex);
 		goto out;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 8c52472d2efa..aecd0859eacb 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -43,7 +43,6 @@ struct cachefiles_object {
 	loff_t				i_size;		/* object size */
 	unsigned long			flags;
 #define CACHEFILES_OBJECT_ACTIVE	0		/* T if marked active */
-#define CACHEFILES_OBJECT_BURIED	1		/* T if preemptively buried */
 	atomic_t			usage;		/* object usage count */
 	uint8_t				type;		/* object type */
 	uint8_t				new;		/* T if object new */
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ab857ab9f40d..fc1056f5c96a 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -97,7 +97,8 @@ static noinline void cachefiles_printk_object(struct cachefiles_object *object,
  *   call vfs_unlink(), vfs_rmdir() or vfs_rename()
  */
 static void cachefiles_mark_object_buried(struct cachefiles_cache *cache,
-					  struct dentry *dentry)
+					  struct dentry *dentry,
+					  enum fscache_why_object_killed why)
 {
 	struct cachefiles_object *object;
 	struct rb_node *p;
@@ -132,8 +133,9 @@ found_dentry:
 		pr_err("\n");
 		pr_err("Error: Can't preemptively bury live object\n");
 		cachefiles_printk_object(object, NULL);
-	} else if (test_and_set_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
-		pr_err("Error: Object already preemptively buried\n");
+	} else {
+		if (why != FSCACHE_OBJECT_IS_STALE)
+			fscache_object_mark_killed(&object->fscache, why);
 	}
 
 	write_unlock(&cache->active_lock);
@@ -265,7 +267,8 @@ requeue:
 static int cachefiles_bury_object(struct cachefiles_cache *cache,
 				  struct dentry *dir,
 				  struct dentry *rep,
-				  bool preemptive)
+				  bool preemptive,
+				  enum fscache_why_object_killed why)
 {
 	struct dentry *grave, *trap;
 	struct path path, path_to_graveyard;
@@ -289,7 +292,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
 			ret = vfs_unlink(d_inode(dir), rep, NULL);
 
 			if (preemptive)
-				cachefiles_mark_object_buried(cache, rep);
+				cachefiles_mark_object_buried(cache, rep, why);
 		}
 
 		mutex_unlock(&d_inode(dir)->i_mutex);
@@ -394,7 +397,7 @@ try_again:
 					    "Rename failed with error %d", ret);
 
 		if (preemptive)
-			cachefiles_mark_object_buried(cache, rep);
+			cachefiles_mark_object_buried(cache, rep, why);
 	}
 
 	unlock_rename(cache->graveyard, dir);
@@ -422,7 +425,7 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 
 	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
 
-	if (test_bit(CACHEFILES_OBJECT_BURIED, &object->flags)) {
+	if (test_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->fscache.flags)) {
 		/* object allocation for the same key preemptively deleted this
 		 * object's file so that it could create its own file */
 		_debug("object preemptively buried");
@@ -433,7 +436,8 @@ int cachefiles_delete_object(struct cachefiles_cache *cache,
 		 * may have been renamed */
 		if (dir == object->dentry->d_parent) {
 			ret = cachefiles_bury_object(cache, dir,
-						     object->dentry, false);
+						     object->dentry, false,
+						     FSCACHE_OBJECT_WAS_RETIRED);
 		} else {
 			/* it got moved, presumably by cachefilesd culling it,
 			 * so it's no longer in the key path and we can ignore
@@ -522,7 +526,7 @@ lookup_again:
 		if (d_is_negative(next)) {
 			ret = cachefiles_has_space(cache, 1, 0);
 			if (ret < 0)
-				goto create_error;
+				goto no_space_error;
 
 			path.dentry = dir;
 			ret = security_path_mkdir(&path, next, 0);
@@ -551,7 +555,7 @@ lookup_again:
 		if (d_is_negative(next)) {
 			ret = cachefiles_has_space(cache, 1, 0);
 			if (ret < 0)
-				goto create_error;
+				goto no_space_error;
 
 			path.dentry = dir;
 			ret = security_path_mknod(&path, next, S_IFREG, 0);
@@ -602,7 +606,8 @@ lookup_again:
 			 * mutex) */
 			object->dentry = NULL;
 
-			ret = cachefiles_bury_object(cache, dir, next, true);
+			ret = cachefiles_bury_object(cache, dir, next, true,
+						     FSCACHE_OBJECT_IS_STALE);
 			dput(next);
 			next = NULL;
 
@@ -610,6 +615,7 @@ lookup_again:
 				goto delete_error;
 
 			_debug("redo lookup");
+			fscache_object_retrying_stale(&object->fscache);
 			goto lookup_again;
 		}
 	}
@@ -662,6 +668,8 @@ lookup_again:
 	_leave(" = 0 [%lu]", d_backing_inode(object->dentry)->i_ino);
 	return 0;
 
+no_space_error:
+	fscache_object_mark_killed(&object->fscache, FSCACHE_OBJECT_NO_SPACE);
 create_error:
 	_debug("create error %d", ret);
 	if (ret == -EIO)
@@ -927,7 +935,8 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
 	/*  actually remove the victim (drops the dir mutex) */
 	_debug("bury");
 
-	ret = cachefiles_bury_object(cache, dir, victim, false);
+	ret = cachefiles_bury_object(cache, dir, victim, false,
+				     FSCACHE_OBJECT_WAS_CULLED);
 	if (ret < 0)
 		goto error;
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index faf92095e105..8b79d87eaf46 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -962,7 +962,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	pos = iocb->ki_pos;
 	count = iov_iter_count(from);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index d6f7a76a1f5b..f829fe963f5b 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -79,7 +79,7 @@ void coda_sysctl_clean(void);
 
 static inline struct coda_inode_info *ITOC(struct inode *inode)
 {
-	return list_entry(inode, struct coda_inode_info, vfs_inode);
+	return container_of(inode, struct coda_inode_info, vfs_inode);
 }
 
 static __inline__ struct CodaFid *coda_i2f(struct inode *inode)
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 8d89f5fd0331..eae87575e681 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -236,7 +236,7 @@ void configfs_drop_dentry(struct configfs_dirent * sd, struct dentry * parent)
 
 	if (dentry) {
 		spin_lock(&dentry->d_lock);
-		if (!d_unhashed(dentry) && d_really_is_positive(dentry)) {
+		if (simple_positive(dentry)) {
 			dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
diff --git a/fs/coredump.c b/fs/coredump.c
index e52e0064feac..c5ecde6f3eed 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -140,7 +140,7 @@ static int cn_print_exe_file(struct core_name *cn)
 		goto put_exe_file;
 	}
 
-	path = d_path(&exe_file->f_path, pathbuf, PATH_MAX);
+	path = file_path(exe_file, pathbuf, PATH_MAX);
 	if (IS_ERR(path)) {
 		ret = PTR_ERR(path);
 		goto free_buf;
diff --git a/fs/dax.c b/fs/dax.c
index 99b5fbc38992..c3e21ccfc358 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -155,7 +155,7 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 		}
 
 		if (iov_iter_rw(iter) == WRITE)
-			len = copy_from_iter(addr, max - pos, iter);
+			len = copy_from_iter_nocache(addr, max - pos, iter);
 		else if (!hole)
 			len = copy_to_iter(addr, max - pos, iter);
 		else
@@ -209,7 +209,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	}
 
 	/* Protects against truncate */
-	inode_dio_begin(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_begin(inode);
 
 	retval = dax_io(inode, iter, pos, end, get_block, &bh);
 
@@ -219,7 +220,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	if ((retval > 0) && end_io)
 		end_io(iocb, pos, retval, bh.b_private);
 
-	inode_dio_end(inode);
+	if (!(flags & DIO_SKIP_DIO_COUNT))
+		inode_dio_end(inode);
  out:
 	return retval;
 }
diff --git a/fs/dcache.c b/fs/dcache.c
index 910968b4b6bf..7a3f3e5f9cea 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1673,7 +1673,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 				DCACHE_OP_COMPARE	|
 				DCACHE_OP_REVALIDATE	|
 				DCACHE_OP_WEAK_REVALIDATE	|
-				DCACHE_OP_DELETE ));
+				DCACHE_OP_DELETE	|
+				DCACHE_OP_SELECT_INODE));
 	dentry->d_op = op;
 	if (!op)
 		return;
@@ -1689,6 +1690,8 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 		dentry->d_flags |= DCACHE_OP_DELETE;
 	if (op->d_prune)
 		dentry->d_flags |= DCACHE_OP_PRUNE;
+	if (op->d_select_inode)
+		dentry->d_flags |= DCACHE_OP_SELECT_INODE;
 
 }
 EXPORT_SYMBOL(d_set_d_op);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index d6d1cf004123..c711be8d6a3c 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -44,11 +44,6 @@ static struct inode *debugfs_get_inode(struct super_block *sb)
 	return inode;
 }
 
-static inline int debugfs_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 struct debugfs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
@@ -522,7 +517,7 @@ static int __debugfs_remove(struct dentry *dentry, struct dentry *parent)
 {
 	int ret = 0;
 
-	if (debugfs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		dget(dentry);
 		if (d_is_dir(dentry))
 			ret = simple_rmdir(d_inode(parent), dentry);
@@ -602,7 +597,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 	 */
 	spin_lock(&parent->d_lock);
 	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!debugfs_positive(child))
+		if (!simple_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
@@ -623,7 +618,7 @@ void debugfs_remove_recursive(struct dentry *dentry)
 		 * from d_subdirs. When releasing the parent->d_lock we can
 		 * no longer trust that the next pointer is valid.
 		 * Restart the loop. We'll skip this one with the
-		 * debugfs_positive() check.
+		 * simple_positive() check.
 		 */
 		goto loop;
 	}
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 4deb0b05b011..e5bb2abf77f9 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -44,12 +44,6 @@ static inline void exofs_put_page(struct page *page)
 	page_cache_release(page);
 }
 
-/* Accesses dir's inode->i_size must be called under inode lock */
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-}
-
 static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	loff_t last_byte = inode->i_size;
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 796b491e6978..0c6638b40f21 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -70,11 +70,6 @@ static inline void ext2_put_page(struct page *page)
 	page_cache_release(page);
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 /*
  * Return the offset into page `page_nr' of the last valid
  * byte in that page, plus one.
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5c787647afe2..58987b5c514b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -452,7 +452,7 @@ void __ext4_error_file(struct file *file, const char *function,
 	es = EXT4_SB(inode->i_sb)->s_es;
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	if (ext4_error_ratelimit(inode->i_sb)) {
-		path = d_path(&(file->f_path), pathname, sizeof(pathname));
+		path = file_path(file, pathname, sizeof(pathname));
 		if (IS_ERR(path))
 			path = "(unknown)";
 		va_start(args, fmt);
diff --git a/fs/file.c b/fs/file.c
index 93c5f89c248b..6c672ad329e9 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -147,6 +147,13 @@ static int expand_fdtable(struct files_struct *files, int nr)
 
 	spin_unlock(&files->file_lock);
 	new_fdt = alloc_fdtable(nr);
+
+	/* make sure all __fd_install() have seen resize_in_progress
+	 * or have finished their rcu_read_lock_sched() section.
+	 */
+	if (atomic_read(&files->count) > 1)
+		synchronize_sched();
+
 	spin_lock(&files->file_lock);
 	if (!new_fdt)
 		return -ENOMEM;
@@ -158,21 +165,14 @@ static int expand_fdtable(struct files_struct *files, int nr)
 		__free_fdtable(new_fdt);
 		return -EMFILE;
 	}
-	/*
-	 * Check again since another task may have expanded the fd table while
-	 * we dropped the lock
-	 */
 	cur_fdt = files_fdtable(files);
-	if (nr >= cur_fdt->max_fds) {
-		/* Continue as planned */
-		copy_fdtable(new_fdt, cur_fdt);
-		rcu_assign_pointer(files->fdt, new_fdt);
-		if (cur_fdt != &files->fdtab)
-			call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
-	} else {
-		/* Somebody else expanded, so undo our attempt */
-		__free_fdtable(new_fdt);
-	}
+	BUG_ON(nr < cur_fdt->max_fds);
+	copy_fdtable(new_fdt, cur_fdt);
+	rcu_assign_pointer(files->fdt, new_fdt);
+	if (cur_fdt != &files->fdtab)
+		call_rcu(&cur_fdt->rcu, free_fdtable_rcu);
+	/* coupled with smp_rmb() in __fd_install() */
+	smp_wmb();
 	return 1;
 }
 
@@ -185,21 +185,38 @@ static int expand_fdtable(struct files_struct *files, int nr)
  * The files->file_lock should be held on entry, and will be held on exit.
  */
 static int expand_files(struct files_struct *files, int nr)
+	__releases(files->file_lock)
+	__acquires(files->file_lock)
 {
 	struct fdtable *fdt;
+	int expanded = 0;
 
+repeat:
 	fdt = files_fdtable(files);
 
 	/* Do we need to expand? */
 	if (nr < fdt->max_fds)
-		return 0;
+		return expanded;
 
 	/* Can we expand? */
 	if (nr >= sysctl_nr_open)
 		return -EMFILE;