mm: multi-gen LRU: kill switch

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/r/20220128131006.67712-1-michel@lespinasse.org/
[3] https://lore.kernel.org/r/20220426150616.3937571-1-Liam.Howlett@oracle.com/

Link: https://lkml.kernel.org/r/20220918080010.2920238-11-yuzhao@google.com
Signed-off-by: Yu Zhao <yuzhao@google.com>
Acked-by: Brian Geffon <bgeffon@google.com>
Acked-by: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Acked-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Acked-by: Steven Barrett <steven@liquorix.net>
Acked-by: Suleiman Souhlal <suleiman@google.com>
Tested-by: Daniel Byrne <djbyrne@mtu.edu>
Tested-by: Donald Carr <d@chaos-reins.com>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Konstantin Kharlamov <Hi-Angel@yandex.ru>
Tested-by: Shuang Zhai <szhai2@cs.rochester.edu>
Tested-by: Sofia Trinh <sofia.trinh@edi.works>
Tested-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Larabel <Michael@MichaelLarabel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 223 insertions, 5 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7d8eec2310cc..2f4be18b57cb 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -51,6 +51,7 @@
 #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>
@@ -3070,6 +3071,14 @@ static bool can_age_anon_pages(struct pglist_data *pgdat,
 
 #ifdef CONFIG_LRU_GEN
 
+#ifdef CONFIG_LRU_GEN_ENABLED
+DEFINE_STATIC_KEY_ARRAY_TRUE(lru_gen_caps, NR_LRU_GEN_CAPS);
+#define get_cap(cap)	static_branch_likely(&lru_gen_caps[cap])
+#else
+DEFINE_STATIC_KEY_ARRAY_FALSE(lru_gen_caps, NR_LRU_GEN_CAPS);
+#define get_cap(cap)	static_branch_unlikely(&lru_gen_caps[cap])
+#endif
+
 /******************************************************************************
  *                          shorthand helpers
  ******************************************************************************/
@@ -3946,7 +3955,8 @@ 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;
 		}
@@ -4044,10 +4054,12 @@ restart:
 		walk->mm_stats[MM_NONLEAF_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, args, bitmap, &pos);
+			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
+		}
 #endif
 		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
 			continue;
@@ -4309,7 +4321,7 @@ 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 (!arch_has_hw_pte_young()) {
+	if (!(arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))) {
 		success = iterate_mm_list_nowalk(lruvec, max_seq);
 		goto done;
 	}
@@ -5075,6 +5087,208 @@ done:
 }
 
 /******************************************************************************
+ *                          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;
+		}
+	}
+
+	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 folio *folio = lru_to_folio(head);
+
+			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio) != active, folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_lru_gen(folio) != -1, folio);
+
+			lruvec_del_folio(lruvec, folio);
+			success = lru_gen_add_folio(lruvec, folio, false);
+			VM_WARN_ON_ONCE(!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 folio *folio = lru_to_folio(head);
+
+			VM_WARN_ON_ONCE_FOLIO(folio_test_unevictable(folio), folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_test_active(folio), folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_is_file_lru(folio) != type, folio);
+			VM_WARN_ON_ONCE_FOLIO(folio_zonenum(folio) != zone, folio);
+
+			success = lru_gen_del_folio(lruvec, folio, false);
+			VM_WARN_ON_ONCE(!success);
+			lruvec_add_folio(lruvec, folio);
+
+			if (!--remaining)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static void lru_gen_change_state(bool enabled)
+{
+	static DEFINE_MUTEX(state_mutex);
+
+	struct mem_cgroup *memcg;
+
+	cgroup_lock();
+	cpus_read_lock();
+	get_online_mems();
+	mutex_lock(&state_mutex);
+
+	if (enabled == lru_gen_enabled())
+		goto unlock;
+
+	if (enabled)
+		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 lruvec *lruvec = get_lruvec(memcg, nid);
+
+			if (!lruvec)
+				continue;
+
+			spin_lock_irq(&lruvec->lru_lock);
+
+			VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
+			VM_WARN_ON_ONCE(!state_is_valid(lruvec));
+
+			lruvec->lrugen.enabled = enabled;
+
+			while (!(enabled ? 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_enabled(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_enabled(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 enabled = caps & BIT(i);
+
+		if (i == LRU_GEN_CORE)
+			lru_gen_change_state(enabled);
+		else if (enabled)
+			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_enabled, store_enabled
+);
+
+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
  ******************************************************************************/
 
@@ -5084,6 +5298,7 @@ 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]);
@@ -5123,6 +5338,9 @@ 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);
 
+	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);