mm: have order > 0 compaction start near a pageblock with free pages

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

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8f65abe..07f1924 100644 (file)
--- 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;
 }
 
@@ -2116,8 +2127,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 
                page = get_page_from_freelist(gfp_mask, nodemask,
                                order, zonelist, high_zoneidx,
-                               alloc_flags, preferred_zone,
-                               migratetype);
+                               alloc_flags & ~ALLOC_NO_WATERMARKS,
+                               preferred_zone, migratetype);
                if (page) {
                        preferred_zone->compact_considered = 0;
                        preferred_zone->compact_defer_shift = 0;
@@ -2209,8 +2220,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 retry:
        page = get_page_from_freelist(gfp_mask, nodemask, order,
                                        zonelist, high_zoneidx,
-                                       alloc_flags, preferred_zone,
-                                       migratetype);
+                                       alloc_flags & ~ALLOC_NO_WATERMARKS,
+                                       preferred_zone, migratetype);
 
        /*
         * If an allocation failed after direct reclaim, it could be because
@@ -2296,7 +2307,11 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
        if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
                if (gfp_mask & __GFP_MEMALLOC)
                        alloc_flags |= ALLOC_NO_WATERMARKS;
-               else if (likely(!(gfp_mask & __GFP_NOMEMALLOC)) && !in_interrupt())
+               else if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
+                       alloc_flags |= ALLOC_NO_WATERMARKS;
+               else if (!in_interrupt() &&
+                               ((current->flags & PF_MEMALLOC) ||
+                                unlikely(test_thread_flag(TIF_MEMDIE))))
                        alloc_flags |= ALLOC_NO_WATERMARKS;
        }
 
@@ -2374,11 +2389,19 @@ rebalance:
 
        /* Allocate without watermarks if the context allows */
        if (alloc_flags & ALLOC_NO_WATERMARKS) {
+               /*
+                * Ignore mempolicies if ALLOC_NO_WATERMARKS on the grounds
+                * the allocation is high priority and these type of
+                * allocations are system rather than user orientated
+                */
+               zonelist = node_zonelist(numa_node_id(), gfp_mask);
+
                page = __alloc_pages_high_priority(gfp_mask, order,
                                zonelist, high_zoneidx, nodemask,
                                preferred_zone, migratetype);
-               if (page)
+               if (page) {
                        goto got_pg;
+               }
        }
 
        /* Atomic allocations - we can't balance anything */
@@ -2495,14 +2518,6 @@ nopage:
        warn_alloc_failed(gfp_mask, order, NULL);
        return page;
 got_pg:
-       /*
-        * page->pfmemalloc is set when the caller had PFMEMALLOC set, is
-        * been OOM killed or specified __GFP_MEMALLOC. 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);
-
        if (kmemcheck_enabled)
                kmemcheck_pagealloc_alloc(page, order, gfp_mask);
 
@@ -2557,8 +2572,6 @@ 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);
 
@@ -4365,6 +4378,8 @@ void __init set_pageblock_order(void)
  *   - mark all pages reserved
  *   - mark all memory queues empty
  *   - clear the memory bitmaps
+ *
+ * NOTE: pgdat should get zeroed by caller.
  */
 static void __paginginit free_area_init_core(struct pglist_data *pgdat,
                unsigned long *zones_size, unsigned long *zholes_size)
@@ -4375,9 +4390,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
        int ret;
 
        pgdat_resize_init(pgdat);
-       pgdat->nr_zones = 0;
        init_waitqueue_head(&pgdat->kswapd_wait);
-       pgdat->kswapd_max_order = 0;
+       init_waitqueue_head(&pgdat->pfmemalloc_wait);
        pgdat_page_cgroup_init(pgdat);
 
        for (j = 0; j < MAX_NR_ZONES; j++) {
@@ -4438,11 +4452,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 
                zone_pcp_init(zone);
                lruvec_init(&zone->lruvec, zone);
-               zap_zone_vm_stats(zone);
-               zone->flags = 0;
-#ifdef CONFIG_MEMORY_ISOLATION
-               zone->nr_pageblock_isolate = 0;
-#endif
                if (!size)
                        continue;
 
@@ -4502,6 +4511,9 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 {
        pg_data_t *pgdat = NODE_DATA(nid);
 
+       /* pg_data_t should be reset to zero when it's allocated */
+       WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
+
        pgdat->node_id = nid;
        pgdat->node_start_pfn = node_start_pfn;
        calculate_node_totalpages(pgdat, zones_size, zholes_size);