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/vmscan.c | 2027 +++++++++++++++++++++++++++++++++--------------------------
1 files changed, 1,133 insertions(+), 894 deletions(-)
diff --git a/kernel/mm/vmscan.c b/kernel/mm/vmscan.c
index 17de2f3..f94f52e 100644
--- a/kernel/mm/vmscan.c
+++ b/kernel/mm/vmscan.c
@@ -63,6 +63,12 @@
#define CREATE_TRACE_POINTS
#include <trace/events/vmscan.h>
+#undef CREATE_TRACE_POINTS
+#include <trace/hooks/vmscan.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(mm_vmscan_direct_reclaim_begin);
+EXPORT_TRACEPOINT_SYMBOL_GPL(mm_vmscan_direct_reclaim_end);
+
struct scan_control {
/* How many pages shrink_list() should reclaim */
unsigned long nr_to_reclaim;
@@ -79,6 +85,19 @@
*/
struct mem_cgroup *target_mem_cgroup;
+ /*
+ * Scan pressure balancing between anon and file LRUs
+ */
+ unsigned long anon_cost;
+ unsigned long file_cost;
+
+ /* Can active pages be deactivated as part of reclaim? */
+#define DEACTIVATE_ANON 1
+#define DEACTIVATE_FILE 2
+ unsigned int may_deactivate:2;
+ unsigned int force_deactivate:1;
+ unsigned int skipped_deactivate:1;
+
/* Writepage batching in laptop mode; RECLAIM_WRITE */
unsigned int may_writepage:1;
@@ -89,9 +108,12 @@
unsigned int may_swap:1;
/*
- * Cgroups are not reclaimed below their configured memory.low,
- * unless we threaten to OOM. If any cgroups are skipped due to
- * memory.low and nothing was reclaimed, go back for memory.low.
+ * Cgroup memory below memory.low is protected as long as we
+ * don't threaten to OOM. If any cgroup is reclaimed at
+ * reduced force or passed over entirely due to its memory.low
+ * setting (memcg_low_skipped), and nothing is reclaimed as a
+ * result, then go back for one more cycle that reclaims the protected
+ * memory (memcg_low_reclaim) to avert OOM.
*/
unsigned int memcg_low_reclaim:1;
unsigned int memcg_low_skipped:1;
@@ -100,6 +122,12 @@
/* One of the zones is ready for compaction */
unsigned int compaction_ready:1;
+
+ /* There is easily reclaimable cold cache in the current node */
+ unsigned int cache_trim_mode:1;
+
+ /* The file pages on the current node are dangerously low */
+ unsigned int file_is_tiny:1;
/* Allocation order */
s8 order;
@@ -128,21 +156,10 @@
unsigned int file_taken;
unsigned int taken;
} nr;
-};
-#ifdef ARCH_HAS_PREFETCH
-#define prefetch_prev_lru_page(_page, _base, _field) \
- do { \
- if ((_page)->lru.prev != _base) { \
- struct page *prev; \
- \
- prev = lru_to_page(&(_page->lru)); \
- prefetch(&prev->_field); \
- } \
- } while (0)
-#else
-#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
-#endif
+ /* for recording the reclaimed slab by now */
+ struct reclaim_state reclaim_state;
+};
#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_page(_page, _base, _field) \
@@ -159,20 +176,43 @@
#endif
/*
- * From 0 .. 100. Higher means more swappy.
+ * From 0 .. 200. Higher means more swappy.
*/
int vm_swappiness = 60;
-/*
- * The total number of pages which are beyond the high watermark within all
- * zones.
- */
-unsigned long vm_total_pages;
+
+#define DEF_KSWAPD_THREADS_PER_NODE 1
+static int kswapd_threads = DEF_KSWAPD_THREADS_PER_NODE;
+static int __init kswapd_per_node_setup(char *str)
+{
+ int tmp;
+
+ if (kstrtoint(str, 0, &tmp) < 0)
+ return 0;
+
+ if (tmp > MAX_KSWAPD_THREADS || tmp <= 0)
+ return 0;
+
+ kswapd_threads = tmp;
+ return 1;
+}
+__setup("kswapd_per_node=", kswapd_per_node_setup);
+
+static void set_task_reclaim_state(struct task_struct *task,
+ struct reclaim_state *rs)
+{
+ /* Check for an overwrite */
+ WARN_ON_ONCE(rs && task->reclaim_state);
+
+ /* Check for the nulling of an already-nulled member */
+ WARN_ON_ONCE(!rs && !task->reclaim_state);
+
+ task->reclaim_state = rs;
+}
static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);
-#ifdef CONFIG_MEMCG_KMEM
-
+#ifdef CONFIG_MEMCG
/*
* We allow subsystems to populate their shrinker-related
* LRU lists before register_shrinker_prepared() is called
@@ -224,25 +264,14 @@
idr_remove(&shrinker_idr, id);
up_write(&shrinker_rwsem);
}
-#else /* CONFIG_MEMCG_KMEM */
-static int prealloc_memcg_shrinker(struct shrinker *shrinker)
-{
- return 0;
-}
-static void unregister_memcg_shrinker(struct shrinker *shrinker)
+static bool cgroup_reclaim(struct scan_control *sc)
{
-}
-#endif /* CONFIG_MEMCG_KMEM */
-
-#ifdef CONFIG_MEMCG
-static bool global_reclaim(struct scan_control *sc)
-{
- return !sc->target_mem_cgroup;
+ return sc->target_mem_cgroup;
}
/**
- * sane_reclaim - is the usual dirty throttling mechanism operational?
+ * writeback_throttling_sane - is the usual dirty throttling mechanism available?
* @sc: scan_control in question
*
* The normal page dirty throttling mechanism in balance_dirty_pages() is
@@ -254,11 +283,9 @@
* This function tests whether the vmscan currently in progress can assume
* that the normal dirty throttling mechanism is operational.
*/
-static bool sane_reclaim(struct scan_control *sc)
+static bool writeback_throttling_sane(struct scan_control *sc)
{
- struct mem_cgroup *memcg = sc->target_mem_cgroup;
-
- if (!memcg)
+ if (!cgroup_reclaim(sc))
return true;
#ifdef CONFIG_CGROUP_WRITEBACK
if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
@@ -266,50 +293,24 @@
#endif
return false;
}
-
-static void set_memcg_congestion(pg_data_t *pgdat,
- struct mem_cgroup *memcg,
- bool congested)
-{
- struct mem_cgroup_per_node *mn;
-
- if (!memcg)
- return;
-
- mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
- WRITE_ONCE(mn->congested, congested);
-}
-
-static bool memcg_congested(pg_data_t *pgdat,
- struct mem_cgroup *memcg)
-{
- struct mem_cgroup_per_node *mn;
-
- mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
- return READ_ONCE(mn->congested);
-
-}
#else
-static bool global_reclaim(struct scan_control *sc)
+static int prealloc_memcg_shrinker(struct shrinker *shrinker)
{
- return true;
+ return 0;
}
-static bool sane_reclaim(struct scan_control *sc)
-{
- return true;
-}
-
-static inline void set_memcg_congestion(struct pglist_data *pgdat,
- struct mem_cgroup *memcg, bool congested)
+static void unregister_memcg_shrinker(struct shrinker *shrinker)
{
}
-static inline bool memcg_congested(struct pglist_data *pgdat,
- struct mem_cgroup *memcg)
+static bool cgroup_reclaim(struct scan_control *sc)
{
return false;
+}
+static bool writeback_throttling_sane(struct scan_control *sc)
+{
+ return true;
}
#endif
@@ -339,31 +340,21 @@
*/
unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx)
{
- unsigned long lru_size;
+ unsigned long size = 0;
int zid;
- if (!mem_cgroup_disabled())
- lru_size = mem_cgroup_get_lru_size(lruvec, lru);
- else
- lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
-
- for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) {
+ for (zid = 0; zid <= zone_idx && zid < MAX_NR_ZONES; zid++) {
struct zone *zone = &lruvec_pgdat(lruvec)->node_zones[zid];
- unsigned long size;
if (!managed_zone(zone))
continue;
if (!mem_cgroup_disabled())
- size = mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
+ size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid);
else
- size = zone_page_state(&lruvec_pgdat(lruvec)->node_zones[zid],
- NR_ZONE_LRU_BASE + lru);
- lru_size -= min(size, lru_size);
+ size += zone_page_state(zone, NR_ZONE_LRU_BASE + lru);
}
-
- return lru_size;
-
+ return size;
}
/*
@@ -371,7 +362,7 @@
*/
int prealloc_shrinker(struct shrinker *shrinker)
{
- size_t size = sizeof(*shrinker->nr_deferred);
+ unsigned int size = sizeof(*shrinker->nr_deferred);
if (shrinker->flags & SHRINKER_NUMA_AWARE)
size *= nr_node_ids;
@@ -409,7 +400,7 @@
{
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
if (shrinker->flags & SHRINKER_MEMCG_AWARE)
idr_replace(&shrinker_idr, shrinker, shrinker->id);
#endif
@@ -475,13 +466,22 @@
nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
total_scan = nr;
- delta = freeable >> priority;
- delta *= 4;
- do_div(delta, shrinker->seeks);
+ if (shrinker->seeks) {
+ delta = freeable >> priority;
+ delta *= 4;
+ do_div(delta, shrinker->seeks);
+ } else {
+ /*
+ * These objects don't require any IO to create. Trim
+ * them aggressively under memory pressure to keep
+ * them from causing refetches in the IO caches.
+ */
+ delta = freeable / 2;
+ }
total_scan += delta;
if (total_scan < 0) {
- pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
+ pr_err("shrink_slab: %pS negative objects to delete nr=%ld\n",
shrinker->scan_objects, total_scan);
total_scan = freeable;
next_deferred = nr;
@@ -567,7 +567,7 @@
return freed;
}
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
@@ -575,7 +575,7 @@
unsigned long ret, freed = 0;
int i;
- if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
+ if (!mem_cgroup_online(memcg))
return 0;
if (!down_read_trylock(&shrinker_rwsem))
@@ -600,6 +600,11 @@
clear_bit(i, map->map);
continue;
}
+
+ /* Call non-slab shrinkers even though kmem is disabled */
+ if (!memcg_kmem_enabled() &&
+ !(shrinker->flags & SHRINKER_NONSLAB))
+ continue;
ret = do_shrink_slab(&sc, shrinker, priority);
if (ret == SHRINK_EMPTY) {
@@ -637,13 +642,13 @@
up_read(&shrinker_rwsem);
return freed;
}
-#else /* CONFIG_MEMCG_KMEM */
+#else /* CONFIG_MEMCG */
static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg, int priority)
{
return 0;
}
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG */
/**
* shrink_slab - shrink slab caches
@@ -665,12 +670,17 @@
*
* Returns the number of reclaimed slab objects.
*/
-static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
+unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
int priority)
{
unsigned long ret, freed = 0;
struct shrinker *shrinker;
+ bool bypass = false;
+
+ trace_android_vh_shrink_slab_bypass(gfp_mask, nid, memcg, priority, &bypass);
+ if (bypass)
+ return 0;
/*
* The root memcg might be allocated even though memcg is disabled
@@ -698,7 +708,7 @@
freed += ret;
/*
* Bail out if someone want to register a new shrinker to
- * prevent the regsitration from being stalled for long periods
+ * prevent the registration from being stalled for long periods
* by parallel ongoing shrinking.
*/
if (rwsem_is_contended(&shrinker_rwsem)) {
@@ -712,6 +722,7 @@
cond_resched();
return freed;
}
+EXPORT_SYMBOL_GPL(shrink_slab);
void drop_slab_node(int nid)
{
@@ -719,6 +730,9 @@
do {
struct mem_cgroup *memcg = NULL;
+
+ if (fatal_signal_pending(current))
+ return;
freed = 0;
memcg = mem_cgroup_iter(NULL, NULL, NULL);
@@ -740,15 +754,14 @@
{
/*
* A freeable page cache page is referenced only by the caller
- * that isolated the page, the page cache radix tree and
- * optional buffer heads at page->private.
+ * that isolated the page, the page cache and optional buffer
+ * heads at page->private.
*/
- int radix_pins = PageTransHuge(page) && PageSwapCache(page) ?
- HPAGE_PMD_NR : 1;
- return page_count(page) - page_has_private(page) == 1 + radix_pins;
+ int page_cache_pins = thp_nr_pages(page);
+ return page_count(page) - page_has_private(page) == 1 + page_cache_pins;
}
-static int may_write_to_inode(struct inode *inode, struct scan_control *sc)
+static int may_write_to_inode(struct inode *inode)
{
if (current->flags & PF_SWAPWRITE)
return 1;
@@ -796,8 +809,7 @@
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
-static pageout_t pageout(struct page *page, struct address_space *mapping,
- struct scan_control *sc)
+static pageout_t pageout(struct page *page, struct address_space *mapping)
{
/*
* If the page is dirty, only perform writeback if that write
@@ -833,7 +845,7 @@
}
if (mapping->a_ops->writepage == NULL)
return PAGE_ACTIVATE;
- if (!may_write_to_inode(mapping->host, sc))
+ if (!may_write_to_inode(mapping->host))
return PAGE_KEEP;
if (clear_page_dirty_for_io(page)) {
@@ -872,10 +884,11 @@
* gets returned with a refcount of 0.
*/
static int __remove_mapping(struct address_space *mapping, struct page *page,
- bool reclaimed)
+ bool reclaimed, struct mem_cgroup *target_memcg)
{
unsigned long flags;
int refcount;
+ void *shadow = NULL;
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
@@ -906,10 +919,7 @@
* Note that if SetPageDirty is always performed via set_page_dirty,
* and thus under the i_pages lock, then this ordering is not required.
*/
- if (unlikely(PageTransHuge(page)) && PageSwapCache(page))
- refcount = 1 + HPAGE_PMD_NR;
- else
- refcount = 2;
+ refcount = 1 + compound_nr(page);
if (!page_ref_freeze(page, refcount))
goto cannot_free;
/* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */
@@ -921,12 +931,13 @@
if (PageSwapCache(page)) {
swp_entry_t swap = { .val = page_private(page) };
mem_cgroup_swapout(page, swap);
- __delete_from_swap_cache(page);
+ if (reclaimed && !mapping_exiting(mapping))
+ shadow = workingset_eviction(page, target_memcg);
+ __delete_from_swap_cache(page, swap, shadow);
xa_unlock_irqrestore(&mapping->i_pages, flags);
put_swap_page(page, swap);
} else {
void (*freepage)(struct page *);
- void *shadow = NULL;
freepage = mapping->a_ops->freepage;
/*
@@ -934,7 +945,7 @@
* order to detect refaults, thus thrashing, later on.
*
* But don't store shadows in an address space that is
- * already exiting. This is not just an optizimation,
+ * already exiting. This is not just an optimization,
* inode reclaim needs to empty out the radix tree or
* the nodes are lost. Don't plant shadows behind its
* back.
@@ -945,9 +956,9 @@
* exceptional entries and shadow exceptional entries in the
* same address_space.
*/
- if (reclaimed && page_is_file_cache(page) &&
+ if (reclaimed && page_is_file_lru(page) &&
!mapping_exiting(mapping) && !dax_mapping(mapping))
- shadow = workingset_eviction(mapping, page);
+ shadow = workingset_eviction(page, target_memcg);
__delete_from_page_cache(page, shadow);
xa_unlock_irqrestore(&mapping->i_pages, flags);
@@ -970,7 +981,7 @@
*/
int remove_mapping(struct address_space *mapping, struct page *page)
{
- if (__remove_mapping(mapping, page, false)) {
+ if (__remove_mapping(mapping, page, false, NULL)) {
/*
* Unfreezing the refcount with 1 rather than 2 effectively
* drops the pagecache ref for us without requiring another
@@ -1009,11 +1020,24 @@
{
int referenced_ptes, referenced_page;
unsigned long vm_flags;
+ bool should_protect = false;
+ bool trylock_fail = false;
+ int ret = 0;
+ trace_android_vh_page_should_be_protected(page, &should_protect);
+ if (unlikely(should_protect))
+ return PAGEREF_ACTIVATE;
+
+ trace_android_vh_page_trylock_set(page);
+ trace_android_vh_check_page_look_around_ref(page, &ret);
+ if (ret)
+ return ret;
referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
&vm_flags);
referenced_page = TestClearPageReferenced(page);
-
+ trace_android_vh_page_trylock_get_result(page, &trylock_fail);
+ if (trylock_fail)
+ return PAGEREF_KEEP;
/*
* Mlock lost the isolation race with us. Let try_to_unmap()
* move the page to the unevictable list.
@@ -1021,9 +1045,11 @@
if (vm_flags & VM_LOCKED)
return PAGEREF_RECLAIM;
+ /* rmap lock contention: rotate */
+ if (referenced_ptes == -1)
+ return PAGEREF_KEEP;
+
if (referenced_ptes) {
- if (PageSwapBacked(page))
- return PAGEREF_ACTIVATE;
/*
* All mapped pages start out with page table
* references from the instantiating fault, so we need
@@ -1046,7 +1072,7 @@
/*
* Activate file-backed executable pages after first usage.
*/
- if (vm_flags & VM_EXEC)
+ if ((vm_flags & VM_EXEC) && !PageSwapBacked(page))
return PAGEREF_ACTIVATE;
return PAGEREF_KEEP;
@@ -1069,7 +1095,7 @@
* Anonymous pages are not handled by flushers and must be written
* from reclaim context. Do not stall reclaim based on them
*/
- if (!page_is_file_cache(page) ||
+ if (!page_is_file_lru(page) ||
(PageAnon(page) && !PageSwapBacked(page))) {
*dirty = false;
*writeback = false;
@@ -1092,33 +1118,27 @@
/*
* shrink_page_list() returns the number of reclaimed pages
*/
-static unsigned long shrink_page_list(struct list_head *page_list,
- struct pglist_data *pgdat,
- struct scan_control *sc,
- enum ttu_flags ttu_flags,
- struct reclaim_stat *stat,
- bool force_reclaim)
+static unsigned int shrink_page_list(struct list_head *page_list,
+ struct pglist_data *pgdat,
+ struct scan_control *sc,
+ struct reclaim_stat *stat,
+ bool ignore_references)
{
LIST_HEAD(ret_pages);
LIST_HEAD(free_pages);
- int pgactivate = 0;
- unsigned nr_unqueued_dirty = 0;
- unsigned nr_dirty = 0;
- unsigned nr_congested = 0;
- unsigned nr_reclaimed = 0;
- unsigned nr_writeback = 0;
- unsigned nr_immediate = 0;
- unsigned nr_ref_keep = 0;
- unsigned nr_unmap_fail = 0;
+ unsigned int nr_reclaimed = 0;
+ unsigned int pgactivate = 0;
+ bool page_trylock_result;
+ memset(stat, 0, sizeof(*stat));
cond_resched();
while (!list_empty(page_list)) {
struct address_space *mapping;
struct page *page;
- int may_enter_fs;
- enum page_references references = PAGEREF_RECLAIM_CLEAN;
- bool dirty, writeback;
+ enum page_references references = PAGEREF_RECLAIM;
+ bool dirty, writeback, may_enter_fs;
+ unsigned int nr_pages;
cond_resched();
@@ -1130,18 +1150,16 @@
VM_BUG_ON_PAGE(PageActive(page), page);
- sc->nr_scanned++;
+ nr_pages = compound_nr(page);
+
+ /* Account the number of base pages even though THP */
+ sc->nr_scanned += nr_pages;
if (unlikely(!page_evictable(page)))
goto activate_locked;
if (!sc->may_unmap && page_mapped(page))
goto keep_locked;
-
- /* Double the slab pressure for mapped and swapcache pages */
- if ((page_mapped(page) || PageSwapCache(page)) &&
- !(PageAnon(page) && !PageSwapBacked(page)))
- sc->nr_scanned++;
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
@@ -1154,10 +1172,10 @@
*/
page_check_dirty_writeback(page, &dirty, &writeback);
if (dirty || writeback)
- nr_dirty++;
+ stat->nr_dirty++;
if (dirty && !writeback)
- nr_unqueued_dirty++;
+ stat->nr_unqueued_dirty++;
/*
* Treat this page as congested if the underlying BDI is or if
@@ -1169,7 +1187,7 @@
if (((dirty || writeback) && mapping &&
inode_write_congested(mapping->host)) ||
(writeback && PageReclaim(page)))
- nr_congested++;
+ stat->nr_congested++;
/*
* If a page at the tail of the LRU is under writeback, there
@@ -1218,11 +1236,11 @@
if (current_is_kswapd() &&
PageReclaim(page) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
- nr_immediate++;
+ stat->nr_immediate++;
goto activate_locked;
/* Case 2 above */
- } else if (sane_reclaim(sc) ||
+ } else if (writeback_throttling_sane(sc) ||
!PageReclaim(page) || !may_enter_fs) {
/*
* This is slightly racy - end_page_writeback()
@@ -1236,7 +1254,7 @@
* and it's also appropriate in global reclaim.
*/
SetPageReclaim(page);
- nr_writeback++;
+ stat->nr_writeback++;
goto activate_locked;
/* Case 3 above */
@@ -1249,14 +1267,14 @@
}
}
- if (!force_reclaim)
+ if (!ignore_references)
references = page_check_references(page, sc);
switch (references) {
case PAGEREF_ACTIVATE:
goto activate_locked;
case PAGEREF_KEEP:
- nr_ref_keep++;
+ stat->nr_ref_keep += nr_pages;
goto keep_locked;
case PAGEREF_RECLAIM:
case PAGEREF_RECLAIM_CLEAN:
@@ -1271,6 +1289,8 @@
if (PageAnon(page) && PageSwapBacked(page)) {
if (!PageSwapCache(page)) {
if (!(sc->gfp_mask & __GFP_IO))
+ goto keep_locked;
+ if (page_maybe_dma_pinned(page))
goto keep_locked;
if (PageTransHuge(page)) {
/* cannot split THP, skip it */
@@ -1288,7 +1308,7 @@
}
if (!add_to_swap(page)) {
if (!PageTransHuge(page))
- goto activate_locked;
+ goto activate_locked_split;
/* Fallback to swap normal pages */
if (split_huge_page_to_list(page,
page_list))
@@ -1297,10 +1317,10 @@
count_vm_event(THP_SWPOUT_FALLBACK);
#endif
if (!add_to_swap(page))
- goto activate_locked;
+ goto activate_locked_split;
}
- may_enter_fs = 1;
+ may_enter_fs = true;
/* Adding to swap updated mapping */
mapping = page_mapping(page);
@@ -1312,16 +1332,33 @@
}
/*
+ * THP may get split above, need minus tail pages and update
+ * nr_pages to avoid accounting tail pages twice.
+ *
+ * The tail pages that are added into swap cache successfully
+ * reach here.
+ */
+ if ((nr_pages > 1) && !PageTransHuge(page)) {
+ sc->nr_scanned -= (nr_pages - 1);
+ nr_pages = 1;
+ }
+
+ /*
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
if (page_mapped(page)) {
- enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
+ enum ttu_flags flags = TTU_BATCH_FLUSH;
+ bool was_swapbacked = PageSwapBacked(page);
if (unlikely(PageTransHuge(page)))
flags |= TTU_SPLIT_HUGE_PMD;
+ if (!ignore_references)
+ trace_android_vh_page_trylock_set(page);
if (!try_to_unmap(page, flags)) {
- nr_unmap_fail++;
+ stat->nr_unmap_fail += nr_pages;
+ if (!was_swapbacked && PageSwapBacked(page))
+ stat->nr_lazyfree_fail += nr_pages;
goto activate_locked;
}
}
@@ -1337,7 +1374,7 @@
* the rest of the LRU for clean pages and see
* the same dirty pages again (PageReclaim).
*/
- if (page_is_file_cache(page) &&
+ if (page_is_file_lru(page) &&
(!current_is_kswapd() || !PageReclaim(page) ||
!test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
@@ -1365,12 +1402,14 @@
* starts and then write it out here.
*/
try_to_unmap_flush_dirty();
- switch (pageout(page, mapping, sc)) {
+ switch (pageout(page, mapping)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
goto activate_locked;
case PAGE_SUCCESS:
+ stat->nr_pageout += thp_nr_pages(page);
+
if (PageWriteback(page))
goto keep;
if (PageDirty(page))
@@ -1426,6 +1465,7 @@
* increment nr_reclaimed here (and
* leave it off the LRU).
*/
+ trace_android_vh_page_trylock_clear(page);
nr_reclaimed++;
continue;
}
@@ -1443,30 +1483,38 @@
count_vm_event(PGLAZYFREED);
count_memcg_page_event(page, PGLAZYFREED);
- } else if (!mapping || !__remove_mapping(mapping, page, true))
+ } else if (!mapping || !__remove_mapping(mapping, page, true,
+ sc->target_mem_cgroup))
goto keep_locked;
- /*
- * At this point, we have no other references and there is
- * no way to pick any more up (removed from LRU, removed
- * from pagecache). Can use non-atomic bitops now (and
- * we obviously don't have to worry about waking up a process
- * waiting on the page lock, because there are no references.
- */
- __ClearPageLocked(page);
+
+ unlock_page(page);
free_it:
- nr_reclaimed++;
+ /*
+ * THP may get swapped out in a whole, need account
+ * all base pages.
+ */
+ nr_reclaimed += nr_pages;
/*
* Is there need to periodically free_page_list? It would
* appear not as the counts should be low
*/
- if (unlikely(PageTransHuge(page))) {
- mem_cgroup_uncharge(page);
- (*get_compound_page_dtor(page))(page);
- } else
+ trace_android_vh_page_trylock_clear(page);
+ if (unlikely(PageTransHuge(page)))
+ destroy_compound_page(page);
+ else
list_add(&page->lru, &free_pages);
continue;
+activate_locked_split:
+ /*
+ * The tail pages that are failed to add into swap cache
+ * reach here. Fixup nr_scanned and nr_pages.
+ */
+ if (nr_pages > 1) {
+ sc->nr_scanned -= (nr_pages - 1);
+ nr_pages = 1;
+ }
activate_locked:
/* Not a candidate for swapping, so reclaim swap space. */
if (PageSwapCache(page) && (mem_cgroup_swap_full(page) ||
@@ -1474,16 +1522,31 @@
try_to_free_swap(page);
VM_BUG_ON_PAGE(PageActive(page), page);
if (!PageMlocked(page)) {
+ int type = page_is_file_lru(page);
SetPageActive(page);
- pgactivate++;
+ stat->nr_activate[type] += nr_pages;
count_memcg_page_event(page, PGACTIVATE);
}
keep_locked:
+ /*
+ * The page with trylock-bit will be added ret_pages and
+ * handled in trace_android_vh_handle_failed_page_trylock.
+ * In the progress[unlock_page, handled], the page carried
+ * with trylock-bit will cause some error-issues in other
+ * scene, so clear trylock-bit here.
+ * trace_android_vh_page_trylock_get_result will clear
+ * trylock-bit and return if page tyrlock failed in
+ * reclaim-process. Here we just want to clear trylock-bit
+ * so that ignore page_trylock_result.
+ */
+ trace_android_vh_page_trylock_get_result(page, &page_trylock_result);
unlock_page(page);
keep:
list_add(&page->lru, &ret_pages);
VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
}
+
+ pgactivate = stat->nr_activate[0] + stat->nr_activate[1];
mem_cgroup_uncharge_list(&free_pages);
try_to_unmap_flush();
@@ -1492,20 +1555,10 @@
list_splice(&ret_pages, page_list);
count_vm_events(PGACTIVATE, pgactivate);
- if (stat) {
- stat->nr_dirty = nr_dirty;
- stat->nr_congested = nr_congested;
- stat->nr_unqueued_dirty = nr_unqueued_dirty;
- stat->nr_writeback = nr_writeback;
- stat->nr_immediate = nr_immediate;
- stat->nr_activate = pgactivate;
- stat->nr_ref_keep = nr_ref_keep;
- stat->nr_unmap_fail = nr_unmap_fail;
- }
return nr_reclaimed;
}
-unsigned long reclaim_clean_pages_from_list(struct zone *zone,
+unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *page_list)
{
struct scan_control sc = {
@@ -1513,23 +1566,35 @@
.priority = DEF_PRIORITY,
.may_unmap = 1,
};
- unsigned long ret;
+ struct reclaim_stat stat;
+ unsigned int nr_reclaimed;
struct page *page, *next;
LIST_HEAD(clean_pages);
list_for_each_entry_safe(page, next, page_list, lru) {
- if (page_is_file_cache(page) && !PageDirty(page) &&
+ if (page_is_file_lru(page) && !PageDirty(page) &&
!__PageMovable(page) && !PageUnevictable(page)) {
ClearPageActive(page);
list_move(&page->lru, &clean_pages);
}
}
- ret = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
- TTU_IGNORE_ACCESS, NULL, true);
+ nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
+ &stat, true);
list_splice(&clean_pages, page_list);
- mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE, -ret);
- return ret;
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+ -(long)nr_reclaimed);
+ /*
+ * Since lazyfree pages are isolated from file LRU from the beginning,
+ * they will rotate back to anonymous LRU in the end if it failed to
+ * discard so isolated count will be mismatched.
+ * Compensate the isolated count for both LRU lists.
+ */
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_ANON,
+ stat.nr_lazyfree_fail);
+ mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
+ -(long)stat.nr_lazyfree_fail);
+ return nr_reclaimed;
}
/*
@@ -1612,7 +1677,7 @@
/*
* Update LRU sizes after isolating pages. The LRU size updates must
- * be complete before mem_cgroup_update_lru_size due to a santity check.
+ * be complete before mem_cgroup_update_lru_size due to a sanity check.
*/
static __always_inline void update_lru_sizes(struct lruvec *lruvec,
enum lru_list lru, unsigned long *nr_zone_taken)
@@ -1623,16 +1688,13 @@
if (!nr_zone_taken[zid])
continue;
- __update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
-#ifdef CONFIG_MEMCG
- mem_cgroup_update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
-#endif
+ update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
}
}
-/*
- * zone_lru_lock is heavily contended. Some of the functions that
+/**
+ * pgdat->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages
* and working on them outside the LRU lock.
*
@@ -1646,7 +1708,6 @@
* @dst: The temp list to put pages on to.
* @nr_scanned: The number of pages that were scanned.
* @sc: The scan_control struct for this reclaim session
- * @mode: One of the LRU isolation modes
* @lru: LRU list id for isolating
*
* returns how many pages were moved onto *@dst.
@@ -1654,7 +1715,7 @@
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
struct lruvec *lruvec, struct list_head *dst,
unsigned long *nr_scanned, struct scan_control *sc,
- isolate_mode_t mode, enum lru_list lru)
+ enum lru_list lru)
{
struct list_head *src = &lruvec->lists[lru];
unsigned long nr_taken = 0;
@@ -1663,11 +1724,11 @@
unsigned long skipped = 0;
unsigned long scan, total_scan, nr_pages;
LIST_HEAD(pages_skipped);
+ isolate_mode_t mode = (sc->may_unmap ? 0 : ISOLATE_UNMAPPED);
+ total_scan = 0;
scan = 0;
- for (total_scan = 0;
- scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
- total_scan++) {
+ while (scan < nr_to_scan && !list_empty(src)) {
struct page *page;
page = lru_to_page(src);
@@ -1675,9 +1736,12 @@
VM_BUG_ON_PAGE(!PageLRU(page), page);
+ nr_pages = compound_nr(page);
+ total_scan += nr_pages;
+
if (page_zonenum(page) > sc->reclaim_idx) {
list_move(&page->lru, &pages_skipped);
- nr_skipped[page_zonenum(page)]++;
+ nr_skipped[page_zonenum(page)] += nr_pages;
continue;
}
@@ -1686,13 +1750,17 @@
* return with no isolated pages if the LRU mostly contains
* ineligible pages. This causes the VM to not reclaim any
* pages, triggering a premature OOM.
+ *
+ * Account all tail pages of THP. This would not cause
+ * premature OOM since __isolate_lru_page() returns -EBUSY
+ * only when the page is being freed somewhere else.
*/
- scan++;
+ scan += nr_pages;
switch (__isolate_lru_page(page, mode)) {
case 0:
- nr_pages = hpage_nr_pages(page);
nr_taken += nr_pages;
nr_zone_taken[page_zonenum(page)] += nr_pages;
+ trace_android_vh_del_page_from_lrulist(page, false, lru);
list_move(&page->lru, dst);
break;
@@ -1753,7 +1821,7 @@
* Restrictions:
*
* (1) Must be called with an elevated refcount on the page. This is a
- * fundamentnal difference from isolate_lru_pages (which is called
+ * fundamental difference from isolate_lru_pages (which is called
* without a stable reference).
* (2) the lru_lock must not be held.
* (3) interrupts must be enabled.
@@ -1766,11 +1834,11 @@
WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
if (PageLRU(page)) {
- struct zone *zone = page_zone(page);
+ pg_data_t *pgdat = page_pgdat(page);
struct lruvec *lruvec;
- spin_lock_irq(zone_lru_lock(zone));
- lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
+ spin_lock_irq(&pgdat->lru_lock);
+ lruvec = mem_cgroup_page_lruvec(page, pgdat);
if (PageLRU(page)) {
int lru = page_lru(page);
get_page(page);
@@ -1778,14 +1846,14 @@
del_page_from_lru_list(page, lruvec, lru);
ret = 0;
}
- spin_unlock_irq(zone_lru_lock(zone));
+ spin_unlock_irq(&pgdat->lru_lock);
}
return ret;
}
/*
* A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
- * then get resheduled. When there are massive number of tasks doing page
+ * then get rescheduled. When there are massive number of tasks doing page
* allocation, such sleeping direct reclaimers may keep piling up on each CPU,
* the LRU list will go small and be scanned faster than necessary, leading to
* unnecessary swapping, thrashing and OOM.
@@ -1798,7 +1866,7 @@
if (current_is_kswapd())
return 0;
- if (!sane_reclaim(sc))
+ if (!writeback_throttling_sane(sc))
return 0;
if (file) {
@@ -1820,40 +1888,55 @@
return isolated > inactive;
}
-static noinline_for_stack void
-putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
+/*
+ * This moves pages from @list to corresponding LRU list.
+ *
+ * We move them the other way if the page is referenced by one or more
+ * processes, from rmap.
+ *
+ * If the pages are mostly unmapped, the processing is fast and it is
+ * appropriate to hold zone_lru_lock across the whole operation. But if
+ * the pages are mapped, the processing is slow (page_referenced()) so we
+ * should drop zone_lru_lock around each page. It's impossible to balance
+ * this, so instead we remove the pages from the LRU while processing them.
+ * It is safe to rely on PG_active against the non-LRU pages in here because
+ * nobody will play with that bit on a non-LRU page.
+ *
+ * The downside is that we have to touch page->_refcount against each page.
+ * But we had to alter page->flags anyway.
+ *
+ * Returns the number of pages moved to the given lruvec.
+ */
+
+static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
+ struct list_head *list)
{
- struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+ int nr_pages, nr_moved = 0;
LIST_HEAD(pages_to_free);
+ struct page *page;
+ enum lru_list lru;
- /*
- * Put back any unfreeable pages.
- */
- while (!list_empty(page_list)) {
- struct page *page = lru_to_page(page_list);
- int lru;
-
+ while (!list_empty(list)) {
+ page = lru_to_page(list);
VM_BUG_ON_PAGE(PageLRU(page), page);
- list_del(&page->lru);
if (unlikely(!page_evictable(page))) {
+ list_del(&page->lru);
spin_unlock_irq(&pgdat->lru_lock);
putback_lru_page(page);
spin_lock_irq(&pgdat->lru_lock);
continue;
}
-
lruvec = mem_cgroup_page_lruvec(page, pgdat);
SetPageLRU(page);
lru = page_lru(page);
- add_page_to_lru_list(page, lruvec, lru);
- if (is_active_lru(lru)) {
- int file = is_file_lru(lru);
- int numpages = hpage_nr_pages(page);
- reclaim_stat->recent_rotated[file] += numpages;
- }
+ nr_pages = thp_nr_pages(page);
+ update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
+ list_move(&page->lru, &lruvec->lists[lru]);
+ trace_android_vh_add_page_to_lrulist(page, false, lru);
+
if (put_page_testzero(page)) {
__ClearPageLRU(page);
__ClearPageActive(page);
@@ -1861,29 +1944,34 @@
if (unlikely(PageCompound(page))) {
spin_unlock_irq(&pgdat->lru_lock);
- mem_cgroup_uncharge(page);
- (*get_compound_page_dtor(page))(page);
+ destroy_compound_page(page);
spin_lock_irq(&pgdat->lru_lock);
} else
list_add(&page->lru, &pages_to_free);
+ } else {
+ nr_moved += nr_pages;
+ if (PageActive(page))
+ workingset_age_nonresident(lruvec, nr_pages);
}
}
/*
* To save our caller's stack, now use input list for pages to free.
*/
- list_splice(&pages_to_free, page_list);
+ list_splice(&pages_to_free, list);
+
+ return nr_moved;
}
/*
* If a kernel thread (such as nfsd for loop-back mounts) services
- * a backing device by writing to the page cache it sets PF_LESS_THROTTLE.
+ * a backing device by writing to the page cache it sets PF_LOCAL_THROTTLE.
* In that case we should only throttle if the backing device it is
* writing to is congested. In other cases it is safe to throttle.
*/
static int current_may_throttle(void)
{
- return !(current->flags & PF_LESS_THROTTLE) ||
+ return !(current->flags & PF_LOCAL_THROTTLE) ||
current->backing_dev_info == NULL ||
bdi_write_congested(current->backing_dev_info);
}
@@ -1898,13 +1986,12 @@
{
LIST_HEAD(page_list);
unsigned long nr_scanned;
- unsigned long nr_reclaimed = 0;
+ unsigned int nr_reclaimed = 0;
unsigned long nr_taken;
- struct reclaim_stat stat = {};
- isolate_mode_t isolate_mode = 0;
- int file = is_file_lru(lru);
+ struct reclaim_stat stat;
+ bool file = is_file_lru(lru);
+ enum vm_event_item item;
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
bool stalled = false;
while (unlikely(too_many_isolated(pgdat, file, sc))) {
@@ -1922,54 +2009,37 @@
lru_add_drain();
- if (!sc->may_unmap)
- isolate_mode |= ISOLATE_UNMAPPED;
-
spin_lock_irq(&pgdat->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
- &nr_scanned, sc, isolate_mode, lru);
+ &nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
- reclaim_stat->recent_scanned[file] += nr_taken;
+ item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
+ if (!cgroup_reclaim(sc))
+ __count_vm_events(item, nr_scanned);
+ __count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
+ __count_vm_events(PGSCAN_ANON + file, nr_scanned);
- if (current_is_kswapd()) {
- if (global_reclaim(sc))
- __count_vm_events(PGSCAN_KSWAPD, nr_scanned);
- count_memcg_events(lruvec_memcg(lruvec), PGSCAN_KSWAPD,
- nr_scanned);
- } else {
- if (global_reclaim(sc))
- __count_vm_events(PGSCAN_DIRECT, nr_scanned);
- count_memcg_events(lruvec_memcg(lruvec), PGSCAN_DIRECT,
- nr_scanned);
- }
spin_unlock_irq(&pgdat->lru_lock);
if (nr_taken == 0)
return 0;
- nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0,
- &stat, false);
+ nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
+ trace_android_vh_handle_failed_page_trylock(&page_list);
spin_lock_irq(&pgdat->lru_lock);
- if (current_is_kswapd()) {
- if (global_reclaim(sc))
- __count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
- count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_KSWAPD,
- nr_reclaimed);
- } else {
- if (global_reclaim(sc))
- __count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
- count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_DIRECT,
- nr_reclaimed);
- }
-
- putback_inactive_pages(lruvec, &page_list);
+ move_pages_to_lru(lruvec, &page_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-
+ lru_note_cost(lruvec, file, stat.nr_pageout);
+ item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+ if (!cgroup_reclaim(sc))
+ __count_vm_events(item, nr_reclaimed);
+ __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
+ __count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
spin_unlock_irq(&pgdat->lru_lock);
mem_cgroup_uncharge_list(&page_list);
@@ -2003,73 +2073,6 @@
return nr_reclaimed;
}
-/*
- * This moves pages from the active list to the inactive list.
- *
- * We move them the other way if the page is referenced by one or more
- * processes, from rmap.
- *
- * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold zone_lru_lock across the whole operation. But if
- * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop zone_lru_lock around each page. It's impossible to balance
- * this, so instead we remove the pages from the LRU while processing them.
- * It is safe to rely on PG_active against the non-LRU pages in here because
- * nobody will play with that bit on a non-LRU page.
- *
- * The downside is that we have to touch page->_refcount against each page.
- * But we had to alter page->flags anyway.
- *
- * Returns the number of pages moved to the given lru.
- */
-
-static unsigned move_active_pages_to_lru(struct lruvec *lruvec,
- struct list_head *list,
- struct list_head *pages_to_free,
- enum lru_list lru)
-{
- struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- struct page *page;
- int nr_pages;
- int nr_moved = 0;
-
- while (!list_empty(list)) {
- page = lru_to_page(list);
- lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
- VM_BUG_ON_PAGE(PageLRU(page), page);
- SetPageLRU(page);
-
- nr_pages = hpage_nr_pages(page);
- update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
- list_move(&page->lru, &lruvec->lists[lru]);
-
- if (put_page_testzero(page)) {
- __ClearPageLRU(page);
- __ClearPageActive(page);
- del_page_from_lru_list(page, lruvec, lru);
-
- if (unlikely(PageCompound(page))) {
- spin_unlock_irq(&pgdat->lru_lock);
- mem_cgroup_uncharge(page);
- (*get_compound_page_dtor(page))(page);
- spin_lock_irq(&pgdat->lru_lock);
- } else
- list_add(&page->lru, pages_to_free);
- } else {
- nr_moved += nr_pages;
- }
- }
-
- if (!is_active_lru(lru)) {
- __count_vm_events(PGDEACTIVATE, nr_moved);
- count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
- nr_moved);
- }
-
- return nr_moved;
-}
-
static void shrink_active_list(unsigned long nr_to_scan,
struct lruvec *lruvec,
struct scan_control *sc,
@@ -2082,28 +2085,25 @@
LIST_HEAD(l_active);
LIST_HEAD(l_inactive);
struct page *page;
- struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
unsigned nr_deactivate, nr_activate;
unsigned nr_rotated = 0;
- isolate_mode_t isolate_mode = 0;
int file = is_file_lru(lru);
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+ bool bypass = false;
+ bool should_protect = false;
lru_add_drain();
-
- if (!sc->may_unmap)
- isolate_mode |= ISOLATE_UNMAPPED;
spin_lock_irq(&pgdat->lru_lock);
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
- &nr_scanned, sc, isolate_mode, lru);
+ &nr_scanned, sc, lru);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
- reclaim_stat->recent_scanned[file] += nr_taken;
- __count_vm_events(PGREFILL, nr_scanned);
- count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
+ if (!cgroup_reclaim(sc))
+ __count_vm_events(PGREFILL, nr_scanned);
+ __count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
spin_unlock_irq(&pgdat->lru_lock);
@@ -2125,9 +2125,20 @@
}
}
+ trace_android_vh_page_should_be_protected(page, &should_protect);
+ if (unlikely(should_protect)) {
+ nr_rotated += thp_nr_pages(page);
+ list_add(&page->lru, &l_active);
+ continue;
+ }
+
+ trace_android_vh_page_referenced_check_bypass(page, nr_to_scan, lru, &bypass);
+ if (bypass)
+ goto skip_page_referenced;
+ trace_android_vh_page_trylock_set(page);
+ /* Referenced or rmap lock contention: rotate */
if (page_referenced(page, 0, sc->target_mem_cgroup,
- &vm_flags)) {
- nr_rotated += hpage_nr_pages(page);
+ &vm_flags) != 0) {
/*
* Identify referenced, file-backed active pages and
* give them one more trip around the active list. So
@@ -2137,12 +2148,15 @@
* IO, plus JVM can create lots of anon VM_EXEC pages,
* so we ignore them here.
*/
- if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
+ if ((vm_flags & VM_EXEC) && page_is_file_lru(page)) {
+ trace_android_vh_page_trylock_clear(page);
+ nr_rotated += thp_nr_pages(page);
list_add(&page->lru, &l_active);
continue;
}
}
-
+ trace_android_vh_page_trylock_clear(page);
+skip_page_referenced:
ClearPageActive(page); /* we are de-activating */
SetPageWorkingset(page);
list_add(&page->lru, &l_inactive);
@@ -2152,23 +2166,91 @@
* Move pages back to the lru list.
*/
spin_lock_irq(&pgdat->lru_lock);
- /*
- * Count referenced pages from currently used mappings as rotated,
- * even though only some of them are actually re-activated. This
- * helps balance scan pressure between file and anonymous pages in
- * get_scan_count.
- */
- reclaim_stat->recent_rotated[file] += nr_rotated;
- nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
- nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
+ nr_activate = move_pages_to_lru(lruvec, &l_active);
+ nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
+ /* Keep all free pages in l_active list */
+ list_splice(&l_inactive, &l_active);
+
+ __count_vm_events(PGDEACTIVATE, nr_deactivate);
+ __count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
+
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&pgdat->lru_lock);
- mem_cgroup_uncharge_list(&l_hold);
- free_unref_page_list(&l_hold);
+ mem_cgroup_uncharge_list(&l_active);
+ free_unref_page_list(&l_active);
trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
nr_deactivate, nr_rotated, sc->priority, file);
+}
+
+unsigned long reclaim_pages(struct list_head *page_list)
+{
+ int nid = NUMA_NO_NODE;
+ unsigned int nr_reclaimed = 0;
+ LIST_HEAD(node_page_list);
+ struct reclaim_stat dummy_stat;
+ struct page *page;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .priority = DEF_PRIORITY,
+ .may_writepage = 1,
+ .may_unmap = 1,
+ .may_swap = 1,
+ };
+
+ while (!list_empty(page_list)) {
+ page = lru_to_page(page_list);
+ if (nid == NUMA_NO_NODE) {
+ nid = page_to_nid(page);
+ INIT_LIST_HEAD(&node_page_list);
+ }
+
+ if (nid == page_to_nid(page)) {
+ ClearPageActive(page);
+ list_move(&page->lru, &node_page_list);
+ continue;
+ }
+
+ nr_reclaimed += shrink_page_list(&node_page_list,
+ NODE_DATA(nid),
+ &sc, &dummy_stat, false);
+ while (!list_empty(&node_page_list)) {
+ page = lru_to_page(&node_page_list);
+ list_del(&page->lru);
+ putback_lru_page(page);
+ }
+
+ nid = NUMA_NO_NODE;
+ }
+
+ if (!list_empty(&node_page_list)) {
+ nr_reclaimed += shrink_page_list(&node_page_list,
+ NODE_DATA(nid),
+ &sc, &dummy_stat, false);
+ while (!list_empty(&node_page_list)) {
+ page = lru_to_page(&node_page_list);
+ list_del(&page->lru);
+ putback_lru_page(page);
+ }
+ }
+
+ return nr_reclaimed;
+}
+EXPORT_SYMBOL_GPL(reclaim_pages);
+
+static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
+ struct lruvec *lruvec, struct scan_control *sc)
+{
+ if (is_active_lru(lru)) {
+ if (sc->may_deactivate & (1 << is_file_lru(lru)))
+ shrink_active_list(nr_to_scan, lruvec, sc, lru);
+ else
+ sc->skipped_deactivate = 1;
+ return 0;
+ }
+
+ return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
/*
@@ -2199,62 +2281,31 @@
* 1TB 101 10GB
* 10TB 320 32GB
*/
-static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
- struct scan_control *sc, bool trace)
+static bool inactive_is_low(struct lruvec *lruvec, enum lru_list inactive_lru)
{
- enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
- struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- enum lru_list inactive_lru = file * LRU_FILE;
+ enum lru_list active_lru = inactive_lru + LRU_ACTIVE;
unsigned long inactive, active;
unsigned long inactive_ratio;
- unsigned long refaults;
unsigned long gb;
+ bool skip = false;
- /*
- * If we don't have swap space, anonymous page deactivation
- * is pointless.
- */
- if (!file && !total_swap_pages)
- return false;
+ inactive = lruvec_page_state(lruvec, NR_LRU_BASE + inactive_lru);
+ active = lruvec_page_state(lruvec, NR_LRU_BASE + active_lru);
- inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
- active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
+ gb = (inactive + active) >> (30 - PAGE_SHIFT);
+ trace_android_vh_inactive_is_low(gb, &inactive_ratio, inactive_lru, &skip);
+ if (skip)
+ goto out;
- /*
- * When refaults are being observed, it means a new workingset
- * is being established. Disable active list protection to get
- * rid of the stale workingset quickly.
- */
- refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
- if (file && lruvec->refaults != refaults) {
- inactive_ratio = 0;
- } else {
- gb = (inactive + active) >> (30 - PAGE_SHIFT);
- if (gb)
- inactive_ratio = int_sqrt(10 * gb);
- else
- inactive_ratio = 1;
- }
+ if (gb)
+ inactive_ratio = int_sqrt(10 * gb);
+ else
+ inactive_ratio = 1;
- if (trace)
- trace_mm_vmscan_inactive_list_is_low(pgdat->node_id, sc->reclaim_idx,
- lruvec_lru_size(lruvec, inactive_lru, MAX_NR_ZONES), inactive,
- lruvec_lru_size(lruvec, active_lru, MAX_NR_ZONES), active,
- inactive_ratio, file);
+ trace_android_vh_tune_inactive_ratio(&inactive_ratio, is_file_lru(inactive_lru));
+out:
return inactive * inactive_ratio < active;
-}
-
-static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
- struct lruvec *lruvec, struct scan_control *sc)
-{
- if (is_active_lru(lru)) {
- if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
- shrink_active_list(nr_to_scan, lruvec, sc, lru);
- return 0;
- }
-
- return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
}
enum scan_balance {
@@ -2273,20 +2324,18 @@
* nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
* nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
*/
-static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
- struct scan_control *sc, unsigned long *nr,
- unsigned long *lru_pages)
+static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
+ unsigned long *nr)
{
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ unsigned long anon_cost, file_cost, total_cost;
int swappiness = mem_cgroup_swappiness(memcg);
- struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
- u64 fraction[2];
+ u64 fraction[ANON_AND_FILE];
u64 denominator = 0; /* gcc */
- struct pglist_data *pgdat = lruvec_pgdat(lruvec);
- unsigned long anon_prio, file_prio;
enum scan_balance scan_balance;
- unsigned long anon, file;
unsigned long ap, fp;
enum lru_list lru;
+ bool balance_anon_file_reclaim = false;
/* If we have no swap space, do not bother scanning anon pages. */
if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
@@ -2294,6 +2343,7 @@
goto out;
}
+ trace_android_vh_tune_swappiness(&swappiness);
/*
* Global reclaim will swap to prevent OOM even with no
* swappiness, but memcg users want to use this knob to
@@ -2301,7 +2351,7 @@
* using the memory controller's swap limit feature would be
* too expensive.
*/
- if (!global_reclaim(sc) && !swappiness) {
+ if (cgroup_reclaim(sc) && !swappiness) {
scan_balance = SCAN_FILE;
goto out;
}
@@ -2317,129 +2367,133 @@
}
/*
- * Prevent the reclaimer from falling into the cache trap: as
- * cache pages start out inactive, every cache fault will tip
- * the scan balance towards the file LRU. And as the file LRU
- * shrinks, so does the window for rotation from references.
- * This means we have a runaway feedback loop where a tiny
- * thrashing file LRU becomes infinitely more attractive than
- * anon pages. Try to detect this based on file LRU size.
+ * If the system is almost out of file pages, force-scan anon.
*/
- if (global_reclaim(sc)) {
- unsigned long pgdatfile;
- unsigned long pgdatfree;
- int z;
- unsigned long total_high_wmark = 0;
-
- pgdatfree = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
- pgdatfile = node_page_state(pgdat, NR_ACTIVE_FILE) +
- node_page_state(pgdat, NR_INACTIVE_FILE);
-
- for (z = 0; z < MAX_NR_ZONES; z++) {
- struct zone *zone = &pgdat->node_zones[z];
- if (!managed_zone(zone))
- continue;
-
- total_high_wmark += high_wmark_pages(zone);
- }
-
- if (unlikely(pgdatfile + pgdatfree <= total_high_wmark)) {
- /*
- * Force SCAN_ANON if there are enough inactive
- * anonymous pages on the LRU in eligible zones.
- * Otherwise, the small LRU gets thrashed.
- */
- if (!inactive_list_is_low(lruvec, false, sc, false) &&
- lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
- >> sc->priority) {
- scan_balance = SCAN_ANON;
- goto out;
- }
- }
+ if (sc->file_is_tiny) {
+ scan_balance = SCAN_ANON;
+ goto out;
}
+ trace_android_rvh_set_balance_anon_file_reclaim(&balance_anon_file_reclaim);
+
/*
- * If there is enough inactive page cache, i.e. if the size of the
- * inactive list is greater than that of the active list *and* the
- * inactive list actually has some pages to scan on this priority, we
- * do not reclaim anything from the anonymous working set right now.
- * Without the second condition we could end up never scanning an
- * lruvec even if it has plenty of old anonymous pages unless the
- * system is under heavy pressure.
+ * If there is enough inactive page cache, we do not reclaim
+ * anything from the anonymous working right now. But when balancing
+ * anon and page cache files for reclaim, allow swapping of anon pages
+ * even if there are a number of inactive file cache pages.
*/
- if (!inactive_list_is_low(lruvec, true, sc, false) &&
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
+ if (!balance_anon_file_reclaim && sc->cache_trim_mode) {
scan_balance = SCAN_FILE;
goto out;
}
scan_balance = SCAN_FRACT;
-
/*
- * With swappiness at 100, anonymous and file have the same priority.
- * This scanning priority is essentially the inverse of IO cost.
- */
- anon_prio = swappiness;
- file_prio = 200 - anon_prio;
-
- /*
- * OK, so we have swap space and a fair amount of page cache
- * pages. We use the recently rotated / recently scanned
- * ratios to determine how valuable each cache is.
+ * Calculate the pressure balance between anon and file pages.
*
- * Because workloads change over time (and to avoid overflow)
- * we keep these statistics as a floating average, which ends
- * up weighing recent references more than old ones.
+ * The amount of pressure we put on each LRU is inversely
+ * proportional to the cost of reclaiming each list, as
+ * determined by the share of pages that are refaulting, times
+ * the relative IO cost of bringing back a swapped out
+ * anonymous page vs reloading a filesystem page (swappiness).
*
- * anon in [0], file in [1]
+ * Although we limit that influence to ensure no list gets
+ * left behind completely: at least a third of the pressure is
+ * applied, before swappiness.
+ *
+ * With swappiness at 100, anon and file have equal IO cost.
*/
+ total_cost = sc->anon_cost + sc->file_cost;
+ anon_cost = total_cost + sc->anon_cost;
+ file_cost = total_cost + sc->file_cost;
+ total_cost = anon_cost + file_cost;
- anon = lruvec_lru_size(lruvec, LRU_ACTIVE_ANON, MAX_NR_ZONES) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, MAX_NR_ZONES);
- file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES) +
- lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, MAX_NR_ZONES);
+ ap = swappiness * (total_cost + 1);
+ ap /= anon_cost + 1;
- spin_lock_irq(&pgdat->lru_lock);
- if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
- reclaim_stat->recent_scanned[0] /= 2;
- reclaim_stat->recent_rotated[0] /= 2;
- }
-
- if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
- reclaim_stat->recent_scanned[1] /= 2;
- reclaim_stat->recent_rotated[1] /= 2;
- }
-
- /*
- * The amount of pressure on anon vs file pages is inversely
- * proportional to the fraction of recently scanned pages on
- * each list that were recently referenced and in active use.
- */
- ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
- ap /= reclaim_stat->recent_rotated[0] + 1;
-
- fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
- fp /= reclaim_stat->recent_rotated[1] + 1;
- spin_unlock_irq(&pgdat->lru_lock);
+ fp = (200 - swappiness) * (total_cost + 1);
+ fp /= file_cost + 1;
fraction[0] = ap;
fraction[1] = fp;
- denominator = ap + fp + 1;
+ denominator = ap + fp;
out:
- *lru_pages = 0;
+ trace_android_vh_tune_scan_type((char *)(&scan_balance));
for_each_evictable_lru(lru) {
int file = is_file_lru(lru);
- unsigned long size;
+ unsigned long lruvec_size;
+ unsigned long low, min;
unsigned long scan;
- size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
- scan = size >> sc->priority;
+ lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
+ mem_cgroup_protection(sc->target_mem_cgroup, memcg,
+ &min, &low);
+
+ if (min || low) {
+ /*
+ * Scale a cgroup's reclaim pressure by proportioning
+ * its current usage to its memory.low or memory.min
+ * setting.
+ *
+ * This is important, as otherwise scanning aggression
+ * becomes extremely binary -- from nothing as we
+ * approach the memory protection threshold, to totally
+ * nominal as we exceed it. This results in requiring
+ * setting extremely liberal protection thresholds. It
+ * also means we simply get no protection at all if we
+ * set it too low, which is not ideal.
+ *
+ * If there is any protection in place, we reduce scan
+ * pressure by how much of the total memory used is
+ * within protection thresholds.
+ *
+ * There is one special case: in the first reclaim pass,
+ * we skip over all groups that are within their low
+ * protection. If that fails to reclaim enough pages to
+ * satisfy the reclaim goal, we come back and override
+ * the best-effort low protection. However, we still
+ * ideally want to honor how well-behaved groups are in
+ * that case instead of simply punishing them all
+ * equally. As such, we reclaim them based on how much
+ * memory they are using, reducing the scan pressure
+ * again by how much of the total memory used is under
+ * hard protection.
+ */
+ unsigned long cgroup_size = mem_cgroup_size(memcg);
+ unsigned long protection;
+
+ /* memory.low scaling, make sure we retry before OOM */
+ if (!sc->memcg_low_reclaim && low > min) {
+ protection = low;
+ sc->memcg_low_skipped = 1;
+ } else {
+ protection = min;
+ }
+
+ /* Avoid TOCTOU with earlier protection check */
+ cgroup_size = max(cgroup_size, protection);
+
+ scan = lruvec_size - lruvec_size * protection /
+ (cgroup_size + 1);
+
+ /*
+ * Minimally target SWAP_CLUSTER_MAX pages to keep
+ * reclaim moving forwards, avoiding decrementing
+ * sc->priority further than desirable.
+ */
+ scan = max(scan, SWAP_CLUSTER_MAX);
+ } else {
+ scan = lruvec_size;
+ }
+
+ scan >>= sc->priority;
+
/*
* If the cgroup's already been deleted, make sure to
* scrape out the remaining cache.
*/
if (!scan && !mem_cgroup_online(memcg))
- scan = min(size, SWAP_CLUSTER_MAX);
+ scan = min(lruvec_size, SWAP_CLUSTER_MAX);
switch (scan_balance) {
case SCAN_EQUAL:
@@ -2461,38 +2515,30 @@
case SCAN_FILE:
case SCAN_ANON:
/* Scan one type exclusively */
- if ((scan_balance == SCAN_FILE) != file) {
- size = 0;
+ if ((scan_balance == SCAN_FILE) != file)
scan = 0;
- }
break;
default:
/* Look ma, no brain */
BUG();
}
- *lru_pages += size;
nr[lru] = scan;
}
}
-/*
- * This is a basic per-node page freer. Used by both kswapd and direct reclaim.
- */
-static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg,
- struct scan_control *sc, unsigned long *lru_pages)
+static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
{
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
unsigned long nr[NR_LRU_LISTS];
unsigned long targets[NR_LRU_LISTS];
unsigned long nr_to_scan;
enum lru_list lru;
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
+ bool proportional_reclaim;
struct blk_plug plug;
- bool scan_adjusted;
- get_scan_count(lruvec, memcg, sc, nr, lru_pages);
+ get_scan_count(lruvec, sc, nr);
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
@@ -2508,8 +2554,8 @@
* abort proportional reclaim if either the file or anon lru has already
* dropped to zero at the first pass.
*/
- scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
- sc->priority == DEF_PRIORITY);
+ proportional_reclaim = (!cgroup_reclaim(sc) && !current_is_kswapd() &&
+ sc->priority == DEF_PRIORITY);
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -2529,7 +2575,7 @@
cond_resched();
- if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
+ if (nr_reclaimed < nr_to_reclaim || proportional_reclaim)
continue;
/*
@@ -2580,8 +2626,6 @@
nr_scanned = targets[lru] - nr[lru];
nr[lru] = targets[lru] * (100 - percentage) / 100;
nr[lru] -= min(nr[lru], nr_scanned);
-
- scan_adjusted = true;
}
blk_finish_plug(&plug);
sc->nr_reclaimed += nr_reclaimed;
@@ -2590,7 +2634,7 @@
* Even if we did not try to evict anon pages at all, we want to
* rebalance the anon lru active/inactive ratio.
*/
- if (inactive_list_is_low(lruvec, false, sc, true))
+ if (total_swap_pages && inactive_is_low(lruvec, LRU_INACTIVE_ANON))
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
sc, LRU_ACTIVE_ANON);
}
@@ -2610,12 +2654,11 @@
* Reclaim/compaction is used for high-order allocation requests. It reclaims
* order-0 pages before compacting the zone. should_continue_reclaim() returns
* true if more pages should be reclaimed such that when the page allocator
- * calls try_to_compact_zone() that it will have enough free pages to succeed.
+ * calls try_to_compact_pages() that it will have enough free pages to succeed.
* It will give up earlier than that if there is difficulty reclaiming pages.
*/
static inline bool should_continue_reclaim(struct pglist_data *pgdat,
unsigned long nr_reclaimed,
- unsigned long nr_scanned,
struct scan_control *sc)
{
unsigned long pages_for_compaction;
@@ -2626,40 +2669,18 @@
if (!in_reclaim_compaction(sc))
return false;
- /* Consider stopping depending on scan and reclaim activity */
- if (sc->gfp_mask & __GFP_RETRY_MAYFAIL) {
- /*
- * For __GFP_RETRY_MAYFAIL allocations, stop reclaiming if the
- * full LRU list has been scanned and we are still failing
- * to reclaim pages. This full LRU scan is potentially
- * expensive but a __GFP_RETRY_MAYFAIL caller really wants to succeed
- */
- if (!nr_reclaimed && !nr_scanned)
- return false;
- } else {
- /*
- * For non-__GFP_RETRY_MAYFAIL allocations which can presumably
- * fail without consequence, stop if we failed to reclaim
- * any pages from the last SWAP_CLUSTER_MAX number of
- * pages that were scanned. This will return to the
- * caller faster at the risk reclaim/compaction and
- * the resulting allocation attempt fails
- */
- if (!nr_reclaimed)
- return false;
- }
-
/*
- * If we have not reclaimed enough pages for compaction and the
- * inactive lists are large enough, continue reclaiming
+ * Stop if we failed to reclaim any pages from the last SWAP_CLUSTER_MAX
+ * number of pages that were scanned. This will return to the caller
+ * with the risk reclaim/compaction and the resulting allocation attempt
+ * fails. In the past we have tried harder for __GFP_RETRY_MAYFAIL
+ * allocations through requiring that the full LRU list has been scanned
+ * first, by assuming that zero delta of sc->nr_scanned means full LRU
+ * scan, but that approximation was wrong, and there were corner cases
+ * where always a non-zero amount of pages were scanned.
*/
- pages_for_compaction = compact_gap(sc->order);
- inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
- if (get_nr_swap_pages() > 0)
- inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
- if (sc->nr_reclaimed < pages_for_compaction &&
- inactive_lru_pages > pages_for_compaction)
- return true;
+ if (!nr_reclaimed)
+ return false;
/* If compaction would go ahead or the allocation would succeed, stop */
for (z = 0; z <= sc->reclaim_idx; z++) {
@@ -2676,179 +2697,262 @@
;
}
}
- return true;
+
+ /*
+ * If we have not reclaimed enough pages for compaction and the
+ * inactive lists are large enough, continue reclaiming
+ */
+ pages_for_compaction = compact_gap(sc->order);
+ inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
+ if (get_nr_swap_pages() > 0)
+ inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
+
+ return inactive_lru_pages > pages_for_compaction;
}
-static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
+static void shrink_node_memcgs(pg_data_t *pgdat, struct scan_control *sc)
{
- return test_bit(PGDAT_CONGESTED, &pgdat->flags) ||
- (memcg && memcg_congested(pgdat, memcg));
+ struct mem_cgroup *target_memcg = sc->target_mem_cgroup;
+ struct mem_cgroup *memcg;
+
+ memcg = mem_cgroup_iter(target_memcg, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ unsigned long reclaimed;
+ unsigned long scanned;
+ bool skip = false;
+
+ /*
+ * This loop can become CPU-bound when target memcgs
+ * aren't eligible for reclaim - either because they
+ * don't have any reclaimable pages, or because their
+ * memory is explicitly protected. Avoid soft lockups.
+ */
+ cond_resched();
+
+ trace_android_vh_shrink_node_memcgs(memcg, &skip);
+ if (skip)
+ continue;
+
+ mem_cgroup_calculate_protection(target_memcg, memcg);
+
+ if (mem_cgroup_below_min(memcg)) {
+ /*
+ * Hard protection.
+ * If there is no reclaimable memory, OOM.
+ */
+ continue;
+ } else if (mem_cgroup_below_low(memcg)) {
+ /*
+ * Soft protection.
+ * Respect the protection only as long as
+ * there is an unprotected supply
+ * of reclaimable memory from other cgroups.
+ */
+ if (!sc->memcg_low_reclaim) {
+ sc->memcg_low_skipped = 1;
+ continue;
+ }
+ memcg_memory_event(memcg, MEMCG_LOW);
+ }
+
+ reclaimed = sc->nr_reclaimed;
+ scanned = sc->nr_scanned;
+
+ shrink_lruvec(lruvec, sc);
+
+ shrink_slab(sc->gfp_mask, pgdat->node_id, memcg,
+ sc->priority);
+
+ /* Record the group's reclaim efficiency */
+ vmpressure(sc->gfp_mask, memcg, false,
+ sc->nr_scanned - scanned,
+ sc->nr_reclaimed - reclaimed);
+
+ } while ((memcg = mem_cgroup_iter(target_memcg, memcg, NULL)));
}
-static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
+static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
+ struct lruvec *target_lruvec;
bool reclaimable = false;
+ unsigned long file;
- do {
- struct mem_cgroup *root = sc->target_mem_cgroup;
- struct mem_cgroup_reclaim_cookie reclaim = {
- .pgdat = pgdat,
- .priority = sc->priority,
- };
- unsigned long node_lru_pages = 0;
- struct mem_cgroup *memcg;
+ target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
- memset(&sc->nr, 0, sizeof(sc->nr));
+again:
+ memset(&sc->nr, 0, sizeof(sc->nr));
- nr_reclaimed = sc->nr_reclaimed;
- nr_scanned = sc->nr_scanned;
+ nr_reclaimed = sc->nr_reclaimed;
+ nr_scanned = sc->nr_scanned;
- memcg = mem_cgroup_iter(root, NULL, &reclaim);
- do {
- unsigned long lru_pages;
- unsigned long reclaimed;
- unsigned long scanned;
+ /*
+ * Determine the scan balance between anon and file LRUs.
+ */
+ spin_lock_irq(&pgdat->lru_lock);
+ sc->anon_cost = target_lruvec->anon_cost;
+ sc->file_cost = target_lruvec->file_cost;
+ spin_unlock_irq(&pgdat->lru_lock);
- /*
- * This loop can become CPU-bound when target memcgs
- * aren't eligible for reclaim - either because they
- * don't have any reclaimable pages, or because their
- * memory is explicitly protected. Avoid soft lockups.
- */
- cond_resched();
+ /*
+ * Target desirable inactive:active list ratios for the anon
+ * and file LRU lists.
+ */
+ if (!sc->force_deactivate) {
+ unsigned long refaults;
- switch (mem_cgroup_protected(root, memcg)) {
- case MEMCG_PROT_MIN:
- /*
- * Hard protection.
- * If there is no reclaimable memory, OOM.
- */
+ refaults = lruvec_page_state(target_lruvec,
+ WORKINGSET_ACTIVATE_ANON);
+ if (refaults != target_lruvec->refaults[0] ||
+ inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
+ sc->may_deactivate |= DEACTIVATE_ANON;
+ else
+ sc->may_deactivate &= ~DEACTIVATE_ANON;
+
+ /*
+ * When refaults are being observed, it means a new
+ * workingset is being established. Deactivate to get
+ * rid of any stale active pages quickly.
+ */
+ refaults = lruvec_page_state(target_lruvec,
+ WORKINGSET_ACTIVATE_FILE);
+ if (refaults != target_lruvec->refaults[1] ||
+ inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
+ sc->may_deactivate |= DEACTIVATE_FILE;
+ else
+ sc->may_deactivate &= ~DEACTIVATE_FILE;
+ } else
+ sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
+
+ /*
+ * If we have plenty of inactive file pages that aren't
+ * thrashing, try to reclaim those first before touching
+ * anonymous pages.
+ */
+ file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
+ if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
+ sc->cache_trim_mode = 1;
+ else
+ sc->cache_trim_mode = 0;
+
+ /*
+ * Prevent the reclaimer from falling into the cache trap: as
+ * cache pages start out inactive, every cache fault will tip
+ * the scan balance towards the file LRU. And as the file LRU
+ * shrinks, so does the window for rotation from references.
+ * This means we have a runaway feedback loop where a tiny
+ * thrashing file LRU becomes infinitely more attractive than
+ * anon pages. Try to detect this based on file LRU size.
+ */
+ if (!cgroup_reclaim(sc)) {
+ unsigned long total_high_wmark = 0;
+ unsigned long free, anon;
+ int z;
+
+ free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
+ file = node_page_state(pgdat, NR_ACTIVE_FILE) +
+ node_page_state(pgdat, NR_INACTIVE_FILE);
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = &pgdat->node_zones[z];
+ if (!managed_zone(zone))
continue;
- case MEMCG_PROT_LOW:
- /*
- * Soft protection.
- * Respect the protection only as long as
- * there is an unprotected supply
- * of reclaimable memory from other cgroups.
- */
- if (!sc->memcg_low_reclaim) {
- sc->memcg_low_skipped = 1;
- continue;
- }
- memcg_memory_event(memcg, MEMCG_LOW);
- break;
- case MEMCG_PROT_NONE:
- break;
- }
- reclaimed = sc->nr_reclaimed;
- scanned = sc->nr_scanned;
- shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
- node_lru_pages += lru_pages;
-
- shrink_slab(sc->gfp_mask, pgdat->node_id,
- memcg, sc->priority);
-
- /* Record the group's reclaim efficiency */
- vmpressure(sc->gfp_mask, memcg, false,
- sc->nr_scanned - scanned,
- sc->nr_reclaimed - reclaimed);
-
- /*
- * Direct reclaim and kswapd have to scan all memory
- * cgroups to fulfill the overall scan target for the
- * node.
- *
- * Limit reclaim, on the other hand, only cares about
- * nr_to_reclaim pages to be reclaimed and it will
- * retry with decreasing priority if one round over the
- * whole hierarchy is not sufficient.
- */
- if (!global_reclaim(sc) &&
- sc->nr_reclaimed >= sc->nr_to_reclaim) {
- mem_cgroup_iter_break(root, memcg);
- break;
- }
- } while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
-
- if (reclaim_state) {
- sc->nr_reclaimed += reclaim_state->reclaimed_slab;
- reclaim_state->reclaimed_slab = 0;
- }
-
- /* Record the subtree's reclaim efficiency */
- vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
- sc->nr_scanned - nr_scanned,
- sc->nr_reclaimed - nr_reclaimed);
-
- if (sc->nr_reclaimed - nr_reclaimed)
- reclaimable = true;
-
- if (current_is_kswapd()) {
- /*
- * If reclaim is isolating dirty pages under writeback,
- * it implies that the long-lived page allocation rate
- * is exceeding the page laundering rate. Either the
- * global limits are not being effective at throttling
- * processes due to the page distribution throughout
- * zones or there is heavy usage of a slow backing
- * device. The only option is to throttle from reclaim
- * context which is not ideal as there is no guarantee
- * the dirtying process is throttled in the same way
- * balance_dirty_pages() manages.
- *
- * Once a node is flagged PGDAT_WRITEBACK, kswapd will
- * count the number of pages under pages flagged for
- * immediate reclaim and stall if any are encountered
- * in the nr_immediate check below.
- */
- if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
- set_bit(PGDAT_WRITEBACK, &pgdat->flags);
-
- /*
- * Tag a node as congested if all the dirty pages
- * scanned were backed by a congested BDI and
- * wait_iff_congested will stall.
- */
- if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
- set_bit(PGDAT_CONGESTED, &pgdat->flags);
-
- /* Allow kswapd to start writing pages during reclaim.*/
- if (sc->nr.unqueued_dirty == sc->nr.file_taken)
- set_bit(PGDAT_DIRTY, &pgdat->flags);
-
- /*
- * If kswapd scans pages marked marked for immediate
- * reclaim and under writeback (nr_immediate), it
- * implies that pages are cycling through the LRU
- * faster than they are written so also forcibly stall.
- */
- if (sc->nr.immediate)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ total_high_wmark += high_wmark_pages(zone);
}
/*
- * Legacy memcg will stall in page writeback so avoid forcibly
- * stalling in wait_iff_congested().
+ * Consider anon: if that's low too, this isn't a
+ * runaway file reclaim problem, but rather just
+ * extreme pressure. Reclaim as per usual then.
*/
- if (!global_reclaim(sc) && sane_reclaim(sc) &&
- sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
- set_memcg_congestion(pgdat, root, true);
+ anon = node_page_state(pgdat, NR_INACTIVE_ANON);
+
+ sc->file_is_tiny =
+ file + free <= total_high_wmark &&
+ !(sc->may_deactivate & DEACTIVATE_ANON) &&
+ anon >> sc->priority;
+ }
+
+ shrink_node_memcgs(pgdat, sc);
+
+ if (reclaim_state) {
+ sc->nr_reclaimed += reclaim_state->reclaimed_slab;
+ reclaim_state->reclaimed_slab = 0;
+ }
+
+ /* Record the subtree's reclaim efficiency */
+ vmpressure(sc->gfp_mask, sc->target_mem_cgroup, true,
+ sc->nr_scanned - nr_scanned,
+ sc->nr_reclaimed - nr_reclaimed);
+
+ if (sc->nr_reclaimed - nr_reclaimed)
+ reclaimable = true;
+
+ if (current_is_kswapd()) {
+ /*
+ * If reclaim is isolating dirty pages under writeback,
+ * it implies that the long-lived page allocation rate
+ * is exceeding the page laundering rate. Either the
+ * global limits are not being effective at throttling
+ * processes due to the page distribution throughout
+ * zones or there is heavy usage of a slow backing
+ * device. The only option is to throttle from reclaim
+ * context which is not ideal as there is no guarantee
+ * the dirtying process is throttled in the same way
+ * balance_dirty_pages() manages.
+ *
+ * Once a node is flagged PGDAT_WRITEBACK, kswapd will
+ * count the number of pages under pages flagged for
+ * immediate reclaim and stall if any are encountered
+ * in the nr_immediate check below.
+ */
+ if (sc->nr.writeback && sc->nr.writeback == sc->nr.taken)
+ set_bit(PGDAT_WRITEBACK, &pgdat->flags);
+
+ /* Allow kswapd to start writing pages during reclaim.*/
+ if (sc->nr.unqueued_dirty == sc->nr.file_taken)
+ set_bit(PGDAT_DIRTY, &pgdat->flags);
/*
- * Stall direct reclaim for IO completions if underlying BDIs
- * and node is congested. Allow kswapd to continue until it
- * starts encountering unqueued dirty pages or cycling through
- * the LRU too quickly.
+ * If kswapd scans pages marked for immediate
+ * reclaim and under writeback (nr_immediate), it
+ * implies that pages are cycling through the LRU
+ * faster than they are written so also forcibly stall.
*/
- if (!sc->hibernation_mode && !current_is_kswapd() &&
- current_may_throttle() && pgdat_memcg_congested(pgdat, root))
- wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+ if (sc->nr.immediate)
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+ }
- } while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
- sc->nr_scanned - nr_scanned, sc));
+ /*
+ * Tag a node/memcg as congested if all the dirty pages
+ * scanned were backed by a congested BDI and
+ * wait_iff_congested will stall.
+ *
+ * Legacy memcg will stall in page writeback so avoid forcibly
+ * stalling in wait_iff_congested().
+ */
+ if ((current_is_kswapd() ||
+ (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) &&
+ sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+ set_bit(LRUVEC_CONGESTED, &target_lruvec->flags);
+
+ /*
+ * Stall direct reclaim for IO completions if underlying BDIs
+ * and node is congested. Allow kswapd to continue until it
+ * starts encountering unqueued dirty pages or cycling through
+ * the LRU too quickly.
+ */
+ if (!current_is_kswapd() && current_may_throttle() &&
+ !sc->hibernation_mode &&
+ test_bit(LRUVEC_CONGESTED, &target_lruvec->flags))
+ wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+
+ if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
+ sc))
+ goto again;
/*
* Kswapd gives up on balancing particular nodes after too
@@ -2858,8 +2962,6 @@
*/
if (reclaimable)
pgdat->kswapd_failures = 0;
-
- return reclaimable;
}
/*
@@ -2928,7 +3030,7 @@
* Take care memory controller reclaiming has small influence
* to global LRU.
*/
- if (global_reclaim(sc)) {
+ if (!cgroup_reclaim(sc)) {
if (!cpuset_zone_allowed(zone,
GFP_KERNEL | __GFP_HARDWALL))
continue;
@@ -2987,19 +3089,17 @@
sc->gfp_mask = orig_mask;
}
-static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
+static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
{
- struct mem_cgroup *memcg;
+ struct lruvec *target_lruvec;
+ unsigned long refaults;
- memcg = mem_cgroup_iter(root_memcg, NULL, NULL);
- do {
- unsigned long refaults;
- struct lruvec *lruvec;
-
- lruvec = mem_cgroup_lruvec(pgdat, memcg);
- refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
- lruvec->refaults = refaults;
- } while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
+ target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_ANON);
+ target_lruvec->refaults[0] = refaults;
+ refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE_FILE);
+ target_lruvec->refaults[1] = refaults;
+ trace_android_vh_snapshot_refaults(target_lruvec);
}
/*
@@ -3028,7 +3128,7 @@
retry:
delayacct_freepages_start();
- if (global_reclaim(sc))
+ if (!cgroup_reclaim(sc))
__count_zid_vm_events(ALLOCSTALL, sc->reclaim_idx, 1);
do {
@@ -3057,8 +3157,16 @@
if (zone->zone_pgdat == last_pgdat)
continue;
last_pgdat = zone->zone_pgdat;
+
snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat);
- set_memcg_congestion(last_pgdat, sc->target_mem_cgroup, false);
+
+ if (cgroup_reclaim(sc)) {
+ struct lruvec *lruvec;
+
+ lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup,
+ zone->zone_pgdat);
+ clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
+ }
}
delayacct_freepages_end();
@@ -3070,9 +3178,26 @@
if (sc->compaction_ready)
return 1;
+ /*
+ * We make inactive:active ratio decisions based on the node's
+ * composition of memory, but a restrictive reclaim_idx or a
+ * memory.low cgroup setting can exempt large amounts of
+ * memory from reclaim. Neither of which are very common, so
+ * instead of doing costly eligibility calculations of the
+ * entire cgroup subtree up front, we assume the estimates are
+ * good, and retry with forcible deactivation if that fails.
+ */
+ if (sc->skipped_deactivate) {
+ sc->priority = initial_priority;
+ sc->force_deactivate = 1;
+ sc->skipped_deactivate = 0;
+ goto retry;
+ }
+
/* Untapped cgroup reserves? Don't OOM, retry. */
if (sc->memcg_low_skipped) {
sc->priority = initial_priority;
+ sc->force_deactivate = 0;
sc->memcg_low_reclaim = 1;
sc->memcg_low_skipped = 0;
goto retry;
@@ -3112,8 +3237,8 @@
/* kswapd must be awake if processes are being throttled */
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
- if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
- WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+ if (READ_ONCE(pgdat->kswapd_highest_zoneidx) > ZONE_NORMAL)
+ WRITE_ONCE(pgdat->kswapd_highest_zoneidx, ZONE_NORMAL);
wake_up_interruptible(&pgdat->kswapd_wait);
}
@@ -3246,25 +3371,26 @@
if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
return 1;
- trace_mm_vmscan_direct_reclaim_begin(order,
- sc.may_writepage,
- sc.gfp_mask,
- sc.reclaim_idx);
+ set_task_reclaim_state(current, &sc.reclaim_state);
+ trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+ set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
#ifdef CONFIG_MEMCG
+/* Only used by soft limit reclaim. Do not reuse for anything else. */
unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
gfp_t gfp_mask, bool noswap,
pg_data_t *pgdat,
unsigned long *nr_scanned)
{
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
struct scan_control sc = {
.nr_to_reclaim = SWAP_CLUSTER_MAX,
.target_mem_cgroup = memcg,
@@ -3273,15 +3399,14 @@
.reclaim_idx = MAX_NR_ZONES - 1,
.may_swap = !noswap,
};
- unsigned long lru_pages;
+
+ WARN_ON_ONCE(!current->reclaim_state);
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
- sc.may_writepage,
- sc.gfp_mask,
- sc.reclaim_idx);
+ sc.gfp_mask);
/*
* NOTE: Although we can get the priority field, using it
@@ -3290,11 +3415,12 @@
* will pick up pages from other mem cgroup's as well. We hack
* the priority and make it zero.
*/
- shrink_node_memcg(pgdat, memcg, &sc, &lru_pages);
+ shrink_lruvec(lruvec, &sc);
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
*nr_scanned = sc.nr_scanned;
+
return sc.nr_reclaimed;
}
@@ -3303,10 +3429,7 @@
gfp_t gfp_mask,
bool may_swap)
{
- struct zonelist *zonelist;
unsigned long nr_reclaimed;
- unsigned long pflags;
- int nid;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
@@ -3319,78 +3442,101 @@
.may_unmap = 1,
.may_swap = may_swap,
};
-
/*
- * Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
- * take care of from where we get pages. So the node where we start the
- * scan does not need to be the current node.
+ * Traverse the ZONELIST_FALLBACK zonelist of the current node to put
+ * equal pressure on all the nodes. This is based on the assumption that
+ * the reclaim does not bail out early.
*/
- nid = mem_cgroup_select_victim_node(memcg);
+ struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
- zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
-
- trace_mm_vmscan_memcg_reclaim_begin(0,
- sc.may_writepage,
- sc.gfp_mask,
- sc.reclaim_idx);
-
- psi_memstall_enter(&pflags);
+ set_task_reclaim_state(current, &sc.reclaim_state);
+ trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
memalloc_noreclaim_restore(noreclaim_flag);
- psi_memstall_leave(&pflags);
-
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+ set_task_reclaim_state(current, NULL);
return nr_reclaimed;
}
+EXPORT_SYMBOL_GPL(try_to_free_mem_cgroup_pages);
#endif
static void age_active_anon(struct pglist_data *pgdat,
struct scan_control *sc)
{
struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
if (!total_swap_pages)
return;
+ lruvec = mem_cgroup_lruvec(NULL, pgdat);
+ if (!inactive_is_low(lruvec, LRU_INACTIVE_ANON))
+ return;
+
memcg = mem_cgroup_iter(NULL, NULL, NULL);
do {
- struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
-
- if (inactive_list_is_low(lruvec, false, sc, true))
- shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
- sc, LRU_ACTIVE_ANON);
-
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
+ sc, LRU_ACTIVE_ANON);
memcg = mem_cgroup_iter(NULL, memcg, NULL);
} while (memcg);
}
+static bool pgdat_watermark_boosted(pg_data_t *pgdat, int highest_zoneidx)
+{
+ int i;
+ struct zone *zone;
+
+ /*
+ * Check for watermark boosts top-down as the higher zones
+ * are more likely to be boosted. Both watermarks and boosts
+ * should not be checked at the same time as reclaim would
+ * start prematurely when there is no boosting and a lower
+ * zone is balanced.
+ */
+ for (i = highest_zoneidx; i >= 0; i--) {
+ zone = pgdat->node_zones + i;
+ if (!managed_zone(zone))
+ continue;
+
+ if (zone->watermark_boost)
+ return true;
+ }
+
+ return false;
+}
+
/*
* Returns true if there is an eligible zone balanced for the request order
- * and classzone_idx
+ * and highest_zoneidx
*/
-static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
+static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long mark = -1;
struct zone *zone;
- for (i = 0; i <= classzone_idx; i++) {
+ /*
+ * Check watermarks bottom-up as lower zones are more likely to
+ * meet watermarks.
+ */
+ for (i = 0; i <= highest_zoneidx; i++) {
zone = pgdat->node_zones + i;
if (!managed_zone(zone))
continue;
mark = high_wmark_pages(zone);
- if (zone_watermark_ok_safe(zone, order, mark, classzone_idx))
+ if (zone_watermark_ok_safe(zone, order, mark, highest_zoneidx))
return true;
}
/*
- * If a node has no populated zone within classzone_idx, it does not
+ * If a node has no populated zone within highest_zoneidx, it does not
* need balancing by definition. This can happen if a zone-restricted
* allocation tries to wake a remote kswapd.
*/
@@ -3403,7 +3549,9 @@
/* Clear pgdat state for congested, dirty or under writeback. */
static void clear_pgdat_congested(pg_data_t *pgdat)
{
- clear_bit(PGDAT_CONGESTED, &pgdat->flags);
+ struct lruvec *lruvec = mem_cgroup_lruvec(NULL, pgdat);
+
+ clear_bit(LRUVEC_CONGESTED, &lruvec->flags);
clear_bit(PGDAT_DIRTY, &pgdat->flags);
clear_bit(PGDAT_WRITEBACK, &pgdat->flags);
}
@@ -3414,7 +3562,8 @@
*
* Returns true if kswapd is ready to sleep
*/
-static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
+static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order,
+ int highest_zoneidx)
{
/*
* The throttled processes are normally woken up in balance_pgdat() as
@@ -3436,7 +3585,7 @@
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
return true;
- if (pgdat_balanced(pgdat, order, classzone_idx)) {
+ if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
clear_pgdat_congested(pgdat);
return true;
}
@@ -3496,37 +3645,57 @@
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
- * found to have free_pages <= high_wmark_pages(zone), any page is that zone
+ * found to have free_pages <= high_wmark_pages(zone), any page in that zone
* or lower is eligible for reclaim until at least one usable zone is
* balanced.
*/
-static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx)
+static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
{
int i;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
unsigned long pflags;
+ unsigned long nr_boost_reclaim;
+ unsigned long zone_boosts[MAX_NR_ZONES] = { 0, };
+ bool boosted;
struct zone *zone;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.order = order,
- .priority = DEF_PRIORITY,
- .may_writepage = !laptop_mode,
.may_unmap = 1,
- .may_swap = 1,
};
+ set_task_reclaim_state(current, &sc.reclaim_state);
psi_memstall_enter(&pflags);
__fs_reclaim_acquire();
count_vm_event(PAGEOUTRUN);
+ /*
+ * Account for the reclaim boost. Note that the zone boost is left in
+ * place so that parallel allocations that are near the watermark will
+ * stall or direct reclaim until kswapd is finished.
+ */
+ nr_boost_reclaim = 0;
+ for (i = 0; i <= highest_zoneidx; i++) {
+ zone = pgdat->node_zones + i;
+ if (!managed_zone(zone))
+ continue;
+
+ nr_boost_reclaim += zone->watermark_boost;
+ zone_boosts[i] = zone->watermark_boost;
+ }
+ boosted = nr_boost_reclaim;
+
+restart:
+ sc.priority = DEF_PRIORITY;
do {
unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
+ bool balanced;
bool ret;
- sc.reclaim_idx = classzone_idx;
+ sc.reclaim_idx = highest_zoneidx;
/*
* If the number of buffer_heads exceeds the maximum allowed
@@ -3550,12 +3719,38 @@
}
/*
- * Only reclaim if there are no eligible zones. Note that
- * sc.reclaim_idx is not used as buffer_heads_over_limit may
- * have adjusted it.
+ * If the pgdat is imbalanced then ignore boosting and preserve
+ * the watermarks for a later time and restart. Note that the
+ * zone watermarks will be still reset at the end of balancing
+ * on the grounds that the normal reclaim should be enough to
+ * re-evaluate if boosting is required when kswapd next wakes.
*/
- if (pgdat_balanced(pgdat, sc.order, classzone_idx))
+ balanced = pgdat_balanced(pgdat, sc.order, highest_zoneidx);
+ if (!balanced && nr_boost_reclaim) {
+ nr_boost_reclaim = 0;
+ goto restart;
+ }
+
+ /*
+ * If boosting is not active then only reclaim if there are no
+ * eligible zones. Note that sc.reclaim_idx is not used as
+ * buffer_heads_over_limit may have adjusted it.
+ */
+ if (!nr_boost_reclaim && balanced)
goto out;
+
+ /* Limit the priority of boosting to avoid reclaim writeback */
+ if (nr_boost_reclaim && sc.priority == DEF_PRIORITY - 2)
+ raise_priority = false;
+
+ /*
+ * Do not writeback or swap pages for boosted reclaim. The
+ * intent is to relieve pressure not issue sub-optimal IO
+ * from reclaim context. If no pages are reclaimed, the
+ * reclaim will be aborted.
+ */
+ sc.may_writepage = !laptop_mode && !nr_boost_reclaim;
+ sc.may_swap = !nr_boost_reclaim;
/*
* Do some background aging of the anon list, to give
@@ -3608,6 +3803,16 @@
* progress in reclaiming pages
*/
nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
+ nr_boost_reclaim -= min(nr_boost_reclaim, nr_reclaimed);
+
+ /*
+ * If reclaim made no progress for a boost, stop reclaim as
+ * IO cannot be queued and it could be an infinite loop in
+ * extreme circumstances.
+ */
+ if (nr_boost_reclaim && !nr_reclaimed)
+ break;
+
if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
@@ -3616,9 +3821,33 @@
pgdat->kswapd_failures++;
out:
+ /* If reclaim was boosted, account for the reclaim done in this pass */
+ if (boosted) {
+ unsigned long flags;
+
+ for (i = 0; i <= highest_zoneidx; i++) {
+ if (!zone_boosts[i])
+ continue;
+
+ /* Increments are under the zone lock */
+ zone = pgdat->node_zones + i;
+ spin_lock_irqsave(&zone->lock, flags);
+ zone->watermark_boost -= min(zone->watermark_boost, zone_boosts[i]);
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+
+ /*
+ * As there is now likely space, wakeup kcompact to defragment
+ * pageblocks.
+ */
+ wakeup_kcompactd(pgdat, pageblock_order, highest_zoneidx);
+ }
+
snapshot_refaults(NULL, pgdat);
__fs_reclaim_release();
psi_memstall_leave(&pflags);
+ set_task_reclaim_state(current, NULL);
+
/*
* Return the order kswapd stopped reclaiming at as
* prepare_kswapd_sleep() takes it into account. If another caller
@@ -3629,22 +3858,22 @@
}
/*
- * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be
- * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not
- * a valid index then either kswapd runs for first time or kswapd couldn't sleep
- * after previous reclaim attempt (node is still unbalanced). In that case
- * return the zone index of the previous kswapd reclaim cycle.
+ * The pgdat->kswapd_highest_zoneidx is used to pass the highest zone index to
+ * be reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is
+ * not a valid index then either kswapd runs for first time or kswapd couldn't
+ * sleep after previous reclaim attempt (node is still unbalanced). In that
+ * case return the zone index of the previous kswapd reclaim cycle.
*/
-static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
- enum zone_type prev_classzone_idx)
+static enum zone_type kswapd_highest_zoneidx(pg_data_t *pgdat,
+ enum zone_type prev_highest_zoneidx)
{
- enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+ enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
- return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
+ return curr_idx == MAX_NR_ZONES ? prev_highest_zoneidx : curr_idx;
}
static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
- unsigned int classzone_idx)
+ unsigned int highest_zoneidx)
{
long remaining = 0;
DEFINE_WAIT(wait);
@@ -3661,7 +3890,7 @@
* eligible zone balanced that it's also unlikely that compaction will
* succeed.
*/
- if (prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
+ if (prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
/*
* Compaction records what page blocks it recently failed to
* isolate pages from and skips them in the future scanning.
@@ -3674,18 +3903,19 @@
* We have freed the memory, now we should compact it to make
* allocation of the requested order possible.
*/
- wakeup_kcompactd(pgdat, alloc_order, classzone_idx);
+ wakeup_kcompactd(pgdat, alloc_order, highest_zoneidx);
remaining = schedule_timeout(HZ/10);
/*
- * If woken prematurely then reset kswapd_classzone_idx and
+ * If woken prematurely then reset kswapd_highest_zoneidx and
* order. The values will either be from a wakeup request or
* the previous request that slept prematurely.
*/
if (remaining) {
- WRITE_ONCE(pgdat->kswapd_classzone_idx,
- kswapd_classzone_idx(pgdat, classzone_idx));
+ WRITE_ONCE(pgdat->kswapd_highest_zoneidx,
+ kswapd_highest_zoneidx(pgdat,
+ highest_zoneidx));
if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
@@ -3700,7 +3930,7 @@
* go fully to sleep until explicitly woken up.
*/
if (!remaining &&
- prepare_kswapd_sleep(pgdat, reclaim_order, classzone_idx)) {
+ prepare_kswapd_sleep(pgdat, reclaim_order, highest_zoneidx)) {
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
/*
@@ -3742,18 +3972,13 @@
static int kswapd(void *p)
{
unsigned int alloc_order, reclaim_order;
- unsigned int classzone_idx = MAX_NR_ZONES - 1;
+ unsigned int highest_zoneidx = MAX_NR_ZONES - 1;
pg_data_t *pgdat = (pg_data_t*)p;
struct task_struct *tsk = current;
-
- struct reclaim_state reclaim_state = {
- .reclaimed_slab = 0,
- };
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
if (!cpumask_empty(cpumask))
set_cpus_allowed_ptr(tsk, cpumask);
- current->reclaim_state = &reclaim_state;
/*
* Tell the memory management that we're a "memory allocator",
@@ -3771,22 +3996,24 @@
set_freezable();
WRITE_ONCE(pgdat->kswapd_order, 0);
- WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
+ WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
for ( ; ; ) {
bool ret;
alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
- classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
+ highest_zoneidx = kswapd_highest_zoneidx(pgdat,
+ highest_zoneidx);
kswapd_try_sleep:
kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
- classzone_idx);
+ highest_zoneidx);
- /* Read the new order and classzone_idx */
+ /* Read the new order and highest_zoneidx */
alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
- classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
+ highest_zoneidx = kswapd_highest_zoneidx(pgdat,
+ highest_zoneidx);
WRITE_ONCE(pgdat->kswapd_order, 0);
- WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
+ WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES);
ret = try_to_freeze();
if (kthread_should_stop())
@@ -3807,17 +4034,57 @@
* but kcompactd is woken to compact for the original
* request (alloc_order).
*/
- trace_mm_vmscan_kswapd_wake(pgdat->node_id, classzone_idx,
+ trace_mm_vmscan_kswapd_wake(pgdat->node_id, highest_zoneidx,
alloc_order);
- reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
+ reclaim_order = balance_pgdat(pgdat, alloc_order,
+ highest_zoneidx);
if (reclaim_order < alloc_order)
goto kswapd_try_sleep;
}
tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
- current->reclaim_state = NULL;
return 0;
+}
+
+static int kswapd_per_node_run(int nid)
+{
+ pg_data_t *pgdat = NODE_DATA(nid);
+ int hid;
+ int ret = 0;
+
+ for (hid = 0; hid < kswapd_threads; ++hid) {
+ pgdat->mkswapd[hid] = kthread_run(kswapd, pgdat, "kswapd%d:%d",
+ nid, hid);
+ if (IS_ERR(pgdat->mkswapd[hid])) {
+ /* failure at boot is fatal */
+ WARN_ON(system_state < SYSTEM_RUNNING);
+ pr_err("Failed to start kswapd%d on node %d\n",
+ hid, nid);
+ ret = PTR_ERR(pgdat->mkswapd[hid]);
+ pgdat->mkswapd[hid] = NULL;
+ continue;
+ }
+ if (!pgdat->kswapd)
+ pgdat->kswapd = pgdat->mkswapd[hid];
+ }
+
+ return ret;
+}
+
+static void kswapd_per_node_stop(int nid)
+{
+ int hid = 0;
+ struct task_struct *kswapd;
+
+ for (hid = 0; hid < kswapd_threads; hid++) {
+ kswapd = NODE_DATA(nid)->mkswapd[hid];
+ if (kswapd) {
+ kthread_stop(kswapd);
+ NODE_DATA(nid)->mkswapd[hid] = NULL;
+ }
+ }
+ NODE_DATA(nid)->kswapd = NULL;
}
/*
@@ -3828,7 +4095,7 @@
* needed.
*/
void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
- enum zone_type classzone_idx)
+ enum zone_type highest_zoneidx)
{
pg_data_t *pgdat;
enum zone_type curr_idx;
@@ -3840,10 +4107,10 @@
return;
pgdat = zone->zone_pgdat;
- curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+ curr_idx = READ_ONCE(pgdat->kswapd_highest_zoneidx);
- if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
- WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+ if (curr_idx == MAX_NR_ZONES || curr_idx < highest_zoneidx)
+ WRITE_ONCE(pgdat->kswapd_highest_zoneidx, highest_zoneidx);
if (READ_ONCE(pgdat->kswapd_order) < order)
WRITE_ONCE(pgdat->kswapd_order, order);
@@ -3853,7 +4120,8 @@
/* Hopeless node, leave it to direct reclaim if possible */
if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
- pgdat_balanced(pgdat, order, classzone_idx)) {
+ (pgdat_balanced(pgdat, order, highest_zoneidx) &&
+ !pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
/*
* There may be plenty of free memory available, but it's too
* fragmented for high-order allocations. Wake up kcompactd
@@ -3862,11 +4130,11 @@
* ratelimit its work.
*/
if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
- wakeup_kcompactd(pgdat, order, classzone_idx);
+ wakeup_kcompactd(pgdat, order, highest_zoneidx);
return;
}
- trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order,
+ trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, highest_zoneidx, order,
gfp_flags);
wake_up_interruptible(&pgdat->kswapd_wait);
}
@@ -3882,7 +4150,6 @@
*/
unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
{
- struct reclaim_state reclaim_state;
struct scan_control sc = {
.nr_to_reclaim = nr_to_reclaim,
.gfp_mask = GFP_HIGHUSER_MOVABLE,
@@ -3894,45 +4161,22 @@
.hibernation_mode = 1,
};
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
- struct task_struct *p = current;
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
fs_reclaim_acquire(sc.gfp_mask);
noreclaim_flag = memalloc_noreclaim_save();
- reclaim_state.reclaimed_slab = 0;
- p->reclaim_state = &reclaim_state;
+ set_task_reclaim_state(current, &sc.reclaim_state);
nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
- p->reclaim_state = NULL;
+ set_task_reclaim_state(current, NULL);
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */
-
-/* It's optimal to keep kswapds on the same CPUs as their memory, but
- not required for correctness. So if the last cpu in a node goes
- away, we get changed to run anywhere: as the first one comes back,
- restore their cpu bindings. */
-static int kswapd_cpu_online(unsigned int cpu)
-{
- int nid;
-
- for_each_node_state(nid, N_MEMORY) {
- pg_data_t *pgdat = NODE_DATA(nid);
- const struct cpumask *mask;
-
- mask = cpumask_of_node(pgdat->node_id);
-
- if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
- /* One of our CPUs online: restore mask */
- set_cpus_allowed_ptr(pgdat->kswapd, mask);
- }
- return 0;
-}
/*
* This kswapd start function will be called by init and node-hot-add.
@@ -3945,6 +4189,9 @@
if (pgdat->kswapd)
return 0;
+
+ if (kswapd_threads > 1)
+ return kswapd_per_node_run(nid);
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
if (IS_ERR(pgdat->kswapd)) {
@@ -3965,6 +4212,11 @@
{
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
+ if (kswapd_threads > 1) {
+ kswapd_per_node_stop(nid);
+ return;
+ }
+
if (kswapd) {
kthread_stop(kswapd);
NODE_DATA(nid)->kswapd = NULL;
@@ -3973,15 +4225,11 @@
static int __init kswapd_init(void)
{
- int nid, ret;
+ int nid;
swap_setup();
for_each_node_state(nid, N_MEMORY)
kswapd_run(nid);
- ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
- "mm/vmscan:online", kswapd_cpu_online,
- NULL);
- WARN_ON(ret < 0);
return 0;
}
@@ -3996,10 +4244,13 @@
*/
int node_reclaim_mode __read_mostly;
-#define RECLAIM_OFF 0
-#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
-#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
-#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
+/*
+ * These bit locations are exposed in the vm.zone_reclaim_mode sysctl
+ * ABI. New bits are OK, but existing bits can never change.
+ */
+#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
+#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
+#define RECLAIM_UNMAP (1<<2) /* Unmap pages during reclaim */
/*
* Priority for NODE_RECLAIM. This determines the fraction of pages
@@ -4070,7 +4321,6 @@
/* Minimum pages needed in order to stay on node */
const unsigned long nr_pages = 1 << order;
struct task_struct *p = current;
- struct reclaim_state reclaim_state;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
@@ -4083,6 +4333,9 @@
.reclaim_idx = gfp_zone(gfp_mask),
};
+ trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
+ sc.gfp_mask);
+
cond_resched();
fs_reclaim_acquire(sc.gfp_mask);
/*
@@ -4092,8 +4345,7 @@
*/
noreclaim_flag = memalloc_noreclaim_save();
p->flags |= PF_SWAPWRITE;
- reclaim_state.reclaimed_slab = 0;
- p->reclaim_state = &reclaim_state;
+ set_task_reclaim_state(p, &sc.reclaim_state);
if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
/*
@@ -4105,10 +4357,13 @@
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
}
- p->reclaim_state = NULL;
+ set_task_reclaim_state(p, NULL);
current->flags &= ~PF_SWAPWRITE;
memalloc_noreclaim_restore(noreclaim_flag);
fs_reclaim_release(sc.gfp_mask);
+
+ trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);
+
return sc.nr_reclaimed >= nr_pages;
}
@@ -4127,7 +4382,8 @@
* unmapped file backed pages.
*/
if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
- node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+ node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B) <=
+ pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;
/*
@@ -4158,29 +4414,6 @@
}
#endif
-/*
- * page_evictable - test whether a page is evictable
- * @page: the page to test
- *
- * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
- *
- * Reasons page might not be evictable:
- * (1) page's mapping marked unevictable
- * (2) page is part of an mlocked VMA
- *
- */
-int page_evictable(struct page *page)
-{
- int ret;
-
- /* Prevent address_space of inode and swap cache from being freed */
- rcu_read_lock();
- ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
- rcu_read_unlock();
- return ret;
-}
-
/**
* check_move_unevictable_pages - check pages for evictability and move to
* appropriate zone lru list
@@ -4201,8 +4434,14 @@
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
struct pglist_data *pagepgdat = page_pgdat(page);
+ int nr_pages;
- pgscanned++;
+ if (PageTransTail(page))
+ continue;
+
+ nr_pages = thp_nr_pages(page);
+ pgscanned += nr_pages;
+
if (pagepgdat != pgdat) {
if (pgdat)
spin_unlock_irq(&pgdat->lru_lock);
@@ -4221,7 +4460,7 @@
ClearPageUnevictable(page);
del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
add_page_to_lru_list(page, lruvec, lru);
- pgrescued++;
+ pgrescued += nr_pages;
}
}
--
Gitblit v1.6.2