[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
+#endif
+#ifdef CONFIG_MOVABLE_NODE
+ [N_MEMORY] = { { [0] = 1UL } },
#endif
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
__free_one_page(page, zone, 0, mt);
trace_mm_page_pcpu_drain(page, 0, mt);
- if (is_migrate_cma(mt))
- __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
+ if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) {
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1);
+ if (is_migrate_cma(mt))
+ __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
+ }
} while (--to_free && --batch_free && !list_empty(list));
}
- __mod_zone_page_state(zone, NR_FREE_PAGES, count);
spin_unlock(&zone->lock);
}
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)
{
unsigned int nr_pages = 1 << order;
set_page_count(p, 0);
}
+ page_zone(page)->managed_pages += 1 << order;
set_page_refcounted(page);
__free_pages(page, order);
}
zone = page_zone(page);
order = page_order(page);
+ mt = get_pageblock_migratetype(page);
- /* Obey watermarks as if the page was being allocated */
- watermark = low_wmark_pages(zone) + (1 << order);
- if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
- return 0;
+ if (mt != MIGRATE_ISOLATE) {
+ /* Obey watermarks as if the page was being allocated */
+ watermark = low_wmark_pages(zone) + (1 << order);
+ if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+ return 0;
+
+ __mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
+ }
/* Remove page from free list */
list_del(&page->lru);
zone->free_area[order].nr_free--;
rmv_page_order(page);
- mt = get_pageblock_migratetype(page);
- if (unlikely(mt != MIGRATE_ISOLATE))
- __mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
-
if (alloc_order != order)
expand(zone, page, alloc_order, order,
&zone->free_area[order], migratetype);
}
}
- return 1UL << order;
+ return 1UL << alloc_order;
}
/*
*
* If the zonelist cache is present in the passed in zonelist, then
* returns a pointer to the allowed node mask (either the current
- * tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
+ * tasks mems_allowed, or node_states[N_MEMORY].)
*
* If the zonelist cache is not available for this zonelist, does
* nothing and returns NULL.
allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
&cpuset_current_mems_allowed :
- &node_states[N_HIGH_MEMORY];
+ &node_states[N_MEMORY];
return allowednodes;
}
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
high_zoneidx, nodemask) {
- if (NUMA_BUILD && zlc_active &&
+ if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if ((alloc_flags & ALLOC_CPUSET) &&
classzone_idx, alloc_flags))
goto try_this_zone;
- if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+ if (IS_ENABLED(CONFIG_NUMA) &&
+ !did_zlc_setup && nr_online_nodes > 1) {
/*
* we do zlc_setup if there are multiple nodes
* and before considering the first zone allowed
* As we may have just activated ZLC, check if the first
* eligible zone has failed zone_reclaim recently.
*/
- if (NUMA_BUILD && zlc_active &&
+ if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if (page)
break;
this_zone_full:
- if (NUMA_BUILD)
+ if (IS_ENABLED(CONFIG_NUMA))
zlc_mark_zone_full(zonelist, z);
}
- if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
+ if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
zlc_active = 0;
goto zonelist_scan;
return NULL;
/* After successful reclaim, reconsider all zones for allocation */
- if (NUMA_BUILD)
+ if (IS_ENABLED(CONFIG_NUMA))
zlc_clear_zones_full(zonelist);
retry:
* allowed per node queues are empty and that nodes are
* over allocated.
*/
- if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+ if (IS_ENABLED(CONFIG_NUMA) &&
+ (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
restart:
- wake_all_kswapd(order, zonelist, high_zoneidx,
- zone_idx(preferred_zone));
+ if (!(gfp_mask & __GFP_NO_KSWAPD))
+ wake_all_kswapd(order, zonelist, high_zoneidx,
+ zone_idx(preferred_zone));
/*
* OK, we're below the kswapd watermark and have kicked background
* system then fail the allocation instead of entering direct reclaim.
*/
if ((deferred_compaction || contended_compaction) &&
- (gfp_mask & (__GFP_MOVABLE|__GFP_REPEAT)) == __GFP_MOVABLE)
+ (gfp_mask & __GFP_NO_KSWAPD))
goto nopage;
/* Try direct reclaim and then allocating */
static inline void show_node(struct zone *zone)
{
- if (NUMA_BUILD)
+ if (IS_ENABLED(CONFIG_NUMA))
printk("Node %d ", zone_to_nid(zone));
}
#define K(x) ((x) << (PAGE_SHIFT-10))
+static void show_migration_types(unsigned char type)
+{
+ static const char types[MIGRATE_TYPES] = {
+ [MIGRATE_UNMOVABLE] = 'U',
+ [MIGRATE_RECLAIMABLE] = 'E',
+ [MIGRATE_MOVABLE] = 'M',
+ [MIGRATE_RESERVE] = 'R',
+#ifdef CONFIG_CMA
+ [MIGRATE_CMA] = 'C',
+#endif
+ [MIGRATE_ISOLATE] = 'I',
+ };
+ char tmp[MIGRATE_TYPES + 1];
+ char *p = tmp;
+ int i;
+
+ for (i = 0; i < MIGRATE_TYPES; i++) {
+ if (type & (1 << i))
+ *p++ = types[i];
+ }
+
+ *p = '\0';
+ printk("(%s) ", tmp);
+}
+
/*
* Show free area list (used inside shift_scroll-lock stuff)
* We also calculate the percentage fragmentation. We do this by counting the
" isolated(anon):%lukB"
" isolated(file):%lukB"
" present:%lukB"
+ " managed:%lukB"
" mlocked:%lukB"
" dirty:%lukB"
" writeback:%lukB"
K(zone_page_state(zone, NR_ISOLATED_ANON)),
K(zone_page_state(zone, NR_ISOLATED_FILE)),
K(zone->present_pages),
+ K(zone->managed_pages),
K(zone_page_state(zone, NR_MLOCK)),
K(zone_page_state(zone, NR_FILE_DIRTY)),
K(zone_page_state(zone, NR_WRITEBACK)),
for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
+ unsigned char types[MAX_ORDER];
if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
- nr[order] = zone->free_area[order].nr_free;
+ struct free_area *area = &zone->free_area[order];
+ int type;
+
+ nr[order] = area->nr_free;
total += nr[order] << order;
+
+ types[order] = 0;
+ for (type = 0; type < MIGRATE_TYPES; type++) {
+ if (!list_empty(&area->free_list[type]))
+ types[order] |= 1 << type;
+ }
}
spin_unlock_irqrestore(&zone->lock, flags);
- for (order = 0; order < MAX_ORDER; order++)
+ for (order = 0; order < MAX_ORDER; order++) {
printk("%lu*%lukB ", nr[order], K(1UL) << order);
+ if (nr[order])
+ show_migration_types(types[order]);
+ }
printk("= %lukB\n", K(total));
}
return node;
}
- for_each_node_state(n, N_HIGH_MEMORY) {
+ for_each_node_state(n, N_MEMORY) {
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
* local memory, NODE_ORDER may be suitable.
*/
average_size = total_size /
- (nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
+ (nodes_weight(node_states[N_MEMORY]) + 1);
for_each_online_node(nid) {
low_kmem_size = 0;
total_size = 0;
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
+static unsigned long __paginginit calc_memmap_size(unsigned long spanned_pages,
+ unsigned long present_pages)
+{
+ unsigned long pages = spanned_pages;
+
+ /*
+ * Provide a more accurate estimation if there are holes within
+ * the zone and SPARSEMEM is in use. If there are holes within the
+ * zone, each populated memory region may cost us one or two extra
+ * memmap pages due to alignment because memmap pages for each
+ * populated regions may not naturally algined on page boundary.
+ * So the (present_pages >> 4) heuristic is a tradeoff for that.
+ */
+ if (spanned_pages > present_pages + (present_pages >> 4) &&
+ IS_ENABLED(CONFIG_SPARSEMEM))
+ pages = present_pages;
+
+ return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
+}
+
/*
* Set up the zone data structures:
* - mark all pages reserved
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
- unsigned long size, realsize, memmap_pages;
+ unsigned long size, realsize, freesize, memmap_pages;
size = zone_spanned_pages_in_node(nid, j, zones_size);
- realsize = size - zone_absent_pages_in_node(nid, j,
+ realsize = freesize = size - zone_absent_pages_in_node(nid, j,
zholes_size);
/*
- * Adjust realsize so that it accounts for how much memory
+ * Adjust freesize so that it accounts for how much memory
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
- memmap_pages =
- PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
- if (realsize >= memmap_pages) {
- realsize -= memmap_pages;
+ memmap_pages = calc_memmap_size(size, realsize);
+ if (freesize >= memmap_pages) {
+ freesize -= memmap_pages;
if (memmap_pages)
printk(KERN_DEBUG
" %s zone: %lu pages used for memmap\n",
zone_names[j], memmap_pages);
} else
printk(KERN_WARNING
- " %s zone: %lu pages exceeds realsize %lu\n",
- zone_names[j], memmap_pages, realsize);
+ " %s zone: %lu pages exceeds freesize %lu\n",
+ zone_names[j], memmap_pages, freesize);
/* Account for reserved pages */
- if (j == 0 && realsize > dma_reserve) {
- realsize -= dma_reserve;
+ if (j == 0 && freesize > dma_reserve) {
+ freesize -= dma_reserve;
printk(KERN_DEBUG " %s zone: %lu pages reserved\n",
zone_names[0], dma_reserve);
}
if (!is_highmem_idx(j))
- nr_kernel_pages += realsize;
- nr_all_pages += realsize;
+ nr_kernel_pages += freesize;
+ /* Charge for highmem memmap if there are enough kernel pages */
+ else if (nr_kernel_pages > memmap_pages * 2)
+ nr_kernel_pages -= memmap_pages;
+ nr_all_pages += freesize;
zone->spanned_pages = size;
- zone->present_pages = realsize;
+ zone->present_pages = freesize;
+ /*
+ * Set an approximate value for lowmem here, it will be adjusted
+ * when the bootmem allocator frees pages into the buddy system.
+ * And all highmem pages will be managed by the buddy system.
+ */
+ zone->managed_pages = is_highmem_idx(j) ? realsize : freesize;
#ifdef CONFIG_NUMA
zone->node = nid;
- zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio)
+ zone->min_unmapped_pages = (freesize*sysctl_min_unmapped_ratio)
/ 100;
- zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100;
+ zone->min_slab_pages = (freesize * sysctl_min_slab_ratio) / 100;
#endif
zone->name = zone_names[j];
spin_lock_init(&zone->lock);
/*
* early_calculate_totalpages()
* Sum pages in active regions for movable zone.
- * Populate N_HIGH_MEMORY for calculating usable_nodes.
+ * Populate N_MEMORY for calculating usable_nodes.
*/
static unsigned long __init early_calculate_totalpages(void)
{
totalpages += pages;
if (pages)
- node_set_state(nid, N_HIGH_MEMORY);
+ node_set_state(nid, N_MEMORY);
}
return totalpages;
}
unsigned long usable_startpfn;
unsigned long kernelcore_node, kernelcore_remaining;
/* save the state before borrow the nodemask */
- nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
+ nodemask_t saved_node_state = node_states[N_MEMORY];
unsigned long totalpages = early_calculate_totalpages();
- int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
+ int usable_nodes = nodes_weight(node_states[N_MEMORY]);
/*
* If movablecore was specified, calculate what size of
restart:
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
- for_each_node_state(nid, N_HIGH_MEMORY) {
+ for_each_node_state(nid, N_MEMORY) {
unsigned long start_pfn, end_pfn;
/*
out:
/* restore the node_state */
- node_states[N_HIGH_MEMORY] = saved_node_state;
+ node_states[N_MEMORY] = saved_node_state;
}
-/* Any regular memory on that node ? */
-static void __init check_for_regular_memory(pg_data_t *pgdat)
+/* Any regular or high memory on that node ? */
+static void check_for_memory(pg_data_t *pgdat, int nid)
{
-#ifdef CONFIG_HIGHMEM
enum zone_type zone_type;
- for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
+ if (N_MEMORY == N_NORMAL_MEMORY)
+ return;
+
+ for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
if (zone->present_pages) {
- node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+ node_set_state(nid, N_HIGH_MEMORY);
+ if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
+ zone_type <= ZONE_NORMAL)
+ node_set_state(nid, N_NORMAL_MEMORY);
break;
}
}
-#endif
}
/**
/* Any memory on that node */
if (pgdat->node_present_pages)
- node_set_state(nid, N_HIGH_MEMORY);
- check_for_regular_memory(pgdat);
+ node_set_state(nid, N_MEMORY);
+ check_for_memory(pgdat, nid);
}
}
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);
}
* MIGRATE_MOVABLE block might include unmovable pages. It means you can't
* expect this function should be exact.
*/
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+ bool skip_hwpoisoned_pages)
{
unsigned long pfn, iter, found;
int mt;
continue;
}
+ /*
+ * The HWPoisoned page may be not in buddy system, and
+ * page_count() is not 0.
+ */
+ if (skip_hwpoisoned_pages && PageHWPoison(page))
+ continue;
+
if (!PageLRU(page))
found++;
/*
zone->zone_start_pfn + zone->spanned_pages <= pfn)
return false;
- return !has_unmovable_pages(zone, page, 0);
+ return !has_unmovable_pages(zone, page, 0, true);
}
#ifdef CONFIG_CMA
unsigned int tries = 0;
int ret = 0;
- migrate_prep_local();
+ migrate_prep();
while (pfn < end || !list_empty(&cc->migratepages)) {
if (fatal_signal_pending(current)) {
0, false, MIGRATE_SYNC);
}
- putback_lru_pages(&cc->migratepages);
+ putback_movable_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, false);
- }
- }
-
- /* 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
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;
*/
ret = start_isolate_page_range(pfn_max_align_down(start),
- pfn_max_align_up(end), migratetype);
+ pfn_max_align_up(end), migratetype,
+ false);
if (ret)
return ret;
}
/* Make sure the range is really isolated. */
- if (test_pages_isolated(outer_start, end)) {
+ if (test_pages_isolated(outer_start, end, false)) {
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(&cc, outer_start, end);
}
#endif
-#ifdef CONFIG_MEMORY_HOTREMOVE
void zone_pcp_reset(struct zone *zone)
{
unsigned long flags;
local_irq_restore(flags);
}
+#ifdef CONFIG_MEMORY_HOTREMOVE
/*
* All pages in the range must be isolated before calling this.
*/
continue;
}
page = pfn_to_page(pfn);
+ /*
+ * The HWPoisoned page may be not in buddy system, and
+ * page_count() is not 0.
+ */
+ if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
+ pfn++;
+ SetPageReserved(page);
+ continue;
+ }
+
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
order = page_order(page);
list_del(&page->lru);
rmv_page_order(page);
zone->free_area[order].nr_free--;
- __mod_zone_page_state(zone, NR_FREE_PAGES,
- - (1UL << order));
for (i = 0; i < (1 << order); i++)
SetPageReserved((page+i));
pfn += (1 << order);