[PATCH v7 05/19] mm: memcontrol: decouple reference counting from page accounting

[Roman Gushchin <guro@fb.com>]

From: Johannes Weiner <hannes@cmpxchg.org>

The reference counting of a memcg is currently coupled directly to how
many 4k pages are charged to it.  This doesn't work well with Roman's new
slab controller, which maintains pools of objects and doesn't want to keep
an extra balance sheet for the pages backing those objects.

This unusual refcounting design (reference counts usually track pointers
to an object) is only for historical reasons: memcg used to not take any
css references and simply stalled offlining until all charges had been
reparented and the page counters had dropped to zero.  When we got rid of
the reparenting requirement, the simple mechanical translation was to take
a reference for every charge.

More historical context can be found in commit e8ea14cc6ead ("mm:
memcontrol: take a css reference for each charged page"), commit
64f219938941 ("mm: memcontrol: remove obsolete kmemcg pinning tricks") and
commit b2052564e66d ("mm: memcontrol: continue cache reclaim from offlined
groups").

The new slab controller exposes the limitations in this scheme, so let's
switch it to a more idiomatic reference counting model based on actual
kernel pointers to the memcg:

- The per-cpu stock holds a reference to the memcg its caching

- User pages hold a reference for their page->mem_cgroup. Transparent
  huge pages will no longer acquire tail references in advance, we'll
  get them if needed during the split.

- Kernel pages hold a reference for their page->mem_cgroup

- Pages allocated in the root cgroup will acquire and release css
  references for simplicity. css_get() and css_put() optimize that.

- The current memcg_charge_slab() already hacked around the per-charge
  references; this change gets rid of that as well.

Roman:
1) Rebased on top of the current mm tree: added css_get() in
   mem_cgroup_charge(), dropped mem_cgroup_try_charge() part
2) I've reformatted commit references in the commit log to make
   checkpatch.pl happy.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
---
 mm/memcontrol.c | 37 +++++++++++++++++++++----------------
 mm/slab.h       |  2 --
 2 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a6216f7369b2..3e5597f8dec5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2094,13 +2094,17 @@ static void drain_stock(struct memcg_stock_pcp *stock)
 {
 	struct mem_cgroup *old = stock->cached;
 
+	if (!old)
+		return;
+
 	if (stock->nr_pages) {
 		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_memsw_account())
 			page_counter_uncharge(&old->memsw, stock->nr_pages);
-		css_put_many(&old->css, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
+
+	css_put(&old->css);
 	stock->cached = NULL;
 }
 
@@ -2136,6 +2140,7 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 	stock = this_cpu_ptr(&memcg_stock);
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
+		css_get(&memcg->css);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
@@ -2594,12 +2599,10 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_charge(&memcg->memsw, nr_pages);
-	css_get_many(&memcg->css, nr_pages);
 
 	return 0;
 
 done_restock:
-	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
 
@@ -2657,8 +2660,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_uncharge(&memcg->memsw, nr_pages);
-
-	css_put_many(&memcg->css, nr_pages);
 }
 #endif
 
@@ -2966,6 +2967,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
 		if (!ret) {
 			page->mem_cgroup = memcg;
 			__SetPageKmemcg(page);
+			return 0;
 		}
 	}
 	css_put(&memcg->css);
@@ -2988,12 +2990,11 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 	__memcg_kmem_uncharge(memcg, nr_pages);
 	page->mem_cgroup = NULL;
+	css_put(&memcg->css);
 
 	/* slab pages do not have PageKmemcg flag set */
 	if (PageKmemcg(page))
 		__ClearPageKmemcg(page);
-
-	css_put_many(&memcg->css, nr_pages);
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
@@ -3005,13 +3006,16 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
+	struct mem_cgroup *memcg = head->mem_cgroup;
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	for (i = 1; i < HPAGE_PMD_NR; i++)
-		head[i].mem_cgroup = head->mem_cgroup;
+	for (i = 1; i < HPAGE_PMD_NR; i++) {
+		css_get(&memcg->css);
+		head[i].mem_cgroup = memcg;
+	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -5456,7 +5460,10 @@ static int mem_cgroup_move_account(struct page *page,
 	 */
 	smp_mb();
 
-	page->mem_cgroup = to; 	/* caller should have done css_get */
+	css_get(&to->css);
+	css_put(&from->css);
+
+	page->mem_cgroup = to;
 
 	__unlock_page_memcg(from);
 
@@ -6506,6 +6513,7 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 	if (ret)
 		goto out_put;
 
+	css_get(&memcg->css);
 	commit_charge(page, memcg);
 
 	local_irq_disable();
@@ -6560,9 +6568,6 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 	__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_pages);
 	memcg_check_events(ug->memcg, ug->dummy_page);
 	local_irq_restore(flags);
-
-	if (!mem_cgroup_is_root(ug->memcg))
-		css_put_many(&ug->memcg->css, ug->nr_pages);
 }
 
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
@@ -6600,6 +6605,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 
 	ug->dummy_page = page;
 	page->mem_cgroup = NULL;
+	css_put(&ug->memcg->css);
 }
 
 static void uncharge_list(struct list_head *page_list)
@@ -6705,8 +6711,8 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 	page_counter_charge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_charge(&memcg->memsw, nr_pages);
-	css_get_many(&memcg->css, nr_pages);
 
+	css_get(&memcg->css);
 	commit_charge(newpage, memcg);
 
 	local_irq_save(flags);
@@ -6943,8 +6949,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	mem_cgroup_charge_statistics(memcg, page, -nr_entries);
 	memcg_check_events(memcg, page);
 
-	if (!mem_cgroup_is_root(memcg))
-		css_put_many(&memcg->css, nr_entries);
+	css_put(&memcg->css);
 }
 
 /**
diff --git a/mm/slab.h b/mm/slab.h
index cc6afddd5632..1e2d80991904 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -401,9 +401,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 	lruvec = mem_cgroup_lruvec(memcg, page_pgdat(page));
 	mod_lruvec_state(lruvec, cache_vmstat_idx(s), nr_pages << PAGE_SHIFT);
 
-	/* transer try_charge() page references to kmem_cache */
 	percpu_ref_get_many(&s->memcg_params.refcnt, nr_pages);
-	css_put_many(&memcg->css, nr_pages);
 out:
 	css_put(&memcg->css);
 	return ret;
-- 
2.26.2