[PATCH 0/25 v2] fs: Convert all embedded bdis into separate ones

[PATCH 0/25 v2] fs: Convert all embedded bdis into separate ones

[Jan Kara]

Hello,

this is the second revision of the patch series which converts all embedded
occurences of struct backing_dev_info to use standalone dynamically allocated
structures. This makes bdi handling unified across all bdi users and generally
removes some boilerplate code from filesystems setting up their own bdi. It
also allows us to remove some code from generic bdi implementation.

The patches were only compile-tested for most filesystems (I've tested
mounting only for NFS & btrfs) so fs maintainers please have a look whether
the changes look sound to you.

This series is based on top of bdi fixes that were merged into linux-block
git tree into for-next branch. I have pushed out the result as a branch to

git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs.git bdi

Changes since v1:
* Added some acks
* Added further FUSE cleanup patch
* Added removal of unused argument to bdi_register()
* Fixed up some compilation failures spotted by 0-day testing

								Honza

[PATCH 04/25] fs: Provide infrastructure for dynamic BDIs in filesystems

[Jan Kara]

Provide helper functions for setting up dynamically allocated
backing_dev_info structures for filesystems and cleaning them up on
superblock destruction.

CC: linux-mtd@lists.infradead.org
CC: linux-nfs@vger.kernel.org
CC: Petr Vandrovec <petr@vandrovec.name>
CC: linux-nilfs@vger.kernel.org
CC: cluster-devel@redhat.com
CC: osd-dev@open-osd.org
CC: codalist@coda.cs.cmu.edu
CC: linux-afs@lists.infradead.org
CC: ecryptfs@vger.kernel.org
CC: linux-cifs@vger.kernel.org
CC: ceph-devel@vger.kernel.org
CC: linux-btrfs@vger.kernel.org
CC: v9fs-developer@lists.sourceforge.net
CC: lustre-devel@lists.lustre.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/super.c                       | 49 ++++++++++++++++++++++++++++++++++++++++
 include/linux/backing-dev-defs.h |  2 +-
 include/linux/fs.h               |  6 +++++
 3 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/fs/super.c b/fs/super.c
index b8b6a086c03b..0f51a437c269 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -446,6 +446,11 @@ void generic_shutdown_super(struct super_block *sb)
 	hlist_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
+	if (sb->s_iflags & SB_I_DYNBDI) {
+		bdi_put(sb->s_bdi);
+		sb->s_bdi = &noop_backing_dev_info;
+		sb->s_iflags &= ~SB_I_DYNBDI;
+	}
 }
 
 EXPORT_SYMBOL(generic_shutdown_super);
@@ -1256,6 +1261,50 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 }
 
 /*
+ * Setup private BDI for given superblock. It gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
+{
+	struct backing_dev_info *bdi;
+	int err;
+	va_list args;
+
+	bdi = bdi_alloc(GFP_KERNEL);
+	if (!bdi)
+		return -ENOMEM;
+
+	bdi->name = sb->s_type->name;
+
+	va_start(args, fmt);
+	err = bdi_register_va(bdi, NULL, fmt, args);
+	va_end(args);
+	if (err) {
+		bdi_put(bdi);
+		return err;
+	}
+	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
+	sb->s_bdi = bdi;
+	sb->s_iflags |= SB_I_DYNBDI;
+
+	return 0;
+}
+EXPORT_SYMBOL(super_setup_bdi_name);
+
+/*
+ * Setup private BDI for given superblock. I gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi(struct super_block *sb)
+{
+	static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+	return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
+				    atomic_long_inc_return(&bdi_seq));
+}
+EXPORT_SYMBOL(super_setup_bdi);
+
+/*
  * This is an internal function, please use sb_end_{write,pagefault,intwrite}
  * instead.
  */
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index e66d4722db8e..866c433e7d32 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -146,7 +146,7 @@ struct backing_dev_info {
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
 
-	char *name;
+	const char *name;
 
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7251f7bb45e8..98cf14ea78c0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1272,6 +1272,9 @@ struct mm_struct;
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 
+/* Temporary flag until all filesystems are converted to dynamic bdis */
+#define SB_I_DYNBDI	0x00000100
+
 /* Possible states of 'frozen' field */
 enum {
 	SB_UNFROZEN = 0,		/* FS is unfrozen */
@@ -2121,6 +2124,9 @@ extern int vfs_ustat(dev_t, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
+extern __printf(2, 3)
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
+extern int super_setup_bdi(struct super_block *sb);
 
 extern int current_umask(void);
 
-- 
2.10.2

[PATCH 21/25] nfs: Convert to separately allocated bdi

[Jan Kara]

Allocate struct backing_dev_info separately instead of embedding it
inside the superblock. This unifies handling of bdi among users.

CC: Trond Myklebust <trond.myklebust@primarydata.com>
CC: Anna Schumaker <anna.schumaker@netapp.com>
CC: linux-nfs@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/nfs/client.c           | 10 ----------
 fs/nfs/internal.h         |  6 +++---
 fs/nfs/super.c            | 34 +++++++++++++++++++---------------
 fs/nfs/write.c            | 13 ++++++-------
 include/linux/nfs_fs_sb.h |  1 -
 5 files changed, 28 insertions(+), 36 deletions(-)

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 390ada8741bc..04d15a0045e3 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -761,9 +761,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
 	server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	server->backing_dev_info.name = "nfs";
-	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
-
 	if (server->wsize > max_rpc_payload)
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
@@ -917,12 +914,6 @@ struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 	}
 
-	if (bdi_init(&server->backing_dev_info)) {
-		nfs_free_iostats(server->io_stats);
-		kfree(server);
-		return NULL;
-	}
-
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
@@ -953,7 +944,6 @@ void nfs_free_server(struct nfs_server *server)
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
 	nfs_free_iostats(server->io_stats);
-	bdi_destroy(&server->backing_dev_info);
 	kfree(server);
 	nfs_release_automount_timer();
 	dprintk("<-- nfs_free_server()\n");
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7b38fedb7e03..9dc65d7ae754 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -139,7 +139,7 @@ struct nfs_mount_request {
 };
 
 struct nfs_mount_info {
-	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*fill_super)(struct super_block *, struct nfs_mount_info *);
 	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
 	struct nfs_parsed_mount_data *parsed;
 	struct nfs_clone_mount *cloned;
@@ -407,7 +407,7 @@ struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *
 struct dentry * nfs_xdev_mount_common(struct file_system_type *, int,
 		const char *, struct nfs_mount_info *);
 void nfs_kill_super(struct super_block *);
-void nfs_fill_super(struct super_block *, struct nfs_mount_info *);
+int nfs_fill_super(struct super_block *, struct nfs_mount_info *);
 
 extern struct rpc_stat nfs_rpcstat;
 
@@ -458,7 +458,7 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 
 /* super.c */
-void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
+int nfs_clone_super(struct super_block *, struct nfs_mount_info *);
 void nfs_umount_begin(struct super_block *);
 int  nfs_statfs(struct dentry *, struct kstatfs *);
 int  nfs_show_options(struct seq_file *, struct dentry *);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 54e0f9f2dd94..8d97aa70407e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2315,18 +2315,17 @@ inline void nfs_initialise_sb(struct super_block *sb)
 		sb->s_blocksize = nfs_block_bits(server->wsize,
 						 &sb->s_blocksize_bits);
 
-	sb->s_bdi = &server->backing_dev_info;
-
 	nfs_super_set_maxbytes(sb, server->maxfilesize);
 }
 
 /*
  * Finish setting up an NFS2/3 superblock
  */
-void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
+	int ret;
 
 	sb->s_blocksize_bits = 0;
 	sb->s_blocksize = 0;
@@ -2344,13 +2343,21 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 	}
 
  	nfs_initialise_sb(sb);
+
+	ret = super_setup_bdi_name(sb, "%u:%u", MAJOR(server->s_dev),
+				   MINOR(server->s_dev));
+	if (ret)
+		return ret;
+	sb->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
+	return 0;
+
 }
 EXPORT_SYMBOL_GPL(nfs_fill_super);
 
 /*
  * Finish setting up a cloned NFS2/3/4 superblock
  */
-void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+int nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2370,6 +2377,11 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 	}
 
  	nfs_initialise_sb(sb);
+
+	sb->s_bdi = bdi_get(old_sb->s_bdi);
+	sb->s_iflags |= SB_I_DYNBDI;
+
+	return 0;
 }
 
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
@@ -2522,11 +2534,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 }
 #endif
 
-static int nfs_bdi_register(struct nfs_server *server)
-{
-	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
-}
-
 int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
 			struct nfs_mount_info *mount_info)
 {
@@ -2594,17 +2601,14 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		nfs_free_server(server);
 		server = NULL;
 	} else {
-		error = nfs_bdi_register(server);
-		if (error) {
-			mntroot = ERR_PTR(error);
-			goto error_splat_super;
-		}
 		server->super = s;
 	}
 
 	if (!s->s_root) {
 		/* initial superblock/root creation */
-		mount_info->fill_super(s, mount_info);
+		error = mount_info->fill_super(s, mount_info);
+		if (error)
+			goto error_splat_super;
 		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
 	}
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index abb2c8a3be42..cc341fc7fd44 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -263,16 +263,15 @@ int nfs_congestion_kb;
 
 static void nfs_set_page_writeback(struct page *page)
 {
-	struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host);
+	struct inode *inode = page_file_mapping(page)->host;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int ret = test_set_page_writeback(page);
 
 	WARN_ON_ONCE(ret != 0);
 
 	if (atomic_long_inc_return(&nfss->writeback) >
-			NFS_CONGESTION_ON_THRESH) {
-		set_bdi_congested(&nfss->backing_dev_info,
-					BLK_RW_ASYNC);
-	}
+			NFS_CONGESTION_ON_THRESH)
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 static void nfs_end_page_writeback(struct nfs_page *req)
@@ -285,7 +284,7 @@ static void nfs_end_page_writeback(struct nfs_page *req)
 
 	end_page_writeback(req->wb_page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 
@@ -1808,7 +1807,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	}
 	nfss = NFS_SERVER(data->inode);
 	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);
 
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
 	nfs_commit_end(cinfo.mds);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index b34097c67848..e1502c55741e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -133,7 +133,6 @@ struct nfs_server {
 	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
 	struct nlm_host		*nlm_host;	/* NLM client handle */
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
-	struct backing_dev_info	backing_dev_info;
 	atomic_long_t		writeback;	/* number of writeback pages */
 	int			flags;		/* various flags */
 	unsigned int		caps;		/* server capabilities */
-- 
2.10.2

Re: [PATCH 04/25] fs: Provide infrastructure for dynamic BDIs in filesystems

[Christoph Hellwig]

> +	if (sb->s_iflags & SB_I_DYNBDI) {
> +		bdi_put(sb->s_bdi);
> +		sb->s_bdi = &noop_backing_dev_info;

At some point I'd really like to get rid of noop_backing_dev_info and
have a NULL here..

Otherwise this looks fine..

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 21/25] nfs: Convert to separately allocated bdi

[Christoph Hellwig]

>  /*
>   * Finish setting up an NFS2/3 superblock
>   */

I was just looking why you didn't update the v4 variant, but it seems
like the comment above is simply incorrect..

Thus the patch looks fine:

Reviewed-by: Christoph Hellwig <hch@lst.de>

Re: [PATCH 21/25] nfs: Convert to separately allocated bdi

[Jan Kara]

On Wed 12-04-17 01:20:34, Christoph Hellwig wrote:
> >  /*
> >   * Finish setting up an NFS2/3 superblock
> >   */
> 
> I was just looking why you didn't update the v4 variant, but it seems
> like the comment above is simply incorrect..

Yes, it's used for NFS4 as well AFAICT.

> Thus the patch looks fine:
> 
> Reviewed-by: Christoph Hellwig <hch@lst.de>

Thanks.

								Honza
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR

[PATCH 04/25] fs: Provide infrastructure for dynamic BDIs in filesystems

[Jan Kara]

Provide helper functions for setting up dynamically allocated
backing_dev_info structures for filesystems and cleaning them up on
superblock destruction.

CC: linux-mtd@lists.infradead.org
CC: linux-nfs@vger.kernel.org
CC: Petr Vandrovec <petr@vandrovec.name>
CC: linux-nilfs@vger.kernel.org
CC: cluster-devel@redhat.com
CC: osd-dev@open-osd.org
CC: codalist@coda.cs.cmu.edu
CC: linux-afs@lists.infradead.org
CC: ecryptfs@vger.kernel.org
CC: linux-cifs@vger.kernel.org
CC: ceph-devel@vger.kernel.org
CC: linux-btrfs@vger.kernel.org
CC: v9fs-developer@lists.sourceforge.net
CC: lustre-devel@lists.lustre.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/super.c                       | 49 ++++++++++++++++++++++++++++++++++++++++
 include/linux/backing-dev-defs.h |  2 +-
 include/linux/fs.h               |  6 +++++
 3 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/fs/super.c b/fs/super.c
index b8b6a086c03b..0f51a437c269 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -446,6 +446,11 @@ void generic_shutdown_super(struct super_block *sb)
 	hlist_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
+	if (sb->s_iflags & SB_I_DYNBDI) {
+		bdi_put(sb->s_bdi);
+		sb->s_bdi = &noop_backing_dev_info;
+		sb->s_iflags &= ~SB_I_DYNBDI;
+	}
 }
 
 EXPORT_SYMBOL(generic_shutdown_super);
@@ -1256,6 +1261,50 @@ mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
 }
 
 /*
+ * Setup private BDI for given superblock. It gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
+{
+	struct backing_dev_info *bdi;
+	int err;
+	va_list args;
+
+	bdi = bdi_alloc(GFP_KERNEL);
+	if (!bdi)
+		return -ENOMEM;
+
+	bdi->name = sb->s_type->name;
+
+	va_start(args, fmt);
+	err = bdi_register_va(bdi, NULL, fmt, args);
+	va_end(args);
+	if (err) {
+		bdi_put(bdi);
+		return err;
+	}
+	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
+	sb->s_bdi = bdi;
+	sb->s_iflags |= SB_I_DYNBDI;
+
+	return 0;
+}
+EXPORT_SYMBOL(super_setup_bdi_name);
+
+/*
+ * Setup private BDI for given superblock. I gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi(struct super_block *sb)
+{
+	static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+	return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
+				    atomic_long_inc_return(&bdi_seq));
+}
+EXPORT_SYMBOL(super_setup_bdi);
+
+/*
  * This is an internal function, please use sb_end_{write,pagefault,intwrite}
  * instead.
  */
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index e66d4722db8e..866c433e7d32 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -146,7 +146,7 @@ struct backing_dev_info {
 	congested_fn *congested_fn; /* Function pointer if device is md/dm */
 	void *congested_data;	/* Pointer to aux data for congested func */
 
-	char *name;
+	const char *name;
 
 	struct kref refcnt;	/* Reference counter for the structure */
 	unsigned int capabilities; /* Device capabilities */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7251f7bb45e8..98cf14ea78c0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1272,6 +1272,9 @@ struct mm_struct;
 /* sb->s_iflags to limit user namespace mounts */
 #define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 
+/* Temporary flag until all filesystems are converted to dynamic bdis */
+#define SB_I_DYNBDI	0x00000100
+
 /* Possible states of 'frozen' field */
 enum {
 	SB_UNFROZEN = 0,		/* FS is unfrozen */
@@ -2121,6 +2124,9 @@ extern int vfs_ustat(dev_t, struct kstatfs *);
 extern int freeze_super(struct super_block *super);
 extern int thaw_super(struct super_block *super);
 extern bool our_mnt(struct vfsmount *mnt);
+extern __printf(2, 3)
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
+extern int super_setup_bdi(struct super_block *sb);
 
 extern int current_umask(void);
 
-- 
2.12.0