summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c703
1 files changed, 274 insertions, 429 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 446bb36ee59d..208e4c7e771b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -169,19 +169,19 @@ void pm_restrict_gfp_mask(void)
WARN_ON(!mutex_is_locked(&pm_mutex));
WARN_ON(saved_gfp_mask);
saved_gfp_mask = gfp_allowed_mask;
- gfp_allowed_mask &= ~GFP_IOFS;
+ gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
}
bool pm_suspended_storage(void)
{
- if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ if ((gfp_allowed_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
return false;
return true;
}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
-int pageblock_order __read_mostly;
+unsigned int pageblock_order __read_mostly;
#endif
static void __free_pages_ok(struct page *page, unsigned int order);
@@ -229,6 +229,15 @@ static char * const zone_names[MAX_NR_ZONES] = {
#endif
};
+static void free_compound_page(struct page *page);
+compound_page_dtor * const compound_page_dtors[] = {
+ NULL,
+ free_compound_page,
+#ifdef CONFIG_HUGETLB_PAGE
+ free_huge_page,
+#endif
+};
+
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
@@ -436,15 +445,15 @@ out:
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
- * The first PAGE_SIZE page is called the "head page".
+ * The first PAGE_SIZE page is called the "head page" and have PG_head set.
*
- * The remaining PAGE_SIZE pages are called "tail pages".
+ * The remaining PAGE_SIZE pages are called "tail pages". PageTail() is encoded
+ * in bit 0 of page->compound_head. The rest of bits is pointer to head page.
*
- * All pages have PG_compound set. All tail pages have their ->first_page
- * pointing at the head page.
+ * The first tail page's ->compound_dtor holds the offset in array of compound
+ * page destructors. See compound_page_dtors.
*
- * The first tail page's ->lru.next holds the address of the compound page's
- * put_page() function. Its ->lru.prev holds the order of allocation.
+ * The first tail page's ->compound_order holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
@@ -453,21 +462,18 @@ static void free_compound_page(struct page *page)
__free_pages_ok(page, compound_order(page));
}
-void prep_compound_page(struct page *page, unsigned long order)
+void prep_compound_page(struct page *page, unsigned int order)
{
int i;
int nr_pages = 1 << order;
- set_compound_page_dtor(page, free_compound_page);
+ set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
set_page_count(p, 0);
- p->first_page = page;
- /* Make sure p->first_page is always valid for PageTail() */
- smp_wmb();
- __SetPageTail(p);
+ set_compound_head(p, page);
}
}
@@ -656,7 +662,7 @@ static inline void __free_one_page(struct page *page,
unsigned long combined_idx;
unsigned long uninitialized_var(buddy_idx);
struct page *buddy;
- int max_order = MAX_ORDER;
+ unsigned int max_order = MAX_ORDER;
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
@@ -669,7 +675,7 @@ static inline void __free_one_page(struct page *page,
* pageblock. Without this, pageblock isolation
* could cause incorrect freepage accounting.
*/
- max_order = min(MAX_ORDER, pageblock_order + 1);
+ max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
} else {
__mod_zone_freepage_state(zone, 1 << order, migratetype);
}
@@ -817,7 +823,6 @@ static void free_pcppages_bulk(struct zone *zone, int count,
if (unlikely(has_isolate_pageblock(zone)))
mt = get_pageblock_migratetype(page);
- /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
__free_one_page(page, page_to_pfn(page), zone, 0, mt);
trace_mm_page_pcpu_drain(page, 0, mt);
} while (--to_free && --batch_free && !list_empty(list));
@@ -846,17 +851,30 @@ static void free_one_page(struct zone *zone,
static int free_tail_pages_check(struct page *head_page, struct page *page)
{
- if (!IS_ENABLED(CONFIG_DEBUG_VM))
- return 0;
+ int ret = 1;
+
+ /*
+ * We rely page->lru.next never has bit 0 set, unless the page
+ * is PageTail(). Let's make sure that's true even for poisoned ->lru.
+ */
+ BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1);
+
+ if (!IS_ENABLED(CONFIG_DEBUG_VM)) {
+ ret = 0;
+ goto out;
+ }
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set", 0);
- return 1;
+ goto out;
}
- if (unlikely(page->first_page != head_page)) {
- bad_page(page, "first_page not consistent", 0);
- return 1;
+ if (unlikely(compound_head(page) != head_page)) {
+ bad_page(page, "compound_head not consistent", 0);
+ goto out;
}
- return 0;
+ ret = 0;
+out:
+ clear_compound_head(page);
+ return ret;
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
@@ -923,6 +941,10 @@ void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
struct page *page = pfn_to_page(start_pfn);
init_reserved_page(start_pfn);
+
+ /* Avoid false-positive PageTail() */
+ INIT_LIST_HEAD(&page->lru);
+
SetPageReserved(page);
}
}
@@ -1417,15 +1439,14 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
* the free lists for the desirable migrate type are depleted
*/
static int fallbacks[MIGRATE_TYPES][4] = {
- [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
- [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
- [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
+ [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
+ [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
+ [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
#ifdef CONFIG_CMA
- [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */
+ [MIGRATE_CMA] = { MIGRATE_TYPES }, /* Never used */
#endif
- [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */
#ifdef CONFIG_MEMORY_ISOLATION
- [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */
+ [MIGRATE_ISOLATE] = { MIGRATE_TYPES }, /* Never used */
#endif
};
@@ -1450,7 +1471,7 @@ int move_freepages(struct zone *zone,
int migratetype)
{
struct page *page;
- unsigned long order;
+ unsigned int order;
int pages_moved = 0;
#ifndef CONFIG_HOLES_IN_ZONE
@@ -1563,7 +1584,7 @@ static bool can_steal_fallback(unsigned int order, int start_mt)
static void steal_suitable_fallback(struct zone *zone, struct page *page,
int start_type)
{
- int current_order = page_order(page);
+ unsigned int current_order = page_order(page);
int pages;
/* Take ownership for orders >= pageblock_order */
@@ -1598,7 +1619,7 @@ int find_suitable_fallback(struct free_area *area, unsigned int order,
*can_steal = false;
for (i = 0;; i++) {
fallback_mt = fallbacks[migratetype][i];
- if (fallback_mt == MIGRATE_RESERVE)
+ if (fallback_mt == MIGRATE_TYPES)
break;
if (list_empty(&area->free_list[fallback_mt]))
@@ -1617,6 +1638,101 @@ int find_suitable_fallback(struct free_area *area, unsigned int order,
return -1;
}
+/*
+ * Reserve a pageblock for exclusive use of high-order atomic allocations if
+ * there are no empty page blocks that contain a page with a suitable order
+ */
+static void reserve_highatomic_pageblock(struct page *page, struct zone *zone,
+ unsigned int alloc_order)
+{
+ int mt;
+ unsigned long max_managed, flags;
+
+ /*
+ * Limit the number reserved to 1 pageblock or roughly 1% of a zone.
+ * Check is race-prone but harmless.
+ */
+ max_managed = (zone->managed_pages / 100) + pageblock_nr_pages;
+ if (zone->nr_reserved_highatomic >= max_managed)
+ return;
+
+ spin_lock_irqsave(&zone->lock, flags);
+
+ /* Recheck the nr_reserved_highatomic limit under the lock */
+ if (zone->nr_reserved_highatomic >= max_managed)
+ goto out_unlock;
+
+ /* Yoink! */
+ mt = get_pageblock_migratetype(page);
+ if (mt != MIGRATE_HIGHATOMIC &&
+ !is_migrate_isolate(mt) && !is_migrate_cma(mt)) {
+ zone->nr_reserved_highatomic += pageblock_nr_pages;
+ set_pageblock_migratetype(page, MIGRATE_HIGHATOMIC);
+ move_freepages_block(zone, page, MIGRATE_HIGHATOMIC);
+ }
+
+out_unlock:
+ spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+/*
+ * Used when an allocation is about to fail under memory pressure. This
+ * potentially hurts the reliability of high-order allocations when under
+ * intense memory pressure but failed atomic allocations should be easier
+ * to recover from than an OOM.
+ */
+static void unreserve_highatomic_pageblock(const struct alloc_context *ac)
+{
+ struct zonelist *zonelist = ac->zonelist;
+ unsigned long flags;
+ struct zoneref *z;
+ struct zone *zone;
+ struct page *page;
+ int order;
+
+ for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
+ ac->nodemask) {
+ /* Preserve at least one pageblock */
+ if (zone->nr_reserved_highatomic <= pageblock_nr_pages)
+ continue;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++) {
+ struct free_area *area = &(zone->free_area[order]);
+
+ if (list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ continue;
+
+ page = list_entry(area->free_list[MIGRATE_HIGHATOMIC].next,
+ struct page, lru);
+
+ /*
+ * It should never happen but changes to locking could
+ * inadvertently allow a per-cpu drain to add pages
+ * to MIGRATE_HIGHATOMIC while unreserving so be safe
+ * and watch for underflows.
+ */
+ zone->nr_reserved_highatomic -= min(pageblock_nr_pages,
+ zone->nr_reserved_highatomic);
+
+ /*
+ * Convert to ac->migratetype and avoid the normal
+ * pageblock stealing heuristics. Minimally, the caller
+ * is doing the work and needs the pages. More
+ * importantly, if the block was always converted to
+ * MIGRATE_UNMOVABLE or another type then the number
+ * of pageblocks that cannot be completely freed
+ * may increase.
+ */
+ set_pageblock_migratetype(page, ac->migratetype);
+ move_freepages_block(zone, page, ac->migratetype);
+ spin_unlock_irqrestore(&zone->lock, flags);
+ return;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+}
+
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
@@ -1672,29 +1788,17 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
* Call me with the zone->lock already held.
*/
static struct page *__rmqueue(struct zone *zone, unsigned int order,
- int migratetype)
+ int migratetype, gfp_t gfp_flags)
{
struct page *page;
-retry_reserve:
page = __rmqueue_smallest(zone, order, migratetype);
-
- if (unlikely(!page) && migratetype != MIGRATE_RESERVE) {
+ if (unlikely(!page)) {
if (migratetype == MIGRATE_MOVABLE)
page = __rmqueue_cma_fallback(zone, order);
if (!page)
page = __rmqueue_fallback(zone, order, migratetype);
-
- /*
- * Use MIGRATE_RESERVE rather than fail an allocation. goto
- * is used because __rmqueue_smallest is an inline function
- * and we want just one call site
- */
- if (!page) {
- migratetype = MIGRATE_RESERVE;
- goto retry_reserve;
- }
}
trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -1714,7 +1818,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
- struct page *page = __rmqueue(zone, order, migratetype);
+ struct page *page = __rmqueue(zone, order, migratetype, 0);
if (unlikely(page == NULL))
break;
@@ -2086,7 +2190,7 @@ int split_free_page(struct page *page)
static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
struct zone *zone, unsigned int order,
- gfp_t gfp_flags, int migratetype)
+ gfp_t gfp_flags, int alloc_flags, int migratetype)
{
unsigned long flags;
struct page *page;
@@ -2129,7 +2233,15 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
WARN_ON_ONCE(order > 1);
}
spin_lock_irqsave(&zone->lock, flags);
- page = __rmqueue(zone, order, migratetype);
+
+ page = NULL;
+ if (alloc_flags & ALLOC_HARDER) {
+ page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
+ if (page)
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
+ }
+ if (!page)
+ page = __rmqueue(zone, order, migratetype, gfp_flags);
spin_unlock(&zone->lock);
if (!page)
goto failed;
@@ -2160,11 +2272,11 @@ static struct {
struct fault_attr attr;
bool ignore_gfp_highmem;
- bool ignore_gfp_wait;
+ bool ignore_gfp_reclaim;
u32 min_order;
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
- .ignore_gfp_wait = true,
+ .ignore_gfp_reclaim = true,
.ignore_gfp_highmem = true,
.min_order = 1,
};
@@ -2183,7 +2295,8 @@ static bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
return false;
if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
return false;
- if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
+ if (fail_page_alloc.ignore_gfp_reclaim &&
+ (gfp_mask & __GFP_DIRECT_RECLAIM))
return false;
return should_fail(&fail_page_alloc.attr, 1 << order);
@@ -2202,7 +2315,7 @@ static int __init fail_page_alloc_debugfs(void)
return PTR_ERR(dir);
if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
- &fail_page_alloc.ignore_gfp_wait))
+ &fail_page_alloc.ignore_gfp_reclaim))
goto fail;
if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
&fail_page_alloc.ignore_gfp_highmem))
@@ -2232,42 +2345,77 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
#endif /* CONFIG_FAIL_PAGE_ALLOC */
/*
- * Return true if free pages are above 'mark'. This takes into account the order
- * of the allocation.
+ * Return true if free base pages are above 'mark'. For high-order checks it
+ * will return true of the order-0 watermark is reached and there is at least
+ * one free page of a suitable size. Checking now avoids taking the zone lock
+ * to check in the allocation paths if no pages are free.
*/
static bool __zone_watermark_ok(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, int alloc_flags,
long free_pages)
{
- /* free_pages may go negative - that's OK */
long min = mark;
int o;
- long free_cma = 0;
+ const int alloc_harder = (alloc_flags & ALLOC_HARDER);
+ /* free_pages may go negative - that's OK */
free_pages -= (1 << order) - 1;
+
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- if (alloc_flags & ALLOC_HARDER)
+
+ /*
+ * If the caller does not have rights to ALLOC_HARDER then subtract
+ * the high-atomic reserves. This will over-estimate the size of the
+ * atomic reserve but it avoids a search.
+ */
+ if (likely(!alloc_harder))
+ free_pages -= z->nr_reserved_highatomic;
+ else
min -= min / 4;
+
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
if (!(alloc_flags & ALLOC_CMA))
- free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
+ free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
- if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx])
+ /*
+ * Check watermarks for an order-0 allocation request. If these
+ * are not met, then a high-order request also cannot go ahead
+ * even if a suitable page happened to be free.
+ */
+ if (free_pages <= min + z->lowmem_reserve[classzone_idx])
return false;
- for (o = 0; o < order; o++) {
- /* At the next order, this order's pages become unavailable */
- free_pages -= z->free_area[o].nr_free << o;
- /* Require fewer higher order pages to be free */
- min >>= 1;
+ /* If this is an order-0 request then the watermark is fine */
+ if (!order)
+ return true;
+
+ /* For a high-order request, check at least one suitable page is free */
+ for (o = order; o < MAX_ORDER; o++) {
+ struct free_area *area = &z->free_area[o];
+ int mt;
+
+ if (!area->nr_free)
+ continue;
+
+ if (alloc_harder)
+ return true;
+
+ for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
+ if (!list_empty(&area->free_list[mt]))
+ return true;
+ }
- if (free_pages <= min)
- return false;
+#ifdef CONFIG_CMA
+ if ((alloc_flags & ALLOC_CMA) &&
+ !list_empty(&area->free_list[MIGRATE_CMA])) {
+ return true;
+ }
+#endif
}
- return true;
+ return false;
}
bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
@@ -2278,134 +2426,18 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
}
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx, int alloc_flags)
+ unsigned long mark, int classzone_idx)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
- return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+ return __zone_watermark_ok(z, order, mark, classzone_idx, 0,
free_pages);
}
#ifdef CONFIG_NUMA
-/*
- * zlc_setup - Setup for "zonelist cache". Uses cached zone data to
- * skip over zones that are not allowed by the cpuset, or that have
- * been recently (in last second) found to be nearly full. See further
- * comments in mmzone.h. Reduces cache footprint of zonelist scans
- * that have to skip over a lot of full or unallowed zones.
- *
- * If the zonelist cache is present in the passed zonelist, then
- * returns a pointer to the allowed node mask (either the current
- * tasks mems_allowed, or node_states[N_MEMORY].)
- *
- * If the zonelist cache is not available for this zonelist, does
- * nothing and returns NULL.
- *
- * If the fullzones BITMAP in the zonelist cache is stale (more than
- * a second since last zap'd) then we zap it out (clear its bits.)
- *
- * We hold off even calling zlc_setup, until after we've checked the
- * first zone in the zonelist, on the theory that most allocations will
- * be satisfied from that first zone, so best to examine that zone as
- * quickly as we can.
- */
-static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
-{
- struct zonelist_cache *zlc; /* cached zonelist speedup info */
- nodemask_t *allowednodes; /* zonelist_cache approximation */
-
- zlc = zonelist->zlcache_ptr;
- if (!zlc)
- return NULL;
-
- if (time_after(jiffies, zlc->last_full_zap + HZ)) {
- bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
- zlc->last_full_zap = jiffies;
- }
-
- allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
- &cpuset_current_mems_allowed :
- &node_states[N_MEMORY];
- return allowednodes;
-}
-
-/*
- * Given 'z' scanning a zonelist, run a couple of quick checks to see
- * if it is worth looking at further for free memory:
- * 1) Check that the zone isn't thought to be full (doesn't have its
- * bit set in the zonelist_cache fullzones BITMAP).
- * 2) Check that the zones node (obtained from the zonelist_cache
- * z_to_n[] mapping) is allowed in the passed in allowednodes mask.
- * Return true (non-zero) if zone is worth looking at further, or
- * else return false (zero) if it is not.
- *
- * This check -ignores- the distinction between various watermarks,
- * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is
- * found to be full for any variation of these watermarks, it will
- * be considered full for up to one second by all requests, unless
- * we are so low on memory on all allowed nodes that we are forced
- * into the second scan of the zonelist.
- *
- * In the second scan we ignore this zonelist cache and exactly
- * apply the watermarks to all zones, even it is slower to do so.
- * We are low on memory in the second scan, and should leave no stone
- * unturned looking for a free page.
- */
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
- nodemask_t *allowednodes)
-{
- struct zonelist_cache *zlc; /* cached zonelist speedup info */
- int i; /* index of *z in zonelist zones */
- int n; /* node that zone *z is on */
-
- zlc = zonelist->zlcache_ptr;
- if (!zlc)
- return 1;
-
- i = z - zonelist->_zonerefs;
- n = zlc->z_to_n[i];
-
- /* This zone is worth trying if it is allowed but not full */
- return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
-}
-
-/*
- * Given 'z' scanning a zonelist, set the corresponding bit in
- * zlc->fullzones, so that subsequent attempts to allocate a page
- * from that zone don't waste time re-examining it.
- */
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
-{
- struct zonelist_cache *zlc; /* cached zonelist speedup info */
- int i; /* index of *z in zonelist zones */
-
- zlc = zonelist->zlcache_ptr;
- if (!zlc)
- return;
-
- i = z - zonelist->_zonerefs;
-
- set_bit(i, zlc->fullzones);
-}
-
-/*
- * clear all zones full, called after direct reclaim makes progress so that
- * a zone that was recently full is not skipped over for up to a second
- */
-static void zlc_clear_zones_full(struct zonelist *zonelist)
-{
- struct zonelist_cache *zlc; /* cached zonelist speedup info */
-
- zlc = zonelist->zlcache_ptr;
- if (!zlc)
- return;
-
- bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
-}
-
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
return local_zone->node == zone->node;
@@ -2416,28 +2448,7 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
RECLAIM_DISTANCE;
}
-
#else /* CONFIG_NUMA */
-
-static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
-{
- return NULL;
-}
-
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
- nodemask_t *allowednodes)
-{
- return 1;
-}
-
-static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
-{
-}
-
-static void zlc_clear_zones_full(struct zonelist *zonelist)
-{
-}
-
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
return true;
@@ -2447,7 +2458,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
}
-
#endif /* CONFIG_NUMA */
static void reset_alloc_batches(struct zone *preferred_zone)
@@ -2474,11 +2484,6 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
struct zoneref *z;
struct page *page = NULL;
struct zone *zone;
- nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
- int zlc_active = 0; /* set if using zonelist_cache */
- int did_zlc_setup = 0; /* just call zlc_setup() one time */
- bool consider_zone_dirty = (alloc_flags & ALLOC_WMARK_LOW) &&
- (gfp_mask & __GFP_WRITE);
int nr_fair_skipped = 0;
bool zonelist_rescan;
@@ -2493,9 +2498,6 @@ zonelist_scan:
ac->nodemask) {
unsigned long mark;
- if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
- !zlc_zone_worth_trying(zonelist, z, allowednodes))
- continue;
if (cpusets_enabled() &&
(alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed(zone, gfp_mask))
@@ -2533,14 +2535,14 @@ zonelist_scan:
*
* XXX: For now, allow allocations to potentially
* exceed the per-zone dirty limit in the slowpath
- * (ALLOC_WMARK_LOW unset) before going into reclaim,
+ * (spread_dirty_pages unset) before going into reclaim,
* which is important when on a NUMA setup the allowed
* zones are together not big enough to reach the
* global limit. The proper fix for these situations
* will require awareness of zones in the
* dirty-throttling and the flusher threads.
*/
- if (consider_zone_dirty && !zone_dirty_ok(zone))
+ if (ac->spread_dirty_pages && !zone_dirty_ok(zone))
continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
@@ -2553,28 +2555,8 @@ zonelist_scan:
if (alloc_flags & ALLOC_NO_WATERMARKS)
goto try_this_zone;
- if (IS_ENABLED(CONFIG_NUMA) &&
- !did_zlc_setup && nr_online_nodes > 1) {
- /*
- * we do zlc_setup if there are multiple nodes
- * and before considering the first zone allowed
- * by the cpuset.
- */
- allowednodes = zlc_setup(zonelist, alloc_flags);
- zlc_active = 1;
- did_zlc_setup = 1;
- }
-
if (zone_reclaim_mode == 0 ||
!zone_allows_reclaim(ac->preferred_zone, zone))
- goto this_zone_full;
-
- /*
- * As we may have just activated ZLC, check if the first
- * eligible zone has failed zone_reclaim recently.
- */
- if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
- !zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
ret = zone_reclaim(zone, gfp_mask, order);
@@ -2591,34 +2573,26 @@ zonelist_scan:
ac->classzone_idx, alloc_flags))
goto try_this_zone;
- /*
- * Failed to reclaim enough to meet watermark.
- * Only mark the zone full if checking the min
- * watermark or if we failed to reclaim just
- * 1<<order pages or else the page allocator
- * fastpath will prematurely mark zones full
- * when the watermark is between the low and
- * min watermarks.
- */
- if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) ||
- ret == ZONE_RECLAIM_SOME)
- goto this_zone_full;
-
continue;
}
}
try_this_zone:
page = buffered_rmqueue(ac->preferred_zone, zone, order,
- gfp_mask, ac->migratetype);
+ gfp_mask, alloc_flags, ac->migratetype);
if (page) {
if (prep_new_page(page, order, gfp_mask, alloc_flags))
goto try_this_zone;
+
+ /*
+ * If this is a high-order atomic allocation then check
+ * if the pageblock should be reserved for the future
+ */
+ if (unlikely(order && (alloc_flags & ALLOC_HARDER)))
+ reserve_highatomic_pageblock(page, zone, order);
+
return page;
}
-this_zone_full:
- if (IS_ENABLED(CONFIG_NUMA) && zlc_active)
- zlc_mark_zone_full(zonelist, z);
}
/*
@@ -2639,12 +2613,6 @@ this_zone_full:
zonelist_rescan = true;
}
- if (unlikely(IS_ENABLED(CONFIG_NUMA) && zlc_active)) {
- /* Disable zlc cache for second zonelist scan */
- zlc_active = 0;
- zonelist_rescan = true;
- }
-
if (zonelist_rescan)
goto zonelist_scan;
@@ -2669,7 +2637,7 @@ static DEFINE_RATELIMIT_STATE(nopage_rs,
DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
-void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...)
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
@@ -2686,7 +2654,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
if (test_thread_flag(TIF_MEMDIE) ||
(current->flags & (PF_MEMALLOC | PF_EXITING)))
filter &= ~SHOW_MEM_FILTER_NODES;
- if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+ if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
filter &= ~SHOW_MEM_FILTER_NODES;
if (fmt) {
@@ -2703,7 +2671,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
va_end(args);
}
- pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
+ pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n",
current->comm, order, gfp_mask);
dump_stack();
@@ -2889,19 +2857,17 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
if (unlikely(!(*did_some_progress)))
return NULL;
- /* After successful reclaim, reconsider all zones for allocation */
- if (IS_ENABLED(CONFIG_NUMA))
- zlc_clear_zones_full(ac->zonelist);
-
retry:
page = get_page_from_freelist(gfp_mask, order,
alloc_flags & ~ALLOC_NO_WATERMARKS, ac);
/*
* If an allocation failed after direct reclaim, it could be because
- * pages are pinned on the per-cpu lists. Drain them and try again
+ * pages are pinned on the per-cpu lists or in high alloc reserves.
+ * Shrink them them and try again
*/
if (!page && !drained) {
+ unreserve_highatomic_pageblock(ac);
drain_all_pages(NULL);
drained = true;
goto retry;
@@ -2946,7 +2912,6 @@ static inline int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD));
/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
@@ -2955,11 +2920,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
- * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
+ * set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
- if (atomic) {
+ if (gfp_mask & __GFP_ATOMIC) {
/*
* Not worth trying to allocate harder for __GFP_NOMEMALLOC even
* if it can't schedule.
@@ -2996,11 +2961,16 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
return !!(gfp_to_alloc_flags(gfp_mask) & ALLOC_NO_WATERMARKS);
}
+static inline bool is_thp_gfp_mask(gfp_t gfp_mask)
+{
+ return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
+}
+
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
{
- const gfp_t wait = gfp_mask & __GFP_WAIT;
+ bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
struct page *page = NULL;
int alloc_flags;
unsigned long pages_reclaimed = 0;
@@ -3021,15 +2991,23 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
}
/*
+ * We also sanity check to catch abuse of atomic reserves being used by
+ * callers that are not in atomic context.
+ */
+ if (WARN_ON_ONCE((gfp_mask & (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)) ==
+ (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
+ gfp_mask &= ~__GFP_ATOMIC;
+
+ /*
* If this allocation cannot block and it is for a specific node, then
* fail early. There's no need to wakeup kswapd or retry for a
* speculative node-specific allocation.
*/
- if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait)
+ if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim)
goto nopage;
retry:
- if (!(gfp_mask & __GFP_NO_KSWAPD))
+ if (gfp_mask & __GFP_KSWAPD_RECLAIM)
wake_all_kswapds(order, ac);
/*
@@ -3072,8 +3050,8 @@ retry:
}
}
- /* Atomic allocations - we can't balance anything */
- if (!wait) {
+ /* Caller is not willing to reclaim, we can't balance anything */
+ if (!can_direct_reclaim) {
/*
* All existing users of the deprecated __GFP_NOFAIL are
* blockable, so warn of any new users that actually allow this
@@ -3103,7 +3081,7 @@ retry:
goto got_pg;
/* Checks for THP-specific high-order allocations */
- if ((gfp_mask & GFP_TRANSHUGE) == GFP_TRANSHUGE) {
+ if (is_thp_gfp_mask(gfp_mask)) {
/*
* If compaction is deferred for high-order allocations, it is
* because sync compaction recently failed. If this is the case
@@ -3138,8 +3116,7 @@ retry:
* fault, so use asynchronous memory compaction for THP unless it is
* khugepaged trying to collapse.
*/
- if ((gfp_mask & GFP_TRANSHUGE) != GFP_TRANSHUGE ||
- (current->flags & PF_KTHREAD))
+ if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD))
migration_mode = MIGRATE_SYNC_LIGHT;
/* Try direct reclaim and then allocating */
@@ -3210,7 +3187,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
lockdep_trace_alloc(gfp_mask);
- might_sleep_if(gfp_mask & __GFP_WAIT);
+ might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
return NULL;
@@ -3231,6 +3208,10 @@ retry_cpuset:
/* We set it here, as __alloc_pages_slowpath might have changed it */
ac.zonelist = zonelist;
+
+ /* Dirty zone balancing only done in the fast path */
+ ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
+
/* The preferred zone is used for statistics later */
preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx,
ac.nodemask ? : &cpuset_current_mems_allowed,
@@ -3249,6 +3230,7 @@ retry_cpuset:
* complete.
*/
alloc_mask = memalloc_noio_flags(gfp_mask);
+ ac.spread_dirty_pages = false;
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
}
@@ -3467,7 +3449,8 @@ void free_kmem_pages(unsigned long addr, unsigned int order)
}
}
-static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
+static void *make_alloc_exact(unsigned long addr, unsigned int order,
+ size_t size)
{
if (addr) {
unsigned long alloc_end = addr + (PAGE_SIZE << order);
@@ -3517,7 +3500,7 @@ EXPORT_SYMBOL(alloc_pages_exact);
*/
void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
{
- unsigned order = get_order(size);
+ unsigned int order = get_order(size);
struct page *p = alloc_pages_node(nid, gfp_mask, order);
if (!p)
return NULL;
@@ -3666,7 +3649,6 @@ static void show_migration_types(unsigned char type)
[MIGRATE_UNMOVABLE] = 'U',
[MIGRATE_RECLAIMABLE] = 'E',
[MIGRATE_MOVABLE] = 'M',
- [MIGRATE_RESERVE] = 'R',
#ifdef CONFIG_CMA
[MIGRATE_CMA] = 'C',
#endif
@@ -3819,7 +3801,8 @@ void show_free_areas(unsigned int filter)
}
for_each_populated_zone(zone) {
- unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ unsigned int order;
+ unsigned long nr[MAX_ORDER], flags, total = 0;
unsigned char types[MAX_ORDER];
if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -4168,7 +4151,7 @@ static void build_zonelists(pg_data_t *pgdat)
nodemask_t used_mask;
int local_node, prev_node;
struct zonelist *zonelist;
- int order = current_zonelist_order;
+ unsigned int order = current_zonelist_order;
/* initialize zonelists */
for (i = 0; i < MAX_ZONELISTS; i++) {
@@ -4212,20 +4195,6 @@ static void build_zonelists(pg_data_t *pgdat)
build_thisnode_zonelists(pgdat);
}
-/* Construct the zonelist performance cache - see further mmzone.h */
-static void build_zonelist_cache(pg_data_t *pgdat)
-{
- struct zonelist *zonelist;
- struct zonelist_cache *zlc;
- struct zoneref *z;
-
- zonelist = &pgdat->node_zonelists[0];
- zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
- bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
- for (z = zonelist->_zonerefs; z->zone; z++)
- zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
-}
-
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
/*
* Return node id of node used for "local" allocations.
@@ -4286,12 +4255,6 @@ static void build_zonelists(pg_data_t *pgdat)
zonelist->_zonerefs[j].zone_idx = 0;
}
-/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
-static void build_zonelist_cache(pg_data_t *pgdat)
-{
- pgdat->node_zonelists[0].zlcache_ptr = NULL;
-}
-
#endif /* CONFIG_NUMA */
/*
@@ -4332,14 +4295,12 @@ static int __build_all_zonelists(void *data)
if (self && !node_online(self->node_id)) {
build_zonelists(self);
- build_zonelist_cache(self);
}
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
build_zonelists(pgdat);
- build_zonelist_cache(pgdat);
}
/*
@@ -4499,120 +4460,6 @@ static inline unsigned long wait_table_bits(unsigned long size)
}
/*
- * Check if a pageblock contains reserved pages
- */
-static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
-{
- unsigned long pfn;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
- if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
- return 1;
- }
- return 0;
-}
-
-/*
- * Mark a number of pageblocks as MIGRATE_RESERVE. The number
- * of blocks reserved is based on min_wmark_pages(zone). The memory within
- * the reserve will tend to store contiguous free pages. Setting min_free_kbytes
- * higher will lead to a bigger reserve which will get freed as contiguous
- * blocks as reclaim kicks in
- */
-static void setup_zone_migrate_reserve(struct zone *zone)
-{
- unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
- struct page *page;
- unsigned long block_migratetype;
- int reserve;
- int old_reserve;
-
- /*
- * Get the start pfn, end pfn and the number of blocks to reserve
- * We have to be careful to be aligned to pageblock_nr_pages to
- * make sure that we always check pfn_valid for the first page in
- * the block.
- */
- start_pfn = zone->zone_start_pfn;
- end_pfn = zone_end_pfn(zone);
- start_pfn = roundup(start_pfn, pageblock_nr_pages);
- reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
- pageblock_order;
-
- /*
- * Reserve blocks are generally in place to help high-order atomic
- * allocations that are short-lived. A min_free_kbytes value that
- * would result in more than 2 reserve blocks for atomic allocations
- * is assumed to be in place to help anti-fragmentation for the
- * future allocation of hugepages at runtime.
- */
- reserve = min(2, reserve);
- old_reserve = zone->nr_migrate_reserve_block;
-
- /* When memory hot-add, we almost always need to do nothing */
- if (reserve == old_reserve)
- return;
- zone->nr_migrate_reserve_block = reserve;
-
- for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
- if (!early_page_nid_uninitialised(pfn, zone_to_nid(zone)))
- return;
-
- if (!pfn_valid(pfn))
- continue;
- page = pfn_to_page(pfn);
-
- /* Watch out for overlapping nodes */
- if (page_to_nid(page) != zone_to_nid(zone))
- continue;
-
- block_migratetype = get_pageblock_migratetype(page);
-
- /* Only test what is necessary when the reserves are not met */
- if (reserve > 0) {
- /*
- * Blocks with reserved pages will never free, skip
- * them.
- */
- block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
- if (pageblock_is_reserved(pfn, block_end_pfn))
- continue;
-
- /* If this block is reserved, account for it */
- if (block_migratetype == MIGRATE_RESERVE) {
- reserve--;
- continue;
- }
-
- /* Suitable for reserving if this block is movable */
- if (block_migratetype == MIGRATE_MOVABLE) {
- set_pageblock_migratetype(page,
- MIGRATE_RESERVE);
- move_freepages_block(zone, page,
- MIGRATE_RESERVE);
- reserve--;
- continue;
- }
- } else if (!old_reserve) {
- /*
- * At boot time we don't need to scan the whole zone
- * for turning off MIGRATE_RESERVE.
- */
- break;
- }
-
- /*
- * If the reserve is met and this is a previous reserved block,
- * take it back
- */
- if (block_migratetype == MIGRATE_RESERVE) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- move_freepages_block(zone, page, MIGRATE_MOVABLE);
- }
- }
-}
-
-/*
* Initially all pages are reserved - free ones are freed
* up by free_all_bootmem() once the early boot process is
* done. Non-atomic initialization, single-pass.
@@ -4651,9 +4498,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
* movable at startup. This will force kernel allocations
* to reserve their blocks rather than leaking throughout
* the address space during boot when many long-lived
- * kernel allocations are made. Later some blocks near
- * the start are marked MIGRATE_RESERVE by
- * setup_zone_migrate_reserve()
+ * kernel allocations are made.
*
* bitmap is created for zone's valid pfn range. but memmap
* can be created for invalid pages (for alignment)
@@ -6214,7 +6059,6 @@ static void __setup_per_zone_wmarks(void)
high_wmark_pages(zone) - low_wmark_pages(zone) -
atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
- setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -6836,7 +6680,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
unsigned migratetype)
{
unsigned long outer_start, outer_end;
- int ret = 0, order;
+ unsigned int order;
+ int ret = 0;
struct compact_control cc = {
.nr_migratepages = 0,