Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/workingset.c b/mm/workingset.c
index c963831..975a4d2 100644
--- a/mm/workingset.c
+++ b/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>
@@ -156,8 +157,8 @@
*
* 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
@@ -214,27 +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
+ * @target_memcg: the cgroup that is causing the reclaim
* @page: the page being evicted
*
* 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 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));
}
@@ -244,13 +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;
@@ -277,49 +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();
@@ -345,8 +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();
}
@@ -426,12 +491,14 @@
struct lruvec *lruvec;
int i;
- lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg);
+ 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);
- pages += lruvec_page_state_local(lruvec, NR_SLAB_UNRECLAIMABLE);
+ 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);
@@ -452,12 +519,11 @@
void *arg) __must_hold(lru_lock)
{
struct xa_node *node = container_of(item, struct xa_node, private_list);
- XA_STATE(xas, node->array, 0);
struct address_space *mapping;
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
@@ -492,15 +558,7 @@
if (WARN_ON_ONCE(node->count != node->nr_values))
goto out_invalid;
mapping->nrexceptional -= node->nr_values;
- xas.xa_node = xa_parent_locked(&mapping->i_pages, node);
- xas.xa_offset = node->offset;
- xas.xa_shift = node->shift + XA_CHUNK_SHIFT;
- xas_set_update(&xas, workingset_update_node);
- /*
- * We could store a shadow entry here which was the minimum of the
- * shadow entries we were tracking ...
- */
- xas_store(&xas, NULL);
+ xa_delete_node(node, workingset_update_node);
__inc_lruvec_slab_state(node, WORKINGSET_NODERECLAIM);
out_invalid: