1 files changed, 77 insertions, 57 deletions

diff --git a/mm/rmap.c b/mm/rmap.c
index 914d04b98b..d85a99d28c 100644
--- 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)
@@ -225,7 +225,7 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 
 /*
  * At what user virtual address is page expected in vma? checking that the
- * page matches the vma: currently only used by unuse_process, on anon pages.
+ * page matches the vma: currently only used on anon pages, by unuse_vma;
  */
 unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 {
@@ -234,7 +234,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
                     (void *)page->mapping - PAGE_MAPPING_ANON)
                         return -EFAULT;
         } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
-                if (vma->vm_file->f_mapping != page->mapping)
+                if (!vma->vm_file ||
+                    vma->vm_file->f_mapping != page->mapping)
                         return -EFAULT;
         } else
                 return -EFAULT;
@@ -289,7 +290,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
  * repeatedly from either page_referenced_anon or page_referenced_file.
  */
 static int page_referenced_one(struct page *page,
-        struct vm_area_struct *vma, unsigned int *mapcount, int ignore_token)
+        struct vm_area_struct *vma, unsigned int *mapcount)
 {
         struct mm_struct *mm = vma->vm_mm;
         unsigned long address;
@@ -310,7 +311,7 @@ static int page_referenced_one(struct page *page,
 
         /* Pretend the page is referenced if the task has the
            swap token and is in the middle of a page fault. */
-        if (mm != current->mm && !ignore_token && has_swap_token(mm) &&
+        if (mm != current->mm && has_swap_token(mm) &&
                         rwsem_is_locked(&mm->mmap_sem))
                 referenced++;
 
@@ -320,7 +321,7 @@ out:
         return referenced;
 }
 
-static int page_referenced_anon(struct page *page, int ignore_token)
+static int page_referenced_anon(struct page *page)
 {
         unsigned int mapcount;
         struct anon_vma *anon_vma;
@@ -333,8 +334,7 @@ static int page_referenced_anon(struct page *page, int ignore_token)
 
         mapcount = page_mapcount(page);
         list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-                referenced += page_referenced_one(page, vma, &mapcount,
-                                                        ignore_token);
+                referenced += page_referenced_one(page, vma, &mapcount);
                 if (!mapcount)
                         break;
         }
@@ -353,7 +353,7 @@ static int page_referenced_anon(struct page *page, int ignore_token)
  *
  * This function is only called from page_referenced for object-based pages.
  */
-static int page_referenced_file(struct page *page, int ignore_token)
+static int page_referenced_file(struct page *page)
 {
         unsigned int mapcount;
         struct address_space *mapping = page->mapping;
@@ -391,8 +391,7 @@ static int page_referenced_file(struct page *page, int ignore_token)
                         referenced++;
                         break;
                 }
-                referenced += page_referenced_one(page, vma, &mapcount,
-                                                        ignore_token);
+                referenced += page_referenced_one(page, vma, &mapcount);
                 if (!mapcount)
                         break;
         }
@@ -409,13 +408,10 @@ static int page_referenced_file(struct page *page, int ignore_token)
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
  */
-int page_referenced(struct page *page, int is_locked, int ignore_token)
+int page_referenced(struct page *page, int is_locked)
 {
         int referenced = 0;
 
-        if (!swap_token_default_timeout)
-                ignore_token = 1;
-
         if (page_test_and_clear_young(page))
                 referenced++;
 
@@ -424,15 +420,14 @@ int page_referenced(struct page *page, int is_locked, int ignore_token)
 
         if (page_mapped(page) && page->mapping) {
                 if (PageAnon(page))
-                        referenced += page_referenced_anon(page, ignore_token);
+                        referenced += page_referenced_anon(page);
                 else if (is_locked)
-                        referenced += page_referenced_file(page, ignore_token);
+                        referenced += page_referenced_file(page);
                 else if (TestSetPageLocked(page))
                         referenced++;
                 else {
                         if (page->mapping)
-                                referenced += page_referenced_file(page,
-                                                                ignore_token);
+                                referenced += page_referenced_file(page);
                         unlock_page(page);
                 }
         }
@@ -440,6 +435,30 @@ int page_referenced(struct page *page, int is_locked, int ignore_token)
 }
 
 /**
+ * page_set_anon_rmap - setup new anonymous rmap
+ * @page:       the page to add the mapping to
+ * @vma:        the vm area in which the mapping is added
+ * @address:    the user virtual address mapped
+ */
+static void __page_set_anon_rmap(struct page *page,
+        struct vm_area_struct *vma, unsigned long address)
+{
+        struct anon_vma *anon_vma = vma->anon_vma;
+
+        BUG_ON(!anon_vma);
+        anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+        page->mapping = (struct address_space *) anon_vma;
+
+        page->index = linear_page_index(vma, address);
+
+        /*
+         * nr_mapped state can be updated without turning off
+         * interrupts because it is not modified via interrupt.
+         */
+        __inc_page_state(nr_mapped);
+}
+
+/**
  * page_add_anon_rmap - add pte mapping to an anonymous page
  * @page:       the page to add the mapping to
  * @vma:        the vm area in which the mapping is added
@@ -450,20 +469,27 @@ int page_referenced(struct page *page, int is_locked, int ignore_token)
 void page_add_anon_rmap(struct page *page,
         struct vm_area_struct *vma, unsigned long address)
 {
-        if (atomic_inc_and_test(&page->_mapcount)) {
-                struct anon_vma *anon_vma = vma->anon_vma;
-
-                BUG_ON(!anon_vma);
-                anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
-                page->mapping = (struct address_space *) anon_vma;
-
-                page->index = linear_page_index(vma, address);
-
-                inc_page_state(nr_mapped);
-        }
+        if (atomic_inc_and_test(&page->_mapcount))
+                __page_set_anon_rmap(page, vma, address);
         /* else checking page index and mapping is racy */
 }
 
+/*
+ * page_add_new_anon_rmap - add pte mapping to a new anonymous page
+ * @page:       the page to add the mapping to
+ * @vma:        the vm area in which the mapping is added
+ * @address:    the user virtual address mapped
+ *
+ * Same as page_add_anon_rmap but must only be called on *new* pages.
+ * This means the inc-and-test can be bypassed.
+ */
+void page_add_new_anon_rmap(struct page *page,
+        struct vm_area_struct *vma, unsigned long address)
+{
+        atomic_set(&page->_mapcount, 0); /* elevate count by 1 (starts at -1) */
+        __page_set_anon_rmap(page, vma, address);
+}
+
 /**
  * page_add_file_rmap - add pte mapping to a file page
  * @page: the page to add the mapping to
@@ -476,7 +502,7 @@ void page_add_file_rmap(struct page *page)
         BUG_ON(!pfn_valid(page_to_pfn(page)));
 
         if (atomic_inc_and_test(&page->_mapcount))
-                inc_page_state(nr_mapped);
+                __inc_page_state(nr_mapped);
 }
 
 /**
@@ -488,6 +514,13 @@ 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,
@@ -500,7 +533,7 @@ void page_remove_rmap(struct page *page)
                  */
                 if (page_test_and_clear_dirty(page))
                         set_page_dirty(page);
-                dec_page_state(nr_mapped);
+                __dec_page_state(nr_mapped);
         }
 }
 
@@ -529,10 +562,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma)
          * If the page is mlock()d, we cannot swap it out.
          * If it's recently referenced (perhaps page_referenced
          * skipped over this mm) then we should reactivate it.
-         *
-         * Pages belonging to VM_RESERVED regions should not happen here.
          */
-        if ((vma->vm_flags & (VM_LOCKED|VM_RESERVED)) ||
+        if ((vma->vm_flags & VM_LOCKED) ||
                         ptep_clear_flush_young(vma, address, pte)) {
                 ret = SWAP_FAIL;
                 goto out_unmap;
@@ -613,7 +644,6 @@ static void try_to_unmap_cluster(unsigned long cursor,
         struct page *page;
         unsigned long address;
         unsigned long end;
-        unsigned long pfn;
 
         address = (vma->vm_start + cursor) & CLUSTER_MASK;
         end = address + CLUSTER_SIZE;
@@ -642,21 +672,14 @@ static void try_to_unmap_cluster(unsigned long cursor,
         for (; address < end; pte++, address += PAGE_SIZE) {
                 if (!pte_present(*pte))
                         continue;
-
-                pfn = pte_pfn(*pte);
-                if (unlikely(!pfn_valid(pfn))) {
-                        print_bad_pte(vma, *pte, address);
-                        continue;
-                }
-
-                page = pfn_to_page(pfn);
-                BUG_ON(PageAnon(page));
+                page = vm_normal_page(vma, address, *pte);
+                BUG_ON(!page || PageAnon(page));
 
                 if (ptep_clear_flush_young(vma, address, pte))
                         continue;
 
                 /* Nuke the page table entry. */
-                flush_cache_page(vma, address, pfn);
+                flush_cache_page(vma, address, pte_pfn(*pte));
                 pteval = ptep_clear_flush(vma, address, pte);
 
                 /* If nonlinear, store the file page offset in the pte. */
@@ -727,7 +750,7 @@ static int try_to_unmap_file(struct page *page)
 
         list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
                                                 shared.vm_set.list) {
-                if (vma->vm_flags & (VM_LOCKED|VM_RESERVED))
+                if (vma->vm_flags & VM_LOCKED)
                         continue;
                 cursor = (unsigned long) vma->vm_private_data;
                 if (cursor > max_nl_cursor)
@@ -761,7 +784,7 @@ static int try_to_unmap_file(struct page *page)
         do {
                 list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
                                                 shared.vm_set.list) {
-                        if (vma->vm_flags & (VM_LOCKED|VM_RESERVED))
+                        if (vma->vm_flags & VM_LOCKED)
                                 continue;
                         cursor = (unsigned long) vma->vm_private_data;
                         while ( cursor < max_nl_cursor &&
@@ -783,11 +806,8 @@ static int try_to_unmap_file(struct page *page)
          * in locked vmas).  Reset cursor on all unreserved nonlinear
          * vmas, now forgetting on which ones it had fallen behind.
          */
-        list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
-                                                shared.vm_set.list) {
-                if (!(vma->vm_flags & VM_RESERVED))
-                        vma->vm_private_data = NULL;
-        }
+        list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
+                vma->vm_private_data = NULL;
 out:
         spin_unlock(&mapping->i_mmap_lock);
         return ret;