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

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...

4 files changed, 44 insertions, 150 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index deec4e50eb3..f16f3c58f11 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -468,14 +468,13 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 {
 	struct perf_cgroup *cgrp;
 	struct cgroup_subsys_state *css;
-	struct file *file;
-	int ret = 0, fput_needed;
+	struct fd f = fdget(fd);
+	int ret = 0;
 
-	file = fget_light(fd, &fput_needed);
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
-	css = cgroup_css_from_dir(file, perf_subsys_id);
+	css = cgroup_css_from_dir(f.file, perf_subsys_id);
 	if (IS_ERR(css)) {
 		ret = PTR_ERR(css);
 		goto out;
@@ -501,7 +500,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event,
 		ret = -EINVAL;
 	}
 out:
-	fput_light(file, fput_needed);
+	fdput(f);
 	return ret;
 }
 
@@ -3234,21 +3233,18 @@ unlock:
 
 static const struct file_operations perf_fops;
 
-static struct file *perf_fget_light(int fd, int *fput_needed)
+static inline int perf_fget_light(int fd, struct fd *p)
 {
-	struct file *file;
-
-	file = fget_light(fd, fput_needed);
-	if (!file)
-		return ERR_PTR(-EBADF);
+	struct fd f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
 
-	if (file->f_op != &perf_fops) {
-		fput_light(file, *fput_needed);
-		*fput_needed = 0;
-		return ERR_PTR(-EBADF);
+	if (f.file->f_op != &perf_fops) {
+		fdput(f);
+		return -EBADF;
 	}
-
-	return file;
+	*p = f;
+	return 0;
 }
 
 static int perf_event_set_output(struct perf_event *event,
@@ -3280,22 +3276,19 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 	case PERF_EVENT_IOC_SET_OUTPUT:
 	{
-		struct file *output_file = NULL;
-		struct perf_event *output_event = NULL;
-		int fput_needed = 0;
 		int ret;
-
 		if (arg != -1) {
-			output_file = perf_fget_light(arg, &fput_needed);
-			if (IS_ERR(output_file))
-				return PTR_ERR(output_file);
-			output_event = output_file->private_data;
+			struct perf_event *output_event;
+			struct fd output;
+			ret = perf_fget_light(arg, &output);
+			if (ret)
+				return ret;
+			output_event = output.file->private_data;
+			ret = perf_event_set_output(event, output_event);
+			fdput(output);
+		} else {
+			ret = perf_event_set_output(event, NULL);
 		}
-
-		ret = perf_event_set_output(event, output_event);
-		if (output_event)
-			fput_light(output_file, fput_needed);
-
 		return ret;
 	}
 
@@ -6443,12 +6436,11 @@ SYSCALL_DEFINE5(perf_event_open,
 	struct perf_event_attr attr;
 	struct perf_event_context *ctx;
 	struct file *event_file = NULL;
-	struct file *group_file = NULL;
+	struct fd group = {NULL, 0};
 	struct task_struct *task = NULL;
 	struct pmu *pmu;
 	int event_fd;
 	int move_group = 0;
-	int fput_needed = 0;
 	int err;
 
 	/* for future expandability... */
@@ -6478,17 +6470,15 @@ SYSCALL_DEFINE5(perf_event_open,
 	if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1))
 		return -EINVAL;
 
-	event_fd = get_unused_fd_flags(O_RDWR);
+	event_fd = get_unused_fd();
 	if (event_fd < 0)
 		return event_fd;
 
 	if (group_fd != -1) {
-		group_file = perf_fget_light(group_fd, &fput_needed);
-		if (IS_ERR(group_file)) {
-			err = PTR_ERR(group_file);
+		err = perf_fget_light(group_fd, &group);
+		if (err)
 			goto err_fd;
-		}
-		group_leader = group_file->private_data;
+		group_leader = group.file->private_data;
 		if (flags & PERF_FLAG_FD_OUTPUT)
 			output_event = group_leader;
 		if (flags & PERF_FLAG_FD_NO_GROUP)
@@ -6664,7 +6654,7 @@ SYSCALL_DEFINE5(perf_event_open,
 	 * of the group leader will find the pointer to itself in
 	 * perf_group_detach().
 	 */
-	fput_light(group_file, fput_needed);
+	fdput(group);
 	fd_install(event_fd, event_file);
 	return event_fd;
 
@@ -6678,7 +6668,7 @@ err_task:
 	if (task)
 		put_task_struct(task);
 err_group_fd:
-	fput_light(group_file, fput_needed);
+	fdput(group);
 err_fd:
 	put_unused_fd(event_fd);
 	return err;
diff --git a/kernel/exit.c b/kernel/exit.c
index 42f25952edd..346616c0092 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -457,108 +457,13 @@ void daemonize(const char *name, ...)
 	/* Become as one with the init task */
 
 	daemonize_fs_struct();
-	exit_files(current);
-	current->files = init_task.files;
-	atomic_inc(&current->files->count);
+	daemonize_descriptors();
 
 	reparent_to_kthreadd();
 }
 
 EXPORT_SYMBOL(daemonize);
 
-static void close_files(struct files_struct * files)
-{
-	int i, j;
-	struct fdtable *fdt;
-
-	j = 0;
-
-	/*
-	 * It is safe to dereference the fd table without RCU or
-	 * ->file_lock because this is the last reference to the
-	 * files structure.  But use RCU to shut RCU-lockdep up.
-	 */
-	rcu_read_lock();
-	fdt = files_fdtable(files);
-	rcu_read_unlock();
-	for (;;) {
-		unsigned long set;
-		i = j * BITS_PER_LONG;
-		if (i >= fdt->max_fds)
-			break;
-		set = fdt->open_fds[j++];
-		while (set) {
-			if (set & 1) {
-				struct file * file = xchg(&fdt->fd[i], NULL);
-				if (file) {
-					filp_close(file, files);
-					cond_resched();
-				}
-			}
-			i++;
-			set >>= 1;
-		}
-	}
-}
-
-struct files_struct *get_files_struct(struct task_struct *task)
-{
-	struct files_struct *files;
-
-	task_lock(task);
-	files = task->files;
-	if (files)
-		atomic_inc(&files->count);
-	task_unlock(task);
-
-	return files;
-}
-
-void put_files_struct(struct files_struct *files)
-{
-	struct fdtable *fdt;
-
-	if (atomic_dec_and_test(&files->count)) {
-		close_files(files);
-		/*
-		 * Free the fd and fdset arrays if we expanded them.
-		 * If the fdtable was embedded, pass files for freeing
-		 * at the end of the RCU grace period. Otherwise,
-		 * you can free files immediately.
-		 */
-		rcu_read_lock();
-		fdt = files_fdtable(files);
-		if (fdt != &files->fdtab)
-			kmem_cache_free(files_cachep, files);
-		free_fdtable(fdt);
-		rcu_read_unlock();
-	}
-}
-
-void reset_files_struct(struct files_struct *files)
-{
-	struct task_struct *tsk = current;
-	struct files_struct *old;
-
-	old = tsk->files;
-	task_lock(tsk);
-	tsk->files = files;
-	task_unlock(tsk);
-	put_files_struct(old);
-}
-
-void exit_files(struct task_struct *tsk)
-{
-	struct files_struct * files = tsk->files;
-
-	if (files) {
-		task_lock(tsk);
-		tsk->files = NULL;
-		task_unlock(tsk);
-		put_files_struct(files);
-	}
-}
-
 #ifdef CONFIG_MM_OWNER
 /*
  * A task is exiting.   If it owned this mm, find a new owner for the mm.
diff --git a/kernel/sys.c b/kernel/sys.c
index 241507f23ec..f9492284e5d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1788,15 +1788,15 @@ SYSCALL_DEFINE1(umask, int, mask)
 #ifdef CONFIG_CHECKPOINT_RESTORE
 static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 {
-	struct file *exe_file;
+	struct fd exe;
 	struct dentry *dentry;
 	int err;
 
-	exe_file = fget(fd);
-	if (!exe_file)
+	exe = fdget(fd);
+	if (!exe.file)
 		return -EBADF;
 
-	dentry = exe_file->f_path.dentry;
+	dentry = exe.file->f_path.dentry;
 
 	/*
 	 * Because the original mm->exe_file points to executable file, make
@@ -1805,7 +1805,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 	 */
 	err = -EACCES;
 	if (!S_ISREG(dentry->d_inode->i_mode)	||
-	    exe_file->f_path.mnt->mnt_flags & MNT_NOEXEC)
+	    exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC)
 		goto exit;
 
 	err = inode_permission(dentry->d_inode, MAY_EXEC);
@@ -1839,12 +1839,12 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
 		goto exit_unlock;
 
 	err = 0;
-	set_mm_exe_file(mm, exe_file);
+	set_mm_exe_file(mm, exe.file);	/* this grabs a reference to exe.file */
 exit_unlock:
 	up_write(&mm->mmap_sem);
 
 exit:
-	fput(exe_file);
+	fdput(exe);
 	return err;
 }
 
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 5eab1f3edfa..610f0838d55 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -424,16 +424,15 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *na;
 	size_t size;
 	u32 fd;
-	struct file *file;
-	int fput_needed;
+	struct fd f;
 
 	na = info->attrs[CGROUPSTATS_CMD_ATTR_FD];
 	if (!na)
 		return -EINVAL;
 
 	fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]);
-	file = fget_light(fd, &fput_needed);
-	if (!file)
+	f = fdget(fd);
+	if (!f.file)
 		return 0;
 
 	size = nla_total_size(sizeof(struct cgroupstats));
@@ -453,7 +452,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	stats = nla_data(na);
 	memset(stats, 0, sizeof(*stats));
 
-	rc = cgroupstats_build(stats, file->f_dentry);
+	rc = cgroupstats_build(stats, f.file->f_dentry);
 	if (rc < 0) {
 		nlmsg_free(rep_skb);
 		goto err;
@@ -462,7 +461,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
 	rc = send_reply(rep_skb, info);
 
 err:
-	fput_light(file, fput_needed);
+	fdput(f);
 	return rc;
 }