mm: remove cgroup_mm_owner_callbacks

cgroup_mm_owner_callbacks() was brought in to support the memrlimit
controller, but sneaked into mainline ahead of it.  That controller has
now been shelved, and the mm_owner_changed() args were inadequate for it
anyway (they needed an mm pointer instead of a task pointer).

Remove the dead code, and restore mm_update_next_owner() locking to how it
was before: taking mmap_sem there does nothing for memcontrol.c, now the
only user of mm->owner.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Cc: Paul Menage <menage@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 1164963..08b78c0 100644 (file)
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -329,13 +329,7 @@ struct cgroup_subsys {
                        struct cgroup *cgrp);
        void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
        void (*bind)(struct cgroup_subsys *ss, struct cgroup *root);
-       /*
-        * This routine is called with the task_lock of mm->owner held
-        */
-       void (*mm_owner_changed)(struct cgroup_subsys *ss,
-                                       struct cgroup *old,
-                                       struct cgroup *new,
-                                       struct task_struct *p);
+
        int subsys_id;
        int active;
        int disabled;
@@ -400,9 +394,6 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
 
-void cgroup_mm_owner_callbacks(struct task_struct *old,
-                              struct task_struct *new);
-
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
@@ -420,9 +411,6 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
        return -EINVAL;
 }
 
-static inline void cgroup_mm_owner_callbacks(struct task_struct *old,
-                                            struct task_struct *new) {}
-
 #endif /* !CONFIG_CGROUPS */
 
 #endif /* _LINUX_CGROUP_H */

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 87bb025..f221446 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -116,7 +116,6 @@ static int root_count;
  * be called.
  */
 static int need_forkexit_callback __read_mostly;
-static int need_mm_owner_callback __read_mostly;
 
 /* convenient tests for these bits */
 inline int cgroup_is_removed(const struct cgroup *cgrp)
@@ -2539,7 +2538,6 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
        init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
 
        need_forkexit_callback |= ss->fork || ss->exit;
-       need_mm_owner_callback |= !!ss->mm_owner_changed;
 
        /* At system boot, before all subsystems have been
         * registered, no tasks have been forked, so we don't
@@ -2789,37 +2787,6 @@ void cgroup_fork_callbacks(struct task_struct *child)
        }
 }
 
-#ifdef CONFIG_MM_OWNER
-/**
- * cgroup_mm_owner_callbacks - run callbacks when the mm->owner changes
- * @p: the new owner
- *
- * Called on every change to mm->owner. mm_init_owner() does not
- * invoke this routine, since it assigns the mm->owner the first time
- * and does not change it.
- *
- * The callbacks are invoked with mmap_sem held in read mode.
- */
-void cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
-{
-       struct cgroup *oldcgrp, *newcgrp = NULL;
-
-       if (need_mm_owner_callback) {
-               int i;
-               for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-                       struct cgroup_subsys *ss = subsys[i];
-                       oldcgrp = task_cgroup(old, ss->subsys_id);
-                       if (new)
-                               newcgrp = task_cgroup(new, ss->subsys_id);
-                       if (oldcgrp == newcgrp)
-                               continue;
-                       if (ss->mm_owner_changed)
-                               ss->mm_owner_changed(ss, oldcgrp, newcgrp, new);
-               }
-       }
-}
-#endif /* CONFIG_MM_OWNER */
-
 /**
  * cgroup_post_fork - called on a new task after adding it to the task list
  * @child: the task in question

diff --git a/kernel/exit.c b/kernel/exit.c
index c9e5a1c..f923724 100644 (file)
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -642,35 +642,31 @@ retry:
        /*
         * We found no owner yet mm_users > 1: this implies that we are
         * most likely racing with swapoff (try_to_unuse()) or /proc or
-        * ptrace or page migration (get_task_mm()).  Mark owner as NULL,
-        * so that subsystems can understand the callback and take action.
+        * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
         */
-       down_write(&mm->mmap_sem);
-       cgroup_mm_owner_callbacks(mm->owner, NULL);
        mm->owner = NULL;
-       up_write(&mm->mmap_sem);
        return;
 
 assign_new_owner:
        BUG_ON(c == p);
        get_task_struct(c);
-       read_unlock(&tasklist_lock);
-       down_write(&mm->mmap_sem);
        /*
         * The task_lock protects c->mm from changing.
         * We always want mm->owner->mm == mm
         */
        task_lock(c);
+       /*
+        * Delay read_unlock() till we have the task_lock()
+        * to ensure that c does not slip away underneath us
+        */
+       read_unlock(&tasklist_lock);
        if (c->mm != mm) {
                task_unlock(c);
-               up_write(&mm->mmap_sem);
                put_task_struct(c);
                goto retry;
        }
-       cgroup_mm_owner_callbacks(mm->owner, c);
        mm->owner = c;
        task_unlock(c);
-       up_write(&mm->mmap_sem);
        put_task_struct(c);
 }
 #endif /* CONFIG_MM_OWNER */