[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 13/25] mtd: Convert to dynamically allocated bdi infrastructure

[Jan Kara]

MTD already allocates backing_dev_info dynamically. Convert it to use
generic infrastructure for this including proper refcounting. We drop
mtd->backing_dev_info as its only use was to pass mtd_bdi pointer from
one file into another and if we wanted to keep that in a clean way, we'd
have to make mtd hold and drop bdi reference as needed which seems
pointless for passing one global pointer...

CC: David Woodhouse <dwmw2@infradead.org>
CC: Brian Norris <computersforpeace@gmail.com>
CC: linux-mtd@lists.infradead.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 drivers/mtd/mtdcore.c   | 23 ++++++++++++-----------
 drivers/mtd/mtdsuper.c  |  7 ++++++-
 include/linux/mtd/mtd.h |  5 -----
 3 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 66a9dedd1062..23e2e56ca54e 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -46,7 +46,7 @@
 
 #include "mtdcore.h"
 
-static struct backing_dev_info *mtd_bdi;
+struct backing_dev_info *mtd_bdi;
 
 #ifdef CONFIG_PM_SLEEP
 
@@ -496,11 +496,9 @@ int add_mtd_device(struct mtd_info *mtd)
 	 * mtd_device_parse_register() multiple times on the same master MTD,
 	 * especially with CONFIG_MTD_PARTITIONED_MASTER=y.
 	 */
-	if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
+	if (WARN_ONCE(mtd->dev.type, "MTD already registered\n"))
 		return -EEXIST;
 
-	mtd->backing_dev_info = mtd_bdi;
-
 	BUG_ON(mtd->writesize == 0);
 	mutex_lock(&mtd_table_mutex);
 
@@ -1775,13 +1773,18 @@ static struct backing_dev_info * __init mtd_bdi_init(char *name)
 	struct backing_dev_info *bdi;
 	int ret;
 
-	bdi = kzalloc(sizeof(*bdi), GFP_KERNEL);
+	bdi = bdi_alloc(GFP_KERNEL);
 	if (!bdi)
 		return ERR_PTR(-ENOMEM);
 
-	ret = bdi_setup_and_register(bdi, name);
+	bdi->name = name;
+	/*
+	 * We put '-0' suffix to the name to get the same name format as we
+	 * used to get. Since this is called only once, we get a unique name. 
+	 */
+	ret = bdi_register(bdi, NULL, "%.28s-0", name);
 	if (ret)
-		kfree(bdi);
+		bdi_put(bdi);
 
 	return ret ? ERR_PTR(ret) : bdi;
 }
@@ -1813,8 +1816,7 @@ static int __init init_mtd(void)
 out_procfs:
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
-	bdi_destroy(mtd_bdi);
-	kfree(mtd_bdi);
+	bdi_put(mtd_bdi);
 err_bdi:
 	class_unregister(&mtd_class);
 err_reg:
@@ -1828,8 +1830,7 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	bdi_destroy(mtd_bdi);
-	kfree(mtd_bdi);
+	bdi_put(mtd_bdi);
 	idr_destroy(&mtd_idr);
 }
 
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index 20c02a3b7417..e69e7855e31f 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -18,6 +18,7 @@
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/major.h>
+#include <linux/backing-dev.h>
 
 /*
  * compare superblocks to see if they're equivalent
@@ -38,6 +39,8 @@ static int get_sb_mtd_compare(struct super_block *sb, void *_mtd)
 	return 0;
 }
 
+extern struct backing_dev_info *mtd_bdi;
+
 /*
  * mark the superblock by the MTD device it is using
  * - set the device number to be the correct MTD block device for pesuperstence
@@ -49,7 +52,9 @@ static int get_sb_mtd_set(struct super_block *sb, void *_mtd)
 
 	sb->s_mtd = mtd;
 	sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
-	sb->s_bdi = mtd->backing_dev_info;
+	sb->s_bdi = bdi_get(mtd_bdi);
+	sb->s_iflags |= SB_I_DYNBDI;
+
 	return 0;
 }
 
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index eebdc63cf6af..79b176eca04a 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -334,11 +334,6 @@ struct mtd_info {
 	int (*_get_device) (struct mtd_info *mtd);
 	void (*_put_device) (struct mtd_info *mtd);
 
-	/* Backing device capabilities for this device
-	 * - provides mmap capabilities
-	 */
-	struct backing_dev_info *backing_dev_info;
-
 	struct notifier_block reboot_notifier;  /* default mode before reboot */
 
 	/* ECC status information */
-- 
2.10.2

[PATCH 22/25] ubifs: 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: Richard Weinberger <richard@nod.at>
CC: Artem Bityutskiy <dedekind1@gmail.com>
CC: Adrian Hunter <adrian.hunter@intel.com>
CC: linux-mtd@lists.infradead.org
Acked-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ubifs/super.c | 25 +++++++++----------------
 fs/ubifs/ubifs.h |  3 ---
 2 files changed, 9 insertions(+), 19 deletions(-)

diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index b73811bd7676..cf4cc99b75b5 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1827,7 +1827,6 @@ static void ubifs_put_super(struct super_block *sb)
 	}
 
 	ubifs_umount(c);
-	bdi_destroy(&c->bdi);
 	ubi_close_volume(c->ubi);
 	mutex_unlock(&c->umount_mutex);
 }
@@ -2019,29 +2018,25 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 	}
 
+	err = ubifs_parse_options(c, data, 0);
+	if (err)
+		goto out_close;
+
 	/*
 	 * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
 	 * UBIFS, I/O is not deferred, it is done immediately in readpage,
 	 * which means the user would have to wait not just for their own I/O
 	 * but the read-ahead I/O as well i.e. completely pointless.
 	 *
-	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
+	 * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also
+	 * @sb->s_bdi->capabilities are initialized to 0 so there won't be any
+	 * writeback happening.
 	 */
-	c->bdi.name = "ubifs",
-	c->bdi.capabilities = 0;
-	err  = bdi_init(&c->bdi);
+	err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num,
+				   c->vi.vol_id);
 	if (err)
 		goto out_close;
-	err = bdi_register(&c->bdi, NULL, "ubifs_%d_%d",
-			   c->vi.ubi_num, c->vi.vol_id);
-	if (err)
-		goto out_bdi;
-
-	err = ubifs_parse_options(c, data, 0);
-	if (err)
-		goto out_bdi;
 
-	sb->s_bdi = &c->bdi;
 	sb->s_fs_info = c;
 	sb->s_magic = UBIFS_SUPER_MAGIC;
 	sb->s_blocksize = UBIFS_BLOCK_SIZE;
@@ -2080,8 +2075,6 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 	ubifs_umount(c);
 out_unlock:
 	mutex_unlock(&c->umount_mutex);
-out_bdi:
-	bdi_destroy(&c->bdi);
 out_close:
 	ubi_close_volume(c->ubi);
 out:
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 4d57e488038e..4da10a6d702a 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -972,7 +972,6 @@ struct ubifs_debug_info;
  * struct ubifs_info - UBIFS file-system description data structure
  * (per-superblock).
  * @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable read-ahead
  *
  * @highest_inum: highest used inode number
  * @max_sqnum: current global sequence number
@@ -1220,7 +1219,6 @@ struct ubifs_debug_info;
  */
 struct ubifs_info {
 	struct super_block *vfs_sb;
-	struct backing_dev_info bdi;
 
 	ino_t highest_inum;
 	unsigned long long max_sqnum;
@@ -1461,7 +1459,6 @@ extern const struct inode_operations ubifs_file_inode_operations;
 extern const struct file_operations ubifs_dir_operations;
 extern const struct inode_operations ubifs_dir_inode_operations;
 extern const struct inode_operations ubifs_symlink_inode_operations;
-extern struct backing_dev_info ubifs_backing_dev_info;
 extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
 
 /* io.c */
-- 
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 13/25] mtd: Convert to dynamically allocated bdi infrastructure

[Christoph Hellwig]

> +	sb->s_bdi = bdi_get(mtd_bdi);
> +	sb->s_iflags |= SB_I_DYNBDI;

FTI, while I think this is a faithful conversion of the existing code,
the single bdi for all MTD devices looks rather bogus to me..

Otherwise this looks good:

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

Re: [PATCH 22/25] ubifs: Convert to separately allocated bdi

[Christoph Hellwig]

Looks fine,

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

Re: [PATCH 13/25] mtd: Convert to dynamically allocated bdi infrastructure

[Jan Kara]

On Wed 12-04-17 01:14:06, Christoph Hellwig wrote:
> > +	sb->s_bdi = bdi_get(mtd_bdi);
> > +	sb->s_iflags |= SB_I_DYNBDI;
> 
> FTI, while I think this is a faithful conversion of the existing code,
> the single bdi for all MTD devices looks rather bogus to me..

Yeah, I don't understand why they don't allocate backing_dev_info per
superblock as other places do but I didn't dare to change that since there
are user visible consequences of that. I suspect they don't really want
anything from the bdi and allocate it only so that other parts of the
kernel are happy.

> Otherwise this looks good:
> 
> 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