In preparation for the dax implementation to start associating dax pages
to inodes via page->mapping, we need to provide a 'struct
address_space_operations' instance for dax. Otherwise, direct-I/O
triggers incorrect page cache assumptions and warnings.
Cc: "Theodore Ts'o" <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: [email protected]
Cc: Jan Kara <[email protected]>
Signed-off-by: Dan Williams <[email protected]>
---
fs/ext4/inode.c | 42 +++++++++++++++++++++++++++++++-----------
1 file changed, 31 insertions(+), 11 deletions(-)
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c94780075b04..249a97b19181 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2725,12 +2725,6 @@ static int ext4_writepages(struct address_space *mapping,
percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
- if (dax_mapping(mapping)) {
- ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
- wbc);
- goto out_writepages;
- }
-
/*
* No pages to write? This is mainly a kludge to avoid starting
* a transaction for special inodes like journal inode on last iput()
@@ -2955,6 +2949,27 @@ static int ext4_writepages(struct address_space *mapping,
return ret;
}
+static int ext4_dax_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ int ret;
+ long nr_to_write = wbc->nr_to_write;
+ struct inode *inode = mapping->host;
+ struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
+
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
+ percpu_down_read(&sbi->s_journal_flag_rwsem);
+ trace_ext4_writepages(inode, wbc);
+
+ ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+ trace_ext4_writepages_result(inode, wbc, ret,
+ nr_to_write - wbc->nr_to_write);
+ percpu_up_read(&sbi->s_journal_flag_rwsem);
+ return ret;
+}
+
static int ext4_nonda_switch(struct super_block *sb)
{
s64 free_clusters, dirty_clusters;
@@ -3857,10 +3872,6 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
if (ext4_has_inline_data(inode))
return 0;
- /* DAX uses iomap path now */
- if (WARN_ON_ONCE(IS_DAX(inode)))
- return 0;
-
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
if (iov_iter_rw(iter) == READ)
ret = ext4_direct_IO_read(iocb, iter);
@@ -3946,6 +3957,13 @@ static const struct address_space_operations ext4_da_aops = {
.error_remove_page = generic_error_remove_page,
};
+static const struct address_space_operations ext4_dax_aops = {
+ .writepages = ext4_dax_writepages,
+ .direct_IO = noop_direct_IO,
+ .set_page_dirty = noop_set_page_dirty,
+ .invalidatepage = noop_invalidatepage,
+};
+
void ext4_set_aops(struct inode *inode)
{
switch (ext4_inode_journal_mode(inode)) {
@@ -3958,7 +3976,9 @@ void ext4_set_aops(struct inode *inode)
default:
BUG();
}
- if (test_opt(inode->i_sb, DELALLOC))
+ if (IS_DAX(inode))
+ inode->i_mapping->a_ops = &ext4_dax_aops;
+ else if (test_opt(inode->i_sb, DELALLOC))
inode->i_mapping->a_ops = &ext4_da_aops;
else
inode->i_mapping->a_ops = &ext4_aops;
On Fri 30-03-18 21:02:36, Dan Williams wrote:
> In preparation for the dax implementation to start associating dax pages
> to inodes via page->mapping, we need to provide a 'struct
> address_space_operations' instance for dax. Otherwise, direct-I/O
> triggers incorrect page cache assumptions and warnings.
>
> Cc: "Theodore Ts'o" <[email protected]>
> Cc: Andreas Dilger <[email protected]>
> Cc: [email protected]
> Cc: Jan Kara <[email protected]>
> Signed-off-by: Dan Williams <[email protected]>
Looks good. You can add:
Reviewed-by: Jan Kara <[email protected]>
Honza
> ---
> fs/ext4/inode.c | 42 +++++++++++++++++++++++++++++++-----------
> 1 file changed, 31 insertions(+), 11 deletions(-)
>
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index c94780075b04..249a97b19181 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -2725,12 +2725,6 @@ static int ext4_writepages(struct address_space *mapping,
> percpu_down_read(&sbi->s_journal_flag_rwsem);
> trace_ext4_writepages(inode, wbc);
>
> - if (dax_mapping(mapping)) {
> - ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
> - wbc);
> - goto out_writepages;
> - }
> -
> /*
> * No pages to write? This is mainly a kludge to avoid starting
> * a transaction for special inodes like journal inode on last iput()
> @@ -2955,6 +2949,27 @@ static int ext4_writepages(struct address_space *mapping,
> return ret;
> }
>
> +static int ext4_dax_writepages(struct address_space *mapping,
> + struct writeback_control *wbc)
> +{
> + int ret;
> + long nr_to_write = wbc->nr_to_write;
> + struct inode *inode = mapping->host;
> + struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
> +
> + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
> + return -EIO;
> +
> + percpu_down_read(&sbi->s_journal_flag_rwsem);
> + trace_ext4_writepages(inode, wbc);
> +
> + ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
> + trace_ext4_writepages_result(inode, wbc, ret,
> + nr_to_write - wbc->nr_to_write);
> + percpu_up_read(&sbi->s_journal_flag_rwsem);
> + return ret;
> +}
> +
> static int ext4_nonda_switch(struct super_block *sb)
> {
> s64 free_clusters, dirty_clusters;
> @@ -3857,10 +3872,6 @@ static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
> if (ext4_has_inline_data(inode))
> return 0;
>
> - /* DAX uses iomap path now */
> - if (WARN_ON_ONCE(IS_DAX(inode)))
> - return 0;
> -
> trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
> if (iov_iter_rw(iter) == READ)
> ret = ext4_direct_IO_read(iocb, iter);
> @@ -3946,6 +3957,13 @@ static const struct address_space_operations ext4_da_aops = {
> .error_remove_page = generic_error_remove_page,
> };
>
> +static const struct address_space_operations ext4_dax_aops = {
> + .writepages = ext4_dax_writepages,
> + .direct_IO = noop_direct_IO,
> + .set_page_dirty = noop_set_page_dirty,
> + .invalidatepage = noop_invalidatepage,
> +};
> +
> void ext4_set_aops(struct inode *inode)
> {
> switch (ext4_inode_journal_mode(inode)) {
> @@ -3958,7 +3976,9 @@ void ext4_set_aops(struct inode *inode)
> default:
> BUG();
> }
> - if (test_opt(inode->i_sb, DELALLOC))
> + if (IS_DAX(inode))
> + inode->i_mapping->a_ops = &ext4_dax_aops;
> + else if (test_opt(inode->i_sb, DELALLOC))
> inode->i_mapping->a_ops = &ext4_da_aops;
> else
> inode->i_mapping->a_ops = &ext4_aops;
>
--
Jan Kara <jack-IBi9RG/[email protected]>
SUSE Labs, CR