pid: Use generic ns_common::count

Switch over pid namespaces to use the newly introduced common lifetime
counter.

Currently every namespace type has its own lifetime counter which is stored
in the specific namespace struct. The lifetime counters are used
identically for all namespaces types. Namespaces may of course have
additional unrelated counters and these are not altered.

This introduces a common lifetime counter into struct ns_common. The
ns_common struct encompasses information that all namespaces share. That
should include the lifetime counter since its common for all of them.

It also allows us to unify the type of the counters across all namespaces.
Most of them use refcount_t but one uses atomic_t and at least one uses
kref. Especially the last one doesn't make much sense since it's just a
wrapper around refcount_t since 2016 and actually complicates cleanup
operations by having to use container_of() to cast the correct namespace
struct out of struct ns_common.

Having the lifetime counter for the namespaces in one place reduces
maintenance cost. Not just because after switching all namespaces over we
will have removed more code than we added but also because the logic is
more easily understandable and we indicate to the user that the basic
lifetime requirements for all namespaces are currently identical.

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Link: https://lore.kernel.org/r/159644979226.604812.7512601754841882036.stgit@localhost.localdomain
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 5a5cb45..7c7e627 100644 (file)
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -8,7 +8,6 @@
 #include <linux/workqueue.h>
 #include <linux/threads.h>
 #include <linux/nsproxy.h>
-#include <linux/kref.h>
 #include <linux/ns_common.h>
 #include <linux/idr.h>
 
@@ -18,7 +17,6 @@
 struct fs_pin;
 
 struct pid_namespace {
-       struct kref kref;
        struct idr idr;
        struct rcu_head rcu;
        unsigned int pid_allocated;
@@ -43,7 +41,7 @@ extern struct pid_namespace init_pid_ns;
 static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns)
 {
        if (ns != &init_pid_ns)
-               kref_get(&ns->kref);
+               refcount_inc(&ns->ns.count);
        return ns;
 }
 

diff --git a/kernel/pid.c b/kernel/pid.c
index b2562a7..2b97bed 100644 (file)
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -72,7 +72,7 @@ int pid_max_max = PID_MAX_LIMIT;
  * the scheme scales to up to 4 million PIDs, runtime.
  */
 struct pid_namespace init_pid_ns = {
-       .kref = KREF_INIT(2),
+       .ns.count = REFCOUNT_INIT(2),
        .idr = IDR_INIT(init_pid_ns.idr),
        .pid_allocated = PIDNS_ADDING,
        .level = 0,

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index ac135bd..166a91c 100644 (file)
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -102,7 +102,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
                goto out_free_idr;
        ns->ns.ops = &pidns_operations;
 
-       kref_init(&ns->kref);
+       refcount_set(&ns->ns.count, 1);
        ns->level = level;
        ns->parent = get_pid_ns(parent_pid_ns);
        ns->user_ns = get_user_ns(user_ns);
@@ -148,22 +148,15 @@ struct pid_namespace *copy_pid_ns(unsigned long flags,
        return create_pid_namespace(user_ns, old_ns);
 }
 
-static void free_pid_ns(struct kref *kref)
-{
-       struct pid_namespace *ns;
-
-       ns = container_of(kref, struct pid_namespace, kref);
-       destroy_pid_namespace(ns);
-}
-
 void put_pid_ns(struct pid_namespace *ns)
 {
        struct pid_namespace *parent;
 
        while (ns != &init_pid_ns) {
                parent = ns->parent;
-               if (!kref_put(&ns->kref, free_pid_ns))
+               if (!refcount_dec_and_test(&ns->ns.count))
                        break;
+               destroy_pid_namespace(ns);
                ns = parent;
        }
 }