[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-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
CC: linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: Petr Vandrovec <petr-vPk2MGR0e28uaRcfnNAh7A@public.gmane.org>
CC: linux-nilfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: cluster-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org
CC: osd-dev-yNzVSZO3znNg9hUCZPvPmw@public.gmane.org
CC: codalist-/uMB558Y47wP4a1z8dhFYw@public.gmane.org
CC: linux-afs-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
CC: ecryptfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: linux-cifs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: ceph-devel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: linux-btrfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
CC: v9fs-developer-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org
CC: lustre-devel-aLEFhgZF4x6X6Mz3xDxJMA@public.gmane.org
Signed-off-by: Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
---
 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 09/25] ceph: Convert to separately allocated bdi

[Jan Kara]

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

CC: Ilya Dryomov <idryomov@gmail.com>
CC: "Yan, Zheng" <zyan@redhat.com>
CC: Sage Weil <sage@redhat.com>
CC: ceph-devel@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ceph/addr.c    |  6 +++---
 fs/ceph/debugfs.c |  2 +-
 fs/ceph/super.c   | 35 +++++++++++++----------------------
 fs/ceph/super.h   |  2 --
 4 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1a3e1b40799a..9ecb2fd348cb 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -578,7 +578,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -700,7 +700,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 			if (atomic_long_dec_return(&fsc->writeback_count) <
 			     CONGESTION_OFF_THRESH(
 					fsc->mount_options->congestion_kb))
-				clear_bdi_congested(&fsc->backing_dev_info,
+				clear_bdi_congested(inode_to_bdi(inode),
 						    BLK_RW_ASYNC);
 
 			if (rc < 0)
@@ -979,7 +979,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
-				set_bdi_congested(&fsc->backing_dev_info,
+				set_bdi_congested(inode_to_bdi(inode),
 						  BLK_RW_ASYNC);
 			}
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f2ae393e2c31..3ef11bc8d728 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -251,7 +251,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 		goto out;
 
 	snprintf(name, sizeof(name), "../../bdi/%s",
-		 dev_name(fsc->backing_dev_info.dev));
+		 dev_name(fsc->sb->s_bdi->dev));
 	fsc->debugfs_bdi =
 		debugfs_create_symlink("bdi",
 				       fsc->client->debugfs_dir,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 0ec8d0114e57..a8c81b2052ca 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -579,10 +579,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 
 	atomic_long_set(&fsc->writeback_count, 0);
 
-	err = bdi_init(&fsc->backing_dev_info);
-	if (err < 0)
-		goto fail_client;
-
 	err = -ENOMEM;
 	/*
 	 * The number of concurrent works can be high but they don't need
@@ -590,7 +586,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	 */
 	fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
 	if (fsc->wb_wq == NULL)
-		goto fail_bdi;
+		goto fail_client;
 	fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
 	if (fsc->pg_inv_wq == NULL)
 		goto fail_wb_wq;
@@ -624,8 +620,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
 	destroy_workqueue(fsc->wb_wq);
-fail_bdi:
-	bdi_destroy(&fsc->backing_dev_info);
 fail_client:
 	ceph_destroy_client(fsc->client);
 fail:
@@ -643,8 +637,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	destroy_workqueue(fsc->pg_inv_wq);
 	destroy_workqueue(fsc->trunc_wq);
 
-	bdi_destroy(&fsc->backing_dev_info);
-
 	mempool_destroy(fsc->wb_pagevec_pool);
 
 	destroy_mount_options(fsc->mount_options);
@@ -937,33 +929,32 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb,
-			     struct ceph_fs_client *fsc)
+static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
 {
 	int err;
 
+	err = super_setup_bdi_name(sb, "ceph-%ld",
+				   atomic_long_inc_return(&bdi_seq));
+	if (err)
+		return err;
+
 	/* set ra_pages based on rasize mount option? */
 	if (fsc->mount_options->rasize >= PAGE_SIZE)
-		fsc->backing_dev_info.ra_pages =
+		sb->s_bdi->ra_pages =
 			(fsc->mount_options->rasize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else
-		fsc->backing_dev_info.ra_pages =
-			VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+		sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 
 	if (fsc->mount_options->rsize > fsc->mount_options->rasize &&
 	    fsc->mount_options->rsize >= PAGE_SIZE)
-		fsc->backing_dev_info.io_pages =
+		sb->s_bdi->io_pages =
 			(fsc->mount_options->rsize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else if (fsc->mount_options->rsize == 0)
-		fsc->backing_dev_info.io_pages = ULONG_MAX;
+		sb->s_bdi->io_pages = ULONG_MAX;
 
-	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
-			   atomic_long_inc_return(&bdi_seq));
-	if (!err)
-		sb->s_bdi = &fsc->backing_dev_info;
-	return err;
+	return 0;
 }
 
 static struct dentry *ceph_mount(struct file_system_type *fs_type,
@@ -1018,7 +1009,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 		dout("get_sb got existing client %p\n", fsc);
 	} else {
 		dout("get_sb using new client %p\n", fsc);
-		err = ceph_register_bdi(sb, fsc);
+		err = ceph_setup_bdi(sb, fsc);
 		if (err < 0) {
 			res = ERR_PTR(err);
 			goto out_splat;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe6b9cfc4013..176186b12457 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -92,8 +92,6 @@ struct ceph_fs_client {
 	struct workqueue_struct *trunc_wq;
 	atomic_long_t writeback_count;
 
-	struct backing_dev_info backing_dev_info;
-
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
-- 
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 09/25] ceph: Convert to separately allocated bdi

[Christoph Hellwig]

Looks fine,

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

[PATCH 09/25] ceph: Convert to separately allocated bdi

[Jan Kara]

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

CC: Ilya Dryomov <idryomov@gmail.com>
CC: "Yan, Zheng" <zyan@redhat.com>
CC: Sage Weil <sage@redhat.com>
CC: ceph-devel@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/ceph/addr.c    |  6 +++---
 fs/ceph/debugfs.c |  2 +-
 fs/ceph/super.c   | 35 +++++++++++++----------------------
 fs/ceph/super.h   |  2 --
 4 files changed, 17 insertions(+), 28 deletions(-)

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 1a3e1b40799a..9ecb2fd348cb 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -578,7 +578,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -700,7 +700,7 @@ static void writepages_finish(struct ceph_osd_request *req)
 			if (atomic_long_dec_return(&fsc->writeback_count) <
 			     CONGESTION_OFF_THRESH(
 					fsc->mount_options->congestion_kb))
-				clear_bdi_congested(&fsc->backing_dev_info,
+				clear_bdi_congested(inode_to_bdi(inode),
 						    BLK_RW_ASYNC);
 
 			if (rc < 0)
@@ -979,7 +979,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
-				set_bdi_congested(&fsc->backing_dev_info,
+				set_bdi_congested(inode_to_bdi(inode),
 						  BLK_RW_ASYNC);
 			}
 
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f2ae393e2c31..3ef11bc8d728 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -251,7 +251,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 		goto out;
 
 	snprintf(name, sizeof(name), "../../bdi/%s",
-		 dev_name(fsc->backing_dev_info.dev));
+		 dev_name(fsc->sb->s_bdi->dev));
 	fsc->debugfs_bdi =
 		debugfs_create_symlink("bdi",
 				       fsc->client->debugfs_dir,
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 0ec8d0114e57..a8c81b2052ca 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -579,10 +579,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 
 	atomic_long_set(&fsc->writeback_count, 0);
 
-	err = bdi_init(&fsc->backing_dev_info);
-	if (err < 0)
-		goto fail_client;
-
 	err = -ENOMEM;
 	/*
 	 * The number of concurrent works can be high but they don't need
@@ -590,7 +586,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	 */
 	fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
 	if (fsc->wb_wq == NULL)
-		goto fail_bdi;
+		goto fail_client;
 	fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
 	if (fsc->pg_inv_wq == NULL)
 		goto fail_wb_wq;
@@ -624,8 +620,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
 	destroy_workqueue(fsc->wb_wq);
-fail_bdi:
-	bdi_destroy(&fsc->backing_dev_info);
 fail_client:
 	ceph_destroy_client(fsc->client);
 fail:
@@ -643,8 +637,6 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 	destroy_workqueue(fsc->pg_inv_wq);
 	destroy_workqueue(fsc->trunc_wq);
 
-	bdi_destroy(&fsc->backing_dev_info);
-
 	mempool_destroy(fsc->wb_pagevec_pool);
 
 	destroy_mount_options(fsc->mount_options);
@@ -937,33 +929,32 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb,
-			     struct ceph_fs_client *fsc)
+static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
 {
 	int err;
 
+	err = super_setup_bdi_name(sb, "ceph-%ld",
+				   atomic_long_inc_return(&bdi_seq));
+	if (err)
+		return err;
+
 	/* set ra_pages based on rasize mount option? */
 	if (fsc->mount_options->rasize >= PAGE_SIZE)
-		fsc->backing_dev_info.ra_pages =
+		sb->s_bdi->ra_pages =
 			(fsc->mount_options->rasize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else
-		fsc->backing_dev_info.ra_pages =
-			VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+		sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 
 	if (fsc->mount_options->rsize > fsc->mount_options->rasize &&
 	    fsc->mount_options->rsize >= PAGE_SIZE)
-		fsc->backing_dev_info.io_pages =
+		sb->s_bdi->io_pages =
 			(fsc->mount_options->rsize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else if (fsc->mount_options->rsize == 0)
-		fsc->backing_dev_info.io_pages = ULONG_MAX;
+		sb->s_bdi->io_pages = ULONG_MAX;
 
-	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
-			   atomic_long_inc_return(&bdi_seq));
-	if (!err)
-		sb->s_bdi = &fsc->backing_dev_info;
-	return err;
+	return 0;
 }
 
 static struct dentry *ceph_mount(struct file_system_type *fs_type,
@@ -1018,7 +1009,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 		dout("get_sb got existing client %p\n", fsc);
 	} else {
 		dout("get_sb using new client %p\n", fsc);
-		err = ceph_register_bdi(sb, fsc);
+		err = ceph_setup_bdi(sb, fsc);
 		if (err < 0) {
 			res = ERR_PTR(err);
 			goto out_splat;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fe6b9cfc4013..176186b12457 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -92,8 +92,6 @@ struct ceph_fs_client {
 	struct workqueue_struct *trunc_wq;
 	atomic_long_t writeback_count;
 
-	struct backing_dev_info backing_dev_info;
-
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
-- 
2.12.0