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()
  ...

5 files changed, 28 insertions, 32 deletions

diff --git a/mm/fadvise.c b/mm/fadvise.c
index 9b75a045dbf4..a47f0f50c89f 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -26,7 +26,7 @@
  */
 SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 {
-	struct file *file = fget(fd);
+	struct fd f = fdget(fd);
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
 	loff_t endbyte;			/* inclusive */
@@ -35,15 +35,15 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 	unsigned long nrpages;
 	int ret = 0;
 
-	if (!file)
+	if (!f.file)
 		return -EBADF;
 
-	if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) {
+	if (S_ISFIFO(f.file->f_path.dentry->d_inode->i_mode)) {
 		ret = -ESPIPE;
 		goto out;
 	}
 
-	mapping = file->f_mapping;
+	mapping = f.file->f_mapping;
 	if (!mapping || len < 0) {
 		ret = -EINVAL;
 		goto out;
@@ -76,21 +76,21 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 
 	switch (advice) {
 	case POSIX_FADV_NORMAL:
-		file->f_ra.ra_pages = bdi->ra_pages;
-		spin_lock(&file->f_lock);
-		file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		f.file->f_ra.ra_pages = bdi->ra_pages;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_RANDOM:
-		spin_lock(&file->f_lock);
-		file->f_mode |= FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode |= FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_SEQUENTIAL:
-		file->f_ra.ra_pages = bdi->ra_pages * 2;
-		spin_lock(&file->f_lock);
-		file->f_mode &= ~FMODE_RANDOM;
-		spin_unlock(&file->f_lock);
+		f.file->f_ra.ra_pages = bdi->ra_pages * 2;
+		spin_lock(&f.file->f_lock);
+		f.file->f_mode &= ~FMODE_RANDOM;
+		spin_unlock(&f.file->f_lock);
 		break;
 	case POSIX_FADV_WILLNEED:
 		/* First and last PARTIAL page! */
@@ -106,7 +106,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		 * Ignore return value because fadvise() shall return
 		 * success even if filesystem can't retrieve a hint,
 		 */
-		force_page_cache_readahead(mapping, file, start_index,
+		force_page_cache_readahead(mapping, f.file, start_index,
 					   nrpages);
 		break;
 	case POSIX_FADV_NOREUSE:
@@ -128,7 +128,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		ret = -EINVAL;
 	}
 out:
-	fput(file);
+	fdput(f);
 	return ret;
 }
 #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
diff --git a/mm/fremap.c b/mm/fremap.c
index 9ed4fd432467..048659c0c03d 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -195,10 +195,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 		 */
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
-			struct file *file = vma->vm_file;
+			struct file *file = get_file(vma->vm_file);
 
 			flags &= MAP_NONBLOCK;
-			get_file(file);
 			addr = mmap_region(file, start, size,
 					flags, vma->vm_flags, pgoff);
 			fput(file);
diff --git a/mm/mmap.c b/mm/mmap.c
index ae18a48e7e4e..872441e81914 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1301,8 +1301,7 @@ munmap_back:
 				goto free_vma;
 			correct_wcount = 1;
 		}
-		vma->vm_file = file;
-		get_file(file);
+		vma->vm_file = get_file(file);
 		error = file->f_op->mmap(file, vma);
 		if (error)
 			goto unmap_and_free_vma;
diff --git a/mm/nommu.c b/mm/nommu.c
index d4b0c10872de..dee2ff89fd58 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1282,10 +1282,8 @@ unsigned long do_mmap_pgoff(struct file *file,
 	vma->vm_pgoff = pgoff;
 
 	if (file) {
-		region->vm_file = file;
-		get_file(file);
-		vma->vm_file = file;
-		get_file(file);
+		region->vm_file = get_file(file);
+		vma->vm_file = get_file(file);
 		if (vm_flags & VM_EXECUTABLE) {
 			added_exe_file_vma(current->mm);
 			vma->vm_mm = current->mm;
diff --git a/mm/readahead.c b/mm/readahead.c
index ea8f8fa21649..7963f2391236 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -579,19 +579,19 @@ do_readahead(struct address_space *mapping, struct file *filp,
 SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
-	struct file *file;
+	struct fd f;
 
 	ret = -EBADF;
-	file = fget(fd);
-	if (file) {
-		if (file->f_mode & FMODE_READ) {
-			struct address_space *mapping = file->f_mapping;
+	f = fdget(fd);
+	if (f.file) {
+		if (f.file->f_mode & FMODE_READ) {
+			struct address_space *mapping = f.file->f_mapping;
 			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
 			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
 			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, file, start, len);
+			ret = do_readahead(mapping, f.file, start, len);
 		}
-		fput(file);
+		fdput(f);
 	}
 	return ret;
 }