close_range(): fix the logics in descriptor table trimming

Cloning a descriptor table picks the size that would cover all currently
opened files.  That's fine for clone() and unshare(), but for close_range()
there's an additional twist - we clone before we close, and it would be
a shame to have
	close_range(3, ~0U, CLOSE_RANGE_UNSHARE)
leave us with a huge descriptor table when we are not going to keep
anything past stderr, just because some large file descriptor used to
be open before our call has taken it out.

Unfortunately, it had been dealt with in an inherently racy way -
sane_fdtable_size() gets a "don't copy anything past that" argument
(passed via unshare_fd() and dup_fd()), close_range() decides how much
should be trimmed and passes that to unshare_fd().

The problem is, a range that used to extend to the end of descriptor
table back when close_range() had looked at it might very well have stuff
grown after it by the time dup_fd() has allocated a new files_struct
and started to figure out the capacity of fdtable to be attached to that.

That leads to interesting pathological cases; at the very least it's a
QoI issue, since unshare(CLONE_FILES) is atomic in a sense that it takes
a snapshot of descriptor table one might have observed at some point.
Since CLOSE_RANGE_UNSHARE close_range() is supposed to be a combination
of unshare(CLONE_FILES) with plain close_range(), ending up with a
weird state that would never occur with unshare(2) is confusing, to put
it mildly.

It's not hard to get rid of - all it takes is passing both ends of the
range down to sane_fdtable_size().  There we are under ->files_lock,
so the race is trivially avoided.

So we do the following:
	* switch close_files() from calling unshare_fd() to calling
dup_fd().
	* undo the calling convention change done to unshare_fd() in
60997c3d45d9 "close_range: add CLOSE_RANGE_UNSHARE"
	* introduce struct fd_range, pass a pointer to that to dup_fd()
and sane_fdtable_size() instead of "trim everything past that point"
they are currently getting.  NULL means "we are not going to be punching
any holes"; NR_OPEN_MAX is gone.
	* make sane_fdtable_size() use find_last_bit() instead of
open-coding it; it's easier to follow that way.
	* while we are at it, have dup_fd() report errors by returning
ERR_PTR(), no need to use a separate int *errorp argument.

Fixes: 60997c3d45d9 "close_range: add CLOSE_RANGE_UNSHARE"
Cc: stable@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 14 insertions, 18 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 60c0b4868fd4..89ceb4a68af2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1756,33 +1756,30 @@ static int copy_files(unsigned long clone_flags, struct task_struct *tsk,
 		      int no_files)
 {
 	struct files_struct *oldf, *newf;
-	int error = 0;
 
 	/*
 	 * A background process may not have any files ...
 	 */
 	oldf = current->files;
 	if (!oldf)
-		goto out;
+		return 0;
 
 	if (no_files) {
 		tsk->files = NULL;
-		goto out;
+		return 0;
 	}
 
 	if (clone_flags & CLONE_FILES) {
 		atomic_inc(&oldf->count);
-		goto out;
+		return 0;
 	}
 
-	newf = dup_fd(oldf, NR_OPEN_MAX, &error);
-	if (!newf)
-		goto out;
+	newf = dup_fd(oldf, NULL);
+	if (IS_ERR(newf))
+		return PTR_ERR(newf);
 
 	tsk->files = newf;
-	error = 0;
-out:
-	return error;
+	return 0;
 }
 
 static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
@@ -3238,17 +3235,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 /*
  * Unshare file descriptor table if it is being shared
  */
-int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
-	       struct files_struct **new_fdp)
+static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
 {
 	struct files_struct *fd = current->files;
-	int error = 0;
 
 	if ((unshare_flags & CLONE_FILES) &&
 	    (fd && atomic_read(&fd->count) > 1)) {
-		*new_fdp = dup_fd(fd, max_fds, &error);
-		if (!*new_fdp)
-			return error;
+		fd = dup_fd(fd, NULL);
+		if (IS_ERR(fd))
+			return PTR_ERR(fd);
+		*new_fdp = fd;
 	}
 
 	return 0;
@@ -3306,7 +3302,7 @@ int ksys_unshare(unsigned long unshare_flags)
 	err = unshare_fs(unshare_flags, &new_fs);
 	if (err)
 		goto bad_unshare_out;
-	err = unshare_fd(unshare_flags, NR_OPEN_MAX, &new_fd);
+	err = unshare_fd(unshare_flags, &new_fd);
 	if (err)
 		goto bad_unshare_cleanup_fs;
 	err = unshare_userns(unshare_flags, &new_cred);
@@ -3398,7 +3394,7 @@ int unshare_files(void)
 	struct files_struct *old, *copy = NULL;
 	int error;
 
-	error = unshare_fd(CLONE_FILES, NR_OPEN_MAX, &copy);
+	error = unshare_fd(CLONE_FILES, &copy);
 	if (error || !copy)
 		return error;