1 files changed, 393 insertions, 260 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index b44e4c559786..cd4a3db4659a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/fs/file_table.c
  *
@@ -8,11 +9,12 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/fs.h>
+#include <linux/filelock.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/eventpoll.h>
 #include <linux/rcupdate.h>
 #include <linux/mount.h>
@@ -20,42 +22,62 @@
 #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>
 #include <linux/task_work.h>
-#include <linux/ima.h>
+#include <linux/swap.h>
+#include <linux/kmemleak.h>
 
 #include <linux/atomic.h>
 
 #include "internal.h"
 
 /* sysctl tunables... */
-struct files_stat_struct files_stat = {
+static struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DEFINE_STATIC_LGLOCK(files_lglock);
-
 /* SLAB cache for file structures */
-static struct kmem_cache *filp_cachep __read_mostly;
+static struct kmem_cache *filp_cachep __ro_after_init;
+static struct kmem_cache *bfilp_cachep __ro_after_init;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
-static void file_free_rcu(struct rcu_head *head)
+/* Container for backing file with optional user path */
+struct backing_file {
+	struct file file;
+	union {
+		struct path user_path;
+		freeptr_t bf_freeptr;
+	};
+};
+
+#define backing_file(f) container_of(f, struct backing_file, file)
+
+const struct path *backing_file_user_path(const struct file *f)
 {
-	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
+	return &backing_file(f)->user_path;
+}
+EXPORT_SYMBOL_GPL(backing_file_user_path);
 
-	put_cred(f->f_cred);
-	kmem_cache_free(filp_cachep, f);
+void backing_file_set_user_path(struct file *f, const struct path *path)
+{
+	backing_file(f)->user_path = *path;
 }
+EXPORT_SYMBOL_GPL(backing_file_set_user_path);
 
 static inline void file_free(struct file *f)
 {
-	percpu_counter_dec(&nr_files);
-	file_check_state(f);
-	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
+	security_file_free(f);
+	if (likely(!(f->f_mode & FMODE_NOACCOUNT)))
+		percpu_counter_dec(&nr_files);
+	put_cred(f->f_cred);
+	if (unlikely(f->f_mode & FMODE_BACKING)) {
+		path_put(backing_file_user_path(f));
+		kmem_cache_free(bfilp_cachep, backing_file(f));
+	} else {
+		kmem_cache_free(filp_cachep, f);
+	}
 }
 
 /*
@@ -75,24 +97,114 @@ unsigned long get_max_files(void)
 }
 EXPORT_SYMBOL_GPL(get_max_files);
 
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+
 /*
  * Handle nr_files sysctl
  */
-#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(ctl_table *table, int write,
-                     void __user *buffer, size_t *lenp, loff_t *ppos)
+static int proc_nr_files(const struct ctl_table *table, int write, void *buffer,
+			 size_t *lenp, loff_t *ppos)
 {
-	files_stat.nr_files = get_nr_files();
+	files_stat.nr_files = percpu_counter_sum_positive(&nr_files);
 	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
-#else
-int proc_nr_files(ctl_table *table, int write,
-                     void __user *buffer, size_t *lenp, loff_t *ppos)
+
+static const struct ctl_table fs_stat_sysctls[] = {
+	{
+		.procname	= "file-nr",
+		.data		= &files_stat,
+		.maxlen		= sizeof(files_stat),
+		.mode		= 0444,
+		.proc_handler	= proc_nr_files,
+	},
+	{
+		.procname	= "file-max",
+		.data		= &files_stat.max_files,
+		.maxlen		= sizeof(files_stat.max_files),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra1		= SYSCTL_LONG_ZERO,
+		.extra2		= SYSCTL_LONG_MAX,
+	},
+	{
+		.procname	= "nr_open",
+		.data		= &sysctl_nr_open,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= &sysctl_nr_open_min,
+		.extra2		= &sysctl_nr_open_max,
+	},
+};
+
+static int __init init_fs_stat_sysctls(void)
 {
-	return -ENOSYS;
+	register_sysctl_init("fs", fs_stat_sysctls);
+	if (IS_ENABLED(CONFIG_BINFMT_MISC)) {
+		struct ctl_table_header *hdr;
+
+		hdr = register_sysctl_mount_point("fs/binfmt_misc");
+		kmemleak_not_leak(hdr);
+	}
+	return 0;
 }
+fs_initcall(init_fs_stat_sysctls);
 #endif
 
+static int init_file(struct file *f, int flags, const struct cred *cred)
+{
+	int error;
+
+	f->f_cred = get_cred(cred);
+	error = security_file_alloc(f);
+	if (unlikely(error)) {
+		put_cred(f->f_cred);
+		return error;
+	}
+
+	spin_lock_init(&f->f_lock);
+	/*
+	 * Note that f_pos_lock is only used for files raising
+	 * FMODE_ATOMIC_POS and directories. Other files such as pipes
+	 * don't need it and since f_pos_lock is in a union may reuse
+	 * the space for other purposes. They are expected to initialize
+	 * the respective member when opening the file.
+	 */
+	mutex_init(&f->f_pos_lock);
+	memset(&f->__f_path, 0, sizeof(f->f_path));
+	memset(&f->f_ra, 0, sizeof(f->f_ra));
+
+	f->f_flags	= flags;
+	f->f_mode	= OPEN_FMODE(flags);
+
+	f->f_op		= NULL;
+	f->f_mapping	= NULL;
+	f->private_data = NULL;
+	f->f_inode	= NULL;
+	f->f_owner	= NULL;
+#ifdef CONFIG_EPOLL
+	f->f_ep		= NULL;
+#endif
+
+	f->f_iocb_flags = 0;
+	f->f_pos	= 0;
+	f->f_wb_err	= 0;
+	f->f_sb_err	= 0;
+
+	/*
+	 * We're SLAB_TYPESAFE_BY_RCU so initialize f_ref last. While
+	 * fget-rcu pattern users need to be able to handle spurious
+	 * refcount bumps we should reinitialize the reused file first.
+	 */
+	file_ref_init(&f->f_ref, 1);
+	/*
+	 * Disable permission and pre-content events for all files by default.
+	 * They may be enabled later by fsnotify_open_perm_and_set_mode().
+	 */
+	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
+	return 0;
+}
+
 /* Find an unused file structure and return a pointer to it.
  * Returns an error pointer if some error happend e.g. we over file
  * structures limit, run out of memory or operation is not permitted.
@@ -103,9 +215,8 @@ int proc_nr_files(ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -113,7 +224,8 @@ struct file *get_empty_filp(void)
 	/*
 	 * Privileged users can go above max_files
 	 */
-	if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
+	if (unlikely(get_nr_files() >= files_stat.max_files) &&
+	    !capable(CAP_SYS_ADMIN)) {
 		/*
 		 * percpu_counters are inaccurate.  Do an expensive check before
 		 * we go and fail.
@@ -122,24 +234,18 @@ struct file *get_empty_filp(void)
 			goto over;
 	}
 
-	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
+	f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
-	f->f_cred = get_cred(cred);
-	error = security_file_alloc(f);
+	error = init_file(f, flags, cred);
 	if (unlikely(error)) {
-		file_free(f);
+		kmem_cache_free(filp_cachep, f);
 		return ERR_PTR(error);
 	}
 
-	INIT_LIST_HEAD(&f->f_u.fu_list);
-	atomic_long_set(&f->f_count, 1);
-	rwlock_init(&f->f_owner.lock);
-	spin_lock_init(&f->f_lock);
-	eventpoll_init_file(f);
-	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
+
 	return f;
 
 over:
@@ -151,74 +257,184 @@ over:
 	return ERR_PTR(-ENFILE);
 }
 
-/**
- * alloc_file - allocate and initialize a 'struct file'
- * @mnt: the vfsmount on which the file will reside
- * @dentry: the dentry representing the new file
- * @mode: the mode with which the new file will be opened
- * @fop: the 'struct file_operations' for the new file
+/*
+ * Variant of alloc_empty_file() that doesn't check and modify nr_files.
  *
- * Use this instead of get_empty_filp() to get a new
- * 'struct file'.  Do so because of the same initialization
- * pitfalls reasons listed for init_file().  This is a
- * preferred interface to using init_file().
+ * This is only for kernel internal use, and the allocate file must not be
+ * installed into file tables or such.
+ */
+struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
+{
+	struct file *f;
+	int error;
+
+	f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
+	if (unlikely(!f))
+		return ERR_PTR(-ENOMEM);
+
+	error = init_file(f, flags, cred);
+	if (unlikely(error)) {
+		kmem_cache_free(filp_cachep, f);
+		return ERR_PTR(error);
+	}
+
+	f->f_mode |= FMODE_NOACCOUNT;
+
+	return f;
+}
+
+/*
+ * Variant of alloc_empty_file() that allocates a backing_file container
+ * and doesn't check and modify nr_files.
  *
- * If all the callers of init_file() are eliminated, its
- * code should be moved into this function.
+ * This is only for kernel internal use, and the allocate file must not be
+ * installed into file tables or such.
  */
-struct file *alloc_file(struct path *path, fmode_t mode,
-		const struct file_operations *fop)
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 {
-	struct file *file;
+	struct backing_file *ff;
+	int error;
 
-	file = get_empty_filp();
-	if (IS_ERR(file))
-		return file;
+	ff = kmem_cache_alloc(bfilp_cachep, GFP_KERNEL);
+	if (unlikely(!ff))
+		return ERR_PTR(-ENOMEM);
 
-	file->f_path = *path;
+	error = init_file(&ff->file, flags, cred);
+	if (unlikely(error)) {
+		kmem_cache_free(bfilp_cachep, ff);
+		return ERR_PTR(error);
+	}
+
+	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
+	return &ff->file;
+}
+
+/**
+ * file_init_path - initialize a 'struct file' based on path
+ *
+ * @file: the file to set up
+ * @path: the (dentry, vfsmount) pair for the new file
+ * @fop: the 'struct file_operations' for the new file
+ */
+static void file_init_path(struct file *file, const struct path *path,
+			   const struct file_operations *fop)
+{
+	file->__f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
-	file->f_mode = mode;
+	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
+	file->f_sb_err = file_sample_sb_err(file);
+	if (fop->llseek)
+		file->f_mode |= FMODE_LSEEK;
+	if ((file->f_mode & FMODE_READ) &&
+	     likely(fop->read || fop->read_iter))
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
+	     likely(fop->write || fop->write_iter))
+		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_iocb_flags = iocb_flags(file);
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
-
-	/*
-	 * These mounts don't really matter in practice
-	 * for r/o bind mounts.  They aren't userspace-
-	 * visible.  We do this for consistency, and so
-	 * that we can do debugging checks at __fput()
-	 */
-	if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
-		file_take_write(file);
-		WARN_ON(mnt_clone_write(path->mnt));
-	}
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
-	return file;
 }
-EXPORT_SYMBOL(alloc_file);
 
 /**
- * drop_file_write_access - give up ability to write to a file
- * @file: the file to which we will stop writing
+ * alloc_file - allocate and initialize a 'struct file'
  *
- * This is a central place which will give up the ability
- * to write to @file, along with access to write through
- * its vfsmount.
+ * @path: the (dentry, vfsmount) pair for the new file
+ * @flags: O_... flags with which the new file will be opened
+ * @fop: the 'struct file_operations' for the new file
  */
-static void drop_file_write_access(struct file *file)
+static struct file *alloc_file(const struct path *path, int flags,
+		const struct file_operations *fop)
 {
-	struct vfsmount *mnt = file->f_path.mnt;
-	struct dentry *dentry = file->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
+	struct file *file;
 
-	put_write_access(inode);
+	file = alloc_empty_file(flags, current_cred());
+	if (!IS_ERR(file))
+		file_init_path(file, path, fop);
+	return file;
+}
 
-	if (special_file(inode->i_mode))
-		return;
-	if (file_check_writeable(file) != 0)
-		return;
-	__mnt_drop_write(mnt);
-	file_release_write(file);
+static inline int alloc_path_pseudo(const char *name, struct inode *inode,
+				    struct vfsmount *mnt, struct path *path)
+{
+	path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name));
+	if (!path->dentry)
+		return -ENOMEM;
+	path->mnt = mntget(mnt);
+	d_instantiate(path->dentry, inode);
+	return 0;
+}
+
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+			       const char *name, int flags,
+			       const struct file_operations *fops)
+{
+	int ret;
+	struct path path;
+	struct file *file;
+
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+		return file;
+	}
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
+struct file *alloc_file_pseudo_noaccount(struct inode *inode,
+					 struct vfsmount *mnt, const char *name,
+					 int flags,
+					 const struct file_operations *fops)
+{
+	int ret;
+	struct path path;
+	struct file *file;
+
+	ret = alloc_path_pseudo(name, inode, mnt, &path);
+	if (ret)
+		return ERR_PTR(ret);
+
+	file = alloc_empty_file_noaccount(flags, current_cred());
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+		return file;
+	}
+	file_init_path(file, &path, fops);
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
+	return file;
+}
+EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);
+
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f;
+
+	f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
 }
 
 /* the real guts of fput() - releasing the last reference to file
@@ -228,6 +444,10 @@ static void __fput(struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
+	fmode_t mode = file->f_mode;
+
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
 
 	might_sleep();
 
@@ -237,51 +457,47 @@ static void __fput(struct file *file)
 	 * in the file cleanup chain.
 	 */
 	eventpoll_release(file);
-	locks_remove_flock(file);
+	locks_remove_file(file);
 
+	security_file_release(file);
 	if (unlikely(file->f_flags & FASYNC)) {
-		if (file->f_op && file->f_op->fasync)
+		if (file->f_op->fasync)
 			file->f_op->fasync(-1, file, 0);
 	}
-	ima_file_free(file);
-	if (file->f_op && file->f_op->release)
+	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
-		     !(file->f_mode & FMODE_PATH))) {
+		     !(mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
 	}
 	fops_put(file->f_op);
-	put_pid(file->f_owner.pid);
-	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
-		i_readcount_dec(inode);
-	if (file->f_mode & FMODE_WRITE)
-		drop_file_write_access(file);
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
+	file_f_owner_release(file);
+	put_file_access(file);
 	dput(dentry);
+	if (unlikely(mode & FMODE_NEED_UNMOUNT))
+		dissolve_on_fput(mnt);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
 static void delayed_fput(struct work_struct *unused)
 {
 	struct llist_node *node = llist_del_all(&delayed_fput_list);
-	struct llist_node *next;
+	struct file *f, *t;
 
-	for (; node; node = next) {
-		next = llist_next(node);
-		__fput(llist_entry(node, struct file, f_u.fu_llist));
-	}
+	llist_for_each_entry_safe(f, t, node, f_llist)
+		__fput(f);
 }
 
 static void ____fput(struct callback_head *work)
 {
-	__fput(container_of(work, struct file, f_u.fu_rcuhead));
+	__fput(container_of(work, struct file, f_task_work));
 }
 
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
+
 /*
  * If kernel thread really needs to have the final fput() it has done
  * to complete, call this.  The only user right now is the boot - we
@@ -295,32 +511,40 @@ static void ____fput(struct callback_head *work)
 void flush_delayed_fput(void)
 {
 	delayed_fput(NULL);
+	flush_delayed_work(&delayed_fput_work);
 }
+EXPORT_SYMBOL_GPL(flush_delayed_fput);
+
+static void __fput_deferred(struct file *file)
+{
+	struct task_struct *task = current;
 
-static DECLARE_WORK(delayed_fput_work, delayed_fput);
+	if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
+		file_free(file);
+		return;
+	}
+
+	if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
+		init_task_work(&file->f_task_work, ____fput);
+		if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
+			return;
+		/*
+		 * After this task has run exit_task_work(),
+		 * task_work_add() will fail.  Fall through to delayed
+		 * fput to avoid leaking *file.
+		 */
+	}
+
+	if (llist_add(&file->f_llist, &delayed_fput_list))
+		schedule_delayed_work(&delayed_fput_work, 1);
+}
 
 void fput(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		struct task_struct *task = current;
-
-		file_sb_list_del(file);
-		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
-			init_task_work(&file->f_u.fu_rcuhead, ____fput);
-			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
-				return;
-			/*
-			 * After this task has run exit_task_work(),
-			 * task_work_add() will fail.  free_ipc_ns()->
-			 * shm_destroy() can do this.  Fall through to delayed
-			 * fput to avoid leaking *file.
-			 */
-		}
-
-		if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
-			schedule_work(&delayed_fput_work);
-	}
+	if (unlikely(file_ref_put(&file->f_ref)))
+		__fput_deferred(file);
 }
+EXPORT_SYMBOL(fput);
 
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
@@ -332,156 +556,65 @@ void fput(struct file *file)
  */
 void __fput_sync(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		struct task_struct *task = current;
-		file_sb_list_del(file);
-		BUG_ON(!(task->flags & PF_KTHREAD));
+	if (file_ref_put(&file->f_ref))
 		__fput(file);
-	}
-}
-
-EXPORT_SYMBOL(fput);
-
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_sb_list_del(file);
-		file_free(file);
-	}
 }
+EXPORT_SYMBOL(__fput_sync);
 
-static inline int file_list_cpu(struct file *file)
-{
-#ifdef CONFIG_SMP
-	return file->f_sb_list_cpu;
-#else
-	return smp_processor_id();
-#endif
-}
-
-/* helper for file_sb_list_add to reduce ifdefs */
-static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	struct list_head *list;
-#ifdef CONFIG_SMP
-	int cpu;
-	cpu = smp_processor_id();
-	file->f_sb_list_cpu = cpu;
-	list = per_cpu_ptr(sb->s_files, cpu);
-#else
-	list = &sb->s_files;
-#endif
-	list_add(&file->f_u.fu_list, list);
-}
-
-/**
- * file_sb_list_add - add a file to the sb's file list
- * @file: file to add
- * @sb: sb to add it to
+/*
+ * Equivalent to __fput_sync(), but optimized for being called with the last
+ * reference.
  *
- * Use this function to associate a file with the superblock of the inode it
- * refers to.
+ * See file_ref_put_close() for details.
  */
-void file_sb_list_add(struct file *file, struct super_block *sb)
+void fput_close_sync(struct file *file)
 {
-	lg_local_lock(&files_lglock);
-	__file_sb_list_add(file, sb);
-	lg_local_unlock(&files_lglock);
+	if (likely(file_ref_put_close(&file->f_ref)))
+		__fput(file);
 }
 
-/**
- * file_sb_list_del - remove a file from the sb's file list
- * @file: file to remove
- * @sb: sb to remove it from
+/*
+ * Equivalent to fput(), but optimized for being called with the last
+ * reference.
  *
- * Use this function to remove a file from its superblock.
+ * See file_ref_put_close() for details.
  */
-void file_sb_list_del(struct file *file)
+void fput_close(struct file *file)
 {
-	if (!list_empty(&file->f_u.fu_list)) {
-		lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
-		list_del_init(&file->f_u.fu_list);
-		lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
-	}
-}
-
-#ifdef CONFIG_SMP
-
-/*
- * These macros iterate all files on all CPUs for a given superblock.
- * files_lglock must be held globally.
- */
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	int i;							\
-	for_each_possible_cpu(i) {				\
-		struct list_head *list;				\
-		list = per_cpu_ptr((__sb)->s_files, i);		\
-		list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-	}							\
+	if (file_ref_put_close(&file->f_ref))
+		__fput_deferred(file);
 }
 
-#else
-
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	struct list_head *list;					\
-	list = &(sb)->s_files;					\
-	list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
+void __init files_init(void)
+{
+	struct kmem_cache_args args = {
+		.use_freeptr_offset = true,
+		.freeptr_offset = offsetof(struct file, f_freeptr),
+	};
+
+	filp_cachep = kmem_cache_create("filp", sizeof(struct file), &args,
+				SLAB_HWCACHE_ALIGN | SLAB_PANIC |
+				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
+
+	args.freeptr_offset = offsetof(struct backing_file, bf_freeptr);
+	bfilp_cachep = kmem_cache_create("bfilp", sizeof(struct backing_file),
+				&args, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
+				SLAB_ACCOUNT | SLAB_TYPESAFE_BY_RCU);
+	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
 }
 
-#endif
-
-/**
- *	mark_files_ro - mark all files read-only
- *	@sb: superblock in question
- *
- *	All files are marked read-only.  We don't care about pending
- *	delete files so this should be used in 'force' mode only.
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
  */
-void mark_files_ro(struct super_block *sb)
+void __init files_maxfiles_init(void)
 {
-	struct file *f;
-
-	lg_global_lock(&files_lglock);
-	do_file_list_for_each_entry(sb, f) {
-		if (!S_ISREG(file_inode(f)->i_mode))
-		       continue;
-		if (!file_count(f))
-			continue;
-		if (!(f->f_mode & FMODE_WRITE))
-			continue;
-		spin_lock(&f->f_lock);
-		f->f_mode &= ~FMODE_WRITE;
-		spin_unlock(&f->f_lock);
-		if (file_check_writeable(f) != 0)
-			continue;
-		__mnt_drop_write(f->f_path.mnt);
-		file_release_write(f);
-	} while_file_list_for_each_entry;
-	lg_global_unlock(&files_lglock);
-}
-
-void __init files_init(unsigned long mempages)
-{ 
 	unsigned long n;
+	unsigned long nr_pages = totalram_pages();
+	unsigned long memreserve = (nr_pages - nr_free_pages()) * 3/2;
 
-	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
-			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+	memreserve = min(memreserve, nr_pages - 1);
+	n = ((nr_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
 
-	/*
-	 * One file with associated inode and dcache is very roughly 1K.
-	 * Per default don't use more than 10% of our memory for files. 
-	 */ 
-
-	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
-	files_defer_init();
-	lg_lock_init(&files_lglock, "files_lglock");
-	percpu_counter_init(&nr_files, 0);
-} 
+}