mm: tracking dirty pages -v13

Index: linux-2.6-dirty/mm/memory.c
===================================================================
@@ -1457,14 +1457,19 @@ static int do_wp_page(struct mm_struct *
 {
 	struct page *old_page, *new_page;
 	pte_t entry;
-	int reuse, ret = VM_FAULT_MINOR;
+	int reuse = 0, ret = VM_FAULT_MINOR;
+	struct page *dirty_page = NULL;
 
 	old_page = vm_normal_page(vma, address, orig_pte);
 	if (!old_page)
 		goto gotten;
 
-	if (unlikely((vma->vm_flags & (VM_SHARED|VM_WRITE)) ==
-				(VM_SHARED|VM_WRITE))) {
+	/*
+	 * Only catch write-faults on shared writable pages, read-only
+	 * shared pages can get COWed by get_user_pages(.write=1, .force=1).
+	 */
+	if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+					(VM_WRITE|VM_SHARED))) {
 		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
 			/*
 			 * Notify the address space that the page is about to

@@ -1493,13 +1498,12 @@ static int do_wp_page(struct mm_struct *
 			if (!pte_same(*page_table, orig_pte))
 				goto unlock;
 		}
-
+		dirty_page = old_page;
+		get_page(dirty_page);
 		reuse = 1;
 	} else if (PageAnon(old_page) && !TestSetPageLocked(old_page)) {
 		reuse = can_share_swap_page(old_page);
 		unlock_page(old_page);
-	} else {
-		reuse = 0;
 	}
 
 	if (reuse) {

@@ -1565,6 +1569,10 @@ gotten:
 		page_cache_release(old_page);
 unlock:
 	pte_unmap_unlock(page_table, ptl);
+	if (dirty_page) {
+		set_page_dirty(dirty_page);
+		put_page(dirty_page);
+	}
 	return ret;
 oom:
 	if (old_page)

@@ -2094,6 +2102,7 @@ static int do_no_page(struct mm_struct *
 	unsigned int sequence = 0;
 	int ret = VM_FAULT_MINOR;
 	int anon = 0;
+	struct page *dirty_page = NULL;
 
 	pte_unmap(page_table);
 	BUG_ON(vma->vm_flags & VM_PFNMAP);

@@ -2188,6 +2197,10 @@ retry:
 		} else {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(new_page);
+			if (write_access) {
+				dirty_page = new_page;
+				get_page(dirty_page);
+			}
 		}
 	} else {
 		/* One of our sibling threads was faster, back out. */

@@ -2200,6 +2213,10 @@ retry:
 	lazy_mmu_prot_update(entry);
 unlock:
 	pte_unmap_unlock(page_table, ptl);
+	if (dirty_page) {
+		set_page_dirty(dirty_page);
+		put_page(dirty_page);
+	}
 	return ret;
 oom:
 	page_cache_release(new_page);

Index: linux-2.6-dirty/mm/mmap.c
===================================================================
@@ -1090,12 +1090,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	/* Don't make the VMA automatically writable if it's shared, but the
-	 * backer wishes to know when pages are first written to */
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
-		vma->vm_page_prot =
-			protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)];
-
 	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
 	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
 	 * that memory reservation must be checked; but that reservation

@@ -1113,6 +1107,10 @@ munmap_back:
 	pgoff = vma->vm_pgoff;
 	vm_flags = vma->vm_flags;
 
+	if (vma_wants_writenotify(vma, 0))
+		vma->vm_page_prot =
+			protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)];
+
 	if (!file || !vma_merge(mm, prev, addr, vma->vm_end,
 			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
 		file = vma->vm_file;

Index: linux-2.6-dirty/mm/mprotect.c
===================================================================
@@ -123,8 +123,7 @@ mprotect_fixup(struct vm_area_struct *vm
 	unsigned long oldflags = vma->vm_flags;
 	long nrpages = (end - start) >> PAGE_SHIFT;
 	unsigned long charged = 0;
-	unsigned int mask;
-	pgprot_t newprot;
+	unsigned long mask = VM_READ|VM_WRITE|VM_EXEC|VM_SHARED;
 	pgoff_t pgoff;
 	int error;
 

@@ -176,24 +175,19 @@ mprotect_fixup(struct vm_area_struct *vm
 	}
 
 success:
-	/* Don't make the VMA automatically writable if it's shared, but the
-	 * backer wishes to know when pages are first written to */
-	mask = VM_READ|VM_WRITE|VM_EXEC|VM_SHARED;
-	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
-		mask &= ~VM_SHARED;
-
-	newprot = protection_map[newflags & mask];
-
 	/*
 	 * vm_flags and vm_page_prot are protected by the mmap_sem
 	 * held in write mode.
 	 */
 	vma->vm_flags = newflags;
-	vma->vm_page_prot = newprot;
+	if (vma_wants_writenotify(vma, VM_NOTIFY_NO_PROT))
+		mask &= ~VM_SHARED;
+	vma->vm_page_prot = protection_map[newflags & mask];
+
 	if (is_vm_hugetlb_page(vma))
-		hugetlb_change_protection(vma, start, end, newprot);
+		hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
 	else
-		change_protection(vma, start, end, newprot);
+		change_protection(vma, start, end, vma->vm_page_prot);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;

Index: linux-2.6-dirty/mm/page-writeback.c
===================================================================
@@ -29,6 +29,7 @@
 #include <linux/sysctl.h>
 #include <linux/cpu.h>
 #include <linux/syscalls.h>
+#include <linux/rmap.h>
 
 /*
  * The maximum number of pages to writeout in a single bdflush/kupdate

@@ -566,7 +567,7 @@ int do_writepages(struct address_space *
 		return 0;
 	wbc->for_writepages = 1;
 	if (mapping->a_ops->writepages)
-		ret =  mapping->a_ops->writepages(mapping, wbc);
+		ret = mapping->a_ops->writepages(mapping, wbc);
 	else
 		ret = generic_writepages(mapping, wbc);
 	wbc->for_writepages = 0;

@@ -728,8 +729,14 @@ int test_clear_page_dirty(struct page *p
 						page_index(page),
 						PAGECACHE_TAG_DIRTY);
 			write_unlock_irqrestore(&mapping->tree_lock, flags);
-			if (mapping_cap_account_dirty(mapping))
+			/*
+			 * We can continue to use `mapping' here because the
+			 * page is locked, which pins the address_space
+			 */
+			if (mapping_cap_account_dirty(mapping)) {
+				page_mkclean(page);
 				dec_page_state(nr_dirty);
+			}
 			return 1;
 		}
 		write_unlock_irqrestore(&mapping->tree_lock, flags);

@@ -759,8 +766,10 @@ int clear_page_dirty_for_io(struct page 
 
 	if (mapping) {
 		if (TestClearPageDirty(page)) {
-			if (mapping_cap_account_dirty(mapping))
+			if (mapping_cap_account_dirty(mapping)) {
+				page_mkclean(page);
 				dec_page_state(nr_dirty);
+			}
 			return 1;
 		}
 		return 0;

72 lines not on this page · raw message

Index: linux-2.6-dirty/include/linux/rmap.h
===================================================================
@@ -103,6 +103,14 @@ pte_t *page_check_address(struct page *,
  */
 unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
 
+/*
+ * Cleans the PTEs of shared mappings.
+ * (and since clean PTEs should also be readonly, write protects them too)
+ *
+ * returns the number of cleaned PTEs.
+ */
+int page_mkclean(struct page *);
+
 #else	/* !CONFIG_MMU */
 
 #define anon_vma_init()		do {} while (0)

Index: linux-2.6-dirty/fs/buffer.c
===================================================================
@@ -2983,6 +2983,7 @@ int try_to_free_buffers(struct page *pag
 
 	spin_lock(&mapping->private_lock);
 	ret = drop_buffers(page, &buffers_to_free);
+	spin_unlock(&mapping->private_lock);
 	if (ret) {
 		/*
 		 * If the filesystem writes its buffers by hand (eg ext3)

@@ -2994,7 +2995,6 @@ int try_to_free_buffers(struct page *pag
 		 */
 		clear_page_dirty(page);
 	}
-	spin_unlock(&mapping->private_lock);
 out:
 	if (buffers_to_free) {
 		struct buffer_head *bh = buffers_to_free;

Index: linux-2.6-dirty/include/linux/mm.h
===================================================================
@@ -14,6 +14,7 @@
 #include <linux/prio_tree.h>
 #include <linux/fs.h>
 #include <linux/mutex.h>
+#include <linux/backing-dev.h>
 
 struct mempolicy;
 struct anon_vma;

@@ -796,6 +797,44 @@ struct shrinker;
 extern struct shrinker *set_shrinker(int, shrinker_t);
 extern void remove_shrinker(struct shrinker *shrinker);
 
+#define VM_NOTIFY_NO_PROT	0x01
+#define VM_NOTIFY_NO_MKWRITE	0x02
+
+/*
+ * Some shared mappigns will want the pages marked read-only
+ * to track write events. If so, we'll downgrade vm_page_prot
+ * to the private version (using protection_map[] without the
+ * VM_SHARED bit).
+ */
+static inline int vma_wants_writenotify(struct vm_area_struct *vma, int flags)
+{
+	unsigned int vm_flags = vma->vm_flags;
+
+	/* If it was private or non-writable, the write bit is already clear */
+	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
+		return 0;
+
+	/* The backer wishes to know when pages are first written to? */
+	if (!(flags & VM_NOTIFY_NO_MKWRITE) &&
+			vma->vm_ops && vma->vm_ops->page_mkwrite)
+		return 1;
+
+	/* The open routine did something to the protections already? */
+	if (!(flags & VM_NOTIFY_NO_PROT) &&
+			pgprot_val(vma->vm_page_prot) !=
+			pgprot_val(protection_map[vm_flags &
+				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]))
+		return 0;
+
+	/* Specialty mapping? */
+	if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE))
+		return 0;
+
+	/* Can the mapping track the dirty pages? */
+	return vma->vm_file && vma->vm_file->f_mapping &&
+		mapping_cap_account_dirty(vma->vm_file->f_mapping);
+}
+
 extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl));
 
 int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);

@@ -625,6 +625,7 @@ EXPORT_SYMBOL(write_one_page);
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
+	WARN_ON_ONCE(!PageLocked(page));
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;

@@ -722,6 +723,7 @@ int test_clear_page_dirty(struct page *p
 	struct address_space *mapping = page_mapping(page);
 	unsigned long flags;
 
+	WARN_ON_ONCE(!PageLocked(page));
 	if (mapping) {
 		write_lock_irqsave(&mapping->tree_lock, flags);
 		if (TestClearPageDirty(page)) {

Index: linux-2.6-dirty/mm/memory.c
===================================================================
@@ -48,6 +48,7 @@
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/writeback.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>

@@ -1570,7 +1571,7 @@ gotten:
 unlock:
 	pte_unmap_unlock(page_table, ptl);
 	if (dirty_page) {
-		set_page_dirty(dirty_page);
+		set_page_dirty_balance(dirty_page);
 		put_page(dirty_page);
 	}
 	return ret;

@@ -2214,7 +2215,7 @@ retry:
 unlock:
 	pte_unmap_unlock(page_table, ptl);
 	if (dirty_page) {
-		set_page_dirty(dirty_page);
+		set_page_dirty_balance(dirty_page);
 		put_page(dirty_page);
 	}
 	return ret;

Index: linux-2.6-dirty/include/linux/writeback.h
===================================================================
@@ -115,6 +115,7 @@ int sync_page_range(struct inode *inode,
 			loff_t pos, loff_t count);
 int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
 			   loff_t pos, loff_t count);
+void set_page_dirty_balance(struct page *page);
 
 /* pdflush.c */
 extern int nr_pdflush_threads;	/* Global so it can be exported to sysctl

Index: linux-2.6-dirty/mm/page-writeback.c
===================================================================
@@ -256,6 +256,16 @@ static void balance_dirty_pages(struct a
 		pdflush_operation(background_writeout, 0);
 }
 
+void set_page_dirty_balance(struct page *page)
+{
+	if (set_page_dirty(page)) {
+		struct address_space *mapping = page_mapping(page);
+
+		if (mapping)
+			balance_dirty_pages_ratelimited(mapping);
+	}
+}
+
 /**
  * balance_dirty_pages_ratelimited_nr - balance dirty memory state
  * @mapping: address_space which was dirtied

Index: 2.6-mm/mm/msync.c
===================================================================
@@ -7,149 +7,33 @@
 /*
  * The msync() system call.
  */
-#include <linux/slab.h>
-#include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/hugetlb.h>
-#include <linux/writeback.h>
 #include <linux/file.h>
 #include <linux/syscalls.h>
 
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-
-static unsigned long msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-				unsigned long addr, unsigned long end)
-{
-	pte_t *pte;
-	spinlock_t *ptl;
-	int progress = 0;
-	unsigned long ret = 0;
-
-again:
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	do {
-		struct page *page;
-
-		if (progress >= 64) {
-			progress = 0;
-			if (need_resched() || need_lockbreak(ptl))
-				break;
-		}
-		progress++;
-		if (!pte_present(*pte))
-			continue;
-		if (!pte_maybe_dirty(*pte))
-			continue;
-		page = vm_normal_page(vma, addr, *pte);
-		if (!page)
-			continue;
-		if (ptep_clear_flush_dirty(vma, addr, pte) ||
-				page_test_and_clear_dirty(page))
-			ret += set_page_dirty(page);
-		progress += 3;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
-	if (addr != end)
-		goto again;
-	return ret;
-}
-
-static inline unsigned long msync_pmd_range(struct vm_area_struct *vma,
-			pud_t *pud, unsigned long addr, unsigned long end)
-{
-	pmd_t *pmd;
-	unsigned long next;
-	unsigned long ret = 0;
-
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
-		ret += msync_pte_range(vma, pmd, addr, next);
-	} while (pmd++, addr = next, addr != end);
-	return ret;
-}
-
-static inline unsigned long msync_pud_range(struct vm_area_struct *vma,
-			pgd_t *pgd, unsigned long addr, unsigned long end)
-{
-	pud_t *pud;
-	unsigned long next;
-	unsigned long ret = 0;
-
-	pud = pud_offset(pgd, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		ret += msync_pmd_range(vma, pud, addr, next);
-	} while (pud++, addr = next, addr != end);
-	return ret;
-}
-
-static unsigned long msync_page_range(struct vm_area_struct *vma,
-				unsigned long addr, unsigned long end)
-{
-	pgd_t *pgd;
-	unsigned long next;
-	unsigned long ret = 0;
-
-	/* For hugepages we can't go walking the page table normally,
-	 * but that's ok, hugetlbfs is memory based, so we don't need
-	 * to do anything more on an msync().
-	 */
-	if (vma->vm_flags & VM_HUGETLB)
-		return 0;
-
-	BUG_ON(addr >= end);
-	pgd = pgd_offset(vma->vm_mm, addr);
-	flush_cache_range(vma, addr, end);
-	do {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		ret += msync_pud_range(vma, pgd, addr, next);
-	} while (pgd++, addr = next, addr != end);
-	return ret;
-}
-
 /*
  * MS_SYNC syncs the entire file - including mappings.
  *
- * MS_ASYNC does not start I/O (it used to, up to 2.5.67).  Instead, it just
- * marks the relevant pages dirty.  The application may now run fsync() to
+ * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
+ * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
+ * Now it doesn't do anything, since dirty pages are properly tracked.
+ *
+ * The application may now run fsync() to
  * write out the dirty pages and wait on the writeout and check the result.
  * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
  * async writeout immediately.
  * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
  * applications.
  */
-static int msync_interval(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long end, int flags,
-			unsigned long *nr_pages_dirtied)
-{
-	struct file *file = vma->vm_file;
-
-	if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))
-		return -EBUSY;
-
-	if (file && (vma->vm_flags & VM_SHARED))
-		*nr_pages_dirtied = msync_page_range(vma, addr, end);
-	return 0;
-}
-
 asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 {
 	unsigned long end;
+	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int unmapped_error = 0;
 	int error = -EINVAL;
-	int done = 0;
 
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;

@@ -169,64 +53,48 @@ asmlinkage long sys_msync(unsigned long 
 	 * If the interval [start,end) covers some unmapped address ranges,
 	 * just ignore them, but return -ENOMEM at the end.
 	 */
-	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm, start);
-	if (!vma) {
-		error = -ENOMEM;
-		goto out_unlock;
-	}
-	do {
-		unsigned long nr_pages_dirtied = 0;
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
+	for (;;) {
 		struct file *file;
 
+		/* Still start < end. */
+		error = -ENOMEM;
+		if (!vma)
+			goto out_unlock;
 		/* Here start < vma->vm_end. */
 		if (start < vma->vm_start) {
-			unmapped_error = -ENOMEM;
 			start = vma->vm_start;
+			if (start >= end)
+				goto out_unlock;
+			unmapped_error = -ENOMEM;
 		}
 		/* Here vma->vm_start <= start < vma->vm_end. */
-		if (end <= vma->vm_end) {
-			if (start < end) {
-				error = msync_interval(vma, start, end, flags,
-							&nr_pages_dirtied);
-				if (error)
-					goto out_unlock;
-			}
-			error = unmapped_error;
-			done = 1;
-		} else {
-			/* Here vma->vm_start <= start < vma->vm_end < end. */
-			error = msync_interval(vma, start, vma->vm_end, flags,
-						&nr_pages_dirtied);
-			if (error)
-				goto out_unlock;
+		if ((flags & MS_INVALIDATE) &&
+				(vma->vm_flags & VM_LOCKED)) {
+			error = -EBUSY;
+			goto out_unlock;
 		}
 		file = vma->vm_file;
 		start = vma->vm_end;
-		if ((flags & MS_ASYNC) && file && nr_pages_dirtied) {
-			get_file(file);
-			up_read(&current->mm->mmap_sem);
-			balance_dirty_pages_ratelimited_nr(file->f_mapping,
-							nr_pages_dirtied);
-			fput(file);
-			down_read(&current->mm->mmap_sem);
-			vma = find_vma(current->mm, start);
-		} else if ((flags & MS_SYNC) && file &&
+		if ((flags & MS_SYNC) && file &&
 				(vma->vm_flags & VM_SHARED)) {
 			get_file(file);
-			up_read(&current->mm->mmap_sem);
+			up_read(&mm->mmap_sem);
 			error = do_fsync(file, 0);
 			fput(file);
-			down_read(&current->mm->mmap_sem);
-			if (error)
-				goto out_unlock;
-			vma = find_vma(current->mm, start);
+			if (error || start >= end)
+				goto out;
+			down_read(&mm->mmap_sem);
+			vma = find_vma(mm, start);
 		} else {
+			if (start >= end)
+				goto out_unlock;
 			vma = vma->vm_next;
 		}
-	} while (vma && !done);
+	}
 out_unlock:
-	up_read(&current->mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 out:
-	return error;
+	return error ? : unmapped_error;
 }

Index: linux-2.6-dirty/mm/mprotect.c
===================================================================
@@ -27,7 +27,8 @@
 #include <asm/tlbflush.h>
 
 static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
-		unsigned long addr, unsigned long end, pgprot_t newprot)
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable)
 {
 	pte_t *pte, oldpte;
 	spinlock_t *ptl;

@@ -42,7 +43,14 @@ static void change_pte_range(struct mm_s
 			 * bits by wiping the pte and then setting the new pte
 			 * into place.
 			 */
-			ptent = pte_modify(ptep_get_and_clear(mm, addr, pte), newprot);
+			ptent = ptep_get_and_clear(mm, addr, pte);
+			ptent = pte_modify(ptent, newprot);
+			/*
+			 * Avoid taking write faults for pages we know to be
+			 * dirty.
+			 */
+			if (dirty_accountable && pte_dirty(ptent))
+				ptent = pte_mkwrite(ptent);
 			set_pte_at(mm, addr, pte, ptent);
 			lazy_mmu_prot_update(ptent);
 #ifdef CONFIG_MIGRATION

@@ -66,7 +74,8 @@ static void change_pte_range(struct mm_s
 }
 
 static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
-		unsigned long addr, unsigned long end, pgprot_t newprot)
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable)
 {
 	pmd_t *pmd;
 	unsigned long next;

@@ -76,12 +85,13 @@ static inline void change_pmd_range(stru
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		change_pte_range(mm, pmd, addr, next, newprot);
+		change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);
 	} while (pmd++, addr = next, addr != end);
 }
 
 static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
-		unsigned long addr, unsigned long end, pgprot_t newprot)
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable)
 {
 	pud_t *pud;
 	unsigned long next;

@@ -91,12 +101,13 @@ static inline void change_pud_range(stru
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		change_pmd_range(mm, pud, addr, next, newprot);
+		change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable);
 	} while (pud++, addr = next, addr != end);
 }
 
 static void change_protection(struct vm_area_struct *vma,
-		unsigned long addr, unsigned long end, pgprot_t newprot)
+		unsigned long addr, unsigned long end, pgprot_t newprot,
+		int dirty_accountable)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;

@@ -110,7 +121,7 @@ static void change_protection(struct vm_
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		change_pud_range(mm, pgd, addr, next, newprot);
+		change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
 	} while (pgd++, addr = next, addr != end);
 	flush_tlb_range(vma, start, end);
 }

@@ -126,6 +137,7 @@ mprotect_fixup(struct vm_area_struct *vm
 	unsigned long mask = VM_READ|VM_WRITE|VM_EXEC|VM_SHARED;
 	pgoff_t pgoff;
 	int error;
+	int dirty_accountable = 0;
 
 	if (newflags == oldflags) {
 		*pprev = vma;

@@ -180,14 +192,16 @@ success:
 	 * held in write mode.
 	 */
 	vma->vm_flags = newflags;
-	if (vma_wants_writenotify(vma, VM_NOTIFY_NO_PROT))
+	if (vma_wants_writenotify(vma, VM_NOTIFY_NO_PROT)) {
 		mask &= ~VM_SHARED;
+		dirty_accountable = 1;
+	}
 	vma->vm_page_prot = protection_map[newflags & mask];
 
 	if (is_vm_hugetlb_page(vma))
 		hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
 	else
-		change_protection(vma, start, end, vma->vm_page_prot);
+		change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;

Index: 2.6-mm/mm/fremap.c
===================================================================
@@ -79,9 +79,9 @@ int install_page(struct mm_struct *mm, s
 		inc_mm_counter(mm, file_rss);
 
 	flush_icache_page(vma, page);
-	set_pte_at(mm, addr, pte, mk_pte(page, prot));
+	pte_val = mk_pte(page, prot);
+	set_pte_at(mm, addr, pte, pte_val);
 	page_add_file_rmap(page);
-	pte_val = *pte;
 	update_mmu_cache(vma, addr, pte_val);
 	lazy_mmu_prot_update(pte_val);
 	err = 0;