fs, close_range: add flag CLOSE_RANGE_CLOEXEC

When the flag CLOSE_RANGE_CLOEXEC is set, close_range doesn't
immediately close the files but it sets the close-on-exec bit.

It is useful for e.g. container runtimes that usually install a
seccomp profile "as late as possible" before execv'ing the container
process itself.  The container runtime could either do:
  1                                  2
- install_seccomp_profile();       - close_range(MIN_FD, MAX_INT, 0);
- close_range(MIN_FD, MAX_INT, 0); - install_seccomp_profile();
- execve(...);                     - execve(...);

Both alternative have some disadvantages.

In the first variant the seccomp_profile cannot block the close_range
syscall, as well as opendir/read/close/... for the fallback on older
kernels.
In the second variant, close_range() can be used only on the fds
that are not going to be needed by the runtime anymore, and it must be
potentially called multiple times to account for the different ranges
that must be closed.

Using close_range(..., ..., CLOSE_RANGE_CLOEXEC) solves these issues.
The runtime is able to use the existing open fds, the seccomp profile
can block close_range() and the syscalls used for its fallback.

Signed-off-by: Giuseppe Scrivano <gscrivan@redhat.com>
Link: https://lore.kernel.org/r/20201118104746.873084-2-gscrivan@redhat.com
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

fs/file.c

@@ -674,6 +674,35 @@ int __close_fd(struct files_struct *files, unsigned fd)
 }
 EXPORT_SYMBOL(__close_fd); /* for ksys_close() */
 
+static inline void __range_cloexec(struct files_struct *cur_fds,
+				   unsigned int fd, unsigned int max_fd)
+{
+	struct fdtable *fdt;
+
+	if (fd > max_fd)
+		return;
+
+	spin_lock(&cur_fds->file_lock);
+	fdt = files_fdtable(cur_fds);
+	bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+	spin_unlock(&cur_fds->file_lock);
+}
+
+static inline void __range_close(struct files_struct *cur_fds, unsigned int fd,
+				 unsigned int max_fd)
+{
+	while (fd <= max_fd) {
+		struct file *file;
+
+		file = pick_file(cur_fds, fd++);
+		if (!file)
+			continue;
+
+		filp_close(file, cur_fds);
+		cond_resched();
+	}
+}
+
 /**
  * __close_range() - Close all file descriptors in a given range.
  *
@@ -689,7 +718,7 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 	struct task_struct *me = current;
 	struct files_struct *cur_fds = me->files, *fds = NULL;
 
-	if (flags & ~CLOSE_RANGE_UNSHARE)
+	if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC))
 		return -EINVAL;
 
 	if (fd > max_fd)
@@ -727,16 +756,11 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
 	}
 
 	max_fd = min(max_fd, cur_max);
-	while (fd <= max_fd) {
-		struct file *file;
 
-		file = pick_file(cur_fds, fd++);
-		if (!file)
-			continue;
-
-		filp_close(file, cur_fds);
-		cond_resched();
-	}
+	if (flags & CLOSE_RANGE_CLOEXEC)
+		__range_cloexec(cur_fds, fd, max_fd);
+	else
+		__range_close(cur_fds, fd, max_fd);
 
 	if (fds) {
 		/*

include/uapi/linux/close_range.h

@@ -5,5 +5,8 @@
 /* Unshare the file descriptor table before closing file descriptors. */
 #define CLOSE_RANGE_UNSHARE	(1U << 1)
 
+/* Set the FD_CLOEXEC bit instead of closing the file descriptor. */
+#define CLOSE_RANGE_CLOEXEC	(1U << 2)
+
 #endif /* _UAPI_LINUX_CLOSE_RANGE_H */