[PATCH] catch valid mem range at onlining memory

This patch allows hot-add memory which is not aligned to section.

Now, hot-added memory has to be aligned to section size.  Considering big
section sized archs, this is not useful.

When hot-added memory is registerd as iomem resoruce by iomem resource
patch, we can make use of that information to detect valid memory range.

Note: With this, not-aligned memory can be registerd. To allow hot-add
      memory with holes, we have to do more work around add_memory().
      (It doesn't allows add memory to already existing mem section.)

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 65 insertions, 4 deletions

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index cd6bd001ba4e..edfc733b1575 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -105,6 +105,9 @@ extern int allocate_resource(struct resource *root, struct resource *new,
 int adjust_resource(struct resource *res, unsigned long start,
                     unsigned long size);
 
+/* get registered SYSTEM_RAM resources in specified area */
+extern int find_next_system_ram(struct resource *res);
+
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)    __request_region(&ioport_resource, (start), (n), (name))
 #define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name))
diff --git a/kernel/resource.c b/kernel/resource.c
index e3080fcc66a3..2404f9b0bc47 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -232,6 +232,44 @@ int release_resource(struct resource *old)
 
 EXPORT_SYMBOL(release_resource);
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Finds the lowest memory reosurce exists within [res->start.res->end)
+ * the caller must specify res->start, res->end, res->flags.
+ * If found, returns 0, res is overwritten, if not found, returns -1.
+ */
+int find_next_system_ram(struct resource *res)
+{
+        resource_size_t start, end;
+        struct resource *p;
+
+        BUG_ON(!res);
+
+        start = res->start;
+        end = res->end;
+
+        read_lock(&resource_lock);
+        for (p = iomem_resource.child; p ; p = p->sibling) {
+                /* system ram is just marked as IORESOURCE_MEM */
+                if (p->flags != res->flags)
+                        continue;
+                if (p->start > end) {
+                        p = NULL;
+                        break;
+                }
+                if (p->start >= start)
+                        break;
+        }
+        read_unlock(&resource_lock);
+        if (!p)
+                return -1;
+        /* copy data */
+        res->start = p->start;
+        res->end = p->end;
+        return 0;
+}
+#endif
+
 /*
  * Find empty slot in the resource tree given range and alignment.
  */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0b11a8543441..f13783e81eb6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -127,6 +127,9 @@ 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 +152,27 @@ 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 (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;