memory hotplug: release memory regions in PAGES_PER_SECTION chunks

[linux-2.6-omap-h63xx.git] / mm / memory_hotplug.c

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0fb05b258f0c037050acd7d294b8b573addc3f63..6837a1014372556c7dd78d66d9ba9ea9cb931832 100644 (file)
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -26,6 +26,7 @@
 #include <linux/delay.h>
 #include <linux/migrate.h>
 #include <linux/page-isolation.h>
+#include <linux/pfn.h>
 
 #include <asm/tlbflush.h>
 
@@ -323,11 +324,11 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
        BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
        BUG_ON(nr_pages % PAGES_PER_SECTION);
 
-       release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE);
-
        sections_to_remove = nr_pages / PAGES_PER_SECTION;
        for (i = 0; i < sections_to_remove; i++) {
                unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
+               release_mem_region(pfn << PAGE_SHIFT,
+                                  PAGES_PER_SECTION << PAGE_SHIFT);
                ret = __remove_section(zone, __pfn_to_section(pfn));
                if (ret)
                        break;
@@ -429,7 +430,9 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 
        if (need_zonelists_rebuild)
                build_all_zonelists();
-       vm_total_pages = nr_free_pagecache_pages();
+       else
+               vm_total_pages = nr_free_pagecache_pages();
+
        writeback_set_ratelimit();
 
        if (onlined_pages)
@@ -520,6 +523,66 @@ error:
 EXPORT_SYMBOL_GPL(add_memory);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
+/*
+ * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
+ * set and the size of the free page is given by page_order(). Using this,
+ * the function determines if the pageblock contains only free pages.
+ * Due to buddy contraints, a free page at least the size of a pageblock will
+ * be located at the start of the pageblock
+ */
+static inline int pageblock_free(struct page *page)
+{
+       return PageBuddy(page) && page_order(page) >= pageblock_order;
+}
+
+/* Return the start of the next active pageblock after a given page */
+static struct page *next_active_pageblock(struct page *page)
+{
+       int pageblocks_stride;
+
+       /* Ensure the starting page is pageblock-aligned */
+       BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
+
+       /* Move forward by at least 1 * pageblock_nr_pages */
+       pageblocks_stride = 1;
+
+       /* If the entire pageblock is free, move to the end of free page */
+       if (pageblock_free(page))
+               pageblocks_stride += page_order(page) - pageblock_order;
+
+       return page + (pageblocks_stride * pageblock_nr_pages);
+}
+
+/* Checks if this range of memory is likely to be hot-removable. */
+int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
+{
+       int type;
+       struct page *page = pfn_to_page(start_pfn);
+       struct page *end_page = page + nr_pages;
+
+       /* Check the starting page of each pageblock within the range */
+       for (; page < end_page; page = next_active_pageblock(page)) {
+               type = get_pageblock_migratetype(page);
+
+               /*
+                * A pageblock containing MOVABLE or free pages is considered
+                * removable
+                */
+               if (type != MIGRATE_MOVABLE && !pageblock_free(page))
+                       return 0;
+
+               /*
+                * A pageblock starting with a PageReserved page is not
+                * considered removable.
+                */
+               if (PageReserved(page))
+                       return 0;
+       }
+
+       /* All pageblocks in the memory block are likely to be hot-removable */
+       return 1;
+}
+
 /*
  * Confirm all pages in a range [start, end) is belongs to the same zone.
  */
@@ -595,8 +658,9 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
                 * We can skip free pages. And we can only deal with pages on
                 * LRU.
                 */
-               ret = isolate_lru_page(page, &source);
+               ret = isolate_lru_page(page);
                if (!ret) { /* Success */
+                       list_add_tail(&page->lru, &source);
                        move_pages--;
                } else {
                        /* Becasue we don't have big zone->lock. we should
@@ -787,10 +851,19 @@ failed_removal:
 
        return ret;
 }
+
+int remove_memory(u64 start, u64 size)
+{
+       unsigned long start_pfn, end_pfn;
+
+       start_pfn = PFN_DOWN(start);
+       end_pfn = start_pfn + PFN_DOWN(size);
+       return offline_pages(start_pfn, end_pfn, 120 * HZ);
+}
 #else
 int remove_memory(u64 start, u64 size)
 {
        return -EINVAL;
 }
-EXPORT_SYMBOL_GPL(remove_memory);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
+EXPORT_SYMBOL_GPL(remove_memory);