4 files changed, 132 insertions, 65 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index e78cb9688421..7fcd3a52e68d 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -51,6 +51,47 @@ static inline bool migrate_async_suitable(int migratetype)
 }
 
 /*
+ * Compaction requires the taking of some coarse locks that are potentially
+ * very heavily contended. Check if the process needs to be scheduled or
+ * if the lock is contended. For async compaction, back out in the event
+ * if contention is severe. For sync compaction, schedule.
+ *
+ * Returns true if the lock is held.
+ * Returns false if the lock is released and compaction should abort
+ */
+static bool compact_checklock_irqsave(spinlock_t *lock, unsigned long *flags,
+                                      bool locked, struct compact_control *cc)
+{
+        if (need_resched() || spin_is_contended(lock)) {
+                if (locked) {
+                        spin_unlock_irqrestore(lock, *flags);
+                        locked = false;
+                }
+
+                /* async aborts if taking too long or contended */
+                if (!cc->sync) {
+                        if (cc->contended)
+                                *cc->contended = true;
+                        return false;
+                }
+
+                cond_resched();
+                if (fatal_signal_pending(current))
+                        return false;
+        }
+
+        if (!locked)
+                spin_lock_irqsave(lock, *flags);
+        return true;
+}
+
+static inline bool compact_trylock_irqsave(spinlock_t *lock,
+                        unsigned long *flags, struct compact_control *cc)
+{
+        return compact_checklock_irqsave(lock, flags, false, cc);
+}
+
+/*
  * Isolate free pages onto a private freelist. Caller must hold zone->lock.
  * If @strict is true, will abort returning 0 on any invalid PFNs or non-free
  * pages inside of the pageblock (even though it may still end up isolating
@@ -173,7 +214,7 @@ isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 /* Update the number of anon and file isolated pages in the zone */
-static void acct_isolated(struct zone *zone, struct compact_control *cc)
+static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc)
 {
         struct page *page;
         unsigned int count[2] = { 0, };
@@ -181,8 +222,14 @@ static void acct_isolated(struct zone *zone, struct compact_control *cc)
         list_for_each_entry(page, &cc->migratepages, lru)
                 count[!!page_is_file_cache(page)]++;
 
-        __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
-        __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+        /* If locked we can use the interrupt unsafe versions */
+        if (locked) {
+                __mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+                __mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+        } else {
+                mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+                mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
+        }
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -228,6 +275,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
         struct list_head *migratelist = &cc->migratepages;
         isolate_mode_t mode = 0;
         struct lruvec *lruvec;
+        unsigned long flags;
+        bool locked;
 
         /*
          * Ensure that there are not too many pages isolated from the LRU
@@ -247,25 +296,22 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
         /* Time to isolate some pages for migration */
         cond_resched();
-        spin_lock_irq(&zone->lru_lock);
+        spin_lock_irqsave(&zone->lru_lock, flags);
+        locked = true;
         for (; low_pfn < end_pfn; low_pfn++) {
                 struct page *page;
-                bool locked = true;
 
                 /* give a chance to irqs before checking need_resched() */
                 if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
-                        spin_unlock_irq(&zone->lru_lock);
+                        spin_unlock_irqrestore(&zone->lru_lock, flags);
                         locked = false;
                 }
-                if (need_resched() || spin_is_contended(&zone->lru_lock)) {
-                        if (locked)
-                                spin_unlock_irq(&zone->lru_lock);
-                        cond_resched();
-                        spin_lock_irq(&zone->lru_lock);
-                        if (fatal_signal_pending(current))
-                                break;
-                } else if (!locked)
-                        spin_lock_irq(&zone->lru_lock);
+
+                /* Check if it is ok to still hold the lock */
+                locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
+                                                                locked, cc);
+                if (!locked)
+                        break;
 
                 /*
                  * migrate_pfn does not necessarily start aligned to a
@@ -349,9 +395,10 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
                 }
         }
 
-        acct_isolated(zone, cc);
+        acct_isolated(zone, locked, cc);
 
-        spin_unlock_irq(&zone->lru_lock);
+        if (locked)
+                spin_unlock_irqrestore(&zone->lru_lock, flags);
 
         trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
 
@@ -384,6 +431,20 @@ static bool suitable_migration_target(struct page *page)
 }
 
 /*
+ * Returns the start pfn of the last page block in a zone.  This is the starting
+ * point for full compaction of a zone.  Compaction searches for free pages from
+ * the end of each zone, while isolate_freepages_block scans forward inside each
+ * page block.
+ */
+static unsigned long start_free_pfn(struct zone *zone)
+{
+        unsigned long free_pfn;
+        free_pfn = zone->zone_start_pfn + zone->spanned_pages;
+        free_pfn &= ~(pageblock_nr_pages-1);
+        return free_pfn;
+}
+
+/*
  * Based on information in the current compact_control, find blocks
  * suitable for isolating free pages from and then isolate them.
  */
@@ -422,17 +483,6 @@ static void isolate_freepages(struct zone *zone,
                                         pfn -= pageblock_nr_pages) {
                 unsigned long isolated;
 
-                /*
-                 * Skip ahead if another thread is compacting in the area
-                 * simultaneously. If we wrapped around, we can only skip
-                 * ahead if zone->compact_cached_free_pfn also wrapped to
-                 * above our starting point.
-                 */
-                if (cc->order > 0 && (!cc->wrapped ||
-                                      zone->compact_cached_free_pfn >
-                                      cc->start_free_pfn))
-                        pfn = min(pfn, zone->compact_cached_free_pfn);
-
                 if (!pfn_valid(pfn))
                         continue;
 
@@ -458,7 +508,16 @@ static void isolate_freepages(struct zone *zone,
                  * are disabled
                  */
                 isolated = 0;
-                spin_lock_irqsave(&zone->lock, flags);
+
+                /*
+                 * The zone lock must be held to isolate freepages. This
+                 * unfortunately this is a very coarse lock and can be
+                 * heavily contended if there are parallel allocations
+                 * or parallel compactions. For async compaction do not
+                 * spin on the lock
+                 */
+                if (!compact_trylock_irqsave(&zone->lock, &flags, cc))
+                        break;
                 if (suitable_migration_target(page)) {
                         end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
                         isolated = isolate_freepages_block(pfn, end_pfn,
@@ -474,7 +533,15 @@ static void isolate_freepages(struct zone *zone,
                  */
                 if (isolated) {
                         high_pfn = max(high_pfn, pfn);
-                        if (cc->order > 0)
+
+                        /*
+                         * If the free scanner has wrapped, update
+                         * compact_cached_free_pfn to point to the highest
+                         * pageblock with free pages. This reduces excessive
+                         * scanning of full pageblocks near the end of the
+                         * zone
+                         */
+                        if (cc->order > 0 && cc->wrapped)
                                 zone->compact_cached_free_pfn = high_pfn;
                 }
         }
@@ -484,6 +551,11 @@ static void isolate_freepages(struct zone *zone,
 
         cc->free_pfn = high_pfn;
         cc->nr_freepages = nr_freepages;
+
+        /* If compact_cached_free_pfn is reset then set it now */
+        if (cc->order > 0 && !cc->wrapped &&
+                        zone->compact_cached_free_pfn == start_free_pfn(zone))
+                zone->compact_cached_free_pfn = high_pfn;
 }
 
 /*
@@ -570,20 +642,6 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
         return ISOLATE_SUCCESS;
 }
 
-/*
- * Returns the start pfn of the last page block in a zone.  This is the starting
- * point for full compaction of a zone.  Compaction searches for free pages from
- * the end of each zone, while isolate_freepages_block scans forward inside each
- * page block.
- */
-static unsigned long start_free_pfn(struct zone *zone)
-{
-        unsigned long free_pfn;
-        free_pfn = zone->zone_start_pfn + zone->spanned_pages;
-        free_pfn &= ~(pageblock_nr_pages-1);
-        return free_pfn;
-}
-
 static int compact_finished(struct zone *zone,
                             struct compact_control *cc)
 {
@@ -771,7 +829,7 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
                                  int order, gfp_t gfp_mask,
-                                 bool sync)
+                                 bool sync, bool *contended)
 {
         struct compact_control cc = {
                 .nr_freepages = 0,
@@ -780,6 +838,7 @@ static unsigned long compact_zone_order(struct zone *zone,
                 .migratetype = allocflags_to_migratetype(gfp_mask),
                 .zone = zone,
                 .sync = sync,
+                .contended = contended,
         };
         INIT_LIST_HEAD(&cc.freepages);
         INIT_LIST_HEAD(&cc.migratepages);
@@ -801,7 +860,7 @@ int sysctl_extfrag_threshold = 500;
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
                         int order, gfp_t gfp_mask, nodemask_t *nodemask,
-                        bool sync)
+                        bool sync, bool *contended)
 {
         enum zone_type high_zoneidx = gfp_zone(gfp_mask);
         int may_enter_fs = gfp_mask & __GFP_FS;
@@ -825,7 +884,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
                                                                 nodemask) {
                 int status;
 
-                status = compact_zone_order(zone, order, gfp_mask, sync);
+                status = compact_zone_order(zone, order, gfp_mask, sync,
+                                                contended);
                 rc = max(status, rc);
 
                 /* If a normal allocation would succeed, stop compacting */
@@ -861,7 +921,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
                 if (cc->order > 0) {
                         int ok = zone_watermark_ok(zone, cc->order,
                                                 low_wmark_pages(zone), 0, 0);
-                        if (ok && cc->order > zone->compact_order_failed)
+                        if (ok && cc->order >= zone->compact_order_failed)
                                 zone->compact_order_failed = cc->order + 1;
                         /* Currently async compaction is never deferred. */
                         else if (!ok && cc->sync)
diff --git a/mm/internal.h b/mm/internal.h
index 3314f79d775a..b8c91b342e24 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -130,6 +130,7 @@ struct compact_control {
         int order;                      /* order a direct compactor needs */
         int migratetype;                /* MOVABLE, RECLAIMABLE etc */
         struct zone *zone;
+        bool *contended;                /* True if a lock was contended */
 };
 
 unsigned long
diff --git a/mm/mmap.c b/mm/mmap.c
index e3e86914f11a..9adee9fc0d8a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2309,7 +2309,7 @@ void exit_mmap(struct mm_struct *mm)
         }
         vm_unacct_memory(nr_accounted);
 
-        BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
+        WARN_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
 }
 
 /* Insert vm structure into process list sorted by address
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 009ac285fea7..c66fb875104a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1928,6 +1928,17 @@ this_zone_full:
                 zlc_active = 0;
                 goto zonelist_scan;
         }
+
+        if (page)
+                /*
+                 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
+                 * necessary to allocate the page. The expectation is
+                 * that the caller is taking steps that will free more
+                 * memory. The caller should avoid the page being used
+                 * for !PFMEMALLOC purposes.
+                 */
+                page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+
         return page;
 }
 
@@ -2091,7 +2102,7 @@ __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, bool sync_migration,
-        bool *deferred_compaction,
+        bool *contended_compaction, bool *deferred_compaction,
         unsigned long *did_some_progress)
 {
         struct page *page;
@@ -2106,7 +2117,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
         current->flags |= PF_MEMALLOC;
         *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-                                                nodemask, sync_migration);
+                                                nodemask, sync_migration,
+                                                contended_compaction);
         current->flags &= ~PF_MEMALLOC;
         if (*did_some_progress != COMPACT_SKIPPED) {
 
@@ -2152,7 +2164,7 @@ __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, bool sync_migration,
-        bool *deferred_compaction,
+        bool *contended_compaction, bool *deferred_compaction,
         unsigned long *did_some_progress)
 {
         return NULL;
@@ -2325,6 +2337,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
         unsigned long did_some_progress;
         bool sync_migration = false;
         bool deferred_compaction = false;
+        bool contended_compaction = false;
 
         /*
          * In the slowpath, we sanity check order to avoid ever trying to
@@ -2389,14 +2402,6 @@ rebalance:
                                 zonelist, high_zoneidx, nodemask,
                                 preferred_zone, migratetype);
                 if (page) {
-                        /*
-                         * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was
-                         * necessary to allocate the page. The expectation is
-                         * that the caller is taking steps that will free more
-                         * memory. The caller should avoid the page being used
-                         * for !PFMEMALLOC purposes.
-                         */
-                        page->pfmemalloc = true;
                         goto got_pg;
                 }
         }
@@ -2422,6 +2427,7 @@ rebalance:
                                         nodemask,
                                         alloc_flags, preferred_zone,
                                         migratetype, sync_migration,
+                                        &contended_compaction,
                                         &deferred_compaction,
                                         &did_some_progress);
         if (page)
@@ -2431,10 +2437,11 @@ rebalance:
         /*
          * 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
+         * requested a movable allocation that does not heavily disrupt the
+         * system then fail the allocation instead of entering direct reclaim.
          */
-        if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+        if ((deferred_compaction || contended_compaction) &&
+                                                (gfp_mask & __GFP_NO_KSWAPD))
                 goto nopage;
 
         /* Try direct reclaim and then allocating */
@@ -2505,6 +2512,7 @@ rebalance:
                                         nodemask,
                                         alloc_flags, preferred_zone,
                                         migratetype, sync_migration,
+                                        &contended_compaction,
                                         &deferred_compaction,
                                         &did_some_progress);
                 if (page)
@@ -2569,8 +2577,6 @@ retry_cpuset:
                 page = __alloc_pages_slowpath(gfp_mask, order,
                                 zonelist, high_zoneidx, nodemask,
                                 preferred_zone, migratetype);
-        else
-                page->pfmemalloc = false;
 
         trace_mm_page_alloc(page, order, gfp_mask, migratetype);