Merge branch 'cgroup-rmdir-updates' into cgroup/for-3.8

Pull rmdir updates into for-3.8 so that further callback updates can
be put on top.  This pull created a trivial conflict between the
following two commits.

  8c7f6edbda ("cgroup: mark subsystems with broken hierarchy support and whine if cgroups are nested for them")
  ed95779340 ("cgroup: kill cgroup_subsys->__DEPRECATED_clear_css_refs")

The former added a field to cgroup_subsys and the latter removed one
from it.  They happen to be colocated causing the conflict.  Keeping
what's added and removing what's removed resolves the conflict.

Signed-off-by: Tejun Heo <tj@kernel.org>

2 files changed, 93 insertions, 99 deletions

diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a3f358fb8a0c..0d3a1a317731 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -155,18 +155,13 @@ out:
  * Force the hugetlb cgroup to empty the hugetlb resources by moving them to
  * the parent cgroup.
  */
-static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
+static void hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
 {
         struct hstate *h;
         struct page *page;
-        int ret = 0, idx = 0;
+        int idx = 0;
 
         do {
-                if (cgroup_task_count(cgroup) ||
-                    !list_empty(&cgroup->children)) {
-                        ret = -EBUSY;
-                        goto out;
-                }
                 for_each_hstate(h) {
                         spin_lock(&hugetlb_lock);
                         list_for_each_entry(page, &h->hugepage_activelist, lru)
@@ -177,8 +172,6 @@ static int hugetlb_cgroup_pre_destroy(struct cgroup *cgroup)
                 }
                 cond_resched();
         } while (hugetlb_cgroup_have_usage(cgroup));
-out:
-        return ret;
 }
 
 int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7acf43bf04a2..08adaaae6fcc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2337,7 +2337,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 again:
         if (*ptr) { /* css should be a valid one */
                 memcg = *ptr;
-                VM_BUG_ON(css_is_removed(&memcg->css));
                 if (mem_cgroup_is_root(memcg))
                         goto done;
                 if (nr_pages == 1 && consume_stock(memcg))
@@ -2477,9 +2476,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller must check css_is_removed() or some if
- * it's concern. (dropping refcnt from swap can be called against removed
- * memcg.)
+ * rcu_read_lock().  The caller is responsible for calling css_tryget if
+ * the mem_cgroup is used for charging. (dropping refcnt from swap can be
+ * called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
@@ -2676,13 +2675,6 @@ static int mem_cgroup_move_account(struct page *page,
         /* caller should have done css_get */
         pc->mem_cgroup = to;
         mem_cgroup_charge_statistics(to, anon, nr_pages);
-        /*
-         * We charges against "to" which may not have any tasks. Then, "to"
-         * can be under rmdir(). But in current implementation, caller of
-         * this function is just force_empty() and move charge, so it's
-         * guaranteed that "to" is never removed. So, we don't check rmdir
-         * status here.
-         */
         move_unlock_mem_cgroup(from, &flags);
         ret = 0;
 unlock:
@@ -2696,10 +2688,27 @@ out:
         return ret;
 }
 
-/*
- * move charges to its parent.
+/**
+ * mem_cgroup_move_parent - moves page to the parent group
+ * @page: the page to move
+ * @pc: page_cgroup of the page
+ * @child: page's cgroup
+ *
+ * move charges to its parent or the root cgroup if the group has no
+ * parent (aka use_hierarchy==0).
+ * Although this might fail (get_page_unless_zero, isolate_lru_page or
+ * mem_cgroup_move_account fails) the failure is always temporary and
+ * it signals a race with a page removal/uncharge or migration. In the
+ * first case the page is on the way out and it will vanish from the LRU
+ * on the next attempt and the call should be retried later.
+ * Isolation from the LRU fails only if page has been isolated from
+ * the LRU since we looked at it and that usually means either global
+ * reclaim or migration going on. The page will either get back to the
+ * LRU or vanish.
+ * Finaly mem_cgroup_move_account fails only if the page got uncharged
+ * (!PageCgroupUsed) or moved to a different group. The page will
+ * disappear in the next attempt.
  */
-
 static int mem_cgroup_move_parent(struct page *page,
                                   struct page_cgroup *pc,
                                   struct mem_cgroup *child)
@@ -2709,9 +2718,7 @@ static int mem_cgroup_move_parent(struct page *page,
         unsigned long uninitialized_var(flags);
         int ret;
 
-        /* Is ROOT ? */
-        if (mem_cgroup_is_root(child))
-                return -EINVAL;
+        VM_BUG_ON(mem_cgroup_is_root(child));
 
         ret = -EBUSY;
         if (!get_page_unless_zero(page))
@@ -2728,8 +2735,10 @@ static int mem_cgroup_move_parent(struct page *page,
         if (!parent)
                 parent = root_mem_cgroup;
 
-        if (nr_pages > 1)
+        if (nr_pages > 1) {
+                VM_BUG_ON(!PageTransHuge(page));
                 flags = compound_lock_irqsave(page);
+        }
 
         ret = mem_cgroup_move_account(page, nr_pages,
                                 pc, child, parent);
@@ -2871,7 +2880,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
                 return;
         if (!memcg)
                 return;
-        cgroup_exclude_rmdir(&memcg->css);
 
         __mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
         /*
@@ -2885,12 +2893,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
                 swp_entry_t ent = {.val = page_private(page)};
                 mem_cgroup_uncharge_swap(ent);
         }
-        /*
-         * At swapin, we may charge account against cgroup which has no tasks.
-         * So, rmdir()->pre_destroy() can be called while we do this charge.
-         * In that case, we need to call pre_destroy() again. check it here.
-         */
-        cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page,
@@ -3338,8 +3340,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 
         if (!memcg)
                 return;
-        /* blocks rmdir() */
-        cgroup_exclude_rmdir(&memcg->css);
+
         if (!migration_ok) {
                 used = oldpage;
                 unused = newpage;
@@ -3373,13 +3374,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
          */
         if (anon)
                 mem_cgroup_uncharge_page(used);
-        /*
-         * At migration, we may charge account against cgroup which has no
-         * tasks.
-         * So, rmdir()->pre_destroy() can be called while we do this charge.
-         * In that case, we need to call pre_destroy() again. check it here.
-         */
-        cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 /*
@@ -3679,17 +3673,22 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
         return nr_reclaimed;
 }
 
-/*
+/**
+ * mem_cgroup_force_empty_list - clears LRU of a group
+ * @memcg: group to clear
+ * @node: NUMA node
+ * @zid: zone id
+ * @lru: lru to to clear
+ *
  * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - it just removes the page_cgroups.
- * Returns true if some page_cgroups were not freed, indicating that the caller
- * must retry this operation.
+ * reclaim the pages page themselves - pages are moved to the parent (or root)
+ * group.
  */
-static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
                                 int node, int zid, enum lru_list lru)
 {
         struct mem_cgroup_per_zone *mz;
-        unsigned long flags, loop;
+        unsigned long flags;
         struct list_head *list;
         struct page *busy;
         struct zone *zone;
@@ -3698,11 +3697,8 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
         mz = mem_cgroup_zoneinfo(memcg, node, zid);
         list = &mz->lruvec.lists[lru];
 
-        loop = mz->lru_size[lru];
-        /* give some margin against EBUSY etc...*/
-        loop += 256;
         busy = NULL;
-        while (loop--) {
+        do {
                 struct page_cgroup *pc;
                 struct page *page;
 
@@ -3728,76 +3724,72 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
                         cond_resched();
                 } else
                         busy = NULL;
-        }
-        return !list_empty(list);
+        } while (!list_empty(list));
 }
 
 /*
- * make mem_cgroup's charge to be 0 if there is no task.
+ * make mem_cgroup's charge to be 0 if there is no task by moving
+ * all the charges and pages to the parent.
  * This enables deleting this mem_cgroup.
+ *
+ * Caller is responsible for holding css reference on the memcg.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
+static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
-        int ret;
-        int node, zid, shrink;
-        int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-        struct cgroup *cgrp = memcg->css.cgroup;
-
-        css_get(&memcg->css);
+        int node, zid;
 
-        shrink = 0;
-        /* should free all ? */
-        if (free_all)
-                goto try_to_free;
-move_account:
         do {
-                ret = -EBUSY;
-                if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
-                        goto out;
                 /* This is for making all *used* pages to be on LRU. */
                 lru_add_drain_all();
                 drain_all_stock_sync(memcg);
-                ret = 0;
                 mem_cgroup_start_move(memcg);
                 for_each_node_state(node, N_HIGH_MEMORY) {
-                        for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
+                        for (zid = 0; zid < MAX_NR_ZONES; zid++) {
                                 enum lru_list lru;
                                 for_each_lru(lru) {
-                                        ret = mem_cgroup_force_empty_list(memcg,
+                                        mem_cgroup_force_empty_list(memcg,
                                                         node, zid, lru);
-                                        if (ret)
-                                                break;
                                 }
                         }
-                        if (ret)
-                                break;
                 }
                 mem_cgroup_end_move(memcg);
                 memcg_oom_recover(memcg);
                 cond_resched();
-        /* "ret" should also be checked to ensure all lists are empty. */
-        } while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
-out:
-        css_put(&memcg->css);
-        return ret;
 
-try_to_free:
+                /*
+                 * This is a safety check because mem_cgroup_force_empty_list
+                 * could have raced with mem_cgroup_replace_page_cache callers
+                 * so the lru seemed empty but the page could have been added
+                 * right after the check. RES_USAGE should be safe as we always
+                 * charge before adding to the LRU.
+                 */
+        } while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0);
+}
+
+/*
+ * Reclaims as many pages from the given memcg as possible and moves
+ * the rest to the parent.
+ *
+ * Caller is responsible for holding css reference for memcg.
+ */
+static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
+{
+        int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+        struct cgroup *cgrp = memcg->css.cgroup;
+
         /* returns EBUSY if there is a task or if we come here twice. */
-        if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
-                ret = -EBUSY;
-                goto out;
-        }
+        if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+                return -EBUSY;
+
         /* we call try-to-free pages for make this cgroup empty */
         lru_add_drain_all();
         /* try to free all pages in this cgroup */
-        shrink = 1;
         while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
                 int progress;
 
-                if (signal_pending(current)) {
-                        ret = -EINTR;
-                        goto out;
-                }
+                if (signal_pending(current))
+                        return -EINTR;
+
                 progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
                                                 false);
                 if (!progress) {
@@ -3808,13 +3800,23 @@ try_to_free:
 
         }
         lru_add_drain();
-        /* try move_account...there may be some *locked* pages. */
-        goto move_account;
+        mem_cgroup_reparent_charges(memcg);
+
+        return 0;
 }
 
 static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
 {
-        return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+        struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+        int ret;
+
+        if (mem_cgroup_is_root(memcg))
+                return -EINVAL;
+        css_get(&memcg->css);
+        ret = mem_cgroup_force_empty(memcg);
+        css_put(&memcg->css);
+
+        return ret;
 }
 
 
@@ -5001,11 +5003,11 @@ free_out:
         return ERR_PTR(error);
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_pre_destroy(struct cgroup *cont)
 {
         struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-        return mem_cgroup_force_empty(memcg, false);
+        mem_cgroup_reparent_charges(memcg);
 }
 
 static void mem_cgroup_destroy(struct cgroup *cont)
@@ -5607,7 +5609,6 @@ struct cgroup_subsys mem_cgroup_subsys = {
         .base_cftypes = mem_cgroup_files,
         .early_init = 0,
         .use_id = 1,
-        .__DEPRECATED_clear_css_refs = true,
 };
 
 #ifdef CONFIG_MEMCG_SWAP