Add /sys/kernel/mm/lru_gen/enabled to enable and disable the
multigenerational lru at runtime.
Add /sys/kernel/mm/lru_gen/min_ttl_ms to protect the working set of a
given number of milliseconds. The OOM killer is invoked if this
working set cannot be kept in memory.
Add /sys/kernel/debug/lru_gen to monitor the multigenerational lru and
invoke the aging and the eviction. This file has the following output:
memcg memcg_id memcg_path
node node_id
min_gen birth_time anon_size file_size
...
max_gen birth_time anon_size file_size
min_gen is the oldest generation number and max_gen is the youngest
generation number. birth_time is in milliseconds. anon_size and
file_size are in pages.
This file takes the following input:
+ memcg_id node_id max_gen [swappiness] [use_bloom_filter]
- memcg_id node_id min_gen [swappiness] [nr_to_reclaim]
The first command line invokes the aging, which scans PTEs for
accessed pages and then creates the next generation max_gen+1. A swap
file and a non-zero swappiness, which overrides vm.swappiness, are
required to scan PTEs mapping anon pages. The second command line
invokes the eviction, which evicts generations less than or equal to
min_gen. min_gen should be less than max_gen-1 as max_gen and
max_gen-1 are not fully aged and therefore cannot be evicted.
Setting nr_to_reclaim to N limits the number of pages to evict.
Setting use_bloom_filter to 0 overrides the default behavior which
only scans PTE tables found populated. Multiple command lines are
supported, as is concatenation with delimiters "," and ";".
Signed-off-by: Yu Zhao <yuzhao@xxxxxxxxxx>
Tested-by: Konstantin Kharlamov <Hi-Angel@xxxxxxxxx>
---
include/linux/nodemask.h | 1 +
mm/vmscan.c | 415 +++++++++++++++++++++++++++++++++++++++
2 files changed, 416 insertions(+)
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 567c3ddba2c4..90840c459abc 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -486,6 +486,7 @@ static inline int num_node_state(enum node_states state)
#define first_online_node 0
#define first_memory_node 0
#define next_online_node(nid) (MAX_NUMNODES)
+#define next_memory_node(nid) (MAX_NUMNODES)
#define nr_node_ids 1U
#define nr_online_nodes 1U
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c5ac8e8b610f..7c3a49173902 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -53,6 +53,8 @@
#include <linux/memory.h>
#include <linux/pagewalk.h>
#include <linux/shmem_fs.h>
+#include <linux/ctype.h>
+#include <linux/debugfs.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
@@ -4875,6 +4877,413 @@ void lru_gen_change_state(bool enable, bool main, bool swap)
mem_hotplug_done();
}
+/******************************************************************************
+ * sysfs interface
+ ******************************************************************************/
+
+static ssize_t show_min_ttl(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+ return sprintf(buf, "%u\n", jiffies_to_msecs(READ_ONCE(lru_gen_min_ttl)));
+}
+
+static ssize_t store_min_ttl(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t len)
+{
+ unsigned int msecs;
+
+ if (kstrtouint(buf, 10, &msecs))
+ return -EINVAL;
+
+ WRITE_ONCE(lru_gen_min_ttl, msecs_to_jiffies(msecs));
+
+ return len;
+}
+
+static struct kobj_attribute lru_gen_min_ttl_attr = __ATTR(
+ min_ttl_ms, 0644, show_min_ttl, store_min_ttl
+);
+
+static ssize_t show_enable(struct kobject *kobj, struct kobj_attribute *attr, char *buf)
+{
+ return snprintf(buf, PAGE_SIZE, "%d\n", lru_gen_enabled());
+}
+
+static ssize_t store_enable(struct kobject *kobj, struct kobj_attribute *attr,
+ const char *buf, size_t len)
+{
+ bool enable;
+
+ if (kstrtobool(buf, &enable))
+ return -EINVAL;
+
+ lru_gen_change_state(enable, true, false);
+
+ 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_min_ttl_attr.attr,
+ &lru_gen_enabled_attr.attr,
+ NULL
+};
+
+static struct attribute_group lru_gen_attr_group = {
+ .name = "lru_gen",
+ .attrs = lru_gen_attrs,
+};
+
+/******************************************************************************
+ * debugfs interface
+ ******************************************************************************/
+
+static void *lru_gen_seq_start(struct seq_file *m, loff_t *pos)
+{
+ struct mem_cgroup *memcg;
+ loff_t nr_to_skip = *pos;
+
+ m->private = kvmalloc(PATH_MAX, GFP_KERNEL);
+ if (!m->private)
+ return ERR_PTR(-ENOMEM);
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ int nid;
+
+ for_each_node_state(nid, N_MEMORY) {
+ if (!nr_to_skip--)
+ return get_lruvec(nid, memcg);
+ }
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+ return NULL;
+}
+
+static void lru_gen_seq_stop(struct seq_file *m, void *v)
+{
+ if (!IS_ERR_OR_NULL(v))
+ mem_cgroup_iter_break(NULL, lruvec_memcg(v));
+
+ kvfree(m->private);
+ m->private = NULL;
+}
+
+static void *lru_gen_seq_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ int nid = lruvec_pgdat(v)->node_id;
+ struct mem_cgroup *memcg = lruvec_memcg(v);
+
+ ++*pos;
+
+ nid = next_memory_node(nid);
+ if (nid == MAX_NUMNODES) {
+ memcg = mem_cgroup_iter(NULL, memcg, NULL);
+ if (!memcg)
+ return NULL;
+
+ nid = first_memory_node;
+ }
+
+ return get_lruvec(nid, memcg);
+}
+
+static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
+ unsigned long max_seq, unsigned long *min_seq,
+ unsigned long seq)
+{
+ int i;
+ int type, tier;
+ int hist = lru_hist_from_seq(seq);
+ struct lrugen *lrugen = &lruvec->evictable;
+
+ for (tier = 0; tier < MAX_NR_TIERS; tier++) {
+ seq_printf(m, " %10d", tier);
+ for (type = 0; type < ANON_AND_FILE; type++) {
+ unsigned long n[3] = {};
+
+ if (seq == max_seq) {
+ n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
+ n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
+
+ seq_printf(m, " %10luR %10luT %10lu ", n[0], n[1], n[2]);
+ } else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
+ n[0] = atomic_long_read(&lrugen->refaulted[hist][type][tier]);
+ n[1] = atomic_long_read(&lrugen->evicted[hist][type][tier]);
+ if (tier)
+ n[2] = READ_ONCE(lrugen->protected[hist][type][tier - 1]);
+
+ seq_printf(m, " %10lur %10lue %10lup", n[0], n[1], n[2]);
+ } else
+ seq_puts(m, " 0 0 0 ");
+ }
+ seq_putc(m, '\n');
+ }
+
+ seq_puts(m, " ");
+ for (i = 0; i < NR_MM_STATS; i++) {
+ if (seq == max_seq && NR_HIST_GENS == 1)
+ seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_walk.stats[hist][i]),
+ toupper(MM_STAT_CODES[i]));
+ else if (seq != max_seq && NR_HIST_GENS > 1)
+ seq_printf(m, " %10lu%c", READ_ONCE(lruvec->mm_walk.stats[hist][i]),
+ MM_STAT_CODES[i]);
+ else
+ seq_puts(m, " 0 ");
+ }
+ seq_putc(m, '\n');
+}
+
+static int lru_gen_seq_show(struct seq_file *m, void *v)
+{
+ unsigned long seq;
+ bool full = !debugfs_real_fops(m->file)->write;
+ struct lruvec *lruvec = v;
+ struct lrugen *lrugen = &lruvec->evictable;
+ int nid = lruvec_pgdat(lruvec)->node_id;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MAX_SEQ(lruvec);
+ DEFINE_MIN_SEQ(lruvec);
+
+ if (nid == first_memory_node) {
+ const char *path = memcg ? m->private : "";
+
+#ifdef CONFIG_MEMCG
+ if (memcg)
+ cgroup_path(memcg->css.cgroup, m->private, PATH_MAX);
+#endif
+ seq_printf(m, "memcg %5hu %s\n", mem_cgroup_id(memcg), path);
+ }
+
+ seq_printf(m, " node %5d\n", nid);
+
+ if (!full)
+ seq = min_seq[0];
+ else if (max_seq >= MAX_NR_GENS)
+ seq = max_seq - MAX_NR_GENS + 1;
+ else
+ seq = 0;
+
+ for (; seq <= max_seq; seq++) {
+ int gen, type, zone;
+ unsigned int msecs;
+
+ gen = lru_gen_from_seq(seq);
+ msecs = jiffies_to_msecs(jiffies - READ_ONCE(lrugen->timestamps[gen]));
+
+ seq_printf(m, " %10lu %10u", seq, msecs);
+
+ for (type = 0; type < ANON_AND_FILE; type++) {
+ long size = 0;
+
+ if (seq < min_seq[type]) {
+ seq_puts(m, " -0 ");
+ continue;
+ }
+
+ for (zone = 0; zone < MAX_NR_ZONES; zone++)
+ size += READ_ONCE(lrugen->sizes[gen][type][zone]);
+
+ seq_printf(m, " %10lu ", max(size, 0L));
+ }
+
+ seq_putc(m, '\n');
+
+ if (full)
+ lru_gen_seq_show_full(m, lruvec, max_seq, min_seq, seq);
+ }
+
+ return 0;
+}
+
+static const struct seq_operations lru_gen_seq_ops = {
+ .start = lru_gen_seq_start,
+ .stop = lru_gen_seq_stop,
+ .next = lru_gen_seq_next,
+ .show = lru_gen_seq_show,
+};
+
+static int run_aging(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
+ unsigned long seq, bool use_filter)
+{
+ DEFINE_MAX_SEQ(lruvec);
+
+ if (seq == max_seq)
+ try_to_inc_max_seq(lruvec, sc, swappiness, max_seq, use_filter);
+
+ return seq > max_seq ? -EINVAL : 0;
+}
+
+static int run_eviction(struct lruvec *lruvec, struct scan_control *sc, int swappiness,
+ unsigned long seq, unsigned long nr_to_reclaim)
+{
+ struct blk_plug plug;
+ int err = -EINTR;
+ DEFINE_MAX_SEQ(lruvec);
+
+ if (seq >= max_seq - 1)
+ return -EINVAL;
+
+ sc->nr_reclaimed = 0;
+
+ blk_start_plug(&plug);
+
+ while (!signal_pending(current)) {
+ DEFINE_MIN_SEQ(lruvec);
+
+ if (seq < min_seq[!swappiness] || sc->nr_reclaimed >= nr_to_reclaim ||
+ !evict_pages(lruvec, sc, swappiness)) {
+ err = 0;
+ break;
+ }
+
+ cond_resched();
+ }
+
+ blk_finish_plug(&plug);
+
+ return err;
+}
+
+static int run_cmd(char cmd, int memcg_id, int nid, struct scan_control *sc,
+ int swappiness, unsigned long seq, unsigned long opt)
+{
+ struct lruvec *lruvec;
+ int err = -EINVAL;
+ struct mem_cgroup *memcg = NULL;
+
+ if (!mem_cgroup_disabled()) {
+ rcu_read_lock();
+ memcg = mem_cgroup_from_id(memcg_id);
+#ifdef CONFIG_MEMCG
+ if (memcg && !css_tryget(&memcg->css))
+ memcg = NULL;
+#endif
+ rcu_read_unlock();
+
+ if (!memcg)
+ goto done;
+ }
+ if (memcg_id != mem_cgroup_id(memcg))
+ goto done;
+
+ if (nid < 0 || nid >= MAX_NUMNODES || !node_state(nid, N_MEMORY))
+ goto done;
+
+ lruvec = get_lruvec(nid, memcg);
+
+ if (swappiness < 0)
+ swappiness = get_swappiness(memcg);
+ else if (swappiness > 200)
+ goto done;
+
+ switch (cmd) {
+ case '+':
+ err = run_aging(lruvec, sc, swappiness, seq, opt);
+ break;
+ case '-':
+ err = run_eviction(lruvec, sc, swappiness, seq, opt);
+ break;
+ }
+done:
+ mem_cgroup_put(memcg);
+
+ return err;
+}
+
+static ssize_t lru_gen_seq_write(struct file *file, const char __user *src,
+ size_t len, loff_t *pos)
+{
+ void *buf;
+ char *cur, *next;
+ unsigned int flags;
+ int err = 0;
+ struct scan_control sc = {
+ .may_writepage = 1,
+ .may_unmap = 1,
+ .may_swap = 1,
+ .reclaim_idx = MAX_NR_ZONES - 1,
+ .gfp_mask = GFP_KERNEL,
+ };
+
+ buf = kvmalloc(len + 1, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, src, len)) {
+ kvfree(buf);
+ return -EFAULT;
+ }
+
+ next = buf;
+ next[len] = '\0';
+
+ sc.reclaim_state.mm_walk_args = alloc_mm_walk_args();
+ if (!sc.reclaim_state.mm_walk_args) {
+ kvfree(buf);
+ return -ENOMEM;
+ }
+
+ flags = memalloc_noreclaim_save();
+ set_task_reclaim_state(current, &sc.reclaim_state);
+
+ while ((cur = strsep(&next, ",;\n"))) {
+ int n;
+ int end;
+ char cmd;
+ unsigned int memcg_id;
+ unsigned int nid;
+ unsigned long seq;
+ unsigned int swappiness = -1;
+ unsigned long opt = -1;
+
+ cur = skip_spaces(cur);
+ if (!*cur)
+ continue;
+
+ n = sscanf(cur, "%c %u %u %lu %n %u %n %lu %n", &cmd, &memcg_id, &nid,
+ &seq, &end, &swappiness, &end, &opt, &end);
+ if (n < 4 || cur[end]) {
+ err = -EINVAL;
+ break;
+ }
+
+ err = run_cmd(cmd, memcg_id, nid, &sc, swappiness, seq, opt);
+ if (err)
+ break;
+ }
+
+ set_task_reclaim_state(current, NULL);
+ memalloc_noreclaim_restore(flags);
+
+ free_mm_walk_args(sc.reclaim_state.mm_walk_args);
+ kvfree(buf);
+
+ return err ? : len;
+}
+
+static int lru_gen_seq_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &lru_gen_seq_ops);
+}
+
+static const struct file_operations lru_gen_rw_fops = {
+ .open = lru_gen_seq_open,
+ .read = seq_read,
+ .write = lru_gen_seq_write,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static const struct file_operations lru_gen_ro_fops = {
+ .open = lru_gen_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
/******************************************************************************
* initialization
******************************************************************************/
@@ -4945,6 +5354,12 @@ 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");
+
+ debugfs_create_file("lru_gen", 0644, NULL, NULL, &lru_gen_rw_fops);
+ debugfs_create_file("lru_gen_full", 0444, NULL, NULL, &lru_gen_ro_fops);
+
return 0;
};
late_initcall(init_lru_gen);
--
2.34.0.rc0.344.g81b53c2807-goog
