mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset

For each new populated zone of hotadded node, need to update its pagesets
with dynamically allocated per_cpu_pageset struct for all possible CPUs:

    1) Detach zone->pageset from the shared boot_pageset
       at end of __build_all_zonelists().

    2) Use mutex to protect zone->pageset when it's still
       shared in onlined_pages()

Otherwises, multiple zones of different nodes would share same boot strapping
boot_pageset for same CPU, which will finally cause below kernel panic:

  ------------[ cut here ]------------
  kernel BUG at mm/page_alloc.c:1239!
  invalid opcode: 0000 [#1] SMP
  ...
  Call Trace:
   [<ffffffff811300c1>] __alloc_pages_nodemask+0x131/0x7b0
   [<ffffffff81162e67>] alloc_pages_current+0x87/0xd0
   [<ffffffff81128407>] __page_cache_alloc+0x67/0x70
   [<ffffffff811325f0>] __do_page_cache_readahead+0x120/0x260
   [<ffffffff81132751>] ra_submit+0x21/0x30
   [<ffffffff811329c6>] ondemand_readahead+0x166/0x2c0
   [<ffffffff81132ba0>] page_cache_async_readahead+0x80/0xa0
   [<ffffffff8112a0e4>] generic_file_aio_read+0x364/0x670
   [<ffffffff81266cfa>] nfs_file_read+0xca/0x130
   [<ffffffff8117b20a>] do_sync_read+0xfa/0x140
   [<ffffffff8117bf75>] vfs_read+0xb5/0x1a0
   [<ffffffff8117c151>] sys_read+0x51/0x80
   [<ffffffff8103c032>] system_call_fastpath+0x16/0x1b
  RIP  [<ffffffff8112ff13>] get_page_from_freelist+0x883/0x900
   RSP <ffff88000d1e78a8>
  ---[ end trace 4bda28328b9990db ]

[akpm@linux-foundation.org: merge fix]
Signed-off-by: Haicheng Li <haicheng.li@linux.intel.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Andi Kleen <andi.kleen@intel.com>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 29 insertions, 12 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index f6f2c505fa7e..a367ed5bb3fe 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -652,7 +652,7 @@ typedef struct pglist_data {
 
 void get_zone_counts(unsigned long *active, unsigned long *inactive,
                         unsigned long *free);
-void build_all_zonelists(void);
+void build_all_zonelists(void *data);
 void wakeup_kswapd(struct zone *zone, int order);
 int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
                 int classzone_idx, int alloc_flags);
diff --git a/init/main.c b/init/main.c
index 22881b5e95e3..3bdb152f412f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -567,7 +567,7 @@ asmlinkage void __init start_kernel(void)
         setup_per_cpu_areas();
         smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
 
-        build_all_zonelists();
+        build_all_zonelists(NULL);
         page_alloc_init();
 
         printk(KERN_NOTICE "Kernel command line: %s\n", boot_command_line);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a3fbcc0a0abc..3e8b3ba27175 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -358,7 +358,7 @@ int __cpuinit cpu_up(unsigned int cpu)
         }
 
         if (pgdat->node_zonelists->_zonerefs->zone == NULL)
-                build_all_zonelists();
+                build_all_zonelists(NULL);
 #endif
 
         cpu_maps_update_begin();
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 85eb4d342ac5..089cc97aed3c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -389,6 +389,11 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         int nid;
         int ret;
         struct memory_notify arg;
+        /*
+         * mutex to protect zone->pageset when it's still shared
+         * in onlined_pages()
+         */
+        static DEFINE_MUTEX(zone_pageset_mutex);
 
         arg.start_pfn = pfn;
         arg.nr_pages = nr_pages;
@@ -415,12 +420,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
          * This means the page allocator ignores this zone.
          * So, zonelist must be updated after online.
          */
+        mutex_lock(&zone_pageset_mutex);
         if (!populated_zone(zone))
                 need_zonelists_rebuild = 1;
 
         ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
                 online_pages_range);
         if (ret) {
+                mutex_unlock(&zone_pageset_mutex);
                 printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
                         nr_pages, pfn);
                 memory_notify(MEM_CANCEL_ONLINE, &arg);
@@ -429,8 +436,12 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 
         zone->present_pages += onlined_pages;
         zone->zone_pgdat->node_present_pages += onlined_pages;
+        if (need_zonelists_rebuild)
+                build_all_zonelists(zone);
+        else
+                zone_pcp_update(zone);
 
-        zone_pcp_update(zone);
+        mutex_unlock(&zone_pageset_mutex);
         setup_per_zone_wmarks();
         calculate_zone_inactive_ratio(zone);
         if (onlined_pages) {
@@ -438,10 +449,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
                 node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
         }
 
-        if (need_zonelists_rebuild)
-                build_all_zonelists();
-        else
-                vm_total_pages = nr_free_pagecache_pages();
+        vm_total_pages = nr_free_pagecache_pages();
 
         writeback_set_ratelimit();
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 595d0ac211e2..21c52d2d8624 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2572,7 +2572,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
                                 NUMA_ZONELIST_ORDER_LEN);
                         user_zonelist_order = oldval;
                 } else if (oldval != user_zonelist_order)
-                        build_all_zonelists();
+                        build_all_zonelists(NULL);
         }
 out:
         mutex_unlock(&zl_order_mutex);
@@ -2922,9 +2922,10 @@ static void build_zonelist_cache(pg_data_t *pgdat)
  */
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
+static void setup_zone_pageset(struct zone *zone);
 
 /* return values int ....just for stop_machine() */
-static int __build_all_zonelists(void *dummy)
+static __init_refok int __build_all_zonelists(void *data)
 {
         int nid;
         int cpu;
@@ -2939,6 +2940,14 @@ static int __build_all_zonelists(void *dummy)
                 build_zonelist_cache(pgdat);
         }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+        /* Setup real pagesets for the new zone */
+        if (data) {
+                struct zone *zone = data;
+                setup_zone_pageset(zone);
+        }
+#endif
+
         /*
          * Initialize the boot_pagesets that are going to be used
          * for bootstrapping processors. The real pagesets for
@@ -2958,7 +2967,7 @@ static int __build_all_zonelists(void *dummy)
         return 0;
 }
 
-void build_all_zonelists(void)
+void build_all_zonelists(void *data)
 {
         set_zonelist_order();
 
@@ -2969,7 +2978,7 @@ void build_all_zonelists(void)
         } else {
                 /* we have to stop all cpus to guarantee there is no user
                    of zonelist */
-                stop_machine(__build_all_zonelists, NULL, NULL);
+                stop_machine(__build_all_zonelists, data, NULL);
                 /* cpuset refresh routine should be here */
         }
         vm_total_pages = nr_free_pagecache_pages();