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()
  ...

6 files changed, 83 insertions, 70 deletions

diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 505f0ce3f10b..15656b8573f3 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -793,30 +793,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 {
 	struct p9_trans_fd *p;
-	int ret, fd;
+	struct file *file;
+	int ret;
 
 	p = kmalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	csocket->sk->sk_allocation = GFP_NOIO;
-	fd = sock_map_fd(csocket, 0);
-	if (fd < 0) {
+	file = sock_alloc_file(csocket, 0, NULL);
+	if (IS_ERR(file)) {
 		pr_err("%s (%d): failed to map fd\n",
 		       __func__, task_pid_nr(current));
 		sock_release(csocket);
 		kfree(p);
-		return fd;
+		return PTR_ERR(file);
 	}
 
-	get_file(csocket->file);
-	get_file(csocket->file);
-	p->wr = p->rd = csocket->file;
+	get_file(file);
+	p->wr = p->rd = file;
 	client->trans = p;
 	client->status = Connected;
 
-	sys_close(fd);	/* still racy */
-
 	p->rd->f_flags |= O_NONBLOCK;
 
 	p->conn = p9_conn_create(client);
diff --git a/net/compat.c b/net/compat.c
index 74ed1d7a84a2..79ae88485001 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -301,8 +301,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
-		get_file(fp[i]);
-		fd_install(new_fd, fp[i]);
+		fd_install(new_fd, get_file(fp[i]));
 	}
 
 	if (i > 0) {
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 4a83fb3c8e87..79285a36035f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -239,38 +239,24 @@ out_free_devname:
 	return ret;
 }
 
+static int update_netprio(const void *v, struct file *file, unsigned n)
+{
+	int err;
+	struct socket *sock = sock_from_file(file, &err);
+	if (sock)
+		sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
+	return 0;
+}
+
 void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
+	void *v;
 
 	cgroup_taskset_for_each(p, cgrp, tset) {
-		unsigned int fd;
-		struct fdtable *fdt;
-		struct files_struct *files;
-
 		task_lock(p);
-		files = p->files;
-		if (!files) {
-			task_unlock(p);
-			continue;
-		}
-
-		spin_lock(&files->file_lock);
-		fdt = files_fdtable(files);
-		for (fd = 0; fd < fdt->max_fds; fd++) {
-			struct file *file;
-			struct socket *sock;
-			int err;
-
-			file = fcheck_files(files, fd);
-			if (!file)
-				continue;
-
-			sock = sock_from_file(file, &err);
-			if (sock)
-				sock_update_netprioidx(sock->sk, p);
-		}
-		spin_unlock(&files->file_lock);
+		v = (void *)(unsigned long)task_netprioidx(p);
+		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
 	}
 }
diff --git a/net/core/scm.c b/net/core/scm.c
index 9c1c63da3ca8..ab570841a532 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -301,11 +301,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
-		get_file(fp[i]);
 		sock = sock_from_file(fp[i], &err);
 		if (sock)
 			sock_update_netprioidx(sock->sk, current);
-		fd_install(new_fd, fp[i]);
+		fd_install(new_fd, get_file(fp[i]));
 	}
 
 	if (i > 0)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d37d24ff197f..59d16ea927f0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -70,6 +70,7 @@
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
+#include <linux/file.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -4292,6 +4293,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 {
 	sctp_peeloff_arg_t peeloff;
 	struct socket *newsock;
+	struct file *newfile;
 	int retval = 0;
 
 	if (len < sizeof(sctp_peeloff_arg_t))
@@ -4305,22 +4307,35 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 		goto out;
 
 	/* Map the socket to an unused fd that can be returned to the user.  */
-	retval = sock_map_fd(newsock, 0);
+	retval = get_unused_fd();
 	if (retval < 0) {
 		sock_release(newsock);
 		goto out;
 	}
 
+	newfile = sock_alloc_file(newsock, 0, NULL);
+	if (unlikely(IS_ERR(newfile))) {
+		put_unused_fd(retval);
+		sock_release(newsock);
+		return PTR_ERR(newfile);
+	}
+
 	SCTP_DEBUG_PRINTK("%s: sk: %p newsk: %p sd: %d\n",
 			  __func__, sk, newsock->sk, retval);
 
 	/* Return the fd mapped to the new socket.  */
+	if (put_user(len, optlen)) {
+		fput(newfile);
+		put_unused_fd(retval);
+		return -EFAULT;
+	}
 	peeloff.sd = retval;
-	if (put_user(len, optlen))
+	if (copy_to_user(optval, &peeloff, len)) {
+		fput(newfile);
+		put_unused_fd(retval);
 		return -EFAULT;
-	if (copy_to_user(optval, &peeloff, len))
-		retval = -EFAULT;
-
+	}
+	fd_install(retval, newfile);
 out:
 	return retval;
 }
diff --git a/net/socket.c b/net/socket.c
index 80dc7e84b046..d92c490e66fa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -347,17 +347,11 @@ static struct file_system_type sock_fs_type = {
  *	but we take care of internal coherence yet.
  */
 
-static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
-			   const char *dname)
+struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
 	struct qstr name = { .name = "" };
 	struct path path;
 	struct file *file;
-	int fd;
-
-	fd = get_unused_fd_flags(flags);
-	if (unlikely(fd < 0))
-		return fd;
 
 	if (dname) {
 		name.name = dname;
@@ -367,10 +361,8 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
 		name.len = strlen(name.name);
 	}
 	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
-	if (unlikely(!path.dentry)) {
-		put_unused_fd(fd);
-		return -ENOMEM;
-	}
+	if (unlikely(!path.dentry))
+		return ERR_PTR(-ENOMEM);
 	path.mnt = mntget(sock_mnt);
 
 	d_instantiate(path.dentry, SOCK_INODE(sock));
@@ -382,30 +374,33 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
 		/* drop dentry, keep inode */
 		ihold(path.dentry->d_inode);
 		path_put(&path);
-		put_unused_fd(fd);
-		return -ENFILE;
+		return ERR_PTR(-ENFILE);
 	}
 
 	sock->file = file;
 	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
 	file->f_pos = 0;
 	file->private_data = sock;
-
-	*f = file;
-	return fd;
+	return file;
 }
+EXPORT_SYMBOL(sock_alloc_file);
 
-int sock_map_fd(struct socket *sock, int flags)
+static int sock_map_fd(struct socket *sock, int flags)
 {
 	struct file *newfile;
-	int fd = sock_alloc_file(sock, &newfile, flags, NULL);
+	int fd = get_unused_fd_flags(flags);
+	if (unlikely(fd < 0))
+		return fd;
 
-	if (likely(fd >= 0))
+	newfile = sock_alloc_file(sock, flags, NULL);
+	if (likely(!IS_ERR(newfile))) {
 		fd_install(fd, newfile);
+		return fd;
+	}
 
-	return fd;
+	put_unused_fd(fd);
+	return PTR_ERR(newfile);
 }
-EXPORT_SYMBOL(sock_map_fd);
 
 struct socket *sock_from_file(struct file *file, int *err)
 {
@@ -1466,17 +1461,32 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
 	if (err < 0)
 		goto out_release_both;
 
-	fd1 = sock_alloc_file(sock1, &newfile1, flags, NULL);
+	fd1 = get_unused_fd_flags(flags);
 	if (unlikely(fd1 < 0)) {
 		err = fd1;
 		goto out_release_both;
 	}
-
-	fd2 = sock_alloc_file(sock2, &newfile2, flags, NULL);
+	fd2 = get_unused_fd_flags(flags);
 	if (unlikely(fd2 < 0)) {
 		err = fd2;
+		put_unused_fd(fd1);
+		goto out_release_both;
+	}
+
+	newfile1 = sock_alloc_file(sock1, flags, NULL);
+	if (unlikely(IS_ERR(newfile1))) {
+		err = PTR_ERR(newfile1);
+		put_unused_fd(fd1);
+		put_unused_fd(fd2);
+		goto out_release_both;
+	}
+
+	newfile2 = sock_alloc_file(sock2, flags, NULL);
+	if (IS_ERR(newfile2)) {
+		err = PTR_ERR(newfile2);
 		fput(newfile1);
 		put_unused_fd(fd1);
+		put_unused_fd(fd2);
 		sock_release(sock2);
 		goto out;
 	}
@@ -1608,13 +1618,19 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 	 */
 	__module_get(newsock->ops->owner);
 
-	newfd = sock_alloc_file(newsock, &newfile, flags,
-				sock->sk->sk_prot_creator->name);
+	newfd = get_unused_fd_flags(flags);
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);
 		goto out_put;
 	}
+	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
+	if (unlikely(IS_ERR(newfile))) {
+		err = PTR_ERR(newfile);
+		put_unused_fd(newfd);
+		sock_release(newsock);
+		goto out_put;
+	}
 
 	err = security_socket_accept(sock, newsock);
 	if (err)