mm/page_alloc.c: broken deferred calculation

[sfrench/cifs-2.6.git] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7ca668e946e5c9077e71a5705aa9ee1e7474b6c1..8f2b9ad2e23fc647820779c778149bfbfe0225a7 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -82,6 +82,8 @@ DEFINE_PER_CPU(int, numa_node);
 EXPORT_PER_CPU_SYMBOL(numa_node);
 #endif
 
+DEFINE_STATIC_KEY_TRUE(vm_numa_stat_key);
+
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 /*
  * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly.
@@ -289,28 +291,37 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+
+/*
+ * Determine how many pages need to be initialized durig early boot
+ * (non-deferred initialization).
+ * The value of first_deferred_pfn will be set later, once non-deferred pages
+ * are initialized, but for now set it ULONG_MAX.
+ */
 static inline void reset_deferred_meminit(pg_data_t *pgdat)
 {
-       unsigned long max_initialise;
-       unsigned long reserved_lowmem;
+       phys_addr_t start_addr, end_addr;
+       unsigned long max_pgcnt;
+       unsigned long reserved;
 
        /*
         * Initialise at least 2G of a node but also take into account that
         * two large system hashes that can take up 1GB for 0.25TB/node.
         */
-       max_initialise = max(2UL << (30 - PAGE_SHIFT),
-               (pgdat->node_spanned_pages >> 8));
+       max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
+                       (pgdat->node_spanned_pages >> 8));
 
        /*
         * Compensate the all the memblock reservations (e.g. crash kernel)
         * from the initial estimation to make sure we will initialize enough
         * memory to boot.
         */
-       reserved_lowmem = memblock_reserved_memory_within(pgdat->node_start_pfn,
-                       pgdat->node_start_pfn + max_initialise);
-       max_initialise += reserved_lowmem;
+       start_addr = PFN_PHYS(pgdat->node_start_pfn);
+       end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
+       reserved = memblock_reserved_memory_within(start_addr, end_addr);
+       max_pgcnt += PHYS_PFN(reserved);
 
-       pgdat->static_init_size = min(max_initialise, pgdat->node_spanned_pages);
+       pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
        pgdat->first_deferred_pfn = ULONG_MAX;
 }
 
@@ -337,7 +348,7 @@ static inline bool update_defer_init(pg_data_t *pgdat,
        if (zone_end < pgdat_end_pfn(pgdat))
                return true;
        (*nr_initialised)++;
-       if ((*nr_initialised > pgdat->static_init_size) &&
+       if ((*nr_initialised > pgdat->static_init_pgcnt) &&
            (pfn & (PAGES_PER_SECTION - 1)) == 0) {
                pgdat->first_deferred_pfn = pfn;
                return false;
@@ -2777,6 +2788,10 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
 #ifdef CONFIG_NUMA
        enum numa_stat_item local_stat = NUMA_LOCAL;
 
+       /* skip numa counters update if numa stats is disabled */
+       if (!static_branch_likely(&vm_numa_stat_key))
+               return;
+
        if (z->node != numa_node_id())
                local_stat = NUMA_OTHER;
 
@@ -3035,9 +3050,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                if (!area->nr_free)
                        continue;
 
-               if (alloc_harder)
-                       return true;
-
                for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
                        if (!list_empty(&area->free_list[mt]))
                                return true;
@@ -3049,6 +3061,9 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
                        return true;
                }
 #endif
+               if (alloc_harder &&
+                       !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+                       return true;
        }
        return false;
 }
@@ -3897,8 +3912,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
        enum compact_result compact_result;
        int compaction_retries;
        int no_progress_loops;
-       unsigned long alloc_start = jiffies;
-       unsigned int stall_timeout = 10 * HZ;
        unsigned int cpuset_mems_cookie;
        int reserve_flags;
 
@@ -4030,14 +4043,6 @@ retry:
        if (!can_direct_reclaim)
                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 & ~__GFP_NOWARN, ac->nodemask,
-                       "page allocation stalls for %ums, order:%u",
-                       jiffies_to_msecs(jiffies-alloc_start), order);
-               stall_timeout += 10 * HZ;
-       }
-
        /* Avoid recursion of direct reclaim */
        if (current->flags & PF_MEMALLOC)
                goto nopage;