Merge branch 'xfs-dax-updates' into for-next

[karo-tx-linux.git] / fs / xfs / xfs_file.c

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3bf4c099dd2e71edf3faa7c5779293c5e0fee8c..39743efae79501f3d590b05722ebd0c30deb50f4 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1493,7 +1493,7 @@ xfs_file_llseek(
  *
  * mmap_sem (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmap_lock (XFS - truncate serialisation)
+ *     i_mmaplock (XFS - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */
@@ -1519,8 +1519,7 @@ xfs_filemap_page_mkwrite(
        xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
        if (IS_DAX(inode)) {
-               ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
-                                   xfs_end_io_dax_write);
+               ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
        } else {
                ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
                ret = block_page_mkwrite_return(ret);
@@ -1554,7 +1553,7 @@ xfs_filemap_fault(
                 * changes to xfs_get_blocks_direct() to map unwritten extent
                 * ioend for conversion on read-only mappings.
                 */
-               ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+               ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
        } else
                ret = filemap_fault(vma, vmf);
        xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1562,6 +1561,13 @@ xfs_filemap_fault(
        return ret;
 }
 
+/*
+ * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
+ * both read and write faults. Hence we need to handle both cases. There is no
+ * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * handle both cases here. @flags carries the information on the type of fault
+ * occuring.
+ */
 STATIC int
 xfs_filemap_pmd_fault(
        struct vm_area_struct   *vma,
@@ -1578,15 +1584,54 @@ xfs_filemap_pmd_fault(
 
        trace_xfs_filemap_pmd_fault(ip);
 
-       sb_start_pagefault(inode->i_sb);
-       file_update_time(vma->vm_file);
+       if (flags & FAULT_FLAG_WRITE) {
+               sb_start_pagefault(inode->i_sb);
+               file_update_time(vma->vm_file);
+       }
+
        xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-       ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
-                                   xfs_end_io_dax_write);
+       ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
+                             NULL);
        xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-       sb_end_pagefault(inode->i_sb);
 
+       if (flags & FAULT_FLAG_WRITE)
+               sb_end_pagefault(inode->i_sb);
+
+       return ret;
+}
+
+/*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
+ * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
+ * barrier in place.
+ */
+static int
+xfs_filemap_pfn_mkwrite(
+       struct vm_area_struct   *vma,
+       struct vm_fault         *vmf)
+{
+
+       struct inode            *inode = file_inode(vma->vm_file);
+       struct xfs_inode        *ip = XFS_I(inode);
+       int                     ret = VM_FAULT_NOPAGE;
+       loff_t                  size;
+
+       trace_xfs_filemap_pfn_mkwrite(ip);
+
+       sb_start_pagefault(inode->i_sb);
+       file_update_time(vma->vm_file);
+
+       /* check if the faulting page hasn't raced with truncate */
+       xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+       size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+       if (vmf->pgoff >= size)
+               ret = VM_FAULT_SIGBUS;
+       xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+       sb_end_pagefault(inode->i_sb);
        return ret;
+
 }
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
@@ -1594,6 +1639,7 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
        .pmd_fault      = xfs_filemap_pmd_fault,
        .map_pages      = filemap_map_pages,
        .page_mkwrite   = xfs_filemap_page_mkwrite,
+       .pfn_mkwrite    = xfs_filemap_pfn_mkwrite,
 };
 
 STATIC int