From d55cd5742835f03e5c155d865499c64c8312c1e2 Mon Sep 17 00:00:00 2001 From: piaojun Date: Wed, 31 Jan 2018 16:14:44 -0800 Subject: ocfs2: return -EROFS to mount.ocfs2 if inode block is invalid [ Upstream commit 025bcbde3634b2c9b316f227fed13ad6ad6817fb ] If metadata is corrupted such as 'invalid inode block', we will get failed by calling 'mount()' and then set filesystem readonly as below: ocfs2_mount ocfs2_initialize_super ocfs2_init_global_system_inodes ocfs2_iget ocfs2_read_locked_inode ocfs2_validate_inode_block ocfs2_error ocfs2_handle_error ocfs2_set_ro_flag(osb, 0); // set readonly In this situation we need return -EROFS to 'mount.ocfs2', so that user can fix it by fsck. And then mount again. In addition, 'mount.ocfs2' should be updated correspondingly as it only return 1 for all errno. And I will post a patch for 'mount.ocfs2' too. Link: http://lkml.kernel.org/r/5A4302FA.2010606@huawei.com Signed-off-by: Jun Piao Reviewed-by: Alex Chen Reviewed-by: Joseph Qi Reviewed-by: Changwei Ge Reviewed-by: Gang He Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/super.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs/ocfs2') diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 2de4c8a9340c..4f5141350af8 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -477,9 +477,8 @@ static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb) new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); if (!new) { ocfs2_release_system_inodes(osb); - status = -EINVAL; + status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; mlog_errno(status); - /* FIXME: Should ERROR_RO_FS */ mlog(ML_ERROR, "Unable to load system inode %d, " "possibly corrupt fs?", i); goto bail; @@ -508,7 +507,7 @@ static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb) new = ocfs2_get_system_file_inode(osb, i, osb->slot_num); if (!new) { ocfs2_release_system_inodes(osb); - status = -EINVAL; + status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL; mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n", status, i, osb->slot_num); goto bail; -- cgit v1.2.3 From b35bb8a41795caa05e09c3aacf7d78f1f20bac04 Mon Sep 17 00:00:00 2001 From: piaojun Date: Wed, 31 Jan 2018 16:14:59 -0800 Subject: ocfs2/acl: use 'ip_xattr_sem' to protect getting extended attribute [ Upstream commit 16c8d569f5704a84164f30ff01b29879f3438065 ] The race between *set_acl and *get_acl will cause getting incomplete xattr data as below: processA processB ocfs2_set_acl ocfs2_xattr_set __ocfs2_xattr_set_handle ocfs2_get_acl_nolock ocfs2_xattr_get_nolock: processB may get incomplete xattr data if processA hasn't set_acl done. So we should use 'ip_xattr_sem' to protect getting extended attribute in ocfs2_get_acl_nolock(), as other processes could be changing it concurrently. Link: http://lkml.kernel.org/r/5A5DDCFF.7030001@huawei.com Signed-off-by: Jun Piao Reviewed-by: Alex Chen Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Cc: Changwei Ge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/acl.c | 6 ++++++ fs/ocfs2/xattr.c | 2 ++ 2 files changed, 8 insertions(+) (limited to 'fs/ocfs2') diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 164307b99405..1e0d8da0d3cd 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -314,7 +314,9 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) return ERR_PTR(ret); } + down_read(&OCFS2_I(inode)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(inode, type, di_bh); + up_read(&OCFS2_I(inode)->ip_xattr_sem); ocfs2_inode_unlock(inode, 0); brelse(di_bh); @@ -333,7 +335,9 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) return 0; + down_read(&OCFS2_I(inode)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); + up_read(&OCFS2_I(inode)->ip_xattr_sem); if (IS_ERR(acl) || !acl) return PTR_ERR(acl); ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); @@ -364,8 +368,10 @@ int ocfs2_init_acl(handle_t *handle, if (!S_ISLNK(inode->i_mode)) { if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { + down_read(&OCFS2_I(dir)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT, dir_bh); + up_read(&OCFS2_I(dir)->ip_xattr_sem); if (IS_ERR(acl)) return PTR_ERR(acl); } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 877830b05e12..4f0788232f2f 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -639,9 +639,11 @@ int ocfs2_calc_xattr_init(struct inode *dir, si->value_len); if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) { + down_read(&OCFS2_I(dir)->ip_xattr_sem); acl_len = ocfs2_xattr_get_nolock(dir, dir_bh, OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT, "", NULL, 0); + up_read(&OCFS2_I(dir)->ip_xattr_sem); if (acl_len > 0) { a_size = ocfs2_xattr_entry_real_size(0, acl_len); if (S_ISDIR(mode)) -- cgit v1.2.3 From d278dc22cc79b2caadd07045d0cfd59d9c7f2411 Mon Sep 17 00:00:00 2001 From: piaojun Date: Wed, 31 Jan 2018 16:15:32 -0800 Subject: ocfs2: return error when we attempt to access a dirty bh in jbd2 [ Upstream commit d984187e3a1ad7d12447a7ab2c43ce3717a2b5b3 ] We should not reuse the dirty bh in jbd2 directly due to the following situation: 1. When removing extent rec, we will dirty the bhs of extent rec and truncate log at the same time, and hand them over to jbd2. 2. The bhs are submitted to jbd2 area successfully. 3. The write-back thread of device help flush the bhs to disk but encounter write error due to abnormal storage link. 4. After a while the storage link become normal. Truncate log flush worker triggered by the next space reclaiming found the dirty bh of truncate log and clear its 'BH_Write_EIO' and then set it uptodate in __ocfs2_journal_access(): ocfs2_truncate_log_worker ocfs2_flush_truncate_log __ocfs2_flush_truncate_log ocfs2_replay_truncate_records ocfs2_journal_access_di __ocfs2_journal_access // here we clear io_error and set 'tl_bh' uptodata. 5. Then jbd2 will flush the bh of truncate log to disk, but the bh of extent rec is still in error state, and unfortunately nobody will take care of it. 6. At last the space of extent rec was not reduced, but truncate log flush worker have given it back to globalalloc. That will cause duplicate cluster problem which could be identified by fsck.ocfs2. Sadly we can hardly revert this but set fs read-only in case of ruining atomicity and consistency of space reclaim. Link: http://lkml.kernel.org/r/5A6E8092.8090701@huawei.com Fixes: acf8fdbe6afb ("ocfs2: do not BUG if buffer not uptodate in __ocfs2_journal_access") Signed-off-by: Jun Piao Reviewed-by: Yiwen Jiang Reviewed-by: Changwei Ge Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Joseph Qi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/journal.c | 23 ++++++++++++----------- 1 file changed, 12 insertions(+), 11 deletions(-) (limited to 'fs/ocfs2') diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 13534f4fe5b5..722eb5bc9b8f 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -666,23 +666,24 @@ static int __ocfs2_journal_access(handle_t *handle, /* we can safely remove this assertion after testing. */ if (!buffer_uptodate(bh)) { mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n"); - mlog(ML_ERROR, "b_blocknr=%llu\n", - (unsigned long long)bh->b_blocknr); + mlog(ML_ERROR, "b_blocknr=%llu, b_state=0x%lx\n", + (unsigned long long)bh->b_blocknr, bh->b_state); lock_buffer(bh); /* - * A previous attempt to write this buffer head failed. - * Nothing we can do but to retry the write and hope for - * the best. + * A previous transaction with a couple of buffer heads fail + * to checkpoint, so all the bhs are marked as BH_Write_EIO. + * For current transaction, the bh is just among those error + * bhs which previous transaction handle. We can't just clear + * its BH_Write_EIO and reuse directly, since other bhs are + * not written to disk yet and that will cause metadata + * inconsistency. So we should set fs read-only to avoid + * further damage. */ if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) { - clear_buffer_write_io_error(bh); - set_buffer_uptodate(bh); - } - - if (!buffer_uptodate(bh)) { unlock_buffer(bh); - return -EIO; + return ocfs2_error(osb->sb, "A previous attempt to " + "write this buffer head failed\n"); } unlock_buffer(bh); } -- cgit v1.2.3 From 6b6933fdb14c030dd082dde9ff3b1f0db87fc62f Mon Sep 17 00:00:00 2001 From: Jun Piao Date: Thu, 5 Apr 2018 16:18:48 -0700 Subject: ocfs2/dlm: don't handle migrate lockres if already in shutdown [ Upstream commit bb34f24c7d2c98d0c81838a7700e6068325b17a0 ] We should not handle migrate lockres if we are already in 'DLM_CTXT_IN_SHUTDOWN', as that will cause lockres remains after leaving dlm domain. At last other nodes will get stuck into infinite loop when requsting lock from us. The problem is caused by concurrency umount between nodes. Before receiveing N1's DLM_BEGIN_EXIT_DOMAIN_MSG, N2 has picked up N1 as the migrate target. So N2 will continue sending lockres to N1 even though N1 has left domain. N1 N2 (owner) touch file access the file, and get pr lock begin leave domain and pick up N1 as new owner begin leave domain and migrate all lockres done begin migrate lockres to N1 end leave domain, but the lockres left unexpectedly, because migrate task has passed [piaojun@huawei.com: v3] Link: http://lkml.kernel.org/r/5A9CBD19.5020107@huawei.com Link: http://lkml.kernel.org/r/5A99F028.2090902@huawei.com Signed-off-by: Jun Piao Reviewed-by: Yiwen Jiang Reviewed-by: Joseph Qi Reviewed-by: Changwei Ge Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Greg Kroah-Hartman --- fs/ocfs2/dlm/dlmdomain.c | 14 -------------- fs/ocfs2/dlm/dlmdomain.h | 25 ++++++++++++++++++++++++- fs/ocfs2/dlm/dlmrecovery.c | 9 +++++++++ 3 files changed, 33 insertions(+), 15 deletions(-) (limited to 'fs/ocfs2') diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 2ee7fe747cea..c55a9c47ac17 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -674,20 +674,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm) spin_unlock(&dlm->spinlock); } -int dlm_shutting_down(struct dlm_ctxt *dlm) -{ - int ret = 0; - - spin_lock(&dlm_domain_lock); - - if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN) - ret = 1; - - spin_unlock(&dlm_domain_lock); - - return ret; -} - void dlm_unregister_domain(struct dlm_ctxt *dlm) { int leave = 0; diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h index fd6122a38dbd..8a9281411c18 100644 --- a/fs/ocfs2/dlm/dlmdomain.h +++ b/fs/ocfs2/dlm/dlmdomain.h @@ -28,7 +28,30 @@ extern spinlock_t dlm_domain_lock; extern struct list_head dlm_domains; -int dlm_shutting_down(struct dlm_ctxt *dlm); +static inline int dlm_joined(struct dlm_ctxt *dlm) +{ + int ret = 0; + + spin_lock(&dlm_domain_lock); + if (dlm->dlm_state == DLM_CTXT_JOINED) + ret = 1; + spin_unlock(&dlm_domain_lock); + + return ret; +} + +static inline int dlm_shutting_down(struct dlm_ctxt *dlm) +{ + int ret = 0; + + spin_lock(&dlm_domain_lock); + if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN) + ret = 1; + spin_unlock(&dlm_domain_lock); + + return ret; +} + void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm, int node_num); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 4a338803e7e9..88149b4387c2 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1377,6 +1377,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, if (!dlm_grab(dlm)) return -EINVAL; + if (!dlm_joined(dlm)) { + mlog(ML_ERROR, "Domain %s not joined! " + "lockres %.*s, master %u\n", + dlm->name, mres->lockname_len, + mres->lockname, mres->master); + dlm_put(dlm); + return -EINVAL; + } + BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION))); real_master = mres->master; -- cgit v1.2.3