mm: memcontrol: rewrite uncharge API

The memcg uncharging code that is involved towards the end of a page's
lifetime - truncation, reclaim, swapout, migration - is impressively
complicated and fragile.

Because anonymous and file pages were always charged before they had their
page->mapping established, uncharges had to happen when the page type
could still be known from the context; as in unmap for anonymous, page
cache removal for file and shmem pages, and swap cache truncation for swap
pages.  However, these operations happen well before the page is actually
freed, and so a lot of synchronization is necessary:

- Charging, uncharging, page migration, and charge migration all need
  to take a per-page bit spinlock as they could race with uncharging.

- Swap cache truncation happens during both swap-in and swap-out, and
  possibly repeatedly before the page is actually freed.  This means
  that the memcg swapout code is called from many contexts that make
  no sense and it has to figure out the direction from page state to
  make sure memory and memory+swap are always correctly charged.

- On page migration, the old page might be unmapped but then reused,
  so memcg code has to prevent untimely uncharging in that case.
  Because this code - which should be a simple charge transfer - is so
  special-cased, it is not reusable for replace_page_cache().

But now that charged pages always have a page->mapping, introduce
mem_cgroup_uncharge(), which is called after the final put_page(), when we
know for sure that nobody is looking at the page anymore.

For page migration, introduce mem_cgroup_migrate(), which is called after
the migration is successful and the new page is fully rmapped.  Because
the old page is no longer uncharged after migration, prevent double
charges by decoupling the page's memcg association (PCG_USED and
pc->mem_cgroup) from the page holding an actual charge.  The new bits
PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
to the new page during migration.

mem_cgroup_migrate() is suitable for replace_page_cache() as well,
which gets rid of mem_cgroup_replace_page_cache().  However, care
needs to be taken because both the source and the target page can
already be charged and on the LRU when fuse is splicing: grab the page
lock on the charge moving side to prevent changing pc->mem_cgroup of a
page under migration.  Also, the lruvecs of both pages change as we
uncharge the old and charge the new during migration, and putback may
race with us, so grab the lru lock and isolate the pages iff on LRU to
prevent races and ensure the pages are on the right lruvec afterward.

Swap accounting is massively simplified: because the page is no longer
uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
before the final put_page() in page reclaim.

Finally, page_cgroup changes are now protected by whatever protection the
page itself offers: anonymous pages are charged under the page table lock,
whereas page cache insertions, swapin, and migration hold the page lock.
Uncharging happens under full exclusion with no outstanding references.
Charging and uncharging also ensure that the page is off-LRU, which
serializes against charge migration.  Remove the very costly page_cgroup
lock and set pc->flags non-atomically.

[mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
[vdavydov@parallels.com: fix flags definition]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Tested-by: Jet Chen <jet.chen@intel.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Felipe Balbi <balbi@ti.com>
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 28 insertions, 76 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1a9a096858e0..806b8fa15c5f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -60,15 +60,17 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
                               bool lrucare);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+void mem_cgroup_uncharge(struct page *page);
+
+/* Batched uncharging */
+void mem_cgroup_uncharge_start(void);
+void mem_cgroup_uncharge_end(void);
 
-/* For coalescing uncharge for reducing memcg' overhead*/
-extern void mem_cgroup_uncharge_start(void);
-extern void mem_cgroup_uncharge_end(void);
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
+                        bool lrucare);
 
-extern void mem_cgroup_uncharge_page(struct page *page);
-extern void mem_cgroup_uncharge_cache_page(struct page *page);
+struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
+struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
 bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
                                   struct mem_cgroup *memcg);
@@ -96,12 +98,6 @@ bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 
-extern void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-                             struct mem_cgroup **memcgp);
-extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-        struct page *oldpage, struct page *newpage, bool migration_ok);
-
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
                                    struct mem_cgroup *,
                                    struct mem_cgroup_reclaim_cookie *);
@@ -116,8 +112,6 @@ unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list);
 void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int);
 extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
                                         struct task_struct *p);
-extern void mem_cgroup_replace_page_cache(struct page *oldpage,
-                                        struct page *newpage);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -235,19 +229,21 @@ static inline void mem_cgroup_cancel_charge(struct page *page,
 {
 }
 
-static inline void mem_cgroup_uncharge_start(void)
+static inline void mem_cgroup_uncharge(struct page *page)
 {
 }
 
-static inline void mem_cgroup_uncharge_end(void)
+static inline void mem_cgroup_uncharge_start(void)
 {
 }
 
-static inline void mem_cgroup_uncharge_page(struct page *page)
+static inline void mem_cgroup_uncharge_end(void)
 {
 }
 
-static inline void mem_cgroup_uncharge_cache_page(struct page *page)
+static inline void mem_cgroup_migrate(struct page *oldpage,
+                                      struct page *newpage,
+                                      bool lrucare)
 {
 }
 
@@ -286,17 +282,6 @@ static inline struct cgroup_subsys_state
         return NULL;
 }
 
-static inline void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-                             struct mem_cgroup **memcgp)
-{
-}
-
-static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-                struct page *oldpage, struct page *newpage, bool migration_ok)
-{
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
                 struct mem_cgroup *prev,
@@ -392,10 +377,6 @@ static inline
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
-static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
-                                struct page *newpage)
-{
-}
 #endif /* CONFIG_MEMCG */
 
 #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 777a524716db..9bfb8e68a595 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -3,9 +3,9 @@
 
 enum {
         /* flags for mem_cgroup */
-        PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-        PCG_USED, /* this object is in use. */
-        PCG_MIGRATION, /* under page migration */
+        PCG_USED = 0x01,        /* This page is charged to a memcg */
+        PCG_MEM = 0x02,         /* This page holds a memory charge */
+        PCG_MEMSW = 0x04,       /* This page holds a memory+swap charge */
         __NR_PCG_FLAGS,
 };
 
@@ -44,42 +44,9 @@ static inline void __init page_cgroup_init(void)
 struct page_cgroup *lookup_page_cgroup(struct page *page);
 struct page *lookup_cgroup_page(struct page_cgroup *pc);
 
-#define TESTPCGFLAG(uname, lname)                       \
-static inline int PageCgroup##uname(struct page_cgroup *pc)     \
-        { return test_bit(PCG_##lname, &pc->flags); }
-
-#define SETPCGFLAG(uname, lname)                        \
-static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
-        { set_bit(PCG_##lname, &pc->flags);  }
-
-#define CLEARPCGFLAG(uname, lname)                      \
-static inline void ClearPageCgroup##uname(struct page_cgroup *pc)       \
-        { clear_bit(PCG_##lname, &pc->flags);  }
-
-#define TESTCLEARPCGFLAG(uname, lname)                  \
-static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)    \
-        { return test_and_clear_bit(PCG_##lname, &pc->flags);  }
-
-TESTPCGFLAG(Used, USED)
-CLEARPCGFLAG(Used, USED)
-SETPCGFLAG(Used, USED)
-
-SETPCGFLAG(Migration, MIGRATION)
-CLEARPCGFLAG(Migration, MIGRATION)
-TESTPCGFLAG(Migration, MIGRATION)
-
-static inline void lock_page_cgroup(struct page_cgroup *pc)
-{
-        /*
-         * Don't take this lock in IRQ context.
-         * This lock is for pc->mem_cgroup, USED, MIGRATION
-         */
-        bit_spin_lock(PCG_LOCK, &pc->flags);
-}
-
-static inline void unlock_page_cgroup(struct page_cgroup *pc)
+static inline int PageCgroupUsed(struct page_cgroup *pc)
 {
-        bit_spin_unlock(PCG_LOCK, &pc->flags);
+        return !!(pc->flags & PCG_USED);
 }
 
 #else /* CONFIG_MEMCG */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 46a649e4e8cd..1b72060f093a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -381,9 +381,13 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 #ifdef CONFIG_MEMCG_SWAP
-extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
+extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
+extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
 #else
-static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
+static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+}
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
 {
 }
 #endif
@@ -443,7 +447,7 @@ extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
-extern void swapcache_free(swp_entry_t, struct page *page);
+extern void swapcache_free(swp_entry_t);
 extern int free_swap_and_cache(swp_entry_t);
 extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
@@ -507,7 +511,7 @@ static inline void swap_free(swp_entry_t swp)
 {
 }
 
-static inline void swapcache_free(swp_entry_t swp, struct page *page)
+static inline void swapcache_free(swp_entry_t swp)
 {
 }