#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
+#include <linux/migrate.h>
+#include <linux/page-debug-flags.h>
+#include <linux/nmi.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
+/*
+ * When calculating the number of globally allowed dirty pages, there
+ * is a certain number of per-zone reserves that should not be
+ * considered dirtyable memory. This is the sum of those reserves
+ * over all existing zones that contribute dirtyable memory.
+ */
+unsigned long dirty_balance_reserve __read_mostly;
+
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~GFP_IOFS;
}
+
+bool pm_suspended_storage(void)
+{
+ if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ return false;
+ return true;
+}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
clear_highpage(page + i);
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
+unsigned int _debug_guardpage_minorder;
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+ unsigned long res;
+
+ if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
+ printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+ return 0;
+ }
+ _debug_guardpage_minorder = res;
+ printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+ return 0;
+}
+__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
+
+static inline void set_page_guard_flag(struct page *page)
+{
+ __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+
+static inline void clear_page_guard_flag(struct page *page)
+{
+ __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+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)
{
set_page_private(page, order);
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);
+ return 1;
+ }
+
if (PageBuddy(buddy) && page_order(buddy) == order) {
VM_BUG_ON(page_count(buddy) != 0);
return 1;
* free pages of length of (1 << order) and marked with _mapcount -2. 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.
+ * other. That is, if we allocate a small block, and both were
+ * free, the remainder of the region must be split into blocks.
* If a block is freed, and its buddy is also free, then this
- * triggers coalescing into a block of larger size.
+ * triggers coalescing into a block of larger size.
*
* -- wli
*/
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
break;
-
- /* Our buddy is free, merge with it and move up one order. */
- list_del(&buddy->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(buddy);
+ /*
+ * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
+ * merge with it and move up one order.
+ */
+ if (page_is_guard(buddy)) {
+ clear_page_guard_flag(buddy);
+ set_page_private(page, 0);
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+ } else {
+ list_del(&buddy->lru);
+ zone->free_area[order].nr_free--;
+ rmv_page_order(buddy);
+ }
combined_idx = buddy_idx & page_idx;
page = page + (combined_idx - page_idx);
page_idx = combined_idx;
combined_idx = buddy_idx & page_idx;
higher_page = page + (combined_idx - page_idx);
buddy_idx = __find_buddy_index(combined_idx, order + 1);
- higher_buddy = page + (buddy_idx - combined_idx);
+ higher_buddy = higher_page + (buddy_idx - combined_idx);
if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
int i;
int bad = 0;
- trace_mm_page_free_direct(page, order);
+ trace_mm_page_free(page, order);
kmemcheck_free_shadow(page, order);
if (PageAnon(page))
}
}
+#ifdef CONFIG_CMA
+/* Free whole pageblock and set it's migration type to MIGRATE_CMA. */
+void __init init_cma_reserved_pageblock(struct page *page)
+{
+ unsigned i = pageblock_nr_pages;
+ struct page *p = page;
+
+ do {
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
+ } while (++p, --i);
+
+ set_page_refcounted(page);
+ set_pageblock_migratetype(page, MIGRATE_CMA);
+ __free_pages(page, pageblock_order);
+ totalram_pages += pageblock_nr_pages;
+}
+#endif
/*
* The order of subdivision here is critical for the IO subsystem.
high--;
size >>= 1;
VM_BUG_ON(bad_range(zone, &page[size]));
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ if (high < debug_guardpage_minorder()) {
+ /*
+ * Mark as guard pages (or page), that will allow to
+ * merge back to allocator when buddy will be freed.
+ * Corresponding page table entries will not be touched,
+ * pages will stay not present in virtual address space
+ */
+ INIT_LIST_HEAD(&page[size].lru);
+ set_page_guard_flag(&page[size]);
+ set_page_private(&page[size], high);
+ /* Guard pages are not available for any usage */
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << high));
+ continue;
+ }
+#endif
list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
-static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = {
- [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
- [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
- [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
- [MIGRATE_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */
+static int fallbacks[MIGRATE_TYPES][4] = {
+ [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
+ [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
+#ifdef CONFIG_CMA
+ [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
+ [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */
+#else
+ [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
+#endif
+ [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */
+ [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */
};
/*
/* Find the largest possible block of pages in the other list */
for (current_order = MAX_ORDER-1; current_order >= order;
--current_order) {
- for (i = 0; i < MIGRATE_TYPES - 1; i++) {
+ for (i = 0;; i++) {
migratetype = fallbacks[start_migratetype][i];
/* MIGRATE_RESERVE handled later if necessary */
if (migratetype == MIGRATE_RESERVE)
- continue;
+ break;
area = &(zone->free_area[current_order]);
if (list_empty(&area->free_list[migratetype]))
* 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 (unlikely(current_order >= (pageblock_order >> 1)) ||
- start_migratetype == MIGRATE_RECLAIMABLE ||
- page_group_by_mobility_disabled) {
- unsigned long pages;
+ 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);
rmv_page_order(page);
/* Take ownership for orders >= pageblock_order */
- if (current_order >= pageblock_order)
+ if (current_order >= pageblock_order &&
+ !is_migrate_cma(migratetype))
change_pageblock_range(page, current_order,
start_migratetype);
- expand(zone, page, order, current_order, area, migratetype);
+ 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);
return page;
}
-/*
+/*
* Obtain a specified number of elements from the buddy allocator, all under
* a single hold of the lock, for efficiency. Add them to the supplied list.
* Returns the number of new pages which were placed at *list.
*/
-static int rmqueue_bulk(struct zone *zone, unsigned int order,
+static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
int migratetype, int cold)
{
- int i;
-
+ int mt = migratetype, i;
+
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype);
list_add(&page->lru, list);
else
list_add_tail(&page->lru, list);
- set_page_private(page, migratetype);
+ if (IS_ENABLED(CONFIG_CMA)) {
+ mt = get_pageblock_migratetype(page);
+ if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE)
+ mt = migratetype;
+ }
+ set_page_private(page, mt);
list = &page->lru;
}
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
#ifdef CONFIG_HIBERNATION
+/*
+ * Touch the watchdog for every WD_PAGE_COUNT pages.
+ */
+#define WD_PAGE_COUNT (128*1024)
+
void mark_free_pages(struct zone *zone)
{
- unsigned long pfn, max_zone_pfn;
+ unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
unsigned long flags;
int order, t;
struct list_head *curr;
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
+ if (!--page_count) {
+ touch_nmi_watchdog();
+ page_count = WD_PAGE_COUNT;
+ }
+
if (!swsusp_page_is_forbidden(page))
swsusp_unset_page_free(page);
}
unsigned long i;
pfn = page_to_pfn(list_entry(curr, struct page, lru));
- for (i = 0; i < (1UL << order); i++)
+ for (i = 0; i < (1UL << order); i++) {
+ if (!--page_count) {
+ touch_nmi_watchdog();
+ page_count = WD_PAGE_COUNT;
+ }
swsusp_set_page_free(pfn_to_page(pfn + i));
+ }
}
}
spin_unlock_irqrestore(&zone->lock, flags);
local_irq_restore(flags);
}
+/*
+ * Free a list of 0-order pages
+ */
+void free_hot_cold_page_list(struct list_head *list, int cold)
+{
+ struct page *page, *next;
+
+ list_for_each_entry_safe(page, next, list, lru) {
+ trace_mm_page_free_batched(page, cold);
+ free_hot_cold_page(page, cold);
+ }
+}
+
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
if (order >= pageblock_order - 1) {
struct page *endpage = page + (1 << order) - 1;
- for (; page < endpage; page += pageblock_nr_pages)
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ for (; page < endpage; page += pageblock_nr_pages) {
+ int mt = get_pageblock_migratetype(page);
+ if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt))
+ set_pageblock_migratetype(page,
+ MIGRATE_MOVABLE);
+ }
}
return 1 << order;
static int __init fail_page_alloc_debugfs(void)
{
- mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
long min = mark;
int o;
- free_pages -= (1 << order) + 1;
+ free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (alloc_flags & ALLOC_HARDER)
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+ debug_guardpage_minorder() > 0)
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
static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+ unsigned long did_some_progress,
unsigned long pages_reclaimed)
{
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
return 0;
+ /* Always retry if specifically requested */
+ if (gfp_mask & __GFP_NOFAIL)
+ return 1;
+
+ /*
+ * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+ * making forward progress without invoking OOM. Suspend also disables
+ * storage devices so kswapd will not help. Bail if we are suspending.
+ */
+ if (!did_some_progress && pm_suspended_storage())
+ return 0;
+
/*
* In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
* means __GFP_NOFAIL, but that may not be true in other
if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
return 1;
- /*
- * Don't let big-order allocations loop unless the caller
- * explicitly requests that.
- */
- if (gfp_mask & __GFP_NOFAIL)
- return 1;
-
return 0;
}
__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, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
struct page *page;
- if (!order || compaction_deferred(preferred_zone))
+ if (!order)
return NULL;
+ if (compaction_deferred(preferred_zone)) {
+ *deferred_compaction = true;
+ return NULL;
+ }
+
current->flags |= PF_MEMALLOC;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
nodemask, sync_migration);
* but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
- defer_compaction(preferred_zone);
+
+ /*
+ * As async compaction considers a subset of pageblocks, only
+ * defer if the failure was a sync compaction failure.
+ */
+ if (sync_migration)
+ defer_compaction(preferred_zone);
cond_resched();
}
__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, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
return NULL;
}
#endif /* CONFIG_COMPACTION */
-/* The really slow allocator path where we enter direct reclaim */
-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)
+/* Perform direct synchronous page reclaim */
+static int
+__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist,
+ nodemask_t *nodemask)
{
- struct page *page = NULL;
struct reclaim_state reclaim_state;
- bool drained = false;
+ int progress;
cond_resched();
reclaim_state.reclaimed_slab = 0;
current->reclaim_state = &reclaim_state;
- *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
+ progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
current->reclaim_state = NULL;
lockdep_clear_current_reclaim_state();
cond_resched();
+ return progress;
+}
+
+/* The really slow allocator path where we enter direct reclaim */
+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)
+{
+ struct page *page = NULL;
+ bool drained = false;
+
+ *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+ nodemask);
if (unlikely(!(*did_some_progress)))
return NULL;
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);
* 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())
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
bool sync_migration = false;
+ bool deferred_compaction = false;
/*
* In the slowpath, we sanity check order to avoid ever trying to
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
sync_migration = true;
+ /*
+ * If compaction is deferred for high-order allocations, it is because
+ * sync compaction recently failed. In this is the case and the caller
+ * has requested the system not be heavily disrupted, fail the
+ * allocation now instead of entering direct reclaim
+ */
+ if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+ goto nopage;
+
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
zonelist, high_zoneidx,
/* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
- if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+ if (should_alloc_retry(gfp_mask, order, did_some_progress,
+ pages_reclaimed)) {
/* Wait for some write requests to complete then retry */
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
goto rebalance;
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
}
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zone *preferred_zone;
- struct page *page;
+ struct page *page = NULL;
int migratetype = allocflags_to_migratetype(gfp_mask);
+ unsigned int cpuset_mems_cookie;
gfp_mask &= gfp_allowed_mask;
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
- get_mems_allowed();
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+
/* The preferred zone is used for statistics later */
first_zones_zonelist(zonelist, high_zoneidx,
nodemask ? : &cpuset_current_mems_allowed,
&preferred_zone);
- if (!preferred_zone) {
- put_mems_allowed();
- return NULL;
- }
+ if (!preferred_zone)
+ goto out;
/* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
page = __alloc_pages_slowpath(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
- put_mems_allowed();
trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+ /*
+ * When updating a task's mems_allowed, it is possible to race with
+ * parallel threads in such a way that an allocation can fail while
+ * 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))
+ goto retry_cpuset;
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
}
EXPORT_SYMBOL(get_zeroed_page);
-void __pagevec_free(struct pagevec *pvec)
-{
- int i = pagevec_count(pvec);
-
- while (--i >= 0) {
- trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
- free_hot_cold_page(pvec->pages[i], pvec->cold);
- }
-}
-
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
bool skip_free_areas_node(unsigned int flags, int nid)
{
bool ret = false;
+ unsigned int cpuset_mems_cookie;
if (!(flags & SHOW_MEM_FILTER_NODES))
goto out;
- get_mems_allowed();
- ret = !node_isset(nid, cpuset_current_mems_allowed);
- put_mems_allowed();
+ do {
+ cpuset_mems_cookie = get_mems_allowed();
+ ret = !node_isset(nid, cpuset_current_mems_allowed);
+ } while (!put_mems_allowed(cpuset_mems_cookie));
out:
return ret;
}
* round what is now in bits to nearest long in bits, then return it in
* bytes.
*/
-static unsigned long __init usemap_size(unsigned long zonesize)
+static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
{
unsigned long usemapsize;
+ zonesize += zone_start_pfn & (pageblock_nr_pages-1);
usemapsize = roundup(zonesize, pageblock_nr_pages);
usemapsize = usemapsize >> pageblock_order;
usemapsize *= NR_PAGEBLOCK_BITS;
}
static void __init setup_usemap(struct pglist_data *pgdat,
- struct zone *zone, unsigned long zonesize)
+ struct zone *zone,
+ unsigned long zone_start_pfn,
+ unsigned long zonesize)
{
- unsigned long usemapsize = usemap_size(zonesize);
+ unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
zone->pageblock_flags = NULL;
if (usemapsize)
zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
usemapsize);
}
#else
-static inline void setup_usemap(struct pglist_data *pgdat,
- struct zone *zone, unsigned long zonesize) {}
+static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
+ unsigned long zone_start_pfn, unsigned long zonesize) {}
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
-/* Return a sensible default order for the pageblock size. */
-static inline int pageblock_default_order(void)
-{
- if (HPAGE_SHIFT > PAGE_SHIFT)
- return HUGETLB_PAGE_ORDER;
-
- return MAX_ORDER-1;
-}
-
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-static inline void __init set_pageblock_order(unsigned int order)
+void __init set_pageblock_order(void)
{
+ unsigned int order;
+
/* Check that pageblock_nr_pages has not already been setup */
if (pageblock_order)
return;
+ if (HPAGE_SHIFT > PAGE_SHIFT)
+ order = HUGETLB_PAGE_ORDER;
+ else
+ order = MAX_ORDER - 1;
+
/*
* Assume the largest contiguous order of interest is a huge page.
- * This value may be variable depending on boot parameters on IA64
+ * This value may be variable depending on boot parameters on IA64 and
+ * powerpc.
*/
pageblock_order = order;
}
/*
* When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
- * and pageblock_default_order() are unused as pageblock_order is set
- * at compile-time. See include/linux/pageblock-flags.h for the values of
- * pageblock_order based on the kernel config
+ * is unused as pageblock_order is set at compile-time. See
+ * include/linux/pageblock-flags.h for the values of pageblock_order based on
+ * the kernel config
*/
-static inline int pageblock_default_order(unsigned int order)
+void __init set_pageblock_order(void)
{
- return MAX_ORDER-1;
}
-#define set_pageblock_order(x) do {} while (0)
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
init_waitqueue_head(&pgdat->kswapd_wait);
pgdat->kswapd_max_order = 0;
pgdat_page_cgroup_init(pgdat);
-
+
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, memmap_pages;
if (!size)
continue;
- set_pageblock_order(pageblock_default_order());
- setup_usemap(pgdat, zone, size);
+ set_pageblock_order();
+ setup_usemap(pgdat, zone, zone_start_pfn, size);
ret = init_currently_empty_zone(zone, zone_start_pfn,
size, MEMMAP_EARLY);
BUG_ON(ret);
if (max > zone->present_pages)
max = zone->present_pages;
reserve_pages += max;
+ /*
+ * Lowmem reserves are not available to
+ * GFP_HIGHUSER page cache allocations and
+ * kswapd tries to balance zones to their high
+ * watermark. As a result, neither should be
+ * regarded as dirtyable memory, to prevent a
+ * situation where reclaim has to clean pages
+ * in order to balance the zones.
+ */
+ zone->dirty_balance_reserve = max;
}
}
+ dirty_balance_reserve = reserve_pages;
totalreserve_pages = reserve_pages;
}
calculate_totalreserve_pages();
}
-/**
- * setup_per_zone_wmarks - called when min_free_kbytes changes
- * or when memory is hot-{added|removed}
- *
- * Ensures that the watermark[min,low,high] values for each zone are set
- * correctly with respect to min_free_kbytes.
- */
-void setup_per_zone_wmarks(void)
+static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+
+ zone->watermark[WMARK_MIN] += cma_wmark_pages(zone);
+ zone->watermark[WMARK_LOW] += cma_wmark_pages(zone);
+ zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone);
+
setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lock, flags);
}
calculate_totalreserve_pages();
}
+/**
+ * setup_per_zone_wmarks - called when min_free_kbytes changes
+ * or when memory is hot-{added|removed}
+ *
+ * Ensures that the watermark[min,low,high] values for each zone are set
+ * correctly with respect to min_free_kbytes.
+ */
+void setup_per_zone_wmarks(void)
+{
+ mutex_lock(&zonelists_mutex);
+ __setup_per_zone_wmarks();
+ mutex_unlock(&zonelists_mutex);
+}
+
/*
* The inactive anon list should be small enough that the VM never has to
* do too much work, but large enough that each inactive page has a chance
pfn &= (PAGES_PER_SECTION-1);
return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
- pfn = pfn - zone->zone_start_pfn;
+ pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages);
return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
}
__count_immobile_pages(struct zone *zone, struct page *page, int count)
{
unsigned long pfn, iter, found;
+ int mt;
+
/*
* For avoiding noise data, lru_add_drain_all() should be called
* If ZONE_MOVABLE, the zone never contains immobile pages
*/
if (zone_idx(zone) == ZONE_MOVABLE)
return true;
-
- if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE)
+ mt = get_pageblock_migratetype(page);
+ if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt))
return true;
pfn = page_to_pfn(page);
return ret;
}
-void unset_migratetype_isolate(struct page *page)
+void unset_migratetype_isolate(struct page *page, unsigned migratetype)
{
struct zone *zone;
unsigned long flags;
spin_lock_irqsave(&zone->lock, flags);
if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
goto out;
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- move_freepages_block(zone, page, MIGRATE_MOVABLE);
+ set_pageblock_migratetype(page, migratetype);
+ move_freepages_block(zone, page, migratetype);
out:
spin_unlock_irqrestore(&zone->lock, flags);
}
+#ifdef CONFIG_CMA
+
+static unsigned long pfn_max_align_down(unsigned long pfn)
+{
+ return pfn & ~(max_t(unsigned long, MAX_ORDER_NR_PAGES,
+ pageblock_nr_pages) - 1);
+}
+
+static unsigned long pfn_max_align_up(unsigned long pfn)
+{
+ return ALIGN(pfn, max_t(unsigned long, MAX_ORDER_NR_PAGES,
+ pageblock_nr_pages));
+}
+
+static struct page *
+__alloc_contig_migrate_alloc(struct page *page, unsigned long private,
+ int **resultp)
+{
+ gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE;
+
+ if (PageHighMem(page))
+ gfp_mask |= __GFP_HIGHMEM;
+
+ return alloc_page(gfp_mask);
+}
+
+/* [start, end) must belong to a single zone. */
+static int __alloc_contig_migrate_range(unsigned long start, unsigned long end)
+{
+ /* This function is based on compact_zone() from compaction.c. */
+
+ unsigned long pfn = start;
+ unsigned int tries = 0;
+ int ret = 0;
+
+ struct compact_control cc = {
+ .nr_migratepages = 0,
+ .order = -1,
+ .zone = page_zone(pfn_to_page(start)),
+ .sync = true,
+ };
+ INIT_LIST_HEAD(&cc.migratepages);
+
+ migrate_prep_local();
+
+ while (pfn < end || !list_empty(&cc.migratepages)) {
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
+ if (list_empty(&cc.migratepages)) {
+ cc.nr_migratepages = 0;
+ pfn = isolate_migratepages_range(cc.zone, &cc,
+ pfn, end);
+ if (!pfn) {
+ ret = -EINTR;
+ break;
+ }
+ tries = 0;
+ } else if (++tries == 5) {
+ ret = ret < 0 ? ret : -EBUSY;
+ break;
+ }
+
+ ret = migrate_pages(&cc.migratepages,
+ __alloc_contig_migrate_alloc,
+ 0, false, MIGRATE_SYNC);
+ }
+
+ putback_lru_pages(&cc.migratepages);
+ return ret > 0 ? 0 : ret;
+}
+
+/*
+ * Update zone's cma pages counter used for watermark level calculation.
+ */
+static inline void __update_cma_watermarks(struct zone *zone, int count)
+{
+ unsigned long flags;
+ spin_lock_irqsave(&zone->lock, flags);
+ zone->min_cma_pages += count;
+ spin_unlock_irqrestore(&zone->lock, flags);
+ setup_per_zone_wmarks();
+}
+
+/*
+ * Trigger memory pressure bump to reclaim some pages in order to be able to
+ * allocate 'count' pages in single page units. Does similar work as
+ *__alloc_pages_slowpath() function.
+ */
+static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
+{
+ enum zone_type high_zoneidx = gfp_zone(gfp_mask);
+ struct zonelist *zonelist = node_zonelist(0, gfp_mask);
+ int did_some_progress = 0;
+ int order = 1;
+
+ /*
+ * Increase level of watermarks to force kswapd do his job
+ * to stabilise at new watermark level.
+ */
+ __update_cma_watermarks(zone, count);
+
+ /* Obey watermarks as if the page was being allocated */
+ while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) {
+ wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone));
+
+ did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
+ NULL);
+ if (!did_some_progress) {
+ /* Exhausted what can be done so it's blamo time */
+ out_of_memory(zonelist, gfp_mask, order, NULL);
+ }
+ }
+
+ /* Restore original watermark levels. */
+ __update_cma_watermarks(zone, -count);
+
+ return count;
+}
+
+/**
+ * alloc_contig_range() -- tries to allocate given range of pages
+ * @start: start PFN to allocate
+ * @end: one-past-the-last PFN to allocate
+ * @migratetype: migratetype of the underlaying pageblocks (either
+ * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks
+ * in range must have the same migratetype and it must
+ * be either of the two.
+ *
+ * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
+ * aligned, however it's the caller's responsibility to guarantee that
+ * we are the only thread that changes migrate type of pageblocks the
+ * pages fall in.
+ *
+ * The PFN range must belong to a single zone.
+ *
+ * Returns zero on success or negative error code. On success all
+ * pages which PFN is in [start, end) are allocated for the caller and
+ * need to be freed with free_contig_range().
+ */
+int alloc_contig_range(unsigned long start, unsigned long end,
+ unsigned migratetype)
+{
+ struct zone *zone = page_zone(pfn_to_page(start));
+ unsigned long outer_start, outer_end;
+ int ret = 0, order;
+
+ /*
+ * What we do here is we mark all pageblocks in range as
+ * MIGRATE_ISOLATE. Because pageblock and max order pages may
+ * have different sizes, and due to the way page allocator
+ * work, we align the range to biggest of the two pages so
+ * that page allocator won't try to merge buddies from
+ * different pageblocks and change MIGRATE_ISOLATE to some
+ * other migration type.
+ *
+ * Once the pageblocks are marked as MIGRATE_ISOLATE, we
+ * migrate the pages from an unaligned range (ie. pages that
+ * we are interested in). This will put all the pages in
+ * range back to page allocator as MIGRATE_ISOLATE.
+ *
+ * When this is done, we take the pages in range from page
+ * allocator removing them from the buddy system. This way
+ * page allocator will never consider using them.
+ *
+ * This lets us mark the pageblocks back as
+ * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the
+ * aligned range but not in the unaligned, original range are
+ * put back to page allocator so that buddy can use them.
+ */
+
+ ret = start_isolate_page_range(pfn_max_align_down(start),
+ pfn_max_align_up(end), migratetype);
+ if (ret)
+ goto done;
+
+ ret = __alloc_contig_migrate_range(start, end);
+ if (ret)
+ goto done;
+
+ /*
+ * Pages from [start, end) are within a MAX_ORDER_NR_PAGES
+ * aligned blocks that are marked as MIGRATE_ISOLATE. What's
+ * more, all pages in [start, end) are free in page allocator.
+ * What we are going to do is to allocate all pages from
+ * [start, end) (that is remove them from page allocator).
+ *
+ * The only problem is that pages at the beginning and at the
+ * end of interesting range may be not aligned with pages that
+ * page allocator holds, ie. they can be part of higher order
+ * pages. Because of this, we reserve the bigger range and
+ * once this is done free the pages we are not interested in.
+ *
+ * We don't have to hold zone->lock here because the pages are
+ * isolated thus they won't get removed from buddy.
+ */
+
+ lru_add_drain_all();
+ drain_all_pages();
+
+ order = 0;
+ outer_start = start;
+ while (!PageBuddy(pfn_to_page(outer_start))) {
+ if (++order >= MAX_ORDER) {
+ ret = -EBUSY;
+ goto done;
+ }
+ outer_start &= ~0UL << order;
+ }
+
+ /* Make sure the range is really isolated. */
+ if (test_pages_isolated(outer_start, end)) {
+ pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
+ outer_start, end);
+ ret = -EBUSY;
+ goto done;
+ }
+
+ /*
+ * Reclaim enough pages to make sure that contiguous allocation
+ * will not starve the system.
+ */
+ __reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start);
+
+ /* Grab isolated pages from freelists. */
+ outer_end = isolate_freepages_range(outer_start, end);
+ if (!outer_end) {
+ ret = -EBUSY;
+ goto done;
+ }
+
+ /* Free head and tail (if any) */
+ if (start != outer_start)
+ free_contig_range(outer_start, start - outer_start);
+ if (end != outer_end)
+ free_contig_range(end, outer_end - end);
+
+done:
+ undo_isolate_page_range(pfn_max_align_down(start),
+ pfn_max_align_up(end), migratetype);
+ return ret;
+}
+
+void free_contig_range(unsigned long pfn, unsigned nr_pages)
+{
+ for (; nr_pages--; ++pfn)
+ __free_page(pfn_to_page(pfn));
+}
+#endif
+
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* All pages in the range must be isolated before calling this.
zone->free_area[order].nr_free--;
__mod_zone_page_state(zone, NR_FREE_PAGES,
- (1UL << order));
+#ifdef CONFIG_HIGHMEM
+ if (PageHighMem(page))
+ totalhigh_pages -= 1 << order;
+#endif
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);
git.openpandora.org / pandora-kernel.git / blobdiff