From b5501504cb6a70d55c3dcf1b2ceb15386e615237 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Thu, 21 Nov 2019 17:33:30 +0800
Subject: btrfs: sysfs, rename devices kobject holder to devices_kobj

The struct member btrfs_device::device_dir_kobj holds the kobj of the
sysfs directory /sys/fs/btrfs/UUID/devices, so rename it from
device_dir_kobj to devices_kobj. No functional changes.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/sysfs.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 5ebbe8a5ee76..3799af42ee29 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -734,10 +734,10 @@ static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add)
 
 static void __btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs)
 {
-	if (fs_devs->device_dir_kobj) {
-		kobject_del(fs_devs->device_dir_kobj);
-		kobject_put(fs_devs->device_dir_kobj);
-		fs_devs->device_dir_kobj = NULL;
+	if (fs_devs->devices_kobj) {
+		kobject_del(fs_devs->devices_kobj);
+		kobject_put(fs_devs->devices_kobj);
+		fs_devs->devices_kobj = NULL;
 	}
 
 	if (fs_devs->fsid_kobj.state_initialized) {
@@ -969,15 +969,14 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 	struct hd_struct *disk;
 	struct kobject *disk_kobj;
 
-	if (!fs_devices->device_dir_kobj)
+	if (!fs_devices->devices_kobj)
 		return -EINVAL;
 
 	if (one_device && one_device->bdev) {
 		disk = one_device->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
-		sysfs_remove_link(fs_devices->device_dir_kobj,
-						disk_kobj->name);
+		sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name);
 	}
 
 	if (one_device)
@@ -990,8 +989,7 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 		disk = one_device->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
-		sysfs_remove_link(fs_devices->device_dir_kobj,
-						disk_kobj->name);
+		sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name);
 	}
 
 	return 0;
@@ -999,11 +997,11 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 
 int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs)
 {
-	if (!fs_devs->device_dir_kobj)
-		fs_devs->device_dir_kobj = kobject_create_and_add("devices",
-						&fs_devs->fsid_kobj);
+	if (!fs_devs->devices_kobj)
+		fs_devs->devices_kobj = kobject_create_and_add("devices",
+							&fs_devs->fsid_kobj);
 
-	if (!fs_devs->device_dir_kobj)
+	if (!fs_devs->devices_kobj)
 		return -ENOMEM;
 
 	return 0;
@@ -1028,7 +1026,7 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 		disk = dev->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
-		error = sysfs_create_link(fs_devices->device_dir_kobj,
+		error = sysfs_create_link(fs_devices->devices_kobj,
 					  disk_kobj, disk_kobj->name);
 		if (error)
 			break;
-- 
cgit v1.2.3-70-g09d2


From c6761a9ed329dd41fee09dc2926126768e5ca34c Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Thu, 21 Nov 2019 17:33:32 +0800
Subject: btrfs: sysfs, btrfs_sysfs_add_fsid() drop unused argument parent

Commit 24bd69cb ("Btrfs: sysfs: add support to add parent for fsid")
added parent argument in preparation to show the seed fsid under the
sprout fsid as in the patch [1] in the mailing list.

 [1] Btrfs: sysfs: support seed devices in the sysfs layout

But later this idea was superseded by another idea to rename the fsid as
in the commit f93c39970b1d ("btrfs: factor out sysfs code for updating
sprout fsid").

So we don't need parent argument anymore.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c |  2 +-
 fs/btrfs/sysfs.c   | 11 ++++++-----
 fs/btrfs/sysfs.h   |  5 ++---
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e0edfdc9c82b..639104326691 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3082,7 +3082,7 @@ int __cold open_ctree(struct super_block *sb,
 
 	btrfs_free_extra_devids(fs_devices, 1);
 
-	ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
+	ret = btrfs_sysfs_add_fsid(fs_devices);
 	if (ret) {
 		btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
 				ret);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 3799af42ee29..1d8ee57da164 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1065,18 +1065,19 @@ void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices,
 static struct kset *btrfs_kset;
 
 /*
+ * Creates:
+ *		/sys/fs/btrfs/UUID
+ *
  * Can be called by the device discovery thread.
- * And parent can be specified for seed device
  */
-int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
-				struct kobject *parent)
+int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs)
 {
 	int error;
 
 	init_completion(&fs_devs->kobj_unregister);
 	fs_devs->fsid_kobj.kset = btrfs_kset;
-	error = kobject_init_and_add(&fs_devs->fsid_kobj,
-				&btrfs_ktype, parent, "%pU", fs_devs->fsid);
+	error = kobject_init_and_add(&fs_devs->fsid_kobj, &btrfs_ktype, NULL,
+				     "%pU", fs_devs->fsid);
 	if (error) {
 		kobject_put(&fs_devs->fsid_kobj);
 		return error;
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index e10c3adfc30f..a0454947f41a 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -18,9 +18,8 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 		struct btrfs_device *one_device);
 int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
                 struct btrfs_device *one_device);
-int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
-				struct kobject *parent);
-int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
+int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs);
+int btrfs_sysfs_add_devices_kobj(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices,
 				    const u8 *fsid);
-- 
cgit v1.2.3-70-g09d2


From be2cf92e0a2f64efe0709a2cfe5d9f4852d14b61 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Thu, 21 Nov 2019 17:33:33 +0800
Subject: btrfs: sysfs, rename btrfs_sysfs_add_device()

btrfs_sysfs_add_device() creates the directory
/sys/fs/btrfs/UUID/devices but its function name is misleading. Rename
it to btrfs_sysfs_add_devices_kobj() instead. No functional changes.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 2 +-
 fs/btrfs/sysfs.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 639104326691..65cfd0fd0f83 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3089,7 +3089,7 @@ int __cold open_ctree(struct super_block *sb,
 		goto fail_block_groups;
 	}
 
-	ret = btrfs_sysfs_add_device(fs_devices);
+	ret = btrfs_sysfs_add_devices_kobj(fs_devices);
 	if (ret) {
 		btrfs_err(fs_info, "failed to init sysfs device interface: %d",
 				ret);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 1d8ee57da164..c76c38d74972 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -995,7 +995,7 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 	return 0;
 }
 
-int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs)
+int btrfs_sysfs_add_devices_kobj(struct btrfs_fs_devices *fs_devs)
 {
 	if (!fs_devs->devices_kobj)
 		fs_devs->devices_kobj = kobject_create_and_add("devices",
-- 
cgit v1.2.3-70-g09d2


From bc036bb33524dcb2525d74c336e9694d5d3c0047 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Thu, 21 Nov 2019 17:33:34 +0800
Subject: btrfs: sysfs, merge btrfs_sysfs_add devices_kobj and fsid

Merge btrfs_sysfs_add_fsid() and btrfs_sysfs_add_devices_kobj() functions
as these two are small and they are called one after the other.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c |  7 -------
 fs/btrfs/sysfs.c   | 21 +++++++++------------
 fs/btrfs/sysfs.h   |  1 -
 3 files changed, 9 insertions(+), 20 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 65cfd0fd0f83..ab888d89d844 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3089,13 +3089,6 @@ int __cold open_ctree(struct super_block *sb,
 		goto fail_block_groups;
 	}
 
-	ret = btrfs_sysfs_add_devices_kobj(fs_devices);
-	if (ret) {
-		btrfs_err(fs_info, "failed to init sysfs device interface: %d",
-				ret);
-		goto fail_fsdev_sysfs;
-	}
-
 	ret = btrfs_sysfs_add_mounted(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c76c38d74972..16379f491ca1 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -995,18 +995,6 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 	return 0;
 }
 
-int btrfs_sysfs_add_devices_kobj(struct btrfs_fs_devices *fs_devs)
-{
-	if (!fs_devs->devices_kobj)
-		fs_devs->devices_kobj = kobject_create_and_add("devices",
-							&fs_devs->fsid_kobj);
-
-	if (!fs_devs->devices_kobj)
-		return -ENOMEM;
-
-	return 0;
-}
-
 int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 				struct btrfs_device *one_device)
 {
@@ -1083,6 +1071,15 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs)
 		return error;
 	}
 
+	fs_devs->devices_kobj = kobject_create_and_add("devices",
+						       &fs_devs->fsid_kobj);
+	if (!fs_devs->devices_kobj) {
+		btrfs_err(fs_devs->fs_info,
+			  "failed to init sysfs device interface");
+		kobject_put(&fs_devs->fsid_kobj);
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index a0454947f41a..3d27b39eaf94 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -19,7 +19,6 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
                 struct btrfs_device *one_device);
 int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs);
-int btrfs_sysfs_add_devices_kobj(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
 void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices,
 				    const u8 *fsid);
-- 
cgit v1.2.3-70-g09d2


From 71e8978eb456958784539f02fa56087300f3a993 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Fri, 13 Dec 2019 16:22:17 -0800
Subject: btrfs: sysfs: add removal calls for debug/

We probably should call sysfs_remove_group() on debug/.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/sysfs.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 16379f491ca1..4c022757ffa4 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -771,6 +771,10 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
 		kobject_del(fs_info->space_info_kobj);
 		kobject_put(fs_info->space_info_kobj);
 	}
+#ifdef CONFIG_BTRFS_DEBUG
+	sysfs_remove_group(&fs_info->fs_devices->fsid_kobj,
+			   &btrfs_debug_feature_attr_group);
+#endif
 	addrm_unknown_feature_attrs(fs_info, false);
 	sysfs_remove_group(&fs_info->fs_devices->fsid_kobj, &btrfs_feature_attr_group);
 	sysfs_remove_files(&fs_info->fs_devices->fsid_kobj, btrfs_attrs);
@@ -1205,6 +1209,9 @@ void __cold btrfs_exit_sysfs(void)
 	sysfs_unmerge_group(&btrfs_kset->kobj,
 			    &btrfs_static_feature_attr_group);
 	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
+#ifdef CONFIG_BTRFS_DEBUG
+	sysfs_remove_group(&btrfs_kset->kobj, &btrfs_debug_feature_attr_group);
+#endif
 	kset_unregister(btrfs_kset);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 93945cb43ead1e22e0d5ab50ae361a62cb783ab2 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Fri, 13 Dec 2019 16:22:18 -0800
Subject: btrfs: sysfs: make UUID/debug have its own kobject

Btrfs only allowed attributes to be exposed in debug/. Let's let other
groups be created by making debug its own kobject.

This also makes the per-fs debug options separate from the global
features mount attributes. This seems to be needed as
sysfs_create_files() requires const struct attribute * while
sysfs_create_group() can take struct attribute *. This seems nicer as
per file system, you'll probably use to_fs_info().

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h |  4 ++++
 fs/btrfs/sysfs.c | 20 ++++++++++++++++----
 2 files changed, 20 insertions(+), 4 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d15a4aa721aa..0626e5562993 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -927,6 +927,10 @@ struct btrfs_fs_info {
 	spinlock_t ref_verify_lock;
 	struct rb_root block_tree;
 #endif
+
+#ifdef CONFIG_BTRFS_DEBUG
+	struct kobject *debug_kobj;
+#endif
 };
 
 static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4c022757ffa4..5a09c7a14124 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -344,6 +344,10 @@ static const struct attribute_group btrfs_static_feature_attr_group = {
  * /sys/fs/btrfs/debug - applies to module or all filesystems
  * /sys/fs/btrfs/UUID  - applies only to the given filesystem
  */
+static const struct attribute *btrfs_debug_mount_attrs[] = {
+	NULL,
+};
+
 static struct attribute *btrfs_debug_feature_attrs[] = {
 	NULL
 };
@@ -772,8 +776,11 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
 		kobject_put(fs_info->space_info_kobj);
 	}
 #ifdef CONFIG_BTRFS_DEBUG
-	sysfs_remove_group(&fs_info->fs_devices->fsid_kobj,
-			   &btrfs_debug_feature_attr_group);
+	if (fs_info->debug_kobj) {
+		sysfs_remove_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
+		kobject_del(fs_info->debug_kobj);
+		kobject_put(fs_info->debug_kobj);
+	}
 #endif
 	addrm_unknown_feature_attrs(fs_info, false);
 	sysfs_remove_group(&fs_info->fs_devices->fsid_kobj, &btrfs_feature_attr_group);
@@ -1111,8 +1118,13 @@ int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info)
 		goto failure;
 
 #ifdef CONFIG_BTRFS_DEBUG
-	error = sysfs_create_group(fsid_kobj,
-				   &btrfs_debug_feature_attr_group);
+	fs_info->debug_kobj = kobject_create_and_add("debug", fsid_kobj);
+	if (!fs_info->debug_kobj) {
+		error = -ENOMEM;
+		goto failure;
+	}
+
+	error = sysfs_create_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
 	if (error)
 		goto failure;
 #endif
-- 
cgit v1.2.3-70-g09d2


From e4faab844a55edb9b628bf1f982fbc30f07b9700 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Fri, 13 Dec 2019 16:22:19 -0800
Subject: btrfs: sysfs: add UUID/debug/discard directory

Setup base sysfs directory for discard stats + tunables.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h |  1 +
 fs/btrfs/sysfs.c | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0626e5562993..71317047c321 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -930,6 +930,7 @@ struct btrfs_fs_info {
 
 #ifdef CONFIG_BTRFS_DEBUG
 	struct kobject *debug_kobj;
+	struct kobject *discard_debug_kobj;
 #endif
 };
 
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 5a09c7a14124..0eec1a8d45bd 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -338,6 +338,13 @@ static const struct attribute_group btrfs_static_feature_attr_group = {
 
 #ifdef CONFIG_BTRFS_DEBUG
 
+/*
+ * Discard statistics and tunables
+ */
+static const struct attribute *discard_debug_attrs[] = {
+	NULL,
+};
+
 /*
  * Runtime debugging exported via sysfs
  *
@@ -776,6 +783,12 @@ void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info)
 		kobject_put(fs_info->space_info_kobj);
 	}
 #ifdef CONFIG_BTRFS_DEBUG
+	if (fs_info->discard_debug_kobj) {
+		sysfs_remove_files(fs_info->discard_debug_kobj,
+				   discard_debug_attrs);
+		kobject_del(fs_info->discard_debug_kobj);
+		kobject_put(fs_info->discard_debug_kobj);
+	}
 	if (fs_info->debug_kobj) {
 		sysfs_remove_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
 		kobject_del(fs_info->debug_kobj);
@@ -1127,6 +1140,19 @@ int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info)
 	error = sysfs_create_files(fs_info->debug_kobj, btrfs_debug_mount_attrs);
 	if (error)
 		goto failure;
+
+	/* Discard directory */
+	fs_info->discard_debug_kobj = kobject_create_and_add("discard",
+						     fs_info->debug_kobj);
+	if (!fs_info->discard_debug_kobj) {
+		error = -ENOMEM;
+		goto failure;
+	}
+
+	error = sysfs_create_files(fs_info->discard_debug_kobj,
+				   discard_debug_attrs);
+	if (error)
+		goto failure;
 #endif
 
 	error = addrm_unknown_feature_attrs(fs_info, true);
-- 
cgit v1.2.3-70-g09d2


From dfb79ddb130e0a239e3e90aaf5f5b908555f52bb Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Fri, 13 Dec 2019 16:22:20 -0800
Subject: btrfs: track discardable extents for async discard

The number of discardable extents will serve as the rate limiting metric
for how often we should discard. This keeps track of discardable extents
in the free space caches by maintaining deltas and propagating them to
the global count.

The deltas are calculated from 2 values stored in PREV and CURR entries,
then propagated up to the global discard ctl.  The current counter value
becomes the previous counter value after update.

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h            |   9 ++++
 fs/btrfs/discard.c          |  31 +++++++++++++
 fs/btrfs/discard.h          |   4 ++
 fs/btrfs/free-space-cache.c | 106 ++++++++++++++++++++++++++++++++++++++++----
 fs/btrfs/free-space-cache.h |   2 +
 fs/btrfs/sysfs.c            |  15 +++++++
 6 files changed, 158 insertions(+), 9 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 71317047c321..533c5ea0e8c0 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -101,6 +101,14 @@ struct btrfs_ref;
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
+/*
+ * Deltas are an effective way to populate global statistics.  Give macro names
+ * to make it clear what we're doing.  An example is discard_extents in
+ * btrfs_free_space_ctl.
+ */
+#define BTRFS_STAT_NR_ENTRIES	2
+#define BTRFS_STAT_CURR		0
+#define BTRFS_STAT_PREV		1
 
 /*
  * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
@@ -458,6 +466,7 @@ struct btrfs_discard_ctl {
 	spinlock_t lock;
 	struct btrfs_block_group *block_group;
 	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
+	atomic_t discardable_extents;
 };
 
 /* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index cb9a23217ec6..99663641abf4 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -342,6 +342,35 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl)
 		test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags));
 }
 
+/**
+ * btrfs_discard_update_discardable - propagate discard counters
+ * @block_group: block_group of interest
+ * @ctl: free_space_ctl of @block_group
+ *
+ * This propagates deltas of counters up to the discard_ctl.  It maintains a
+ * current counter and a previous counter passing the delta up to the global
+ * stat.  Then the current counter value becomes the previous counter value.
+ */
+void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
+				      struct btrfs_free_space_ctl *ctl)
+{
+	struct btrfs_discard_ctl *discard_ctl;
+	s32 extents_delta;
+
+	if (!block_group || !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
+		return;
+
+	discard_ctl = &block_group->fs_info->discard_ctl;
+
+	extents_delta = ctl->discardable_extents[BTRFS_STAT_CURR] -
+			ctl->discardable_extents[BTRFS_STAT_PREV];
+	if (extents_delta) {
+		atomic_add(extents_delta, &discard_ctl->discardable_extents);
+		ctl->discardable_extents[BTRFS_STAT_PREV] =
+			ctl->discardable_extents[BTRFS_STAT_CURR];
+	}
+}
+
 /**
  * btrfs_discard_punt_unused_bgs_list - punt unused_bgs list to discard lists
  * @fs_info: fs_info of interest
@@ -423,6 +452,8 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 
 	for (i = 0; i < BTRFS_NR_DISCARD_LISTS; i++)
 		INIT_LIST_HEAD(&discard_ctl->discard_list[i]);
+
+	atomic_set(&discard_ctl->discardable_extents, 0);
 }
 
 void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 3c5a04f8714f..0f2f89b1b0b9 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -16,6 +16,10 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 				 bool override);
 bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
 
+/* Update operations */
+void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
+				      struct btrfs_free_space_ctl *ctl);
+
 /* Setup/cleanup operations */
 void btrfs_discard_punt_unused_bgs_list(struct btrfs_fs_info *fs_info);
 void btrfs_discard_resume(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 2e8fbd67ec9b..ed97d082feac 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -32,6 +32,8 @@ struct btrfs_trim_range {
 	struct list_head list;
 };
 
+static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl,
+				struct btrfs_free_space *bitmap_info);
 static int link_free_space(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info);
 static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
@@ -816,12 +818,17 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 		ret = io_ctl_read_bitmap(&io_ctl, e);
 		if (ret)
 			goto free_cache;
+		e->bitmap_extents = count_bitmap_extents(ctl, e);
+		if (!btrfs_free_space_trimmed(e))
+			ctl->discardable_extents[BTRFS_STAT_CURR] +=
+				e->bitmap_extents;
 	}
 
 	io_ctl_drop_pages(&io_ctl);
 	merge_space_tree(ctl);
 	ret = 1;
 out:
+	btrfs_discard_update_discardable(ctl->private, ctl);
 	io_ctl_free(&io_ctl);
 	return ret;
 free_cache:
@@ -1635,6 +1642,9 @@ __unlink_free_space(struct btrfs_free_space_ctl *ctl,
 {
 	rb_erase(&info->offset_index, &ctl->free_space_offset);
 	ctl->free_extents--;
+
+	if (!info->bitmap && !btrfs_free_space_trimmed(info))
+		ctl->discardable_extents[BTRFS_STAT_CURR]--;
 }
 
 static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
@@ -1655,6 +1665,9 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
 	if (ret)
 		return ret;
 
+	if (!info->bitmap && !btrfs_free_space_trimmed(info))
+		ctl->discardable_extents[BTRFS_STAT_CURR]++;
+
 	ctl->free_space += info->bytes;
 	ctl->free_extents++;
 	return ret;
@@ -1711,17 +1724,29 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 				       struct btrfs_free_space *info,
 				       u64 offset, u64 bytes)
 {
-	unsigned long start, count;
+	unsigned long start, count, end;
+	int extent_delta = -1;
 
 	start = offset_to_bit(info->offset, ctl->unit, offset);
 	count = bytes_to_bits(bytes, ctl->unit);
-	ASSERT(start + count <= BITS_PER_BITMAP);
+	end = start + count;
+	ASSERT(end <= BITS_PER_BITMAP);
 
 	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
 	if (info->max_extent_size > ctl->unit)
 		info->max_extent_size = 0;
+
+	if (start && test_bit(start - 1, info->bitmap))
+		extent_delta++;
+
+	if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap))
+		extent_delta++;
+
+	info->bitmap_extents += extent_delta;
+	if (!btrfs_free_space_trimmed(info))
+		ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
 }
 
 static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
@@ -1736,16 +1761,28 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl,
 			    struct btrfs_free_space *info, u64 offset,
 			    u64 bytes)
 {
-	unsigned long start, count;
+	unsigned long start, count, end;
+	int extent_delta = 1;
 
 	start = offset_to_bit(info->offset, ctl->unit, offset);
 	count = bytes_to_bits(bytes, ctl->unit);
-	ASSERT(start + count <= BITS_PER_BITMAP);
+	end = start + count;
+	ASSERT(end <= BITS_PER_BITMAP);
 
 	bitmap_set(info->bitmap, start, count);
 
 	info->bytes += bytes;
 	ctl->free_space += bytes;
+
+	if (start && test_bit(start - 1, info->bitmap))
+		extent_delta--;
+
+	if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap))
+		extent_delta--;
+
+	info->bitmap_extents += extent_delta;
+	if (!btrfs_free_space_trimmed(info))
+		ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
 }
 
 /*
@@ -1881,11 +1918,35 @@ out:
 	return NULL;
 }
 
+static int count_bitmap_extents(struct btrfs_free_space_ctl *ctl,
+				struct btrfs_free_space *bitmap_info)
+{
+	struct btrfs_block_group *block_group = ctl->private;
+	u64 bytes = bitmap_info->bytes;
+	unsigned int rs, re;
+	int count = 0;
+
+	if (!block_group || !bytes)
+		return count;
+
+	bitmap_for_each_set_region(bitmap_info->bitmap, rs, re, 0,
+				   BITS_PER_BITMAP) {
+		bytes -= (rs - re) * ctl->unit;
+		count++;
+
+		if (!bytes)
+			break;
+	}
+
+	return count;
+}
+
 static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 			   struct btrfs_free_space *info, u64 offset)
 {
 	info->offset = offset_to_bitmap(ctl, offset);
 	info->bytes = 0;
+	info->bitmap_extents = 0;
 	INIT_LIST_HEAD(&info->list);
 	link_free_space(ctl, info);
 	ctl->total_bitmaps++;
@@ -1991,8 +2052,12 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
 	 * This is a tradeoff to make bitmap trim state minimal.  We mark the
 	 * whole bitmap untrimmed if at any point we add untrimmed regions.
 	 */
-	if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED)
+	if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED) {
+		if (btrfs_free_space_trimmed(info))
+			ctl->discardable_extents[BTRFS_STAT_CURR] +=
+				info->bitmap_extents;
 		info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
+	}
 
 	end = info->offset + (u64)(BITS_PER_BITMAP * ctl->unit);
 
@@ -2428,6 +2493,7 @@ link:
 	if (ret)
 		kmem_cache_free(btrfs_free_space_cachep, info);
 out:
+	btrfs_discard_update_discardable(block_group, ctl);
 	spin_unlock(&ctl->tree_lock);
 
 	if (ret) {
@@ -2560,6 +2626,7 @@ again:
 		goto again;
 	}
 out_lock:
+	btrfs_discard_update_discardable(block_group, ctl);
 	spin_unlock(&ctl->tree_lock);
 out:
 	return ret;
@@ -2645,8 +2712,16 @@ __btrfs_return_cluster_to_free_space(
 
 		bitmap = (entry->bitmap != NULL);
 		if (!bitmap) {
+			/* Merging treats extents as if they were new */
+			if (!btrfs_free_space_trimmed(entry))
+				ctl->discardable_extents[BTRFS_STAT_CURR]--;
+
 			try_merge_free_space(ctl, entry, false);
 			steal_from_bitmap(ctl, entry, false);
+
+			/* As we insert directly, update these statistics */
+			if (!btrfs_free_space_trimmed(entry))
+				ctl->discardable_extents[BTRFS_STAT_CURR]++;
 		}
 		tree_insert_offset(&ctl->free_space_offset,
 				   entry->offset, &entry->offset_index, bitmap);
@@ -2703,6 +2778,7 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group)
 		cond_resched_lock(&ctl->tree_lock);
 	}
 	__btrfs_remove_free_space_cache_locked(ctl);
+	btrfs_discard_update_discardable(block_group, ctl);
 	spin_unlock(&ctl->tree_lock);
 
 }
@@ -2777,6 +2853,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			link_free_space(ctl, entry);
 	}
 out:
+	btrfs_discard_update_discardable(block_group, ctl);
 	spin_unlock(&ctl->tree_lock);
 
 	if (align_gap_len)
@@ -2941,6 +3018,8 @@ out:
 					entry->bitmap);
 			ctl->total_bitmaps--;
 			ctl->op->recalc_thresholds(ctl);
+		} else if (!btrfs_free_space_trimmed(entry)) {
+			ctl->discardable_extents[BTRFS_STAT_CURR]--;
 		}
 		kmem_cache_free(btrfs_free_space_cachep, entry);
 	}
@@ -3435,15 +3514,24 @@ static void reset_trimming_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset)
 
 	spin_lock(&ctl->tree_lock);
 	entry = tree_search_offset(ctl, offset, 1, 0);
-	if (entry)
+	if (entry) {
+		if (btrfs_free_space_trimmed(entry))
+			ctl->discardable_extents[BTRFS_STAT_CURR] +=
+				entry->bitmap_extents;
 		entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
+	}
+
 	spin_unlock(&ctl->tree_lock);
 }
 
-static void end_trimming_bitmap(struct btrfs_free_space *entry)
+static void end_trimming_bitmap(struct btrfs_free_space_ctl *ctl,
+				struct btrfs_free_space *entry)
 {
-	if (btrfs_free_space_trimming_bitmap(entry))
+	if (btrfs_free_space_trimming_bitmap(entry)) {
 		entry->trim_state = BTRFS_TRIM_STATE_TRIMMED;
+		ctl->discardable_extents[BTRFS_STAT_CURR] -=
+			entry->bitmap_extents;
+	}
 }
 
 /*
@@ -3501,7 +3589,7 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 			 * if BTRFS_TRIM_STATE_TRIMMED is set on a bitmap.
 			 */
 			if (ret2 && !minlen)
-				end_trimming_bitmap(entry);
+				end_trimming_bitmap(ctl, entry);
 			else
 				entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 			spin_unlock(&ctl->tree_lock);
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 765c5cbd99a5..bd1e7a542271 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -28,6 +28,7 @@ struct btrfs_free_space {
 	unsigned long *bitmap;
 	struct list_head list;
 	enum btrfs_trim_state trim_state;
+	s32 bitmap_extents;
 };
 
 static inline bool btrfs_free_space_trimmed(struct btrfs_free_space *info)
@@ -50,6 +51,7 @@ struct btrfs_free_space_ctl {
 	int total_bitmaps;
 	int unit;
 	u64 start;
+	s32 discardable_extents[BTRFS_STAT_NR_ENTRIES];
 	const struct btrfs_free_space_op *op;
 	void *private;
 	struct mutex cache_writeout_mutex;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 0eec1a8d45bd..0ac122c67065 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -12,6 +12,7 @@
 #include <crypto/hash.h>
 
 #include "ctree.h"
+#include "discard.h"
 #include "disk-io.h"
 #include "transaction.h"
 #include "sysfs.h"
@@ -341,7 +342,21 @@ static const struct attribute_group btrfs_static_feature_attr_group = {
 /*
  * Discard statistics and tunables
  */
+#define discard_to_fs_info(_kobj)	to_fs_info((_kobj)->parent->parent)
+
+static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
+					      struct kobj_attribute *a,
+					      char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			atomic_read(&fs_info->discard_ctl.discardable_extents));
+}
+BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show);
+
 static const struct attribute *discard_debug_attrs[] = {
+	BTRFS_ATTR_PTR(discard, discardable_extents),
 	NULL,
 };
 
-- 
cgit v1.2.3-70-g09d2


From 5dc7c10b87474c98116d3438739743cd77263e9f Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Fri, 13 Dec 2019 16:22:21 -0800
Subject: btrfs: keep track of discardable_bytes for async discard

Keep track of this metric so that we can understand how ahead or behind
we are in discarding rate. This uses the same accounting method as
discardable_extents, deltas between previous/current values and
propagating them up.

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h            |  1 +
 fs/btrfs/discard.c          | 10 ++++++++++
 fs/btrfs/free-space-cache.c | 41 ++++++++++++++++++++++++++++++++---------
 fs/btrfs/free-space-cache.h |  1 +
 fs/btrfs/sysfs.c            | 12 ++++++++++++
 5 files changed, 56 insertions(+), 9 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 533c5ea0e8c0..7c1c236d13ae 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -467,6 +467,7 @@ struct btrfs_discard_ctl {
 	struct btrfs_block_group *block_group;
 	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
 	atomic_t discardable_extents;
+	atomic64_t discardable_bytes;
 };
 
 /* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 99663641abf4..62298a438fa5 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -356,6 +356,7 @@ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
 {
 	struct btrfs_discard_ctl *discard_ctl;
 	s32 extents_delta;
+	s64 bytes_delta;
 
 	if (!block_group || !btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC))
 		return;
@@ -369,6 +370,14 @@ void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
 		ctl->discardable_extents[BTRFS_STAT_PREV] =
 			ctl->discardable_extents[BTRFS_STAT_CURR];
 	}
+
+	bytes_delta = ctl->discardable_bytes[BTRFS_STAT_CURR] -
+		      ctl->discardable_bytes[BTRFS_STAT_PREV];
+	if (bytes_delta) {
+		atomic64_add(bytes_delta, &discard_ctl->discardable_bytes);
+		ctl->discardable_bytes[BTRFS_STAT_PREV] =
+			ctl->discardable_bytes[BTRFS_STAT_CURR];
+	}
 }
 
 /**
@@ -454,6 +463,7 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 		INIT_LIST_HEAD(&discard_ctl->discard_list[i]);
 
 	atomic_set(&discard_ctl->discardable_extents, 0);
+	atomic64_set(&discard_ctl->discardable_bytes, 0);
 }
 
 void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index ed97d082feac..40fb918a82f4 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -819,9 +819,11 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 		if (ret)
 			goto free_cache;
 		e->bitmap_extents = count_bitmap_extents(ctl, e);
-		if (!btrfs_free_space_trimmed(e))
+		if (!btrfs_free_space_trimmed(e)) {
 			ctl->discardable_extents[BTRFS_STAT_CURR] +=
 				e->bitmap_extents;
+			ctl->discardable_bytes[BTRFS_STAT_CURR] += e->bytes;
+		}
 	}
 
 	io_ctl_drop_pages(&io_ctl);
@@ -1643,8 +1645,10 @@ __unlink_free_space(struct btrfs_free_space_ctl *ctl,
 	rb_erase(&info->offset_index, &ctl->free_space_offset);
 	ctl->free_extents--;
 
-	if (!info->bitmap && !btrfs_free_space_trimmed(info))
+	if (!info->bitmap && !btrfs_free_space_trimmed(info)) {
 		ctl->discardable_extents[BTRFS_STAT_CURR]--;
+		ctl->discardable_bytes[BTRFS_STAT_CURR] -= info->bytes;
+	}
 }
 
 static void unlink_free_space(struct btrfs_free_space_ctl *ctl,
@@ -1665,8 +1669,10 @@ static int link_free_space(struct btrfs_free_space_ctl *ctl,
 	if (ret)
 		return ret;
 
-	if (!info->bitmap && !btrfs_free_space_trimmed(info))
+	if (!info->bitmap && !btrfs_free_space_trimmed(info)) {
 		ctl->discardable_extents[BTRFS_STAT_CURR]++;
+		ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes;
+	}
 
 	ctl->free_space += info->bytes;
 	ctl->free_extents++;
@@ -1745,8 +1751,10 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 		extent_delta++;
 
 	info->bitmap_extents += extent_delta;
-	if (!btrfs_free_space_trimmed(info))
+	if (!btrfs_free_space_trimmed(info)) {
 		ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
+		ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
+	}
 }
 
 static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
@@ -1781,8 +1789,10 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl,
 		extent_delta--;
 
 	info->bitmap_extents += extent_delta;
-	if (!btrfs_free_space_trimmed(info))
+	if (!btrfs_free_space_trimmed(info)) {
 		ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta;
+		ctl->discardable_bytes[BTRFS_STAT_CURR] += bytes;
+	}
 }
 
 /*
@@ -2053,9 +2063,11 @@ static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl,
 	 * whole bitmap untrimmed if at any point we add untrimmed regions.
 	 */
 	if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED) {
-		if (btrfs_free_space_trimmed(info))
+		if (btrfs_free_space_trimmed(info)) {
 			ctl->discardable_extents[BTRFS_STAT_CURR] +=
 				info->bitmap_extents;
+			ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes;
+		}
 		info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 	}
 
@@ -2713,15 +2725,21 @@ __btrfs_return_cluster_to_free_space(
 		bitmap = (entry->bitmap != NULL);
 		if (!bitmap) {
 			/* Merging treats extents as if they were new */
-			if (!btrfs_free_space_trimmed(entry))
+			if (!btrfs_free_space_trimmed(entry)) {
 				ctl->discardable_extents[BTRFS_STAT_CURR]--;
+				ctl->discardable_bytes[BTRFS_STAT_CURR] -=
+					entry->bytes;
+			}
 
 			try_merge_free_space(ctl, entry, false);
 			steal_from_bitmap(ctl, entry, false);
 
 			/* As we insert directly, update these statistics */
-			if (!btrfs_free_space_trimmed(entry))
+			if (!btrfs_free_space_trimmed(entry)) {
 				ctl->discardable_extents[BTRFS_STAT_CURR]++;
+				ctl->discardable_bytes[BTRFS_STAT_CURR] +=
+					entry->bytes;
+			}
 		}
 		tree_insert_offset(&ctl->free_space_offset,
 				   entry->offset, &entry->offset_index, bitmap);
@@ -3011,6 +3029,8 @@ out:
 	spin_lock(&ctl->tree_lock);
 
 	ctl->free_space -= bytes;
+	if (!entry->bitmap && !btrfs_free_space_trimmed(entry))
+		ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
 	if (entry->bytes == 0) {
 		ctl->free_extents--;
 		if (entry->bitmap) {
@@ -3515,9 +3535,11 @@ static void reset_trimming_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset)
 	spin_lock(&ctl->tree_lock);
 	entry = tree_search_offset(ctl, offset, 1, 0);
 	if (entry) {
-		if (btrfs_free_space_trimmed(entry))
+		if (btrfs_free_space_trimmed(entry)) {
 			ctl->discardable_extents[BTRFS_STAT_CURR] +=
 				entry->bitmap_extents;
+			ctl->discardable_bytes[BTRFS_STAT_CURR] += entry->bytes;
+		}
 		entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED;
 	}
 
@@ -3531,6 +3553,7 @@ static void end_trimming_bitmap(struct btrfs_free_space_ctl *ctl,
 		entry->trim_state = BTRFS_TRIM_STATE_TRIMMED;
 		ctl->discardable_extents[BTRFS_STAT_CURR] -=
 			entry->bitmap_extents;
+		ctl->discardable_bytes[BTRFS_STAT_CURR] -= entry->bytes;
 	}
 }
 
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index bd1e7a542271..5018190a49a3 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -52,6 +52,7 @@ struct btrfs_free_space_ctl {
 	int unit;
 	u64 start;
 	s32 discardable_extents[BTRFS_STAT_NR_ENTRIES];
+	s64 discardable_bytes[BTRFS_STAT_NR_ENTRIES];
 	const struct btrfs_free_space_op *op;
 	void *private;
 	struct mutex cache_writeout_mutex;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 0ac122c67065..ce1da3fcd6c9 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -344,6 +344,17 @@ static const struct attribute_group btrfs_static_feature_attr_group = {
  */
 #define discard_to_fs_info(_kobj)	to_fs_info((_kobj)->parent->parent)
 
+static ssize_t btrfs_discardable_bytes_show(struct kobject *kobj,
+					    struct kobj_attribute *a,
+					    char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%lld\n",
+			atomic64_read(&fs_info->discard_ctl.discardable_bytes));
+}
+BTRFS_ATTR(discard, discardable_bytes, btrfs_discardable_bytes_show);
+
 static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
 					      struct kobj_attribute *a,
 					      char *buf)
@@ -356,6 +367,7 @@ static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
 BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show);
 
 static const struct attribute *discard_debug_attrs[] = {
+	BTRFS_ATTR_PTR(discard, discardable_bytes),
 	BTRFS_ATTR_PTR(discard, discardable_extents),
 	NULL,
 };
-- 
cgit v1.2.3-70-g09d2


From a2309300841207de28307ecd2f0e031fccde37a3 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Thu, 2 Jan 2020 16:26:35 -0500
Subject: btrfs: calculate discard delay based on number of extents

An earlier patch keeps track of discardable_extents. These are
undiscarded extents managed by the free space cache. Here, we will use
this to dynamically calculate the discard delay interval.

There are 3 rate to consider. The first is the target convergence rate,
the rate to discard all discardable_extents over the
BTRFS_DISCARD_TARGET_MSEC time frame. This is clamped by the lower
limit, the iops limit or BTRFS_DISCARD_MIN_DELAY (1ms), and the upper
limit, BTRFS_DISCARD_MAX_DELAY (1s). We reevaluate this delay every
transaction commit.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  2 ++
 fs/btrfs/discard.c     | 55 ++++++++++++++++++++++++++++++++++++++++++++++----
 fs/btrfs/discard.h     |  1 +
 fs/btrfs/extent-tree.c |  4 +++-
 fs/btrfs/sysfs.c       | 31 ++++++++++++++++++++++++++++
 5 files changed, 88 insertions(+), 5 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7c1c236d13ae..451dade0a4bb 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -468,6 +468,8 @@ struct btrfs_discard_ctl {
 	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
 	atomic_t discardable_extents;
 	atomic64_t discardable_bytes;
+	unsigned long delay;
+	u32 iops_limit;
 };
 
 /* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 62298a438fa5..29645676427b 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -15,6 +15,12 @@
 #define BTRFS_DISCARD_DELAY		(120ULL * NSEC_PER_SEC)
 #define BTRFS_DISCARD_UNUSED_DELAY	(10ULL * NSEC_PER_SEC)
 
+/* Target completion latency of discarding all discardable extents */
+#define BTRFS_DISCARD_TARGET_MSEC	(6 * 60 * 60UL * MSEC_PER_SEC)
+#define BTRFS_DISCARD_MIN_DELAY_MSEC	(1UL)
+#define BTRFS_DISCARD_MAX_DELAY_MSEC	(1000UL)
+#define BTRFS_DISCARD_MAX_IOPS		(10U)
+
 static struct list_head *get_discard_list(struct btrfs_discard_ctl *discard_ctl,
 					  struct btrfs_block_group *block_group)
 {
@@ -235,11 +241,17 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
-		u64 delay = 0;
+		unsigned long delay = discard_ctl->delay;
+
+		/*
+		 * This timeout is to hopefully prevent immediate discarding
+		 * in a recently allocated block group.
+		 */
+		if (now < block_group->discard_eligible_time) {
+			u64 bg_timeout = block_group->discard_eligible_time - now;
 
-		if (now < block_group->discard_eligible_time)
-			delay = nsecs_to_jiffies(
-				block_group->discard_eligible_time - now);
+			delay = max(delay, nsecs_to_jiffies(bg_timeout));
+		}
 
 		mod_delayed_work(discard_ctl->discard_workers,
 				 &discard_ctl->work, delay);
@@ -342,6 +354,39 @@ bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl)
 		test_bit(BTRFS_FS_DISCARD_RUNNING, &fs_info->flags));
 }
 
+/**
+ * btrfs_discard_calc_delay - recalculate the base delay
+ * @discard_ctl: discard control
+ *
+ * Recalculate the base delay which is based off the total number of
+ * discardable_extents.  Clamp this between the lower_limit (iops_limit or 1ms)
+ * and the upper_limit (BTRFS_DISCARD_MAX_DELAY_MSEC).
+ */
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl)
+{
+	s32 discardable_extents;
+	u32 iops_limit;
+	unsigned long delay;
+	unsigned long lower_limit = BTRFS_DISCARD_MIN_DELAY_MSEC;
+
+	discardable_extents = atomic_read(&discard_ctl->discardable_extents);
+	if (!discardable_extents)
+		return;
+
+	spin_lock(&discard_ctl->lock);
+
+	iops_limit = READ_ONCE(discard_ctl->iops_limit);
+	if (iops_limit)
+		lower_limit = max_t(unsigned long, lower_limit,
+				    MSEC_PER_SEC / iops_limit);
+
+	delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents;
+	delay = clamp(delay, lower_limit, BTRFS_DISCARD_MAX_DELAY_MSEC);
+	discard_ctl->delay = msecs_to_jiffies(delay);
+
+	spin_unlock(&discard_ctl->lock);
+}
+
 /**
  * btrfs_discard_update_discardable - propagate discard counters
  * @block_group: block_group of interest
@@ -464,6 +509,8 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 
 	atomic_set(&discard_ctl->discardable_extents, 0);
 	atomic64_set(&discard_ctl->discardable_bytes, 0);
+	discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
+	discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
 }
 
 void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 0f2f89b1b0b9..5250fe178e49 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -17,6 +17,7 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 bool btrfs_run_discard_work(struct btrfs_discard_ctl *discard_ctl);
 
 /* Update operations */
+void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl);
 void btrfs_discard_update_discardable(struct btrfs_block_group *block_group,
 				      struct btrfs_free_space_ctl *ctl);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2c12366cfde5..0163fdd59f8f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2935,8 +2935,10 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 		cond_resched();
 	}
 
-	if (btrfs_test_opt(fs_info, DISCARD_ASYNC))
+	if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) {
+		btrfs_discard_calc_delay(&fs_info->discard_ctl);
 		btrfs_discard_schedule_work(&fs_info->discard_ctl, true);
+	}
 
 	/*
 	 * Transaction is finished.  We don't need the lock anymore.  We
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index ce1da3fcd6c9..4155174245ff 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -366,9 +366,40 @@ static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
 }
 BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show);
 
+static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj,
+					     struct kobj_attribute *a,
+					     char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			READ_ONCE(fs_info->discard_ctl.iops_limit));
+}
+
+static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj,
+					      struct kobj_attribute *a,
+					      const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+	struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
+	u32 iops_limit;
+	int ret;
+
+	ret = kstrtou32(buf, 10, &iops_limit);
+	if (ret)
+		return -EINVAL;
+
+	WRITE_ONCE(discard_ctl->iops_limit, iops_limit);
+
+	return len;
+}
+BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show,
+	      btrfs_discard_iops_limit_store);
+
 static const struct attribute *discard_debug_attrs[] = {
 	BTRFS_ATTR_PTR(discard, discardable_bytes),
 	BTRFS_ATTR_PTR(discard, discardable_extents),
+	BTRFS_ATTR_PTR(discard, iops_limit),
 	NULL,
 };
 
-- 
cgit v1.2.3-70-g09d2


From e93591bb6ecf3e31c8f5366eac143f4f9c270915 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Thu, 2 Jan 2020 16:26:36 -0500
Subject: btrfs: add kbps discard rate limit for async discard

Provide the ability to rate limit based on kbps in addition to iops as
additional guides for the target discard rate. The delay used ends up
being max(kbps_delay, iops_delay).

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h   |  2 ++
 fs/btrfs/discard.c | 23 +++++++++++++++++++++--
 fs/btrfs/sysfs.c   | 31 +++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 2 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 451dade0a4bb..f58b1cfeeca6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -466,10 +466,12 @@ struct btrfs_discard_ctl {
 	spinlock_t lock;
 	struct btrfs_block_group *block_group;
 	struct list_head discard_list[BTRFS_NR_DISCARD_LISTS];
+	u64 prev_discard;
 	atomic_t discardable_extents;
 	atomic64_t discardable_bytes;
 	unsigned long delay;
 	u32 iops_limit;
+	u32 kbps_limit;
 };
 
 /* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 29645676427b..565931f9a9aa 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/ktime.h>
 #include <linux/list.h>
+#include <linux/math64.h>
 #include <linux/sizes.h>
 #include <linux/workqueue.h>
 #include "ctree.h"
@@ -222,8 +223,8 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl,
  * @override: override the current timer
  *
  * Discards are issued by a delayed workqueue item.  @override is used to
- * update the current delay as the baseline delay interview is reevaluated
- * on transaction commit.  This is also maxed with any other rate limit.
+ * update the current delay as the baseline delay interval is reevaluated on
+ * transaction commit.  This is also maxed with any other rate limit.
  */
 void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 				 bool override)
@@ -242,6 +243,20 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
 		unsigned long delay = discard_ctl->delay;
+		u32 kbps_limit = READ_ONCE(discard_ctl->kbps_limit);
+
+		/*
+		 * A single delayed workqueue item is responsible for
+		 * discarding, so we can manage the bytes rate limit by keeping
+		 * track of the previous discard.
+		 */
+		if (kbps_limit && discard_ctl->prev_discard) {
+			u64 bps_limit = ((u64)kbps_limit) * SZ_1K;
+			u64 bps_delay = div64_u64(discard_ctl->prev_discard *
+						  MSEC_PER_SEC, bps_limit);
+
+			delay = max(delay, msecs_to_jiffies(bps_delay));
+		}
 
 		/*
 		 * This timeout is to hopefully prevent immediate discarding
@@ -316,6 +331,8 @@ static void btrfs_discard_workfn(struct work_struct *work)
 				       btrfs_block_group_end(block_group),
 				       0, true);
 
+	discard_ctl->prev_discard = trimmed;
+
 	/* Determine next steps for a block_group */
 	if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
 		if (discard_state == BTRFS_DISCARD_BITMAPS) {
@@ -507,10 +524,12 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 	for (i = 0; i < BTRFS_NR_DISCARD_LISTS; i++)
 		INIT_LIST_HEAD(&discard_ctl->discard_list[i]);
 
+	discard_ctl->prev_discard = 0;
 	atomic_set(&discard_ctl->discardable_extents, 0);
 	atomic64_set(&discard_ctl->discardable_bytes, 0);
 	discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
 	discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
+	discard_ctl->kbps_limit = 0;
 }
 
 void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4155174245ff..0168bc12875e 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -396,10 +396,41 @@ static ssize_t btrfs_discard_iops_limit_store(struct kobject *kobj,
 BTRFS_ATTR_RW(discard, iops_limit, btrfs_discard_iops_limit_show,
 	      btrfs_discard_iops_limit_store);
 
+static ssize_t btrfs_discard_kbps_limit_show(struct kobject *kobj,
+					     struct kobj_attribute *a,
+					     char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			READ_ONCE(fs_info->discard_ctl.kbps_limit));
+}
+
+static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj,
+					      struct kobj_attribute *a,
+					      const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+	struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
+	u32 kbps_limit;
+	int ret;
+
+	ret = kstrtou32(buf, 10, &kbps_limit);
+	if (ret)
+		return -EINVAL;
+
+	WRITE_ONCE(discard_ctl->kbps_limit, kbps_limit);
+
+	return len;
+}
+BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show,
+	      btrfs_discard_kbps_limit_store);
+
 static const struct attribute *discard_debug_attrs[] = {
 	BTRFS_ATTR_PTR(discard, discardable_bytes),
 	BTRFS_ATTR_PTR(discard, discardable_extents),
 	BTRFS_ATTR_PTR(discard, iops_limit),
+	BTRFS_ATTR_PTR(discard, kbps_limit),
 	NULL,
 };
 
-- 
cgit v1.2.3-70-g09d2


From 19b2a2c71979f849cadc33af3577f739cc95e1f0 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Thu, 2 Jan 2020 16:26:38 -0500
Subject: btrfs: make max async discard size tunable

Expose max_discard_size as a tunable via sysfs and switch the current
fixed maximum to the default value.

Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h            |  1 +
 fs/btrfs/discard.c          |  1 +
 fs/btrfs/discard.h          |  2 +-
 fs/btrfs/free-space-cache.c | 20 +++++++++++++-------
 fs/btrfs/sysfs.c            | 31 +++++++++++++++++++++++++++++++
 5 files changed, 47 insertions(+), 8 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f58b1cfeeca6..fa6c95fdf5c6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -469,6 +469,7 @@ struct btrfs_discard_ctl {
 	u64 prev_discard;
 	atomic_t discardable_extents;
 	atomic64_t discardable_bytes;
+	u64 max_discard_size;
 	unsigned long delay;
 	u32 iops_limit;
 	u32 kbps_limit;
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 565931f9a9aa..5fdd82c356a4 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -527,6 +527,7 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 	discard_ctl->prev_discard = 0;
 	atomic_set(&discard_ctl->discardable_extents, 0);
 	atomic64_set(&discard_ctl->discardable_bytes, 0);
+	discard_ctl->max_discard_size = BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE;
 	discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
 	discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
 	discard_ctl->kbps_limit = 0;
diff --git a/fs/btrfs/discard.h b/fs/btrfs/discard.h
index 562c60fab77a..f9445ee5dcc3 100644
--- a/fs/btrfs/discard.h
+++ b/fs/btrfs/discard.h
@@ -10,7 +10,7 @@ struct btrfs_discard_ctl;
 struct btrfs_block_group;
 
 /* Discard size limits */
-#define BTRFS_ASYNC_DISCARD_MAX_SIZE	(SZ_64M)
+#define BTRFS_ASYNC_DISCARD_DEFAULT_MAX_SIZE		(SZ_64M)
 
 /* Work operations */
 void btrfs_discard_cancel_work(struct btrfs_discard_ctl *discard_ctl,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 438043aab6fb..db90bea30a8d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -3428,6 +3428,8 @@ static int trim_no_bitmap(struct btrfs_block_group *block_group,
 			  u64 *total_trimmed, u64 start, u64 end, u64 minlen,
 			  bool async)
 {
+	struct btrfs_discard_ctl *discard_ctl =
+					&block_group->fs_info->discard_ctl;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry;
 	struct rb_node *node;
@@ -3436,6 +3438,7 @@ static int trim_no_bitmap(struct btrfs_block_group *block_group,
 	u64 extent_bytes;
 	enum btrfs_trim_state extent_trim_state;
 	u64 bytes;
+	const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size);
 
 	while (start < end) {
 		struct btrfs_trim_range trim_entry;
@@ -3475,11 +3478,11 @@ static int trim_no_bitmap(struct btrfs_block_group *block_group,
 				goto next;
 			}
 			unlink_free_space(ctl, entry);
-			if (bytes > BTRFS_ASYNC_DISCARD_MAX_SIZE) {
-				bytes = BTRFS_ASYNC_DISCARD_MAX_SIZE;
-				extent_bytes = BTRFS_ASYNC_DISCARD_MAX_SIZE;
-				entry->offset += BTRFS_ASYNC_DISCARD_MAX_SIZE;
-				entry->bytes -= BTRFS_ASYNC_DISCARD_MAX_SIZE;
+			if (max_discard_size && bytes > max_discard_size) {
+				bytes = max_discard_size;
+				extent_bytes = max_discard_size;
+				entry->offset += max_discard_size;
+				entry->bytes -= max_discard_size;
 				link_free_space(ctl, entry);
 			} else {
 				kmem_cache_free(btrfs_free_space_cachep, entry);
@@ -3584,12 +3587,15 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 			u64 *total_trimmed, u64 start, u64 end, u64 minlen,
 			bool async)
 {
+	struct btrfs_discard_ctl *discard_ctl =
+					&block_group->fs_info->discard_ctl;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry;
 	int ret = 0;
 	int ret2;
 	u64 bytes;
 	u64 offset = offset_to_bitmap(ctl, start);
+	const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size);
 
 	while (offset < end) {
 		bool next_bitmap = false;
@@ -3659,8 +3665,8 @@ static int trim_bitmaps(struct btrfs_block_group *block_group,
 			goto next;
 		}
 
-		if (async && bytes > BTRFS_ASYNC_DISCARD_MAX_SIZE)
-			bytes = BTRFS_ASYNC_DISCARD_MAX_SIZE;
+		if (async && max_discard_size && bytes > max_discard_size)
+			bytes = max_discard_size;
 
 		bitmap_clear_bits(ctl, entry, start, bytes);
 		if (entry->bytes == 0)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 0168bc12875e..eac0155bf8c7 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -426,11 +426,42 @@ static ssize_t btrfs_discard_kbps_limit_store(struct kobject *kobj,
 BTRFS_ATTR_RW(discard, kbps_limit, btrfs_discard_kbps_limit_show,
 	      btrfs_discard_kbps_limit_store);
 
+static ssize_t btrfs_discard_max_discard_size_show(struct kobject *kobj,
+						   struct kobj_attribute *a,
+						   char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+			READ_ONCE(fs_info->discard_ctl.max_discard_size));
+}
+
+static ssize_t btrfs_discard_max_discard_size_store(struct kobject *kobj,
+						    struct kobj_attribute *a,
+						    const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+	struct btrfs_discard_ctl *discard_ctl = &fs_info->discard_ctl;
+	u64 max_discard_size;
+	int ret;
+
+	ret = kstrtou64(buf, 10, &max_discard_size);
+	if (ret)
+		return -EINVAL;
+
+	WRITE_ONCE(discard_ctl->max_discard_size, max_discard_size);
+
+	return len;
+}
+BTRFS_ATTR_RW(discard, max_discard_size, btrfs_discard_max_discard_size_show,
+	      btrfs_discard_max_discard_size_store);
+
 static const struct attribute *discard_debug_attrs[] = {
 	BTRFS_ATTR_PTR(discard, discardable_bytes),
 	BTRFS_ATTR_PTR(discard, discardable_extents),
 	BTRFS_ATTR_PTR(discard, iops_limit),
 	BTRFS_ATTR_PTR(discard, kbps_limit),
+	BTRFS_ATTR_PTR(discard, max_discard_size),
 	NULL,
 };
 
-- 
cgit v1.2.3-70-g09d2


From 9ddf648f9c2a492cef4e41e31c50515a817d0562 Mon Sep 17 00:00:00 2001
From: Dennis Zhou <dennis@kernel.org>
Date: Thu, 2 Jan 2020 16:26:41 -0500
Subject: btrfs: keep track of discard reuse stats

Keep track of how much we are discarding and how often we are reusing
with async discard. The discard_*_bytes values don't need any special
protection because the work item provides the single threaded access.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h            |  3 +++
 fs/btrfs/discard.c          |  5 +++++
 fs/btrfs/free-space-cache.c | 14 ++++++++++++++
 fs/btrfs/sysfs.c            | 36 ++++++++++++++++++++++++++++++++++++
 4 files changed, 58 insertions(+)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 486b9d1532eb..569931dd0ce5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -473,6 +473,9 @@ struct btrfs_discard_ctl {
 	unsigned long delay;
 	u32 iops_limit;
 	u32 kbps_limit;
+	u64 discard_extent_bytes;
+	u64 discard_bitmap_bytes;
+	atomic64_t discard_bytes_saved;
 };
 
 /* delayed seq elem */
diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c
index 5af42e0317b7..40dcb5dcdc95 100644
--- a/fs/btrfs/discard.c
+++ b/fs/btrfs/discard.c
@@ -417,11 +417,13 @@ static void btrfs_discard_workfn(struct work_struct *work)
 				       block_group->discard_cursor,
 				       btrfs_block_group_end(block_group),
 				       minlen, maxlen, true);
+		discard_ctl->discard_bitmap_bytes += trimmed;
 	} else {
 		btrfs_trim_block_group_extents(block_group, &trimmed,
 				       block_group->discard_cursor,
 				       btrfs_block_group_end(block_group),
 				       minlen, true);
+		discard_ctl->discard_extent_bytes += trimmed;
 	}
 
 	discard_ctl->prev_discard = trimmed;
@@ -626,6 +628,9 @@ void btrfs_discard_init(struct btrfs_fs_info *fs_info)
 	discard_ctl->delay = BTRFS_DISCARD_MAX_DELAY_MSEC;
 	discard_ctl->iops_limit = BTRFS_DISCARD_MAX_IOPS;
 	discard_ctl->kbps_limit = 0;
+	discard_ctl->discard_extent_bytes = 0;
+	discard_ctl->discard_bitmap_bytes = 0;
+	atomic64_set(&discard_ctl->discard_bytes_saved, 0);
 }
 
 void btrfs_discard_cleanup(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index a4340657b7f1..802e06d6303d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2842,6 +2842,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 			       u64 *max_extent_size)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct btrfs_discard_ctl *discard_ctl =
+					&block_group->fs_info->discard_ctl;
 	struct btrfs_free_space *entry = NULL;
 	u64 bytes_search = bytes + empty_size;
 	u64 ret = 0;
@@ -2858,6 +2860,10 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 	ret = offset;
 	if (entry->bitmap) {
 		bitmap_clear_bits(ctl, entry, offset, bytes);
+
+		if (!btrfs_free_space_trimmed(entry))
+			atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
+
 		if (!entry->bytes)
 			free_bitmap(ctl, entry);
 	} else {
@@ -2866,6 +2872,9 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group,
 		align_gap = entry->offset;
 		align_gap_trim_state = entry->trim_state;
 
+		if (!btrfs_free_space_trimmed(entry))
+			atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
+
 		entry->offset = offset + bytes;
 		WARN_ON(entry->bytes < bytes + align_gap_len);
 
@@ -2969,6 +2978,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group,
 			     u64 min_start, u64 *max_extent_size)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+	struct btrfs_discard_ctl *discard_ctl =
+					&block_group->fs_info->discard_ctl;
 	struct btrfs_free_space *entry = NULL;
 	struct rb_node *node;
 	u64 ret = 0;
@@ -3033,6 +3044,9 @@ out:
 
 	spin_lock(&ctl->tree_lock);
 
+	if (!btrfs_free_space_trimmed(entry))
+		atomic64_add(bytes, &discard_ctl->discard_bytes_saved);
+
 	ctl->free_space -= bytes;
 	if (!entry->bitmap && !btrfs_free_space_trimmed(entry))
 		ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes;
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index eac0155bf8c7..55e4ed1af29c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -366,6 +366,39 @@ static ssize_t btrfs_discardable_extents_show(struct kobject *kobj,
 }
 BTRFS_ATTR(discard, discardable_extents, btrfs_discardable_extents_show);
 
+static ssize_t btrfs_discard_bitmap_bytes_show(struct kobject *kobj,
+					       struct kobj_attribute *a,
+					       char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%lld\n",
+			fs_info->discard_ctl.discard_bitmap_bytes);
+}
+BTRFS_ATTR(discard, discard_bitmap_bytes, btrfs_discard_bitmap_bytes_show);
+
+static ssize_t btrfs_discard_bytes_saved_show(struct kobject *kobj,
+					      struct kobj_attribute *a,
+					      char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%lld\n",
+		atomic64_read(&fs_info->discard_ctl.discard_bytes_saved));
+}
+BTRFS_ATTR(discard, discard_bytes_saved, btrfs_discard_bytes_saved_show);
+
+static ssize_t btrfs_discard_extent_bytes_show(struct kobject *kobj,
+					       struct kobj_attribute *a,
+					       char *buf)
+{
+	struct btrfs_fs_info *fs_info = discard_to_fs_info(kobj);
+
+	return snprintf(buf, PAGE_SIZE, "%lld\n",
+			fs_info->discard_ctl.discard_extent_bytes);
+}
+BTRFS_ATTR(discard, discard_extent_bytes, btrfs_discard_extent_bytes_show);
+
 static ssize_t btrfs_discard_iops_limit_show(struct kobject *kobj,
 					     struct kobj_attribute *a,
 					     char *buf)
@@ -459,6 +492,9 @@ BTRFS_ATTR_RW(discard, max_discard_size, btrfs_discard_max_discard_size_show,
 static const struct attribute *discard_debug_attrs[] = {
 	BTRFS_ATTR_PTR(discard, discardable_bytes),
 	BTRFS_ATTR_PTR(discard, discardable_extents),
+	BTRFS_ATTR_PTR(discard, discard_bitmap_bytes),
+	BTRFS_ATTR_PTR(discard, discard_bytes_saved),
+	BTRFS_ATTR_PTR(discard, discard_extent_bytes),
 	BTRFS_ATTR_PTR(discard, iops_limit),
 	BTRFS_ATTR_PTR(discard, kbps_limit),
 	BTRFS_ATTR_PTR(discard, max_discard_size),
-- 
cgit v1.2.3-70-g09d2


From 668e48af7a94985be7cf3b97a860d9819271d8bf Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Mon, 6 Jan 2020 19:38:31 +0800
Subject: btrfs: sysfs, add devid/dev_state kobject and device attributes

New sysfs attributes that track the filesystem status of devices, stored
in the per-filesystem directory in /sys/fs/btrfs/FSID/devinfo . There's
a directory for each device, with name corresponding to the numerical
device id.

  in_fs_metadata    - device is in the list of fs metadata
  missing           - device is missing (no device node or block device)
  replace_target    - device is target of replace
  writeable         - writes from fs are allowed

These attributes reflect the state of the device::dev_state and created
at mount time.

Sample output:
  $ pwd
   /sys/fs/btrfs/6e1961f1-5918-4ecc-a22f-948897b409f7/devinfo/1/
  $ ls
    in_fs_metadata  missing  replace_target  writeable
  $ cat missing
    0

The output from these attributes are 0 or 1. 0 indicates unset and 1
indicates set.  These attributes are readonly.

It is observed that the device delete thread and sysfs read thread will
not race because the delete thread calls sysfs kobject_put() which in
turn waits for existing sysfs read to complete.

Note for device replace devid swap:

During the replace the target device temporarily assumes devid 0 before
assigning the devid of the soruce device.

In btrfs_dev_replace_finishing() we remove source sysfs devid using the
function btrfs_sysfs_remove_devices_attr(), so after that call
kobject_rename() to update the devid in the sysfs.  This adds and calls
btrfs_sysfs_update_devid() helper function to update the device id.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c |   1 +
 fs/btrfs/sysfs.c       | 155 +++++++++++++++++++++++++++++++++++++++++--------
 fs/btrfs/sysfs.h       |   1 +
 fs/btrfs/volumes.h     |   4 ++
 4 files changed, 138 insertions(+), 23 deletions(-)

(limited to 'fs/btrfs/sysfs.c')

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f639dde2a679..8600beb9c086 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -707,6 +707,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	/* replace the sysfs entry */
 	btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device);
+	btrfs_sysfs_update_devid(tgt_device);
 	btrfs_rm_dev_replace_free_srcdev(src_device);
 
 	/* write back the superblocks */
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 55e4ed1af29c..7436422194da 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1152,29 +1152,117 @@ int btrfs_sysfs_rm_device_link(struct btrfs_fs_devices *fs_devices,
 	if (!fs_devices->devices_kobj)
 		return -EINVAL;
 
-	if (one_device && one_device->bdev) {
-		disk = one_device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
+	if (one_device) {
+		if (one_device->bdev) {
+			disk = one_device->bdev->bd_part;
+			disk_kobj = &part_to_dev(disk)->kobj;
+			sysfs_remove_link(fs_devices->devices_kobj,
+					  disk_kobj->name);
+		}
 
-		sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name);
-	}
+		kobject_del(&one_device->devid_kobj);
+		kobject_put(&one_device->devid_kobj);
+
+		wait_for_completion(&one_device->kobj_unregister);
 
-	if (one_device)
 		return 0;
+	}
 
-	list_for_each_entry(one_device,
-			&fs_devices->devices, dev_list) {
-		if (!one_device->bdev)
-			continue;
-		disk = one_device->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
+	list_for_each_entry(one_device, &fs_devices->devices, dev_list) {
+
+		if (one_device->bdev) {
+			disk = one_device->bdev->bd_part;
+			disk_kobj = &part_to_dev(disk)->kobj;
+			sysfs_remove_link(fs_devices->devices_kobj,
+					  disk_kobj->name);
+		}
+		kobject_del(&one_device->devid_kobj);
+		kobject_put(&one_device->devid_kobj);
 
-		sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name);
+		wait_for_completion(&one_device->kobj_unregister);
 	}
 
 	return 0;
 }
 
+static ssize_t btrfs_devinfo_in_fs_metadata_show(struct kobject *kobj,
+					         struct kobj_attribute *a,
+					         char *buf)
+{
+	int val;
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	val = !!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+BTRFS_ATTR(devid, in_fs_metadata, btrfs_devinfo_in_fs_metadata_show);
+
+static ssize_t btrfs_sysfs_missing_show(struct kobject *kobj,
+					struct kobj_attribute *a, char *buf)
+{
+	int val;
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	val = !!test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+BTRFS_ATTR(devid, missing, btrfs_sysfs_missing_show);
+
+static ssize_t btrfs_devinfo_replace_target_show(struct kobject *kobj,
+					         struct kobj_attribute *a,
+					         char *buf)
+{
+	int val;
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	val = !!test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+BTRFS_ATTR(devid, replace_target, btrfs_devinfo_replace_target_show);
+
+static ssize_t btrfs_devinfo_writeable_show(struct kobject *kobj,
+					    struct kobj_attribute *a, char *buf)
+{
+	int val;
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	val = !!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+BTRFS_ATTR(devid, writeable, btrfs_devinfo_writeable_show);
+
+static struct attribute *devid_attrs[] = {
+	BTRFS_ATTR_PTR(devid, in_fs_metadata),
+	BTRFS_ATTR_PTR(devid, missing),
+	BTRFS_ATTR_PTR(devid, replace_target),
+	BTRFS_ATTR_PTR(devid, writeable),
+	NULL
+};
+ATTRIBUTE_GROUPS(devid);
+
+static void btrfs_release_devid_kobj(struct kobject *kobj)
+{
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	memset(&device->devid_kobj, 0, sizeof(struct kobject));
+	complete(&device->kobj_unregister);
+}
+
+static struct kobj_type devid_ktype = {
+	.sysfs_ops	= &kobj_sysfs_ops,
+	.default_groups = devid_groups,
+	.release	= btrfs_release_devid_kobj,
+};
+
 int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 				struct btrfs_device *one_device)
 {
@@ -1182,22 +1270,31 @@ int btrfs_sysfs_add_device_link(struct btrfs_fs_devices *fs_devices,
 	struct btrfs_device *dev;
 
 	list_for_each_entry(dev, &fs_devices->devices, dev_list) {
-		struct hd_struct *disk;
-		struct kobject *disk_kobj;
-
-		if (!dev->bdev)
-			continue;
 
 		if (one_device && one_device != dev)
 			continue;
 
-		disk = dev->bdev->bd_part;
-		disk_kobj = &part_to_dev(disk)->kobj;
+		if (dev->bdev) {
+			struct hd_struct *disk;
+			struct kobject *disk_kobj;
+
+			disk = dev->bdev->bd_part;
+			disk_kobj = &part_to_dev(disk)->kobj;
+
+			error = sysfs_create_link(fs_devices->devices_kobj,
+						  disk_kobj, disk_kobj->name);
+			if (error)
+				break;
+		}
 
-		error = sysfs_create_link(fs_devices->devices_kobj,
-					  disk_kobj, disk_kobj->name);
-		if (error)
+		init_completion(&dev->kobj_unregister);
+		error = kobject_init_and_add(&dev->devid_kobj, &devid_ktype,
+					     fs_devices->devices_kobj, "%llu",
+					     dev->devid);
+		if (error) {
+			kobject_put(&dev->devid_kobj);
 			break;
+		}
 	}
 
 	return error;
@@ -1229,6 +1326,18 @@ void btrfs_sysfs_update_sprout_fsid(struct btrfs_fs_devices *fs_devices,
 				"sysfs: failed to create fsid for sprout");
 }
 
+void btrfs_sysfs_update_devid(struct btrfs_device *device)
+{
+	char tmp[24];
+
+	snprintf(tmp, sizeof(tmp), "%llu", device->devid);
+
+	if (kobject_rename(&device->devid_kobj, tmp))
+		btrfs_warn(device->fs_devices->fs_info,
+			   "sysfs: failed to update devid for %llu",
+			   device->devid);
+}
+
 /* /sys/fs/btrfs/ entry */
 static struct kset *btrfs_kset;
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 3d27b39eaf94..c68582add92e 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -34,5 +34,6 @@ void btrfs_sysfs_add_block_group_type(struct btrfs_block_group *cache);
 int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info);
 void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info);
+void btrfs_sysfs_update_devid(struct btrfs_device *device);
 
 #endif
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 9c7d4fe5c39a..690d4f5a0653 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -136,6 +136,10 @@ struct btrfs_device {
 	atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];
 
 	struct extent_io_tree alloc_state;
+
+	struct completion kobj_unregister;
+	/* For sysfs/FSID/devinfo/devid/ */
+	struct kobject devid_kobj;
 };
 
 /*
-- 
cgit v1.2.3-70-g09d2