From 11bcac89c0d73dea42f1cb8646b532035796a5d6 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 14 Feb 2014 13:42:13 -0800 Subject: Revert "btrfs: add ioctl to export size of global metadata reservation" This reverts commit 01e219e8069516cdb98594d417b8bb8d906ed30d. David Sterba found a different way to provide these features without adding a new ioctl. We haven't released any progs with this ioctl yet, so I'm taking this out for now until we finalize things. Signed-off-by: Chris Mason Signed-off-by: David Sterba CC: Jeff Mahoney --- fs/btrfs/ioctl.c | 16 ---------------- include/uapi/linux/btrfs.h | 1 - 2 files changed, 17 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ebdd866d4cfd..9a9044585da7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3559,20 +3559,6 @@ out: return ret; } -static long btrfs_ioctl_global_rsv(struct btrfs_root *root, void __user *arg) -{ - struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv; - u64 reserved; - - spin_lock(&block_rsv->lock); - reserved = block_rsv->reserved; - spin_unlock(&block_rsv->lock); - - if (arg && copy_to_user(arg, &reserved, sizeof(reserved))) - return -EFAULT; - return 0; -} - /* * there are many ways the trans_start and trans_end ioctls can lead * to deadlocks. They should only be used by applications that @@ -4779,8 +4765,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_logical_to_ino(root, argp); case BTRFS_IOC_SPACE_INFO: return btrfs_ioctl_space_info(root, argp); - case BTRFS_IOC_GLOBAL_RSV: - return btrfs_ioctl_global_rsv(root, argp); case BTRFS_IOC_SYNC: { int ret; diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 1b8a0f4c9590..b4d69092fbdb 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -558,7 +558,6 @@ static inline char *btrfs_err_str(enum btrfs_err_code err_code) #define BTRFS_IOC_DEFAULT_SUBVOL _IOW(BTRFS_IOCTL_MAGIC, 19, __u64) #define BTRFS_IOC_SPACE_INFO _IOWR(BTRFS_IOCTL_MAGIC, 20, \ struct btrfs_ioctl_space_args) -#define BTRFS_IOC_GLOBAL_RSV _IOR(BTRFS_IOCTL_MAGIC, 20, __u64) #define BTRFS_IOC_START_SYNC _IOR(BTRFS_IOCTL_MAGIC, 24, __u64) #define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64) #define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \ -- cgit v1.2.3-59-g8ed1b From a9d2d4adb6a87e515912a7033b227acbd9c8835e Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Sat, 8 Feb 2014 15:33:08 +0800 Subject: Btrfs: fix a lockdep warning when cleaning up aborted transaction Given now we have 2 spinlock for management of delayed refs, CONFIG_DEBUG_SPINLOCK=y helped me find this, [ 4723.413809] BUG: spinlock wrong CPU on CPU#1, btrfs-transacti/2258 [ 4723.414882] lock: 0xffff880048377670, .magic: dead4ead, .owner: btrfs-transacti/2258, .owner_cpu: 2 [ 4723.417146] CPU: 1 PID: 2258 Comm: btrfs-transacti Tainted: G W O 3.12.0+ #4 [ 4723.421321] Call Trace: [ 4723.421872] [] dump_stack+0x54/0x74 [ 4723.422753] [] spin_dump+0x8c/0x91 [ 4723.424979] [] spin_bug+0x21/0x26 [ 4723.425846] [] do_raw_spin_unlock+0x66/0x90 [ 4723.434424] [] _raw_spin_unlock+0x27/0x40 [ 4723.438747] [] btrfs_cleanup_one_transaction+0x35e/0x710 [btrfs] [ 4723.443321] [] btrfs_cleanup_transaction+0x104/0x570 [btrfs] [ 4723.444692] [] ? trace_hardirqs_on_caller+0xfd/0x1c0 [ 4723.450336] [] ? trace_hardirqs_on+0xd/0x10 [ 4723.451332] [] transaction_kthread+0x22e/0x270 [btrfs] [ 4723.452543] [] ? btrfs_cleanup_transaction+0x570/0x570 [btrfs] [ 4723.457833] [] kthread+0xea/0xf0 [ 4723.458990] [] ? kthread_create_on_node+0x140/0x140 [ 4723.460133] [] ret_from_fork+0x7c/0xb0 [ 4723.460865] [] ? kthread_create_on_node+0x140/0x140 [ 4723.496521] ------------[ cut here ]------------ ---------------------------------------------------------------------- The reason is that we get to call cond_resched_lock(&head_ref->lock) while still holding @delayed_refs->lock. So it's different with __btrfs_run_delayed_refs(), where we do drop-acquire dance before and after actually processing delayed refs. Here we don't drop the lock, others are not able to add new delayed refs to head_ref, so cond_resched_lock(&head_ref->lock) is not necessary here. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 1 - 1 file changed, 1 deletion(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3903bd3f8d2b..fcf367581073 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3842,7 +3842,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans, rb_erase(&ref->rb_node, &head->ref_root); atomic_dec(&delayed_refs->num_entries); btrfs_put_delayed_ref(ref); - cond_resched_lock(&head->lock); } if (head->must_insert_reserved) pin_bytes = true; -- cgit v1.2.3-59-g8ed1b From feb5f96589302b39a2b10fc210db7c47a73e4168 Mon Sep 17 00:00:00 2001 From: Mitch Harder Date: Thu, 13 Feb 2014 09:13:16 -0600 Subject: Btrfs: fix max_inline mount option Currently, the only mount option for max_inline that has any effect is max_inline=0. Any other value that is supplied to max_inline will be adjusted to a minimum of 4k. Since max_inline has an effective maximum of ~3900 bytes due to page size limitations, the current behaviour only has meaning for max_inline=0. This patch will allow the the max_inline mount option to accept non-zero values as indicated in the documentation. Signed-off-by: Mitch Harder Signed-off-by: Chris Mason --- fs/btrfs/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 97cc24198554..e73c80eec11b 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -566,7 +566,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) kfree(num); if (info->max_inline) { - info->max_inline = max_t(u64, + info->max_inline = min_t(u64, info->max_inline, root->sectorsize); } -- cgit v1.2.3-59-g8ed1b From 3a0dfa6a12e4bb64a434426ecb17d4842092db5e Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 14 Feb 2014 13:43:48 -0500 Subject: Btrfs: unset DCACHE_DISCONNECTED when mounting default subvol A user was running into errors from an NFS export of a subvolume that had a default subvol set. When we mount a default subvol we will use d_obtain_alias() to find an existing dentry for the subvolume in the case that the root subvol has already been mounted, or a dummy one is allocated in the case that the root subvol has not already been mounted. This allows us to connect the dentry later on if we wander into the path. However if we don't ever wander into the path we will keep DCACHE_DISCONNECTED set for a long time, which angers NFS. It doesn't appear to cause any problems but it is annoying nonetheless, so simply unset DCACHE_DISCONNECTED in the get_default_root case and switch btrfs_lookup() to use d_materialise_unique() instead which will make everything play nicely together and reconnect stuff if we wander into the defaul subvol path from a different way. With this patch I'm no longer getting the NFS errors when exporting a volume that has been mounted with a default subvol set. Thanks, cc: bfields@fieldses.org cc: ebiederm@xmission.com Signed-off-by: Josef Bacik Acked-by: "Eric W. Biederman" Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 2 +- fs/btrfs/super.c | 9 ++++++++- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1af34d0c744b..4ffb6d79f9f0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5150,7 +5150,7 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, return ERR_CAST(inode); } - return d_splice_alias(inode, dentry); + return d_materialise_unique(dentry, inode); } unsigned char btrfs_filetype_table[] = { diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index e73c80eec11b..d04db817be5c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -855,6 +855,7 @@ static struct dentry *get_default_root(struct super_block *sb, struct btrfs_path *path; struct btrfs_key location; struct inode *inode; + struct dentry *dentry; u64 dir_id; int new = 0; @@ -925,7 +926,13 @@ setup_root: return dget(sb->s_root); } - return d_obtain_alias(inode); + dentry = d_obtain_alias(inode); + if (!IS_ERR(dentry)) { + spin_lock(&dentry->d_lock); + dentry->d_flags &= ~DCACHE_DISCONNECTED; + spin_unlock(&dentry->d_lock); + } + return dentry; } static int btrfs_fill_super(struct super_block *sb, -- cgit v1.2.3-59-g8ed1b From f085381e6d08f4c8d6882825f31accd455c54d70 Mon Sep 17 00:00:00 2001 From: Anand Jain Date: Wed, 15 Jan 2014 17:22:28 +0800 Subject: btrfs: fix null pointer deference at btrfs_sysfs_add_one+0x105 bdev is null when disk has disappeared and mounted with the degrade option stack trace --------- btrfs_sysfs_add_one+0x105/0x1c0 [btrfs] open_ctree+0x15f3/0x1fe0 [btrfs] btrfs_mount+0x5db/0x790 [btrfs] ? alloc_pages_current+0xa4/0x160 mount_fs+0x34/0x1b0 vfs_kern_mount+0x62/0xf0 do_mount+0x22e/0xa80 ? __get_free_pages+0x9/0x40 ? copy_mount_options+0x31/0x170 SyS_mount+0x7e/0xc0 system_call_fastpath+0x16/0x1b --------- reproducer: ------- mkfs.btrfs -draid1 -mraid1 /dev/sdc /dev/sdd (detach a disk) devmgt detach /dev/sdc [1] mount -o degrade /dev/sdd /btrfs ------- [1] github.com/anajain/devmgt.git Signed-off-by: Anand Jain Tested-by: Hidetoshi Seto Signed-off-by: Chris Mason --- fs/btrfs/sysfs.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 782374d8fd19..865f4cf9a769 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -578,8 +578,14 @@ static int add_device_membership(struct btrfs_fs_info *fs_info) return -ENOMEM; list_for_each_entry(dev, &fs_devices->devices, dev_list) { - struct hd_struct *disk = dev->bdev->bd_part; - struct kobject *disk_kobj = &part_to_dev(disk)->kobj; + struct hd_struct *disk; + struct kobject *disk_kobj; + + if (!dev->bdev) + continue; + + disk = dev->bdev->bd_part; + disk_kobj = &part_to_dev(disk)->kobj; error = sysfs_create_link(fs_info->device_dir_kobj, disk_kobj, disk_kobj->name); -- cgit v1.2.3-59-g8ed1b From 93de4ba86480a9e0d1062cb1d535fa97fb81af48 Mon Sep 17 00:00:00 2001 From: Filipe David Borba Manana Date: Sat, 15 Feb 2014 15:53:16 +0000 Subject: Btrfs: use right clone root offset for compressed extents For non compressed extents, iterate_extent_inodes() gives us offsets that take into account the data offset from the file extent items, while for compressed extents it doesn't. Therefore we have to adjust them before placing them in a send clone instruction. Not doing this adjustment leads to the receiving end requesting for a wrong a file range to the clone ioctl, which results in different file content from the one in the original send root. Issue reproducible with the following excerpt from the test I made for xfstests: _scratch_mkfs _scratch_mount "-o compress-force=lzo" $XFS_IO_PROG -f -c "truncate 118811" $SCRATCH_MNT/foo $XFS_IO_PROG -c "pwrite -S 0x0d -b 39987 92267 39987" $SCRATCH_MNT/foo $BTRFS_UTIL_PROG subvolume snapshot -r $SCRATCH_MNT $SCRATCH_MNT/mysnap1 $XFS_IO_PROG -c "pwrite -S 0x3e -b 80000 200000 80000" $SCRATCH_MNT/foo $BTRFS_UTIL_PROG filesystem sync $SCRATCH_MNT $XFS_IO_PROG -c "pwrite -S 0xdc -b 10000 250000 10000" $SCRATCH_MNT/foo $XFS_IO_PROG -c "pwrite -S 0xff -b 10000 300000 10000" $SCRATCH_MNT/foo # will be used for incremental send to be able to issue clone operations $BTRFS_UTIL_PROG subvolume snapshot -r $SCRATCH_MNT $SCRATCH_MNT/clones_snap $BTRFS_UTIL_PROG subvolume snapshot -r $SCRATCH_MNT $SCRATCH_MNT/mysnap2 $FSSUM_PROG -A -f -w $tmp/1.fssum $SCRATCH_MNT/mysnap1 $FSSUM_PROG -A -f -w $tmp/2.fssum -x $SCRATCH_MNT/mysnap2/mysnap1 \ -x $SCRATCH_MNT/mysnap2/clones_snap $SCRATCH_MNT/mysnap2 $FSSUM_PROG -A -f -w $tmp/clones.fssum $SCRATCH_MNT/clones_snap \ -x $SCRATCH_MNT/clones_snap/mysnap1 -x $SCRATCH_MNT/clones_snap/mysnap2 $BTRFS_UTIL_PROG send $SCRATCH_MNT/mysnap1 -f $tmp/1.snap $BTRFS_UTIL_PROG send $SCRATCH_MNT/clones_snap -f $tmp/clones.snap $BTRFS_UTIL_PROG send -p $SCRATCH_MNT/mysnap1 \ -c $SCRATCH_MNT/clones_snap $SCRATCH_MNT/mysnap2 -f $tmp/2.snap _scratch_unmount _scratch_mkfs _scratch_mount $BTRFS_UTIL_PROG receive $SCRATCH_MNT -f $tmp/1.snap $FSSUM_PROG -r $tmp/1.fssum $SCRATCH_MNT/mysnap1 2>> $seqres.full $BTRFS_UTIL_PROG receive $SCRATCH_MNT -f $tmp/clones.snap $FSSUM_PROG -r $tmp/clones.fssum $SCRATCH_MNT/clones_snap 2>> $seqres.full $BTRFS_UTIL_PROG receive $SCRATCH_MNT -f $tmp/2.snap $FSSUM_PROG -r $tmp/2.fssum $SCRATCH_MNT/mysnap2 2>> $seqres.full Signed-off-by: Filipe David Borba Manana Signed-off-by: Chris Mason --- fs/btrfs/send.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9c8d1a3fdc3a..9dde9717c1b9 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1332,6 +1332,16 @@ verbose_printk(KERN_DEBUG "btrfs: find_extent_clone: data_offset=%llu, " } if (cur_clone_root) { + if (compressed != BTRFS_COMPRESS_NONE) { + /* + * Offsets given by iterate_extent_inodes() are relative + * to the start of the extent, we need to add logical + * offset from the file extent item. + * (See why at backref.c:check_extent_in_eb()) + */ + cur_clone_root->offset += btrfs_file_extent_offset(eb, + fi); + } *found = cur_clone_root; ret = 0; } else { -- cgit v1.2.3-59-g8ed1b