summaryrefslogtreecommitdiff
path: root/fs/file.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/file.c')
-rw-r--r--fs/file.c48
1 files changed, 24 insertions, 24 deletions
diff --git a/fs/file.c b/fs/file.c
index 25c6e53b03f8..1ba03662ae66 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -279,10 +279,6 @@ repeat:
if (nr < fdt->max_fds)
return 0;
- /* Can we expand? */
- if (nr >= sysctl_nr_open)
- return -EMFILE;
-
if (unlikely(files->resize_in_progress)) {
spin_unlock(&files->file_lock);
wait_event(files->resize_wait, !files->resize_in_progress);
@@ -290,6 +286,10 @@ repeat:
goto repeat;
}
+ /* Can we expand? */
+ if (unlikely(nr >= sysctl_nr_open))
+ return -EMFILE;
+
/* All good, so we try */
files->resize_in_progress = true;
error = expand_fdtable(files, nr);
@@ -418,17 +418,25 @@ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_ho
old_fds = old_fdt->fd;
new_fds = new_fdt->fd;
+ /*
+ * We may be racing against fd allocation from other threads using this
+ * files_struct, despite holding ->file_lock.
+ *
+ * alloc_fd() might have already claimed a slot, while fd_install()
+ * did not populate it yet. Note the latter operates locklessly, so
+ * the file can show up as we are walking the array below.
+ *
+ * At the same time we know no files will disappear as all other
+ * operations take the lock.
+ *
+ * Instead of trying to placate userspace racing with itself, we
+ * ref the file if we see it and mark the fd slot as unused otherwise.
+ */
for (i = open_files; i != 0; i--) {
- struct file *f = *old_fds++;
+ struct file *f = rcu_dereference_raw(*old_fds++);
if (f) {
get_file(f);
} else {
- /*
- * The fd may be claimed in the fd bitmap but not yet
- * instantiated in the files array if a sibling thread
- * is partway through open(). So make sure that this
- * fd is available to the new process.
- */
__clear_open_fd(open_files - i, new_fdt);
}
rcu_assign_pointer(*new_fds++, f);
@@ -679,7 +687,7 @@ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd)
return NULL;
fd = array_index_nospec(fd, fdt->max_fds);
- file = fdt->fd[fd];
+ file = rcu_dereference_raw(fdt->fd[fd]);
if (file) {
rcu_assign_pointer(fdt->fd[fd], NULL);
__put_unused_fd(files, fd);
@@ -1231,21 +1239,13 @@ __releases(&files->file_lock)
/*
* We need to detect attempts to do dup2() over allocated but still
- * not finished descriptor. NB: OpenBSD avoids that at the price of
- * extra work in their equivalent of fget() - they insert struct
- * file immediately after grabbing descriptor, mark it larval if
- * more work (e.g. actual opening) is needed and make sure that
- * fget() treats larval files as absent. Potentially interesting,
- * but while extra work in fget() is trivial, locking implications
- * and amount of surgery on open()-related paths in VFS are not.
- * FreeBSD fails with -EBADF in the same situation, NetBSD "solution"
- * deadlocks in rather amusing ways, AFAICS. All of that is out of
- * scope of POSIX or SUS, since neither considers shared descriptor
- * tables and this condition does not arise without those.
+ * not finished descriptor.
+ *
+ * POSIX is silent on the issue, we return -EBUSY.
*/
fdt = files_fdtable(files);
fd = array_index_nospec(fd, fdt->max_fds);
- tofree = fdt->fd[fd];
+ tofree = rcu_dereference_raw(fdt->fd[fd]);
if (!tofree && fd_is_open(fd, fdt))
goto Ebusy;
get_file(file);