From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/workingset.c | 227 ++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 145 insertions(+), 82 deletions(-)
diff --git a/kernel/mm/workingset.c b/kernel/mm/workingset.c
index 8abfd26..975a4d2 100644
--- a/kernel/mm/workingset.c
+++ b/kernel/mm/workingset.c
@@ -6,6 +6,7 @@
*/
#include <linux/memcontrol.h>
+#include <linux/mm_inline.h>
#include <linux/writeback.h>
#include <linux/shmem_fs.h>
#include <linux/pagemap.h>
@@ -156,24 +157,24 @@
*
* Implementation
*
- * For each node's file LRU lists, a counter for inactive evictions
- * and activations is maintained (node->inactive_age).
+ * For each node's LRU lists, a counter for inactive evictions and
+ * activations is maintained (node->nonresident_age).
*
* On eviction, a snapshot of this counter (along with some bits to
- * identify the node) is stored in the now empty page cache radix tree
+ * identify the node) is stored in the now empty page cache
* slot of the evicted page. This is called a shadow entry.
*
* On cache misses for which there are shadow entries, an eligible
* refault distance will immediately activate the refaulting page.
*/
-#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \
+#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \
1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT)
#define EVICTION_MASK (~0UL >> EVICTION_SHIFT)
/*
* Eviction timestamps need to be able to cover the full range of
- * actionable refaults. However, bits are tight in the radix tree
+ * actionable refaults. However, bits are tight in the xarray
* entry, and after storing the identifier for the lruvec there might
* not be enough left to represent every single actionable refault. In
* that case, we have to sacrifice granularity for distance, and group
@@ -185,22 +186,21 @@
bool workingset)
{
eviction >>= bucket_order;
+ eviction &= EVICTION_MASK;
eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid;
eviction = (eviction << NODES_SHIFT) | pgdat->node_id;
eviction = (eviction << 1) | workingset;
- eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT);
- return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY);
+ return xa_mk_value(eviction);
}
static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat,
unsigned long *evictionp, bool *workingsetp)
{
- unsigned long entry = (unsigned long)shadow;
+ unsigned long entry = xa_to_value(shadow);
int memcgid, nid;
bool workingset;
- entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT;
workingset = entry & 1;
entry >>= 1;
nid = entry & ((1UL << NODES_SHIFT) - 1);
@@ -215,28 +215,58 @@
}
/**
+ * workingset_age_nonresident - age non-resident entries as LRU ages
+ * @lruvec: the lruvec that was aged
+ * @nr_pages: the number of pages to count
+ *
+ * As in-memory pages are aged, non-resident pages need to be aged as
+ * well, in order for the refault distances later on to be comparable
+ * to the in-memory dimensions. This function allows reclaim and LRU
+ * operations to drive the non-resident aging along in parallel.
+ */
+void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages)
+{
+ /*
+ * Reclaiming a cgroup means reclaiming all its children in a
+ * round-robin fashion. That means that each cgroup has an LRU
+ * order that is composed of the LRU orders of its child
+ * cgroups; and every page has an LRU position not just in the
+ * cgroup that owns it, but in all of that group's ancestors.
+ *
+ * So when the physical inactive list of a leaf cgroup ages,
+ * the virtual inactive lists of all its parents, including
+ * the root cgroup's, age as well.
+ */
+ do {
+ atomic_long_add(nr_pages, &lruvec->nonresident_age);
+ } while ((lruvec = parent_lruvec(lruvec)));
+}
+
+/**
* workingset_eviction - note the eviction of a page from memory
- * @mapping: address space the page was backing
+ * @target_memcg: the cgroup that is causing the reclaim
* @page: the page being evicted
*
- * Returns a shadow entry to be stored in @mapping->i_pages in place
+ * Returns a shadow entry to be stored in @page->mapping->i_pages in place
* of the evicted @page so that a later refault can be detected.
*/
-void *workingset_eviction(struct address_space *mapping, struct page *page)
+void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
{
struct pglist_data *pgdat = page_pgdat(page);
- struct mem_cgroup *memcg = page_memcg(page);
- int memcgid = mem_cgroup_id(memcg);
unsigned long eviction;
struct lruvec *lruvec;
+ int memcgid;
/* Page is fully exclusive and pins page->mem_cgroup */
VM_BUG_ON_PAGE(PageLRU(page), page);
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
- eviction = atomic_long_inc_return(&lruvec->inactive_age);
+ lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+ workingset_age_nonresident(lruvec, thp_nr_pages(page));
+ /* XXX: target_memcg can be NULL, go through lruvec */
+ memcgid = mem_cgroup_id(lruvec_memcg(lruvec));
+ eviction = atomic_long_read(&lruvec->nonresident_age);
return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page));
}
@@ -246,13 +276,17 @@
* @shadow: shadow entry of the evicted page
*
* Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the node it was allocated in.
+ * evicted page in the context of the node and the memcg whose memory
+ * pressure caused the eviction.
*/
void workingset_refault(struct page *page, void *shadow)
{
+ bool file = page_is_file_lru(page);
+ struct mem_cgroup *eviction_memcg;
+ struct lruvec *eviction_lruvec;
unsigned long refault_distance;
+ unsigned long workingset_size;
struct pglist_data *pgdat;
- unsigned long active_file;
struct mem_cgroup *memcg;
unsigned long eviction;
struct lruvec *lruvec;
@@ -279,49 +313,78 @@
* would be better if the root_mem_cgroup existed in all
* configurations instead.
*/
- memcg = mem_cgroup_from_id(memcgid);
- if (!mem_cgroup_disabled() && !memcg)
+ eviction_memcg = mem_cgroup_from_id(memcgid);
+ if (!mem_cgroup_disabled() && !eviction_memcg)
goto out;
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
- refault = atomic_long_read(&lruvec->inactive_age);
- active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES);
+ eviction_lruvec = mem_cgroup_lruvec(eviction_memcg, pgdat);
+ refault = atomic_long_read(&eviction_lruvec->nonresident_age);
/*
* Calculate the refault distance
*
* The unsigned subtraction here gives an accurate distance
- * across inactive_age overflows in most cases. There is a
+ * across nonresident_age overflows in most cases. There is a
* special case: usually, shadow entries have a short lifetime
* and are either refaulted or reclaimed along with the inode
* before they get too old. But it is not impossible for the
- * inactive_age to lap a shadow entry in the field, which can
- * then result in a false small refault distance, leading to a
- * false activation should this old entry actually refault
- * again. However, earlier kernels used to deactivate
+ * nonresident_age to lap a shadow entry in the field, which
+ * can then result in a false small refault distance, leading
+ * to a false activation should this old entry actually
+ * refault again. However, earlier kernels used to deactivate
* unconditionally with *every* reclaim invocation for the
* longest time, so the occasional inappropriate activation
* leading to pressure on the active list is not a problem.
*/
refault_distance = (refault - eviction) & EVICTION_MASK;
- inc_lruvec_state(lruvec, WORKINGSET_REFAULT);
+ /*
+ * The activation decision for this page is made at the level
+ * where the eviction occurred, as that is where the LRU order
+ * during page reclaim is being determined.
+ *
+ * However, the cgroup that will own the page is the one that
+ * is actually experiencing the refault event.
+ */
+ memcg = page_memcg(page);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+ inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
/*
* Compare the distance to the existing workingset size. We
- * don't act on pages that couldn't stay resident even if all
- * the memory was available to the page cache.
+ * don't activate pages that couldn't stay resident even if
+ * all the memory was available to the workingset. Whether
+ * workingset competition needs to consider anon or not depends
+ * on having swap.
*/
- if (refault_distance > active_file)
+ workingset_size = lruvec_page_state(eviction_lruvec, NR_ACTIVE_FILE);
+ if (!file) {
+ workingset_size += lruvec_page_state(eviction_lruvec,
+ NR_INACTIVE_FILE);
+ }
+ if (mem_cgroup_get_nr_swap_pages(memcg) > 0) {
+ workingset_size += lruvec_page_state(eviction_lruvec,
+ NR_ACTIVE_ANON);
+ if (file) {
+ workingset_size += lruvec_page_state(eviction_lruvec,
+ NR_INACTIVE_ANON);
+ }
+ }
+ if (refault_distance > workingset_size)
goto out;
SetPageActive(page);
- atomic_long_inc(&lruvec->inactive_age);
- inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE);
+ workingset_age_nonresident(lruvec, thp_nr_pages(page));
+ inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
/* Page was active prior to eviction */
if (workingset) {
SetPageWorkingset(page);
- inc_lruvec_state(lruvec, WORKINGSET_RESTORE);
+ /* XXX: Move to lru_cache_add() when it supports new vs putback */
+ spin_lock_irq(&page_pgdat(page)->lru_lock);
+ lru_note_cost_page(page);
+ spin_unlock_irq(&page_pgdat(page)->lru_lock);
+ inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
}
out:
rcu_read_unlock();
@@ -347,8 +410,8 @@
memcg = page_memcg_rcu(page);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_lruvec(page_pgdat(page), memcg);
- atomic_long_inc(&lruvec->inactive_age);
+ lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page));
+ workingset_age_nonresident(lruvec, thp_nr_pages(page));
out:
rcu_read_unlock();
}
@@ -367,7 +430,7 @@
static struct list_lru shadow_nodes;
-void workingset_update_node(struct radix_tree_node *node)
+void workingset_update_node(struct xa_node *node)
{
/*
* Track non-empty nodes that contain only shadow entries;
@@ -377,12 +440,18 @@
* already where they should be. The list_empty() test is safe
* as node->private_list is protected by the i_pages lock.
*/
- if (node->count && node->count == node->exceptional) {
- if (list_empty(&node->private_list))
+ VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */
+
+ if (node->count && node->count == node->nr_values) {
+ if (list_empty(&node->private_list)) {
list_lru_add(&shadow_nodes, &node->private_list);
+ __inc_lruvec_slab_state(node, WORKINGSET_NODES);
+ }
} else {
- if (!list_empty(&node->private_list))
+ if (!list_empty(&node->private_list)) {
list_lru_del(&shadow_nodes, &node->private_list);
+ __dec_lruvec_slab_state(node, WORKINGSET_NODES);
+ }
}
}
@@ -391,12 +460,12 @@
{
unsigned long max_nodes;
unsigned long nodes;
- unsigned long cache;
+ unsigned long pages;
nodes = list_lru_shrink_count(&shadow_nodes, sc);
/*
- * Approximate a reasonable limit for the radix tree nodes
+ * Approximate a reasonable limit for the nodes
* containing shadow entries. We don't need to keep more
* shadow entries than possible pages on the active list,
* since refault distances bigger than that are dismissed.
@@ -411,20 +480,30 @@
* worst-case density of 1/8th. Below that, not all eligible
* refaults can be detected anymore.
*
- * On 64-bit with 7 radix_tree_nodes per page and 64 slots
+ * On 64-bit with 7 xa_nodes per page and 64 slots
* each, this will reclaim shadow entries when they consume
* ~1.8% of available memory:
*
- * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE
+ * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE
*/
+#ifdef CONFIG_MEMCG
if (sc->memcg) {
- cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
- LRU_ALL_FILE);
- } else {
- cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) +
- node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE);
- }
- max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3);
+ struct lruvec *lruvec;
+ int i;
+
+ lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
+ for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
+ pages += lruvec_page_state_local(lruvec,
+ NR_LRU_BASE + i);
+ pages += lruvec_page_state_local(
+ lruvec, NR_SLAB_RECLAIMABLE_B) >> PAGE_SHIFT;
+ pages += lruvec_page_state_local(
+ lruvec, NR_SLAB_UNRECLAIMABLE_B) >> PAGE_SHIFT;
+ } else
+#endif
+ pages = node_present_pages(sc->nid);
+
+ max_nodes = pages >> (XA_CHUNK_SHIFT - 3);
if (!nodes)
return SHRINK_EMPTY;
@@ -437,27 +516,25 @@
static enum lru_status shadow_lru_isolate(struct list_head *item,
struct list_lru_one *lru,
spinlock_t *lru_lock,
- void *arg)
+ void *arg) __must_hold(lru_lock)
{
+ struct xa_node *node = container_of(item, struct xa_node, private_list);
struct address_space *mapping;
- struct radix_tree_node *node;
- unsigned int i;
int ret;
/*
- * Page cache insertions and deletions synchroneously maintain
+ * Page cache insertions and deletions synchronously maintain
* the shadow node LRU under the i_pages lock and the
* lru_lock. Because the page cache tree is emptied before
* the inode can be destroyed, holding the lru_lock pins any
- * address_space that has radix tree nodes on the LRU.
+ * address_space that has nodes on the LRU.
*
* We can then safely transition to the i_pages lock to
* pin only the address_space of the particular node we want
* to reclaim, take the node off-LRU, and drop the lru_lock.
*/
- node = container_of(item, struct radix_tree_node, private_list);
- mapping = container_of(node->root, struct address_space, i_pages);
+ mapping = container_of(node->array, struct address_space, i_pages);
/* Coming from the list, invert the lock order */
if (!xa_trylock(&mapping->i_pages)) {
@@ -467,6 +544,8 @@
}
list_lru_isolate(lru, item);
+ __dec_lruvec_slab_state(node, WORKINGSET_NODES);
+
spin_unlock(lru_lock);
/*
@@ -474,29 +553,13 @@
* no pages, so we expect to be able to remove them all and
* delete and free the empty node afterwards.
*/
- if (WARN_ON_ONCE(!node->exceptional))
+ if (WARN_ON_ONCE(!node->nr_values))
goto out_invalid;
- if (WARN_ON_ONCE(node->count != node->exceptional))
+ if (WARN_ON_ONCE(node->count != node->nr_values))
goto out_invalid;
- for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
- if (node->slots[i]) {
- if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i])))
- goto out_invalid;
- if (WARN_ON_ONCE(!node->exceptional))
- goto out_invalid;
- if (WARN_ON_ONCE(!mapping->nrexceptional))
- goto out_invalid;
- node->slots[i] = NULL;
- node->exceptional--;
- node->count--;
- mapping->nrexceptional--;
- }
- }
- if (WARN_ON_ONCE(node->exceptional))
- goto out_invalid;
- inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM);
- __radix_tree_delete_node(&mapping->i_pages, node,
- workingset_lookup_update(mapping));
+ mapping->nrexceptional -= node->nr_values;
+ xa_delete_node(node, workingset_update_node);
+ __inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
out_invalid:
xa_unlock_irq(&mapping->i_pages);
@@ -518,7 +581,7 @@
static struct shrinker workingset_shadow_shrinker = {
.count_objects = count_shadow_nodes,
.scan_objects = scan_shadow_nodes,
- .seeks = DEFAULT_SEEKS,
+ .seeks = 0, /* ->count reports only fully expendable nodes */
.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE,
};
@@ -543,7 +606,7 @@
* double the initial memory by using totalram_pages as-is.
*/
timestamp_bits = BITS_PER_LONG - EVICTION_SHIFT;
- max_order = fls_long(totalram_pages - 1);
+ max_order = fls_long(totalram_pages() - 1);
if (max_order > timestamp_bits)
bucket_order = max_order - timestamp_bits;
pr_info("workingset: timestamp_bits=%d max_order=%d bucket_order=%u\n",
--
Gitblit v1.6.2