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()
  ...

11 files changed, 67 insertions, 176 deletions

diff --git a/drivers/base/dma-buf.c b/drivers/base/dma-buf.c
index c30f3e1d0efc..460e22dee36d 100644
--- a/drivers/base/dma-buf.c
+++ b/drivers/base/dma-buf.c
@@ -460,8 +460,7 @@ int dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma,
 	if (vma->vm_file)
 		fput(vma->vm_file);
 
-	vma->vm_file = dmabuf->file;
-	get_file(vma->vm_file);
+	vma->vm_file = get_file(dmabuf->file);
 
 	vma->vm_pgoff = pgoff;
 
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7972bae2e9b3..2709ff581392 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1183,7 +1183,7 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file,
 	struct rdma_ucm_migrate_id cmd;
 	struct rdma_ucm_migrate_resp resp;
 	struct ucma_context *ctx;
-	struct file *filp;
+	struct fd f;
 	struct ucma_file *cur_file;
 	int ret = 0;
 
@@ -1191,12 +1191,12 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file,
 		return -EFAULT;
 
 	/* Get current fd to protect against it being closed */
-	filp = fget(cmd.fd);
-	if (!filp)
+	f = fdget(cmd.fd);
+	if (!f.file)
 		return -ENOENT;
 
 	/* Validate current fd and prevent destruction of id. */
-	ctx = ucma_get_ctx(filp->private_data, cmd.id);
+	ctx = ucma_get_ctx(f.file->private_data, cmd.id);
 	if (IS_ERR(ctx)) {
 		ret = PTR_ERR(ctx);
 		goto file_put;
@@ -1230,7 +1230,7 @@ response:
 
 	ucma_put_ctx(ctx);
 file_put:
-	fput(filp);
+	fdput(f);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index f9d0d7c413a2..0cb0007724a2 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -705,7 +705,7 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 	struct ib_udata			udata;
 	struct ib_uxrcd_object         *obj;
 	struct ib_xrcd                 *xrcd = NULL;
-	struct file                    *f = NULL;
+	struct fd			f = {NULL, 0};
 	struct inode                   *inode = NULL;
 	int				ret = 0;
 	int				new_xrcd = 0;
@@ -724,18 +724,13 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 
 	if (cmd.fd != -1) {
 		/* search for file descriptor */
-		f = fget(cmd.fd);
-		if (!f) {
-			ret = -EBADF;
-			goto err_tree_mutex_unlock;
-		}
-
-		inode = f->f_dentry->d_inode;
-		if (!inode) {
+		f = fdget(cmd.fd);
+		if (!f.file) {
 			ret = -EBADF;
 			goto err_tree_mutex_unlock;
 		}
 
+		inode = f.file->f_path.dentry->d_inode;
 		xrcd = find_xrcd(file->device, inode);
 		if (!xrcd && !(cmd.oflags & O_CREAT)) {
 			/* no file descriptor. Need CREATE flag */
@@ -800,8 +795,8 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 		goto err_copy;
 	}
 
-	if (f)
-		fput(f);
+	if (f.file)
+		fdput(f);
 
 	mutex_lock(&file->mutex);
 	list_add_tail(&obj->uobject.list, &file->ucontext->xrcd_list);
@@ -830,8 +825,8 @@ err:
 	put_uobj_write(&obj->uobject);
 
 err_tree_mutex_unlock:
-	if (f)
-		fput(f);
+	if (f.file)
+		fdput(f);
 
 	mutex_unlock(&file->device->xrcd_tree_mutex);
 
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 604556d73d25..6f2ce6fa98f8 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -541,16 +541,15 @@ struct file *ib_uverbs_alloc_event_file(struct ib_uverbs_file *uverbs_file,
 struct ib_uverbs_event_file *ib_uverbs_lookup_comp_file(int fd)
 {
 	struct ib_uverbs_event_file *ev_file = NULL;
-	struct file *filp;
+	struct fd f = fdget(fd);
 
-	filp = fget(fd);
-	if (!filp)
+	if (!f.file)
 		return NULL;
 
-	if (filp->f_op != &uverbs_event_fops)
+	if (f.file->f_op != &uverbs_event_fops)
 		goto out;
 
-	ev_file = filp->private_data;
+	ev_file = f.file->private_data;
 	if (ev_file->is_async) {
 		ev_file = NULL;
 		goto out;
@@ -559,7 +558,7 @@ struct ib_uverbs_event_file *ib_uverbs_lookup_comp_file(int fd)
 	kref_get(&ev_file->ref);
 
 out:
-	fput(filp);
+	fdput(f);
 	return ev_file;
 }
 
diff --git a/drivers/staging/android/binder.c b/drivers/staging/android/binder.c
index b1937ca13575..7b0ba92e7e46 100644
--- a/drivers/staging/android/binder.c
+++ b/drivers/staging/android/binder.c
@@ -362,71 +362,22 @@ struct binder_transaction {
 static void
 binder_defer_work(struct binder_proc *proc, enum binder_deferred_state defer);
 
-/*
- * copied from get_unused_fd_flags
- */
 static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
 {
 	struct files_struct *files = proc->files;
-	int fd, error;
-	struct fdtable *fdt;
 	unsigned long rlim_cur;
 	unsigned long irqs;
 
 	if (files == NULL)
 		return -ESRCH;
 
-	error = -EMFILE;
-	spin_lock(&files->file_lock);
-
-repeat:
-	fdt = files_fdtable(files);
-	fd = find_next_zero_bit(fdt->open_fds, fdt->max_fds, files->next_fd);
-
-	/*
-	 * N.B. For clone tasks sharing a files structure, this test
-	 * will limit the total number of files that can be opened.
-	 */
-	rlim_cur = 0;
-	if (lock_task_sighand(proc->tsk, &irqs)) {
-		rlim_cur = proc->tsk->signal->rlim[RLIMIT_NOFILE].rlim_cur;
-		unlock_task_sighand(proc->tsk, &irqs);
-	}
-	if (fd >= rlim_cur)
-		goto out;
-
-	/* Do we need to expand the fd array or fd set?  */
-	error = expand_files(files, fd);
-	if (error < 0)
-		goto out;
-
-	if (error) {
-		/*
-		 * If we needed to expand the fs array we
-		 * might have blocked - try again.
-		 */
-		error = -EMFILE;
-		goto repeat;
-	}
-
-	__set_open_fd(fd, fdt);
-	if (flags & O_CLOEXEC)
-		__set_close_on_exec(fd, fdt);
-	else
-		__clear_close_on_exec(fd, fdt);
-	files->next_fd = fd + 1;
-
-	/* Sanity check */
-	if (fdt->fd[fd] != NULL) {
-		pr_warn("get_unused_fd: slot %d not NULL!\n", fd);
-		fdt->fd[fd] = NULL;
-	}
+	if (!lock_task_sighand(proc->tsk, &irqs))
+		return -EMFILE;
 
-	error = fd;
+	rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
+	unlock_task_sighand(proc->tsk, &irqs);
 
-out:
-	spin_unlock(&files->file_lock);
-	return error;
+	return __alloc_fd(files, 0, rlim_cur, flags);
 }
 
 /*
@@ -435,28 +386,8 @@ out:
 static void task_fd_install(
 	struct binder_proc *proc, unsigned int fd, struct file *file)
 {
-	struct files_struct *files = proc->files;
-	struct fdtable *fdt;
-
-	if (files == NULL)
-		return;
-
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	BUG_ON(fdt->fd[fd] != NULL);
-	rcu_assign_pointer(fdt->fd[fd], file);
-	spin_unlock(&files->file_lock);
-}
-
-/*
- * copied from __put_unused_fd in open.c
- */
-static void __put_unused_fd(struct files_struct *files, unsigned int fd)
-{
-	struct fdtable *fdt = files_fdtable(files);
-	__clear_open_fd(fd, fdt);
-	if (fd < files->next_fd)
-		files->next_fd = fd;
+	if (proc->files)
+		__fd_install(proc->files, fd, file);
 }
 
 /*
@@ -464,27 +395,12 @@ static void __put_unused_fd(struct files_struct *files, unsigned int fd)
  */
 static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 {
-	struct file *filp;
-	struct files_struct *files = proc->files;
-	struct fdtable *fdt;
 	int retval;
 
-	if (files == NULL)
+	if (proc->files == NULL)
 		return -ESRCH;
 
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_unlock;
-	filp = fdt->fd[fd];
-	if (!filp)
-		goto out_unlock;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__clear_close_on_exec(fd, fdt);
-	__put_unused_fd(files, fd);
-	spin_unlock(&files->file_lock);
-	retval = filp_close(filp, files);
-
+	retval = __close_fd(proc->files, fd);
 	/* can't restart close syscall because file table entry was cleared */
 	if (unlikely(retval == -ERESTARTSYS ||
 		     retval == -ERESTARTNOINTR ||
@@ -493,10 +409,6 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
 		retval = -EINTR;
 
 	return retval;
-
-out_unlock:
-	spin_unlock(&files->file_lock);
-	return -EBADF;
 }
 
 static void binder_set_nice(long nice)
@@ -2793,6 +2705,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	const char *failure_string;
 	struct binder_buffer *buffer;
 
+	if (proc->tsk != current)
+		return -EINVAL;
+
 	if ((vma->vm_end - vma->vm_start) > SZ_4M)
 		vma->vm_end = vma->vm_start + SZ_4M;
 
@@ -2857,7 +2772,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	binder_insert_free_buffer(proc, buffer);
 	proc->free_async_space = proc->buffer_size / 2;
 	barrier();
-	proc->files = get_files_struct(proc->tsk);
+	proc->files = get_files_struct(current);
 	proc->vma = vma;
 	proc->vma_vm_mm = vma->vm_mm;
 
diff --git a/drivers/staging/omapdrm/omap_gem.c b/drivers/staging/omapdrm/omap_gem.c
index c8287438e0dc..3434e6ec0142 100644
--- a/drivers/staging/omapdrm/omap_gem.c
+++ b/drivers/staging/omapdrm/omap_gem.c
@@ -592,9 +592,8 @@ int omap_gem_mmap_obj(struct drm_gem_object *obj,
 		 * in particular in the case of mmap'd dmabufs)
 		 */
 		fput(vma->vm_file);
-		get_file(obj->filp);
 		vma->vm_pgoff = 0;
-		vma->vm_file  = obj->filp;
+		vma->vm_file  = get_file(obj->filp);
 
 		vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
 	}
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 8a5a8b064616..2ea176b2280e 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -1166,10 +1166,8 @@ ssize_t redirected_tty_write(struct file *file, const char __user *buf,
 	struct file *p = NULL;
 
 	spin_lock(&redirect_lock);
-	if (redirect) {
-		get_file(redirect);
-		p = redirect;
-	}
+	if (redirect)
+		p = get_file(redirect);
 	spin_unlock(&redirect_lock);
 
 	if (p) {
@@ -2264,8 +2262,7 @@ static int tioccons(struct file *file)
 		spin_unlock(&redirect_lock);
 		return -EBUSY;
 	}
-	get_file(file);
-	redirect = file;
+	redirect = get_file(file);
 	spin_unlock(&redirect_lock);
 	return 0;
 }
@@ -2809,6 +2806,13 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd,
 }
 #endif
 
+static int this_tty(const void *t, struct file *file, unsigned fd)
+{
+	if (likely(file->f_op->read != tty_read))
+		return 0;
+	return file_tty(file) != t ? 0 : fd + 1;
+}
+	
 /*
  * This implements the "Secure Attention Key" ---  the idea is to
  * prevent trojan horses by killing all processes associated with this
@@ -2836,8 +2840,6 @@ void __do_SAK(struct tty_struct *tty)
 	struct task_struct *g, *p;
 	struct pid *session;
 	int		i;
-	struct file	*filp;
-	struct fdtable *fdt;
 
 	if (!tty)
 		return;
@@ -2867,27 +2869,12 @@ void __do_SAK(struct tty_struct *tty)
 			continue;
 		}
 		task_lock(p);
-		if (p->files) {
-			/*
-			 * We don't take a ref to the file, so we must
-			 * hold ->file_lock instead.
-			 */
-			spin_lock(&p->files->file_lock);
-			fdt = files_fdtable(p->files);
-			for (i = 0; i < fdt->max_fds; i++) {
-				filp = fcheck_files(p->files, i);
-				if (!filp)
-					continue;
-				if (filp->f_op->read == tty_read &&
-				    file_tty(filp) == tty) {
-					printk(KERN_NOTICE "SAK: killed process %d"
-					    " (%s): fd#%d opened to the tty\n",
-					    task_pid_nr(p), p->comm, i);
-					force_sig(SIGKILL, p);
-					break;
-				}
-			}
-			spin_unlock(&p->files->file_lock);
+		i = iterate_fd(p->files, 0, this_tty, tty);
+		if (i != 0) {
+			printk(KERN_NOTICE "SAK: killed process %d"
+			    " (%s): fd#%d opened to the tty\n",
+				    task_pid_nr(p), p->comm, i - 1);
+			force_sig(SIGKILL, p);
 		}
 		task_unlock(p);
 	} while_each_thread(g, p);
diff --git a/drivers/usb/gadget/f_fs.c b/drivers/usb/gadget/f_fs.c
index a26c43a151fd..64c4ec10d1fc 100644
--- a/drivers/usb/gadget/f_fs.c
+++ b/drivers/usb/gadget/f_fs.c
@@ -340,7 +340,7 @@ ffs_sb_create_file(struct super_block *sb, const char *name, void *data,
 
 static int ffs_mutex_lock(struct mutex *mutex, unsigned nonblock)
 	__attribute__((warn_unused_result, nonnull));
-static char *ffs_prepare_buffer(const char * __user buf, size_t len)
+static char *ffs_prepare_buffer(const char __user *buf, size_t len)
 	__attribute__((warn_unused_result, nonnull));
 
 
@@ -2445,7 +2445,7 @@ static int ffs_mutex_lock(struct mutex *mutex, unsigned nonblock)
 		: mutex_lock_interruptible(mutex);
 }
 
-static char *ffs_prepare_buffer(const char * __user buf, size_t len)
+static char *ffs_prepare_buffer(const char __user *buf, size_t len)
 {
 	char *data;
 
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 17830c9c7cc6..56097c6d072d 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1014,7 +1014,7 @@ static void vfio_group_try_dissolve_container(struct vfio_group *group)
 
 static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 {
-	struct file *filep;
+	struct fd f;
 	struct vfio_container *container;
 	struct vfio_iommu_driver *driver;
 	int ret = 0;
@@ -1022,17 +1022,17 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 	if (atomic_read(&group->container_users))
 		return -EINVAL;
 
-	filep = fget(container_fd);
-	if (!filep)
+	f = fdget(container_fd);
+	if (!f.file)
 		return -EBADF;
 
 	/* Sanity check, is this really our fd? */
-	if (filep->f_op != &vfio_fops) {
-		fput(filep);
+	if (f.file->f_op != &vfio_fops) {
+		fdput(f);
 		return -EINVAL;
 	}
 
-	container = filep->private_data;
+	container = f.file->private_data;
 	WARN_ON(!container); /* fget ensures we don't race vfio_release */
 
 	mutex_lock(&container->group_lock);
@@ -1054,8 +1054,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd)
 
 unlock_out:
 	mutex_unlock(&container->group_lock);
-	fput(filep);
-
+	fdput(f);
 	return ret;
 }
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ef82a0d18489..99ac2cb08b43 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -636,8 +636,8 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 
 static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 {
-	struct file *eventfp, *filep = NULL,
-		    *pollstart = NULL, *pollstop = NULL;
+	struct file *eventfp, *filep = NULL;
+	bool pollstart = false, pollstop = false;
 	struct eventfd_ctx *ctx = NULL;
 	u32 __user *idxp = argp;
 	struct vhost_virtqueue *vq;
@@ -763,8 +763,8 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
 			break;
 		}
 		if (eventfp != vq->kick) {
-			pollstop = filep = vq->kick;
-			pollstart = vq->kick = eventfp;
+			pollstop = (filep = vq->kick) != NULL;
+			pollstart = (vq->kick = eventfp) != NULL;
 		} else
 			filep = eventfp;
 		break;
diff --git a/drivers/video/msm/mdp.c b/drivers/video/msm/mdp.c
index d1f881e8030e..2e0f3bab6114 100644
--- a/drivers/video/msm/mdp.c
+++ b/drivers/video/msm/mdp.c
@@ -257,19 +257,17 @@ int get_img(struct mdp_img *img, struct fb_info *info,
 	    unsigned long *start, unsigned long *len,
 	    struct file **filep)
 {
-	int put_needed, ret = 0;
-	struct file *file;
-
-	file = fget_light(img->memory_id, &put_needed);
-	if (file == NULL)
+	int ret = 0;
+	struct fd f = fdget(img->memory_id);
+	if (f.file == NULL)
 		return -1;
 
-	if (MAJOR(file->f_dentry->d_inode->i_rdev) == FB_MAJOR) {
+	if (MAJOR(f.file->f_dentry->d_inode->i_rdev) == FB_MAJOR) {
 		*start = info->fix.smem_start;
 		*len = info->fix.smem_len;
 	} else
 		ret = -1;
-	fput_light(file, put_needed);
+	fdput(f);
 
 	return ret;
 }