1 files changed, 80 insertions, 34 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a794945fd19..eec1481ba44 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -119,6 +119,44 @@ static void background_writeout(unsigned long _min_pages);
  * We make sure that the background writeout level is below the adjusted
  * clamping level.
  */
+
+static unsigned long highmem_dirtyable_memory(unsigned long total)
+{
+#ifdef CONFIG_HIGHMEM
+	int node;
+	unsigned long x = 0;
+
+	for_each_online_node(node) {
+		struct zone *z =
+			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+
+		x += zone_page_state(z, NR_FREE_PAGES)
+			+ zone_page_state(z, NR_INACTIVE)
+			+ zone_page_state(z, NR_ACTIVE);
+	}
+	/*
+	 * Make sure that the number of highmem pages is never larger
+	 * than the number of the total dirtyable memory. This can only
+	 * occur in very strange VM situations but we want to make sure
+	 * that this does not occur.
+	 */
+	return min(x, total);
+#else
+	return 0;
+#endif
+}
+
+static unsigned long determine_dirtyable_memory(void)
+{
+	unsigned long x;
+
+	x = global_page_state(NR_FREE_PAGES)
+		+ global_page_state(NR_INACTIVE)
+		+ global_page_state(NR_ACTIVE);
+	x -= highmem_dirtyable_memory(x);
+	return x + 1;	/* Ensure that we never return 0 */
+}
+
 static void
 get_dirty_limits(long *pbackground, long *pdirty,
 					struct address_space *mapping)
@@ -128,20 +166,12 @@ get_dirty_limits(long *pbackground, long *pdirty,
 	int unmapped_ratio;
 	long background;
 	long dirty;
-	unsigned long available_memory = vm_total_pages;
+	unsigned long available_memory = determine_dirtyable_memory();
 	struct task_struct *tsk;
 
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * We always exclude high memory from our count.
-	 */
-	available_memory -= totalhigh_pages;
-#endif
-
-
 	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES)) * 100) /
-					vm_total_pages;
+					available_memory;
 
 	dirty_ratio = vm_dirty_ratio;
 	if (dirty_ratio > unmapped_ratio / 2)
@@ -558,31 +588,27 @@ void __init page_writeback_init(void)
 }
 
 /**
- * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
+ * write_cache_pages - walk the list of dirty pages of the given address space and write all of them.
  * @mapping: address space structure to write
  * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ * @writepage: function called for each page
+ * @data: data passed to writepage function
  *
- * This is a library function, which implements the writepages()
- * address_space_operation.
- *
- * If a page is already under I/O, generic_writepages() skips it, even
+ * If a page is already under I/O, write_cache_pages() skips it, even
  * if it's dirty.  This is desirable behaviour for memory-cleaning writeback,
  * but it is INCORRECT for data-integrity system calls such as fsync().  fsync()
  * and msync() need to guarantee that all the data which was dirty at the time
  * the call was made get new I/O started against them.  If wbc->sync_mode is
  * WB_SYNC_ALL then we were called for data integrity and we must wait for
  * existing IO to complete.
- *
- * Derived from mpage_writepages() - if you fix this you should check that
- * also!
  */
-int generic_writepages(struct address_space *mapping,
-		       struct writeback_control *wbc)
+int write_cache_pages(struct address_space *mapping,
+		      struct writeback_control *wbc, writepage_t writepage,
+		      void *data)
 {
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	int ret = 0;
 	int done = 0;
-	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	struct pagevec pvec;
 	int nr_pages;
 	pgoff_t index;
@@ -595,12 +621,6 @@ int generic_writepages(struct address_space *mapping,
 		return 0;
 	}
 
-	writepage = mapping->a_ops->writepage;
-
-	/* deal with chardevs and other special file */
-	if (!writepage)
-		return 0;
-
 	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
 		index = mapping->writeback_index; /* Start from prev offset */
@@ -652,13 +672,7 @@ retry:
 				continue;
 			}
 
-			ret = (*writepage)(page, wbc);
-			if (ret) {
-				if (ret == -ENOSPC)
-					set_bit(AS_ENOSPC, &mapping->flags);
-				else
-					set_bit(AS_EIO, &mapping->flags);
-			}
+			ret = (*writepage)(page, wbc, data);
 
 			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE))
 				unlock_page(page);
@@ -685,6 +699,38 @@ retry:
 		mapping->writeback_index = index;
 	return ret;
 }
+EXPORT_SYMBOL(write_cache_pages);
+
+/*
+ * Function used by generic_writepages to call the real writepage
+ * function and set the mapping flags on error
+ */
+static int __writepage(struct page *page, struct writeback_control *wbc,
+		       void *data)
+{
+	struct address_space *mapping = data;
+	int ret = mapping->a_ops->writepage(page, wbc);
+	mapping_set_error(mapping, ret);
+	return ret;
+}
+
+/**
+ * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
+ * @mapping: address space structure to write
+ * @wbc: subtract the number of written pages from *@wbc->nr_to_write
+ *
+ * This is a library function, which implements the writepages()
+ * address_space_operation.
+ */
+int generic_writepages(struct address_space *mapping,
+		       struct writeback_control *wbc)
+{
+	/* deal with chardevs and other special file */
+	if (!mapping->a_ops->writepage)
+		return 0;
+
+	return write_cache_pages(mapping, wbc, __writepage, mapping);
+}
 
 EXPORT_SYMBOL(generic_writepages);