#include <linux/mempolicy.h>
#include <linux/memremap.h>
#include <linux/stop_machine.h>
+#include <linux/random.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
+#include "shuffle.h"
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#if MAX_NUMNODES > 1
-int nr_node_ids __read_mostly = MAX_NUMNODES;
-int nr_online_nodes __read_mostly = 1;
+unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
+unsigned int nr_online_nodes __read_mostly = 1;
EXPORT_SYMBOL(nr_node_ids);
EXPORT_SYMBOL(nr_online_nodes);
#endif
}
/*
- * Returns true when the remaining initialisation should be deferred until
- * later in the boot cycle when it can be parallelised.
+ * Calculate first_deferred_pfn in case:
+ * - in MEMMAP_EARLY context
+ * - this is the last zone
+ *
+ * If the first aligned section doesn't exceed the end_pfn, set it to
+ * first_deferred_pfn and return it.
*/
-static bool __meminit
-defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
+unsigned long __meminit
+defer_pfn(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum memmap_context context)
{
- static unsigned long prev_end_pfn, nr_initialised;
+ struct pglist_data *pgdat = NODE_DATA(nid);
+ unsigned long pfn;
- /*
- * prev_end_pfn static that contains the end of previous zone
- * No need to protect because called very early in boot before smp_init.
- */
- if (prev_end_pfn != end_pfn) {
- prev_end_pfn = end_pfn;
- nr_initialised = 0;
- }
+ if (context != MEMMAP_EARLY)
+ return end_pfn;
- /* Always populate low zones for address-constrained allocations */
- if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
- return false;
+ /* Always populate low zones */
+ if (end_pfn < pgdat_end_pfn(pgdat))
+ return end_pfn;
- /*
- * We start only with one section of pages, more pages are added as
- * needed until the rest of deferred pages are initialized.
- */
- nr_initialised++;
- if ((nr_initialised > PAGES_PER_SECTION) &&
- (pfn & (PAGES_PER_SECTION - 1)) == 0) {
- NODE_DATA(nid)->first_deferred_pfn = pfn;
- return true;
+ pfn = roundup(start_pfn + PAGES_PER_SECTION - 1, PAGES_PER_SECTION);
+ if (end_pfn > pfn) {
+ pgdat->first_deferred_pfn = pfn;
+ end_pfn = pfn;
}
- return false;
+ return end_pfn;
}
#else
#define kasan_free_nondeferred_pages(p, o) kasan_free_pages(p, o)
return false;
}
-static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
+unsigned long __meminit
+defer_pfn(int nid, unsigned long start_pfn, unsigned long end_pfn,
+ enum memmap_context context)
{
- return false;
+ return end_pfn;
}
#endif
__SetPageBuddy(page);
}
-static inline void rmv_page_order(struct page *page)
-{
- __ClearPageBuddy(page);
- set_page_private(page, 0);
-}
-
/*
* This function checks whether a page is free && is the buddy
* we can coalesce a page and its buddy if
return 0;
}
+#ifdef CONFIG_COMPACTION
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+ struct capture_control *capc = current->capture_control;
+
+ return capc &&
+ !(current->flags & PF_KTHREAD) &&
+ !capc->page &&
+ capc->cc->zone == zone &&
+ capc->cc->direct_compaction ? capc : NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+ int order, int migratetype)
+{
+ if (!capc || order != capc->cc->order)
+ return false;
+
+ /* Do not accidentally pollute CMA or isolated regions*/
+ if (is_migrate_cma(migratetype) ||
+ is_migrate_isolate(migratetype))
+ return false;
+
+ /*
+ * Do not let lower order allocations polluate a movable pageblock.
+ * This might let an unmovable request use a reclaimable pageblock
+ * and vice-versa but no more than normal fallback logic which can
+ * have trouble finding a high-order free page.
+ */
+ if (order < pageblock_order && migratetype == MIGRATE_MOVABLE)
+ return false;
+
+ capc->page = page;
+ return true;
+}
+
+#else
+static inline struct capture_control *task_capc(struct zone *zone)
+{
+ return NULL;
+}
+
+static inline bool
+compaction_capture(struct capture_control *capc, struct page *page,
+ int order, int migratetype)
+{
+ return false;
+}
+#endif /* CONFIG_COMPACTION */
+
/*
* Freeing function for a buddy system allocator.
*
unsigned long uninitialized_var(buddy_pfn);
struct page *buddy;
unsigned int max_order;
+ struct capture_control *capc = task_capc(zone);
max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
continue_merging:
while (order < max_order - 1) {
+ if (compaction_capture(capc, page, order, migratetype)) {
+ __mod_zone_freepage_state(zone, -(1 << order),
+ migratetype);
+ return;
+ }
buddy_pfn = __find_buddy_pfn(pfn, order);
buddy = page + (buddy_pfn - pfn);
* 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)) {
+ if (page_is_guard(buddy))
clear_page_guard(zone, buddy, order, migratetype);
- } else {
- list_del(&buddy->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(buddy);
- }
+ else
+ del_page_from_free_area(buddy, &zone->free_area[order],
+ migratetype);
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
* so it's less likely to be used soon and more likely to be merged
* as a higher order page
*/
- if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)) {
+ if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
+ && !is_shuffle_order(order)) {
struct page *higher_page, *higher_buddy;
combined_pfn = buddy_pfn & pfn;
higher_page = page + (combined_pfn - pfn);
higher_buddy = higher_page + (buddy_pfn - combined_pfn);
if (pfn_valid_within(buddy_pfn) &&
page_is_buddy(higher_page, higher_buddy, order + 1)) {
- list_add_tail(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
- goto out;
+ add_to_free_area_tail(page, &zone->free_area[order],
+ migratetype);
+ return;
}
}
- list_add(&page->lru, &zone->free_area[order].free_list[migratetype]);
-out:
- zone->free_area[order].nr_free++;
+ if (is_shuffle_order(order))
+ add_to_free_area_random(page, &zone->free_area[order],
+ migratetype);
+ else
+ add_to_free_area(page, &zone->free_area[order], migratetype);
+
}
/*
if (PageMappingFlags(page))
page->mapping = NULL;
if (memcg_kmem_enabled() && PageKmemcg(page))
- memcg_kmem_uncharge(page, order);
+ __memcg_kmem_uncharge(page, order);
if (check_free)
bad += free_pages_check(page);
if (bad)
spin_unlock(&zone->lock);
}
-static void __meminit __init_single_page(struct page *page, unsigned long pfn,
- unsigned long zone, int nid)
+static void __meminit __init_struct_page_nolru(struct page *page,
+ unsigned long pfn,
+ unsigned long zone, int nid,
+ bool is_reserved)
{
mm_zero_struct_page(page);
- set_page_links(page, zone, nid, pfn);
+
+ /*
+ * We can use a non-atomic operation for setting the
+ * PG_reserved flag as we are still initializing the pages.
+ */
+ set_page_links(page, zone, nid, pfn, is_reserved);
init_page_count(page);
page_mapcount_reset(page);
page_cpupid_reset_last(page);
page_kasan_tag_reset(page);
- INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
/* The shift won't overflow because ZONE_NORMAL is below 4G. */
if (!is_highmem_idx(zone))
#endif
}
+static void __meminit __init_single_page(struct page *page, unsigned long pfn,
+ unsigned long zone, int nid)
+{
+ __init_struct_page_nolru(page, pfn, zone, nid, false);
+ INIT_LIST_HEAD(&page->lru);
+}
+
+static void __meminit __init_pageblock(unsigned long start_pfn,
+ unsigned long nr_pages,
+ unsigned long zone, int nid,
+ struct dev_pagemap *pgmap,
+ bool is_reserved)
+{
+ unsigned long nr_pgmask = pageblock_nr_pages - 1;
+ struct page *start_page = pfn_to_page(start_pfn);
+ unsigned long pfn = start_pfn + nr_pages - 1;
+ struct page *page;
+
+ /*
+ * Enforce the following requirements:
+ * size > 0
+ * size < pageblock_nr_pages
+ * start_pfn -> pfn does not cross pageblock_nr_pages boundary
+ */
+ VM_BUG_ON(((start_pfn ^ pfn) | (nr_pages - 1)) > nr_pgmask);
+
+ /*
+ * Work from highest page to lowest, this way we will still be
+ * warm in the cache when we call set_pageblock_migratetype
+ * below.
+ *
+ * The loop is based around the page pointer as the main index
+ * instead of the pfn because pfn is not used inside the loop if
+ * the section number is not in page flags and WANT_PAGE_VIRTUAL
+ * is not defined.
+ */
+ for (page = start_page + nr_pages; page-- != start_page; pfn--) {
+ __init_struct_page_nolru(page, pfn, zone, nid, is_reserved);
+
+ /*
+ * ZONE_DEVICE pages union ->lru with a ->pgmap back
+ * pointer and hmm_data. It is a bug if a ZONE_DEVICE
+ * page is ever freed or placed on a driver-private list.
+ */
+ page->pgmap = pgmap;
+ if (!pgmap)
+ INIT_LIST_HEAD(&page->lru);
+ }
+
+ /*
+ * Mark the block movable so that blocks are reserved for
+ * movable at startup. This will force kernel allocations
+ * to reserve their blocks rather than leaking throughout
+ * the address space during boot when many long-lived
+ * kernel allocations are made.
+ *
+ * bitmap is created for zone's valid pfn range. but memmap
+ * can be created for invalid pages (for alignment)
+ * check here not to call set_pageblock_migratetype() against
+ * pfn out of zone.
+ *
+ * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+ * because this is done early in sparse_add_one_section
+ */
+ if (!(start_pfn & nr_pgmask))
+ set_pageblock_migratetype(start_page, MIGRATE_MOVABLE);
+}
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __meminit init_reserved_page(unsigned long pfn)
{
local_irq_restore(flags);
}
-static void __init __free_pages_boot_core(struct page *page, unsigned int order)
+void __free_pages_core(struct page *page, unsigned int order)
{
unsigned int nr_pages = 1 << order;
struct page *p = page;
#endif
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
+/* Only safe to use early in boot when initialisation is single-threaded */
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
int nid;
- nid = __early_pfn_to_nid(pfn, state);
+ nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
if (nid >= 0 && nid != node)
return false;
return true;
}
-/* Only safe to use early in boot when initialisation is single-threaded */
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
-}
-
#else
-
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
return true;
}
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
-{
- return true;
-}
#endif
{
if (early_page_uninitialised(pfn))
return;
- return __free_pages_boot_core(page, order);
+ __free_pages_core(page, order);
}
/*
}
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void __init deferred_free_range(unsigned long pfn,
- unsigned long nr_pages)
-{
- struct page *page;
- unsigned long i;
-
- if (!nr_pages)
- return;
-
- page = pfn_to_page(pfn);
-
- /* Free a large naturally-aligned chunk if possible */
- if (nr_pages == pageblock_nr_pages &&
- (pfn & (pageblock_nr_pages - 1)) == 0) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, pageblock_order);
- return;
- }
-
- for (i = 0; i < nr_pages; i++, page++, pfn++) {
- if ((pfn & (pageblock_nr_pages - 1)) == 0)
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- __free_pages_boot_core(page, 0);
- }
-}
-
/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
}
/*
- * Returns true if page needs to be initialized or freed to buddy allocator.
+ * Returns count if page range needs to be initialized or freed
*
- * First we check if pfn is valid on architectures where it is possible to have
- * holes within pageblock_nr_pages. On systems where it is not possible, this
- * function is optimized out.
+ * First we check if the contiguous pfns are valid on architectures where it
+ * is possible to have holes within pageblock_nr_pages. On systems where it
+ * is not possible, this function is optimized out.
*
- * Then, we check if a current large page is valid by only checking the validity
- * of the head pfn.
+ * Then, we check if a current large page is valid by only checking the
+ * validity of the head pfn.
*
- * Finally, meminit_pfn_in_nid is checked on systems where pfns can interleave
- * within a node: a pfn is between start and end of a node, but does not belong
- * to this memory node.
*/
-static inline bool __init
-deferred_pfn_valid(int nid, unsigned long pfn,
- struct mminit_pfnnid_cache *nid_init_state)
+static unsigned long __next_pfn_valid_range(unsigned long *pfn,
+ unsigned long *i,
+ unsigned long end_pfn)
{
- if (!pfn_valid_within(pfn))
- return false;
- if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
- return false;
- if (!meminit_pfn_in_nid(pfn, nid, nid_init_state))
- return false;
- return true;
+ unsigned long start_pfn = *i;
+
+ while (start_pfn < end_pfn) {
+ unsigned long t = ALIGN(start_pfn + 1, pageblock_nr_pages);
+ unsigned long pageblock_pfn = min(t, end_pfn);
+ unsigned long count = 0;
+
+#ifndef CONFIG_HOLES_IN_ZONE
+ if (pfn_valid(start_pfn))
+ count = pageblock_pfn - start_pfn;
+ start_pfn = pageblock_pfn;
+#else
+ while (start_pfn < pageblock_pfn) {
+ if (pfn_valid(start_pfn++)) {
+ count++;
+ continue;
+ }
+
+ if (!count)
+ continue;
+
+ /*
+ * The last PFN was invalid, report the block of
+ * PFNs we currently have available and skip over
+ * the invalid one.
+ */
+ *pfn = start_pfn - (count + 1);
+ *i = start_pfn;
+ return count;
+ }
+#endif
+ if (!count)
+ continue;
+
+ *pfn = start_pfn - count;
+ *i = start_pfn;
+ return count;
+ }
+
+ return 0;
}
+#define for_each_deferred_pfn_valid_range(pfn, count, i, start_pfn, end_pfn) \
+ for (i = (start_pfn), \
+ count = __next_pfn_valid_range(&pfn, &i, (end_pfn)); \
+ count; \
+ count = __next_pfn_valid_range(&pfn, &i, (end_pfn)))
+
/*
* Free pages to buddy allocator. Try to free aligned pages in
* pageblock_nr_pages sizes.
*/
-static void __init deferred_free_pages(int nid, int zid, unsigned long pfn,
+static void __init deferred_free_pages(unsigned long start_pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
- unsigned long nr_pgmask = pageblock_nr_pages - 1;
- unsigned long nr_free = 0;
-
- for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
- deferred_free_range(pfn - nr_free, nr_free);
- nr_free = 0;
- } else if (!(pfn & nr_pgmask)) {
- deferred_free_range(pfn - nr_free, nr_free);
- nr_free = 1;
- touch_nmi_watchdog();
+ unsigned long i, pfn, count;
+
+ for_each_deferred_pfn_valid_range(pfn, count, i, start_pfn, end_pfn) {
+ struct page *page = pfn_to_page(pfn);
+
+ if (count == pageblock_nr_pages) {
+ __free_pages_core(page, pageblock_order);
} else {
- nr_free++;
+ while (count--)
+ __free_pages_core(page++, 0);
}
+
+ touch_nmi_watchdog();
}
- /* Free the last block of pages to allocator */
- deferred_free_range(pfn - nr_free, nr_free);
}
/*
* by performing it only once every pageblock_nr_pages.
* Return number of pages initialized.
*/
-static unsigned long __init deferred_init_pages(int nid, int zid,
- unsigned long pfn,
+static unsigned long __init deferred_init_pages(struct zone *zone,
+ unsigned long start_pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
- unsigned long nr_pgmask = pageblock_nr_pages - 1;
+ int nid = zone_to_nid(zone);
+ unsigned long i, pfn, count;
unsigned long nr_pages = 0;
- struct page *page = NULL;
+ int zid = zone_idx(zone);
+
+ for_each_deferred_pfn_valid_range(pfn, count, i, start_pfn, end_pfn) {
+ nr_pages += count;
+ __init_pageblock(pfn, count, zid, nid, NULL, false);
+
+ touch_nmi_watchdog();
+ }
+
+ return nr_pages;
+}
+
+/*
+ * This function is meant to pre-load the iterator for the zone init.
+ * Specifically it walks through the ranges until we are caught up to the
+ * first_init_pfn value and exits there. If we never encounter the value we
+ * return false indicating there are no valid ranges left.
+ */
+static bool __init
+deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
+ unsigned long *spfn, unsigned long *epfn,
+ unsigned long first_init_pfn)
+{
+ u64 j;
- for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
- page = NULL;
+ /*
+ * Start out by walking through the ranges in this zone that have
+ * already been initialized. We don't need to do anything with them
+ * so we just need to flush them out of the system.
+ */
+ for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
+ if (*epfn <= first_init_pfn)
continue;
- } else if (!page || !(pfn & nr_pgmask)) {
- page = pfn_to_page(pfn);
- touch_nmi_watchdog();
- } else {
- page++;
- }
- __init_single_page(page, pfn, zid, nid);
- nr_pages++;
+ if (*spfn < first_init_pfn)
+ *spfn = first_init_pfn;
+ *i = j;
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * Initialize and free pages. We do it in two loops: first we initialize
+ * struct page, than free to buddy allocator, because while we are
+ * freeing pages we can access pages that are ahead (computing buddy
+ * page in __free_one_page()).
+ *
+ * In order to try and keep some memory in the cache we have the loop
+ * broken along max page order boundaries. This way we will not cause
+ * any issues with the buddy page computation.
+ */
+static unsigned long __init
+deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
+ unsigned long *end_pfn)
+{
+ unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
+ unsigned long spfn = *start_pfn, epfn = *end_pfn;
+ unsigned long nr_pages = 0;
+ u64 j = *i;
+
+ /* First we loop through and initialize the page values */
+ for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
+ unsigned long t;
+
+ if (mo_pfn <= spfn)
+ break;
+
+ t = min(mo_pfn, epfn);
+ nr_pages += deferred_init_pages(zone, spfn, t);
+
+ if (mo_pfn <= epfn)
+ break;
+ }
+
+ /* Reset values and now loop through freeing pages as needed */
+ j = *i;
+
+ for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
+ unsigned long t;
+
+ if (mo_pfn <= *start_pfn)
+ break;
+
+ t = min(mo_pfn, *end_pfn);
+ deferred_free_pages(*start_pfn, t);
+ *start_pfn = t;
+
+ if (mo_pfn < *end_pfn)
+ break;
}
- return (nr_pages);
+
+ /* Store our current values to be reused on the next iteration */
+ *i = j;
+
+ return nr_pages;
}
/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
- int nid = pgdat->node_id;
+ const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+ unsigned long spfn = 0, epfn = 0, nr_pages = 0;
+ unsigned long first_init_pfn, flags;
unsigned long start = jiffies;
- unsigned long nr_pages = 0;
- unsigned long spfn, epfn, first_init_pfn, flags;
- phys_addr_t spa, epa;
- int zid;
struct zone *zone;
- const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+ int zid;
u64 i;
/* Bind memory initialisation thread to a local node if possible */
if (first_init_pfn < zone_end_pfn(zone))
break;
}
- first_init_pfn = max(zone->zone_start_pfn, first_init_pfn);
+
+ /* If the zone is empty somebody else may have cleared out the zone */
+ if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ first_init_pfn))
+ goto zone_empty;
/*
- * Initialize and free pages. We do it in two loops: first we initialize
- * struct page, than free to buddy allocator, because while we are
- * freeing pages we can access pages that are ahead (computing buddy
- * page in __free_one_page()).
+ * Initialize and free pages in MAX_ORDER sized increments so
+ * that we can avoid introducing any issues with the buddy
+ * allocator.
*/
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
- nr_pages += deferred_init_pages(nid, zid, spfn, epfn);
- }
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
- deferred_free_pages(nid, zid, spfn, epfn);
- }
+ while (spfn < epfn)
+ nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+zone_empty:
pgdat_resize_unlock(pgdat, &flags);
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
- pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
- jiffies_to_msecs(jiffies - start));
+ pr_info("node %d initialised, %lu pages in %ums\n",
+ pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
- int zid = zone_idx(zone);
- int nid = zone_to_nid(zone);
- pg_data_t *pgdat = NODE_DATA(nid);
unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
- unsigned long nr_pages = 0;
- unsigned long first_init_pfn, spfn, epfn, t, flags;
+ pg_data_t *pgdat = zone->zone_pgdat;
unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
- phys_addr_t spa, epa;
+ unsigned long spfn, epfn, flags;
+ unsigned long nr_pages = 0;
u64 i;
/* Only the last zone may have deferred pages */
return true;
}
- first_init_pfn = max(zone->zone_start_pfn, first_deferred_pfn);
-
- if (first_init_pfn >= pgdat_end_pfn(pgdat)) {
+ /* If the zone is empty somebody else may have cleared out the zone */
+ if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ first_deferred_pfn)) {
+ pgdat->first_deferred_pfn = ULONG_MAX;
pgdat_resize_unlock(pgdat, &flags);
- return false;
+ return true;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
-
- while (spfn < epfn && nr_pages < nr_pages_needed) {
- t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
- first_deferred_pfn = min(t, epfn);
- nr_pages += deferred_init_pages(nid, zid, spfn,
- first_deferred_pfn);
- spfn = first_deferred_pfn;
- }
-
- if (nr_pages >= nr_pages_needed)
- break;
+ /*
+ * Initialize and free pages in MAX_ORDER sized increments so
+ * that we can avoid introducing any issues with the buddy
+ * allocator.
+ */
+ while (spfn < epfn && nr_pages < nr_pages_needed) {
+ nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+ first_deferred_pfn = spfn;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa));
- deferred_free_pages(nid, zid, spfn, epfn);
-
- if (first_deferred_pfn == epfn)
- break;
- }
pgdat->first_deferred_pfn = first_deferred_pfn;
pgdat_resize_unlock(pgdat, &flags);
void __init page_alloc_init_late(void)
{
struct zone *zone;
+ int nid;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
- int nid;
/* There will be num_node_state(N_MEMORY) threads */
atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
memblock_discard();
#endif
+ for_each_node_state(nid, N_MEMORY)
+ shuffle_free_memory(NODE_DATA(nid));
+
for_each_populated_zone(zone)
set_zone_contiguous(zone);
}
if (set_page_guard(zone, &page[size], high, migratetype))
continue;
- list_add(&page[size].lru, &area->free_list[migratetype]);
+ add_to_free_area(&page[size], area, migratetype);
area->nr_free++;
set_page_order(&page[size], high);
}
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
- kernel_poison_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
+ kernel_poison_pages(page, 1 << order, 1);
set_page_owner(page, order, gfp_flags);
}
/* Find a page of the appropriate size in the preferred list */
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = &(zone->free_area[current_order]);
- page = list_first_entry_or_null(&area->free_list[migratetype],
- struct page, lru);
+ page = get_page_from_free_area(area, migratetype);
if (!page)
continue;
- list_del(&page->lru);
- rmv_page_order(page);
- area->nr_free--;
+ del_page_from_free_area(page, area, migratetype);
expand(zone, page, order, current_order, area, migratetype);
set_pcppage_migratetype(page, migratetype);
return page;
}
order = page_order(page);
- list_move(&page->lru,
- &zone->free_area[order].free_list[migratetype]);
+ move_to_free_area(page, &zone->free_area[order], migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
single_page:
area = &zone->free_area[current_order];
- list_move(&page->lru, &area->free_list[start_type]);
+ move_to_free_area(page, area, start_type);
}
/*
if (fallback_mt == MIGRATE_TYPES)
break;
- if (list_empty(&area->free_list[fallback_mt]))
+ if (free_area_empty(area, fallback_mt))
continue;
if (can_steal_fallback(order, migratetype))
for (order = 0; order < MAX_ORDER; order++) {
struct free_area *area = &(zone->free_area[order]);
- page = list_first_entry_or_null(
- &area->free_list[MIGRATE_HIGHATOMIC],
- struct page, lru);
+ page = get_page_from_free_area(area, MIGRATE_HIGHATOMIC);
if (!page)
continue;
VM_BUG_ON(current_order == MAX_ORDER);
do_steal:
- page = list_first_entry(&area->free_list[fallback_mt],
- struct page, lru);
+ page = get_page_from_free_area(area, fallback_mt);
steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
can_steal);
int __isolate_free_page(struct page *page, unsigned int order)
{
+ struct free_area *area = &page_zone(page)->free_area[order];
unsigned long watermark;
struct zone *zone;
int mt;
* watermark, because we already know our high-order page
* exists.
*/
- watermark = min_wmark_pages(zone) + (1UL << order);
+ watermark = zone->_watermark[WMARK_MIN] + (1UL << order);
if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
return 0;
}
/* Remove page from free list */
- list_del(&page->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(page);
+
+ del_page_from_free_area(page, area, mt);
/*
* Set the pageblock if the isolated page is at least half of a
dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
&fail_page_alloc.attr);
- if (IS_ERR(dir))
- return PTR_ERR(dir);
-
- if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
- &fail_page_alloc.ignore_gfp_reclaim))
- goto fail;
- if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
- &fail_page_alloc.ignore_gfp_highmem))
- goto fail;
- if (!debugfs_create_u32("min-order", mode, dir,
- &fail_page_alloc.min_order))
- goto fail;
- return 0;
-fail:
- debugfs_remove_recursive(dir);
+ debugfs_create_bool("ignore-gfp-wait", mode, dir,
+ &fail_page_alloc.ignore_gfp_reclaim);
+ debugfs_create_bool("ignore-gfp-highmem", mode, dir,
+ &fail_page_alloc.ignore_gfp_highmem);
+ debugfs_create_u32("min-order", mode, dir, &fail_page_alloc.min_order);
- return -ENOMEM;
+ return 0;
}
late_initcall(fail_page_alloc_debugfs);
continue;
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
- if (!list_empty(&area->free_list[mt]))
+ if (!free_area_empty(area, mt))
return true;
}
#ifdef CONFIG_CMA
if ((alloc_flags & ALLOC_CMA) &&
- !list_empty(&area->free_list[MIGRATE_CMA])) {
+ !free_area_empty(area, MIGRATE_CMA)) {
return true;
}
#endif
unsigned int alloc_flags, const struct alloc_context *ac,
enum compact_priority prio, enum compact_result *compact_result)
{
- struct page *page;
+ struct page *page = NULL;
unsigned long pflags;
unsigned int noreclaim_flag;
noreclaim_flag = memalloc_noreclaim_save();
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
- prio);
+ prio, &page);
memalloc_noreclaim_restore(noreclaim_flag);
psi_memstall_leave(&pflags);
- if (*compact_result <= COMPACT_INACTIVE)
+ if (*compact_result <= COMPACT_INACTIVE) {
+ WARN_ON_ONCE(page);
return NULL;
+ }
/*
* At least in one zone compaction wasn't deferred or skipped, so let's
*/
count_vm_event(COMPACTSTALL);
- page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
+ /* Prep a captured page if available */
+ if (page)
+ prep_new_page(page, order, gfp_mask, alloc_flags);
+
+ /* Try get a page from the freelist if available */
+ if (!page)
+ page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
if (page) {
struct zone *zone = page_zone(page);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
- unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) {
__free_pages(page, order);
page = NULL;
}
types[order] = 0;
for (type = 0; type < MIGRATE_TYPES; type++) {
- if (!list_empty(&area->free_list[type]))
+ if (!free_area_empty(area, type))
types[order] |= 1 << type;
}
}
else
page_group_by_mobility_disabled = 0;
- pr_info("Built %i zonelists, mobility grouping %s. Total pages: %ld\n",
+ pr_info("Built %u zonelists, mobility grouping %s. Total pages: %ld\n",
nr_online_nodes,
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
return false;
}
+static void __meminit __memmap_init_hotplug(unsigned long size, int nid,
+ unsigned long zone,
+ unsigned long start_pfn,
+ struct dev_pagemap *pgmap)
+{
+ unsigned long pfn = start_pfn + size;
+
+ while (pfn != start_pfn) {
+ unsigned long stride = pfn;
+
+ pfn = max(ALIGN_DOWN(pfn - 1, pageblock_nr_pages), start_pfn);
+ stride -= pfn;
+
+ /*
+ * The last argument of __init_pageblock is a boolean
+ * value indicating if the page will be marked as reserved.
+ *
+ * Mark page reserved as it will need to wait for onlining
+ * phase for it to be fully associated with a zone.
+ *
+ * Under certain circumstances ZONE_DEVICE pages may not
+ * need to be marked as reserved, however there is still
+ * code that is depending on this being set for now.
+ */
+ __init_pageblock(pfn, stride, zone, nid, pgmap, true);
+
+ cond_resched();
+ }
+}
+
/*
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
struct vmem_altmap *altmap)
{
unsigned long pfn, end_pfn = start_pfn + size;
- struct page *page;
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
+ if (context == MEMMAP_HOTPLUG) {
#ifdef CONFIG_ZONE_DEVICE
- /*
- * Honor reservation requested by the driver for this ZONE_DEVICE
- * memory. We limit the total number of pages to initialize to just
- * those that might contain the memory mapping. We will defer the
- * ZONE_DEVICE page initialization until after we have released
- * the hotplug lock.
- */
- if (zone == ZONE_DEVICE) {
- if (!altmap)
- return;
+ /*
+ * Honor reservation requested by the driver for this
+ * ZONE_DEVICE memory. We limit the total number of pages to
+ * initialize to just those that might contain the memory
+ * mapping. We will defer the ZONE_DEVICE page initialization
+ * until after we have released the hotplug lock.
+ */
+ if (zone == ZONE_DEVICE) {
+ if (!altmap)
+ return;
+
+ if (start_pfn == altmap->base_pfn)
+ start_pfn += altmap->reserve;
+ end_pfn = altmap->base_pfn +
+ vmem_altmap_offset(altmap);
+ }
+#endif
+ /*
+ * For these ZONE_DEVICE pages we don't need to record the
+ * pgmap as they should represent only those pages used to
+ * store the memory map. The actual ZONE_DEVICE pages will
+ * be initialized later.
+ */
+ __memmap_init_hotplug(end_pfn - start_pfn, nid, zone,
+ start_pfn, NULL);
- if (start_pfn == altmap->base_pfn)
- start_pfn += altmap->reserve;
- end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+ return;
}
-#endif
+
+ end_pfn = defer_pfn(nid, start_pfn, end_pfn, context);
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ struct page *page;
+
/*
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
- if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
- continue;
- if (!early_pfn_in_nid(pfn, nid))
- continue;
- if (overlap_memmap_init(zone, &pfn))
- continue;
- if (defer_init(nid, pfn, end_pfn))
- break;
- }
+ if (!early_pfn_valid(pfn))
+ continue;
+ if (!early_pfn_in_nid(pfn, nid))
+ continue;
+ if (overlap_memmap_init(zone, &pfn))
+ continue;
page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid);
- if (context == MEMMAP_HOTPLUG)
- __SetPageReserved(page);
/*
* Mark the block movable so that blocks are reserved for
unsigned long size,
struct dev_pagemap *pgmap)
{
- unsigned long pfn, end_pfn = start_pfn + size;
struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long zone_idx = zone_idx(zone);
unsigned long start = jiffies;
*/
if (pgmap->altmap_valid) {
struct vmem_altmap *altmap = &pgmap->altmap;
+ unsigned long end_pfn = start_pfn + size;
start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
size = end_pfn - start_pfn;
}
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
- struct page *page = pfn_to_page(pfn);
-
- __init_single_page(page, pfn, zone_idx, nid);
-
- /*
- * Mark page reserved as it will need to wait for onlining
- * phase for it to be fully associated with a zone.
- *
- * We can use the non-atomic __set_bit operation for setting
- * the flag as we are still initializing the pages.
- */
- __SetPageReserved(page);
-
- /*
- * ZONE_DEVICE pages union ->lru with a ->pgmap back
- * pointer and hmm_data. It is a bug if a ZONE_DEVICE
- * page is ever freed or placed on a driver-private list.
- */
- page->pgmap = pgmap;
- page->hmm_data = 0;
-
- /*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
- *
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
- *
- * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
- * because this is done early in sparse_add_one_section
- */
- if (!(pfn & (pageblock_nr_pages - 1))) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- cond_resched();
- }
- }
+ __memmap_init_hotplug(size, nid, zone_idx, start_pfn, pgmap);
pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev),
size, jiffies_to_msecs(jiffies - start));
return state->last_nid;
nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
- if (nid != -1) {
+ if (nid != NUMA_NO_NODE) {
state->last_start = start_pfn;
state->last_end = end_pfn;
state->last_nid = nid;
{
unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
zone->pageblock_flags = NULL;
- if (usemapsize)
+ if (usemapsize) {
zone->pageblock_flags =
- memblock_alloc_node_nopanic(usemapsize,
- pgdat->node_id);
+ memblock_alloc_node(usemapsize, SMP_CACHE_BYTES,
+ pgdat->node_id);
+ if (!zone->pageblock_flags)
+ panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n",
+ usemapsize, zone->name, pgdat->node_id);
+ }
}
#else
static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
end = pgdat_end_pfn(pgdat);
end = ALIGN(end, MAX_ORDER_NR_PAGES);
size = (end - start) * sizeof(struct page);
- map = memblock_alloc_node_nopanic(size, pgdat->node_id);
+ map = memblock_alloc_node(size, SMP_CACHE_BYTES,
+ pgdat->node_id);
+ if (!map)
+ panic("Failed to allocate %ld bytes for node %d memory map\n",
+ size, pgdat->node_id);
pgdat->node_mem_map = map + offset;
}
pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
{
unsigned long accl_mask = 0, last_end = 0;
unsigned long start, end, mask;
- int last_nid = -1;
+ int last_nid = NUMA_NO_NODE;
int i, nid;
for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
* value here.
*
* The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
- * deltas control asynch page reclaim, and so should
+ * deltas control async page reclaim, and so should
* not be capped for highmem.
*/
unsigned long min_pages;
size = bucketsize << log2qty;
if (flags & HASH_EARLY) {
if (flags & HASH_ZERO)
- table = memblock_alloc_nopanic(size,
- SMP_CACHE_BYTES);
+ table = memblock_alloc(size, SMP_CACHE_BYTES);
else
table = memblock_alloc_raw(size,
SMP_CACHE_BYTES);
/*
* Hugepages are not in LRU lists, but they're movable.
- * We need not scan over tail pages bacause we don't
+ * We need not scan over tail pages because we don't
* handle each tail page individually in migration.
*/
if (PageHuge(page)) {
*/
lru_add_drain_all();
- drain_all_pages(cc.zone);
order = 0;
outer_start = start;
pfn_max_align_up(end), migratetype);
return ret;
}
+#endif
-void free_contig_range(unsigned long pfn, unsigned nr_pages)
+void free_contig_range(unsigned long pfn, unsigned int nr_pages)
{
unsigned int count = 0;
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
-#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/*
spin_lock_irqsave(&zone->lock, flags);
pfn = start_pfn;
while (pfn < end_pfn) {
+ struct free_area *area;
+ int mt;
+
if (!pfn_valid(pfn)) {
pfn++;
continue;
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
order = page_order(page);
+ area = &zone->free_area[order];
#ifdef CONFIG_DEBUG_VM
pr_info("remove from free list %lx %d %lx\n",
pfn, 1 << order, end_pfn);
#endif
- list_del(&page->lru);
- rmv_page_order(page);
- zone->free_area[order].nr_free--;
+ mt = get_pageblock_migratetype(page);
+ del_page_from_free_area(page, area, mt);
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);