Merge commit 'c104f1fa1ecf4ee0fc06e31b1f77630b2551be81' into stable/for-linus-3.4

* commit 'c104f1fa1ecf4ee0fc06e31b1f77630b2551be81': (14566 commits)
  cpufreq: OMAP: fix build errors: depends on ARCH_OMAP2PLUS
  sparc64: Eliminate obsolete __handle_softirq() function
  sparc64: Fix bootup crash on sun4v.
  kconfig: delete last traces of __enabled_ from autoconf.h
  Revert "kconfig: fix __enabled_ macros definition for invisible and un-selected symbols"
  kconfig: fix IS_ENABLED to not require all options to be defined
  irq_domain: fix type mismatch in debugfs output format
  staging: android: fix mem leaks in __persistent_ram_init()
  staging: vt6656: Don't leak memory in drivers/staging/vt6656/ioctl.c::private_ioctl()
  staging: iio: hmc5843: Fix crash in probe function.
  panic: fix stack dump print on direct call to panic()
  drivers/rtc/rtc-pl031.c: enable clock on all ST variants
  Revert "mm: vmscan: fix misused nr_reclaimed in shrink_mem_cgroup_zone()"
  hugetlb: fix race condition in hugetlb_fault()
  drivers/rtc/rtc-twl.c: use static register while reading time
  drivers/rtc/rtc-s3c.c: add placeholder for driver private data
  drivers/rtc/rtc-s3c.c: fix compilation error
  MAINTAINERS: add PCDP console maintainer
  memcg: do not open code accesses to res_counter members
  drivers/rtc/rtc-efi.c: fix section mismatch warning
  ...

1 files changed, 132 insertions, 42 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 794e6715c226..a712fb9e04ce 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1161,11 +1161,47 @@ void drain_local_pages(void *arg)
 }
 
 /*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
  */
 void drain_all_pages(void)
 {
-        on_each_cpu(drain_local_pages, NULL, 1);
+        int cpu;
+        struct per_cpu_pageset *pcp;
+        struct zone *zone;
+
+        /*
+         * Allocate in the BSS so we wont require allocation in
+         * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+         */
+        static cpumask_t cpus_with_pcps;
+
+        /*
+         * We don't care about racing with CPU hotplug event
+         * as offline notification will cause the notified
+         * cpu to drain that CPU pcps and on_each_cpu_mask
+         * disables preemption as part of its processing
+         */
+        for_each_online_cpu(cpu) {
+                bool has_pcps = false;
+                for_each_populated_zone(zone) {
+                        pcp = per_cpu_ptr(zone->pageset, cpu);
+                        if (pcp->pcp.count) {
+                                has_pcps = true;
+                                break;
+                        }
+                }
+                if (has_pcps)
+                        cpumask_set_cpu(cpu, &cpus_with_pcps);
+                else
+                        cpumask_clear_cpu(cpu, &cpus_with_pcps);
+        }
+        on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1968,7 +2004,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
                         goto out;
         }
         /* Exhausted what can be done so it's blamo time */
-        out_of_memory(zonelist, gfp_mask, order, nodemask);
+        out_of_memory(zonelist, gfp_mask, order, nodemask, false);
 
 out:
         clear_zonelist_oom(zonelist, gfp_mask);
@@ -1981,14 +2017,20 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
         struct zonelist *zonelist, enum zone_type high_zoneidx,
         nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-        int migratetype, unsigned long *did_some_progress,
-        bool sync_migration)
+        int migratetype, bool sync_migration,
+        bool *deferred_compaction,
+        unsigned long *did_some_progress)
 {
         struct page *page;
 
-        if (!order || compaction_deferred(preferred_zone))
+        if (!order)
                 return NULL;
 
+        if (compaction_deferred(preferred_zone, order)) {
+                *deferred_compaction = true;
+                return NULL;
+        }
+
         current->flags |= PF_MEMALLOC;
         *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
                                                 nodemask, sync_migration);
@@ -2006,6 +2048,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                 if (page) {
                         preferred_zone->compact_considered = 0;
                         preferred_zone->compact_defer_shift = 0;
+                        if (order >= preferred_zone->compact_order_failed)
+                                preferred_zone->compact_order_failed = order + 1;
                         count_vm_event(COMPACTSUCCESS);
                         return page;
                 }
@@ -2016,7 +2060,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
                  * but not enough to satisfy watermarks.
                  */
                 count_vm_event(COMPACTFAIL);
-                defer_compaction(preferred_zone);
+
+                /*
+                 * As async compaction considers a subset of pageblocks, only
+                 * defer if the failure was a sync compaction failure.
+                 */
+                if (sync_migration)
+                        defer_compaction(preferred_zone, order);
 
                 cond_resched();
         }
@@ -2028,8 +2078,9 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
         struct zonelist *zonelist, enum zone_type high_zoneidx,
         nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-        int migratetype, unsigned long *did_some_progress,
-        bool sync_migration)
+        int migratetype, bool sync_migration,
+        bool *deferred_compaction,
+        unsigned long *did_some_progress)
 {
         return NULL;
 }
@@ -2179,6 +2230,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
         unsigned long pages_reclaimed = 0;
         unsigned long did_some_progress;
         bool sync_migration = false;
+        bool deferred_compaction = false;
 
         /*
          * In the slowpath, we sanity check order to avoid ever trying to
@@ -2259,12 +2311,22 @@ rebalance:
                                         zonelist, high_zoneidx,
                                         nodemask,
                                         alloc_flags, preferred_zone,
-                                        migratetype, &did_some_progress,
-                                        sync_migration);
+                                        migratetype, sync_migration,
+                                        &deferred_compaction,
+                                        &did_some_progress);
         if (page)
                 goto got_pg;
         sync_migration = true;
 
+        /*
+         * If compaction is deferred for high-order allocations, it is because
+         * sync compaction recently failed. In this is the case and the caller
+         * has requested the system not be heavily disrupted, fail the
+         * allocation now instead of entering direct reclaim
+         */
+        if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+                goto nopage;
+
         /* Try direct reclaim and then allocating */
         page = __alloc_pages_direct_reclaim(gfp_mask, order,
                                         zonelist, high_zoneidx,
@@ -2282,6 +2344,10 @@ rebalance:
                 if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
                         if (oom_killer_disabled)
                                 goto nopage;
+                        /* Coredumps can quickly deplete all memory reserves */
+                        if ((current->flags & PF_DUMPCORE) &&
+                            !(gfp_mask & __GFP_NOFAIL))
+                                goto nopage;
                         page = __alloc_pages_may_oom(gfp_mask, order,
                                         zonelist, high_zoneidx,
                                         nodemask, preferred_zone,
@@ -2328,8 +2394,9 @@ rebalance:
                                         zonelist, high_zoneidx,
                                         nodemask,
                                         alloc_flags, preferred_zone,
-                                        migratetype, &did_some_progress,
-                                        sync_migration);
+                                        migratetype, sync_migration,
+                                        &deferred_compaction,
+                                        &did_some_progress);
                 if (page)
                         goto got_pg;
         }
@@ -2353,8 +2420,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
         enum zone_type high_zoneidx = gfp_zone(gfp_mask);
         struct zone *preferred_zone;
-        struct page *page;
+        struct page *page = NULL;
         int migratetype = allocflags_to_migratetype(gfp_mask);
+        unsigned int cpuset_mems_cookie;
 
         gfp_mask &= gfp_allowed_mask;
 
@@ -2373,15 +2441,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
         if (unlikely(!zonelist->_zonerefs->zone))
                 return NULL;
 
-        get_mems_allowed();
+retry_cpuset:
+        cpuset_mems_cookie = get_mems_allowed();
+
         /* The preferred zone is used for statistics later */
         first_zones_zonelist(zonelist, high_zoneidx,
                                 nodemask ? : &cpuset_current_mems_allowed,
                                 &preferred_zone);
-        if (!preferred_zone) {
-                put_mems_allowed();
-                return NULL;
-        }
+        if (!preferred_zone)
+                goto out;
 
         /* First allocation attempt */
         page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2391,9 +2459,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
                 page = __alloc_pages_slowpath(gfp_mask, order,
                                 zonelist, high_zoneidx, nodemask,
                                 preferred_zone, migratetype);
-        put_mems_allowed();
 
         trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+        /*
+         * When updating a task's mems_allowed, it is possible to race with
+         * parallel threads in such a way that an allocation can fail while
+         * the mask is being updated. If a page allocation is about to fail,
+         * check if the cpuset changed during allocation and if so, retry.
+         */
+        if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+                goto retry_cpuset;
+
         return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2607,13 +2685,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
         bool ret = false;
+        unsigned int cpuset_mems_cookie;
 
         if (!(flags & SHOW_MEM_FILTER_NODES))
                 goto out;
 
-        get_mems_allowed();
-        ret = !node_isset(nid, cpuset_current_mems_allowed);
-        put_mems_allowed();
+        do {
+                cpuset_mems_cookie = get_mems_allowed();
+                ret = !node_isset(nid, cpuset_current_mems_allowed);
+        } while (!put_mems_allowed(cpuset_mems_cookie));
 out:
         return ret;
 }
@@ -3900,18 +3980,6 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
         }
 }
 
-int __init add_from_early_node_map(struct range *range, int az,
-                                   int nr_range, int nid)
-{
-        unsigned long start_pfn, end_pfn;
-        int i;
-
-        /* need to go over early_node_map to find out good range for node */
-        for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL)
-                nr_range = add_range(range, az, nr_range, start_pfn, end_pfn);
-        return nr_range;
-}
-
 /**
  * sparse_memory_present_with_active_regions - Call memory_present for each active range
  * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
@@ -4237,7 +4305,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
         for (j = 0; j < MAX_NR_ZONES; j++) {
                 struct zone *zone = pgdat->node_zones + j;
                 unsigned long size, realsize, memmap_pages;
-                enum lru_list l;
+                enum lru_list lru;
 
                 size = zone_spanned_pages_in_node(nid, j, zones_size);
                 realsize = size - zone_absent_pages_in_node(nid, j,
@@ -4287,8 +4355,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
                 zone->zone_pgdat = pgdat;
 
                 zone_pcp_init(zone);
-                for_each_lru(l)
-                        INIT_LIST_HEAD(&zone->lru[l].list);
+                for_each_lru(lru)
+                        INIT_LIST_HEAD(&zone->lruvec.lists[lru]);
                 zone->reclaim_stat.recent_rotated[0] = 0;
                 zone->reclaim_stat.recent_rotated[1] = 0;
                 zone->reclaim_stat.recent_scanned[0] = 0;
@@ -4496,7 +4564,7 @@ static unsigned long __init early_calculate_totalpages(void)
  * memory. When they don't, some nodes will have more kernelcore than
  * others
  */
-static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+static void __init find_zone_movable_pfns_for_nodes(void)
 {
         int i, nid;
         unsigned long usable_startpfn;
@@ -4642,8 +4710,10 @@ static void check_for_regular_memory(pg_data_t *pgdat)
 
         for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
                 struct zone *zone = &pgdat->node_zones[zone_type];
-                if (zone->present_pages)
+                if (zone->present_pages) {
                         node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+                        break;
+                }
         }
 #endif
 }
@@ -4686,7 +4756,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 
         /* Find the PFNs that ZONE_MOVABLE begins at in each node */
         memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
-        find_zone_movable_pfns_for_nodes(zone_movable_pfn);
+        find_zone_movable_pfns_for_nodes();
 
         /* Print out the zone ranges */
         printk("Zone PFN ranges:\n");
@@ -4796,6 +4866,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self,
         int cpu = (unsigned long)hcpu;
 
         if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+                lru_add_drain_cpu(cpu);
                 drain_pages(cpu);
 
                 /*
@@ -5209,6 +5280,7 @@ void *__init alloc_large_system_hash(const char *tablename,
                 max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
                 do_div(max, bucketsize);
         }
+        max = min(max, 0x80000000ULL);
 
         if (numentries > max)
                 numentries = max;
@@ -5386,7 +5458,25 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count)
 
 bool is_pageblock_removable_nolock(struct page *page)
 {
-        struct zone *zone = page_zone(page);
+        struct zone *zone;
+        unsigned long pfn;
+
+        /*
+         * We have to be careful here because we are iterating over memory
+         * sections which are not zone aware so we might end up outside of
+         * the zone but still within the section.
+         * We have to take care about the node as well. If the node is offline
+         * its NODE_DATA will be NULL - see page_zone.
+         */
+        if (!node_online(page_to_nid(page)))
+                return false;
+
+        zone = page_zone(page);
+        pfn = page_to_pfn(page);
+        if (zone->zone_start_pfn > pfn ||
+                        zone->zone_start_pfn + zone->spanned_pages <= pfn)
+                return false;
+
         return __count_immobile_pages(zone, page, 0);
 }