Merge ../linux-2.6

[pandora-kernel.git] / mm / rmap.c

diff --git a/mm/rmap.c b/mm/rmap.c
index 6f3f7db..df2c41c 100644 (file)
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -20,20 +20,20 @@
 /*
  * Lock ordering in mm:
  *
- * inode->i_sem        (while writing or truncating, not reading or faulting)
+ * inode->i_mutex      (while writing or truncating, not reading or faulting)
  *   inode->i_alloc_sem
  *
  * When a page fault occurs in writing from user to file, down_read
- * of mmap_sem nests within i_sem; in sys_msync, i_sem nests within
- * down_read of mmap_sem; i_sem and down_write of mmap_sem are never
- * taken together; in truncation, i_sem is taken outermost.
+ * of mmap_sem nests within i_mutex; in sys_msync, i_mutex nests within
+ * down_read of mmap_sem; i_mutex and down_write of mmap_sem are never
+ * taken together; in truncation, i_mutex is taken outermost.
  *
  * mm->mmap_sem
  *   page->flags PG_locked (lock_page)
  *     mapping->i_mmap_lock
  *       anon_vma->lock
  *         mm->page_table_lock or pte_lock
- *           zone->lru_lock (in mark_page_accessed)
+ *           zone->lru_lock (in mark_page_accessed, isolate_lru_page)
  *           swap_lock (in swap_duplicate, swap_info_get)
  *             mmlist_lock (in mmput, drain_mmlist and others)
  *             mapping->private_lock (in __set_page_dirty_buffers)
@@ -52,6 +52,7 @@
 #include <linux/init.h>
 #include <linux/rmap.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #include <asm/tlbflush.h>
 
@@ -205,6 +206,36 @@ out:
        return anon_vma;
 }
 
+#ifdef CONFIG_MIGRATION
+/*
+ * Remove an anonymous page from swap replacing the swap pte's
+ * through real pte's pointing to valid pages and then releasing
+ * the page from the swap cache.
+ *
+ * Must hold page lock on page.
+ */
+void remove_from_swap(struct page *page)
+{
+       struct anon_vma *anon_vma;
+       struct vm_area_struct *vma;
+
+       if (!PageAnon(page) || !PageSwapCache(page))
+               return;
+
+       anon_vma = page_lock_anon_vma(page);
+       if (!anon_vma)
+               return;
+
+       list_for_each_entry(vma, &anon_vma->head, anon_vma_node)
+               remove_vma_swap(vma, page);
+
+       spin_unlock(&anon_vma->lock);
+
+       delete_from_swap_cache(page);
+}
+EXPORT_SYMBOL(remove_from_swap);
+#endif
+
 /*
  * At what user virtual address is page expected in vma?
  */
@@ -514,6 +545,13 @@ void page_add_file_rmap(struct page *page)
 void page_remove_rmap(struct page *page)
 {
        if (atomic_add_negative(-1, &page->_mapcount)) {
+               if (page_mapcount(page) < 0) {
+                       printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
+                       printk (KERN_EMERG "  page->flags = %lx\n", page->flags);
+                       printk (KERN_EMERG "  page->count = %x\n", page_count(page));
+                       printk (KERN_EMERG "  page->mapping = %p\n", page->mapping);
+               }
+
                BUG_ON(page_mapcount(page) < 0);
                /*
                 * It would be tidy to reset the PageAnon mapping here,
@@ -534,7 +572,8 @@ void page_remove_rmap(struct page *page)
  * Subfunctions of try_to_unmap: try_to_unmap_one called
  * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
  */
-static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
+static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
+                               int ignore_refs)
 {
        struct mm_struct *mm = vma->vm_mm;
        unsigned long address;
@@ -557,7 +596,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
         * skipped over this mm) then we should reactivate it.
         */
        if ((vma->vm_flags & VM_LOCKED) ||
-                       ptep_clear_flush_young(vma, address, pte)) {
+                       (ptep_clear_flush_young(vma, address, pte)
+                               && !ignore_refs)) {
                ret = SWAP_FAIL;
                goto out_unmap;
        }
@@ -691,7 +731,7 @@ static void try_to_unmap_cluster(unsigned long cursor,
        pte_unmap_unlock(pte - 1, ptl);
 }
 
-static int try_to_unmap_anon(struct page *page)
+static int try_to_unmap_anon(struct page *page, int ignore_refs)
 {
        struct anon_vma *anon_vma;
        struct vm_area_struct *vma;
@@ -702,7 +742,7 @@ static int try_to_unmap_anon(struct page *page)
                return ret;
 
        list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-               ret = try_to_unmap_one(page, vma);
+               ret = try_to_unmap_one(page, vma, ignore_refs);
                if (ret == SWAP_FAIL || !page_mapped(page))
                        break;
        }
@@ -719,7 +759,7 @@ static int try_to_unmap_anon(struct page *page)
  *
  * This function is only called from try_to_unmap for object-based pages.
  */
-static int try_to_unmap_file(struct page *page)
+static int try_to_unmap_file(struct page *page, int ignore_refs)
 {
        struct address_space *mapping = page->mapping;
        pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -733,7 +773,7 @@ static int try_to_unmap_file(struct page *page)
 
        spin_lock(&mapping->i_mmap_lock);
        vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
-               ret = try_to_unmap_one(page, vma);
+               ret = try_to_unmap_one(page, vma, ignore_refs);
                if (ret == SWAP_FAIL || !page_mapped(page))
                        goto out;
        }
@@ -818,16 +858,16 @@ out:
  * SWAP_AGAIN  - we missed a mapping, try again later
  * SWAP_FAIL   - the page is unswappable
  */
-int try_to_unmap(struct page *page)
+int try_to_unmap(struct page *page, int ignore_refs)
 {
        int ret;
 
        BUG_ON(!PageLocked(page));
 
        if (PageAnon(page))
-               ret = try_to_unmap_anon(page);
+               ret = try_to_unmap_anon(page, ignore_refs);
        else
-               ret = try_to_unmap_file(page);
+               ret = try_to_unmap_file(page, ignore_refs);
 
        if (!page_mapped(page))
                ret = SWAP_SUCCESS;