From 5fb1beb069dcf616e88be9d330b86878a79aa4ff Mon Sep 17 00:00:00 2001 From: alex chen Date: Mon, 23 Jun 2014 13:22:07 -0700 Subject: ocfs2: should add inode into orphan dir after updating entry in ocfs2_rename() There are two files a and b in dir /mnt/ocfs2. node A node B mv a b In ocfs2_rename(), after calling ocfs2_orphan_add(), the inode of file b will be added into orphan dir. If ocfs2_update_entry() fails, ocfs2_rename return error and mv operation fails. But file b still exists in the parent dir. ocfs2_queue_orphan_scan -> ocfs2_queue_recovery_completion -> ocfs2_complete_recovery -> ocfs2_recover_orphans The inode of the file b will be put with iput(). ocfs2_evict_inode -> ocfs2_delete_inode -> ocfs2_wipe_inode -> ocfs2_remove_inode OCFS2_VALID_FL in the inode i_flags will be cleared. The file b still can be accessed on node B. ls /mnt/ocfs2 When first read the file b with ocfs2_read_inode_block(). It will validate the inode using ocfs2_validate_inode_block(). Because OCFS2_VALID_FL not set in the inode i_flags, so the file system will be readonly. So we should add inode into orphan dir after updating entry in ocfs2_rename(). Signed-off-by: alex.chen Reviewed-by: Mark Fasheh Cc: Joel Becker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/namei.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'fs/ocfs2/namei.c') diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 2060fc398445..5819bb5d6483 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -1098,6 +1098,7 @@ static int ocfs2_rename(struct inode *old_dir, struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, }; struct ocfs2_dir_lookup_result orphan_insert = { NULL, }; struct ocfs2_dir_lookup_result target_insert = { NULL, }; + bool should_add_orphan = false; /* At some point it might be nice to break this function up a * bit. */ @@ -1304,6 +1305,7 @@ static int ocfs2_rename(struct inode *old_dir, mlog_errno(status); goto bail; } + should_add_orphan = true; } } else { BUG_ON(new_dentry->d_parent->d_inode != new_dir); @@ -1348,17 +1350,6 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } - if (S_ISDIR(new_inode->i_mode) || - (ocfs2_read_links_count(newfe) == 1)) { - status = ocfs2_orphan_add(osb, handle, new_inode, - newfe_bh, orphan_name, - &orphan_insert, orphan_dir); - if (status < 0) { - mlog_errno(status); - goto bail; - } - } - /* change the dirent to point to the correct inode */ status = ocfs2_update_entry(new_dir, handle, &target_lookup_res, old_inode); @@ -1373,6 +1364,15 @@ static int ocfs2_rename(struct inode *old_dir, else ocfs2_add_links_count(newfe, -1); ocfs2_journal_dirty(handle, newfe_bh); + if (should_add_orphan) { + status = ocfs2_orphan_add(osb, handle, new_inode, + newfe_bh, orphan_name, + &orphan_insert, orphan_dir); + if (status < 0) { + mlog_errno(status); + goto bail; + } + } } else { /* if the name was not found in new_dir, add it now */ status = ocfs2_add_entry(handle, new_dentry, old_inode, -- cgit v1.2.3 From f7a14f32e7e1e7e025d88e7b4c8e3cc99770f756 Mon Sep 17 00:00:00 2001 From: Yiwen Jiang Date: Mon, 23 Jun 2014 13:22:09 -0700 Subject: ocfs2: fix a tiny race when running dirop_fileop_racer When running dirop_fileop_racer we found a dead lock case. 2 nodes, say Node A and Node B, mount the same ocfs2 volume. Create /race/16/1 in the filesystem, and let the inode number of dir 16 is less than the inode number of dir race. Node A Node B mv /race/16/1 /race/ right after Node A has got the EX mode of /race/16/, and tries to get EX mode of /race ls /race/16/ In this case, Node A has got the EX mode of /race/16/, and wants to get EX mode of /race/. Node B has got the PR mode of /race/, and wants to get the PR mode of /race/16/. Since EX and PR are mutually exclusive, dead lock happens. This patch fixes this case by locking in ancestor order before trying inode number order. Signed-off-by: Yiwen Jiang Signed-off-by: Joseph Qi Cc: Joel Becker Reviewed-by: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/namei.c | 96 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 94 insertions(+), 2 deletions(-) (limited to 'fs/ocfs2/namei.c') diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 5819bb5d6483..879f9f36b607 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -991,6 +991,65 @@ leave: return status; } +static int ocfs2_check_if_ancestor(struct ocfs2_super *osb, + u64 src_inode_no, u64 dest_inode_no) +{ + int ret = 0, i = 0; + u64 parent_inode_no = 0; + u64 child_inode_no = src_inode_no; + struct inode *child_inode; + +#define MAX_LOOKUP_TIMES 32 + while (1) { + child_inode = ocfs2_iget(osb, child_inode_no, 0, 0); + if (IS_ERR(child_inode)) { + ret = PTR_ERR(child_inode); + break; + } + + ret = ocfs2_inode_lock(child_inode, NULL, 0); + if (ret < 0) { + iput(child_inode); + if (ret != -ENOENT) + mlog_errno(ret); + break; + } + + ret = ocfs2_lookup_ino_from_name(child_inode, "..", 2, + &parent_inode_no); + ocfs2_inode_unlock(child_inode, 0); + iput(child_inode); + if (ret < 0) { + ret = -ENOENT; + break; + } + + if (parent_inode_no == dest_inode_no) { + ret = 1; + break; + } + + if (parent_inode_no == osb->root_inode->i_ino) { + ret = 0; + break; + } + + child_inode_no = parent_inode_no; + + if (++i >= MAX_LOOKUP_TIMES) { + mlog(ML_NOTICE, "max lookup times reached, filesystem " + "may have nested directories, " + "src inode: %llu, dest inode: %llu.\n", + (unsigned long long)src_inode_no, + (unsigned long long)dest_inode_no); + ret = 0; + break; + } + } + + return ret; +} + /* * The only place this should be used is rename! * if they have the same id, then the 1st one is the only one locked. @@ -1002,6 +1061,7 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, struct inode *inode2) { int status; + int inode1_is_ancestor, inode2_is_ancestor; struct ocfs2_inode_info *oi1 = OCFS2_I(inode1); struct ocfs2_inode_info *oi2 = OCFS2_I(inode2); struct buffer_head **tmpbh; @@ -1015,9 +1075,26 @@ static int ocfs2_double_lock(struct ocfs2_super *osb, if (*bh2) *bh2 = NULL; - /* we always want to lock the one with the lower lockid first. */ + /* we always want to lock the one with the lower lockid first. + * and if they are nested, we lock ancestor first */ if (oi1->ip_blkno != oi2->ip_blkno) { - if (oi1->ip_blkno < oi2->ip_blkno) { + inode1_is_ancestor = ocfs2_check_if_ancestor(osb, oi2->ip_blkno, + oi1->ip_blkno); + if (inode1_is_ancestor < 0) { + status = inode1_is_ancestor; + goto bail; + } + + inode2_is_ancestor = ocfs2_check_if_ancestor(osb, oi1->ip_blkno, + oi2->ip_blkno); + if (inode2_is_ancestor < 0) { + status = inode2_is_ancestor; + goto bail; + } + + if ((inode1_is_ancestor == 1) || + (oi1->ip_blkno < oi2->ip_blkno && + inode2_is_ancestor == 0)) { /* switch id1 and id2 around */ tmpbh = bh2; bh2 = bh1; @@ -1135,6 +1212,21 @@ static int ocfs2_rename(struct inode *old_dir, goto bail; } rename_lock = 1; + + /* here we cannot guarantee the inodes haven't just been + * changed, so check if they are nested again */ + status = ocfs2_check_if_ancestor(osb, new_dir->i_ino, + old_inode->i_ino); + if (status < 0) { + mlog_errno(status); + goto bail; + } else if (status == 1) { + status = -EPERM; + trace_ocfs2_rename_not_permitted( + (unsigned long long)old_inode->i_ino, + (unsigned long long)new_dir->i_ino); + goto bail; + } } /* if old and new are the same, this'll just do one lock. */ -- cgit v1.2.3 From 595297a8f9bc27f8f4a537fd57ed6d0a2060fb46 Mon Sep 17 00:00:00 2001 From: jiangyiwen Date: Mon, 23 Jun 2014 13:22:09 -0700 Subject: ocfs2: manually do the iput once ocfs2_add_entry failed in ocfs2_symlink and ocfs2_mknod When the call to ocfs2_add_entry() failed in ocfs2_symlink() and ocfs2_mknod(), iput() will not be called during dput(dentry) because no d_instantiate(), and this will lead to umount hung. Signed-off-by: jiangyiwen Cc: Joel Becker Reviewed-by: Mark Fasheh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/namei.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'fs/ocfs2/namei.c') diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 879f9f36b607..8add6f1030d7 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -205,6 +205,21 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) return inode; } +static void ocfs2_cleanup_add_entry_failure(struct ocfs2_super *osb, + struct dentry *dentry, struct inode *inode) +{ + struct ocfs2_dentry_lock *dl = dentry->d_fsdata; + + ocfs2_simple_drop_lockres(osb, &dl->dl_lockres); + ocfs2_lock_res_free(&dl->dl_lockres); + BUG_ON(dl->dl_count != 1); + spin_lock(&dentry_attach_lock); + dentry->d_fsdata = NULL; + spin_unlock(&dentry_attach_lock); + kfree(dl); + iput(inode); +} + static int ocfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, @@ -231,6 +246,7 @@ static int ocfs2_mknod(struct inode *dir, sigset_t oldset; int did_block_signals = 0; struct posix_acl *default_acl = NULL, *acl = NULL; + struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_mknod(dir, dentry, dentry->d_name.len, dentry->d_name.name, (unsigned long long)OCFS2_I(dir)->ip_blkno, @@ -423,6 +439,8 @@ static int ocfs2_mknod(struct inode *dir, goto leave; } + dl = dentry->d_fsdata; + status = ocfs2_add_entry(handle, dentry, inode, OCFS2_I(inode)->ip_blkno, parent_fe_bh, &lookup); @@ -469,6 +487,9 @@ leave: * ocfs2_delete_inode will mutex_lock again. */ if ((status < 0) && inode) { + if (dl) + ocfs2_cleanup_add_entry_failure(osb, dentry, inode); + OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); @@ -1734,6 +1755,7 @@ static int ocfs2_symlink(struct inode *dir, struct ocfs2_dir_lookup_result lookup = { NULL, }; sigset_t oldset; int did_block_signals = 0; + struct ocfs2_dentry_lock *dl = NULL; trace_ocfs2_symlink_begin(dir, dentry, symname, dentry->d_name.len, dentry->d_name.name); @@ -1922,6 +1944,8 @@ static int ocfs2_symlink(struct inode *dir, goto bail; } + dl = dentry->d_fsdata; + status = ocfs2_add_entry(handle, dentry, inode, le64_to_cpu(fe->i_blkno), parent_fe_bh, &lookup); @@ -1956,6 +1980,9 @@ bail: if (xattr_ac) ocfs2_free_alloc_context(xattr_ac); if ((status < 0) && inode) { + if (dl) + ocfs2_cleanup_add_entry_failure(osb, dentry, inode); + OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SKIP_ORPHAN_DIR; clear_nlink(inode); iput(inode); -- cgit v1.2.3