[PATCH] mm: split page table lock

[mirror_ubuntu-artful-kernel.git] / mm / vmscan.c

diff --git a/mm/vmscan.c b/mm/vmscan.c
index cfffe5098d538e6d54d1954c523d455924cbf7fc..135bf8ca96ee60ac78783caac94fa30f2bfabfc8 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -70,7 +70,7 @@ struct scan_control {
        unsigned int priority;
 
        /* This context's GFP mask */
-       unsigned int gfp_mask;
+       gfp_t gfp_mask;
 
        int may_writepage;
 
@@ -186,7 +186,7 @@ EXPORT_SYMBOL(remove_shrinker);
  *
  * Returns the number of slab objects which we shrunk.
  */
-static int shrink_slab(unsigned long scanned, unsigned int gfp_mask,
+static int shrink_slab(unsigned long scanned, gfp_t gfp_mask,
                        unsigned long lru_pages)
 {
        struct shrinker *shrinker;
@@ -417,7 +417,9 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
                 * Anonymous process memory has backing store?
                 * Try to allocate it some swap space here.
                 */
-               if (PageAnon(page) && !PageSwapCache(page) && sc->may_swap) {
+               if (PageAnon(page) && !PageSwapCache(page)) {
+                       if (!sc->may_swap)
+                               goto keep_locked;
                        if (!add_to_swap(page))
                                goto activate_locked;
                }
@@ -511,14 +513,15 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
                 * PageDirty _after_ making sure that the page is freeable and
                 * not in use by anybody.       (pagecache + us == 2)
                 */
-               if (page_count(page) != 2 || PageDirty(page)) {
-                       write_unlock_irq(&mapping->tree_lock);
-                       goto keep_locked;
-               }
+               if (unlikely(page_count(page) != 2))
+                       goto cannot_free;
+               smp_rmb();
+               if (unlikely(PageDirty(page)))
+                       goto cannot_free;
 
 #ifdef CONFIG_SWAP
                if (PageSwapCache(page)) {
-                       swp_entry_t swap = { .val = page->private };
+                       swp_entry_t swap = { .val = page_private(page) };
                        __delete_from_swap_cache(page);
                        write_unlock_irq(&mapping->tree_lock);
                        swap_free(swap);
@@ -538,6 +541,10 @@ free_it:
                        __pagevec_release_nonlru(&freed_pvec);
                continue;
 
+cannot_free:
+               write_unlock_irq(&mapping->tree_lock);
+               goto keep_locked;
+
 activate_locked:
                SetPageActive(page);
                pgactivate++;
@@ -822,6 +829,8 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
        unsigned long nr_active;
        unsigned long nr_inactive;
 
+       atomic_inc(&zone->reclaim_in_progress);
+
        /*
         * Add one to `nr_to_scan' just to make sure that the kernel will
         * slowly sift through the active list.
@@ -861,6 +870,8 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
        }
 
        throttle_vm_writeout();
+
+       atomic_dec(&zone->reclaim_in_progress);
 }
 
 /*
@@ -890,7 +901,7 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
                if (zone->present_pages == 0)
                        continue;
 
-               if (!cpuset_zone_allowed(zone))
+               if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
                        continue;
 
                zone->temp_priority = sc->priority;
@@ -900,9 +911,7 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
                if (zone->all_unreclaimable && sc->priority != DEF_PRIORITY)
                        continue;       /* Let kswapd poll it */
 
-               atomic_inc(&zone->reclaim_in_progress);
                shrink_zone(zone, sc);
-               atomic_dec(&zone->reclaim_in_progress);
        }
 }
  
@@ -919,7 +928,7 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
  */
-int try_to_free_pages(struct zone **zones, unsigned int gfp_mask)
+int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 {
        int priority;
        int ret = 0;
@@ -938,7 +947,7 @@ int try_to_free_pages(struct zone **zones, unsigned int gfp_mask)
        for (i = 0; zones[i] != NULL; i++) {
                struct zone *zone = zones[i];
 
-               if (!cpuset_zone_allowed(zone))
+               if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
                        continue;
 
                zone->temp_priority = DEF_PRIORITY;
@@ -984,7 +993,7 @@ out:
        for (i = 0; zones[i] != 0; i++) {
                struct zone *zone = zones[i];
 
-               if (!cpuset_zone_allowed(zone))
+               if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
                        continue;
 
                zone->prev_priority = zone->temp_priority;
@@ -1254,11 +1263,11 @@ void wakeup_kswapd(struct zone *zone, int order)
                return;
        if (pgdat->kswapd_max_order < order)
                pgdat->kswapd_max_order = order;
-       if (!cpuset_zone_allowed(zone))
+       if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
                return;
-       if (!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
+       if (!waitqueue_active(&pgdat->kswapd_wait))
                return;
-       wake_up_interruptible(&zone->zone_pgdat->kswapd_wait);
+       wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
 #ifdef CONFIG_PM
@@ -1331,7 +1340,7 @@ module_init(kswapd_init)
 /*
  * Try to free up some pages from this zone through reclaim.
  */
-int zone_reclaim(struct zone *zone, unsigned int gfp_mask, unsigned int order)
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 {
        struct scan_control sc;
        int nr_pages = 1 << order;
@@ -1358,14 +1367,13 @@ int zone_reclaim(struct zone *zone, unsigned int gfp_mask, unsigned int order)
                sc.swap_cluster_max = SWAP_CLUSTER_MAX;
 
        /* Don't reclaim the zone if there are other reclaimers active */
-       if (!atomic_inc_and_test(&zone->reclaim_in_progress))
+       if (atomic_read(&zone->reclaim_in_progress) > 0)
                goto out;
 
        shrink_zone(zone, &sc);
        total_reclaimed = sc.nr_reclaimed;
 
  out:
-       atomic_dec(&zone->reclaim_in_progress);
        return total_reclaimed;
 }
 
@@ -1375,6 +1383,9 @@ asmlinkage long sys_set_zone_reclaim(unsigned int node, unsigned int zone,
        struct zone *z;
        int i;
 
+       if (!capable(CAP_SYS_ADMIN))
+               return -EACCES;
+
        if (node >= MAX_NUMNODES || !node_online(node))
                return -EINVAL;