1 files changed, 270 insertions, 15 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cdbb7a84cb6e..597d58101872 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -87,6 +87,10 @@ int do_swap_account __read_mostly;
 #define do_swap_account		0
 #endif
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+static DECLARE_WAIT_QUEUE_HEAD(memcg_cgwb_frn_waitq);
+#endif
+
 /* Whether legacy memory+swap accounting is active */
 static bool do_memsw_account(void)
 {
@@ -752,15 +756,13 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update memcg */
 	__mod_memcg_state(memcg, idx, val);
 
+	/* Update lruvec */
+	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup_per_node *pi;
 
-		/*
-		 * Batch local counters to keep them in sync with
-		 * the hierarchical ones.
-		 */
-		__this_cpu_add(pn->lruvec_stat_local->count[idx], x);
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
 			atomic_long_add(x, &pi->lruvec_stat[idx]);
 		x = 0;
@@ -768,6 +770,26 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	__this_cpu_write(pn->lruvec_stat_cpu->count[idx], x);
 }
 
+void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val)
+{
+	struct page *page = virt_to_head_page(p);
+	pg_data_t *pgdat = page_pgdat(page);
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = memcg_from_slab_page(page);
+
+	/* Untracked pages have no memcg, no lruvec. Update only the node */
+	if (!memcg || memcg == root_mem_cgroup) {
+		__mod_node_page_state(pgdat, idx, val);
+	} else {
+		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		__mod_lruvec_state(lruvec, idx, val);
+	}
+	rcu_read_unlock();
+}
+
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
@@ -1130,26 +1152,45 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 		css_put(&prev->css);
 }
 
-static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+static void __invalidate_reclaim_iterators(struct mem_cgroup *from,
+					struct mem_cgroup *dead_memcg)
 {
-	struct mem_cgroup *memcg = dead_memcg;
 	struct mem_cgroup_reclaim_iter *iter;
 	struct mem_cgroup_per_node *mz;
 	int nid;
 	int i;
 
-	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		for_each_node(nid) {
-			mz = mem_cgroup_nodeinfo(memcg, nid);
-			for (i = 0; i <= DEF_PRIORITY; i++) {
-				iter = &mz->iter[i];
-				cmpxchg(&iter->position,
-					dead_memcg, NULL);
-			}
+	for_each_node(nid) {
+		mz = mem_cgroup_nodeinfo(from, nid);
+		for (i = 0; i <= DEF_PRIORITY; i++) {
+			iter = &mz->iter[i];
+			cmpxchg(&iter->position,
+				dead_memcg, NULL);
 		}
 	}
 }
 
+static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
+{
+	struct mem_cgroup *memcg = dead_memcg;
+	struct mem_cgroup *last;
+
+	do {
+		__invalidate_reclaim_iterators(memcg, dead_memcg);
+		last = memcg;
+	} while ((memcg = parent_mem_cgroup(memcg)));
+
+	/*
+	 * When cgruop1 non-hierarchy mode is used,
+	 * parent_mem_cgroup() does not walk all the way up to the
+	 * cgroup root (root_mem_cgroup). So we have to handle
+	 * dead_memcg from cgroup root separately.
+	 */
+	if (last != root_mem_cgroup)
+		__invalidate_reclaim_iterators(root_mem_cgroup,
+						dead_memcg);
+}
+
 /**
  * mem_cgroup_scan_tasks - iterate over tasks of a memory cgroup hierarchy
  * @memcg: hierarchy root
@@ -3221,6 +3262,72 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	}
 }
 
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
+{
+	unsigned long stat[MEMCG_NR_STAT];
+	struct mem_cgroup *mi;
+	int node, cpu, i;
+	int min_idx, max_idx;
+
+	if (slab_only) {
+		min_idx = NR_SLAB_RECLAIMABLE;
+		max_idx = NR_SLAB_UNRECLAIMABLE;
+	} else {
+		min_idx = 0;
+		max_idx = MEMCG_NR_STAT;
+	}
+
+	for (i = min_idx; i < max_idx; i++)
+		stat[i] = 0;
+
+	for_each_online_cpu(cpu)
+		for (i = min_idx; i < max_idx; i++)
+			stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
+
+	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+		for (i = min_idx; i < max_idx; i++)
+			atomic_long_add(stat[i], &mi->vmstats[i]);
+
+	if (!slab_only)
+		max_idx = NR_VM_NODE_STAT_ITEMS;
+
+	for_each_node(node) {
+		struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
+		struct mem_cgroup_per_node *pi;
+
+		for (i = min_idx; i < max_idx; i++)
+			stat[i] = 0;
+
+		for_each_online_cpu(cpu)
+			for (i = min_idx; i < max_idx; i++)
+				stat[i] += per_cpu(
+					pn->lruvec_stat_cpu->count[i], cpu);
+
+		for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
+			for (i = min_idx; i < max_idx; i++)
+				atomic_long_add(stat[i], &pi->lruvec_stat[i]);
+	}
+}
+
+static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
+{
+	unsigned long events[NR_VM_EVENT_ITEMS];
+	struct mem_cgroup *mi;
+	int cpu, i;
+
+	for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+		events[i] = 0;
+
+	for_each_online_cpu(cpu)
+		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+			events[i] += per_cpu(memcg->vmstats_percpu->events[i],
+					     cpu);
+
+	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+			atomic_long_add(events[i], &mi->vmevents[i]);
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
@@ -3270,7 +3377,14 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	if (!parent)
 		parent = root_mem_cgroup;
 
+	/*
+	 * Deactivate and reparent kmem_caches. Then flush percpu
+	 * slab statistics to have precise values at the parent and
+	 * all ancestor levels. It's required to keep slab stats
+	 * accurate after the reparenting of kmem_caches.
+	 */
 	memcg_deactivate_kmem_caches(memcg, parent);
+	memcg_flush_percpu_vmstats(memcg, true);
 
 	kmemcg_id = memcg->kmemcg_id;
 	BUG_ON(kmemcg_id < 0);
@@ -4062,6 +4176,8 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
+#include <trace/events/writeback.h>
+
 static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
 {
 	return wb_domain_init(&memcg->cgwb_domain, gfp);
@@ -4145,6 +4261,130 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	}
 }
 
+/*
+ * Foreign dirty flushing
+ *
+ * There's an inherent mismatch between memcg and writeback.  The former
+ * trackes ownership per-page while the latter per-inode.  This was a
+ * deliberate design decision because honoring per-page ownership in the
+ * writeback path is complicated, may lead to higher CPU and IO overheads
+ * and deemed unnecessary given that write-sharing an inode across
+ * different cgroups isn't a common use-case.
+ *
+ * Combined with inode majority-writer ownership switching, this works well
+ * enough in most cases but there are some pathological cases.  For
+ * example, let's say there are two cgroups A and B which keep writing to
+ * different but confined parts of the same inode.  B owns the inode and
+ * A's memory is limited far below B's.  A's dirty ratio can rise enough to
+ * trigger balance_dirty_pages() sleeps but B's can be low enough to avoid
+ * triggering background writeback.  A will be slowed down without a way to
+ * make writeback of the dirty pages happen.
+ *
+ * Conditions like the above can lead to a cgroup getting repatedly and
+ * severely throttled after making some progress after each
+ * dirty_expire_interval while the underyling IO device is almost
+ * completely idle.
+ *
+ * Solving this problem completely requires matching the ownership tracking
+ * granularities between memcg and writeback in either direction.  However,
+ * the more egregious behaviors can be avoided by simply remembering the
+ * most recent foreign dirtying events and initiating remote flushes on
+ * them when local writeback isn't enough to keep the memory clean enough.
+ *
+ * The following two functions implement such mechanism.  When a foreign
+ * page - a page whose memcg and writeback ownerships don't match - is
+ * dirtied, mem_cgroup_track_foreign_dirty() records the inode owning
+ * bdi_writeback on the page owning memcg.  When balance_dirty_pages()
+ * decides that the memcg needs to sleep due to high dirty ratio, it calls
+ * mem_cgroup_flush_foreign() which queues writeback on the recorded
+ * foreign bdi_writebacks which haven't expired.  Both the numbers of
+ * recorded bdi_writebacks and concurrent in-flight foreign writebacks are
+ * limited to MEMCG_CGWB_FRN_CNT.
+ *
+ * The mechanism only remembers IDs and doesn't hold any object references.
+ * As being wrong occasionally doesn't matter, updates and accesses to the
+ * records are lockless and racy.
+ */
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+					     struct bdi_writeback *wb)
+{
+	struct mem_cgroup *memcg = page->mem_cgroup;
+	struct memcg_cgwb_frn *frn;
+	u64 now = get_jiffies_64();
+	u64 oldest_at = now;
+	int oldest = -1;
+	int i;
+
+	trace_track_foreign_dirty(page, wb);
+
+	/*
+	 * Pick the slot to use.  If there is already a slot for @wb, keep
+	 * using it.  If not replace the oldest one which isn't being
+	 * written out.
+	 */
+	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+		frn = &memcg->cgwb_frn[i];
+		if (frn->bdi_id == wb->bdi->id &&
+		    frn->memcg_id == wb->memcg_css->id)
+			break;
+		if (time_before64(frn->at, oldest_at) &&
+		    atomic_read(&frn->done.cnt) == 1) {
+			oldest = i;
+			oldest_at = frn->at;
+		}
+	}
+
+	if (i < MEMCG_CGWB_FRN_CNT) {
+		/*
+		 * Re-using an existing one.  Update timestamp lazily to
+		 * avoid making the cacheline hot.  We want them to be
+		 * reasonably up-to-date and significantly shorter than
+		 * dirty_expire_interval as that's what expires the record.
+		 * Use the shorter of 1s and dirty_expire_interval / 8.
+		 */
+		unsigned long update_intv =
+			min_t(unsigned long, HZ,
+			      msecs_to_jiffies(dirty_expire_interval * 10) / 8);
+
+		if (time_before64(frn->at, now - update_intv))
+			frn->at = now;
+	} else if (oldest >= 0) {
+		/* replace the oldest free one */
+		frn = &memcg->cgwb_frn[oldest];
+		frn->bdi_id = wb->bdi->id;
+		frn->memcg_id = wb->memcg_css->id;
+		frn->at = now;
+	}
+}
+
+/* issue foreign writeback flushes for recorded foreign dirtying events */
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
+	unsigned long intv = msecs_to_jiffies(dirty_expire_interval * 10);
+	u64 now = jiffies_64;
+	int i;
+
+	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++) {
+		struct memcg_cgwb_frn *frn = &memcg->cgwb_frn[i];
+
+		/*
+		 * If the record is older than dirty_expire_interval,
+		 * writeback on it has already started.  No need to kick it
+		 * off again.  Also, don't start a new one if there's
+		 * already one in flight.
+		 */
+		if (time_after64(frn->at, now - intv) &&
+		    atomic_read(&frn->done.cnt) == 1) {
+			frn->at = 0;
+			trace_flush_foreign(wb, frn->bdi_id, frn->memcg_id);
+			cgroup_writeback_by_id(frn->bdi_id, frn->memcg_id, 0,
+					       WB_REASON_FOREIGN_FLUSH,
+					       &frn->done);
+		}
+	}
+}
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
@@ -4643,6 +4883,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
+	/*
+	 * Flush percpu vmstats and vmevents to guarantee the value correctness
+	 * on parent's and all ancestor levels.
+	 */
+	memcg_flush_percpu_vmstats(memcg, false);
+	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
@@ -4661,6 +4907,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	struct mem_cgroup *memcg;
 	unsigned int size;
 	int node;
+	int __maybe_unused i;
 
 	size = sizeof(struct mem_cgroup);
 	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
@@ -4704,6 +4951,9 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 #endif
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
+	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+		memcg->cgwb_frn[i].done =
+			__WB_COMPLETION_INIT(&memcg_cgwb_frn_waitq);
 #endif
 	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
@@ -4833,7 +5083,12 @@ static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	int __maybe_unused i;
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+	for (i = 0; i < MEMCG_CGWB_FRN_CNT; i++)
+		wb_wait_for_completion(&memcg->cgwb_frn[i].done);
+#endif
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
 		static_branch_dec(&memcg_sockets_enabled_key);