Merge rsync://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	include/linux/kernel.h

1 files changed, 147 insertions, 7 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 70df5c0d957e..01c9fb97c619 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -4,7 +4,6 @@
  *  Copyright (C)
  */
 
-#include <linux/config.h>
 #include <linux/stddef.h>
 #include <linux/mm.h>
 #include <linux/swap.h>
@@ -21,12 +20,13 @@
 #include <linux/memory_hotplug.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
+#include <linux/ioport.h>
 
 #include <asm/tlbflush.h>
 
 extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
                           unsigned long size);
-static void __add_zone(struct zone *zone, unsigned long phys_start_pfn)
+static int __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 {
         struct pglist_data *pgdat = zone->zone_pgdat;
         int nr_pages = PAGES_PER_SECTION;
@@ -34,8 +34,15 @@ static void __add_zone(struct zone *zone, unsigned long phys_start_pfn)
         int zone_type;
 
         zone_type = zone - pgdat->node_zones;
+        if (!populated_zone(zone)) {
+                int ret = 0;
+                ret = init_currently_empty_zone(zone, phys_start_pfn, nr_pages);
+                if (ret < 0)
+                        return ret;
+        }
         memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
         zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
+        return 0;
 }
 
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
@@ -50,7 +57,11 @@ static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
         if (ret < 0)
                 return ret;
 
-        __add_zone(zone, phys_start_pfn);
+        ret = __add_zone(zone, phys_start_pfn);
+
+        if (ret < 0)
+                return ret;
+
         return register_new_memory(__pfn_to_section(phys_start_pfn));
 }
 
@@ -115,7 +126,11 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         unsigned long i;
         unsigned long flags;
         unsigned long onlined_pages = 0;
+        struct resource res;
+        u64 section_end;
+        unsigned long start_pfn;
         struct zone *zone;
+        int need_zonelists_rebuild = 0;
 
         /*
          * This doesn't need a lock to do pfn_to_page().
@@ -128,15 +143,140 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
         grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
         pgdat_resize_unlock(zone->zone_pgdat, &flags);
 
-        for (i = 0; i < nr_pages; i++) {
-                struct page *page = pfn_to_page(pfn + i);
-                online_page(page);
-                onlined_pages++;
+        /*
+         * If this zone is not populated, then it is not in zonelist.
+         * This means the page allocator ignores this zone.
+         * So, zonelist must be updated after online.
+         */
+        if (!populated_zone(zone))
+                need_zonelists_rebuild = 1;
+
+        res.start = (u64)pfn << PAGE_SHIFT;
+        res.end = res.start + ((u64)nr_pages << PAGE_SHIFT) - 1;
+        res.flags = IORESOURCE_MEM; /* we just need system ram */
+        section_end = res.end;
+
+        while (find_next_system_ram(&res) >= 0) {
+                start_pfn = (unsigned long)(res.start >> PAGE_SHIFT);
+                nr_pages = (unsigned long)
+                           ((res.end + 1 - res.start) >> PAGE_SHIFT);
+
+                if (PageReserved(pfn_to_page(start_pfn))) {
+                        /* this region's page is not onlined now */
+                        for (i = 0; i < nr_pages; i++) {
+                                struct page *page = pfn_to_page(start_pfn + i);
+                                online_page(page);
+                                onlined_pages++;
+                        }
+                }
+
+                res.start = res.end + 1;
+                res.end = section_end;
         }
         zone->present_pages += onlined_pages;
         zone->zone_pgdat->node_present_pages += onlined_pages;
 
         setup_per_zone_pages_min();
 
+        if (need_zonelists_rebuild)
+                build_all_zonelists();
+        vm_total_pages = nr_free_pagecache_pages();
         return 0;
 }
+
+static pg_data_t *hotadd_new_pgdat(int nid, u64 start)
+{
+        struct pglist_data *pgdat;
+        unsigned long zones_size[MAX_NR_ZONES] = {0};
+        unsigned long zholes_size[MAX_NR_ZONES] = {0};
+        unsigned long start_pfn = start >> PAGE_SHIFT;
+
+        pgdat = arch_alloc_nodedata(nid);
+        if (!pgdat)
+                return NULL;
+
+        arch_refresh_nodedata(nid, pgdat);
+
+        /* we can use NODE_DATA(nid) from here */
+
+        /* init node's zones as empty zones, we don't have any present pages.*/
+        free_area_init_node(nid, pgdat, zones_size, start_pfn, zholes_size);
+
+        return pgdat;
+}
+
+static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
+{
+        arch_refresh_nodedata(nid, NULL);
+        arch_free_nodedata(pgdat);
+        return;
+}
+
+/* add this memory to iomem resource */
+static void register_memory_resource(u64 start, u64 size)
+{
+        struct resource *res;
+
+        res = kzalloc(sizeof(struct resource), GFP_KERNEL);
+        BUG_ON(!res);
+
+        res->name = "System RAM";
+        res->start = start;
+        res->end = start + size - 1;
+        res->flags = IORESOURCE_MEM;
+        if (request_resource(&iomem_resource, res) < 0) {
+                printk("System RAM resource %llx - %llx cannot be added\n",
+                (unsigned long long)res->start, (unsigned long long)res->end);
+                kfree(res);
+        }
+}
+
+
+
+int add_memory(int nid, u64 start, u64 size)
+{
+        pg_data_t *pgdat = NULL;
+        int new_pgdat = 0;
+        int ret;
+
+        if (!node_online(nid)) {
+                pgdat = hotadd_new_pgdat(nid, start);
+                if (!pgdat)
+                        return -ENOMEM;
+                new_pgdat = 1;
+                ret = kswapd_run(nid);
+                if (ret)
+                        goto error;
+        }
+
+        /* call arch's memory hotadd */
+        ret = arch_add_memory(nid, start, size);
+
+        if (ret < 0)
+                goto error;
+
+        /* we online node here. we can't roll back from here. */
+        node_set_online(nid);
+
+        if (new_pgdat) {
+                ret = register_one_node(nid);
+                /*
+                 * If sysfs file of new node can't create, cpu on the node
+                 * can't be hot-added. There is no rollback way now.
+                 * So, check by BUG_ON() to catch it reluctantly..
+                 */
+                BUG_ON(ret);
+        }
+
+        /* register this memory as resource */
+        register_memory_resource(start, size);
+
+        return ret;
+error:
+        /* rollback pgdat allocation and others */
+        if (new_pgdat)
+                rollback_node_hotadd(nid, pgdat);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(add_memory);