Merge branch 'next' into for-linus

Prepare input updates for 5.3 merge window.

1 files changed, 130 insertions, 93 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6e1469b80cb7..81a0d3914ec9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,6 +39,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
+#include <linux/vm_event_item.h>
 #include <linux/smp.h>
 #include <linux/page-flags.h>
 #include <linux/backing-dev.h>
@@ -248,6 +249,12 @@ enum res_type {
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
+static inline bool should_force_charge(void)
+{
+	return tsk_is_oom_victim(current) || fatal_signal_pending(current) ||
+		(current->flags & PF_EXITING);
+}
+
 /* Some nice accessors for the vmpressure. */
 struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 {
@@ -1293,32 +1300,39 @@ static const char *const memcg1_stat_names[] = {
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /**
- * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
+ * mem_cgroup_print_oom_context: Print OOM information relevant to
+ * memory controller.
  * @memcg: The memory cgroup that went over limit
  * @p: Task that is going to be killed
  *
  * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
  * enabled
  */
-void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct mem_cgroup *iter;
-	unsigned int i;
-
 	rcu_read_lock();
 
+	if (memcg) {
+		pr_cont(",oom_memcg=");
+		pr_cont_cgroup_path(memcg->css.cgroup);
+	} else
+		pr_cont(",global_oom");
 	if (p) {
-		pr_info("Task in ");
+		pr_cont(",task_memcg=");
 		pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id));
-		pr_cont(" killed as a result of limit of ");
-	} else {
-		pr_info("Memory limit reached of cgroup ");
 	}
-
-	pr_cont_cgroup_path(memcg->css.cgroup);
-	pr_cont("\n");
-
 	rcu_read_unlock();
+}
+
+/**
+ * mem_cgroup_print_oom_meminfo: Print OOM memory information relevant to
+ * memory controller.
+ * @memcg: The memory cgroup that went over limit
+ */
+void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *iter;
+	unsigned int i;
 
 	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
 		K((u64)page_counter_read(&memcg->memory)),
@@ -1382,8 +1396,13 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	};
 	bool ret;
 
-	mutex_lock(&oom_lock);
-	ret = out_of_memory(&oc);
+	if (mutex_lock_killable(&oom_lock))
+		return true;
+	/*
+	 * A few threads which were not waiting at mutex_lock_killable() can
+	 * fail to bail out. Therefore, check again after holding oom_lock.
+	 */
+	ret = should_force_charge() || out_of_memory(&oc);
 	mutex_unlock(&oom_lock);
 	return ret;
 }
@@ -1666,6 +1685,9 @@ enum oom_status {
 
 static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
+	enum oom_status ret;
+	bool locked;
+
 	if (order > PAGE_ALLOC_COSTLY_ORDER)
 		return OOM_SKIPPED;
 
@@ -1700,10 +1722,23 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int
 		return OOM_ASYNC;
 	}
 
+	mem_cgroup_mark_under_oom(memcg);
+
+	locked = mem_cgroup_oom_trylock(memcg);
+
+	if (locked)
+		mem_cgroup_oom_notify(memcg);
+
+	mem_cgroup_unmark_under_oom(memcg);
 	if (mem_cgroup_out_of_memory(memcg, mask, order))
-		return OOM_SUCCESS;
+		ret = OOM_SUCCESS;
+	else
+		ret = OOM_FAILED;
+
+	if (locked)
+		mem_cgroup_oom_unlock(memcg);
 
-	return OOM_FAILED;
+	return ret;
 }
 
 /**
@@ -2186,9 +2221,7 @@ retry:
 	 * bypass the last charges so that they can exit quickly and
 	 * free their memory.
 	 */
-	if (unlikely(tsk_is_oom_victim(current) ||
-		     fatal_signal_pending(current) ||
-		     current->flags & PF_EXITING))
+	if (unlikely(should_force_charge()))
 		goto force;
 
 	/*
@@ -2329,13 +2362,13 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 static void lock_page_lru(struct page *page, int *isolated)
 {
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
-	spin_lock_irq(zone_lru_lock(zone));
+	spin_lock_irq(&pgdat->lru_lock);
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		*isolated = 1;
@@ -2345,17 +2378,17 @@ static void lock_page_lru(struct page *page, int *isolated)
 
 static void unlock_page_lru(struct page *page, int isolated)
 {
-	struct zone *zone = page_zone(page);
+	pg_data_t *pgdat = page_pgdat(page);
 
 	if (isolated) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 		add_page_to_lru_list(page, lruvec, page_lru(page));
 	}
-	spin_unlock_irq(zone_lru_lock(zone));
+	spin_unlock_irq(&pgdat->lru_lock);
 }
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2550,7 +2583,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep)
 }
 
 /**
- * memcg_kmem_charge_memcg: charge a kmem page
+ * __memcg_kmem_charge_memcg: charge a kmem page
  * @page: page to charge
  * @gfp: reclaim mode
  * @order: allocation order
@@ -2558,7 +2591,7 @@ void memcg_kmem_put_cache(struct kmem_cache *cachep)
  *
  * Returns 0 on success, an error code on failure.
  */
-int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 			    struct mem_cgroup *memcg)
 {
 	unsigned int nr_pages = 1 << order;
@@ -2581,24 +2614,24 @@ int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 }
 
 /**
- * memcg_kmem_charge: charge a kmem page to the current memory cgroup
+ * __memcg_kmem_charge: charge a kmem page to the current memory cgroup
  * @page: page to charge
  * @gfp: reclaim mode
  * @order: allocation order
  *
  * Returns 0 on success, an error code on failure.
  */
-int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
 	struct mem_cgroup *memcg;
 	int ret = 0;
 
-	if (mem_cgroup_disabled() || memcg_kmem_bypass())
+	if (memcg_kmem_bypass())
 		return 0;
 
 	memcg = get_mem_cgroup_from_current();
 	if (!mem_cgroup_is_root(memcg)) {
-		ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
+		ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
 		if (!ret)
 			__SetPageKmemcg(page);
 	}
@@ -2606,11 +2639,11 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 	return ret;
 }
 /**
- * memcg_kmem_uncharge: uncharge a kmem page
+ * __memcg_kmem_uncharge: uncharge a kmem page
  * @page: page to uncharge
  * @order: allocation order
  */
-void memcg_kmem_uncharge(struct page *page, int order)
+void __memcg_kmem_uncharge(struct page *page, int order)
 {
 	struct mem_cgroup *memcg = page->mem_cgroup;
 	unsigned int nr_pages = 1 << order;
@@ -2641,7 +2674,7 @@ void memcg_kmem_uncharge(struct page *page, int order)
 
 /*
  * Because tail pages are not marked as "used", set it. We're under
- * zone_lru_lock and migration entries setup in all page mappings.
+ * pgdat->lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
@@ -3314,7 +3347,7 @@ static int memcg_numa_stat_show(struct seq_file *m, void *v)
 	const struct numa_stat *stat;
 	int nid;
 	unsigned long nr;
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
 	for (stat = stats; stat < stats + ARRAY_SIZE(stats); stat++) {
 		nr = mem_cgroup_nr_lru_pages(memcg, stat->lru_mask);
@@ -3365,7 +3398,7 @@ static const char *const memcg1_event_names[] = {
 
 static int memcg_stat_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 	unsigned long memory, memsw;
 	struct mem_cgroup *mi;
 	unsigned int i;
@@ -3603,8 +3636,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 	size = thresholds->primary ? thresholds->primary->size + 1 : 1;
 
 	/* Allocate memory for new array of thresholds */
-	new = kmalloc(sizeof(*new) + size * sizeof(struct mem_cgroup_threshold),
-			GFP_KERNEL);
+	new = kmalloc(struct_size(new, entries, size), GFP_KERNEL);
 	if (!new) {
 		ret = -ENOMEM;
 		goto unlock;
@@ -3798,7 +3830,7 @@ static void mem_cgroup_oom_unregister_event(struct mem_cgroup *memcg,
 
 static int mem_cgroup_oom_control_read(struct seq_file *sf, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(sf));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(sf);
 
 	seq_printf(sf, "oom_kill_disable %d\n", memcg->oom_kill_disable);
 	seq_printf(sf, "under_oom %d\n", (bool)memcg->under_oom);
@@ -3850,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 	return &memcg->cgwb_domain;
 }
 
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page().
+ */
+static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
+{
+	long x = atomic_long_read(&memcg->stat[idx]);
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx];
+	if (x < 0)
+		x = 0;
+	return x;
+}
+
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
@@ -3875,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
+	*pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
 
 	/* this should eventually include NR_UNSTABLE_NFS */
-	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
+	*pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
 	*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
 						     (1 << LRU_ACTIVE_FILE));
 	*pheadroom = PAGE_COUNTER_MAX;
@@ -4397,7 +4445,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	size_t size;
+	unsigned int size;
 	int node;
 
 	size = sizeof(struct mem_cgroup);
@@ -5331,6 +5379,16 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 		root_mem_cgroup->use_hierarchy = false;
 }
 
+static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
+{
+	if (value == PAGE_COUNTER_MAX)
+		seq_puts(m, "max\n");
+	else
+		seq_printf(m, "%llu\n", (u64)value * PAGE_SIZE);
+
+	return 0;
+}
+
 static u64 memory_current_read(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
@@ -5341,15 +5399,8 @@ static u64 memory_current_read(struct cgroup_subsys_state *css,
 
 static int memory_min_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	unsigned long min = READ_ONCE(memcg->memory.min);
-
-	if (min == PAGE_COUNTER_MAX)
-		seq_puts(m, "max\n");
-	else
-		seq_printf(m, "%llu\n", (u64)min * PAGE_SIZE);
-
-	return 0;
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->memory.min));
 }
 
 static ssize_t memory_min_write(struct kernfs_open_file *of,
@@ -5371,15 +5422,8 @@ static ssize_t memory_min_write(struct kernfs_open_file *of,
 
 static int memory_low_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	unsigned long low = READ_ONCE(memcg->memory.low);
-
-	if (low == PAGE_COUNTER_MAX)
-		seq_puts(m, "max\n");
-	else
-		seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE);
-
-	return 0;
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->memory.low));
 }
 
 static ssize_t memory_low_write(struct kernfs_open_file *of,
@@ -5401,15 +5445,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of,
 
 static int memory_high_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	unsigned long high = READ_ONCE(memcg->high);
-
-	if (high == PAGE_COUNTER_MAX)
-		seq_puts(m, "max\n");
-	else
-		seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE);
-
-	return 0;
+	return seq_puts_memcg_tunable(m, READ_ONCE(mem_cgroup_from_seq(m)->high));
 }
 
 static ssize_t memory_high_write(struct kernfs_open_file *of,
@@ -5438,15 +5474,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
 
 static int memory_max_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	unsigned long max = READ_ONCE(memcg->memory.max);
-
-	if (max == PAGE_COUNTER_MAX)
-		seq_puts(m, "max\n");
-	else
-		seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
-
-	return 0;
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->memory.max));
 }
 
 static ssize_t memory_max_write(struct kernfs_open_file *of,
@@ -5500,7 +5529,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 
 static int memory_events_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
 	seq_printf(m, "low %lu\n",
 		   atomic_long_read(&memcg->memory_events[MEMCG_LOW]));
@@ -5518,7 +5547,7 @@ static int memory_events_show(struct seq_file *m, void *v)
 
 static int memory_stat_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 	struct accumulated_stats acc;
 	int i;
 
@@ -5559,6 +5588,15 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "file_writeback %llu\n",
 		   (u64)acc.stat[NR_WRITEBACK] * PAGE_SIZE);
 
+	/*
+	 * TODO: We should eventually replace our own MEMCG_RSS_HUGE counter
+	 * with the NR_ANON_THP vm counter, but right now it's a pain in the
+	 * arse because it requires migrating the work out of rmap to a place
+	 * where the page->mem_cgroup is set up and stable.
+	 */
+	seq_printf(m, "anon_thp %llu\n",
+		   (u64)acc.stat[MEMCG_RSS_HUGE] * PAGE_SIZE);
+
 	for (i = 0; i < NR_LRU_LISTS; i++)
 		seq_printf(m, "%s %llu\n", mem_cgroup_lru_names[i],
 			   (u64)acc.lru_pages[i] * PAGE_SIZE);
@@ -5590,12 +5628,18 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "pglazyfree %lu\n", acc.events[PGLAZYFREE]);
 	seq_printf(m, "pglazyfreed %lu\n", acc.events[PGLAZYFREED]);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	seq_printf(m, "thp_fault_alloc %lu\n", acc.events[THP_FAULT_ALLOC]);
+	seq_printf(m, "thp_collapse_alloc %lu\n",
+		   acc.events[THP_COLLAPSE_ALLOC]);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 	return 0;
 }
 
 static int memory_oom_group_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
 	seq_printf(m, "%d\n", memcg->oom_group);
 
@@ -5724,7 +5768,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
  *
  *             | memory.current, if memory.current < memory.low
  * low_usage = |
-	       | 0, otherwise.
+ *	       | 0, otherwise.
  *
  *
  * Such definition of the effective memory.low provides the expected
@@ -6578,15 +6622,8 @@ static u64 swap_current_read(struct cgroup_subsys_state *css,
 
 static int swap_max_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	unsigned long max = READ_ONCE(memcg->swap.max);
-
-	if (max == PAGE_COUNTER_MAX)
-		seq_puts(m, "max\n");
-	else
-		seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
-
-	return 0;
+	return seq_puts_memcg_tunable(m,
+		READ_ONCE(mem_cgroup_from_seq(m)->swap.max));
 }
 
 static ssize_t swap_max_write(struct kernfs_open_file *of,
@@ -6608,7 +6645,7 @@ static ssize_t swap_max_write(struct kernfs_open_file *of,
 
 static int swap_events_show(struct seq_file *m, void *v)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
 
 	seq_printf(m, "max %lu\n",
 		   atomic_long_read(&memcg->memory_events[MEMCG_SWAP_MAX]));