#endif
/* work_structs for global per-cpu drains */
+struct pcpu_drain {
+ struct zone *zone;
+ struct work_struct work;
+};
DEFINE_MUTEX(pcpu_drain_mutex);
-DEFINE_PER_CPU(struct work_struct, pcpu_drain);
+DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
#endif
};
-char * const migratetype_names[MIGRATE_TYPES] = {
+const char * const migratetype_names[MIGRATE_TYPES] = {
"Unmovable",
"Movable",
"Reclaimable",
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+int watermark_boost_factor __read_mostly = 15000;
int watermark_scale_factor = 10;
-static unsigned long nr_kernel_pages __meminitdata;
-static unsigned long nr_all_pages __meminitdata;
-static unsigned long dma_reserve __meminitdata;
+static unsigned long nr_kernel_pages __initdata;
+static unsigned long nr_all_pages __initdata;
+static unsigned long dma_reserve __initdata;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __meminitdata;
-static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
+static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long required_kernelcore __initdata;
static unsigned long required_kernelcore_percent __initdata;
static unsigned long required_movablecore __initdata;
static unsigned long required_movablecore_percent __initdata;
-static unsigned long zone_movable_pfn[MAX_NUMNODES] __meminitdata;
+static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata;
static bool mirrored_kernelcore __meminitdata;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+/*
+ * During boot we initialize deferred pages on-demand, as needed, but once
+ * page_alloc_init_late() has finished, the deferred pages are all initialized,
+ * and we can permanently disable that path.
+ */
+static DEFINE_STATIC_KEY_TRUE(deferred_pages);
+
+/*
+ * Calling kasan_free_pages() only after deferred memory initialization
+ * has completed. Poisoning pages during deferred memory init will greatly
+ * lengthen the process and cause problem in large memory systems as the
+ * deferred pages initialization is done with interrupt disabled.
+ *
+ * Assuming that there will be no reference to those newly initialized
+ * pages before they are ever allocated, this should have no effect on
+ * KASAN memory tracking as the poison will be properly inserted at page
+ * allocation time. The only corner case is when pages are allocated by
+ * on-demand allocation and then freed again before the deferred pages
+ * initialization is done, but this is not likely to happen.
+ */
+static inline void kasan_free_nondeferred_pages(struct page *page, int order)
+{
+ if (!static_branch_unlikely(&deferred_pages))
+ kasan_free_pages(page, order);
+}
+
/* Returns true if the struct page for the pfn is uninitialised */
static inline bool __meminit early_page_uninitialised(unsigned long pfn)
{
/* Always populate low zones for address-constrained allocations */
if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
return false;
+
+ /*
+ * 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 > NODE_DATA(nid)->static_init_pgcnt) &&
+ if ((nr_initialised > PAGES_PER_SECTION) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
NODE_DATA(nid)->first_deferred_pfn = pfn;
return true;
return false;
}
#else
+#define kasan_free_nondeferred_pages(p, o) kasan_free_pages(p, o)
+
static inline bool early_page_uninitialised(unsigned long pfn)
{
return false;
unsigned long old_word, word;
BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
+ BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
bitmap = get_pageblock_bitmap(page, pfn);
bitidx = pfn_to_bitidx(page, pfn);
arch_free_page(page, order);
kernel_poison_pages(page, 1 << order, 0);
kernel_map_pages(page, 1 << order, 0);
- kasan_free_pages(page, order);
+ kasan_free_nondeferred_pages(page, order);
return true;
}
return 0;
}
-/*
- * During boot we initialize deferred pages on-demand, as needed, but once
- * page_alloc_init_late() has finished, the deferred pages are all initialized,
- * and we can permanently disable that path.
- */
-static DEFINE_STATIC_KEY_TRUE(deferred_pages);
-
/*
* If this zone has deferred pages, try to grow it by initializing enough
* deferred pages to satisfy the allocation specified by order, rounded up to
return false;
}
+static inline void boost_watermark(struct zone *zone)
+{
+ unsigned long max_boost;
+
+ if (!watermark_boost_factor)
+ return;
+
+ max_boost = mult_frac(zone->_watermark[WMARK_HIGH],
+ watermark_boost_factor, 10000);
+ max_boost = max(pageblock_nr_pages, max_boost);
+
+ zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages,
+ max_boost);
+}
+
/*
* This function implements actual steal behaviour. If order is large enough,
* we can steal whole pageblock. If not, we first move freepages in this
* itself, so pages freed in the future will be put on the correct free list.
*/
static void steal_suitable_fallback(struct zone *zone, struct page *page,
- int start_type, bool whole_block)
+ unsigned int alloc_flags, int start_type, bool whole_block)
{
unsigned int current_order = page_order(page);
struct free_area *area;
goto single_page;
}
+ /*
+ * Boost watermarks to increase reclaim pressure to reduce the
+ * likelihood of future fallbacks. Wake kswapd now as the node
+ * may be balanced overall and kswapd will not wake naturally.
+ */
+ boost_watermark(zone);
+ if (alloc_flags & ALLOC_KSWAPD)
+ wakeup_kswapd(zone, 0, 0, zone_idx(zone));
+
/* We are not allowed to try stealing from the whole block */
if (!whole_block)
goto single_page;
* condition simpler.
*/
static __always_inline bool
-__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
+__rmqueue_fallback(struct zone *zone, int order, int start_migratetype,
+ unsigned int alloc_flags)
{
struct free_area *area;
int current_order;
+ int min_order = order;
struct page *page;
int fallback_mt;
bool can_steal;
+ /*
+ * Do not steal pages from freelists belonging to other pageblocks
+ * i.e. orders < pageblock_order. If there are no local zones free,
+ * the zonelists will be reiterated without ALLOC_NOFRAGMENT.
+ */
+ if (alloc_flags & ALLOC_NOFRAGMENT)
+ min_order = pageblock_order;
+
/*
* Find the largest available free page in the other list. This roughly
* approximates finding the pageblock with the most free pages, which
* would be too costly to do exactly.
*/
- for (current_order = MAX_ORDER - 1; current_order >= order;
+ for (current_order = MAX_ORDER - 1; current_order >= min_order;
--current_order) {
area = &(zone->free_area[current_order]);
fallback_mt = find_suitable_fallback(area, current_order,
page = list_first_entry(&area->free_list[fallback_mt],
struct page, lru);
- steal_suitable_fallback(zone, page, start_migratetype, can_steal);
+ steal_suitable_fallback(zone, page, alloc_flags, start_migratetype,
+ can_steal);
trace_mm_page_alloc_extfrag(page, order, current_order,
start_migratetype, fallback_mt);
* Call me with the zone->lock already held.
*/
static __always_inline struct page *
-__rmqueue(struct zone *zone, unsigned int order, int migratetype)
+__rmqueue(struct zone *zone, unsigned int order, int migratetype,
+ unsigned int alloc_flags)
{
struct page *page;
if (migratetype == MIGRATE_MOVABLE)
page = __rmqueue_cma_fallback(zone, order);
- if (!page && __rmqueue_fallback(zone, order, migratetype))
+ if (!page && __rmqueue_fallback(zone, order, migratetype,
+ alloc_flags))
goto retry;
}
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype)
+ int migratetype, unsigned int alloc_flags)
{
int i, alloced = 0;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
- struct page *page = __rmqueue(zone, order, migratetype);
+ struct page *page = __rmqueue(zone, order, migratetype,
+ alloc_flags);
if (unlikely(page == NULL))
break;
static void drain_local_pages_wq(struct work_struct *work)
{
+ struct pcpu_drain *drain;
+
+ drain = container_of(work, struct pcpu_drain, work);
+
/*
* drain_all_pages doesn't use proper cpu hotplug protection so
* we can race with cpu offline when the WQ can move this from
* a different one.
*/
preempt_disable();
- drain_local_pages(NULL);
+ drain_local_pages(drain->zone);
preempt_enable();
}
}
for_each_cpu(cpu, &cpus_with_pcps) {
- struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
- INIT_WORK(work, drain_local_pages_wq);
- queue_work_on(cpu, mm_percpu_wq, work);
+ struct pcpu_drain *drain = per_cpu_ptr(&pcpu_drain, cpu);
+
+ drain->zone = zone;
+ INIT_WORK(&drain->work, drain_local_pages_wq);
+ queue_work_on(cpu, mm_percpu_wq, &drain->work);
}
for_each_cpu(cpu, &cpus_with_pcps)
- flush_work(per_cpu_ptr(&pcpu_drain, cpu));
+ flush_work(&per_cpu_ptr(&pcpu_drain, cpu)->work);
mutex_unlock(&pcpu_drain_mutex);
}
/* Remove page from the per-cpu list, caller must protect the list */
static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
+ unsigned int alloc_flags,
struct per_cpu_pages *pcp,
struct list_head *list)
{
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
- migratetype);
+ migratetype, alloc_flags);
if (unlikely(list_empty(list)))
return NULL;
}
/* 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)
+ gfp_t gfp_flags, int migratetype,
+ unsigned int alloc_flags)
{
struct per_cpu_pages *pcp;
struct list_head *list;
local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list = &pcp->lists[migratetype];
- page = __rmqueue_pcplist(zone, migratetype, pcp, list);
+ page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list);
if (page) {
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
if (likely(order == 0)) {
page = rmqueue_pcplist(preferred_zone, zone, order,
- gfp_flags, migratetype);
+ gfp_flags, migratetype, alloc_flags);
goto out;
}
trace_mm_page_alloc_zone_locked(page, order, migratetype);
}
if (!page)
- page = __rmqueue(zone, order, migratetype);
+ page = __rmqueue(zone, order, migratetype, alloc_flags);
} while (page && check_new_pages(page, order));
spin_unlock(&zone->lock);
if (!page)
}
#endif /* CONFIG_NUMA */
+/*
+ * The restriction on ZONE_DMA32 as being a suitable zone to use to avoid
+ * fragmentation is subtle. If the preferred zone was HIGHMEM then
+ * premature use of a lower zone may cause lowmem pressure problems that
+ * are worse than fragmentation. If the next zone is ZONE_DMA then it is
+ * probably too small. It only makes sense to spread allocations to avoid
+ * fragmentation between the Normal and DMA32 zones.
+ */
+static inline unsigned int
+alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
+{
+ unsigned int alloc_flags = 0;
+
+ if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ alloc_flags |= ALLOC_KSWAPD;
+
+#ifdef CONFIG_ZONE_DMA32
+ if (zone_idx(zone) != ZONE_NORMAL)
+ goto out;
+
+ /*
+ * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
+ * the pointer is within zone->zone_pgdat->node_zones[]. Also assume
+ * on UMA that if Normal is populated then so is DMA32.
+ */
+ BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
+ if (nr_online_nodes > 1 && !populated_zone(--zone))
+ goto out;
+
+out:
+#endif /* CONFIG_ZONE_DMA32 */
+ return alloc_flags;
+}
+
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
const struct alloc_context *ac)
{
- struct zoneref *z = ac->preferred_zoneref;
+ struct zoneref *z;
struct zone *zone;
struct pglist_data *last_pgdat_dirty_limit = NULL;
+ bool no_fallback;
+retry:
/*
* Scan zonelist, looking for a zone with enough free.
* See also __cpuset_node_allowed() comment in kernel/cpuset.c.
*/
+ no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
+ z = ac->preferred_zoneref;
for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
ac->nodemask) {
struct page *page;
}
}
- mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
+ if (no_fallback && nr_online_nodes > 1 &&
+ zone != ac->preferred_zoneref->zone) {
+ int local_nid;
+
+ /*
+ * If moving to a remote node, retry but allow
+ * fragmenting fallbacks. Locality is more important
+ * than fragmentation avoidance.
+ */
+ local_nid = zone_to_nid(ac->preferred_zoneref->zone);
+ if (zone_to_nid(zone) != local_nid) {
+ alloc_flags &= ~ALLOC_NOFRAGMENT;
+ goto retry;
+ }
+ }
+
+ mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
if (!zone_watermark_fast(zone, order, mark,
ac_classzone_idx(ac), alloc_flags)) {
int ret;
}
}
+ /*
+ * It's possible on a UMA machine to get through all zones that are
+ * fragmented. If avoiding fragmentation, reset and try again.
+ */
+ if (no_fallback) {
+ alloc_flags &= ~ALLOC_NOFRAGMENT;
+ goto retry;
+ }
+
return NULL;
}
va_start(args, fmt);
vaf.fmt = fmt;
vaf.va = &args;
- pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl\n",
+ pr_warn("%s: %pV, mode:%#x(%pGg), nodemask=%*pbl",
current->comm, &vaf, gfp_mask, &gfp_mask,
nodemask_pr_args(nodemask));
va_end(args);
cpuset_print_current_mems_allowed();
-
+ pr_cont("\n");
dump_stack();
warn_alloc_show_mem(gfp_mask, nodemask);
}
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
+ if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ alloc_flags |= ALLOC_KSWAPD;
+
#ifdef CONFIG_CMA
if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
if (!ac->preferred_zoneref->zone)
goto nopage;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
/*
retry:
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
+ if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
finalise_ac(gfp_mask, &ac);
+ /*
+ * Forbid the first pass from falling back to types that fragment
+ * memory until all local zones are considered.
+ */
+ alloc_flags |= alloc_flags_nofragment(ac.preferred_zoneref->zone, gfp_mask);
+
/* First allocation attempt */
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
if (likely(page))
}
EXPORT_SYMBOL(get_zeroed_page);
-void __free_pages(struct page *page, unsigned int order)
+static inline void free_the_page(struct page *page, unsigned int order)
{
- if (put_page_testzero(page)) {
- if (order == 0)
- free_unref_page(page);
- else
- __free_pages_ok(page, order);
- }
+ if (order == 0) /* Via pcp? */
+ free_unref_page(page);
+ else
+ __free_pages_ok(page, order);
}
+void __free_pages(struct page *page, unsigned int order)
+{
+ if (put_page_testzero(page))
+ free_the_page(page, order);
+}
EXPORT_SYMBOL(__free_pages);
void free_pages(unsigned long addr, unsigned int order)
{
VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
- if (page_ref_sub_and_test(page, count)) {
- unsigned int order = compound_order(page);
-
- if (order == 0)
- free_unref_page(page);
- else
- __free_pages_ok(page, order);
- }
+ if (page_ref_sub_and_test(page, count))
+ free_the_page(page, compound_order(page));
}
EXPORT_SYMBOL(__page_frag_cache_drain);
{
struct page *page = virt_to_head_page(addr);
- if (unlikely(put_page_testzero(page))) {
- unsigned int order = compound_order(page);
-
- if (order == 0) /* Via pcp? */
- free_unref_page(page);
- else
- __free_pages_ok(page, order);
- }
+ if (unlikely(put_page_testzero(page)))
+ free_the_page(page, compound_order(page));
}
EXPORT_SYMBOL(page_frag_free);
pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
for_each_zone(zone)
- wmark_low += zone->watermark[WMARK_LOW];
+ wmark_low += low_wmark_pages(zone);
/*
* Estimate the amount of memory available for userspace allocations,
* with no available memory, a warning is printed and the start and end
* PFNs will be 0.
*/
-void __meminit get_pfn_range_for_nid(unsigned int nid,
+void __init get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn)
{
unsigned long this_start_pfn, this_end_pfn;
* highest usable zone for ZONE_MOVABLE. This preserves the assumption that
* zones within a node are in order of monotonic increases memory addresses
*/
-static void __meminit adjust_zone_range_for_zone_movable(int nid,
+static void __init adjust_zone_range_for_zone_movable(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
* Return the number of pages a zone spans in a node, including holes
* present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
*/
-static unsigned long __meminit zone_spanned_pages_in_node(int nid,
+static unsigned long __init zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
* Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
* then all holes in the requested range will be accounted for.
*/
-unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __init __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
}
/* Return the number of page frames in holes in a zone on a node */
-static unsigned long __meminit zone_absent_pages_in_node(int nid,
+static unsigned long __init zone_absent_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
}
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
+static inline unsigned long __init zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
return zones_size[zone_type];
}
-static inline unsigned long __meminit zone_absent_pages_in_node(int nid,
+static inline unsigned long __init zone_absent_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
+static void __init calculate_node_totalpages(struct pglist_data *pgdat,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
unsigned long *zones_size,
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
{
- /*
- * We start only with one section of pages, more pages are added as
- * needed until the rest of deferred pages are initialized.
- */
- pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
- pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
#else
}
EXPORT_SYMBOL(adjust_managed_page_count);
-unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
+unsigned long free_reserved_area(void *start, void *end, int poison, const char *s)
{
void *pos;
unsigned long pages = 0;
min_pages = zone_managed_pages(zone) / 1024;
min_pages = clamp(min_pages, SWAP_CLUSTER_MAX, 128UL);
- zone->watermark[WMARK_MIN] = min_pages;
+ zone->_watermark[WMARK_MIN] = min_pages;
} else {
/*
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = tmp;
+ zone->_watermark[WMARK_MIN] = tmp;
}
/*
mult_frac(zone_managed_pages(zone),
watermark_scale_factor, 10000));
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
+ zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
+ zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
+ zone->watermark_boost = 0;
spin_unlock_irqrestore(&zone->lock, flags);
}
return 0;
}
+int watermark_boost_factor_sysctl_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *length, loff_t *ppos)
+{
+ int rc;
+
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{