From 6be49d100c22ffea3287a4b19d7639d259888e33 Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 28 Mar 2023 02:53:18 +0900 Subject: nilfs2: fix potential UAF of struct nilfs_sc_info in nilfs_segctor_thread() The finalization of nilfs_segctor_thread() can race with nilfs_segctor_kill_thread() which terminates that thread, potentially causing a use-after-free BUG as KASAN detected. At the end of nilfs_segctor_thread(), it assigns NULL to "sc_task" member of "struct nilfs_sc_info" to indicate the thread has finished, and then notifies nilfs_segctor_kill_thread() of this using waitqueue "sc_wait_task" on the struct nilfs_sc_info. However, here, immediately after the NULL assignment to "sc_task", it is possible that nilfs_segctor_kill_thread() will detect it and return to continue the deallocation, freeing the nilfs_sc_info structure before the thread does the notification. This fixes the issue by protecting the NULL assignment to "sc_task" and its notification, with spinlock "sc_state_lock" of the struct nilfs_sc_info. Since nilfs_segctor_kill_thread() does a final check to see if "sc_task" is NULL with "sc_state_lock" locked, this can eliminate the race. Link: https://lkml.kernel.org/r/20230327175318.8060-1-konishi.ryusuke@gmail.com Reported-by: syzbot+b08ebcc22f8f3e6be43a@syzkaller.appspotmail.com Link: https://lkml.kernel.org/r/00000000000000660d05f7dfa877@google.com Signed-off-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'fs/nilfs2/segment.c') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 19446a8243d7..6ad41390fa74 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2609,11 +2609,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } -- cgit From ef832747a82dfbc22a3702219cc716f449b24e4a Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Tue, 18 Apr 2023 02:35:13 +0900 Subject: nilfs2: initialize unused bytes in segment summary blocks Syzbot still reports uninit-value in nilfs_add_checksums_on_logs() for KMSAN enabled kernels after applying commit 7397031622e0 ("nilfs2: initialize "struct nilfs_binfo_dat"->bi_pad field"). This is because the unused bytes at the end of each block in segment summaries are not initialized. So this fixes the issue by padding the unused bytes with null bytes. Link: https://lkml.kernel.org/r/20230417173513.12598-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+048585f3f4227bb2b49b@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=048585f3f4227bb2b49b Cc: Alexander Potapenko Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'fs/nilfs2/segment.c') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 6ad41390fa74..228659612c0d 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -430,6 +430,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -438,6 +455,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -542,6 +560,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -1533,6 +1552,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; -- cgit From 28a65b49eb53e172d23567005465019658bfdb4d Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Thu, 27 Apr 2023 10:15:26 +0900 Subject: nilfs2: do not write dirty data after degenerating to read-only According to syzbot's report, mark_buffer_dirty() called from nilfs_segctor_do_construct() outputs a warning with some patterns after nilfs2 detects metadata corruption and degrades to read-only mode. After such read-only degeneration, page cache data may be cleared through nilfs_clear_dirty_page() which may also clear the uptodate flag for their buffer heads. However, even after the degeneration, log writes are still performed by unmount processing etc., which causes mark_buffer_dirty() to be called for buffer heads without the "uptodate" flag and causes the warning. Since any writes should not be done to a read-only file system in the first place, this fixes the warning in mark_buffer_dirty() by letting nilfs_segctor_do_construct() abort early if in read-only mode. This also changes the retry check of nilfs_segctor_write_out() to avoid unnecessary log write retries if it detects -EROFS that nilfs_segctor_do_construct() returned. Link: https://lkml.kernel.org/r/20230427011526.13457-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Tested-by: Ryusuke Konishi Reported-by: syzbot+2af3bc9585be7f23f290@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=2af3bc9585be7f23f290 Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segment.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/nilfs2/segment.c') diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 228659612c0d..ac949fd7603f 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2041,6 +2041,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode) struct the_nilfs *nilfs = sci->sc_super->s_fs_info; int err; + if (sb_rdonly(sci->sc_super)) + return -EROFS; + nilfs_sc_cstage_set(sci, NILFS_ST_INIT); sci->sc_cno = nilfs->ns_cno; @@ -2724,7 +2727,7 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci) flush_work(&sci->sc_iput_work); - } while (ret && retrycount-- > 0); + } while (ret && ret != -EROFS && retrycount-- > 0); } /** -- cgit From 679bd7ebdd315bf457a4740b306ae99f1d0a403d Mon Sep 17 00:00:00 2001 From: Ryusuke Konishi Date: Fri, 9 Jun 2023 12:57:32 +0900 Subject: nilfs2: fix buffer corruption due to concurrent device reads As a result of analysis of a syzbot report, it turned out that in three cases where nilfs2 allocates block device buffers directly via sb_getblk, concurrent reads to the device can corrupt the allocated buffers. Nilfs2 uses sb_getblk for segment summary blocks, that make up a log header, and the super root block, that is the trailer, and when moving and writing the second super block after fs resize. In any of these, since the uptodate flag is not set when storing metadata to be written in the allocated buffers, the stored metadata will be overwritten if a device read of the same block occurs concurrently before the write. This causes metadata corruption and misbehavior in the log write itself, causing warnings in nilfs_btree_assign() as reported. Fix these issues by setting an uptodate flag on the buffer head on the first or before modifying each buffer obtained with sb_getblk, and clearing the flag on failure. When setting the uptodate flag, the lock_buffer/unlock_buffer pair is used to perform necessary exclusive control, and the buffer is filled to ensure that uninitialized bytes are not mixed into the data read from others. As for buffers for segment summary blocks, they are filled incrementally, so if the uptodate flag was unset on their allocation, set the flag and zero fill the buffer once at that point. Also, regarding the superblock move routine, the starting point of the memset call to zerofill the block is incorrectly specified, which can cause a buffer overflow on file systems with block sizes greater than 4KiB. In addition, if the superblock is moved within a large block, it is necessary to assume the possibility that the data in the superblock will be destroyed by zero-filling before copying. So fix these potential issues as well. Link: https://lkml.kernel.org/r/20230609035732.20426-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi Reported-by: syzbot+31837fe952932efc8fb9@syzkaller.appspotmail.com Closes: https://lkml.kernel.org/r/00000000000030000a05e981f475@google.com Tested-by: Ryusuke Konishi Cc: Signed-off-by: Andrew Morton --- fs/nilfs2/segbuf.c | 6 ++++++ fs/nilfs2/segment.c | 7 +++++++ fs/nilfs2/super.c | 23 ++++++++++++++++++++++- 3 files changed, 35 insertions(+), 1 deletion(-) (limited to 'fs/nilfs2/segment.c') diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1362ccb64ec7..6e59dc19a732 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf) if (unlikely(!bh)) return -ENOMEM; + lock_buffer(bh); + if (!buffer_uptodate(bh)) { + memset(bh->b_data, 0, bh->b_size); + set_buffer_uptodate(bh); + } + unlock_buffer(bh); nilfs_segbuf_add_segsum_buffer(segbuf, bh); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index ac949fd7603f..c2553024bd25 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -981,10 +981,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, unsigned int isz, srsz; bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root; + + lock_buffer(bh_sr); raw_sr = (struct nilfs_super_root *)bh_sr->b_data; isz = nilfs->ns_inode_size; srsz = NILFS_SR_BYTES(isz); + raw_sr->sr_sum = 0; /* Ensure initialization within this update */ raw_sr->sr_bytes = cpu_to_le16(srsz); raw_sr->sr_nongc_ctime = cpu_to_le64(nilfs_doing_gc() ? @@ -998,6 +1001,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci, nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr + NILFS_SR_SUFILE_OFFSET(isz), 1); memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz); + set_buffer_uptodate(bh_sr); + unlock_buffer(bh_sr); } static void nilfs_redirty_inodes(struct list_head *head) @@ -1780,6 +1785,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(segbuf, logs, sb_list) { list_for_each_entry(bh, &segbuf->sb_segsum_buffers, b_assoc_buffers) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { if (bd_page) end_page_writeback(bd_page); @@ -1791,6 +1797,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) b_assoc_buffers) { clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { + clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 77f1e5778d1c..9ba4933087af 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off) goto out; } nsbp = (void *)nsbh->b_data + offset; - memset(nsbp, 0, nilfs->ns_blocksize); + lock_buffer(nsbh); if (sb2i >= 0) { + /* + * The position of the second superblock only changes by 4KiB, + * which is larger than the maximum superblock data size + * (= 1KiB), so there is no need to use memmove() to allow + * overlap between source and destination. + */ memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize); + + /* + * Zero fill after copy to avoid overwriting in case of move + * within the same block. + */ + memset(nsbh->b_data, 0, offset); + memset((void *)nsbp + nilfs->ns_sbsize, 0, + nsbh->b_size - offset - nilfs->ns_sbsize); + } else { + memset(nsbh->b_data, 0, nsbh->b_size); + } + set_buffer_uptodate(nsbh); + unlock_buffer(nsbh); + + if (sb2i >= 0) { brelse(nilfs->ns_sbh[sb2i]); nilfs->ns_sbh[sb2i] = nsbh; nilfs->ns_sbp[sb2i] = nsbp; -- cgit