#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
+#include <linux/ratelimit.h>
#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
+#include <linux/vmstat.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <trace/events/kmem.h>
#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
+#include <linux/prefetch.h>
+#include <linux/page-debug-flags.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
+/*
+ * When calculating the number of globally allowed dirty pages, there
+ * is a certain number of per-zone reserves that should not be
+ * considered dirtyable memory. This is the sum of those reserves
+ * over all existing zones that contribute dirtyable memory.
+ */
+unsigned long dirty_balance_reserve __read_mostly;
+
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~GFP_IOFS;
}
+
+bool pm_suspended_storage(void)
+{
+ if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ return false;
+ return true;
+}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
- /*
- * MAX_ACTIVE_REGIONS determines the maximum number of distinct
- * ranges of memory (RAM) that may be registered with add_active_range().
- * Ranges passed to add_active_range() will be merged if possible
- * so the number of times add_active_range() can be called is
- * related to the number of nodes and the number of holes
- */
- #ifdef CONFIG_MAX_ACTIVE_REGIONS
- /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
- #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
- #else
- #if MAX_NUMNODES >= 32
- /* If there can be many nodes, allow up to 50 holes per node */
- #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
- #else
- /* By default, allow up to 256 distinct regions */
- #define MAX_ACTIVE_REGIONS 256
- #endif
- #endif
-
- static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS];
- static int __meminitdata nr_nodemap_entries;
- static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
- static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
- static unsigned long __initdata required_kernelcore;
- static unsigned long __initdata required_movablecore;
- static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
-
- /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
- int movable_zone;
- EXPORT_SYMBOL(movable_zone);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
+static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+static unsigned long __initdata required_kernelcore;
+static unsigned long __initdata required_movablecore;
+static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
+
+/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
+int movable_zone;
+EXPORT_SYMBOL(movable_zone);
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
current->comm, page_to_pfn(page));
dump_page(page);
+ print_modules();
dump_stack();
out:
/* Leave bad fields for debug, except PageBuddy could make trouble */
*
* The remaining PAGE_SIZE pages are called "tail pages".
*
- * All pages have PG_compound set. All pages have their ->private pointing at
- * the head page (even the head page has this).
+ * All pages have PG_compound set. All tail pages have their ->first_page
+ * pointing at the head page.
*
* The first tail page's ->lru.next holds the address of the compound page's
* put_page() function. Its ->lru.prev holds the order of allocation.
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
-
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
clear_highpage(page + i);
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
+unsigned int _debug_guardpage_minorder;
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+ unsigned long res;
+
+ if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
+ printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+ return 0;
+ }
+ _debug_guardpage_minorder = res;
+ printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+ return 0;
+}
+__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
+
+static inline void set_page_guard_flag(struct page *page)
+{
+ __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+
+static inline void clear_page_guard_flag(struct page *page)
+{
+ __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline void set_page_guard_flag(struct page *page) { }
+static inline void clear_page_guard_flag(struct page *page) { }
+#endif
+
static inline void set_page_order(struct page *page, int order)
{
set_page_private(page, order);
if (page_zone_id(page) != page_zone_id(buddy))
return 0;
+ if (page_is_guard(buddy) && page_order(buddy) == order) {
+ VM_BUG_ON(page_count(buddy) != 0);
+ return 1;
+ }
+
if (PageBuddy(buddy) && page_order(buddy) == order) {
VM_BUG_ON(page_count(buddy) != 0);
return 1;
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
break;
-
- /* Our buddy is free, merge with it and move up one order. */
- list_del(&buddy->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(buddy);
+ /*
+ * 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)) {
+ clear_page_guard_flag(buddy);
+ set_page_private(page, 0);
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+ } else {
+ list_del(&buddy->lru);
+ zone->free_area[order].nr_free--;
+ rmv_page_order(buddy);
+ }
combined_idx = buddy_idx & page_idx;
page = page + (combined_idx - page_idx);
page_idx = combined_idx;
int i;
int bad = 0;
- trace_mm_page_free_direct(page, order);
+#ifdef CONFIG_XEN
+ if (PageForeign(page)) {
+ PageForeignDestructor(page, order);
+ return false;
+ }
+#endif
+
+ trace_mm_page_free(page, order);
kmemcheck_free_shadow(page, order);
if (PageAnon(page))
unsigned long flags;
int wasMlocked = __TestClearPageMlocked(page);
+#ifdef CONFIG_XEN
+ WARN_ON(PageForeign(page) && wasMlocked);
+#endif
if (!free_pages_prepare(page, order))
return;
local_irq_restore(flags);
}
-/*
- * permit the bootmem allocator to evade page validation on high-order frees
- */
void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
{
- if (order == 0) {
- __ClearPageReserved(page);
- set_page_count(page, 0);
- set_page_refcounted(page);
- __free_page(page);
- } else {
- int loop;
+ unsigned int nr_pages = 1 << order;
+ unsigned int loop;
- prefetchw(page);
- for (loop = 0; loop < BITS_PER_LONG; loop++) {
- struct page *p = &page[loop];
-
- if (loop + 1 < BITS_PER_LONG)
- prefetchw(p + 1);
- __ClearPageReserved(p);
- set_page_count(p, 0);
- }
+ prefetchw(page);
+ for (loop = 0; loop < nr_pages; loop++) {
+ struct page *p = &page[loop];
- set_page_refcounted(page);
- __free_pages(page, order);
+ if (loop + 1 < nr_pages)
+ prefetchw(p + 1);
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
}
+
+ set_page_refcounted(page);
+ __free_pages(page, order);
}
high--;
size >>= 1;
VM_BUG_ON(bad_range(zone, &page[size]));
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ if (high < debug_guardpage_minorder()) {
+ /*
+ * Mark as guard pages (or page), that will allow to
+ * merge back to allocator when buddy will be freed.
+ * Corresponding page table entries will not be touched,
+ * pages will stay not present in virtual address space
+ */
+ INIT_LIST_HEAD(&page[size].lru);
+ set_page_guard_flag(&page[size]);
+ set_page_private(&page[size], high);
+ /* Guard pages are not available for any usage */
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << high));
+ continue;
+ }
+#endif
list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
* If breaking a large block of pages, move all free
* pages to the preferred allocation list. If falling
* back for a reclaimable kernel allocation, be more
- * agressive about taking ownership of free pages
+ * aggressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
start_migratetype == MIGRATE_RECLAIMABLE ||
}
/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
*/
void drain_all_pages(void)
{
- on_each_cpu(drain_local_pages, NULL, 1);
+ int cpu;
+ struct per_cpu_pageset *pcp;
+ struct zone *zone;
+
+ /*
+ * Allocate in the BSS so we wont require allocation in
+ * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+ */
+ static cpumask_t cpus_with_pcps;
+
+ /*
+ * We don't care about racing with CPU hotplug event
+ * as offline notification will cause the notified
+ * cpu to drain that CPU pcps and on_each_cpu_mask
+ * disables preemption as part of its processing
+ */
+ for_each_online_cpu(cpu) {
+ bool has_pcps = false;
+ for_each_populated_zone(zone) {
+ pcp = per_cpu_ptr(zone->pageset, cpu);
+ if (pcp->pcp.count) {
+ has_pcps = true;
+ break;
+ }
+ }
+ if (has_pcps)
+ cpumask_set_cpu(cpu, &cpus_with_pcps);
+ else
+ cpumask_clear_cpu(cpu, &cpus_with_pcps);
+ }
+ on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
}
#ifdef CONFIG_HIBERNATION
int migratetype;
int wasMlocked = __TestClearPageMlocked(page);
+#ifdef CONFIG_XEN
+ WARN_ON(PageForeign(page) && wasMlocked);
+#endif
if (!free_pages_prepare(page, 0))
return;
}
/*
+ * Free a list of 0-order pages
+ */
+void free_hot_cold_page_list(struct list_head *list, int cold)
+{
+ struct page *page, *next;
+
+ list_for_each_entry_safe(page, next, list, lru) {
+ trace_mm_page_free_batched(page, cold);
+ free_hot_cold_page(page, cold);
+ }
+}
+
+/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
* Each sub-page must be freed individually.
#ifdef CONFIG_FAIL_PAGE_ALLOC
-static struct fail_page_alloc_attr {
+static struct {
struct fault_attr attr;
u32 ignore_gfp_highmem;
u32 ignore_gfp_wait;
u32 min_order;
-
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-
- struct dentry *ignore_gfp_highmem_file;
- struct dentry *ignore_gfp_wait_file;
- struct dentry *min_order_file;
-
-#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
-
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_gfp_wait = 1,
static int __init fail_page_alloc_debugfs(void)
{
- mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+ umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
- int err;
-
- err = init_fault_attr_dentries(&fail_page_alloc.attr,
- "fail_page_alloc");
- if (err)
- return err;
- dir = fail_page_alloc.attr.dentries.dir;
-
- fail_page_alloc.ignore_gfp_wait_file =
- debugfs_create_bool("ignore-gfp-wait", mode, dir,
- &fail_page_alloc.ignore_gfp_wait);
-
- fail_page_alloc.ignore_gfp_highmem_file =
- debugfs_create_bool("ignore-gfp-highmem", mode, dir,
- &fail_page_alloc.ignore_gfp_highmem);
- fail_page_alloc.min_order_file =
- debugfs_create_u32("min-order", mode, dir,
- &fail_page_alloc.min_order);
-
- if (!fail_page_alloc.ignore_gfp_wait_file ||
- !fail_page_alloc.ignore_gfp_highmem_file ||
- !fail_page_alloc.min_order_file) {
- err = -ENOMEM;
- debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
- debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
- debugfs_remove(fail_page_alloc.min_order_file);
- cleanup_fault_attr_dentries(&fail_page_alloc.attr);
- }
- return err;
+ 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_wait))
+ 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);
+
+ return -ENOMEM;
}
late_initcall(fail_page_alloc_debugfs);
long min = mark;
int o;
- free_pages -= (1 << order) + 1;
+ free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (alloc_flags & ALLOC_HARDER)
set_bit(i, zlc->fullzones);
}
+/*
+ * clear all zones full, called after direct reclaim makes progress so that
+ * a zone that was recently full is not skipped over for up to a second
+ */
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+ struct zonelist_cache *zlc; /* cached zonelist speedup info */
+
+ zlc = zonelist->zlcache_ptr;
+ if (!zlc)
+ return;
+
+ bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+}
+
#else /* CONFIG_NUMA */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
+
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+}
#endif /* CONFIG_NUMA */
/*
continue;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
- goto try_next_zone;
+ continue;
+ /*
+ * When allocating a page cache page for writing, we
+ * want to get it from a zone that is within its dirty
+ * limit, such that no single zone holds more than its
+ * proportional share of globally allowed dirty pages.
+ * The dirty limits take into account the zone's
+ * lowmem reserves and high watermark so that kswapd
+ * should be able to balance it without having to
+ * write pages from its LRU list.
+ *
+ * This may look like it could increase pressure on
+ * lower zones by failing allocations in higher zones
+ * before they are full. But the pages that do spill
+ * over are limited as the lower zones are protected
+ * by this very same mechanism. It should not become
+ * a practical burden to them.
+ *
+ * XXX: For now, allow allocations to potentially
+ * exceed the per-zone dirty limit in the slowpath
+ * (ALLOC_WMARK_LOW unset) before going into reclaim,
+ * which is important when on a NUMA setup the allowed
+ * zones are together not big enough to reach the
+ * global limit. The proper fix for these situations
+ * will require awareness of zones in the
+ * dirty-throttling and the flusher threads.
+ */
+ if ((alloc_flags & ALLOC_WMARK_LOW) &&
+ (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+ goto this_zone_full;
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
classzone_idx, alloc_flags))
goto try_this_zone;
+ if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+ /*
+ * we do zlc_setup if there are multiple nodes
+ * and before considering the first zone allowed
+ * by the cpuset.
+ */
+ allowednodes = zlc_setup(zonelist, alloc_flags);
+ zlc_active = 1;
+ did_zlc_setup = 1;
+ }
+
if (zone_reclaim_mode == 0)
goto this_zone_full;
+ /*
+ * As we may have just activated ZLC, check if the first
+ * eligible zone has failed zone_reclaim recently.
+ */
+ if (NUMA_BUILD && zlc_active &&
+ !zlc_zone_worth_trying(zonelist, z, allowednodes))
+ continue;
+
ret = zone_reclaim(zone, gfp_mask, order);
switch (ret) {
case ZONE_RECLAIM_NOSCAN:
/* did not scan */
- goto try_next_zone;
+ continue;
case ZONE_RECLAIM_FULL:
/* scanned but unreclaimable */
- goto this_zone_full;
+ continue;
default:
/* did we reclaim enough */
if (!zone_watermark_ok(zone, order, mark,
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
-try_next_zone:
- if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
- /*
- * we do zlc_setup after the first zone is tried but only
- * if there are multiple nodes make it worthwhile
- */
- allowednodes = zlc_setup(zonelist, alloc_flags);
- zlc_active = 1;
- did_zlc_setup = 1;
- }
}
if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
return ret;
}
+static DEFINE_RATELIMIT_STATE(nopage_rs,
+ DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
+
+void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
+{
+ unsigned int filter = SHOW_MEM_FILTER_NODES;
+
+ if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+ debug_guardpage_minorder() > 0)
+ return;
+
+ /*
+ * This documents exceptions given to allocations in certain
+ * contexts that are allowed to allocate outside current's set
+ * of allowed nodes.
+ */
+ if (!(gfp_mask & __GFP_NOMEMALLOC))
+ if (test_thread_flag(TIF_MEMDIE) ||
+ (current->flags & (PF_MEMALLOC | PF_EXITING)))
+ filter &= ~SHOW_MEM_FILTER_NODES;
+ if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
+ filter &= ~SHOW_MEM_FILTER_NODES;
+
+ if (fmt) {
+ struct va_format vaf;
+ va_list args;
+
+ va_start(args, fmt);
+
+ vaf.fmt = fmt;
+ vaf.va = &args;
+
+ pr_warn("%pV", &vaf);
+
+ va_end(args);
+ }
+
+ if (!(gfp_mask & __GFP_WAIT)) {
+ pr_info("The following is only an harmless informational message.\n");
+ pr_info("Unless you get a _continuous_flood_ of these messages it means\n");
+ pr_info("everything is working fine. Allocations from irqs cannot be\n");
+ pr_info("perfectly reliable and the kernel is designed to handle that.\n");
+ }
+ pr_info("%s: page allocation failure. order:%d, mode:0x%x\n",
+ current->comm, order, gfp_mask);
+
+ dump_stack();
+ if (!should_suppress_show_mem())
+ show_mem(filter);
+}
+
static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+ unsigned long did_some_progress,
unsigned long pages_reclaimed)
{
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
return 0;
+ /* Always retry if specifically requested */
+ if (gfp_mask & __GFP_NOFAIL)
+ return 1;
+
+ /*
+ * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+ * making forward progress without invoking OOM. Suspend also disables
+ * storage devices so kswapd will not help. Bail if we are suspending.
+ */
+ if (!did_some_progress && pm_suspended_storage())
+ return 0;
+
/*
* In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
* means __GFP_NOFAIL, but that may not be true in other
if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
return 1;
- /*
- * Don't let big-order allocations loop unless the caller
- * explicitly requests that.
- */
- if (gfp_mask & __GFP_NOFAIL)
- return 1;
-
return 0;
}
goto out;
}
/* Exhausted what can be done so it's blamo time */
- out_of_memory(zonelist, gfp_mask, order, nodemask);
+ out_of_memory(zonelist, gfp_mask, order, nodemask, false);
out:
clear_zonelist_oom(zonelist, gfp_mask);
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
struct page *page;
- if (!order || compaction_deferred(preferred_zone))
+ if (!order)
return NULL;
+ if (compaction_deferred(preferred_zone, order)) {
+ *deferred_compaction = true;
+ return NULL;
+ }
+
current->flags |= PF_MEMALLOC;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
nodemask, sync_migration);
if (page) {
preferred_zone->compact_considered = 0;
preferred_zone->compact_defer_shift = 0;
+ if (order >= preferred_zone->compact_order_failed)
+ preferred_zone->compact_order_failed = order + 1;
count_vm_event(COMPACTSUCCESS);
return page;
}
* but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
- defer_compaction(preferred_zone);
+
+ /*
+ * As async compaction considers a subset of pageblocks, only
+ * defer if the failure was a sync compaction failure.
+ */
+ if (sync_migration)
+ defer_compaction(preferred_zone, order);
cond_resched();
}
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
return NULL;
}
if (unlikely(!(*did_some_progress)))
return NULL;
+ /* After successful reclaim, reconsider all zones for allocation */
+ if (NUMA_BUILD)
+ zlc_clear_zones_full(zonelist);
+
retry:
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx,
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
bool sync_migration = false;
+ bool deferred_compaction = false;
/*
* In the slowpath, we sanity check order to avoid ever trying to
first_zones_zonelist(zonelist, high_zoneidx, NULL,
&preferred_zone);
+rebalance:
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
if (page)
goto got_pg;
-rebalance:
/* Allocate without watermarks if the context allows */
if (alloc_flags & ALLOC_NO_WATERMARKS) {
page = __alloc_pages_high_priority(gfp_mask, order,
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
- sync_migration = !(gfp_mask & __GFP_NO_KSWAPD);
+ sync_migration = true;
+
+ /*
+ * If compaction is deferred for high-order allocations, it is because
+ * sync compaction recently failed. In this is the case and the caller
+ * has requested the system not be heavily disrupted, fail the
+ * allocation now instead of entering direct reclaim
+ */
+ if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+ goto nopage;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
if (oom_killer_disabled)
goto nopage;
+ /* Coredumps can quickly deplete all memory reserves */
+ if ((current->flags & PF_DUMPCORE) &&
+ !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
page = __alloc_pages_may_oom(gfp_mask, order,
zonelist, high_zoneidx,
nodemask, preferred_zone,
/* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
- if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+ if (should_alloc_retry(gfp_mask, order, did_some_progress,
+ pages_reclaimed)) {
/* Wait for some write requests to complete then retry */
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
goto rebalance;
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
}
nopage:
- if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
- unsigned int filter = SHOW_MEM_FILTER_NODES;
-
- /*
- * This documents exceptions given to allocations in certain
- * contexts that are allowed to allocate outside current's set
- * of allowed nodes.
- */
- if (!(gfp_mask & __GFP_NOMEMALLOC))
- if (test_thread_flag(TIF_MEMDIE) ||
- (current->flags & (PF_MEMALLOC | PF_EXITING)))
- filter &= ~SHOW_MEM_FILTER_NODES;
- if (in_interrupt() || !wait)
- filter &= ~SHOW_MEM_FILTER_NODES;
-
- if (!wait) {
- pr_info("The following is only an harmless informational message.\n");
- pr_info("Unless you get a _continuous_flood_ of these messages it means\n");
- pr_info("everything is working fine. Allocations from irqs cannot be\n");
- pr_info("perfectly reliable and the kernel is designed to handle that.\n");
- }
- pr_info("%s: page allocation failure. order:%d, mode:0x%x\n",
- current->comm, order, gfp_mask);
- dump_stack();
- if (!should_suppress_show_mem())
- show_mem(filter);
- }
+ warn_alloc_failed(gfp_mask, order, NULL);
return page;
got_pg:
if (kmemcheck_enabled)
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zone *preferred_zone;
- struct page *page;
+ struct page *page = NULL;
int migratetype = allocflags_to_migratetype(gfp_mask);
+ unsigned int cpuset_mems_cookie;
gfp_mask &= gfp_allowed_mask;
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
- get_mems_allowed();
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+
/* The preferred zone is used for statistics later */
first_zones_zonelist(zonelist, high_zoneidx,
nodemask ? : &cpuset_current_mems_allowed,
&preferred_zone);
- if (!preferred_zone) {
- put_mems_allowed();
- return NULL;
- }
+ if (!preferred_zone)
+ goto out;
/* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
page = __alloc_pages_slowpath(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
- put_mems_allowed();
trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+ /*
+ * 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(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
}
EXPORT_SYMBOL(get_zeroed_page);
-void __pagevec_free(struct pagevec *pvec)
-{
- int i = pagevec_count(pvec);
-
- while (--i >= 0) {
- trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
- free_hot_cold_page(pvec->pages[i], pvec->cold);
- }
-}
-
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
EXPORT_SYMBOL(free_pages);
+static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size)
+{
+ if (addr) {
+ unsigned long alloc_end = addr + (PAGE_SIZE << order);
+ unsigned long used = addr + PAGE_ALIGN(size);
+
+ split_page(virt_to_page((void *)addr), order);
+ while (used < alloc_end) {
+ free_page(used);
+ used += PAGE_SIZE;
+ }
+ }
+ return (void *)addr;
+}
+
/**
* alloc_pages_exact - allocate an exact number physically-contiguous pages.
* @size: the number of bytes to allocate
unsigned long addr;
addr = __get_free_pages(gfp_mask, order);
- if (addr) {
- unsigned long alloc_end = addr + (PAGE_SIZE << order);
- unsigned long used = addr + PAGE_ALIGN(size);
-
- split_page(virt_to_page((void *)addr), order);
- while (used < alloc_end) {
- free_page(used);
- used += PAGE_SIZE;
- }
- }
-
- return (void *)addr;
+ return make_alloc_exact(addr, order, size);
}
EXPORT_SYMBOL(alloc_pages_exact);
/**
+ * alloc_pages_exact_nid - allocate an exact number of physically-contiguous
+ * pages on a node.
+ * @nid: the preferred node ID where memory should be allocated
+ * @size: the number of bytes to allocate
+ * @gfp_mask: GFP flags for the allocation
+ *
+ * Like alloc_pages_exact(), but try to allocate on node nid first before falling
+ * back.
+ * Note this is not alloc_pages_exact_node() which allocates on a specific node,
+ * but is not exact.
+ */
+void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
+{
+ unsigned order = get_order(size);
+ struct page *p = alloc_pages_node(nid, gfp_mask, order);
+ if (!p)
+ return NULL;
+ return make_alloc_exact((unsigned long)page_address(p), order, size);
+}
+EXPORT_SYMBOL(alloc_pages_exact_nid);
+
+/**
* free_pages_exact - release memory allocated via alloc_pages_exact()
* @virt: the value returned by alloc_pages_exact.
* @size: size of allocation, same value as passed to alloc_pages_exact().
#endif
/*
- * Determine whether the zone's node should be displayed or not, depending on
- * whether SHOW_MEM_FILTER_NODES was passed to __show_free_areas().
+ * Determine whether the node should be displayed or not, depending on whether
+ * SHOW_MEM_FILTER_NODES was passed to show_free_areas().
*/
-static bool skip_free_areas_zone(unsigned int flags, const struct zone *zone)
+bool skip_free_areas_node(unsigned int flags, int nid)
{
bool ret = false;
+ unsigned int cpuset_mems_cookie;
if (!(flags & SHOW_MEM_FILTER_NODES))
goto out;
- get_mems_allowed();
- ret = !node_isset(zone->zone_pgdat->node_id,
- cpuset_current_mems_allowed);
- put_mems_allowed();
+ do {
+ cpuset_mems_cookie = get_mems_allowed();
+ ret = !node_isset(nid, cpuset_current_mems_allowed);
+ } while (!put_mems_allowed(cpuset_mems_cookie));
out:
return ret;
}
* Suppresses nodes that are not allowed by current's cpuset if
* SHOW_MEM_FILTER_NODES is passed.
*/
-void __show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter)
{
int cpu;
struct zone *zone;
for_each_populated_zone(zone) {
- if (skip_free_areas_zone(filter, zone))
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
show_node(zone);
printk("%s per-cpu:\n", zone->name);
for_each_populated_zone(zone) {
int i;
- if (skip_free_areas_zone(filter, zone))
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
show_node(zone);
printk("%s"
for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
- if (skip_free_areas_zone(filter, zone))
+ if (skip_free_areas_node(filter, zone_to_nid(zone)))
continue;
show_node(zone);
printk("%s: ", zone->name);
show_swap_cache_info();
}
-void show_free_areas(void)
-{
- __show_free_areas(0);
-}
-
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
* Called with zonelists_mutex held always
* unless system_state == SYSTEM_BOOTING.
*/
-void build_all_zonelists(void *data)
+void __ref build_all_zonelists(void *data)
{
set_zonelist_order();
#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
/*
+ * Check if a pageblock contains reserved pages
+ */
+static int pageblock_is_reserved(unsigned long start_pfn, unsigned long end_pfn)
+{
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ if (!pfn_valid_within(pfn) || PageReserved(pfn_to_page(pfn)))
+ return 1;
+ }
+ return 0;
+}
+
+/*
* Mark a number of pageblocks as MIGRATE_RESERVE. The number
* of blocks reserved is based on min_wmark_pages(zone). The memory within
* the reserve will tend to store contiguous free pages. Setting min_free_kbytes
*/
static void setup_zone_migrate_reserve(struct zone *zone)
{
- unsigned long start_pfn, pfn, end_pfn;
+ unsigned long start_pfn, pfn, end_pfn, block_end_pfn;
struct page *page;
unsigned long block_migratetype;
int reserve;
- /* Get the start pfn, end pfn and the number of blocks to reserve */
+ /*
+ * Get the start pfn, end pfn and the number of blocks to reserve
+ * We have to be careful to be aligned to pageblock_nr_pages to
+ * make sure that we always check pfn_valid for the first page in
+ * the block.
+ */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
+ start_pfn = roundup(start_pfn, pageblock_nr_pages);
reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
if (page_to_nid(page) != zone_to_nid(zone))
continue;
- /* Blocks with reserved pages will never free, skip them. */
- if (PageReserved(page))
- continue;
-
block_migratetype = get_pageblock_migratetype(page);
- /* If this block is reserved, account for it */
- if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
- reserve--;
- continue;
- }
+ /* Only test what is necessary when the reserves are not met */
+ if (reserve > 0) {
+ /*
+ * Blocks with reserved pages will never free, skip
+ * them.
+ */
+ block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+ if (pageblock_is_reserved(pfn, block_end_pfn))
+ continue;
- /* Suitable for reserving if this block is movable */
- if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
- set_pageblock_migratetype(page, MIGRATE_RESERVE);
- move_freepages_block(zone, page, MIGRATE_RESERVE);
- reserve--;
- continue;
+ /* If this block is reserved, account for it */
+ if (block_migratetype == MIGRATE_RESERVE) {
+ reserve--;
+ continue;
+ }
+
+ /* Suitable for reserving if this block is movable */
+ if (block_migratetype == MIGRATE_MOVABLE) {
+ set_pageblock_migratetype(page,
+ MIGRATE_RESERVE);
+ move_freepages_block(zone, page,
+ MIGRATE_RESERVE);
+ reserve--;
+ continue;
+ }
}
/*
pcp->batch = PAGE_SHIFT * 8;
}
-static __meminit void setup_zone_pageset(struct zone *zone)
+static void setup_zone_pageset(struct zone *zone)
{
int cpu;
if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
- alloc_bootmem_node(pgdat, alloc_size);
+ alloc_bootmem_node_nopanic(pgdat, alloc_size);
} else {
/*
* This case means that a zone whose size was 0 gets new memory
return 0;
}
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
-/*
- * Basic iterator support. Return the first range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns first region regardless of node
- */
-static int __meminit first_active_region_index_in_nid(int nid)
-{
- int i;
-
- for (i = 0; i < nr_nodemap_entries; i++)
- if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
- return i;
-
- return -1;
-}
-
-/*
- * Basic iterator support. Return the next active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardless of node
- */
-static int __meminit next_active_region_index_in_nid(int index, int nid)
-{
- for (index = index + 1; index < nr_nodemap_entries; index++)
- if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
- return index;
-
- return -1;
-}
-
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
/*
* Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
*/
int __meminit __early_pfn_to_nid(unsigned long pfn)
{
- int i;
-
- for (i = 0; i < nr_nodemap_entries; i++) {
- unsigned long start_pfn = early_node_map[i].start_pfn;
- unsigned long end_pfn = early_node_map[i].end_pfn;
+ unsigned long start_pfn, end_pfn;
+ int i, nid;
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
if (start_pfn <= pfn && pfn < end_pfn)
- return early_node_map[i].nid;
- }
+ return nid;
/* This is a memory hole */
return -1;
}
}
#endif
-/* Basic iterator support to walk early_node_map[] */
-#define for_each_active_range_index_in_nid(i, nid) \
- for (i = first_active_region_index_in_nid(nid); i != -1; \
- i = next_active_region_index_in_nid(i, nid))
-
/**
* free_bootmem_with_active_regions - Call free_bootmem_node for each active range
* @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
* add_active_ranges() contain no holes and may be freed, this
* this function may be used instead of calling free_bootmem() manually.
*/
-void __init free_bootmem_with_active_regions(int nid,
- unsigned long max_low_pfn)
-{
- int i;
-
- for_each_active_range_index_in_nid(i, nid) {
- unsigned long size_pages = 0;
- unsigned long end_pfn = early_node_map[i].end_pfn;
-
- if (early_node_map[i].start_pfn >= max_low_pfn)
- continue;
-
- if (end_pfn > max_low_pfn)
- end_pfn = max_low_pfn;
-
- size_pages = end_pfn - early_node_map[i].start_pfn;
- free_bootmem_node(NODE_DATA(early_node_map[i].nid),
- PFN_PHYS(early_node_map[i].start_pfn),
- size_pages << PAGE_SHIFT);
- }
-}
-
-#ifdef CONFIG_HAVE_MEMBLOCK
-/*
- * Basic iterator support. Return the last range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns last region regardless of node
- */
-static int __meminit last_active_region_index_in_nid(int nid)
-{
- int i;
-
- for (i = nr_nodemap_entries - 1; i >= 0; i--)
- if (nid == MAX_NUMNODES || early_node_map[i].nid == nid)
- return i;
-
- return -1;
-}
-
-/*
- * Basic iterator support. Return the previous active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardless of node
- */
-static int __meminit previous_active_region_index_in_nid(int index, int nid)
+void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
{
- for (index = index - 1; index >= 0; index--)
- if (nid == MAX_NUMNODES || early_node_map[index].nid == nid)
- return index;
-
- return -1;
-}
-
-#define for_each_active_range_index_in_nid_reverse(i, nid) \
- for (i = last_active_region_index_in_nid(nid); i != -1; \
- i = previous_active_region_index_in_nid(i, nid))
-
-u64 __init find_memory_core_early(int nid, u64 size, u64 align,
- u64 goal, u64 limit)
-{
- int i;
-
- /* Need to go over early_node_map to find out good range for node */
- for_each_active_range_index_in_nid_reverse(i, nid) {
- u64 addr;
- u64 ei_start, ei_last;
- u64 final_start, final_end;
-
- ei_last = early_node_map[i].end_pfn;
- ei_last <<= PAGE_SHIFT;
- ei_start = early_node_map[i].start_pfn;
- ei_start <<= PAGE_SHIFT;
-
- final_start = max(ei_start, goal);
- final_end = min(ei_last, limit);
-
- if (final_start >= final_end)
- continue;
-
- addr = memblock_find_in_range(final_start, final_end, size, align);
-
- if (addr == MEMBLOCK_ERROR)
- continue;
-
- return addr;
- }
-
- return MEMBLOCK_ERROR;
-}
-#endif
+ unsigned long start_pfn, end_pfn;
+ int i, this_nid;
-int __init add_from_early_node_map(struct range *range, int az,
- int nr_range, int nid)
-{
- int i;
- u64 start, end;
+ for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) {
+ start_pfn = min(start_pfn, max_low_pfn);
+ end_pfn = min(end_pfn, max_low_pfn);
- /* need to go over early_node_map to find out good range for node */
- for_each_active_range_index_in_nid(i, nid) {
- start = early_node_map[i].start_pfn;
- end = early_node_map[i].end_pfn;
- nr_range = add_range(range, az, nr_range, start, end);
+ if (start_pfn < end_pfn)
+ free_bootmem_node(NODE_DATA(this_nid),
+ PFN_PHYS(start_pfn),
+ (end_pfn - start_pfn) << PAGE_SHIFT);
}
- return nr_range;
}
-void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
-{
- int i;
- int ret;
-
- for_each_active_range_index_in_nid(i, nid) {
- ret = work_fn(early_node_map[i].start_pfn,
- early_node_map[i].end_pfn, data);
- if (ret)
- break;
- }
-}
/**
* sparse_memory_present_with_active_regions - Call memory_present for each active range
* @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
*/
void __init sparse_memory_present_with_active_regions(int nid)
{
- int i;
+ unsigned long start_pfn, end_pfn;
+ int i, this_nid;
- for_each_active_range_index_in_nid(i, nid)
- memory_present(early_node_map[i].nid,
- early_node_map[i].start_pfn,
- early_node_map[i].end_pfn);
+ for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
+ memory_present(this_nid, start_pfn, end_pfn);
}
/**
void __meminit get_pfn_range_for_nid(unsigned int nid,
unsigned long *start_pfn, unsigned long *end_pfn)
{
+ unsigned long this_start_pfn, this_end_pfn;
int i;
+
*start_pfn = -1UL;
*end_pfn = 0;
- for_each_active_range_index_in_nid(i, nid) {
- *start_pfn = min(*start_pfn, early_node_map[i].start_pfn);
- *end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
+ for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
+ *start_pfn = min(*start_pfn, this_start_pfn);
+ *end_pfn = max(*end_pfn, this_end_pfn);
}
if (*start_pfn == -1UL)
/*
* The zone ranges provided by the architecture do not include ZONE_MOVABLE
- * because it is sized independant of architecture. Unlike the other zones,
+ * because it is sized independent of architecture. Unlike the other zones,
* the starting point for ZONE_MOVABLE is not fixed. It may be different
* in each node depending on the size of each node and how evenly kernelcore
* is distributed. This helper function adjusts the zone ranges
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
- int i = 0;
- unsigned long prev_end_pfn = 0, hole_pages = 0;
- unsigned long start_pfn;
-
- /* Find the end_pfn of the first active range of pfns in the node */
- i = first_active_region_index_in_nid(nid);
- if (i == -1)
- return 0;
-
- prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
-
- /* Account for ranges before physical memory on this node */
- if (early_node_map[i].start_pfn > range_start_pfn)
- hole_pages = prev_end_pfn - range_start_pfn;
-
- /* Find all holes for the zone within the node */
- for (; i != -1; i = next_active_region_index_in_nid(i, nid)) {
-
- /* No need to continue if prev_end_pfn is outside the zone */
- if (prev_end_pfn >= range_end_pfn)
- break;
-
- /* Make sure the end of the zone is not within the hole */
- start_pfn = min(early_node_map[i].start_pfn, range_end_pfn);
- prev_end_pfn = max(prev_end_pfn, range_start_pfn);
+ unsigned long nr_absent = range_end_pfn - range_start_pfn;
+ unsigned long start_pfn, end_pfn;
+ int i;
- /* Update the hole size cound and move on */
- if (start_pfn > range_start_pfn) {
- BUG_ON(prev_end_pfn > start_pfn);
- hole_pages += start_pfn - prev_end_pfn;
- }
- prev_end_pfn = early_node_map[i].end_pfn;
+ for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+ start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
+ end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
+ nr_absent -= end_pfn - start_pfn;
}
-
- /* Account for ranges past physical memory on this node */
- if (range_end_pfn > prev_end_pfn)
- hole_pages += range_end_pfn -
- max(range_start_pfn, prev_end_pfn);
-
- return hole_pages;
+ return nr_absent;
}
/**
unsigned long zone_type,
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];
unsigned long node_start_pfn, node_end_pfn;
unsigned long zone_start_pfn, zone_end_pfn;
get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn);
- zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type],
- node_start_pfn);
- zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type],
- node_end_pfn);
+ 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,
return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
}
-#else
+#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
unsigned long zone_type,
unsigned long *zones_size)
return zholes_size[zone_type];
}
-#endif
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
unsigned long usemapsize = usemap_size(zonesize);
zone->pageblock_flags = NULL;
if (usemapsize)
- zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
+ zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
+ usemapsize);
}
#else
static inline void setup_usemap(struct pglist_data *pgdat,
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, memmap_pages;
- enum lru_list l;
+ enum lru_list lru;
size = zone_spanned_pages_in_node(nid, j, zones_size);
realsize = size - zone_absent_pages_in_node(nid, j,
zone->zone_pgdat = pgdat;
zone_pcp_init(zone);
- for_each_lru(l) {
- INIT_LIST_HEAD(&zone->lru[l].list);
- zone->reclaim_stat.nr_saved_scan[l] = 0;
- }
+ for_each_lru(lru)
+ INIT_LIST_HEAD(&zone->lruvec.lists[lru]);
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
zone->reclaim_stat.recent_scanned[0] = 0;
size = (end - start) * sizeof(struct page);
map = alloc_remap(pgdat->node_id, size);
if (!map)
- map = alloc_bootmem_node(pgdat, size);
+ map = alloc_bootmem_node_nopanic(pgdat, size);
pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
*/
if (pgdat == NODE_DATA(0)) {
mem_map = NODE_DATA(0)->node_mem_map;
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
free_area_init_core(pgdat, zones_size, zholes_size);
}
-#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
#if MAX_NUMNODES > 1
/*
#endif
/**
- * add_active_range - Register a range of PFNs backed by physical memory
- * @nid: The node ID the range resides on
- * @start_pfn: The start PFN of the available physical memory
- * @end_pfn: The end PFN of the available physical memory
+ * node_map_pfn_alignment - determine the maximum internode alignment
+ *
+ * This function should be called after node map is populated and sorted.
+ * It calculates the maximum power of two alignment which can distinguish
+ * all the nodes.
+ *
+ * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
+ * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the
+ * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is
+ * shifted, 1GiB is enough and this function will indicate so.
*
- * These ranges are stored in an early_node_map[] and later used by
- * free_area_init_nodes() to calculate zone sizes and holes. If the
- * range spans a memory hole, it is up to the architecture to ensure
- * the memory is not freed by the bootmem allocator. If possible
- * the range being registered will be merged with existing ranges.
+ * This is used to test whether pfn -> nid mapping of the chosen memory
+ * model has fine enough granularity to avoid incorrect mapping for the
+ * populated node map.
+ *
+ * Returns the determined alignment in pfn's. 0 if there is no alignment
+ * requirement (single node).
*/
-void __init add_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn)
+unsigned long __init node_map_pfn_alignment(void)
{
- int i;
-
- mminit_dprintk(MMINIT_TRACE, "memory_register",
- "Entering add_active_range(%d, %#lx, %#lx) "
- "%d entries of %d used\n",
- nid, start_pfn, end_pfn,
- nr_nodemap_entries, MAX_ACTIVE_REGIONS);
-
- mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
+ unsigned long accl_mask = 0, last_end = 0;
+ unsigned long start, end, mask;
+ int last_nid = -1;
+ int i, nid;
- /* Merge with existing active regions if possible */
- for (i = 0; i < nr_nodemap_entries; i++) {
- if (early_node_map[i].nid != nid)
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
+ if (!start || last_nid < 0 || last_nid == nid) {
+ last_nid = nid;
+ last_end = end;
continue;
-
- /* Skip if an existing region covers this new one */
- if (start_pfn >= early_node_map[i].start_pfn &&
- end_pfn <= early_node_map[i].end_pfn)
- return;
-
- /* Merge forward if suitable */
- if (start_pfn <= early_node_map[i].end_pfn &&
- end_pfn > early_node_map[i].end_pfn) {
- early_node_map[i].end_pfn = end_pfn;
- return;
}
- /* Merge backward if suitable */
- if (start_pfn < early_node_map[i].start_pfn &&
- end_pfn >= early_node_map[i].start_pfn) {
- early_node_map[i].start_pfn = start_pfn;
- return;
- }
- }
+ /*
+ * Start with a mask granular enough to pin-point to the
+ * start pfn and tick off bits one-by-one until it becomes
+ * too coarse to separate the current node from the last.
+ */
+ mask = ~((1 << __ffs(start)) - 1);
+ while (mask && last_end <= (start & (mask << 1)))
+ mask <<= 1;
- /* Check that early_node_map is large enough */
- if (i >= MAX_ACTIVE_REGIONS) {
- printk(KERN_CRIT "More than %d memory regions, truncating\n",
- MAX_ACTIVE_REGIONS);
- return;
+ /* accumulate all internode masks */
+ accl_mask |= mask;
}
- early_node_map[i].nid = nid;
- early_node_map[i].start_pfn = start_pfn;
- early_node_map[i].end_pfn = end_pfn;
- nr_nodemap_entries = i + 1;
-}
-
-/**
- * remove_active_range - Shrink an existing registered range of PFNs
- * @nid: The node id the range is on that should be shrunk
- * @start_pfn: The new PFN of the range
- * @end_pfn: The new PFN of the range
- *
- * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept near the end physical page range that has already been
- * registered. This function allows an arch to shrink an existing registered
- * range.
- */
-void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
- unsigned long end_pfn)
-{
- int i, j;
- int removed = 0;
-
- printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
- nid, start_pfn, end_pfn);
-
- /* Find the old active region end and shrink */
- for_each_active_range_index_in_nid(i, nid) {
- if (early_node_map[i].start_pfn >= start_pfn &&
- early_node_map[i].end_pfn <= end_pfn) {
- /* clear it */
- early_node_map[i].start_pfn = 0;
- early_node_map[i].end_pfn = 0;
- removed = 1;
- continue;
- }
- if (early_node_map[i].start_pfn < start_pfn &&
- early_node_map[i].end_pfn > start_pfn) {
- unsigned long temp_end_pfn = early_node_map[i].end_pfn;
- early_node_map[i].end_pfn = start_pfn;
- if (temp_end_pfn > end_pfn)
- add_active_range(nid, end_pfn, temp_end_pfn);
- continue;
- }
- if (early_node_map[i].start_pfn >= start_pfn &&
- early_node_map[i].end_pfn > end_pfn &&
- early_node_map[i].start_pfn < end_pfn) {
- early_node_map[i].start_pfn = end_pfn;
- continue;
- }
- }
-
- if (!removed)
- return;
-
- /* remove the blank ones */
- for (i = nr_nodemap_entries - 1; i > 0; i--) {
- if (early_node_map[i].nid != nid)
- continue;
- if (early_node_map[i].end_pfn)
- continue;
- /* we found it, get rid of it */
- for (j = i; j < nr_nodemap_entries - 1; j++)
- memcpy(&early_node_map[j], &early_node_map[j+1],
- sizeof(early_node_map[j]));
- j = nr_nodemap_entries - 1;
- memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
- nr_nodemap_entries--;
- }
-}
-
-/**
- * remove_all_active_ranges - Remove all currently registered regions
- *
- * During discovery, it may be found that a table like SRAT is invalid
- * and an alternative discovery method must be used. This function removes
- * all currently registered regions.
- */
-void __init remove_all_active_ranges(void)
-{
- memset(early_node_map, 0, sizeof(early_node_map));
- nr_nodemap_entries = 0;
-}
-
-/* Compare two active node_active_regions */
-static int __init cmp_node_active_region(const void *a, const void *b)
-{
- struct node_active_region *arange = (struct node_active_region *)a;
- struct node_active_region *brange = (struct node_active_region *)b;
-
- /* Done this way to avoid overflows */
- if (arange->start_pfn > brange->start_pfn)
- return 1;
- if (arange->start_pfn < brange->start_pfn)
- return -1;
-
- return 0;
-}
-
-/* sort the node_map by start_pfn */
-void __init sort_node_map(void)
-{
- sort(early_node_map, (size_t)nr_nodemap_entries,
- sizeof(struct node_active_region),
- cmp_node_active_region, NULL);
+ /* convert mask to number of pages */
+ return ~accl_mask + 1;
}
/* Find the lowest pfn for a node */
static unsigned long __init find_min_pfn_for_node(int nid)
{
- int i;
unsigned long min_pfn = ULONG_MAX;
+ unsigned long start_pfn;
+ int i;
- /* Assuming a sorted map, the first range found has the starting pfn */
- for_each_active_range_index_in_nid(i, nid)
- min_pfn = min(min_pfn, early_node_map[i].start_pfn);
+ for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL)
+ min_pfn = min(min_pfn, start_pfn);
if (min_pfn == ULONG_MAX) {
printk(KERN_WARNING
*/
static unsigned long __init early_calculate_totalpages(void)
{
- int i;
unsigned long totalpages = 0;
+ unsigned long start_pfn, end_pfn;
+ int i, nid;
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+ unsigned long pages = end_pfn - start_pfn;
- for (i = 0; i < nr_nodemap_entries; i++) {
- unsigned long pages = early_node_map[i].end_pfn -
- early_node_map[i].start_pfn;
totalpages += pages;
if (pages)
- node_set_state(early_node_map[i].nid, N_HIGH_MEMORY);
+ node_set_state(nid, N_HIGH_MEMORY);
}
return totalpages;
}
* memory. When they don't, some nodes will have more kernelcore than
* others
*/
-static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+static void __init find_zone_movable_pfns_for_nodes(void)
{
int i, nid;
unsigned long usable_startpfn;
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
for_each_node_state(nid, N_HIGH_MEMORY) {
+ unsigned long start_pfn, end_pfn;
+
/*
* Recalculate kernelcore_node if the division per node
* now exceeds what is necessary to satisfy the requested
kernelcore_remaining = kernelcore_node;
/* Go through each range of PFNs within this node */
- for_each_active_range_index_in_nid(i, nid) {
- unsigned long start_pfn, end_pfn;
+ for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
unsigned long size_pages;
- start_pfn = max(early_node_map[i].start_pfn,
- zone_movable_pfn[nid]);
- end_pfn = early_node_map[i].end_pfn;
+ start_pfn = max(start_pfn, zone_movable_pfn[nid]);
if (start_pfn >= end_pfn)
continue;
for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
- if (zone->present_pages)
+ if (zone->present_pages) {
node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+ break;
+ }
}
#endif
}
*/
void __init free_area_init_nodes(unsigned long *max_zone_pfn)
{
- unsigned long nid;
- int i;
-
- /* Sort early_node_map as initialisation assumes it is sorted */
- sort_node_map();
+ unsigned long start_pfn, end_pfn;
+ int i, nid;
/* Record where the zone boundaries are */
memset(arch_zone_lowest_possible_pfn, 0,
/* Find the PFNs that ZONE_MOVABLE begins at in each node */
memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
- find_zone_movable_pfns_for_nodes(zone_movable_pfn);
+ find_zone_movable_pfns_for_nodes();
/* Print out the zone ranges */
printk("Zone PFN ranges:\n");
}
/* Print out the early_node_map[] */
- printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
- for (i = 0; i < nr_nodemap_entries; i++)
- printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
- early_node_map[i].start_pfn,
- early_node_map[i].end_pfn);
+ printk("Early memory PFN ranges\n");
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
+ printk(" %3d: %0#10lx -> %0#10lx\n", nid, start_pfn, end_pfn);
/* Initialise every node */
mminit_verify_pageflags_layout();
early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);
-#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
+#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
/**
* set_dma_reserve - set the specified number of pages reserved in the first zone
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+ lru_add_drain_cpu(cpu);
drain_pages(cpu);
/*
if (max > zone->present_pages)
max = zone->present_pages;
reserve_pages += max;
+ /*
+ * Lowmem reserves are not available to
+ * GFP_HIGHUSER page cache allocations and
+ * kswapd tries to balance zones to their high
+ * watermark. As a result, neither should be
+ * regarded as dirtyable memory, to prevent a
+ * situation where reclaim has to clean pages
+ * in order to balance the zones.
+ */
+ zone->dirty_balance_reserve = max;
}
}
+ dirty_balance_reserve = reserve_pages;
totalreserve_pages = reserve_pages;
}
spin_unlock_irqrestore(&zone->lock, flags);
}
+#ifdef CONFIG_XEN
+ for_each_populated_zone(zone) {
+ unsigned int cpu;
+
+ for_each_online_cpu(cpu) {
+ unsigned long high;
+
+ high = percpu_pagelist_fraction
+ ? zone->present_pages / percpu_pagelist_fraction
+ : 5 * zone_batchsize(zone);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
+ }
+ }
+#endif
+
/* update totalreserve_pages */
calculate_totalreserve_pages();
}
* 1TB 101 10GB
* 10TB 320 32GB
*/
-void calculate_zone_inactive_ratio(struct zone *zone)
+static void __meminit calculate_zone_inactive_ratio(struct zone *zone)
{
unsigned int gb, ratio;
zone->inactive_ratio = ratio;
}
-static void __init setup_per_zone_inactive_ratio(void)
+static void __meminit setup_per_zone_inactive_ratio(void)
{
struct zone *zone;
* 8192MB: 11584k
* 16384MB: 16384k
*/
-static int __init init_per_zone_wmark_min(void)
+int __meminit init_per_zone_wmark_min(void)
{
unsigned long lowmem_kbytes;
if (min_free_kbytes > 65536)
min_free_kbytes = 65536;
setup_per_zone_wmarks();
+ refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
setup_per_zone_inactive_ratio();
return 0;
int ret;
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
- if (!write || (ret == -EINVAL))
+ if (!write || (ret < 0))
return ret;
for_each_populated_zone(zone) {
for_each_possible_cpu(cpu) {
max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
do_div(max, bucketsize);
}
+ max = min(max, 0x80000000ULL);
if (numentries > max)
numentries = max;
bool is_pageblock_removable_nolock(struct page *page)
{
- struct zone *zone = page_zone(page);
+ struct zone *zone;
+ unsigned long pfn;
+
+ /*
+ * We have to be careful here because we are iterating over memory
+ * sections which are not zone aware so we might end up outside of
+ * the zone but still within the section.
+ * We have to take care about the node as well. If the node is offline
+ * its NODE_DATA will be NULL - see page_zone.
+ */
+ if (!node_online(page_to_nid(page)))
+ return false;
+
+ zone = page_zone(page);
+ pfn = page_to_pfn(page);
+ if (zone->zone_start_pfn > pfn ||
+ zone->zone_start_pfn + zone->spanned_pages <= pfn)
+ return false;
+
return __count_immobile_pages(zone, page, 0);
}
struct memory_isolate_notify arg;
int notifier_ret;
int ret = -EBUSY;
- int zone_idx;
zone = page_zone(page);
- zone_idx = zone_idx(zone);
spin_lock_irqsave(&zone->lock, flags);