On Mon 09-10-17 14:29:10, Tejun Heo wrote:
> Add wbc->blkcg_css so that the blkcg_css association can be specified
> independently and implement submit_bh_blkcg_css() using it. This will
> be used to override cgroup membership on specific buffer_heads.
>
> Signed-off-by: Tejun Heo <t...@kernel.org>
> Cc: Jan Kara <j...@suse.cz>
> Cc: Jens Axboe <ax...@kernel.dk>
Hum, I dislike growing wbc just to pass blkcg_css through one function in
fs/buffer.c (in otherwise empty wbc). Not that space would be a big concern
for wbc but it just gets messier... Cannot we just refactor the code a
bit like:
1) Create function
struct bio *create_bio_bh(int op, int op_flags, struct buffer_head *bh,
enum rw_hint write_hint);
which would create bio from bh.
2) Make submit_bh(), submit_bh_wbc(), submit_bh_blkcg_css() use this and
the latter two would further tweak the bio as needed before submitting.
Thoughts?
Honza
> ---
> fs/buffer.c | 12 ++++++++++++
> fs/fs-writeback.c | 1 +
> include/linux/buffer_head.h | 11 +++++++++++
> include/linux/writeback.h | 6 ++++--
> 4 files changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/fs/buffer.c b/fs/buffer.c
> index 170df85..fac4f9a 100644
> --- a/fs/buffer.c
> +++ b/fs/buffer.c
> @@ -3143,6 +3143,18 @@ int submit_bh(int op, int op_flags, struct buffer_head
> *bh)
> }
> EXPORT_SYMBOL(submit_bh);
>
> +#ifdef CONFIG_CGROUP_WRITEBACK
> +int submit_bh_blkcg_css(int op, int op_flags, struct buffer_head *bh,
> + struct cgroup_subsys_state *blkcg_css)
> +{
> + struct writeback_control wbc = { .blkcg_css = blkcg_css };
> +
> + /* @wbc is used just to override the bio's blkcg_css */
> + return submit_bh_wbc(op, op_flags, bh, 0, &wbc);
> +}
> +EXPORT_SYMBOL(submit_bh_blkcg_css);
> +#endif
> +
> /**
> * ll_rw_block: low-level access to block devices (DEPRECATED)
> * @op: whether to %READ or %WRITE
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 245c430..cd882e6 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -538,6 +538,7 @@ void wbc_attach_and_unlock_inode(struct writeback_control
> *wbc,
> }
>
> wbc->wb = inode_to_wb(inode);
> + wbc->blkcg_css = wbc->wb->blkcg_css;
> wbc->inode = inode;
>
> wbc->wb_id = wbc->wb->memcg_css->id;
> diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
> index c8dae55..abb4dd4 100644
> --- a/include/linux/buffer_head.h
> +++ b/include/linux/buffer_head.h
> @@ -13,6 +13,7 @@
> #include <linux/pagemap.h>
> #include <linux/wait.h>
> #include <linux/atomic.h>
> +#include <linux/cgroup.h>
>
> #ifdef CONFIG_BLOCK
>
> @@ -205,6 +206,16 @@ int bh_submit_read(struct buffer_head *bh);
> loff_t page_cache_seek_hole_data(struct inode *inode, loff_t offset,
> loff_t length, int whence);
>
> +#ifdef CONFIG_CGROUP_WRITEBACK
> +int submit_bh_blkcg(int op, int op_flags, struct buffer_head *bh,
> + struct cgroup_subsys_state *blkcg_css);
> +#else
> +static inline int submit_bh_blkcg(int op, int op_flags, struct buffer_head
> *bh,
> + struct cgroup_subsys_state *blkcg_css)
> +{
> + return submit_bh(op, op_flags, bh);
> +}
> +#endif
> extern int buffer_heads_over_limit;
>
> /*
> diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> index d581579..81e5946 100644
> --- a/include/linux/writeback.h
> +++ b/include/linux/writeback.h
> @@ -91,6 +91,8 @@ struct writeback_control {
> unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
> #ifdef CONFIG_CGROUP_WRITEBACK
> struct bdi_writeback *wb; /* wb this writeback is issued under */
> + struct cgroup_subsys_state *blkcg_css; /* usually wb->blkcg_css but
> + may be overridden */
> struct inode *inode; /* inode being written out */
>
> /* foreign inode detection, see wbc_detach_inode() */
> @@ -277,8 +279,8 @@ static inline void wbc_init_bio(struct writeback_control
> *wbc, struct bio *bio)
> * behind a slow cgroup. Ultimately, we want pageout() to kick off
> * regular writeback instead of writing things out itself.
> */
> - if (wbc->wb)
> - bio_associate_blkcg(bio, wbc->wb->blkcg_css);
> + if (wbc->blkcg_css)
> + bio_associate_blkcg(bio, wbc->blkcg_css);
> }
>
> #else /* CONFIG_CGROUP_WRITEBACK */
> --
> 2.9.5
>
--
Jan Kara <j...@suse.com>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
