[PATCH] cpusets: oom_kill tweaks

[linux-2.6] / mm / page_alloc.c

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c9f7f88112543d2e72021c576cc377a2244e295..14d7032c1d120b12ee1d9c9c6d1d8cadfb8b1edf 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -42,13 +42,13 @@
  * MCD - HACK: Find somewhere to initialize this EARLY, or make this
  * initializer cleaner
  */
-nodemask_t node_online_map = { { [0] = 1UL } };
+nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
 EXPORT_SYMBOL(node_online_map);
-nodemask_t node_possible_map = NODE_MASK_ALL;
+nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
 EXPORT_SYMBOL(node_possible_map);
-struct pglist_data *pgdat_list;
-unsigned long totalram_pages;
-unsigned long totalhigh_pages;
+struct pglist_data *pgdat_list __read_mostly;
+unsigned long totalram_pages __read_mostly;
+unsigned long totalhigh_pages __read_mostly;
 long nr_swap_pages;
 
 /*
@@ -68,7 +68,7 @@ EXPORT_SYMBOL(nr_swap_pages);
  * Used by page_zone() to look up the address of the struct zone whose
  * id is encoded in the upper bits of page->flags
  */
-struct zone *zone_table[1 << ZONETABLE_SHIFT];
+struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
 EXPORT_SYMBOL(zone_table);
 
 static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
@@ -329,7 +329,7 @@ static inline void free_pages_check(const char *function, struct page *page)
                        1 << PG_writeback )))
                bad_page(function, page);
        if (PageDirty(page))
-               ClearPageDirty(page);
+               __ClearPageDirty(page);
 }
 
 /*
@@ -897,12 +897,6 @@ rebalance:
        cond_resched();
 
        if (likely(did_some_progress)) {
-               /*
-                * Go through the zonelist yet one more time, keep
-                * very high watermark here, this is only to catch
-                * a parallel oom killing, we must fail if we're still
-                * under heavy pressure.
-                */
                for (i = 0; (z = zones[i]) != NULL; i++) {
                        if (!zone_watermark_ok(z, order, z->pages_min,
                                               classzone_idx, can_try_harder,
@@ -936,7 +930,7 @@ rebalance:
                                goto got_pg;
                }
 
-               out_of_memory(gfp_mask);
+               out_of_memory(gfp_mask, order);
                goto restart;
        }
 
@@ -1067,20 +1061,19 @@ unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
 
 static unsigned int nr_free_zone_pages(int offset)
 {
-       pg_data_t *pgdat;
+       /* Just pick one node, since fallback list is circular */
+       pg_data_t *pgdat = NODE_DATA(numa_node_id());
        unsigned int sum = 0;
 
-       for_each_pgdat(pgdat) {
-               struct zonelist *zonelist = pgdat->node_zonelists + offset;
-               struct zone **zonep = zonelist->zones;
-               struct zone *zone;
+       struct zonelist *zonelist = pgdat->node_zonelists + offset;
+       struct zone **zonep = zonelist->zones;
+       struct zone *zone;
 
-               for (zone = *zonep++; zone; zone = *zonep++) {
-                       unsigned long size = zone->present_pages;
-                       unsigned long high = zone->pages_high;
-                       if (size > high)
-                               sum += size - high;
-               }
+       for (zone = *zonep++; zone; zone = *zonep++) {
+               unsigned long size = zone->present_pages;
+               unsigned long high = zone->pages_high;
+               if (size > high)
+                       sum += size - high;
        }
 
        return sum;
@@ -1137,19 +1130,20 @@ EXPORT_SYMBOL(nr_pagecache);
 DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
 #endif
 
-void __get_page_state(struct page_state *ret, int nr)
+void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 {
        int cpu = 0;
 
        memset(ret, 0, sizeof(*ret));
+       cpus_and(*cpumask, *cpumask, cpu_online_map);
 
-       cpu = first_cpu(cpu_online_map);
+       cpu = first_cpu(*cpumask);
        while (cpu < NR_CPUS) {
                unsigned long *in, *out, off;
 
                in = (unsigned long *)&per_cpu(page_states, cpu);
 
-               cpu = next_cpu(cpu, cpu_online_map);
+               cpu = next_cpu(cpu, *cpumask);
 
                if (cpu < NR_CPUS)
                        prefetch(&per_cpu(page_states, cpu));
@@ -1160,19 +1154,33 @@ void __get_page_state(struct page_state *ret, int nr)
        }
 }
 
+void get_page_state_node(struct page_state *ret, int node)
+{
+       int nr;
+       cpumask_t mask = node_to_cpumask(node);
+
+       nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+       nr /= sizeof(unsigned long);
+
+       __get_page_state(ret, nr+1, &mask);
+}
+
 void get_page_state(struct page_state *ret)
 {
        int nr;
+       cpumask_t mask = CPU_MASK_ALL;
 
        nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
        nr /= sizeof(unsigned long);
 
-       __get_page_state(ret, nr + 1);
+       __get_page_state(ret, nr + 1, &mask);
 }
 
 void get_full_page_state(struct page_state *ret)
 {
-       __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
+       cpumask_t mask = CPU_MASK_ALL;
+
+       __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
 }
 
 unsigned long __read_page_state(unsigned long offset)
@@ -1867,7 +1875,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
                unsigned long *zones_size, unsigned long *zholes_size)
 {
        unsigned long i, j;
-       const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
        int cpu, nid = pgdat->node_id;
        unsigned long zone_start_pfn = pgdat->node_start_pfn;
 
@@ -1917,7 +1924,7 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
                zone->nr_scan_inactive = 0;
                zone->nr_active = 0;
                zone->nr_inactive = 0;
-               atomic_set(&zone->reclaim_in_progress, -1);
+               atomic_set(&zone->reclaim_in_progress, 0);
                if (!size)
                        continue;
 
@@ -1940,9 +1947,6 @@ static void __init free_area_init_core(struct pglist_data *pgdat,
                zone->zone_mem_map = pfn_to_page(zone_start_pfn);
                zone->zone_start_pfn = zone_start_pfn;
 
-               if ((zone_start_pfn) & (zone_required_alignment-1))
-                       printk(KERN_CRIT "BUG: wrong zone alignment, it will crash\n");
-
                memmap_init(size, nid, j, zone_start_pfn);
 
                zonetable_add(zone, nid, j, zone_start_pfn, size);