writeback: add {CONFIG|BDI_CAP|FS}_CGROUP_WRITEBACK
cgroup writeback requires support from both bdi and filesystem sides.
Add BDI_CAP_CGROUP_WRITEBACK and FS_CGROUP_WRITEBACK to indicate
support and enable BDI_CAP_CGROUP_WRITEBACK on block based bdi's by
default. Also, define CONFIG_CGROUP_WRITEBACK which is enabled if
both MEMCG and BLK_CGROUP are enabled.
inode_cgwb_enabled() which determines whether a given inode's both bdi
and fs support cgroup writeback is added.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/block/blk-core.c b/block/blk-core.c
index c3ba9c3..c114a61 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -621,7 +621,7 @@
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
- q->backing_dev_info.capabilities = 0;
+ q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK;
q->backing_dev_info.name = "block";
q->node = node_id;
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index bfdaa18..6bb3123 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -134,12 +134,15 @@
* BDI_CAP_NO_WRITEBACK: Don't write pages back
* BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages
* BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold.
+ *
+ * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback.
*/
#define BDI_CAP_NO_ACCT_DIRTY 0x00000001
#define BDI_CAP_NO_WRITEBACK 0x00000002
#define BDI_CAP_NO_ACCT_WB 0x00000004
#define BDI_CAP_STABLE_WRITES 0x00000008
#define BDI_CAP_STRICTLIMIT 0x00000010
+#define BDI_CAP_CGROUP_WRITEBACK 0x00000020
#define BDI_CAP_NO_ACCT_AND_WRITEBACK \
(BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB)
@@ -229,4 +232,31 @@
return 0;
}
-#endif /* _LINUX_BACKING_DEV_H */
+#ifdef CONFIG_CGROUP_WRITEBACK
+
+/**
+ * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
+ * @inode: inode of interest
+ *
+ * cgroup writeback requires support from both the bdi and filesystem.
+ * Test whether @inode has both.
+ */
+static inline bool inode_cgwb_enabled(struct inode *inode)
+{
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
+
+ return bdi_cap_account_dirty(bdi) &&
+ (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
+ (inode->i_sb->s_type->fs_flags & FS_CGROUP_WRITEBACK);
+}
+
+#else /* CONFIG_CGROUP_WRITEBACK */
+
+static inline bool inode_cgwb_enabled(struct inode *inode)
+{
+ return false;
+}
+
+#endif /* CONFIG_CGROUP_WRITEBACK */
+
+#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ce100b87..74e0ae0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1897,6 +1897,7 @@
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */
+#define FS_CGROUP_WRITEBACK 32 /* Supports cgroup-aware writeback */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
diff --git a/init/Kconfig b/init/Kconfig
index dc24dec..d4f7633 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1141,6 +1141,11 @@
Enable some debugging help. Currently it exports additional stat
files in a cgroup which can be useful for debugging.
+config CGROUP_WRITEBACK
+ bool
+ depends on MEMCG && BLK_CGROUP
+ default y
+
endif # CGROUPS
config CHECKPOINT_RESTORE