dax: add dax_zero_page_range

This new function allows us to support hole-punch for DAX files by zeroing
a partial page, as opposed to the dax_truncate_page() function which can
only truncate to the end of the page.  Reimplement dax_truncate_page() to
call dax_zero_page_range().

[ross.zwisler@linux.intel.com: ported to 3.13-rc2]
[akpm@linux-foundation.org: fix typos in comments]
Signed-off-by: Matthew Wilcox <matthew.r.wilcox@intel.com>
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Andreas Dilger <andreas.dilger@intel.com>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/filesystems/dax.txt b/Documentation/filesystems/dax.txt
index 635adaa1e425d67576fafa50e5ff2e6e58015c4c..ebcd97f03654c8544faa906691122efad65fd29d 100644 (file)
--- a/Documentation/filesystems/dax.txt
+++ b/Documentation/filesystems/dax.txt
@@ -62,6 +62,7 @@ Filesystem support consists of
   for fault and page_mkwrite (which should probably call dax_fault() and
   dax_mkwrite(), passing the appropriate get_block() callback)
 - calling dax_truncate_page() instead of block_truncate_page() for DAX files
+- calling dax_zero_page_range() instead of zero_user() for DAX files
 - ensuring that there is sufficient locking between reads, writes,
   truncates and page faults
 

diff --git a/fs/dax.c b/fs/dax.c
index ebf9b2231b0f824738437ec95a04050ddbf8bff4..ed1619ec6537c25707ea801e772571f3c2fcaf5d 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -464,31 +464,35 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 EXPORT_SYMBOL_GPL(dax_fault);
 
 /**
- * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * dax_zero_page_range - zero a range within a page of a DAX file
  * @inode: The file being truncated
  * @from: The file offset that is being truncated to
+ * @length: The number of bytes to zero
  * @get_block: The filesystem method used to translate file offsets to blocks
  *
- * Similar to block_truncate_page(), this function can be called by a
- * filesystem when it is truncating an DAX file to handle the partial page.
+ * This function can be called by a filesystem when it is zeroing part of a
+ * page in a DAX file.  This is intended for hole-punch operations.  If
+ * you are truncating a file, the helper function dax_truncate_page() may be
+ * more convenient.
  *
  * We work in terms of PAGE_CACHE_SIZE here for commonality with
  * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
  * took care of disposing of the unnecessary blocks.  Even if the filesystem
  * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
- * since the file might be mmaped.
+ * since the file might be mmapped.
  */
-int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
+                                                       get_block_t get_block)
 {
        struct buffer_head bh;
        pgoff_t index = from >> PAGE_CACHE_SHIFT;
        unsigned offset = from & (PAGE_CACHE_SIZE-1);
-       unsigned length = PAGE_CACHE_ALIGN(from) - from;
        int err;
 
        /* Block boundary? Nothing to do */
        if (!length)
                return 0;
+       BUG_ON((offset + length) > PAGE_CACHE_SIZE);
 
        memset(&bh, 0, sizeof(bh));
        bh.b_size = PAGE_CACHE_SIZE;
@@ -505,4 +509,26 @@ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
 
        return 0;
 }
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
+/**
+ * dax_truncate_page - handle a partial page being truncated in a DAX file
+ * @inode: The file being truncated
+ * @from: The file offset that is being truncated to
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * Similar to block_truncate_page(), this function can be called by a
+ * filesystem when it is truncating a DAX file to handle the partial page.
+ *
+ * We work in terms of PAGE_CACHE_SIZE here for commonality with
+ * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
+ * took care of disposing of the unnecessary blocks.  Even if the filesystem
+ * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
+ * since the file might be mmapped.
+ */
+int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
+{
+       unsigned length = PAGE_CACHE_ALIGN(from) - from;
+       return dax_zero_page_range(inode, from, length, get_block);
+}
 EXPORT_SYMBOL_GPL(dax_truncate_page);

diff --git a/include/linux/fs.h b/include/linux/fs.h
index d46f8fe6a0ea758bc29c215e29a4235e5e93e41f..ed5a0900b94d49989b9eb0fdff8db935fabc66a9 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2589,6 +2589,7 @@ extern int nonseekable_open(struct inode * inode, struct file * filp);
 ssize_t dax_do_io(int rw, struct kiocb *, struct inode *, struct iov_iter *,
                loff_t, get_block_t, dio_iodone_t, int flags);
 int dax_clear_blocks(struct inode *, sector_t block, long size);
+int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
 int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
 #define dax_mkwrite(vma, vmf, gb)      dax_fault(vma, vmf, gb)