summaryrefslogtreecommitdiffstats
path: root/fs
Commit message (Collapse)AuthorAgeFilesLines
* f2fs: fix to avoid GC/mmap race with f2fs_truncate()Chao Yu2021-04-061-1/+6
| | | | | | | | | It missed to hold i_gc_rwsem and i_map_sem around f2fs_truncate() in f2fs_file_write_iter() to avoid racing with background GC and mmap, fix it. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: set checkpoint_merge by defaultJaegeuk Kim2021-04-011-0/+1
| | | | | | | | Once we introduced checkpoint_merge, we've seen some contention w/o the option. In order to avoid it, let's set it by default. Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: Fix a hungtask problem in atomic writeYi Zhuang2021-03-311-13/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In the cache writing process, if it is an atomic file, increase the page count of F2FS_WB_CP_DATA, otherwise increase the page count of F2FS_WB_DATA. When you step into the hook branch due to insufficient memory in f2fs_write_begin, f2fs_drop_inmem_pages_all will be called to traverse all atomic inodes and clear the FI_ATOMIC_FILE mark of all atomic files. In f2fs_drop_inmem_pages，first acquire the inmem_lock , revoke all the inmem_pages, and then clear the FI_ATOMIC_FILE mark. Before this mark is cleared, other threads may hold inmem_lock to add inmem_pages to the inode that has just been emptied inmem_pages, and increase the page count of F2FS_WB_CP_DATA. When the IO returns, it is found that the FI_ATOMIC_FILE flag is cleared by f2fs_drop_inmem_pages_all, and f2fs_is_atomic_file returns false,which causes the page count of F2FS_WB_DATA to be decremented. The page count of F2FS_WB_CP_DATA cannot be cleared. Finally, hungtask is triggered in f2fs_wait_on_all_pages because get_pages will never return zero. process A: process B: f2fs_drop_inmem_pages_all ->f2fs_drop_inmem_pages of inode#1 ->mutex_lock(&fi->inmem_lock) ->__revoke_inmem_pages of inode#1 f2fs_ioc_commit_atomic_write ->mutex_unlock(&fi->inmem_lock) ->f2fs_commit_inmem_pages of inode#1 ->mutex_lock(&fi->inmem_lock) ->__f2fs_commit_inmem_pages ->f2fs_do_write_data_page ->f2fs_outplace_write_data ->do_write_page ->f2fs_submit_page_write ->inc_page_count(sbi, F2FS_WB_CP_DATA ) ->mutex_unlock(&fi->inmem_lock) ->spin_lock(&sbi->inode_lock[ATOMIC_FILE]); ->clear_inode_flag(inode, FI_ATOMIC_FILE) ->spin_unlock(&sbi->inode_lock[ATOMIC_FILE]) f2fs_write_end_io ->dec_page_count(sbi, F2FS_WB_DATA ); We can fix the problem by putting the action of clearing the FI_ATOMIC_FILE mark into the inmem_lock lock. This operation can ensure that no one will submit the inmem pages before the FI_ATOMIC_FILE mark is cleared, so that there will be no atomic writes waiting for writeback. Fixes: 57864ae5ce3a ("f2fs: limit # of inmemory pages") Signed-off-by: Yi Zhuang <zhuangyi1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to restrict mount condition on readonly block deviceChao Yu2021-03-301-4/+12
| | | | | | | | | | | When we mount an unclean f2fs image in a readonly block device, let's make mount() succeed only when there is no recoverable data in that image, otherwise after mount(), file fsyned won't be recovered as user expected. Fixes: 938a184265d7 ("f2fs: give a warning only for readonly partition") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: introduce gc_merge mount optionChao Yu2021-03-305-8/+59
| | | | | | | | | | | | | | | In this patch, we will add two new mount options: "gc_merge" and "nogc_merge", when background_gc is on, "gc_merge" option can be set to let background GC thread to handle foreground GC requests, it can eliminate the sluggish issue caused by slow foreground GC operation when GC is triggered from a process with limited I/O and CPU resources. Original idea is from Xiang. Signed-off-by: Gao Xiang <xiang@kernel.org> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to cover __allocate_new_section() with curseg_lockChao Yu2021-03-261-0/+4
| | | | | | | | In order to avoid race with f2fs_do_replace_block(). Fixes: f5a53edcf01e ("f2fs: support aligned pinned file") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix wrong alloc_type in f2fs_do_replace_blockWang Xiaojun2021-03-261-0/+3
| | | | | | | | | | If the alloc_type of the original curseg is LFS, when we change_curseg and then do recover curseg, the alloc_type becomes SSR. Signed-off-by: Wang Xiaojun <wangxiaojun11@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: delete empty compress.hChao Yu2021-03-261-0/+0
| | | | | | | | Commit 75e91c888989 ("f2fs: compress: fix compression chksum") wrongly introduced empty compress.h, delete it. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix a typo in inode.cRuiqi Gong2021-03-261-1/+1
| | | | | | | | | | Do a trivial typo fix. s/runing/running Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: Ruiqi Gong <gongruiqi1@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: allow to change discard policy based on cached discard cmdsSahitya Tummala2021-03-263-1/+11
| | | | | | | | | | | | | With the default DPOLICY_BG discard thread is ioaware, which prevents the discard thread from issuing the discard commands. On low RAM setups, it is observed that these discard commands in the cache are consuming high memory. This patch aims to relax the memory pressure on the system due to f2fs pending discard cmds by changing the policy to DPOLICY_FORCE based on the nm_i->ram_thresh configured. Signed-off-by: Sahitya Tummala <stummala@codeaurora.org> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to avoid touching checkpointed data in get_victim()Chao Yu2021-03-264-24/+55
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In CP disabling mode, there are two issues when using LFS or SSR | AT_SSR mode to select victim: 1. LFS is set to find source section during GC, the victim should have no checkpointed data, since after GC, section could not be set free for reuse. Previously, we only check valid chpt blocks in current segment rather than section, fix it. 2. SSR | AT_SSR are set to find target segment for writes which can be fully filled by checkpointed and newly written blocks, we should never select such segment, otherwise it can cause panic or data corruption during allocation, potential case is described as below: a) target segment has 'n' (n < 512) ckpt valid blocks b) GC migrates 'n' valid blocks to other segment (segment is still in dirty list) c) GC migrates '512 - n' blocks to target segment (segment has 'n' cp_vblocks and '512 - n' vblocks) d) If GC selects target segment via {AT,}SSR allocator, however there is no free space in targe segment. Fixes: 4354994f097d ("f2fs: checkpoint disabling") Fixes: 093749e296e2 ("f2fs: support age threshold based garbage collection") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to update last i_size if fallocate partially succeedsChao Yu2021-03-251-11/+11
| | | | | | | | | | | In the case of expanding pinned file, map.m_lblk and map.m_len will update in each round of section allocation, so in error path, last i_size will be calculated with wrong m_lblk and m_len, fix it. Fixes: f5a53edcf01e ("f2fs: support aligned pinned file") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix error path of f2fs_remount()Chao Yu2021-03-251-13/+34
| | | | | | | | | | | | | | | In error path of f2fs_remount(), it missed to restart/stop kernel thread or enable/disable checkpoint, then mount option status may not be consistent with real condition of filesystem, so let's reorder remount flow a bit as below and do recovery correctly in error path: 1) handle gc thread 2) handle ckpt thread 3) handle flush thread 4) handle checkpoint disabling Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix wrong comment of nat_tree_lockqiulaibin2021-03-251-1/+1
| | | | | | | | Do trivial comment fix of nat_tree_lock. Signed-off-by: qiulaibin <qiulaibin@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to avoid out-of-bounds memory accessChao Yu2021-03-251-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | butt3rflyh4ck <butterflyhuangxx@gmail.com> reported a bug found by syzkaller fuzzer with custom modifications in 5.12.0-rc3+ [1]: dump_stack+0xfa/0x151 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x82/0x32c mm/kasan/report.c:232 __kasan_report mm/kasan/report.c:399 [inline] kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416 f2fs_test_bit fs/f2fs/f2fs.h:2572 [inline] current_nat_addr fs/f2fs/node.h:213 [inline] get_next_nat_page fs/f2fs/node.c:123 [inline] __flush_nat_entry_set fs/f2fs/node.c:2888 [inline] f2fs_flush_nat_entries+0x258e/0x2960 fs/f2fs/node.c:2991 f2fs_write_checkpoint+0x1372/0x6a70 fs/f2fs/checkpoint.c:1640 f2fs_issue_checkpoint+0x149/0x410 fs/f2fs/checkpoint.c:1807 f2fs_sync_fs+0x20f/0x420 fs/f2fs/super.c:1454 __sync_filesystem fs/sync.c:39 [inline] sync_filesystem fs/sync.c:67 [inline] sync_filesystem+0x1b5/0x260 fs/sync.c:48 generic_shutdown_super+0x70/0x370 fs/super.c:448 kill_block_super+0x97/0xf0 fs/super.c:1394 The root cause is, if nat entry in checkpoint journal area is corrupted, e.g. nid of journalled nat entry exceeds max nid value, during checkpoint, once it tries to flush nat journal to NAT area, get_next_nat_page() may access out-of-bounds memory on nat_bitmap due to it uses wrong nid value as bitmap offset. [1] https://lore.kernel.org/lkml/CAFcO6XOMWdr8pObek6eN6-fs58KG9doRFadgJj-FnF-1x43s2g@mail.gmail.com/T/#u Reported-and-tested-by: butt3rflyh4ck <butterflyhuangxx@gmail.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: don't start checkpoint thread in readonly mountpointChao Yu2021-03-251-5/+5
| | | | | | | | In readonly mountpoint, there should be no write IOs include checkpoint IO, so that it's not needed to create kernel checkpoint thread. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: do not use AT_SSR mode in FG_GC & high urgent BG_GCWeichao Guo2021-03-252-2/+5
| | | | | | | | | | | | | AT_SSR mode is introduced by age threshold based GC for better hot/cold data seperation and avoiding free segment cost. However, LFS write mode is preferred in the scenario of foreground or high urgent GC, which should be finished ASAP. Let's only use AT_SSR in background GC and not high urgent GC modes. Signed-off-by: Weichao Guo <guoweichao@oppo.com> Signed-off-by: Huang Jianan <huangjianan@oppo.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: add sysfs nodes to get runtime compression statDaeho Jeong2021-03-253-0/+58
| | | | | | | | | | I've added new sysfs nodes to show runtime compression stat since mount. compr_written_block - show the block count written after compression compr_saved_block - show the saved block count with compression compr_new_inode - show the count of inode newly enabled for compression Signed-off-by: Daeho Jeong <daehojeong@google.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to use per-inode maxbytes in f2fs_fiemapChengguang Xu2021-03-251-0/+10
| | | | | | | | | F2FS inode may have different max size, so change to use per-inode maxbytes. Signed-off-by: Chengguang Xu <cgxu519@mykernel.net> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to align to section for fallocate() on pinned fileChao Yu2021-03-233-19/+36
| | | | | | | | | | | | | | | Now, fallocate() on a pinned file only allocates blocks which aligns to segment rather than section, so GC may try to migrate pinned file's block, and after several times of failure, pinned file's block could be migrated to other place, however user won't be aware of such condition, and then old obsolete block address may be readed/written incorrectly. To avoid such condition, let's try to allocate pinned file's blocks with section alignment. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: expose # of overprivision segmentsJaegeuk Kim2021-03-121-0/+9
| | | | | | | This is useful when checking conditions during checkpoint=disable in Android. Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix error handling in f2fs_end_enable_verity()Eric Biggers2021-03-121-21/+54
| | | | | | | | | | | | | | | | | | | | | | | | | f2fs didn't properly clean up if verity failed to be enabled on a file: - It left verity metadata (pages past EOF) in the page cache, which would be exposed to userspace if the file was later extended. - It didn't truncate the verity metadata at all (either from cache or from disk) if an error occurred while setting the verity bit. Fix these bugs by adding a call to truncate_inode_pages() and ensuring that we truncate the verity metadata (both from cache and from disk) in all error paths. Also rework the code to cleanly separate the success path from the error paths, which makes it much easier to understand. Finally, log a message if f2fs_truncate() fails, since it might otherwise fail silently. Reported-by: Yunlei He <heyunlei@hihonor.com> Fixes: 95ae251fe828 ("f2fs: add fs-verity support") Cc: <stable@vger.kernel.org> # v5.4+ Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix a redundant call to f2fs_balance_fs if an error occursColin Ian King2021-03-121-1/+2
| | | | | | | | | | | | | | | | | The uninitialized variable dn.node_changed does not get set when a call to f2fs_get_node_page fails. This uninitialized value gets used in the call to f2fs_balance_fs() that may or not may not balances dirty node and dentry pages depending on the uninitialized state of the variable. Fix this by only calling f2fs_balance_fs if err is not set. Thanks to Jaegeuk Kim for suggesting an appropriate fix. Addresses-Coverity: ("Uninitialized scalar variable") Fixes: 2a3407607028 ("f2fs: call f2fs_balance_fs only when node was changed") Signed-off-by: Colin Ian King <colin.king@canonical.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: remove unused file_clear_encrypt()Chao Yu2021-03-121-3/+8
| | | | | | | | - file_clear_encrypt() was never be used, remove it. - In addition, relocating macros for cleanup. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: check if swapfile is section-allignedhuangjianan@oppo.com2021-03-121-21/+88
| | | | | | | | | | | | | If the swapfile isn't created by pin and fallocate, it can't be guaranteed section-aligned, so it may be selected by f2fs gc. When gc_pin_file_threshold is reached, the address of swapfile may change, but won't be synchronized to swap_extent, so swap will write to wrong address, which will cause data corruption. Signed-off-by: Huang Jianan <huangjianan@oppo.com> Signed-off-by: Guo Weichao <guoweichao@oppo.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix last_lblock check in check_swap_activate_fasthuangjianan@oppo.com2021-03-121-1/+1
| | | | | | | | | | Because page_no < sis->max guarantees that the while loop break out normally, the wrong check contidion here doesn't cause a problem. Signed-off-by: Huang Jianan <huangjianan@oppo.com> Signed-off-by: Guo Weichao <guoweichao@oppo.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: remove unnecessary IS_SWAPFILE checkhuangjianan@oppo.com2021-03-122-3/+2
| | | | | | | | | | | Now swapfile in f2fs directly submit IO to blockdev according to swapfile extents reported by f2fs when swapon, therefore there is no need to check IS_SWAPFILE when exec filesystem operation. Signed-off-by: Huang Jianan <huangjianan@oppo.com> Signed-off-by: Guo Weichao <guoweichao@oppo.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: Replace one-element array with flexible-array memberGustavo A. R. Silva2021-03-121-2/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use “flexible array members”[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. Refactor the code according to the use of a flexible-array member in struct f2fs_checkpoint, instead of a one-element arrays. Notice that a temporary pointer to void '*tmp_ptr' was used in order to fix the following errors when using a flexible array instead of a one element array in struct f2fs_checkpoint: CC [M] fs/f2fs/dir.o In file included from fs/f2fs/dir.c:13: fs/f2fs/f2fs.h: In function ‘__bitmap_ptr’: fs/f2fs/f2fs.h:2227:40: error: invalid use of flexible array member 2227 | return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32); | ^ fs/f2fs/f2fs.h:2227:49: error: invalid use of flexible array member 2227 | return &ckpt->sit_nat_version_bitmap + offset + sizeof(__le32); | ^ fs/f2fs/f2fs.h:2238:40: error: invalid use of flexible array member 2238 | return &ckpt->sit_nat_version_bitmap + offset; | ^ make[2]: *** [scripts/Makefile.build:287: fs/f2fs/dir.o] Error 1 make[1]: *** [scripts/Makefile.build:530: fs/f2fs] Error 2 make: *** [Makefile:1819: fs] Error 2 [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.9/process/deprecated.html#zero-length-and-one-element-arrays Link: https://github.com/KSPP/linux/issues/79 Build-tested-by: kernel test robot <lkp@intel.com> Link: https://lore.kernel.org/lkml/603647e4.DeEFbl4eqljuwAUe%25lkp@intel.com/ Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: compress: Allow modular (de)compression algorithmsGeert Uytterhoeven2021-03-121-9/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If F2FS_FS is modular, enabling the compressions options F2FS_FS_{LZ4,LZ4HZ,LZO,LZORLE,ZSTD} will make the (de)compression algorithms {LZ4,LZ4HC,LZO,ZSTD}_{,DE}COMPRESS builtin instead of modular, as the former depend on an intermediate boolean F2FS_FS_COMPRESSION, which in-turn depends on tristate F2FS_FS. Indeed, if a boolean symbol A depends directly on a tristate symbol B and selects another tristate symbol C: tristate B tristate C bool A depends on B select C and B is modular, then C will also be modular. However, if there is an intermediate boolean D in the dependency chain between A and B: tristate B tristate C bool D depends on B bool A depends on D select C then the modular state won't propagate from B to C, and C will be builtin instead of modular. As modular dependency propagation through intermediate symbols is obscure, fix this in a robust way by moving the selection of tristate (de)compression algorithms from the boolean compression options to the tristate main F2FS_FS option. Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org> Reviewed-by: Chao Yu <yuchao0@huawei.com> Reviewed-by: Masahiro Yamada <masahiroy@kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: check discard command number before traversing discard pending listChao Yu2021-03-121-0/+2
| | | | | | | | | In trim thread, let's add a condition to check discard command number before traversing discard pending list, it can avoid unneeded traversing if there is no discard command. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: update comments for explicit memory barrierChao Yu2021-03-122-2/+10
| | | | | | | | Add more detailed comments for explicit memory barrier used by f2fs, in order to enhance code readability. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: remove unused FORCE_FG_GC macroChao Yu2021-03-121-2/+0
| | | | | | | | FORCE_FG_GC was introduced by commit 6aefd93b0137 ("f2fs: introduce background_gc=sync mount option"), but never be used, remove it. Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: avoid unused f2fs_show_compress_options()Chao Yu2021-03-121-0/+2
| | | | | | | | | | | | | | | LKP reports: fs/f2fs/super.c:1516:20: warning: unused function 'f2fs_show_compress_options' [-Wunused-function] static inline void f2fs_show_compress_options(struct seq_file *seq, Fix this issue by covering f2fs_show_compress_options() with CONFIG_F2FS_FS_COMPRESSION macro. Fixes: 4c8ff7095bef ("f2fs: support data compression") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix panic during f2fs_resize_fs()Chao Yu2021-03-121-0/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | f2fs_resize_fs() hangs in below callstack with testcase: - mkfs 16GB image & mount image - dd 8GB fileA - dd 8GB fileB - sync - rm fileA - sync - resize filesystem to 8GB kernel BUG at segment.c:2484! Call Trace: allocate_segment_by_default+0x92/0xf0 [f2fs] f2fs_allocate_data_block+0x44b/0x7e0 [f2fs] do_write_page+0x5a/0x110 [f2fs] f2fs_outplace_write_data+0x55/0x100 [f2fs] f2fs_do_write_data_page+0x392/0x850 [f2fs] move_data_page+0x233/0x320 [f2fs] do_garbage_collect+0x14d9/0x1660 [f2fs] free_segment_range+0x1f7/0x310 [f2fs] f2fs_resize_fs+0x118/0x330 [f2fs] __f2fs_ioctl+0x487/0x3680 [f2fs] __x64_sys_ioctl+0x8e/0xd0 do_syscall_64+0x33/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The root cause is we forgot to check that whether we have enough space in resized filesystem to store all valid blocks in before-resizing filesystem, then allocator will run out-of-space during block migration in free_segment_range(). Fixes: b4b10061ef98 ("f2fs: refactor resize_fs to avoid meta updates in progress") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix to allow migrating fully valid segmentChao Yu2021-03-125-16/+20
| | | | | | | | | | | | | | F2FS_IOC_FLUSH_DEVICE/F2FS_IOC_RESIZE_FS needs to migrate all blocks of target segment to other place, no matter the segment has partially or fully valid blocks. However, after commit 803e74be04b3 ("f2fs: stop GC when the victim becomes fully valid"), we may skip migration due to target segment is fully valid, result in failing the ioctl interface, fix this. Fixes: 803e74be04b3 ("f2fs: stop GC when the victim becomes fully valid") Signed-off-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* f2fs: fix a spacing coding stylejiahao2021-03-121-1/+1
| | | | | | | | Add a space before the plus. Signed-off-by: jiahao <jiahao@xiaomi.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
* Merge tag 'configfs-for-5.12' of git://git.infradead.org/users/hch/configfsLinus Torvalds2021-03-121-4/+2
|\ | | | | | | | | | | | | | | | | Pull configfs fix from Christoph Hellwig: - fix a use-after-free in __configfs_open_file (Daiyue Zhang) * tag 'configfs-for-5.12' of git://git.infradead.org/users/hch/configfs: configfs: fix a use-after-free in __configfs_open_file
| * configfs: fix a use-after-free in __configfs_open_fileDaiyue Zhang2021-03-111-4/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit b0841eefd969 ("configfs: provide exclusion between IO and removals") uses ->frag_dead to mark the fragment state, thus no bothering with extra refcount on config_item when opening a file. The configfs_get_config_item was removed in __configfs_open_file, but not with config_item_put. So the refcount on config_item will lost its balance, causing use-after-free issues in some occasions like this: Test: 1. Mount configfs on /config with read-only items: drwxrwx--- 289 root root 0 2021-04-01 11:55 /config drwxr-xr-x 2 root root 0 2021-04-01 11:54 /config/a --w--w--w- 1 root root 4096 2021-04-01 11:53 /config/a/1.txt ...... 2. Then run: for file in /config do echo $file grep -R 'key' $file done 3. __configfs_open_file will be called in parallel, the first one got called will do: if (file->f_mode & FMODE_READ) { if (!(inode->i_mode & S_IRUGO)) goto out_put_module; config_item_put(buffer->item); kref_put() package_details_release() kfree() the other one will run into use-after-free issues like this: BUG: KASAN: use-after-free in __configfs_open_file+0x1bc/0x3b0 Read of size 8 at addr fffffff155f02480 by task grep/13096 CPU: 0 PID: 13096 Comm: grep VIP: 00 Tainted: G W 4.14.116-kasan #1 TGID: 13096 Comm: grep Call trace: dump_stack+0x118/0x160 kasan_report+0x22c/0x294 __asan_load8+0x80/0x88 __configfs_open_file+0x1bc/0x3b0 configfs_open_file+0x28/0x34 do_dentry_open+0x2cc/0x5c0 vfs_open+0x80/0xe0 path_openat+0xd8c/0x2988 do_filp_open+0x1c4/0x2fc do_sys_open+0x23c/0x404 SyS_openat+0x38/0x48 Allocated by task 2138: kasan_kmalloc+0xe0/0x1ac kmem_cache_alloc_trace+0x334/0x394 packages_make_item+0x4c/0x180 configfs_mkdir+0x358/0x740 vfs_mkdir2+0x1bc/0x2e8 SyS_mkdirat+0x154/0x23c el0_svc_naked+0x34/0x38 Freed by task 13096: kasan_slab_free+0xb8/0x194 kfree+0x13c/0x910 package_details_release+0x524/0x56c kref_put+0xc4/0x104 config_item_put+0x24/0x34 __configfs_open_file+0x35c/0x3b0 configfs_open_file+0x28/0x34 do_dentry_open+0x2cc/0x5c0 vfs_open+0x80/0xe0 path_openat+0xd8c/0x2988 do_filp_open+0x1c4/0x2fc do_sys_open+0x23c/0x404 SyS_openat+0x38/0x48 el0_svc_naked+0x34/0x38 To fix this issue, remove the config_item_put in __configfs_open_file to balance the refcount of config_item. Fixes: b0841eefd969 ("configfs: provide exclusion between IO and removals") Signed-off-by: Daiyue Zhang <zhangdaiyue1@huawei.com> Signed-off-by: Yi Chen <chenyi77@huawei.com> Signed-off-by: Ge Qiu <qiuge@huawei.com> Reviewed-by: Chao Yu <yuchao0@huawei.com> Acked-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Christoph Hellwig <hch@lst.de>
* | Merge tag 'gfs2-v5.12-rc2-fixes' of ↵Linus Torvalds2021-03-126-19/+22
|\ \ | |/ |/| | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2 Pull gfs2 fixes from Andreas Gruenbacher: "Various gfs2 fixes" * tag 'gfs2-v5.12-rc2-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: gfs2: bypass log flush if the journal is not live gfs2: bypass signal_our_withdraw if no journal gfs2: fix use-after-free in trans_drain gfs2: make function gfs2_make_fs_ro() to void type
| * gfs2: bypass log flush if the journal is not liveBob Peterson2021-03-121-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Patch fe3e397668775 ("gfs2: Rework the log space allocation logic") changed gfs2_log_flush to reserve a set of journal blocks in case no transaction is active. However, gfs2_log_flush also gets called in cases where we don't have an active journal, for example, for spectator mounts. In that case, trying to reserve blocks would sleep forever, but we want gfs2_log_flush to be a no-op instead. Fixes: fe3e397668775 ("gfs2: Rework the log space allocation logic") Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
| * gfs2: bypass signal_our_withdraw if no journalBob Peterson2021-03-121-5/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Before this patch, function signal_our_withdraw referenced the journal inode immediately. But corrupt file systems may have some invalid journals, in which case our attempt to read it in will withdraw and the resulting signal_our_withdraw would dereference the NULL value. This patch adds a check to signal_our_withdraw so that if the journal has not yet been initialized, it simply returns and does the old-style withdraw. Thanks, Andy Price, for his analysis. Reported-by: syzbot+50a8a9cf8127f2c6f5df@syzkaller.appspotmail.com Fixes: 601ef0d52e96 ("gfs2: Force withdraw to replay journals and wait for it to finish") Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
| * gfs2: fix use-after-free in trans_drainBob Peterson2021-03-072-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds code to function trans_drain to remove drained bd elements from the ail lists, if queued, before freeing the bd. If we don't remove the bd from the ail, function ail_drain will try to reference the bd after it has been freed by trans_drain. Thanks to Andy Price for his analysis of the problem. Reported-by: Andy Price <anprice@redhat.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
| * gfs2: make function gfs2_make_fs_ro() to void typeYang Li2021-03-074-13/+5
| | | | | | | | | | | | | | | | | | | | | | It fixes the following warning detected by coccinelle: ./fs/gfs2/super.c:592:5-10: Unneeded variable: "error". Return "0" on line 628 Reported-by: Abaci Robot <abaci@linux.alibaba.com> Signed-off-by: Yang Li <yang.lee@linux.alibaba.com> Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
* | Merge tag 's390-5.12-3' of ↵Linus Torvalds2021-03-101-1/+1
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux Pull s390 fixes from Heiko Carstens: - fix various user space visible copy_to_user() instances which return the number of bytes left to copy instead of -EFAULT - make TMPFS_INODE64 available again for s390 and alpha, now that both architectures have been switched to 64-bit ino_t (see commit 96c0a6a72d18: "s390,alpha: switch to 64-bit ino_t") - make sure to release a shared hypervisor resource within the zcore device driver also on restart and power down; also remove unneeded surrounding debugfs_create return value checks - for the new hardware counter set device driver rename the uapi header file to be a bit more generic; also remove 60 second read limit which is not really necessary and without the limit the interface can be easier tested - some small cleanups, the largest being to convert all long long in our time and idle code to longs - update defconfigs * tag 's390-5.12-3' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux: s390: remove IBM_PARTITION and CONFIGFS_FS from zfcpdump defconfig s390: update defconfigs s390,alpha: make TMPFS_INODE64 available again s390/cio: return -EFAULT if copy_to_user() fails s390/tty3270: avoid comma separated statements s390/cpumf: remove unneeded semicolon s390/crypto: return -EFAULT if copy_to_user() fails s390/cio: return -EFAULT if copy_to_user() fails s390/cpumf: rename header file to hwctrset.h s390/zcore: release dump save area on restart or power down s390/zcore: no need to check return value of debugfs_create functions s390/cpumf: remove 60 seconds read limit s390/topology: remove always false if check s390/time,idle: get rid of unsigned long long
| * | s390,alpha: make TMPFS_INODE64 available againHeiko Carstens2021-03-081-1/+1
| |/ | | | | | | | | | | | | | | | | | | | | Both s390 and alpha have been switched to 64-bit ino_t with commit 96c0a6a72d18 ("s390,alpha: switch to 64-bit ino_t"). Therefore enable TMPFS_INODE64 for both architectures again. Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Link: https://lore.kernel.org/linux-mm/YCV7QiyoweJwvN+m@osiris/ Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
* | Merge tag 'for-linus-2021-03-10' of ↵Linus Torvalds2021-03-101-1/+1
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux Pull detached mounts fix from Christian Brauner: "Creating a series of detached mounts, attaching them to the filesystem, and unmounting them can be used to trigger an integer overflow in ns->mounts causing the kernel to block any new mounts in count_mounts() and returning ENOSPC because it falsely assumes that the maximum number of mounts in the mount namespace has been reached, i.e. it thinks it can't fit the new mounts into the mount namespace anymore. Without this fix heavy use of the new mount API with move_mount() will cause the host to become unuseable and thus blocks some xfstest patches I want to resend. Depending on the number of mounts in your system, this can be reproduced on any kernel that supportes open_tree() and move_mount(). A reproducer has been sent for inclusion with xfstests. It takes care to do this in another mount namespace, not in the host's mount namespace so there shouldn't be any risk in running it but if one did run it on the host it would require a reboot in order to be able to mount again. See https://lore.kernel.org/fstests/20210309121041.753359-1-christian.brauner@ubuntu.com The root cause of this is that detached mounts aren't handled correctly when source and target mount are identical and reside on a shared mount causing a broken mount tree where the detached source itself is propagated which propagation prevents for regular bind-mounts and new mounts. This ultimately leads to a miscalculation of the number of mounts in the mount namespace. Detached mounts created via 'open_tree(fd, path, OPEN_TREE_CLONE)' are essentially like an unattached bind-mount. They can then later on be attached to the filesystem via move_mount() which calls into attach_recursive_mount(). Part of attaching it to the filesystem is making sure that mounts get correctly propagated in case the destination mountpoint is MS_SHARED, i.e. is a shared mountpoint. This is done by calling into propagate_mnt() which walks the list of peers calling propagate_one() on each mount in this list making sure it receives the propagation event. The propagate_one() function thereby skips both new mounts and bind mounts to not propagate them "into themselves". Both are identified by checking whether the mount is already attached to any mount namespace in mnt->mnt_ns. The is what the IS_MNT_NEW() helper is responsible for. However, detached mounts have an anonymous mount namespace attached to them stashed in mnt->mnt_ns which means that IS_MNT_NEW() doesn't realize they need to be skipped causing the mount to propagate "into itself" breaking the mount table and causing a disconnect between the number of mounts recorded as being beneath or reachable from the target mountpoint and the number of mounts actually recorded/counted in ns->mounts ultimately causing an overflow which in turn prevents any new mounts via the ENOSPC issue. So teach propagation to handle detached mounts by making it aware of them. I've been tracking this issue down for the last couple of days and then verifying that the fix is correct by unmounting everything in my current mount table leaving only /proc and /sys mounted and running the reproducer above overnight verifying the number of mounts counted in ns->mounts. With this fix the counts are correct and the ENOSPC issue can't be reproduced. This change will only have an effect on mounts created with the new mount API since detached mounts cannot be created with the old mount API so regressions are extremely unlikely. Here's an illustration: #### mount(): ubuntu@f1-vm:~$ sudo mount --bind /mnt/ /mnt/ ubuntu@f1-vm:~$ findmnt | grep -i mnt ├─/mnt /dev/sda2[/mnt] ext4 rw,relatime #### open_tree(OPEN_TREE_CLONE) + move_mount() with bug: ubuntu@f1-vm:~$ sudo ./mount-new /mnt/ /mnt/ ubuntu@f1-vm:~$ findmnt | grep -i mnt ├─/mnt /dev/sda2[/mnt] ext4 rw,relatime │ └─/mnt /dev/sda2[/mnt] ext4 rw,relatime #### open_tree(OPEN_TREE_CLONE) + move_mount() with the fix: ubuntu@f1-vm:~$ sudo ./mount-new /mnt /mnt ubuntu@f1-vm:~$ findmnt | grep -i mnt └─/mnt /dev/sda2[/mnt] ext4 rw,relatime" * tag 'for-linus-2021-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: mount: fix mounting of detached mounts onto targets that reside on shared mounts
| * | mount: fix mounting of detached mounts onto targets that reside on shared mountsChristian Brauner2021-03-081-1/+1
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Creating a series of detached mounts, attaching them to the filesystem, and unmounting them can be used to trigger an integer overflow in ns->mounts causing the kernel to block any new mounts in count_mounts() and returning ENOSPC because it falsely assumes that the maximum number of mounts in the mount namespace has been reached, i.e. it thinks it can't fit the new mounts into the mount namespace anymore. Depending on the number of mounts in your system, this can be reproduced on any kernel that supportes open_tree() and move_mount() by compiling and running the following program: /* SPDX-License-Identifier: LGPL-2.1+ */ #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <getopt.h> #include <limits.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/mount.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/types.h> #include <unistd.h> /* open_tree() */ #ifndef OPEN_TREE_CLONE #define OPEN_TREE_CLONE 1 #endif #ifndef OPEN_TREE_CLOEXEC #define OPEN_TREE_CLOEXEC O_CLOEXEC #endif #ifndef __NR_open_tree #if defined __alpha__ #define __NR_open_tree 538 #elif defined _MIPS_SIM #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ #define __NR_open_tree 4428 #endif #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ #define __NR_open_tree 6428 #endif #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ #define __NR_open_tree 5428 #endif #elif defined __ia64__ #define __NR_open_tree (428 + 1024) #else #define __NR_open_tree 428 #endif #endif /* move_mount() */ #ifndef MOVE_MOUNT_F_EMPTY_PATH #define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */ #endif #ifndef __NR_move_mount #if defined __alpha__ #define __NR_move_mount 539 #elif defined _MIPS_SIM #if _MIPS_SIM == _MIPS_SIM_ABI32 /* o32 */ #define __NR_move_mount 4429 #endif #if _MIPS_SIM == _MIPS_SIM_NABI32 /* n32 */ #define __NR_move_mount 6429 #endif #if _MIPS_SIM == _MIPS_SIM_ABI64 /* n64 */ #define __NR_move_mount 5429 #endif #elif defined __ia64__ #define __NR_move_mount (428 + 1024) #else #define __NR_move_mount 429 #endif #endif static inline int sys_open_tree(int dfd, const char *filename, unsigned int flags) { return syscall(__NR_open_tree, dfd, filename, flags); } static inline int sys_move_mount(int from_dfd, const char *from_pathname, int to_dfd, const char *to_pathname, unsigned int flags) { return syscall(__NR_move_mount, from_dfd, from_pathname, to_dfd, to_pathname, flags); } static bool is_shared_mountpoint(const char *path) { bool shared = false; FILE *f = NULL; char *line = NULL; int i; size_t len = 0; f = fopen("/proc/self/mountinfo", "re"); if (!f) return 0; while (getline(&line, &len, f) > 0) { char *slider1, *slider2; for (slider1 = line, i = 0; slider1 && i < 4; i++) slider1 = strchr(slider1 + 1, ' '); if (!slider1) continue; slider2 = strchr(slider1 + 1, ' '); if (!slider2) continue; *slider2 = '\0'; if (strcmp(slider1 + 1, path) == 0) { /* This is the path. Is it shared? */ slider1 = strchr(slider2 + 1, ' '); if (slider1 && strstr(slider1, "shared:")) { shared = true; break; } } } fclose(f); free(line); return shared; } static void usage(void) { const char *text = "mount-new [--recursive] <base-dir>\n"; fprintf(stderr, "%s", text); _exit(EXIT_SUCCESS); } #define exit_usage(format, ...) \ ({ \ fprintf(stderr, format "\n", ##__VA_ARGS__); \ usage(); \ }) #define exit_log(format, ...) \ ({ \ fprintf(stderr, format "\n", ##__VA_ARGS__); \ exit(EXIT_FAILURE); \ }) static const struct option longopts[] = { {"help", no_argument, 0, 'a'}, { NULL, no_argument, 0, 0 }, }; int main(int argc, char *argv[]) { int exit_code = EXIT_SUCCESS, index = 0; int dfd, fd_tree, new_argc, ret; char *base_dir; char *const *new_argv; char target[PATH_MAX]; while ((ret = getopt_long_only(argc, argv, "", longopts, &index)) != -1) { switch (ret) { case 'a': /* fallthrough */ default: usage(); } } new_argv = &argv[optind]; new_argc = argc - optind; if (new_argc < 1) exit_usage("Missing base directory\n"); base_dir = new_argv[0]; if (*base_dir != '/') exit_log("Please specify an absolute path"); /* Ensure that target is a shared mountpoint. */ if (!is_shared_mountpoint(base_dir)) exit_log("Please ensure that \"%s\" is a shared mountpoint", base_dir); dfd = open(base_dir, O_RDONLY | O_DIRECTORY | O_CLOEXEC); if (dfd < 0) exit_log("%m - Failed to open base directory \"%s\"", base_dir); ret = mkdirat(dfd, "detached-move-mount", 0755); if (ret < 0) exit_log("%m - Failed to create required temporary directories"); ret = snprintf(target, sizeof(target), "%s/detached-move-mount", base_dir); if (ret < 0 || (size_t)ret >= sizeof(target)) exit_log("%m - Failed to assemble target path"); /* * Having a mount table with 10000 mounts is already quite excessive * and shoult account even for weird test systems. */ for (size_t i = 0; i < 10000; i++) { fd_tree = sys_open_tree(dfd, "detached-move-mount", OPEN_TREE_CLONE | OPEN_TREE_CLOEXEC | AT_EMPTY_PATH); if (fd_tree < 0) { fprintf(stderr, "%m - Failed to open %d(detached-move-mount)", dfd); exit_code = EXIT_FAILURE; break; } ret = sys_move_mount(fd_tree, "", dfd, "detached-move-mount", MOVE_MOUNT_F_EMPTY_PATH); if (ret < 0) { if (errno == ENOSPC) fprintf(stderr, "%m - Buggy mount counting"); else fprintf(stderr, "%m - Failed to attach mount to %d(detached-move-mount)", dfd); exit_code = EXIT_FAILURE; break; } close(fd_tree); ret = umount2(target, MNT_DETACH); if (ret < 0) { fprintf(stderr, "%m - Failed to unmount %s", target); exit_code = EXIT_FAILURE; break; } } (void)unlinkat(dfd, "detached-move-mount", AT_REMOVEDIR); close(dfd); exit(exit_code); } and wait for the kernel to refuse any new mounts by returning ENOSPC. How many iterations are needed depends on the number of mounts in your system. Assuming you have something like 50 mounts on a standard system it should be almost instantaneous. The root cause of this is that detached mounts aren't handled correctly when source and target mount are identical and reside on a shared mount causing a broken mount tree where the detached source itself is propagated which propagation prevents for regular bind-mounts and new mounts. This ultimately leads to a miscalculation of the number of mounts in the mount namespace. Detached mounts created via open_tree(fd, path, OPEN_TREE_CLONE) are essentially like an unattached new mount, or an unattached bind-mount. They can then later on be attached to the filesystem via move_mount() which calls into attach_recursive_mount(). Part of attaching it to the filesystem is making sure that mounts get correctly propagated in case the destination mountpoint is MS_SHARED, i.e. is a shared mountpoint. This is done by calling into propagate_mnt() which walks the list of peers calling propagate_one() on each mount in this list making sure it receives the propagation event. The propagate_one() functions thereby skips both new mounts and bind mounts to not propagate them "into themselves". Both are identified by checking whether the mount is already attached to any mount namespace in mnt->mnt_ns. The is what the IS_MNT_NEW() helper is responsible for. However, detached mounts have an anonymous mount namespace attached to them stashed in mnt->mnt_ns which means that IS_MNT_NEW() doesn't realize they need to be skipped causing the mount to propagate "into itself" breaking the mount table and causing a disconnect between the number of mounts recorded as being beneath or reachable from the target mountpoint and the number of mounts actually recorded/counted in ns->mounts ultimately causing an overflow which in turn prevents any new mounts via the ENOSPC issue. So teach propagation to handle detached mounts by making it aware of them. I've been tracking this issue down for the last couple of days and then verifying that the fix is correct by unmounting everything in my current mount table leaving only /proc and /sys mounted and running the reproducer above overnight verifying the number of mounts counted in ns->mounts. With this fix the counts are correct and the ENOSPC issue can't be reproduced. This change will only have an effect on mounts created with the new mount API since detached mounts cannot be created with the old mount API so regressions are extremely unlikely. Link: https://lore.kernel.org/r/20210306101010.243666-1-christian.brauner@ubuntu.com Fixes: 2db154b3ea8e ("vfs: syscall: Add move_mount(2) to move mounts around") Cc: David Howells <dhowells@redhat.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: linux-fsdevel@vger.kernel.org Cc: <stable@vger.kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
* | cifs: do not send close in compound create+close requestsPaulo Alcantara2021-03-086-21/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In case of interrupted syscalls, prevent sending CLOSE commands for compound CREATE+CLOSE requests by introducing an CIFS_CP_CREATE_CLOSE_OP flag to indicate lower layers that it should not send a CLOSE command to the MIDs corresponding the compound CREATE+CLOSE request. A simple reproducer: #!/bin/bash mount //server/share /mnt -o username=foo,password=*** tc qdisc add dev eth0 root netem delay 450ms stat -f /mnt &>/dev/null & pid=$! sleep 0.01 kill $pid tc qdisc del dev eth0 root umount /mnt Before patch: ... 6 0.256893470 192.168.122.2 → 192.168.122.15 SMB2 402 Create Request File: ;GetInfo Request FS_INFO/FileFsFullSizeInformation;Close Request 7 0.257144491 192.168.122.15 → 192.168.122.2 SMB2 498 Create Response File: ;GetInfo Response;Close Response 9 0.260798209 192.168.122.2 → 192.168.122.15 SMB2 146 Close Request File: 10 0.260841089 192.168.122.15 → 192.168.122.2 SMB2 130 Close Response, Error: STATUS_FILE_CLOSED Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com> Reviewed-by: Aurelien Aptel <aaptel@suse.com> CC: <stable@vger.kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
* | cifs: return proper error code in statfs(2)Paulo Alcantara2021-03-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | In cifs_statfs(), if server->ops->queryfs is not NULL, then we should use its return value rather than always returning 0. Instead, use rc variable as it is properly set to 0 in case there is no server->ops->queryfs. Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz> Reviewed-by: Aurelien Aptel <aaptel@suse.com> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com> CC: <stable@vger.kernel.org> Signed-off-by: Steve French <stfrench@microsoft.com>
* | cifs: change noisy error message to FYIPaulo Alcantara2021-03-081-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A customer has reported that their dmesg were being flooded by CIFS: VFS: \\server Cancelling wait for mid xxx cmd: a CIFS: VFS: \\server Cancelling wait for mid yyy cmd: b CIFS: VFS: \\server Cancelling wait for mid zzz cmd: c because some processes that were performing statfs(2) on the share had been interrupted due to their automount setup when certain users logged in and out. Change it to FYI as they should be mostly informative rather than error messages. Signed-off-by: Paulo Alcantara (SUSE) <pc@cjr.nz> Reviewed-by: Aurelien Aptel <aaptel@suse.com> Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com> Signed-off-by: Steve French <stfrench@microsoft.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-15 14:21:22 +0000