dax: support dirty DAX entries in radix tree

Add support for tracking dirty DAX entries in the struct address_space
radix tree.  This tree is already used for dirty page writeback, and it
already supports the use of exceptional (non struct page*) entries.

In order to properly track dirty DAX pages we will insert new
exceptional entries into the radix tree that represent dirty DAX PTE or
PMD pages.  These exceptional entries will also contain the writeback
addresses for the PTE or PMD faults that we can use at fsync/msync time.

There are currently two types of exceptional entries (shmem and shadow)
that can be placed into the radix tree, and this adds a third.  We rely
on the fact that only one type of exceptional entry can be found in a
given radix tree based on its usage.  This happens for free with DAX vs
shmem but we explicitly prevent shadow entries from being added to radix
trees for DAX mappings.

The only shadow entries that would be generated for DAX radix trees
would be to track zero page mappings that were created for holes.  These
pages would receive minimal benefit from having shadow entries, and the
choice to have only one type of exceptional entry in a given radix tree
makes the logic simpler both in clear_exceptional_entry() and in the
rest of DAX.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jan Kara <jack@suse.com>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 16 insertions, 1 deletions

diff --git a/include/linux/dax.h b/include/linux/dax.h
index b415e521528d..e9d57f680f50 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -36,4 +36,9 @@ static inline bool vma_is_dax(struct vm_area_struct *vma)
 {
 	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
 }
+
+static inline bool dax_mapping(struct address_space *mapping)
+{
+	return mapping->host && IS_DAX(mapping->host);
+}
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index eb73d74ed992..0d7570320d63 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -433,7 +433,8 @@ struct address_space {
 	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
-	unsigned long		nrshadows;	/* number of shadow entries */
+	/* number of shadow or DAX exceptional entries */
+	unsigned long		nrexceptional;
 	pgoff_t			writeback_index;/* writeback starts here */
 	const struct address_space_operations *a_ops;	/* methods */
 	unsigned long		flags;		/* error bits/gfp mask */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 57e7d87d2d4c..7c88ad156a29 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -51,6 +51,15 @@
 #define RADIX_TREE_EXCEPTIONAL_ENTRY	2
 #define RADIX_TREE_EXCEPTIONAL_SHIFT	2
 
+#define RADIX_DAX_MASK	0xf
+#define RADIX_DAX_SHIFT	4
+#define RADIX_DAX_PTE  (0x4 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_PMD  (0x8 | RADIX_TREE_EXCEPTIONAL_ENTRY)
+#define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_MASK)
+#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT))
+#define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \
+		RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE)))
+
 static inline int radix_tree_is_indirect_ptr(void *ptr)
 {
 	return (int)((unsigned long)ptr & RADIX_TREE_INDIRECT_PTR);