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
  ...

Author: torvalds

Documentation/filesystems/caching/backend-api.txt

@@ -676,6 +676,29 @@ FS-Cache provides some utilities that a cache backend may make use of:
      as possible.
 
 
+ (*) Indicate that a stale object was found and discarded:
+
+	void fscache_object_retrying_stale(struct fscache_object *object);
+
+     This is called to indicate that the lookup procedure found an object in
+     the cache that the netfs decided was stale.  The object has been
+     discarded from the cache and the lookup will be performed again.
+
+
+ (*) Indicate that the caching backend killed an object:
+
+	void fscache_object_mark_killed(struct fscache_object *object,
+					enum fscache_why_object_killed why);
+
+     This is called to indicate that the cache backend preemptively killed an
+     object.  The why parameter should be set to indicate the reason:
+
+	FSCACHE_OBJECT_IS_STALE - the object was stale and needs discarding.
+	FSCACHE_OBJECT_NO_SPACE - there was insufficient cache space
+	FSCACHE_OBJECT_WAS_RETIRED - the object was retired when relinquished.
+	FSCACHE_OBJECT_WAS_CULLED - the object was culled to make space.
+
+
  (*) Get and release references on a retrieval record:
 
 	void fscache_get_retrieval(struct fscache_retrieval *op);

Documentation/filesystems/caching/fscache.txt

@@ -284,8 +284,9 @@ proc files.
 		enq=N	Number of times async ops queued for processing
 		can=N	Number of async ops cancelled
 		rej=N	Number of async ops rejected due to object lookup/create failure
+		ini=N	Number of async ops initialised
 		dfr=N	Number of async ops queued for deferred release
-		rel=N	Number of async ops released
+		rel=N	Number of async ops released (should equal ini=N when idle)
 		gc=N	Number of deferred-release async ops garbage collected
 	CacheOp	alo=N	Number of in-progress alloc_object() cache ops
 		luo=N	Number of in-progress lookup_object() cache ops
@@ -303,6 +304,10 @@ proc files.
 		wrp=N	Number of in-progress write_page() cache ops
 		ucp=N	Number of in-progress uncache_page() cache ops
 		dsp=N	Number of in-progress dissociate_pages() cache ops
+	CacheEv	nsp=N	Number of object lookups/creations rejected due to lack of space
+		stl=N	Number of stale objects deleted
+		rtr=N	Number of objects retired when relinquished
+		cul=N	Number of objects culled
 
 
  (*) /proc/fs/fscache/histogram

Documentation/filesystems/dax.txt

@@ -18,8 +18,10 @@ Usage
 -----
 
 If you have a block device which supports DAX, you can make a filesystem
-on it as usual.  When mounting it, use the -o dax option manually
-or add 'dax' to the options in /etc/fstab.
+on it as usual.  The DAX code currently only supports files with a block
+size equal to your kernel's PAGE_SIZE, so you may need to specify a block
+size when creating the filesystem.  When mounting it, use the "-o dax"
+option on the command line or add 'dax' to the options in /etc/fstab.
 
 
 Implementation Tips for Block Driver Writers

Documentation/filesystems/porting

@@ -500,3 +500,7 @@ in your dentry operations instead.
 	dentry,  it does not get nameidata at all and it gets called only when cookie
 	is non-NULL.  Note that link body isn't available anymore, so if you need it,
 	store it as cookie.
+--
+[mandatory]
+	__fd_install() & fd_install() can now sleep. Callers should not
+	hold a spinlock	or other resources that do not allow a schedule.

arch/arc/kernel/troubleshoot.c

@@ -71,15 +71,12 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 	mmput(mm);
 
 	if (exe_file) {
-		path = exe_file->f_path;
-		path_get(&exe_file->f_path);
+		path_nm = file_path(exe_file, buf, 255);
 		fput(exe_file);
-		path_nm = d_path(&path, buf, 255);
-		path_put(&path);
 	}
 
 done:
-	pr_info("Path: %s\n", path_nm);
+	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
 }
 
 static void show_faulting_vma(unsigned long address, char *buf)
@@ -103,8 +100,7 @@ static void show_faulting_vma(unsigned long address, char *buf)
 	if (vma && (vma->vm_start <= address)) {
 		struct file *file = vma->vm_file;
 		if (file) {
-			struct path *path = &file->f_path;
-			nm = d_path(path, buf, PAGE_SIZE - 1);
+			nm = file_path(file, buf, PAGE_SIZE - 1);
 			inode = file_inode(vma->vm_file);
 			dev = inode->i_sb->s_dev;
 			ino = inode->i_ino;

arch/blackfin/kernel/trace.c

@@ -136,7 +136,7 @@ void decode_address(char *buf, unsigned long address)
 				struct file *file = vma->vm_file;
 
 				if (file) {
-					char *d_name = d_path(&file->f_path, _tmpbuf,
+					char *d_name = file_path(file, _tmpbuf,
 						      sizeof(_tmpbuf));
 					if (!IS_ERR(d_name))
 						name = d_name;

arch/powerpc/platforms/cell/spufs/inode.c

@@ -166,7 +166,7 @@ static void spufs_prune_dir(struct dentry *dir)
 	mutex_lock(&d_inode(dir)->i_mutex);
 	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_child) {
 		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);

arch/s390/hypfs/inode.c

@@ -62,18 +62,13 @@ static void hypfs_add_dentry(struct dentry *dentry)
 	hypfs_last_dentry = dentry;
 }
 
-static inline int hypfs_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static void hypfs_remove(struct dentry *dentry)
 {
 	struct dentry *parent;
 
 	parent = dentry->d_parent;
 	mutex_lock(&d_inode(parent)->i_mutex);
-	if (hypfs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		if (d_is_dir(dentry))
 			simple_rmdir(d_inode(parent), dentry);
 		else

arch/tile/kernel/stack.c

@@ -332,7 +332,7 @@ static void describe_addr(struct KBacktraceIterator *kbt,
 	}
 
 	if (vma->vm_file) {
-		p = d_path(&vma->vm_file->f_path, buf, bufsize);
+		p = file_path(vma->vm_file, buf, bufsize);
 		if (IS_ERR(p))
 			p = "?";
 		name = kbasename(p);

arch/tile/mm/elf.c

@@ -56,7 +56,7 @@ static int notify_exec(struct mm_struct *mm)
 	if (exe_file == NULL)
 		goto done_free;
 
-	path = d_path(&exe_file->f_path, buf, PAGE_SIZE);
+	path = file_path(exe_file, buf, PAGE_SIZE);
 	if (IS_ERR(path))
 		goto done_put;
 

drivers/block/drbd/drbd_debugfs.c

@@ -419,14 +419,6 @@ static int in_flight_summary_show(struct seq_file *m, void *pos)
 	return 0;
 }
 
-/* simple_positive(file->f_path.dentry) respectively debugfs_positive(),
- * but neither is "reachable" from here.
- * So we have our own inline version of it above.  :-( */
-static inline int debugfs_positive(struct dentry *dentry)
-{
-        return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 /* make sure at *open* time that the respective object won't go away. */
 static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, void *),
 		                void *data, struct kref *kref,
@@ -444,7 +436,7 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
 	/* serialize with d_delete() */
 	mutex_lock(&d_inode(parent)->i_mutex);
 	/* Make sure the object is still alive */
-	if (debugfs_positive(file->f_path.dentry)
+	if (simple_positive(file->f_path.dentry)
 	&& kref_get_unless_zero(kref))
 		ret = 0;
 	mutex_unlock(&d_inode(parent)->i_mutex);

drivers/block/loop.c

@@ -588,7 +588,7 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
 
 	spin_lock_irq(&lo->lo_lock);
 	if (lo->lo_backing_file)
-		p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
+		p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1);
 	spin_unlock_irq(&lo->lo_lock);
 
 	if (IS_ERR_OR_NULL(p))

drivers/infiniband/hw/ipath/ipath_fs.c

@@ -277,7 +277,7 @@ static int remove_file(struct dentry *parent, char *name)
 	}
 
 	spin_lock(&tmp->d_lock);
-	if (!d_unhashed(tmp) && d_really_is_positive(tmp)) {
+	if (simple_positive(tmp)) {
 		dget_dlock(tmp);
 		__d_drop(tmp);
 		spin_unlock(&tmp->d_lock);

drivers/infiniband/hw/qib/qib_fs.c

@@ -455,7 +455,7 @@ static int remove_file(struct dentry *parent, char *name)
 	}
 
 	spin_lock(&tmp->d_lock);
-	if (!d_unhashed(tmp) && d_really_is_positive(tmp)) {
+	if (simple_positive(tmp)) {
 		__d_drop(tmp);
 		spin_unlock(&tmp->d_lock);
 		simple_unlink(d_inode(parent), tmp);

drivers/md/bitmap.c

@@ -839,7 +839,7 @@ static void bitmap_file_kick(struct bitmap *bitmap)
 		if (bitmap->storage.file) {
 			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			if (path)
-				ptr = d_path(&bitmap->storage.file->f_path,
+				ptr = file_path(bitmap->storage.file,
 					     path, PAGE_SIZE);
 
 			printk(KERN_ALERT
@@ -1927,7 +1927,7 @@ void bitmap_status(struct seq_file *seq, struct bitmap *bitmap)
 		   chunk_kb ? "KB" : "B");
 	if (bitmap->storage.file) {
 		seq_printf(seq, ", file: ");
-		seq_path(seq, &bitmap->storage.file->f_path, " \t\n");
+		seq_file_path(seq, bitmap->storage.file, " \t\n");
 	}
 
 	seq_printf(seq, "\n");

drivers/md/md.c

@@ -5766,7 +5766,7 @@ static int get_bitmap_file(struct mddev *mddev, void __user * arg)
 	/* bitmap disabled, zero the first byte and copy out */
 	if (!mddev->bitmap_info.file)
 		file->pathname[0] = '\0';
-	else if ((ptr = d_path(&mddev->bitmap_info.file->f_path,
+	else if ((ptr = file_path(mddev->bitmap_info.file,
 			       file->pathname, sizeof(file->pathname))),
 		 IS_ERR(ptr))
 		err = PTR_ERR(ptr);

drivers/usb/gadget/function/f_mass_storage.c

@@ -2936,7 +2936,7 @@ int fsg_common_create_lun(struct fsg_common *common, struct fsg_lun_config *cfg,
 	if (fsg_lun_is_open(lun)) {
 		p = "(error)";
 		if (pathbuf) {
-			p = d_path(&lun->filp->f_path, pathbuf, PATH_MAX);
+			p = file_path(lun->filp, pathbuf, PATH_MAX);
 			if (IS_ERR(p))
 				p = "(error)";
 		}

drivers/usb/gadget/function/storage_common.c

@@ -341,7 +341,7 @@ ssize_t fsg_show_file(struct fsg_lun *curlun, struct rw_semaphore *filesem,
 
 	down_read(filesem);
 	if (fsg_lun_is_open(curlun)) {	/* Get the complete pathname */
-		p = d_path(&curlun->filp->f_path, buf, PAGE_SIZE - 1);
+		p = file_path(curlun->filp, buf, PAGE_SIZE - 1);
 		if (IS_ERR(p))
 			rc = PTR_ERR(p);
 		else {

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);
 }
 
 /*

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);

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

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;

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);

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;

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 */