From: Andrei Vagin <[email protected]>
seccomp_unotify allows more privileged processes do actions on behalf
of less privileged processes.
In many cases, the workflow is fully synchronous. It means a target
process triggers a system call and passes controls to a supervisor
process that handles the system call and returns controls to the target
process. In this context, "synchronous" means that only one process is
running and another one is waiting.
There is the WF_CURRENT_CPU flag that is used to advise the scheduler to
move the wakee to the current CPU. For such synchronous workflows, it
makes context switches a few times faster.
Right now, each interaction takes 12µs. With this patch, it takes about
3µs.
This change introduce the SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP flag that
it used to enable the sync mode.
Signed-off-by: Andrei Vagin <[email protected]>
---
include/uapi/linux/seccomp.h | 4 ++++
kernel/seccomp.c | 31 +++++++++++++++++++++++++++++--
2 files changed, 33 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/seccomp.h b/include/uapi/linux/seccomp.h
index 0fdc6ef02b94..dbfc9b37fcae 100644
--- a/include/uapi/linux/seccomp.h
+++ b/include/uapi/linux/seccomp.h
@@ -115,6 +115,8 @@ struct seccomp_notif_resp {
__u32 flags;
};
+#define SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP (1UL << 0)
+
/* valid flags for seccomp_notif_addfd */
#define SECCOMP_ADDFD_FLAG_SETFD (1UL << 0) /* Specify remote fd */
#define SECCOMP_ADDFD_FLAG_SEND (1UL << 1) /* Addfd and return it, atomically */
@@ -150,4 +152,6 @@ struct seccomp_notif_addfd {
#define SECCOMP_IOCTL_NOTIF_ADDFD SECCOMP_IOW(3, \
struct seccomp_notif_addfd)
+#define SECCOMP_IOCTL_NOTIF_SET_FLAGS SECCOMP_IOW(4, __u64)
+
#endif /* _UAPI_LINUX_SECCOMP_H */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 876022e9c88c..0a62d44f4898 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -143,9 +143,12 @@ struct seccomp_kaddfd {
* filter->notify_lock.
* @next_id: The id of the next request.
* @notifications: A list of struct seccomp_knotif elements.
+ * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags.
*/
+
struct notification {
atomic_t requests;
+ u32 flags;
u64 next_id;
struct list_head notifications;
};
@@ -1117,7 +1120,10 @@ static int seccomp_do_user_notification(int this_syscall,
INIT_LIST_HEAD(&n.addfd);
atomic_add(1, &match->notif->requests);
- wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ if (match->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ wake_up_poll_on_current_cpu(&match->wqh, EPOLLIN | EPOLLRDNORM);
+ else
+ wake_up_poll(&match->wqh, EPOLLIN | EPOLLRDNORM);
/*
* This is where we wait for a reply from userspace.
@@ -1593,7 +1599,10 @@ static long seccomp_notify_send(struct seccomp_filter *filter,
knotif->error = resp.error;
knotif->val = resp.val;
knotif->flags = resp.flags;
- complete(&knotif->ready);
+ if (filter->notif->flags & SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ complete_on_current_cpu(&knotif->ready);
+ else
+ complete(&knotif->ready);
out:
mutex_unlock(&filter->notify_lock);
return ret;
@@ -1623,6 +1632,22 @@ static long seccomp_notify_id_valid(struct seccomp_filter *filter,
return ret;
}
+static long seccomp_notify_set_flags(struct seccomp_filter *filter,
+ unsigned long flags)
+{
+ long ret;
+
+ if (flags & ~SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP)
+ return -EINVAL;
+
+ ret = mutex_lock_interruptible(&filter->notify_lock);
+ if (ret < 0)
+ return ret;
+ filter->notif->flags = flags;
+ mutex_unlock(&filter->notify_lock);
+ return 0;
+}
+
static long seccomp_notify_addfd(struct seccomp_filter *filter,
struct seccomp_notif_addfd __user *uaddfd,
unsigned int size)
@@ -1752,6 +1777,8 @@ 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);
+ case SECCOMP_IOCTL_NOTIF_SET_FLAGS:
+ return seccomp_notify_set_flags(filter, arg);
}
/* Extensible Argument ioctls */
--
2.39.0.314.g84b9a713c41-goog
On Tue, Jan 10, 2023 at 01:30:09PM -0800, Andrei Vagin wrote:
> From: Andrei Vagin <[email protected]>
>
> seccomp_unotify allows more privileged processes do actions on behalf
> of less privileged processes.
>
> In many cases, the workflow is fully synchronous. It means a target
> process triggers a system call and passes controls to a supervisor
> process that handles the system call and returns controls to the target
> process. In this context, "synchronous" means that only one process is
> running and another one is waiting.
>
> There is the WF_CURRENT_CPU flag that is used to advise the scheduler to
> move the wakee to the current CPU. For such synchronous workflows, it
> makes context switches a few times faster.
>
> Right now, each interaction takes 12?s. With this patch, it takes about
> 3?s.
>
> This change introduce the SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP flag that
> it used to enable the sync mode.
What about just not having a flag and using the new primitives all the
time? Is there any reason not to?
Tycho
On Thu, Jan 12, 2023 at 7:00 AM Tycho Andersen <[email protected]> wrote:
>
> On Tue, Jan 10, 2023 at 01:30:09PM -0800, Andrei Vagin wrote:
> > From: Andrei Vagin <[email protected]>
> >
> > seccomp_unotify allows more privileged processes do actions on behalf
> > of less privileged processes.
> >
> > In many cases, the workflow is fully synchronous. It means a target
> > process triggers a system call and passes controls to a supervisor
> > process that handles the system call and returns controls to the target
> > process. In this context, "synchronous" means that only one process is
> > running and another one is waiting.
> >
> > There is the WF_CURRENT_CPU flag that is used to advise the scheduler to
> > move the wakee to the current CPU. For such synchronous workflows, it
> > makes context switches a few times faster.
> >
> > Right now, each interaction takes 12盜. With this patch, it takes about
> > 3盜.
> >
> > This change introduces the SECCOMP_USER_NOTIF_FD_SYNC_WAKE_UP flag that
> > it used to enable the sync mode.
>
> What about just not having a flag and using the new primitives all the
> time? Is there any reason not to?
I was thinking about that but then I decided that it can have a
negative impact in cases
when workflows are not synchronous. This can happen when one process wakes up
another one and continues running on cpu. With the flag, both
processes are scheduled
on the same cpu. Without the flag, they can be scheduled on different
cpu-s and run
concurrently.
In the seccomp unotify, switches from tracee to supervisor are always
synchronous.
Switches into the opposite direction can be either type.
I think it is better to let users decide what type is more suitable
for their workloads.
Thanks,
Andrei