iomap: Add a page_prepare callback

Move the page_done callback into a separate iomap_page_ops structure and
add a page_prepare calback to be called before the next page is written
to.  In gfs2, we'll want to start a transaction in page_prepare and end
it in page_done.  Other filesystems that implement data journaling will
require the same kind of mechanism.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 02b2646d84b3a38d967a6811b35e911aab658681..f6d1a3893f5a1ff60aa934db25fd5a799f4f1b3f 100644 (file)
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -965,15 +965,20 @@ static void gfs2_write_unlock(struct inode *inode)
        gfs2_glock_dq_uninit(&ip->i_gh);
 }
 
-static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
-                               unsigned copied, struct page *page,
-                               struct iomap *iomap)
+static void gfs2_iomap_page_done(struct inode *inode, loff_t pos,
+                                unsigned copied, struct page *page,
+                                struct iomap *iomap)
 {
        struct gfs2_inode *ip = GFS2_I(inode);
 
-       gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+       if (page)
+               gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
 }
 
+static const struct iomap_page_ops gfs2_iomap_page_ops = {
+       .page_done = gfs2_iomap_page_done,
+};
+
 static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
                                  loff_t length, unsigned flags,
                                  struct iomap *iomap,
@@ -1051,7 +1056,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
                }
        }
        if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
-               iomap->page_done = gfs2_iomap_journaled_page_done;
+               iomap->page_ops = &gfs2_iomap_page_ops;
        return 0;
 
 out_trans_end:

diff --git a/fs/iomap.c b/fs/iomap.c
index e6453c1c831e7093913dcfc9498777a3a5c67906..fbfe20b7f6f0a14772642d0d896ad4c9b20e78a0 100644 (file)
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -657,6 +657,7 @@ static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
                struct page **pagep, struct iomap *iomap)
 {
+       const struct iomap_page_ops *page_ops = iomap->page_ops;
        pgoff_t index = pos >> PAGE_SHIFT;
        struct page *page;
        int status = 0;
@@ -666,9 +667,17 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
        if (fatal_signal_pending(current))
                return -EINTR;
 
+       if (page_ops && page_ops->page_prepare) {
+               status = page_ops->page_prepare(inode, pos, len, iomap);
+               if (status)
+                       return status;
+       }
+
        page = grab_cache_page_write_begin(inode->i_mapping, index, flags);
-       if (!page)
-               return -ENOMEM;
+       if (!page) {
+               status = -ENOMEM;
+               goto out_no_page;
+       }
 
        if (iomap->type == IOMAP_INLINE)
                iomap_read_inline_data(inode, page, iomap);
@@ -676,15 +685,21 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
                status = __block_write_begin_int(page, pos, len, NULL, iomap);
        else
                status = __iomap_write_begin(inode, pos, len, page, iomap);
-       if (unlikely(status)) {
-               unlock_page(page);
-               put_page(page);
-               page = NULL;
 
-               iomap_write_failed(inode, pos, len);
-       }
+       if (unlikely(status))
+               goto out_unlock;
 
        *pagep = page;
+       return 0;
+
+out_unlock:
+       unlock_page(page);
+       put_page(page);
+       iomap_write_failed(inode, pos, len);
+
+out_no_page:
+       if (page_ops && page_ops->page_done)
+               page_ops->page_done(inode, pos, 0, NULL, iomap);
        return status;
 }
 
@@ -758,6 +773,7 @@ static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
                unsigned copied, struct page *page, struct iomap *iomap)
 {
+       const struct iomap_page_ops *page_ops = iomap->page_ops;
        int ret;
 
        if (iomap->type == IOMAP_INLINE) {
@@ -770,8 +786,8 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
        }
 
        __generic_write_end(inode, pos, ret, page);
-       if (iomap->page_done)
-               iomap->page_done(inode, pos, copied, page, iomap);
+       if (page_ops && page_ops->page_done)
+               page_ops->page_done(inode, pos, copied, page, iomap);
        put_page(page);
 
        if (ret < len)

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 0fefb5455bdaf9a0c0167701b7477fc172ee7eca..2103b94cb1bff008e2b3fb47504f068181ae694a 100644 (file)
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -53,6 +53,8 @@ struct vm_fault;
  */
 #define IOMAP_NULL_ADDR -1ULL  /* addr is not valid */
 
+struct iomap_page_ops;
+
 struct iomap {
        u64                     addr; /* disk offset of mapping, bytes */
        loff_t                  offset; /* file offset of mapping, bytes */
@@ -63,12 +65,22 @@ struct iomap {
        struct dax_device       *dax_dev; /* dax_dev for dax operations */
        void                    *inline_data;
        void                    *private; /* filesystem private */
+       const struct iomap_page_ops *page_ops;
+};
 
-       /*
-        * Called when finished processing a page in the mapping returned in
-        * this iomap.  At least for now this is only supported in the buffered
-        * write path.
-        */
+/*
+ * When a filesystem sets page_ops in an iomap mapping it returns, page_prepare
+ * and page_done will be called for each page written to.  This only applies to
+ * buffered writes as unbuffered writes will not typically have pages
+ * associated with them.
+ *
+ * When page_prepare succeeds, page_done will always be called to do any
+ * cleanup work necessary.  In that page_done call, @page will be NULL if the
+ * associated page could not be obtained.
+ */
+struct iomap_page_ops {
+       int (*page_prepare)(struct inode *inode, loff_t pos, unsigned len,
+                       struct iomap *iomap);
        void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
                        struct page *page, struct iomap *iomap);
 };