In preparation for users of the "install a received file" logic outside of net/ (pidfd and seccomp), relocate and rename __scm_install_fd() from net/core/scm.c to __receive_fd() in fs/file.c, and provide a wrapper named receive_fd_user(), as future patches will change the interface to __receive_fd().

Reviewed-by: Sargun Dhillon sargun@sargun.me Acked-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Kees Cook keescook@chromium.org --- fs/file.c | 41 +++++++++++++++++++++++++++++++++++++++++ include/linux/file.h | 8 ++++++++ include/net/scm.h | 1 - net/compat.c | 2 +- net/core/scm.c | 27 +-------------------------- 5 files changed, 51 insertions(+), 28 deletions(-)

diff --git a/fs/file.c b/fs/file.c index abb8b7081d7a..6220bf440809 100644 --- a/fs/file.c +++ b/fs/file.c @@ -18,6 +18,7 @@ #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> +#include <net/sock.h>

unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; @@ -931,6 +932,46 @@ 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) +{ + 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 sock usage counts, if any. */ + __receive_sock(file); + fd_install(new_fd, get_file(file)); + return 0; +} + static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; diff --git a/include/linux/file.h b/include/linux/file.h index 122f80084a3e..b14ff2ffd0bd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -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 *);

diff --git a/include/net/scm.h b/include/net/scm.h index 581a94d6c613..1ce365f4c256 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -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); diff --git a/net/compat.c b/net/compat.c index 27d477fdcaa0..e74cd3dae8b0 100644 --- a/net/compat.c +++ b/net/compat.c @@ -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; } diff --git a/net/core/scm.c b/net/core/scm.c index 44f03213dcab..67c166a7820d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -280,31 +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) -{ - 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 sock usage counts, if any. */ - __receive_sock(file); - fd_install(new_fd, get_file(file)); - return 0; -} - static int scm_max_fds(struct msghdr *msg) { if (msg->msg_controllen <= sizeof(struct cmsghdr)) @@ -331,7 +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; }

Replace the open-coded version of receive_fd() with a call to the new helper.

Thanks to Vamshi K Sthambamkadi vamshi.k.sthambamkadi@gmail.com for catching a missed fput() in an earlier version of this patch.

Reviewed-by: Sargun Dhillon sargun@sargun.me Acked-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Kees Cook keescook@chromium.org --- kernel/pid.c | 15 ++------------- 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/kernel/pid.c b/kernel/pid.c index 85ed00abdc7c..da5aea5f04fa 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -636,19 +636,8 @@ 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); - __receive_sock(file); - } + ret = receive_fd(file, O_CLOEXEC); + fput(file);

return ret; }

From: Sargun Dhillon sargun@sargun.me

The current SECCOMP_RET_USER_NOTIF API allows for syscall supervision over an fd. It is often used in settings where a supervising task emulates syscalls on behalf of a supervised task in userspace, either to further restrict the supervisee's syscall abilities or to circumvent kernel enforced restrictions the supervisor deems safe to lift (e.g. actually performing a mount(2) for an unprivileged container).

While SECCOMP_RET_USER_NOTIF allows for the interception of any syscall, only a certain subset of syscalls could be correctly emulated. Over the last few development cycles, the set of syscalls which can't be emulated has been reduced due to the addition of pidfd_getfd(2). With this we are now able to, for example, intercept syscalls that require the supervisor to operate on file descriptors of the supervisee such as connect(2).

However, syscalls that cause new file descriptors to be installed can not currently be correctly emulated since there is no way for the supervisor to inject file descriptors into the supervisee. This patch adds a new addfd ioctl to remove this restriction by allowing the supervisor to install file descriptors into the intercepted task. By implementing this feature via seccomp the supervisor effectively instructs the supervisee to install a set of file descriptors into its own file descriptor table during the intercepted syscall. This way it is possible to intercept syscalls such as open() or accept(), and install (or replace, like dup2(2)) the supervisor's resulting fd into the supervisee. One replacement use-case would be to redirect the stdout and stderr of a supervisee into log file descriptors opened by the supervisor.

The ioctl handling is based on the discussions[1] of how Extensible Arguments should interact with ioctls. Instead of building size into the addfd structure, make it a function of the ioctl command (which is how sizes are normally passed to ioctls). To support forward and backward compatibility, just mask out the direction and size, and match everything. The size (and any future direction) checks are done along with copy_struct_from_user() logic.

As a note, the seccomp_notif_addfd structure is laid out based on 8-byte alignment without requiring packing as there have been packing issues with uapi highlighted before[2][3]. Although we could overload the newfd field and use -1 to indicate that it is not to be used, doing so requires changing the size of the fd field, and introduces struct packing complexity.

[1]: https://lore.kernel.org/lkml/87o8w9bcaf.fsf@mid.deneb.enyo.de/ [2]: https://lore.kernel.org/lkml/a328b91d-fd8f-4f27-b3c2-91a9c45f18c0@rasmusvill... [3]: https://lore.kernel.org/lkml/20200612104629.GA15814@ircssh-2.c.rugged-nimbus...

Suggested-by: Matt Denton mpdenton@google.com Link: https://lore.kernel.org/r/20200603011044.7972-4-sargun@sargun.me Signed-off-by: Sargun Dhillon sargun@sargun.me Co-developed-by: Kees Cook keescook@chromium.org Signed-off-by: Kees Cook keescook@chromium.org --- include/linux/seccomp.h | 4 + include/uapi/linux/seccomp.h | 22 +++++ kernel/seccomp.c | 173 ++++++++++++++++++++++++++++++++++- 3 files changed, 198 insertions(+), 1 deletion(-)

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index babcd6c02d09..881c90b6aa25 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -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> diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 965290f7dcc2..6ba18b82a02e 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.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 */ diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 866a432cd746..b2725a2a9f3e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -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(addfd) < SECCOMP_NOTIFY_ADDFD_SIZE_VER0); + BUILD_BUG_ON(sizeof(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; }

From: Sargun Dhillon sargun@sargun.me

Test whether we can add file descriptors in response to notifications. This injects the file descriptors via notifications, and then uses kcmp to determine whether or not it has been successful.

It also includes some basic sanity checking for arguments.

Signed-off-by: Sargun Dhillon sargun@sargun.me Link: https://lore.kernel.org/r/20200603011044.7972-5-sargun@sargun.me Co-developed-by: Kees Cook keescook@chromium.org Signed-off-by: Kees Cook keescook@chromium.org --- tools/testing/selftests/seccomp/seccomp_bpf.c | 229 ++++++++++++++++++ 1 file changed, 229 insertions(+)

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 4662a25bc9e8..3f41b32b9165 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -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 @@ -3740,6 +3776,199 @@ 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