Quoting Oren Laadan (orenl@xxxxxxxxxxx):
> Ensure that all members of a thread group are in sys_restart before
> restoring any of them. Otherwise, restore may modify shared state and
> crash or fault a thread still in userspace,
>
> For thread groups, each thread scans the entire group and tests for
> PF_RESTARTING on every member. If not all are set, then we wait, and
> when woken up try again (unless signaled). If all are set, then we're
> done and wakeup all threads.
>
> Signed-off-by: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
> ---
> checkpoint/restart.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 files changed, 52 insertions(+), 0 deletions(-)
>
> diff --git a/checkpoint/restart.c b/checkpoint/restart.c
> index 5d936cf..37454c5 100644
> --- a/checkpoint/restart.c
> +++ b/checkpoint/restart.c
> @@ -695,6 +695,54 @@ static int do_ghost_task(void)
> /* NOT REACHED */
> }
>
> +/*
> + * Ensure that all members of a thread group are in sys_restart before
> + * restoring any of them. Otherwise, restore may modify shared state
> + * and crash or fault a thread still in userspace,
> + */
> +static int wait_sync_threads(void)
> +{
> + struct task_struct *p, *leader;
> +
> + if (thread_group_empty(current))
> + return 0;
> +
> + p = leader = current->group_leader;
> +
> + /*
> + * Our PF_RESTARTING is already set. Each thread loops through
> + * the group testing everyone's PF_RESTARTING. If not set on
> + * all members, it sleeps to retry later. Otherwise it wakes
> + * up all sleepers and returns.
> + */
> + retry:
> + __set_current_state(TASK_INTERRUPTIBLE);
> +
> + read_lock(&tasklist_lock);
> + do {
> + if (!(p->flags & PF_RESTARTING))
> + break;
> + p = next_thread(p);
> + } while (p != leader);
> +
> + if (p != leader) {
> + read_unlock(&tasklist_lock);
> + if (signal_pending(current))
Not sure... but do you need to get back to TASK_RUNNING
in this case? (the schedule() below does it automatically,
but not this failure case)
> + return -EINTR;
> + schedule();
> + goto retry;
> + }
> +
> + do {
> + wake_up_process(p);
> + p = next_thread(p);
> + } while (p != leader);
> + read_unlock(&tasklist_lock);
> +
> + __set_current_state(TASK_RUNNING);
> + return 0;
> +}
> +
> static int do_restore_task(void)
> {
> struct ckpt_ctx *ctx;
> @@ -706,6 +754,10 @@ static int do_restore_task(void)
>
> current->flags |= PF_RESTARTING;
>
> + ret = wait_sync_threads();
> + if (ret < 0)
> + return ret;
> +
> /* wait for our turn, do the restore, and tell next task in line */
> ret = wait_task_active(ctx);
> if (ret < 0)
> --
> 1.6.0.4
>
> _______________________________________________
> Containers mailing list
> Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
> https://lists.linux-foundation.org/mailman/listinfo/containers
_______________________________________________
Containers mailing list
Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/containers
