August 2020 - Linux-stable-mirror

FAILED: patch "[PATCH] btrfs: add missing check for nocow and compression inode" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From f37c563bab4297024c300b05c8f48430e323809d Mon Sep 17 00:00:00 2001 From: David Sterba <dsterba(a)suse.com> Date: Fri, 10 Jul 2020 09:49:56 +0200 Subject: [PATCH] btrfs: add missing check for nocow and compression inode flags User Forza reported on IRC that some invalid combinations of file attributes are accepted by chattr. The NODATACOW and compression file flags/attributes are mutually exclusive, but they could be set by 'chattr +c +C' on an empty file. The nodatacow will be in effect because it's checked first in btrfs_run_delalloc_range. Extend the flag validation to catch the following cases: - input flags are conflicting - old and new flags are conflicting - initialize the local variable with inode flags after inode ls locked Inode attributes take precedence over mount options and are an independent setting. Nocompress would be a no-op with nodatacow, but we don't want to mix any compression-related options with nodatacow. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b4ddf51ae377..bd3511c5ca81 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -164,8 +164,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg) return 0; } -/* Check if @flags are a supported and valid set of FS_*_FL flags */ -static int check_fsflags(unsigned int flags) +/* + * Check if @flags are a supported and valid set of FS_*_FL flags and that + * the old and new flags are not conflicting + */ +static int check_fsflags(unsigned int old_flags, unsigned int flags) { if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ @@ -174,9 +177,19 @@ static int check_fsflags(unsigned int flags) FS_NOCOW_FL)) return -EOPNOTSUPP; + /* COMPR and NOCOMP on new/old are valid */ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; + if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL)) + return -EINVAL; + + /* NOCOW and compression options are mutually exclusive */ + if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + return 0; } @@ -190,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags = binode->flags; + u32 binode_flags; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -201,22 +214,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (copy_from_user(&fsflags, arg, sizeof(fsflags))) return -EFAULT; - ret = check_fsflags(fsflags); - if (ret) - return ret; - ret = mnt_want_write_file(file); if (ret) return ret; inode_lock(inode); - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); if (ret) goto out_unlock; + ret = check_fsflags(old_fsflags, fsflags); + if (ret) + goto out_unlock; + + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; else

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: add missing check for nocow and compression inode" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From f37c563bab4297024c300b05c8f48430e323809d Mon Sep 17 00:00:00 2001 From: David Sterba <dsterba(a)suse.com> Date: Fri, 10 Jul 2020 09:49:56 +0200 Subject: [PATCH] btrfs: add missing check for nocow and compression inode flags User Forza reported on IRC that some invalid combinations of file attributes are accepted by chattr. The NODATACOW and compression file flags/attributes are mutually exclusive, but they could be set by 'chattr +c +C' on an empty file. The nodatacow will be in effect because it's checked first in btrfs_run_delalloc_range. Extend the flag validation to catch the following cases: - input flags are conflicting - old and new flags are conflicting - initialize the local variable with inode flags after inode ls locked Inode attributes take precedence over mount options and are an independent setting. Nocompress would be a no-op with nodatacow, but we don't want to mix any compression-related options with nodatacow. CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index b4ddf51ae377..bd3511c5ca81 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -164,8 +164,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg) return 0; } -/* Check if @flags are a supported and valid set of FS_*_FL flags */ -static int check_fsflags(unsigned int flags) +/* + * Check if @flags are a supported and valid set of FS_*_FL flags and that + * the old and new flags are not conflicting + */ +static int check_fsflags(unsigned int old_flags, unsigned int flags) { if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \ FS_NOATIME_FL | FS_NODUMP_FL | \ @@ -174,9 +177,19 @@ static int check_fsflags(unsigned int flags) FS_NOCOW_FL)) return -EOPNOTSUPP; + /* COMPR and NOCOMP on new/old are valid */ if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL)) return -EINVAL; + if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL)) + return -EINVAL; + + /* NOCOW and compression options are mutually exclusive */ + if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL))) + return -EINVAL; + return 0; } @@ -190,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) unsigned int fsflags, old_fsflags; int ret; const char *comp = NULL; - u32 binode_flags = binode->flags; + u32 binode_flags; if (!inode_owner_or_capable(inode)) return -EPERM; @@ -201,22 +214,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) if (copy_from_user(&fsflags, arg, sizeof(fsflags))) return -EFAULT; - ret = check_fsflags(fsflags); - if (ret) - return ret; - ret = mnt_want_write_file(file); if (ret) return ret; inode_lock(inode); - fsflags = btrfs_mask_fsflags_for_type(inode, fsflags); old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags); + ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags); if (ret) goto out_unlock; + ret = check_fsflags(old_fsflags, fsflags); + if (ret) + goto out_unlock; + + binode_flags = binode->flags; if (fsflags & FS_SYNC_FL) binode_flags |= BTRFS_INODE_SYNC; else

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: move the chunk_mutex in btrfs_read_chunk_tree" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 01d01caf19ff7c537527d352d169c4368375c0a1 Mon Sep 17 00:00:00 2001 From: Josef Bacik <josef(a)toxicpanda.com> Date: Fri, 17 Jul 2020 15:12:28 -0400 Subject: [PATCH] btrfs: move the chunk_mutex in btrfs_read_chunk_tree We are currently getting this lockdep splat in btrfs/161: ====================================================== WARNING: possible circular locking dependency detected 5.8.0-rc5+ #20 Tainted: G E ------------------------------------------------------ mount/678048 is trying to acquire lock: ffff9b769f15b6e0 (&fs_devs->device_list_mutex){+.+.}-{3:3}, at: clone_fs_devices+0x4d/0x170 [btrfs] but task is already holding lock: ffff9b76abdb08d0 (&fs_info->chunk_mutex){+.+.}-{3:3}, at: btrfs_read_chunk_tree+0x6a/0x800 [btrfs] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&fs_info->chunk_mutex){+.+.}-{3:3}: __mutex_lock+0x8b/0x8f0 btrfs_init_new_device+0x2d2/0x1240 [btrfs] btrfs_ioctl+0x1de/0x2d20 [btrfs] ksys_ioctl+0x87/0xc0 __x64_sys_ioctl+0x16/0x20 do_syscall_64+0x52/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 -> #0 (&fs_devs->device_list_mutex){+.+.}-{3:3}: __lock_acquire+0x1240/0x2460 lock_acquire+0xab/0x360 __mutex_lock+0x8b/0x8f0 clone_fs_devices+0x4d/0x170 [btrfs] btrfs_read_chunk_tree+0x330/0x800 [btrfs] open_ctree+0xb7c/0x18ce [btrfs] btrfs_mount_root.cold+0x13/0xfa [btrfs] legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 fc_mount+0xe/0x40 vfs_kern_mount.part.0+0x71/0x90 btrfs_mount+0x13b/0x3e0 [btrfs] legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 do_mount+0x7de/0xb30 __x64_sys_mount+0x8e/0xd0 do_syscall_64+0x52/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&fs_info->chunk_mutex); lock(&fs_devs->device_list_mutex); lock(&fs_info->chunk_mutex); lock(&fs_devs->device_list_mutex); *** DEADLOCK *** 3 locks held by mount/678048: #0: ffff9b75ff5fb0e0 (&type->s_umount_key#63/1){+.+.}-{3:3}, at: alloc_super+0xb5/0x380 #1: ffffffffc0c2fbc8 (uuid_mutex){+.+.}-{3:3}, at: btrfs_read_chunk_tree+0x54/0x800 [btrfs] #2: ffff9b76abdb08d0 (&fs_info->chunk_mutex){+.+.}-{3:3}, at: btrfs_read_chunk_tree+0x6a/0x800 [btrfs] stack backtrace: CPU: 2 PID: 678048 Comm: mount Tainted: G E 5.8.0-rc5+ #20 Hardware name: To Be Filled By O.E.M. To Be Filled By O.E.M./890FX Deluxe5, BIOS P1.40 05/03/2011 Call Trace: dump_stack+0x96/0xd0 check_noncircular+0x162/0x180 __lock_acquire+0x1240/0x2460 ? asm_sysvec_apic_timer_interrupt+0x12/0x20 lock_acquire+0xab/0x360 ? clone_fs_devices+0x4d/0x170 [btrfs] __mutex_lock+0x8b/0x8f0 ? clone_fs_devices+0x4d/0x170 [btrfs] ? rcu_read_lock_sched_held+0x52/0x60 ? cpumask_next+0x16/0x20 ? module_assert_mutex_or_preempt+0x14/0x40 ? __module_address+0x28/0xf0 ? clone_fs_devices+0x4d/0x170 [btrfs] ? static_obj+0x4f/0x60 ? lockdep_init_map_waits+0x43/0x200 ? clone_fs_devices+0x4d/0x170 [btrfs] clone_fs_devices+0x4d/0x170 [btrfs] btrfs_read_chunk_tree+0x330/0x800 [btrfs] open_ctree+0xb7c/0x18ce [btrfs] ? super_setup_bdi_name+0x79/0xd0 btrfs_mount_root.cold+0x13/0xfa [btrfs] ? vfs_parse_fs_string+0x84/0xb0 ? rcu_read_lock_sched_held+0x52/0x60 ? kfree+0x2b5/0x310 legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 fc_mount+0xe/0x40 vfs_kern_mount.part.0+0x71/0x90 btrfs_mount+0x13b/0x3e0 [btrfs] ? cred_has_capability+0x7c/0x120 ? rcu_read_lock_sched_held+0x52/0x60 ? legacy_get_tree+0x30/0x50 legacy_get_tree+0x30/0x50 vfs_get_tree+0x28/0xc0 do_mount+0x7de/0xb30 ? memdup_user+0x4e/0x90 __x64_sys_mount+0x8e/0xd0 do_syscall_64+0x52/0xb0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 This is because btrfs_read_chunk_tree() can come upon DEV_EXTENT's and then read the device, which takes the device_list_mutex. The device_list_mutex needs to be taken before the chunk_mutex, so this is a problem. We only really need the chunk mutex around adding the chunk, so move the mutex around read_one_chunk. An argument could be made that we don't even need the chunk_mutex here as it's during mount, and we are protected by various other locks. However we already have special rules for ->device_list_mutex, and I'd rather not have another special case for ->chunk_mutex. CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Anand Jain <anand.jain(a)oracle.com> Signed-off-by: Josef Bacik <josef(a)toxicpanda.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 084b8227ea2c..d7670e2a9f39 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7077,7 +7077,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * otherwise we don't need it. */ mutex_lock(&uuid_mutex); - mutex_lock(&fs_info->chunk_mutex); /* * It is possible for mount and umount to race in such a way that @@ -7135,7 +7134,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) { struct btrfs_chunk *chunk; chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + mutex_lock(&fs_info->chunk_mutex); ret = read_one_chunk(&found_key, leaf, chunk); + mutex_unlock(&fs_info->chunk_mutex); if (ret) goto error; } @@ -7165,7 +7166,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) } ret = 0; error: - mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&uuid_mutex); btrfs_free_path(path);

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: only commit delayed items at fsync if we are logging a" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 5aa7d1a7f4a2f8ca6be1f32415e9365d026e8fa7 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Thu, 2 Jul 2020 12:32:20 +0100 Subject: [PATCH] btrfs: only commit delayed items at fsync if we are logging a directory When logging an inode we are committing its delayed items if either the inode is a directory or if it is a new inode, created in the current transaction. We need to do it for directories, since new directory indexes are stored as delayed items of the inode and when logging a directory we need to be able to access all indexes from the fs/subvolume tree in order to figure out which index ranges need to be logged. However for new inodes that are not directories, we do not need to do it because the only type of delayed item they can have is the inode item, and we are guaranteed to always log an up to date version of the inode item: *) for a full fsync we do it by committing the delayed inode and then copying the item from the fs/subvolume tree with copy_inode_items_to_log(); *) for a fast fsync we always log the inode item based on the contents of the in-memory struct btrfs_inode. We guarantee this is always done since commit e4545de5b035c7 ("Btrfs: fix fsync data loss after append write"). So stop running delayed items for a new inodes that are not directories, since that forces committing the delayed inode into the fs/subvolume tree, wasting time and adding contention to the tree when a full fsync is not required. We will only do it in case a fast fsync is needed. This patch is part of a series that has the following patches: 1/4 btrfs: only commit the delayed inode when doing a full fsync 2/4 btrfs: only commit delayed items at fsync if we are logging a directory 3/4 btrfs: stop incremening log_batch for the log root tree when syncing log 4/4 btrfs: remove no longer needed use of log_writers for the log root tree After the entire patchset applied I saw about 12% decrease on max latency reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of ram, using kvm and using a raw NVMe device directly (no intermediary fs on the host). The test was invoked like the following: mkfs.btrfs -f /dev/sdk mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk dbench -D /mnt/sdk -t 300 8 umount /mnt/dsk CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 44bbf8919883..7c325451d47f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5123,7 +5123,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, const loff_t end, struct btrfs_log_ctx *ctx) { - struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; struct btrfs_path *dst_path; struct btrfs_key min_key; @@ -5166,15 +5165,17 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, max_key.offset = (u64)-1; /* - * Only run delayed items if we are a dir or a new file. + * Only run delayed items if we are a directory. We want to make sure + * all directory indexes hit the fs/subvolume tree so we can find them + * and figure out which index ranges have to be logged. + * * Otherwise commit the delayed inode only if the full sync flag is set, * as we want to make sure an up to date version is in the subvolume * tree so copy_inode_items_to_log() / copy_items() can find it and copy * it to the log tree. For a non full sync, we always log the inode item * based on the in-memory struct btrfs_inode which is always up to date. */ - if (S_ISDIR(inode->vfs_inode.i_mode) || - inode->generation > fs_info->last_trans_committed) + if (S_ISDIR(inode->vfs_inode.i_mode)) ret = btrfs_commit_inode_delayed_items(trans, inode); else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) ret = btrfs_commit_inode_delayed_inode(inode);

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: only commit the delayed inode when doing a full fsync" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8c8648dd1f6d62aeb912deeb788b6ac33cb782e7 Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Thu, 2 Jul 2020 12:31:59 +0100 Subject: [PATCH] btrfs: only commit the delayed inode when doing a full fsync Commit 2c2c452b0cafdc ("Btrfs: fix fsync when extend references are added to an inode") forced a commit of the delayed inode when logging an inode in order to ensure we would end up logging the inode item during a full fsync. By committing the delayed inode, we updated the inode item in the fs/subvolume tree and then later when copying items from leafs modified in the current transaction into the log tree (with copy_inode_items_to_log()) we ended up copying the inode item from the fs/subvolume tree into the log tree. Logging an up to date version of the inode item is required to make sure at log replay time we get the link count fixup triggered among other things (replay xattr deletes, etc). The test case generic/040 from fstests exercises the bug which that commit fixed. However for a fast fsync we don't need to commit the delayed inode because we always log an up to date version of the inode item based on the struct btrfs_inode we have in-memory. We started doing this for fast fsyncs since commit e4545de5b035c7 ("Btrfs: fix fsync data loss after append write"). So just stop committing the delayed inode if we are doing a fast fsync, we are only wasting time and adding contention on fs/subvolume tree. This patch is part of a series that has the following patches: 1/4 btrfs: only commit the delayed inode when doing a full fsync 2/4 btrfs: only commit delayed items at fsync if we are logging a directory 3/4 btrfs: stop incremening log_batch for the log root tree when syncing log 4/4 btrfs: remove no longer needed use of log_writers for the log root tree After the entire patchset applied I saw about 12% decrease on max latency reported by dbench. The test was done on a qemu vm, with 8 cores, 16Gb of ram, using kvm and using a raw NVMe device directly (no intermediary fs on the host). The test was invoked like the following: mkfs.btrfs -f /dev/sdk mount -o ssd -o nospace_cache /dev/sdk /mnt/sdk dbench -D /mnt/sdk -t 300 8 umount /mnt/dsk CC: stable(a)vger.kernel.org # 5.4+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index df6d4e3e40b1..44bbf8919883 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5130,7 +5130,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_key max_key; struct btrfs_root *log = root->log_root; int err = 0; - int ret; + int ret = 0; bool fast_search = false; u64 ino = btrfs_ino(inode); struct extent_map_tree *em_tree = &inode->extent_tree; @@ -5167,14 +5167,16 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, /* * Only run delayed items if we are a dir or a new file. - * Otherwise commit the delayed inode only, which is needed in - * order for the log replay code to mark inodes for link count - * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items). + * Otherwise commit the delayed inode only if the full sync flag is set, + * as we want to make sure an up to date version is in the subvolume + * tree so copy_inode_items_to_log() / copy_items() can find it and copy + * it to the log tree. For a non full sync, we always log the inode item + * based on the in-memory struct btrfs_inode which is always up to date. */ if (S_ISDIR(inode->vfs_inode.i_mode) || inode->generation > fs_info->last_trans_committed) ret = btrfs_commit_inode_delayed_items(trans, inode); - else + else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags)) ret = btrfs_commit_inode_delayed_inode(inode); if (ret) {

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: preallocate anon block device at first phase of" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: [PATCH] btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+… CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4adfdfa28e53..ab34179d7cbc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir, return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..3a7c392fbcc9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6f65fff6cf50..98f7860af5e9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,6 +151,8 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; };

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: preallocate anon block device at first phase of" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: [PATCH] btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+… CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4adfdfa28e53..ab34179d7cbc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir, return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..3a7c392fbcc9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6f65fff6cf50..98f7860af5e9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,6 +151,8 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; };

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: preallocate anon block device at first phase of" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: [PATCH] btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+… CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4adfdfa28e53..ab34179d7cbc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir, return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..3a7c392fbcc9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6f65fff6cf50..98f7860af5e9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,6 +151,8 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; };

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: preallocate anon block device at first phase of" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: [PATCH] btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+… CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4adfdfa28e53..ab34179d7cbc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir, return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..3a7c392fbcc9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6f65fff6cf50..98f7860af5e9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,6 +151,8 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; };

4 years, 4 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: preallocate anon block device at first phase of" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 2dfb1e43f57dd3aeaa66f7cf05d068db2d4c8788 Mon Sep 17 00:00:00 2001 From: Qu Wenruo <wqu(a)suse.com> Date: Tue, 16 Jun 2020 10:17:36 +0800 Subject: [PATCH] btrfs: preallocate anon block device at first phase of snapshot creation [BUG] When the anonymous block device pool is exhausted, subvolume/snapshot creation fails with EMFILE (Too many files open). This has been reported by a user. The allocation happens in the second phase during transaction commit where it's only way out is to abort the transaction BTRFS: Transaction aborted (error -24) WARNING: CPU: 17 PID: 17041 at fs/btrfs/transaction.c:1576 create_pending_snapshot+0xbc4/0xd10 [btrfs] RIP: 0010:create_pending_snapshot+0xbc4/0xd10 [btrfs] Call Trace: create_pending_snapshots+0x82/0xa0 [btrfs] btrfs_commit_transaction+0x275/0x8c0 [btrfs] btrfs_mksubvol+0x4b9/0x500 [btrfs] btrfs_ioctl_snap_create_transid+0x174/0x180 [btrfs] btrfs_ioctl_snap_create_v2+0x11c/0x180 [btrfs] btrfs_ioctl+0x11a4/0x2da0 [btrfs] do_vfs_ioctl+0xa9/0x640 ksys_ioctl+0x67/0x90 __x64_sys_ioctl+0x1a/0x20 do_syscall_64+0x5a/0x110 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ---[ end trace 33f2f83f3d5250e9 ]--- BTRFS: error (device sda1) in create_pending_snapshot:1576: errno=-24 unknown BTRFS info (device sda1): forced readonly BTRFS warning (device sda1): Skipping commit of aborted transaction. BTRFS: error (device sda1) in cleanup_transaction:1831: errno=-24 unknown [CAUSE] When the global anonymous block device pool is exhausted, the following call chain will fail, and lead to transaction abort: btrfs_ioctl_snap_create_v2() |- btrfs_ioctl_snap_create_transid() |- btrfs_mksubvol() |- btrfs_commit_transaction() |- create_pending_snapshot() |- btrfs_get_fs_root() |- btrfs_init_fs_root() |- get_anon_bdev() [FIX] Although we can't enlarge the anonymous block device pool, at least we can preallocate anon_dev for subvolume/snapshot in the first phase, outside of transaction context and exactly at the moment the user calls the creation ioctl. Reported-by: Greed Rong <greedrong(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CA+UqX+NTrZ6boGnWHhSeZmEY5J76CTqmYjO2S+… CC: stable(a)vger.kernel.org # 4.4+ Signed-off-by: Qu Wenruo <wqu(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index c90edf04a9db..9b307034d32c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1391,7 +1391,12 @@ struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root, goto out; } -static int btrfs_init_fs_root(struct btrfs_root *root) +/* + * Initialize subvolume root in-memory structure + * + * @anon_dev: anonymous device to attach to the root, if zero, allocate new + */ +static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev) { int ret; unsigned int nofs_flag; @@ -1430,9 +1435,13 @@ static int btrfs_init_fs_root(struct btrfs_root *root) */ if (is_fstree(root->root_key.objectid) && btrfs_root_refs(&root->root_item) > 0) { - ret = get_anon_bdev(&root->anon_dev); - if (ret) - goto fail; + if (!anon_dev) { + ret = get_anon_bdev(&root->anon_dev); + if (ret) + goto fail; + } else { + root->anon_dev = anon_dev; + } } mutex_lock(&root->objectid_mutex); @@ -1537,8 +1546,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) } -struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, bool check_ref) +/* + * Get an in-memory reference of a root structure. + * + * For essential trees like root/extent tree, we grab it from fs_info directly. + * For subvolume trees, we check the cached filesystem roots first. If not + * found, then read it from disk and add it to cached fs roots. + * + * Caller should release the root by calling btrfs_put_root() after the usage. + * + * NOTE: Reloc and log trees can't be read by this function as they share the + * same root objectid. + * + * @objectid: root id + * @anon_dev: preallocated anonymous block device number for new roots, + * pass 0 for new allocation. + * @check_ref: whether to check root item references, If true, return -ENOENT + * for orphan roots + */ +static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev, + bool check_ref) { struct btrfs_root *root; struct btrfs_path *path; @@ -1567,6 +1595,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { + /* Shouldn't get preallocated anon_dev for cached roots */ + ASSERT(!anon_dev); if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1586,7 +1616,7 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, goto fail; } - ret = btrfs_init_fs_root(root); + ret = btrfs_init_fs_root(root, anon_dev); if (ret) goto fail; @@ -1619,6 +1649,33 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, return ERR_PTR(ret); } +/* + * Get in-memory reference of a root structure + * + * @objectid: tree objectid + * @check_ref: if set, verify that the tree exists and the item has at least + * one reference + */ +struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, bool check_ref) +{ + return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); +} + +/* + * Get in-memory reference of a root structure, created as new, optionally pass + * the anonymous block device id + * + * @objectid: tree objectid + * @anon_dev: if zero, allocate a new anonymous block device or use the + * parameter value + */ +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev) +{ + return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); +} + static int btrfs_congested_fn(void *congested_data, int bdi_bits) { struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index bf43245406c4..00dc39d47ed3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); +struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, + u64 objectid, dev_t anon_dev); void btrfs_free_fs_info(struct btrfs_fs_info *fs_info); int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4adfdfa28e53..ab34179d7cbc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -566,6 +566,7 @@ static noinline int create_subvol(struct inode *dir, struct inode *inode; int ret; int err; + dev_t anon_dev = 0; u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; @@ -578,6 +579,10 @@ static noinline int create_subvol(struct inode *dir, if (ret) goto fail_free; + ret = get_anon_bdev(&anon_dev); + if (ret < 0) + goto fail_free; + /* * Don't create subvolume whose level is not zero. Or qgroup will be * screwed up since it assumes subvolume qgroup's level to be 0. @@ -660,12 +665,15 @@ static noinline int create_subvol(struct inode *dir, goto fail; key.offset = (u64)-1; - new_root = btrfs_get_fs_root(fs_info, objectid, true); + new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); if (IS_ERR(new_root)) { + free_anon_bdev(anon_dev); ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); goto fail; } + /* Freeing will be done in btrfs_put_root() of new_root */ + anon_dev = 0; btrfs_record_root_in_trans(trans, new_root); @@ -735,6 +743,8 @@ static noinline int create_subvol(struct inode *dir, return ret; fail_free: + if (anon_dev) + free_anon_bdev(anon_dev); kfree(root_item); return ret; } @@ -762,6 +772,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (!pending_snapshot) return -ENOMEM; + ret = get_anon_bdev(&pending_snapshot->anon_dev); + if (ret < 0) + goto free_pending; pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item), GFP_KERNEL); pending_snapshot->path = btrfs_alloc_path(); @@ -823,10 +836,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, d_instantiate(dentry, inode); ret = 0; + pending_snapshot->anon_dev = 0; fail: + /* Prevent double freeing of anon_dev */ + if (ret && pending_snapshot->snap) + pending_snapshot->snap->anon_dev = 0; btrfs_put_root(pending_snapshot->snap); btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); free_pending: + if (pending_snapshot->anon_dev) + free_anon_bdev(pending_snapshot->anon_dev); kfree(pending_snapshot->root_item); btrfs_free_path(pending_snapshot->path); kfree(pending_snapshot); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index b359d4b17658..3a7c392fbcc9 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1630,7 +1630,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_fs_root(fs_info, objectid, true); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6f65fff6cf50..98f7860af5e9 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -151,6 +151,8 @@ struct btrfs_pending_snapshot { struct btrfs_block_rsv block_rsv; /* extra metadata reservation for relocation */ int error; + /* Preallocated anonymous block device number */ + dev_t anon_dev; bool readonly; struct list_head list; };

4 years, 4 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror August 2020