summaryrefslogtreecommitdiff
path: root/include/linux/memcontrol.h
diff options
context:
space:
mode:
Diffstat (limited to 'include/linux/memcontrol.h')
-rw-r--r--include/linux/memcontrol.h218
1 files changed, 217 insertions, 1 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 11ddc7ffeba8..0108a56f814e 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 {
@@ -181,7 +184,14 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
gfp_t gfp_mask,
unsigned long *total_scanned);
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
+void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx);
+static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
+ enum vm_event_item idx)
+{
+ if (mem_cgroup_disabled())
+ return;
+ __mem_cgroup_count_vm_event(mm, idx);
+}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void mem_cgroup_split_huge_fixup(struct page *head);
#endif
@@ -407,5 +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);
+}
+
+/**
+ * memcg_kmem_commit_charge: embeds correct memcg in a page
+ * @page: pointer to struct page recently allocated
+ * @memcg: the memcg structure we charged against
+ * @order: allocation order.
+ *
+ * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
+ * failure of the allocation. if @page is NULL, this function will revert the
+ * charges. Otherwise, it will commit the memcg given by @memcg to the
+ * corresponding page_cgroup.
+ */
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+ if (memcg_kmem_enabled() && memcg)
+ __memcg_kmem_commit_charge(page, memcg, order);
+}
+
+/**
+ * memcg_kmem_get_cache: selects the correct per-memcg cache for allocation
+ * @cachep: the original global kmem cache
+ * @gfp: allocation flags.
+ *
+ * This function assumes that the task allocating, which determines the memcg
+ * in the page allocator, belongs to the same cgroup throughout the whole
+ * process. Misacounting can happen if the task calls memcg_kmem_get_cache()
+ * while belonging to a cgroup, and later on changes. This is considered
+ * acceptable, and should only happen upon task migration.
+ *
+ * Before the cache is created by the memcg core, there is also a possible
+ * imbalance: the task belongs to a memcg, but the cache being allocated from
+ * is the global cache, since the child cache is not yet guaranteed to be
+ * ready. This case is also fine, since in this case the GFP_KMEMCG will not be
+ * passed and the page allocator will not attempt any cgroup accounting.
+ */
+static __always_inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+ if (!memcg_kmem_enabled())
+ return cachep;
+ if (gfp & __GFP_NOFAIL)
+ return cachep;
+ if (in_interrupt() || (!current->mm) || (current->flags & PF_KTHREAD))
+ return cachep;
+ if (unlikely(fatal_signal_pending(current)))
+ return cachep;
+
+ return __memcg_kmem_get_cache(cachep, gfp);
+}
+#else
+#define for_each_memcg_cache_index(_idx) \
+ for (; NULL; )
+
+static inline bool memcg_kmem_enabled(void)
+{
+ return false;
+}
+
+static inline bool
+memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
+{
+ return true;
+}
+
+static inline void memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+}
+
+static inline void
+memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
+{
+}
+
+static inline int memcg_cache_id(struct mem_cgroup *memcg)
+{
+ return -1;
+}
+
+static inline int
+memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+ struct kmem_cache *root_cache)
+{
+ return 0;
+}
+
+static inline void memcg_release_cache(struct kmem_cache *cachep)
+{
+}
+
+static inline void memcg_cache_list_add(struct mem_cgroup *memcg,
+ struct kmem_cache *s)
+{
+}
+
+static inline struct kmem_cache *
+memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+{
+ return cachep;
+}
+
+static inline void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
#endif /* _LINUX_MEMCONTROL_H */