summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorRodrigo Campos <rodrigo@kinvolk.io>2021-05-17 12:39:07 -0700
committerKees Cook <keescook@chromium.org>2021-06-28 12:49:52 -0700
commit0ae71c7720e3ae3aabd2e8a072d27f7bd173d25c (patch)
tree6508fb49112c155cd9113a62fb7968c586f1f4d0 /kernel
parentddc473916955f7710d1eb17c1273d91c8622a9fe (diff)
seccomp: Support atomic "addfd + send reply"
Alban Crequy reported a race condition userspace faces when we want to add some fds and make the syscall return them[1] using seccomp notify. The problem is that currently two different ioctl() calls are needed by the process handling the syscalls (agent) for another userspace process (target): SECCOMP_IOCTL_NOTIF_ADDFD to allocate the fd and SECCOMP_IOCTL_NOTIF_SEND to return that value. Therefore, it is possible for the agent to do the first ioctl to add a file descriptor but the target is interrupted (EINTR) before the agent does the second ioctl() call. This patch adds a flag to the ADDFD ioctl() so it adds the fd and returns that value atomically to the target program, as suggested by Kees Cook[2]. This is done by simply allowing seccomp_do_user_notification() to add the fd and return it in this case. Therefore, in this case the target wakes up from the wait in seccomp_do_user_notification() either to interrupt the syscall or to add the fd and return it. This "allocate an fd and return" functionality is useful for syscalls that return a file descriptor only, like connect(2). Other syscalls that return a file descriptor but not as return value (or return more than one fd), like socketpair(), pipe(), recvmsg with SCM_RIGHTs, will not work with this flag. This effectively combines SECCOMP_IOCTL_NOTIF_ADDFD and SECCOMP_IOCTL_NOTIF_SEND into an atomic opteration. The notification's return value, nor error can be set by the user. Upon successful invocation of the SECCOMP_IOCTL_NOTIF_ADDFD ioctl with the SECCOMP_ADDFD_FLAG_SEND flag, the notifying process's errno will be 0, and the return value will be the file descriptor number that was installed. [1]: https://lore.kernel.org/lkml/CADZs7q4sw71iNHmV8EOOXhUKJMORPzF7thraxZYddTZsxta-KQ@mail.gmail.com/ [2]: https://lore.kernel.org/lkml/202012011322.26DCBC64F2@keescook/ Signed-off-by: Rodrigo Campos <rodrigo@kinvolk.io> Signed-off-by: Sargun Dhillon <sargun@sargun.me> Acked-by: Tycho Andersen <tycho@tycho.pizza> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Kees Cook <keescook@chromium.org> Link: https://lore.kernel.org/r/20210517193908.3113-4-sargun@sargun.me
Diffstat (limited to 'kernel')
-rw-r--r--kernel/seccomp.c51
1 files changed, 45 insertions, 6 deletions
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 9f58049ac16d..057e17f3215d 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -107,6 +107,7 @@ struct seccomp_knotif {
* installing process should allocate the fd as normal.
* @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
* is allowed.
+ * @ioctl_flags: The flags used for the seccomp_addfd ioctl.
* @ret: The return value of the installing process. It is set to the fd num
* upon success (>= 0).
* @completion: Indicates that the installing process has completed fd
@@ -118,6 +119,7 @@ struct seccomp_kaddfd {
struct file *file;
int fd;
unsigned int flags;
+ __u32 ioctl_flags;
union {
bool setfd;
@@ -1065,18 +1067,37 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
return filter->notif->next_id++;
}
-static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_knotif *n)
{
+ int fd;
+
/*
* Remove the notification, and reset the list pointers, indicating
* that it has been handled.
*/
list_del_init(&addfd->list);
if (!addfd->setfd)
- addfd->ret = receive_fd(addfd->file, addfd->flags);
+ fd = receive_fd(addfd->file, addfd->flags);
else
- addfd->ret = receive_fd_replace(addfd->fd, addfd->file,
- addfd->flags);
+ fd = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
+ addfd->ret = fd;
+
+ if (addfd->ioctl_flags & SECCOMP_ADDFD_FLAG_SEND) {
+ /* If we fail reset and return an error to the notifier */
+ if (fd < 0) {
+ n->state = SECCOMP_NOTIFY_SENT;
+ } else {
+ /* Return the FD we just added */
+ n->flags = 0;
+ n->error = 0;
+ n->val = fd;
+ }
+ }
+
+ /*
+ * Mark the notification as completed. From this point, addfd mem
+ * might be invalidated and we can't safely read it anymore.
+ */
complete(&addfd->completion);
}
@@ -1120,7 +1141,7 @@ static int seccomp_do_user_notification(int this_syscall,
struct seccomp_kaddfd, list);
/* Check if we were woken up by a addfd message */
if (addfd)
- seccomp_handle_addfd(addfd);
+ seccomp_handle_addfd(addfd, &n);
} while (n.state != SECCOMP_NOTIFY_REPLIED);
@@ -1581,7 +1602,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
if (addfd.newfd_flags & ~O_CLOEXEC)
return -EINVAL;
- if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+ if (addfd.flags & ~(SECCOMP_ADDFD_FLAG_SETFD | SECCOMP_ADDFD_FLAG_SEND))
return -EINVAL;
if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
@@ -1591,6 +1612,7 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
if (!kaddfd.file)
return -EBADF;
+ kaddfd.ioctl_flags = addfd.flags;
kaddfd.flags = addfd.newfd_flags;
kaddfd.setfd = addfd.flags & SECCOMP_ADDFD_FLAG_SETFD;
kaddfd.fd = addfd.newfd;
@@ -1616,6 +1638,23 @@ static long seccomp_notify_addfd(struct seccomp_filter *filter,
goto out_unlock;
}
+ if (addfd.flags & SECCOMP_ADDFD_FLAG_SEND) {
+ /*
+ * Disallow queuing an atomic addfd + send reply while there are
+ * some addfd requests still to process.
+ *
+ * There is no clear reason to support it and allows us to keep
+ * the loop on the other side straight-forward.
+ */
+ if (!list_empty(&knotif->addfd)) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+
+ /* Allow exactly only one reply */
+ knotif->state = SECCOMP_NOTIFY_REPLIED;
+ }
+
list_add(&kaddfd.list, &knotif->addfd);
complete(&knotif->ready);
mutex_unlock(&filter->notify_lock);