commit 299910dcb4525ac0274f3efa9527876315ba4f67 upstream.

After detecting file system corruption and degrading to a read-only mount, dirty folios and buffers in the page cache are cleared, and a large number of warnings are output at that time, often filling up the kernel log.

In this case, since the degrading to a read-only mount is output to the kernel log, these warnings are not very meaningful, and are rather a nuisance in system management and debugging.

The related nilfs2-specific page/folio routines have a silent argument that suppresses the warning output, but since it is not currently used meaningfully, remove both the silent argument and the warning output.

[konishi.ryusuke@gmail.com: adjusted for page/folio conversion] Link: https://lkml.kernel.org/r/20240816090128.4561-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Stable-dep-of: ca76bb226bf4 ("nilfs2: do not force clear folio if buffer is referenced") --- fs/nilfs2/inode.c | 4 ++-- fs/nilfs2/mdt.c | 6 +++--- fs/nilfs2/page.c | 20 +++----------------- fs/nilfs2/page.h | 4 ++-- 4 files changed, 10 insertions(+), 24 deletions(-)

diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 97c1beb00637..78d11e3275b3 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -162,7 +162,7 @@ static int nilfs_writepages(struct address_space *mapping, int err = 0;

if (sb_rdonly(inode->i_sb)) { - nilfs_clear_dirty_pages(mapping, false); + nilfs_clear_dirty_pages(mapping); return -EROFS; }

@@ -185,7 +185,7 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) * have dirty pages that try to be flushed in background. * So, here we simply discard this dirty page. */ - nilfs_clear_dirty_page(page, false); + nilfs_clear_dirty_page(page); unlock_page(page); return -EROFS; } diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index bd3e0f9144ff..8156d2b5ec6c 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -410,7 +410,7 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc) * have dirty pages that try to be flushed in background. * So, here we simply discard this dirty page. */ - nilfs_clear_dirty_page(page, false); + nilfs_clear_dirty_page(page); unlock_page(page); return -EROFS; } @@ -632,10 +632,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) if (mi->mi_palloc_cache) nilfs_palloc_clear_cache(inode);

- nilfs_clear_dirty_pages(inode->i_mapping, true); + nilfs_clear_dirty_pages(inode->i_mapping); nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping);

- nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true); + nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping); nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping, NILFS_I(shadow->inode)->i_assoc_inode->i_mapping);

diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index d2d6d5c761e8..93f24fa3ab10 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -354,9 +354,8 @@ void nilfs_copy_back_pages(struct address_space *dmap, /** * nilfs_clear_dirty_pages - discard dirty pages in address space * @mapping: address space with dirty pages for discarding - * @silent: suppress [true] or print [false] warning messages */ -void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) +void nilfs_clear_dirty_pages(struct address_space *mapping) { struct pagevec pvec; unsigned int i; @@ -377,7 +376,7 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) * was acquired. Skip processing in that case. */ if (likely(page->mapping == mapping)) - nilfs_clear_dirty_page(page, silent); + nilfs_clear_dirty_page(page);

unlock_page(page); } @@ -389,19 +388,11 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent) /** * nilfs_clear_dirty_page - discard dirty page * @page: dirty page that will be discarded - * @silent: suppress [true] or print [false] warning messages */ -void nilfs_clear_dirty_page(struct page *page, bool silent) +void nilfs_clear_dirty_page(struct page *page) { - struct inode *inode = page->mapping->host; - struct super_block *sb = inode->i_sb; - BUG_ON(!PageLocked(page));

- if (!silent) - nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu", - page_offset(page), inode->i_ino); - ClearPageUptodate(page); ClearPageMappedToDisk(page); ClearPageChecked(page); @@ -417,11 +408,6 @@ void nilfs_clear_dirty_page(struct page *page, bool silent) bh = head = page_buffers(page); do { lock_buffer(bh); - if (!silent) - nilfs_warn(sb, - "discard dirty block: blocknr=%llu, size=%zu", - (u64)bh->b_blocknr, bh->b_size); - set_mask_bits(&bh->b_state, clear_bits, 0); unlock_buffer(bh); } while (bh = bh->b_this_page, bh != head); diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index 62b9bb469e92..a5b9b5a457ab 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -41,8 +41,8 @@ void nilfs_page_bug(struct page *);

int nilfs_copy_dirty_pages(struct address_space *, struct address_space *); void nilfs_copy_back_pages(struct address_space *, struct address_space *); -void nilfs_clear_dirty_page(struct page *, bool); -void nilfs_clear_dirty_pages(struct address_space *, bool); +void nilfs_clear_dirty_page(struct page *page); +void nilfs_clear_dirty_pages(struct address_space *mapping); void nilfs_mapping_init(struct address_space *mapping, struct inode *inode); unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int, unsigned int);

commit ca76bb226bf47ff04c782cacbd299f12ddee1ec1 upstream.

Patch series "nilfs2: protect busy buffer heads from being force-cleared".

This series fixes the buffer head state inconsistency issues reported by syzbot that occurs when the filesystem is corrupted and falls back to read-only, and the associated buffer head use-after-free issue.

This patch (of 2):

Syzbot has reported that after nilfs2 detects filesystem corruption and falls back to read-only, inconsistencies in the buffer state may occur.

One of the inconsistencies is that when nilfs2 calls mark_buffer_dirty() to set a data or metadata buffer as dirty, but it detects that the buffer is not in the uptodate state:

WARNING: CPU: 0 PID: 6049 at fs/buffer.c:1177 mark_buffer_dirty+0x2e5/0x520 fs/buffer.c:1177 ... Call Trace: <TASK> nilfs_palloc_commit_alloc_entry+0x4b/0x160 fs/nilfs2/alloc.c:598 nilfs_ifile_create_inode+0x1dd/0x3a0 fs/nilfs2/ifile.c:73 nilfs_new_inode+0x254/0x830 fs/nilfs2/inode.c:344 nilfs_mkdir+0x10d/0x340 fs/nilfs2/namei.c:218 vfs_mkdir+0x2f9/0x4f0 fs/namei.c:4257 do_mkdirat+0x264/0x3a0 fs/namei.c:4280 __do_sys_mkdirat fs/namei.c:4295 [inline] __se_sys_mkdirat fs/namei.c:4293 [inline] __x64_sys_mkdirat+0x87/0xa0 fs/namei.c:4293 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The other is when nilfs_btree_propagate(), which propagates the dirty state to the ancestor nodes of a b-tree that point to a dirty buffer, detects that the origin buffer is not dirty, even though it should be:

WARNING: CPU: 0 PID: 5245 at fs/nilfs2/btree.c:2089 nilfs_btree_propagate+0xc79/0xdf0 fs/nilfs2/btree.c:2089 ... Call Trace: <TASK> nilfs_bmap_propagate+0x75/0x120 fs/nilfs2/bmap.c:345 nilfs_collect_file_data+0x4d/0xd0 fs/nilfs2/segment.c:587 nilfs_segctor_apply_buffers+0x184/0x340 fs/nilfs2/segment.c:1006 nilfs_segctor_scan_file+0x28c/0xa50 fs/nilfs2/segment.c:1045 nilfs_segctor_collect_blocks fs/nilfs2/segment.c:1216 [inline] nilfs_segctor_collect fs/nilfs2/segment.c:1540 [inline] nilfs_segctor_do_construct+0x1c28/0x6b90 fs/nilfs2/segment.c:2115 nilfs_segctor_construct+0x181/0x6b0 fs/nilfs2/segment.c:2479 nilfs_segctor_thread_construct fs/nilfs2/segment.c:2587 [inline] nilfs_segctor_thread+0x69e/0xe80 fs/nilfs2/segment.c:2701 kthread+0x2f0/0x390 kernel/kthread.c:389 ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244 </TASK>

Both of these issues are caused by the callbacks that handle the page/folio write requests, forcibly clear various states, including the working state of the buffers they hold, at unexpected times when they detect read-only fallback.

Fix these issues by checking if the buffer is referenced before clearing the page/folio state, and skipping the clear if it is.

[konishi.ryusuke@gmail.com: adjusted for page/folio conversion] Link: https://lkml.kernel.org/r/20250107200202.6432-1-konishi.ryusuke@gmail.com Link: https://lkml.kernel.org/r/20250107200202.6432-2-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Reported-by: syzbot+b2b14916b77acf8626d7@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=b2b14916b77acf8626d7 Reported-by: syzbot+d98fd19acd08b36ff422@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=d98fd19acd08b36ff422 Fixes: 8c26c4e2694a ("nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption") Tested-by: syzbot+b2b14916b77acf8626d7@syzkaller.appspotmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org --- fs/nilfs2/page.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-)

diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 93f24fa3ab10..ce5947cf4bd5 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -388,24 +388,44 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) /** * nilfs_clear_dirty_page - discard dirty page * @page: dirty page that will be discarded + * + * nilfs_clear_dirty_page() clears working states including dirty state for + * the page and its buffers. If the page has buffers, clear only if it is + * confirmed that none of the buffer heads are busy (none have valid + * references and none are locked). */ void nilfs_clear_dirty_page(struct page *page) { BUG_ON(!PageLocked(page));

- ClearPageUptodate(page); - ClearPageMappedToDisk(page); - ClearPageChecked(page); - if (page_has_buffers(page)) { - struct buffer_head *bh, *head; + struct buffer_head *bh, *head = page_buffers(page); const unsigned long clear_bits = (BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) | BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) | BIT(BH_Delay)); + bool busy, invalidated = false;

- bh = head = page_buffers(page); +recheck_buffers: + busy = false; + bh = head; + do { + if (atomic_read(&bh->b_count) | buffer_locked(bh)) { + busy = true; + break; + } + } while (bh = bh->b_this_page, bh != head); + + if (busy) { + if (invalidated) + return; + invalidate_bh_lrus(); + invalidated = true; + goto recheck_buffers; + } + + bh = head; do { lock_buffer(bh); set_mask_bits(&bh->b_state, clear_bits, 0); @@ -413,6 +433,9 @@ void nilfs_clear_dirty_page(struct page *page) } while (bh = bh->b_this_page, bh != head); }

+ ClearPageUptodate(page); + ClearPageMappedToDisk(page); + ClearPageChecked(page); __nilfs_clear_page_dirty(page); }