aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/compaction.c249
-rw-r--r--mm/filemap.c341
-rw-r--r--mm/internal.h22
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memory-failure.c4
-rw-r--r--mm/memory_hotplug.c2
-rw-r--r--mm/mempolicy.c4
-rw-r--r--mm/migrate.c56
-rw-r--r--mm/mincore.c20
-rw-r--r--mm/page_alloc.c62
-rw-r--r--mm/readahead.c27
-rw-r--r--mm/shmem.c122
-rw-r--r--mm/swap.c51
-rw-r--r--mm/truncate.c74
-rw-r--r--mm/vmscan.c36
15 files changed, 697 insertions, 375 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index 5e38e5706f62..4229fc22a477 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -89,7 +89,8 @@ static void __reset_isolation_suitable(struct zone *zone)
unsigned long end_pfn = zone_end_pfn(zone);
unsigned long pfn;
- zone->compact_cached_migrate_pfn = start_pfn;
+ zone->compact_cached_migrate_pfn[0] = start_pfn;
+ zone->compact_cached_migrate_pfn[1] = start_pfn;
zone->compact_cached_free_pfn = end_pfn;
zone->compact_blockskip_flush = false;
@@ -131,9 +132,10 @@ void reset_isolation_suitable(pg_data_t *pgdat)
*/
static void update_pageblock_skip(struct compact_control *cc,
struct page *page, unsigned long nr_isolated,
- bool migrate_scanner)
+ bool set_unsuitable, bool migrate_scanner)
{
struct zone *zone = cc->zone;
+ unsigned long pfn;
if (cc->ignore_skip_hint)
return;
@@ -141,20 +143,32 @@ static void update_pageblock_skip(struct compact_control *cc,
if (!page)
return;
- if (!nr_isolated) {
- unsigned long pfn = page_to_pfn(page);
+ if (nr_isolated)
+ return;
+
+ /*
+ * Only skip pageblocks when all forms of compaction will be known to
+ * fail in the near future.
+ */
+ if (set_unsuitable)
set_pageblock_skip(page);
- /* Update where compaction should restart */
- if (migrate_scanner) {
- if (!cc->finished_update_migrate &&
- pfn > zone->compact_cached_migrate_pfn)
- zone->compact_cached_migrate_pfn = pfn;
- } else {
- if (!cc->finished_update_free &&
- pfn < zone->compact_cached_free_pfn)
- zone->compact_cached_free_pfn = pfn;
- }
+ pfn = page_to_pfn(page);
+
+ /* Update where async and sync compaction should restart */
+ if (migrate_scanner) {
+ if (cc->finished_update_migrate)
+ return;
+ if (pfn > zone->compact_cached_migrate_pfn[0])
+ zone->compact_cached_migrate_pfn[0] = pfn;
+ if (cc->mode != MIGRATE_ASYNC &&
+ pfn > zone->compact_cached_migrate_pfn[1])
+ zone->compact_cached_migrate_pfn[1] = pfn;
+ } else {
+ if (cc->finished_update_free)
+ return;
+ if (pfn < zone->compact_cached_free_pfn)
+ zone->compact_cached_free_pfn = pfn;
}
}
#else
@@ -166,7 +180,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
static void update_pageblock_skip(struct compact_control *cc,
struct page *page, unsigned long nr_isolated,
- bool migrate_scanner)
+ bool set_unsuitable, bool migrate_scanner)
{
}
#endif /* CONFIG_COMPACTION */
@@ -195,7 +209,7 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
}
/* async aborts if taking too long or contended */
- if (!cc->sync) {
+ if (cc->mode == MIGRATE_ASYNC) {
cc->contended = true;
return false;
}
@@ -208,10 +222,28 @@ static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
return true;
}
-static inline bool compact_trylock_irqsave(spinlock_t *lock,
- unsigned long *flags, struct compact_control *cc)
+/*
+ * Aside from avoiding lock contention, compaction also periodically checks
+ * need_resched() and either schedules in sync compaction or aborts async
+ * compaction. This is similar to what compact_checklock_irqsave() does, but
+ * is used where no lock is concerned.
+ *
+ * Returns false when no scheduling was needed, or sync compaction scheduled.
+ * Returns true when async compaction should abort.
+ */
+static inline bool compact_should_abort(struct compact_control *cc)
{
- return compact_checklock_irqsave(lock, flags, false, cc);
+ /* async compaction aborts if contended */
+ if (need_resched()) {
+ if (cc->mode == MIGRATE_ASYNC) {
+ cc->contended = true;
+ return true;
+ }
+
+ cond_resched();
+ }
+
+ return false;
}
/* Returns true if the page is within a block suitable for migration to */
@@ -329,7 +361,8 @@ isolate_fail:
/* Update the pageblock-skip if the whole pageblock was scanned */
if (blockpfn == end_pfn)
- update_pageblock_skip(cc, valid_page, total_isolated, false);
+ update_pageblock_skip(cc, valid_page, total_isolated, true,
+ false);
count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
if (total_isolated)
@@ -464,8 +497,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
unsigned long flags;
bool locked = false;
struct page *page = NULL, *valid_page = NULL;
- bool skipped_async_unsuitable = false;
- const isolate_mode_t mode = (!cc->sync ? ISOLATE_ASYNC_MIGRATE : 0) |
+ bool set_unsuitable = true;
+ const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
+ ISOLATE_ASYNC_MIGRATE : 0) |
(unevictable ? ISOLATE_UNEVICTABLE : 0);
/*
@@ -475,7 +509,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/
while (unlikely(too_many_isolated(zone))) {
/* async migration should just abort */
- if (!cc->sync)
+ if (cc->mode == MIGRATE_ASYNC)
return 0;
congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -484,8 +518,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
return 0;
}
+ if (compact_should_abort(cc))
+ return 0;
+
/* Time to isolate some pages for migration */
- cond_resched();
for (; low_pfn < end_pfn; low_pfn++) {
/* give a chance to irqs before checking need_resched() */
if (locked && !(low_pfn % SWAP_CLUSTER_MAX)) {
@@ -540,9 +576,9 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
* the minimum amount of work satisfies the allocation
*/
mt = get_pageblock_migratetype(page);
- if (!cc->sync && !migrate_async_suitable(mt)) {
- cc->finished_update_migrate = true;
- skipped_async_unsuitable = true;
+ if (cc->mode == MIGRATE_ASYNC &&
+ !migrate_async_suitable(mt)) {
+ set_unsuitable = false;
goto next_pageblock;
}
}
@@ -646,11 +682,10 @@ next_pageblock:
/*
* Update the pageblock-skip information and cached scanner pfn,
* if the whole pageblock was scanned without isolating any page.
- * This is not done when pageblock was skipped due to being unsuitable
- * for async compaction, so that eventual sync compaction can try.
*/
- if (low_pfn == end_pfn && !skipped_async_unsuitable)
- update_pageblock_skip(cc, valid_page, nr_isolated, true);
+ if (low_pfn == end_pfn)
+ update_pageblock_skip(cc, valid_page, nr_isolated,
+ set_unsuitable, true);
trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
@@ -671,7 +706,9 @@ static void isolate_freepages(struct zone *zone,
struct compact_control *cc)
{
struct page *page;
- unsigned long high_pfn, low_pfn, pfn, z_end_pfn;
+ unsigned long block_start_pfn; /* start of current pageblock */
+ unsigned long block_end_pfn; /* end of current pageblock */
+ unsigned long low_pfn; /* lowest pfn scanner is able to scan */
int nr_freepages = cc->nr_freepages;
struct list_head *freelist = &cc->freepages;
@@ -679,41 +716,38 @@ static void isolate_freepages(struct zone *zone,
* Initialise the free scanner. The starting point is where we last
* successfully isolated from, zone-cached value, or the end of the
* zone when isolating for the first time. We need this aligned to
- * the pageblock boundary, because we do pfn -= pageblock_nr_pages
- * in the for loop.
+ * the pageblock boundary, because we do
+ * block_start_pfn -= pageblock_nr_pages in the for loop.
+ * For ending point, take care when isolating in last pageblock of a
+ * a zone which ends in the middle of a pageblock.
* The low boundary is the end of the pageblock the migration scanner
* is using.
*/
- pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+ block_start_pfn = cc->free_pfn & ~(pageblock_nr_pages-1);
+ block_end_pfn = min(block_start_pfn + pageblock_nr_pages,
+ zone_end_pfn(zone));
low_pfn = ALIGN(cc->migrate_pfn + 1, pageblock_nr_pages);
/*
- * Take care that if the migration scanner is at the end of the zone
- * that the free scanner does not accidentally move to the next zone
- * in the next isolation cycle.
- */
- high_pfn = min(low_pfn, pfn);
-
- z_end_pfn = zone_end_pfn(zone);
-
- /*
* Isolate free pages until enough are available to migrate the
* pages on cc->migratepages. We stop searching if the migrate
* and free page scanners meet or enough free pages are isolated.
*/
- for (; pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
- pfn -= pageblock_nr_pages) {
+ for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages;
+ block_end_pfn = block_start_pfn,
+ block_start_pfn -= pageblock_nr_pages) {
unsigned long isolated;
- unsigned long end_pfn;
/*
* This can iterate a massively long zone without finding any
* suitable migration targets, so periodically check if we need
- * to schedule.
+ * to schedule, or even abort async compaction.
*/
- cond_resched();
+ if (!(block_start_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
+ && compact_should_abort(cc))
+ break;
- if (!pfn_valid(pfn))
+ if (!pfn_valid(block_start_pfn))
continue;
/*
@@ -723,7 +757,7 @@ static void isolate_freepages(struct zone *zone,
* i.e. it's possible that all pages within a zones range of
* pages do not belong to a single zone.
*/
- page = pfn_to_page(pfn);
+ page = pfn_to_page(block_start_pfn);
if (page_zone(page) != zone)
continue;
@@ -736,26 +770,26 @@ static void isolate_freepages(struct zone *zone,
continue;
/* Found a block suitable for isolating free pages from */
- isolated = 0;
+ cc->free_pfn = block_start_pfn;
+ isolated = isolate_freepages_block(cc, block_start_pfn,
+ block_end_pfn, freelist, false);
+ nr_freepages += isolated;
/*
- * Take care when isolating in last pageblock of a zone which
- * ends in the middle of a pageblock.
+ * Set a flag that we successfully isolated in this pageblock.
+ * In the next loop iteration, zone->compact_cached_free_pfn
+ * will not be updated and thus it will effectively contain the
+ * highest pageblock we isolated pages from.
*/
- end_pfn = min(pfn + pageblock_nr_pages, z_end_pfn);
- isolated = isolate_freepages_block(cc, pfn, end_pfn,
- freelist, false);
- nr_freepages += isolated;
+ if (isolated)
+ cc->finished_update_free = true;
/*
- * Record the highest PFN we isolated pages from. When next
- * looking for free pages, the search will restart here as
- * page migration may have returned some pages to the allocator
+ * isolate_freepages_block() might have aborted due to async
+ * compaction being contended
*/
- if (isolated) {
- cc->finished_update_free = true;
- high_pfn = max(high_pfn, pfn);
- }
+ if (cc->contended)
+ break;
}
/* split_free_page does not map the pages */
@@ -765,10 +799,9 @@ static void isolate_freepages(struct zone *zone,
* If we crossed the migrate scanner, we want to keep it that way
* so that compact_finished() may detect this
*/
- if (pfn < low_pfn)
- cc->free_pfn = max(pfn, zone->zone_start_pfn);
- else
- cc->free_pfn = high_pfn;
+ if (block_start_pfn < low_pfn)
+ cc->free_pfn = cc->migrate_pfn;
+
cc->nr_freepages = nr_freepages;
}
@@ -783,9 +816,13 @@ static struct page *compaction_alloc(struct page *migratepage,
struct compact_control *cc = (struct compact_control *)data;
struct page *freepage;
- /* Isolate free pages if necessary */
+ /*
+ * Isolate free pages if necessary, and if we are not aborting due to
+ * contention.
+ */
if (list_empty(&cc->freepages)) {
- isolate_freepages(cc->zone, cc);
+ if (!cc->contended)
+ isolate_freepages(cc->zone, cc);
if (list_empty(&cc->freepages))
return NULL;
@@ -799,23 +836,16 @@ static struct page *compaction_alloc(struct page *migratepage,
}
/*
- * We cannot control nr_migratepages and nr_freepages fully when migration is
- * running as migrate_pages() has no knowledge of compact_control. When
- * migration is complete, we count the number of pages on the lists by hand.
+ * This is a migrate-callback that "frees" freepages back to the isolated
+ * freelist. All pages on the freelist are from the same zone, so there is no
+ * special handling needed for NUMA.
*/
-static void update_nr_listpages(struct compact_control *cc)
+static void compaction_free(struct page *page, unsigned long data)
{
- int nr_migratepages = 0;
- int nr_freepages = 0;
- struct page *page;
-
- list_for_each_entry(page, &cc->migratepages, lru)
- nr_migratepages++;
- list_for_each_entry(page, &cc->freepages, lru)
- nr_freepages++;
+ struct compact_control *cc = (struct compact_control *)data;
- cc->nr_migratepages = nr_migratepages;
- cc->nr_freepages = nr_freepages;
+ list_add(&page->lru, &cc->freepages);
+ cc->nr_freepages++;
}
/* possible outcome of isolate_migratepages */
@@ -862,13 +892,14 @@ static int compact_finished(struct zone *zone,
unsigned int order;
unsigned long watermark;
- if (fatal_signal_pending(current))
+ if (cc->contended || fatal_signal_pending(current))
return COMPACT_PARTIAL;
/* Compaction run completes if the migrate and free scanner meet */
if (cc->free_pfn <= cc->migrate_pfn) {
/* Let the next compaction start anew. */
- zone->compact_cached_migrate_pfn = zone->zone_start_pfn;
+ zone->compact_cached_migrate_pfn[0] = zone->zone_start_pfn;
+ zone->compact_cached_migrate_pfn[1] = zone->zone_start_pfn;
zone->compact_cached_free_pfn = zone_end_pfn(zone);
/*
@@ -968,6 +999,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
int ret;
unsigned long start_pfn = zone->zone_start_pfn;
unsigned long end_pfn = zone_end_pfn(zone);
+ const bool sync = cc->mode != MIGRATE_ASYNC;
ret = compaction_suitable(zone, cc->order);
switch (ret) {
@@ -993,7 +1025,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
* information on where the scanners should start but check that it
* is initialised by ensuring the values are within zone boundaries.
*/
- cc->migrate_pfn = zone->compact_cached_migrate_pfn;
+ cc->migrate_pfn = zone->compact_cached_migrate_pfn[sync];
cc->free_pfn = zone->compact_cached_free_pfn;
if (cc->free_pfn < start_pfn || cc->free_pfn > end_pfn) {
cc->free_pfn = end_pfn & ~(pageblock_nr_pages-1);
@@ -1001,7 +1033,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
}
if (cc->migrate_pfn < start_pfn || cc->migrate_pfn > end_pfn) {
cc->migrate_pfn = start_pfn;
- zone->compact_cached_migrate_pfn = cc->migrate_pfn;
+ zone->compact_cached_migrate_pfn[0] = cc->migrate_pfn;
+ zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn;
}
trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn);
@@ -1009,7 +1042,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
migrate_prep_local();
while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
- unsigned long nr_migrate, nr_remaining;
int err;
switch (isolate_migratepages(zone, cc)) {
@@ -1024,21 +1056,20 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
;
}
- nr_migrate = cc->nr_migratepages;
+ if (!cc->nr_migratepages)
+ continue;
+
err = migrate_pages(&cc->migratepages, compaction_alloc,
- (unsigned long)cc,
- cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC,
+ compaction_free, (unsigned long)cc, cc->mode,
MR_COMPACTION);
- update_nr_listpages(cc);
- nr_remaining = cc->nr_migratepages;
- trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
- nr_remaining);
+ trace_mm_compaction_migratepages(cc->nr_migratepages, err,
+ &cc->migratepages);
- /* Release isolated pages not migrated */
+ /* All pages were either migrated or will be released */
+ cc->nr_migratepages = 0;
if (err) {
putback_movable_pages(&cc->migratepages);
- cc->nr_migratepages = 0;
/*
* migrate_pages() may return -ENOMEM when scanners meet
* and we want compact_finished() to detect it
@@ -1060,9 +1091,8 @@ out:
return ret;
}
-static unsigned long compact_zone_order(struct zone *zone,
- int order, gfp_t gfp_mask,
- bool sync, bool *contended)
+static unsigned long compact_zone_order(struct zone *zone, int order,
+ gfp_t gfp_mask, enum migrate_mode mode, bool *contended)
{
unsigned long ret;
struct compact_control cc = {
@@ -1071,7 +1101,7 @@ static unsigned long compact_zone_order(struct zone *zone,
.order = order,
.migratetype = allocflags_to_migratetype(gfp_mask),
.zone = zone,
- .sync = sync,
+ .mode = mode,
};
INIT_LIST_HEAD(&cc.freepages);
INIT_LIST_HEAD(&cc.migratepages);
@@ -1093,7 +1123,7 @@ int sysctl_extfrag_threshold = 500;
* @order: The order of the current allocation
* @gfp_mask: The GFP mask of the current allocation
* @nodemask: The allowed nodes to allocate from
- * @sync: Whether migration is synchronous or not
+ * @mode: The migration mode for async, sync light, or sync migration
* @contended: Return value that is true if compaction was aborted due to lock contention
* @page: Optionally capture a free page of the requested order during compaction
*
@@ -1101,7 +1131,7 @@ int sysctl_extfrag_threshold = 500;
*/
unsigned long try_to_compact_pages(struct zonelist *zonelist,
int order, gfp_t gfp_mask, nodemask_t *nodemask,
- bool sync, bool *contended)
+ enum migrate_mode mode, bool *contended)
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1126,7 +1156,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
nodemask) {
int status;
- status = compact_zone_order(zone, order, gfp_mask, sync,
+ status = compact_zone_order(zone, order, gfp_mask, mode,
contended);
rc = max(status, rc);
@@ -1165,9 +1195,6 @@ static void __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
if (zone_watermark_ok(zone, cc->order,
low_wmark_pages(zone), 0, 0))
compaction_defer_reset(zone, cc->order, false);
- /* Currently async compaction is never deferred. */
- else if (cc->sync)
- defer_compaction(zone, cc->order);
}
VM_BUG_ON(!list_empty(&cc->freepages));
@@ -1179,7 +1206,7 @@ void compact_pgdat(pg_data_t *pgdat, int order)
{
struct compact_control cc = {
.order = order,
- .sync = false,
+ .mode = MIGRATE_ASYNC,
};
if (!order)
@@ -1192,7 +1219,7 @@ static void compact_node(int nid)
{
struct compact_control cc = {
.order = -1,
- .sync = true,
+ .mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
};
diff --git a/mm/filemap.c b/mm/filemap.c
index 4cbc4cd512e4..bdaa21555abe 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -448,6 +448,29 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
+static int page_cache_tree_insert(struct address_space *mapping,
+ struct page *page)
+{
+ void **slot;
+ int error;
+
+ slot = radix_tree_lookup_slot(&mapping->page_tree, page->index);
+ if (slot) {
+ void *p;
+
+ p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
+ if (!radix_tree_exceptional_entry(p))
+ return -EEXIST;
+ radix_tree_replace_slot(slot, page);
+ mapping->nrpages++;
+ return 0;
+ }
+ error = radix_tree_insert(&mapping->page_tree, page->index, page);
+ if (!error)
+ mapping->nrpages++;
+ return error;
+}
+
/**
* add_to_page_cache_locked - add a locked page to the pagecache
* @page: page to add
@@ -482,11 +505,10 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
page->index = offset;
spin_lock_irq(&mapping->tree_lock);
- error = radix_tree_insert(&mapping->page_tree, offset, page);
+ error = page_cache_tree_insert(mapping, page);
radix_tree_preload_end();
if (unlikely(error))
goto err_insert;
- mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
spin_unlock_irq(&mapping->tree_lock);
trace_mm_filemap_add_to_page_cache(page);
@@ -688,14 +710,101 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
}
/**
- * find_get_page - find and get a page reference
+ * page_cache_next_hole - find the next hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the
+ * lowest indexed hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'return - index >=
+ * max_scan' will be true). In rare cases of index wrap-around, 0 will
+ * be returned.
+ *
+ * page_cache_next_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 5, then subsequently a hole is created at
+ * index 10, page_cache_next_hole covering both indexes may return 10
+ * if called under rcu_read_lock.
+ */
+pgoff_t page_cache_next_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ struct page *page;
+
+ page = radix_tree_lookup(&mapping->page_tree, index);
+ if (!page || radix_tree_exceptional_entry(page))
+ break;
+ index++;
+ if (index == 0)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(page_cache_next_hole);
+
+/**
+ * page_cache_prev_hole - find the prev hole (not-present entry)
+ * @mapping: mapping
+ * @index: index
+ * @max_scan: maximum range to search
+ *
+ * Search backwards in the range [max(index-max_scan+1, 0), index] for
+ * the first hole.
+ *
+ * Returns: the index of the hole if found, otherwise returns an index
+ * outside of the set specified (in which case 'index - return >=
+ * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX
+ * will be returned.
+ *
+ * page_cache_prev_hole may be called under rcu_read_lock. However,
+ * like radix_tree_gang_lookup, this will not atomically search a
+ * snapshot of the tree at a single point in time. For example, if a
+ * hole is created at index 10, then subsequently a hole is created at
+ * index 5, page_cache_prev_hole covering both indexes may return 5 if
+ * called under rcu_read_lock.
+ */
+pgoff_t page_cache_prev_hole(struct address_space *mapping,
+ pgoff_t index, unsigned long max_scan)
+{
+ unsigned long i;
+
+ for (i = 0; i < max_scan; i++) {
+ struct page *page;
+
+ page = radix_tree_lookup(&mapping->page_tree, index);
+ if (!page || radix_tree_exceptional_entry(page))
+ break;
+ index--;
+ if (index == ULONG_MAX)
+ break;
+ }
+
+ return index;
+}
+EXPORT_SYMBOL(page_cache_prev_hole);
+
+/**
+ * find_get_entry - find and get a page cache entry
* @mapping: the address_space to search
- * @offset: the page index
+ * @offset: the page cache index
*
- * Is there a pagecache struct page at the given (mapping, offset) tuple?
- * If yes, increment its refcount and return it; if no, return NULL.
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned with an increased refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
*/
-struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
void **pagep;
struct page *page;
@@ -736,24 +845,50 @@ out:
return page;
}
-EXPORT_SYMBOL(find_get_page);
+EXPORT_SYMBOL(find_get_entry);
/**
- * find_lock_page - locate, pin and lock a pagecache page
+ * find_get_page - find and get a page reference
* @mapping: the address_space to search
* @offset: the page index
*
- * Locates the desired pagecache page, locks it, increments its reference
- * count and returns its address.
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned with an increased refcount.
*
- * Returns zero if the page was not present. find_lock_page() may sleep.
+ * Otherwise, %NULL is returned.
*/
-struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
+{
+ struct page *page = find_get_entry(mapping, offset);
+
+ if (radix_tree_exceptional_entry(page))
+ page = NULL;
+ return page;
+}
+EXPORT_SYMBOL(find_get_page);
+
+/**
+ * find_lock_entry - locate, pin and lock a page cache entry
+ * @mapping: the address_space to search
+ * @offset: the page cache index
+ *
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the slot holds a shadow entry of a previously evicted page, it
+ * is returned.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_entry() may sleep.
+ */
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset)
{
struct page *page;
repeat:
- page = find_get_page(mapping, offset);
+ page = find_get_entry(mapping, offset);
if (page && !radix_tree_exception(page)) {
lock_page(page);
/* Has the page been truncated? */
@@ -766,6 +901,29 @@ repeat:
}
return page;
}
+EXPORT_SYMBOL(find_lock_entry);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ * @mapping: the address_space to search
+ * @offset: the page index
+ *
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * Otherwise, %NULL is returned.
+ *
+ * find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
+{
+ struct page *page = find_lock_entry(mapping, offset);
+
+ if (radix_tree_exceptional_entry(page))
+ page = NULL;
+ return page;
+}
EXPORT_SYMBOL(find_lock_page);
/**
@@ -774,16 +932,18 @@ EXPORT_SYMBOL(find_lock_page);
* @index: the page's index into the mapping
* @gfp_mask: page allocation mode
*
- * Locates a page in the pagecache. If the page is not present, a new page
- * is allocated using @gfp_mask and is added to the pagecache and to the VM's
- * LRU list. The returned page is locked and has its reference count
- * incremented.
+ * Looks up the page cache slot at @mapping & @offset. If there is a
+ * page cache page, it is returned locked and with an increased
+ * refcount.
+ *
+ * If the page is not present, a new page is allocated using @gfp_mask
+ * and added to the page cache and the VM's LRU list. The page is
+ * returned locked and with an increased refcount.
*
- * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
- * allocation!
+ * On memory exhaustion, %NULL is returned.
*
- * find_or_create_page() returns the desired page's address, or zero on
- * memory exhaustion.
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an
+ * atomic allocation!
*/
struct page *find_or_create_page(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask)
@@ -816,6 +976,76 @@ repeat:
EXPORT_SYMBOL(find_or_create_page);
/**
+ * find_get_entries - gang pagecache lookup
+ * @mapping: The address_space to search
+ * @start: The starting page cache index
+ * @nr_entries: The maximum number of entries
+ * @entries: Where the resulting entries are placed
+ * @indices: The cache indices corresponding to the entries in @entries
+ *
+ * find_get_entries() will search for and return a group of up to
+ * @nr_entries entries in the mapping. The entries are placed at
+ * @entries. find_get_entries() takes a reference against any actual
+ * pages it returns.
+ *
+ * The search returns a group of mapping-contiguous page cache entries
+ * with ascending indexes. There may be holes in the indices due to
+ * not-present pages.
+ *
+ * Any shadow entries of evicted pages are included in the returned
+ * array.
+ *
+ * find_get_entries() returns the number of pages and shadow entries
+ * which were found.
+ */
+unsigned find_get_entries(struct address_space *mapping,
+ pgoff_t start, unsigned int nr_entries,
+ struct page **entries, pgoff_t *indices)
+{
+ void **slot;
+ unsigned int ret = 0;
+ struct radix_tree_iter iter;
+
+ if (!nr_entries)
+ return 0;
+
+ rcu_read_lock();
+restart:
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+ struct page *page;
+repeat:
+ page = radix_tree_deref_slot(slot);
+ if (unlikely(!page))
+ continue;
+ if (radix_tree_exception(page)) {
+ if (radix_tree_deref_retry(page))
+ goto restart;
+ /*
+ * Otherwise, we must be storing a swap entry
+ * here as an exceptional entry: so return it
+ * without attempting to raise page count.
+ */
+ goto export;
+ }
+ if (!page_cache_get_speculative(page))
+ goto repeat;
+
+ /* Has the page moved? */
+ if (unlikely(page != *slot)) {
+ page_cache_release(page);
+ goto repeat;
+ }
+export:
+ indices[ret] = iter.index;
+ entries[ret] = page;
+ if (++ret == nr_entries)
+ break;
+ }
+ rcu_read_unlock();
+ return ret;
+}
+
+/**
* find_get_pages - gang pagecache lookup
* @mapping: The address_space to search
* @start: The starting page index
@@ -1797,6 +2027,18 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
EXPORT_SYMBOL(generic_file_mmap);
EXPORT_SYMBOL(generic_file_readonly_mmap);
+static struct page *wait_on_page_read(struct page *page)
+{
+ if (!IS_ERR(page)) {
+ wait_on_page_locked(page);
+ if (!PageUptodate(page)) {
+ page_cache_release(page);
+ page = ERR_PTR(-EIO);
+ }
+ }
+ return page;
+}
+
static struct page *__read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *, struct page *),
@@ -1823,6 +2065,8 @@ repeat:
if (err < 0) {
page_cache_release(page);
page = ERR_PTR(err);
+ } else {
+ page = wait_on_page_read(page);
}
}
return page;
@@ -1859,6 +2103,10 @@ retry:
if (err < 0) {
page_cache_release(page);
return ERR_PTR(err);
+ } else {
+ page = wait_on_page_read(page);
+ if (IS_ERR(page))
+ return page;
}
out:
mark_page_accessed(page);
@@ -1866,40 +2114,25 @@ out:
}
/**
- * read_cache_page_async - read into page cache, fill it if needed
+ * read_cache_page - read into page cache, fill it if needed
* @mapping: the page's address_space
* @index: the page index
* @filler: function to perform the read
* @data: first arg to filler(data, page) function, often left as NULL
*
- * Same as read_cache_page, but don't wait for page to become unlocked
- * after submitting it to the filler.
- *
* Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page but don't wait for it to become unlocked.
+ * not set, try to fill the page and wait for it to become unlocked.
*
* If the page does not get brought uptodate, return -EIO.
*/
-struct page *read_cache_page_async(struct address_space *mapping,
+struct page *read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *, struct page *),
void *data)
{
return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
}
-EXPORT_SYMBOL(read_cache_page_async);
-
-static struct page *wait_on_page_read(struct page *page)
-{
- if (!IS_ERR(page)) {
- wait_on_page_locked(page);
- if (!PageUptodate(page)) {
- page_cache_release(page);
- page = ERR_PTR(-EIO);
- }
- }
- return page;
-}
+EXPORT_SYMBOL(read_cache_page);
/**
* read_cache_page_gfp - read into page cache, using specified page allocation flags.
@@ -1918,31 +2151,10 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
{
filler_t *filler = (filler_t *)mapping->a_ops->readpage;
- return wait_on_page_read(do_read_cache_page(mapping, index, filler, NULL, gfp));
+ return do_read_cache_page(mapping, index, filler, NULL, gfp);
}
EXPORT_SYMBOL(read_cache_page_gfp);
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping: the page's address_space
- * @index: the page index
- * @filler: function to perform the read
- * @data: first arg to filler(data, page) function, often left as NULL
- *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page then wait for it to become unlocked.
- *
- * If the page does not get brought uptodate, return -EIO.
- */
-struct page *read_cache_page(struct address_space *mapping,
- pgoff_t index,
- int (*filler)(void *, struct page *),
- void *data)
-{
- return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
-}
-EXPORT_SYMBOL(read_cache_page);
-
static size_t __iovec_copy_from_user_inatomic(char *vaddr,
const struct iovec *iov, size_t base, size_t bytes)
{
@@ -1976,7 +2188,6 @@ size_t iov_iter_copy_from_user_atomic(struct page *page,
char *kaddr;
size_t copied;
- BUG_ON(!pagefault_disabled());
kaddr = kmap_atomic(page);
if (likely(i->nr_segs == 1)) {
int left;
@@ -2350,9 +2561,7 @@ again:
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
- pagefault_disable();
copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
- pagefault_enable();
flush_dcache_page(page);
mark_page_accessed(page);
diff --git a/mm/internal.h b/mm/internal.h
index 3e910000fda4..1a8a0d4b687a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -11,6 +11,7 @@
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
+#include <linux/fs.h>
#include <linux/mm.h>
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
@@ -21,6 +22,20 @@ static inline void set_page_count(struct page *page, int v)
atomic_set(&page->_count, v);
}
+extern int __do_page_cache_readahead(struct address_space *mapping,
+ struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+ unsigned long lookahead_size);
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static inline unsigned long ra_submit(struct file_ra_state *ra,
+ struct address_space *mapping, struct file *filp)
+{
+ return __do_page_cache_readahead(mapping, filp,
+ ra->start, ra->size, ra->async_size);
+}
+
/*
* Turn a non-refcounted page (->_count == 0) into refcounted with
* a count of one.
@@ -119,7 +134,7 @@ struct compact_control {
unsigned long nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
- bool sync; /* Synchronous migration */
+ enum migrate_mode mode; /* Async or sync migration mode */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
bool finished_update_free; /* True when the zone cached pfns are
* no longer being updated
@@ -129,7 +144,10 @@ struct compact_control {
int order; /* order a direct compactor needs */
int migratetype; /* MOVABLE, RECLAIMABLE etc */
struct zone *zone;
- bool contended; /* True if a lock was contended */
+ bool contended; /* True if a lock was contended, or
+ * need_resched() true during async
+ * compaction
+ */
};
unsigned long
diff --git a/mm/madvise.c b/mm/madvise.c
index 539eeb96b323..a402f8fdc68e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
for (; start < end; start += PAGE_SIZE) {
index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- page = find_get_page(mapping, index);
+ page = find_get_entry(mapping, index);
if (!radix_tree_exceptional_entry(page)) {
if (page)
page_cache_release(page);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 33365e9ce6a7..a98c7fce470a 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1540,7 +1540,7 @@ static int soft_offline_huge_page(struct page *page, int flags)
/* Keep page count to indicate a given hugepage is isolated. */
list_move(&hpage->lru, &pagelist);
- ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+ ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
@@ -1621,7 +1621,7 @@ static int __soft_offline_page(struct page *page, int flags)
inc_zone_page_state(page, NR_ISOLATED_ANON +
page_is_file_cache(page));
list_add(&page->lru, &pagelist);
- ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+ ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
MIGRATE_SYNC, MR_MEMORY_FAILURE);
if (ret) {
if (!list_empty(&pagelist)) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a650db29606f..f6f23833de44 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1332,7 +1332,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
* alloc_migrate_target should be improooooved!!
* migrate_pages returns # of failed pages.
*/
- ret = migrate_pages(&source, alloc_migrate_target, 0,
+ ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
if (ret)
putback_movable_pages(&source);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 796c7e6cf93b..e8fff0fa1202 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1060,7 +1060,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
if (!list_empty(&pagelist)) {
- err = migrate_pages(&pagelist, new_node_page, dest,
+ err = migrate_pages(&pagelist, new_node_page, NULL, dest,
MIGRATE_SYNC, MR_SYSCALL);
if (err)
putback_movable_pages(&pagelist);
@@ -1306,7 +1306,7 @@ static long do_mbind(unsigned long start, unsigned long len,
if (!list_empty(&pagelist)) {
WARN_ON_ONCE(flags & MPOL_MF_LAZY);
- nr_failed = migrate_pages(&pagelist, new_page,
+ nr_failed = migrate_pages(&pagelist, new_page, NULL,
start, MIGRATE_SYNC, MR_MEMPOLICY_MBIND);
if (nr_failed)
putback_movable_pages(&pagelist);
diff --git a/mm/migrate.c b/mm/migrate.c
index 13f47fbe3550..3acac4a62c4b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -941,8 +941,9 @@ out:
* Obtain the lock on page, remove all ptes and migrate the page
* to the newly allocated page in newpage.
*/
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
- struct page *page, int force, enum migrate_mode mode)
+static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page,
+ unsigned long private, struct page *page, int force,
+ enum migrate_mode mode)
{
int rc = 0;
int *result = NULL;
@@ -986,11 +987,18 @@ out:
page_is_file_cache(page));
putback_lru_page(page);
}
+
/*
- * Move the new page to the LRU. If migration was not successful
- * then this will free the page.
+ * If migration was not successful and there's a freeing callback, use
+ * it. Otherwise, putback_lru_page() will drop the reference grabbed
+ * during isolation.
*/
- putback_lru_page(newpage);
+ if (rc != MIGRATEPAGE_SUCCESS && put_new_page) {
+ ClearPageSwapBacked(newpage);
+ put_new_page(newpage, private);
+ } else
+ putback_lru_page(newpage);
+
if (result) {
if (rc)
*result = rc;
@@ -1019,8 +1027,9 @@ out:
* will wait in the page fault for migration to complete.
*/
static int unmap_and_move_huge_page(new_page_t get_new_page,
- unsigned long private, struct page *hpage,
- int force, enum migrate_mode mode)
+ free_page_t put_new_page, unsigned long private,
+ struct page *hpage, int force,
+ enum migrate_mode mode)
{
int rc = 0;
int *result = NULL;
@@ -1059,20 +1068,30 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
if (!page_mapped(hpage))
rc = move_to_new_page(new_hpage, hpage, 1, mode);
- if (rc)
+ if (rc != MIGRATEPAGE_SUCCESS)
remove_migration_ptes(hpage, hpage);
if (anon_vma)
put_anon_vma(anon_vma);
- if (!rc)
+ if (rc == MIGRATEPAGE_SUCCESS)
hugetlb_cgroup_migrate(hpage, new_hpage);
unlock_page(hpage);
out:
if (rc != -EAGAIN)
putback_active_hugepage(hpage);
- put_page(new_hpage);
+
+ /*
+ * If migration was not successful and there's a freeing callback, use
+ * it. Otherwise, put_page() will drop the reference grabbed during
+ * isolation.
+ */
+ if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
+ put_new_page(new_hpage, private);
+ else
+ put_page(new_hpage);
+
if (result) {
if (rc)
*result = rc;
@@ -1089,6 +1108,8 @@ out:
* @from: The list of pages to be migrated.
* @get_new_page: The function used to allocate free pages to be used
* as the target of the page migration.
+ * @put_new_page: The function used to free target pages if migration
+ * fails, or NULL if no special handling is necessary.
* @private: Private data to be passed on to get_new_page()
* @mode: The migration mode that specifies the constraints for
* page migration, if any.
@@ -1102,7 +1123,8 @@ out:
* Returns the number of pages that were not migrated, or an error code.
*/
int migrate_pages(struct list_head *from, new_page_t get_new_page,
- unsigned long private, enum migrate_mode mode, int reason)
+ free_page_t put_new_page, unsigned long private,
+ enum migrate_mode mode, int reason)
{
int retry = 1;
int nr_failed = 0;
@@ -1124,10 +1146,11 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
if (PageHuge(page))
rc = unmap_and_move_huge_page(get_new_page,
- private, page, pass > 2, mode);
+ put_new_page, private, page,
+ pass > 2, mode);
else
- rc = unmap_and_move(get_new_page, private,
- page, pass > 2, mode);
+ rc = unmap_and_move(get_new_page, put_new_page,
+ private, page, pass > 2, mode);
switch(rc) {
case -ENOMEM:
@@ -1276,7 +1299,7 @@ set_status:
err = 0;
if (!list_empty(&pagelist)) {
- err = migrate_pages(&pagelist, new_page_node,
+ err = migrate_pages(&pagelist, new_page_node, NULL,
(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
if (err)
putback_movable_pages(&pagelist);
@@ -1732,7 +1755,8 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
list_add(&page->lru, &migratepages);
nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
- node, MIGRATE_ASYNC, MR_NUMA_MISPLACED);
+ NULL, node, MIGRATE_ASYNC,
+ MR_NUMA_MISPLACED);
if (nr_remaining) {
if (!list_empty(&migratepages)) {
list_del(&page->lru);
diff --git a/mm/mincore.c b/mm/mincore.c
index 101623378fbf..725c80961048 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -70,13 +70,21 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
* any other file mapping (ie. marked !present and faulted in with
* tmpfs's .fault). So swapped out tmpfs mappings are tested here.
*/
- page = find_get_page(mapping, pgoff);
#ifdef CONFIG_SWAP
- /* shmem/tmpfs may return swap: account for swapcache page too. */
- if (radix_tree_exceptional_entry(page)) {
- swp_entry_t swap = radix_to_swp_entry(page);
- page = find_get_page(swap_address_space(swap), swap.val);
- }
+ if (shmem_mapping(mapping)) {
+ page = find_get_entry(mapping, pgoff);
+ /*
+ * shmem/tmpfs may return swap: account for swapcache
+ * page too.
+ */
+ if (radix_tree_exceptional_entry(page)) {
+ swp_entry_t swp = radix_to_swp_entry(page);
+ page = find_get_page(swap_address_space(swp), swp.val);
+ }
+ } else
+ page = find_get_page(mapping, pgoff);
+#else
+ page = find_get_page(mapping, pgoff);
#endif
if (page) {
present = PageUptodate(page);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c69f474a1b60..139a57ee6b20 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -980,6 +980,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
rmv_page_order(page);
area->nr_free--;
expand(zone, page, order, current_order, area, migratetype);
+ set_freepage_migratetype(page, migratetype);
return page;
}
@@ -1106,7 +1107,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
/*
* When borrowing from MIGRATE_CMA, we need to release the excess
- * buddy pages to CMA itself.
+ * buddy pages to CMA itself. We also ensure the freepage_migratetype
+ * is set to CMA so it is returned to the correct freelist in case
+ * the page ends up being not actually allocated from the pcp lists.
*/
if (is_migrate_cma(fallback_type))
return fallback_type;
@@ -1174,6 +1177,12 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
expand(zone, page, order, current_order, area,
new_type);
+ /* The freepage_migratetype may differ from pageblock's
+ * migratetype depending on the decisions in
+ * try_to_steal_freepages. This is OK as long as it does
+ * not differ for MIGRATE_CMA type.
+ */
+ set_freepage_migratetype(page, new_type);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, migratetype, new_type);
@@ -1224,7 +1233,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, int cold)
{
- int mt = migratetype, i;
+ int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
@@ -1245,14 +1254,8 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
list_add(&page->lru, list);
else
list_add_tail(&page->lru, list);
- if (IS_ENABLED(CONFIG_CMA)) {
- mt = get_pageblock_migratetype(page);
- if (!is_migrate_cma(mt) && !is_migrate_isolate(mt))
- mt = migratetype;
- }
- set_freepage_migratetype(page, mt);
list = &page->lru;
- if (is_migrate_cma(mt))
+ if (is_migrate_cma(get_freepage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
@@ -1639,7 +1642,7 @@ again:
goto failed;
}
__mod_zone_freepage_state(zone, -(1 << order),
- get_pageblock_migratetype(page));
+ get_freepage_migratetype(page));
spin_unlock(&zone->lock);
}
@@ -2302,7 +2305,7 @@ static struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, bool sync_migration,
+ int migratetype, enum migrate_mode mode,
bool *contended_compaction, bool *deferred_compaction,
unsigned long *did_some_progress)
{
@@ -2316,7 +2319,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
current->flags |= PF_MEMALLOC;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
- nodemask, sync_migration,
+ nodemask, mode,
contended_compaction);
current->flags &= ~PF_MEMALLOC;
@@ -2349,7 +2352,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
* As async compaction considers a subset of pageblocks, only
* defer if the failure was a sync compaction failure.
*/
- if (sync_migration)
+ if (mode != MIGRATE_ASYNC)
defer_compaction(preferred_zone, order);
cond_resched();
@@ -2362,9 +2365,8 @@ static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, bool sync_migration,
- bool *contended_compaction, bool *deferred_compaction,
- unsigned long *did_some_progress)
+ int migratetype, enum migrate_mode mode, bool *contended_compaction,
+ bool *deferred_compaction, unsigned long *did_some_progress)
{
return NULL;
}
@@ -2559,7 +2561,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
int alloc_flags;
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
- bool sync_migration = false;
+ enum migrate_mode migration_mode = MIGRATE_ASYNC;
bool deferred_compaction = false;
bool contended_compaction = false;
@@ -2653,17 +2655,15 @@ rebalance:
* Try direct compaction. The first pass is asynchronous. Subsequent
* attempts after direct reclaim are synchronous
*/
- page = __alloc_pages_direct_compact(gfp_mask, order,
- zonelist, high_zoneidx,
- nodemask,
- alloc_flags, preferred_zone,
- migratetype, sync_migration,
- &contended_compaction,
+ page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+ high_zoneidx, nodemask, alloc_flags,
+ preferred_zone, migratetype,
+ migration_mode, &contended_compaction,
&deferred_compaction,
&did_some_progress);
if (page)
goto got_pg;
- sync_migration = true;
+ migration_mode = MIGRATE_SYNC_LIGHT;
/*
* If compaction is deferred for high-order allocations, it is because
@@ -2738,12 +2738,10 @@ rebalance:
* direct reclaim and reclaim/compaction depends on compaction
* being called after reclaim so call directly if necessary
*/
- page = __alloc_pages_direct_compact(gfp_mask, order,
- zonelist, high_zoneidx,
- nodemask,
- alloc_flags, preferred_zone,
- migratetype, sync_migration,
- &contended_compaction,
+ page = __alloc_pages_direct_compact(gfp_mask, order, zonelist,
+ high_zoneidx, nodemask, alloc_flags,
+ preferred_zone, migratetype,
+ migration_mode, &contended_compaction,
&deferred_compaction,
&did_some_progress);
if (page)
@@ -6318,7 +6316,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
cc->nr_migratepages -= nr_reclaimed;
ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
- 0, MIGRATE_SYNC, MR_CMA);
+ NULL, 0, cc->mode, MR_CMA);
}
if (ret < 0) {
putback_movable_pages(&cc->migratepages);
@@ -6357,7 +6355,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
.nr_migratepages = 0,
.order = -1,
.zone = page_zone(pfn_to_page(start)),
- .sync = true,
+ .mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
};
INIT_LIST_HEAD(&cc.migratepages);
diff --git a/mm/readahead.c b/mm/readahead.c
index 1fa0d6fca556..0ca36a7770b1 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -8,9 +8,7 @@
*/
#include <linux/kernel.h>
-#include <linux/fs.h>
#include <linux/gfp.h>
-#include <linux/mm.h>
#include <linux/export.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -20,6 +18,8 @@
#include <linux/syscalls.h>
#include <linux/file.h>
+#include "internal.h"
+
/*
* Initialise a struct file's readahead state. Assumes that the caller has
* memset *ra to zero.
@@ -149,8 +149,7 @@ out:
*
* Returns the number of pages requested, or the maximum amount of I/O allowed.
*/
-static int
-__do_page_cache_readahead(struct address_space *mapping, struct file *filp,
+int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
pgoff_t offset, unsigned long nr_to_read,
unsigned long lookahead_size)
{
@@ -179,7 +178,7 @@ __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
rcu_read_lock();
page = radix_tree_lookup(&mapping->page_tree, page_offset);
rcu_read_unlock();
- if (page)
+ if (page && !radix_tree_exceptional_entry(page))
continue;
page = page_cache_alloc_readahead(mapping);
@@ -244,20 +243,6 @@ unsigned long max_sane_readahead(unsigned long nr)
}
/*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-unsigned long ra_submit(struct file_ra_state *ra,
- struct address_space *mapping, struct file *filp)
-{
- int actual;
-
- actual = __do_page_cache_readahead(mapping, filp,
- ra->start, ra->size, ra->async_size);
-
- return actual;
-}
-
-/*
* Set the initial window size, round to next power of 2 and square
* for small size, x 4 for medium, and x 2 for large
* for 128k (32 page) max ra
@@ -347,7 +332,7 @@ static pgoff_t count_history_pages(struct address_space *mapping,
pgoff_t head;
rcu_read_lock();
- head = radix_tree_prev_hole(&mapping->page_tree, offset - 1, max);
+ head = page_cache_prev_hole(mapping, offset - 1, max);
rcu_read_unlock();
return offset - 1 - head;
@@ -427,7 +412,7 @@ ondemand_readahead(struct address_space *mapping,
pgoff_t start;
rcu_read_lock();
- start = radix_tree_next_hole(&mapping->page_tree, offset+1,max);
+ start = page_cache_next_hole(mapping, offset + 1, max);
rcu_read_unlock();
if (!start || start - offset > max)
diff --git a/mm/shmem.c b/mm/shmem.c
index f0d698ba7d0f..0f1447563f17 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -243,19 +243,17 @@ static int shmem_radix_tree_replace(struct address_space *mapping,
pgoff_t index, void *expected, void *replacement)
{
void **pslot;
- void *item = NULL;
+ void *item;
VM_BUG_ON(!expected);
+ VM_BUG_ON(!replacement);
pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
- if (pslot)
- item = radix_tree_deref_slot_protected(pslot,
- &mapping->tree_lock);
+ if (!pslot)
+ return -ENOENT;
+ item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);
if (item != expected)
return -ENOENT;
- if (replacement)
- radix_tree_replace_slot(pslot, replacement);
- else
- radix_tree_delete(&mapping->page_tree, index);
+ radix_tree_replace_slot(pslot, replacement);
return 0;
}
@@ -332,84 +330,20 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap)
}
/*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
- pgoff_t start, unsigned int nr_pages,
- struct page **pages, pgoff_t *indices)
-{
- void **slot;
- unsigned int ret = 0;
- struct radix_tree_iter iter;
-
- if (!nr_pages)
- return 0;
-
- rcu_read_lock();
-restart:
- radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
- struct page *page;
-repeat:
- page = radix_tree_deref_slot(slot);
- if (unlikely(!page))
- continue;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page))
- goto restart;
- /*
- * Otherwise, we must be storing a swap entry
- * here as an exceptional entry: so return it
- * without attempting to raise page count.
- */
- goto export;
- }
- if (!page_cache_get_speculative(page))
- goto repeat;
-
- /* Has the page moved? */
- if (unlikely(page != *slot)) {
- page_cache_release(page);
- goto repeat;
- }
-export:
- indices[ret] = iter.index;
- pages[ret] = page;
- if (++ret == nr_pages)
- break;
- }
- rcu_read_unlock();
- return ret;
-}
-
-/*
* Remove swap entry from radix tree, free the swap and its page cache.
*/
static int shmem_free_swap(struct address_space *mapping,
pgoff_t index, void *radswap)
{
- int error;
+ void *old;
spin_lock_irq(&mapping->tree_lock);
- error = shmem_radix_tree_replace(mapping, index, radswap, NULL);
+ old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
spin_unlock_irq(&mapping->tree_lock);
- if (!error)
- free_swap_and_cache(radix_to_swp_entry(radswap));
- return error;
-}
-
-/*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
- int i, j;
-
- for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
- struct page *page = pvec->pages[i];
- if (!radix_tree_exceptional_entry(page))
- pvec->pages[j++] = page;
- }
- pvec->nr = j;
+ if (old != radswap)
+ return -ENOENT;
+ free_swap_and_cache(radix_to_swp_entry(radswap));
+ return 0;
}
/*
@@ -430,12 +364,12 @@ void shmem_unlock_mapping(struct address_space *mapping)
* Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
* has finished, if it hits a row of PAGEVEC_SIZE swap entries.
*/
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
- PAGEVEC_SIZE, pvec.pages, indices);
+ pvec.nr = find_get_entries(mapping, index,
+ PAGEVEC_SIZE, pvec.pages, indices);
if (!pvec.nr)
break;
index = indices[pvec.nr - 1] + 1;
- shmem_deswap_pagevec(&pvec);
+ pagevec_remove_exceptionals(&pvec);
check_move_unevictable_pages(pvec.pages, pvec.nr);
pagevec_release(&pvec);
cond_resched();
@@ -467,9 +401,9 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
pagevec_init(&pvec, 0);
index = start;
while (index < end) {
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE),
- pvec.pages, indices);
+ pvec.nr = find_get_entries(mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE),
+ pvec.pages, indices);
if (!pvec.nr)
break;
mem_cgroup_uncharge_start();
@@ -498,7 +432,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
}
unlock_page(page);
}
- shmem_deswap_pagevec(&pvec);
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
cond_resched();
@@ -536,9 +470,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
index = start;
while (index < end) {
cond_resched();
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+
+ pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
- pvec.pages, indices);
+ pvec.pages, indices);
if (!pvec.nr) {
/* If all gone or hole-punch or unfalloc, we're done */
if (index == start || end != -1)
@@ -581,7 +516,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
}
unlock_page(page);
}
- shmem_deswap_pagevec(&pvec);
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
index++;
@@ -1088,7 +1023,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
return -EFBIG;
repeat:
swap.val = 0;
- page = find_lock_page(mapping, index);
+ page = find_lock_entry(mapping, index);
if (radix_tree_exceptional_entry(page)) {
swap = radix_to_swp_entry(page);
page = NULL;
@@ -1483,6 +1418,11 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
return inode;
}
+bool shmem_mapping(struct address_space *mapping)
+{
+ return mapping->backing_dev_info == &shmem_backing_dev_info;
+}
+
#ifdef CONFIG_TMPFS
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_short_symlink_operations;
@@ -1795,7 +1735,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
pagevec_init(&pvec, 0);
pvec.nr = 1; /* start small: we may be there already */
while (!done) {
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+ pvec.nr = find_get_entries(mapping, index,
pvec.nr, pvec.pages, indices);
if (!pvec.nr) {
if (whence == SEEK_DATA)
@@ -1822,7 +1762,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
break;
}
}
- shmem_deswap_pagevec(&pvec);
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
pvec.nr = PAGEVEC_SIZE;
cond_resched();
diff --git a/mm/swap.c b/mm/swap.c
index 01fc47983d7c..ba288569e796 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -954,6 +954,57 @@ void __pagevec_lru_add(struct pagevec *pvec)
EXPORT_SYMBOL(__pagevec_lru_add);
/**
+ * pagevec_lookup_entries - gang pagecache lookup
+ * @pvec: Where the resulting entries are placed
+ * @mapping: The address_space to search
+ * @start: The starting entry index
+ * @nr_entries: The maximum number of entries
+ * @indices: The cache indices corresponding to the entries in @pvec
+ *
+ * pagevec_lookup_entries() will search for and return a group of up
+ * to @nr_entries pages and shadow entries in the mapping. All
+ * entries are placed in @pvec. pagevec_lookup_entries() takes a
+ * reference against actual pages in @pvec.
+ *
+ * The search returns a group of mapping-contiguous entries with
+ * ascending indexes. There may be holes in the indices due to
+ * not-present entries.
+ *
+ * pagevec_lookup_entries() returns the number of entries which were
+ * found.
+ */
+unsigned pagevec_lookup_entries(struct pagevec *pvec,
+ struct address_space *mapping,
+ pgoff_t start, unsigned nr_pages,
+ pgoff_t *indices)
+{
+ pvec->nr = find_get_entries(mapping, start, nr_pages,
+ pvec->pages, indices);
+ return pagevec_count(pvec);
+}
+
+/**
+ * pagevec_remove_exceptionals - pagevec exceptionals pruning
+ * @pvec: The pagevec to prune
+ *
+ * pagevec_lookup_entries() fills both pages and exceptional radix
+ * tree entries into the pagevec. This function prunes all
+ * exceptionals from @pvec without leaving holes, so that it can be
+ * passed on to page-only pagevec operations.
+ */
+void pagevec_remove_exceptionals(struct pagevec *pvec)
+{
+ int i, j;
+
+ for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+ struct page *page = pvec->pages[i];
+ if (!radix_tree_exceptional_entry(page))
+ pvec->pages[j++] = page;
+ }
+ pvec->nr = j;
+}
+
+/**
* pagevec_lookup - gang pagecache lookup
* @pvec: Where the resulting pages are placed
* @mapping: The address_space to search
diff --git a/mm/truncate.c b/mm/truncate.c
index ac18edc30649..827ad8d2b5cd 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -23,6 +23,22 @@
#include <linux/rmap.h>
#include "internal.h"
+static void clear_exceptional_entry(struct address_space *mapping,
+ pgoff_t index, void *entry)
+{
+ /* Handled by shmem itself */
+ if (shmem_mapping(mapping))
+ return;
+
+ spin_lock_irq(&mapping->tree_lock);
+ /*
+ * Regular page slots are stabilized by the page lock even
+ * without the tree itself locked. These unlocked entries
+ * need verification under the tree lock.
+ */
+ radix_tree_delete_item(&mapping->page_tree, index, entry);
+ spin_unlock_irq(&mapping->tree_lock);
+}
/**
* do_invalidatepage - invalidate part or all of a page
@@ -209,6 +225,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
unsigned int partial_start; /* inclusive */
unsigned int partial_end; /* exclusive */
struct pagevec pvec;
+ pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index;
int i;
@@ -239,17 +256,23 @@ void truncate_inode_pages_range(struct address_space *mapping,
pagevec_init(&pvec, 0);
index = start;
- while (index < end && pagevec_lookup(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+ while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE),
+ indices)) {
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
- index = page->index;
+ index = indices[i];
if (index >= end)
break;
+ if (radix_tree_exceptional_entry(page)) {
+ clear_exceptional_entry(mapping, index, page);
+ continue;
+ }
+
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
@@ -260,6 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
truncate_inode_page(mapping, page);
unlock_page(page);
}
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
cond_resched();
@@ -308,14 +332,16 @@ void truncate_inode_pages_range(struct address_space *mapping,
index = start;
for ( ; ; ) {
cond_resched();
- if (!pagevec_lookup(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE))) {
+ if (!pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE),
+ indices)) {
if (index == start)
break;
index = start;
continue;
}
- if (index == start && pvec.pages[0]->index >= end) {
+ if (index == start && indices[0] >= end) {
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
break;
}
@@ -324,16 +350,22 @@ void truncate_inode_pages_range(struct address_space *mapping,
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
- index = page->index;
+ index = indices[i];
if (index >= end)
break;
+ if (radix_tree_exceptional_entry(page)) {
+ clear_exceptional_entry(mapping, index, page);
+ continue;
+ }
+
lock_page(page);
WARN_ON(page->index != index);
wait_on_page_writeback(page);
truncate_inode_page(mapping, page);
unlock_page(page);
}
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
index++;
@@ -376,6 +408,7 @@ EXPORT_SYMBOL(truncate_inode_pages);
unsigned long invalidate_mapping_pages(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
+ pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
pgoff_t index = start;
unsigned long ret;
@@ -391,17 +424,23 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
*/
pagevec_init(&pvec, 0);
- while (index <= end && pagevec_lookup(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+ while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+ indices)) {
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
- index = page->index;
+ index = indices[i];
if (index > end)
break;
+ if (radix_tree_exceptional_entry(page)) {
+ clear_exceptional_entry(mapping, index, page);
+ continue;
+ }
+
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
@@ -415,6 +454,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
deactivate_page(page);
count += ret;
}
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
cond_resched();
@@ -482,6 +522,7 @@ static int do_launder_page(struct address_space *mapping, struct page *page)
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
+ pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
pgoff_t index;
int i;
@@ -492,17 +533,23 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
cleancache_invalidate_inode(mapping);
pagevec_init(&pvec, 0);
index = start;
- while (index <= end && pagevec_lookup(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+ while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+ indices)) {
mem_cgroup_uncharge_start();
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
- index = page->index;
+ index = indices[i];
if (index > end)
break;
+ if (radix_tree_exceptional_entry(page)) {
+ clear_exceptional_entry(mapping, index, page);
+ continue;
+ }
+
lock_page(page);
WARN_ON(page->index != index);
if (page->mapping != mapping) {
@@ -540,6 +587,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
ret = ret2;
unlock_page(page);
}
+ pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
mem_cgroup_uncharge_end();
cond_resched();
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0c0b36e5b4f8..deb139e6b8ed 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2018,13 +2018,27 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
unsigned long nr_reclaimed = 0;
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
struct blk_plug plug;
- bool scan_adjusted = false;
+ bool scan_adjusted;
get_scan_count(lruvec, sc, nr);
/* Record the original scan target for proportional adjustments later */
memcpy(targets, nr, sizeof(nr));
+ /*
+ * Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
+ * event that can occur when there is little memory pressure e.g.
+ * multiple streaming readers/writers. Hence, we do not abort scanning
+ * when the requested number of pages are reclaimed when scanning at
+ * DEF_PRIORITY on the assumption that the fact we are direct
+ * reclaiming implies that kswapd is not keeping up and it is best to
+ * do a batch of work at once. For memcg reclaim one check is made to
+ * 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);
+
blk_start_plug(&plug);
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
nr[LRU_INACTIVE_FILE]) {
@@ -2045,17 +2059,8 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
continue;
/*
- * For global direct reclaim, reclaim only the number of pages
- * requested. Less care is taken to scan proportionally as it
- * is more important to minimise direct reclaim stall latency
- * than it is to properly age the LRU lists.
- */
- if (global_reclaim(sc) && !current_is_kswapd())
- break;
-
- /*
* For kswapd and memcg, reclaim at least the number of pages
- * requested. Ensure that the anon and file LRUs shrink
+ * requested. Ensure that the anon and file LRUs are scanned
* proportionally what was requested by get_scan_count(). We
* stop reclaiming one LRU and reduce the amount scanning
* proportional to the original scan target.
@@ -2063,6 +2068,15 @@ static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
+ /*
+ * It's just vindictive to attack the larger once the smaller
+ * has gone to zero. And given the way we stop scanning the
+ * smaller below, this makes sure that we only make one nudge
+ * towards proportionality once we've got nr_to_reclaim.
+ */
+ if (!nr_file || !nr_anon)
+ break;
+
if (nr_file > nr_anon) {
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
targets[LRU_ACTIVE_ANON] + 1;
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-25 10:44:42 +0000