#endif
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
-volatile u64 latent_entropy __latent_entropy;
+volatile unsigned long latent_entropy __latent_entropy;
EXPORT_SYMBOL(latent_entropy);
#endif
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+
+/*
+ * Determine how many pages need to be initialized durig early boot
+ * (non-deferred initialization).
+ * The value of first_deferred_pfn will be set later, once non-deferred pages
+ * are initialized, but for now set it ULONG_MAX.
+ */
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
+ phys_addr_t start_addr, end_addr;
+ unsigned long max_pgcnt;
+ unsigned long reserved;
+
+ /*
+ * Initialise at least 2G of a node but also take into account that
+ * two large system hashes that can take up 1GB for 0.25TB/node.
+ */
+ max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
+ (pgdat->node_spanned_pages >> 8));
+
+ /*
+ * Compensate the all the memblock reservations (e.g. crash kernel)
+ * from the initial estimation to make sure we will initialize enough
+ * memory to boot.
+ */
+ start_addr = PFN_PHYS(pgdat->node_start_pfn);
+ end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
+ reserved = memblock_reserved_memory_within(start_addr, end_addr);
+ max_pgcnt += PHYS_PFN(reserved);
+
+ pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
unsigned long pfn, unsigned long zone_end,
unsigned long *nr_initialised)
{
- unsigned long max_initialise;
-
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
- /*
- * Initialise at least 2G of a node but also take into account that
- * two large system hashes that can take up 1GB for 0.25TB/node.
- */
- max_initialise = max(2UL << (30 - PAGE_SHIFT),
- (pgdat->node_spanned_pages >> 8));
-
(*nr_initialised)++;
- if ((*nr_initialised > max_initialise) &&
+ if ((*nr_initialised > pgdat->static_init_pgcnt) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
/* 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_populated_zone(zone)
set_zone_contiguous(zone);
#endif
for (page = start_page; page <= end_page;) {
- /* Make sure we are not inadvertently changing nodes */
- VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
+ /* Make sure we are not inadvertently changing nodes */
+ VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+
if (!PageBuddy(page)) {
page++;
continue;
continue;
/*
- * It should never happen but changes to locking could
- * inadvertently allow a per-cpu drain to add pages
- * to MIGRATE_HIGHATOMIC while unreserving so be safe
- * and watch for underflows.
+ * In page freeing path, migratetype change is racy so
+ * we can counter several free pages in a pageblock
+ * in this loop althoug we changed the pageblock type
+ * from highatomic to ac->migratetype. So we should
+ * adjust the count once.
*/
- zone->nr_reserved_highatomic -= min(pageblock_nr_pages,
- zone->nr_reserved_highatomic);
+ if (get_pageblock_migratetype(page) ==
+ MIGRATE_HIGHATOMIC) {
+ /*
+ * It should never happen but changes to
+ * locking could inadvertently allow a per-cpu
+ * drain to add pages to MIGRATE_HIGHATOMIC
+ * while unreserving so be safe and watch for
+ * underflows.
+ */
+ zone->nr_reserved_highatomic -= min(
+ pageblock_nr_pages,
+ zone->nr_reserved_highatomic);
+ }
/*
* Convert to ac->migratetype and avoid the normal
unsigned long count, struct list_head *list,
int migratetype, bool cold)
{
- int i;
+ int i, alloced = 0;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
else
list_add_tail(&page->lru, list);
list = &page->lru;
+ alloced++;
if (is_migrate_cma(get_pcppage_migratetype(page)))
__mod_zone_page_state(zone, NR_FREE_CMA_PAGES,
-(1 << order));
}
+
+ /*
+ * i pages were removed from the buddy list even if some leak due
+ * to check_pcp_refill failing so adjust NR_FREE_PAGES based
+ * on i. Do not confuse with 'alloced' which is the number of
+ * pages added to the pcp list.
+ */
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
spin_unlock(&zone->lock);
- return i;
+ return alloced;
}
#ifdef CONFIG_NUMA
* Update NUMA hit/miss statistics
*
* Must be called with interrupts disabled.
- *
- * When __GFP_OTHER_NODE is set assume the node of the preferred
- * zone is the local node. This is useful for daemons who allocate
- * memory on behalf of other processes.
*/
static inline void zone_statistics(struct zone *preferred_zone, struct zone *z,
gfp_t flags)
{
#ifdef CONFIG_NUMA
- int local_nid = numa_node_id();
enum zone_stat_item local_stat = NUMA_LOCAL;
- if (unlikely(flags & __GFP_OTHER_NODE)) {
+ if (z->node != numa_node_id())
local_stat = NUMA_OTHER;
- local_nid = preferred_zone->node;
- }
- if (z->node == local_nid) {
+ if (z->node == preferred_zone->node)
__inc_zone_state(z, NUMA_HIT);
- __inc_zone_state(z, local_stat);
- } else {
+ else {
__inc_zone_state(z, NUMA_MISS);
__inc_zone_state(preferred_zone, NUMA_FOREIGN);
}
+ __inc_zone_state(z, local_stat);
#endif
}
if (!area->nr_free)
continue;
- if (alloc_harder)
- return true;
-
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
if (!list_empty(&area->free_list[mt]))
return true;
return true;
}
#endif
+ if (alloc_harder &&
+ !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ return true;
}
return false;
}
#ifdef CONFIG_NUMA
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
- return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
+ return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
enum compact_priority prio, enum compact_result *compact_result)
{
struct page *page;
+ unsigned int noreclaim_flag = current->flags & PF_MEMALLOC;
if (!order)
return NULL;
current->flags |= PF_MEMALLOC;
*compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac,
prio);
- current->flags &= ~PF_MEMALLOC;
+ current->flags = (current->flags & ~PF_MEMALLOC) | noreclaim_flag;
if (*compact_result <= COMPACT_INACTIVE)
return NULL;
}
/*
- * Maximum number of reclaim retries without any progress before OOM killer
- * is consider as the only way to move forward.
- */
-#define MAX_RECLAIM_RETRIES 16
-
-/*
* Checks whether it makes sense to retry the reclaim to make a forward progress
* for the given allocation request.
* The reclaim feedback represented by did_some_progress (any progress during
struct page *page = NULL;
unsigned int alloc_flags;
unsigned long did_some_progress;
- enum compact_priority compact_priority = DEF_COMPACT_PRIORITY;
+ enum compact_priority compact_priority;
enum compact_result compact_result;
- int compaction_retries = 0;
- int no_progress_loops = 0;
- unsigned long alloc_start = jiffies;
- unsigned int stall_timeout = 10 * HZ;
+ int compaction_retries;
+ int no_progress_loops;
+ unsigned int cpuset_mems_cookie;
/*
* In the slowpath, we sanity check order to avoid ever trying to
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
+retry_cpuset:
+ compaction_retries = 0;
+ no_progress_loops = 0;
+ compact_priority = DEF_COMPACT_PRIORITY;
+ cpuset_mems_cookie = read_mems_allowed_begin();
+ /*
+ * We need to recalculate the starting point for the zonelist iterator
+ * because we might have used different nodemask in the fast path, or
+ * there was a cpuset modification and we are retrying - otherwise we
+ * could end up iterating over non-eligible zones endlessly.
+ */
+ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+ ac->high_zoneidx, ac->nodemask);
+ if (!ac->preferred_zoneref->zone)
+ goto nopage;
+
+
/*
* The fast path uses conservative alloc_flags to succeed only until
* kswapd needs to be woken up, and to avoid the cost of setting up
* orientated.
*/
if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) {
- ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
ac->high_zoneidx, ac->nodemask);
}
if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
goto nopage;
- /* Make sure we know about allocations which stall for too long */
- if (time_after(jiffies, alloc_start + stall_timeout)) {
- warn_alloc(gfp_mask,
- "page alloction stalls for %ums, order:%u\n",
- jiffies_to_msecs(jiffies-alloc_start), order);
- stall_timeout += 10 * HZ;
- }
-
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
did_some_progress > 0, &no_progress_loops))
goto retry;
&compaction_retries))
goto retry;
+ /*
+ * It's possible we raced with cpuset update so the OOM would be
+ * premature (see below the nopage: label for full explanation).
+ */
+ if (read_mems_allowed_retry(cpuset_mems_cookie))
+ goto retry_cpuset;
+
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
if (page)
}
nopage:
+ /*
+ * When updating a task's mems_allowed or mempolicy nodemask, it is
+ * possible to race with parallel threads in such a way that our
+ * allocation can fail while the mask is being updated. If we are about
+ * to fail, check if the cpuset changed during allocation and if so,
+ * retry.
+ */
+ if (read_mems_allowed_retry(cpuset_mems_cookie))
+ goto retry_cpuset;
+
warn_alloc(gfp_mask,
"page allocation failure: order:%u", order);
got_pg:
struct zonelist *zonelist, nodemask_t *nodemask)
{
struct page *page;
- unsigned int cpuset_mems_cookie;
unsigned int alloc_flags = ALLOC_WMARK_LOW;
gfp_t alloc_mask = gfp_mask; /* The gfp_t that was actually used for allocation */
struct alloc_context ac = {
if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
alloc_flags |= ALLOC_CMA;
-retry_cpuset:
- cpuset_mems_cookie = read_mems_allowed_begin();
-
/* Dirty zone balancing only done in the fast path */
ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
*/
ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
ac.high_zoneidx, ac.nodemask);
- if (!ac.preferred_zoneref) {
+ if (!ac.preferred_zoneref->zone) {
page = NULL;
+ /*
+ * This might be due to race with cpuset_current_mems_allowed
+ * update, so make sure we retry with original nodemask in the
+ * slow path.
+ */
goto no_zone;
}
if (likely(page))
goto out;
+no_zone:
/*
* Runtime PM, block IO and its error handling path can deadlock
* because I/O on the device might not complete.
* Restore the original nodemask if it was potentially replaced with
* &cpuset_current_mems_allowed to optimize the fast-path attempt.
*/
- if (cpusets_enabled())
+ if (unlikely(ac.nodemask != nodemask))
ac.nodemask = nodemask;
- page = __alloc_pages_slowpath(alloc_mask, order, &ac);
-no_zone:
- /*
- * When updating a task's mems_allowed, it is possible to race with
- * parallel threads in such a way that an allocation can fail while
- * the mask is being updated. If a page allocation is about to fail,
- * check if the cpuset changed during allocation and if so, retry.
- */
- if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) {
- alloc_mask = gfp_mask;
- goto retry_cpuset;
- }
+ page = __alloc_pages_slowpath(alloc_mask, order, &ac);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
- page_ref_add(page, size - 1);
+ page_ref_add(page, size);
/* reset page count bias and offset to start of new frag */
nc->pfmemalloc = page_is_pfmemalloc(page);
- nc->pagecnt_bias = size;
+ nc->pagecnt_bias = size + 1;
nc->offset = size;
}
size = nc->size;
#endif
/* OK, page count is 0, we can safely set it */
- set_page_count(page, size);
+ set_page_count(page, size + 1);
/* reset page count bias and offset to start of new frag */
- nc->pagecnt_bias = size;
+ nc->pagecnt_bias = size + 1;
offset = size - fragsz;
}
}
*p = '\0';
- printk("(%s) ", tmp);
+ printk(KERN_CONT "(%s) ", tmp);
}
/*
K(node_page_state(pgdat, NR_FILE_MAPPED)),
K(node_page_state(pgdat, NR_FILE_DIRTY)),
K(node_page_state(pgdat, NR_WRITEBACK)),
+ K(node_page_state(pgdat, NR_SHMEM)),
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)
* HPAGE_PMD_NR),
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
- K(node_page_state(pgdat, NR_SHMEM)),
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
node_page_state(pgdat, NR_PAGES_SCANNED),
- !pgdat_reclaimable(pgdat) ? "yes" : "no");
+ pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
+ "yes" : "no");
}
for_each_populated_zone(zone) {
free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
show_node(zone);
- printk("%s"
+ printk(KERN_CONT
+ "%s"
" free:%lukB"
" min:%lukB"
" low:%lukB"
K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
- printk(" %ld", zone->lowmem_reserve[i]);
- printk("\n");
+ printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
+ printk(KERN_CONT "\n");
}
for_each_populated_zone(zone) {
if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
show_node(zone);
- printk("%s: ", zone->name);
+ printk(KERN_CONT "%s: ", zone->name);
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
}
spin_unlock_irqrestore(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
- printk("%lu*%lukB ", nr[order], K(1UL) << order);
+ printk(KERN_CONT "%lu*%lukB ",
+ nr[order], K(1UL) << order);
if (nr[order])
show_migration_types(types[order]);
}
- printk("= %lukB\n", K(total));
+ printk(KERN_CONT "= %lukB\n", K(total));
}
hugetlb_show_meminfo();
}
/*
- * Helper functions to size the waitqueue hash table.
- * Essentially these want to choose hash table sizes sufficiently
- * large so that collisions trying to wait on pages are rare.
- * But in fact, the number of active page waitqueues on typical
- * systems is ridiculously low, less than 200. So this is even
- * conservative, even though it seems large.
- *
- * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
- * waitqueues, i.e. the size of the waitq table given the number of pages.
- */
-#define PAGES_PER_WAITQUEUE 256
-
-#ifndef CONFIG_MEMORY_HOTPLUG
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
- unsigned long size = 1;
-
- pages /= PAGES_PER_WAITQUEUE;
-
- while (size < pages)
- size <<= 1;
-
- /*
- * Once we have dozens or even hundreds of threads sleeping
- * on IO we've got bigger problems than wait queue collision.
- * Limit the size of the wait table to a reasonable size.
- */
- size = min(size, 4096UL);
-
- return max(size, 4UL);
-}
-#else
-/*
- * A zone's size might be changed by hot-add, so it is not possible to determine
- * a suitable size for its wait_table. So we use the maximum size now.
- *
- * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie:
- *
- * i386 (preemption config) : 4096 x 16 = 64Kbyte.
- * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
- * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte.
- *
- * The maximum entries are prepared when a zone's memory is (512K + 256) pages
- * or more by the traditional way. (See above). It equals:
- *
- * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte.
- * ia64(16K page size) : = ( 8G + 4M)byte.
- * powerpc (64K page size) : = (32G +16M)byte.
- */
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
- return 4096UL;
-}
-#endif
-
-/*
- * This is an integer logarithm so that shifts can be used later
- * to extract the more random high bits from the multiplicative
- * hash function before the remainder is taken.
- */
-static inline unsigned long wait_table_bits(unsigned long size)
-{
- return ffz(~size);
-}
-
-/*
* Initially all pages are reserved - free ones are freed
* up by free_all_bootmem() once the early boot process is
* done. Non-atomic initialization, single-pass.
alloc_percpu(struct per_cpu_nodestat);
}
-static noinline __ref
-int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
-{
- int i;
- size_t alloc_size;
-
- /*
- * The per-page waitqueue mechanism uses hashed waitqueues
- * per zone.
- */
- zone->wait_table_hash_nr_entries =
- wait_table_hash_nr_entries(zone_size_pages);
- zone->wait_table_bits =
- wait_table_bits(zone->wait_table_hash_nr_entries);
- alloc_size = zone->wait_table_hash_nr_entries
- * sizeof(wait_queue_head_t);
-
- if (!slab_is_available()) {
- zone->wait_table = (wait_queue_head_t *)
- memblock_virt_alloc_node_nopanic(
- alloc_size, zone->zone_pgdat->node_id);
- } else {
- /*
- * This case means that a zone whose size was 0 gets new memory
- * via memory hot-add.
- * But it may be the case that a new node was hot-added. In
- * this case vmalloc() will not be able to use this new node's
- * memory - this wait_table must be initialized to use this new
- * node itself as well.
- * To use this new node's memory, further consideration will be
- * necessary.
- */
- zone->wait_table = vmalloc(alloc_size);
- }
- if (!zone->wait_table)
- return -ENOMEM;
-
- for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
- init_waitqueue_head(zone->wait_table + i);
-
- return 0;
-}
-
static __meminit void zone_pcp_init(struct zone *zone)
{
/*
unsigned long size)
{
struct pglist_data *pgdat = zone->zone_pgdat;
- int ret;
- ret = zone_wait_table_init(zone, size);
- if (ret)
- return ret;
+
pgdat->nr_zones = zone_idx(zone) + 1;
zone->zone_start_pfn = zone_start_pfn;
zone_start_pfn, (zone_start_pfn + size));
zone_init_free_lists(zone);
+ zone->initialized = 1;
return 0;
}
unsigned long *zone_end_pfn,
unsigned long *ignored)
{
+ unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
+ unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
/* Get the start and end of the zone */
- *zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
- *zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+ *zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
+ *zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
zone_start_pfn, zone_end_pfn);
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
- reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
pgdat->per_cpu_nodestats = NULL;
(unsigned long)pgdat->node_mem_map);
#endif
+ reset_deferred_meminit(pgdat);
free_area_init_core(pgdat);
}
}
if (pages && s)
- pr_info("Freeing %s memory: %ldK (%p - %p)\n",
- s, pages << (PAGE_SHIFT - 10), start, end);
+ pr_info("Freeing %s memory: %ldK\n",
+ s, pages << (PAGE_SHIFT - 10));
return pages;
}
/*
* In case of -EBUSY, we'd like to know which page causes problem.
- * So, just fall through. We will check it in test_pages_isolated().
+ * So, just fall through. test_pages_isolated() has a tracepoint
+ * which will report the busy page.
+ *
+ * It is possible that busy pages could become available before
+ * the call to test_pages_isolated, and the range will actually be
+ * allocated. So, if we fall through be sure to clear ret so that
+ * -EBUSY is not accidentally used or returned to caller.
*/
ret = __alloc_contig_migrate_range(&cc, start, end);
if (ret && ret != -EBUSY)
goto done;
+ ret =0;
/*
* Pages from [start, end) are within a MAX_ORDER_NR_PAGES
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
- pr_info("%s: [%lx, %lx) PFNs busy\n",
+ pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
goto done;