[PATCH 1/4 RESEND] Btrfs: all super blocks of the replaced disk must be scratched

[PATCH 1/4 RESEND] Btrfs: all super blocks of the replaced disk must be scratched

[Anand Jain]

From: Anand Jain <Anand.Jain@oracle.com>

In a normal scenario when sys-admin replaces a disk, the
expeted is btrfs will release the disk completely.

However the below test case gives a wrong impression that
replaced disk is still is in use.

$ btrfs rep start /dev/sde /dev/sdg4 /btrfs
$ mkfs.btrfs /dev/sde
/dev/sde appears to contain an existing filesystem (btrfs).
Error: Use the -f option to force overwrite.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
 fs/btrfs/volumes.c | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b4660c4..19e68f7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6280,16 +6280,33 @@ int btrfs_scratch_superblock(struct btrfs_device *device)
 {
 	struct buffer_head *bh;
 	struct btrfs_super_block *disk_super;
+	int i;
+	u64 bytenr;
 
-	bh = btrfs_read_dev_super(device->bdev);
-	if (!bh)
-		return -EINVAL;
-	disk_super = (struct btrfs_super_block *)bh->b_data;
+	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+		bytenr = btrfs_sb_offset(i);
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+				i_size_read(device->bdev->bd_inode))
+			break;
 
-	memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-	set_buffer_dirty(bh);
-	sync_dirty_buffer(bh);
-	brelse(bh);
+		bh = __bread(device->bdev, bytenr / 4096,
+					BTRFS_SUPER_INFO_SIZE);
+		if (!bh)
+			continue;
+
+		disk_super = (struct btrfs_super_block *)bh->b_data;
+		if (btrfs_super_bytenr(disk_super) != bytenr ||
+				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
+			brelse(bh);
+			continue;
+		}
+
+		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+
+		set_buffer_dirty(bh);
+		sync_dirty_buffer(bh);
+		brelse(bh);
+	}
 
 	return 0;
 }
-- 
1.8.5.3

[PATCH 2/4 RESEND] btrfs: btrfs_rm_device() should zero mirror SB as well

[Anand Jain]

This fix will ensure all SB copies on the disk is zeroed
when the disk is intentionally removed. This helps to
better manage disks in the user land.

This version of patch also merges the Zach patch as below.

 btrfs: don't double brelse on device rm

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: Zach Brown <zab@redhat.com>
---
 fs/btrfs/volumes.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 19e68f7..1567439 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1681,12 +1681,43 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	 * remove it from the devices list and zero out the old super
 	 */
 	if (clear_super && disk_super) {
+		u64 bytenr;
+		int i;
+
 		/* make sure this device isn't detected as part of
 		 * the FS anymore
 		 */
 		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
 		set_buffer_dirty(bh);
 		sync_dirty_buffer(bh);
+
+		/* clear the mirror copies of super block on the disk
+		 * being removed, 0th copy is been taken care above and
+		 * the below would take of the rest
+		 */
+		for (i = 1; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+			bytenr = btrfs_sb_offset(i);
+			if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+					i_size_read(bdev->bd_inode))
+				break;
+
+			brelse(bh);
+			bh = __bread(bdev, bytenr / 4096,
+					BTRFS_SUPER_INFO_SIZE);
+			if (!bh)
+				continue;
+
+			disk_super = (struct btrfs_super_block *)bh->b_data;
+
+			if (btrfs_super_bytenr(disk_super) != bytenr ||
+				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
+				continue;
+			}
+			memset(&disk_super->magic, 0,
+						sizeof(disk_super->magic));
+			set_buffer_dirty(bh);
+			sync_dirty_buffer(bh);
+		}
 	}
 
 	ret = 0;
-- 
1.8.5.3

[PATCH 3/4 RESEND] btrfs: add framework to read fs info from btrfs-control

[Anand Jain]

This adds ioctl BTRFS_IOC_GET_FSIDS which reads the fs
info through the btrfs-control, needed to optimize
heavily used btrfs-progs function check_mounted()
plus few other minor uses.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
 fs/btrfs/super.c           | 66 +++++++++++++++++++++++++++++++++++++++++-----
 fs/btrfs/volumes.c         | 39 +++++++++++++++++++++++++++
 fs/btrfs/volumes.h         |  2 ++
 include/uapi/linux/btrfs.h | 19 +++++++++++++
 4 files changed, 120 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d4878dd..b42cd50 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1717,38 +1717,92 @@ static struct file_system_type btrfs_fs_type = {
 };
 MODULE_ALIAS_FS("btrfs");
 
+static int btrfs_ioc_get_fslist(void __user *arg)
+{
+	int ret = 0;
+	u64 sz_fslist_arg;
+	u64 sz_fslist;
+	u64 sz_out;
+	struct btrfs_ioctl_fslist_args *fslist_arg;
+	struct btrfs_ioctl_fslist_args *fslist_arg_tmp;
+	struct btrfs_ioctl_fslist *fslist;
+
+	u64 cnt = 0, ucnt;
+
+	sz_fslist_arg = sizeof(*fslist_arg);
+	sz_fslist = sizeof(*fslist);
+	if (copy_from_user(&ucnt,
+		(struct btrfs_ioctl_fslist_args __user *)(arg +
+		offsetof(struct btrfs_ioctl_fslist_args, count)),
+			sizeof(ucnt)))
+		return -EFAULT;
+
+	cnt = btrfs_get_fslist_cnt();
+
+	if (cnt > ucnt) {
+		if (copy_to_user(arg +
+		offsetof(struct btrfs_ioctl_fslist_args, count),
+			&cnt, sizeof(cnt)))
+			return -EFAULT;
+		return 1;
+	}
+
+	sz_out = sz_fslist_arg + sz_fslist * cnt;
+	fslist_arg_tmp = fslist_arg = memdup_user(arg, sz_out);
+	if (IS_ERR(fslist_arg))
+		return PTR_ERR(fslist_arg);
+	fslist = (struct btrfs_ioctl_fslist *) (++fslist_arg_tmp);
+	cnt = btrfs_get_fslist(fslist, cnt);
+	fslist_arg->count = cnt;
+	if (copy_to_user(arg, fslist_arg, sz_out)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	ret = 0;
+out:
+	kfree(fslist_arg);
+	return ret;
+}
+
 /*
  * used by btrfsctl to scan devices when no FS is mounted
  */
 static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
-	struct btrfs_ioctl_vol_args *vol;
+	struct btrfs_ioctl_vol_args *vol = NULL;
 	struct btrfs_fs_devices *fs_devices;
 	int ret = -ENOTTY;
+	void __user *argp = (void __user *)arg;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	vol = memdup_user((void __user *)arg, sizeof(*vol));
-	if (IS_ERR(vol))
-		return PTR_ERR(vol);
-
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
+		vol = memdup_user((void __user *)arg, sizeof(*vol));
+		if (IS_ERR(vol))
+			return PTR_ERR(vol);
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
 					    &btrfs_fs_type, &fs_devices);
+		kfree(vol);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
+		vol = memdup_user((void __user *)arg, sizeof(*vol));
+		if (IS_ERR(vol))
+			return PTR_ERR(vol);
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
 					    &btrfs_fs_type, &fs_devices);
+		kfree(vol);
 		if (ret)
 			break;
 		ret = !(fs_devices->num_devices == fs_devices->total_devices);
 		break;
+	case BTRFS_IOC_GET_FSLIST:
+		ret = btrfs_ioc_get_fslist(argp);
+		break;
 	}
 
-	kfree(vol);
 	return ret;
 }
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1567439..e22ac22 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6341,3 +6341,42 @@ int btrfs_scratch_superblock(struct btrfs_device *device)
 
 	return 0;
 }
+
+int btrfs_get_fslist_cnt(void)
+{
+	int cnt = 0;
+	struct btrfs_fs_devices *fs_devices;
+
+	mutex_lock(&uuid_mutex);
+	list_for_each_entry(fs_devices, &fs_uuids, list)
+		cnt++;
+	mutex_unlock(&uuid_mutex);
+
+	return cnt;
+}
+
+u64 btrfs_get_fslist(struct btrfs_ioctl_fslist *fslist, u64 ucnt)
+{
+	u64 cnt = 0;
+	struct btrfs_fs_devices *fs_devices;
+
+	mutex_lock(&uuid_mutex);
+	list_for_each_entry(fs_devices, &fs_uuids, list) {
+		if (!(cnt < ucnt))
+			break;
+		memcpy(fslist->fsid, fs_devices->fsid,
+				BTRFS_FSID_SIZE);
+		fslist->num_devices = fs_devices->num_devices;
+		fslist->missing_devices = fs_devices->missing_devices;
+		fslist->total_devices = fs_devices->total_devices;
+
+		if (fs_devices->opened)
+			fslist->flags = BTRFS_FS_MOUNTED;
+
+		fslist++;
+		cnt++;
+	}
+	mutex_unlock(&uuid_mutex);
+
+	return cnt;
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 80754f9..0b97fcf 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -391,4 +391,6 @@ static inline void btrfs_dev_stat_reset(struct btrfs_device *dev,
 {
 	btrfs_dev_stat_set(dev, index, 0);
 }
+int btrfs_get_fslist_cnt(void);
+u64 btrfs_get_fslist(struct btrfs_ioctl_fslist *fslist, u64 ucnt);
 #endif
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index b4d6909..76b91d6 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -518,6 +518,23 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 	}
 }
 
+/* fs flags */
+#define BTRFS_FS_MOUNTED	(1LLU << 0)
+
+struct btrfs_ioctl_fslist {
+	__u64 self_sz;			/* in/out */
+	__u8 fsid[BTRFS_FSID_SIZE];	/* out */
+	__u64 num_devices;
+	__u64 missing_devices;
+	__u64 total_devices;
+	__u64 flags;
+};
+
+struct btrfs_ioctl_fslist_args {
+	__u64 self_sz;		/* in/out */
+	__u64 count;		/* out */
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
@@ -612,6 +629,8 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code)
 				    struct btrfs_ioctl_dev_replace_args)
 #define BTRFS_IOC_FILE_EXTENT_SAME _IOWR(BTRFS_IOCTL_MAGIC, 54, \
 					 struct btrfs_ioctl_same_args)
+#define BTRFS_IOC_GET_FSLIST _IOWR(BTRFS_IOCTL_MAGIC, 56, \
+					struct btrfs_ioctl_fslist_args)
 #define BTRFS_IOC_GET_FEATURES _IOR(BTRFS_IOCTL_MAGIC, 57, \
 				   struct btrfs_ioctl_feature_flags)
 #define BTRFS_IOC_SET_FEATURES _IOW(BTRFS_IOCTL_MAGIC, 57, \
-- 
1.8.5.3

[PATCH 4/4 RESEND] btrfs: scrub maintenance event should be recorded in the messages

[Anand Jain]

so to help problem understanding and solving

Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
 fs/btrfs/ioctl.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e174770..ff27c08 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3702,10 +3702,17 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
 			goto out;
 	}
 
+	btrfs_info(root->fs_info, "Scrub started");
+
 	ret = btrfs_scrub_dev(root->fs_info, sa->devid, sa->start, sa->end,
 			      &sa->progress, sa->flags & BTRFS_SCRUB_READONLY,
 			      0);
 
+	if (ret)
+		btrfs_info(root->fs_info, "Scrub failed - %d", ret);
+	else
+		btrfs_info(root->fs_info, "Scrub finished");
+
 	if (copy_to_user(arg, sa, sizeof(*sa)))
 		ret = -EFAULT;
 
-- 
1.8.5.3

[PATCH 1/4 RESEND V3] Btrfs: all super blocks of the replaced disk must be scratched

[Anand Jain]

From: Anand Jain <Anand.Jain@oracle.com>

In a normal scenario when sys-admin replaces a disk, the
expectation is that btrfs will release the disk completely.

However the below test case gives a wrong impression that
replaced disk is still is in use.

$ btrfs rep start /dev/sde /dev/sdg4 /btrfs
$ mkfs.btrfs /dev/sde
/dev/sde appears to contain an existing filesystem (btrfs).
Error: Use the -f option to force overwrite.

Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
v2->v3: fix commit typo error. thanks Brendan
v1->v2: add missing signed-off

 fs/btrfs/volumes.c |   33 +++++++++++++++++++++++++--------
 1 files changed, 25 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index b4660c4..19e68f7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6280,16 +6280,33 @@ int btrfs_scratch_superblock(struct btrfs_device *device)
 {
 	struct buffer_head *bh;
 	struct btrfs_super_block *disk_super;
+	int i;
+	u64 bytenr;
 
-	bh = btrfs_read_dev_super(device->bdev);
-	if (!bh)
-		return -EINVAL;
-	disk_super = (struct btrfs_super_block *)bh->b_data;
+	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
+		bytenr = btrfs_sb_offset(i);
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+				i_size_read(device->bdev->bd_inode))
+			break;
 
-	memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-	set_buffer_dirty(bh);
-	sync_dirty_buffer(bh);
-	brelse(bh);
+		bh = __bread(device->bdev, bytenr / 4096,
+					BTRFS_SUPER_INFO_SIZE);
+		if (!bh)
+			continue;
+
+		disk_super = (struct btrfs_super_block *)bh->b_data;
+		if (btrfs_super_bytenr(disk_super) != bytenr ||
+				btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
+			brelse(bh);
+			continue;
+		}
+
+		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
+
+		set_buffer_dirty(bh);
+		sync_dirty_buffer(bh);
+		brelse(bh);
+	}
 
 	return 0;
 }
-- 
1.7.1