#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);
__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
* 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]);
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);
+
}
/*
#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
*
* 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 inline bool __init deferred_pfn_valid(unsigned long 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;
}
* 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 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)) {
+ if (!deferred_pfn_valid(pfn)) {
deferred_free_range(pfn - nr_free, nr_free);
nr_free = 0;
} else if (!(pfn & nr_pgmask)) {
* 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,
+static unsigned long __init deferred_init_pages(struct zone *zone,
unsigned long 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 nr_pages = 0;
+ int zid = zone_idx(zone);
struct page *page = NULL;
for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
+ if (!deferred_pfn_valid(pfn)) {
page = NULL;
continue;
} else if (!page || !(pfn & nr_pgmask)) {
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;
+
+ /*
+ * 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;
+ 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, then 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, start_pfn, end_pfn) {
+ unsigned long t;
+
+ if (mo_pfn <= *start_pfn)
+ break;
+
+ t = min(mo_pfn, *end_pfn);
+ nr_pages += deferred_init_pages(zone, *start_pfn, t);
+
+ if (mo_pfn < *end_pfn) {
+ *start_pfn = mo_pfn;
+ break;
+ }
+ }
+
+ /* Reset values and now loop through freeing pages as needed */
+ swap(j, *i);
+
+ 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);
+ deferred_free_pages(spfn, t);
+
+ if (mo_pfn <= epfn)
+ break;
+ }
+
+ 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));
+ /*
+ * Initialize and free pages in MAX_ORDER sized increments so
+ * that we can avoid introducing any issues with the buddy
+ * allocator.
+ */
+ while (spfn < epfn) {
+ /* update our first deferred PFN for this section */
+ first_deferred_pfn = spfn;
- 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;
- }
+ nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
+
+ /* We should only stop along section boundaries */
+ if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
+ continue;
+ /* If our quota has been met we can stop here */
if (nr_pages >= nr_pages_needed)
break;
}
- 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->first_deferred_pfn = spfn;
pgdat_resize_unlock(pgdat, &flags);
return nr_pages > 0;
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));
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
#endif
-#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+
/* Discard memblock private 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]);
- area->nr_free++;
+ add_to_free_area(&page[size], area, migratetype);
set_page_order(&page[size], high);
}
}
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
if (unlikely(page_ref_count(page) != 0))
- bad_reason = "nonzero _count";
+ bad_reason = "nonzero _refcount";
if (unlikely(page->flags & __PG_HWPOISON)) {
bad_reason = "HWPoisoned (hardware-corrupted)";
bad_flags = __PG_HWPOISON;
/* 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);
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;
}
/* 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);
/*
* Set the pageblock if the isolated page is at least half of a
/* Lock and remove page from the per-cpu list */
static struct page *rmqueue_pcplist(struct zone *preferred_zone,
- struct zone *zone, unsigned int order,
- gfp_t gfp_flags, int migratetype,
- unsigned int alloc_flags)
+ struct zone *zone, gfp_t gfp_flags,
+ int migratetype, unsigned int alloc_flags)
{
struct per_cpu_pages *pcp;
struct list_head *list;
list = &pcp->lists[migratetype];
page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list);
if (page) {
- __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
+ __count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
zone_statistics(preferred_zone, zone);
}
local_irq_restore(flags);
struct page *page;
if (likely(order == 0)) {
- page = rmqueue_pcplist(preferred_zone, zone, order,
- gfp_flags, migratetype, alloc_flags);
+ page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
+ migratetype, alloc_flags);
goto out;
}
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
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;
}
}
* All pages in the range must be in a single zone and isolated
* before calling this.
*/
-void
+unsigned long
__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
struct page *page;
unsigned int order, i;
unsigned long pfn;
unsigned long flags;
+ unsigned long offlined_pages = 0;
+
/* find the first valid pfn */
for (pfn = start_pfn; pfn < end_pfn; pfn++)
if (pfn_valid(pfn))
break;
if (pfn == end_pfn)
- return;
+ return offlined_pages;
+
offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags);
if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
pfn++;
SetPageReserved(page);
+ offlined_pages++;
continue;
}
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
order = page_order(page);
+ offlined_pages += 1 << 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--;
+ del_page_from_free_area(page, &zone->free_area[order]);
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);
+
+ return offlined_pages;
}
#endif
projects / linux-2.6-microblaze.git / blobdiff