mm: multi-gen LRU: kill switch

mainline inclusion
from mainline-v6.1-rc1
commit 354ed597
category: feature
bugzilla: https://gitee.com/openeuler/open-source-summer/issues/I55Z0L
CVE: NA
Reference: https://android-review.googlesource.com/c/kernel/common/+/2050915/10

----------------------------------------------------------------------

Add /sys/kernel/mm/lru_gen/enabled as a kill switch. Components that
can be disabled include:
  0x0001: the multi-gen LRU core
  0x0002: walking page table, when arch_has_hw_pte_young() returns
          true
  0x0004: clearing the accessed bit in non-leaf PMD entries, when
          CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG=y
  [yYnN]: apply to all the components above
E.g.,
  echo y >/sys/kernel/mm/lru_gen/enabled
  cat /sys/kernel/mm/lru_gen/enabled
  0x0007
  echo 5 >/sys/kernel/mm/lru_gen/enabled
  cat /sys/kernel/mm/lru_gen/enabled
  0x0005

NB: the page table walks happen on the scale of seconds under heavy
memory pressure, in which case the mmap_lock contention is a lesser
concern, compared with the LRU lock contention and the I/O congestion.
So far the only well-known case of the mmap_lock contention happens on
Android, due to Scudo [1] which allocates several thousand VMAs for
merely a few hundred MBs. The SPF and the Maple Tree also have
provided their own assessments [2][3]. However, if walking page tables
does worsen the mmap_lock contention, the kill switch can be used to
disable it. In this case the multi-gen LRU will suffer a minor
performance degradation, as shown previously.

Clearing the accessed bit in non-leaf PMD entries can also be
disabled, since this behavior was not tested on x86 varieties other
than Intel and AMD.

[1] https://source.android.com/devices/tech/debug/scudo
[2] https://lore.kernel.org/lkml/20220128131006.67712-1-michel@lespinasse.org/
[3] https://lore.kernel.org/lkml/20220202024137.2516438-1-Liam.Howlett@oracle.com/

Link: https://lore.kernel.org/r/20220309021230.721028-11-yuzhao@google.com/Signed-off-by: NYu Zhao <yuzhao@google.com>
Acked-by: NBrian Geffon <bgeffon@google.com>
Acked-by: NJan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: NOleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: NSteven Barrett <steven@liquorix.net>
Acked-by: NSuleiman Souhlal <suleiman@google.com>
Tested-by: NDaniel Byrne <djbyrne@mtu.edu>
Tested-by: NDonald Carr <d@chaos-reins.com>
Tested-by: NHolger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: NKonstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: NShuang Zhai <szhai2@cs.rochester.edu>
Tested-by: NSofia Trinh <sofia.trinh@edi.works>
Tested-by: NVaibhav Jain <vaibhav@linux.ibm.com>
Bug: 227651406
Signed-off-by: NKalesh Singh <kaleshsingh@google.com>
Change-Id: I71801d9470a2588cad8bfd14fbcfafc7b010aa03
Signed-off-by: NYuLinjia <3110442349@qq.com>

include/linux/cgroup.h

@@ -432,6 +432,18 @@ static inline void cgroup_put(struct cgroup *cgrp)
 	css_put(&cgrp->self);
 }
 
+extern struct mutex cgroup_mutex;
+
+static inline void cgroup_lock(void)
+{
+	mutex_lock(&cgroup_mutex);
+}
+
+static inline void cgroup_unlock(void)
+{
+	mutex_unlock(&cgroup_mutex);
+}
+
 /**
  * task_css_set_check - obtain a task's css_set with extra access conditions
  * @task: the task to obtain css_set for
@@ -446,7 +458,6 @@ static inline void cgroup_put(struct cgroup *cgrp)
  * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
-extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
@@ -704,6 +715,8 @@ struct cgroup;
 static inline u64 cgroup_id(const struct cgroup *cgrp) { return 1; }
 static inline void css_get(struct cgroup_subsys_state *css) {}
 static inline void css_put(struct cgroup_subsys_state *css) {}
+static inline void cgroup_lock(void) {}
+static inline void cgroup_unlock(void) {}
 static inline int cgroup_attach_task_all(struct task_struct *from,
 					 struct task_struct *t) { return 0; }
 static inline int cgroupstats_build(struct cgroupstats *stats,

include/linux/mm_inline.h

@@ -112,7 +112,15 @@ static __always_inline enum lru_list page_lru(struct page *page)
 
 static inline bool lru_gen_enabled(void)
 {
-	return true;
+#ifdef CONFIG_LRU_GEN_ENABLED
+	DECLARE_STATIC_KEY_TRUE(lru_gen_caps[NR_LRU_GEN_CAPS]);
+
+	return static_branch_likely(&lru_gen_caps[LRU_GEN_CORE]);
+#else
+	DECLARE_STATIC_KEY_FALSE(lru_gen_caps[NR_LRU_GEN_CAPS]);
+
+	return static_branch_unlikely(&lru_gen_caps[LRU_GEN_CORE]);
+#endif
 }
 
 static inline bool lru_gen_in_fault(void)
@@ -202,7 +210,7 @@ static inline bool lru_gen_add_page(struct lruvec *lruvec, struct page *page, bo
 	int zone = page_zonenum(page);
 	struct lru_gen_struct *lrugen = &lruvec->lrugen;
 
-	if (PageUnevictable(page))
+	if (PageUnevictable(page) || !lrugen->enabled)
 		return false;
 	/*
 	 * There are three common cases for this page:

include/linux/mmzone.h

@@ -346,6 +346,13 @@ enum {
 	LRU_GEN_FILE,
 };
 
+enum {
+	LRU_GEN_CORE,
+	LRU_GEN_MM_WALK,
+	LRU_GEN_NONLEAF_YOUNG,
+	NR_LRU_GEN_CAPS
+};
+
 #define MIN_LRU_BATCH		BITS_PER_LONG
 #define MAX_LRU_BATCH		(MIN_LRU_BATCH * 128)
 
@@ -384,6 +391,8 @@ struct lru_gen_struct {
 	/* can be modified without holding the LRU lock */
 	atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
+	/* whether the multi-gen LRU is enabled */
+	bool enabled;
 };
 
 enum {

kernel/cgroup/cgroup-internal.h

@@ -165,7 +165,6 @@ struct cgroup_mgctx {
 #define DEFINE_CGROUP_MGCTX(name)						\
 	struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name)
 
-extern struct mutex cgroup_mutex;
 extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;

mm/Kconfig

@@ -994,6 +994,12 @@ config LRU_GEN
 	help
 	  A high performance LRU implementation to overcommit memory.
 
+config LRU_GEN_ENABLED
+	bool "Enable by default"
+	depends on LRU_GEN
+	help
+	  This option enables the multi-gen LRU by default.
+
 config LRU_GEN_STATS
 	bool "Full stats for debugging"
 	depends on LRU_GEN

mm/vmscan.c

@@ -54,6 +54,7 @@
 #include <linux/psi.h>
 #include <linux/pagewalk.h>
 #include <linux/shmem_fs.h>
+#include <linux/ctype.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -2763,6 +2764,12 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 
 #ifdef CONFIG_LRU_GEN
 
+#ifdef CONFIG_LRU_GEN_ENABLED
+DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS);
+#else
+DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
+#endif
+
 /******************************************************************************
  *                          shorthand helpers
  ******************************************************************************/
@@ -2799,6 +2806,15 @@ static int page_lru_tier(struct page *page)
 	return lru_tier_from_refs(refs);
 }
 
+static bool get_cap(int cap)
+{
+#ifdef CONFIG_LRU_GEN_ENABLED
+	return static_branch_likely(&lru_gen_caps[cap]);
+#else
+	return static_branch_unlikely(&lru_gen_caps[cap]);
+#endif
+}
+
 static struct lruvec *get_lruvec(struct mem_cgroup *memcg, int nid)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
@@ -3604,7 +3620,8 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG))
+			if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
+			    get_cap(LRU_GEN_NONLEAF_YOUNG))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
 		}
@@ -3711,10 +3728,12 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 		priv->mm_stats[MM_PMD_TOTAL]++;
 
 #ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
-		if (!pmd_young(val))
-			continue;
+		if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
+			if (!pmd_young(val))
+				continue;
 
-		walk_pmd_range_locked(pud, addr, vma, walk, &pos);
+			walk_pmd_range_locked(pud, addr, vma, walk, &pos);
+		}
 #endif
 		if (!priv->full_scan && !test_bloom_filter(priv->lruvec, priv->max_seq, pmd + i))
 			continue;
@@ -3955,7 +3974,7 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long max_seq,
 	 * handful of PTEs. Spreading the work out over a period of time usually
 	 * is less efficient, but it avoids bursty page faults.
 	 */
-	if (!full_scan && !arch_has_hw_pte_young()) {
+	if (!full_scan && (!arch_has_hw_pte_young() || !get_cap(LRU_GEN_MM_WALK))) {
 		success = iterate_mm_list_nowalk(lruvec, max_seq);
 		goto done;
 	}
@@ -4680,6 +4699,223 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
 	blk_finish_plug(&plug);
 }
 
+/******************************************************************************
+ *                          state change
+ ******************************************************************************/
+
+static bool __maybe_unused state_is_valid(struct lruvec *lruvec)
+{
+	struct lru_gen_struct *lrugen = &lruvec->lrugen;
+
+	if (lrugen->enabled) {
+		enum lru_list lru;
+
+		for_each_evictable_lru(lru) {
+			if (!list_empty(&lruvec->lists[lru]))
+				return false;
+		}
+	} else {
+		int gen, type, zone;
+
+		for_each_gen_type_zone(gen, type, zone) {
+			if (!list_empty(&lrugen->lists[gen][type][zone]))
+				return false;
+
+			/* unlikely but not a bug when reset_batch_size() is pending */
+			VM_WARN_ON(lrugen->nr_pages[gen][type][zone]);
+		}
+	}
+
+	return true;
+}
+
+static bool fill_evictable(struct lruvec *lruvec)
+{
+	enum lru_list lru;
+	int remaining = MAX_LRU_BATCH;
+
+	for_each_evictable_lru(lru) {
+		int type = is_file_lru(lru);
+		bool active = is_active_lru(lru);
+		struct list_head *head = &lruvec->lists[lru];
+
+		while (!list_empty(head)) {
+			bool success;
+			struct page *page = lru_to_page(head);
+
+			VM_BUG_ON_PAGE(PageTail(page), page);
+			VM_BUG_ON_PAGE(PageUnevictable(page), page);
+			VM_BUG_ON_PAGE(PageActive(page) != active, page);
+			VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
+			VM_BUG_ON_PAGE(page_lru_gen(page) < MAX_NR_GENS, page);
+
+			prefetchw_prev_lru_page(page, head, flags);
+
+			del_page_from_lru_list(page, lruvec, page_lru(page));
+			success = lru_gen_add_page(lruvec, page, false);
+			VM_BUG_ON(!success);
+
+			if (!--remaining)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static bool drain_evictable(struct lruvec *lruvec)
+{
+	int gen, type, zone;
+	int remaining = MAX_LRU_BATCH;
+
+	for_each_gen_type_zone(gen, type, zone) {
+		struct list_head *head = &lruvec->lrugen.lists[gen][type][zone];
+
+		while (!list_empty(head)) {
+			bool success;
+			struct page *page = lru_to_page(head);
+
+			VM_BUG_ON_PAGE(PageTail(page), page);
+			VM_BUG_ON_PAGE(PageUnevictable(page), page);
+			VM_BUG_ON_PAGE(PageActive(page), page);
+			VM_BUG_ON_PAGE(page_is_file_lru(page) != type, page);
+			VM_BUG_ON_PAGE(page_zonenum(page) != zone, page);
+
+			prefetchw_prev_lru_page(page, head, flags);
+
+			success = lru_gen_del_page(lruvec, page, false);
+			VM_BUG_ON(!success);
+			add_page_to_lru_list(page, lruvec, page_lru(page));
+
+			if (!--remaining)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static void lru_gen_change_state(bool enable)
+{
+	static DEFINE_MUTEX(state_mutex);
+
+	struct mem_cgroup *memcg;
+
+	cgroup_lock();
+	cpus_read_lock();
+	get_online_mems();
+	mutex_lock(&state_mutex);
+
+	if (enable == lru_gen_enabled())
+		goto unlock;
+
+	if (enable)
+		static_branch_enable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
+	else
+		static_branch_disable_cpuslocked(&lru_gen_caps[LRU_GEN_CORE]);
+
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
+	do {
+		int nid;
+
+		for_each_node(nid) {
+			struct pglist_data *pgdat = NODE_DATA(nid);
+			struct lruvec *lruvec = get_lruvec(memcg, nid);
+
+			if (!lruvec)
+				continue;
+
+			if (!pgdat) {
+				lruvec->lrugen.enabled = enable;
+				continue;
+			}
+
+			spin_lock_irq(&lruvec->lru_lock);
+
+			VM_BUG_ON(!seq_is_valid(lruvec));
+			VM_BUG_ON(!state_is_valid(lruvec));
+
+			lruvec->lrugen.enabled = enable;
+
+			while (!(enable ? fill_evictable(lruvec) : drain_evictable(lruvec))) {
+				spin_unlock_irq(&lruvec->lru_lock);
+				cond_resched();
+				spin_lock_irq(&lruvec->lru_lock);
+			}
+
+			spin_unlock_irq(&lruvec->lru_lock);
+		}
+
+		cond_resched();
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+unlock:
+	mutex_unlock(&state_mutex);
+	put_online_mems();
+	cpus_read_unlock();
+	cgroup_unlock();
+}
+
+/******************************************************************************
+ *                          sysfs interface
+ ******************************************************************************/
+
+static ssize_t show_enable(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+	unsigned int caps = 0;
+
+	if (get_cap(LRU_GEN_CORE))
+		caps |= BIT(LRU_GEN_CORE);
+
+	if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
+		caps |= BIT(LRU_GEN_MM_WALK);
+
+	if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
+		caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
+
+	return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);
+}
+
+static ssize_t store_enable(struct kobject *kobj, struct kobj_attribute *attr,
+			    const char *buf, size_t len)
+{
+	int i;
+	unsigned int caps;
+
+	if (tolower(*buf) == 'n')
+		caps = 0;
+	else if (tolower(*buf) == 'y')
+		caps = -1;
+	else if (kstrtouint(buf, 0, &caps))
+		return -EINVAL;
+
+	for (i = 0; i < NR_LRU_GEN_CAPS; i++) {
+		bool enable = caps & BIT(i);
+
+		if (i == LRU_GEN_CORE)
+			lru_gen_change_state(enable);
+		else if (enable)
+			static_branch_enable(&lru_gen_caps[i]);
+		else
+			static_branch_disable(&lru_gen_caps[i]);
+	}
+
+	return len;
+}
+
+static struct kobj_attribute lru_gen_enabled_attr = __ATTR(
+	enabled, 0644, show_enable, store_enable
+);
+
+static struct attribute *lru_gen_attrs[] = {
+	&lru_gen_enabled_attr.attr,
+	NULL
+};
+
+static struct attribute_group lru_gen_attr_group = {
+	.name = "lru_gen",
+	.attrs = lru_gen_attrs,
+};
+
 /******************************************************************************
  *                          initialization
  ******************************************************************************/
@@ -4690,6 +4926,7 @@ void lru_gen_init_lruvec(struct lruvec *lruvec)
 	struct lru_gen_struct *lrugen = &lruvec->lrugen;
 
 	lrugen->max_seq = MIN_NR_GENS + 1;
+	lrugen->enabled = lru_gen_enabled();
 
 	for_each_gen_type_zone(gen, type, zone)
 		INIT_LIST_HEAD(&lrugen->lists[gen][type][zone]);
@@ -4730,6 +4967,9 @@ static int __init init_lru_gen(void)
 	BUILD_BUG_ON(BIT(LRU_GEN_WIDTH) <= MAX_NR_GENS);
 	BUILD_BUG_ON(sizeof(MM_STAT_CODES) != NR_MM_STATS + 1);
 
+	if (sysfs_create_group(mm_kobj, &lru_gen_attr_group))
+		pr_err("lru_gen: failed to create sysfs group\n");
+
 	return 0;
 };
 late_initcall(init_lru_gen);