V3: fix one missing issue in do_write_page()
V2: fix one missing issue in f2fs_invalidate_blocks()
V1: fix main error
Chao Yu (2): Revert: "f2fs: check last page index in cached bio to decide submission" f2fs: fix to truncate meta inode pages forcely
fs/f2fs/checkpoint.c | 3 +-- fs/f2fs/data.c | 41 ++++++++++++++++++++--------------------- fs/f2fs/f2fs.h | 30 ++++++++++++++++++++++++++++-- fs/f2fs/gc.c | 3 +-- fs/f2fs/node.c | 11 +++++------ fs/f2fs/segment.c | 19 ++++++++----------- include/linux/f2fs_fs.h | 1 + 7 files changed, 64 insertions(+), 44 deletions(-)
From: Chao Yu yuchao0@huawei.com
mainline inclusion from mainline-v4.20-rc1 commit bab475c5414e8d1fa182fd17ae966864e9c85741 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9HKE5 CVE: CVE-2024-26869
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
There is one case that we can leave bio in f2fs, result in hanging page writeback waiter.
Thread A Thread B - f2fs_write_cache_pages - f2fs_submit_page_write page #0 cached in bio #0 of cold log - f2fs_submit_page_write page #1 cached in bio #1 of warm log - f2fs_write_cache_pages - f2fs_submit_page_write bio is full, submit bio #1 contain page #1 - f2fs_submit_merged_write_cond(, page #1) fail to submit bio #0 due to page #1 is not in any cached bios.
Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org
Conflicts: fs/f2fs/data.c Signed-off-by: Zizhi Wo wozizhi@huawei.com --- fs/f2fs/checkpoint.c | 3 +-- fs/f2fs/data.c | 38 +++++++++++++++++++------------------- fs/f2fs/f2fs.h | 4 ++-- fs/f2fs/node.c | 11 +++++------ fs/f2fs/segment.c | 11 +++++------ 5 files changed, 32 insertions(+), 35 deletions(-)
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 388500eec729..8abd8e3283f5 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -282,8 +282,7 @@ static int __f2fs_write_meta_page(struct page *page, dec_page_count(sbi, F2FS_DIRTY_META);
if (wbc->for_reclaim) - f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, META); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, META);
unlock_page(page);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 44e8355978c7..fa683a854341 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -326,8 +326,8 @@ static void __submit_merged_bio(struct f2fs_bio_info *io) io->bio = NULL; }
-static bool __has_merged_page(struct f2fs_bio_info *io, - struct inode *inode, nid_t ino, pgoff_t idx) +static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode, + struct page *page, nid_t ino) { struct bio_vec *bvec; struct page *target; @@ -336,7 +336,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, if (!io->bio) return false;
- if (!inode && !ino) + if (!inode && !page && !ino) return true;
bio_for_each_segment_all(bvec, io->bio, i) { @@ -346,11 +346,10 @@ static bool __has_merged_page(struct f2fs_bio_info *io, else target = fscrypt_control_page(bvec->bv_page);
- if (idx != target->index) - continue; - if (inode && inode == target->mapping->host) return true; + if (page && page == target) + return true; if (ino && ino == ino_of_node(target)) return true; } @@ -359,7 +358,8 @@ static bool __has_merged_page(struct f2fs_bio_info *io, }
static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, - nid_t ino, pgoff_t idx, enum page_type type) + struct page *page, nid_t ino, + enum page_type type) { enum page_type btype = PAGE_TYPE_OF_BIO(type); enum temp_type temp; @@ -370,7 +370,7 @@ static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode, io = sbi->write_io[btype] + temp;
down_read(&io->io_rwsem); - ret = __has_merged_page(io, inode, ino, idx); + ret = __has_merged_page(io, inode, page, ino); up_read(&io->io_rwsem);
/* TODO: use HOT temp only for meta pages now. */ @@ -401,12 +401,12 @@ static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi, }
static void __submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type, bool force) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type, bool force) { enum temp_type temp;
- if (!force && !has_merged_page(sbi, inode, ino, idx, type)) + if (!force && !has_merged_page(sbi, inode, page, ino, type)) return;
for (temp = HOT; temp < NR_TEMP_TYPE; temp++) { @@ -425,10 +425,10 @@ void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type) }
void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type) + struct inode *inode, struct page *page, + nid_t ino, enum page_type type) { - __submit_merged_write_cond(sbi, inode, ino, idx, type, false); + __submit_merged_write_cond(sbi, inode, page, ino, type, false); }
void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi) @@ -1967,7 +1967,7 @@ static int __write_data_page(struct page *page, bool *submitted, }
if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, DATA); clear_inode_flag(inode, FI_HOT_DATA); f2fs_remove_dirty_inode(inode); submitted = NULL; @@ -2025,10 +2025,10 @@ static int f2fs_write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - pgoff_t last_idx = ULONG_MAX; int cycled; int range_whole = 0; int tag; + int nwritten = 0;
pagevec_init(&pvec);
@@ -2131,7 +2131,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, done = 1; break; } else if (submitted) { - last_idx = page->index; + nwritten++; }
if (--wbc->nr_to_write <= 0 && @@ -2153,9 +2153,9 @@ static int f2fs_write_cache_pages(struct address_space *mapping, if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index;
- if (last_idx != ULONG_MAX) + if (nwritten) f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host, - 0, last_idx, DATA); + NULL, 0, DATA);
return ret; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 8cbc9da523dc..6be5cb26d064 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3041,8 +3041,8 @@ int f2fs_init_post_read_processing(void); void f2fs_destroy_post_read_processing(void); void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type); void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi, - struct inode *inode, nid_t ino, pgoff_t idx, - enum page_type type); + struct inode *inode, struct page *page, + nid_t ino, enum page_type type); void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi); int f2fs_submit_page_bio(struct f2fs_io_info *fio); void f2fs_submit_page_write(struct f2fs_io_info *fio); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 748521237fa7..de4144d11e96 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1575,8 +1575,7 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, up_read(&sbi->node_write);
if (wbc->for_reclaim) { - f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, - page->index, NODE); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, NODE); submitted = NULL; }
@@ -1641,13 +1640,13 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, unsigned int *seq_id) { pgoff_t index; - pgoff_t last_idx = ULONG_MAX; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; int nr_pages; + int nwritten = 0;
if (atomic) { last_page = last_fsync_dnode(sbi, ino); @@ -1725,7 +1724,7 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, f2fs_put_page(last_page, 0); break; } else if (submitted) { - last_idx = page->index; + nwritten++; }
if (page == last_page) { @@ -1751,8 +1750,8 @@ int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, goto retry; } out: - if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); + if (nwritten) + f2fs_submit_merged_write_cond(sbi, NULL, NULL, ino, NODE); return ret ? -EIO: 0; }
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 0e3e590a250f..0fdfbbaeb386 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -392,7 +392,7 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) .io_type = FS_DATA_IO, }; struct list_head revoke_list; - pgoff_t last_idx = ULONG_MAX; + bool submit_bio = false; int err = 0;
INIT_LIST_HEAD(&revoke_list); @@ -427,14 +427,14 @@ static int __f2fs_commit_inmem_pages(struct inode *inode) } /* record old blkaddr for revoking */ cur->old_addr = fio.old_blkaddr; - last_idx = page->index; + submit_bio = true; } unlock_page(page); list_move_tail(&cur->list, &revoke_list); }
- if (last_idx != ULONG_MAX) - f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA); + if (submit_bio) + f2fs_submit_merged_write_cond(sbi, inode, NULL, 0, DATA);
if (err) { /* @@ -3209,8 +3209,7 @@ void f2fs_wait_on_page_writeback(struct page *page, if (PageWriteback(page)) { struct f2fs_sb_info *sbi = F2FS_P_SB(page);
- f2fs_submit_merged_write_cond(sbi, page->mapping->host, - 0, page->index, type); + f2fs_submit_merged_write_cond(sbi, NULL, page, 0, type); if (ordered) wait_on_page_writeback(page); else
From: Chao Yu chao@kernel.org
stable inclusion from stable-v6.6.23 commit c92f2927df860a60ba815d3ee610a944b92a8694 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9HKE5 CVE: CVE-2024-26869
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
[ Upstream commit 9f0c4a46be1fe9b97dbe66d49204c1371e3ece65 ]
Below race case can cause data corruption:
Thread A GC thread - gc_data_segment - ra_data_block - locked meta_inode page - f2fs_inplace_write_data - invalidate_mapping_pages : fail to invalidate meta_inode page due to lock failure or dirty|writeback status - f2fs_submit_page_bio : write last dirty data to old blkaddr - move_data_block - load old data from meta_inode page - f2fs_submit_page_write : write old data to new blkaddr
Because invalidate_mapping_pages() will skip invalidating page which has unclear status including locked, dirty, writeback and so on, so we need to use truncate_inode_pages_range() instead of invalidate_mapping_pages() to make sure meta_inode page will be dropped.
Fixes: 6aa58d8ad20a ("f2fs: readahead encrypted block during GC") Fixes: e3b49ea36802 ("f2fs: invalidate META_MAPPING before IPU/DIO write") Signed-off-by: Chao Yu chao@kernel.org Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org
Conflicts: fs/f2fs/data.c fs/f2fs/gc.c fs/f2fs/segment.c fs/f2fs/f2fs.h Signed-off-by: Zizhi Wo wozizhi@huawei.com --- fs/f2fs/data.c | 3 +-- fs/f2fs/f2fs.h | 26 ++++++++++++++++++++++++++ fs/f2fs/gc.c | 3 +-- fs/f2fs/segment.c | 8 +++----- include/linux/f2fs_fs.h | 1 + 5 files changed, 32 insertions(+), 9 deletions(-)
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index fa683a854341..06224270d5ce 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -914,8 +914,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, &sum, seg_type, NULL, false); if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) - invalidate_mapping_pages(META_MAPPING(sbi), - old_blkaddr, old_blkaddr); + f2fs_truncate_meta_inode_pages(sbi, old_blkaddr, 1); f2fs_set_data_blkaddr(dn);
/* diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6be5cb26d064..8e8b2d46211d 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3496,6 +3496,32 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate,
#endif
+static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int cnt) +{ + bool need_submit = false; + int i = 0; + + do { + struct page *page; + + page = find_get_page(META_MAPPING(sbi), blkaddr + i); + if (page) { + if (PageWriteback(page)) + need_submit = true; + f2fs_put_page(page, 0); + } + } while (++i < cnt && !need_submit); + + if (need_submit) + f2fs_submit_merged_write_cond(sbi, sbi->meta_inode, + NULL, 0, DATA); + + truncate_inode_pages_range(META_MAPPING(sbi), + F2FS_BLK_TO_BYTES((loff_t)blkaddr), + F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1))); +} + #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f4f7b8feebef..44781a160a29 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -759,8 +759,7 @@ static void move_data_block(struct inode *inode, block_t bidx, updated = true; } f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); + f2fs_truncate_meta_inode_pages(fio.sbi, fio.old_blkaddr, 1); if (updated) goto write_page; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 0fdfbbaeb386..2d02ac46657e 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2101,7 +2101,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) if (addr == NEW_ADDR) return;
- invalidate_mapping_pages(META_MAPPING(sbi), addr, addr); + f2fs_truncate_meta_inode_pages(sbi, addr, 1);
/* add it into sit main buffer */ down_write(&sit_i->sentry_lock); @@ -3003,8 +3003,7 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio, true); if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) - invalidate_mapping_pages(META_MAPPING(fio->sbi), - fio->old_blkaddr, fio->old_blkaddr); + f2fs_truncate_meta_inode_pages(fio->sbi, fio->old_blkaddr, 1);
/* writeout dirty page into bdev */ f2fs_submit_page_write(fio); @@ -3165,8 +3164,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, if (!recover_curseg || recover_newaddr) update_sit_entry(sbi, new_blkaddr, 1); if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { - invalidate_mapping_pages(META_MAPPING(sbi), - old_blkaddr, old_blkaddr); + f2fs_truncate_meta_inode_pages(sbi, old_blkaddr, 1); update_sit_entry(sbi, old_blkaddr, -1); }
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h index 40fec5f94949..214d4cb9df2a 100644 --- a/include/linux/f2fs_fs.h +++ b/include/linux/f2fs_fs.h @@ -29,6 +29,7 @@
#define F2FS_BYTES_TO_BLK(bytes) ((bytes) >> F2FS_BLKSIZE_BITS) #define F2FS_BLK_TO_BYTES(blk) ((blk) << F2FS_BLKSIZE_BITS) +#define F2FS_BLK_END_BYTES(blk) (F2FS_BLK_TO_BYTES(blk + 1) - 1)
/* 0, 1(node nid), 2(meta nid) are reserved node id */ #define F2FS_RESERVED_NODE_NUM 3
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitee.com/openeuler/kernel/pulls/6456 邮件列表地址：https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/Y...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/6456 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/Y...
-
patchwork bot -
Zizhi Wo