Merge tag 'cpumask-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git...

[deliverable/linux.git] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index eab8e2018a463498074a4654e5e804c4f5959fad..ebffa0e4a9c0451cfbd78bcf4835825ffd72c6de 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1371,7 +1371,7 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
        int to_drain, batch;
 
        local_irq_save(flags);
-       batch = ACCESS_ONCE(pcp->batch);
+       batch = READ_ONCE(pcp->batch);
        to_drain = min(pcp->count, batch);
        if (to_drain > 0) {
                free_pcppages_bulk(zone, to_drain, pcp);
@@ -1570,7 +1570,7 @@ void free_hot_cold_page(struct page *page, bool cold)
                list_add_tail(&page->lru, &pcp->lists[migratetype]);
        pcp->count++;
        if (pcp->count >= pcp->high) {
-               unsigned long batch = ACCESS_ONCE(pcp->batch);
+               unsigned long batch = READ_ONCE(pcp->batch);
                free_pcppages_bulk(zone, batch, pcp);
                pcp->count -= batch;
        }
@@ -2412,13 +2412,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
                        *did_some_progress = 1;
                        goto out;
                }
-               /*
-                * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
-                * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
-                * The caller should handle page allocation failure by itself if
-                * it specifies __GFP_THISNODE.
-                * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
-                */
+               /* The OOM killer may not free memory on a specific node */
                if (gfp_mask & __GFP_THISNODE)
                        goto out;
        }
@@ -2673,15 +2667,11 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
        }
 
        /*
-        * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
-        * __GFP_NOWARN set) should not cause reclaim since the subsystem
-        * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
-        * using a larger set of nodes after it has established that the
-        * allowed per node queues are empty and that nodes are
-        * over allocated.
+        * If this allocation cannot block and it is for a specific node, then
+        * fail early.  There's no need to wakeup kswapd or retry for a
+        * speculative node-specific allocation.
         */
-       if (IS_ENABLED(CONFIG_NUMA) &&
-           (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+       if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !wait)
                goto nopage;
 
 retry:
@@ -2874,7 +2864,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
        /*
         * 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
+        * of __GFP_THISNODE and a memoryless node
         */
        if (unlikely(!zonelist->_zonerefs->zone))
                return NULL;
@@ -3255,7 +3245,6 @@ static void show_migration_types(unsigned char type)
  * Bits in @filter:
  * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's
  *   cpuset.
- * SHOW_MEM_PERCPU_LISTS: display full per-node per-cpu pcp lists
  */
 void show_free_areas(unsigned int filter)
 {
@@ -3267,25 +3256,8 @@ void show_free_areas(unsigned int filter)
                if (skip_free_areas_node(filter, zone_to_nid(zone)))
                        continue;
 
-               if (filter & SHOW_MEM_PERCPU_LISTS) {
-                       show_node(zone);
-                       printk("%s per-cpu:\n", zone->name);
-               }
-
-               for_each_online_cpu(cpu) {
-                       struct per_cpu_pageset *pageset;
-
-                       pageset = per_cpu_ptr(zone->pageset, cpu);
-
-                       free_pcp += pageset->pcp.count;
-
-                       if (!(filter & SHOW_MEM_PERCPU_LISTS))
-                               continue;
-
-                       printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
-                              cpu, pageset->pcp.high,
-                              pageset->pcp.batch, pageset->pcp.count);
-               }
+               for_each_online_cpu(cpu)
+                       free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
        }
 
        printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
@@ -5788,7 +5760,7 @@ static void __setup_per_zone_wmarks(void)
                         * value here.
                         *
                         * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN)
-                        * deltas controls asynch page reclaim, and so should
+                        * deltas control asynch page reclaim, and so should
                         * not be capped for highmem.
                         */
                        unsigned long min_pages;
@@ -6235,7 +6207,7 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
        mask <<= (BITS_PER_LONG - bitidx - 1);
        flags <<= (BITS_PER_LONG - bitidx - 1);
 
-       word = ACCESS_ONCE(bitmap[word_bitidx]);
+       word = READ_ONCE(bitmap[word_bitidx]);
        for (;;) {
                old_word = cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flags);
                if (word == old_word)