From 60eed1e3d45045623e46944ebc7c42c30a4350f0 Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Fri, 17 Feb 2023 08:37:17 +0800 Subject: ocfs2: fix defrag path triggering jbd2 ASSERT code path: ocfs2_ioctl_move_extents ocfs2_move_extents ocfs2_defrag_extent __ocfs2_move_extent + ocfs2_journal_access_di + ocfs2_split_extent //sub-paths call jbd2_journal_restart + ocfs2_journal_dirty //crash by jbs2 ASSERT crash stacks: PID: 11297 TASK: ffff974a676dcd00 CPU: 67 COMMAND: "defragfs.ocfs2" #0 [ffffb25d8dad3900] machine_kexec at ffffffff8386fe01 #1 [ffffb25d8dad3958] __crash_kexec at ffffffff8395959d #2 [ffffb25d8dad3a20] crash_kexec at ffffffff8395a45d #3 [ffffb25d8dad3a38] oops_end at ffffffff83836d3f #4 [ffffb25d8dad3a58] do_trap at ffffffff83833205 #5 [ffffb25d8dad3aa0] do_invalid_op at ffffffff83833aa6 #6 [ffffb25d8dad3ac0] invalid_op at ffffffff84200d18 [exception RIP: jbd2_journal_dirty_metadata+0x2ba] RIP: ffffffffc09ca54a RSP: ffffb25d8dad3b70 RFLAGS: 00010207 RAX: 0000000000000000 RBX: ffff9706eedc5248 RCX: 0000000000000000 RDX: 0000000000000001 RSI: ffff97337029ea28 RDI: ffff9706eedc5250 RBP: ffff9703c3520200 R8: 000000000f46b0b2 R9: 0000000000000000 R10: 0000000000000001 R11: 00000001000000fe R12: ffff97337029ea28 R13: 0000000000000000 R14: ffff9703de59bf60 R15: ffff9706eedc5250 ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018 #7 [ffffb25d8dad3ba8] ocfs2_journal_dirty at ffffffffc137fb95 [ocfs2] #8 [ffffb25d8dad3be8] __ocfs2_move_extent at ffffffffc139a950 [ocfs2] #9 [ffffb25d8dad3c80] ocfs2_defrag_extent at ffffffffc139b2d2 [ocfs2] Analysis This bug has the same root cause of 'commit 7f27ec978b0e ("ocfs2: call ocfs2_journal_access_di() before ocfs2_journal_dirty() in ocfs2_write_end_nolock()")'. For this bug, jbd2_journal_restart() is called by ocfs2_split_extent() during defragmenting. How to fix For ocfs2_split_extent() can handle journal operations totally by itself. Caller doesn't need to call journal access/dirty pair, and caller only needs to call journal start/stop pair. The fix method is to remove journal access/dirty from __ocfs2_move_extent(). The discussion for this patch: https://oss.oracle.com/pipermail/ocfs2-devel/2023-February/000647.html Link: https://lkml.kernel.org/r/20230217003717.32469-1-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton --- fs/ocfs2/move_extents.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 192cad0662d8..6251748c695b 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -105,14 +105,6 @@ static int __ocfs2_move_extent(handle_t *handle, */ replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED; - ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), - context->et.et_root_bh, - OCFS2_JOURNAL_ACCESS_WRITE); - if (ret) { - mlog_errno(ret); - goto out; - } - ret = ocfs2_split_extent(handle, &context->et, path, index, &replace_rec, context->meta_ac, &context->dealloc); @@ -121,8 +113,6 @@ static int __ocfs2_move_extent(handle_t *handle, goto out; } - ocfs2_journal_dirty(handle, context->et.et_root_bh); - context->new_phys_cpos = new_p_cpos; /* -- cgit v1.2.3 From 236b9254f8d1edc273ad88b420aa85fbd84f492d Mon Sep 17 00:00:00 2001 From: Heming Zhao via Ocfs2-devel Date: Mon, 20 Feb 2023 13:05:26 +0800 Subject: ocfs2: fix non-auto defrag path not working issue This fixes three issues on move extents ioctl without auto defrag: a) In ocfs2_find_victim_alloc_group(), we have to convert bits to block first in case of global bitmap. b) In ocfs2_probe_alloc_group(), when finding enough bits in block group bitmap, we have to back off move_len to start pos as well, otherwise it may corrupt filesystem. c) In ocfs2_ioctl_move_extents(), set me_threshold both for non-auto and auto defrag paths. Otherwise it will set move_max_hop to 0 and finally cause unexpectedly ENOSPC error. Currently there are no tools triggering the above issues since defragfs.ocfs2 enables auto defrag by default. Tested with manually changing defragfs.ocfs2 to run non auto defrag path. Link: https://lkml.kernel.org/r/20230220050526.22020-1-heming.zhao@suse.com Signed-off-by: Heming Zhao Reviewed-by: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Cc: Signed-off-by: Andrew Morton --- fs/ocfs2/move_extents.c | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 6251748c695b..b1e32ec4a9d4 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -434,7 +434,7 @@ static int ocfs2_find_victim_alloc_group(struct inode *inode, bg = (struct ocfs2_group_desc *)gd_bh->b_data; if (vict_blkno < (le64_to_cpu(bg->bg_blkno) + - le16_to_cpu(bg->bg_bits))) { + (le16_to_cpu(bg->bg_bits) << bits_per_unit))) { *ret_bh = gd_bh; *vict_bit = (vict_blkno - blkno) >> @@ -549,6 +549,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh, last_free_bits++; if (last_free_bits == move_len) { + i -= move_len; *goal_bit = i; *phys_cpos = base_cpos + i; break; @@ -1020,18 +1021,19 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) context->range = ⦥ + /* + * ok, the default theshold for the defragmentation + * is 1M, since our maximum clustersize was 1M also. + * any thought? + */ + if (!range.me_threshold) + range.me_threshold = 1024 * 1024; + + if (range.me_threshold > i_size_read(inode)) + range.me_threshold = i_size_read(inode); + if (range.me_flags & OCFS2_MOVE_EXT_FL_AUTO_DEFRAG) { context->auto_defrag = 1; - /* - * ok, the default theshold for the defragmentation - * is 1M, since our maximum clustersize was 1M also. - * any thought? - */ - if (!range.me_threshold) - range.me_threshold = 1024 * 1024; - - if (range.me_threshold > i_size_read(inode)) - range.me_threshold = i_size_read(inode); if (range.me_flags & OCFS2_MOVE_EXT_FL_PART_DEFRAG) context->partial = 1; -- cgit v1.2.3 From 07db5e247ab5858439b14dd7cc1fe538b9efcf32 Mon Sep 17 00:00:00 2001 From: Dongliang Mu Date: Sun, 26 Feb 2023 20:49:47 +0800 Subject: fs: hfsplus: fix UAF issue in hfsplus_put_super The current hfsplus_put_super first calls hfs_btree_close on sbi->ext_tree, then invokes iput on sbi->hidden_dir, resulting in an use-after-free issue in hfsplus_release_folio. As shown in hfsplus_fill_super, the error handling code also calls iput before hfs_btree_close. To fix this error, we move all iput calls before hfsplus_btree_close. Note that this patch is tested on Syzbot. Link: https://lkml.kernel.org/r/20230226124948.3175736-1-mudongliangabcd@gmail.com Reported-by: syzbot+57e3e98f7e3b80f64d56@syzkaller.appspotmail.com Tested-by: Dongliang Mu Signed-off-by: Dongliang Mu Cc: Bart Van Assche Cc: Jens Axboe Cc: Muchun Song Cc: Roman Gushchin Cc: "Theodore Ts'o" Cc: Signed-off-by: Andrew Morton --- fs/hfsplus/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 122ed89ebf9f..1986b4f18a90 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -295,11 +295,11 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + iput(sbi->alloc_file); + iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); - iput(sbi->alloc_file); - iput(sbi->hidden_dir); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); -- cgit v1.2.3 From 3e35102666f873a135d31a726ac1ec8af4905206 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sun, 26 Feb 2023 12:31:11 -0800 Subject: fs/cramfs/inode.c: initialize file_ra_state file_ra_state_init() assumes that the file_ra_state has been zeroed out. Fixes a KMSAN used-unintialized issue (at least). Fixes: cf948cbc35e80 ("cramfs: read_mapping_page() is synchronous") Reported-by: syzbot Link: https://lkml.kernel.org/r/0000000000008f74e905f56df987@google.com Cc: Matthew Wilcox Cc: Nicolas Pitre Cc: Signed-off-by: Andrew Morton --- fs/cramfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index e3d168911dbe..006ef68d7ff6 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -183,7 +183,7 @@ static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset, unsigned int len) { struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; - struct file_ra_state ra; + struct file_ra_state ra = {}; struct page *pages[BLKS_PER_BUF]; unsigned i, blocknr, buffer; unsigned long devsize; -- cgit v1.2.3