From 8ac932a4921a96ca52f61935dbba64ea87bbd5dc Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Sat, 29 Oct 2022 13:49:12 +0900 Subject: nilfs2: fix deadlock in nilfs_count_free_blocks() A semaphore deadlock can occur if nilfs_get_block() detects metadata corruption while locating data blocks and a superblock writeback occurs at the same time: task 1 task 2 ------ ------ * A file operation * nilfs_truncate() nilfs_get_block() down_read(rwsem A) <-- nilfs_bmap_lookup_contig() ... generic_shutdown_super() nilfs_put_super() * Prepare to write superblock * down_write(rwsem B) <-- nilfs_cleanup_super() * Detect b-tree corruption * nilfs_set_log_cursor() nilfs_bmap_convert_error() nilfs_count_free_blocks() __nilfs_error() down_read(rwsem A) <-- nilfs_set_error() down_write(rwsem B) <-- *** DEADLOCK *** Here, nilfs_get_block() readlocks rwsem A (= NILFS_MDT(dat_inode)->mi_sem) and then calls nilfs_bmap_lookup_contig(), but if it fails due to metadata corruption, __nilfs_error() is called from nilfs_bmap_convert_error() inside the lock section. Since __nilfs_error() calls nilfs_set_error() unless the filesystem is read-only and nilfs_set_error() attempts to writelock rwsem B (= nilfs->ns_sem) to write back superblock exclusively, hierarchical lock acquisition occurs in the order rwsem A -> rwsem B. Now, if another task starts updating the superblock, it may writelock rwsem B during the lock sequence above, and can deadlock trying to readlock rwsem A in nilfs_count_free_blocks(). However, there is actually no need to take rwsem A in nilfs_count_free_blocks() because it, within the lock section, only reads a single integer data on a shared struct with nilfs_sufile_get_ncleansegs(). This has been the case after commit aa474a220180 ("nilfs2: add local variable to cache the number of clean segments"), that is, even before this bug was introduced. So, this resolves the deadlock problem by just not taking the semaphore in nilfs_count_free_blocks(). Link: https://lkml.kernel.org/r/20221029044912.9139-1-konishi.ryusuke@gmail.com Fixes: e828949e5b42 ("nilfs2: call nilfs_error inside bmap routines") Signed-off-by: Ryusuke Konishi Reported-by: syzbot+45d6ce7b7ad7ef455d03@syzkaller.appspotmail.com Tested-by: Ryusuke Konishi Cc: [2.6.38+ Signed-off-by: Andrew Morton --- fs/nilfs2/the_nilfs.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/nilfs2') diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 3b4a079c9617..c8b89b4f94e0 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -690,9 +690,7 @@ int nilfs_count_free_blocks(struct the_nilfs *nilfs, sector_t *nblocks) { unsigned long ncleansegs; - down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); ncleansegs = nilfs_sufile_get_ncleansegs(nilfs->ns_sufile); - up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem); *nblocks = (sector_t)ncleansegs * nilfs->ns_blocks_per_segment; return 0; } -- cgit v1.2.3 From 8cccf05fe857a18ee26e20d11a8455a73ffd4efd Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 4 Nov 2022 23:29:59 +0900 Subject: nilfs2: fix use-after-free bug of ns_writer on remount If a nilfs2 filesystem is downgraded to read-only due to metadata corruption on disk and is remounted read/write, or if emergency read-only remount is performed, detaching a log writer and synchronizing the filesystem can be done at the same time. In these cases, use-after-free of the log writer (hereinafter nilfs->ns_writer) can happen as shown in the scenario below: Task1 Task2 -------------------------------- ------------------------------ nilfs_construct_segment nilfs_segctor_sync init_wait init_waitqueue_entry add_wait_queue schedule nilfs_remount (R/W remount case) nilfs_attach_log_writer nilfs_detach_log_writer nilfs_segctor_destroy kfree finish_wait _raw_spin_lock_irqsave __raw_spin_lock_irqsave do_raw_spin_lock debug_spin_lock_before <-- use-after-free While Task1 is sleeping, nilfs->ns_writer is freed by Task2. After Task1 waked up, Task1 accesses nilfs->ns_writer which is already freed. This scenario diagram is based on the Shigeru Yoshida's post [1]. This patch fixes the issue by not detaching nilfs->ns_writer on remount so that this UAF race doesn't happen. Along with this change, this patch also inserts a few necessary read-only checks with superblock instance where only the ns_writer pointer was used to check if the filesystem is read-only. Link: https://syzkaller.appspot.com/bug?id=79a4c002e960419ca173d55e863bd09e8112df8b Link: https://lkml.kernel.org/r/20221103141759.1836312-1-syoshida@redhat.com [1] Link: https://lkml.kernel.org/r/20221104142959.28296-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+f816fa82f8783f7a02bb@syzkaller.appspotmail.com Reported-by: Shigeru Yoshida Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 15 ++++++++------- fs/nilfs2/super.c | 2 -- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'fs/nilfs2') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index b4cebad21b48..3335ef352915 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -317,7 +317,7 @@ void nilfs_relax_pressure_in_lock(struct super_block *sb) struct the_nilfs *nilfs = sb->s_fs_info; struct nilfs_sc_info *sci = nilfs->ns_writer; - if (!sci || !sci->sc_flush_request) + if (sb_rdonly(sb) || unlikely(!sci) || !sci->sc_flush_request) return; set_bit(NILFS_SC_PRIOR_FLUSH, &sci->sc_flags); @@ -2242,7 +2242,7 @@ int nilfs_construct_segment(struct super_block *sb) struct nilfs_sc_info *sci = nilfs->ns_writer; struct nilfs_transaction_info *ti; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; /* A call inside transactions causes a deadlock. */ @@ -2280,7 +2280,7 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, struct nilfs_transaction_info ti; int err = 0; - if (!sci) + if (sb_rdonly(sb) || unlikely(!sci)) return -EROFS; nilfs_transaction_lock(sb, &ti, 0); @@ -2776,11 +2776,12 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root) if (nilfs->ns_writer) { /* - * This happens if the filesystem was remounted - * read/write after nilfs_error degenerated it into a - * read-only mount. + * This happens if the filesystem is made read-only by + * __nilfs_error or nilfs_remount and then remounted + * read/write. In these cases, reuse the existing + * writer. */ - nilfs_detach_log_writer(sb); + return 0; } nilfs->ns_writer = nilfs_segctor_new(sb, root); diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index ba108f915391..6edb6e0dd61f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1133,8 +1133,6 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data) if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb)) goto out; if (*flags & SB_RDONLY) { - /* Shutting down log writer */ - nilfs_detach_log_writer(sb); sb->s_flags |= SB_RDONLY; /* -- cgit v1.2.3 From 512c5ca01a3610ab14ff6309db363de51f1c13a6 Mon Sep 17 00:00:00 2001 From: Chen Zhongjin Date: Fri, 18 Nov 2022 14:33:04 +0800 Subject: nilfs2: fix nilfs_sufile_mark_dirty() not set segment usage as dirty When extending segments, nilfs_sufile_alloc() is called to get an unassigned segment, then mark it as dirty to avoid accidentally allocating the same segment in the future. But for some special cases such as a corrupted image it can be unreliable. If such corruption of the dirty state of the segment occurs, nilfs2 may reallocate a segment that is in use and pick the same segment for writing twice at the same time. This will cause the problem reported by syzkaller: https://syzkaller.appspot.com/bug?id=c7c4748e11ffcc367cef04f76e02e931833cbd24 This case started with segbuf1.segnum = 3, nextnum = 4 when constructed. It supposed segment 4 has already been allocated and marked as dirty. However the dirty state was corrupted and segment 4 usage was not dirty. For the first time nilfs_segctor_extend_segments() segment 4 was allocated again, which made segbuf2 and next segbuf3 had same segment 4. sb_getblk() will get same bh for segbuf2 and segbuf3, and this bh is added to both buffer lists of two segbuf. It makes the lists broken which causes NULL pointer dereference. Fix the problem by setting usage as dirty every time in nilfs_sufile_mark_dirty(), which is called during constructing current segment to be written out and before allocating next segment. [chenzhongjin@huawei.com: add lock protection per Ryusuke] Link: https://lkml.kernel.org/r/20221121091141.214703-1-chenzhongjin@huawei.com Link: https://lkml.kernel.org/r/20221118063304.140187-1-chenzhongjin@huawei.com Fixes: 9ff05123e3bf ("nilfs2: segment constructor") Signed-off-by: Chen Zhongjin Reported-by: Reported-by: Liu Shixin Acked-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/sufile.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs/nilfs2') diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index 77ff8e95421f..dc359b56fdfa 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -495,14 +495,22 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum, int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum) { struct buffer_head *bh; + void *kaddr; + struct nilfs_segment_usage *su; int ret; + down_write(&NILFS_MDT(sufile)->mi_sem); ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh); if (!ret) { mark_buffer_dirty(bh); nilfs_mdt_mark_dirty(sufile); + kaddr = kmap_atomic(bh->b_page); + su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr); + nilfs_segment_usage_set_dirty(su); + kunmap_atomic(kaddr); brelse(bh); } + up_write(&NILFS_MDT(sufile)->mi_sem); return ret; } -- cgit v1.2.3 From f0a0ccda18d6fd826d7c7e7ad48a6ed61c20f8b4 Mon Sep 17 00:00:00 2001 From: ZhangPeng Date: Sat, 19 Nov 2022 21:05:42 +0900 Subject: nilfs2: fix NULL pointer dereference in nilfs_palloc_commit_free_entry() Syzbot reported a null-ptr-deref bug: NILFS (loop0): segctord starting. Construction interval = 5 seconds, CP frequency < 30 seconds general protection fault, probably for non-canonical address 0xdffffc0000000002: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] CPU: 1 PID: 3603 Comm: segctord Not tainted 6.1.0-rc2-syzkaller-00105-gb229b6ca5abb #0 Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 10/11/2022 RIP: 0010:nilfs_palloc_commit_free_entry+0xe5/0x6b0 fs/nilfs2/alloc.c:608 Code: 00 00 00 00 fc ff df 80 3c 02 00 0f 85 cd 05 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 73 08 49 8d 7e 10 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 26 05 00 00 49 8b 46 10 be a6 00 00 00 48 c7 c7 RSP: 0018:ffffc90003dff830 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: ffff88802594e218 RCX: 000000000000000d RDX: 0000000000000002 RSI: 0000000000002000 RDI: 0000000000000010 RBP: ffff888071880222 R08: 0000000000000005 R09: 000000000000003f R10: 000000000000000d R11: 0000000000000000 R12: ffff888071880158 R13: ffff88802594e220 R14: 0000000000000000 R15: 0000000000000004 FS: 0000000000000000(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fb1c08316a8 CR3: 0000000018560000 CR4: 0000000000350ee0 Call Trace: nilfs_dat_commit_free fs/nilfs2/dat.c:114 [inline] nilfs_dat_commit_end+0x464/0x5f0 fs/nilfs2/dat.c:193 nilfs_dat_commit_update+0x26/0x40 fs/nilfs2/dat.c:236 nilfs_btree_commit_update_v+0x87/0x4a0 fs/nilfs2/btree.c:1940 nilfs_btree_commit_propagate_v fs/nilfs2/btree.c:2016 [inline] nilfs_btree_propagate_v fs/nilfs2/btree.c:2046 [inline] nilfs_btree_propagate+0xa00/0xd60 fs/nilfs2/btree.c:2088 nilfs_bmap_propagate+0x73/0x170 fs/nilfs2/bmap.c:337 nilfs_collect_file_data+0x45/0xd0 fs/nilfs2/segment.c:568 nilfs_segctor_apply_buffers+0x14a/0x470 fs/nilfs2/segment.c:1018 nilfs_segctor_scan_file+0x3f4/0x6f0 fs/nilfs2/segment.c:1067 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1197 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1503 [inline] nilfs_segctor_do_construct+0x12fc/0x6af0 fs/nilfs2/segment.c:2045 nilfs_segctor_construct+0x8e3/0xb30 fs/nilfs2/segment.c:2379 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2487 [inline] nilfs_segctor_thread+0x3c3/0xf30 fs/nilfs2/segment.c:2570 kthread+0x2e4/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 ... If DAT metadata file is corrupted on disk, there is a case where req->pr_desc_bh is NULL and blocknr is 0 at nilfs_dat_commit_end() during a b-tree operation that cascadingly updates ancestor nodes of the b-tree, because nilfs_dat_commit_alloc() for a lower level block can initialize the blocknr on the same DAT entry between nilfs_dat_prepare_end() and nilfs_dat_commit_end(). If this happens, nilfs_dat_commit_end() calls nilfs_dat_commit_free() without valid buffer heads in req->pr_desc_bh and req->pr_bitmap_bh, and causes the NULL pointer dereference above in nilfs_palloc_commit_free_entry() function, which leads to a crash. Fix this by adding a NULL check on req->pr_desc_bh and req->pr_bitmap_bh before nilfs_palloc_commit_free_entry() in nilfs_dat_commit_free(). This also calls nilfs_error() in that case to notify that there is a fatal flaw in the filesystem metadata and prevent further operations. Link: https://lkml.kernel.org/r/00000000000097c20205ebaea3d6@google.com Link: https://lkml.kernel.org/r/20221114040441.1649940-1-zhangpeng362@huawei.com Link: https://lkml.kernel.org/r/20221119120542.17204-1-konishi.ryusuke@gmail.com Signed-off-by: ZhangPeng Signed-off-by: Ryusuke Konishi Reported-by: syzbot+ebe05ee8e98f755f61d0@syzkaller.appspotmail.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/dat.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'fs/nilfs2') diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 3b55e239705f..9930fa901039 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -111,6 +111,13 @@ static void nilfs_dat_commit_free(struct inode *dat, kunmap_atomic(kaddr); nilfs_dat_commit_entry(dat, req); + + if (unlikely(req->pr_desc_bh == NULL || req->pr_bitmap_bh == NULL)) { + nilfs_error(dat->i_sb, + "state inconsistency probably due to duplicate use of vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + return; + } nilfs_palloc_commit_free_entry(dat, req); } -- cgit v1.2.3