From 49cb2fc42ce4b7a656ee605e30c302efaa39c1a7 Mon Sep 17 00:00:00 2001 From: Adrian Reber Date: Fri, 15 Nov 2019 13:36:20 +0100 Subject: fork: extend clone3() to support setting a PID The main motivation to add set_tid to clone3() is CRIU. To restore a process with the same PID/TID CRIU currently uses /proc/sys/kernel/ns_last_pid. It writes the desired (PID - 1) to ns_last_pid and then (quickly) does a clone(). This works most of the time, but it is racy. It is also slow as it requires multiple syscalls. Extending clone3() to support *set_tid makes it possible restore a process using CRIU without accessing /proc/sys/kernel/ns_last_pid and race free (as long as the desired PID/TID is available). This clone3() extension places the same restrictions (CAP_SYS_ADMIN) on clone3() with *set_tid as they are currently in place for ns_last_pid. The original version of this change was using a single value for set_tid. At the 2019 LPC, after presenting set_tid, it was, however, decided to change set_tid to an array to enable setting the PID of a process in multiple PID namespaces at the same time. If a process is created in a PID namespace it is possible to influence the PID inside and outside of the PID namespace. Details also in the corresponding selftest. To create a process with the following PIDs: PID NS level Requested PID 0 (host) 31496 1 42 2 1 For that example the two newly introduced parameters to struct clone_args (set_tid and set_tid_size) would need to be: set_tid[0] = 1; set_tid[1] = 42; set_tid[2] = 31496; set_tid_size = 3; If only the PIDs of the two innermost nested PID namespaces should be defined it would look like this: set_tid[0] = 1; set_tid[1] = 42; set_tid_size = 2; The PID of the newly created process would then be the next available free PID in the PID namespace level 0 (host) and 42 in the PID namespace at level 1 and the PID of the process in the innermost PID namespace would be 1. The set_tid array is used to specify the PID of a process starting from the innermost nested PID namespaces up to set_tid_size PID namespaces. set_tid_size cannot be larger then the current PID namespace level. Signed-off-by: Adrian Reber Reviewed-by: Christian Brauner Reviewed-by: Oleg Nesterov Reviewed-by: Dmitry Safonov <0x7f454c46@gmail.com> Acked-by: Andrei Vagin Link: https://lore.kernel.org/r/20191115123621.142252-1-areber@redhat.com Signed-off-by: Christian Brauner --- kernel/pid.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 57 insertions(+), 15 deletions(-) (limited to 'kernel/pid.c') diff --git a/kernel/pid.c b/kernel/pid.c index 7b5f6c963d72..2278e249141d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -157,7 +157,8 @@ void free_pid(struct pid *pid) call_rcu(&pid->rcu, delayed_put_pid); } -struct pid *alloc_pid(struct pid_namespace *ns) +struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, + size_t set_tid_size) { struct pid *pid; enum pid_type type; @@ -166,6 +167,17 @@ struct pid *alloc_pid(struct pid_namespace *ns) struct upid *upid; int retval = -ENOMEM; + /* + * set_tid_size contains the size of the set_tid array. Starting at + * the most nested currently active PID namespace it tells alloc_pid() + * which PID to set for a process in that most nested PID namespace + * up to set_tid_size PID namespaces. It does not have to set the PID + * for a process in all nested PID namespaces but set_tid_size must + * never be greater than the current ns->level + 1. + */ + if (set_tid_size > ns->level + 1) + return ERR_PTR(-EINVAL); + pid = kmem_cache_alloc(ns->pid_cachep, GFP_KERNEL); if (!pid) return ERR_PTR(retval); @@ -174,24 +186,54 @@ struct pid *alloc_pid(struct pid_namespace *ns) pid->level = ns->level; for (i = ns->level; i >= 0; i--) { - int pid_min = 1; + int tid = 0; + + if (set_tid_size) { + tid = set_tid[ns->level - i]; + + retval = -EINVAL; + if (tid < 1 || tid >= pid_max) + goto out_free; + /* + * Also fail if a PID != 1 is requested and + * no PID 1 exists. + */ + if (tid != 1 && !tmp->child_reaper) + goto out_free; + retval = -EPERM; + if (!ns_capable(tmp->user_ns, CAP_SYS_ADMIN)) + goto out_free; + set_tid_size--; + } idr_preload(GFP_KERNEL); spin_lock_irq(&pidmap_lock); - /* - * init really needs pid 1, but after reaching the maximum - * wrap back to RESERVED_PIDS - */ - if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) - pid_min = RESERVED_PIDS; - - /* - * Store a null pointer so find_pid_ns does not find - * a partially initialized PID (see below). - */ - nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, - pid_max, GFP_ATOMIC); + if (tid) { + nr = idr_alloc(&tmp->idr, NULL, tid, + tid + 1, GFP_ATOMIC); + /* + * If ENOSPC is returned it means that the PID is + * alreay in use. Return EEXIST in that case. + */ + if (nr == -ENOSPC) + nr = -EEXIST; + } else { + int pid_min = 1; + /* + * init really needs pid 1, but after reaching the + * maximum wrap back to RESERVED_PIDS + */ + if (idr_get_cursor(&tmp->idr) > RESERVED_PIDS) + pid_min = RESERVED_PIDS; + + /* + * Store a null pointer so find_pid_ns does not find + * a partially initialized PID (see below). + */ + nr = idr_alloc_cyclic(&tmp->idr, NULL, pid_min, + pid_max, GFP_ATOMIC); + } spin_unlock_irq(&pidmap_lock); idr_preload_end(); -- cgit v1.2.3