xfs: support CoW in fsdax mode

In fsdax mode, WRITE and ZERO on a shared extent need CoW performed.
After that, new allocated extents needs to be remapped to the file.  So,
add a CoW identification in ->iomap_begin(), and implement ->iomap_end()
to do the remapping work.

[akpm@linux-foundation.org: make xfs_dax_fault() static]
Link: https://lkml.kernel.org/r/20220603053738.1218681-14-ruansy.fnst@fujitsu.com
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.wiliams@intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.com>
Cc: Goldwyn Rodrigues <rgoldwyn@suse.de>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5a171c0b244b7cd5640f9b6ed8e69b0131eeea2e..45d8e64188f368b02afd61757e33384658904bb3 100644 (file)
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -25,6 +25,7 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 
+#include <linux/dax.h>
 #include <linux/falloc.h>
 #include <linux/backing-dev.h>
 #include <linux/mman.h>
@@ -669,7 +670,7 @@ xfs_file_dax_write(
        pos = iocb->ki_pos;
 
        trace_xfs_file_dax_write(iocb, from);
-       ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
+       ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops);
        if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
                i_size_write(inode, iocb->ki_pos);
                error = xfs_setfilesize(ip, pos, ret);
@@ -1254,6 +1255,31 @@ xfs_file_llseek(
        return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
+#ifdef CONFIG_FS_DAX
+static int
+xfs_dax_fault(
+       struct vm_fault         *vmf,
+       enum page_entry_size    pe_size,
+       bool                    write_fault,
+       pfn_t                   *pfn)
+{
+       return dax_iomap_fault(vmf, pe_size, pfn, NULL,
+                       (write_fault && !vmf->cow_page) ?
+                               &xfs_dax_write_iomap_ops :
+                               &xfs_read_iomap_ops);
+}
+#else
+static int
+xfs_dax_fault(
+       struct vm_fault         *vmf,
+       enum page_entry_size    pe_size,
+       bool                    write_fault,
+       pfn_t                   *pfn)
+{
+       return 0;
+}
+#endif
+
 /*
  * Locking for serialisation of IO during page faults. This results in a lock
  * ordering of:
@@ -1285,10 +1311,7 @@ __xfs_filemap_fault(
                pfn_t pfn;
 
                xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-               ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
-                               (write_fault && !vmf->cow_page) ?
-                                &xfs_direct_write_iomap_ops :
-                                &xfs_read_iomap_ops);
+               ret = xfs_dax_fault(vmf, pe_size, write_fault, &pfn);
                if (ret & VM_FAULT_NEEDDSYNC)
                        ret = dax_finish_sync_fault(vmf, pe_size, pfn);
                xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 5a393259a3a38bb37c8eee02a198a8533ef2c0ba..4c07f5e718fb15466c610b09857f66c0a94e442d 100644 (file)
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -773,7 +773,8 @@ xfs_direct_write_iomap_begin(
 
                /* may drop and re-acquire the ilock */
                error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-                               &lockmode, flags & IOMAP_DIRECT);
+                               &lockmode,
+                               (flags & IOMAP_DIRECT) || IS_DAX(inode));
                if (error)
                        goto out_unlock;
                if (shared)
@@ -867,6 +868,33 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
        .iomap_begin            = xfs_direct_write_iomap_begin,
 };
 
+static int
+xfs_dax_write_iomap_end(
+       struct inode            *inode,
+       loff_t                  pos,
+       loff_t                  length,
+       ssize_t                 written,
+       unsigned                flags,
+       struct iomap            *iomap)
+{
+       struct xfs_inode        *ip = XFS_I(inode);
+
+       if (!xfs_is_cow_inode(ip))
+               return 0;
+
+       if (!written) {
+               xfs_reflink_cancel_cow_range(ip, pos, length, true);
+               return 0;
+       }
+
+       return xfs_reflink_end_cow(ip, pos, written);
+}
+
+const struct iomap_ops xfs_dax_write_iomap_ops = {
+       .iomap_begin    = xfs_direct_write_iomap_begin,
+       .iomap_end      = xfs_dax_write_iomap_end,
+};
+
 static int
 xfs_buffered_write_iomap_begin(
        struct inode            *inode,

diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index e88dc162c785ee05f67ecebe4fcdc49d21160568..c782e8c0479c0afc6ff27028ea36fc9d20350f2b 100644 (file)
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -51,5 +51,6 @@ extern const struct iomap_ops xfs_direct_write_iomap_ops;
 extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/