summaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c738
1 files changed, 514 insertions, 224 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8fcced7823fa..dd886fac451a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -56,14 +56,20 @@
#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
+#include <linux/mm_inline.h>
#include <linux/migrate.h>
#include <linux/page-debug-flags.h>
+#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
+#include <asm/sections.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
+/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
+static DEFINE_MUTEX(pcp_batch_high_lock);
+
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -99,6 +105,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
};
EXPORT_SYMBOL(node_states);
+/* Protect totalram_pages and zone->managed_pages */
+static DEFINE_SPINLOCK(managed_page_count_lock);
+
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
/*
@@ -196,6 +205,7 @@ static char * const zone_names[MAX_NR_ZONES] = {
};
int min_free_kbytes = 1024;
+int user_min_free_kbytes;
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
@@ -479,8 +489,10 @@ __find_buddy_index(unsigned long page_idx, unsigned int order)
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
- * For recording whether a page is in the buddy system, we set ->_mapcount -2.
- * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set ->_mapcount
+ * PAGE_BUDDY_MAPCOUNT_VALUE.
+ * Setting, clearing, and testing _mapcount PAGE_BUDDY_MAPCOUNT_VALUE is
+ * serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
@@ -518,8 +530,9 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with _mapcount -2. Page's
- * order is recorded in page_private(page) field.
+ * free pages of length of (1 << order) and marked with _mapcount
+ * PAGE_BUDDY_MAPCOUNT_VALUE. Page's order is recorded in page_private(page)
+ * field.
* So when we are allocating or freeing one, we can derive the state of the
* other. That is, if we allocate a small block, and both were
* free, the remainder of the region must be split into blocks.
@@ -638,7 +651,6 @@ static void free_pcppages_bulk(struct zone *zone, int count,
int to_free = count;
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
while (to_free) {
@@ -687,7 +699,6 @@ static void free_one_page(struct zone *zone, struct page *page, int order,
int migratetype)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
__free_one_page(page, zone, order, migratetype);
@@ -712,7 +723,8 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
return false;
if (!PageHighMem(page)) {
- debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
+ debug_check_no_locks_freed(page_address(page),
+ PAGE_SIZE << order);
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
@@ -738,35 +750,28 @@ static void __free_pages_ok(struct page *page, unsigned int order)
local_irq_restore(flags);
}
-/*
- * Read access to zone->managed_pages is safe because it's unsigned long,
- * but we still need to serialize writers. Currently all callers of
- * __free_pages_bootmem() except put_page_bootmem() should only be used
- * at boot time. So for shorter boot time, we shift the burden to
- * put_page_bootmem() to serialize writers.
- */
-void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
+ struct page *p = page;
unsigned int loop;
- prefetchw(page);
- for (loop = 0; loop < nr_pages; loop++) {
- struct page *p = &page[loop];
-
- if (loop + 1 < nr_pages)
- prefetchw(p + 1);
+ prefetchw(p);
+ for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
+ prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
- page_zone(page)->managed_pages += 1 << order;
+ page_zone(page)->managed_pages += nr_pages;
set_page_refcounted(page);
__free_pages(page, order);
}
#ifdef CONFIG_CMA
-/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */
+/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
@@ -780,11 +785,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
set_page_refcounted(page);
set_pageblock_migratetype(page, MIGRATE_CMA);
__free_pages(page, pageblock_order);
- totalram_pages += pageblock_nr_pages;
-#ifdef CONFIG_HIGHMEM
- if (PageHighMem(page))
- totalhigh_pages += pageblock_nr_pages;
-#endif
+ adjust_managed_page_count(page, pageblock_nr_pages);
}
#endif
@@ -887,7 +888,7 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
- struct free_area * area;
+ struct free_area *area;
struct page *page;
/* Find a page of the appropriate size in the preferred list */
@@ -1009,14 +1010,60 @@ static void change_pageblock_range(struct page *pageblock_page,
}
}
+/*
+ * If breaking a large block of pages, move all free pages to the preferred
+ * allocation list. If falling back for a reclaimable kernel allocation, be
+ * more aggressive about taking ownership of free pages.
+ *
+ * On the other hand, never change migration type of MIGRATE_CMA pageblocks
+ * nor move CMA pages to different free lists. We don't want unmovable pages
+ * to be allocated from MIGRATE_CMA areas.
+ *
+ * Returns the new migratetype of the pageblock (or the same old migratetype
+ * if it was unchanged).
+ */
+static int try_to_steal_freepages(struct zone *zone, struct page *page,
+ int start_type, int fallback_type)
+{
+ int current_order = page_order(page);
+
+ if (is_migrate_cma(fallback_type))
+ return fallback_type;
+
+ /* Take ownership for orders >= pageblock_order */
+ if (current_order >= pageblock_order) {
+ change_pageblock_range(page, current_order, start_type);
+ return start_type;
+ }
+
+ if (current_order >= pageblock_order / 2 ||
+ start_type == MIGRATE_RECLAIMABLE ||
+ page_group_by_mobility_disabled) {
+ int pages;
+
+ pages = move_freepages_block(zone, page, start_type);
+
+ /* Claim the whole block if over half of it is free */
+ if (pages >= (1 << (pageblock_order-1)) ||
+ page_group_by_mobility_disabled) {
+
+ set_pageblock_migratetype(page, start_type);
+ return start_type;
+ }
+
+ }
+
+ return fallback_type;
+}
+
/* 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)
{
- struct free_area * area;
+ struct free_area *area;
int current_order;
struct page *page;
- int migratetype, i;
+ 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;
@@ -1036,51 +1083,29 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
struct page, lru);
area->nr_free--;
- /*
- * If breaking a large block of pages, move all free
- * pages to the preferred allocation list. If falling
- * back for a reclaimable kernel allocation, be more
- * aggressive about taking ownership of free pages
- *
- * On the other hand, never change migration
- * type of MIGRATE_CMA pageblocks nor move CMA
- * pages on different free lists. We don't
- * want unmovable pages to be allocated from
- * MIGRATE_CMA areas.
- */
- if (!is_migrate_cma(migratetype) &&
- (unlikely(current_order >= pageblock_order / 2) ||
- start_migratetype == MIGRATE_RECLAIMABLE ||
- page_group_by_mobility_disabled)) {
- int pages;
- pages = move_freepages_block(zone, page,
- start_migratetype);
-
- /* Claim the whole block if over half of it is free */
- if (pages >= (1 << (pageblock_order-1)) ||
- page_group_by_mobility_disabled)
- set_pageblock_migratetype(page,
- start_migratetype);
-
- migratetype = start_migratetype;
- }
+ new_type = try_to_steal_freepages(zone, page,
+ start_migratetype,
+ migratetype);
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
- /* Take ownership for orders >= pageblock_order */
- if (current_order >= pageblock_order &&
- !is_migrate_cma(migratetype))
- change_pageblock_range(page, current_order,
- start_migratetype);
-
+ /*
+ * 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);
- trace_mm_page_alloc_extfrag(page, order, current_order,
- start_migratetype, migratetype);
+ trace_mm_page_alloc_extfrag(page, order,
+ current_order, start_migratetype, migratetype,
+ new_type == start_migratetype);
return page;
}
@@ -1178,10 +1203,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
unsigned long flags;
int to_drain;
+ unsigned long batch;
local_irq_save(flags);
- if (pcp->count >= pcp->batch)
- to_drain = pcp->batch;
+ batch = ACCESS_ONCE(pcp->batch);
+ if (pcp->count >= batch)
+ to_drain = batch;
else
to_drain = pcp->count;
if (to_drain > 0) {
@@ -1281,7 +1308,7 @@ void mark_free_pages(struct zone *zone)
int order, t;
struct list_head *curr;
- if (!zone->spanned_pages)
+ if (zone_is_empty(zone))
return;
spin_lock_irqsave(&zone->lock, flags);
@@ -1349,8 +1376,9 @@ void free_hot_cold_page(struct page *page, int cold)
list_add(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
- free_pcppages_bulk(zone, pcp->batch, pcp);
- pcp->count -= pcp->batch;
+ unsigned long batch = ACCESS_ONCE(pcp->batch);
+ free_pcppages_bulk(zone, batch, pcp);
+ pcp->count -= batch;
}
out:
@@ -1397,6 +1425,7 @@ void split_page(struct page *page, unsigned int order)
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
}
+EXPORT_SYMBOL_GPL(split_page);
static int __isolate_free_page(struct page *page, unsigned int order)
{
@@ -1524,6 +1553,7 @@ again:
get_pageblock_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);
@@ -1626,6 +1656,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
long min = mark;
long lowmem_reserve = z->lowmem_reserve[classzone_idx];
int o;
+ long free_cma = 0;
free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH)
@@ -1635,9 +1666,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
#ifdef CONFIG_CMA
/* If allocation can't use CMA areas don't use free CMA pages */
if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+ free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
- if (free_pages <= min + lowmem_reserve)
+
+ if (free_pages - free_cma <= min + lowmem_reserve)
return false;
for (o = 0; o < order; o++) {
/* At the next order, this order's pages become unavailable */
@@ -1788,6 +1820,11 @@ static void zlc_clear_zones_full(struct zonelist *zonelist)
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
}
+static bool zone_local(struct zone *local_zone, struct zone *zone)
+{
+ return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+}
+
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_isset(local_zone->node, zone->zone_pgdat->reclaim_nodes);
@@ -1825,6 +1862,11 @@ static void zlc_clear_zones_full(struct zonelist *zonelist)
{
}
+static bool zone_local(struct zone *local_zone, struct zone *zone)
+{
+ return true;
+}
+
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return true;
@@ -1856,16 +1898,41 @@ get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
- * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ * See also __cpuset_node_allowed_softwall() comment in kernel/cpuset.c.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
high_zoneidx, nodemask) {
+ unsigned long mark;
+
if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if ((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)
+ continue;
+ if (zone_reclaim_mode &&
+ !zone_local(preferred_zone, zone))
+ continue;
+ }
/*
* When allocating a page cache page for writing, we
* want to get it from a zone that is within its dirty
@@ -1896,16 +1963,11 @@ zonelist_scan:
(gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
goto this_zone_full;
- BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
- if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
- unsigned long mark;
+ mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (!zone_watermark_ok(zone, order, mark,
+ classzone_idx, alloc_flags)) {
int ret;
- mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
- if (zone_watermark_ok(zone, order, mark,
- classzone_idx, alloc_flags))
- goto try_this_zone;
-
if (IS_ENABLED(CONFIG_NUMA) &&
!did_zlc_setup && nr_online_nodes > 1) {
/*
@@ -1940,9 +2002,24 @@ zonelist_scan:
continue;
default:
/* did we reclaim enough */
- if (!zone_watermark_ok(zone, order, mark,
+ if (zone_watermark_ok(zone, order, mark,
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;
}
}
@@ -2002,6 +2079,13 @@ 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.
@@ -2295,16 +2379,30 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
return page;
}
-static inline
-void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
- enum zone_type high_zoneidx,
- enum zone_type classzone_idx)
+static void prepare_slowpath(gfp_t gfp_mask, 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, classzone_idx);
+ 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
+ * actually part of this zonelist's round-robin cycle.
+ */
+ if (zone_reclaim_mode && !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));
+ }
}
static inline int
@@ -2400,9 +2498,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
goto nopage;
restart:
- if (!(gfp_mask & __GFP_NO_KSWAPD))
- wake_all_kswapd(order, zonelist, high_zoneidx,
- zone_idx(preferred_zone));
+ prepare_slowpath(gfp_mask, order, zonelist,
+ high_zoneidx, preferred_zone);
/*
* OK, we're below the kswapd watermark and have kicked background
@@ -2813,7 +2910,7 @@ EXPORT_SYMBOL(free_pages_exact);
* nr_free_zone_pages() counts the number of counts pages which are beyond the
* high watermark within all zones at or below a given zone index. For each
* zone, the number of pages is calculated as:
- * present_pages - high_pages
+ * managed_pages - high_pages
*/
static unsigned long nr_free_zone_pages(int offset)
{
@@ -2880,9 +2977,13 @@ EXPORT_SYMBOL(si_meminfo);
#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
+ int zone_type; /* needs to be signed */
+ unsigned long managed_pages = 0;
pg_data_t *pgdat = NODE_DATA(nid);
- val->totalram = pgdat->node_present_pages;
+ for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
+ managed_pages += pgdat->node_zones[zone_type].managed_pages;
+ val->totalram = managed_pages;
val->freeram = node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].managed_pages;
@@ -3065,7 +3166,7 @@ void show_free_areas(unsigned int filter)
K(zone_page_state(zone, NR_FREE_CMA_PAGES)),
K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
zone->pages_scanned,
- (zone->all_unreclaimable ? "yes" : "no")
+ (!zone_reclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
@@ -3074,7 +3175,7 @@ void show_free_areas(unsigned int filter)
}
for_each_populated_zone(zone) {
- unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ unsigned long nr[MAX_ORDER], flags, order, total = 0;
unsigned char types[MAX_ORDER];
if (skip_free_areas_node(filter, zone_to_nid(zone)))
@@ -3105,6 +3206,8 @@ void show_free_areas(unsigned int filter)
printk("= %lukB\n", K(total));
}
+ hugetlb_show_meminfo();
+
printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
show_swap_cache_info();
@@ -3122,12 +3225,10 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
* Add all populated zones of a node to the zonelist.
*/
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
- int nr_zones, enum zone_type zone_type)
+ int nr_zones)
{
struct zone *zone;
-
- BUG_ON(zone_type >= MAX_NR_ZONES);
- zone_type++;
+ enum zone_type zone_type = MAX_NR_ZONES;
do {
zone_type--;
@@ -3137,8 +3238,8 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
-
} while (zone_type);
+
return nr_zones;
}
@@ -3222,18 +3323,25 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
static DEFINE_MUTEX(zl_order_mutex);
mutex_lock(&zl_order_mutex);
- if (write)
- strcpy(saved_string, (char*)table->data);
+ if (write) {
+ if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) {
+ ret = -EINVAL;
+ goto out;
+ }
+ strcpy(saved_string, (char *)table->data);
+ }
ret = proc_dostring(table, write, buffer, length, ppos);
if (ret)
goto out;
if (write) {
int oldval = user_zonelist_order;
- if (__parse_numa_zonelist_order((char*)table->data)) {
+
+ ret = __parse_numa_zonelist_order((char *)table->data);
+ if (ret) {
/*
* bogus value. restore saved string
*/
- strncpy((char*)table->data, saved_string,
+ strncpy((char *)table->data, saved_string,
NUMA_ZONELIST_ORDER_LEN);
user_zonelist_order = oldval;
} else if (oldval != user_zonelist_order) {
@@ -3325,8 +3433,7 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
zonelist = &pgdat->node_zonelists[0];
for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
@@ -3340,7 +3447,7 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
struct zonelist *zonelist;
zonelist = &pgdat->node_zonelists[1];
- j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+ j = build_zonelists_node(pgdat, zonelist, 0);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
@@ -3380,11 +3487,11 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
static int default_zonelist_order(void)
{
int nid, zone_type;
- unsigned long low_kmem_size,total_size;
+ unsigned long low_kmem_size, total_size;
struct zone *z;
int average_size;
/*
- * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
+ * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
* If they are really small and used heavily, the system can fall
* into OOM very easily.
* This function detect ZONE_DMA/DMA32 size and configures zone order.
@@ -3397,8 +3504,8 @@ static int default_zonelist_order(void)
z = &NODE_DATA(nid)->node_zones[zone_type];
if (populated_zone(z)) {
if (zone_type < ZONE_NORMAL)
- low_kmem_size += z->present_pages;
- total_size += z->present_pages;
+ low_kmem_size += z->managed_pages;
+ total_size += z->managed_pages;
} else if (zone_type == ZONE_NORMAL) {
/*
* If any node has only lowmem, then node order
@@ -3416,9 +3523,9 @@ static int default_zonelist_order(void)
return ZONELIST_ORDER_NODE;
/*
* look into each node's config.
- * If there is a node whose DMA/DMA32 memory is very big area on
- * local memory, NODE_ORDER may be suitable.
- */
+ * If there is a node whose DMA/DMA32 memory is very big area on
+ * local memory, NODE_ORDER may be suitable.
+ */
average_size = total_size /
(nodes_weight(node_states[N_MEMORY]) + 1);
for_each_online_node(nid) {
@@ -3548,7 +3655,7 @@ static void build_zonelists(pg_data_t *pgdat)
local_node = pgdat->node_id;
zonelist = &pgdat->node_zonelists[0];
- j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
+ j = build_zonelists_node(pgdat, zonelist, 0);
/*
* Now we build the zonelist so that it contains the zones
@@ -3561,14 +3668,12 @@ static void build_zonelists(pg_data_t *pgdat)
for (node = local_node + 1; node < MAX_NUMNODES; node++) {
if (!node_online(node))
continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
}
for (node = 0; node < local_node; node++) {
if (!node_online(node))
continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j,
- MAX_NR_ZONES - 1);
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j);
}
zonelist->_zonerefs[j].zone = NULL;
@@ -3677,12 +3782,12 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
mminit_verify_zonelist();
cpuset_init_current_mems_allowed();
} else {
- /* we have to stop all cpus to guarantee there is no user
- of zonelist */
#ifdef CONFIG_MEMORY_HOTPLUG
if (zone)
setup_zone_pageset(zone);
#endif
+ /* we have to stop all cpus to guarantee there is no user
+ of zonelist */
stop_machine(__build_all_zonelists, pgdat, NULL);
/* cpuset refresh routine should be here */
}
@@ -4004,7 +4109,40 @@ static int __meminit zone_batchsize(struct zone *zone)
#endif
}
-static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+/*
+ * pcp->high and pcp->batch values are related and dependent on one another:
+ * ->batch must never be higher then ->high.
+ * The following function updates them in a safe manner without read side
+ * locking.
+ *
+ * Any new users of pcp->batch and pcp->high should ensure they can cope with
+ * those fields changing asynchronously (acording the the above rule).
+ *
+ * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
+ * outside of boot time (or some other assurance that no concurrent updaters
+ * exist).
+ */
+static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
+ unsigned long batch)
+{
+ /* start with a fail safe value for batch */
+ pcp->batch = 1;
+ smp_wmb();
+
+ /* Update high, then batch, in order */
+ pcp->high = high;
+ smp_wmb();
+
+ pcp->batch = batch;
+}
+
+/* a companion to pageset_set_high() */
+static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
+{
+ pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
+}
+
+static void pageset_init(struct per_cpu_pageset *p)
{
struct per_cpu_pages *pcp;
int migratetype;
@@ -4013,45 +4151,55 @@ static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
pcp = &p->pcp;
pcp->count = 0;
- pcp->high = 6 * batch;
- pcp->batch = max(1UL, 1 * batch);
for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
INIT_LIST_HEAD(&pcp->lists[migratetype]);
}
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+{
+ pageset_init(p);
+ pageset_set_batch(p, batch);
+}
+
/*
- * setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
+ * pageset_set_high() sets the high water mark for hot per_cpu_pagelist
* to the value high for the pageset p.
*/
-
-static void setup_pagelist_highmark(struct per_cpu_pageset *p,
+static void pageset_set_high(struct per_cpu_pageset *p,
unsigned long high)
{
- struct per_cpu_pages *pcp;
+ unsigned long batch = max(1UL, high / 4);
+ if ((high / 4) > (PAGE_SHIFT * 8))
+ batch = PAGE_SHIFT * 8;
- pcp = &p->pcp;
- pcp->high = high;
- pcp->batch = max(1UL, high/4);
- if ((high/4) > (PAGE_SHIFT * 8))
- pcp->batch = PAGE_SHIFT * 8;
+ pageset_update(&p->pcp, high, batch);
}
-static void __meminit setup_zone_pageset(struct zone *zone)
+static void __meminit pageset_set_high_and_batch(struct zone *zone,
+ struct per_cpu_pageset *pcp)
{
- int cpu;
-
- zone->pageset = alloc_percpu(struct per_cpu_pageset);
+ if (percpu_pagelist_fraction)
+ pageset_set_high(pcp,
+ (zone->managed_pages /
+ percpu_pagelist_fraction));
+ else
+ pageset_set_batch(pcp, zone_batchsize(zone));
+}
- for_each_possible_cpu(cpu) {
- struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
+static void __meminit zone_pageset_init(struct zone *zone, int cpu)
+{
+ struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
- setup_pageset(pcp, zone_batchsize(zone));
+ pageset_init(pcp);
+ pageset_set_high_and_batch(zone, pcp);
+}
- if (percpu_pagelist_fraction)
- setup_pagelist_highmark(pcp,
- (zone->managed_pages /
- percpu_pagelist_fraction));
- }
+static void __meminit setup_zone_pageset(struct zone *zone)
+{
+ int cpu;
+ zone->pageset = alloc_percpu(struct per_cpu_pageset);
+ for_each_possible_cpu(cpu)
+ zone_pageset_init(zone, cpu);
}
/*
@@ -4103,7 +4251,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
if (!zone->wait_table)
return -ENOMEM;
- for(i = 0; i < zone->wait_table_hash_nr_entries; ++i)
+ for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
init_waitqueue_head(zone->wait_table + i);
return 0;
@@ -4160,13 +4308,25 @@ int __meminit init_currently_empty_zone(struct zone *zone,
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
unsigned long start_pfn, end_pfn;
- int i, nid;
+ int nid;
+ /*
+ * NOTE: The following SMP-unsafe globals are only used early in boot
+ * when the kernel is running single-threaded.
+ */
+ static unsigned long __meminitdata last_start_pfn, last_end_pfn;
+ static int __meminitdata last_nid;
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
- if (start_pfn <= pfn && pfn < end_pfn)
- return nid;
- /* This is a memory hole */
- return -1;
+ if (last_start_pfn <= pfn && pfn < last_end_pfn)
+ return last_nid;
+
+ nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+ if (nid != -1) {
+ last_start_pfn = start_pfn;
+ last_end_pfn = end_pfn;
+ last_nid = nid;
+ }
+
+ return nid;
}
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
@@ -4327,13 +4487,13 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid,
*/
static unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *ignored)
{
- unsigned long node_start_pfn, node_end_pfn;
unsigned long zone_start_pfn, zone_end_pfn;
- /* Get the start and end of the node and zone */
- get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
+ /* Get the start and end of the zone */
zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
adjust_zone_range_for_zone_movable(nid, zone_type,
@@ -4388,14 +4548,14 @@ unsigned long __init absent_pages_in_range(unsigned long start_pfn,
/* Return the number of page frames in holes in a zone on a node */
static unsigned long __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *ignored)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
- unsigned long node_start_pfn, node_end_pfn;
unsigned long zone_start_pfn, zone_end_pfn;
- get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
@@ -4408,6 +4568,8 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *zones_size)
{
return zones_size[zone_type];
@@ -4415,6 +4577,8 @@ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_type,
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
unsigned long *zholes_size)
{
if (!zholes_size)
@@ -4426,21 +4590,27 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
- unsigned long *zones_size, unsigned long *zholes_size)
+ unsigned long node_start_pfn,
+ unsigned long node_end_pfn,
+ unsigned long *zones_size,
+ unsigned long *zholes_size)
{
unsigned long realtotalpages, totalpages = 0;
enum zone_type i;
for (i = 0; i < MAX_NR_ZONES; i++)
totalpages += zone_spanned_pages_in_node(pgdat->node_id, i,
- zones_size);
+ node_start_pfn,
+ node_end_pfn,
+ zones_size);
pgdat->node_spanned_pages = totalpages;
realtotalpages = totalpages;
for (i = 0; i < MAX_NR_ZONES; i++)
realtotalpages -=
zone_absent_pages_in_node(pgdat->node_id, i,
- zholes_size);
+ node_start_pfn, node_end_pfn,
+ zholes_size);
pgdat->node_present_pages = realtotalpages;
printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id,
realtotalpages);
@@ -4486,7 +4656,7 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-void __init set_pageblock_order(void)
+void __paginginit set_pageblock_order(void)
{
unsigned int order;
@@ -4514,7 +4684,7 @@ void __init set_pageblock_order(void)
* include/linux/pageblock-flags.h for the values of pageblock_order based on
* the kernel config
*/
-void __init set_pageblock_order(void)
+void __paginginit set_pageblock_order(void)
{
}
@@ -4549,6 +4719,7 @@ static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
* NOTE: pgdat should get zeroed by caller.
*/
static void __paginginit free_area_init_core(struct pglist_data *pgdat,
+ unsigned long node_start_pfn, unsigned long node_end_pfn,
unsigned long *zones_size, unsigned long *zholes_size)
{
enum zone_type j;
@@ -4570,8 +4741,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
- size = zone_spanned_pages_in_node(nid, j, zones_size);
+ size = zone_spanned_pages_in_node(nid, j, node_start_pfn,
+ node_end_pfn, zones_size);
realsize = freesize = size - zone_absent_pages_in_node(nid, j,
+ node_start_pfn,
+ node_end_pfn,
zholes_size);
/*
@@ -4624,8 +4798,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
spin_lock_init(&zone->lru_lock);
zone_seqlock_init(zone);
zone->zone_pgdat = pgdat;
-
zone_pcp_init(zone);
+
+ /* For bootup, initialized properly in watermark setup */
+ mod_zone_page_state(zone, NR_ALLOC_BATCH, zone->managed_pages);
+
lruvec_init(&zone->lruvec);
if (!size)
continue;
@@ -4685,6 +4862,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
unsigned long node_start_pfn, unsigned long *zholes_size)
{
pg_data_t *pgdat = NODE_DATA(nid);
+ unsigned long start_pfn = 0;
+ unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
@@ -4692,7 +4871,11 @@ 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);
- calculate_node_totalpages(pgdat, zones_size, zholes_size);
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+#endif
+ calculate_node_totalpages(pgdat, start_pfn, end_pfn,
+ zones_size, zholes_size);
alloc_node_mem_map(pgdat);
#ifdef CONFIG_FLAT_NODE_MEM_MAP
@@ -4701,7 +4884,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
(unsigned long)pgdat->node_mem_map);
#endif
- free_area_init_core(pgdat, zones_size, zholes_size);
+ free_area_init_core(pgdat, start_pfn, end_pfn,
+ zones_size, zholes_size);
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -4710,7 +4894,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
/*
* Figure out the number of possible node ids.
*/
-static void __init setup_nr_node_ids(void)
+void __init setup_nr_node_ids(void)
{
unsigned int node;
unsigned int highest = 0;
@@ -4719,10 +4903,6 @@ static void __init setup_nr_node_ids(void)
highest = node;
nr_node_ids = highest + 1;
}
-#else
-static inline void setup_nr_node_ids(void)
-{
-}
#endif
/**
@@ -4823,7 +5003,7 @@ static unsigned long __init early_calculate_totalpages(void)
if (pages)
node_set_state(nid, N_MEMORY);
}
- return totalpages;
+ return totalpages;
}
/*
@@ -4940,7 +5120,7 @@ restart:
/*
* Some kernelcore has been met, update counts and
* break if the kernelcore for this node has been
- * satisified
+ * satisfied
*/
required_kernelcore -= min(required_kernelcore,
size_pages);
@@ -4954,7 +5134,7 @@ restart:
* If there is still required_kernelcore, we do another pass with one
* less node in the count. This will push zone_movable_pfn[nid] further
* along on the nodes that still have memory until kernelcore is
- * satisified
+ * satisfied
*/
usable_nodes--;
if (usable_nodes && required_kernelcore > usable_nodes)
@@ -5113,6 +5293,103 @@ early_param("movablecore", cmdline_parse_movablecore);
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+void adjust_managed_page_count(struct page *page, long count)
+{
+ spin_lock(&managed_page_count_lock);
+ page_zone(page)->managed_pages += count;
+ totalram_pages += count;
+#ifdef CONFIG_HIGHMEM
+ if (PageHighMem(page))
+ totalhigh_pages += count;
+#endif
+ spin_unlock(&managed_page_count_lock);
+}
+EXPORT_SYMBOL(adjust_managed_page_count);
+
+unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
+{
+ void *pos;
+ unsigned long pages = 0;
+
+ start = (void *)PAGE_ALIGN((unsigned long)start);
+ end = (void *)((unsigned long)end & PAGE_MASK);
+ for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+ if ((unsigned int)poison <= 0xFF)
+ memset(pos, poison, PAGE_SIZE);
+ free_reserved_page(virt_to_page(pos));
+ }
+
+ if (pages && s)
+ pr_info("Freeing %s memory: %ldK (%p - %p)\n",
+ s, pages << (PAGE_SHIFT - 10), start, end);
+
+ return pages;
+}
+EXPORT_SYMBOL(free_reserved_area);
+
+#ifdef CONFIG_HIGHMEM
+void free_highmem_page(struct page *page)
+{
+ __free_reserved_page(page);
+ totalram_pages++;
+ page_zone(page)->managed_pages++;
+ totalhigh_pages++;
+}
+#endif
+
+
+void __init mem_init_print_info(const char *str)
+{
+ unsigned long physpages, codesize, datasize, rosize, bss_size;
+ unsigned long init_code_size, init_data_size;
+
+ physpages = get_num_physpages();
+ codesize = _etext - _stext;
+ datasize = _edata - _sdata;
+ rosize = __end_rodata - __start_rodata;
+ bss_size = __bss_stop - __bss_start;
+ init_data_size = __init_end - __init_begin;
+ init_code_size = _einittext - _sinittext;
+
+ /*
+ * Detect special cases and adjust section sizes accordingly:
+ * 1) .init.* may be embedded into .data sections
+ * 2) .init.text.* may be out of [__init_begin, __init_end],
+ * please refer to arch/tile/kernel/vmlinux.lds.S.
+ * 3) .rodata.* may be embedded into .text or .data sections.
+ */
+#define adj_init_size(start, end, size, pos, adj) \
+ do { \
+ if (start <= pos && pos < end && size > adj) \
+ size -= adj; \
+ } while (0)
+
+ adj_init_size(__init_begin, __init_end, init_data_size,
+ _sinittext, init_code_size);
+ adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size);
+ adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size);
+ adj_init_size(_stext, _etext, codesize, __start_rodata, rosize);
+ adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize);
+
+#undef adj_init_size
+
+ printk("Memory: %luK/%luK available "
+ "(%luK kernel code, %luK rwdata, %luK rodata, "
+ "%luK init, %luK bss, %luK reserved"
+#ifdef CONFIG_HIGHMEM
+ ", %luK highmem"
+#endif
+ "%s%s)\n",
+ nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
+ codesize >> 10, datasize >> 10, rosize >> 10,
+ (init_data_size + init_code_size) >> 10, bss_size >> 10,
+ (physpages - totalram_pages) << (PAGE_SHIFT-10),
+#ifdef CONFIG_HIGHMEM
+ totalhigh_pages << (PAGE_SHIFT-10),
+#endif
+ str ? ", " : "", str ? str : "");
+}
+
/**
* set_dma_reserve - set the specified number of pages reserved in the first zone
* @new_dma_reserve: The number of pages to mark reserved
@@ -5159,7 +5436,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
* This is only okay since the processor is dead and cannot
* race with what we are doing.
*/
- refresh_cpu_vm_stats(cpu);
+ cpu_vm_stats_fold(cpu);
}
return NOTIFY_OK;
}
@@ -5296,6 +5573,11 @@ static void __setup_per_zone_wmarks(void)
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ __mod_zone_page_state(zone, NR_ALLOC_BATCH,
+ high_wmark_pages(zone) -
+ low_wmark_pages(zone) -
+ zone_page_state(zone, NR_ALLOC_BATCH));
+
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -5368,7 +5650,7 @@ static void __meminit setup_per_zone_inactive_ratio(void)
* we want it large (64MB max). But it is not linear, because network
* bandwidth does not increase linearly with machine size. We use
*
- * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
* min_free_kbytes = sqrt(lowmem_kbytes * 16)
*
* which yields
@@ -5388,14 +5670,21 @@ static void __meminit setup_per_zone_inactive_ratio(void)
int __meminit init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
+ int new_min_free_kbytes;
lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
-
- min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
- if (min_free_kbytes < 128)
- min_free_kbytes = 128;
- if (min_free_kbytes > 65536)
- min_free_kbytes = 65536;
+ new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
+
+ if (new_min_free_kbytes > user_min_free_kbytes) {
+ min_free_kbytes = new_min_free_kbytes;
+ if (min_free_kbytes < 128)
+ min_free_kbytes = 128;
+ if (min_free_kbytes > 65536)
+ min_free_kbytes = 65536;
+ } else {
+ pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
+ new_min_free_kbytes, user_min_free_kbytes);
+ }
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
@@ -5405,16 +5694,18 @@ int __meminit init_per_zone_wmark_min(void)
module_init(init_per_zone_wmark_min)
/*
- * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
+ * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* 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(ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, buffer, length, ppos);
- if (write)
+ if (write) {
+ user_min_free_kbytes = min_free_kbytes;
setup_per_zone_wmarks();
+ }
return 0;
}
@@ -5471,10 +5762,9 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
/*
* percpu_pagelist_fraction - changes the pcp->high for each zone on each
- * 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.
+ * 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,
void __user *buffer, size_t *length, loff_t *ppos)
{
@@ -5485,14 +5775,16 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (!write || (ret < 0))
return ret;
+
+ mutex_lock(&pcp_batch_high_lock);
for_each_populated_zone(zone) {
- for_each_possible_cpu(cpu) {
- unsigned long high;
- high = zone->managed_pages / percpu_pagelist_fraction;
- setup_pagelist_highmark(
- per_cpu_ptr(zone->pageset, cpu), high);
- }
+ unsigned long high;
+ high = zone->managed_pages / percpu_pagelist_fraction;
+ for_each_possible_cpu(cpu)
+ pageset_set_high(per_cpu_ptr(zone->pageset, cpu),
+ high);
}
+ mutex_unlock(&pcp_batch_high_lock);
return 0;
}
@@ -5533,9 +5825,10 @@ void *__init alloc_large_system_hash(const char *tablename,
if (!numentries) {
/* round applicable memory size up to nearest megabyte */
numentries = nr_kernel_pages;
- numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
- numentries >>= 20 - PAGE_SHIFT;
- numentries <<= 20 - PAGE_SHIFT;
+
+ /* It isn't necessary when PAGE_SIZE >= 1MB */
+ if (PAGE_SHIFT < 20)
+ numentries = round_up(numentries, (1<<20)/PAGE_SIZE);
/* limit to 1 bucket per 2^scale bytes of low memory */
if (scale > PAGE_SHIFT)
@@ -5688,7 +5981,7 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
* This function checks whether pageblock includes unmovable pages or not.
* If @count is not zero, it is okay to include less @count unmovable pages
*
- * PageLRU check wihtout isolation or lru_lock could race so that
+ * PageLRU check without isolation or lru_lock could race so that
* MIGRATE_MOVABLE block might include unmovable pages. It means you can't
* expect this function should be exact.
*/
@@ -5716,6 +6009,17 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
continue;
page = pfn_to_page(check);
+
+ /*
+ * Hugepages are not in LRU lists, but they're movable.
+ * We need not scan over tail pages bacause we don't
+ * handle each tail page individually in migration.
+ */
+ if (PageHuge(page)) {
+ iter = round_up(iter + 1, 1<<compound_order(page)) - 1;
+ continue;
+ }
+
/*
* We can't use page_count without pin a page
* because another CPU can free compound page.
@@ -5981,32 +6285,18 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit __zone_pcp_update(void *data)
-{
- struct zone *zone = data;
- int cpu;
- unsigned long batch = zone_batchsize(zone), flags;
-
- for_each_possible_cpu(cpu) {
- struct per_cpu_pageset *pset;
- struct per_cpu_pages *pcp;
-
- pset = per_cpu_ptr(zone->pageset, cpu);
- pcp = &pset->pcp;
-
- local_irq_save(flags);
- if (pcp->count > 0)
- free_pcppages_bulk(zone, pcp->count, pcp);
- drain_zonestat(zone, pset);
- setup_pageset(pset, batch);
- local_irq_restore(flags);
- }
- return 0;
-}
-
+/*
+ * The zone indicated has a new number of managed_pages; batch sizes and percpu
+ * page high values need to be recalulated.
+ */
void __meminit zone_pcp_update(struct zone *zone)
{
- stop_machine(__zone_pcp_update, zone, NULL);
+ unsigned cpu;
+ mutex_lock(&pcp_batch_high_lock);
+ for_each_possible_cpu(cpu)
+ pageset_set_high_and_batch(zone,
+ per_cpu_ptr(zone->pageset, cpu));
+ mutex_unlock(&pcp_batch_high_lock);
}
#endif
generated by cgit (git 2.34.1) at 2025-08-14 10:26:23 +0000