@@ -1793,6 +1793,9 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
p->parent = p->real_parent = p->group_leader = p;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
+ p->caba = p->real_parent;
+ INIT_LIST_HEAD(&p->cabds);
+ INIT_LIST_HEAD(&p->cabd);
strncpy(p->comm, type, sizeof(p->comm)-1);
}
@@ -1136,6 +1136,7 @@ static int de_thread(struct task_struct *tsk)
list_replace_rcu(&leader->tasks, &tsk->tasks);
list_replace_init(&leader->sibling, &tsk->sibling);
+ list_replace_init(&leader->cabd, &tsk->cabd);
tsk->group_leader = tsk;
leader->group_leader = tsk;
@@ -151,11 +151,26 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
const struct cred *cred;
pid_t ppid, tpid = 0, tgid, ngid;
unsigned int max_fds = 0;
+ struct task_struct *caba;
+ struct pid *caba_pid;
+ int caba_level = 0;
+ pid_t caba_pids[MAX_PID_NS_LEVEL] = {};
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
+#ifdef CONFIG_PID_NS
+ caba = rcu_dereference(p->caba);
+ caba_pid = get_task_pid(caba, PIDTYPE_PID);
+ if (caba_pid) {
+ caba_level = caba_pid->level;
+ for (g = ns->level; g <= caba_level; g++)
+ caba_pids[g] = task_pid_nr_ns(caba, caba_pid->numbers[g].ns);
+ put_pid(caba_pid);
+ }
+#endif
+
tracer = ptrace_parent(p);
if (tracer)
tpid = task_pid_nr_ns(tracer, ns);
@@ -214,6 +229,9 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
seq_puts(m, "\nNSsid:");
for (g = ns->level; g <= pid->level; g++)
seq_put_decimal_ull(m, "\t", task_session_nr_ns(p, pid->numbers[g].ns));
+ seq_puts(m, "\nNScaba:");
+ for (g = ns->level; g <= caba_level; g++)
+ seq_put_decimal_ull(m, "\t", caba_pids[g]);
#endif
seq_putc(m, '\n');
}
@@ -973,6 +973,13 @@ struct task_struct {
struct list_head sibling;
struct task_struct *group_leader;
+ /* Closest Alive Born Ancestor process: */
+ struct task_struct __rcu *caba;
+
+ /* Closest Alive Born Descendants list: */
+ struct list_head cabds;
+ struct list_head cabd;
+
/*
* 'ptraced' is the list of tasks this task is using ptrace() on.
*
@@ -109,6 +109,9 @@ struct task_struct init_task
.children = LIST_HEAD_INIT(init_task.children),
.sibling = LIST_HEAD_INIT(init_task.sibling),
.group_leader = &init_task,
+ .caba = &init_task,
+ .cabds = LIST_HEAD_INIT(init_task.cabds),
+ .cabd = LIST_HEAD_INIT(init_task.cabd),
RCU_POINTER_INITIALIZER(real_cred, &init_cred),
RCU_POINTER_INITIALIZER(cred, &init_cred),
.comm = INIT_TASK_COMM,
@@ -82,6 +82,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead)
list_del_rcu(&p->tasks);
list_del_init(&p->sibling);
+ list_del_init(&p->cabd);
__this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_group);
@@ -562,11 +563,11 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
* 3. give it to the init process (PID 1) in our pid namespace
*/
static struct task_struct *find_new_reaper(struct task_struct *father,
- struct task_struct *child_reaper)
+ struct task_struct *child_reaper,
+ struct task_struct *thread)
{
- struct task_struct *thread, *reaper;
+ struct task_struct *reaper;
- thread = find_alive_thread(father);
if (thread)
return thread;
@@ -620,6 +621,31 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
kill_orphaned_pgrp(p, father);
}
+static struct task_struct *find_new_caba(struct task_struct *father,
+ struct task_struct *thread)
+{
+ struct task_struct *caba;
+
+ if (thread)
+ return thread;
+
+ caba = father->caba;
+ while (1) {
+ if (caba == &init_task)
+ break;
+ if (WARN_ON_ONCE(caba->caba == caba))
+ break;
+
+ thread = find_alive_thread(caba);
+ if (thread)
+ return thread;
+
+ caba = caba->caba;
+ }
+
+ return caba;
+}
+
/*
* This does two things:
*
@@ -631,17 +657,19 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
static void forget_original_parent(struct task_struct *father,
struct list_head *dead)
{
- struct task_struct *p, *t, *reaper;
+ struct task_struct *p, *t, *reaper, *thread, *caba;
if (unlikely(!list_empty(&father->ptraced)))
exit_ptrace(father, dead);
/* Can drop and reacquire tasklist_lock */
reaper = find_child_reaper(father, dead);
+ thread = find_alive_thread(father);
+
if (list_empty(&father->children))
- return;
+ goto caba;
- reaper = find_new_reaper(father, reaper);
+ reaper = find_new_reaper(father, reaper, thread);
list_for_each_entry(p, &father->children, sibling) {
for_each_thread(p, t) {
RCU_INIT_POINTER(t->real_parent, reaper);
@@ -661,6 +689,16 @@ static void forget_original_parent(struct task_struct *father,
reparent_leader(father, p, dead);
}
list_splice_tail_init(&father->children, &reaper->children);
+caba:
+ if (list_empty(&father->cabds))
+ return;
+
+ caba = find_new_caba(father, thread);
+ list_for_each_entry(p, &father->cabds, cabd) {
+ for_each_thread(p, t)
+ RCU_INIT_POINTER(t->caba, caba);
+ }
+ list_splice_tail_init(&father->cabds, &caba->cabds);
}
/*
@@ -2123,6 +2123,8 @@ static __latent_entropy struct task_struct *copy_process(
p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
+ INIT_LIST_HEAD(&p->cabds);
+ INIT_LIST_HEAD(&p->cabd);
rcu_copy_process(p);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
@@ -2386,6 +2388,7 @@ static __latent_entropy struct task_struct *copy_process(
p->parent_exec_id = current->self_exec_id;
p->exit_signal = args->exit_signal;
}
+ p->caba = p->real_parent;
klp_copy_process(p);
@@ -2437,6 +2440,7 @@ static __latent_entropy struct task_struct *copy_process(
p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
p->real_parent->signal->is_child_subreaper;
list_add_tail(&p->sibling, &p->real_parent->children);
+ list_add_tail(&p->cabd, &p->caba->cabds);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
attach_pid(p, PIDTYPE_TGID);
attach_pid(p, PIDTYPE_PGID);
In linux after parent (father) process dies, children processes are moved (reparented) to a reaper process. Roughly speaking: 1) If father has other yet alive thread, this thread would be a reaper. 2) Else if there is father's ancestor (with no pidns level change in the middle), which has PR_SET_CHILD_SUBREAPER set, this ancestor would be a reaper. 3) Else father's pidns init would be a reaper for fathers children. The problem with this for CRIU is that when CRIU comes to dump processes it does not know the order in which processes and their resources were created. And processes can have resources which a) can only be inherited when we clone processes, b) can only be created by specific processes and c) are shared between several processes (the example of such a resource is process session). For such resources CRIU restore would need to re-invent such order of process creation which at the same time creates the desired process tree topology and allows to inherit all resources right. When process reparenting involves child-sub-reapers one can drastically mix processes in process tree so that it is not obvious how to restore everything right. So this is what we came up with to help CRIU to overcome this problem: CABA = Closest Alive Born Ancestor CABD = Closest Alive Born Descendant We want to put processes in one more tree - CABA tree. This tree is not affecting reparenting or process creation in any way except for providing a new information to CRIU so that it can understand from where the reparented child had reparented, though original father is already dead and probably a fathers father too, we can still have information about the process which is still alive and was originally a parent of process sequence (of already dead processes) which lead to us - CABA. CC: Eric Biederman <ebiederm@xmission.com> CC: Kees Cook <keescook@chromium.org> CC: Alexander Viro <viro@zeniv.linux.org.uk> CC: Ingo Molnar <mingo@redhat.com> CC: Peter Zijlstra <peterz@infradead.org> CC: Juri Lelli <juri.lelli@redhat.com> CC: Vincent Guittot <vincent.guittot@linaro.org> CC: Dietmar Eggemann <dietmar.eggemann@arm.com> CC: Steven Rostedt <rostedt@goodmis.org> CC: Ben Segall <bsegall@google.com> CC: Mel Gorman <mgorman@suse.de> CC: Daniel Bristot de Oliveira <bristot@redhat.com> CC: Valentin Schneider <vschneid@redhat.com> CC: Andrew Morton <akpm@linux-foundation.org> CC: linux-ia64@vger.kernel.org CC: linux-kernel@vger.kernel.org CC: linux-mm@kvack.org CC: linux-fsdevel@vger.kernel.org Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com> --- arch/ia64/kernel/mca.c | 3 +++ fs/exec.c | 1 + fs/proc/array.c | 18 +++++++++++++++ include/linux/sched.h | 7 ++++++ init/init_task.c | 3 +++ kernel/exit.c | 50 +++++++++++++++++++++++++++++++++++++----- kernel/fork.c | 4 ++++ 7 files changed, 80 insertions(+), 6 deletions(-)