diff options
| -rw-r--r-- | Documentation/userspace-api/seccomp_filter.rst | 10 | ||||
| -rw-r--r-- | include/linux/seccomp.h | 3 | ||||
| -rw-r--r-- | include/uapi/linux/seccomp.h | 2 | ||||
| -rw-r--r-- | kernel/seccomp.c | 42 |
4 files changed, 54 insertions, 3 deletions
diff --git a/Documentation/userspace-api/seccomp_filter.rst b/Documentation/userspace-api/seccomp_filter.rst index 539e9d4a4860..d1e2b9193f09 100644 --- a/Documentation/userspace-api/seccomp_filter.rst +++ b/Documentation/userspace-api/seccomp_filter.rst @@ -271,6 +271,16 @@ notifying process it will be replaced. The supervisor can also add an FD, and respond atomically by using the ``SECCOMP_ADDFD_FLAG_SEND`` flag and the return value will be the injected file descriptor number. +The notifying process can be preempted, resulting in the notification being +aborted. This can be problematic when trying to take actions on behalf of the +notifying process that are long-running and typically retryable (mounting a +filesytem). Alternatively, at filter installation time, the +``SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV`` flag can be set. This flag makes it +such that when a user notification is received by the supervisor, the notifying +process will ignore non-fatal signals until the response is sent. Signals that +are sent prior to the notification being received by userspace are handled +normally. + It is worth noting that ``struct seccomp_data`` contains the values of register arguments to the syscall, but does not contain pointers to memory. The task's memory is accessible to suitably privileged traces via ``ptrace()`` or diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index 0c564e5d40ff..d31d76be4982 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -8,7 +8,8 @@ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ - SECCOMP_FILTER_FLAG_TSYNC_ESRCH) + SECCOMP_FILTER_FLAG_TSYNC_ESRCH | \ + SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h index 78074254ab98..0fdc6ef02b94 100644 --- a/include/uapi/linux/seccomp.h +++ b/include/uapi/linux/seccomp.h @@ -23,6 +23,8 @@ #define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2) #define SECCOMP_FILTER_FLAG_NEW_LISTENER (1UL << 3) #define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4) +/* Received notifications wait in killable state (only respond to fatal signals) */ +#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5) /* * All BPF programs must return a 32-bit value. diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 3caa0fe85235..e9852d1b4a5e 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -200,6 +200,8 @@ static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter) * the filter can be freed. * @cache: cache of arch/syscall mappings to actions * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged + * @wait_killable_recv: Put notifying process in killable state once the + * notification is received by the userspace listener. * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information @@ -220,6 +222,7 @@ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; + bool wait_killable_recv; struct action_cache cache; struct seccomp_filter *prev; struct bpf_prog *prog; @@ -893,6 +896,10 @@ static long seccomp_attach_filter(unsigned int flags, if (flags & SECCOMP_FILTER_FLAG_LOG) filter->log = true; + /* Set wait killable flag, if present. */ + if (flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) + filter->wait_killable_recv = true; + /* * If there is an existing filter, make it the prev and don't drop its * task reference. @@ -1080,6 +1087,12 @@ static void seccomp_handle_addfd(struct seccomp_kaddfd *addfd, struct seccomp_kn complete(&addfd->completion); } +static bool should_sleep_killable(struct seccomp_filter *match, + struct seccomp_knotif *n) +{ + return match->wait_killable_recv && n->state == SECCOMP_NOTIFY_SENT; +} + static int seccomp_do_user_notification(int this_syscall, struct seccomp_filter *match, const struct seccomp_data *sd) @@ -1110,11 +1123,25 @@ static int seccomp_do_user_notification(int this_syscall, * This is where we wait for a reply from userspace. */ do { + bool wait_killable = should_sleep_killable(match, &n); + mutex_unlock(&match->notify_lock); - err = wait_for_completion_interruptible(&n.ready); + if (wait_killable) + err = wait_for_completion_killable(&n.ready); + else + err = wait_for_completion_interruptible(&n.ready); mutex_lock(&match->notify_lock); - if (err != 0) + + if (err != 0) { + /* + * Check to see if the notifcation got picked up and + * whether we should switch to wait killable. + */ + if (!wait_killable && should_sleep_killable(match, &n)) + continue; + goto interrupted; + } addfd = list_first_entry_or_null(&n.addfd, struct seccomp_kaddfd, list); @@ -1484,6 +1511,9 @@ out: mutex_lock(&filter->notify_lock); knotif = find_notification(filter, unotif.id); if (knotif) { + /* Reset the process to make sure it's not stuck */ + if (should_sleep_killable(filter, knotif)) + complete(&knotif->ready); knotif->state = SECCOMP_NOTIFY_INIT; up(&filter->notif->request); } @@ -1829,6 +1859,14 @@ static long seccomp_set_mode_filter(unsigned int flags, ((flags & SECCOMP_FILTER_FLAG_TSYNC_ESRCH) == 0)) return -EINVAL; + /* + * The SECCOMP_FILTER_FLAG_WAIT_KILLABLE_SENT flag doesn't make sense + * without the SECCOMP_FILTER_FLAG_NEW_LISTENER flag. + */ + if ((flags & SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV) && + ((flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) == 0)) + return -EINVAL; + /* Prepare the new filter before holding any locks. */ prepared = seccomp_prepare_user_filter(filter); if (IS_ERR(prepared)) |