The patch titled
pid namespaces: destroy pid namespace on init's death
has been added to the -mm tree. Its filename is
pid-namespaces-destroy-pid-namespace-on-inits-death.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: pid namespaces: destroy pid namespace on init's death
From: Sukadev Bhattiprolu <sukadev@xxxxxxxxxx>
Terminate all processes in a namespace when the reaper of the namespace is
exiting. We do this by walking the pidmap of the namespace and sending
SIGKILL to all processes.
Signed-off-by: Sukadev Bhattiprolu <sukadev@xxxxxxxxxx>
Acked-by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Sukadev Bhattiprolu <sukadev@xxxxxxxxxx>
Cc: Paul Menage <menage@xxxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/pid.h | 1 +
kernel/exit.c | 27 ++++++++++++++++++++++++++-
kernel/pid.c | 38 ++++++++++++++++++++++++++++++++++++++
3 files changed, 65 insertions(+), 1 deletion(-)
diff -puN include/linux/pid.h~pid-namespaces-destroy-pid-namespace-on-inits-death include/linux/pid.h
--- a/include/linux/pid.h~pid-namespaces-destroy-pid-namespace-on-inits-death
+++ a/include/linux/pid.h
@@ -125,6 +125,7 @@ extern struct pid *find_ge_pid(int nr, s
extern struct pid *alloc_pid(struct pid_namespace *ns);
extern void FASTCALL(free_pid(struct pid *pid));
+extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
/*
* the helpers to get the pid's id seen from different namespaces
diff -puN kernel/exit.c~pid-namespaces-destroy-pid-namespace-on-inits-death kernel/exit.c
--- a/kernel/exit.c~pid-namespaces-destroy-pid-namespace-on-inits-death
+++ a/kernel/exit.c
@@ -880,7 +880,32 @@ static inline void exit_child_reaper(str
if (likely(tsk->group_leader != task_child_reaper(tsk)))
return;
- panic("Attempted to kill init!");
+ if (tsk->nsproxy->pid_ns == &init_pid_ns)
+ panic("Attempted to kill init!");
+
+ /*
+ * @tsk is the last thread in the 'container-init' and is exiting.
+ * Terminate all remaining processes in the namespace and reap them
+ * before exiting @tsk.
+ *
+ * Note that @tsk (last thread of container-init) may not necessarily
+ * be the child-reaper (i.e main thread of container-init) of the
+ * namespace i.e the child_reaper may have already exited.
+ *
+ * Even after a child_reaper exits, we let it inherit orphaned children,
+ * because, pid_ns->child_reaper remains valid as long as there is
+ * at least one living sub-thread in the container init.
+
+ * This living sub-thread of the container-init will be notified when
+ * a child inherited by the 'child-reaper' exits (do_notify_parent()
+ * uses __group_send_sig_info()). Further, when reaping child processes,
+ * do_wait() iterates over children of all living sub threads.
+
+ * i.e even though 'child_reaper' thread is listed as the parent of the
+ * orphaned children, any living sub-thread in the container-init can
+ * perform the role of the child_reaper.
+ */
+ zap_pid_ns_processes(tsk->nsproxy->pid_ns);
}
fastcall NORET_TYPE void do_exit(long code)
diff -puN kernel/pid.c~pid-namespaces-destroy-pid-namespace-on-inits-death kernel/pid.c
--- a/kernel/pid.c~pid-namespaces-destroy-pid-namespace-on-inits-death
+++ a/kernel/pid.c
@@ -34,6 +34,7 @@
#include <linux/hash.h>
#include <linux/pid_namespace.h>
#include <linux/init_task.h>
+#include <linux/syscalls.h>
#define pid_hashfn(nr, ns) \
hash_long((unsigned long)nr + (unsigned long)ns, pidhash_shift)
@@ -566,6 +567,43 @@ void free_pid_ns(struct kref *kref)
put_pid_ns(parent);
}
+void zap_pid_ns_processes(struct pid_namespace *pid_ns)
+{
+ int nr;
+ int rc;
+
+ /*
+ * The last thread in the container-init thread group is terminating.
+ * Find remaining pid_ts in the namespace, signal and wait for them
+ * to exit.
+ *
+ * Note: This signals each threads in the namespace - even those that
+ * belong to the same thread group, To avoid this, we would have
+ * to walk the entire tasklist looking a processes in this
+ * namespace, but that could be unnecessarily expensive if the
+ * pid namespace has just a few processes. Or we need to
+ * maintain a tasklist for each pid namespace.
+ *
+ */
+ read_lock(&tasklist_lock);
+ nr = next_pidmap(pid_ns, 1);
+ while (nr > 0) {
+ kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
+ nr = next_pidmap(pid_ns, nr);
+ }
+ read_unlock(&tasklist_lock);
+
+ do {
+ clear_thread_flag(TIF_SIGPENDING);
+ rc = sys_wait4(-1, NULL, __WALL, NULL);
+ } while (rc != -ECHILD);
+
+
+ /* Child reaper for the pid namespace is going away */
+ pid_ns->child_reaper = NULL;
+ return;
+}
+
/*
* The pid hash table is scaled according to the amount of memory in the
* machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
_
Patches currently in -mm which might be from sukadev@xxxxxxxxxx are
handle-the-multi-threaded-inits-exit-properly.patch
pid-namespaces-round-up-the-api.patch
pid-namespaces-make-get_pid_ns-return-the-namespace-itself.patch
pid-namespaces-dynamic-kmem-cache-allocator-for-pid-namespaces.patch
pid-namespaces-dynamic-kmem-cache-allocator-for-pid-namespaces-fix.patch
pid-namespaces-define-and-use-task_active_pid_ns-wrapper.patch
pid-namespaces-rename-child_reaper-function.patch
pid-namespaces-use-task_pid-to-find-leaders-pid.patch
pid-namespaces-define-is_global_init-and-is_container_init.patch
pid-namespaces-define-is_global_init-and-is_container_init-fix.patch
pid-namespaces-define-is_global_init-and-is_container_init-m32r-fix.patch
pid-namespaces-define-is_global_init-and-is_container_init-kernel-pidc-remove-unused-exports.patch
pid-namespaces-move-alloc_pid-to-copy_process.patch
pid-namespaces-rework-forget_original_parent.patch
pid-namespaces-move-exit_task_namespaces.patch
pid-namespaces-introduce-ms_kernmount-flag.patch
pid-namespaces-prepare-proc_flust_task-to-flush-entries-from-multiple-proc-trees.patch
pid-namespaces-introduce-struct-upid.patch
pid-namespaces-add-support-for-pid-namespaces-hierarchy.patch
pid-namespaces-make-alloc_pid-free_pid-and-put_pid-work-with-struct-upid.patch
pid-namespaces-helpers-to-obtain-pid-numbers.patch
pid-namespaces-helpers-to-find-the-task-by-its-numerical-ids.patch
pid-namespaces-move-alloc_pid-lower-in-copy_process.patch
pid-namespaces-make-proc-have-multiple-superblocks-one-for-each-namespace.patch
pid-namespaces-miscelaneous-preparations-for-pid-namespaces.patch
pid-namespaces-allow-cloning-of-new-namespace.patch
pid-namespaces-make-proc_flush_task-actually-from-entries-from-multiple-namespaces.patch
pid-namespaces-initialize-the-namespaces-proc_mnt.patch
pid-namespaces-create-a-slab-cache-for-struct-pid_namespace.patch
pid-namespaces-allow-signalling-container-init.patch
pid-namespaces-destroy-pid-namespace-on-inits-death.patch
pid-namespaces-changes-to-show-virtual-ids-to-user.patch
pid-namespaces-remove-the-struct-pid-unneeded-fields.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
