Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

[karo-tx-linux.git] / kernel / cgroup.c

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index f1603c153890d2b9dbd37a5c687fd297c6137f24..470f6536b9e8cfb029eedb5ecdb3c3e8c3c341be 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -97,6 +97,12 @@ static DEFINE_SPINLOCK(css_set_lock);
  */
 static DEFINE_SPINLOCK(cgroup_idr_lock);
 
+/*
+ * Protects cgroup_file->kn for !self csses.  It synchronizes notifications
+ * against file removal/re-creation across css hiding.
+ */
+static DEFINE_SPINLOCK(cgroup_file_kn_lock);
+
 /*
  * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
  * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
@@ -754,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset)
        if (!atomic_dec_and_test(&cset->refcount))
                return;
 
-       /* This css_set is dead. unlink it and release cgroup refcounts */
-       for_each_subsys(ss, ssid)
+       /* This css_set is dead. unlink it and release cgroup and css refs */
+       for_each_subsys(ss, ssid) {
                list_del(&cset->e_cset_node[ssid]);
+               css_put(cset->subsys[ssid]);
+       }
        hash_del(&cset->hlist);
        css_set_count--;
 
@@ -1056,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset,
        key = css_set_hash(cset->subsys);
        hash_add(css_set_table, &cset->hlist, key);
 
-       for_each_subsys(ss, ssid)
+       for_each_subsys(ss, ssid) {
+               struct cgroup_subsys_state *css = cset->subsys[ssid];
+
                list_add_tail(&cset->e_cset_node[ssid],
-                             &cset->subsys[ssid]->cgroup->e_csets[ssid]);
+                             &css->cgroup->e_csets[ssid]);
+               css_get(css);
+       }
 
        spin_unlock_bh(&css_set_lock);
 
@@ -1393,6 +1405,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
        char name[CGROUP_FILE_NAME_MAX];
 
        lockdep_assert_held(&cgroup_mutex);
+
+       if (cft->file_offset) {
+               struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss);
+               struct cgroup_file *cfile = (void *)css + cft->file_offset;
+
+               spin_lock_irq(&cgroup_file_kn_lock);
+               cfile->kn = NULL;
+               spin_unlock_irq(&cgroup_file_kn_lock);
+       }
+
        kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
@@ -1856,7 +1878,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 
        INIT_LIST_HEAD(&cgrp->self.sibling);
        INIT_LIST_HEAD(&cgrp->self.children);
-       INIT_LIST_HEAD(&cgrp->self.files);
        INIT_LIST_HEAD(&cgrp->cset_links);
        INIT_LIST_HEAD(&cgrp->pidlists);
        mutex_init(&cgrp->pidlist_mutex);
@@ -2216,6 +2237,9 @@ struct cgroup_taskset {
        struct list_head        src_csets;
        struct list_head        dst_csets;
 
+       /* the subsys currently being processed */
+       int                     ssid;
+
        /*
         * Fields for cgroup_taskset_*() iteration.
         *
@@ -2278,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task,
 /**
  * cgroup_taskset_first - reset taskset and return the first task
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * @tset iteration is initialized and the first task is returned.
  */
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+                                        struct cgroup_subsys_state **dst_cssp)
 {
        tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
        tset->cur_task = NULL;
 
-       return cgroup_taskset_next(tset);
+       return cgroup_taskset_next(tset, dst_cssp);
 }
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * Return the next task in @tset.  Iteration must have been initialized
  * with cgroup_taskset_first().
  */
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+                                       struct cgroup_subsys_state **dst_cssp)
 {
        struct css_set *cset = tset->cur_cset;
        struct task_struct *task = tset->cur_task;
@@ -2311,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
                if (&task->cg_list != &cset->mg_tasks) {
                        tset->cur_cset = cset;
                        tset->cur_task = task;
+
+                       /*
+                        * This function may be called both before and
+                        * after cgroup_taskset_migrate().  The two cases
+                        * can be distinguished by looking at whether @cset
+                        * has its ->mg_dst_cset set.
+                        */
+                       if (cset->mg_dst_cset)
+                               *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+                       else
+                               *dst_cssp = cset->subsys[tset->ssid];
+
                        return task;
                }
 
@@ -2346,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
        /* check that we can legitimately attach to the cgroup */
        for_each_e_css(css, i, dst_cgrp) {
                if (css->ss->can_attach) {
-                       ret = css->ss->can_attach(css, tset);
+                       tset->ssid = i;
+                       ret = css->ss->can_attach(tset);
                        if (ret) {
                                failed_css = css;
                                goto out_cancel_attach;
@@ -2379,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
         */
        tset->csets = &tset->dst_csets;
 
-       for_each_e_css(css, i, dst_cgrp)
-               if (css->ss->attach)
-                       css->ss->attach(css, tset);
+       for_each_e_css(css, i, dst_cgrp) {
+               if (css->ss->attach) {
+                       tset->ssid = i;
+                       css->ss->attach(tset);
+               }
+       }
 
        ret = 0;
        goto out_release_tset;
@@ -2390,8 +2434,10 @@ out_cancel_attach:
        for_each_e_css(css, i, dst_cgrp) {
                if (css == failed_css)
                        break;
-               if (css->ss->cancel_attach)
-                       css->ss->cancel_attach(css, tset);
+               if (css->ss->cancel_attach) {
+                       tset->ssid = i;
+                       css->ss->cancel_attach(tset);
+               }
        }
 out_release_tset:
        spin_lock_bh(&css_set_lock);
@@ -3313,9 +3359,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
        if (cft->file_offset) {
                struct cgroup_file *cfile = (void *)css + cft->file_offset;
 
-               kernfs_get(kn);
+               spin_lock_irq(&cgroup_file_kn_lock);
                cfile->kn = kn;
-               list_add(&cfile->node, &css->files);
+               spin_unlock_irq(&cgroup_file_kn_lock);
        }
 
        return 0;
@@ -3552,6 +3598,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
        return cgroup_add_cftypes(ss, cfts);
 }
 
+/**
+ * cgroup_file_notify - generate a file modified event for a cgroup_file
+ * @cfile: target cgroup_file
+ *
+ * @cfile must have been obtained by setting cftype->file_offset.
+ */
+void cgroup_file_notify(struct cgroup_file *cfile)
+{
+       unsigned long flags;
+
+       spin_lock_irqsave(&cgroup_file_kn_lock, flags);
+       if (cfile->kn)
+               kernfs_notify(cfile->kn);
+       spin_unlock_irqrestore(&cgroup_file_kn_lock, flags);
+}
+
 /**
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
@@ -4613,13 +4675,9 @@ static void css_free_work_fn(struct work_struct *work)
                container_of(work, struct cgroup_subsys_state, destroy_work);
        struct cgroup_subsys *ss = css->ss;
        struct cgroup *cgrp = css->cgroup;
-       struct cgroup_file *cfile;
 
        percpu_ref_exit(&css->refcnt);
 
-       list_for_each_entry(cfile, &css->files, node)
-               kernfs_put(cfile->kn);
-
        if (ss) {
                /* css free path */
                int id = css->id;
@@ -4724,7 +4782,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
        css->ss = ss;
        INIT_LIST_HEAD(&css->sibling);
        INIT_LIST_HEAD(&css->children);
-       INIT_LIST_HEAD(&css->files);
        css->serial_nr = css_serial_nr_next++;
 
        if (cgroup_parent(cgrp)) {