#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/migrate.h>
-#include <linux/page_ext.h>
#include <linux/hugetlb.h>
#include <linux/sched/rt.h>
#include <linux/page_owner.h>
int _node_numa_mem_[MAX_NUMNODES];
#endif
+/* work_structs for global per-cpu drains */
+DEFINE_MUTEX(pcpu_drain_mutex);
+DEFINE_PER_CPU(struct work_struct, pcpu_drain);
+
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
EXPORT_SYMBOL(latent_entropy);
{
int migratetype = 0;
int batch_free = 0;
- unsigned long nr_scanned;
+ unsigned long nr_scanned, flags;
bool isolated_pageblocks;
- spin_lock(&zone->lock);
+ spin_lock_irqsave(&zone->lock, flags);
isolated_pageblocks = has_isolate_pageblock(zone);
nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
trace_mm_page_pcpu_drain(page, 0, mt);
} while (--count && --batch_free && !list_empty(list));
}
- spin_unlock(&zone->lock);
+ spin_unlock_irqrestore(&zone->lock, flags);
}
static void free_one_page(struct zone *zone,
unsigned int order,
int migratetype)
{
- unsigned long nr_scanned;
- spin_lock(&zone->lock);
+ unsigned long nr_scanned, flags;
+ spin_lock_irqsave(&zone->lock, flags);
+ __count_vm_events(PGFREE, 1 << order);
nr_scanned = node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED);
if (nr_scanned)
__mod_node_page_state(zone->zone_pgdat, NR_PAGES_SCANNED, -nr_scanned);
migratetype = get_pfnblock_migratetype(page, pfn);
}
__free_one_page(page, pfn, zone, order, migratetype);
- spin_unlock(&zone->lock);
+ spin_unlock_irqrestore(&zone->lock, flags);
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
static void __free_pages_ok(struct page *page, unsigned int order)
{
- unsigned long flags;
int migratetype;
unsigned long pfn = page_to_pfn(page);
return;
migratetype = get_pfnblock_migratetype(page, pfn);
- local_irq_save(flags);
- __count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, pfn, order, migratetype);
- local_irq_restore(flags);
}
static void __init __free_pages_boot_core(struct page *page, unsigned int order)
int migratetype, bool cold)
{
int i, alloced = 0;
+ unsigned long flags;
- spin_lock(&zone->lock);
+ spin_lock_irqsave(&zone->lock, flags);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
* pages added to the pcp list.
*/
__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
- spin_unlock(&zone->lock);
+ spin_unlock_irqrestore(&zone->lock, flags);
return alloced;
}
drain_pages(cpu);
}
+static void drain_local_pages_wq(struct work_struct *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 cpu pinned worker to an unbound one. We can operate on a different
+ * cpu which is allright but we also have to make sure to not move to
+ * a different one.
+ */
+ preempt_disable();
+ drain_local_pages(NULL);
+ preempt_enable();
+}
+
/*
* Spill all the per-cpu pages from all CPUs back into the buddy allocator.
*
* When zone parameter is non-NULL, spill just the single zone's pages.
*
- * 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().
+ * Note that this can be extremely slow as the draining happens in a workqueue.
*/
void drain_all_pages(struct zone *zone)
{
*/
static cpumask_t cpus_with_pcps;
+ /* Workqueues cannot recurse */
+ if (current->flags & PF_WQ_WORKER)
+ return;
+
+ /*
+ * Do not drain if one is already in progress unless it's specific to
+ * a zone. Such callers are primarily CMA and memory hotplug and need
+ * the drain to be complete when the call returns.
+ */
+ if (unlikely(!mutex_trylock(&pcpu_drain_mutex))) {
+ if (!zone)
+ return;
+ mutex_lock(&pcpu_drain_mutex);
+ }
+
/*
* We don't care about racing with CPU hotplug event
* as offline notification will cause the notified
else
cpumask_clear_cpu(cpu, &cpus_with_pcps);
}
- on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
- zone, 1);
+
+ for_each_cpu(cpu, &cpus_with_pcps) {
+ struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu);
+ INIT_WORK(work, drain_local_pages_wq);
+ schedule_work_on(cpu, work);
+ }
+ for_each_cpu(cpu, &cpus_with_pcps)
+ flush_work(per_cpu_ptr(&pcpu_drain, cpu));
+
+ mutex_unlock(&pcpu_drain_mutex);
}
#ifdef CONFIG_HIBERNATION
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
- unsigned long flags;
unsigned long pfn = page_to_pfn(page);
int migratetype;
+ if (in_interrupt()) {
+ __free_pages_ok(page, 0);
+ return;
+ }
+
if (!free_pcp_prepare(page))
return;
migratetype = get_pfnblock_migratetype(page, pfn);
set_pcppage_migratetype(page, migratetype);
- local_irq_save(flags);
- __count_vm_event(PGFREE);
+ preempt_disable();
/*
* We only track unmovable, reclaimable and movable on pcp lists.
migratetype = MIGRATE_MOVABLE;
}
+ __count_vm_event(PGFREE);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (!cold)
list_add(&page->lru, &pcp->lists[migratetype]);
}
out:
- local_irq_restore(flags);
+ preempt_enable();
}
/*
#endif
}
+/* Remove page from the per-cpu list, caller must protect the list */
+static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
+ bool cold, struct per_cpu_pages *pcp,
+ struct list_head *list)
+{
+ struct page *page;
+
+ VM_BUG_ON(in_interrupt());
+
+ do {
+ if (list_empty(list)) {
+ pcp->count += rmqueue_bulk(zone, 0,
+ pcp->batch, list,
+ migratetype, cold);
+ if (unlikely(list_empty(list)))
+ return NULL;
+ }
+
+ if (cold)
+ page = list_last_entry(list, struct page, lru);
+ else
+ page = list_first_entry(list, struct page, lru);
+
+ list_del(&page->lru);
+ pcp->count--;
+ } while (check_new_pcp(page));
+
+ return page;
+}
+
+/* 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)
+{
+ struct per_cpu_pages *pcp;
+ struct list_head *list;
+ bool cold = ((gfp_flags & __GFP_COLD) != 0);
+ struct page *page;
+
+ preempt_disable();
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
+ list = &pcp->lists[migratetype];
+ page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list);
+ if (page) {
+ __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
+ zone_statistics(preferred_zone, zone);
+ }
+ preempt_enable();
+ return page;
+}
+
/*
* Allocate a page from the given zone. Use pcplists for order-0 allocations.
*/
static inline
-struct page *buffered_rmqueue(struct zone *preferred_zone,
+struct page *rmqueue(struct zone *preferred_zone,
struct zone *zone, unsigned int order,
gfp_t gfp_flags, unsigned int alloc_flags,
int migratetype)
{
unsigned long flags;
struct page *page;
- bool cold = ((gfp_flags & __GFP_COLD) != 0);
-
- if (likely(order == 0)) {
- struct per_cpu_pages *pcp;
- struct list_head *list;
-
- local_irq_save(flags);
- do {
- pcp = &this_cpu_ptr(zone->pageset)->pcp;
- list = &pcp->lists[migratetype];
- if (list_empty(list)) {
- pcp->count += rmqueue_bulk(zone, 0,
- pcp->batch, list,
- migratetype, cold);
- if (unlikely(list_empty(list)))
- goto failed;
- }
-
- if (cold)
- page = list_last_entry(list, struct page, lru);
- else
- page = list_first_entry(list, struct page, lru);
- list_del(&page->lru);
- pcp->count--;
+ if (likely(order == 0) && !in_interrupt()) {
+ page = rmqueue_pcplist(preferred_zone, zone, order,
+ gfp_flags, migratetype);
+ goto out;
+ }
- } while (check_new_pcp(page));
- } else {
- /*
- * We most definitely don't want callers attempting to
- * allocate greater than order-1 page units with __GFP_NOFAIL.
- */
- WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
- spin_lock_irqsave(&zone->lock, flags);
+ /*
+ * We most definitely don't want callers attempting to
+ * allocate greater than order-1 page units with __GFP_NOFAIL.
+ */
+ WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
+ spin_lock_irqsave(&zone->lock, flags);
- do {
- page = NULL;
- if (alloc_flags & ALLOC_HARDER) {
- page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
- if (page)
- trace_mm_page_alloc_zone_locked(page, order, migratetype);
- }
- if (!page)
- page = __rmqueue(zone, order, migratetype);
- } while (page && check_new_pages(page, order));
- spin_unlock(&zone->lock);
+ do {
+ page = NULL;
+ if (alloc_flags & ALLOC_HARDER) {
+ page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
+ if (page)
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
+ }
if (!page)
- goto failed;
- __mod_zone_freepage_state(zone, -(1 << order),
- get_pcppage_migratetype(page));
- }
+ page = __rmqueue(zone, order, migratetype);
+ } while (page && check_new_pages(page, order));
+ spin_unlock(&zone->lock);
+ if (!page)
+ goto failed;
+ __mod_zone_freepage_state(zone, -(1 << order),
+ get_pcppage_migratetype(page));
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
- VM_BUG_ON_PAGE(bad_range(zone, page), page);
+out:
+ VM_BUG_ON_PAGE(page && bad_range(zone, page), page);
return page;
failed:
#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 */
}
try_this_zone:
- page = buffered_rmqueue(ac->preferred_zoneref->zone, zone, order,
+ page = rmqueue(ac->preferred_zoneref->zone, zone, order,
gfp_mask, alloc_flags, ac->migratetype);
if (page) {
prep_new_page(page, order, gfp_mask, alloc_flags);
return ret;
}
-static void warn_alloc_show_mem(gfp_t gfp_mask)
+static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
filter &= ~SHOW_MEM_FILTER_NODES;
- show_mem(filter);
+ show_mem(filter, nodemask);
}
-void warn_alloc(gfp_t gfp_mask, const char *fmt, ...)
+void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
{
struct va_format vaf;
va_list args;
pr_cont("%pV", &vaf);
va_end(args);
- pr_cont(", mode:%#x(%pGg)\n", gfp_mask, &gfp_mask);
+ pr_cont(", mode:%#x(%pGg), nodemask=", gfp_mask, &gfp_mask);
+ if (nodemask)
+ pr_cont("%*pbl\n", nodemask_pr_args(nodemask));
+ else
+ pr_cont("(null)\n");
+
+ cpuset_print_current_mems_allowed();
dump_stack();
- warn_alloc_show_mem(gfp_mask);
+ warn_alloc_show_mem(gfp_mask, nodemask);
+}
+
+static inline struct page *
+__alloc_pages_cpuset_fallback(gfp_t gfp_mask, unsigned int order,
+ unsigned int alloc_flags,
+ const struct alloc_context *ac)
+{
+ struct page *page;
+
+ page = get_page_from_freelist(gfp_mask, order,
+ alloc_flags|ALLOC_CPUSET, ac);
+ /*
+ * fallback to ignore cpuset restriction if our nodes
+ * are depleted
+ */
+ if (!page)
+ page = get_page_from_freelist(gfp_mask, order,
+ alloc_flags, ac);
+
+ return page;
}
static inline struct page *
if (page)
goto out;
- if (!(gfp_mask & __GFP_NOFAIL)) {
- /* Coredumps can quickly deplete all memory reserves */
- if (current->flags & PF_DUMPCORE)
- goto out;
- /* The OOM killer will not help higher order allocs */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
- goto out;
- /* The OOM killer does not needlessly kill tasks for lowmem */
- if (ac->high_zoneidx < ZONE_NORMAL)
- goto out;
- if (pm_suspended_storage())
- goto out;
- /*
- * XXX: GFP_NOFS allocations should rather fail than rely on
- * other request to make a forward progress.
- * We are in an unfortunate situation where out_of_memory cannot
- * do much for this context but let's try it to at least get
- * access to memory reserved if the current task is killed (see
- * out_of_memory). Once filesystems are ready to handle allocation
- * failures more gracefully we should just bail out here.
- */
+ /* Coredumps can quickly deplete all memory reserves */
+ if (current->flags & PF_DUMPCORE)
+ goto out;
+ /* The OOM killer will not help higher order allocs */
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ goto out;
+ /* The OOM killer does not needlessly kill tasks for lowmem */
+ if (ac->high_zoneidx < ZONE_NORMAL)
+ goto out;
+ if (pm_suspended_storage())
+ goto out;
+ /*
+ * XXX: GFP_NOFS allocations should rather fail than rely on
+ * other request to make a forward progress.
+ * We are in an unfortunate situation where out_of_memory cannot
+ * do much for this context but let's try it to at least get
+ * access to memory reserved if the current task is killed (see
+ * out_of_memory). Once filesystems are ready to handle allocation
+ * failures more gracefully we should just bail out here.
+ */
+
+ /* The OOM killer may not free memory on a specific node */
+ if (gfp_mask & __GFP_THISNODE)
+ goto out;
- /* The OOM killer may not free memory on a specific node */
- if (gfp_mask & __GFP_THISNODE)
- goto out;
- }
/* Exhausted what can be done so it's blamo time */
if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
*did_some_progress = 1;
- if (gfp_mask & __GFP_NOFAIL) {
- page = get_page_from_freelist(gfp_mask, order,
- ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);
- /*
- * fallback to ignore cpuset restriction if our nodes
- * are depleted
- */
- if (!page)
- page = get_page_from_freelist(gfp_mask, order,
+ /*
+ * Help non-failing allocations by giving them access to memory
+ * reserves
+ */
+ if (gfp_mask & __GFP_NOFAIL)
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order,
ALLOC_NO_WATERMARKS, ac);
- }
}
out:
mutex_unlock(&oom_lock);
no_progress_loops = 0;
compact_priority = DEF_COMPACT_PRIORITY;
cpuset_mems_cookie = read_mems_allowed_begin();
+
+ /*
+ * 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
+ * alloc_flags precisely. So we do that now.
+ */
+ alloc_flags = gfp_to_alloc_flags(gfp_mask);
+
/*
* We need to recalculate the starting point for the zonelist iterator
* because we might have used different nodemask in the fast path, or
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
- * alloc_flags precisely. So we do that now.
- */
- alloc_flags = gfp_to_alloc_flags(gfp_mask);
-
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
wake_all_kswapds(order, ac);
goto got_pg;
/* Caller is not willing to reclaim, we can't balance anything */
- if (!can_direct_reclaim) {
- /*
- * All existing users of the __GFP_NOFAIL are blockable, so warn
- * of any new users that actually allow this type of allocation
- * to fail.
- */
- WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
+ if (!can_direct_reclaim)
goto nopage;
- }
- /* Avoid recursion of direct reclaim */
- if (current->flags & PF_MEMALLOC) {
- /*
- * __GFP_NOFAIL request from this context is rather bizarre
- * because we cannot reclaim anything and only can loop waiting
- * for somebody to do a work for us.
- */
- if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
- cond_resched();
- goto retry;
- }
- 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, ac->nodemask,
+ "page allocation stalls for %ums, order:%u",
+ jiffies_to_msecs(jiffies-alloc_start), order);
+ stall_timeout += 10 * HZ;
}
- /* Avoid allocations with no watermarks from looping endlessly */
- if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+ /* Avoid recursion of direct reclaim */
+ if (current->flags & PF_MEMALLOC)
goto nopage;
-
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
&did_some_progress);
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 allocation stalls for %ums, order:%u",
- 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;
if (page)
goto got_pg;
+ /* Avoid allocations with no watermarks from looping endlessly */
+ if (test_thread_flag(TIF_MEMDIE))
+ goto nopage;
+
/* Retry as long as the OOM killer is making progress */
if (did_some_progress) {
no_progress_loops = 0;
if (read_mems_allowed_retry(cpuset_mems_cookie))
goto retry_cpuset;
- warn_alloc(gfp_mask,
+ /*
+ * Make sure that __GFP_NOFAIL request doesn't leak out and make sure
+ * we always retry
+ */
+ if (gfp_mask & __GFP_NOFAIL) {
+ /*
+ * All existing users of the __GFP_NOFAIL are blockable, so warn
+ * of any new users that actually require GFP_NOWAIT
+ */
+ if (WARN_ON_ONCE(!can_direct_reclaim))
+ goto fail;
+
+ /*
+ * PF_MEMALLOC request from this context is rather bizarre
+ * because we cannot reclaim anything and only can loop waiting
+ * for somebody to do a work for us
+ */
+ WARN_ON_ONCE(current->flags & PF_MEMALLOC);
+
+ /*
+ * non failing costly orders are a hard requirement which we
+ * are not prepared for much so let's warn about these users
+ * so that we can identify them and convert them to something
+ * else.
+ */
+ WARN_ON_ONCE(order > PAGE_ALLOC_COSTLY_ORDER);
+
+ /*
+ * Help non-failing allocations by giving them access to memory
+ * reserves but do not use ALLOC_NO_WATERMARKS because this
+ * could deplete whole memory reserves which would just make
+ * the situation worse
+ */
+ page = __alloc_pages_cpuset_fallback(gfp_mask, order, ALLOC_HARDER, ac);
+ if (page)
+ goto got_pg;
+
+ cond_resched();
+ goto retry;
+ }
+fail:
+ warn_alloc(gfp_mask, ac->nodemask,
"page allocation failure: order:%u", order);
got_pg:
return page;
}
-/*
- * This is the 'heart' of the zoned buddy allocator.
- */
-struct page *
-__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist, nodemask_t *nodemask)
+static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask,
+ struct alloc_context *ac, gfp_t *alloc_mask,
+ unsigned int *alloc_flags)
{
- struct page *page;
- 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 = {
- .high_zoneidx = gfp_zone(gfp_mask),
- .zonelist = zonelist,
- .nodemask = nodemask,
- .migratetype = gfpflags_to_migratetype(gfp_mask),
- };
+ ac->high_zoneidx = gfp_zone(gfp_mask);
+ ac->zonelist = zonelist;
+ ac->nodemask = nodemask;
+ ac->migratetype = gfpflags_to_migratetype(gfp_mask);
if (cpusets_enabled()) {
- alloc_mask |= __GFP_HARDWALL;
- alloc_flags |= ALLOC_CPUSET;
- if (!ac.nodemask)
- ac.nodemask = &cpuset_current_mems_allowed;
+ *alloc_mask |= __GFP_HARDWALL;
+ if (!ac->nodemask)
+ ac->nodemask = &cpuset_current_mems_allowed;
+ else
+ *alloc_flags |= ALLOC_CPUSET;
}
- gfp_mask &= gfp_allowed_mask;
-
lockdep_trace_alloc(gfp_mask);
might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
if (should_fail_alloc_page(gfp_mask, order))
- return NULL;
+ return false;
- /*
- * Check the zones suitable for the gfp_mask contain at least one
- * valid zone. It's possible to have an empty zonelist as a result
- * of __GFP_THISNODE and a memoryless node
- */
- if (unlikely(!zonelist->_zonerefs->zone))
- return NULL;
+ if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+ *alloc_flags |= ALLOC_CMA;
- if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE)
- alloc_flags |= ALLOC_CMA;
+ return true;
+}
+/* Determine whether to spread dirty pages and what the first usable zone */
+static inline void finalise_ac(gfp_t gfp_mask,
+ unsigned int order, struct alloc_context *ac)
+{
/* Dirty zone balancing only done in the fast path */
- ac.spread_dirty_pages = (gfp_mask & __GFP_WRITE);
+ ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
/*
* The preferred zone is used for statistics but crucially it is
* also used as the starting point for the zonelist iterator. It
* may get reset for allocations that ignore memory policies.
*/
- ac.preferred_zoneref = first_zones_zonelist(ac.zonelist,
- ac.high_zoneidx, ac.nodemask);
- 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;
- }
+ ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
+ ac->high_zoneidx, ac->nodemask);
+}
+
+/*
+ * This is the 'heart' of the zoned buddy allocator.
+ */
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
+{
+ struct page *page;
+ 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 = { };
+
+ gfp_mask &= gfp_allowed_mask;
+ if (!prepare_alloc_pages(gfp_mask, order, zonelist, nodemask, &ac, &alloc_mask, &alloc_flags))
+ return NULL;
+
+ finalise_ac(gfp_mask, order, &ac);
/* First allocation attempt */
page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac);
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.
* Determine whether the node should be displayed or not, depending on whether
* SHOW_MEM_FILTER_NODES was passed to show_free_areas().
*/
-bool skip_free_areas_node(unsigned int flags, int nid)
+static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask)
{
- bool ret = false;
- unsigned int cpuset_mems_cookie;
-
if (!(flags & SHOW_MEM_FILTER_NODES))
- goto out;
+ return false;
- do {
- cpuset_mems_cookie = read_mems_allowed_begin();
- ret = !node_isset(nid, cpuset_current_mems_allowed);
- } while (read_mems_allowed_retry(cpuset_mems_cookie));
-out:
- return ret;
+ /*
+ * no node mask - aka implicit memory numa policy. Do not bother with
+ * the synchronization - read_mems_allowed_begin - because we do not
+ * have to be precise here.
+ */
+ if (!nodemask)
+ nodemask = &cpuset_current_mems_allowed;
+
+ return !node_isset(nid, *nodemask);
}
#define K(x) ((x) << (PAGE_SHIFT-10))
* SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
* cpuset.
*/
-void show_free_areas(unsigned int filter)
+void show_free_areas(unsigned int filter, nodemask_t *nodemask)
{
unsigned long free_pcp = 0;
int cpu;
pg_data_t *pgdat;
for_each_populated_zone(zone) {
- if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
for_each_online_cpu(cpu)
global_page_state(NR_FREE_CMA_PAGES));
for_each_online_pgdat(pgdat) {
+ if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
+ continue;
+
printk("Node %d"
" active_anon:%lukB"
" inactive_anon:%lukB"
for_each_populated_zone(zone) {
int i;
- if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
free_pcp = 0;
unsigned long nr[MAX_ORDER], flags, total = 0;
unsigned char types[MAX_ORDER];
- if (skip_free_areas_node(filter, zone_to_nid(zone)))
+ if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask))
continue;
show_node(zone);
printk(KERN_CONT "%s: ", zone->name);
* the zone and SPARSEMEM is in use. If there are holes within the
* zone, each populated memory region may cost us one or two extra
* memmap pages due to alignment because memmap pages for each
- * populated regions may not naturally algined on page boundary.
+ * populated regions may not be naturally aligned on page boundary.
* So the (present_pages >> 4) heuristic is a tradeoff for that.
*/
if (spanned_pages > present_pages + (present_pages >> 4) &&
start_pfn = end_pfn;
}
- arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
- arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;
/* Find the PFNs that ZONE_MOVABLE begins at in each node */
memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
* If @count is not zero, it is okay to include less @count unmovable pages
*
* PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
- * expect this function should be exact.
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
*/
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
bool skip_hwpoisoned_pages)
if (skip_hwpoisoned_pages && PageHWPoison(page))
continue;
+ if (__PageMovable(page))
+ continue;
+
if (!PageLRU(page))
found++;
/*
* #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks
* in range must have the same migratetype and it must
* be either of the two.
+ * @gfp_mask: GFP mask to use during compaction
*
* The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
* aligned, however it's the caller's responsibility to guarantee that
* need to be freed with free_contig_range().
*/
int alloc_contig_range(unsigned long start, unsigned long end,
- unsigned migratetype)
+ unsigned migratetype, gfp_t gfp_mask)
{
unsigned long outer_start, outer_end;
unsigned int order;
.zone = page_zone(pfn_to_page(start)),
.mode = MIGRATE_SYNC,
.ignore_skip_hint = true,
- .gfp_mask = GFP_KERNEL,
+ .gfp_mask = memalloc_noio_flags(gfp_mask),
};
INIT_LIST_HEAD(&cc.migratepages);