[PATCH v6 0/7] Add seccomp notifier ioctl that enables adding fds

@@ -937,6 +937,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 /**
  * __receive_fd() - Install received file into file descriptor table
  *
+ * @fd: fd to install into (if negative, a new fd will be allocated)
  * @file: struct file that was received from another process
  * @ufd: __user pointer to write new fd number to
  * @o_flags: the O_* flags to apply to the new fd entry

@@ -950,7 +951,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
  *
  * Returns newly install fd or -ve on error.
  */
-int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+int __receive_fd(int fd, struct file *file, int __user *ufd, unsigned int o_flags)
 {
 	struct socket *sock;
 	int new_fd;

@@ -960,18 +961,30 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	if (error)
 		return error;
 
-	new_fd = get_unused_fd_flags(o_flags);
-	if (new_fd < 0)
-		return new_fd;
+	if (fd < 0) {
+		new_fd = get_unused_fd_flags(o_flags);
+		if (new_fd < 0)
+			return new_fd;
+	} else
+		new_fd = fd;
 
 	if (ufd) {
 		error = put_user(new_fd, ufd);
 		if (error) {
-			put_unused_fd(new_fd);
+			if (fd < 0)
+				put_unused_fd(new_fd);
 			return error;
 		}
 	}
 
+	if (fd < 0)
+		fd_install(new_fd, get_file(file));
+	else {
+		error = replace_fd(new_fd, file, o_flags);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Bump the usage count and install the file. The resulting value of
 	 * "error" is ignored here since we only need to take action when

@@ -982,7 +995,6 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
 	}
-	fd_install(new_fd, get_file(file));
 	return new_fd;
 }
 

@@ -92,18 +92,22 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
-extern int __receive_fd(struct file *file, int __user *ufd,
+extern int __receive_fd(int fd, struct file *file, int __user *ufd,
 			unsigned int o_flags);
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
 	if (ufd == NULL)
 		return -EFAULT;
-	return __receive_fd(file, ufd, o_flags);
+	return __receive_fd(-1, file, ufd, o_flags);
 }
 static inline int receive_fd(struct file *file, unsigned int o_flags)
 {
-	return __receive_fd(file, NULL, o_flags);
+	return __receive_fd(-1, file, NULL, o_flags);
+}
+static inline int receive_fd_replace(int fd, struct file *file, unsigned int o_flags)
+{
+	return __receive_fd(fd, file, NULL, o_flags);
 }
 
 extern void flush_delayed_fput(void);

@@ -635,17 +635,8 @@ static int pidfd_getfd(struct pid *pid, int fd)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
-	ret = security_file_receive(file);
-	if (ret) {
-		fput(file);
-		return ret;
-	}
-
-	ret = get_unused_fd_flags(O_CLOEXEC);
-	if (ret < 0)
-		fput(file);
-	else
-		fd_install(ret, file);
+	ret = receive_fd(file, O_CLOEXEC);
+	fput(file);
 
 	return ret;
 }

@@ -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 +1300,107 @@ 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;
+
+	/* 24 is original sizeof(struct seccomp_notif_addfd) */
+	if (size < 24 || 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);

@@ -1247,9 +1409,17 @@ 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;
 	}
+#undef EA_IOCTL
 }
 
 static __poll_t seccomp_notify_poll(struct file *file,

@@ -45,6 +45,7 @@
 #include <sys/socket.h>
 #include <sys/ioctl.h>
 #include <linux/kcmp.h>
+#include <sys/resource.h>
 
 #include <unistd.h>
 #include <sys/syscall.h>

@@ -168,7 +169,9 @@ struct seccomp_metadata {
 
 #ifndef SECCOMP_FILTER_FLAG_NEW_LISTENER
 #define SECCOMP_FILTER_FLAG_NEW_LISTENER	(1UL << 3)
+#endif
 
+#ifndef SECCOMP_RET_USER_NOTIF
 #define SECCOMP_RET_USER_NOTIF 0x7fc00000U
 
 #define SECCOMP_IOC_MAGIC		'!'

@@ -204,6 +207,39 @@ struct seccomp_notif_sizes {
 };
 #endif
 
+#ifndef SECCOMP_IOCTL_NOTIF_ADDFD
+/* 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)
+
+/* valid flags for seccomp_notif_addfd */
+#define SECCOMP_ADDFD_FLAG_SETFD	(1UL << 0) /* Specify remote fd */
+
+struct seccomp_notif_addfd {
+	__u64 id;
+	__u32 flags;
+	__u32 srcfd;
+	__u32 newfd;
+	__u32 newfd_flags;
+};
+#endif
+
+struct seccomp_notif_addfd_small {
+	__u64 id;
+	char weird[4];
+};
+#define SECCOMP_IOCTL_NOTIF_ADDFD_SMALL	\
+	SECCOMP_IOW(3, struct seccomp_notif_addfd_small)
+
+struct seccomp_notif_addfd_big {
+	union {
+		struct seccomp_notif_addfd addfd;
+		char buf[sizeof(struct seccomp_notif_addfd) + 8];
+	};
+};
+#define SECCOMP_IOCTL_NOTIF_ADDFD_BIG	\
+	SECCOMP_IOWR(3, struct seccomp_notif_addfd_big)
+
 #ifndef PTRACE_EVENTMSG_SYSCALL_ENTRY
 #define PTRACE_EVENTMSG_SYSCALL_ENTRY	1
 #define PTRACE_EVENTMSG_SYSCALL_EXIT	2

@@ -3738,6 +3774,199 @@ TEST(user_notification_filter_empty_threaded)
 	EXPECT_GT((pollfd.revents & POLLHUP) ?: 0, 0);
 }
 
+TEST(user_notification_addfd)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd, fd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif_addfd_small small = {};
+	struct seccomp_notif_addfd_big big = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	/* 100 ms */
+	struct timespec delay = { .tv_nsec = 100000000 };
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0) {
+		if (syscall(__NR_getppid) != USER_NOTIF_MAGIC)
+			exit(1);
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+	}
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	addfd.srcfd = memfd;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0x0;
+
+	/* Verify bad newfd_flags cannot be set */
+	addfd.newfd_flags = ~O_CLOEXEC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.newfd_flags = O_CLOEXEC;
+
+	/* Verify bad flags cannot be set */
+	addfd.flags = 0xff;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.flags = 0;
+
+	/* Verify that remote_fd cannot be set without setting flags */
+	addfd.newfd = 1;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EINVAL);
+	addfd.newfd = 0;
+
+	/* Verify small size cannot be set */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_SMALL, &small), -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* Verify we can't send bits filled in unknown buffer area */
+	memset(&big, 0xAA, sizeof(big));
+	big.addfd = addfd;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big), -1);
+	EXPECT_EQ(errno, E2BIG);
+
+
+	/* Verify we can set an arbitrary remote fd */
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd);
+	/*
+	 * The child has fds 0(stdin), 1(stdout), 2(stderr), 3(memfd),
+	 * 4(listener), so the newly allocated fd should be 5.
+	 */
+	EXPECT_EQ(fd, 5);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0);
+
+	/* Verify we can set an arbitrary remote fd with large size */
+	memset(&big, 0x0, sizeof(big));
+	big.addfd = addfd;
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD_BIG, &big);
+	EXPECT_EQ(fd, 6);
+
+	/* Verify we can set a specific remote fd */
+	addfd.newfd = 42;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+	fd = ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd);
+	EXPECT_EQ(fd, 42);
+	EXPECT_EQ(filecmp(getpid(), pid, memfd, fd), 0);
+
+	/* Resume syscall */
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/*
+	 * This sets the ID of the ADD FD to the last request plus 1. The
+	 * notification ID increments 1 per notification.
+	 */
+	addfd.id = req.id + 1;
+
+	/* This spins until the underlying notification is generated */
+	while (ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd) != -1 &&
+	       errno != -EINPROGRESS)
+		nanosleep(&delay, NULL);
+
+	memset(&req, 0, sizeof(req));
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+	ASSERT_EQ(addfd.id, req.id);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/* Wait for child to finish. */
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
+TEST(user_notification_addfd_rlimit)
+{
+	pid_t pid;
+	long ret;
+	int status, listener, memfd;
+	struct seccomp_notif_addfd addfd = {};
+	struct seccomp_notif req = {};
+	struct seccomp_notif_resp resp = {};
+	const struct rlimit lim = {
+		.rlim_cur	= 0,
+		.rlim_max	= 0,
+	};
+
+	memfd = memfd_create("test", 0);
+	ASSERT_GE(memfd, 0);
+
+	ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+	ASSERT_EQ(0, ret) {
+		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+	}
+
+	/* Check that the basic notification machinery works */
+	listener = user_notif_syscall(__NR_getppid,
+				      SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	ASSERT_GE(listener, 0);
+
+	pid = fork();
+	ASSERT_GE(pid, 0);
+
+	if (pid == 0)
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
+
+
+	ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+
+	ASSERT_EQ(prlimit(pid, RLIMIT_NOFILE, &lim, NULL), 0);
+
+	addfd.srcfd = memfd;
+	addfd.newfd_flags = O_CLOEXEC;
+	addfd.newfd = 0;
+	addfd.id = req.id;
+	addfd.flags = 0;
+
+	/* Should probably spot check /proc/sys/fs/file-nr */
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EMFILE);
+
+	addfd.newfd = 100;
+	addfd.flags = SECCOMP_ADDFD_FLAG_SETFD;
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_ADDFD, &addfd), -1);
+	EXPECT_EQ(errno, EBADF);
+
+	resp.id = req.id;
+	resp.error = 0;
+	resp.val = USER_NOTIF_MAGIC;
+
+	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+	/* Wait for child to finish. */
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(true, WIFEXITED(status));
+	EXPECT_EQ(0, WEXITSTATUS(status));
+
+	close(memfd);
+}
+
 /*
  * TODO:
  * - expand NNP testing

@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/net.h>
 #include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/file.h>

@@ -18,6 +19,8 @@
 #include <linux/bitops.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
+#include <net/cls_cgroup.h>
+#include <net/netprio_cgroup.h>
 
 unsigned int sysctl_nr_open __read_mostly = 1024*1024;
 unsigned int sysctl_nr_open_min = BITS_PER_LONG;

@@ -931,6 +934,51 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
 	return err;
 }
 
+/**
+ * __receive_fd() - Install received file into file descriptor table
+ *
+ * @file: struct file that was received from another process
+ * @ufd: __user pointer to write new fd number to
+ * @o_flags: the O_* flags to apply to the new fd entry
+ *
+ * Installs a received file into the file descriptor table, with appropriate
+ * checks and count updates. Writes the fd number to userspace.
+ *
+ * This helper handles its own reference counting of the incoming
+ * struct file.
+ *
+ * Returns -ve on error.
+ */
+int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
+{
+	struct socket *sock;
+	int new_fd;
+	int error;
+
+	error = security_file_receive(file);
+	if (error)
+		return error;
+
+	new_fd = get_unused_fd_flags(o_flags);
+	if (new_fd < 0)
+		return new_fd;
+
+	error = put_user(new_fd, ufd);
+	if (error) {
+		put_unused_fd(new_fd);
+		return error;
+	}
+
+	/* Bump the usage count and install the file. */
+	sock = sock_from_file(file, &error);
+	if (sock) {
+		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
+		sock_update_classid(&sock->sk->sk_cgrp_data);
+	}
+	fd_install(new_fd, get_file(file));
+	return 0;
+}
+
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;

@@ -91,6 +91,14 @@ extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
 
+extern int __receive_fd(struct file *file, int __user *ufd,
+			unsigned int o_flags);
+static inline int receive_fd_user(struct file *file, int __user *ufd,
+				  unsigned int o_flags)
+{
+	return __receive_fd(file, ufd, o_flags);
+}
+
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);
 

@@ -240,7 +240,16 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg);
 int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags);
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname);
 struct socket *sockfd_lookup(int fd, int *err);
+
+#ifdef CONFIG_NET
 struct socket *sock_from_file(struct file *file, int *err);
+#else
+static inline struct socket *sock_from_file(struct file *file, int *err)
+{
+	return NULL;
+}
+#endif
+
 #define		     sockfd_put(sock) fput(sock->file)
 int net_ratelimit(void);
 

@@ -37,7 +37,6 @@ struct scm_cookie {
 #endif
 };
 
-int __scm_install_fd(struct file *file, int __user *ufd, unsigned int o_flags);
 void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm);
 void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm);
 int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm);

@@ -298,7 +298,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 	int err = 0, i;
 
 	for (i = 0; i < fdmax; i++) {
-		err = __scm_install_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err)
 			break;
 	}

@@ -280,36 +280,6 @@ void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_inter
 }
 EXPORT_SYMBOL(put_cmsg_scm_timestamping);
 
-int __scm_install_fd(struct file *file, int __user *ufd, unsigned int o_flags)
-{
-	struct socket *sock;
-	int new_fd;
-	int error;
-
-	error = security_file_receive(file);
-	if (error)
-		return error;
-
-	new_fd = get_unused_fd_flags(o_flags);
-	if (new_fd < 0)
-		return new_fd;
-
-	error = put_user(new_fd, ufd);
-	if (error) {
-		put_unused_fd(new_fd);
-		return error;
-	}
-
-	/* Bump the usage count and install the file. */
-	sock = sock_from_file(file, &error);
-	if (sock) {
-		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
-		sock_update_classid(&sock->sk->sk_cgrp_data);
-	}
-	fd_install(new_fd, get_file(file));
-	return 0;
-}
-
 static int scm_max_fds(struct msghdr *msg)
 {
 	if (msg->msg_controllen <= sizeof(struct cmsghdr))

@@ -336,7 +306,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 	}
 
 	for (i = 0; i < fdmax; i++) {
-		err = __scm_install_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags);
 		if (err)
 			break;
 	}

@@ -942,12 +942,13 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
  * @o_flags: the O_* flags to apply to the new fd entry
  *
  * Installs a received file into the file descriptor table, with appropriate
- * checks and count updates. Writes the fd number to userspace.
+ * checks and count updates. Optionally writes the fd number to userspace, if
+ * @ufd is non-NULL.
  *
  * This helper handles its own reference counting of the incoming
  * struct file.
  *
- * Returns -ve on error.
+ * Returns newly install fd or -ve on error.
  */
 int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 {

@@ -963,20 +964,26 @@ int __receive_fd(struct file *file, int __user *ufd, unsigned int o_flags)
 	if (new_fd < 0)
 		return new_fd;
 
-	error = put_user(new_fd, ufd);
-	if (error) {
-		put_unused_fd(new_fd);
-		return error;
+	if (ufd) {
+		error = put_user(new_fd, ufd);
+		if (error) {
+			put_unused_fd(new_fd);
+			return error;
+		}
 	}
 
-	/* Bump the usage count and install the file. */
+	/*
+	 * Bump the usage count and install the file. The resulting value of
+	 * "error" is ignored here since we only need to take action when
+	 * the file is a socket and testing "sock" for NULL is sufficient.
+	 */
 	sock = sock_from_file(file, &error);
 	if (sock) {
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
 	}
 	fd_install(new_fd, get_file(file));
-	return 0;
+	return new_fd;
 }
 
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)

@@ -9,6 +9,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/posix_types.h>
+#include <linux/errno.h>
 
 struct file;
 

@@ -96,8 +97,14 @@ extern int __receive_fd(struct file *file, int __user *ufd,
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
+	if (ufd == NULL)
+		return -EFAULT;
 	return __receive_fd(file, ufd, o_flags);
 }
+static inline int receive_fd(struct file *file, unsigned int o_flags)
+{
+	return __receive_fd(file, NULL, o_flags);
+}
 
 extern void flush_delayed_fput(void);
 extern void __fput_sync(struct file *);