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

Pull final vfs updates from Al Viro:
 "Assorted cleanups and fixes all over the place"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  sg_write()/bsg_write() is not fit to be called under KERNEL_DS
  ufs: fix function declaration for ufs_truncate_blocks
  fs: exec: apply CLOEXEC before changing dumpable task flags
  seq_file: reset iterator to first record for zero offset
  vfs: fix isize/pos/len checks for reflink & dedupe
  [iov_iter] fix iterate_all_kinds() on empty iterators
  move aio compat to fs/aio.c
  reorganize do_make_slave()
  clone_private_mount() doesn't need to touch namespace_sem
  remove a bogus claim about namespace_sem being held by callers of mnt_alloc_id()

10 files changed, 162 insertions, 133 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 8edf253484af..8c79e1a53af9 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1367,6 +1367,39 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p)
+{
+	struct kioctx *ioctx = NULL;
+	unsigned long ctx;
+	long ret;
+
+	ret = get_user(ctx, ctx32p);
+	if (unlikely(ret))
+		goto out;
+
+	ret = -EINVAL;
+	if (unlikely(ctx || nr_events == 0)) {
+		pr_debug("EINVAL: ctx %lu nr_events %u\n",
+		         ctx, nr_events);
+		goto out;
+	}
+
+	ioctx = ioctx_alloc(nr_events);
+	ret = PTR_ERR(ioctx);
+	if (!IS_ERR(ioctx)) {
+		/* truncating is ok because it's a user address */
+		ret = put_user((u32)ioctx->user_id, ctx32p);
+		if (ret)
+			kill_ioctx(current->mm, ioctx, NULL);
+		percpu_ref_put(&ioctx->users);
+	}
+
+out:
+	return ret;
+}
+#endif
+
 /* sys_io_destroy:
  *	Destroy the aio_context specified.  May cancel any outstanding 
  *	AIOs and block on completion.  Will fail with -ENOSYS if not
@@ -1591,8 +1624,8 @@ out_put_req:
 	return ret;
 }
 
-long do_io_submit(aio_context_t ctx_id, long nr,
-		  struct iocb __user *__user *iocbpp, bool compat)
+static long do_io_submit(aio_context_t ctx_id, long nr,
+			  struct iocb __user *__user *iocbpp, bool compat)
 {
 	struct kioctx *ctx;
 	long ret = 0;
@@ -1662,6 +1695,44 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
 	return do_io_submit(ctx_id, nr, iocbpp, 0);
 }
 
+#ifdef CONFIG_COMPAT
+static inline long
+copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
+{
+	compat_uptr_t uptr;
+	int i;
+
+	for (i = 0; i < nr; ++i) {
+		if (get_user(uptr, ptr32 + i))
+			return -EFAULT;
+		if (put_user(compat_ptr(uptr), ptr64 + i))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
+
+COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
+		       int, nr, u32 __user *, iocb)
+{
+	struct iocb __user * __user *iocb64;
+	long ret;
+
+	if (unlikely(nr < 0))
+		return -EINVAL;
+
+	if (nr > MAX_AIO_SUBMITS)
+		nr = MAX_AIO_SUBMITS;
+
+	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
+	ret = copy_iocb(nr, iocb, iocb64);
+	if (!ret)
+		ret = do_io_submit(ctx_id, nr, iocb64, 1);
+	return ret;
+}
+#endif
+
 /* lookup_kiocb
  *	Finds a given iocb for cancellation.
  */
@@ -1761,3 +1832,25 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 	}
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
+		       compat_long_t, min_nr,
+		       compat_long_t, nr,
+		       struct io_event __user *, events,
+		       struct compat_timespec __user *, timeout)
+{
+	struct timespec t;
+	struct timespec __user *ut = NULL;
+
+	if (timeout) {
+		if (compat_get_timespec(&t, timeout))
+			return -EFAULT;
+
+		ut = compat_alloc_user_space(sizeof(*ut));
+		if (copy_to_user(ut, &t, sizeof(t)))
+			return -EFAULT;
+	}
+	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
+}
+#endif
diff --git a/fs/compat.c b/fs/compat.c
index 543b48c29ac3..3f4908c28698 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -487,45 +487,6 @@ COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
 	return compat_sys_fcntl64(fd, cmd, arg);
 }
 
-COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p)
-{
-	long ret;
-	aio_context_t ctx64;
-
-	mm_segment_t oldfs = get_fs();
-	if (unlikely(get_user(ctx64, ctx32p)))
-		return -EFAULT;
-
-	set_fs(KERNEL_DS);
-	/* The __user pointer cast is valid because of the set_fs() */
-	ret = sys_io_setup(nr_reqs, (aio_context_t __user *) &ctx64);
-	set_fs(oldfs);
-	/* truncating is ok because it's a user address */
-	if (!ret)
-		ret = put_user((u32) ctx64, ctx32p);
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id,
-		       compat_long_t, min_nr,
-		       compat_long_t, nr,
-		       struct io_event __user *, events,
-		       struct compat_timespec __user *, timeout)
-{
-	struct timespec t;
-	struct timespec __user *ut = NULL;
-
-	if (timeout) {
-		if (compat_get_timespec(&t, timeout))
-			return -EFAULT;
-
-		ut = compat_alloc_user_space(sizeof(*ut));
-		if (copy_to_user(ut, &t, sizeof(t)) )
-			return -EFAULT;
-	} 
-	return sys_io_getevents(ctx_id, min_nr, nr, events, ut);
-}
-
 /* A write operation does a read from user space and vice versa */
 #define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
 
@@ -602,42 +563,6 @@ out:
 	return ret;
 }
 
-static inline long
-copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64)
-{
-	compat_uptr_t uptr;
-	int i;
-
-	for (i = 0; i < nr; ++i) {
-		if (get_user(uptr, ptr32 + i))
-			return -EFAULT;
-		if (put_user(compat_ptr(uptr), ptr64 + i))
-			return -EFAULT;
-	}
-	return 0;
-}
-
-#define MAX_AIO_SUBMITS 	(PAGE_SIZE/sizeof(struct iocb *))
-
-COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
-		       int, nr, u32 __user *, iocb)
-{
-	struct iocb __user * __user *iocb64; 
-	long ret;
-
-	if (unlikely(nr < 0))
-		return -EINVAL;
-
-	if (nr > MAX_AIO_SUBMITS)
-		nr = MAX_AIO_SUBMITS;
-	
-	iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64));
-	ret = copy_iocb(nr, iocb, iocb64);
-	if (!ret)
-		ret = do_io_submit(ctx_id, nr, iocb64, 1);
-	return ret;
-}
-
 struct compat_ncp_mount_data {
 	compat_int_t version;
 	compat_uint_t ncp_fd;
diff --git a/fs/exec.c b/fs/exec.c
index 8112eacf10f3..eadbf5069c38 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -19,7 +19,7 @@
  * current->executable is only used by the procfs.  This allows a dispatch
  * table to check for several different types  of binary formats.  We keep
  * trying until we recognize the file or we run out of supported binary
- * formats. 
+ * formats.
  */
 
 #include <linux/slab.h>
@@ -1268,6 +1268,13 @@ int flush_old_exec(struct linux_binprm * bprm)
 	flush_thread();
 	current->personality &= ~bprm->per_clear;
 
+	/*
+	 * We have to apply CLOEXEC before we change whether the process is
+	 * dumpable (in setup_new_exec) to avoid a race with a process in userspace
+	 * trying to access the should-be-closed file descriptors of a process
+	 * undergoing exec(2).
+	 */
+	do_close_on_exec(current->files);
 	return 0;
 
 out:
@@ -1330,7 +1337,6 @@ void setup_new_exec(struct linux_binprm * bprm)
 	   group */
 	current->self_exec_id++;
 	flush_signal_handlers(current, 0);
-	do_close_on_exec(current->files);
 }
 EXPORT_SYMBOL(setup_new_exec);
 
diff --git a/fs/namespace.c b/fs/namespace.c
index f7e28f8ea04d..b5b1259e064f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -96,10 +96,6 @@ static inline struct hlist_head *mp_hash(struct dentry *dentry)
 	return &mountpoint_hashtable[tmp & mp_hash_mask];
 }
 
-/*
- * allocation is serialized by namespace_sem, but we need the spinlock to
- * serialize with freeing.
- */
 static int mnt_alloc_id(struct mount *mnt)
 {
 	int res;
@@ -1034,6 +1030,8 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 		if (IS_MNT_SLAVE(old))
 			list_add(&mnt->mnt_slave, &old->mnt_slave);
 		mnt->mnt_master = old->mnt_master;
+	} else {
+		CLEAR_MNT_SHARED(mnt);
 	}
 	if (flag & CL_MAKE_SHARED)
 		set_mnt_shared(mnt);
@@ -1828,9 +1826,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 	if (IS_MNT_UNBINDABLE(old_mnt))
 		return ERR_PTR(-EINVAL);
 
-	down_read(&namespace_sem);
 	new_mnt = clone_mnt(old_mnt, path->dentry, CL_PRIVATE);
-	up_read(&namespace_sem);
 	if (IS_ERR(new_mnt))
 		return ERR_CAST(new_mnt);
 
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index d171d2c53f7f..f8933cb53d68 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4834,7 +4834,7 @@ int ocfs2_reflink_remap_range(struct file *file_in,
 
 	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
 			&len, is_dedupe);
-	if (ret || len == 0)
+	if (ret <= 0)
 		goto out_unlock;
 
 	/* Lock out changes to the allocation maps and remap. */
diff --git a/fs/pnode.c b/fs/pnode.c
index 234a9ac49958..06a793f4ae38 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -67,49 +67,47 @@ int get_dominating_id(struct mount *mnt, const struct path *root)
 
 static int do_make_slave(struct mount *mnt)
 {
-	struct mount *peer_mnt = mnt, *master = mnt->mnt_master;
-	struct mount *slave_mnt;
+	struct mount *master, *slave_mnt;
 
-	/*
-	 * slave 'mnt' to a peer mount that has the
-	 * same root dentry. If none is available then
-	 * slave it to anything that is available.
-	 */
-	while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
-	       peer_mnt->mnt.mnt_root != mnt->mnt.mnt_root) ;
-
-	if (peer_mnt == mnt) {
-		peer_mnt = next_peer(mnt);
-		if (peer_mnt == mnt)
-			peer_mnt = NULL;
-	}
-	if (mnt->mnt_group_id && IS_MNT_SHARED(mnt) &&
-	    list_empty(&mnt->mnt_share))
-		mnt_release_group_id(mnt);
-
-	list_del_init(&mnt->mnt_share);
-	mnt->mnt_group_id = 0;
-
-	if (peer_mnt)
-		master = peer_mnt;
-
-	if (master) {
-		list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
-			slave_mnt->mnt_master = master;
-		list_move(&mnt->mnt_slave, &master->mnt_slave_list);
-		list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
-		INIT_LIST_HEAD(&mnt->mnt_slave_list);
+	if (list_empty(&mnt->mnt_share)) {
+		if (IS_MNT_SHARED(mnt)) {
+			mnt_release_group_id(mnt);
+			CLEAR_MNT_SHARED(mnt);
+		}
+		master = mnt->mnt_master;
+		if (!master) {
+			struct list_head *p = &mnt->mnt_slave_list;
+			while (!list_empty(p)) {
+				slave_mnt = list_first_entry(p,
+						struct mount, mnt_slave);
+				list_del_init(&slave_mnt->mnt_slave);
+				slave_mnt->mnt_master = NULL;
+			}
+			return 0;
+		}
 	} else {
-		struct list_head *p = &mnt->mnt_slave_list;
-		while (!list_empty(p)) {
-                        slave_mnt = list_first_entry(p,
-					struct mount, mnt_slave);
-			list_del_init(&slave_mnt->mnt_slave);
-			slave_mnt->mnt_master = NULL;
+		struct mount *m;
+		/*
+		 * slave 'mnt' to a peer mount that has the
+		 * same root dentry. If none is available then
+		 * slave it to anything that is available.
+		 */
+		for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) {
+			if (m->mnt.mnt_root == mnt->mnt.mnt_root) {
+				master = m;
+				break;
+			}
 		}
+		list_del_init(&mnt->mnt_share);
+		mnt->mnt_group_id = 0;
+		CLEAR_MNT_SHARED(mnt);
 	}
+	list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
+		slave_mnt->mnt_master = master;
+	list_move(&mnt->mnt_slave, &master->mnt_slave_list);
+	list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
+	INIT_LIST_HEAD(&mnt->mnt_slave_list);
 	mnt->mnt_master = master;
-	CLEAR_MNT_SHARED(mnt);
 	return 0;
 }
 
diff --git a/fs/read_write.c b/fs/read_write.c
index da6de12b5c46..7537b6b6b5a2 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1669,6 +1669,9 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
  * Check that the two inodes are eligible for cloning, the ranges make
  * sense, and then flush all dirty data.  Caller must ensure that the
  * inodes have been locked against any other modifications.
+ *
+ * Returns: 0 for "nothing to clone", 1 for "something to clone", or
+ * the usual negative error code.
  */
 int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 			       struct inode *inode_out, loff_t pos_out,
@@ -1695,17 +1698,15 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 
 	/* Are we going all the way to the end? */
 	isize = i_size_read(inode_in);
-	if (isize == 0) {
-		*len = 0;
+	if (isize == 0)
 		return 0;
-	}
 
 	/* Zero length dedupe exits immediately; reflink goes to EOF. */
 	if (*len == 0) {
-		if (is_dedupe) {
-			*len = 0;
+		if (is_dedupe || pos_in == isize)
 			return 0;
-		}
+		if (pos_in > isize)
+			return -EINVAL;
 		*len = isize - pos_in;
 	}
 
@@ -1769,7 +1770,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
 			return -EBADE;
 	}
 
-	return 0;
+	return 1;
 }
 EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
 
@@ -1955,6 +1956,9 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
 		goto out;
 	ret = 0;
 
+	if (off + len > i_size_read(src))
+		return -EINVAL;
+
 	/* pre-format output fields to sane values */
 	for (i = 0; i < count; i++) {
 		same->info[i].bytes_deduped = 0ULL;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 368bfb92b115..a11f271800ef 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -190,6 +190,13 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos)
 	 */
 	m->version = file->f_version;
 
+	/*
+	 * if request is to read from zero offset, reset iterator to first
+	 * record as it might have been already advanced by previous requests
+	 */
+	if (*ppos == 0)
+		m->index = 0;
+
 	/* Don't assume *ppos is where we left it */
 	if (unlikely(*ppos != m->read_pos)) {
 		while ((err = traverse(m, *ppos)) == -EAGAIN)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 45ceb94e89e4..1bc0bd6a9848 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -1191,7 +1191,7 @@ out:
 	return err;
 }
 
-void ufs_truncate_blocks(struct inode *inode)
+static void ufs_truncate_blocks(struct inode *inode)
 {
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	      S_ISLNK(inode->i_mode)))
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index aca2d4bd4303..07593a362cd0 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1161,7 +1161,7 @@ xfs_reflink_remap_range(
 
 	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
 			&len, is_dedupe);
-	if (ret || len == 0)
+	if (ret <= 0)
 		goto out_unlock;
 
 	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);