Message-Id: <20210520065355.2736558-10-yuzhao@google.com>
Date:   Thu, 20 May 2021 00:53:50 -0600
From:   Yu Zhao <yuzhao@...gle.com>
To:     linux-mm@...ck.org
Cc:     Alex Shi <alexs@...nel.org>, Andi Kleen <ak@...ux.intel.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Dave Chinner <david@...morbit.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Donald Carr <sirspudd@...il.com>,
        Hillf Danton <hdanton@...a.com>, Jens Axboe <axboe@...nel.dk>,
        Johannes Weiner <hannes@...xchg.org>,
        Jonathan Corbet <corbet@....net>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Konstantin Kharlamov <hi-angel@...dex.ru>,
        Marcus Seyfarth <m.seyfarth@...il.com>,
        Matthew Wilcox <willy@...radead.org>,
        Mel Gorman <mgorman@...e.de>,
        Miaohe Lin <linmiaohe@...wei.com>,
        Michael Larabel <michael@...haellarabel.com>,
        Michal Hocko <mhocko@...e.com>,
        Michel Lespinasse <michel@...pinasse.org>,
        Rik van Riel <riel@...riel.com>,
        Roman Gushchin <guro@...com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Vlastimil Babka <vbabka@...e.cz>,
        Yang Shi <shy828301@...il.com>,
        Ying Huang <ying.huang@...el.com>, Zi Yan <ziy@...dia.com>,
        linux-kernel@...r.kernel.org, lkp@...ts.01.org,
        page-reclaim@...gle.com, Yu Zhao <yuzhao@...gle.com>,
        Konstantin Kharlamov <Hi-Angel@...dex.ru>
Subject: [PATCH v3 09/14] mm: multigenerational lru: mm_struct list

In order to scan page tables, we add an infrastructure to maintain
either a system-wide mm_struct list or per-memcg mm_struct lists, and
track whether an mm_struct is being used or has been used since the
last scan.

Multiple threads can concurrently work on the same mm_struct list, and
each of them will be given a different mm_struct belonging to a
process that has been scheduled since the last scan.

Signed-off-by: Yu Zhao <yuzhao@...gle.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@...dex.ru>
---
 fs/exec.c                  |   2 +
 include/linux/memcontrol.h |   6 +
 include/linux/mm_types.h   | 107 ++++++++++++
 kernel/exit.c              |   1 +
 kernel/fork.c              |  10 ++
 kernel/kthread.c           |   1 +
 kernel/sched/core.c        |   2 +
 mm/memcontrol.c            |  28 ++++
 mm/vmscan.c                | 324 +++++++++++++++++++++++++++++++++++++
 9 files changed, 481 insertions(+)

diff --git a/fs/exec.c b/fs/exec.c
index 18594f11c31f..c691d4d7720c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1008,6 +1008,7 @@ static int exec_mmap(struct mm_struct *mm)
 	active_mm = tsk->active_mm;
 	tsk->active_mm = mm;
 	tsk->mm = mm;
+	lru_gen_add_mm(mm);
 	/*
 	 * This prevents preemption while active_mm is being loaded and
 	 * it and mm are being updated, which could cause problems for
@@ -1018,6 +1019,7 @@ static int exec_mmap(struct mm_struct *mm)
 	if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
 		local_irq_enable();
 	activate_mm(active_mm, mm);
+	lru_gen_switch_mm(active_mm, mm);
 	if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
 		local_irq_enable();
 	tsk->mm->vmacache_seqnum = 0;
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6bcac3d91dd1..60601a997433 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -230,6 +230,8 @@ struct obj_cgroup {
 	};
 };
 
+struct lru_gen_mm_list;
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -349,6 +351,10 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
+#ifdef CONFIG_LRU_GEN
+	struct lru_gen_mm_list *mm_list;
+#endif
+
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5aacc1c10a45..b0f662555eae 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -15,6 +15,8 @@
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
 #include <linux/seqlock.h>
+#include <linux/nodemask.h>
+#include <linux/mmdebug.h>
 
 #include <asm/mmu.h>
 
@@ -561,6 +563,22 @@ struct mm_struct {
 
 #ifdef CONFIG_IOMMU_SUPPORT
 		u32 pasid;
+#endif
+#ifdef CONFIG_LRU_GEN
+		struct {
+			/* the node of a global or per-memcg mm_struct list */
+			struct list_head list;
+#ifdef CONFIG_MEMCG
+			/* points to the memcg of the owner task above */
+			struct mem_cgroup *memcg;
+#endif
+			/* whether this mm_struct has been used since the last walk */
+			nodemask_t nodes;
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+			/* the number of CPUs using this mm_struct */
+			atomic_t nr_cpus;
+#endif
+		} lrugen;
 #endif
 	} __randomize_layout;
 
@@ -588,6 +606,95 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 	return (struct cpumask *)&mm->cpu_bitmap;
 }
 
+#ifdef CONFIG_LRU_GEN
+
+void lru_gen_init_mm(struct mm_struct *mm);
+void lru_gen_add_mm(struct mm_struct *mm);
+void lru_gen_del_mm(struct mm_struct *mm);
+#ifdef CONFIG_MEMCG
+int lru_gen_alloc_mm_list(struct mem_cgroup *memcg);
+void lru_gen_free_mm_list(struct mem_cgroup *memcg);
+void lru_gen_migrate_mm(struct mm_struct *mm);
+#endif
+
+/* Track the usage of each mm_struct so that we can skip inactive ones. */
+static inline void lru_gen_switch_mm(struct mm_struct *old, struct mm_struct *new)
+{
+	/* exclude init_mm, efi_mm, etc. */
+	if (!core_kernel_data((unsigned long)old)) {
+		VM_BUG_ON(old == &init_mm);
+
+		nodes_setall(old->lrugen.nodes);
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+		atomic_dec(&old->lrugen.nr_cpus);
+		VM_BUG_ON_MM(atomic_read(&old->lrugen.nr_cpus) < 0, old);
+#endif
+	} else
+		VM_BUG_ON_MM(READ_ONCE(old->lrugen.list.prev) ||
+			     READ_ONCE(old->lrugen.list.next), old);
+
+	if (!core_kernel_data((unsigned long)new)) {
+		VM_BUG_ON(new == &init_mm);
+
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+		atomic_inc(&new->lrugen.nr_cpus);
+		VM_BUG_ON_MM(atomic_read(&new->lrugen.nr_cpus) < 0, new);
+#endif
+	} else
+		VM_BUG_ON_MM(READ_ONCE(new->lrugen.list.prev) ||
+			     READ_ONCE(new->lrugen.list.next), new);
+}
+
+/* Return whether this mm_struct is being used on any CPUs. */
+static inline bool lru_gen_mm_is_active(struct mm_struct *mm)
+{
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	return !cpumask_empty(mm_cpumask(mm));
+#else
+	return atomic_read(&mm->lrugen.nr_cpus);
+#endif
+}
+
+#else /* CONFIG_LRU_GEN */
+
+static inline void lru_gen_init_mm(struct mm_struct *mm)
+{
+}
+
+static inline void lru_gen_add_mm(struct mm_struct *mm)
+{
+}
+
+static inline void lru_gen_del_mm(struct mm_struct *mm)
+{
+}
+
+#ifdef CONFIG_MEMCG
+static inline int lru_gen_alloc_mm_list(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+
+static inline void lru_gen_free_mm_list(struct mem_cgroup *memcg)
+{
+}
+
+static inline void lru_gen_migrate_mm(struct mm_struct *mm)
+{
+}
+#endif
+
+static inline void lru_gen_switch_mm(struct mm_struct *old, struct mm_struct *new)
+{
+}
+
+static inline bool lru_gen_mm_is_active(struct mm_struct *mm)
+{
+	return false;
+}
+
+#endif /* CONFIG_LRU_GEN */
+
 struct mmu_gather;
 extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
 extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm);
diff --git a/kernel/exit.c b/kernel/exit.c
index fd1c04193e18..b362179852f1 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -423,6 +423,7 @@ void mm_update_next_owner(struct mm_struct *mm)
 		goto retry;
 	}
 	WRITE_ONCE(mm->owner, c);
+	lru_gen_migrate_mm(mm);
 	task_unlock(c);
 	put_task_struct(c);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index dc06afd725cb..2fd7dae9afcb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -669,6 +669,7 @@ static void check_mm(struct mm_struct *mm)
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
 #endif
+	VM_BUG_ON_MM(lru_gen_mm_is_active(mm), mm);
 }
 
 #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
@@ -1061,6 +1062,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 		goto fail_nocontext;
 
 	mm->user_ns = get_user_ns(user_ns);
+	lru_gen_init_mm(mm);
 	return mm;
 
 fail_nocontext:
@@ -1103,6 +1105,7 @@ static inline void __mmput(struct mm_struct *mm)
 	}
 	if (mm->binfmt)
 		module_put(mm->binfmt->module);
+	lru_gen_del_mm(mm);
 	mmdrop(mm);
 }
 
@@ -2524,6 +2527,13 @@ pid_t kernel_clone(struct kernel_clone_args *args)
 		get_task_struct(p);
 	}
 
+	if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+		/* lock the task to synchronize with memcg migration */
+		task_lock(p);
+		lru_gen_add_mm(p->mm);
+		task_unlock(p);
+	}
+
 	wake_up_new_task(p);
 
 	/* forking complete and child started to run, tell ptracer */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index fe3f2a40d61e..b81e49ed31a7 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1325,6 +1325,7 @@ void kthread_use_mm(struct mm_struct *mm)
 	tsk->mm = mm;
 	membarrier_update_current_mm(mm);
 	switch_mm_irqs_off(active_mm, mm, tsk);
+	lru_gen_switch_mm(active_mm, mm);
 	local_irq_enable();
 	task_unlock(tsk);
 #ifdef finish_arch_post_lock_switch
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5226cc26a095..2d4b77f173db 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4323,6 +4323,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 		 * finish_task_switch()'s mmdrop().
 		 */
 		switch_mm_irqs_off(prev->active_mm, next->mm, next);
+		lru_gen_switch_mm(prev->active_mm, next->mm);
 
 		if (!prev->mm) {                        // from kernel
 			/* will mmdrop() in finish_task_switch(). */
@@ -7603,6 +7604,7 @@ void idle_task_exit(void)
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
+		lru_gen_switch_mm(mm, &init_mm);
 		finish_arch_post_lock_switch();
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 64ada9e650a5..58b610ffa0e0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4981,6 +4981,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
+	lru_gen_free_mm_list(memcg);
 	kfree(memcg);
 }
 
@@ -5030,6 +5031,9 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
 
+	if (lru_gen_alloc_mm_list(memcg))
+		goto fail;
+
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
 		goto fail;
 
@@ -5991,6 +5995,29 @@ static void mem_cgroup_move_task(void)
 }
 #endif
 
+#ifdef CONFIG_LRU_GEN
+static void mem_cgroup_attach(struct cgroup_taskset *tset)
+{
+	struct cgroup_subsys_state *css;
+	struct task_struct *task = NULL;
+
+	cgroup_taskset_for_each_leader(task, css, tset)
+		;
+
+	if (!task)
+		return;
+
+	task_lock(task);
+	if (task->mm && task->mm->owner == task)
+		lru_gen_migrate_mm(task->mm);
+	task_unlock(task);
+}
+#else
+static void mem_cgroup_attach(struct cgroup_taskset *tset)
+{
+}
+#endif
+
 static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
 {
 	if (value == PAGE_COUNTER_MAX)
@@ -6332,6 +6359,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_reset = mem_cgroup_css_reset,
 	.css_rstat_flush = mem_cgroup_css_rstat_flush,
 	.can_attach = mem_cgroup_can_attach,
+	.attach = mem_cgroup_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.post_attach = mem_cgroup_move_task,
 	.dfl_cftypes = memory_files,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 84d25079092e..d93d2272e475 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2869,6 +2869,323 @@ static bool positive_ctrl_err(struct controller_pos *sp, struct controller_pos *
 	       sp->refaulted * max(pv->total, 1UL) * pv->gain;
 }
 
+/******************************************************************************
+ *                          mm_struct list
+ ******************************************************************************/
+
+enum {
+	MM_SCHED_ACTIVE,	/* running processes */
+	MM_SCHED_INACTIVE,	/* sleeping processes */
+	MM_LOCK_CONTENTION,	/* lock contentions */
+	MM_VMA_INTERVAL,	/* VMAs within the range of each PUD/PMD/PTE */
+	MM_LEAF_OTHER_NODE,	/* entries not from the node under reclaim */
+	MM_LEAF_OTHER_MEMCG,	/* entries not from the memcg under reclaim */
+	MM_LEAF_OLD,		/* old entries */
+	MM_LEAF_YOUNG,		/* young entries */
+	MM_LEAF_DIRTY,		/* dirty entries */
+	MM_LEAF_HOLE,		/* non-present entries */
+	MM_NONLEAF_OLD,		/* old non-leaf PMD entries */
+	MM_NONLEAF_YOUNG,	/* young non-leaf PMD entries */
+	NR_MM_STATS
+};
+
+/* mnemonic codes for the stats above */
+#define MM_STAT_CODES		"aicvnmoydhlu"
+
+struct lru_gen_mm_list {
+	/* the head of a global or per-memcg mm_struct list */
+	struct list_head head;
+	/* protects the list */
+	spinlock_t lock;
+	struct {
+		/* set to max_seq after each round of walk */
+		unsigned long cur_seq;
+		/* the next mm on the list to walk */
+		struct list_head *iter;
+		/* to wait for the last worker to finish */
+		struct wait_queue_head wait;
+		/* the number of concurrent workers */
+		int nr_workers;
+		/* stats for debugging */
+		unsigned long stats[NR_STAT_GENS][NR_MM_STATS];
+	} nodes[0];
+};
+
+static struct lru_gen_mm_list *global_mm_list;
+
+static struct lru_gen_mm_list *alloc_mm_list(void)
+{
+	int nid;
+	struct lru_gen_mm_list *mm_list;
+
+	mm_list = kzalloc(struct_size(mm_list, nodes, nr_node_ids), GFP_KERNEL);
+	if (!mm_list)
+		return NULL;
+
+	INIT_LIST_HEAD(&mm_list->head);
+	spin_lock_init(&mm_list->lock);
+
+	for_each_node(nid) {
+		mm_list->nodes[nid].cur_seq = MIN_NR_GENS;
+		mm_list->nodes[nid].iter = &mm_list->head;
+		init_waitqueue_head(&mm_list->nodes[nid].wait);
+	}
+
+	return mm_list;
+}
+
+static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
+{
+#ifdef CONFIG_MEMCG
+	if (!mem_cgroup_disabled())
+		return memcg ? memcg->mm_list : root_mem_cgroup->mm_list;
+#endif
+	VM_BUG_ON(memcg);
+
+	return global_mm_list;
+}
+
+void lru_gen_init_mm(struct mm_struct *mm)
+{
+	INIT_LIST_HEAD(&mm->lrugen.list);
+#ifdef CONFIG_MEMCG
+	mm->lrugen.memcg = NULL;
+#endif
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+	atomic_set(&mm->lrugen.nr_cpus, 0);
+#endif
+	nodes_clear(mm->lrugen.nodes);
+}
+
+void lru_gen_add_mm(struct mm_struct *mm)
+{
+	struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
+	struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
+
+	VM_BUG_ON_MM(!list_empty(&mm->lrugen.list), mm);
+#ifdef CONFIG_MEMCG
+	VM_BUG_ON_MM(mm->lrugen.memcg, mm);
+	WRITE_ONCE(mm->lrugen.memcg, memcg);
+#endif
+	spin_lock(&mm_list->lock);
+	list_add_tail(&mm->lrugen.list, &mm_list->head);
+	spin_unlock(&mm_list->lock);
+}
+
+void lru_gen_del_mm(struct mm_struct *mm)
+{
+	int nid;
+#ifdef CONFIG_MEMCG
+	struct lru_gen_mm_list *mm_list = get_mm_list(mm->lrugen.memcg);
+#else
+	struct lru_gen_mm_list *mm_list = get_mm_list(NULL);
+#endif
+
+	spin_lock(&mm_list->lock);
+
+	for_each_node(nid) {
+		if (mm_list->nodes[nid].iter != &mm->lrugen.list)
+			continue;
+
+		mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+		if (mm_list->nodes[nid].iter == &mm_list->head)
+			WRITE_ONCE(mm_list->nodes[nid].cur_seq,
+				   mm_list->nodes[nid].cur_seq + 1);
+	}
+
+	list_del_init(&mm->lrugen.list);
+
+	spin_unlock(&mm_list->lock);
+
+#ifdef CONFIG_MEMCG
+	mem_cgroup_put(mm->lrugen.memcg);
+	WRITE_ONCE(mm->lrugen.memcg, NULL);
+#endif
+}
+
+#ifdef CONFIG_MEMCG
+int lru_gen_alloc_mm_list(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return 0;
+
+	memcg->mm_list = alloc_mm_list();
+
+	return memcg->mm_list ? 0 : -ENOMEM;
+}
+
+void lru_gen_free_mm_list(struct mem_cgroup *memcg)
+{
+	kfree(memcg->mm_list);
+	memcg->mm_list = NULL;
+}
+
+void lru_gen_migrate_mm(struct mm_struct *mm)
+{
+	struct mem_cgroup *memcg;
+
+	lockdep_assert_held(&mm->owner->alloc_lock);
+
+	if (mem_cgroup_disabled())
+		return;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(mm->owner);
+	rcu_read_unlock();
+	if (memcg == mm->lrugen.memcg)
+		return;
+
+	VM_BUG_ON_MM(!mm->lrugen.memcg, mm);
+	VM_BUG_ON_MM(list_empty(&mm->lrugen.list), mm);
+
+	lru_gen_del_mm(mm);
+	lru_gen_add_mm(mm);
+}
+
+static bool mm_has_migrated(struct mm_struct *mm, struct mem_cgroup *memcg)
+{
+	return READ_ONCE(mm->lrugen.memcg) != memcg;
+}
+#else
+static bool mm_has_migrated(struct mm_struct *mm, struct mem_cgroup *memcg)
+{
+	return false;
+}
+#endif
+
+struct mm_walk_args {
+	struct mem_cgroup *memcg;
+	unsigned long max_seq;
+	unsigned long start_pfn;
+	unsigned long end_pfn;
+	unsigned long next_addr;
+	int node_id;
+	int swappiness;
+	int batch_size;
+	int nr_pages[MAX_NR_GENS][ANON_AND_FILE][MAX_NR_ZONES];
+	int mm_stats[NR_MM_STATS];
+	unsigned long bitmap[0];
+};
+
+static int size_of_mm_walk_args(void)
+{
+	int size = sizeof(struct mm_walk_args);
+
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) ||
+	    IS_ENABLED(CONFIG_HAVE_ARCH_PARENT_PMD_YOUNG))
+		size += sizeof(unsigned long) * BITS_TO_LONGS(PTRS_PER_PMD);
+
+	return size;
+}
+
+static void reset_mm_stats(struct lru_gen_mm_list *mm_list, bool last,
+			   struct mm_walk_args *args)
+{
+	int i;
+	int nid = args->node_id;
+	int hist = hist_from_seq_or_gen(args->max_seq);
+
+	lockdep_assert_held(&mm_list->lock);
+
+	for (i = 0; i < NR_MM_STATS; i++) {
+		WRITE_ONCE(mm_list->nodes[nid].stats[hist][i],
+			   mm_list->nodes[nid].stats[hist][i] + args->mm_stats[i]);
+		args->mm_stats[i] = 0;
+	}
+
+	if (!last || NR_STAT_GENS == 1)
+		return;
+
+	hist = hist_from_seq_or_gen(args->max_seq + 1);
+	for (i = 0; i < NR_MM_STATS; i++)
+		WRITE_ONCE(mm_list->nodes[nid].stats[hist][i], 0);
+}
+
+static bool should_skip_mm(struct mm_struct *mm, struct mm_walk_args *args)
+{
+	int type;
+	unsigned long size = 0;
+
+	if (!lru_gen_mm_is_active(mm) && !node_isset(args->node_id, mm->lrugen.nodes))
+		return true;
+
+	if (mm_is_oom_victim(mm))
+		return true;
+
+	for (type = !args->swappiness; type < ANON_AND_FILE; type++) {
+		size += type ? get_mm_counter(mm, MM_FILEPAGES) :
+			       get_mm_counter(mm, MM_ANONPAGES) +
+			       get_mm_counter(mm, MM_SHMEMPAGES);
+	}
+
+	/* leave the legwork to the rmap if mappings are too sparse */
+	if (size < max(SWAP_CLUSTER_MAX, mm_pgtables_bytes(mm) / PAGE_SIZE))
+		return true;
+
+	return !mmget_not_zero(mm);
+}
+
+/* To support multiple workers that concurrently walk an mm_struct list. */
+static bool get_next_mm(struct mm_walk_args *args, struct mm_struct **iter)
+{
+	bool last = true;
+	struct mm_struct *mm = NULL;
+	int nid = args->node_id;
+	struct lru_gen_mm_list *mm_list = get_mm_list(args->memcg);
+
+	if (*iter)
+		mmput_async(*iter);
+	else if (args->max_seq <= READ_ONCE(mm_list->nodes[nid].cur_seq))
+		return false;
+
+	spin_lock(&mm_list->lock);
+
+	VM_BUG_ON(args->max_seq > mm_list->nodes[nid].cur_seq + 1);
+	VM_BUG_ON(*iter && args->max_seq < mm_list->nodes[nid].cur_seq);
+	VM_BUG_ON(*iter && !mm_list->nodes[nid].nr_workers);
+
+	if (args->max_seq <= mm_list->nodes[nid].cur_seq) {
+		last = *iter;
+		goto done;
+	}
+
+	if (mm_list->nodes[nid].iter == &mm_list->head) {
+		VM_BUG_ON(*iter || mm_list->nodes[nid].nr_workers);
+		mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+	}
+
+	while (!mm && mm_list->nodes[nid].iter != &mm_list->head) {
+		mm = list_entry(mm_list->nodes[nid].iter, struct mm_struct, lrugen.list);
+		mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+		if (should_skip_mm(mm, args))
+			mm = NULL;
+
+		args->mm_stats[mm ? MM_SCHED_ACTIVE : MM_SCHED_INACTIVE]++;
+	}
+
+	if (mm_list->nodes[nid].iter == &mm_list->head)
+		WRITE_ONCE(mm_list->nodes[nid].cur_seq,
+			   mm_list->nodes[nid].cur_seq + 1);
+done:
+	if (*iter && !mm)
+		mm_list->nodes[nid].nr_workers--;
+	if (!*iter && mm)
+		mm_list->nodes[nid].nr_workers++;
+
+	last = last && !mm_list->nodes[nid].nr_workers &&
+	       mm_list->nodes[nid].iter == &mm_list->head;
+
+	reset_mm_stats(mm_list, last, args);
+
+	spin_unlock(&mm_list->lock);
+
+	*iter = mm;
+	if (mm)
+		node_clear(nid, mm->lrugen.nodes);
+
+	return last;
+}
+
 /******************************************************************************
  *                          state change
  ******************************************************************************/
@@ -3096,6 +3413,13 @@ static int __init init_lru_gen(void)
 {
 	BUILD_BUG_ON(MIN_NR_GENS + 1 >= MAX_NR_GENS);
 	BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
+	BUILD_BUG_ON(sizeof(MM_STAT_CODES) != NR_MM_STATS + 1);
+
+	if (mem_cgroup_disabled()) {
+		global_mm_list = alloc_mm_list();
+		if (WARN_ON_ONCE(!global_mm_list))
+			return -ENOMEM;
+	}
 
 	if (hotplug_memory_notifier(lru_gen_online_mem, 0))
 		pr_err("lru_gen: failed to subscribe hotplug notifications\n");
-- 
2.31.1.751.gd2f1c929bd-goog

Powered by blists - more mailing lists