diff options
| author | Tao Huang <huangtao@rock-chips.com> | 2018-12-19 18:46:58 +0800 |
|---|---|---|
| committer | Tao Huang <huangtao@rock-chips.com> | 2018-12-19 18:46:58 +0800 |
| commit | 04026c23c8d802ed28790c3f2861e779635ca46f (patch) | |
| tree | cd08dbeeff4756bea34b04c743a3694c6dc7f5ad /fs | |
| parent | 8f3cd5ef835c52e645b83a906b4d9d0fa265a814 (diff) | |
| parent | b6b5ee6576282dc102dfc69463d1147116b2e732 (diff) | |
Merge branch 'linux-linaro-lsk-v4.4-android' of git://git.linaro.org/kernel/linux-linaro-stable.git
* linux-linaro-lsk-v4.4-android: (812 commits)
Linux 4.4.167
mac80211: ignore NullFunc frames in the duplicate detection
mac80211: fix reordering of buffered broadcast packets
mac80211: ignore tx status for PS stations in ieee80211_tx_status_ext
mac80211: Clear beacon_int in ieee80211_do_stop
mac80211_hwsim: Timer should be initialized before device registered
kgdboc: fix KASAN global-out-of-bounds bug in param_set_kgdboc_var()
tty: serial: 8250_mtk: always resume the device in probe.
cifs: Fix separator when building path from dentry
Staging: lustre: remove two build warnings
xhci: Prevent U1/U2 link pm states if exit latency is too long
SUNRPC: Fix leak of krb5p encode pages
virtio/s390: fix race in ccw_io_helper()
virtio/s390: avoid race on vcdev->config
ALSA: pcm: Fix interval evaluation with openmin/max
ALSA: pcm: Call snd_pcm_unlink() conditionally at closing
ALSA: pcm: Fix starvation on down_write_nonblock()
ALSA: hda: Add support for AMD Stoney Ridge
ALSA: usb-audio: Fix UAF decrement if card has no live interfaces in card.c
USB: check usb_get_extra_descriptor for proper size
...
Conflicts:
drivers/gpu/drm/rockchip/rockchip_drm_drv.c
drivers/usb/host/xhci-ring.c
Change-Id: I4304b0875908403a7d88a0d77da52cea04563c11
Diffstat (limited to 'fs')
99 files changed, 1936 insertions, 777 deletions
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index 5cc00e56206e..7d889f56b8e7 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -76,15 +76,6 @@ static inline int dt_type(struct p9_wstat *mistat) return rettype; } -static void p9stat_init(struct p9_wstat *stbuf) -{ - stbuf->name = NULL; - stbuf->uid = NULL; - stbuf->gid = NULL; - stbuf->muid = NULL; - stbuf->extension = NULL; -} - /** * v9fs_alloc_rdir_buf - Allocate buffer used for read and readdir * @filp: opened file structure @@ -145,12 +136,10 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) rdir->tail = n; } while (rdir->head < rdir->tail) { - p9stat_init(&st); err = p9stat_read(fid->clnt, rdir->buf + rdir->head, rdir->tail - rdir->head, &st); if (err) { p9_debug(P9_DEBUG_VFS, "returned %d\n", err); - p9stat_free(&st); return -EIO; } reclen = st.size+2; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 12ceaf52dae6..e7b3d2c4472d 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -204,6 +204,14 @@ static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl) break; if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0) break; + /* + * p9_client_lock_dotl overwrites flock.client_id with the + * server message, free and reuse the client name + */ + if (flock.client_id != fid->clnt->name) { + kfree(flock.client_id); + flock.client_id = fid->clnt->name; + } } /* map 9p status to VFS status */ @@ -235,6 +243,8 @@ out_unlock: locks_lock_file_wait(filp, fl); fl->fl_type = fl_type; } + if (flock.client_id != fid->clnt->name) + kfree(flock.client_id); out: return res; } @@ -269,7 +279,7 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) res = p9_client_getlock_dotl(fid, &glock); if (res < 0) - return res; + goto out; /* map 9p lock type to os lock type */ switch (glock.type) { case P9_LOCK_TYPE_RDLCK: @@ -290,7 +300,9 @@ static int v9fs_file_getlock(struct file *filp, struct file_lock *fl) fl->fl_end = glock.start + glock.length - 1; fl->fl_pid = glock.proc_id; } - kfree(glock.client_id); +out: + if (glock.client_id != fid->clnt->name) + kfree(glock.client_id); return res; } diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c index fdcb4d69f430..4714c55c1ae5 100644 --- a/fs/bfs/inode.c +++ b/fs/bfs/inode.c @@ -350,7 +350,8 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) s->s_magic = BFS_MAGIC; - if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end)) { + if (le32_to_cpu(bfs_sb->s_start) > le32_to_cpu(bfs_sb->s_end) || + le32_to_cpu(bfs_sb->s_start) < BFS_BSIZE) { printf("Superblock is corrupted\n"); goto out1; } @@ -359,9 +360,11 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent) sizeof(struct bfs_inode) + BFS_ROOT_INO - 1; imap_len = (info->si_lasti / 8) + 1; - info->si_imap = kzalloc(imap_len, GFP_KERNEL); - if (!info->si_imap) + info->si_imap = kzalloc(imap_len, GFP_KERNEL | __GFP_NOWARN); + if (!info->si_imap) { + printf("Cannot allocate %u bytes\n", imap_len); goto out1; + } for (i = 0; i < BFS_ROOT_INO; i++) set_bit(i, info->si_imap); diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index ef90667e048b..598343f07569 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -606,28 +606,30 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, * Do the same thing for the memory mapping - between * elf_bss and last_bss is the bss section. */ - k = load_addr + eppnt->p_memsz + eppnt->p_vaddr; + k = load_addr + eppnt->p_vaddr + eppnt->p_memsz; if (k > last_bss) last_bss = k; } } + /* + * Now fill out the bss section: first pad the last page from + * the file up to the page boundary, and zero it from elf_bss + * up to the end of the page. + */ + if (padzero(elf_bss)) { + error = -EFAULT; + goto out; + } + /* + * Next, align both the file and mem bss up to the page size, + * since this is where elf_bss was just zeroed up to, and where + * last_bss will end after the vm_brk() below. + */ + elf_bss = ELF_PAGEALIGN(elf_bss); + last_bss = ELF_PAGEALIGN(last_bss); + /* Finally, if there is still more bss to allocate, do it. */ if (last_bss > elf_bss) { - /* - * Now fill out the bss section. First pad the last page up - * to the page boundary, and then perform a mmap to make sure - * that there are zero-mapped pages up to and including the - * last bss page. - */ - if (padzero(elf_bss)) { - error = -EFAULT; - goto out; - } - - /* What we have mapped so far */ - elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1); - - /* Map the last of the bss segment */ error = vm_brk(elf_bss, last_bss - elf_bss); if (BAD_ADDR(error)) goto out; @@ -1216,11 +1218,13 @@ static int load_elf_library(struct file *file) goto out_free_ph; } - len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr + - ELF_MIN_ALIGN - 1); - bss = eppnt->p_memsz + eppnt->p_vaddr; - if (bss > len) - vm_brk(len, bss - len); + len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr); + bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr); + if (bss > len) { + error = vm_brk(len, bss - len); + if (BAD_ADDR(error)) + goto out_free_ph; + } error = 0; out_free_ph: diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ae6e3a30e61e..1f21c6c33228 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -445,9 +445,9 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree; while (1) { + clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = read_extent_buffer_pages(io_tree, eb, start, WAIT_COMPLETE, btree_get_extent, mirror_num); @@ -459,14 +459,6 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, ret = -EIO; } - /* - * This buffer's crc is fine, but its contents are corrupted, so - * there is no reason to read the other copies, they won't be - * any less wrong. - */ - if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags)) - break; - num_copies = btrfs_num_copies(root->fs_info, eb->start, eb->len); if (num_copies == 1) @@ -1608,8 +1600,8 @@ fail: return ret; } -static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; @@ -4333,6 +4325,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root, static int btrfs_destroy_pinned_extent(struct btrfs_root *root, struct extent_io_tree *pinned_extents) { + struct btrfs_fs_info *fs_info = root->fs_info; struct extent_io_tree *unpin; u64 start; u64 end; @@ -4342,21 +4335,31 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root, unpin = pinned_extents; again: while (1) { + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, NULL); - if (ret) + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } clear_extent_dirty(unpin, start, end, GFP_NOFS); btrfs_error_unpin_extent_range(root, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } if (loop) { - if (unpin == &root->fs_info->freed_extents[0]) - unpin = &root->fs_info->freed_extents[1]; + if (unpin == &fs_info->freed_extents[0]) + unpin = &fs_info->freed_extents[1]; else - unpin = &root->fs_info->freed_extents[0]; + unpin = &fs_info->freed_extents[0]; loop = false; goto again; } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index adeb31830b9c..3c9819403487 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); int btrfs_init_fs_root(struct btrfs_root *root); +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a72f941ca750..13ff0fdae03e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -7835,6 +7835,20 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, buf = btrfs_find_create_tree_block(root, bytenr); if (!buf) return ERR_PTR(-ENOMEM); + + /* + * Extra safety check in case the extent tree is corrupted and extent + * allocator chooses to use a tree block which is already used and + * locked. + */ + if (buf->lock_owner == current->pid) { + btrfs_err_rl(root->fs_info, +"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected", + buf->start, btrfs_header_owner(buf), current->pid); + free_extent_buffer(buf); + return ERR_PTR(-EUCLEAN); + } + btrfs_set_header_generation(buf, trans->transid); btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level); btrfs_tree_lock(buf); @@ -8704,15 +8718,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (eb == root->node) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = eb->start; - else - BUG_ON(root->root_key.objectid != - btrfs_header_owner(eb)); + else if (root->root_key.objectid != btrfs_header_owner(eb)) + goto owner_mismatch; } else { if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF) parent = path->nodes[level + 1]->start; - else - BUG_ON(root->root_key.objectid != - btrfs_header_owner(path->nodes[level + 1])); + else if (root->root_key.objectid != + btrfs_header_owner(path->nodes[level + 1])) + goto owner_mismatch; } btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); @@ -8720,6 +8733,11 @@ out: wc->refs[level] = 0; wc->flags[level] = 0; return 0; + +owner_mismatch: + btrfs_err_rl(root->fs_info, "unexpected tree owner, have %llu expect %llu", + btrfs_header_owner(eb), root->root_key.objectid); + return -EUCLEAN; } static noinline int walk_down_tree(struct btrfs_trans_handle *trans, @@ -8773,6 +8791,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, ret = walk_up_proc(trans, root, path, wc); if (ret > 0) return 0; + if (ret < 0) + return ret; if (path->locks[level]) { btrfs_tree_unlock_rw(path->nodes[level], @@ -9501,6 +9521,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group = btrfs_lookup_first_block_group(info, last); while (block_group) { + wait_block_group_cache_done(block_group); spin_lock(&block_group->lock); if (block_group->iref) break; @@ -9891,7 +9912,7 @@ error: void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root) { - struct btrfs_block_group_cache *block_group, *tmp; + struct btrfs_block_group_cache *block_group; struct btrfs_root *extent_root = root->fs_info->extent_root; struct btrfs_block_group_item item; struct btrfs_key key; @@ -9899,7 +9920,10 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans, bool can_flush_pending_bgs = trans->can_flush_pending_bgs; trans->can_flush_pending_bgs = false; - list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + while (!list_empty(&trans->new_bgs)) { + block_group = list_first_entry(&trans->new_bgs, + struct btrfs_block_group_cache, + bg_list); if (ret) goto next; @@ -10609,6 +10633,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, *trimmed = 0; + /* Discard not supported = nothing to do. */ + if (!blk_queue_discard(bdev_get_queue(device->bdev))) + return 0; + /* Not writeable = nothing to do. */ if (!device->writeable) return 0; @@ -10680,17 +10708,9 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) u64 start; u64 end; u64 trimmed = 0; - u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); int ret = 0; - /* - * try to trim all FS space, our block group may start from non-zero. - */ - if (range->len == total_bytes) - cache = btrfs_lookup_first_block_group(fs_info, range->start); - else - cache = btrfs_lookup_block_group(fs_info, range->start); - + cache = btrfs_lookup_first_block_group(fs_info, range->start); while (cache) { if (cache->key.objectid >= (range->start + range->len)) { btrfs_put_block_group(cache); @@ -10731,8 +10751,8 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) } mutex_lock(&root->fs_info->fs_devices->device_list_mutex); - devices = &root->fs_info->fs_devices->alloc_list; - list_for_each_entry(device, devices, dev_alloc_list) { + devices = &root->fs_info->fs_devices->devices; + list_for_each_entry(device, devices, dev_list) { ret = btrfs_trim_free_extents(device, range->minlen, &group_trimmed); if (ret) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 45934deacfd7..6c0161284a9e 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1699,6 +1699,8 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, bitmap_clear(info->bitmap, start, count); info->bytes -= bytes; + if (info->max_extent_size > ctl->unit) + info->max_extent_size = 0; } static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, @@ -1782,6 +1784,13 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, return -1; } +static inline u64 get_max_extent_size(struct btrfs_free_space *entry) +{ + if (entry->bitmap) + return entry->max_extent_size; + return entry->bytes; +} + /* Cache the size of the max extent in bytes */ static struct btrfs_free_space * find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, @@ -1803,8 +1812,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, for (node = &entry->offset_index; node; node = rb_next(node)) { entry = rb_entry(node, struct btrfs_free_space, offset_index); if (entry->bytes < *bytes) { - if (entry->bytes > *max_extent_size) - *max_extent_size = entry->bytes; + *max_extent_size = max(get_max_extent_size(entry), + *max_extent_size); continue; } @@ -1822,8 +1831,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, } if (entry->bytes < *bytes + align_off) { - if (entry->bytes > *max_extent_size) - *max_extent_size = entry->bytes; + *max_extent_size = max(get_max_extent_size(entry), + *max_extent_size); continue; } @@ -1835,8 +1844,10 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, *offset = tmp; *bytes = size; return entry; - } else if (size > *max_extent_size) { - *max_extent_size = size; + } else { + *max_extent_size = + max(get_max_extent_size(entry), + *max_extent_size); } continue; } @@ -2458,6 +2469,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, struct rb_node *n; int count = 0; + spin_lock(&ctl->tree_lock); for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { info = rb_entry(n, struct btrfs_free_space, offset_index); if (info->bytes >= bytes && !block_group->ro) @@ -2467,6 +2479,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, info->offset, info->bytes, (info->bitmap) ? "yes" : "no"); } + spin_unlock(&ctl->tree_lock); btrfs_info(block_group->fs_info, "block group has cluster?: %s", list_empty(&block_group->cluster_list) ? "no" : "yes"); btrfs_info(block_group->fs_info, @@ -2694,8 +2707,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, err = search_bitmap(ctl, entry, &search_start, &search_bytes, true); if (err) { - if (search_bytes > *max_extent_size) - *max_extent_size = search_bytes; + *max_extent_size = max(get_max_extent_size(entry), + *max_extent_size); return 0; } @@ -2732,8 +2745,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, entry = rb_entry(node, struct btrfs_free_space, offset_index); while (1) { - if (entry->bytes < bytes && entry->bytes > *max_extent_size) - *max_extent_size = entry->bytes; + if (entry->bytes < bytes) + *max_extent_size = max(get_max_extent_size(entry), + *max_extent_size); if (entry->bytes < bytes || (!entry->bitmap && entry->offset < min_start)) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b895be3d4311..383717ccecc7 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -481,6 +481,7 @@ again: pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS); if (!pages) { /* just bail out to the uncompressed code */ + nr_pages = 0; goto cont; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 6caeb946fc1d..3379490ce54d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -378,7 +378,6 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; - u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); int ret; if (!capable(CAP_SYS_ADMIN)) @@ -402,11 +401,15 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) return -EOPNOTSUPP; if (copy_from_user(&range, arg, sizeof(range))) return -EFAULT; - if (range.start > total_bytes || - range.len < fs_info->sb->s_blocksize) + + /* + * NOTE: Don't truncate the range using super->total_bytes. Bytenr of + * block group is in the logical address space, which can be any + * sectorsize aligned bytenr in the range [0, U64_MAX]. + */ + if (range.len < fs_info->sb->s_blocksize) return -EINVAL; - range.len = min(range.len, total_bytes - range.start); range.minlen = max(range.minlen, minlen); ret = btrfs_trim_fs(fs_info->tree_root, &range); if (ret < 0) @@ -3950,9 +3953,17 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index a751937dded5..90e29d40aa82 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2446,6 +2446,7 @@ qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info) qgroup->rfer_cmpr = 0; qgroup->excl = 0; qgroup->excl_cmpr = 0; + qgroup_dirty(fs_info, qgroup); } spin_unlock(&fs_info->qgroup_lock); } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index cfe913d2d3df..d6ccfb31aef0 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1318,7 +1318,7 @@ static void __del_reloc_root(struct btrfs_root *root) struct mapping_node *node = NULL; struct reloc_control *rc = root->fs_info->reloc_ctl; - if (rc) { + if (rc && root->node) { spin_lock(&rc->reloc_root_tree.lock); rb_node = tree_search(&rc->reloc_root_tree.rb_root, root->node->start); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 2c849b08a91b..6a6efb26d52f 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid = key.offset; key.offset++; + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + root = btrfs_lookup_fs_root(tree_root->fs_info, + root_key.objectid); + if (root) { + WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, + &root->state)); + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); + continue; + } + root = btrfs_read_fs_root(tree_root, &root_key); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { @@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); - /* - * The root might have been inserted already, as before we look - * for orphan roots, log replay might have happened, which - * triggers a transaction commit and qgroup accounting, which - * in turn reads and inserts fs roots while doing backref - * walking. - */ - if (err == -EEXIST) - err = 0; if (err) { + BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3bd2233737ac..0f99336c37eb 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2104,6 +2104,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, vol = memdup_user((void __user *)arg, sizeof(*vol)); if (IS_ERR(vol)) return PTR_ERR(vol); + vol->name[BTRFS_PATH_NAME_MAX] = '\0'; switch (cmd) { case BTRFS_IOC_SCAN_DEV: diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index be8eae80ff65..098016338f98 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1821,6 +1821,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, return ret; } + btrfs_trans_release_metadata(trans, root); + trans->block_rsv = NULL; + /* make a pass through all the delayed refs we have so far * any runnings procs may add more while we are here */ @@ -1830,9 +1833,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, return ret; } - btrfs_trans_release_metadata(trans, root); - trans->block_rsv = NULL; - cur_trans = trans->transaction; /* diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2c7f9a5f8717..63f59f17c97e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -5240,9 +5240,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans, dir_inode = btrfs_iget(root->fs_info->sb, &inode_key, root, NULL); - /* If parent inode was deleted, skip it. */ - if (IS_ERR(dir_inode)) - continue; + /* + * If the parent inode was deleted, return an error to + * fallback to a transaction commit. This is to prevent + * getting an inode that was moved from one parent A to + * a parent B, got its former parent A deleted and then + * it got fsync'ed, from existing at both parents after + * a log replay (and the old parent still existing). + * Example: + * + * mkdir /mnt/A + * mkdir /mnt/B + * touch /mnt/B/bar + * sync + * mv /mnt/B/bar /mnt/A/bar + * mv -T /mnt/A /mnt/B + * fsync /mnt/B/bar + * <power fail> + * + * If we ignore the old parent B which got deleted, + * after a log replay we would have file bar linked + * at both parents and the old parent B would still + * exist. + */ + if (IS_ERR(dir_inode)) { + ret = PTR_ERR(dir_inode); + goto out; + } ret = btrfs_log_inode(trans, root, dir_inode, LOG_INODE_ALL, 0, LLONG_MAX, ctx); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index c43b4b08546b..a5f59eed8287 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -317,7 +317,7 @@ try_again: trap = lock_rename(cache->graveyard, dir); /* do some checks before getting the grave dentry */ - if (rep->d_parent != dir) { + if (rep->d_parent != dir || IS_DEADDIR(d_inode(rep))) { /* the entry was probably culled when we dropped the parent dir * lock */ unlock_rename(cache->graveyard, dir); diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 0e72a14228f8..7bc6d27d47a4 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -285,6 +285,9 @@ static ssize_t cifs_stats_proc_write(struct file *file, atomic_set(&totBufAllocCount, 0); atomic_set(&totSmBufAllocCount, 0); #endif /* CONFIG_CIFS_STATS2 */ + atomic_set(&tcpSesReconnectCount, 0); + atomic_set(&tconInfoReconnectCount, 0); + spin_lock(&GlobalMid_Lock); GlobalMaxActiveXid = 0; GlobalCurrentXid = 0; diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 6908080e9b6d..e3f2b7370bd8 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -143,8 +143,10 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo) sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) sprintf(dp, ";sec=mskrb5"); - else - goto out; + else { + cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); + sprintf(dp, ";sec=krb5"); + } dp = description + strlen(description); sprintf(dp, ";uid=0x%x", diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index a0b3e7d1be48..211ac472cb9d 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -101,9 +101,6 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_LESSTHAN: *target = '<'; break; - case SFM_SLASH: - *target = '\\'; - break; case SFM_SPACE: *target = ' '; break; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 63aea21e6298..b9b8f19dce0e 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -577,10 +577,15 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) } count = 0; + /* + * We know that all the name entries in the protocols array + * are short (< 16 bytes anyway) and are NUL terminated. + */ for (i = 0; i < CIFS_NUM_PROT; i++) { - strncpy(pSMB->DialectsArray+count, protocols[i].name, 16); - count += strlen(protocols[i].name) + 1; - /* null at end of source and target buffers anyway */ + size_t len = strlen(protocols[i].name) + 1; + + memcpy(pSMB->DialectsArray+count, protocols[i].name, len); + count += len; } inc_rfc1001_len(pSMB, count); pSMB->ByteCount = cpu_to_le16(count); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 077ad3a06c9a..1eeb4780c3ed 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3674,6 +3674,9 @@ try_mount_again: if (IS_ERR(tcon)) { rc = PTR_ERR(tcon); tcon = NULL; + if (rc == -EACCES) + goto mount_fail_check; + goto remote_path_check; } diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 76dacd5307b9..afd317eb9db9 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -163,7 +163,7 @@ cifs_bp_rename_retry: cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath); memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1); - full_path[dfsplen] = '\\'; + full_path[dfsplen] = dirsep; for (i = 0; i < pplen-1; i++) if (full_path[dfsplen+1+i] == '/') full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 36c8594bb147..5c3187df9ab9 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -756,7 +756,15 @@ cifs_get_inode_info(struct inode **inode, const char *full_path, } else if (rc == -EREMOTE) { cifs_create_dfs_fattr(&fattr, sb); rc = 0; - } else if (rc == -EACCES && backup_cred(cifs_sb)) { + } else if ((rc == -EACCES) && backup_cred(cifs_sb) && + (strcmp(server->vals->version_string, SMB1_VERSION_STRING) + == 0)) { + /* + * For SMB2 and later the backup intent flag is already + * sent if needed on open and there is no path based + * FindFirst operation to use to retry with + */ + srchinf = kzalloc(sizeof(struct cifs_search_info), GFP_KERNEL); if (srchinf == NULL) { diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 0cc699d9b932..61a09ab2752e 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -406,9 +406,17 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; + size_t len = srv->total_read - sizeof(pSMBr->hdr.smb_buf_length); + if (get_bcc(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); + if (data_offset > + len - sizeof(struct file_notify_information)) { + cifs_dbg(FYI, "invalid data_offset %u\n", + data_offset); + return true; + } pnotify = (struct file_notify_information *) ((char *)&pSMBr->hdr.Protocol + data_offset); cifs_dbg(FYI, "dnotify on %s Action: 0x%x\n", diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e6b1795fbf2a..2725085a3f9f 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -914,7 +914,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, } srch_inf->entries_in_buffer = 0; - srch_inf->index_of_last_entry = 0; + srch_inf->index_of_last_entry = 2; rc = SMB2_query_directory(xid, tcon, fid->persistent_fid, fid->volatile_fid, 0, srch_inf); diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c index 0525ebc3aea2..66e8c5d58b21 100644 --- a/fs/configfs/symlink.c +++ b/fs/configfs/symlink.c @@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length) /* back up enough to print this bus id with '/' */ length -= cur; - strncpy(buffer + length,config_item_name(p),cur); + memcpy(buffer + length, config_item_name(p), cur); *(buffer + --length) = '/'; } } diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 355c522f3585..a6c9c2d66af1 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -185,7 +185,8 @@ static void *cramfs_read(struct super_block *sb, unsigned int offset, unsigned i continue; blk_offset = (blocknr - buffer_blocknr[i]) << PAGE_CACHE_SHIFT; blk_offset += offset; - if (blk_offset + len > BUFFER_SIZE) + if (blk_offset > BUFFER_SIZE || + blk_offset + len > BUFFER_SIZE) continue; return read_buffers[i] + blk_offset; } diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index ea372cd53ab6..92c6c0ace1b1 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -93,10 +93,6 @@ static inline bool fscrypt_valid_enc_modes(u32 contents_mode, filenames_mode == FS_ENCRYPTION_MODE_AES_256_CTS) return true; - if (contents_mode == FS_ENCRYPTION_MODE_SPECK128_256_XTS && - filenames_mode == FS_ENCRYPTION_MODE_SPECK128_256_CTS) - return true; - return false; } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 382e828f2f9a..3cbe0eff8767 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -173,16 +173,6 @@ static struct fscrypt_mode { .cipher_str = "cts(cbc(aes))", .keysize = 16, }, - [FS_ENCRYPTION_MODE_SPECK128_256_XTS] = { - .friendly_name = "Speck128/256-XTS", - .cipher_str = "xts(speck128)", - .keysize = 64, - }, - [FS_ENCRYPTION_MODE_SPECK128_256_CTS] = { - .friendly_name = "Speck128/256-CTS-CBC", - .cipher_str = "cts(cbc(speck128))", - .keysize = 32, - }, }; static struct fscrypt_mode * diff --git a/fs/exec.c b/fs/exec.c index dd3a59420506..7b4cd71c7b2d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1077,15 +1077,14 @@ killed: return -EAGAIN; } -char *get_task_comm(char *buf, struct task_struct *tsk) +char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); - strncpy(buf, tsk->comm, sizeof(tsk->comm)); + strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } -EXPORT_SYMBOL_GPL(get_task_comm); +EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable diff --git a/fs/exofs/super.c b/fs/exofs/super.c index b795c567b5e1..360ba74e04e6 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -100,6 +100,7 @@ static int parse_options(char *options, struct exofs_mountopt *opts) token = match_token(p, tokens, args); switch (token) { case Opt_name: + kfree(opts->dev_name); opts->dev_name = match_strdup(&args[0]); if (unlikely(!opts->dev_name)) { EXOFS_ERR("Error allocating dev_name"); @@ -868,8 +869,10 @@ static struct dentry *exofs_mount(struct file_system_type *type, int ret; ret = parse_options(data, &opts); - if (ret) + if (ret) { + kfree(opts.dev_name); return ERR_PTR(ret); + } if (!opts.dev_name) opts.dev_name = dev_name; diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 24736c8b3d51..e66047d6943f 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -606,9 +606,9 @@ skip_replace: } cleanup: - brelse(bh); if (!(bh && header == HDR(bh))) kfree(header); + brelse(bh); up_write(&EXT2_I(inode)->xattr_sem); return error; diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index f6096ee77662..f240cef8b326 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -457,17 +457,9 @@ errout: return err; } -bool ext4_valid_enc_modes(uint32_t contents_mode, uint32_t filenames_mode) +bool ext4_valid_contents_enc_mode(uint32_t mode) { - if (contents_mode == EXT4_ENCRYPTION_MODE_AES_256_XTS) { - return (filenames_mode == EXT4_ENCRYPTION_MODE_AES_256_CTS || - filenames_mode == EXT4_ENCRYPTION_MODE_AES_256_HEH); - } - - if (contents_mode == EXT4_ENCRYPTION_MODE_SPECK128_256_XTS) - return filenames_mode == EXT4_ENCRYPTION_MODE_SPECK128_256_CTS; - - return false; + return (mode == EXT4_ENCRYPTION_MODE_AES_256_XTS); } /** diff --git a/fs/ext4/crypto_fname.c b/fs/ext4/crypto_fname.c index 5e5afb6ef71a..026716bdbbfc 100644 --- a/fs/ext4/crypto_fname.c +++ b/fs/ext4/crypto_fname.c @@ -42,6 +42,12 @@ static void ext4_dir_crypt_complete(struct crypto_async_request *req, int res) complete(&ecr->completion); } +bool ext4_valid_filenames_enc_mode(uint32_t mode) +{ + return (mode == EXT4_ENCRYPTION_MODE_AES_256_CTS || + mode == EXT4_ENCRYPTION_MODE_AES_256_HEH); +} + static unsigned max_name_len(struct inode *inode) { return S_ISLNK(inode->i_mode) ? inode->i_sb->s_blocksize : diff --git a/fs/ext4/crypto_key.c b/fs/ext4/crypto_key.c index 68225223ffd8..14ae7781f2a8 100644 --- a/fs/ext4/crypto_key.c +++ b/fs/ext4/crypto_key.c @@ -258,12 +258,6 @@ int ext4_get_encryption_info(struct inode *inode) case EXT4_ENCRYPTION_MODE_AES_256_HEH: cipher_str = "heh(aes)"; break; - case EXT4_ENCRYPTION_MODE_SPECK128_256_XTS: - cipher_str = "xts(speck128)"; - break; - case EXT4_ENCRYPTION_MODE_SPECK128_256_CTS: - cipher_str = "cts(cbc(speck128))"; - break; default: printk_once(KERN_WARNING "ext4: unsupported key mode %d (ino %u)\n", diff --git a/fs/ext4/crypto_policy.c b/fs/ext4/crypto_policy.c index 818fa45ecf08..e4f4fc4e56ab 100644 --- a/fs/ext4/crypto_policy.c +++ b/fs/ext4/crypto_policy.c @@ -60,12 +60,16 @@ static int ext4_create_encryption_context_from_policy( ctx.format = EXT4_ENCRYPTION_CONTEXT_FORMAT_V1; memcpy(ctx.master_key_descriptor, policy->master_key_descriptor, EXT4_KEY_DESCRIPTOR_SIZE); - if (!ext4_valid_enc_modes(policy->contents_encryption_mode, - policy->filenames_encryption_mode)) { + if (!ext4_valid_contents_enc_mode(policy->contents_encryption_mode)) { printk(KERN_WARNING - "%s: Invalid encryption modes (contents %d, filenames %d)\n", - __func__, policy->contents_encryption_mode, - policy->filenames_encryption_mode); + "%s: Invalid contents encryption mode %d\n", __func__, + policy->contents_encryption_mode); + return -EINVAL; + } + if (!ext4_valid_filenames_enc_mode(policy->filenames_encryption_mode)) { + printk(KERN_WARNING + "%s: Invalid filenames encryption mode %d\n", __func__, + policy->filenames_encryption_mode); return -EINVAL; } if (policy->flags & ~EXT4_POLICY_FLAGS_VALID) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8452a5a405f4..977a74234287 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -589,8 +589,6 @@ enum { #define EXT4_ENCRYPTION_MODE_AES_256_GCM 2 #define EXT4_ENCRYPTION_MODE_AES_256_CBC 3 #define EXT4_ENCRYPTION_MODE_AES_256_CTS 4 -#define EXT4_ENCRYPTION_MODE_SPECK128_256_XTS 7 -#define EXT4_ENCRYPTION_MODE_SPECK128_256_CTS 8 #define EXT4_ENCRYPTION_MODE_AES_256_HEH 126 #include "ext4_crypto.h" @@ -2256,7 +2254,7 @@ int ext4_get_policy(struct inode *inode, /* crypto.c */ extern struct kmem_cache *ext4_crypt_info_cachep; -bool ext4_valid_enc_modes(uint32_t contents_mode, uint32_t filenames_mode); +bool ext4_valid_contents_enc_mode(uint32_t mode); uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size); extern struct workqueue_struct *ext4_read_workqueue; struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode, @@ -2287,6 +2285,7 @@ static inline int ext4_sb_has_crypto(struct super_block *sb) #endif /* crypto_fname.c */ +bool ext4_valid_filenames_enc_mode(uint32_t mode); u32 ext4_fname_crypto_round_up(u32 size, u32 blksize); unsigned ext4_fname_encrypted_size(struct inode *inode, u32 ilen); int ext4_fname_crypto_alloc_buffer(struct inode *inode, @@ -3042,9 +3041,6 @@ extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode, extern int ext4_inline_data_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, int *has_inline, __u64 start, __u64 len); -extern int ext4_try_to_evict_inline_data(handle_t *handle, - struct inode *inode, - int needed); extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline); extern int ext4_convert_inline_data(struct inode *inode); diff --git a/fs/ext4/ext4_crypto.h b/fs/ext4/ext4_crypto.h index f7ba3be9d7ac..e52637d969db 100644 --- a/fs/ext4/ext4_crypto.h +++ b/fs/ext4/ext4_crypto.h @@ -124,10 +124,6 @@ static inline int ext4_encryption_key_size(int mode) return EXT4_AES_256_CTS_KEY_SIZE; case EXT4_ENCRYPTION_MODE_AES_256_HEH: return EXT4_AES_256_HEH_KEY_SIZE; - case EXT4_ENCRYPTION_MODE_SPECK128_256_XTS: - return 64; - case EXT4_ENCRYPTION_MODE_SPECK128_256_CTS: - return 32; default: BUG(); } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index f1375d3ad5c1..99ed5b9f2b86 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -873,7 +873,7 @@ int ext4_da_write_inline_data_begin(struct address_space *mapping, handle_t *handle; struct page *page; struct ext4_iloc iloc; - int retries; + int retries = 0; ret = ext4_get_inode_loc(inode, &iloc); if (ret) @@ -902,11 +902,11 @@ retry_journal: flags |= AOP_FLAG_NOFS; if (ret == -ENOSPC) { + ext4_journal_stop(handle); ret = ext4_da_convert_inline_data_to_extent(mapping, inode, flags, fsdata); - ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry_journal; @@ -1881,42 +1881,6 @@ out: return (error < 0 ? error : 0); } -/* - * Called during xattr set, and if we can sparse space 'needed', - * just create the extent tree evict the data to the outer block. - * - * We use jbd2 instead of page cache to move data to the 1st block - * so that the whole transaction can be committed as a whole and - * the data isn't lost because of the delayed page cache write. - */ -int ext4_try_to_evict_inline_data(handle_t *handle, - struct inode *inode, - int needed) -{ - int error; - struct ext4_xattr_entry *entry; - struct ext4_inode *raw_inode; - struct ext4_iloc iloc; - - error = ext4_get_inode_loc(inode, &iloc); - if (error) - return error; - - raw_inode = ext4_raw_inode(&iloc); - entry = (struct ext4_xattr_entry *)((void *)raw_inode + - EXT4_I(inode)->i_inline_off); - if (EXT4_XATTR_LEN(entry->e_name_len) + - EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) { - error = -ENOSPC; - goto out; - } - - error = ext4_convert_inline_data_nolock(handle, inode, &iloc); -out: - brelse(iloc.bh); - return error; -} - void ext4_inline_data_truncate(struct inode *inode, int *has_inline) { handle_t *handle; diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 05048fcfd602..6b5e2eddd8d7 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -526,9 +526,13 @@ mext_check_arguments(struct inode *orig_inode, orig_inode->i_ino, donor_inode->i_ino); return -EINVAL; } - if (orig_eof < orig_start + *len - 1) + if (orig_eof <= orig_start) + *len = 0; + else if (orig_eof < orig_start + *len - 1) *len = orig_eof - orig_start; - if (donor_eof < donor_start + *len - 1) + if (donor_eof <= donor_start) + *len = 0; + else if (donor_eof < donor_start + *len - 1) *len = donor_eof - donor_start; if (!*len) { ext4_debug("ext4 move extent: len should not be 0 " diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a1f1e53d0e25..aa08e129149d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -124,6 +124,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || @@ -2830,7 +2831,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 783280ebc2fe..bad13f049fb0 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -442,16 +442,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block, block - start, count2); ext4_set_bits(bh->b_data, block - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; @@ -588,7 +590,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -600,9 +601,9 @@ handle_bb: ext4_mark_bitmap_end(group_data[i].blocks_count, sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -617,18 +618,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -659,7 +658,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; @@ -846,6 +844,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); @@ -897,6 +896,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -912,8 +912,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } @@ -1095,8 +1093,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -1991,7 +1991,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) @@ -2027,6 +2027,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 959d734806cb..2cd426a4161d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3730,6 +3730,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -3749,14 +3757,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index a9b96d73d7d2..fdea338ce8e1 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -220,12 +220,12 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh) { int error; - if (buffer_verified(bh)) - return 0; - if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) return -EFSCORRUPTED; + if (buffer_verified(bh)) + return 0; + if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh))) return -EFSBADCRC; error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size, @@ -639,14 +639,20 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, } static int -ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s) +ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s, + struct inode *inode) { - struct ext4_xattr_entry *last; + struct ext4_xattr_entry *last, *next; size_t free, min_offs = s->end - s->base, name_len = strlen(i->name); /* Compute min_offs and last. */ last = s->first; - for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { + for (; !IS_LAST_ENTRY(last); last = next) { + next = EXT4_XATTR_NEXT(last); + if ((void *)next >= s->end) { + EXT4_ERROR_INODE(inode, "corrupted xattr entries"); + return -EFSCORRUPTED; + } if (!last->e_value_block && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) @@ -829,7 +835,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, mb2_cache_entry_delete_block(ext4_mb_cache, hash, bs->bh->b_blocknr); ea_bdebug(bs->bh, "modifying in-place"); - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, inode); if (!error) { if (!IS_LAST_ENTRY(s->first)) ext4_xattr_rehash(header(s->base), @@ -875,7 +881,7 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode, s->end = s->base + sb->s_blocksize; } - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, inode); if (error == -EFSCORRUPTED) goto bad_block; if (error) @@ -1063,23 +1069,9 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); - if (error) { - if (error == -ENOSPC && - ext4_has_inline_data(inode)) { - error = ext4_try_to_evict_inline_data(handle, inode, - EXT4_XATTR_LEN(strlen(i->name) + - EXT4_XATTR_SIZE(i->value_len))); - if (error) - return error; - error = ext4_xattr_ibody_find(inode, i, is); - if (error) - return error; - error = ext4_xattr_set_entry(i, s); - } - if (error) - return error; - } + error = ext4_xattr_set_entry(i, s, inode); + if (error) + return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); @@ -1101,7 +1093,7 @@ static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, if (EXT4_I(inode)->i_extra_isize == 0) return -ENOSPC; - error = ext4_xattr_set_entry(i, s); + error = ext4_xattr_set_entry(i, s, inode); if (error) return error; header = IHDR(inode, ext4_raw_inode(&is->iloc)); @@ -1195,6 +1187,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; @@ -1412,6 +1406,11 @@ retry: /* Find the entry best suited to be pushed into EA block */ entry = NULL; for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { + /* never move system.data out of the inode */ + if ((last->e_name_len == 4) && + (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) && + !memcmp(last->e_name, "data", 4)) + continue; total_size = EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) + EXT4_XATTR_LEN(last->e_name_len); @@ -1517,6 +1516,8 @@ cleanup: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); brelse(bh); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 3f52efa0f94f..f82f916e1f2c 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/f2fs_fs.h> #include "f2fs.h" @@ -53,6 +50,9 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); const char *end = value + size; + if (size < sizeof(struct f2fs_acl_header)) + return ERR_PTR(-EINVAL); + if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) return ERR_PTR(-EINVAL); @@ -397,12 +397,16 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage, error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl, ipage); posix_acl_release(default_acl); + } else { + inode->i_default_acl = NULL; } if (acl) { if (!error) error = __f2fs_set_acl(inode, ACL_TYPE_ACCESS, acl, ipage); posix_acl_release(acl); + } else { + inode->i_acl = NULL; } return error; diff --git a/fs/f2fs/acl.h b/fs/f2fs/acl.h index 2c685185c24d..b96823c59b15 100644 --- a/fs/f2fs/acl.h +++ b/fs/f2fs/acl.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.h * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext2/acl.h * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_ACL_H__ #define __F2FS_ACL_H__ diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index f7cdd3b536e3..4ed2d2a0bf02 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/checkpoint.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/bio.h> @@ -122,11 +119,8 @@ retry: if (PTR_ERR(page) == -EIO && ++count <= DEFAULT_RETRY_IO_COUNT) goto retry; - f2fs_stop_checkpoint(sbi, false); - f2fs_bug_on(sbi, 1); } - return page; } @@ -283,8 +277,7 @@ 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); @@ -697,6 +690,8 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) /* clear Orphan Flag */ clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG); out: + set_sbi_flag(sbi, SBI_IS_RECOVERED); + #ifdef CONFIG_QUOTA /* Turn quotas off */ if (quota_enabled) @@ -1085,6 +1080,21 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi) ckpt->next_free_nid = cpu_to_le32(last_nid); } +static bool __need_flush_quota(struct f2fs_sb_info *sbi) +{ + if (!is_journalled_quota(sbi)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + return false; + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_FLUSH)) + return true; + if (get_pages(sbi, F2FS_DIRTY_QDATA)) + return true; + return false; +} + /* * Freeze all the FS-operations for checkpoint. */ @@ -1096,12 +1106,36 @@ static int block_operations(struct f2fs_sb_info *sbi) .for_reclaim = 0, }; struct blk_plug plug; - int err = 0; + int err = 0, cnt = 0; blk_start_plug(&plug); -retry_flush_dents: +retry_flush_quotas: + if (__need_flush_quota(sbi)) { + int locked; + + if (++cnt > DEFAULT_RETRY_QUOTA_FLUSH_COUNT) { + set_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + f2fs_lock_all(sbi); + goto retry_flush_dents; + } + clear_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + /* only failed during mount/umount/freeze/quotactl */ + locked = down_read_trylock(&sbi->sb->s_umount); + f2fs_quota_sync(sbi->sb, -1); + if (locked) + up_read(&sbi->sb->s_umount); + } + f2fs_lock_all(sbi); + if (__need_flush_quota(sbi)) { + f2fs_unlock_all(sbi); + cond_resched(); + goto retry_flush_quotas; + } + +retry_flush_dents: /* write all the dirty dentry pages */ if (get_pages(sbi, F2FS_DIRTY_DENTS)) { f2fs_unlock_all(sbi); @@ -1109,7 +1143,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } /* @@ -1118,6 +1152,12 @@ retry_flush_dents: */ down_write(&sbi->node_change); + if (__need_flush_quota(sbi)) { + up_write(&sbi->node_change); + f2fs_unlock_all(sbi); + goto retry_flush_quotas; + } + if (get_pages(sbi, F2FS_DIRTY_IMETA)) { up_write(&sbi->node_change); f2fs_unlock_all(sbi); @@ -1125,7 +1165,7 @@ retry_flush_dents: if (err) goto out; cond_resched(); - goto retry_flush_dents; + goto retry_flush_quotas; } retry_flush_nodes: @@ -1216,6 +1256,19 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc) if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) __set_ckpt_flags(ckpt, CP_FSCK_FLAG); + if (is_sbi_flag_set(sbi, SBI_CP_DISABLED)) + __set_ckpt_flags(ckpt, CP_DISABLED_FLAG); + else + __clear_ckpt_flags(ckpt, CP_DISABLED_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_SKIP_FLUSH)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + else + __clear_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + + if (is_sbi_flag_set(sbi, SBI_QUOTA_NEED_REPAIR)) + __set_ckpt_flags(ckpt, CP_QUOTA_NEED_FSCK_FLAG); + /* set this flag to activate crc|cp_ver for recovery */ __set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG); __clear_ckpt_flags(ckpt, CP_NOCRC_RECOVERY_FLAG); @@ -1423,6 +1476,8 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) clear_sbi_flag(sbi, SBI_IS_DIRTY); clear_sbi_flag(sbi, SBI_NEED_CP); + clear_sbi_flag(sbi, SBI_QUOTA_SKIP_FLUSH); + sbi->unusable_block_count = 0; __set_cp_next_pack(sbi); /* @@ -1447,6 +1502,12 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned long long ckpt_ver; int err = 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + if (cpc->reason != CP_PAUSE) + return 0; + f2fs_msg(sbi->sb, KERN_WARNING, + "Start checkpoint disabled!"); + } mutex_lock(&sbi->cp_mutex); if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) && @@ -1498,7 +1559,10 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver); /* write cached NAT/SIT entries to NAT/SIT area */ - f2fs_flush_nat_entries(sbi, cpc); + err = f2fs_flush_nat_entries(sbi, cpc); + if (err) + goto stop; + f2fs_flush_sit_entries(sbi, cpc); /* unlock all the fs_lock[] in do_checkpoint() */ @@ -1507,7 +1571,7 @@ int f2fs_write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) f2fs_release_discard_addrs(sbi); else f2fs_clear_prefree_segments(sbi, cpc); - +stop: unblock_operations(sbi); stat_inc_cp_count(sbi->stat_info); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index c62bec58f37e..8286f2114c37 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/data.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -49,12 +46,29 @@ static bool __is_cp_guaranteed(struct page *page) inode->i_ino == F2FS_NODE_INO(sbi) || S_ISDIR(inode->i_mode) || (S_ISREG(inode->i_mode) && - is_inode_flag_set(inode, FI_ATOMIC_FILE)) || + (f2fs_is_atomic_file(inode) || IS_NOQUOTA(inode))) || is_cold_data(page)) return true; return false; } +static enum count_type __read_io_type(struct page *page) +{ + struct address_space *mapping = page->mapping; + + if (mapping) { + struct inode *inode = mapping->host; + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + + if (inode->i_ino == F2FS_META_INO(sbi)) + return F2FS_RD_META; + + if (inode->i_ino == F2FS_NODE_INO(sbi)) + return F2FS_RD_NODE; + } + return F2FS_RD_DATA; +} + /* postprocessing steps for read bios */ enum bio_post_read_step { STEP_INITIAL = 0, @@ -80,10 +94,12 @@ static void __read_end_io(struct bio *bio) /* PG_error was set if any post_read step failed */ if (bio->bi_error || PageError(page)) { ClearPageUptodate(page); - SetPageError(page); + /* will re-read again later */ + ClearPageError(page); } else { SetPageUptodate(page); } + dec_page_count(F2FS_P_SB(page), __read_io_type(page)); unlock_page(page); } if (bio->bi_private) @@ -126,8 +142,8 @@ static bool f2fs_bio_post_read_required(struct bio *bio) static void f2fs_read_end_io(struct bio *bio) { - if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) { - f2fs_show_injection_info(FAULT_IO); + if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_READ_IO)) { + f2fs_show_injection_info(FAULT_READ_IO); bio->bi_error = -EIO; } @@ -148,6 +164,11 @@ static void f2fs_write_end_io(struct bio *bio) struct bio_vec *bvec; int i; + if (time_to_inject(sbi, FAULT_WRITE_IO)) { + f2fs_show_injection_info(FAULT_WRITE_IO); + bio->bi_error = -EIO; + } + bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; enum count_type type = WB_DATA_TYPE(page); @@ -318,8 +339,8 @@ 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; @@ -328,7 +349,7 @@ 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) { @@ -338,11 +359,10 @@ 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; } @@ -351,7 +371,8 @@ 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; @@ -362,7 +383,7 @@ 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. */ @@ -393,12 +414,12 @@ 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++) { @@ -417,10 +438,10 @@ 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) @@ -455,12 +476,16 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) bio_put(bio); return -EFAULT; } + + if (fio->io_wbc && !is_read_io(fio->op)) + wbc_account_io(fio->io_wbc, page, PAGE_SIZE); + bio_set_op_attrs(bio, fio->op, fio->op_flags); - __submit_bio(fio->sbi, bio, fio->type); + inc_page_count(fio->sbi, is_read_io(fio->op) ? + __read_io_type(page): WB_DATA_TYPE(fio->page)); - if (!is_read_io(fio->op)) - inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page)); + __submit_bio(fio->sbi, bio, fio->type); return 0; } @@ -532,6 +557,9 @@ skip: if (fio->in_list) goto next; out: + if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || + f2fs_is_checkpoint_ready(sbi)) + __submit_merged_bio(io); up_write(&io->io_rwsem); } @@ -564,9 +592,6 @@ static struct bio *f2fs_grab_read_bio(struct inode *inode, block_t blkaddr, ctx->bio = bio; ctx->enabled_steps = post_read_steps; bio->bi_private = ctx; - - /* wait the page to be moved by cleaning */ - f2fs_wait_on_block_writeback(sbi, blkaddr); } return bio; @@ -581,10 +606,15 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, if (IS_ERR(bio)) return PTR_ERR(bio); + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, blkaddr); + if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) { bio_put(bio); return -EFAULT; } + ClearPageError(page); + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); __submit_bio(F2FS_I_SB(inode), bio, DATA); return 0; } @@ -875,7 +905,6 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) struct f2fs_summary sum; struct node_info ni; block_t old_blkaddr; - pgoff_t fofs; blkcnt_t count = 1; int err; @@ -888,7 +917,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); - if (dn->data_blkaddr == NEW_ADDR) + if (dn->data_blkaddr != NULL_ADDR) goto alloc; if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) @@ -904,12 +933,10 @@ alloc: old_blkaddr, old_blkaddr); f2fs_set_data_blkaddr(dn); - /* update i_size */ - fofs = f2fs_start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + - dn->ofs_in_node; - if (i_size_read(dn->inode) < ((loff_t)(fofs + 1) << PAGE_SHIFT)) - f2fs_i_size_write(dn->inode, - ((loff_t)(fofs + 1) << PAGE_SHIFT)); + /* + * i_size will be updated by direct_IO. Otherwise, we'll get stale + * data from unwritten block via dio_read. + */ return 0; } @@ -944,7 +971,7 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from) if (direct_io) { map.m_seg_type = f2fs_rw_hint_to_seg_type(iocb->ki_hint); - flag = f2fs_force_buffered_io(inode, WRITE) ? + flag = f2fs_force_buffered_io(inode, iocb, from) ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; goto map_blocks; @@ -969,7 +996,7 @@ map_blocks: return err; } -static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock) { if (flag == F2FS_GET_BLOCK_PRE_AIO) { if (lock) @@ -1024,6 +1051,11 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, map->m_flags = F2FS_MAP_MAPPED; if (map->m_next_extent) *map->m_next_extent = pgofs + map->m_len; + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); goto out; } @@ -1063,7 +1095,15 @@ next_block: goto sync_out; } - if (!is_valid_data_blkaddr(sbi, blkaddr)) { + if (is_valid_data_blkaddr(sbi, blkaddr)) { + /* use out-place-update for driect IO under LFS mode */ + if (test_opt(sbi, LFS) && create && + flag == F2FS_GET_BLOCK_DIO) { + err = __allocate_data_block(&dn, map->m_seg_type); + if (!err) + set_inode_flag(inode, FI_APPEND_WRITE); + } + } else { if (create) { if (unlikely(f2fs_cp_error(sbi))) { err = -EIO; @@ -1075,6 +1115,8 @@ next_block: last_ofs_in_node = dn.ofs_in_node; } } else { + WARN_ON(flag != F2FS_GET_BLOCK_PRE_DIO && + flag != F2FS_GET_BLOCK_DIO); err = __allocate_data_block(&dn, map->m_seg_type); if (!err) @@ -1172,6 +1214,12 @@ skip: goto next_dnode; sync_out: + + /* for hardware encryption, but to avoid potential issue in future */ + if (flag == F2FS_GET_BLOCK_DIO && map->m_flags & F2FS_MAP_MAPPED) + f2fs_wait_on_block_writeback_range(inode, + map->m_pblk, map->m_len); + if (flag == F2FS_GET_BLOCK_PRECACHE) { if (map->m_flags & F2FS_MAP_MAPPED) { unsigned int ofs = start_pgofs - map->m_lblk; @@ -1254,7 +1302,7 @@ static int get_data_block_dio(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return __get_data_block(inode, iblock, bh_result, create, - F2FS_GET_BLOCK_DEFAULT, NULL, + F2FS_GET_BLOCK_DIO, NULL, f2fs_rw_hint_to_seg_type( inode->i_write_hint)); } @@ -1556,9 +1604,17 @@ submit_and_realloc: } } + /* + * If the page is under writeback, we need to wait for + * its completion to see the correct decrypted data. + */ + f2fs_wait_on_block_writeback(inode, block_nr); + if (bio_add_page(bio, page, blocksize, 0) < blocksize) goto submit_and_realloc; + inc_page_count(F2FS_I_SB(inode), F2FS_RD_DATA); + ClearPageError(page); last_block_in_bio = block_nr; goto next_page; set_error_page: @@ -1623,7 +1679,7 @@ static int encrypt_one_page(struct f2fs_io_info *fio) return 0; /* wait for GCed page writeback via META_MAPPING */ - f2fs_wait_on_block_writeback(fio->sbi, fio->old_blkaddr); + f2fs_wait_on_block_writeback(inode, fio->old_blkaddr); retry_encrypt: fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page, @@ -1680,6 +1736,10 @@ static inline bool check_inplace_update_policy(struct inode *inode, is_inode_flag_set(inode, FI_NEED_IPU)) return true; + if (unlikely(fio && is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + !f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; + return false; } @@ -1703,6 +1763,8 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (S_ISDIR(inode->i_mode)) return true; + if (IS_NOQUOTA(inode)) + return true; if (f2fs_is_atomic_file(inode)) return true; if (fio) { @@ -1710,6 +1772,9 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio) return true; if (IS_ATOMIC_WRITTEN_PAGE(fio->page)) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + f2fs_is_checkpointed_data(sbi, fio->old_blkaddr))) + return true; } return false; } @@ -1761,6 +1826,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio) /* This page is already truncated */ if (fio->old_blkaddr == NULL_ADDR) { ClearPageUptodate(page); + clear_cold_data(page); goto out_writepage; } got_it: @@ -1936,18 +2002,20 @@ done: out: inode_dec_dirty_pages(inode); - if (err) + if (err) { ClearPageUptodate(page); + clear_cold_data(page); + } 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; } unlock_page(page); - if (!S_ISDIR(inode->i_mode)) + if (!S_ISDIR(inode->i_mode) && !IS_NOQUOTA(inode)) f2fs_balance_fs(sbi, need_balance_fs); if (unlikely(f2fs_cp_error(sbi))) { @@ -1998,10 +2066,10 @@ 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, 0); @@ -2104,7 +2172,7 @@ continue_unlock: done = 1; break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (--wbc->nr_to_write <= 0 && @@ -2126,9 +2194,9 @@ continue_unlock: 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; } @@ -2138,6 +2206,8 @@ static inline bool __should_serialize_io(struct inode *inode, { if (!S_ISREG(inode->i_mode)) return false; + if (IS_NOQUOTA(inode)) + return false; if (wbc->sync_mode != WB_SYNC_ALL) return true; if (get_dirty_pages(inode) >= SM_I(F2FS_I_SB(inode))->min_seq_blocks) @@ -2167,7 +2237,8 @@ static int __f2fs_write_data_pages(struct address_space *mapping, if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; - if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE && + if ((S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) && + wbc->sync_mode == WB_SYNC_NONE && get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) && f2fs_available_free_memory(sbi, DIRTY_DENTS)) goto skip_write; @@ -2232,7 +2303,7 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to) down_write(&F2FS_I(inode)->i_mmap_sem); truncate_pagecache(inode, i_size); - f2fs_truncate_blocks(inode, i_size, true); + f2fs_truncate_blocks(inode, i_size, true, true); up_write(&F2FS_I(inode)->i_mmap_sem); up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); @@ -2340,6 +2411,10 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, } trace_f2fs_write_begin(inode, pos, len, flags); + err = f2fs_is_checkpoint_ready(sbi); + if (err) + goto fail; + if ((f2fs_is_atomic_file(inode) && !f2fs_available_free_memory(sbi, INMEM_PAGES)) || is_inode_flag_set(inode, FI_ATOMIC_REVOKE_REQUEST)) { @@ -2377,7 +2452,8 @@ repeat: if (err) goto fail; - if (need_balance && has_not_enough_free_secs(sbi, 0, 0)) { + if (need_balance && !IS_NOQUOTA(inode) && + has_not_enough_free_secs(sbi, 0, 0)) { unlock_page(page); f2fs_balance_fs(sbi, true); lock_page(page); @@ -2390,10 +2466,6 @@ repeat: f2fs_wait_on_page_writeback(page, DATA, false); - /* wait for GCed page writeback via META_MAPPING */ - if (f2fs_post_read_required(inode)) - f2fs_wait_on_block_writeback(sbi, blkaddr); - if (len == PAGE_SIZE || PageUptodate(page)) return 0; @@ -2490,17 +2562,19 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + struct f2fs_inode_info *fi = F2FS_I(inode); size_t count = iov_iter_count(iter); int rw = iov_iter_rw(iter); int err; enum rw_hint hint = iocb->ki_hint; int whint_mode = F2FS_OPTION(sbi).whint_mode; + bool do_opu; err = check_direct_IO(inode, iter, offset); if (err) return err < 0 ? err : 0; - if (f2fs_force_buffered_io(inode, rw)) + if (f2fs_force_buffered_io(inode, iocb, iter)) return 0; if (trace_android_fs_dataread_start_enabled() && @@ -2525,22 +2599,38 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, current->pid, path, current->comm); } + + do_opu = allow_outplace_dio(inode, iocb, iter); + trace_f2fs_direct_IO_enter(inode, offset, count, rw); if (rw == WRITE && whint_mode == WHINT_MODE_OFF) iocb->ki_hint = WRITE_LIFE_NOT_SET; - if (!down_read_trylock(&F2FS_I(inode)->i_gc_rwsem[rw])) { - if (iocb->ki_flags & IOCB_NOWAIT) { + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!down_read_trylock(&fi->i_gc_rwsem[rw])) { iocb->ki_hint = hint; err = -EAGAIN; goto out; } - down_read(&F2FS_I(inode)->i_gc_rwsem[rw]); + if (do_opu && !down_read_trylock(&fi->i_gc_rwsem[READ])) { + up_read(&fi->i_gc_rwsem[rw]); + iocb->ki_hint = hint; + err = -EAGAIN; + goto out; + } + } else { + down_read(&fi->i_gc_rwsem[rw]); + if (do_opu) + down_read(&fi->i_gc_rwsem[READ]); } err = blockdev_direct_IO(iocb, inode, iter, offset, get_data_block_dio); - up_read(&F2FS_I(inode)->i_gc_rwsem[rw]); + + if (do_opu) + up_read(&fi->i_gc_rwsem[READ]); + + up_read(&fi->i_gc_rwsem[rw]); if (rw == WRITE) { if (whint_mode == WHINT_MODE_OFF) @@ -2548,7 +2638,8 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (err > 0) { f2fs_update_iostat(F2FS_I_SB(inode), APP_DIRECT_IO, err); - set_inode_flag(inode, FI_UPDATE_WRITE); + if (!do_opu) + set_inode_flag(inode, FI_UPDATE_WRITE); } else if (err < 0) { f2fs_write_failed(mapping, offset + count); } @@ -2587,6 +2678,8 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset, } } + clear_cold_data(page); + /* This is atomic written page, keep Private */ if (IS_ATOMIC_WRITTEN_PAGE(page)) return f2fs_drop_inmem_page(inode, page); @@ -2605,6 +2698,7 @@ int f2fs_release_page(struct page *page, gfp_t wait) if (IS_ATOMIC_WRITTEN_PAGE(page)) return 0; + clear_cold_data(page); set_page_private(page, 0); ClearPagePrivate(page); return 1; @@ -2620,10 +2714,6 @@ static int f2fs_set_data_page_dirty(struct page *page) if (!PageUptodate(page)) SetPageUptodate(page); - /* don't remain PG_checked flag which was set during GC */ - if (is_cold_data(page)) - clear_cold_data(page); - if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) { if (!IS_ATOMIC_WRITTEN_PAGE(page)) { f2fs_register_inmem_page(inode, page); diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c index 214a968962a1..139b4d5c83d5 100644 --- a/fs/f2fs/debug.c +++ b/fs/f2fs/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs debugging statistics * @@ -5,10 +6,6 @@ * http://www.samsung.com/ * Copyright (c) 2012 Linux Foundation * Copyright (c) 2012 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -58,6 +55,9 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt); si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA); si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA); + si->nr_rd_data = get_pages(sbi, F2FS_RD_DATA); + si->nr_rd_node = get_pages(sbi, F2FS_RD_NODE); + si->nr_rd_meta = get_pages(sbi, F2FS_RD_META); if (SM_I(sbi) && SM_I(sbi)->fcc_info) { si->nr_flushed = atomic_read(&SM_I(sbi)->fcc_info->issued_flush); @@ -104,6 +104,8 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->avail_nids = NM_I(sbi)->available_nids; si->alloc_nids = NM_I(sbi)->nid_cnt[PREALLOC_NID]; si->bg_gc = sbi->bg_gc; + si->io_skip_bggc = sbi->io_skip_bggc; + si->other_skip_bggc = sbi->other_skip_bggc; si->skipped_atomic_files[BG_GC] = sbi->skipped_atomic_files[BG_GC]; si->skipped_atomic_files[FG_GC] = sbi->skipped_atomic_files[FG_GC]; si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg) @@ -121,6 +123,9 @@ static void update_general_status(struct f2fs_sb_info *sbi) si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]); } + for (i = META_CP; i < META_MAX; i++) + si->meta_count[i] = atomic_read(&sbi->meta_count[i]); + for (i = 0; i < 2; i++) { si->segment_count[i] = sbi->segment_count[i]; si->block_count[i] = sbi->block_count[i]; @@ -190,8 +195,7 @@ static void update_mem_info(struct f2fs_sb_info *sbi) si->base_mem += MAIN_SEGS(sbi) * sizeof(struct seg_entry); si->base_mem += f2fs_bitmap_size(MAIN_SEGS(sbi)); si->base_mem += 2 * SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); - if (f2fs_discard_en(sbi)) - si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); + si->base_mem += SIT_VBLOCK_MAP_SIZE * MAIN_SEGS(sbi); si->base_mem += SIT_VBLOCK_MAP_SIZE; if (sbi->segs_per_sec > 1) si->base_mem += MAIN_SECS(sbi) * sizeof(struct sec_entry); @@ -271,7 +275,8 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, "\n=====[ partition info(%pg). #%d, %s, CP: %s]=====\n", si->sbi->sb->s_bdev, i++, f2fs_readonly(si->sbi->sb) ? "RO": "RW", - f2fs_cp_error(si->sbi) ? "Error": "Good"); + is_set_ckpt_flags(si->sbi, CP_DISABLED_FLAG) ? + "Disabled": (f2fs_cp_error(si->sbi) ? "Error": "Good")); seq_printf(s, "[SB: 1] [CP: 2] [SIT: %d] [NAT: %d] ", si->sit_area_segs, si->nat_area_segs); seq_printf(s, "[SSA: %d] [MAIN: %d", @@ -333,6 +338,13 @@ static int stat_show(struct seq_file *s, void *v) si->prefree_count, si->free_segs, si->free_secs); seq_printf(s, "CP calls: %d (BG: %d)\n", si->cp_count, si->bg_cp_count); + seq_printf(s, " - cp blocks : %u\n", si->meta_count[META_CP]); + seq_printf(s, " - sit blocks : %u\n", + si->meta_count[META_SIT]); + seq_printf(s, " - nat blocks : %u\n", + si->meta_count[META_NAT]); + seq_printf(s, " - ssa blocks : %u\n", + si->meta_count[META_SSA]); seq_printf(s, "GC calls: %d (BG: %d)\n", si->call_count, si->bg_gc); seq_printf(s, " - data segments : %d (%d)\n", @@ -349,6 +361,8 @@ static int stat_show(struct seq_file *s, void *v) si->skipped_atomic_files[BG_GC] + si->skipped_atomic_files[FG_GC], si->skipped_atomic_files[BG_GC]); + seq_printf(s, "BG skip : IO: %u, Other: %u\n", + si->io_skip_bggc, si->other_skip_bggc); seq_puts(s, "\nExtent Cache:\n"); seq_printf(s, " - Hit Count: L1-1:%llu L1-2:%llu L2:%llu\n", si->hit_largest, si->hit_cached, @@ -360,7 +374,9 @@ static int stat_show(struct seq_file *s, void *v) seq_printf(s, " - Inner Struct Count: tree: %d(%d), node: %d\n", si->ext_tree, si->zombie_tree, si->ext_node); seq_puts(s, "\nBalancing F2FS Async:\n"); - seq_printf(s, " - IO (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), " + seq_printf(s, " - IO_R (Data: %4d, Node: %4d, Meta: %4d\n", + si->nr_rd_data, si->nr_rd_node, si->nr_rd_meta); + seq_printf(s, " - IO_W (CP: %4d, Data: %4d, Flush: (%4d %4d %4d), " "Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n", si->nr_wb_cp_data, si->nr_wb_data, si->nr_flushing, si->nr_flushed, @@ -445,6 +461,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_stat_info *si; + int i; si = f2fs_kzalloc(sbi, sizeof(struct f2fs_stat_info), GFP_KERNEL); if (!si) @@ -470,6 +487,8 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi) atomic_set(&sbi->inline_inode, 0); atomic_set(&sbi->inline_dir, 0); atomic_set(&sbi->inplace_count, 0); + for (i = META_CP; i < META_MAX; i++) + atomic_set(&sbi->meta_count[i], 0); atomic_set(&sbi->aw_cnt, 0); atomic_set(&sbi->vw_cnt, 0); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 086639556705..eedc07b46a52 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/dir.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -658,9 +655,9 @@ int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) f2fs_put_page(page, 1); clear_inode_flag(inode, FI_NEW_INODE); + f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); fail: up_write(&F2FS_I(inode)->i_sem); - f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return err; } @@ -733,6 +730,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, clear_page_dirty_for_io(page); ClearPagePrivate(page); ClearPageUptodate(page); + clear_cold_data(page); inode_dec_dirty_pages(dir); f2fs_remove_dirty_inode(dir); } @@ -784,9 +782,15 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, struct f2fs_dir_entry *de = NULL; struct fscrypt_str de_name = FSTR_INIT(NULL, 0); struct f2fs_sb_info *sbi = F2FS_I_SB(d->inode); + struct blk_plug plug; + bool readdir_ra = sbi->readdir_ra == 1; + int err = 0; bit_pos = ((unsigned long)ctx->pos % d->max); + if (readdir_ra) + blk_start_plug(&plug); + while (bit_pos < d->max) { bit_pos = find_next_bit_le(d->bitmap, d->max, bit_pos); if (bit_pos >= d->max) @@ -806,29 +810,33 @@ int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d, if (f2fs_encrypted_inode(d->inode)) { int save_len = fstr->len; - int err; err = fscrypt_fname_disk_to_usr(d->inode, (u32)de->hash_code, 0, &de_name, fstr); if (err) - return err; + goto out; de_name = *fstr; fstr->len = save_len; } if (!dir_emit(ctx, de_name.name, de_name.len, - le32_to_cpu(de->ino), d_type)) - return 1; + le32_to_cpu(de->ino), d_type)) { + err = 1; + goto out; + } - if (sbi->readdir_ra == 1) + if (readdir_ra) f2fs_ra_node_page(sbi, le32_to_cpu(de->ino)); bit_pos += GET_DENTRY_SLOTS(le16_to_cpu(de->name_len)); ctx->pos = start_pos + bit_pos; } - return 0; +out: + if (readdir_ra) + blk_finish_plug(&plug); + return err; } static int f2fs_readdir(struct file *file, struct dir_context *ctx) diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index 231b77ef5a53..904ad7ba5a45 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs extent cache support * @@ -5,10 +6,6 @@ * Copyright (c) 2015 Samsung Electronics * Authors: Jaegeuk Kim <jaegeuk@kernel.org> * Chao Yu <chao2.yu@samsung.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -308,14 +305,13 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi, return count - atomic_read(&et->node_cnt); } -static void __drop_largest_extent(struct inode *inode, +static void __drop_largest_extent(struct extent_tree *et, pgoff_t fofs, unsigned int len) { - struct extent_info *largest = &F2FS_I(inode)->extent_tree->largest; - - if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) { - largest->len = 0; - f2fs_mark_inode_dirty_sync(inode, true); + if (fofs < et->largest.fofs + et->largest.len && + fofs + len > et->largest.fofs) { + et->largest.len = 0; + et->largest_updated = true; } } @@ -416,12 +412,11 @@ out: return ret; } -static struct extent_node *__try_merge_extent_node(struct inode *inode, +static struct extent_node *__try_merge_extent_node(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct extent_node *prev_ex, struct extent_node *next_ex) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_node *en = NULL; if (prev_ex && __is_back_mergeable(ei, &prev_ex->ei)) { @@ -443,7 +438,7 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); spin_lock(&sbi->extent_lock); if (!list_empty(&en->list)) { @@ -454,12 +449,11 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode, return en; } -static struct extent_node *__insert_extent_tree(struct inode *inode, +static struct extent_node *__insert_extent_tree(struct f2fs_sb_info *sbi, struct extent_tree *et, struct extent_info *ei, struct rb_node **insert_p, struct rb_node *insert_parent) { - struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct rb_node **p; struct rb_node *parent = NULL; struct extent_node *en = NULL; @@ -476,7 +470,7 @@ do_insert: if (!en) return NULL; - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); /* update in global extent list */ spin_lock(&sbi->extent_lock); @@ -497,6 +491,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, struct rb_node **insert_p = NULL, *insert_parent = NULL; unsigned int end = fofs + len; unsigned int pos = (unsigned int)fofs; + bool updated = false; if (!et) return; @@ -517,7 +512,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, * drop largest extent before lookup, in case it's already * been shrunk from extent tree */ - __drop_largest_extent(inode, fofs, len); + __drop_largest_extent(et, fofs, len); /* 1. lookup first extent node in range [fofs, fofs + len - 1] */ en = (struct extent_node *)f2fs_lookup_rb_tree_ret(&et->root, @@ -550,7 +545,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, set_extent_info(&ei, end, end - dei.fofs + dei.blk, org_end - end); - en1 = __insert_extent_tree(inode, et, &ei, + en1 = __insert_extent_tree(sbi, et, &ei, NULL, NULL); next_en = en1; } else { @@ -570,7 +565,7 @@ static void f2fs_update_extent_tree_range(struct inode *inode, } if (parts) - __try_update_largest_extent(inode, et, en); + __try_update_largest_extent(et, en); else __release_extent_node(sbi, et, en); @@ -590,15 +585,16 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (blkaddr) { set_extent_info(&ei, fofs, blkaddr, len); - if (!__try_merge_extent_node(inode, et, &ei, prev_en, next_en)) - __insert_extent_tree(inode, et, &ei, + if (!__try_merge_extent_node(sbi, et, &ei, prev_en, next_en)) + __insert_extent_tree(sbi, et, &ei, insert_p, insert_parent); /* give up extent_cache, if split and small updates happen */ if (dei.len >= 1 && prev.len < F2FS_MIN_EXTENT_LEN && et->largest.len < F2FS_MIN_EXTENT_LEN) { - __drop_largest_extent(inode, 0, UINT_MAX); + et->largest.len = 0; + et->largest_updated = true; set_inode_flag(inode, FI_NO_EXTENT); } } @@ -606,7 +602,15 @@ static void f2fs_update_extent_tree_range(struct inode *inode, if (is_inode_flag_set(inode, FI_NO_EXTENT)) __free_extent_tree(sbi, et); + if (et->largest_updated) { + et->largest_updated = false; + updated = true; + } + write_unlock(&et->lock); + + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink) @@ -705,6 +709,7 @@ void f2fs_drop_extent_tree(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct extent_tree *et = F2FS_I(inode)->extent_tree; + bool updated = false; if (!f2fs_may_extent_tree(inode)) return; @@ -713,8 +718,13 @@ void f2fs_drop_extent_tree(struct inode *inode) write_lock(&et->lock); __free_extent_tree(sbi, et); - __drop_largest_extent(inode, 0, UINT_MAX); + if (et->largest.len) { + et->largest.len = 0; + updated = true; + } write_unlock(&et->lock); + if (updated) + f2fs_mark_inode_dirty_sync(inode, true); } void f2fs_destroy_extent_tree(struct inode *inode) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 366b28a17950..b5233ce704fe 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1,16 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/f2fs.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef _LINUX_F2FS_H #define _LINUX_F2FS_H +#include <linux/uio.h> #include <linux/types.h> #include <linux/page-flags.h> #include <linux/buffer_head.h> @@ -55,9 +53,10 @@ enum { FAULT_DIR_DEPTH, FAULT_EVICT_INODE, FAULT_TRUNCATE, - FAULT_IO, + FAULT_READ_IO, FAULT_CHECKPOINT, FAULT_DISCARD, + FAULT_WRITE_IO, FAULT_MAX, }; @@ -104,6 +103,7 @@ extern char *f2fs_fault_name[FAULT_MAX]; #define F2FS_MOUNT_QUOTA 0x00400000 #define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 #define F2FS_MOUNT_RESERVE_ROOT 0x01000000 +#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -154,6 +154,7 @@ struct f2fs_mount_info { #define F2FS_FEATURE_INODE_CRTIME 0x0100 #define F2FS_FEATURE_LOST_FOUND 0x0200 #define F2FS_FEATURE_VERITY 0x0400 /* reserved */ +#define F2FS_FEATURE_SB_CHKSUM 0x0800 #define F2FS_HAS_FEATURE(sb, mask) \ ((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0) @@ -243,6 +244,7 @@ enum { #define CP_RECOVERY 0x00000008 #define CP_DISCARD 0x00000010 #define CP_TRIMMED 0x00000020 +#define CP_PAUSE 0x00000040 #define MAX_DISCARD_BLOCKS(sbi) BLKS_PER_SEC(sbi) #define DEF_MAX_DISCARD_REQUEST 8 /* issue 8 discards per round */ @@ -252,6 +254,7 @@ enum { #define DEF_DISCARD_URGENT_UTIL 80 /* do more discard over 80% */ #define DEF_CP_INTERVAL 60 /* 60 secs */ #define DEF_IDLE_INTERVAL 5 /* 5 secs */ +#define DEF_DISABLE_INTERVAL 5 /* 5 secs */ struct cp_control { int reason; @@ -268,6 +271,7 @@ enum { META_NAT, META_SIT, META_SSA, + META_MAX, META_POR, DATA_GENERIC, META_GENERIC, @@ -589,6 +593,9 @@ enum { #define DEFAULT_RETRY_IO_COUNT 8 /* maximum retry read IO count */ +/* maximum retry quota flush count */ +#define DEFAULT_RETRY_QUOTA_FLUSH_COUNT 8 + #define F2FS_LINK_MAX 0xffffffff /* maximum link count per file */ #define MAX_DIR_RA_PAGES 4 /* maximum ra pages of dir */ @@ -634,6 +641,7 @@ struct extent_tree { struct list_head list; /* to be used by sbi->zombie_list */ rwlock_t lock; /* protect extent info rb-tree */ atomic_t node_cnt; /* # of extent node in rb-tree*/ + bool largest_updated; /* largest extent updated */ }; /* @@ -662,6 +670,7 @@ enum { F2FS_GET_BLOCK_DEFAULT, F2FS_GET_BLOCK_FIEMAP, F2FS_GET_BLOCK_BMAP, + F2FS_GET_BLOCK_DIO, F2FS_GET_BLOCK_PRE_DIO, F2FS_GET_BLOCK_PRE_AIO, F2FS_GET_BLOCK_PRECACHE, @@ -816,12 +825,12 @@ static inline bool __is_front_mergeable(struct extent_info *cur, } extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync); -static inline void __try_update_largest_extent(struct inode *inode, - struct extent_tree *et, struct extent_node *en) +static inline void __try_update_largest_extent(struct extent_tree *et, + struct extent_node *en) { if (en->ei.len > et->largest.len) { et->largest = en->ei; - f2fs_mark_inode_dirty_sync(inode, true); + et->largest_updated = true; } } @@ -1006,6 +1015,9 @@ enum count_type { F2FS_DIRTY_IMETA, F2FS_WB_CP_DATA, F2FS_WB_DATA, + F2FS_RD_DATA, + F2FS_RD_NODE, + F2FS_RD_META, NR_COUNT_TYPE, }; @@ -1150,11 +1162,19 @@ enum { SBI_NEED_SB_WRITE, /* need to recover superblock */ SBI_NEED_CP, /* need to checkpoint */ SBI_IS_SHUTDOWN, /* shutdown by ioctl */ + SBI_IS_RECOVERED, /* recovered orphan/data */ + SBI_CP_DISABLED, /* CP was disabled last mount */ + SBI_QUOTA_NEED_FLUSH, /* need to flush quota info in CP */ + SBI_QUOTA_SKIP_FLUSH, /* skip flushing quota in current CP */ + SBI_QUOTA_NEED_REPAIR, /* quota file may be corrupted */ }; enum { CP_TIME, REQ_TIME, + DISCARD_TIME, + GC_TIME, + DISABLE_TIME, MAX_TIME, }; @@ -1271,7 +1291,6 @@ struct f2fs_sb_info { unsigned int total_valid_node_count; /* valid node block count */ loff_t max_file_blocks; /* max block index of file */ int dir_level; /* directory level */ - unsigned int trigger_ssr_threshold; /* threshold to trigger ssr */ int readdir_ra; /* readahead inode in readdir */ block_t user_block_count; /* # of user blocks */ @@ -1281,6 +1300,9 @@ struct f2fs_sb_info { block_t reserved_blocks; /* configurable reserved blocks */ block_t current_reserved_blocks; /* current reserved blocks */ + /* Additional tracking for no checkpoint mode */ + block_t unusable_block_count; /* # of blocks saved by last cp */ + unsigned int nquota_files; /* # of quota sysfile */ u32 s_next_generation; /* for NFS support */ @@ -1319,6 +1341,7 @@ struct f2fs_sb_info { */ #ifdef CONFIG_F2FS_STAT_FS struct f2fs_stat_info *stat_info; /* FS status information */ + atomic_t meta_count[META_MAX]; /* # of meta blocks */ unsigned int segment_count[2]; /* # of allocated segments */ unsigned int block_count[2]; /* # of allocated blocks */ atomic_t inplace_count; /* # of inplace update */ @@ -1334,6 +1357,8 @@ struct f2fs_sb_info { atomic_t max_aw_cnt; /* max # of atomic writes */ atomic_t max_vw_cnt; /* max # of volatile writes */ int bg_gc; /* background gc calls */ + unsigned int io_skip_bggc; /* skip background gc for in-flight IO */ + unsigned int other_skip_bggc; /* skip background gc for other reasons */ unsigned int ndirty_inode[NR_INODE_TYPE]; /* # of dirty inodes */ #endif spinlock_t stat_lock; /* lock for stat operations */ @@ -1368,9 +1393,9 @@ struct f2fs_sb_info { }; #ifdef CONFIG_F2FS_FAULT_INJECTION -#define f2fs_show_injection_info(type) \ - printk("%sF2FS-fs : inject %s in %s of %pF\n", \ - KERN_INFO, f2fs_fault_name[type], \ +#define f2fs_show_injection_info(type) \ + printk_ratelimited("%sF2FS-fs : inject %s in %s of %pF\n", \ + KERN_INFO, f2fs_fault_name[type], \ __func__, __builtin_return_address(0)) static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) { @@ -1406,7 +1431,15 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type) static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type) { - sbi->last_time[type] = jiffies; + unsigned long now = jiffies; + + sbi->last_time[type] = now; + + /* DISCARD_TIME and GC_TIME are based on REQ_TIME */ + if (type == REQ_TIME) { + sbi->last_time[DISCARD_TIME] = now; + sbi->last_time[GC_TIME] = now; + } } static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) @@ -1416,16 +1449,18 @@ static inline bool f2fs_time_over(struct f2fs_sb_info *sbi, int type) return time_after(jiffies, sbi->last_time[type] + interval); } -static inline bool is_idle(struct f2fs_sb_info *sbi) +static inline unsigned int f2fs_time_to_wait(struct f2fs_sb_info *sbi, + int type) { - struct block_device *bdev = sbi->sb->s_bdev; - struct request_queue *q = bdev_get_queue(bdev); - struct request_list *rl = &q->root_rl; + unsigned long interval = sbi->interval_time[type] * HZ; + unsigned int wait_ms = 0; + long delta; - if (rl->count[BLK_RW_SYNC] || rl->count[BLK_RW_ASYNC]) - return false; + delta = (sbi->last_time[type] + interval) - jiffies; + if (delta > 0) + wait_ms = jiffies_to_msecs(delta); - return f2fs_time_over(sbi, REQ_TIME); + return wait_ms; } /* @@ -1766,7 +1801,8 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, true)) avail_user_block_count -= F2FS_OPTION(sbi).root_reserved_blocks; - + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + avail_user_block_count -= sbi->unusable_block_count; if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) @@ -1817,7 +1853,9 @@ static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) atomic_inc(&sbi->nr_pages[count_type]); if (count_type == F2FS_DIRTY_DATA || count_type == F2FS_INMEM_PAGES || - count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA) + count_type == F2FS_WB_CP_DATA || count_type == F2FS_WB_DATA || + count_type == F2FS_RD_DATA || count_type == F2FS_RD_NODE || + count_type == F2FS_RD_META) return; set_sbi_flag(sbi, SBI_IS_DIRTY); @@ -1953,12 +1991,18 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, { block_t valid_block_count; unsigned int valid_node_count; - bool quota = inode && !is_inode; + int err; - if (quota) { - int ret = dquot_reserve_block(inode, 1); - if (ret) - return ret; + if (is_inode) { + if (inode) { + err = dquot_alloc_inode(inode); + if (err) + return err; + } + } else { + err = dquot_reserve_block(inode, 1); + if (err) + return err; } if (time_to_inject(sbi, FAULT_BLOCK)) { @@ -1973,6 +2017,8 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, if (!__allow_reserved_blocks(sbi, inode, false)) valid_block_count += F2FS_OPTION(sbi).root_reserved_blocks; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + valid_block_count += sbi->unusable_block_count; if (unlikely(valid_block_count > sbi->user_block_count)) { spin_unlock(&sbi->stat_lock); @@ -2000,8 +2046,12 @@ static inline int inc_valid_node_count(struct f2fs_sb_info *sbi, return 0; enospc: - if (quota) + if (is_inode) { + if (inode) + dquot_free_inode(inode); + } else { dquot_release_reservation_block(inode, 1); + } return -ENOSPC; } @@ -2022,7 +2072,9 @@ static inline void dec_valid_node_count(struct f2fs_sb_info *sbi, spin_unlock(&sbi->stat_lock); - if (!is_inode) + if (is_inode) + dquot_free_inode(inode); + else f2fs_i_blocks_write(inode, 1, false, true); } @@ -2152,6 +2204,15 @@ static inline struct bio *f2fs_bio_alloc(struct f2fs_sb_info *sbi, return bio_alloc(GFP_KERNEL, npages); } +static inline bool is_idle(struct f2fs_sb_info *sbi, int type) +{ + if (get_pages(sbi, F2FS_RD_DATA) || get_pages(sbi, F2FS_RD_NODE) || + get_pages(sbi, F2FS_RD_META) || get_pages(sbi, F2FS_WB_DATA) || + get_pages(sbi, F2FS_WB_CP_DATA)) + return false; + return f2fs_time_over(sbi, type); +} + static inline void f2fs_radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { @@ -2821,7 +2882,8 @@ static inline bool is_valid_data_blkaddr(struct f2fs_sb_info *sbi, */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); void f2fs_truncate_data_blocks(struct dnode_of_data *dn); -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write); int f2fs_truncate(struct inode *inode); int f2fs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); @@ -2909,6 +2971,7 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) int f2fs_inode_dirtied(struct inode *inode, bool sync); void f2fs_inode_synced(struct inode *inode); int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); +int f2fs_quota_sync(struct super_block *sb, int type); void f2fs_quota_off_umount(struct super_block *sb); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); @@ -2951,7 +3014,7 @@ struct page *f2fs_new_node_page(struct dnode_of_data *dn, unsigned int ofs); void f2fs_ra_node_page(struct f2fs_sb_info *sbi, nid_t nid); struct page *f2fs_get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid); struct page *f2fs_get_node_page_ra(struct page *parent, int start); -void f2fs_move_node_page(struct page *node_page, int gc_type); +int f2fs_move_node_page(struct page *node_page, int gc_type); int f2fs_fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic, unsigned int *seq_id); @@ -2968,7 +3031,7 @@ int f2fs_recover_xattr_data(struct inode *inode, struct page *page); int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page); int f2fs_restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum); -void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc); int f2fs_build_node_manager(struct f2fs_sb_info *sbi); void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi); int __init f2fs_create_node_manager_caches(void); @@ -2996,6 +3059,8 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi); bool f2fs_wait_discard_bios(struct f2fs_sb_info *sbi); void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc); +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi); +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi); void f2fs_release_discard_addrs(struct f2fs_sb_info *sbi); int f2fs_npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra); void f2fs_allocate_new_segments(struct f2fs_sb_info *sbi); @@ -3024,7 +3089,9 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, struct f2fs_io_info *fio, bool add_list); void f2fs_wait_on_page_writeback(struct page *page, enum page_type type, bool ordered); -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr); +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr); +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len); void f2fs_write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk); void f2fs_write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk); int f2fs_lookup_journal_in_cursum(struct f2fs_journal *journal, int type, @@ -3084,8 +3151,8 @@ 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); @@ -3107,6 +3174,7 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index, struct page *f2fs_get_new_data_page(struct inode *inode, struct page *ipage, pgoff_t index, bool new_i_size); int f2fs_do_write_data_page(struct f2fs_io_info *fio); +void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock); int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map, int create, int flag); int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, @@ -3159,6 +3227,8 @@ struct f2fs_stat_info { int free_nids, avail_nids, alloc_nids; int total_count, utilization; int bg_gc, nr_wb_cp_data, nr_wb_data; + int nr_rd_data, nr_rd_node, nr_rd_meta; + unsigned int io_skip_bggc, other_skip_bggc; int nr_flushing, nr_flushed, flush_list_empty; int nr_discarding, nr_discarded; int nr_discard_cmd; @@ -3180,6 +3250,7 @@ struct f2fs_stat_info { int cursec[NR_CURSEG_TYPE]; int curzone[NR_CURSEG_TYPE]; + unsigned int meta_count[META_MAX]; unsigned int segment_count[2]; unsigned int block_count[2]; unsigned int inplace_count; @@ -3195,6 +3266,8 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) #define stat_inc_bg_cp_count(si) ((si)->bg_cp_count++) #define stat_inc_call_count(si) ((si)->call_count++) #define stat_inc_bggc_count(sbi) ((sbi)->bg_gc++) +#define stat_io_skip_bggc_count(sbi) ((sbi)->io_skip_bggc++) +#define stat_other_skip_bggc_count(sbi) ((sbi)->other_skip_bggc++) #define stat_inc_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]++) #define stat_dec_dirty_inode(sbi, type) ((sbi)->ndirty_inode[type]--) #define stat_inc_total_hit(sbi) (atomic64_inc(&(sbi)->total_hit_ext)) @@ -3231,6 +3304,17 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi) if (f2fs_has_inline_dentry(inode)) \ (atomic_dec(&F2FS_I_SB(inode)->inline_dir)); \ } while (0) +#define stat_inc_meta_count(sbi, blkaddr) \ + do { \ + if (blkaddr < SIT_I(sbi)->sit_base_addr) \ + atomic_inc(&(sbi)->meta_count[META_CP]); \ + else if (blkaddr < NM_I(sbi)->nat_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SIT]); \ + else if (blkaddr < SM_I(sbi)->ssa_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_NAT]); \ + else if (blkaddr < SM_I(sbi)->main_blkaddr) \ + atomic_inc(&(sbi)->meta_count[META_SSA]); \ + } while (0) #define stat_inc_seg_type(sbi, curseg) \ ((sbi)->segment_count[(curseg)->alloc_type]++) #define stat_inc_block_count(sbi, curseg) \ @@ -3300,6 +3384,8 @@ void f2fs_destroy_root_stats(void); #define stat_inc_bg_cp_count(si) do { } while (0) #define stat_inc_call_count(si) do { } while (0) #define stat_inc_bggc_count(si) do { } while (0) +#define stat_io_skip_bggc_count(sbi) do { } while (0) +#define stat_other_skip_bggc_count(sbi) do { } while (0) #define stat_inc_dirty_inode(sbi, type) do { } while (0) #define stat_dec_dirty_inode(sbi, type) do { } while (0) #define stat_inc_total_hit(sb) do { } while (0) @@ -3318,6 +3404,7 @@ void f2fs_destroy_root_stats(void); #define stat_inc_volatile_write(inode) do { } while (0) #define stat_dec_volatile_write(inode) do { } while (0) #define stat_update_max_volatile_write(inode) do { } while (0) +#define stat_inc_meta_count(sbi, blkaddr) do { } while (0) #define stat_inc_seg_type(sbi, curseg) do { } while (0) #define stat_inc_block_count(sbi, curseg) do { } while (0) #define stat_inc_inplace_blocks(sbi) do { } while (0) @@ -3438,7 +3525,7 @@ static inline void f2fs_set_encrypted_inode(struct inode *inode) { #ifdef CONFIG_F2FS_FS_ENCRYPTION file_set_encrypt(inode); - inode->i_flags |= S_ENCRYPTED; + f2fs_set_inode_flags(inode); #endif } @@ -3466,6 +3553,7 @@ F2FS_FEATURE_FUNCS(flexible_inline_xattr, FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO); F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); +F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); #ifdef CONFIG_BLK_DEV_ZONED static inline int get_blkz_type(struct f2fs_sb_info *sbi, @@ -3481,11 +3569,20 @@ static inline int get_blkz_type(struct f2fs_sb_info *sbi, } #endif -static inline bool f2fs_discard_en(struct f2fs_sb_info *sbi) +static inline bool f2fs_hw_should_discard(struct f2fs_sb_info *sbi) { - struct request_queue *q = bdev_get_queue(sbi->sb->s_bdev); + return f2fs_sb_has_blkzoned(sbi->sb); +} - return blk_queue_discard(q) || f2fs_sb_has_blkzoned(sbi->sb); +static inline bool f2fs_hw_support_discard(struct f2fs_sb_info *sbi) +{ + return blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev)); +} + +static inline bool f2fs_realtime_discard_enable(struct f2fs_sb_info *sbi) +{ + return (test_opt(sbi, DISCARD) && f2fs_hw_support_discard(sbi)) || + f2fs_hw_should_discard(sbi); } static inline void set_opt_mode(struct f2fs_sb_info *sbi, unsigned int mt) @@ -3514,11 +3611,50 @@ static inline bool f2fs_may_encrypt(struct inode *inode) #endif } -static inline bool f2fs_force_buffered_io(struct inode *inode, int rw) +static inline int block_unaligned_IO(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) { - return (f2fs_post_read_required(inode) || - (rw == WRITE && test_opt(F2FS_I_SB(inode), LFS)) || - F2FS_I_SB(inode)->s_ndevs); + unsigned int i_blkbits = READ_ONCE(inode->i_blkbits); + unsigned int blocksize_mask = (1 << i_blkbits) - 1; + loff_t offset = iocb->ki_pos; + unsigned long align = offset | iov_iter_alignment(iter); + + return align & blocksize_mask; +} + +static inline int allow_outplace_dio(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + return (test_opt(sbi, LFS) && (rw == WRITE) && + !block_unaligned_IO(inode, iocb, iter)); +} + +static inline bool f2fs_force_buffered_io(struct inode *inode, + struct kiocb *iocb, struct iov_iter *iter) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + int rw = iov_iter_rw(iter); + + if (f2fs_post_read_required(inode)) + return true; + if (sbi->s_ndevs) + return true; + /* + * for blkzoned device, fallback direct IO to buffered IO, so + * all IOs can be serialized by log-structured write. + */ + if (f2fs_sb_has_blkzoned(sbi->sb)) + return true; + if (test_opt(sbi, LFS) && (rw == WRITE) && + block_unaligned_IO(inode, iocb, iter)) + return true; + if (is_sbi_flag_set(F2FS_I_SB(inode), SBI_CP_DISABLED)) + return true; + + return false; } #ifdef CONFIG_F2FS_FAULT_INJECTION @@ -3529,3 +3665,16 @@ extern void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, #endif #endif + +static inline bool is_journalled_quota(struct f2fs_sb_info *sbi) +{ +#ifdef CONFIG_QUOTA + if (f2fs_sb_has_quota_ino(sbi->sb)) + return true; + if (F2FS_OPTION(sbi).s_qf_names[USRQUOTA] || + F2FS_OPTION(sbi).s_qf_names[GRPQUOTA] || + F2FS_OPTION(sbi).s_qf_names[PRJQUOTA]) + return true; +#endif + return false; +} diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 8e381b6385e3..3c61f9619be1 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -53,7 +50,7 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct dnode_of_data dn; + struct dnode_of_data dn = { .node_changed = false }; int err; if (unlikely(f2fs_cp_error(sbi))) { @@ -65,19 +62,6 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); - /* block allocation */ - f2fs_lock_op(sbi); - set_new_dnode(&dn, inode, NULL, NULL, 0); - err = f2fs_reserve_block(&dn, page->index); - if (err) { - f2fs_unlock_op(sbi); - goto out; - } - f2fs_put_dnode(&dn); - f2fs_unlock_op(sbi); - - f2fs_balance_fs(sbi, dn.node_changed); - file_update_time(vma->vm_file); down_read(&F2FS_I(inode)->i_mmap_sem); lock_page(page); @@ -89,11 +73,28 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, goto out_sem; } + /* block allocation */ + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true); + set_new_dnode(&dn, inode, NULL, NULL, 0); + err = f2fs_get_block(&dn, page->index); + f2fs_put_dnode(&dn); + __do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false); + if (err) { + unlock_page(page); + goto out_sem; + } + + /* fill the page */ + f2fs_wait_on_page_writeback(page, DATA, false); + + /* wait for GCed page writeback via META_MAPPING */ + f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); + /* * check to see if the page is mapped already (no holes) */ if (PageMappedToDisk(page)) - goto mapped; + goto out_sem; /* page is wholly or partially inside EOF */ if (((loff_t)(page->index + 1) << PAGE_SHIFT) > @@ -108,21 +109,15 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, SetPageUptodate(page); f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); + f2fs_update_time(sbi, REQ_TIME); trace_f2fs_vm_page_mkwrite(page, DATA); -mapped: - /* fill the page */ - f2fs_wait_on_page_writeback(page, DATA, false); - - /* wait for GCed page writeback via META_MAPPING */ - if (f2fs_post_read_required(inode)) - f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); - out_sem: up_read(&F2FS_I(inode)->i_mmap_sem); -out: + + f2fs_balance_fs(sbi, dn.node_changed); + sb_end_pagefault(inode->i_sb); - f2fs_update_time(sbi, REQ_TIME); err: return block_page_mkwrite_return(err); } @@ -218,7 +213,8 @@ static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, }; unsigned int seq_id = 0; - if (unlikely(f2fs_readonly(inode->i_sb))) + if (unlikely(f2fs_readonly(inode->i_sb) || + is_sbi_flag_set(sbi, SBI_CP_DISABLED))) return 0; trace_f2fs_sync_file_enter(inode); @@ -593,7 +589,8 @@ truncate_out: return 0; } -int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) +int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock, + bool buf_write) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; @@ -601,6 +598,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) int count = 0, err = 0; struct page *ipage; bool truncate_page = false; + int flag = buf_write ? F2FS_GET_BLOCK_PRE_AIO : F2FS_GET_BLOCK_PRE_DIO; trace_f2fs_truncate_blocks_enter(inode, from); @@ -610,7 +608,7 @@ int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock) goto free_partial; if (lock) - f2fs_lock_op(sbi); + __do_map_lock(sbi, flag, true); ipage = f2fs_get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { @@ -648,7 +646,7 @@ free_next: err = f2fs_truncate_inode_blocks(inode, free_from); out: if (lock) - f2fs_unlock_op(sbi); + __do_map_lock(sbi, flag, false); free_partial: /* lastly zero out the first data page */ if (!err) @@ -683,7 +681,7 @@ int f2fs_truncate(struct inode *inode) return err; } - err = f2fs_truncate_blocks(inode, i_size_read(inode), true); + err = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); if (err) return err; @@ -793,9 +791,24 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr) !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { + f2fs_lock_op(F2FS_I_SB(inode)); err = dquot_transfer(inode, attr); - if (err) + if (err) { + set_sbi_flag(F2FS_I_SB(inode), + SBI_QUOTA_NEED_REPAIR); + f2fs_unlock_op(F2FS_I_SB(inode)); return err; + } + /* + * update uid/gid under lock_op(), so that dquot and inode can + * be updated atomically. + */ + if (attr->ia_valid & ATTR_UID) + inode->i_uid = attr->ia_uid; + if (attr->ia_valid & ATTR_GID) + inode->i_gid = attr->ia_gid; + f2fs_mark_inode_dirty_sync(inode, true); + f2fs_unlock_op(F2FS_I_SB(inode)); } if (attr->ia_valid & ATTR_SIZE) { @@ -1253,7 +1266,7 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); - ret = f2fs_truncate_blocks(inode, new_size, true); + ret = f2fs_truncate_blocks(inode, new_size, true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (!ret) f2fs_i_size_write(inode, new_size); @@ -1438,7 +1451,7 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); - ret = f2fs_truncate_blocks(inode, i_size_read(inode), true); + ret = f2fs_truncate_blocks(inode, i_size_read(inode), true, false); up_write(&F2FS_I(inode)->i_mmap_sem); if (ret) return ret; @@ -1978,7 +1991,7 @@ static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!blk_queue_discard(q)) + if (!f2fs_hw_support_discard(F2FS_SB(sb))) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, @@ -2162,6 +2175,12 @@ static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + f2fs_msg(sbi->sb, KERN_INFO, + "Skipping Checkpoint. Checkpoints currently disabled."); + return -EINVAL; + } + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -2533,6 +2552,9 @@ static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) if (f2fs_readonly(sbi->sb)) return -EROFS; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return -EINVAL; + if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; @@ -2800,7 +2822,8 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (!f2fs_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)) || f2fs_has_inline_data(inode) || - f2fs_force_buffered_io(inode, WRITE)) { + f2fs_force_buffered_io(inode, + iocb, from)) { clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ada8b8056cd0..843430b55a73 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/module.h> @@ -43,13 +40,16 @@ static int gc_thread_func(void *data) if (gc_th->gc_wake) gc_th->gc_wake = 0; - if (try_to_freeze()) + if (try_to_freeze()) { + stat_other_skip_bggc_count(sbi); continue; + } if (kthread_should_stop()) break; if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { increase_sleep_time(gc_th, &wait_ms); + stat_other_skip_bggc_count(sbi); continue; } @@ -58,8 +58,10 @@ static int gc_thread_func(void *data) f2fs_stop_checkpoint(sbi, false); } - if (!sb_start_write_trylock(sbi->sb)) + if (!sb_start_write_trylock(sbi->sb)) { + stat_other_skip_bggc_count(sbi); continue; + } /* * [GC triggering condition] @@ -80,12 +82,15 @@ static int gc_thread_func(void *data) goto do_gc; } - if (!mutex_trylock(&sbi->gc_mutex)) + if (!mutex_trylock(&sbi->gc_mutex)) { + stat_other_skip_bggc_count(sbi); goto next; + } - if (!is_idle(sbi)) { + if (!is_idle(sbi, GC_TIME)) { increase_sleep_time(gc_th, &wait_ms); mutex_unlock(&sbi->gc_mutex); + stat_io_skip_bggc_count(sbi); goto next; } @@ -365,6 +370,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi, if (sec_usage_check(sbi, secno)) goto next; + /* Don't touch checkpointed data */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED) && + get_ckpt_valid_blocks(sbi, segno))) + goto next; if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; @@ -464,7 +473,7 @@ static int check_valid_map(struct f2fs_sb_info *sbi, * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ -static void gc_node_segment(struct f2fs_sb_info *sbi, +static int gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { struct f2fs_summary *entry; @@ -472,6 +481,7 @@ static void gc_node_segment(struct f2fs_sb_info *sbi, int off; int phase = 0; bool fggc = (gc_type == FG_GC); + int submitted = 0; start_addr = START_BLOCK(sbi, segno); @@ -485,10 +495,11 @@ next_step: nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; struct node_info ni; + int err; /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -525,7 +536,9 @@ next_step: continue; } - f2fs_move_node_page(node_page, gc_type); + err = f2fs_move_node_page(node_page, gc_type); + if (!err && gc_type == FG_GC) + submitted++; stat_inc_node_blk_count(sbi, 1, gc_type); } @@ -534,6 +547,7 @@ next_step: if (fggc) atomic_dec(&sbi->wb_sync_req[NODE]); + return submitted; } /* @@ -669,7 +683,7 @@ put_page: * Move data block via META_MAPPING while keeping locked data page. * This can be used to move blocks, aka LBAs, directly on disk. */ -static void move_data_block(struct inode *inode, block_t bidx, +static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct f2fs_io_info fio = { @@ -688,25 +702,29 @@ static void move_data_block(struct inode *inode, block_t bidx, struct node_info ni; struct page *page, *mpage; block_t newaddr; - int err; + int err = 0; bool lfs_mode = test_opt(fio.sbi, LFS); /* do not read out */ page = f2fs_grab_cache_page(inode->i_mapping, bidx, false); if (!page) - return; + return -ENOMEM; - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; goto out; + } if (f2fs_is_atomic_file(inode)) { F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; goto out; } if (f2fs_is_pinned_file(inode)) { f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; } @@ -717,6 +735,7 @@ static void move_data_block(struct inode *inode, block_t bidx, if (unlikely(dn.data_blkaddr == NULL_ADDR)) { ClearPageUptodate(page); + err = -ENOENT; goto put_out; } @@ -799,6 +818,7 @@ write_page: fio.new_blkaddr = newaddr; f2fs_submit_page_write(&fio); if (fio.retry) { + err = -EAGAIN; if (PageWriteback(fio.encrypted_page)) end_page_writeback(fio.encrypted_page); goto put_page_out; @@ -822,34 +842,42 @@ put_out: f2fs_put_dnode(&dn); out: f2fs_put_page(page, 1); + return err; } -static void move_data_page(struct inode *inode, block_t bidx, int gc_type, +static int move_data_page(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct page *page; + int err = 0; page = f2fs_get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) - return; + return PTR_ERR(page); - if (!check_valid_map(F2FS_I_SB(inode), segno, off)) + if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { + err = -ENOENT; goto out; + } if (f2fs_is_atomic_file(inode)) { F2FS_I(inode)->i_gc_failures[GC_FAILURE_ATOMIC]++; F2FS_I_SB(inode)->skipped_atomic_files[gc_type]++; + err = -EAGAIN; goto out; } if (f2fs_is_pinned_file(inode)) { if (gc_type == FG_GC) f2fs_pin_file_control(inode, true); + err = -EAGAIN; goto out; } if (gc_type == BG_GC) { - if (PageWriteback(page)) + if (PageWriteback(page)) { + err = -EAGAIN; goto out; + } set_page_dirty(page); set_cold_data(page); } else { @@ -867,7 +895,6 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type, .io_type = FS_GC_DATA_IO, }; bool is_dirty = PageDirty(page); - int err; retry: set_page_dirty(page); @@ -892,6 +919,7 @@ retry: } out: f2fs_put_page(page, 1); + return err; } /* @@ -901,7 +929,7 @@ out: * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ -static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, +static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type) { struct super_block *sb = sbi->sb; @@ -909,6 +937,7 @@ static void gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, block_t start_addr; int off; int phase = 0; + int submitted = 0; start_addr = START_BLOCK(sbi, segno); @@ -925,7 +954,7 @@ next_step: /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) - return; + return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; @@ -997,6 +1026,7 @@ next_step: if (inode) { struct f2fs_inode_info *fi = F2FS_I(inode); bool locked = false; + int err; if (S_ISREG(inode->i_mode)) { if (!down_write_trylock(&fi->i_gc_rwsem[READ])) @@ -1016,12 +1046,16 @@ next_step: start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; if (f2fs_post_read_required(inode)) - move_data_block(inode, start_bidx, gc_type, - segno, off); + err = move_data_block(inode, start_bidx, + gc_type, segno, off); else - move_data_page(inode, start_bidx, gc_type, + err = move_data_page(inode, start_bidx, gc_type, segno, off); + if (!err && (gc_type == FG_GC || + f2fs_post_read_required(inode))) + submitted++; + if (locked) { up_write(&fi->i_gc_rwsem[WRITE]); up_write(&fi->i_gc_rwsem[READ]); @@ -1033,6 +1067,8 @@ next_step: if (++phase < 5) goto next_step; + + return submitted; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, @@ -1060,6 +1096,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, int seg_freed = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; + int submitted = 0; /* readahead multi ssa blocks those have contiguous address */ if (sbi->segs_per_sec > 1) @@ -1069,6 +1106,18 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, /* reference all summary page */ while (segno < end_segno) { sum_page = f2fs_get_sum_page(sbi, segno++); + if (IS_ERR(sum_page)) { + int err = PTR_ERR(sum_page); + + end_segno = segno - 1; + for (segno = start_segno; segno < end_segno; segno++) { + sum_page = find_get_page(META_MAPPING(sbi), + GET_SUM_BLOCK(sbi, segno)); + f2fs_put_page(sum_page, 0); + f2fs_put_page(sum_page, 0); + } + return err; + } unlock_page(sum_page); } @@ -1103,10 +1152,11 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, * - lock_page(sum_page) */ if (type == SUM_TYPE_NODE) - gc_node_segment(sbi, sum->entries, segno, gc_type); - else - gc_data_segment(sbi, sum->entries, gc_list, segno, + submitted += gc_node_segment(sbi, sum->entries, segno, gc_type); + else + submitted += gc_data_segment(sbi, sum->entries, gc_list, + segno, gc_type); stat_inc_seg_count(sbi, type, gc_type); @@ -1117,7 +1167,7 @@ next: f2fs_put_page(sum_page, 0); } - if (gc_type == FG_GC) + if (submitted) f2fs_submit_merged_write(sbi, (type == SUM_TYPE_NODE) ? NODE : DATA); @@ -1172,7 +1222,8 @@ gc_more: * threshold, we can make them free by checkpoint. Then, we * secure free segments which doesn't need fggc any more. */ - if (prefree_segments(sbi)) { + if (prefree_segments(sbi) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; @@ -1224,7 +1275,7 @@ gc_more: segno = NULL_SEGNO; goto gc_more; } - if (gc_type == FG_GC) + if (gc_type == FG_GC && !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) ret = f2fs_write_checkpoint(sbi, &cpc); } stop: @@ -1244,7 +1295,7 @@ stop: put_gc_inode(&gc_list); - if (sync) + if (sync && !ret) ret = sec_freed ? 0 : -EAGAIN; return ret; } diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h index c8619e408009..bbac9d3787bd 100644 --- a/fs/f2fs/gc.h +++ b/fs/f2fs/gc.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #define GC_THREAD_MIN_WB_PAGES 1 /* * a threshold to determine diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index eb2e031ea887..cc82f142f811 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/hash.c * @@ -7,10 +8,6 @@ * Portions of this code from linux/fs/ext3/hash.c * * Copyright (C) 2002 by Theodore Ts'o - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/fs.h> diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 202bfff31622..fdf4abcf2dab 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -1,11 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inline.c * Copyright (c) 2013, Intel Corporation * Authors: Huajun Li <huajun.li@intel.com> * Haicheng Li <haicheng.li@intel.com> - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> @@ -318,7 +316,7 @@ process_inline: clear_inode_flag(inode, FI_INLINE_DATA); f2fs_put_page(ipage, 1); } else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) { - if (f2fs_truncate_blocks(inode, 0, false)) + if (f2fs_truncate_blocks(inode, 0, false, false)) return false; goto process_inline; } @@ -490,7 +488,7 @@ static int f2fs_add_inline_entries(struct inode *dir, void *inline_dentry) return 0; punch_dentry_pages: truncate_inode_pages(&dir->i_data, 0); - f2fs_truncate_blocks(dir, 0, false); + f2fs_truncate_blocks(dir, 0, false, false); f2fs_remove_dirty_inode(dir); return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 292f787a65e2..1b1f22faff22 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/inode.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -368,6 +365,12 @@ static int do_read_inode(struct inode *inode) if (f2fs_has_inline_data(inode) && !f2fs_exist_data(inode)) __recover_inline_status(inode, node_page); + /* try to recover cold bit for non-dir inode */ + if (!S_ISDIR(inode->i_mode) && !is_cold_node(node_page)) { + set_cold_node(node_page, false); + set_page_dirty(node_page); + } + /* get rdev by using inline_info */ __get_inode_rdev(inode, ri); @@ -610,6 +613,9 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc) if (!is_inode_flag_set(inode, FI_DIRTY_INODE)) return 0; + if (f2fs_is_checkpoint_ready(sbi)) + return -ENOSPC; + /* * We need to balance fs here to prevent from producing dirty node pages * during the urgent cleaning time when runing out of free sections. @@ -648,7 +654,11 @@ void f2fs_evict_inode(struct inode *inode) if (inode->i_nlink || is_bad_inode(inode)) goto no_delete; - dquot_initialize(inode); + err = dquot_initialize(inode); + if (err) { + err = 0; + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } f2fs_remove_ino_entry(sbi, inode->i_ino, APPEND_INO); f2fs_remove_ino_entry(sbi, inode->i_ino, UPDATE_INO); @@ -680,9 +690,10 @@ retry: goto retry; } - if (err) + if (err) { f2fs_update_inode_page(inode); - dquot_free_inode(inode); + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + } sb_end_intwrite(inode->i_sb); no_delete: dquot_drop(inode); @@ -691,7 +702,8 @@ no_delete: stat_dec_inline_dir(inode); stat_dec_inline_inode(inode); - if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG))) + if (likely(!is_set_ckpt_flags(sbi, CP_ERROR_FLAG) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED))) f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)); else f2fs_inode_synced(inode); diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 05193a103e80..e50f43fa6afc 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/namei.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -19,6 +16,7 @@ #include "f2fs.h" #include "node.h" +#include "segment.h" #include "xattr.h" #include "acl.h" #include <trace/events/f2fs.h> @@ -74,10 +72,6 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (err) goto fail_drop; - err = dquot_alloc_inode(inode); - if (err) - goto fail_drop; - set_inode_flag(inode, FI_NEW_INODE); /* If the directory encrypted, then we should encrypt the inode. */ @@ -124,6 +118,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) if (F2FS_I(inode)->i_flags & F2FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); + f2fs_set_inode_flags(inode); + trace_f2fs_new_inode(inode, 0); return inode; @@ -184,16 +180,19 @@ static inline void set_file_temperature(struct f2fs_sb_info *sbi, struct inode * hot_count = sbi->raw_super->hot_ext_count; for (i = 0; i < cold_count + hot_count; i++) { - if (!is_extension_exist(name, extlist[i])) - continue; - if (i < cold_count) - file_set_cold(inode); - else - file_set_hot(inode); - break; + if (is_extension_exist(name, extlist[i])) + break; } up_read(&sbi->sb_lock); + + if (i == cold_count + hot_count) + return; + + if (i < cold_count) + file_set_cold(inode); + else + file_set_hot(inode); } int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, @@ -272,6 +271,9 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -318,6 +320,9 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_link(old_dentry, dir, dentry); if (err) @@ -561,6 +566,9 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = fscrypt_prepare_symlink(dir, symname, len, dir->i_sb->s_blocksize, &disk_link); @@ -690,6 +698,9 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry, if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; err = dquot_initialize(dir); if (err) @@ -820,10 +831,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_entry; struct f2fs_dir_entry *new_entry; bool is_old_inline = f2fs_has_inline_dentry(old_dir); - int err = -ENOENT; + int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if (is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && (!projid_eq(F2FS_I(new_dir)->i_projid, @@ -844,6 +858,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; } + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -980,6 +995,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; put_out_dir: @@ -1009,10 +1026,13 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, struct f2fs_dir_entry *old_dir_entry = NULL, *new_dir_entry = NULL; struct f2fs_dir_entry *old_entry, *new_entry; int old_nlink = 0, new_nlink = 0; - int err = -ENOENT; + int err; if (unlikely(f2fs_cp_error(sbi))) return -EIO; + err = f2fs_is_checkpoint_ready(sbi); + if (err) + return err; if ((is_inode_flag_set(new_dir, FI_PROJ_INHERIT) && !projid_eq(F2FS_I(new_dir)->i_projid, @@ -1030,6 +1050,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (err) goto out; + err = -ENOENT; old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page); if (!old_entry) { if (IS_ERR(old_page)) @@ -1133,6 +1154,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir)) f2fs_sync_fs(sbi->sb, 1); + + f2fs_update_time(sbi, REQ_TIME); return 0; out_new_dir: if (new_dir_entry) { diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 1af0805915b4..08edc0930831 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -129,6 +126,8 @@ static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) /* get current nat block page with lock */ src_page = get_current_nat_page(sbi, nid); + if (IS_ERR(src_page)) + return src_page; dst_page = f2fs_grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); @@ -1542,8 +1541,10 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + up_read(&sbi->node_write); goto redirty_out; + } if (atomic && !test_opt(sbi, NOBARRIER)) fio.op_flags |= WRITE_FLUSH_FUA; @@ -1564,8 +1565,7 @@ 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; } @@ -1587,8 +1587,10 @@ redirty_out: return AOP_WRITEPAGE_ACTIVATE; } -void f2fs_move_node_page(struct page *node_page, int gc_type) +int f2fs_move_node_page(struct page *node_page, int gc_type) { + int err = 0; + if (gc_type == FG_GC) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, @@ -1600,12 +1602,16 @@ void f2fs_move_node_page(struct page *node_page, int gc_type) f2fs_wait_on_page_writeback(node_page, NODE, true); f2fs_bug_on(F2FS_P_SB(node_page), PageWriteback(node_page)); - if (!clear_page_dirty_for_io(node_page)) + if (!clear_page_dirty_for_io(node_page)) { + err = -EAGAIN; goto out_page; + } if (__write_node_page(node_page, false, NULL, - &wbc, false, FS_GC_NODE_IO, NULL)) + &wbc, false, FS_GC_NODE_IO, NULL)) { + err = -EAGAIN; unlock_page(node_page); + } goto release_page; } else { /* set page dirty and write it */ @@ -1616,6 +1622,7 @@ out_page: unlock_page(node_page); release_page: f2fs_put_page(node_page, 0); + return err; } static int f2fs_write_node_page(struct page *page, @@ -1630,13 +1637,13 @@ 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); @@ -1714,7 +1721,7 @@ continue_unlock: f2fs_put_page(last_page, 0); break; } else if (submitted) { - last_idx = page->index; + nwritten++; } if (page == last_page) { @@ -1740,8 +1747,8 @@ continue_unlock: 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; } @@ -2271,15 +2278,19 @@ static int __f2fs_build_free_nids(struct f2fs_sb_info *sbi, nm_i->nat_block_bitmap)) { struct page *page = get_current_nat_page(sbi, nid); - ret = scan_nat_page(sbi, page, nid); - f2fs_put_page(page, 1); + if (IS_ERR(page)) { + ret = PTR_ERR(page); + } else { + ret = scan_nat_page(sbi, page, nid); + f2fs_put_page(page, 1); + } if (ret) { up_read(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, !mount); f2fs_msg(sbi->sb, KERN_ERR, "NAT is corrupt, run fsck to fix it"); - return -EINVAL; + return ret; } } @@ -2356,8 +2367,9 @@ retry: spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ - f2fs_build_free_nids(sbi, true, false); - goto retry; + if (!f2fs_build_free_nids(sbi, true, false)) + goto retry; + return false; } /* @@ -2540,7 +2552,7 @@ retry: if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); - set_cold_node(page, false); + set_cold_node(ipage, false); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); @@ -2563,6 +2575,13 @@ retry: F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), i_projid)) dst->i_projid = src->i_projid; + + if (f2fs_sb_has_inode_crtime(sbi->sb) && + F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), + i_crtime_nsec)) { + dst->i_crtime = src->i_crtime; + dst->i_crtime_nsec = src->i_crtime_nsec; + } } new_ni = old_ni; @@ -2706,7 +2725,7 @@ static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, __clear_bit_le(nat_index, nm_i->full_nat_bits); } -static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, +static int __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2730,6 +2749,9 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); + if (IS_ERR(page)) + return PTR_ERR(page); + nat_blk = page_address(page); f2fs_bug_on(sbi, !nat_blk); } @@ -2775,12 +2797,13 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); kmem_cache_free(nat_entry_set_slab, set); } + return 0; } /* * This function is called during the checkpointing process. */ -void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) +int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); @@ -2790,6 +2813,7 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); + int err = 0; /* during unmount, let's flush nat_bits before checking dirty_nat_cnt */ if (enabled_nat_bits(sbi, cpc)) { @@ -2799,7 +2823,7 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } if (!nm_i->dirty_nat_cnt) - return; + return 0; down_write(&nm_i->nat_tree_lock); @@ -2822,11 +2846,16 @@ void f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) } /* flush dirty nats in nat entry set */ - list_for_each_entry_safe(set, tmp, &sets, set_list) - __flush_nat_entry_set(sbi, set, cpc); + list_for_each_entry_safe(set, tmp, &sets, set_list) { + err = __flush_nat_entry_set(sbi, set, cpc); + if (err) + break; + } up_write(&nm_i->nat_tree_lock); /* Allow dirty nats by node block allocation in write_begin */ + + return err; } static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) @@ -2853,10 +2882,8 @@ static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) struct page *page; page = f2fs_get_meta_page(sbi, nat_bits_addr++); - if (IS_ERR(page)) { - disable_nat_bits(sbi, true); + if (IS_ERR(page)) return PTR_ERR(page); - } memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 0f4db7a61254..1c73d879a9bc 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/node.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ /* start node id of a node block dedicated to the given node id */ #define START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK) diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 501bb0fdda1b..336273a81fba 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/recovery.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -99,8 +96,12 @@ err_out: return ERR_PTR(err); } -static void del_fsync_inode(struct fsync_inode_entry *entry) +static void del_fsync_inode(struct fsync_inode_entry *entry, int drop) { + if (drop) { + /* inode should not be recovered, drop it */ + f2fs_inode_synced(entry->inode); + } iput(entry->inode); list_del(&entry->list); kmem_cache_free(fsync_entry_slab, entry); @@ -194,6 +195,33 @@ out: return err; } +static int recover_quota_data(struct inode *inode, struct page *page) +{ + struct f2fs_inode *raw = F2FS_INODE(page); + struct iattr attr; + uid_t i_uid = le32_to_cpu(raw->i_uid); + gid_t i_gid = le32_to_cpu(raw->i_gid); + int err; + + memset(&attr, 0, sizeof(attr)); + + attr.ia_uid = make_kuid(&init_user_ns, i_uid); + attr.ia_gid = make_kgid(&init_user_ns, i_gid); + + if (!uid_eq(attr.ia_uid, inode->i_uid)) + attr.ia_valid |= ATTR_UID; + if (!gid_eq(attr.ia_gid, inode->i_gid)) + attr.ia_valid |= ATTR_GID; + + if (!attr.ia_valid) + return 0; + + err = dquot_transfer(inode, &attr); + if (err) + set_sbi_flag(F2FS_I_SB(inode), SBI_QUOTA_NEED_REPAIR); + return err; +} + static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) { if (ri->i_inline & F2FS_PIN_FILE) @@ -206,12 +234,33 @@ static void recover_inline_flags(struct inode *inode, struct f2fs_inode *ri) clear_inode_flag(inode, FI_DATA_EXIST); } -static void recover_inode(struct inode *inode, struct page *page) +static int recover_inode(struct inode *inode, struct page *page) { struct f2fs_inode *raw = F2FS_INODE(page); char *name; + int err; inode->i_mode = le16_to_cpu(raw->i_mode); + + err = recover_quota_data(inode, page); + if (err) + return err; + + i_uid_write(inode, le32_to_cpu(raw->i_uid)); + i_gid_write(inode, le32_to_cpu(raw->i_gid)); + + if (raw->i_inline & F2FS_EXTRA_ATTR) { + if (f2fs_sb_has_project_quota(F2FS_I_SB(inode)->sb) && + F2FS_FITS_IN_INODE(raw, le16_to_cpu(raw->i_extra_isize), + i_projid)) { + projid_t i_projid; + + i_projid = (projid_t)le32_to_cpu(raw->i_projid); + F2FS_I(inode)->i_projid = + make_kprojid(&init_user_ns, i_projid); + } + } + f2fs_i_size_write(inode, le64_to_cpu(raw->i_size)); inode->i_atime.tv_sec = le64_to_cpu(raw->i_atime); inode->i_ctime.tv_sec = le64_to_cpu(raw->i_ctime); @@ -221,9 +270,15 @@ static void recover_inode(struct inode *inode, struct page *page) inode->i_mtime.tv_nsec = le32_to_cpu(raw->i_mtime_nsec); F2FS_I(inode)->i_advise = raw->i_advise; + F2FS_I(inode)->i_flags = le32_to_cpu(raw->i_flags); + f2fs_set_inode_flags(inode); + F2FS_I(inode)->i_gc_failures[GC_FAILURE_PIN] = + le16_to_cpu(raw->i_gc_failures); recover_inline_flags(inode, raw); + f2fs_mark_inode_dirty_sync(inode, true); + if (file_enc_name(inode)) name = "<encrypted>"; else @@ -232,6 +287,7 @@ static void recover_inode(struct inode *inode, struct page *page) f2fs_msg(inode->i_sb, KERN_NOTICE, "recover_inode: ino = %x, name = %s, inline = %x", ino_of_node(page), name, raw->i_inline); + return 0; } static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, @@ -320,12 +376,12 @@ next: return err; } -static void destroy_fsync_dnodes(struct list_head *head) +static void destroy_fsync_dnodes(struct list_head *head, int drop) { struct fsync_inode_entry *entry, *tmp; list_for_each_entry_safe(entry, tmp, head, list) - del_fsync_inode(entry); + del_fsync_inode(entry, drop); } static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, @@ -358,6 +414,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, } sum_page = f2fs_get_sum_page(sbi, segno); + if (IS_ERR(sum_page)) + return PTR_ERR(sum_page); sum_node = (struct f2fs_summary_block *)page_address(sum_page); sum = sum_node->entries[blkoff]; f2fs_put_page(sum_page, 1); @@ -560,7 +618,7 @@ out: } static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, - struct list_head *dir_list) + struct list_head *tmp_inode_list, struct list_head *dir_list) { struct curseg_info *curseg; struct page *page = NULL; @@ -598,8 +656,11 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, * In this case, we can lose the latest inode(x). * So, call recover_inode for the inode update. */ - if (IS_INODE(page)) - recover_inode(entry->inode, page); + if (IS_INODE(page)) { + err = recover_inode(entry->inode, page); + if (err) + break; + } if (entry->last_dentry == blkaddr) { err = recover_dentry(entry->inode, page, dir_list); if (err) { @@ -614,7 +675,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list, } if (entry->blkaddr == blkaddr) - del_fsync_inode(entry); + list_move_tail(&entry->list, tmp_inode_list); next: /* check next segment */ blkaddr = next_blkaddr_of_node(page); @@ -627,7 +688,7 @@ next: int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) { - struct list_head inode_list; + struct list_head inode_list, tmp_inode_list; struct list_head dir_list; int err; int ret = 0; @@ -658,6 +719,7 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) } INIT_LIST_HEAD(&inode_list); + INIT_LIST_HEAD(&tmp_inode_list); INIT_LIST_HEAD(&dir_list); /* prevent checkpoint */ @@ -676,11 +738,16 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only) need_writecp = true; /* step #2: recover data */ - err = recover_data(sbi, &inode_list, &dir_list); + err = recover_data(sbi, &inode_list, &tmp_inode_list, &dir_list); if (!err) f2fs_bug_on(sbi, !list_empty(&inode_list)); + else { + /* restore s_flags to let iput() trash data */ + sbi->sb->s_flags = s_flags; + } skip: - destroy_fsync_dnodes(&inode_list); + destroy_fsync_dnodes(&inode_list, err); + destroy_fsync_dnodes(&tmp_inode_list, err); /* truncate meta pages to be used by the recovery */ truncate_inode_pages_range(META_MAPPING(sbi), @@ -689,19 +756,23 @@ skip: if (err) { truncate_inode_pages_final(NODE_MAPPING(sbi)); truncate_inode_pages_final(META_MAPPING(sbi)); + } else { + clear_sbi_flag(sbi, SBI_POR_DOING); } - - clear_sbi_flag(sbi, SBI_POR_DOING); mutex_unlock(&sbi->cp_mutex); /* let's drop all the directory inodes for clean checkpoint */ - destroy_fsync_dnodes(&dir_list); + destroy_fsync_dnodes(&dir_list, err); - if (!err && need_writecp) { - struct cp_control cpc = { - .reason = CP_RECOVERY, - }; - err = f2fs_write_checkpoint(sbi, &cpc); + if (need_writecp) { + set_sbi_flag(sbi, SBI_IS_RECOVERED); + + if (!err) { + struct cp_control cpc = { + .reason = CP_RECOVERY, + }; + err = f2fs_write_checkpoint(sbi, &cpc); + } } kmem_cache_destroy(fsync_entry_slab); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index fdc17721e41e..fb4be4629add 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> @@ -179,6 +176,8 @@ bool f2fs_need_SSR(struct f2fs_sb_info *sbi) return false; if (sbi->gc_mode == GC_URGENT) return true; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return true; return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs + SM_I(sbi)->min_ssr_sections + reserved_sections(sbi)); @@ -267,8 +266,10 @@ retry: } next: /* we don't need to invalidate this in the sccessful status */ - if (drop || recover) + if (drop || recover) { ClearPageUptodate(page); + clear_cold_data(page); + } set_page_private(page, 0); ClearPagePrivate(page); f2fs_put_page(page, 1); @@ -374,7 +375,7 @@ 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); @@ -409,14 +410,14 @@ retry: } /* 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) { /* @@ -483,6 +484,9 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need) if (need && excess_cached_nats(sbi)) f2fs_balance_fs_bg(sbi); + if (f2fs_is_checkpoint_ready(sbi)) + return; + /* * We should do GC or end up with checkpoint, if there are so many dirty * dir/node pages without enough free segments. @@ -511,7 +515,7 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi) else f2fs_build_free_nids(sbi, false, false); - if (!is_idle(sbi) && + if (!is_idle(sbi, REQ_TIME) && (!excess_dirty_nats(sbi) && !excess_dirty_nodes(sbi))) return; @@ -799,7 +803,7 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno, static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); - unsigned short valid_blocks; + unsigned short valid_blocks, ckpt_valid_blocks; if (segno == NULL_SEGNO || IS_CURSEG(sbi, segno)) return; @@ -807,8 +811,10 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_lock(&dirty_i->seglist_lock); valid_blocks = get_valid_blocks(sbi, segno, false); + ckpt_valid_blocks = get_ckpt_valid_blocks(sbi, segno); - if (valid_blocks == 0) { + if (valid_blocks == 0 && (!is_sbi_flag_set(sbi, SBI_CP_DISABLED) || + ckpt_valid_blocks == sbi->blocks_per_seg)) { __locate_dirty_segment(sbi, segno, PRE); __remove_dirty_segment(sbi, segno, DIRTY); } else if (valid_blocks < sbi->blocks_per_seg) { @@ -821,6 +827,66 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno) mutex_unlock(&dirty_i->seglist_lock); } +/* This moves currently empty dirty blocks to prefree. Must hold seglist_lock */ +void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (IS_CURSEG(sbi, segno)) + continue; + __locate_dirty_segment(sbi, segno, PRE); + __remove_dirty_segment(sbi, segno, DIRTY); + } + mutex_unlock(&dirty_i->seglist_lock); +} + +int f2fs_disable_cp_again(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + block_t ovp = overprovision_segments(sbi) << sbi->log_blocks_per_seg; + block_t holes[2] = {0, 0}; /* DATA and NODE */ + struct seg_entry *se; + unsigned int segno; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + se = get_seg_entry(sbi, segno); + if (IS_NODESEG(se->type)) + holes[NODE] += sbi->blocks_per_seg - se->valid_blocks; + else + holes[DATA] += sbi->blocks_per_seg - se->valid_blocks; + } + mutex_unlock(&dirty_i->seglist_lock); + + if (holes[DATA] > ovp || holes[NODE] > ovp) + return -EAGAIN; + return 0; +} + +/* This is only used by SBI_CP_DISABLED */ +static unsigned int get_free_segment(struct f2fs_sb_info *sbi) +{ + struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); + unsigned int segno = 0; + + mutex_lock(&dirty_i->seglist_lock); + for_each_set_bit(segno, dirty_i->dirty_segmap[DIRTY], MAIN_SEGS(sbi)) { + if (get_valid_blocks(sbi, segno, false)) + continue; + if (get_ckpt_valid_blocks(sbi, segno)) + continue; + mutex_unlock(&dirty_i->seglist_lock); + return segno; + } + mutex_unlock(&dirty_i->seglist_lock); + return NULL_SEGNO; +} + static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len) @@ -905,9 +971,9 @@ static void __remove_discard_cmd(struct f2fs_sb_info *sbi, dc->error = 0; if (dc->error) - f2fs_msg(sbi->sb, KERN_INFO, - "Issue discard(%u, %u, %u) failed, ret: %d", - dc->lstart, dc->start, dc->len, dc->error); + printk_ratelimited( + "%sF2FS-fs: Issue discard(%u, %u, %u) failed, ret: %d", + KERN_INFO, dc->lstart, dc->start, dc->len, dc->error); __detach_discard_cmd(dcc, dc); } @@ -1391,7 +1457,7 @@ static unsigned int __issue_discard_cmd_orderly(struct f2fs_sb_info *sbi, if (dc->state != D_PREP) goto next; - if (dpolicy->io_aware && !is_idle(sbi)) { + if (dpolicy->io_aware && !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } @@ -1451,7 +1517,7 @@ static int __issue_discard_cmd(struct f2fs_sb_info *sbi, f2fs_bug_on(sbi, dc->state != D_PREP); if (dpolicy->io_aware && i < dpolicy->io_aware_gran && - !is_idle(sbi)) { + !is_idle(sbi, DISCARD_TIME)) { io_interrupted = true; break; } @@ -1680,7 +1746,9 @@ static int issue_discard_thread(void *data) __wait_all_discard_cmd(sbi, &dpolicy); wait_ms = dpolicy.min_interval; } else if (issued == -1){ - wait_ms = dpolicy.mid_interval; + wait_ms = f2fs_time_to_wait(sbi, DISCARD_TIME); + if (!wait_ms) + wait_ms = dpolicy.mid_interval; } else { wait_ms = dpolicy.max_interval; } @@ -1805,11 +1873,11 @@ static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc, struct list_head *head = &SM_I(sbi)->dcc_info->entry_list; int i; - if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi)) + if (se->valid_blocks == max_blocks || !f2fs_hw_support_discard(sbi)) return false; if (!force) { - if (!test_opt(sbi, DISCARD) || !se->valid_blocks || + if (!f2fs_realtime_discard_enable(sbi) || !se->valid_blocks || SM_I(sbi)->dcc_info->nr_discards >= SM_I(sbi)->dcc_info->max_discards) return false; @@ -1915,7 +1983,7 @@ void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi, dirty_i->nr_dirty[PRE]--; } - if (!test_opt(sbi, DISCARD)) + if (!f2fs_realtime_discard_enable(sbi)) continue; if (force && start >= cpc->trim_start && @@ -2105,12 +2173,12 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) del = 0; } - if (f2fs_discard_en(sbi) && - !f2fs_test_and_set_bit(offset, se->discard_map)) + if (!f2fs_test_and_set_bit(offset, se->discard_map)) sbi->discard_blks--; /* don't overwrite by SSR to keep node chain */ - if (IS_NODESEG(se->type)) { + if (IS_NODESEG(se->type) && + !is_sbi_flag_set(sbi, SBI_CP_DISABLED)) { if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map)) se->ckpt_valid_blocks++; } @@ -2132,10 +2200,18 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del) f2fs_bug_on(sbi, 1); se->valid_blocks++; del = 0; + } else if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + /* + * If checkpoints are off, we must not reuse data that + * was used in the previous checkpoint. If it was used + * before, we must track that to know how much space we + * really have. + */ + if (f2fs_test_bit(offset, se->ckpt_valid_map)) + sbi->unusable_block_count++; } - if (f2fs_discard_en(sbi) && - f2fs_test_and_clear_bit(offset, se->discard_map)) + if (f2fs_test_and_clear_bit(offset, se->discard_map)) sbi->discard_blks++; } if (!f2fs_test_bit(offset, se->ckpt_valid_map)) @@ -2415,6 +2491,9 @@ static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type) if (sbi->segs_per_sec != 1) return CURSEG_I(sbi, type)->segno; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (test_opt(sbi, NOHEAP) && (type == CURSEG_HOT_DATA || IS_NODESEG(type))) return 0; @@ -2512,6 +2591,7 @@ static void change_curseg(struct f2fs_sb_info *sbi, int type) __next_free_blkoff(sbi, curseg, 0); sum_page = f2fs_get_sum_page(sbi, new_segno); + f2fs_bug_on(sbi, IS_ERR(sum_page)); sum_node = (struct f2fs_summary_block *)page_address(sum_page); memcpy(curseg->sum_blk, sum_node, SUM_ENTRY_SIZE); f2fs_put_page(sum_page, 1); @@ -2558,6 +2638,15 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) return 1; } } + + /* find valid_blocks=0 in dirty list */ + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { + segno = get_free_segment(sbi); + if (segno != NULL_SEGNO) { + curseg->next_segno = segno; + return 1; + } + } return 0; } @@ -2575,7 +2664,8 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi, else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) && type == CURSEG_WARM_NODE) new_curseg(sbi, type, false); - else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type)) + else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type) && + likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) new_curseg(sbi, type, false); else if (f2fs_need_SSR(sbi) && get_ssr_segment(sbi, type)) change_curseg(sbi, type); @@ -2751,7 +2841,7 @@ int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range) * discard option. User configuration looks like using runtime discard * or periodic fstrim instead of it. */ - if (test_opt(sbi, DISCARD)) + if (f2fs_realtime_discard_enable(sbi)) goto out; start_block = START_BLOCK(sbi, start_segno); @@ -3101,6 +3191,7 @@ void f2fs_do_write_meta_page(struct f2fs_sb_info *sbi, struct page *page, ClearPageError(page); f2fs_submit_page_write(&fio); + stat_inc_meta_count(sbi, page->index); f2fs_update_iostat(sbi, io_type, F2FS_BLKSIZE); } @@ -3263,8 +3354,7 @@ 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 @@ -3272,10 +3362,14 @@ void f2fs_wait_on_page_writeback(struct page *page, } } -void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) +void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr) { + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *cpage; + if (!f2fs_post_read_required(inode)) + return; + if (!is_valid_data_blkaddr(sbi, blkaddr)) return; @@ -3286,6 +3380,15 @@ void f2fs_wait_on_block_writeback(struct f2fs_sb_info *sbi, block_t blkaddr) } } +void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, + block_t len) +{ + block_t i; + + for (i = 0; i < len; i++) + f2fs_wait_on_block_writeback(inode, blkaddr + i); +} + static int read_compacted_summaries(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); @@ -3843,13 +3946,11 @@ static int build_sit_info(struct f2fs_sb_info *sbi) return -ENOMEM; #endif - if (f2fs_discard_en(sbi)) { - sit_i->sentries[start].discard_map - = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, - GFP_KERNEL); - if (!sit_i->sentries[start].discard_map) - return -ENOMEM; - } + sit_i->sentries[start].discard_map + = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, + GFP_KERNEL); + if (!sit_i->sentries[start].discard_map) + return -ENOMEM; } sit_i->tmp_map = f2fs_kzalloc(sbi, SIT_VBLOCK_MAP_SIZE, GFP_KERNEL); @@ -3985,6 +4086,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) se = &sit_i->sentries[start]; page = get_current_sit_page(sbi, start); + if (IS_ERR(page)) + return PTR_ERR(page); sit_blk = (struct f2fs_sit_block *)page_address(page); sit = sit_blk->entries[SIT_ENTRY_OFFSET(sit_i, start)]; f2fs_put_page(page, 1); @@ -3997,18 +4100,16 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) total_node_blocks += se->valid_blocks; /* build discard map only one time */ - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, - se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += - sbi->blocks_per_seg - - se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, + SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, + se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += + sbi->blocks_per_seg - + se->valid_blocks; } if (sbi->segs_per_sec > 1) @@ -4046,16 +4147,13 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) if (IS_NODESEG(se->type)) total_node_blocks += se->valid_blocks; - if (f2fs_discard_en(sbi)) { - if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { - memset(se->discard_map, 0xff, - SIT_VBLOCK_MAP_SIZE); - } else { - memcpy(se->discard_map, se->cur_valid_map, - SIT_VBLOCK_MAP_SIZE); - sbi->discard_blks += old_valid_blocks; - sbi->discard_blks -= se->valid_blocks; - } + if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) { + memset(se->discard_map, 0xff, SIT_VBLOCK_MAP_SIZE); + } else { + memcpy(se->discard_map, se->cur_valid_map, + SIT_VBLOCK_MAP_SIZE); + sbi->discard_blks += old_valid_blocks; + sbi->discard_blks -= se->valid_blocks; } if (sbi->segs_per_sec > 1) { diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index b3d9e317ff0c..ab3465faddf1 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/segment.h * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/blkdev.h> #include <linux/backing-dev.h> @@ -342,6 +339,12 @@ static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi, return get_seg_entry(sbi, segno)->valid_blocks; } +static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi, + unsigned int segno) +{ + return get_seg_entry(sbi, segno)->ckpt_valid_blocks; +} + static inline void seg_info_from_raw_sit(struct seg_entry *se, struct f2fs_sit_entry *rs) { @@ -579,6 +582,15 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, reserved_sections(sbi) + needed); } +static inline int f2fs_is_checkpoint_ready(struct f2fs_sb_info *sbi) +{ + if (likely(!is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; + if (likely(!has_not_enough_free_secs(sbi, 0, 0))) + return 0; + return -ENOSPC; +} + static inline bool excess_prefree_segs(struct f2fs_sb_info *sbi) { return prefree_segments(sbi) > SM_I(sbi)->rec_prefree_segments; diff --git a/fs/f2fs/shrinker.c b/fs/f2fs/shrinker.c index 36cfd816c160..9e13db994fdf 100644 --- a/fs/f2fs/shrinker.c +++ b/fs/f2fs/shrinker.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs shrinker support * the basic infra was copied from fs/ubifs/shrinker.c * * Copyright (c) 2015 Motorola Mobility * Copyright (c) 2015 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 6b71328cbc6f..cabcd988e78f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/super.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/module.h> #include <linux/init.h> @@ -53,9 +50,10 @@ char *f2fs_fault_name[FAULT_MAX] = { [FAULT_DIR_DEPTH] = "too big dir depth", [FAULT_EVICT_INODE] = "evict_inode fail", [FAULT_TRUNCATE] = "truncate fail", - [FAULT_IO] = "IO error", + [FAULT_READ_IO] = "read IO error", [FAULT_CHECKPOINT] = "checkpoint error", [FAULT_DISCARD] = "discard error", + [FAULT_WRITE_IO] = "write IO error", }; void f2fs_build_fault_attr(struct f2fs_sb_info *sbi, unsigned int rate, @@ -138,6 +136,7 @@ enum { Opt_alloc, Opt_fsync, Opt_test_dummy_encryption, + Opt_checkpoint, Opt_err, }; @@ -196,6 +195,7 @@ static match_table_t f2fs_tokens = { {Opt_alloc, "alloc_mode=%s"}, {Opt_fsync, "fsync_mode=%s"}, {Opt_test_dummy_encryption, "test_dummy_encryption"}, + {Opt_checkpoint, "checkpoint=%s"}, {Opt_err, NULL}, }; @@ -207,7 +207,7 @@ void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk_ratelimited("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); + printk("%sF2FS-fs (%s): %pV\n", level, sb->s_id, &vaf); va_end(args); } @@ -361,7 +361,6 @@ static int f2fs_check_quota_options(struct f2fs_sb_info *sbi) static int parse_options(struct super_block *sb, char *options) { struct f2fs_sb_info *sbi = F2FS_SB(sb); - struct request_queue *q; substring_t args[MAX_OPT_ARGS]; char *p, *name; int arg = 0; @@ -416,14 +415,7 @@ static int parse_options(struct super_block *sb, char *options) return -EINVAL; break; case Opt_discard: - q = bdev_get_queue(sb->s_bdev); - if (blk_queue_discard(q)) { - set_opt(sbi, DISCARD); - } else if (!f2fs_sb_has_blkzoned(sb)) { - f2fs_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + set_opt(sbi, DISCARD); break; case Opt_nodiscard: if (f2fs_sb_has_blkzoned(sb)) { @@ -603,28 +595,31 @@ static int parse_options(struct super_block *sb, char *options) } F2FS_OPTION(sbi).write_io_size_bits = arg; break; +#ifdef CONFIG_F2FS_FAULT_INJECTION case Opt_fault_injection: if (args->from && match_int(args, &arg)) return -EINVAL; -#ifdef CONFIG_F2FS_FAULT_INJECTION f2fs_build_fault_attr(sbi, arg, F2FS_ALL_FAULT_TYPE); set_opt(sbi, FAULT_INJECTION); -#else - f2fs_msg(sb, KERN_INFO, - "FAULT_INJECTION was not selected"); -#endif break; + case Opt_fault_type: if (args->from && match_int(args, &arg)) return -EINVAL; -#ifdef CONFIG_F2FS_FAULT_INJECTION f2fs_build_fault_attr(sbi, 0, arg); set_opt(sbi, FAULT_INJECTION); + break; #else + case Opt_fault_injection: f2fs_msg(sb, KERN_INFO, - "FAULT_INJECTION was not selected"); -#endif + "fault_injection options not supported"); + break; + + case Opt_fault_type: + f2fs_msg(sb, KERN_INFO, + "fault_type options not supported"); break; +#endif case Opt_lazytime: sb->s_flags |= MS_LAZYTIME; break; @@ -777,6 +772,23 @@ static int parse_options(struct super_block *sb, char *options) "Test dummy encryption mount option ignored"); #endif break; + case Opt_checkpoint: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + + if (strlen(name) == 6 && + !strncmp(name, "enable", 6)) { + clear_opt(sbi, DISABLE_CHECKPOINT); + } else if (strlen(name) == 7 && + !strncmp(name, "disable", 7)) { + set_opt(sbi, DISABLE_CHECKPOINT); + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; default: f2fs_msg(sb, KERN_ERR, "Unrecognized mount option \"%s\" or missing value", @@ -835,6 +847,12 @@ static int parse_options(struct super_block *sb, char *options) } } + if (test_opt(sbi, DISABLE_CHECKPOINT) && test_opt(sbi, LFS)) { + f2fs_msg(sb, KERN_ERR, + "LFS not compatible with checkpoint=disable\n"); + return -EINVAL; + } + /* Not pass down write hints if the number of active logs is lesser * than NR_CURSEG_TYPE. */ @@ -1022,8 +1040,8 @@ static void f2fs_put_super(struct super_block *sb) * But, the previous checkpoint was not done by umount, it needs to do * clean checkpoint again. */ - if (is_sbi_flag_set(sbi, SBI_IS_DIRTY) || - !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) { + if ((is_sbi_flag_set(sbi, SBI_IS_DIRTY) || + !is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG))) { struct cp_control cpc = { .reason = CP_UMOUNT, }; @@ -1033,7 +1051,8 @@ static void f2fs_put_super(struct super_block *sb) /* be sure to wait for any on-going discard commands */ dropped = f2fs_wait_discard_bios(sbi); - if (f2fs_discard_en(sbi) && !sbi->discard_blks && !dropped) { + if ((f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) && + !sbi->discard_blks && !dropped) { struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; @@ -1095,6 +1114,8 @@ int f2fs_sync_fs(struct super_block *sb, int sync) if (unlikely(f2fs_cp_error(sbi))) return 0; + if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) + return 0; trace_f2fs_sync_fs(sb, sync); @@ -1195,6 +1216,11 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = user_block_count; buf->f_bfree = user_block_count - valid_user_blocks(sbi) - sbi->current_reserved_blocks; + if (unlikely(buf->f_bfree <= sbi->unusable_block_count)) + buf->f_bfree = 0; + else + buf->f_bfree -= sbi->unusable_block_count; + if (buf->f_bfree > F2FS_OPTION(sbi).root_reserved_blocks) buf->f_bavail = buf->f_bfree - F2FS_OPTION(sbi).root_reserved_blocks; @@ -1339,7 +1365,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) from_kgid_munged(&init_user_ns, F2FS_OPTION(sbi).s_resgid)); if (F2FS_IO_SIZE_BITS(sbi)) - seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi)); + seq_printf(seq, ",io_bits=%u", + F2FS_OPTION(sbi).write_io_size_bits); #ifdef CONFIG_F2FS_FAULT_INJECTION if (test_opt(sbi, FAULT_INJECTION)) { seq_printf(seq, ",fault_injection=%u", @@ -1373,6 +1400,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).alloc_mode == ALLOC_MODE_REUSE) seq_printf(seq, ",alloc_mode=%s", "reuse"); + if (test_opt(sbi, DISABLE_CHECKPOINT)) + seq_puts(seq, ",checkpoint=disable"); + if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_POSIX) seq_printf(seq, ",fsync_mode=%s", "posix"); else if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT) @@ -1401,9 +1431,9 @@ static void default_options(struct f2fs_sb_info *sbi) set_opt(sbi, EXTENT_CACHE); set_opt(sbi, NOHEAP); sbi->sb->s_flags |= MS_LAZYTIME; + clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, FLUSH_MERGE); - if (blk_queue_discard(bdev_get_queue(sbi->sb->s_bdev))) - set_opt(sbi, DISCARD); + set_opt(sbi, DISCARD); if (f2fs_sb_has_blkzoned(sbi->sb)) set_opt_mode(sbi, F2FS_MOUNT_LFS); else @@ -1422,6 +1452,57 @@ static void default_options(struct f2fs_sb_info *sbi) #ifdef CONFIG_QUOTA static int f2fs_enable_quotas(struct super_block *sb); #endif + +static int f2fs_disable_checkpoint(struct f2fs_sb_info *sbi) +{ + struct cp_control cpc; + int err; + + sbi->sb->s_flags |= MS_ACTIVE; + + mutex_lock(&sbi->gc_mutex); + f2fs_update_time(sbi, DISABLE_TIME); + + while (!f2fs_time_over(sbi, DISABLE_TIME)) { + err = f2fs_gc(sbi, true, false, NULL_SEGNO); + if (err == -ENODATA) + break; + if (err && err != -EAGAIN) { + mutex_unlock(&sbi->gc_mutex); + return err; + } + } + mutex_unlock(&sbi->gc_mutex); + + err = sync_filesystem(sbi->sb); + if (err) + return err; + + if (f2fs_disable_cp_again(sbi)) + return -EAGAIN; + + mutex_lock(&sbi->gc_mutex); + cpc.reason = CP_PAUSE; + set_sbi_flag(sbi, SBI_CP_DISABLED); + f2fs_write_checkpoint(sbi, &cpc); + + sbi->unusable_block_count = 0; + mutex_unlock(&sbi->gc_mutex); + return 0; +} + +static void f2fs_enable_checkpoint(struct f2fs_sb_info *sbi) +{ + mutex_lock(&sbi->gc_mutex); + f2fs_dirty_to_prefree(sbi); + + clear_sbi_flag(sbi, SBI_CP_DISABLED); + set_sbi_flag(sbi, SBI_IS_DIRTY); + mutex_unlock(&sbi->gc_mutex); + + f2fs_sync_fs(sbi->sb, 1); +} + static int f2fs_remount(struct super_block *sb, int *flags, char *data) { struct f2fs_sb_info *sbi = F2FS_SB(sb); @@ -1431,6 +1512,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) bool need_restart_gc = false; bool need_stop_gc = false; bool no_extent_cache = !test_opt(sbi, EXTENT_CACHE); + bool disable_checkpoint = test_opt(sbi, DISABLE_CHECKPOINT); + bool checkpoint_changed; #ifdef CONFIG_QUOTA int i, j; #endif @@ -1475,6 +1558,8 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) err = parse_options(sb, data); if (err) goto restore_opts; + checkpoint_changed = + disable_checkpoint != test_opt(sbi, DISABLE_CHECKPOINT); /* * Previous and new state of filesystem is RO, @@ -1508,6 +1593,13 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if ((*flags & MS_RDONLY) && test_opt(sbi, DISABLE_CHECKPOINT)) { + err = -EINVAL; + f2fs_msg(sbi->sb, KERN_WARNING, + "disabling checkpoint not compatible with read-only"); + goto restore_opts; + } + /* * We stop the GC thread if FS is mounted as RO * or if background_gc = off is passed in mount @@ -1536,6 +1628,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_IS_CLOSE); } + if (checkpoint_changed) { + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto restore_gc; + } else { + f2fs_enable_checkpoint(sbi); + } + } + /* * We stop issue flush thread if FS is mounted as RO * or if flush_merge is not passed in mount option. @@ -1559,6 +1661,7 @@ skip: (test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0); limit_reserve_root(sbi); + *flags = (*flags & ~MS_LAZYTIME) | (sb->s_flags & MS_LAZYTIME); return 0; restore_gc: if (need_restart_gc) { @@ -1611,6 +1714,7 @@ repeat: congestion_wait(BLK_RW_ASYNC, HZ/50); goto repeat; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return PTR_ERR(page); } @@ -1622,6 +1726,7 @@ repeat: } if (unlikely(!PageUptodate(page))) { f2fs_put_page(page, 1); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); return -EIO; } @@ -1663,6 +1768,7 @@ retry: congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); break; } @@ -1699,6 +1805,12 @@ static qsize_t *f2fs_get_reserved_space(struct inode *inode) static int f2fs_quota_on_mount(struct f2fs_sb_info *sbi, int type) { + if (is_set_ckpt_flags(sbi, CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sbi->sb, KERN_ERR, + "quota sysfile may be corrupted, skip loading it"); + return 0; + } + return dquot_quota_on_mount(sbi->sb, F2FS_OPTION(sbi).s_qf_names[type], F2FS_OPTION(sbi).s_jquota_fmt, type); } @@ -1769,7 +1881,14 @@ static int f2fs_enable_quotas(struct super_block *sb) test_opt(F2FS_SB(sb), PRJQUOTA), }; + if (is_set_ckpt_flags(F2FS_SB(sb), CP_QUOTA_NEED_FSCK_FLAG)) { + f2fs_msg(sb, KERN_ERR, + "quota file may be corrupted, skip loading it"); + return 0; + } + sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE; + for (type = 0; type < MAXQUOTAS; type++) { qf_inum = f2fs_qf_ino(sb, type); if (qf_inum) { @@ -1783,6 +1902,8 @@ static int f2fs_enable_quotas(struct super_block *sb) "fsck to fix.", type, err); for (type--; type >= 0; type--) dquot_quota_off(sb, type); + set_sbi_flag(F2FS_SB(sb), + SBI_QUOTA_NEED_REPAIR); return err; } } @@ -1790,35 +1911,51 @@ static int f2fs_enable_quotas(struct super_block *sb) return 0; } -static int f2fs_quota_sync(struct super_block *sb, int type) +int f2fs_quota_sync(struct super_block *sb, int type) { + struct f2fs_sb_info *sbi = F2FS_SB(sb); struct quota_info *dqopt = sb_dqopt(sb); int cnt; int ret; ret = dquot_writeback_dquots(sb, type); if (ret) - return ret; + goto out; /* * Now when everything is written we can discard the pagecache so * that userspace sees the changes. */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { + struct address_space *mapping; + if (type != -1 && cnt != type) continue; if (!sb_has_quota_active(sb, cnt)) continue; - ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping); + mapping = dqopt->files[cnt]->i_mapping; + + ret = filemap_fdatawrite(mapping); + if (ret) + goto out; + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + continue; + + ret = filemap_fdatawait(mapping); if (ret) - return ret; + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); inode_lock(dqopt->files[cnt]); truncate_inode_pages(&dqopt->files[cnt]->i_data, 0); inode_unlock(dqopt->files[cnt]); } - return 0; +out: + if (ret) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } static int f2fs_quota_on(struct super_block *sb, int type, int format_id, @@ -1839,8 +1976,7 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, inode_lock(inode); F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; - inode_set_flags(inode, S_NOATIME | S_IMMUTABLE, - S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -1855,7 +1991,9 @@ static int f2fs_quota_off(struct super_block *sb, int type) if (!inode || !igrab(inode)) return dquot_quota_off(sb, type); - f2fs_quota_sync(sb, type); + err = f2fs_quota_sync(sb, type); + if (err) + goto out_put; err = dquot_quota_off(sb, type); if (err || f2fs_sb_has_quota_ino(sb)) @@ -1863,7 +2001,7 @@ static int f2fs_quota_off(struct super_block *sb, int type) inode_lock(inode); F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); - inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE); + f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); out_put: @@ -1874,9 +2012,88 @@ out_put: void f2fs_quota_off_umount(struct super_block *sb) { int type; + int err; + + for (type = 0; type < MAXQUOTAS; type++) { + err = f2fs_quota_off(sb, type); + if (err) { + int ret = dquot_quota_off(sb, type); + + f2fs_msg(sb, KERN_ERR, + "Fail to turn off disk quota " + "(type: %d, err: %d, ret:%d), Please " + "run fsck to fix it.", type, err, ret); + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + } + } +} + +static void f2fs_truncate_quota_inode_pages(struct super_block *sb) +{ + struct quota_info *dqopt = sb_dqopt(sb); + int type; + + for (type = 0; type < MAXQUOTAS; type++) { + if (!dqopt->files[type]) + continue; + f2fs_inode_synced(dqopt->files[type]); + } +} + +static int f2fs_dquot_commit(struct dquot *dquot) +{ + int ret; + + ret = dquot_commit(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_acquire(struct dquot *dquot) +{ + int ret; + + ret = dquot_acquire(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + + return ret; +} + +static int f2fs_dquot_release(struct dquot *dquot) +{ + int ret; + + ret = dquot_release(dquot); + if (ret < 0) + set_sbi_flag(F2FS_SB(dquot->dq_sb), SBI_QUOTA_NEED_REPAIR); + return ret; +} + +static int f2fs_dquot_mark_dquot_dirty(struct dquot *dquot) +{ + struct super_block *sb = dquot->dq_sb; + struct f2fs_sb_info *sbi = F2FS_SB(sb); + int ret; + + ret = dquot_mark_dquot_dirty(dquot); + + /* if we are using journalled quota */ + if (is_journalled_quota(sbi)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_FLUSH); + + return ret; +} - for (type = 0; type < MAXQUOTAS; type++) - f2fs_quota_off(sb, type); +static int f2fs_dquot_commit_info(struct super_block *sb, int type) +{ + int ret; + + ret = dquot_commit_info(sb, type); + if (ret < 0) + set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); + return ret; } #if 0 @@ -1889,11 +2106,11 @@ static int f2fs_get_projid(struct inode *inode, kprojid_t *projid) static const struct dquot_operations f2fs_quota_operations = { .get_reserved_space = f2fs_get_reserved_space, - .write_dquot = dquot_commit, - .acquire_dquot = dquot_acquire, - .release_dquot = dquot_release, - .mark_dirty = dquot_mark_dquot_dirty, - .write_info = dquot_commit_info, + .write_dquot = f2fs_dquot_commit, + .acquire_dquot = f2fs_dquot_acquire, + .release_dquot = f2fs_dquot_release, + .mark_dirty = f2fs_dquot_mark_dquot_dirty, + .write_info = f2fs_dquot_commit_info, .alloc_dquot = dquot_alloc, .destroy_dquot = dquot_destroy, #if 0 @@ -1912,6 +2129,11 @@ static const struct quotactl_ops f2fs_quotactl_ops = { .set_dqblk = dquot_set_dqblk, }; #else +int f2fs_quota_sync(struct super_block *sb, int type) +{ + return 0; +} + void f2fs_quota_off_umount(struct super_block *sb) { } @@ -2176,6 +2398,26 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi, (bh->b_data + F2FS_SUPER_OFFSET); struct super_block *sb = sbi->sb; unsigned int blocksize; + size_t crc_offset = 0; + __u32 crc = 0; + + /* Check checksum_offset and crc in superblock */ + if (le32_to_cpu(raw_super->feature) & F2FS_FEATURE_SB_CHKSUM) { + crc_offset = le32_to_cpu(raw_super->checksum_offset); + if (crc_offset != + offsetof(struct f2fs_super_block, crc)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum offset: %zu", + crc_offset); + return 1; + } + crc = le32_to_cpu(raw_super->crc); + if (!f2fs_crc_valid(sbi, crc, raw_super, crc_offset)) { + f2fs_msg(sb, KERN_INFO, + "Invalid SB checksum value: %u", crc); + return 1; + } + } if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic)) { f2fs_msg(sb, KERN_INFO, @@ -2326,7 +2568,7 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int segment_count_main; unsigned int cp_pack_start_sum, cp_payload; block_t user_block_count; - int i; + int i, j; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -2367,11 +2609,43 @@ int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi) if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_NODE_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_node_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Node segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) return 1; + for (j = i + 1; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u, %u) has the same " + "segno: %u", i, j, + le32_to_cpu(ckpt->cur_data_segno[i])); + return 1; + } + } + } + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + for (j = i; j < NR_CURSEG_DATA_TYPE; j++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) == + le32_to_cpu(ckpt->cur_data_segno[j])) { + f2fs_msg(sbi->sb, KERN_ERR, + "Data segment (%u) and Data segment (%u)" + " has the same segno: %u", i, j, + le32_to_cpu(ckpt->cur_node_segno[i])); + return 1; + } + } } sit_bitmap_size = le32_to_cpu(ckpt->sit_ver_bitmap_bytesize); @@ -2429,6 +2703,9 @@ static void init_sb_info(struct f2fs_sb_info *sbi) sbi->dir_level = DEF_DIR_LEVEL; sbi->interval_time[CP_TIME] = DEF_CP_INTERVAL; sbi->interval_time[REQ_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISCARD_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[GC_TIME] = DEF_IDLE_INTERVAL; + sbi->interval_time[DISABLE_TIME] = DEF_DISABLE_INTERVAL; clear_sbi_flag(sbi, SBI_NEED_FSCK); for (i = 0; i < NR_COUNT_TYPE; i++) @@ -2459,8 +2736,12 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) if (err) return err; - return percpu_counter_init(&sbi->total_valid_inode_count, 0, + err = percpu_counter_init(&sbi->total_valid_inode_count, 0, GFP_KERNEL); + if (err) + percpu_counter_destroy(&sbi->alloc_valid_block_count); + + return err; } #ifdef CONFIG_BLK_DEV_ZONED @@ -2595,6 +2876,7 @@ static int read_raw_super_block(struct f2fs_sb_info *sbi, int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) { struct buffer_head *bh; + __u32 crc = 0; int err; if ((recover && f2fs_readonly(sbi->sb)) || @@ -2603,6 +2885,13 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return -EROFS; } + /* we should update superblock crc here */ + if (!recover && f2fs_sb_has_sb_chksum(sbi->sb)) { + crc = f2fs_crc32(sbi, F2FS_RAW_SUPER(sbi), + offsetof(struct f2fs_super_block, crc)); + F2FS_RAW_SUPER(sbi)->crc = cpu_to_le32(crc); + } + /* write back-up superblock first */ bh = sb_bread(sbi->sb, sbi->valid_super_block ? 0 : 1); if (!bh) @@ -2876,7 +3165,7 @@ try_onemore: GFP_KERNEL); if (!sbi->write_io[i]) { err = -ENOMEM; - goto free_options; + goto free_bio_info; } for (j = HOT; j < n; j++) { @@ -2919,6 +3208,9 @@ try_onemore: goto free_meta_inode; } + if (__is_set_ckpt_flags(F2FS_CKPT(sbi), CP_QUOTA_NEED_FSCK_FLAG)) + set_sbi_flag(sbi, SBI_QUOTA_NEED_REPAIR); + /* Initialize device list */ err = f2fs_scan_devices(sbi); if (err) { @@ -3016,11 +3308,9 @@ try_onemore: /* Enable quota usage during mount */ if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) { err = f2fs_enable_quotas(sb); - if (err) { + if (err) f2fs_msg(sb, KERN_ERR, "Cannot turn on quotas: error %d", err); - goto free_sysfs; - } } #endif /* if there are nt orphan nodes free them */ @@ -3028,6 +3318,9 @@ try_onemore: if (err) goto free_meta; + if (unlikely(is_set_ckpt_flags(sbi, CP_DISABLED_FLAG))) + goto skip_recovery; + /* recover fsynced data */ if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) { /* @@ -3067,6 +3360,14 @@ skip_recovery: /* f2fs_recover_fsync_data() cleared this already */ clear_sbi_flag(sbi, SBI_POR_DOING); + if (test_opt(sbi, DISABLE_CHECKPOINT)) { + err = f2fs_disable_checkpoint(sbi); + if (err) + goto free_meta; + } else if (is_set_ckpt_flags(sbi, CP_DISABLED_FLAG)) { + f2fs_enable_checkpoint(sbi); + } + /* * If filesystem is not mounted as read-only then * do start the gc_thread. @@ -3099,10 +3400,10 @@ skip_recovery: free_meta: #ifdef CONFIG_QUOTA + f2fs_truncate_quota_inode_pages(sb); if (f2fs_sb_has_quota_ino(sb) && !f2fs_readonly(sb)) f2fs_quota_off_umount(sbi->sb); #endif - f2fs_sync_inode_meta(sbi); /* * Some dirty meta pages can be produced by f2fs_recover_orphan_inodes() * failed by EIO. Then, iput(node_inode) can trigger balance_fs_bg() @@ -3110,9 +3411,6 @@ free_meta: * falls into an infinite loop in f2fs_sync_meta_pages(). */ truncate_inode_pages_final(META_MAPPING(sbi)); -#ifdef CONFIG_QUOTA -free_sysfs: -#endif f2fs_unregister_sysfs(sbi); free_root_inode: dput(sb->s_root); @@ -3184,6 +3482,9 @@ static void kill_f2fs_super(struct super_block *sb) }; f2fs_write_checkpoint(sbi, &cpc); } + + if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb)) + sb->s_flags &= ~MS_RDONLY; } kill_block_super(sb); } diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 30fd016afeb3..db89741b219b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -1,13 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs sysfs interface * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * Copyright (c) 2017 Chao Yu <chao@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/compiler.h> #include <linux/proc_fs.h> @@ -120,6 +117,9 @@ static ssize_t features_show(struct f2fs_attr *a, if (f2fs_sb_has_lost_found(sb)) len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len ? ", " : "", "lost_found"); + if (f2fs_sb_has_sb_chksum(sb)) + len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", + len ? ", " : "", "sb_checksum"); len += snprintf(buf + len, PAGE_SIZE - len, "\n"); return len; } @@ -337,6 +337,7 @@ enum feat_id { FEAT_QUOTA_INO, FEAT_INODE_CRTIME, FEAT_LOST_FOUND, + FEAT_SB_CHECKSUM, }; static ssize_t f2fs_feature_show(struct f2fs_attr *a, @@ -353,6 +354,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a, case FEAT_QUOTA_INO: case FEAT_INODE_CRTIME: case FEAT_LOST_FOUND: + case FEAT_SB_CHECKSUM: return snprintf(buf, PAGE_SIZE, "supported\n"); } return 0; @@ -407,6 +409,9 @@ F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, + interval_time[DISCARD_TIME]); +F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); @@ -434,6 +439,7 @@ F2FS_FEATURE_RO_ATTR(flexible_inline_xattr, FEAT_FLEXIBLE_INLINE_XATTR); F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO); F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); +F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { @@ -460,6 +466,8 @@ static struct attribute *f2fs_attrs[] = { ATTR_LIST(dirty_nats_ratio), ATTR_LIST(cp_interval), ATTR_LIST(idle_interval), + ATTR_LIST(discard_idle_interval), + ATTR_LIST(gc_idle_interval), ATTR_LIST(iostat_enable), ATTR_LIST(readdir_ra), ATTR_LIST(gc_pin_file_thresh), @@ -491,6 +499,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(quota_ino), ATTR_LIST(inode_crtime), ATTR_LIST(lost_found), + ATTR_LIST(sb_checksum), NULL, }; diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c index a1fcd00bbb2b..ce2a5eb210b6 100644 --- a/fs/f2fs/trace.c +++ b/fs/f2fs/trace.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/trace.h b/fs/f2fs/trace.h index 67db24ac1e85..e8075fc5b228 100644 --- a/fs/f2fs/trace.h +++ b/fs/f2fs/trace.h @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * f2fs IO tracer * * Copyright (c) 2014 Motorola Mobility * Copyright (c) 2014 Jaegeuk Kim <jaegeuk@kernel.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_TRACE_H__ #define __F2FS_TRACE_H__ diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 152078bb4829..c7c3c2a63a85 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.c * @@ -13,10 +14,6 @@ * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include <linux/rwsem.h> #include <linux/f2fs_fs.h> diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 08a4840d6d7d..595d2af00a58 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/xattr.h * @@ -9,10 +10,6 @@ * On-disk format of extended attributes for the ext2 filesystem. * * (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __F2FS_XATTR_H__ #define __F2FS_XATTR_H__ diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index a70e37c47a78..e3fc477728b3 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -681,6 +681,7 @@ int fat_count_free_clusters(struct super_block *sb) if (ops->ent_get(&fatent) == FAT_ENT_FREE) free++; } while (fat_ent_next(sbi, &fatent)); + cond_resched(); } sbi->free_clusters = free; sbi->free_clus_valid = 1; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index d584bcbca80a..e98a75233f68 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -404,12 +404,19 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req) if (test_bit(FR_BACKGROUND, &req->flags)) { spin_lock(&fc->lock); clear_bit(FR_BACKGROUND, &req->flags); - if (fc->num_background == fc->max_background) + if (fc->num_background == fc->max_background) { fc->blocked = 0; - - /* Wake up next waiter, if any */ - if (!fc->blocked && waitqueue_active(&fc->blocked_waitq)) wake_up(&fc->blocked_waitq); + } else if (!fc->blocked) { + /* + * Wake up next waiter, if any. It's okay to use + * waitqueue_active(), as we've already synced up + * fc->blocked with waiters with the wake_up() call + * above. + */ + if (waitqueue_active(&fc->blocked_waitq)) + wake_up(&fc->blocked_waitq); + } if (fc->num_background == fc->congestion_threshold && fc->connected && fc->bdi_initialized) { @@ -1332,12 +1339,14 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file, goto out_end; } list_move_tail(&req->list, &fpq->processing); - spin_unlock(&fpq->lock); + __fuse_get_request(req); set_bit(FR_SENT, &req->flags); + spin_unlock(&fpq->lock); /* matches barrier in request_wait_answer() */ smp_mb__after_atomic(); if (test_bit(FR_INTERRUPTED, &req->flags)) queue_interrupt(fiq, req); + fuse_put_request(fc, req); return reqsize; @@ -1766,8 +1775,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.args[1].size = total_len; err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique); - if (err) + if (err) { fuse_retrieve_end(fc, req); + fuse_put_request(fc, req); + } return err; } @@ -1926,16 +1937,20 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, /* Is it an interrupt reply? */ if (req->intr_unique == oh.unique) { + __fuse_get_request(req); spin_unlock(&fpq->lock); err = -EINVAL; - if (nbytes != sizeof(struct fuse_out_header)) + if (nbytes != sizeof(struct fuse_out_header)) { + fuse_put_request(fc, req); goto err_finish; + } if (oh.error == -ENOSYS) fc->no_interrupt = 1; else if (oh.error == -EAGAIN) queue_interrupt(&fc->iq, req); + fuse_put_request(fc, req); fuse_copy_finish(cs); return nbytes; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 8577f3ba6dc6..7014318f6d18 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -625,7 +625,7 @@ static void fuse_aio_complete_req(struct fuse_conn *fc, struct fuse_req *req) struct fuse_io_priv *io = req->io; ssize_t pos = -1; - fuse_release_user_pages(req, !io->write); + fuse_release_user_pages(req, io->should_dirty); if (io->write) { if (req->misc.write.in.size != req->misc.write.out.size) @@ -1333,7 +1333,6 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, loff_t *ppos, int flags) { int write = flags & FUSE_DIO_WRITE; - bool should_dirty = !write && iter_is_iovec(iter); int cuse = flags & FUSE_DIO_CUSE; struct file *file = io->file; struct inode *inode = file->f_mapping->host; @@ -1362,6 +1361,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, mutex_unlock(&inode->i_mutex); } + io->should_dirty = !write && iter_is_iovec(iter); while (count) { size_t nres; fl_owner_t owner = current->files; @@ -1378,7 +1378,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter, nres = fuse_send_read(req, io, pos, nbytes, owner); if (!io->async) - fuse_release_user_pages(req, should_dirty); + fuse_release_user_pages(req, io->should_dirty); if (req->out.h.error) { if (!res) res = req->out.h.error; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index d88340e84b5f..d40fad13cf43 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -252,6 +252,7 @@ struct fuse_io_priv { size_t size; __u64 offset; bool write; + bool should_dirty; int err; struct kiocb *iocb; struct file *file; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index baab99b69d8a..de7143e2b361 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -71,13 +71,13 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) if (!sdp) return NULL; - sb->s_fs_info = sdp; sdp->sd_vfs = sb; sdp->sd_lkstats = alloc_percpu(struct gfs2_pcpu_lkstats); if (!sdp->sd_lkstats) { kfree(sdp); return NULL; } + sb->s_fs_info = sdp; set_bit(SDF_NOJOURNALID, &sdp->sd_flags); gfs2_tune_init(&sdp->sd_tune); @@ -1353,6 +1353,9 @@ static struct dentry *gfs2_mount_meta(struct file_system_type *fs_type, struct path path; int error; + if (!dev_name || !*dev_name) + return ERR_PTR(-EINVAL); + error = kern_path(dev_name, LOOKUP_FOLLOW, &path); if (error) { pr_warn("path_lookup on %s returned error %d\n", diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index c134c0462cee..ef24894edecc 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -732,6 +732,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) spin_lock(&gl->gl_lockref.lock); gl->gl_object = NULL; spin_unlock(&gl->gl_lockref.lock); + gfs2_rgrp_brelse(rgd); gfs2_glock_add_to_lru(gl); gfs2_glock_put(gl); } @@ -1139,7 +1140,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd) * @rgd: the struct gfs2_rgrpd describing the RG to read in * * Read in all of a Resource Group's header and bitmap blocks. - * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. + * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps. * * Returns: errno */ diff --git a/fs/hfs/brec.c b/fs/hfs/brec.c index 2a6f3c67cb3f..2e713673df42 100644 --- a/fs/hfs/brec.c +++ b/fs/hfs/brec.c @@ -424,6 +424,10 @@ skip: if (new_node) { __be32 cnid; + if (!new_node->parent) { + hfs_btree_inc_height(tree); + new_node->parent = tree->root; + } fd->bnode = hfs_bnode_find(tree, new_node->parent); /* create index key and entry */ hfs_bnode_read_key(new_node, fd->search_key, 14); diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c index 754fdf8c6356..1002a0c08319 100644 --- a/fs/hfsplus/brec.c +++ b/fs/hfsplus/brec.c @@ -427,6 +427,10 @@ skip: if (new_node) { __be32 cnid; + if (!new_node->parent) { + hfs_btree_inc_height(tree); + new_node->parent = tree->root; + } fd->bnode = hfs_bnode_find(tree, new_node->parent); /* create index key and entry */ hfs_bnode_read_key(new_node, fd->search_key, 14); diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 684996c8a3a4..4d5a5a4cc017 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -254,8 +254,8 @@ restart: bh = jh2bh(jh); if (buffer_locked(bh)) { - spin_unlock(&journal->j_list_lock); get_bh(bh); + spin_unlock(&journal->j_list_lock); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); @@ -336,8 +336,8 @@ restart2: jh = transaction->t_checkpoint_io_list; bh = jh2bh(jh); if (buffer_locked(bh)) { - spin_unlock(&journal->j_list_lock); get_bh(bh); + spin_unlock(&journal->j_list_lock); wait_on_buffer(bh); /* the journal_head may have gone by now */ BUFFER_TRACE(bh, "brelse"); diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c index 600da1a4df29..1544f530ccd0 100644 --- a/fs/jffs2/super.c +++ b/fs/jffs2/super.c @@ -285,10 +285,8 @@ static int jffs2_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = c; ret = jffs2_parse_options(c, data); - if (ret) { - kfree(c); + if (ret) return -EINVAL; - } /* Initialize JFFS2 superblock locks, the further initialization will * be done later */ diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index 4c2c03663533..8e1427762eeb 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -1004,12 +1004,14 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) rc = xhandle->list(xhandle, dentry, buffer + len, size - len, xd->xname, xd->name_len); + if (rc > size - len) { + rc = -ERANGE; + goto out; + } } else { rc = xhandle->list(xhandle, dentry, NULL, 0, xd->xname, xd->name_len); } - if (rc < 0) - goto out; len += rc; } rc = len; diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index db272528ab5b..b3b293e2c099 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -88,7 +88,7 @@ static int kernfs_get_target_path(struct kernfs_node *parent, int slen = strlen(kn->name); len -= slen; - strncpy(s + len, kn->name, slen); + memcpy(s + len, kn->name, slen); if (len) s[--len] = '/'; diff --git a/fs/lockd/host.c b/fs/lockd/host.c index d716c9993a26..c7eb47f2fb6c 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -340,7 +340,7 @@ struct nlm_host *nlmsvc_lookup_host(const struct svc_rqst *rqstp, }; struct lockd_net *ln = net_generic(net, lockd_net_id); - dprintk("lockd: %s(host='%*s', vers=%u, proto=%s)\n", __func__, + dprintk("lockd: %s(host='%.*s', vers=%u, proto=%s)\n", __func__, (int)hostname_len, hostname, rqstp->rq_vers, (rqstp->rq_prot == IPPROTO_UDP ? "udp" : "tcp")); diff --git a/fs/namei.c b/fs/namei.c index 5b56423e2e0b..9071bb1bd184 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -884,6 +884,8 @@ static inline void put_link(struct nameidata *nd) int sysctl_protected_symlinks __read_mostly = 0; int sysctl_protected_hardlinks __read_mostly = 0; +int sysctl_protected_fifos __read_mostly; +int sysctl_protected_regular __read_mostly; /** * may_follow_link - Check symlink following for unsafe situations @@ -997,6 +999,45 @@ static int may_linkat(struct path *link) return -EPERM; } +/** + * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory + * should be allowed, or not, on files that already + * exist. + * @dir: the sticky parent directory + * @inode: the inode of the file to open + * + * Block an O_CREAT open of a FIFO (or a regular file) when: + * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled + * - the file already exists + * - we are in a sticky directory + * - we don't own the file + * - the owner of the directory doesn't own the file + * - the directory is world writable + * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 + * the directory doesn't have to be world writable: being group writable will + * be enough. + * + * Returns 0 if the open is allowed, -ve on error. + */ +static int may_create_in_sticky(struct dentry * const dir, + struct inode * const inode) +{ + if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) || + (!sysctl_protected_regular && S_ISREG(inode->i_mode)) || + likely(!(dir->d_inode->i_mode & S_ISVTX)) || + uid_eq(inode->i_uid, dir->d_inode->i_uid) || + uid_eq(current_fsuid(), inode->i_uid)) + return 0; + + if (likely(dir->d_inode->i_mode & 0002) || + (dir->d_inode->i_mode & 0020 && + ((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) || + (sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) { + return -EACCES; + } + return 0; +} + static __always_inline const char *get_link(struct nameidata *nd) { @@ -3198,9 +3239,15 @@ finish_open: error = -ELOOP; goto out; } - error = -EISDIR; - if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) - goto out; + if (open_flag & O_CREAT) { + error = -EISDIR; + if (d_is_dir(nd->path.dentry)) + goto out; + error = may_create_in_sticky(dir, + d_backing_inode(nd->path.dentry)); + if (unlikely(error)) + goto out; + } error = -ENOTDIR; if ((nd->flags & LOOKUP_DIRECTORY) && !d_can_lookup(nd->path.dentry)) goto out; diff --git a/fs/namespace.c b/fs/namespace.c index 996e1046e1ff..cee965df8d7e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1602,8 +1602,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1617,6 +1622,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1699,7 +1705,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1777,8 +1783,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1831,7 +1843,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 63498e1a542a..ae91d1e450be 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -879,10 +879,10 @@ EXPORT_SYMBOL_GPL(nfs4_set_ds_client); /* * Session has been established, and the client marked ready. - * Set the mount rsize and wsize with negotiated fore channel - * attributes which will be bound checked in nfs_server_set_fsinfo. + * Limit the mount rsize, wsize and dtsize using negotiated fore + * channel attributes. */ -static void nfs4_session_set_rwsize(struct nfs_server *server) +static void nfs4_session_limit_rwsize(struct nfs_server *server) { #ifdef CONFIG_NFS_V4_1 struct nfs4_session *sess; @@ -895,9 +895,11 @@ static void nfs4_session_set_rwsize(struct nfs_server *server) server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; - if (!server->rsize || server->rsize > server_resp_sz) + if (server->dtsize > server_resp_sz) + server->dtsize = server_resp_sz; + if (server->rsize > server_resp_sz) server->rsize = server_resp_sz; - if (!server->wsize || server->wsize > server_rqst_sz) + if (server->wsize > server_rqst_sz) server->wsize = server_rqst_sz; #endif /* CONFIG_NFS_V4_1 */ } @@ -944,12 +946,12 @@ static int nfs4_server_common_setup(struct nfs_server *server, (unsigned long long) server->fsid.minor); nfs_display_fhandle(mntfh, "Pseudo-fs root FH"); - nfs4_session_set_rwsize(server); - error = nfs_probe_fsinfo(server, mntfh, fattr); if (error < 0) goto out; + nfs4_session_limit_rwsize(server); + if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) server->namelen = NFS4_MAXNAMLEN; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bfbee8ddf978..c67064d94096 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1632,6 +1632,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (status) { op = &args->ops[0]; op->status = status; + resp->opcnt = 1; goto encode_op; } diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index ffecf89c8c1c..49af618e410d 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -1896,8 +1896,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, /* On error, skip the f_pos to the next block. */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; - brelse(bh); - continue; + break; } if (le64_to_cpu(de->inode)) { unsigned char d_type = DT_UNKNOWN; diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index 4e2162b355db..0cefb036a17e 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -589,9 +589,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm, res->last_used = 0; - spin_lock(&dlm->spinlock); + spin_lock(&dlm->track_lock); list_add_tail(&res->tracking, &dlm->tracking_list); - spin_unlock(&dlm->spinlock); + spin_unlock(&dlm->track_lock); memset(res->lvb, 0, DLM_LVB_LEN); memset(res->refmap, 0, sizeof(res->refmap)); diff --git a/fs/proc/base.c b/fs/proc/base.c index d1a675d32320..d780651a760c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -472,6 +472,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, int err; int i; + /* + * The ability to racily run the kernel stack unwinder on a running task + * and then observe the unwinder output is scary; while it is useful for + * debugging kernel issues, it can also allow an attacker to leak kernel + * stack contents. + * Doing this in a manner that is at least safe from races would require + * some work to ensure that the remote task can not be scheduled; and + * even then, this would still expose the unwinder as local attack + * surface. + * Therefore, this interface is restricted to root. + */ + if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) + return -EACCES; + entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 8b32fdaad468..d424b3d4bf3b 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -184,6 +184,7 @@ struct reiserfs_dentry_buf { struct dir_context ctx; struct dentry *xadir; int count; + int err; struct dentry *dentries[8]; }; @@ -206,6 +207,7 @@ fill_with_dentries(struct dir_context *ctx, const char *name, int namelen, dentry = lookup_one_len(name, dbuf->xadir, namelen); if (IS_ERR(dentry)) { + dbuf->err = PTR_ERR(dentry); return PTR_ERR(dentry); } else if (d_really_is_negative(dentry)) { /* A directory entry exists, but no file? */ @@ -214,6 +216,7 @@ fill_with_dentries(struct dir_context *ctx, const char *name, int namelen, "not found for file %pd.\n", dentry, dbuf->xadir); dput(dentry); + dbuf->err = -EIO; return -EIO; } @@ -261,6 +264,10 @@ static int reiserfs_for_each_xattr(struct inode *inode, err = reiserfs_readdir_inode(d_inode(dir), &buf.ctx); if (err) break; + if (buf.err) { + err = buf.err; + break; + } if (!buf.count) break; for (i = 0; !err && i < buf.count && buf.dentries[i]; i++) { diff --git a/fs/sdcardfs/dentry.c b/fs/sdcardfs/dentry.c index 3795d2c26915..eb279de02ffb 100644 --- a/fs/sdcardfs/dentry.c +++ b/fs/sdcardfs/dentry.c @@ -123,6 +123,12 @@ out: return err; } +/* 1 = delete, 0 = cache */ +static int sdcardfs_d_delete(const struct dentry *d) +{ + return SDCARDFS_SB(d->d_sb)->options.nocache ? 1 : 0; +} + static void sdcardfs_d_release(struct dentry *dentry) { if (!dentry || !dentry->d_fsdata) @@ -182,6 +188,7 @@ static void sdcardfs_canonical_path(const struct path *path, const struct dentry_operations sdcardfs_ci_dops = { .d_revalidate = sdcardfs_d_revalidate, + .d_delete = sdcardfs_d_delete, .d_release = sdcardfs_d_release, .d_hash = sdcardfs_hash_ci, .d_compare = sdcardfs_cmp_ci, diff --git a/fs/sdcardfs/derived_perm.c b/fs/sdcardfs/derived_perm.c index 85126ec6533c..1f142fed5a5e 100644 --- a/fs/sdcardfs/derived_perm.c +++ b/fs/sdcardfs/derived_perm.c @@ -62,6 +62,7 @@ void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, int err; struct qstr q_Android = QSTR_LITERAL("Android"); struct qstr q_data = QSTR_LITERAL("data"); + struct qstr q_sandbox = QSTR_LITERAL("sandbox"); struct qstr q_obb = QSTR_LITERAL("obb"); struct qstr q_media = QSTR_LITERAL("media"); struct qstr q_cache = QSTR_LITERAL("cache"); @@ -110,6 +111,9 @@ void get_derived_permission_new(struct dentry *parent, struct dentry *dentry, if (qstr_case_eq(name, &q_data)) { /* App-specific directories inside; let anyone traverse */ info->data->perm = PERM_ANDROID_DATA; + } else if (qstr_case_eq(name, &q_sandbox)) { + /* App-specific directories inside; let anyone traverse */ + info->data->perm = PERM_ANDROID_DATA; } else if (qstr_case_eq(name, &q_obb)) { /* App-specific directories inside; let anyone traverse */ info->data->perm = PERM_ANDROID_OBB; @@ -356,7 +360,8 @@ int need_graft_path(struct dentry *dentry) struct sdcardfs_sb_info *sbi = SDCARDFS_SB(dentry->d_sb); struct qstr obb = QSTR_LITERAL("obb"); - if (parent_info->data->perm == PERM_ANDROID && + if (!sbi->options.unshared_obb && + parent_info->data->perm == PERM_ANDROID && qstr_case_eq(&dentry->d_name, &obb)) { /* /Android/obb is the base obbpath of DERIVED_UNIFIED */ diff --git a/fs/sdcardfs/main.c b/fs/sdcardfs/main.c index 27ec726e7a46..d890c5711907 100644 --- a/fs/sdcardfs/main.c +++ b/fs/sdcardfs/main.c @@ -34,6 +34,8 @@ enum { Opt_reserved_mb, Opt_gid_derivation, Opt_default_normal, + Opt_nocache, + Opt_unshared_obb, Opt_err, }; @@ -47,7 +49,9 @@ static const match_table_t sdcardfs_tokens = { {Opt_multiuser, "multiuser"}, {Opt_gid_derivation, "derive_gid"}, {Opt_default_normal, "default_normal"}, + {Opt_unshared_obb, "unshared_obb"}, {Opt_reserved_mb, "reserved_mb=%u"}, + {Opt_nocache, "nocache"}, {Opt_err, NULL} }; @@ -71,6 +75,7 @@ static int parse_options(struct super_block *sb, char *options, int silent, /* by default, gid derivation is off */ opts->gid_derivation = false; opts->default_normal = false; + opts->nocache = false; *debug = 0; @@ -128,6 +133,12 @@ static int parse_options(struct super_block *sb, char *options, int silent, case Opt_default_normal: opts->default_normal = true; break; + case Opt_nocache: + opts->nocache = true; + break; + case Opt_unshared_obb: + opts->unshared_obb = true; + break; /* unknown option */ default: if (!silent) @@ -181,13 +192,16 @@ int parse_options_remount(struct super_block *sb, char *options, int silent, return 0; vfsopts->mask = option; break; + case Opt_unshared_obb: case Opt_default_normal: case Opt_multiuser: case Opt_userid: case Opt_fsuid: case Opt_fsgid: case Opt_reserved_mb: - pr_warn("Option \"%s\" can't be changed during remount\n", p); + case Opt_gid_derivation: + if (!silent) + pr_warn("Option \"%s\" can't be changed during remount\n", p); break; /* unknown option */ default: diff --git a/fs/sdcardfs/sdcardfs.h b/fs/sdcardfs/sdcardfs.h index 99227a07a8d6..2bee162921ce 100644 --- a/fs/sdcardfs/sdcardfs.h +++ b/fs/sdcardfs/sdcardfs.h @@ -197,7 +197,9 @@ struct sdcardfs_mount_options { bool multiuser; bool gid_derivation; bool default_normal; + bool unshared_obb; unsigned int reserved_mb; + bool nocache; }; struct sdcardfs_vfsmount_options { diff --git a/fs/sdcardfs/super.c b/fs/sdcardfs/super.c index cffcdb11cb8a..140696ed3ed3 100644 --- a/fs/sdcardfs/super.c +++ b/fs/sdcardfs/super.c @@ -311,6 +311,8 @@ static int sdcardfs_show_options(struct vfsmount *mnt, struct seq_file *m, seq_puts(m, ",default_normal"); if (opts->reserved_mb != 0) seq_printf(m, ",reserved=%uMB", opts->reserved_mb); + if (opts->nocache) + seq_printf(m, ",nocache"); return 0; }; diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 0bb6de356451..7968b7a5e787 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1918,6 +1918,9 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode) int dev, vol; char *endptr; + if (!name || !*name) + return ERR_PTR(-EINVAL); + /* First, try to open using the device node path method */ ubi = ubi_open_volume_path(name, mode); if (!IS_ERR(ubi)) |