[PATCH] oom: cpuset hint

[linux-2.6-microblaze.git] / mm / memory_hotplug.c

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0b11a85..c373195 100644 (file)
--- 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>
@@ -53,6 +52,9 @@ static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
        int nr_pages = PAGES_PER_SECTION;
        int ret;
 
+       if (pfn_valid(phys_start_pfn))
+               return -EEXIST;
+
        ret = sparse_add_one_section(zone, phys_start_pfn, nr_pages);
 
        if (ret < 0)
@@ -77,15 +79,22 @@ int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
 {
        unsigned long i;
        int err = 0;
-
-       for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
-               err = __add_section(zone, phys_start_pfn + i);
-
-               /* We want to keep adding the rest of the
-                * sections if the first ones already exist
+       int start_sec, end_sec;
+       /* during initialize mem_map, align hot-added range to section */
+       start_sec = pfn_to_section_nr(phys_start_pfn);
+       end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
+
+       for (i = start_sec; i <= end_sec; i++) {
+               err = __add_section(zone, i << PFN_SECTION_SHIFT);
+
+               /*
+                * EEXIST is finally dealed with by ioresource collision
+                * check. see add_memory() => register_memory_resource()
+                * Warning will be printed if there is collision.
                 */
                if (err && (err != -EEXIST))
                        break;
+               err = 0;
        }
 
        return err;
@@ -127,6 +136,9 @@ 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;
 
@@ -149,10 +161,27 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
        if (!populated_zone(zone))
                need_zonelists_rebuild = 1;
 
-       for (i = 0; i < nr_pages; i++) {
-               struct page *page = pfn_to_page(pfn + i);
-               online_page(page);
-               onlined_pages++;
+       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 ((res.start < res.end) && (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;
@@ -194,10 +223,9 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 }
 
 /* add this memory to iomem resource */
-static void register_memory_resource(u64 start, u64 size)
+static struct resource *register_memory_resource(u64 start, u64 size)
 {
        struct resource *res;
-
        res = kzalloc(sizeof(struct resource), GFP_KERNEL);
        BUG_ON(!res);
 
@@ -209,7 +237,18 @@ static void register_memory_resource(u64 start, u64 size)
                printk("System RAM resource %llx - %llx cannot be added\n",
                (unsigned long long)res->start, (unsigned long long)res->end);
                kfree(res);
+               res = NULL;
        }
+       return res;
+}
+
+static void release_memory_resource(struct resource *res)
+{
+       if (!res)
+               return;
+       release_resource(res);
+       kfree(res);
+       return;
 }
 
 
@@ -218,8 +257,13 @@ int add_memory(int nid, u64 start, u64 size)
 {
        pg_data_t *pgdat = NULL;
        int new_pgdat = 0;
+       struct resource *res;
        int ret;
 
+       res = register_memory_resource(start, size);
+       if (!res)
+               return -EEXIST;
+
        if (!node_online(nid)) {
                pgdat = hotadd_new_pgdat(nid, start);
                if (!pgdat)
@@ -236,17 +280,26 @@ int add_memory(int nid, u64 start, u64 size)
        if (ret < 0)
                goto error;
 
-       /* we online node here. we have no error path from here. */
+       /* we online node here. we can't roll back from here. */
        node_set_online(nid);
 
-       /* register this memory as resource */
-       register_memory_resource(start, size);
+       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);
+       }
 
        return ret;
 error:
        /* rollback pgdat allocation and others */
        if (new_pgdat)
                rollback_node_hotadd(nid, pgdat);
+       if (res)
+               release_memory_resource(res);
 
        return ret;
 }