4 files changed, 50 insertions, 18 deletions

diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 5105015a75ad..98e0e86093b4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -387,6 +387,8 @@ _xfs_buf_lookup_pages(
                 if (unlikely(page == NULL)) {
                         if (flags & XBF_READ_AHEAD) {
                                 bp->b_page_count = i;
+                                for (i = 0; i < bp->b_page_count; i++)
+                                        unlock_page(bp->b_pages[i]);
                                 return -ENOMEM;
                         }
 
@@ -416,17 +418,24 @@ _xfs_buf_lookup_pages(
                 ASSERT(!PagePrivate(page));
                 if (!PageUptodate(page)) {
                         page_count--;
-                        if (blocksize < PAGE_CACHE_SIZE && !PagePrivate(page)) {
+                        if (blocksize >= PAGE_CACHE_SIZE) {
+                                if (flags & XBF_READ)
+                                        bp->b_flags |= _XBF_PAGE_LOCKED;
+                        } else if (!PagePrivate(page)) {
                                 if (test_page_region(page, offset, nbytes))
                                         page_count++;
                         }
                 }
 
-                unlock_page(page);
                 bp->b_pages[i] = page;
                 offset = 0;
         }
 
+        if (!(bp->b_flags & _XBF_PAGE_LOCKED)) {
+                for (i = 0; i < bp->b_page_count; i++)
+                        unlock_page(bp->b_pages[i]);
+        }
+
         if (page_count == bp->b_page_count)
                 bp->b_flags |= XBF_DONE;
 
@@ -746,6 +755,7 @@ xfs_buf_associate_memory(
         bp->b_count_desired = len;
         bp->b_buffer_length = buflen;
         bp->b_flags |= XBF_MAPPED;
+        bp->b_flags &= ~_XBF_PAGE_LOCKED;
 
         return 0;
 }
@@ -1093,8 +1103,10 @@ _xfs_buf_ioend(
         xfs_buf_t               *bp,
         int                     schedule)
 {
-        if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
+        if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
+                bp->b_flags &= ~_XBF_PAGE_LOCKED;
                 xfs_buf_ioend(bp, schedule);
+        }
 }
 
 STATIC void
@@ -1125,6 +1137,9 @@ xfs_buf_bio_end_io(
 
                 if (--bvec >= bio->bi_io_vec)
                         prefetchw(&bvec->bv_page->flags);
+
+                if (bp->b_flags & _XBF_PAGE_LOCKED)
+                        unlock_page(page);
         } while (bvec >= bio->bi_io_vec);
 
         _xfs_buf_ioend(bp, 1);
@@ -1163,7 +1178,8 @@ _xfs_buf_ioapply(
          * filesystem block size is not smaller than the page size.
          */
         if ((bp->b_buffer_length < PAGE_CACHE_SIZE) &&
-            (bp->b_flags & XBF_READ) &&
+            ((bp->b_flags & (XBF_READ|_XBF_PAGE_LOCKED)) ==
+              (XBF_READ|_XBF_PAGE_LOCKED)) &&
             (blocksize >= PAGE_CACHE_SIZE)) {
                 bio = bio_alloc(GFP_NOIO, 1);
 
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 841d7883528d..f948ec7ba9a4 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -66,6 +66,25 @@ typedef enum {
         _XBF_PAGES = (1 << 18),     /* backed by refcounted pages          */
         _XBF_RUN_QUEUES = (1 << 19),/* run block device task queue         */
         _XBF_DELWRI_Q = (1 << 21),   /* buffer on delwri queue             */
+
+        /*
+         * Special flag for supporting metadata blocks smaller than a FSB.
+         *
+         * In this case we can have multiple xfs_buf_t on a single page and
+         * need to lock out concurrent xfs_buf_t readers as they only
+         * serialise access to the buffer.
+         *
+         * If the FSB size >= PAGE_CACHE_SIZE case, we have no serialisation
+         * between reads of the page. Hence we can have one thread read the
+         * page and modify it, but then race with another thread that thinks
+         * the page is not up-to-date and hence reads it again.
+         *
+         * The result is that the first modifcation to the page is lost.
+         * This sort of AGF/AGI reading race can happen when unlinking inodes
+         * that require truncation and results in the AGI unlinked list
+         * modifications being lost.
+         */
+        _XBF_PAGE_LOCKED = (1 << 22),
 } xfs_buf_flags_t;
 
 typedef enum {
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 65e78c13d4ae..5f60363b9343 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -184,19 +184,24 @@ xfs_file_release(
         return -xfs_release(XFS_I(inode));
 }
 
+/*
+ * We ignore the datasync flag here because a datasync is effectively
+ * identical to an fsync. That is, datasync implies that we need to write
+ * only the metadata needed to be able to access the data that is written
+ * if we crash after the call completes. Hence if we are writing beyond
+ * EOF we have to log the inode size change as well, which makes it a
+ * full fsync. If we don't write beyond EOF, the inode core will be
+ * clean in memory and so we don't need to log the inode, just like
+ * fsync.
+ */
 STATIC int
 xfs_file_fsync(
         struct file     *filp,
         struct dentry   *dentry,
         int             datasync)
 {
-        int             flags = FSYNC_WAIT;
-
-        if (datasync)
-                flags |= FSYNC_DATA;
         xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
-        return -xfs_fsync(XFS_I(dentry->d_inode), flags,
-                        (xfs_off_t)0, (xfs_off_t)-1);
+        return -xfs_fsync(XFS_I(dentry->d_inode));
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 9d73cb5c0fc7..25eb2a9e8d9b 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -230,14 +230,6 @@ static inline void vn_atime_to_time_t(bhv_vnode_t *vp, time_t *tt)
 #define ATTR_NOSIZETOK  0x400   /* Don't get the SIZE token */
 
 /*
- * Flags to vop_fsync/reclaim.
- */
-#define FSYNC_NOWAIT    0       /* asynchronous flush */
-#define FSYNC_WAIT      0x1     /* synchronous fsync or forced reclaim */
-#define FSYNC_INVAL     0x2     /* flush and invalidate cached data */
-#define FSYNC_DATA      0x4     /* synchronous fsync of data only */
-
-/*
  * Tracking vnode activity.
  */
 #if defined(XFS_INODE_TRACE)