dax: Allow DAX code to replace exceptional entries

Currently we forbid page_cache_tree_insert() to replace exceptional radix
tree entries for DAX inodes. However to make DAX faults race free we will
lock radix tree entries and when hole is created, we need to replace
such locked radix tree entry with a hole page. So modify
page_cache_tree_insert() to allow that.

Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>

diff --git a/include/linux/dax.h b/include/linux/dax.h
index 70600b6..aa14893 100644 (file)
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -3,6 +3,7 @@
 
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/radix-tree.h>
 #include <asm/pgtable.h>
 
 /* We use lowest available exceptional entry bit for locking */

diff --git a/mm/filemap.c b/mm/filemap.c
index f2479af..dfe55c2 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -597,14 +597,21 @@ static int page_cache_tree_insert(struct address_space *mapping,
                if (!radix_tree_exceptional_entry(p))
                        return -EEXIST;
 
-               if (WARN_ON(dax_mapping(mapping)))
-                       return -EINVAL;
-
-               if (shadowp)
-                       *shadowp = p;
                mapping->nrexceptional--;
-               if (node)
-                       workingset_node_shadows_dec(node);
+               if (!dax_mapping(mapping)) {
+                       if (shadowp)
+                               *shadowp = p;
+                       if (node)
+                               workingset_node_shadows_dec(node);
+               } else {
+                       /* DAX can replace empty locked entry with a hole */
+                       WARN_ON_ONCE(p !=
+                               (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY |
+                                        RADIX_DAX_ENTRY_LOCK));
+                       /* DAX accounts exceptional entries as normal pages */
+                       if (node)
+                               workingset_node_pages_dec(node);
+               }
        }
        radix_tree_replace_slot(slot, page);
        mapping->nrpages++;