aboutsummaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c807
1 files changed, 485 insertions, 322 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0ee638f76eb..ef44ad736ca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
+#define MIN_PERCPU_PAGELIST_FRACTION (8)
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
@@ -205,7 +206,7 @@ static char * const zone_names[MAX_NR_ZONES] = {
};
int min_free_kbytes = 1024;
-int user_min_free_kbytes;
+int user_min_free_kbytes = -1;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
@@ -234,8 +235,8 @@ int page_group_by_mobility_disabled __read_mostly;
void set_pageblock_migratetype(struct page *page, int migratetype)
{
-
- if (unlikely(page_group_by_mobility_disabled))
+ if (unlikely(page_group_by_mobility_disabled &&
+ migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
set_pageblock_flags_group(page, (unsigned long)migratetype,
@@ -261,8 +262,9 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
} while (zone_span_seqretry(zone, seq));
if (ret)
- pr_err("page %lu outside zone [ %lu - %lu ]\n",
- pfn, start_pfn, start_pfn + sp);
+ pr_err("page 0x%lx outside node %d zone %s [ 0x%lx - 0x%lx ]\n",
+ pfn, zone_to_nid(zone), zone->name,
+ start_pfn, start_pfn + sp);
return ret;
}
@@ -295,7 +297,8 @@ static inline int bad_range(struct zone *zone, struct page *page)
}
#endif
-static void bad_page(struct page *page)
+static void bad_page(struct page *page, const char *reason,
+ unsigned long bad_flags)
{
static unsigned long resume;
static unsigned long nr_shown;
@@ -329,7 +332,7 @@ static void bad_page(struct page *page)
printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
- dump_page(page);
+ dump_page_badflags(page, reason, bad_flags);
print_modules();
dump_stack();
@@ -369,9 +372,11 @@ void prep_compound_page(struct page *page, unsigned long order)
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
- __SetPageTail(p);
set_page_count(p, 0);
p->first_page = page;
+ /* Make sure p->first_page is always valid for PageTail() */
+ smp_wmb();
+ __SetPageTail(p);
}
}
@@ -383,7 +388,7 @@ static int destroy_compound_page(struct page *page, unsigned long order)
int bad = 0;
if (unlikely(compound_order(page) != order)) {
- bad_page(page);
+ bad_page(page, "wrong compound order", 0);
bad++;
}
@@ -392,8 +397,11 @@ static int destroy_compound_page(struct page *page, unsigned long order)
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
- if (unlikely(!PageTail(p) || (p->first_page != page))) {
- bad_page(page);
+ if (unlikely(!PageTail(p))) {
+ bad_page(page, "PageTail not set", 0);
+ bad++;
+ } else if (unlikely(p->first_page != page)) {
+ bad_page(page, "first_page not consistent", 0);
bad++;
}
__ClearPageTail(p);
@@ -402,7 +410,8 @@ static int destroy_compound_page(struct page *page, unsigned long order)
return bad;
}
-static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+static inline void prep_zero_page(struct page *page, unsigned int order,
+ gfp_t gfp_flags)
{
int i;
@@ -446,7 +455,7 @@ static inline void set_page_guard_flag(struct page *page) { }
static inline void clear_page_guard_flag(struct page *page) { }
#endif
-static inline void set_page_order(struct page *page, int order)
+static inline void set_page_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
@@ -497,21 +506,31 @@ __find_buddy_index(unsigned long page_idx, unsigned int order)
* For recording page's order, we use page_private(page).
*/
static inline int page_is_buddy(struct page *page, struct page *buddy,
- int order)
+ unsigned int order)
{
if (!pfn_valid_within(page_to_pfn(buddy)))
return 0;
- if (page_zone_id(page) != page_zone_id(buddy))
- return 0;
-
if (page_is_guard(buddy) && page_order(buddy) == order) {
- VM_BUG_ON(page_count(buddy) != 0);
+ VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+
+ if (page_zone_id(page) != page_zone_id(buddy))
+ return 0;
+
return 1;
}
if (PageBuddy(buddy) && page_order(buddy) == order) {
- VM_BUG_ON(page_count(buddy) != 0);
+ VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+
+ /*
+ * zone check is done late to avoid uselessly
+ * calculating zone/node ids for pages that could
+ * never merge.
+ */
+ if (page_zone_id(page) != page_zone_id(buddy))
+ return 0;
+
return 1;
}
return 0;
@@ -543,6 +562,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
*/
static inline void __free_one_page(struct page *page,
+ unsigned long pfn,
struct zone *zone, unsigned int order,
int migratetype)
{
@@ -559,10 +579,10 @@ static inline void __free_one_page(struct page *page,
VM_BUG_ON(migratetype == -1);
- page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+ page_idx = pfn & ((1 << MAX_ORDER) - 1);
- VM_BUG_ON(page_idx & ((1 << order) - 1));
- VM_BUG_ON(bad_range(zone, page));
+ VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
+ VM_BUG_ON_PAGE(bad_range(zone, page), page);
while (order < MAX_ORDER-1) {
buddy_idx = __find_buddy_index(page_idx, order);
@@ -618,15 +638,26 @@ out:
static inline int free_pages_check(struct page *page)
{
- if (unlikely(page_mapcount(page) |
- (page->mapping != NULL) |
- (atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_FREE) |
- (mem_cgroup_bad_page_check(page)))) {
- bad_page(page);
+ const char *bad_reason = NULL;
+ unsigned long bad_flags = 0;
+
+ if (unlikely(page_mapcount(page)))
+ bad_reason = "nonzero mapcount";
+ if (unlikely(page->mapping != NULL))
+ bad_reason = "non-NULL mapping";
+ if (unlikely(atomic_read(&page->_count) != 0))
+ bad_reason = "nonzero _count";
+ if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) {
+ bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
+ bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
+ }
+ if (unlikely(mem_cgroup_bad_page_check(page)))
+ bad_reason = "cgroup check failed";
+ if (unlikely(bad_reason)) {
+ bad_page(page, bad_reason, bad_flags);
return 1;
}
- page_nid_reset_last(page);
+ page_cpupid_reset_last(page);
if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
return 0;
@@ -683,7 +714,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
list_del(&page->lru);
mt = get_freepage_migratetype(page);
/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
- __free_one_page(page, zone, 0, mt);
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt);
trace_mm_page_pcpu_drain(page, 0, mt);
if (likely(!is_migrate_isolate_page(page))) {
__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
@@ -695,13 +726,15 @@ static void free_pcppages_bulk(struct zone *zone, int count,
spin_unlock(&zone->lock);
}
-static void free_one_page(struct zone *zone, struct page *page, int order,
+static void free_one_page(struct zone *zone,
+ struct page *page, unsigned long pfn,
+ unsigned int order,
int migratetype)
{
spin_lock(&zone->lock);
zone->pages_scanned = 0;
- __free_one_page(page, zone, order, migratetype);
+ __free_one_page(page, pfn, zone, order, migratetype);
if (unlikely(!is_migrate_isolate(migratetype)))
__mod_zone_freepage_state(zone, 1 << order, migratetype);
spin_unlock(&zone->lock);
@@ -738,15 +771,16 @@ static void __free_pages_ok(struct page *page, unsigned int order)
{
unsigned long flags;
int migratetype;
+ unsigned long pfn = page_to_pfn(page);
if (!free_pages_prepare(page, order))
return;
+ migratetype = get_pfnblock_migratetype(page, pfn);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
- migratetype = get_pageblock_migratetype(page);
set_freepage_migratetype(page, migratetype);
- free_one_page(page_zone(page), page, order, migratetype);
+ free_one_page(page_zone(page), page, pfn, order, migratetype);
local_irq_restore(flags);
}
@@ -782,9 +816,21 @@ void __init init_cma_reserved_pageblock(struct page *page)
set_page_count(p, 0);
} while (++p, --i);
- set_page_refcounted(page);
set_pageblock_migratetype(page, MIGRATE_CMA);
- __free_pages(page, pageblock_order);
+
+ if (pageblock_order >= MAX_ORDER) {
+ i = pageblock_nr_pages;
+ p = page;
+ do {
+ set_page_refcounted(p);
+ __free_pages(p, MAX_ORDER - 1);
+ p += MAX_ORDER_NR_PAGES;
+ } while (i -= MAX_ORDER_NR_PAGES);
+ } else {
+ set_page_refcounted(page);
+ __free_pages(page, pageblock_order);
+ }
+
adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif
@@ -813,7 +859,7 @@ static inline void expand(struct zone *zone, struct page *page,
area--;
high--;
size >>= 1;
- VM_BUG_ON(bad_range(zone, &page[size]));
+ VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
#ifdef CONFIG_DEBUG_PAGEALLOC
if (high < debug_guardpage_minorder()) {
@@ -843,18 +889,29 @@ static inline void expand(struct zone *zone, struct page *page,
*/
static inline int check_new_page(struct page *page)
{
- if (unlikely(page_mapcount(page) |
- (page->mapping != NULL) |
- (atomic_read(&page->_count) != 0) |
- (page->flags & PAGE_FLAGS_CHECK_AT_PREP) |
- (mem_cgroup_bad_page_check(page)))) {
- bad_page(page);
+ const char *bad_reason = NULL;
+ unsigned long bad_flags = 0;
+
+ if (unlikely(page_mapcount(page)))
+ bad_reason = "nonzero mapcount";
+ if (unlikely(page->mapping != NULL))
+ bad_reason = "non-NULL mapping";
+ if (unlikely(atomic_read(&page->_count) != 0))
+ bad_reason = "nonzero _count";
+ if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
+ bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
+ bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
+ }
+ if (unlikely(mem_cgroup_bad_page_check(page)))
+ bad_reason = "cgroup check failed";
+ if (unlikely(bad_reason)) {
+ bad_page(page, bad_reason, bad_flags);
return 1;
}
return 0;
}
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags)
{
int i;
@@ -903,6 +960,7 @@ 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;
}
@@ -955,7 +1013,7 @@ int move_freepages(struct zone *zone,
for (page = start_page; page <= end_page;) {
/* Make sure we are not inadvertently changing nodes */
- VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone));
+ VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
@@ -1027,6 +1085,12 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
{
int current_order = page_order(page);
+ /*
+ * When borrowing from MIGRATE_CMA, we need to release the excess
+ * 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;
@@ -1058,16 +1122,17 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page,
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
+__rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
{
struct free_area *area;
- int current_order;
+ unsigned int current_order;
struct page *page;
int migratetype, new_type, i;
/* Find the largest possible block of pages in the other list */
- for (current_order = MAX_ORDER-1; current_order >= order;
- --current_order) {
+ for (current_order = MAX_ORDER-1;
+ current_order >= order && current_order <= MAX_ORDER-1;
+ --current_order) {
for (i = 0;; i++) {
migratetype = fallbacks[start_migratetype][i];
@@ -1091,21 +1156,17 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
list_del(&page->lru);
rmv_page_order(page);
- /*
- * Borrow the excess buddy pages as well, irrespective
- * of whether we stole freepages, or took ownership of
- * the pageblock or not.
- *
- * Exception: When borrowing from MIGRATE_CMA, release
- * the excess buddy pages to CMA itself.
- */
expand(zone, page, order, current_order, area,
- is_migrate_cma(migratetype)
- ? migratetype : start_migratetype);
+ 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 == start_migratetype);
+ trace_mm_page_alloc_extfrag(page, order, current_order,
+ start_migratetype, migratetype, new_type);
return page;
}
@@ -1151,9 +1212,9 @@ retry_reserve:
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype, int cold)
+ int migratetype, bool cold)
{
- int mt = migratetype, i;
+ int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
@@ -1170,18 +1231,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
* merge IO requests if the physical pages are ordered
* properly.
*/
- if (likely(cold == 0))
+ if (likely(!cold))
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));
}
@@ -1305,7 +1360,7 @@ void mark_free_pages(struct zone *zone)
{
unsigned long pfn, max_zone_pfn;
unsigned long flags;
- int order, t;
+ unsigned int order, t;
struct list_head *curr;
if (zone_is_empty(zone))
@@ -1337,19 +1392,20 @@ void mark_free_pages(struct zone *zone)
/*
* Free a 0-order page
- * cold == 1 ? free a cold page : free a hot page
+ * cold == true ? free a cold page : free a hot page
*/
-void free_hot_cold_page(struct page *page, int cold)
+void free_hot_cold_page(struct page *page, bool cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
+ unsigned long pfn = page_to_pfn(page);
int migratetype;
if (!free_pages_prepare(page, 0))
return;
- migratetype = get_pageblock_migratetype(page);
+ migratetype = get_pfnblock_migratetype(page, pfn);
set_freepage_migratetype(page, migratetype);
local_irq_save(flags);
__count_vm_event(PGFREE);
@@ -1363,17 +1419,17 @@ void free_hot_cold_page(struct page *page, int cold)
*/
if (migratetype >= MIGRATE_PCPTYPES) {
if (unlikely(is_migrate_isolate(migratetype))) {
- free_one_page(zone, page, 0, migratetype);
+ free_one_page(zone, page, pfn, 0, migratetype);
goto out;
}
migratetype = MIGRATE_MOVABLE;
}
pcp = &this_cpu_ptr(zone->pageset)->pcp;
- if (cold)
- list_add_tail(&page->lru, &pcp->lists[migratetype]);
- else
+ if (!cold)
list_add(&page->lru, &pcp->lists[migratetype]);
+ else
+ list_add_tail(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
unsigned long batch = ACCESS_ONCE(pcp->batch);
@@ -1388,7 +1444,7 @@ out:
/*
* Free a list of 0-order pages
*/
-void free_hot_cold_page_list(struct list_head *list, int cold)
+void free_hot_cold_page_list(struct list_head *list, bool cold)
{
struct page *page, *next;
@@ -1410,8 +1466,8 @@ void split_page(struct page *page, unsigned int order)
{
int i;
- VM_BUG_ON(PageCompound(page));
- VM_BUG_ON(!page_count(page));
+ VM_BUG_ON_PAGE(PageCompound(page), page);
+ VM_BUG_ON_PAGE(!page_count(page), page);
#ifdef CONFIG_KMEMCHECK
/*
@@ -1500,12 +1556,12 @@ int split_free_page(struct page *page)
*/
static inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
- struct zone *zone, int order, gfp_t gfp_flags,
- int migratetype)
+ struct zone *zone, unsigned int order,
+ gfp_t gfp_flags, int migratetype)
{
unsigned long flags;
struct page *page;
- int cold = !!(gfp_flags & __GFP_COLD);
+ bool cold = ((gfp_flags & __GFP_COLD) != 0);
again:
if (likely(order == 0)) {
@@ -1550,15 +1606,16 @@ again:
if (!page)
goto failed;
__mod_zone_freepage_state(zone, -(1 << order),
- get_pageblock_migratetype(page));
+ get_freepage_migratetype(page));
}
__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
+
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
local_irq_restore(flags);
- VM_BUG_ON(bad_range(zone, page));
+ VM_BUG_ON_PAGE(bad_range(zone, page), page);
if (prep_new_page(page, order, gfp_flags))
goto again;
return page;
@@ -1649,8 +1706,9 @@ static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
* Return true if free pages are above 'mark'. This takes into account the order
* of the allocation.
*/
-static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags, long free_pages)
+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 my go negative - that's OK */
long min = mark;
@@ -1684,15 +1742,15 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
return true;
}
-bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
int classzone_idx, int alloc_flags)
{
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
-bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
- int classzone_idx, int alloc_flags)
+bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
+ unsigned long mark, int classzone_idx, int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
@@ -1711,7 +1769,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
* 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 in zonelist, then
+ * 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].)
*
@@ -1822,23 +1880,13 @@ static void zlc_clear_zones_full(struct zonelist *zonelist)
static bool zone_local(struct zone *local_zone, struct zone *zone)
{
- return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+ return local_zone->node == zone->node;
}
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
- return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes);
-}
-
-static void __paginginit init_zone_allows_reclaim(int nid)
-{
- int i;
-
- for_each_online_node(i)
- if (node_distance(nid, i) <= RECLAIM_DISTANCE)
- node_set(i, NODE_DATA(nid)->reclaim_nodes);
- else
- zone_reclaim_mode = 1;
+ return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
+ RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
@@ -1872,9 +1920,6 @@ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
return true;
}
-static inline void init_zone_allows_reclaim(int nid)
-{
-}
#endif /* CONFIG_NUMA */
/*
@@ -1884,17 +1929,17 @@ static inline void init_zone_allows_reclaim(int nid)
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
- struct zone *preferred_zone, int migratetype)
+ struct zone *preferred_zone, int classzone_idx, int migratetype)
{
struct zoneref *z;
struct page *page = NULL;
- int classzone_idx;
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);
- classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
@@ -1907,30 +1952,20 @@ zonelist_scan:
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
- if ((alloc_flags & ALLOC_CPUSET) &&
+ if (cpusets_enabled() &&
+ (alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
continue;
- BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
- if (unlikely(alloc_flags & ALLOC_NO_WATERMARKS))
- goto try_this_zone;
/*
* Distribute pages in proportion to the individual
* zone size to ensure fair page aging. The zone a
* page was allocated in should have no effect on the
* time the page has in memory before being reclaimed.
- *
- * When zone_reclaim_mode is enabled, try to stay in
- * local zones in the fastpath. If that fails, the
- * slowpath is entered, which will do another pass
- * starting with the local zones, but ultimately fall
- * back to remote zones that do not partake in the
- * fairness round-robin cycle of this zonelist.
*/
- if (alloc_flags & ALLOC_WMARK_LOW) {
- if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
+ if (alloc_flags & ALLOC_FAIR) {
+ if (!zone_local(preferred_zone, zone))
continue;
- if (zone_reclaim_mode &&
- !zone_local(preferred_zone, zone))
+ if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
continue;
}
/*
@@ -1959,15 +1994,19 @@ zonelist_scan:
* will require awareness of zones in the
* dirty-throttling and the flusher threads.
*/
- if ((alloc_flags & ALLOC_WMARK_LOW) &&
- (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
- goto this_zone_full;
+ if (consider_zone_dirty && !zone_dirty_ok(zone))
+ continue;
mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
if (!zone_watermark_ok(zone, order, mark,
classzone_idx, alloc_flags)) {
int ret;
+ /* Checked here to keep the fast path fast */
+ BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
+ if (alloc_flags & ALLOC_NO_WATERMARKS)
+ goto try_this_zone;
+
if (IS_ENABLED(CONFIG_NUMA) &&
!did_zlc_setup && nr_online_nodes > 1) {
/*
@@ -2029,7 +2068,7 @@ try_this_zone:
if (page)
break;
this_zone_full:
- if (IS_ENABLED(CONFIG_NUMA))
+ if (IS_ENABLED(CONFIG_NUMA) && zlc_active)
zlc_mark_zone_full(zonelist, z);
}
@@ -2079,13 +2118,6 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
return;
/*
- * Walking all memory to count page types is very expensive and should
- * be inhibited in non-blockable contexts.
- */
- if (!(gfp_mask & __GFP_WAIT))
- filter |= SHOW_MEM_FILTER_PAGE_COUNT;
-
- /*
* This documents exceptions given to allocations in certain
* contexts that are allowed to allocate outside current's set
* of allowed nodes.
@@ -2165,7 +2197,7 @@ static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, struct zone *preferred_zone,
- int migratetype)
+ int classzone_idx, int migratetype)
{
struct page *page;
@@ -2183,7 +2215,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
order, zonelist, high_zoneidx,
ALLOC_WMARK_HIGH|ALLOC_CPUSET,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (page)
goto out;
@@ -2218,7 +2250,7 @@ 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 classzone_idx, int migratetype, enum migrate_mode mode,
bool *contended_compaction, bool *deferred_compaction,
unsigned long *did_some_progress)
{
@@ -2232,7 +2264,7 @@ __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;
@@ -2246,13 +2278,10 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
page = get_page_from_freelist(gfp_mask, nodemask,
order, zonelist, high_zoneidx,
alloc_flags & ~ALLOC_NO_WATERMARKS,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (page) {
preferred_zone->compact_blockskip_flush = false;
- preferred_zone->compact_considered = 0;
- preferred_zone->compact_defer_shift = 0;
- if (order >= preferred_zone->compact_order_failed)
- preferred_zone->compact_order_failed = order + 1;
+ compaction_defer_reset(preferred_zone, order, true);
count_vm_event(COMPACTSUCCESS);
return page;
}
@@ -2268,7 +2297,7 @@ __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();
@@ -2281,9 +2310,9 @@ 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 classzone_idx, int migratetype,
+ enum migrate_mode mode, bool *contended_compaction,
+ bool *deferred_compaction, unsigned long *did_some_progress)
{
return NULL;
}
@@ -2322,7 +2351,7 @@ static inline struct page *
__alloc_pages_direct_reclaim(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, unsigned long *did_some_progress)
+ int classzone_idx, int migratetype, unsigned long *did_some_progress)
{
struct page *page = NULL;
bool drained = false;
@@ -2340,7 +2369,8 @@ retry:
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx,
alloc_flags & ~ALLOC_NO_WATERMARKS,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx,
+ migratetype);
/*
* If an allocation failed after direct reclaim, it could be because
@@ -2363,14 +2393,14 @@ static inline struct page *
__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, struct zone *preferred_zone,
- int migratetype)
+ int classzone_idx, int migratetype)
{
struct page *page;
do {
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx, ALLOC_NO_WATERMARKS,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (!page && gfp_mask & __GFP_NOFAIL)
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
@@ -2379,37 +2409,45 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
return page;
}
-static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist,
- enum zone_type high_zoneidx,
- struct zone *preferred_zone)
+static void reset_alloc_batches(struct zonelist *zonelist,
+ enum zone_type high_zoneidx,
+ struct zone *preferred_zone)
{
struct zoneref *z;
struct zone *zone;
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
- if (!(gfp_mask & __GFP_NO_KSWAPD))
- wakeup_kswapd(zone, order, zone_idx(preferred_zone));
/*
* Only reset the batches of zones that were actually
- * considered in the fast path, we don't want to
- * thrash fairness information for zones that are not
+ * considered in the fairness pass, we don't want to
+ * trash fairness information for zones that are not
* actually part of this zonelist's round-robin cycle.
*/
- if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
+ if (!zone_local(preferred_zone, zone))
continue;
mod_zone_page_state(zone, NR_ALLOC_BATCH,
- high_wmark_pages(zone) -
- low_wmark_pages(zone) -
- zone_page_state(zone, NR_ALLOC_BATCH));
+ high_wmark_pages(zone) - low_wmark_pages(zone) -
+ atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
}
}
+static void wake_all_kswapds(unsigned int order,
+ struct zonelist *zonelist,
+ enum zone_type high_zoneidx,
+ struct zone *preferred_zone)
+{
+ struct zoneref *z;
+ struct zone *zone;
+
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+ wakeup_kswapd(zone, order, zone_idx(preferred_zone));
+}
+
static inline int
gfp_to_alloc_flags(gfp_t gfp_mask)
{
int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- const gfp_t wait = gfp_mask & __GFP_WAIT;
+ 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);
@@ -2418,20 +2456,20 @@ 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 (!wait) and ALLOC_HIGH (__GFP_HIGH).
+ * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
- if (!wait) {
+ if (atomic) {
/*
- * Not worth trying to allocate harder for
- * __GFP_NOMEMALLOC even if it can't schedule.
+ * Not worth trying to allocate harder for __GFP_NOMEMALLOC even
+ * if it can't schedule.
*/
- if (!(gfp_mask & __GFP_NOMEMALLOC))
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
alloc_flags |= ALLOC_HARDER;
/*
- * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the
+ * comment for __cpuset_node_allowed_softwall().
*/
alloc_flags &= ~ALLOC_CPUSET;
} else if (unlikely(rt_task(current)) && !in_interrupt())
@@ -2463,14 +2501,14 @@ static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, struct zone *preferred_zone,
- int migratetype)
+ int classzone_idx, int migratetype)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
struct page *page = NULL;
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;
@@ -2494,12 +2532,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
* over allocated.
*/
if (IS_ENABLED(CONFIG_NUMA) &&
- (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+ (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
restart:
- prepare_slowpath(gfp_mask, order, zonelist,
- high_zoneidx, preferred_zone);
+ if (!(gfp_mask & __GFP_NO_KSWAPD))
+ wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone);
/*
* OK, we're below the kswapd watermark and have kicked background
@@ -2512,15 +2550,18 @@ restart:
* Find the true preferred zone if the allocation is unconstrained by
* cpusets.
*/
- if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
- first_zones_zonelist(zonelist, high_zoneidx, NULL,
- &preferred_zone);
+ if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) {
+ struct zoneref *preferred_zoneref;
+ preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx,
+ NULL, &preferred_zone);
+ classzone_idx = zonelist_zone_idx(preferred_zoneref);
+ }
rebalance:
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (page)
goto got_pg;
@@ -2535,15 +2576,22 @@ rebalance:
page = __alloc_pages_high_priority(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (page) {
goto got_pg;
}
}
/* Atomic allocations - we can't balance anything */
- if (!wait)
+ if (!wait) {
+ /*
+ * All existing users of the deprecated __GFP_NOFAIL are
+ * blockable, so warn of any new users that actually allow this
+ * type of allocation to fail.
+ */
+ WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
goto nopage;
+ }
/* Avoid recursion of direct reclaim */
if (current->flags & PF_MEMALLOC)
@@ -2557,17 +2605,23 @@ 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,
+ classzone_idx, migratetype,
+ migration_mode, &contended_compaction,
&deferred_compaction,
&did_some_progress);
if (page)
goto got_pg;
- sync_migration = true;
+
+ /*
+ * It can become very expensive to allocate transparent hugepages at
+ * fault, so use asynchronous memory compaction for THP unless it is
+ * khugepaged trying to collapse.
+ */
+ if (!(gfp_mask & __GFP_NO_KSWAPD) || (current->flags & PF_KTHREAD))
+ migration_mode = MIGRATE_SYNC_LIGHT;
/*
* If compaction is deferred for high-order allocations, it is because
@@ -2584,7 +2638,8 @@ rebalance:
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress);
+ classzone_idx, migratetype,
+ &did_some_progress);
if (page)
goto got_pg;
@@ -2593,7 +2648,7 @@ rebalance:
* running out of options and have to consider going OOM
*/
if (!did_some_progress) {
- if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ if (oom_gfp_allowed(gfp_mask)) {
if (oom_killer_disabled)
goto nopage;
/* Coredumps can quickly deplete all memory reserves */
@@ -2603,7 +2658,7 @@ rebalance:
page = __alloc_pages_may_oom(gfp_mask, order,
zonelist, high_zoneidx,
nodemask, preferred_zone,
- migratetype);
+ classzone_idx, migratetype);
if (page)
goto got_pg;
@@ -2642,12 +2697,11 @@ 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,
+ classzone_idx, migratetype,
+ migration_mode, &contended_compaction,
&deferred_compaction,
&did_some_progress);
if (page)
@@ -2673,11 +2727,12 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zone *preferred_zone;
+ struct zoneref *preferred_zoneref;
struct page *page = NULL;
int migratetype = allocflags_to_migratetype(gfp_mask);
unsigned int cpuset_mems_cookie;
- int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET;
- struct mem_cgroup *memcg = NULL;
+ int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR;
+ int classzone_idx;
gfp_mask &= gfp_allowed_mask;
@@ -2696,33 +2751,44 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
- /*
- * Will only have any effect when __GFP_KMEMCG is set. This is
- * verified in the (always inline) callee
- */
- if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
- return NULL;
-
retry_cpuset:
- cpuset_mems_cookie = get_mems_allowed();
+ cpuset_mems_cookie = read_mems_allowed_begin();
/* The preferred zone is used for statistics later */
- first_zones_zonelist(zonelist, high_zoneidx,
+ preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx,
nodemask ? : &cpuset_current_mems_allowed,
&preferred_zone);
if (!preferred_zone)
goto out;
+ classzone_idx = zonelist_zone_idx(preferred_zoneref);
#ifdef CONFIG_CMA
if (allocflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
#endif
+retry:
/* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
zonelist, high_zoneidx, alloc_flags,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
if (unlikely(!page)) {
/*
+ * The first pass makes sure allocations are spread
+ * fairly within the local node. However, the local
+ * node might have free pages left after the fairness
+ * batches are exhausted, and remote zones haven't
+ * even been considered yet. Try once more without
+ * fairness, and include remote zones now, before
+ * entering the slowpath and waking kswapd: prefer
+ * spilling to a remote zone over swapping locally.
+ */
+ if (alloc_flags & ALLOC_FAIR) {
+ reset_alloc_batches(zonelist, high_zoneidx,
+ preferred_zone);
+ alloc_flags &= ~ALLOC_FAIR;
+ goto retry;
+ }
+ /*
* Runtime PM, block IO and its error handling path
* can deadlock because I/O on the device might not
* complete.
@@ -2730,7 +2796,7 @@ retry_cpuset:
gfp_mask = memalloc_noio_flags(gfp_mask);
page = __alloc_pages_slowpath(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
- preferred_zone, migratetype);
+ preferred_zone, classzone_idx, migratetype);
}
trace_mm_page_alloc(page, order, gfp_mask, migratetype);
@@ -2742,11 +2808,9 @@ out:
* the mask is being updated. If a page allocation is about to fail,
* check if the cpuset changed during allocation and if so, retry.
*/
- if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
- memcg_kmem_commit_charge(page, memcg, order);
-
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2781,7 +2845,7 @@ void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
- free_hot_cold_page(page, 0);
+ free_hot_cold_page(page, false);
else
__free_pages_ok(page, order);
}
@@ -2800,27 +2864,51 @@ void free_pages(unsigned long addr, unsigned int order)
EXPORT_SYMBOL(free_pages);
/*
- * __free_memcg_kmem_pages and free_memcg_kmem_pages will free
- * pages allocated with __GFP_KMEMCG.
- *
- * Those pages are accounted to a particular memcg, embedded in the
- * corresponding page_cgroup. To avoid adding a hit in the allocator to search
- * for that information only to find out that it is NULL for users who have no
- * interest in that whatsoever, we provide these functions.
+ * alloc_kmem_pages charges newly allocated pages to the kmem resource counter
+ * of the current memory cgroup.
*
- * The caller knows better which flags it relies on.
+ * It should be used when the caller would like to use kmalloc, but since the
+ * allocation is large, it has to fall back to the page allocator.
+ */
+struct page *alloc_kmem_pages(gfp_t gfp_mask, unsigned int order)
+{
+ struct page *page;
+ struct mem_cgroup *memcg = NULL;
+
+ if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+ return NULL;
+ page = alloc_pages(gfp_mask, order);
+ memcg_kmem_commit_charge(page, memcg, order);
+ return page;
+}
+
+struct page *alloc_kmem_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
+{
+ struct page *page;
+ struct mem_cgroup *memcg = NULL;
+
+ if (!memcg_kmem_newpage_charge(gfp_mask, &memcg, order))
+ return NULL;
+ page = alloc_pages_node(nid, gfp_mask, order);
+ memcg_kmem_commit_charge(page, memcg, order);
+ return page;
+}
+
+/*
+ * __free_kmem_pages and free_kmem_pages will free pages allocated with
+ * alloc_kmem_pages.
*/
-void __free_memcg_kmem_pages(struct page *page, unsigned int order)
+void __free_kmem_pages(struct page *page, unsigned int order)
{
memcg_kmem_uncharge_pages(page, order);
__free_pages(page, order);
}
-void free_memcg_kmem_pages(unsigned long addr, unsigned int order)
+void free_kmem_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
- __free_memcg_kmem_pages(virt_to_page((void *)addr), order);
+ __free_kmem_pages(virt_to_page((void *)addr), order);
}
}
@@ -3010,9 +3098,9 @@ bool skip_free_areas_node(unsigned int flags, int nid)
goto out;
do {
- cpuset_mems_cookie = get_mems_allowed();
+ cpuset_mems_cookie = read_mems_allowed_begin();
ret = !node_isset(nid, cpuset_current_mems_allowed);
- } while (!put_mems_allowed(cpuset_mems_cookie));
+ } while (read_mems_allowed_retry(cpuset_mems_cookie));
out:
return ret;
}
@@ -3314,7 +3402,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order);
/*
* sysctl handler for numa_zonelist_order
*/
-int numa_zonelist_order_handler(ctl_table *table, int write,
+int numa_zonelist_order_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos)
{
@@ -3881,8 +3969,6 @@ static inline unsigned long wait_table_bits(unsigned long size)
return ffz(~size);
}
-#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
-
/*
* Check if a pageblock contains reserved pages
*/
@@ -3910,6 +3996,7 @@ static void setup_zone_migrate_reserve(struct zone *zone)
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
@@ -3931,6 +4018,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
* 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 (!pfn_valid(pfn))
@@ -3968,6 +4061,12 @@ static void setup_zone_migrate_reserve(struct zone *zone)
reserve--;
continue;
}
+ } else if (!old_reserve) {
+ /*
+ * At boot time we don't need to scan the whole zone
+ * for turning off MIGRATE_RESERVE.
+ */
+ break;
}
/*
@@ -4015,7 +4114,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
mminit_verify_page_links(page, zone, nid, pfn);
init_page_count(page);
page_mapcount_reset(page);
- page_nid_reset_last(page);
+ page_cpupid_reset_last(page);
SetPageReserved(page);
/*
* Mark the block movable so that blocks are reserved for
@@ -4047,7 +4146,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
static void __meminit zone_init_free_lists(struct zone *zone)
{
- int order, t;
+ unsigned int order, t;
for_each_migratetype_order(order, t) {
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
zone->free_area[order].nr_free = 0;
@@ -4059,7 +4158,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif
-static int __meminit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
int batch;
@@ -4175,8 +4274,8 @@ static void pageset_set_high(struct per_cpu_pageset *p,
pageset_update(&p->pcp, high, batch);
}
-static void __meminit pageset_set_high_and_batch(struct zone *zone,
- struct per_cpu_pageset *pcp)
+static void pageset_set_high_and_batch(struct zone *zone,
+ struct per_cpu_pageset *pcp)
{
if (percpu_pagelist_fraction)
pageset_set_high(pcp,
@@ -4218,7 +4317,6 @@ static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
int i;
- struct pglist_data *pgdat = zone->zone_pgdat;
size_t alloc_size;
/*
@@ -4234,7 +4332,8 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
- alloc_bootmem_node_nopanic(pgdat, alloc_size);
+ memblock_virt_alloc_node_nopanic(
+ alloc_size, zone->zone_pgdat->node_id);
} else {
/*
* This case means that a zone whose size was 0 gets new memory
@@ -4266,7 +4365,7 @@ static __meminit void zone_pcp_init(struct zone *zone)
*/
zone->pageset = &boot_pageset;
- if (zone->present_pages)
+ if (populated_zone(zone))
printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n",
zone->name, zone->present_pages,
zone_batchsize(zone));
@@ -4301,9 +4400,6 @@ int __meminit init_currently_empty_zone(struct zone *zone,
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
/*
* Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
- * Architectures may implement their own version but if add_active_range()
- * was used and there are no special requirements, this is a convenient
- * alternative
*/
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
@@ -4354,13 +4450,13 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
#endif
/**
- * free_bootmem_with_active_regions - Call free_bootmem_node for each active range
+ * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range
* @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
- * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node
+ * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid
*
- * If an architecture guarantees that all ranges registered with
- * add_active_ranges() contain no holes and may be freed, this
- * this function may be used instead of calling free_bootmem() manually.
+ * If an architecture guarantees that all ranges registered contain no holes
+ * and may be freed, this this function may be used instead of calling
+ * memblock_free_early_nid() manually.
*/
void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
{
@@ -4372,9 +4468,9 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
end_pfn = min(end_pfn, max_low_pfn);
if (start_pfn < end_pfn)
- free_bootmem_node(NODE_DATA(this_nid),
- PFN_PHYS(start_pfn),
- (end_pfn - start_pfn) << PAGE_SHIFT);
+ memblock_free_early_nid(PFN_PHYS(start_pfn),
+ (end_pfn - start_pfn) << PAGE_SHIFT,
+ this_nid);
}
}
@@ -4382,9 +4478,8 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
* sparse_memory_present_with_active_regions - Call memory_present for each active range
* @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
*
- * If an architecture guarantees that all ranges registered with
- * add_active_ranges() contain no holes and may be freed, this
- * function may be used instead of calling memory_present() manually.
+ * If an architecture guarantees that all ranges registered contain no holes and may
+ * be freed, this function may be used instead of calling memory_present() manually.
*/
void __init sparse_memory_present_with_active_regions(int nid)
{
@@ -4402,7 +4497,7 @@ void __init sparse_memory_present_with_active_regions(int nid)
* @end_pfn: Passed by reference. On return, it will have the node end_pfn.
*
* It returns the start and end page frame of a node based on information
- * provided by an arch calling add_active_range(). If called for a node
+ * provided by memblock_set_node(). If called for a node
* with no available memory, a warning is printed and the start and end
* PFNs will be 0.
*/
@@ -4645,8 +4740,9 @@ static void __init setup_usemap(struct pglist_data *pgdat,
unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
zone->pageblock_flags = NULL;
if (usemapsize)
- zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
- usemapsize);
+ zone->pageblock_flags =
+ memblock_virt_alloc_node_nopanic(usemapsize,
+ pgdat->node_id);
}
#else
static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
@@ -4840,7 +4936,8 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
size = (end - start) * sizeof(struct page);
map = alloc_remap(pgdat->node_id, size);
if (!map)
- map = alloc_bootmem_node_nopanic(pgdat, size);
+ map = memblock_virt_alloc_node_nopanic(size,
+ pgdat->node_id);
pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -4870,7 +4967,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
- init_zone_allows_reclaim(nid);
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
#endif
@@ -4978,7 +5074,7 @@ static unsigned long __init find_min_pfn_for_node(int nid)
* find_min_pfn_with_active_regions - Find the minimum PFN registered
*
* It returns the minimum PFN based on information provided via
- * add_active_range().
+ * memblock_set_node().
*/
unsigned long __init find_min_pfn_with_active_regions(void)
{
@@ -5021,9 +5117,33 @@ static void __init find_zone_movable_pfns_for_nodes(void)
nodemask_t saved_node_state = node_states[N_MEMORY];
unsigned long totalpages = early_calculate_totalpages();
int usable_nodes = nodes_weight(node_states[N_MEMORY]);
+ struct memblock_region *r;
+
+ /* Need to find movable_zone earlier when movable_node is specified. */
+ find_usable_zone_for_movable();
/*
- * If movablecore was specified, calculate what size of
+ * If movable_node is specified, ignore kernelcore and movablecore
+ * options.
+ */
+ if (movable_node_is_enabled()) {
+ for_each_memblock(memory, r) {
+ if (!memblock_is_hotpluggable(r))
+ continue;
+
+ nid = r->nid;
+
+ usable_startpfn = PFN_DOWN(r->base);
+ zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
+ min(usable_startpfn, zone_movable_pfn[nid]) :
+ usable_startpfn;
+ }
+
+ goto out2;
+ }
+
+ /*
+ * If movablecore=nn[KMG] was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
* any allocation type is evenly spread. If both kernelcore
* and movablecore are specified, then the value of kernelcore
@@ -5049,7 +5169,6 @@ static void __init find_zone_movable_pfns_for_nodes(void)
goto out;
/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
- find_usable_zone_for_movable();
usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];
restart:
@@ -5140,6 +5259,7 @@ restart:
if (usable_nodes && required_kernelcore > usable_nodes)
goto restart;
+out2:
/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
for (nid = 0; nid < MAX_NUMNODES; nid++)
zone_movable_pfn[nid] =
@@ -5160,7 +5280,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
- if (zone->present_pages) {
+ if (populated_zone(zone)) {
node_set_state(nid, N_HIGH_MEMORY);
if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
zone_type <= ZONE_NORMAL)
@@ -5175,7 +5295,7 @@ static void check_for_memory(pg_data_t *pgdat, int nid)
* @max_zone_pfn: an array of max PFNs for each zone
*
* This will call free_area_init_node() for each active node in the system.
- * Using the page ranges provided by add_active_range(), the size of each
+ * Using the page ranges provided by memblock_set_node(), the size of each
* zone in each node and their holes is calculated. If the maximum PFN
* between two adjacent zones match, it is assumed that the zone is empty.
* For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
@@ -5698,10 +5818,15 @@ module_init(init_per_zone_wmark_min)
* that we can call two helper functions whenever min_free_kbytes
* changes.
*/
-int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
+int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, buffer, length, ppos);
+ int rc;
+
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
+ if (rc)
+ return rc;
+
if (write) {
user_min_free_kbytes = min_free_kbytes;
setup_per_zone_wmarks();
@@ -5710,7 +5835,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
}
#ifdef CONFIG_NUMA
-int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
+int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
@@ -5726,7 +5851,7 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
return 0;
}
-int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
+int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
@@ -5752,7 +5877,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
* minimum watermarks. The lowmem reserve ratio can only make sense
* if in function of the boot time zone sizes.
*/
-int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
+int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec_minmax(table, write, buffer, length, ppos);
@@ -5765,27 +5890,42 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
* cpu. It is the fraction of total pages in each zone that a hot per cpu
* pagelist can have before it gets flushed back to buddy allocator.
*/
-int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
+int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
- unsigned int cpu;
+ int old_percpu_pagelist_fraction;
int ret;
+ mutex_lock(&pcp_batch_high_lock);
+ old_percpu_pagelist_fraction = percpu_pagelist_fraction;
+
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
- if (!write || (ret < 0))
- return ret;
+ if (!write || ret < 0)
+ goto out;
+
+ /* Sanity checking to avoid pcp imbalance */
+ if (percpu_pagelist_fraction &&
+ percpu_pagelist_fraction < MIN_PERCPU_PAGELIST_FRACTION) {
+ percpu_pagelist_fraction = old_percpu_pagelist_fraction;
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* No change? */
+ if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
+ goto out;
- mutex_lock(&pcp_batch_high_lock);
for_each_populated_zone(zone) {
- unsigned long high;
- high = zone->managed_pages / percpu_pagelist_fraction;
+ unsigned int cpu;
+
for_each_possible_cpu(cpu)
- pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
- high);
+ pageset_set_high_and_batch(zone,
+ per_cpu_ptr(zone->pageset, cpu));
}
+out:
mutex_unlock(&pcp_batch_high_lock);
- return 0;
+ return ret;
}
int hashdist = HASHDIST_DEFAULT;
@@ -5866,7 +6006,7 @@ void *__init alloc_large_system_hash(const char *tablename,
do {
size = bucketsize << log2qty;
if (flags & HASH_EARLY)
- table = alloc_bootmem_nopanic(size);
+ table = memblock_virt_alloc_nopanic(size, 0);
else if (hashdist)
table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
else {
@@ -5922,59 +6062,73 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
}
/**
- * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
+ * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
* @page: The page within the block of interest
- * @start_bitidx: The first bit of interest to retrieve
- * @end_bitidx: The last bit of interest
- * returns pageblock_bits flags
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest to retrieve
+ * @mask: mask of bits that the caller is interested in
+ *
+ * Return: pageblock_bits flags
*/
-unsigned long get_pageblock_flags_group(struct page *page,
- int start_bitidx, int end_bitidx)
+unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
+ unsigned long end_bitidx,
+ unsigned long mask)
{
struct zone *zone;
unsigned long *bitmap;
- unsigned long pfn, bitidx;
- unsigned long flags = 0;
- unsigned long value = 1;
+ unsigned long bitidx, word_bitidx;
+ unsigned long word;
zone = page_zone(page);
- pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
+ word_bitidx = bitidx / BITS_PER_LONG;
+ bitidx &= (BITS_PER_LONG-1);
- for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
- if (test_bit(bitidx + start_bitidx, bitmap))
- flags |= value;
-
- return flags;
+ word = bitmap[word_bitidx];
+ bitidx += end_bitidx;
+ return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
}
/**
- * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
* @page: The page within the block of interest
- * @start_bitidx: The first bit of interest
- * @end_bitidx: The last bit of interest
* @flags: The flags to set
+ * @pfn: The target page frame number
+ * @end_bitidx: The last bit of interest
+ * @mask: mask of bits that the caller is interested in
*/
-void set_pageblock_flags_group(struct page *page, unsigned long flags,
- int start_bitidx, int end_bitidx)
+void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
+ unsigned long pfn,
+ unsigned long end_bitidx,
+ unsigned long mask)
{
struct zone *zone;
unsigned long *bitmap;
- unsigned long pfn, bitidx;
- unsigned long value = 1;
+ unsigned long bitidx, word_bitidx;
+ unsigned long old_word, word;
+
+ BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
zone = page_zone(page);
- pfn = page_to_pfn(page);
bitmap = get_pageblock_bitmap(zone, pfn);
bitidx = pfn_to_bitidx(zone, pfn);
- VM_BUG_ON(!zone_spans_pfn(zone, pfn));
+ word_bitidx = bitidx / BITS_PER_LONG;
+ bitidx &= (BITS_PER_LONG-1);
- for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
- if (flags & value)
- __set_bit(bitidx + start_bitidx, bitmap);
- else
- __clear_bit(bitidx + start_bitidx, bitmap);
+ VM_BUG_ON_PAGE(!zone_spans_pfn(zone, pfn), page);
+
+ bitidx += end_bitidx;
+ mask <<= (BITS_PER_LONG - bitidx - 1);
+ flags <<= (BITS_PER_LONG - bitidx - 1);
+
+ word = ACCESS_ONCE(bitmap[word_bitidx]);
+ for (;;) {
+ old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
+ if (word == old_word)
+ break;
+ word = old_word;
+ }
}
/*
@@ -6134,7 +6288,7 @@ 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);
@@ -6173,7 +6327,7 @@ 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);
@@ -6328,7 +6482,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
struct page *page;
struct zone *zone;
- int order, i;
+ unsigned int order, i;
unsigned long pfn;
unsigned long flags;
/* find the first valid pfn */
@@ -6366,10 +6520,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
list_del(&page->lru);
rmv_page_order(page);
zone->free_area[order].nr_free--;
-#ifdef CONFIG_HIGHMEM
- if (PageHighMem(page))
- totalhigh_pages -= 1 << order;
-#endif
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);
@@ -6384,7 +6534,7 @@ bool is_free_buddy_page(struct page *page)
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
- int order;
+ unsigned int order;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
@@ -6470,12 +6620,25 @@ static void dump_page_flags(unsigned long flags)
printk(")\n");
}
-void dump_page(struct page *page)
+void dump_page_badflags(struct page *page, const char *reason,
+ unsigned long badflags)
{
printk(KERN_ALERT
"page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
page, atomic_read(&page->_count), page_mapcount(page),
page->mapping, page->index);
dump_page_flags(page->flags);
+ if (reason)
+ pr_alert("page dumped because: %s\n", reason);
+ if (page->flags & badflags) {
+ pr_alert("bad because of flags:\n");
+ dump_page_flags(page->flags & badflags);
+ }
mem_cgroup_print_bad_page(page);
}
+
+void dump_page(struct page *page, const char *reason)
+{
+ dump_page_badflags(page, reason, 0);
+}
+EXPORT_SYMBOL(dump_page);
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 11:13:10 +0000