1 files changed, 144 insertions, 176 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index 986ff4ed0a7..385bfd31512 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -8,6 +8,7 @@
 #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>
@@ -19,23 +20,32 @@
 #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 <asm/atomic.h>
+#include <linux/atomic.h>
+
+#include "internal.h"
 
 /* sysctl tunables... */
 struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-/* public. Not pretty! */
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);
+/* SLAB cache for file structures */
+static struct kmem_cache *filp_cachep __read_mostly;
 
 static struct percpu_counter nr_files __cacheline_aligned_in_smp;
 
-static inline void file_free_rcu(struct rcu_head *head)
+static void file_free_rcu(struct rcu_head *head)
 {
-	struct file *f =  container_of(head, struct file, f_u.fu_rcuhead);
+	struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
+
+	put_cred(f->f_cred);
 	kmem_cache_free(filp_cachep, f);
 }
 
@@ -48,7 +58,7 @@ static inline void file_free(struct file *f)
 /*
  * Return the total number of open files in the system
  */
-static int get_nr_files(void)
+static long get_nr_files(void)
 {
 	return percpu_counter_read_positive(&nr_files);
 }
@@ -56,7 +66,7 @@ static int get_nr_files(void)
 /*
  * Return the maximum number of open files in the system
  */
-int get_max_files(void)
+unsigned long get_max_files(void)
 {
 	return files_stat.max_files;
 }
@@ -66,14 +76,14 @@ EXPORT_SYMBOL_GPL(get_max_files);
  * Handle nr_files sysctl
  */
 #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
-int proc_nr_files(ctl_table *table, int write, struct file *filp,
+int proc_nr_files(struct ctl_table *table, int write,
                      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	files_stat.nr_files = get_nr_files();
-	return proc_dointvec(table, write, filp, buffer, lenp, ppos);
+	return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 }
 #else
-int proc_nr_files(ctl_table *table, int write, struct file *filp,
+int proc_nr_files(struct ctl_table *table, int write,
                      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	return -ENOSYS;
@@ -81,8 +91,8 @@ int proc_nr_files(ctl_table *table, int write, struct file *filp,
 #endif
 
 /* Find an unused file structure and return a pointer to it.
- * Returns NULL, if there are no more free file structures or
- * we run out of memory.
+ * Returns an error pointer if some error happend e.g. we over file
+ * structures limit, run out of memory or operation is not permitted.
  *
  * Be very careful using this.  You are responsible for
  * getting write access to any mount that you might assign
@@ -92,9 +102,10 @@ int proc_nr_files(ctl_table *table, int write, struct file *filp,
  */
 struct file *get_empty_filp(void)
 {
-	struct task_struct *tsk;
-	static int old_max;
-	struct file * f;
+	const struct cred *cred = current_cred();
+	static long old_max;
+	struct file *f;
+	int error;
 
 	/*
 	 * Privileged users can go above max_files
@@ -109,19 +120,21 @@ struct file *get_empty_filp(void)
 	}
 
 	f = kmem_cache_zalloc(filp_cachep, GFP_KERNEL);
-	if (f == NULL)
-		goto fail;
+	if (unlikely(!f))
+		return ERR_PTR(-ENOMEM);
 
 	percpu_counter_inc(&nr_files);
-	if (security_file_alloc(f))
-		goto fail_sec;
+	f->f_cred = get_cred(cred);
+	error = security_file_alloc(f);
+	if (unlikely(error)) {
+		file_free(f);
+		return ERR_PTR(error);
+	}
 
-	tsk = current;
-	INIT_LIST_HEAD(&f->f_u.fu_list);
-	atomic_set(&f->f_count, 1);
+	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
-	f->f_uid = tsk->fsuid;
-	f->f_gid = tsk->fsgid;
+	spin_lock_init(&f->f_lock);
+	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
 	return f;
@@ -129,20 +142,12 @@ struct file *get_empty_filp(void)
 over:
 	/* Ran out of filps - report that */
 	if (get_nr_files() > old_max) {
-		printk(KERN_INFO "VFS: file-max limit %d reached\n",
-					get_max_files());
+		pr_info("VFS: file-max limit %lu reached\n", get_max_files());
 		old_max = get_nr_files();
 	}
-	goto fail;
-
-fail_sec:
-	file_free(f);
-fail:
-	return NULL;
+	return ERR_PTR(-ENFILE);
 }
 
-EXPORT_SYMBOL(get_empty_filp);
-
 /**
  * alloc_file - allocate and initialize a 'struct file'
  * @mnt: the vfsmount on which the file will reside
@@ -158,67 +163,39 @@ EXPORT_SYMBOL(get_empty_filp);
  * If all the callers of init_file() are eliminated, its
  * code should be moved into this function.
  */
-struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
-		mode_t mode, const struct file_operations *fop)
+struct file *alloc_file(struct path *path, fmode_t mode,
+		const struct file_operations *fop)
 {
 	struct file *file;
-	struct path;
 
 	file = get_empty_filp();
-	if (!file)
-		return NULL;
-
-	init_file(file, mnt, dentry, mode, fop);
-	return file;
-}
-EXPORT_SYMBOL(alloc_file);
-
-/**
- * init_file - initialize a 'struct file'
- * @file: the already allocated 'struct file' to initialized
- * @mnt: the vfsmount on which the file resides
- * @dentry: the dentry representing this file
- * @mode: the mode the file is opened with
- * @fop: the 'struct file_operations' for this file
- *
- * Use this instead of setting the members directly.  Doing so
- * avoids making mistakes like forgetting the mntget() or
- * forgetting to take a write on the mnt.
- *
- * Note: This is a crappy interface.  It is here to make
- * merging with the existing users of get_empty_filp()
- * who have complex failure logic easier.  All users
- * of this should be moving to alloc_file().
- */
-int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
-	   mode_t mode, const struct file_operations *fop)
-{
-	int error = 0;
-	file->f_path.dentry = dentry;
-	file->f_path.mnt = mntget(mnt);
-	file->f_mapping = dentry->d_inode->i_mapping;
+	if (IS_ERR(file))
+		return file;
+
+	file->f_path = *path;
+	file->f_inode = path->dentry->d_inode;
+	file->f_mapping = path->dentry->d_inode->i_mapping;
+	if ((mode & FMODE_READ) &&
+	     likely(fop->read || fop->aio_read || fop->read_iter))
+		mode |= FMODE_CAN_READ;
+	if ((mode & FMODE_WRITE) &&
+	     likely(fop->write || fop->aio_write || fop->write_iter))
+		mode |= FMODE_CAN_WRITE;
 	file->f_mode = mode;
 	file->f_op = fop;
-	return error;
-}
-EXPORT_SYMBOL(init_file);
-
-void fput(struct file *file)
-{
-	if (atomic_dec_and_test(&file->f_count))
-		__fput(file);
+	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_inc(path->dentry->d_inode);
+	return file;
 }
+EXPORT_SYMBOL(alloc_file);
 
-EXPORT_SYMBOL(fput);
-
-/* __fput is called from task context when aio completion releases the last
- * last use of a struct file *.  Do not use otherwise.
+/* the real guts of fput() - releasing the last reference to file
  */
-void __fput(struct file *file)
+static void __fput(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct vfsmount *mnt = file->f_path.mnt;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = file->f_inode;
 
 	might_sleep();
 
@@ -228,140 +205,131 @@ void __fput(struct file *file)
 	 * in the file cleanup chain.
 	 */
 	eventpoll_release(file);
-	locks_remove_flock(file);
+	locks_remove_file(file);
 
-	if (file->f_op && file->f_op->release)
+	if (unlikely(file->f_flags & FASYNC)) {
+		if (file->f_op->fasync)
+			file->f_op->fasync(-1, file, 0);
+	}
+	ima_file_free(file);
+	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))
+	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
+		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
+	}
 	fops_put(file->f_op);
-	if (file->f_mode & FMODE_WRITE)
-		put_write_access(inode);
 	put_pid(file->f_owner.pid);
-	file_kill(file);
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+		i_readcount_dec(inode);
+	if (file->f_mode & FMODE_WRITER) {
+		put_write_access(inode);
+		__mnt_drop_write(mnt);
+	}
 	file->f_path.dentry = NULL;
 	file->f_path.mnt = NULL;
+	file->f_inode = NULL;
 	file_free(file);
 	dput(dentry);
 	mntput(mnt);
 }
 
-struct file *fget(unsigned int fd)
+static LLIST_HEAD(delayed_fput_list);
+static void delayed_fput(struct work_struct *unused)
 {
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	rcu_read_lock();
-	file = fcheck_files(files, fd);
-	if (file) {
-		if (!atomic_inc_not_zero(&file->f_count)) {
-			/* File object ref couldn't be taken */
-			rcu_read_unlock();
-			return NULL;
-		}
-	}
-	rcu_read_unlock();
+	struct llist_node *node = llist_del_all(&delayed_fput_list);
+	struct llist_node *next;
 
-	return file;
+	for (; node; node = next) {
+		next = llist_next(node);
+		__fput(llist_entry(node, struct file, f_u.fu_llist));
+	}
 }
 
-EXPORT_SYMBOL(fget);
+static void ____fput(struct callback_head *work)
+{
+	__fput(container_of(work, struct file, f_u.fu_rcuhead));
+}
 
 /*
- * Lightweight file lookup - no refcnt increment if fd table isn't shared. 
- * You can use this only if it is guranteed that the current task already 
- * holds a refcnt to that file. That check has to be done at fget() only
- * and a flag is returned to be passed to the corresponding fput_light().
- * There must not be a cloning between an fget_light/fput_light pair.
+ * 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
+ * *do* need to make sure our writes to binaries on initramfs has
+ * not left us with opened struct file waiting for __fput() - execve()
+ * won't work without that.  Please, don't add more callers without
+ * very good reasons; in particular, never call that with locks
+ * held and never call that from a thread that might need to do
+ * some work on any kind of umount.
  */
-struct file *fget_light(unsigned int fd, int *fput_needed)
+void flush_delayed_fput(void)
 {
-	struct file *file;
-	struct files_struct *files = current->files;
-
-	*fput_needed = 0;
-	if (likely((atomic_read(&files->count) == 1))) {
-		file = fcheck_files(files, fd);
-	} else {
-		rcu_read_lock();
-		file = fcheck_files(files, fd);
-		if (file) {
-			if (atomic_inc_not_zero(&file->f_count))
-				*fput_needed = 1;
-			else
-				/* Didn't get the reference, someone's freed */
-				file = NULL;
-		}
-		rcu_read_unlock();
-	}
-
-	return file;
+	delayed_fput(NULL);
 }
 
+static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
-void put_filp(struct file *file)
+void fput(struct file *file)
 {
-	if (atomic_dec_and_test(&file->f_count)) {
-		security_file_free(file);
-		file_kill(file);
-		file_free(file);
-	}
-}
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+
+		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.  Fall through to delayed
+			 * fput to avoid leaking *file.
+			 */
+		}
 
-void file_move(struct file *file, struct list_head *list)
-{
-	if (!list)
-		return;
-	file_list_lock();
-	list_move(&file->f_u.fu_list, list);
-	file_list_unlock();
+		if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
+			schedule_delayed_work(&delayed_fput_work, 1);
+	}
 }
 
-void file_kill(struct file *file)
+/*
+ * synchronous analog of fput(); for kernel threads that might be needed
+ * in some umount() (and thus can't use flush_delayed_fput() without
+ * risking deadlocks), need to wait for completion of __fput() and know
+ * for this specific struct file it won't involve anything that would
+ * need them.  Use only if you really need it - at the very least,
+ * don't blindly convert fput() by kernel thread to that.
+ */
+void __fput_sync(struct file *file)
 {
-	if (!list_empty(&file->f_u.fu_list)) {
-		file_list_lock();
-		list_del_init(&file->f_u.fu_list);
-		file_list_unlock();
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		struct task_struct *task = current;
+		BUG_ON(!(task->flags & PF_KTHREAD));
+		__fput(file);
 	}
 }
 
-int fs_may_remount_ro(struct super_block *sb)
-{
-	struct file *file;
-
-	/* Check that no files are currently opened for writing. */
-	file_list_lock();
-	list_for_each_entry(file, &sb->s_files, f_u.fu_list) {
-		struct inode *inode = file->f_path.dentry->d_inode;
-
-		/* File with pending delete? */
-		if (inode->i_nlink == 0)
-			goto too_bad;
+EXPORT_SYMBOL(fput);
 
-		/* Writeable file? */
-		if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE))
-			goto too_bad;
+void put_filp(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count)) {
+		security_file_free(file);
+		file_free(file);
 	}
-	file_list_unlock();
-	return 1; /* Tis' cool bro. */
-too_bad:
-	file_list_unlock();
-	return 0;
 }
 
 void __init files_init(unsigned long mempages)
 { 
-	int n; 
-	/* One file with associated inode and dcache is very roughly 1K. 
+	unsigned long n;
+
+	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
+			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+
+	/*
+	 * 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 = n; 
-	if (files_stat.max_files < NR_FILE)
-		files_stat.max_files = NR_FILE;
-	files_defer_init();
+	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	percpu_counter_init(&nr_files, 0);
 }