@@ -10,6 +10,10 @@
SECCOMP_FILTER_FLAG_NEW_LISTENER | \
SECCOMP_FILTER_FLAG_TSYNC_ESRCH)
+/* sizeof() the first published struct seccomp_notif_addfd */
+#define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24
+#define SECCOMP_NOTIFY_ADDFD_SIZE_LATEST SECCOMP_NOTIFY_ADDFD_SIZE_VER0
+
#ifdef CONFIG_SECCOMP
#include <linux/thread_info.h>
@@ -113,6 +113,25 @@ struct seccomp_notif_resp {
__u32 flags;
};
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
+
+/**
+ * struct seccomp_notif_addfd
+ * @id: The ID of the seccomp notification
+ * @flags: SECCOMP_ADDFD_FLAG_*
+ * @srcfd: The local fd number
+ * @newfd: Optional remote FD number if SETFD option is set, otherwise 0.
+ * @newfd_flags: The O_* flags the remote FD should have applied
+ */
+struct seccomp_notif_addfd {
+ __u64 id;
+ __u32 flags;
+ __u32 srcfd;
+ __u32 newfd;
+ __u32 newfd_flags;
+};
+
#define SECCOMP_IOC_MAGIC '!'
#define SECCOMP_IO(nr) _IO(SECCOMP_IOC_MAGIC, nr)
#define SECCOMP_IOR(nr, type) _IOR(SECCOMP_IOC_MAGIC, nr, type)
@@ -124,5 +143,8 @@ struct seccomp_notif_resp {
#define SECCOMP_IOCTL_NOTIF_SEND SECCOMP_IOWR(1, \
struct seccomp_notif_resp)
#define SECCOMP_IOCTL_NOTIF_ID_VALID SECCOMP_IOW(2, __u64)
+/* On success, the return value is the remote process's added fd number */
+#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
+ struct seccomp_notif_addfd)
#endif /* _UAPI_LINUX_SECCOMP_H */
@@ -87,10 +87,42 @@ struct seccomp_knotif {
long val;
u32 flags;
- /* Signals when this has entered SECCOMP_NOTIFY_REPLIED */
+ /*
+ * Signals when this has changed states, such as the listener
+ * dying, a new seccomp addfd message, or changing to REPLIED
+ */
struct completion ready;
struct list_head list;
+
+ /* outstanding addfd requests */
+ struct list_head addfd;
+};
+
+/**
+ * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages
+ *
+ * @file: A reference to the file to install in the other task
+ * @fd: The fd number to install it at. If the fd number is -1, it means the
+ * installing process should allocate the fd as normal.
+ * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC
+ * is allowed.
+ * @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
+ * installation, or gone away (either due to successful
+ * reply, or signal)
+ *
+ */
+struct seccomp_kaddfd {
+ struct file *file;
+ int fd;
+ unsigned int flags;
+
+ /* To only be set on reply */
+ int ret;
+ struct completion completion;
+ struct list_head list;
};
/**
@@ -793,6 +825,17 @@ static u64 seccomp_next_notify_id(struct seccomp_filter *filter)
return filter->notif->next_id++;
}
+static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd)
+{
+ /*
+ * Remove the notification, and reset the list pointers, indicating
+ * that it has been handled.
+ */
+ list_del_init(&addfd->list);
+ addfd->ret = receive_fd_replace(addfd->fd, addfd->file, addfd->flags);
+ complete(&addfd->completion);
+}
+
static int seccomp_do_user_notification(int this_syscall,
struct seccomp_filter *match,
const struct seccomp_data *sd)
@@ -801,6 +844,7 @@ static int seccomp_do_user_notification(int this_syscall,
u32 flags = 0;
long ret = 0;
struct seccomp_knotif n = {};
+ struct seccomp_kaddfd *addfd, *tmp;
mutex_lock(&match->notify_lock);
err = -ENOSYS;
@@ -813,6 +857,7 @@ static int seccomp_do_user_notification(int this_syscall,
n.id = seccomp_next_notify_id(match);
init_completion(&n.ready);
list_add(&n.list, &match->notif->notifications);
+ INIT_LIST_HEAD(&n.addfd);
up(&match->notif->request);
wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
@@ -821,14 +866,31 @@ static int seccomp_do_user_notification(int this_syscall,
/*
* This is where we wait for a reply from userspace.
*/
+wait:
err = wait_for_completion_interruptible(&n.ready);
mutex_lock(&match->notify_lock);
if (err == 0) {
+ /* Check if we were woken up by a addfd message */
+ addfd = list_first_entry_or_null(&n.addfd,
+ struct seccomp_kaddfd, list);
+ if (addfd && n.state != SECCOMP_NOTIFY_REPLIED) {
+ seccomp_handle_addfd(addfd);
+ mutex_unlock(&match->notify_lock);
+ goto wait;
+ }
ret = n.val;
err = n.error;
flags = n.flags;
}
+ /* If there were any pending addfd calls, clear them out */
+ list_for_each_entry_safe(addfd, tmp, &n.addfd, list) {
+ /* The process went away before we got a chance to handle it */
+ addfd->ret = -ESRCH;
+ list_del_init(&addfd->list);
+ complete(&addfd->completion);
+ }
+
/*
* Note that it's possible the listener died in between the time when
* we were notified of a respons (or a signal) and when we were able to
@@ -1069,6 +1131,11 @@ static int seccomp_notify_release(struct inode *inode, struct file *file)
knotif->error = -ENOSYS;
knotif->val = 0;
+ /*
+ * We do not need to wake up any pending addfd messages, as
+ * the notifier will do that for us, as this just looks
+ * like a standard reply.
+ */
complete(&knotif->ready);
}
@@ -1233,12 +1300,109 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
return ret;
}
+static long seccomp_notify_addfd(struct seccomp_filter *filter,
+ struct seccomp_notif_addfd __user *uaddfd,
+ unsigned int size)
+{
+ struct seccomp_notif_addfd addfd;
+ struct seccomp_knotif *knotif;
+ struct seccomp_kaddfd kaddfd;
+ int ret;
+
+ BUILD_BUG_ON(sizeof(struct seccomp_notify_addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0);
+ BUILD_BUG_ON(sizeof(struct seccomp_notify_addfd) != SECCOMP_NOTIFY_ADDFD_SIZE_LATEST);
+
+ if (size < SECCOMP_NOTIFY_ADDFD_SIZE_VER0 || size >= PAGE_SIZE)
+ return -EINVAL;
+
+ ret = copy_struct_from_user(&addfd, sizeof(addfd), uaddfd, size);
+ if (ret)
+ return ret;
+
+ if (addfd.newfd_flags & ~O_CLOEXEC)
+ return -EINVAL;
+
+ if (addfd.flags & ~SECCOMP_ADDFD_FLAG_SETFD)
+ return -EINVAL;
+
+ if (addfd.newfd && !(addfd.flags & SECCOMP_ADDFD_FLAG_SETFD))
+ return -EINVAL;
+
+ kaddfd.file = fget(addfd.srcfd);
+ if (!kaddfd.file)
+ return -EBADF;
+
+ kaddfd.flags = addfd.newfd_flags;
+ kaddfd.fd = (addfd.flags & SECCOMP_ADDFD_FLAG_SETFD) ?
+ addfd.newfd : -1;
+ init_completion(&kaddfd.completion);
+
+ ret = mutex_lock_interruptible(&filter->notify_lock);
+ if (ret < 0)
+ goto out;
+
+ knotif = find_notification(filter, addfd.id);
+ if (!knotif) {
+ ret = -ENOENT;
+ goto out_unlock;
+ }
+
+ /*
+ * We do not want to allow for FD injection to occur before the
+ * notification has been picked up by a userspace handler, or after
+ * the notification has been replied to.
+ */
+ if (knotif->state != SECCOMP_NOTIFY_SENT) {
+ ret = -EINPROGRESS;
+ goto out_unlock;
+ }
+
+ list_add(&kaddfd.list, &knotif->addfd);
+ complete(&knotif->ready);
+ mutex_unlock(&filter->notify_lock);
+
+ /* Now we wait for it to be processed or be interrupted */
+ ret = wait_for_completion_interruptible(&kaddfd.completion);
+ if (ret == 0) {
+ /*
+ * We had a successful completion. The other side has already
+ * removed us from the addfd queue, and
+ * wait_for_completion_interruptible has a memory barrier upon
+ * success that lets us read this value directly without
+ * locking.
+ */
+ ret = kaddfd.ret;
+ goto out;
+ }
+
+ mutex_lock(&filter->notify_lock);
+ /*
+ * Even though we were woken up by a signal and not a successful
+ * completion, a completion may have happened in the mean time.
+ *
+ * We need to check again if the addfd request has been handled,
+ * and if not, we will remove it from the queue.
+ */
+ if (list_empty(&kaddfd.list))
+ ret = kaddfd.ret;
+ else
+ list_del(&kaddfd.list);
+
+out_unlock:
+ mutex_unlock(&filter->notify_lock);
+out:
+ fput(kaddfd.file);
+
+ return ret;
+}
+
static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct seccomp_filter *filter = file->private_data;
void __user *buf = (void __user *)arg;
+ /* Fixed-size ioctls */
switch (cmd) {
case SECCOMP_IOCTL_NOTIF_RECV:
return seccomp_notify_recv(filter, buf);
@@ -1247,6 +1411,13 @@ static long seccomp_notify_ioctl(struct file *file, unsigned int cmd,
case SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR:
case SECCOMP_IOCTL_NOTIF_ID_VALID:
return seccomp_notify_id_valid(filter, buf);
+ }
+
+ /* Extensible Argument ioctls */
+#define EA_IOCTL(cmd) ((cmd) & ~(IOC_INOUT | IOCSIZE_MASK))
+ switch (EA_IOCTL(cmd)) {
+ case EA_IOCTL(SECCOMP_IOCTL_NOTIF_ADDFD):
+ return seccomp_notify_addfd(filter, buf, _IOC_SIZE(cmd));
default:
return -EINVAL;
}