X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Ffs-writeback.c;h=a9ee474f96918fa1b7b163b476ff32b37944b456;hb=38f21977663126fef53f5585e7f1653d8ebe55c4;hp=16519fe1399c6c49e1ddc2f875db9217681b35fc;hpb=ae8547b0a9e5d718ce272ddc48f91703a0f52a0b;p=safe%2Fjmp%2Flinux-2.6

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 16519fe..a9ee474 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -8,7 +8,7 @@
  * pages against inodes.  ie: data writeback.  Writeout of the
  * inode itself is not handled here.
  *
- * 10Apr2002	akpm@zip.com.au
+ * 10Apr2002	Andrew Morton
  *		Split out of fs/inode.c
  *		Additions for address_space-based writeback
  */
@@ -421,9 +421,6 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * If we're a pdlfush thread, then implement pdflush collision avoidance
  * against the entire list.
  *
- * WB_SYNC_HOLD is a hack for sys_sync(): reattach the inode to sb->s_dirty so
- * that it can be located for waiting on in __writeback_single_inode().
- *
  * If `bdi' is non-zero then we're being asked to writeback a specific queue.
  * This function assumes that the blockdev superblock's inodes are backed by
  * a variety of queues, so all inodes are searched.  For other superblocks,
@@ -439,10 +436,11 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * on the writer throttling path, and we get decent balancing between many
  * throttled threads: we don't want them all piling up on inode_sync_wait.
  */
-static void
-sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
+void generic_sync_sb_inodes(struct super_block *sb,
+				struct writeback_control *wbc)
 {
 	const unsigned long start = jiffies;	/* livelock avoidance */
+	int sync = wbc->sync_mode == WB_SYNC_ALL;
 
 	spin_lock(&inode_lock);
 	if (!wbc->for_kupdate || list_empty(&sb->s_io))
@@ -499,10 +497,6 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		__writeback_single_inode(inode, wbc);
-		if (wbc->sync_mode == WB_SYNC_HOLD) {
-			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &sb->s_dirty);
-		}
 		if (current_is_pdflush())
 			writeback_release(bdi);
 		if (wbc->pages_skipped != pages_skipped) {
@@ -523,9 +517,58 @@ sync_sb_inodes(struct super_block *sb, struct writeback_control *wbc)
 		if (!list_empty(&sb->s_more_io))
 			wbc->more_io = 1;
 	}
-	spin_unlock(&inode_lock);
+
+	if (sync) {
+		struct inode *inode, *old_inode = NULL;
+
+		/*
+		 * Data integrity sync. Must wait for all pages under writeback,
+		 * because there may have been pages dirtied before our sync
+		 * call, but which had writeout started before we write it out.
+		 * In which case, the inode may not be on the dirty list, but
+		 * we still have to wait for that writeout.
+		 */
+		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+			struct address_space *mapping;
+
+			if (inode->i_state & (I_FREEING|I_WILL_FREE))
+				continue;
+			mapping = inode->i_mapping;
+			if (mapping->nrpages == 0)
+				continue;
+			__iget(inode);
+			spin_unlock(&inode_lock);
+			/*
+			 * We hold a reference to 'inode' so it couldn't have
+			 * been removed from s_inodes list while we dropped the
+			 * inode_lock.  We cannot iput the inode now as we can
+			 * be holding the last reference and we cannot iput it
+			 * under inode_lock. So we keep the reference and iput
+			 * it later.
+			 */
+			iput(old_inode);
+			old_inode = inode;
+
+			filemap_fdatawait(mapping);
+
+			cond_resched();
+
+			spin_lock(&inode_lock);
+		}
+		spin_unlock(&inode_lock);
+		iput(old_inode);
+	} else
+		spin_unlock(&inode_lock);
+
 	return;		/* Leave any unwritten inodes on s_io */
 }
+EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
+
+static void sync_sb_inodes(struct super_block *sb,
+				struct writeback_control *wbc)
+{
+	generic_sync_sb_inodes(sb, wbc);
+}
 
 /*
  * Start writeback of dirty pagecache data against all unlocked inodes.
@@ -581,8 +624,7 @@ restart:
 
 /*
  * writeback and wait upon the filesystem's dirty inodes.  The caller will
- * do this in two passes - one to write, and one to wait.  WB_SYNC_HOLD is
- * used to park the written inodes on sb->s_dirty for the wait pass.
+ * do this in two passes - one to write, and one to wait.
  *
  * A finite limit is set on the number of pages which will be written.
  * To prevent infinite livelock of sys_sync().
@@ -593,17 +635,20 @@ restart:
 void sync_inodes_sb(struct super_block *sb, int wait)
 {
 	struct writeback_control wbc = {
-		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_HOLD,
+		.sync_mode	= wait ? WB_SYNC_ALL : WB_SYNC_NONE,
 		.range_start	= 0,
 		.range_end	= LLONG_MAX,
 	};
-	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
-	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
 
-	wbc.nr_to_write = nr_dirty + nr_unstable +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused) +
-			nr_dirty + nr_unstable;
-	wbc.nr_to_write += wbc.nr_to_write / 2;		/* Bit more for luck */
+	if (!wait) {
+		unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+		unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+
+		wbc.nr_to_write = nr_dirty + nr_unstable +
+			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+	} else
+		wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
+
 	sync_sb_inodes(sb, &wbc);
 }