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
  ...

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 */

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;
 

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;
 

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)

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);

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;

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;
 }

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);

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;
 	}

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;

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.

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);

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;
 
+	if (unlikely(files->resize_in_progress)) {
+		spin_unlock(&files->file_lock);
+		expanded = 1;
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		spin_lock(&files->file_lock);
+		goto repeat;
+	}
+
 	/* All good, so we try */
-	return expand_fdtable(files, nr);
+	files->resize_in_progress = true;
+	expanded = expand_fdtable(files, nr);
+	files->resize_in_progress = false;
+
+	wake_up_all(&files->resize_wait);
+	return expanded;
 }
 
 static inline void __set_close_on_exec(int fd, struct fdtable *fdt)
@@ -256,6 +273,8 @@ struct files_struct *dup_fd(struct files_struct *oldf, int *errorp)
 	atomic_set(&newf->count, 1);
 
 	spin_lock_init(&newf->file_lock);
+	newf->resize_in_progress = false;
+	init_waitqueue_head(&newf->resize_wait);
 	newf->next_fd = 0;
 	new_fdt = &newf->fdtab;
 	new_fdt->max_fds = NR_OPEN_DEFAULT;
@@ -553,11 +572,21 @@ void __fd_install(struct files_struct *files, unsigned int fd,
 		struct file *file)
 {
 	struct fdtable *fdt;
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
+
+	might_sleep();
+	rcu_read_lock_sched();
+
+	while (unlikely(files->resize_in_progress)) {
+		rcu_read_unlock_sched();
+		wait_event(files->resize_wait, !files->resize_in_progress);
+		rcu_read_lock_sched();
+	}
+	/* coupled with smp_wmb() in expand_fdtable() */
+	smp_rmb();
+	fdt = rcu_dereference_sched(files->fdt);
 	BUG_ON(fdt->fd[fd] != NULL);
 	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
+	rcu_read_unlock_sched();
 }
 
 void fd_install(unsigned int fd, struct file *file)
@@ -635,11 +664,17 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
 	struct file *file;
 
 	rcu_read_lock();
+loop:
 	file = fcheck_files(files, fd);
 	if (file) {
-		/* File object ref couldn't be taken */
-		if ((file->f_mode & mask) || !get_file_rcu(file))
+		/* File object ref couldn't be taken.
+		 * dup2() atomicity guarantee is the reason
+		 * we loop to catch the new file (or NULL pointer)
+		 */
+		if (file->f_mode & mask)
 			file = NULL;
+		else if (!get_file_rcu(file))
+			goto loop;
 	}
 	rcu_read_unlock();
 

fs/file_table.c

@@ -20,7 +20,6 @@
 #include <linux/cdev.h>
 #include <linux/fsnotify.h>
 #include <linux/sysctl.h>
-#include <linux/lglock.h>
 #include <linux/percpu_counter.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>

fs/freevxfs/vxfs_lookup.c

@@ -61,13 +61,6 @@ const struct file_operations vxfs_dir_operations = {
 	.iterate =		vxfs_readdir,
 };
 
- 
-static inline u_long
-dir_pages(struct inode *inode)
-{
-	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-}
- 
 static inline u_long
 dir_blocks(struct inode *ip)
 {

fs/fscache/cookie.c

@@ -327,7 +327,8 @@ static int fscache_alloc_object(struct fscache_cache *cache,
 
 object_already_extant:
 	ret = -ENOBUFS;
-	if (fscache_object_is_dead(object)) {
+	if (fscache_object_is_dying(object) ||
+	    fscache_cache_is_broken(object)) {
 		spin_unlock(&cookie->lock);
 		goto error;
 	}
@@ -671,7 +672,7 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 	if (!op)
 		return -ENOMEM;
 
-	fscache_operation_init(op, NULL, NULL);
+	fscache_operation_init(op, NULL, NULL, NULL);
 	op->flags = FSCACHE_OP_MYTHREAD |
 		(1 << FSCACHE_OP_WAITING) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -695,8 +696,7 @@ int __fscache_check_consistency(struct fscache_cookie *cookie)
 	/* the work queue now carries its own ref on the object */
 	spin_unlock(&cookie->lock);
 
-	ret = fscache_wait_for_operation_activation(object, op,
-						    NULL, NULL, NULL);
+	ret = fscache_wait_for_operation_activation(object, op, NULL, NULL);
 	if (ret == 0) {
 		/* ask the cache to honour the operation */
 		ret = object->cache->ops->check_consistency(op);

fs/fscache/internal.h

@@ -124,8 +124,7 @@ extern int fscache_submit_exclusive_op(struct fscache_object *,
 				       struct fscache_operation *);
 extern int fscache_submit_op(struct fscache_object *,
 			     struct fscache_operation *);
-extern int fscache_cancel_op(struct fscache_operation *,
-			     void (*)(struct fscache_operation *));
+extern int fscache_cancel_op(struct fscache_operation *, bool);
 extern void fscache_cancel_all_ops(struct fscache_object *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
@@ -138,8 +137,7 @@ extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *);
 extern int fscache_wait_for_operation_activation(struct fscache_object *,
 						 struct fscache_operation *,
 						 atomic_t *,
-						 atomic_t *,
-						 void (*)(struct fscache_operation *));
+						 atomic_t *);
 extern void fscache_invalidate_writes(struct fscache_cookie *);
 
 /*
@@ -164,6 +162,7 @@ extern atomic_t fscache_n_op_pend;
 extern atomic_t fscache_n_op_run;
 extern atomic_t fscache_n_op_enqueue;
 extern atomic_t fscache_n_op_deferred_release;
+extern atomic_t fscache_n_op_initialised;
 extern atomic_t fscache_n_op_release;
 extern atomic_t fscache_n_op_gc;
 extern atomic_t fscache_n_op_cancelled;
@@ -271,6 +270,11 @@ extern atomic_t fscache_n_cop_write_page;
 extern atomic_t fscache_n_cop_uncache_page;
 extern atomic_t fscache_n_cop_dissociate_pages;
 
+extern atomic_t fscache_n_cache_no_space_reject;
+extern atomic_t fscache_n_cache_stale_objects;
+extern atomic_t fscache_n_cache_retired_objects;
+extern atomic_t fscache_n_cache_culled_objects;
+
 static inline void fscache_stat(atomic_t *stat)
 {
 	atomic_inc(stat);

fs/fscache/object.c

@@ -327,6 +327,17 @@ void fscache_object_init(struct fscache_object *object,
 }
 EXPORT_SYMBOL(fscache_object_init);
 
+/*
+ * Mark the object as no longer being live, making sure that we synchronise
+ * against op submission.
+ */
+static inline void fscache_mark_object_dead(struct fscache_object *object)
+{
+	spin_lock(&object->lock);
+	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	spin_unlock(&object->lock);
+}
+
 /*
  * Abort object initialisation before we start it.
  */
@@ -610,6 +621,8 @@ static const struct fscache_state *fscache_lookup_failure(struct fscache_object
 	object->cache->ops->lookup_complete(object);
 	fscache_stat_d(&fscache_n_cop_lookup_complete);
 
+	set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags);
+
 	cookie = object->cookie;
 	set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
 	if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags))
@@ -629,7 +642,7 @@ static const struct fscache_state *fscache_kill_object(struct fscache_object *ob
 	_enter("{OBJ%x,%d,%d},%d",
 	       object->debug_id, object->n_ops, object->n_children, event);
 
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	object->oob_event_mask = 0;
 
 	if (list_empty(&object->dependents) &&
@@ -948,7 +961,8 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj
 	if (!op)
 		goto nomem;
 
-	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
+	fscache_operation_init(op, object->cache->ops->invalidate_object,
+			       NULL, NULL);
 	op->flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_EXCLUSIVE) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -974,13 +988,13 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj
 	return transit_to(UPDATE_OBJECT);
 
 nomem:
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	fscache_unuse_cookie(object);
 	_leave(" [ENOMEM]");
 	return transit_to(KILL_OBJECT);
 
 submit_op_failed:
-	clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags);
+	fscache_mark_object_dead(object);
 	spin_unlock(&cookie->lock);
 	fscache_unuse_cookie(object);
 	kfree(op);
@@ -1016,3 +1030,50 @@ static const struct fscache_state *fscache_update_object(struct fscache_object *
 	_leave("");
 	return transit_to(WAIT_FOR_CMD);
 }
+
+/**
+ * fscache_object_retrying_stale - Note retrying stale object
+ * @object: The object that will be retried
+ *
+ * Note that an object lookup found an on-disk object that was adjudged to be
+ * stale and has been deleted.  The lookup will be retried.
+ */
+void fscache_object_retrying_stale(struct fscache_object *object)
+{
+	fscache_stat(&fscache_n_cache_no_space_reject);
+}
+EXPORT_SYMBOL(fscache_object_retrying_stale);
+
+/**
+ * fscache_object_mark_killed - Note that an object was killed
+ * @object: The object that was culled
+ * @why: The reason the object was killed.
+ *
+ * Note that an object was killed.  Returns true if the object was
+ * already marked killed, false if it wasn't.
+ */
+void fscache_object_mark_killed(struct fscache_object *object,
+				enum fscache_why_object_killed why)
+{
+	if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) {
+		pr_err("Error: Object already killed by cache [%s]\n",
+		       object->cache->identifier);
+		return;
+	}
+
+	switch (why) {
+	case FSCACHE_OBJECT_NO_SPACE:
+		fscache_stat(&fscache_n_cache_no_space_reject);
+		break;
+	case FSCACHE_OBJECT_IS_STALE:
+		fscache_stat(&fscache_n_cache_stale_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_RETIRED:
+		fscache_stat(&fscache_n_cache_retired_objects);
+		break;
+	case FSCACHE_OBJECT_WAS_CULLED:
+		fscache_stat(&fscache_n_cache_culled_objects);
+		break;
+	}
+}
+EXPORT_SYMBOL(fscache_object_mark_killed);

fs/fscache/operation.c

@@ -20,6 +20,35 @@
 atomic_t fscache_op_debug_id;
 EXPORT_SYMBOL(fscache_op_debug_id);
 
+static void fscache_operation_dummy_cancel(struct fscache_operation *op)
+{
+}
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object and processor if needed.
+ */
+void fscache_operation_init(struct fscache_operation *op,
+			    fscache_operation_processor_t processor,
+			    fscache_operation_cancel_t cancel,
+			    fscache_operation_release_t release)
+{
+	INIT_WORK(&op->work, fscache_op_work_func);
+	atomic_set(&op->usage, 1);
+	op->state = FSCACHE_OP_ST_INITIALISED;
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->processor = processor;
+	op->cancel = cancel ?: fscache_operation_dummy_cancel;
+	op->release = release;
+	INIT_LIST_HEAD(&op->pend_link);
+	fscache_stat(&fscache_n_op_initialised);
+}
+EXPORT_SYMBOL(fscache_operation_init);
+
 /**
  * fscache_enqueue_operation - Enqueue an operation for processing
  * @op: The operation to enqueue
@@ -75,6 +104,43 @@ static void fscache_run_op(struct fscache_object *object,
 	fscache_stat(&fscache_n_op_run);
 }
 
+/*
+ * report an unexpected submission
+ */
+static void fscache_report_unexpected_submission(struct fscache_object *object,
+						 struct fscache_operation *op,
+						 const struct fscache_state *ostate)
+{
+	static bool once_only;
+	struct fscache_operation *p;
+	unsigned n;
+
+	if (once_only)
+		return;
+	once_only = true;
+
+	kdebug("unexpected submission OP%x [OBJ%x %s]",
+	       op->debug_id, object->debug_id, object->state->name);
+	kdebug("objstate=%s [%s]", object->state->name, ostate->name);
+	kdebug("objflags=%lx", object->flags);
+	kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
+	kdebug("ops=%u inp=%u exc=%u",
+	       object->n_ops, object->n_in_progress, object->n_exclusive);
+
+	if (!list_empty(&object->pending_ops)) {
+		n = 0;
+		list_for_each_entry(p, &object->pending_ops, pend_link) {
+			ASSERTCMP(p->object, ==, object);
+			kdebug("%p %p", op->processor, op->release);
+			n++;
+		}
+
+		kdebug("n=%u", n);
+	}
+
+	dump_stack();
+}
+
 /*
  * submit an exclusive operation for an object
  * - other ops are excluded from running simultaneously with this one
@@ -83,6 +149,8 @@ static void fscache_run_op(struct fscache_object *object,
 int fscache_submit_exclusive_op(struct fscache_object *object,
 				struct fscache_operation *op)
 {
+	const struct fscache_state *ostate;
+	unsigned long flags;
 	int ret;
 
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
@@ -95,8 +163,21 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
 	ASSERT(list_empty(&op->pend_link));
 
+	ostate = object->state;
+	smp_rmb();
+
 	op->state = FSCACHE_OP_ST_PENDING;
-	if (fscache_object_is_active(object)) {
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
 		op->object = object;
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
@@ -118,7 +199,7 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		/* need to issue a new write op after this */
 		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 		ret = 0;
-	} else if (test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
 		op->object = object;
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
@@ -126,55 +207,21 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
 	} else {
-		/* If we're in any other state, there must have been an I/O
-		 * error of some nature.
-		 */
-		ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
-		ret = -EIO;
+		fscache_report_unexpected_submission(object, op, ostate);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
 	}
 
 	spin_unlock(&object->lock);
 	return ret;
 }
 
-/*
- * report an unexpected submission
- */
-static void fscache_report_unexpected_submission(struct fscache_object *object,
-						 struct fscache_operation *op,
-						 const struct fscache_state *ostate)
-{
-	static bool once_only;
-	struct fscache_operation *p;
-	unsigned n;
-
-	if (once_only)
-		return;
-	once_only = true;
-
-	kdebug("unexpected submission OP%x [OBJ%x %s]",
-	       op->debug_id, object->debug_id, object->state->name);
-	kdebug("objstate=%s [%s]", object->state->name, ostate->name);
-	kdebug("objflags=%lx", object->flags);
-	kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
-	kdebug("ops=%u inp=%u exc=%u",
-	       object->n_ops, object->n_in_progress, object->n_exclusive);
-
-	if (!list_empty(&object->pending_ops)) {
-		n = 0;
-		list_for_each_entry(p, &object->pending_ops, pend_link) {
-			ASSERTCMP(p->object, ==, object);
-			kdebug("%p %p", op->processor, op->release);
-			n++;
-		}
-
-		kdebug("n=%u", n);
-	}
-
-	dump_stack();
-}
-
 /*
  * submit an operation for an object
  * - objects may be submitted only in the following states:
@@ -187,6 +234,7 @@ int fscache_submit_op(struct fscache_object *object,
 		      struct fscache_operation *op)
 {
 	const struct fscache_state *ostate;
+	unsigned long flags;
 	int ret;
 
 	_enter("{OBJ%x OP%x},{%u}",
@@ -204,7 +252,17 @@ int fscache_submit_op(struct fscache_object *object,
 	smp_rmb();
 
 	op->state = FSCACHE_OP_ST_PENDING;
-	if (fscache_object_is_active(object)) {
+	flags = READ_ONCE(object->flags);
+	if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) {
+		fscache_stat(&fscache_n_op_rejected);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -ENOBUFS;
+	} else if (unlikely(fscache_cache_is_broken(object))) {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		ret = -EIO;
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) {
 		op->object = object;
 		object->n_ops++;
 
@@ -222,23 +280,21 @@ int fscache_submit_op(struct fscache_object *object,
 			fscache_run_op(object, op);
 		}
 		ret = 0;
-	} else if (test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) {
+	} else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) {
 		op->object = object;
 		object->n_ops++;
 		atomic_inc(&op->usage);
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
-	} else if (fscache_object_is_dying(object)) {
-		fscache_stat(&fscache_n_op_rejected);
+	} else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) {
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
-	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+	} else {
 		fscache_report_unexpected_submission(object, op, ostate);
 		ASSERT(!fscache_object_is_active(object));
-		op->state = FSCACHE_OP_ST_CANCELLED;
-		ret = -ENOBUFS;
-	} else {
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	}
@@ -293,9 +349,10 @@ void fscache_start_operations(struct fscache_object *object)
  * cancel an operation that's pending on an object
  */
 int fscache_cancel_op(struct fscache_operation *op,
-		      void (*do_cancel)(struct fscache_operation *))
+		      bool cancel_in_progress_op)
 {
 	struct fscache_object *object = op->object;
+	bool put = false;
 	int ret;
 
 	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
@@ -309,19 +366,37 @@ int fscache_cancel_op(struct fscache_operation *op,
 	ret = -EBUSY;
 	if (op->state == FSCACHE_OP_ST_PENDING) {
 		ASSERT(!list_empty(&op->pend_link));
-		fscache_stat(&fscache_n_op_cancelled);
 		list_del_init(&op->pend_link);
-		if (do_cancel)
-			do_cancel(op);
+		put = true;
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		ret = 0;
+	} else if (op->state == FSCACHE_OP_ST_IN_PROGRESS && cancel_in_progress_op) {
+		ASSERTCMP(object->n_in_progress, >, 0);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		fscache_stat(&fscache_n_op_cancelled);
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 			object->n_exclusive--;
 		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
-		fscache_put_operation(op);
 		ret = 0;
 	}
 
+	if (put)
+		fscache_put_operation(op);
 	spin_unlock(&object->lock);
 	_leave(" = %d", ret);
 	return ret;
@@ -345,6 +420,7 @@ void fscache_cancel_all_ops(struct fscache_object *object)
 		list_del_init(&op->pend_link);
 
 		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->cancel(op);
 		op->state = FSCACHE_OP_ST_CANCELLED;
 
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
@@ -377,8 +453,12 @@ void fscache_op_complete(struct fscache_operation *op, bool cancelled)
 
 	spin_lock(&object->lock);
 
-	op->state = cancelled ?
-		FSCACHE_OP_ST_CANCELLED : FSCACHE_OP_ST_COMPLETE;
+	if (!cancelled) {
+		op->state = FSCACHE_OP_ST_COMPLETE;
+	} else {
+		op->cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+	}
 
 	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 		object->n_exclusive--;
@@ -409,9 +489,9 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 
 	_debug("PUT OP");
-	ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_INITIALISED &&
+		    op->state != FSCACHE_OP_ST_COMPLETE,
 		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
-	op->state = FSCACHE_OP_ST_DEAD;
 
 	fscache_stat(&fscache_n_op_release);
 
@@ -419,37 +499,39 @@ void fscache_put_operation(struct fscache_operation *op)
 		op->release(op);
 		op->release = NULL;
 	}
+	op->state = FSCACHE_OP_ST_DEAD;
 
 	object = op->object;
+	if (likely(object)) {
+		if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
+			atomic_dec(&object->n_reads);
+		if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags))
+			fscache_unuse_cookie(object);
+
+		/* now... we may get called with the object spinlock held, so we
+		 * complete the cleanup here only if we can immediately acquire the
+		 * lock, and defer it otherwise */
+		if (!spin_trylock(&object->lock)) {
+			_debug("defer put");
+			fscache_stat(&fscache_n_op_deferred_release);
+
+			cache = object->cache;
+			spin_lock(&cache->op_gc_list_lock);
+			list_add_tail(&op->pend_link, &cache->op_gc_list);
+			spin_unlock(&cache->op_gc_list_lock);
+			schedule_work(&cache->op_gc);
+			_leave(" [defer]");
+			return;
+		}
 
-	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
-		atomic_dec(&object->n_reads);
-	if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags))
-		fscache_unuse_cookie(object);
-
-	/* now... we may get called with the object spinlock held, so we
-	 * complete the cleanup here only if we can immediately acquire the
-	 * lock, and defer it otherwise */
-	if (!spin_trylock(&object->lock)) {
-		_debug("defer put");
-		fscache_stat(&fscache_n_op_deferred_release);
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
 
-		cache = object->cache;
-		spin_lock(&cache->op_gc_list_lock);
-		list_add_tail(&op->pend_link, &cache->op_gc_list);
-		spin_unlock(&cache->op_gc_list_lock);
-		schedule_work(&cache->op_gc);
-		_leave(" [defer]");
-		return;
+		spin_unlock(&object->lock);
 	}
 
-	ASSERTCMP(object->n_ops, >, 0);
-	object->n_ops--;
-	if (object->n_ops == 0)
-		fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
-
-	spin_unlock(&object->lock);
-
 	kfree(op);
 	_leave(" [done]");
 }

fs/fscache/page.c

@@ -213,7 +213,7 @@ int __fscache_attr_changed(struct fscache_cookie *cookie)
 		return -ENOMEM;
 	}
 
-	fscache_operation_init(op, fscache_attr_changed_op, NULL);
+	fscache_operation_init(op, fscache_attr_changed_op, NULL, NULL);
 	op->flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_EXCLUSIVE) |
 		(1 << FSCACHE_OP_UNUSE_COOKIE);
@@ -239,7 +239,7 @@ nobufs_dec:
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_operation(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_attr_changed_nobufs);
@@ -248,6 +248,17 @@ nobufs:
 }
 EXPORT_SYMBOL(__fscache_attr_changed);
 
+/*
+ * Handle cancellation of a pending retrieval op
+ */
+static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	atomic_set(&op->n_pages, 0);
+}
+
 /*
  * release a retrieval op reference
  */
@@ -258,11 +269,12 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op)
 
 	_enter("{OP%x}", op->op.debug_id);
 
-	ASSERTCMP(atomic_read(&op->n_pages), ==, 0);
+	ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED,
+		    atomic_read(&op->n_pages), ==, 0);
 
 	fscache_hist(fscache_retrieval_histogram, op->start_time);
 	if (op->context)
-		fscache_put_context(op->op.object->cookie, op->context);
+		fscache_put_context(op->cookie, op->context);
 
 	_leave("");
 }
@@ -285,15 +297,24 @@ static struct fscache_retrieval *fscache_alloc_retrieval(
 		return NULL;
 	}
 
-	fscache_operation_init(&op->op, NULL, fscache_release_retrieval_op);
+	fscache_operation_init(&op->op, NULL,
+			       fscache_do_cancel_retrieval,
+			       fscache_release_retrieval_op);
 	op->op.flags	= FSCACHE_OP_MYTHREAD |
 		(1UL << FSCACHE_OP_WAITING) |
 		(1UL << FSCACHE_OP_UNUSE_COOKIE);
+	op->cookie	= cookie;
 	op->mapping	= mapping;
 	op->end_io_func	= end_io_func;
 	op->context	= context;
 	op->start_time	= jiffies;
 	INIT_LIST_HEAD(&op->to_do);
+
+	/* Pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure.
+	 */
+	if (context)
+		fscache_get_context(op->cookie, context);
 	return op;
 }
 
@@ -329,25 +350,13 @@ int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 	return 0;
 }
 
-/*
- * Handle cancellation of a pending retrieval op
- */
-static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
-{
-	struct fscache_retrieval *op =
-		container_of(_op, struct fscache_retrieval, op);
-
-	atomic_set(&op->n_pages, 0);
-}
-
 /*
  * wait for an object to become active (or dead)
  */
 int fscache_wait_for_operation_activation(struct fscache_object *object,
 					  struct fscache_operation *op,
 					  atomic_t *stat_op_waits,
-					  atomic_t *stat_object_dead,
-					  void (*do_cancel)(struct fscache_operation *))
+					  atomic_t *stat_object_dead)
 {
 	int ret;
 
@@ -359,7 +368,7 @@ int fscache_wait_for_operation_activation(struct fscache_object *object,
 		fscache_stat(stat_op_waits);
 	if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
 			TASK_INTERRUPTIBLE) != 0) {
-		ret = fscache_cancel_op(op, do_cancel);
+		ret = fscache_cancel_op(op, false);
 		if (ret == 0)
 			return -ERESTARTSYS;
 
@@ -377,11 +386,13 @@ check_if_dead:
 		_leave(" = -ENOBUFS [cancelled]");
 		return -ENOBUFS;
 	}
-	if (unlikely(fscache_object_is_dead(object))) {
-		pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->state);
-		fscache_cancel_op(op, do_cancel);
+	if (unlikely(fscache_object_is_dying(object) ||
+		     fscache_cache_is_broken(object))) {
+		enum fscache_operation_state state = op->state;
+		fscache_cancel_op(op, true);
 		if (stat_object_dead)
 			fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [obj dead %d]", state);
 		return -ENOBUFS;
 	}
 	return 0;
@@ -453,17 +464,12 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_retrieval_ops);
 
-	/* pin the netfs read context in case we need to do the actual netfs
-	 * read because we've encountered a cache read failure */
-	fscache_get_context(object->cookie, op->context);
-
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_retrievals_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -503,7 +509,7 @@ nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
-	kfree(op);
+	fscache_put_retrieval(op);
 nobufs:
 	fscache_stat(&fscache_n_retrievals_nobufs);
 	_leave(" = -ENOBUFS");
@@ -584,17 +590,12 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_retrieval_ops);
 
-	/* pin the netfs read context in case we need to do the actual netfs
-	 * read because we've encountered a cache read failure */
-	fscache_get_context(object->cookie, op->context);
-
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_retrievals_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -632,7 +633,7 @@ nobufs_unlock_dec:
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_retrieval(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 nobufs:
@@ -700,8 +701,7 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	ret = fscache_wait_for_operation_activation(
 		object, &op->op,
 		__fscache_stat(&fscache_n_alloc_op_waits),
-		__fscache_stat(&fscache_n_allocs_object_dead),
-		fscache_do_cancel_retrieval);
+		__fscache_stat(&fscache_n_allocs_object_dead));
 	if (ret < 0)
 		goto error;
 
@@ -726,7 +726,7 @@ nobufs_unlock_dec:
 	wake_cookie = __fscache_unuse_cookie(cookie);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
-	kfree(op);
+	fscache_put_retrieval(op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 nobufs:
@@ -944,7 +944,7 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 	if (!op)
 		goto nomem;
 
-	fscache_operation_init(&op->op, fscache_write_op,
+	fscache_operation_init(&op->op, fscache_write_op, NULL,
 			       fscache_release_write_op);
 	op->op.flags = FSCACHE_OP_ASYNC |
 		(1 << FSCACHE_OP_WAITING) |
@@ -1016,7 +1016,7 @@ already_pending:
 	spin_unlock(&object->lock);
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
-	kfree(op);
+	fscache_put_operation(&op->op);
 	fscache_stat(&fscache_n_stores_ok);
 	_leave(" = 0");
 	return 0;
@@ -1036,7 +1036,7 @@ nobufs_unlock_obj:
 nobufs:
 	spin_unlock(&cookie->lock);
 	radix_tree_preload_end();
-	kfree(op);
+	fscache_put_operation(&op->op);
 	if (wake_cookie)
 		__fscache_wake_unused_cookie(cookie);
 	fscache_stat(&fscache_n_stores_nobufs);
@@ -1044,7 +1044,7 @@ nobufs:
 	return -ENOBUFS;
 
 nomem_free:
-	kfree(op);
+	fscache_put_operation(&op->op);
 nomem:
 	fscache_stat(&fscache_n_stores_oom);
 	_leave(" = -ENOMEM");

fs/fscache/stats.c

@@ -23,6 +23,7 @@ atomic_t fscache_n_op_run;
 atomic_t fscache_n_op_enqueue;
 atomic_t fscache_n_op_requeue;
 atomic_t fscache_n_op_deferred_release;
+atomic_t fscache_n_op_initialised;
 atomic_t fscache_n_op_release;
 atomic_t fscache_n_op_gc;
 atomic_t fscache_n_op_cancelled;
@@ -130,6 +131,11 @@ atomic_t fscache_n_cop_write_page;
 atomic_t fscache_n_cop_uncache_page;
 atomic_t fscache_n_cop_dissociate_pages;
 
+atomic_t fscache_n_cache_no_space_reject;
+atomic_t fscache_n_cache_stale_objects;
+atomic_t fscache_n_cache_retired_objects;
+atomic_t fscache_n_cache_culled_objects;
+
 /*
  * display the general statistics
  */
@@ -246,7 +252,8 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_op_enqueue),
 		   atomic_read(&fscache_n_op_cancelled),
 		   atomic_read(&fscache_n_op_rejected));
-	seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
+	seq_printf(m, "Ops    : ini=%u dfr=%u rel=%u gc=%u\n",
+		   atomic_read(&fscache_n_op_initialised),
 		   atomic_read(&fscache_n_op_deferred_release),
 		   atomic_read(&fscache_n_op_release),
 		   atomic_read(&fscache_n_op_gc));
@@ -271,6 +278,11 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_cop_write_page),
 		   atomic_read(&fscache_n_cop_uncache_page),
 		   atomic_read(&fscache_n_cop_dissociate_pages));
+	seq_printf(m, "CacheEv: nsp=%d stl=%d rtr=%d cul=%d\n",
+		   atomic_read(&fscache_n_cache_no_space_reject),
+		   atomic_read(&fscache_n_cache_stale_objects),
+		   atomic_read(&fscache_n_cache_retired_objects),
+		   atomic_read(&fscache_n_cache_culled_objects));
 	return 0;
 }
 

fs/fuse/file.c

@@ -1169,7 +1169,7 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (err <= 0)
 		goto out;
 
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 

fs/hfs/hfs_fs.h

@@ -252,7 +252,7 @@ extern void hfs_mark_mdb_dirty(struct super_block *sb);
 #define __hfs_u_to_mtime(sec)	cpu_to_be32(sec + 2082844800U - sys_tz.tz_minuteswest * 60)
 #define __hfs_m_to_utime(sec)	(be32_to_cpu(sec) - 2082844800U  + sys_tz.tz_minuteswest * 60)
 
-#define HFS_I(inode)	(list_entry(inode, struct hfs_inode_info, vfs_inode))
+#define HFS_I(inode)	(container_of(inode, struct hfs_inode_info, vfs_inode))
 #define HFS_SB(sb)	((struct hfs_sb_info *)(sb)->s_fs_info)
 
 #define hfs_m_to_utime(time)	(struct timespec){ .tv_sec = __hfs_m_to_utime(time) }

fs/hfsplus/hfsplus_fs.h

@@ -263,7 +263,7 @@ struct hfsplus_inode_info {
 
 static inline struct hfsplus_inode_info *HFSPLUS_I(struct inode *inode)
 {
-	return list_entry(inode, struct hfsplus_inode_info, vfs_inode);
+	return container_of(inode, struct hfsplus_inode_info, vfs_inode);
 }
 
 /*

fs/hpfs/hpfs_fn.h

@@ -304,7 +304,7 @@ extern const struct address_space_operations hpfs_symlink_aops;
 
 static inline struct hpfs_inode_info *hpfs_i(struct inode *inode)
 {
-	return list_entry(inode, struct hpfs_inode_info, vfs_inode);
+	return container_of(inode, struct hpfs_inode_info, vfs_inode);
 }
 
 static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb)

fs/inode.c

@@ -841,7 +841,11 @@ unsigned int get_next_ino(void)
 	}
 #endif
 
-	*p = ++res;
+	res++;
+	/* get_next_ino should not provide a 0 inode number */
+	if (unlikely(!res))
+		res++;
+	*p = res;
 	put_cpu_var(last_ino);
 	return res;
 }
@@ -1674,7 +1678,31 @@ int should_remove_suid(struct dentry *dentry)
 }
 EXPORT_SYMBOL(should_remove_suid);
 
-static int __remove_suid(struct dentry *dentry, int kill)
+/*
+ * Return mask of changes for notify_change() that need to be done as a
+ * response to write or truncate. Return 0 if nothing has to be changed.
+ * Negative value on error (change should be denied).
+ */
+int dentry_needs_remove_privs(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	int mask = 0;
+	int ret;
+
+	if (IS_NOSEC(inode))
+		return 0;
+
+	mask = should_remove_suid(dentry);
+	ret = security_inode_need_killpriv(dentry);
+	if (ret < 0)
+		return ret;
+	if (ret)
+		mask |= ATTR_KILL_PRIV;
+	return mask;
+}
+EXPORT_SYMBOL(dentry_needs_remove_privs);
+
+static int __remove_privs(struct dentry *dentry, int kill)
 {
 	struct iattr newattrs;
 
@@ -1686,33 +1714,32 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	return notify_change(dentry, &newattrs, NULL);
 }
 
-int file_remove_suid(struct file *file)
+/*
+ * Remove special file priviledges (suid, capabilities) when file is written
+ * to or truncated.
+ */
+int file_remove_privs(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
-	int killsuid;
-	int killpriv;
+	int kill;
 	int error = 0;
 
 	/* Fast path for nothing security related */
 	if (IS_NOSEC(inode))
 		return 0;
 
-	killsuid = should_remove_suid(dentry);
-	killpriv = security_inode_need_killpriv(dentry);
-
-	if (killpriv < 0)
-		return killpriv;
-	if (killpriv)
-		error = security_inode_killpriv(dentry);
-	if (!error && killsuid)
-		error = __remove_suid(dentry, killsuid);
-	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
-		inode->i_flags |= S_NOSEC;
+	kill = file_needs_remove_privs(file);
+	if (kill < 0)
+		return kill;
+	if (kill)
+		error = __remove_privs(dentry, kill);
+	if (!error)
+		inode_has_no_xattr(inode);
 
 	return error;
 }
-EXPORT_SYMBOL(file_remove_suid);
+EXPORT_SYMBOL(file_remove_privs);
 
 /**
  *	file_update_time	-	update mtime and ctime time
@@ -1967,9 +1994,8 @@ EXPORT_SYMBOL(inode_dio_wait);
  * inode is being instantiated).  The reason for the cmpxchg() loop
  * --- which wouldn't be necessary if all code paths which modify
  * i_flags actually followed this rule, is that there is at least one
- * code path which doesn't today --- for example,
- * __generic_file_aio_write() calls file_remove_suid() without holding
- * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ * code path which doesn't today so we use cmpxchg() out of an abundance
+ * of caution.
  *
  * In the long run, i_mutex is overkill, and we should probably look
  * at using the i_lock spinlock to protect i_flags, and then make sure

fs/internal.h

@@ -107,6 +107,7 @@ extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 extern long do_handle_open(int mountdirfd,
 			   struct file_handle __user *ufh, int open_flag);
 extern int open_check_o_direct(struct file *f);
+extern int vfs_open(const struct path *, struct file *, const struct cred *);
 
 /*
  * inode.c

fs/jffs2/os-linux.h

@@ -19,7 +19,7 @@
 struct kstatfs;
 struct kvec;
 
-#define JFFS2_INODE_INFO(i) (list_entry(i, struct jffs2_inode_info, vfs_inode))
+#define JFFS2_INODE_INFO(i) (container_of(i, struct jffs2_inode_info, vfs_inode))
 #define OFNI_EDONI_2SFFJ(f)  (&(f)->vfs_inode)
 #define JFFS2_SB_INFO(sb) (sb->s_fs_info)
 #define OFNI_BS_2SFFJ(c)  ((struct super_block *)c->os_priv)

fs/jfs/jfs_incore.h

@@ -206,7 +206,7 @@ struct jfs_sb_info {
 
 static inline struct jfs_inode_info *JFS_IP(struct inode *inode)
 {
-	return list_entry(inode, struct jfs_inode_info, vfs_inode);
+	return container_of(inode, struct jfs_inode_info, vfs_inode);
 }
 
 static inline int jfs_dirtable_inline(struct inode *inode)

fs/libfs.c

@@ -20,11 +20,6 @@
 
 #include "internal.h"
 
-static inline int simple_positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		   struct kstat *stat)
 {

fs/minix/dir.c

@@ -45,11 +45,6 @@ minix_last_byte(struct inode *inode, unsigned long page_nr)
 	return last_byte;
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;

fs/minix/minix.h

@@ -84,7 +84,7 @@ static inline struct minix_sb_info *minix_sb(struct super_block *sb)
 
 static inline struct minix_inode_info *minix_i(struct inode *inode)
 {
-	return list_entry(inode, struct minix_inode_info, vfs_inode);
+	return container_of(inode, struct minix_inode_info, vfs_inode);
 }
 
 static inline unsigned minix_blocks_needed(unsigned bits, unsigned blocksize)

fs/namei.c

@@ -792,7 +792,7 @@ static void set_root(struct nameidata *nd)
 	get_fs_root(current->fs, &nd->root);
 }
 
-static unsigned set_root_rcu(struct nameidata *nd)
+static void set_root_rcu(struct nameidata *nd)
 {
 	struct fs_struct *fs = current->fs;
 	unsigned seq;
@@ -802,7 +802,6 @@ static unsigned set_root_rcu(struct nameidata *nd)
 		nd->root = fs->root;
 		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
 	} while (read_seqcount_retry(&fs->seq, seq));
-	return nd->root_seq;
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -1998,7 +1997,8 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	if (*s == '/') {
 		if (flags & LOOKUP_RCU) {
 			rcu_read_lock();
-			nd->seq = set_root_rcu(nd);
+			set_root_rcu(nd);
+			nd->seq = nd->root_seq;
 		} else {
 			set_root(nd);
 			path_get(&nd->root);

fs/ncpfs/dir.c

@@ -1145,6 +1145,8 @@ static int ncp_rename(struct inode *old_dir, struct dentry *old_dentry,
 		case 0x00:
 			ncp_dbg(1, "renamed %pd -> %pd\n",
 				old_dentry, new_dentry);
+			ncp_d_prune(old_dentry);
+			ncp_d_prune(new_dentry);
 			break;
 		case 0x9E:
 			error = -ENAMETOOLONG;

fs/nfs/dir.c

@@ -1768,7 +1768,7 @@ EXPORT_SYMBOL_GPL(nfs_mkdir);
 
 static void nfs_dentry_handle_enoent(struct dentry *dentry)
 {
-	if (d_really_is_positive(dentry) && !d_unhashed(dentry))
+	if (simple_positive(dentry))
 		d_delete(dentry);
 }
 

fs/nilfs2/dir.c

@@ -61,11 +61,6 @@ static inline void nilfs_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.

fs/nilfs2/inode.c

@@ -307,31 +307,13 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 static ssize_t
 nilfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
-	struct file *file = iocb->ki_filp;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = file->f_mapping->host;
-	size_t count = iov_iter_count(iter);
-	ssize_t size;
+	struct inode *inode = file_inode(iocb->ki_filp);
 
 	if (iov_iter_rw(iter) == WRITE)
 		return 0;
 
 	/* Needs synchronization with the cleaner */
-	size = blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
-
-	/*
-	 * In case of error extending write may have instantiated a few
-	 * blocks outside i_size. Trim these off again.
-	 */
-	if (unlikely(iov_iter_rw(iter) == WRITE && size < 0)) {
-		loff_t isize = i_size_read(inode);
-		loff_t end = offset + count;
-
-		if (end > isize)
-			nilfs_write_failed(mapping, end);
-	}
-
-	return size;
+	return blockdev_direct_IO(iocb, inode, iter, offset, nilfs_get_block);
 }
 
 const struct address_space_operations nilfs_aops = {

fs/ntfs/file.c

@@ -382,7 +382,7 @@ static ssize_t ntfs_prepare_file_for_write(struct kiocb *iocb,
 	base_ni = ni;
 	if (NInoAttr(ni))
 		base_ni = ni->ext.base_ntfs_ino;
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (unlikely(err))
 		goto out;
 	/*

fs/ntfs/inode.h

@@ -239,7 +239,7 @@ typedef struct {
  */
 static inline ntfs_inode *NTFS_I(struct inode *inode)
 {
-	return (ntfs_inode *)list_entry(inode, big_ntfs_inode, vfs_inode);
+	return (ntfs_inode *)container_of(inode, big_ntfs_inode, vfs_inode);
 }
 
 static inline struct inode *VFS_I(ntfs_inode *ni)

fs/open.c

@@ -51,8 +51,10 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 		newattrs.ia_valid |= ATTR_FILE;
 	}
 
-	/* Remove suid/sgid on truncate too */
-	ret = should_remove_suid(dentry);
+	/* Remove suid, sgid, and file capabilities on truncate too */
+	ret = dentry_needs_remove_privs(dentry);
+	if (ret < 0)
+		return ret;
 	if (ret)
 		newattrs.ia_valid |= ret | ATTR_FORCE;
 
@@ -678,18 +680,18 @@ int open_check_o_direct(struct file *f)
 }
 
 static int do_dentry_open(struct file *f,
+			  struct inode *inode,
 			  int (*open)(struct inode *, struct file *),
 			  const struct cred *cred)
 {
 	static const struct file_operations empty_fops = {};
-	struct inode *inode;
 	int error;
 
 	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 
 	path_get(&f->f_path);
-	inode = f->f_inode = f->f_path.dentry->d_inode;
+	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
 
 	if (unlikely(f->f_flags & O_PATH)) {
@@ -793,7 +795,8 @@ int finish_open(struct file *file, struct dentry *dentry,
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, open, current_cred());
+	error = do_dentry_open(file, d_backing_inode(dentry), open,
+			       current_cred());
 	if (!error)
 		*opened |= FILE_OPENED;
 
@@ -822,6 +825,34 @@ int finish_no_open(struct file *file, struct dentry *dentry)
 }
 EXPORT_SYMBOL(finish_no_open);
 
+char *file_path(struct file *filp, char *buf, int buflen)
+{
+	return d_path(&filp->f_path, buf, buflen);
+}
+EXPORT_SYMBOL(file_path);
+
+/**
+ * vfs_open - open the file at the given path
+ * @path: path to open
+ * @file: newly allocated file with f_flag initialized
+ * @cred: credentials to use
+ */
+int vfs_open(const struct path *path, struct file *file,
+	     const struct cred *cred)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = dentry->d_inode;
+
+	file->f_path = *path;
+	if (dentry->d_flags & DCACHE_OP_SELECT_INODE) {
+		inode = dentry->d_op->d_select_inode(dentry, file->f_flags);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+	}
+
+	return do_dentry_open(file, inode, NULL, cred);
+}
+
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *cred)
 {
@@ -853,26 +884,6 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
-/**
- * vfs_open - open the file at the given path
- * @path: path to open
- * @filp: newly allocated file with f_flag initialized
- * @cred: credentials to use
- */
-int vfs_open(const struct path *path, struct file *filp,
-	     const struct cred *cred)
-{
-	struct inode *inode = path->dentry->d_inode;
-
-	if (inode->i_op->dentry_open)
-		return inode->i_op->dentry_open(path->dentry, filp, cred);
-	else {
-		filp->f_path = *path;
-		return do_dentry_open(filp, NULL, cred);
-	}
-}
-EXPORT_SYMBOL(vfs_open);
-
 static inline int build_open_flags(int flags, umode_t mode, struct open_flags *op)
 {
 	int lookup_flags = 0;

fs/overlayfs/inode.c

@@ -337,37 +337,30 @@ static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
 	return true;
 }
 
-static int ovl_dentry_open(struct dentry *dentry, struct file *file,
-		    const struct cred *cred)
+struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags)
 {
 	int err;
 	struct path realpath;
 	enum ovl_path_type type;
-	bool want_write = false;
 
 	type = ovl_path_real(dentry, &realpath);
-	if (ovl_open_need_copy_up(file->f_flags, type, realpath.dentry)) {
-		want_write = true;
+	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
 		if (err)
-			goto out;
+			return ERR_PTR(err);
 
-		if (file->f_flags & O_TRUNC)
+		if (file_flags & O_TRUNC)
 			err = ovl_copy_up_last(dentry, NULL, true);
 		else
 			err = ovl_copy_up(dentry);
+		ovl_drop_write(dentry);
 		if (err)
-			goto out_drop_write;
+			return ERR_PTR(err);
 
 		ovl_path_upper(dentry, &realpath);
 	}
 
-	err = vfs_open(&realpath, file, cred);
-out_drop_write:
-	if (want_write)
-		ovl_drop_write(dentry);
-out:
-	return err;
+	return d_backing_inode(realpath.dentry);
 }
 
 static const struct inode_operations ovl_file_inode_operations = {
@@ -378,7 +371,6 @@ static const struct inode_operations ovl_file_inode_operations = {
 	.getxattr	= ovl_getxattr,
 	.listxattr	= ovl_listxattr,
 	.removexattr	= ovl_removexattr,
-	.dentry_open	= ovl_dentry_open,
 };
 
 static const struct inode_operations ovl_symlink_inode_operations = {

fs/overlayfs/overlayfs.h

@@ -173,6 +173,7 @@ ssize_t ovl_getxattr(struct dentry *dentry, const char *name,
 		     void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 int ovl_removexattr(struct dentry *dentry, const char *name);
+struct inode *ovl_d_select_inode(struct dentry *dentry, unsigned file_flags);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode,
 			    struct ovl_entry *oe);

fs/overlayfs/super.c

@@ -316,6 +316,7 @@ static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
 
 static const struct dentry_operations ovl_dentry_operations = {
 	.d_release = ovl_dentry_release,
+	.d_select_inode = ovl_d_select_inode,
 };
 
 static const struct dentry_operations ovl_reval_dentry_operations = {

fs/posix_acl.c

@@ -547,51 +547,45 @@ posix_acl_create(struct inode *dir, umode_t *mode,
 		struct posix_acl **default_acl, struct posix_acl **acl)
 {
 	struct posix_acl *p;
+	struct posix_acl *clone;
 	int ret;
 
+	*acl = NULL;
+	*default_acl = NULL;
+
 	if (S_ISLNK(*mode) || !IS_POSIXACL(dir))
-		goto no_acl;
+		return 0;
 
 	p = get_acl(dir, ACL_TYPE_DEFAULT);
-	if (IS_ERR(p)) {
-		if (p == ERR_PTR(-EOPNOTSUPP))
-			goto apply_umask;
-		return PTR_ERR(p);
+	if (!p || p == ERR_PTR(-EOPNOTSUPP)) {
+		*mode &= ~current_umask();
+		return 0;
 	}
+	if (IS_ERR(p))
+		return PTR_ERR(p);
 
-	if (!p)
-		goto apply_umask;
-
-	*acl = posix_acl_clone(p, GFP_NOFS);
-	if (!*acl)
+	clone = posix_acl_clone(p, GFP_NOFS);
+	if (!clone)
 		goto no_mem;
 
-	ret = posix_acl_create_masq(*acl, mode);
+	ret = posix_acl_create_masq(clone, mode);
 	if (ret < 0)
 		goto no_mem_clone;
 
-	if (ret == 0) {
-		posix_acl_release(*acl);
-		*acl = NULL;
-	}
+	if (ret == 0)
+		posix_acl_release(clone);
+	else
+		*acl = clone;
 
-	if (!S_ISDIR(*mode)) {
+	if (!S_ISDIR(*mode))
 		posix_acl_release(p);
-		*default_acl = NULL;
-	} else {
+	else
 		*default_acl = p;
-	}
-	return 0;
 
-apply_umask:
-	*mode &= ~current_umask();
-no_acl:
-	*default_acl = NULL;
-	*acl = NULL;
 	return 0;
 
 no_mem_clone:
-	posix_acl_release(*acl);
+	posix_acl_release(clone);
 no_mem:
 	posix_acl_release(p);
 	return -ENOMEM;

fs/proc/nommu.c

@@ -64,7 +64,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
 
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "");
+		seq_file_path(m, file, "");
 	}
 
 	seq_putc(m, '\n');

fs/proc/task_mmu.c

@@ -310,7 +310,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 	 */
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "\n");
+		seq_file_path(m, file, "\n");
 		goto done;
 	}
 
@@ -1509,7 +1509,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 
 	if (file) {
 		seq_puts(m, " file=");
-		seq_path(m, &file->f_path, "\n\t= ");
+		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
 	} else {

fs/proc/task_nommu.c

@@ -180,7 +180,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 
 	if (file) {
 		seq_pad(m, ' ');
-		seq_path(m, &file->f_path, "");
+		seq_file_path(m, file, "");
 	} else if (mm) {
 		pid_t tid = pid_of_stack(priv, vma, is_pid);
 

fs/qnx6/dir.c

@@ -32,11 +32,6 @@ static struct page *qnx6_get_page(struct inode *dir, unsigned long n)
 	return page;
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 static unsigned last_entry(struct inode *inode, unsigned long page_nr)
 {
 	unsigned long last_byte = inode->i_size;

fs/seq_file.c

@@ -490,6 +490,20 @@ int seq_path(struct seq_file *m, const struct path *path, const char *esc)
 }
 EXPORT_SYMBOL(seq_path);
 
+/**
+ * seq_file_path - seq_file interface to print a pathname of a file
+ * @m: the seq_file handle
+ * @file: the struct file to print
+ * @esc: set of characters to escape in the output
+ *
+ * return the absolute path to the file.
+ */
+int seq_file_path(struct seq_file *m, struct file *file, const char *esc)
+{
+	return seq_path(m, &file->f_path, esc);
+}
+EXPORT_SYMBOL(seq_file_path);
+
 /*
  * Same as seq_path, but relative to supplied root.
  */

fs/squashfs/squashfs_fs_i.h

@@ -49,6 +49,6 @@ struct squashfs_inode_info {
 
 static inline struct squashfs_inode_info *squashfs_i(struct inode *inode)
 {
-	return list_entry(inode, struct squashfs_inode_info, vfs_inode);
+	return container_of(inode, struct squashfs_inode_info, vfs_inode);
 }
 #endif

fs/super.c

@@ -842,7 +842,7 @@ int get_anon_bdev(dev_t *p)
 	else if (error)
 		return -EAGAIN;
 
-	if (dev == (1 << MINORBITS)) {
+	if (dev >= (1 << MINORBITS)) {
 		spin_lock(&unnamed_dev_lock);
 		ida_remove(&unnamed_dev_ida, dev);
 		if (unnamed_dev_start > dev)

fs/sysv/dir.c

@@ -33,11 +33,6 @@ static inline void dir_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;
-}
-
 static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 {
 	struct address_space *mapping = page->mapping;

fs/sysv/sysv.h

@@ -73,7 +73,7 @@ struct sysv_inode_info {
 
 static inline struct sysv_inode_info *SYSV_I(struct inode *inode)
 {
-	return list_entry(inode, struct sysv_inode_info, vfs_inode);
+	return container_of(inode, struct sysv_inode_info, vfs_inode);
 }
 
 static inline struct sysv_sb_info *SYSV_SB(struct super_block *sb)

fs/tracefs/inode.c

@@ -496,16 +496,11 @@ struct dentry *tracefs_create_instance_dir(const char *name, struct dentry *pare
 	return dentry;
 }
 
-static inline int tracefs_positive(struct dentry *dentry)
-{
-	return dentry->d_inode && !d_unhashed(dentry);
-}
-
 static int __tracefs_remove(struct dentry *dentry, struct dentry *parent)
 {
 	int ret = 0;
 
-	if (tracefs_positive(dentry)) {
+	if (simple_positive(dentry)) {
 		if (dentry->d_inode) {
 			dget(dentry);
 			switch (dentry->d_inode->i_mode & S_IFMT) {
@@ -582,7 +577,7 @@ void tracefs_remove_recursive(struct dentry *dentry)
 	 */
 	spin_lock(&parent->d_lock);
 	list_for_each_entry(child, &parent->d_subdirs, d_child) {
-		if (!tracefs_positive(child))
+		if (!simple_positive(child))
 			continue;
 
 		/* perhaps simple_empty(child) makes more sense */
@@ -603,7 +598,7 @@ void tracefs_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
-		 * tracefs_positive() check.
+		 * simple_positive() check.
 		 */
 		goto loop;
 	}

fs/udf/udf_i.h

@@ -56,7 +56,7 @@ struct udf_inode_info {
 
 static inline struct udf_inode_info *UDF_I(struct inode *inode)
 {
-	return list_entry(inode, struct udf_inode_info, vfs_inode);
+	return container_of(inode, struct udf_inode_info, vfs_inode);
 }
 
 #endif /* _UDF_I_H) */

fs/ufs/balloc.c

@@ -51,8 +51,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 	
 	if (ufs_fragnum(fragment) + count > uspi->s_fpg)
 		ufs_error (sb, "ufs_free_fragments", "internal error");
-	
-	lock_ufs(sb);
+
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 	cgno = ufs_dtog(uspi, fragment);
 	bit = ufs_dtogd(uspi, fragment);
@@ -115,13 +115,13 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 	if (sb->s_flags & MS_SYNCHRONOUS)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	ufs_mark_sb_dirty(sb);
-	
-	unlock_ufs(sb);
+
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return;
 }
@@ -151,7 +151,7 @@ void ufs_free_blocks(struct inode *inode, u64 fragment, unsigned count)
 		goto failed;
 	}
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	
 do_more:
 	overflow = 0;
@@ -211,12 +211,12 @@ do_more:
 	}
 
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 	return;
 
 failed_unlock:
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 failed:
 	UFSD("EXIT (FAILED)\n");
 	return;
@@ -357,7 +357,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	usb1 = ubh_get_usb_first(uspi);
 	*err = -ENOSPC;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	tmp = ufs_data_ptr_to_cpu(sb, p);
 
 	if (count + ufs_fragnum(fragment) > uspi->s_fpb) {
@@ -378,19 +378,19 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 				  "fragment %llu, tmp %llu\n",
 				  (unsigned long long)fragment,
 				  (unsigned long long)tmp);
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return INVBLOCK;
 		}
 		if (fragment < UFS_I(inode)->i_lastfrag) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
 	else {
 		if (tmp) {
 			UFSD("EXIT (ALREADY ALLOCATED)\n");
-			unlock_ufs(sb);
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			return 0;
 		}
 	}
@@ -399,7 +399,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	 * There is not enough space for user on the device
 	 */
 	if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT (FAILED)\n");
 		return 0;
 	}
@@ -424,7 +424,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 			ufs_clear_frags(inode, result + oldcount,
 					newcount - oldcount, locked_page != NULL);
 		}
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -439,7 +439,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 						fragment + count);
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
 		return result;
 	}
@@ -477,7 +477,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
 		ufs_free_fragments (inode, tmp, oldcount);
@@ -485,7 +485,7 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		return result;
 	}
 
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT (FAILED)\n");
 	return 0;
 }		

fs/ufs/dir.c

@@ -65,11 +65,6 @@ static inline void ufs_put_page(struct page *page)
 	page_cache_release(page);
 }
 
-static inline unsigned long ufs_dir_pages(struct inode *inode)
-{
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
-}
-
 ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 {
 	ino_t res = 0;
@@ -87,7 +82,8 @@ ino_t ufs_inode_by_name(struct inode *dir, const struct qstr *qstr)
 
 /* Releases the page */
 void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
-		  struct page *page, struct inode *inode)
+		  struct page *page, struct inode *inode,
+		  bool update_times)
 {
 	loff_t pos = page_offset(page) +
 			(char *) de - (char *) page_address(page);
@@ -103,7 +99,8 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
 
 	err = ufs_commit_chunk(page, pos, len);
 	ufs_put_page(page);
-	dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
+	if (update_times)
+		dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(dir);
 }
 
@@ -256,7 +253,7 @@ struct ufs_dir_entry *ufs_find_entry(struct inode *dir, const struct qstr *qstr,
 	int namelen = qstr->len;
 	unsigned reclen = UFS_DIR_REC_LEN(namelen);
 	unsigned long start, n;
-	unsigned long npages = ufs_dir_pages(dir);
+	unsigned long npages = dir_pages(dir);
 	struct page *page = NULL;
 	struct ufs_inode_info *ui = UFS_I(dir);
 	struct ufs_dir_entry *de;
@@ -320,7 +317,7 @@ int ufs_add_link(struct dentry *dentry, struct inode *inode)
 	unsigned short rec_len, name_len;
 	struct page *page = NULL;
 	struct ufs_dir_entry *de;
-	unsigned long npages = ufs_dir_pages(dir);
+	unsigned long npages = dir_pages(dir);
 	unsigned long n;
 	char *kaddr;
 	loff_t pos;
@@ -437,7 +434,7 @@ ufs_readdir(struct file *file, struct dir_context *ctx)
 	struct super_block *sb = inode->i_sb;
 	unsigned int offset = pos & ~PAGE_CACHE_MASK;
 	unsigned long n = pos >> PAGE_CACHE_SHIFT;
-	unsigned long npages = ufs_dir_pages(inode);
+	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(UFS_SB(sb)->s_uspi->s_dirblksize - 1);
 	int need_revalidate = file->f_version != inode->i_version;
 	unsigned flags = UFS_SB(sb)->s_flags;
@@ -608,7 +605,7 @@ int ufs_empty_dir(struct inode * inode)
 {
 	struct super_block *sb = inode->i_sb;
 	struct page *page = NULL;
-	unsigned long i, npages = ufs_dir_pages(inode);
+	unsigned long i, npages = dir_pages(inode);
 
 	for (i = 0; i < npages; i++) {
 		char *kaddr;

fs/ufs/ialloc.c

@@ -69,11 +69,11 @@ void ufs_free_inode (struct inode * inode)
 	
 	ino = inode->i_ino;
 
-	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	if (!((ino > 1) && (ino < (uspi->s_ncg * uspi->s_ipg )))) {
 		ufs_warning(sb, "ufs_free_inode", "reserved inode or nonexistent inode %u\n", ino);
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	
@@ -81,7 +81,7 @@ void ufs_free_inode (struct inode * inode)
 	bit = ufs_inotocgoff (ino);
 	ucpi = ufs_load_cylinder (sb, cg);
 	if (!ucpi) {
-		unlock_ufs(sb);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		return;
 	}
 	ucg = ubh_get_ucg(UCPI_UBH(ucpi));
@@ -115,7 +115,7 @@ void ufs_free_inode (struct inode * inode)
 		ubh_sync_block(UCPI_UBH(ucpi));
 	
 	ufs_mark_sb_dirty(sb);
-	unlock_ufs(sb);
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	UFSD("EXIT\n");
 }
 
@@ -193,7 +193,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode)
 	sbi = UFS_SB(sb);
 	uspi = sbi->s_uspi;
 
-	lock_ufs(sb);
+	mutex_lock(&sbi->s_lock);
 
 	/*
 	 * Try to place the inode in its parent directory
@@ -331,21 +331,21 @@ cg_found:
 			sync_dirty_buffer(bh);
 		brelse(bh);
 	}
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 
 	UFSD("allocating inode %lu\n", inode->i_ino);
 	UFSD("EXIT\n");
 	return inode;
 
 fail_remove_inode:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
 	unlock_new_inode(inode);
 	iput(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
-	unlock_ufs(sb);
+	mutex_unlock(&sbi->s_lock);
 	make_bad_inode(inode);
 	iput (inode);
 	UFSD("EXIT (FAILED): err %d\n", err);

fs/ufs/inode.c

@@ -903,6 +903,9 @@ void ufs_evict_inode(struct inode * inode)
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 
-	if (want_delete)
+	if (want_delete) {
+		lock_ufs(inode->i_sb);
 		ufs_free_inode(inode);
+		unlock_ufs(inode->i_sb);
+	}
 }

fs/ufs/namei.c

@@ -56,11 +56,9 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsi
 	if (dentry->d_name.len > UFS_MAXNAMLEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	lock_ufs(dir->i_sb);
 	ino = ufs_inode_by_name(dir, &dentry->d_name);
 	if (ino)
 		inode = ufs_iget(dir->i_sb, ino);
-	unlock_ufs(dir->i_sb);
 	return d_splice_alias(inode, dentry);
 }
 
@@ -76,24 +74,16 @@ static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode,
 		bool excl)
 {
 	struct inode *inode;
-	int err;
-
-	UFSD("BEGIN\n");
 
 	inode = ufs_new_inode(dir, mode);
-	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
 
-	if (!IS_ERR(inode)) {
-		inode->i_op = &ufs_file_inode_operations;
-		inode->i_fop = &ufs_file_operations;
-		inode->i_mapping->a_ops = &ufs_aops;
-		mark_inode_dirty(inode);
-		lock_ufs(dir->i_sb);
-		err = ufs_add_nondir(dentry, inode);
-		unlock_ufs(dir->i_sb);
-	}
-	UFSD("END: err=%d\n", err);
-	return err;
+	inode->i_op = &ufs_file_inode_operations;
+	inode->i_fop = &ufs_file_operations;
+	inode->i_mapping->a_ops = &ufs_aops;
+	mark_inode_dirty(inode);
+	return ufs_add_nondir(dentry, inode);
 }
 
 static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev)
@@ -110,9 +100,7 @@ static int ufs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev
 		init_special_inode(inode, mode, rdev);
 		ufs_set_inode_dev(inode->i_sb, UFS_I(inode), rdev);
 		mark_inode_dirty(inode);
-		lock_ufs(dir->i_sb);
 		err = ufs_add_nondir(dentry, inode);
-		unlock_ufs(dir->i_sb);
 	}
 	return err;
 }
@@ -121,19 +109,18 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 	const char * symname)
 {
 	struct super_block * sb = dir->i_sb;
-	int err = -ENAMETOOLONG;
+	int err;
 	unsigned l = strlen(symname)+1;
 	struct inode * inode;
 
 	if (l > sb->s_blocksize)
-		goto out_notlocked;
+		return -ENAMETOOLONG;
 
 	inode = ufs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		goto out_notlocked;
+		return err;
 
-	lock_ufs(dir->i_sb);
 	if (l > UFS_SB(sb)->s_uspi->s_maxsymlinklen) {
 		/* slow symlink */
 		inode->i_op = &ufs_symlink_inode_operations;
@@ -150,17 +137,13 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 	}
 	mark_inode_dirty(inode);
 
-	err = ufs_add_nondir(dentry, inode);
-out:
-	unlock_ufs(dir->i_sb);
-out_notlocked:
-	return err;
+	return ufs_add_nondir(dentry, inode);
 
 out_fail:
 	inode_dec_link_count(inode);
 	unlock_new_inode(inode);
 	iput(inode);
-	goto out;
+	return err;
 }
 
 static int ufs_link (struct dentry * old_dentry, struct inode * dir,
@@ -169,14 +152,16 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir,
 	struct inode *inode = d_inode(old_dentry);
 	int error;
 
-	lock_ufs(dir->i_sb);
-
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
 	ihold(inode);
 
-	error = ufs_add_nondir(dentry, inode);
-	unlock_ufs(dir->i_sb);
+	error = ufs_add_link(dentry, inode);
+	if (error) {
+		inode_dec_link_count(inode);
+		iput(inode);
+	} else
+		d_instantiate(dentry, inode);
 	return error;
 }
 
@@ -185,9 +170,12 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	struct inode * inode;
 	int err;
 
+	inode_inc_link_count(dir);
+
 	inode = ufs_new_inode(dir, S_IFDIR|mode);
+	err = PTR_ERR(inode);
 	if (IS_ERR(inode))
-		return PTR_ERR(inode);
+		goto out_dir;
 
 	inode->i_op = &ufs_dir_inode_operations;
 	inode->i_fop = &ufs_dir_operations;
@@ -195,9 +183,6 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 
 	inode_inc_link_count(inode);
 
-	lock_ufs(dir->i_sb);
-	inode_inc_link_count(dir);
-
 	err = ufs_make_empty(inode, dir);
 	if (err)
 		goto out_fail;
@@ -205,20 +190,19 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 	err = ufs_add_link(dentry, inode);
 	if (err)
 		goto out_fail;
-	unlock_ufs(dir->i_sb);
 
+	unlock_new_inode(inode);
 	d_instantiate(dentry, inode);
-out:
-	return err;
+	return 0;
 
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
 	unlock_new_inode(inode);
 	iput (inode);
+out_dir:
 	inode_dec_link_count(dir);
-	unlock_ufs(dir->i_sb);
-	goto out;
+	return err;
 }
 
 static int ufs_unlink(struct inode *dir, struct dentry *dentry)
@@ -248,7 +232,6 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry)
 	struct inode * inode = d_inode(dentry);
 	int err= -ENOTEMPTY;
 
-	lock_ufs(dir->i_sb);
 	if (ufs_empty_dir (inode)) {
 		err = ufs_unlink(dir, dentry);
 		if (!err) {
@@ -257,7 +240,6 @@ static int ufs_rmdir (struct inode * dir, struct dentry *dentry)
 			inode_dec_link_count(dir);
 		}
 	}
-	unlock_ufs(dir->i_sb);
 	return err;
 }
 
@@ -295,7 +277,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page);
 		if (!new_de)
 			goto out_dir;
-		ufs_set_link(new_dir, new_de, new_page, old_inode);
+		ufs_set_link(new_dir, new_de, new_page, old_inode, 1);
 		new_inode->i_ctime = CURRENT_TIME_SEC;
 		if (dir_de)
 			drop_nlink(new_inode);
@@ -318,7 +300,12 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	mark_inode_dirty(old_inode);
 
 	if (dir_de) {
-		ufs_set_link(old_inode, dir_de, dir_page, new_dir);
+		if (old_dir != new_dir)
+			ufs_set_link(old_inode, dir_de, dir_page, new_dir, 0);
+		else {
+			kunmap(dir_page);
+			page_cache_release(dir_page);
+		}
 		inode_dec_link_count(old_dir);
 	}
 	return 0;

fs/ufs/super.c

@@ -695,6 +695,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	unsigned flags;
 
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 
 	UFSD("ENTER\n");
 
@@ -712,6 +713,7 @@ static int ufs_sync_fs(struct super_block *sb, int wait)
 	ufs_put_cstotal(sb);
 
 	UFSD("EXIT\n");
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 
 	return 0;
@@ -800,6 +802,7 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	UFSD("flag %u\n", (int)(sb->s_flags & MS_RDONLY));
 	
 	mutex_init(&sbi->mutex);
+	mutex_init(&sbi->s_lock);
 	spin_lock_init(&sbi->work_lock);
 	INIT_DELAYED_WORK(&sbi->sync_work, delayed_sync_fs);
 	/*
@@ -1278,6 +1281,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 
 	sync_filesystem(sb);
 	lock_ufs(sb);
+	mutex_lock(&UFS_SB(sb)->s_lock);
 	uspi = UFS_SB(sb)->s_uspi;
 	flags = UFS_SB(sb)->s_flags;
 	usb1 = ubh_get_usb_first(uspi);
@@ -1291,6 +1295,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	new_mount_opt = 0;
 	ufs_set_opt (new_mount_opt, ONERROR_LOCK);
 	if (!ufs_parse_options (data, &new_mount_opt)) {
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
@@ -1298,12 +1303,14 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		new_mount_opt |= ufstype;
 	} else if ((new_mount_opt & UFS_MOUNT_UFSTYPE) != ufstype) {
 		pr_err("ufstype can't be changed during remount\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 	}
 
 	if ((*mount_flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY)) {
 		UFS_SB(sb)->s_mount_opt = new_mount_opt;
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return 0;
 	}
@@ -1327,6 +1334,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 	 */
 #ifndef CONFIG_UFS_FS_WRITE
 		pr_err("ufs was compiled with read-only support, can't be mounted as read-write\n");
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		unlock_ufs(sb);
 		return -EINVAL;
 #else
@@ -1336,11 +1344,13 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 		    ufstype != UFS_MOUNT_UFSTYPE_SUNx86 &&
 		    ufstype != UFS_MOUNT_UFSTYPE_UFS2) {
 			pr_err("this ufstype is read-only supported\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EINVAL;
 		}
 		if (!ufs_read_cylinder_structures(sb)) {
 			pr_err("failed during remounting\n");
+			mutex_unlock(&UFS_SB(sb)->s_lock);
 			unlock_ufs(sb);
 			return -EPERM;
 		}
@@ -1348,6 +1358,7 @@ static int ufs_remount (struct super_block *sb, int *mount_flags, char *data)
 #endif
 	}
 	UFS_SB(sb)->s_mount_opt = new_mount_opt;
+	mutex_unlock(&UFS_SB(sb)->s_lock);
 	unlock_ufs(sb);
 	return 0;
 }

fs/ufs/ufs.h

@@ -30,6 +30,7 @@ struct ufs_sb_info {
 	int work_queued; /* non-zero if the delayed work is queued */
 	struct delayed_work sync_work; /* FS sync delayed work */
 	spinlock_t work_lock; /* protects sync_work and work_queued */
+	struct mutex s_lock;
 };
 
 struct ufs_inode_info {
@@ -105,7 +106,7 @@ extern int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct page
 extern int ufs_empty_dir (struct inode *);
 extern struct ufs_dir_entry *ufs_dotdot(struct inode *, struct page **);
 extern void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de,
-			 struct page *page, struct inode *inode);
+			 struct page *page, struct inode *inode, bool update_times);
 
 /* file.c */
 extern const struct inode_operations ufs_file_inode_operations;

fs/xfs/xfs_file.c

@@ -577,6 +577,13 @@ restart:
 	if (error)
 		return error;
 
+	/* For changing security info in file_remove_privs() we need i_mutex */
+	if (*iolock == XFS_IOLOCK_SHARED && !IS_NOSEC(inode)) {
+		xfs_rw_iunlock(ip, *iolock);
+		*iolock = XFS_IOLOCK_EXCL;
+		xfs_rw_ilock(ip, *iolock);
+		goto restart;
+	}
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
@@ -637,7 +644,9 @@ restart:
 	 * setgid bits if the process is not being run by root.  This keeps
 	 * people from modifying setuid and setgid binaries.
 	 */
-	return file_remove_suid(file);
+	if (!IS_NOSEC(inode))
+		return file_remove_privs(file);
+	return 0;
 }
 
 /*

include/linux/dcache.h

@@ -160,6 +160,7 @@ struct dentry_operations {
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(struct dentry *, bool);
+	struct inode *(*d_select_inode)(struct dentry *, unsigned);
 } ____cacheline_aligned;
 
 /*
@@ -225,6 +226,7 @@ struct dentry_operations {
 
 #define DCACHE_MAY_FREE			0x00800000
 #define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
+#define DCACHE_OP_SELECT_INODE		0x02000000 /* Unioned entry: dcache op selects inode */
 
 extern seqlock_t rename_lock;
 
@@ -505,6 +507,11 @@ static inline bool d_really_is_positive(const struct dentry *dentry)
 	return dentry->d_inode != NULL;
 }
 
+static inline int simple_positive(struct dentry *dentry)
+{
+	return d_really_is_positive(dentry) && !d_unhashed(dentry);
+}
+
 extern void d_set_fallthru(struct dentry *dentry);
 
 static inline bool d_is_fallthru(const struct dentry *dentry)

include/linux/fdtable.h

@@ -47,6 +47,9 @@ struct files_struct {
    * read mostly part
    */
 	atomic_t count;
+	bool resize_in_progress;
+	wait_queue_head_t resize_wait;
+
 	struct fdtable __rcu *fdt;
 	struct fdtable fdtab;
   /*

include/linux/fs.h

@@ -1654,7 +1654,6 @@ struct inode_operations {
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 
 	/* WARNING: probably going away soon, do not use! */
-	int (*dentry_open)(struct dentry *, struct file *, const struct cred *);
 } ____cacheline_aligned;
 
 ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector,
@@ -2213,7 +2212,6 @@ extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
@@ -2530,6 +2528,8 @@ extern struct file * open_exec(const char *);
 extern int is_subdir(struct dentry *, struct dentry *);
 extern int path_is_under(struct path *, struct path *);
 
+extern char *file_path(struct file *, char *, int);
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
@@ -2581,7 +2581,12 @@ extern struct inode *new_inode_pseudo(struct super_block *sb);
 extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
-extern int file_remove_suid(struct file *);
+extern int file_remove_privs(struct file *);
+extern int dentry_needs_remove_privs(struct dentry *dentry);
+static inline int file_needs_remove_privs(struct file *file)
+{
+	return dentry_needs_remove_privs(file->f_path.dentry);
+}
 
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 static inline void insert_inode_hash(struct inode *inode)

include/linux/fscache-cache.h

@@ -74,6 +74,7 @@ extern wait_queue_head_t fscache_cache_cleared_wq;
  */
 typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
 typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op);
 
 enum fscache_operation_state {
 	FSCACHE_OP_ST_BLANK,		/* Op is not yet submitted */
@@ -109,6 +110,9 @@ struct fscache_operation {
 	 *   the op in a non-pool thread */
 	fscache_operation_processor_t processor;
 
+	/* Operation cancellation cleanup (optional) */
+	fscache_operation_cancel_t cancel;
+
 	/* operation releaser */
 	fscache_operation_release_t release;
 };
@@ -119,33 +123,17 @@ extern void fscache_op_work_func(struct work_struct *work);
 extern void fscache_enqueue_operation(struct fscache_operation *);
 extern void fscache_op_complete(struct fscache_operation *, bool);
 extern void fscache_put_operation(struct fscache_operation *);
-
-/**
- * fscache_operation_init - Do basic initialisation of an operation
- * @op: The operation to initialise
- * @release: The release function to assign
- *
- * Do basic initialisation of an operation.  The caller must still set flags,
- * object and processor if needed.
- */
-static inline void fscache_operation_init(struct fscache_operation *op,
-					fscache_operation_processor_t processor,
-					fscache_operation_release_t release)
-{
-	INIT_WORK(&op->work, fscache_op_work_func);
-	atomic_set(&op->usage, 1);
-	op->state = FSCACHE_OP_ST_INITIALISED;
-	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
-	op->processor = processor;
-	op->release = release;
-	INIT_LIST_HEAD(&op->pend_link);
-}
+extern void fscache_operation_init(struct fscache_operation *,
+				   fscache_operation_processor_t,
+				   fscache_operation_cancel_t,
+				   fscache_operation_release_t);
 
 /*
  * data read operation
  */
 struct fscache_retrieval {
 	struct fscache_operation op;
+	struct fscache_cookie	*cookie;	/* The netfs cookie */
 	struct address_space	*mapping;	/* netfs pages */
 	fscache_rw_complete_t	end_io_func;	/* function to call on I/O completion */
 	void			*context;	/* netfs read context (pinned) */
@@ -371,6 +359,7 @@ struct fscache_object {
 #define FSCACHE_OBJECT_IS_LOOKED_UP	4	/* T if object has been looked up */
 #define FSCACHE_OBJECT_IS_AVAILABLE	5	/* T if object has become active */
 #define FSCACHE_OBJECT_RETIRED		6	/* T if object was retired on relinquishment */
+#define FSCACHE_OBJECT_KILLED_BY_CACHE	7	/* T if object was killed by the cache */
 
 	struct list_head	cache_link;	/* link in cache->object_list */
 	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
@@ -410,17 +399,16 @@ static inline bool fscache_object_is_available(struct fscache_object *object)
 	return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags);
 }
 
-static inline bool fscache_object_is_active(struct fscache_object *object)
+static inline bool fscache_cache_is_broken(struct fscache_object *object)
 {
-	return fscache_object_is_available(object) &&
-		fscache_object_is_live(object) &&
-		!test_bit(FSCACHE_IOERROR, &object->cache->flags);
+	return test_bit(FSCACHE_IOERROR, &object->cache->flags);
 }
 
-static inline bool fscache_object_is_dead(struct fscache_object *object)
+static inline bool fscache_object_is_active(struct fscache_object *object)
 {
-	return fscache_object_is_dying(object) &&
-		test_bit(FSCACHE_IOERROR, &object->cache->flags);
+	return fscache_object_is_available(object) &&
+		fscache_object_is_live(object) &&
+		!fscache_cache_is_broken(object);
 }
 
 /**
@@ -551,4 +539,15 @@ extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
 					       const void *data,
 					       uint16_t datalen);
 
+extern void fscache_object_retrying_stale(struct fscache_object *object);
+
+enum fscache_why_object_killed {
+	FSCACHE_OBJECT_IS_STALE,
+	FSCACHE_OBJECT_NO_SPACE,
+	FSCACHE_OBJECT_WAS_RETIRED,
+	FSCACHE_OBJECT_WAS_CULLED,
+};
+extern void fscache_object_mark_killed(struct fscache_object *object,
+				       enum fscache_why_object_killed why);
+
 #endif /* _LINUX_FSCACHE_CACHE_H */

include/linux/pagemap.h

@@ -671,4 +671,10 @@ static inline int add_to_page_cache(struct page *page,
 	return error;
 }
 
+static inline unsigned long dir_pages(struct inode *inode)
+{
+	return (unsigned long)(inode->i_size + PAGE_CACHE_SIZE - 1) >>
+			       PAGE_CACHE_SHIFT;
+}
+
 #endif /* _LINUX_PAGEMAP_H */

include/linux/seq_file.h

@@ -123,6 +123,7 @@ __printf(2, 3) int seq_printf(struct seq_file *, const char *, ...);
 __printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args);
 
 int seq_path(struct seq_file *, const struct path *, const char *);
+int seq_file_path(struct seq_file *, struct file *, const char *);
 int seq_dentry(struct seq_file *, struct dentry *, const char *);
 int seq_path_root(struct seq_file *m, const struct path *path,
 		  const struct path *root, const char *esc);

kernel/events/core.c

@@ -5794,7 +5794,7 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
 		 * need to add enough zero bytes after the string to handle
 		 * the 64bit alignment we do later.
 		 */
-		name = d_path(&file->f_path, buf, PATH_MAX - sizeof(u64));
+		name = file_path(file, buf, PATH_MAX - sizeof(u64));
 		if (IS_ERR(name)) {
 			name = "//toolong";
 			goto cpy_name;

mm/filemap.c

@@ -2563,7 +2563,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
-	err = file_remove_suid(file);
+	err = file_remove_privs(file);
 	if (err)
 		goto out;
 

mm/memory.c

@@ -3726,7 +3726,7 @@ void print_vma_addr(char *prefix, unsigned long ip)
 		if (buf) {
 			char *p;
 
-			p = d_path(&f->f_path, buf, PAGE_SIZE);
+			p = file_path(f, buf, PAGE_SIZE);
 			if (IS_ERR(p))
 				p = "?";
 			printk("%s%s[%lx+%lx]", prefix, kbasename(p),

mm/swapfile.c

@@ -2032,7 +2032,7 @@ static int swap_show(struct seq_file *swap, void *v)
 	}
 
 	file = si->swap_file;
-	len = seq_path(swap, &file->f_path, " \t\n\\");
+	len = seq_file_path(swap, file, " \t\n\\");
 	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
 			len < 40 ? 40 - len : 1, " ",
 			S_ISBLK(file_inode(file)->i_mode) ?

net/9p/client.c

@@ -843,7 +843,8 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 	if (err < 0) {
 		if (err == -EIO)
 			c->status = Disconnected;
-		goto reterr;
+		if (err != -ERESTARTSYS)
+			goto reterr;
 	}
 	if (req->status == REQ_STATUS_ERROR) {
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
@@ -1582,6 +1583,10 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			p9_free_req(clnt, req);
 			break;
 		}
+		if (rsize < count) {
+			pr_err("bogus RREAD count (%d > %d)\n", count, rsize);
+			count = rsize;
+		}
 
 		p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 		if (!count) {
@@ -1647,6 +1652,11 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 		if (*err) {
 			trace_9p_protocol_dump(clnt, req->rc);
 			p9_free_req(clnt, req);
+			break;
+		}
+		if (rsize < count) {
+			pr_err("bogus RWRITE count (%d > %d)\n", count, rsize);
+			count = rsize;
 		}
 
 		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);

security/inode.c

@@ -25,11 +25,6 @@
 static struct vfsmount *mount;
 static int mount_count;
 
-static inline int positive(struct dentry *dentry)
-{
-	return d_really_is_positive(dentry) && !d_unhashed(dentry);
-}
-
 static int fill_super(struct super_block *sb, void *data, int silent)
 {
 	static struct tree_descr files[] = {{""}};
@@ -201,14 +196,12 @@ void securityfs_remove(struct dentry *dentry)
 		return;
 
 	mutex_lock(&d_inode(parent)->i_mutex);
-	if (positive(dentry)) {
-		if (d_really_is_positive(dentry)) {
-			if (d_is_dir(dentry))
-				simple_rmdir(d_inode(parent), dentry);
-			else
-				simple_unlink(d_inode(parent), dentry);
-			dput(dentry);
-		}
+	if (simple_positive(dentry)) {
+		if (d_is_dir(dentry))
+			simple_rmdir(d_inode(parent), dentry);
+		else
+			simple_unlink(d_inode(parent), dentry);
+		dput(dentry);
 	}
 	mutex_unlock(&d_inode(parent)->i_mutex);
 	simple_release_fs(&mount, &mount_count);