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, 34 insertions, 61 deletions

diff --git a/fs/file.c b/fs/file.c
index 5125607d040a..eb093e736972 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -272,59 +272,45 @@ static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
 	return test_bit(fd, fdt->open_fds);
 }
 
-static unsigned int count_open_files(struct fdtable *fdt)
-{
-	unsigned int size = fdt->max_fds;
-	unsigned int i;
-
-	/* Find the last open fd */
-	for (i = size / BITS_PER_LONG; i > 0; ) {
-		if (fdt->open_fds[--i])
-			break;
-	}
-	i = (i + 1) * BITS_PER_LONG;
-	return i;
-}
-
 /*
  * Note that a sane fdtable size always has to be a multiple of
  * BITS_PER_LONG, since we have bitmaps that are sized by this.
  *
- * 'max_fds' will normally already be properly aligned, but it
- * turns out that in the close_range() -> __close_range() ->
- * unshare_fd() -> dup_fd() -> sane_fdtable_size() we can end
- * up having a 'max_fds' value that isn't already aligned.
- *
- * Rather than make close_range() have to worry about this,
- * just make that BITS_PER_LONG alignment be part of a sane
- * fdtable size. Becuase that's really what it is.
+ * punch_hole is optional - when close_range() is asked to unshare
+ * and close, we don't need to copy descriptors in that range, so
+ * a smaller cloned descriptor table might suffice if the last
+ * currently opened descriptor falls into that range.
  */
-static unsigned int sane_fdtable_size(struct fdtable *fdt, unsigned int max_fds)
+static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole)
 {
-	unsigned int count;
-
-	count = count_open_files(fdt);
-	if (max_fds < NR_OPEN_DEFAULT)
-		max_fds = NR_OPEN_DEFAULT;
-	return ALIGN(min(count, max_fds), BITS_PER_LONG);
+	unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds);
+
+	if (last == fdt->max_fds)
+		return NR_OPEN_DEFAULT;
+	if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) {
+		last = find_last_bit(fdt->open_fds, punch_hole->from);
+		if (last == punch_hole->from)
+			return NR_OPEN_DEFAULT;
+	}
+	return ALIGN(last + 1, BITS_PER_LONG);
 }
 
 /*
- * Allocate a new files structure and copy contents from the
- * passed in files structure.
- * errorp will be valid only when the returned files_struct is NULL.
+ * Allocate a new descriptor table and copy contents from the passed in
+ * instance.  Returns a pointer to cloned table on success, ERR_PTR()
+ * on failure.  For 'punch_hole' see sane_fdtable_size().
  */
-struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int *errorp)
+struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole)
 {
 	struct files_struct *newf;
 	struct file **old_fds, **new_fds;
 	unsigned int open_files, i;
 	struct fdtable *old_fdt, *new_fdt;
+	int error;
 
-	*errorp = -ENOMEM;
 	newf = kmem_cache_alloc(files_cachep, GFP_KERNEL);
 	if (!newf)
-		goto out;
+		return ERR_PTR(-ENOMEM);
 
 	atomic_set(&newf->count, 1);
 
@@ -341,7 +327,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 
 	spin_lock(&oldf->file_lock);
 	old_fdt = files_fdtable(oldf);
-	open_files = sane_fdtable_size(old_fdt, max_fds);
+	open_files = sane_fdtable_size(old_fdt, punch_hole);
 
 	/*
 	 * Check whether we need to allocate a larger fd array and fd set.
@@ -354,14 +340,14 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 
 		new_fdt = alloc_fdtable(open_files - 1);
 		if (!new_fdt) {
-			*errorp = -ENOMEM;
+			error = -ENOMEM;
 			goto out_release;
 		}
 
 		/* beyond sysctl_nr_open; nothing to do */
 		if (unlikely(new_fdt->max_fds < open_files)) {
 			__free_fdtable(new_fdt);
-			*errorp = -EMFILE;
+			error = -EMFILE;
 			goto out_release;
 		}
 
@@ -372,7 +358,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 		 */
 		spin_lock(&oldf->file_lock);
 		old_fdt = files_fdtable(oldf);
-		open_files = sane_fdtable_size(old_fdt, max_fds);
+		open_files = sane_fdtable_size(old_fdt, punch_hole);
 	}
 
 	copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
@@ -406,8 +392,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
 
 out_release:
 	kmem_cache_free(files_cachep, newf);
-out:
-	return NULL;
+	return ERR_PTR(error);
 }
 
 static struct fdtable *close_files(struct files_struct * files)
@@ -748,37 +733,25 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 	if (fd > max_fd)
 		return -EINVAL;
 
-	if (flags & CLOSE_RANGE_UNSHARE) {
-		int ret;
-		unsigned int max_unshare_fds = NR_OPEN_MAX;
+	if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) {
+		struct fd_range range = {fd, max_fd}, *punch_hole = &range;
 
 		/*
 		 * If the caller requested all fds to be made cloexec we always
 		 * copy all of the file descriptors since they still want to
 		 * use them.
 		 */
-		if (!(flags & CLOSE_RANGE_CLOEXEC)) {
-			/*
-			 * If the requested range is greater than the current
-			 * maximum, we're closing everything so only copy all
-			 * file descriptors beneath the lowest file descriptor.
-			 */
-			rcu_read_lock();
-			if (max_fd >= last_fd(files_fdtable(cur_fds)))
-				max_unshare_fds = fd;
-			rcu_read_unlock();
-		}
-
-		ret = unshare_fd(CLONE_FILES, max_unshare_fds, &fds);
-		if (ret)
-			return ret;
+		if (flags & CLOSE_RANGE_CLOEXEC)
+			punch_hole = NULL;
 
+		fds = dup_fd(cur_fds, punch_hole);
+		if (IS_ERR(fds))
+			return PTR_ERR(fds);
 		/*
 		 * We used to share our file descriptor table, and have now
 		 * created a private one, make sure we're using it below.
 		 */
-		if (fds)
-			swap(cur_fds, fds);
+		swap(cur_fds, fds);
 	}
 
 	if (flags & CLOSE_RANGE_CLOEXEC)