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()
  ...

1 files changed, 79 insertions, 101 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 1adfb691e4f1..d06534857e9e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -232,23 +232,18 @@ EXPORT_SYMBOL(vfs_llseek);
 SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, origin)
 {
 	off_t retval;
-	struct file * file;
-	int fput_needed;
-
-	retval = -EBADF;
-	file = fget_light(fd, &fput_needed);
-	if (!file)
-		goto bad;
+	struct fd f = fdget(fd);
+	if (!f.file)
+		return -EBADF;
 
 	retval = -EINVAL;
 	if (origin <= SEEK_MAX) {
-		loff_t res = vfs_llseek(file, offset, origin);
+		loff_t res = vfs_llseek(f.file, offset, origin);
 		retval = res;
 		if (res != (loff_t)retval)
 			retval = -EOVERFLOW;	/* LFS: should only happen on 32 bit platforms */
 	}
-	fput_light(file, fput_needed);
-bad:
+	fdput(f);
 	return retval;
 }
 
@@ -258,20 +253,17 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 		unsigned int, origin)
 {
 	int retval;
-	struct file * file;
+	struct fd f = fdget(fd);
 	loff_t offset;
-	int fput_needed;
 
-	retval = -EBADF;
-	file = fget_light(fd, &fput_needed);
-	if (!file)
-		goto bad;
+	if (!f.file)
+		return -EBADF;
 
 	retval = -EINVAL;
 	if (origin > SEEK_MAX)
 		goto out_putf;
 
-	offset = vfs_llseek(file, ((loff_t) offset_high << 32) | offset_low,
+	offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low,
 			origin);
 
 	retval = (int)offset;
@@ -281,8 +273,7 @@ SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high,
 			retval = 0;
 	}
 out_putf:
-	fput_light(file, fput_needed);
-bad:
+	fdput(f);
 	return retval;
 }
 #endif
@@ -461,34 +452,29 @@ static inline void file_pos_write(struct file *file, loff_t pos)
 
 SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
-		loff_t pos = file_pos_read(file);
-		ret = vfs_read(file, buf, count, &pos);
-		file_pos_write(file, pos);
-		fput_light(file, fput_needed);
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_read(f.file, buf, count, &pos);
+		file_pos_write(f.file, pos);
+		fdput(f);
 	}
-
 	return ret;
 }
 
 SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 		size_t, count)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
-		loff_t pos = file_pos_read(file);
-		ret = vfs_write(file, buf, count, &pos);
-		file_pos_write(file, pos);
-		fput_light(file, fput_needed);
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_write(f.file, buf, count, &pos);
+		file_pos_write(f.file, pos);
+		fdput(f);
 	}
 
 	return ret;
@@ -497,19 +483,18 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
 SYSCALL_DEFINE(pread64)(unsigned int fd, char __user *buf,
 			size_t count, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
+	f = fdget(fd);
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PREAD)
-			ret = vfs_read(file, buf, count, &pos);
-		fput_light(file, fput_needed);
+		if (f.file->f_mode & FMODE_PREAD)
+			ret = vfs_read(f.file, buf, count, &pos);
+		fdput(f);
 	}
 
 	return ret;
@@ -526,19 +511,18 @@ SYSCALL_ALIAS(sys_pread64, SyS_pread64);
 SYSCALL_DEFINE(pwrite64)(unsigned int fd, const char __user *buf,
 			 size_t count, loff_t pos)
 {
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
+	f = fdget(fd);
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PWRITE)  
-			ret = vfs_write(file, buf, count, &pos);
-		fput_light(file, fput_needed);
+		if (f.file->f_mode & FMODE_PWRITE)  
+			ret = vfs_write(f.file, buf, count, &pos);
+		fdput(f);
 	}
 
 	return ret;
@@ -789,16 +773,14 @@ EXPORT_SYMBOL(vfs_writev);
 SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
-		loff_t pos = file_pos_read(file);
-		ret = vfs_readv(file, vec, vlen, &pos);
-		file_pos_write(file, pos);
-		fput_light(file, fput_needed);
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_readv(f.file, vec, vlen, &pos);
+		file_pos_write(f.file, pos);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -810,16 +792,14 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
 SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen)
 {
-	struct file *file;
+	struct fd f = fdget(fd);
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
-		loff_t pos = file_pos_read(file);
-		ret = vfs_writev(file, vec, vlen, &pos);
-		file_pos_write(file, pos);
-		fput_light(file, fput_needed);
+	if (f.file) {
+		loff_t pos = file_pos_read(f.file);
+		ret = vfs_writev(f.file, vec, vlen, &pos);
+		file_pos_write(f.file, pos);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -838,19 +818,18 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
 {
 	loff_t pos = pos_from_hilo(pos_h, pos_l);
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
+	f = fdget(fd);
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PREAD)
-			ret = vfs_readv(file, vec, vlen, &pos);
-		fput_light(file, fput_needed);
+		if (f.file->f_mode & FMODE_PREAD)
+			ret = vfs_readv(f.file, vec, vlen, &pos);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -863,19 +842,18 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
 {
 	loff_t pos = pos_from_hilo(pos_h, pos_l);
-	struct file *file;
+	struct fd f;
 	ssize_t ret = -EBADF;
-	int fput_needed;
 
 	if (pos < 0)
 		return -EINVAL;
 
-	file = fget_light(fd, &fput_needed);
-	if (file) {
+	f = fdget(fd);
+	if (f.file) {
 		ret = -ESPIPE;
-		if (file->f_mode & FMODE_PWRITE)
-			ret = vfs_writev(file, vec, vlen, &pos);
-		fput_light(file, fput_needed);
+		if (f.file->f_mode & FMODE_PWRITE)
+			ret = vfs_writev(f.file, vec, vlen, &pos);
+		fdput(f);
 	}
 
 	if (ret > 0)
@@ -884,31 +862,31 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
-static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
-			   size_t count, loff_t max)
+ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count,
+		    loff_t max)
 {
-	struct file * in_file, * out_file;
-	struct inode * in_inode, * out_inode;
+	struct fd in, out;
+	struct inode *in_inode, *out_inode;
 	loff_t pos;
 	ssize_t retval;
-	int fput_needed_in, fput_needed_out, fl;
+	int fl;
 
 	/*
 	 * Get input file, and verify that it is ok..
 	 */
 	retval = -EBADF;
-	in_file = fget_light(in_fd, &fput_needed_in);
-	if (!in_file)
+	in = fdget(in_fd);
+	if (!in.file)
 		goto out;
-	if (!(in_file->f_mode & FMODE_READ))
+	if (!(in.file->f_mode & FMODE_READ))
 		goto fput_in;
 	retval = -ESPIPE;
 	if (!ppos)
-		ppos = &in_file->f_pos;
+		ppos = &in.file->f_pos;
 	else
-		if (!(in_file->f_mode & FMODE_PREAD))
+		if (!(in.file->f_mode & FMODE_PREAD))
 			goto fput_in;
-	retval = rw_verify_area(READ, in_file, ppos, count);
+	retval = rw_verify_area(READ, in.file, ppos, count);
 	if (retval < 0)
 		goto fput_in;
 	count = retval;
@@ -917,15 +895,15 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	 * Get output file, and verify that it is ok..
 	 */
 	retval = -EBADF;
-	out_file = fget_light(out_fd, &fput_needed_out);
-	if (!out_file)
+	out = fdget(out_fd);
+	if (!out.file)
 		goto fput_in;
-	if (!(out_file->f_mode & FMODE_WRITE))
+	if (!(out.file->f_mode & FMODE_WRITE))
 		goto fput_out;
 	retval = -EINVAL;
-	in_inode = in_file->f_path.dentry->d_inode;
-	out_inode = out_file->f_path.dentry->d_inode;
-	retval = rw_verify_area(WRITE, out_file, &out_file->f_pos, count);
+	in_inode = in.file->f_path.dentry->d_inode;
+	out_inode = out.file->f_path.dentry->d_inode;
+	retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
 	if (retval < 0)
 		goto fput_out;
 	count = retval;
@@ -949,10 +927,10 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	 * and the application is arguably buggy if it doesn't expect
 	 * EAGAIN on a non-blocking file descriptor.
 	 */
-	if (in_file->f_flags & O_NONBLOCK)
+	if (in.file->f_flags & O_NONBLOCK)
 		fl = SPLICE_F_NONBLOCK;
 #endif
-	retval = do_splice_direct(in_file, ppos, out_file, count, fl);
+	retval = do_splice_direct(in.file, ppos, out.file, count, fl);
 
 	if (retval > 0) {
 		add_rchar(current, retval);
@@ -965,9 +943,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 		retval = -EOVERFLOW;
 
 fput_out:
-	fput_light(out_file, fput_needed_out);
+	fdput(out);
 fput_in:
-	fput_light(in_file, fput_needed_in);
+	fdput(in);
 out:
 	return retval;
 }