Merge branch 'akpm' (more patches from Andrew)

Merge patches from Andrew Morton:
 "Most of the rest of MM, plus a few dribs and drabs.

  I still have quite a few irritating patches left around: ones with
  dubious testing results, lack of review, ones which should have gone
  via maintainer trees but the maintainers are slack, etc.

  I need to be more activist in getting these things wrapped up outside
  the merge window, but they're such a PITA."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (48 commits)
  mm/vmscan.c: avoid possible deadlock caused by too_many_isolated()
  vmscan: comment too_many_isolated()
  mm/kmemleak.c: remove obsolete simple_strtoul
  mm/memory_hotplug.c: improve comments
  mm/hugetlb: create hugetlb cgroup file in hugetlb_init
  mm/mprotect.c: coding-style cleanups
  Documentation: ABI: /sys/devices/system/node/
  slub: drop mutex before deleting sysfs entry
  memcg: add comments clarifying aspects of cache attribute propagation
  kmem: add slab-specific documentation about the kmem controller
  slub: slub-specific propagation changes
  slab: propagate tunable values
  memcg: aggregate memcg cache values in slabinfo
  memcg/sl[au]b: shrink dead caches
  memcg/sl[au]b: track all the memcg children of a kmem_cache
  memcg: destroy memcg caches
  sl[au]b: allocate objects from memcg cache
  sl[au]b: always get the cache from its page in kmem_cache_free()
  memcg: skip memcg kmem allocations in specified code regions
  memcg: infrastructure to match an allocation to the right cache
  ...

9 files changed, 285 insertions, 9 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f74856e17e4..0f615eb23d0 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -30,6 +30,7 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL         0x20000u
 #define ___GFP_THISNODE         0x40000u
 #define ___GFP_RECLAIMABLE      0x80000u
+#define ___GFP_KMEMCG           0x100000u
 #define ___GFP_NOTRACK          0x200000u
 #define ___GFP_NO_KSWAPD        0x400000u
 #define ___GFP_OTHER_NODE       0x800000u
@@ -89,6 +90,7 @@ struct vm_area_struct;
 
 #define __GFP_NO_KSWAPD ((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
+#define __GFP_KMEMCG    ((__force gfp_t)___GFP_KMEMCG) /* Allocation comes from a memcg-accounted resource */
 #define __GFP_WRITE     ((__force gfp_t)___GFP_WRITE)   /* Allocator intends to dirty page */
 
 /*
@@ -365,6 +367,9 @@ extern void free_pages(unsigned long addr, unsigned int order);
 extern void free_hot_cold_page(struct page *page, int cold);
 extern void free_hot_cold_page_list(struct list_head *list, int cold);
 
+extern void __free_memcg_kmem_pages(struct page *page, unsigned int order);
+extern void free_memcg_kmem_pages(unsigned long addr, unsigned int order);
+
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index d73878c694b..ce8217f7b5c 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -62,7 +62,7 @@ extern void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
                                          struct page *page);
 extern void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
                                            struct hugetlb_cgroup *h_cg);
-extern int hugetlb_cgroup_file_init(int idx) __init;
+extern void hugetlb_cgroup_file_init(void) __init;
 extern void hugetlb_cgroup_migrate(struct page *oldhpage,
                                    struct page *newhpage);
 
@@ -111,9 +111,8 @@ hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
         return;
 }
 
-static inline int __init hugetlb_cgroup_file_init(int idx)
+static inline void hugetlb_cgroup_file_init(void)
 {
-        return 0;
 }
 
 static inline void hugetlb_cgroup_migrate(struct page *oldhpage,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e98a74c0c9c..0108a56f814 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -21,11 +21,14 @@
 #define _LINUX_MEMCONTROL_H
 #include <linux/cgroup.h>
 #include <linux/vm_event_item.h>
+#include <linux/hardirq.h>
+#include <linux/jump_label.h>
 
 struct mem_cgroup;
 struct page_cgroup;
 struct page;
 struct mm_struct;
+struct kmem_cache;
 
 /* Stats that can be updated by kernel. */
 enum mem_cgroup_page_stat_item {
@@ -414,5 +417,211 @@ static inline void sock_release_memcg(struct sock *sk)
 {
 }
 #endif /* CONFIG_INET && CONFIG_MEMCG_KMEM */
+
+#ifdef CONFIG_MEMCG_KMEM
+extern struct static_key memcg_kmem_enabled_key;
+
+extern int memcg_limited_groups_array_size;
+
+/*
+ * Helper macro to loop through all memcg-specific caches. Callers must still
+ * check if the cache is valid (it is either valid or NULL).
+ * the slab_mutex must be held when looping through those caches
+ */
+#define for_each_memcg_cache_index(_idx)        \
+        for ((_idx) = 0; i < memcg_limited_groups_array_size; (_idx)++)
+
+static inline bool memcg_kmem_enabled(void)
+{
+        return static_key_false(&memcg_kmem_enabled_key);
+}
+
+/*
+ * In general, we'll do everything in our power to not incur in any overhead
+ * for non-memcg users for the kmem functions. Not even a function call, if we
+ * can avoid it.
+ *
+ * Therefore, we'll inline all those functions so that in the best case, we'll
+ * see that kmemcg is off for everybody and proceed quickly.  If it is on,
+ * we'll still do most of the flag checking inline. We check a lot of
+ * conditions, but because they are pretty simple, they are expected to be
+ * fast.
+ */
+bool __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg,
+                                        int order);
+void __memcg_kmem_commit_charge(struct page *page,
+                                       struct mem_cgroup *memcg, int order);
+void __memcg_kmem_uncharge_pages(struct page *page, int order);
+
+int memcg_cache_id(struct mem_cgroup *memcg);
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+                         struct kmem_cache *root_cache);
+void memcg_release_cache(struct kmem_cache *cachep);
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep);
+
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups);
+void memcg_update_array_size(int num_groups);
+
+struct kmem_cache *
+__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp);
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep);
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s);
+
+/**
+ * memcg_kmem_newpage_charge: verify if a new kmem allocation is allowed.
+ * @gfp: the gfp allocation flags.
+ * @memcg: a pointer to the memcg this was charged against.
+ * @order: allocation order.
+ *
+ * returns true if the memcg where the current task belongs can hold this
+ * allocation.
+ *
+ * We return true automatically if this allocation is not to be accounted to
+ * any memcg.
+ */
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+        if (!memcg_kmem_enabled())
+                return true;
+
+        /*
+         * __GFP_NOFAIL allocations will move on even if charging is not
+         * possible. Therefore we don't even try, and have this allocation
+         * unaccounted. We could in theory charge it with
+         * res_counter_charge_nofail, but we hope those allocations are rare,
+         * and won't be worth the trouble.
+         */
+        if (!(gfp & __GFP_KMEMCG) || (gfp & __GFP_NOFAIL))
+                return true;
+        if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+                return true;
+
+        /* If the test is dying, just let it go. */
+        if (unlikely(fatal_signal_pending(current)))
+                return true;
+
+        return __memcg_kmem_newpage_charge(gfp, memcg, order);
+}
+
+/**
+ * memcg_kmem_uncharge_pages: uncharge pages from memcg
+ * @page: pointer to struct page being freed
+ * @order: allocation order.
+ *
+ * there is no need to specify memcg here, since it is embedded in page_cgroup
+ */
+static inline void
+memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+        if (memcg_kmem_enabled())
+                __memcg_kmem_uncharge_pages(page, order);