diff options
Diffstat (limited to 'fs')
67 files changed, 1157 insertions, 475 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index ebf5079096af..c0d17a369bda 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -4583,7 +4583,7 @@ static void check_removing_space_info(struct btrfs_space_info *space_info) for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) { if (space_info->sub_group[i]) { check_removing_space_info(space_info->sub_group[i]); - kfree(space_info->sub_group[i]); + btrfs_sysfs_remove_space_info(space_info->sub_group[i]); space_info->sub_group[i] = NULL; } } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 01f2dbb69832..1b0eb246b714 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2531,8 +2531,8 @@ int btrfs_validate_super(const struct btrfs_fs_info *fs_info, if (mirror_num >= 0 && btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) { - btrfs_err(fs_info, "super offset mismatch %llu != %u", - btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET); + btrfs_err(fs_info, "super offset mismatch %llu != %llu", + btrfs_super_bytenr(sb), btrfs_sb_offset(mirror_num)); ret = -EINVAL; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index ab0d460c7139..ac871efb9763 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4616,21 +4616,32 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, struct inode *inode, bool log_inode_only, u64 logged_isize) { + u64 gen = BTRFS_I(inode)->generation; u64 flags; if (log_inode_only) { - /* set the generation to zero so the recover code - * can tell the difference between an logging - * just to say 'this inode exists' and a logging - * to say 'update this inode with these values' + /* + * Set the generation to zero so the recover code can tell the + * difference between a logging just to say 'this inode exists' + * and a logging to say 'update this inode with these values'. + * But only if the inode was not already logged before. + * We access ->logged_trans directly since it was already set + * up in the call chain by btrfs_log_inode(), and data_race() + * to avoid false alerts from KCSAN and since it was set already + * and one can set it to 0 since that only happens on eviction + * and we are holding a ref on the inode. */ - btrfs_set_inode_generation(leaf, item, 0); + ASSERT(data_race(BTRFS_I(inode)->logged_trans) > 0); + if (data_race(BTRFS_I(inode)->logged_trans) < trans->transid) + gen = 0; + btrfs_set_inode_size(leaf, item, logged_isize); } else { - btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation); btrfs_set_inode_size(leaf, item, inode->i_size); } + btrfs_set_inode_generation(leaf, item, gen); + btrfs_set_inode_uid(leaf, item, i_uid_read(inode)); btrfs_set_inode_gid(leaf, item, i_gid_read(inode)); btrfs_set_inode_mode(leaf, item, inode->i_mode); @@ -5448,42 +5459,63 @@ process: return 0; } -static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode, - struct btrfs_path *path, u64 *size_ret) +static int get_inode_size_to_log(struct btrfs_trans_handle *trans, + struct btrfs_inode *inode, + struct btrfs_path *path, u64 *size_ret) { struct btrfs_key key; + struct btrfs_inode_item *item; int ret; key.objectid = btrfs_ino(inode); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; - ret = btrfs_search_slot(NULL, log, &key, path, 0, 0); - if (ret < 0) { - return ret; - } else if (ret > 0) { - *size_ret = 0; - } else { - struct btrfs_inode_item *item; + /* + * Our caller called inode_logged(), so logged_trans is up to date. + * Use data_race() to silence any warning from KCSAN. Once logged_trans + * is set, it can only be reset to 0 after inode eviction. + */ + if (data_race(inode->logged_trans) == trans->transid) { + ret = btrfs_search_slot(NULL, inode->root->log_root, &key, path, 0, 0); + } else if (inode->generation < trans->transid) { + path->search_commit_root = true; + path->skip_locking = true; + ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0); + path->search_commit_root = false; + path->skip_locking = false; - item = btrfs_item_ptr(path->nodes[0], path->slots[0], - struct btrfs_inode_item); - *size_ret = btrfs_inode_size(path->nodes[0], item); - /* - * If the in-memory inode's i_size is smaller then the inode - * size stored in the btree, return the inode's i_size, so - * that we get a correct inode size after replaying the log - * when before a power failure we had a shrinking truncate - * followed by addition of a new name (rename / new hard link). - * Otherwise return the inode size from the btree, to avoid - * data loss when replaying a log due to previously doing a - * write that expands the inode's size and logging a new name - * immediately after. - */ - if (*size_ret > inode->vfs_inode.i_size) - *size_ret = inode->vfs_inode.i_size; + } else { + *size_ret = 0; + return 0; } + /* + * If the inode was logged before or is from a past transaction, then + * its inode item must exist in the log root or in the commit root. + */ + ASSERT(ret <= 0); + if (WARN_ON_ONCE(ret > 0)) + ret = -ENOENT; + + if (ret < 0) + return ret; + + item = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_inode_item); + *size_ret = btrfs_inode_size(path->nodes[0], item); + /* + * If the in-memory inode's i_size is smaller then the inode size stored + * in the btree, return the inode's i_size, so that we get a correct + * inode size after replaying the log when before a power failure we had + * a shrinking truncate followed by addition of a new name (rename / new + * hard link). Otherwise return the inode size from the btree, to avoid + * data loss when replaying a log due to previously doing a write that + * expands the inode's size and logging a new name immediately after. + */ + if (*size_ret > inode->vfs_inode.i_size) + *size_ret = inode->vfs_inode.i_size; + btrfs_release_path(path); return 0; } @@ -6996,7 +7028,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, ret = drop_inode_items(trans, log, path, inode, BTRFS_XATTR_ITEM_KEY); } else { - if (inode_only == LOG_INODE_EXISTS && ctx->logged_before) { + if (inode_only == LOG_INODE_EXISTS) { /* * Make sure the new inode item we write to the log has * the same isize as the current one (if it exists). @@ -7010,7 +7042,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, * (zeroes), as if an expanding truncate happened, * instead of getting a file of 4Kb only. */ - ret = logged_inode_size(log, inode, path, &logged_isize); + ret = get_inode_size_to_log(trans, inode, path, &logged_isize); if (ret) goto out_unlock; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ab51e6ecfdef..6b8e810a35ce 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -8099,8 +8099,9 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans) smp_rmb(); ret = update_dev_stat_item(trans, device); - if (!ret) - atomic_sub(stats_cnt, &device->dev_stats_ccnt); + if (ret) + break; + atomic_sub(stats_cnt, &device->dev_stats_ccnt); } mutex_unlock(&fs_devices->device_list_mutex); diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 1b7544aa88a2..c676e715b4f8 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -308,7 +308,9 @@ int zlib_compress_bio(struct list_head *ws, struct compressed_bio *cb) } /* Queue the remaining part of the folio. */ if (workspace->strm.total_out > bio->bi_iter.bi_size) { - u32 cur_len = offset_in_folio(out_folio, workspace->strm.total_out); + const u32 cur_len = workspace->strm.total_out - bio->bi_iter.bi_size; + + ASSERT(cur_len <= folio_size(out_folio)); if (!bio_add_folio(bio, out_folio, cur_len, 0)) { ret = -E2BIG; diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile index 72206a292676..3baee4e7c1cf 100644 --- a/fs/ext4/Makefile +++ b/fs/ext4/Makefile @@ -14,7 +14,8 @@ ext4-y := balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \ ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o -ext4-inode-test-objs += inode-test.o -obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-inode-test.o +ext4-test-objs += inode-test.o mballoc-test.o \ + extents-test.o +obj-$(CONFIG_EXT4_KUNIT_TESTS) += ext4-test.o ext4-$(CONFIG_FS_VERITY) += verity.o ext4-$(CONFIG_FS_ENCRYPTION) += crypto.o diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index cf0a0970c095..f41f320f4437 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -163,10 +163,17 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, */ if (handle) { + /* + * Since the inode is new it is ok to pass the + * XATTR_CREATE flag. This is necessary to match the + * remaining journal credits check in the set_handle + * function with the credits allocated for the new + * inode. + */ res = ext4_xattr_set_handle(handle, inode, EXT4_XATTR_INDEX_ENCRYPTION, EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, - ctx, len, 0); + ctx, len, XATTR_CREATE); if (!res) { ext4_set_inode_flag(inode, EXT4_INODE_ENCRYPT); ext4_clear_inode_state(inode, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 293f698b7042..7617e2d454ea 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1570,6 +1570,7 @@ struct ext4_sb_info { struct proc_dir_entry *s_proc; struct kobject s_kobj; struct completion s_kobj_unregister; + struct mutex s_error_notify_mutex; /* protects sysfs_notify vs kobject_del */ struct super_block *s_sb; struct buffer_head *s_mmp_bh; @@ -3944,6 +3945,11 @@ static inline bool ext4_inode_can_atomic_write(struct inode *inode) extern int ext4_block_write_begin(handle_t *handle, struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block); + +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +#define EXPORT_SYMBOL_FOR_EXT4_TEST(sym) \ + EXPORT_SYMBOL_FOR_MODULES(sym, "ext4-test") +#endif #endif /* __KERNEL__ */ #endif /* _EXT4_H */ diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h index c484125d963f..ebaf7cc42430 100644 --- a/fs/ext4/ext4_extents.h +++ b/fs/ext4/ext4_extents.h @@ -264,5 +264,17 @@ static inline void ext4_idx_store_pblock(struct ext4_extent_idx *ix, 0xffff); } +extern int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path); +extern int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex); +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +extern int ext4_ext_space_root_idx_test(struct inode *inode, int check); +extern struct ext4_ext_path *ext4_split_convert_extents_test( + handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map, + struct ext4_ext_path *path, + int flags, unsigned int *allocated); +#endif #endif /* _EXT4_EXTENTS */ diff --git a/fs/ext4/extents-test.c b/fs/ext4/extents-test.c index 7c4690eb7dad..5496b2c8e2cd 100644 --- a/fs/ext4/extents-test.c +++ b/fs/ext4/extents-test.c @@ -142,8 +142,10 @@ static struct file_system_type ext_fs_type = { static void extents_kunit_exit(struct kunit *test) { - struct ext4_sb_info *sbi = k_ctx.k_ei->vfs_inode.i_sb->s_fs_info; + struct super_block *sb = k_ctx.k_ei->vfs_inode.i_sb; + struct ext4_sb_info *sbi = sb->s_fs_info; + ext4_es_unregister_shrinker(sbi); kfree(sbi); kfree(k_ctx.k_ei); kfree(k_ctx.k_data); @@ -280,8 +282,8 @@ static int extents_kunit_init(struct kunit *test) eh->eh_depth = 0; eh->eh_entries = cpu_to_le16(1); eh->eh_magic = EXT4_EXT_MAGIC; - eh->eh_max = - cpu_to_le16(ext4_ext_space_root_idx(&k_ctx.k_ei->vfs_inode, 0)); + eh->eh_max = cpu_to_le16(ext4_ext_space_root_idx_test( + &k_ctx.k_ei->vfs_inode, 0)); eh->eh_generation = 0; /* @@ -384,8 +386,8 @@ static void test_split_convert(struct kunit *test) switch (param->type) { case TEST_SPLIT_CONVERT: - path = ext4_split_convert_extents(NULL, inode, &map, path, - param->split_flags, NULL); + path = ext4_split_convert_extents_test(NULL, inode, &map, + path, param->split_flags, NULL); break; case TEST_CREATE_BLOCKS: ext4_map_create_blocks_helper(test, inode, &map, param->split_flags); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index ae3804f36535..8cce1479be6d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -184,9 +184,9 @@ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, * - ENOMEM * - EIO */ -static int __ext4_ext_dirty(const char *where, unsigned int line, - handle_t *handle, struct inode *inode, - struct ext4_ext_path *path) +int __ext4_ext_dirty(const char *where, unsigned int line, + handle_t *handle, struct inode *inode, + struct ext4_ext_path *path) { int err; @@ -1736,6 +1736,13 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; + if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { + EXT4_ERROR_INODE(inode, + "path[%d].p_idx %p > EXT_LAST_INDEX %p", + k, path[k].p_idx, + EXT_LAST_INDEX(path[k].p_hdr)); + return -EFSCORRUPTED; + } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) @@ -1748,6 +1755,14 @@ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; + if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { + EXT4_ERROR_INODE(inode, + "path[%d].p_idx %p > EXT_LAST_INDEX %p", + k, path[k].p_idx, + EXT_LAST_INDEX(path[k].p_hdr)); + err = -EFSCORRUPTED; + goto clean; + } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) @@ -3144,7 +3159,7 @@ static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) } /* FIXME!! we need to try to merge to left or right after zero-out */ -static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) +int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; @@ -3239,6 +3254,9 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, insert_err = PTR_ERR(path); err = 0; + if (insert_err != -ENOSPC && insert_err != -EDQUOT && + insert_err != -ENOMEM) + goto out_path; /* * Get a new path to try to zeroout or fix the extent length. @@ -3255,13 +3273,20 @@ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, goto out_path; } + depth = ext_depth(inode); + ex = path[depth].p_ext; + if (!ex) { + EXT4_ERROR_INODE(inode, + "bad extent address lblock: %lu, depth: %d pblock %llu", + (unsigned long)ee_block, depth, path[depth].p_block); + err = -EFSCORRUPTED; + goto out; + } + err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; - depth = ext_depth(inode); - ex = path[depth].p_ext; - fix_extent_len: ex->ee_len = orig_ex.ee_len; err = ext4_ext_dirty(handle, inode, path + path->p_depth); @@ -3363,7 +3388,7 @@ static int ext4_split_extent_zeroout(handle_t *handle, struct inode *inode, ext4_ext_mark_initialized(ex); - ext4_ext_dirty(handle, inode, path + depth); + err = ext4_ext_dirty(handle, inode, path + depth); if (err) return err; @@ -4457,9 +4482,13 @@ got_allocated_blocks: path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (IS_ERR(path)) { err = PTR_ERR(path); - if (allocated_clusters) { + /* + * Gracefully handle out of space conditions. If the filesystem + * is inconsistent, we'll just leak allocated blocks to avoid + * causing even more damage. + */ + if (allocated_clusters && (err == -EDQUOT || err == -ENOSPC)) { int fb_flags = 0; - /* * free data blocks we just allocated. * not a good idea to call discard here directly, @@ -6238,6 +6267,33 @@ out: return 0; } -#ifdef CONFIG_EXT4_KUNIT_TESTS -#include "extents-test.c" +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +int ext4_ext_space_root_idx_test(struct inode *inode, int check) +{ + return ext4_ext_space_root_idx(inode, check); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_space_root_idx_test); + +struct ext4_ext_path *ext4_split_convert_extents_test(handle_t *handle, + struct inode *inode, struct ext4_map_blocks *map, + struct ext4_ext_path *path, int flags, + unsigned int *allocated) +{ + return ext4_split_convert_extents(handle, inode, map, path, + flags, allocated); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_split_convert_extents_test); + +EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_insert_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_insert_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_find_extent); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_issue_zeroout); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_query_blocks); #endif diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index f575751f1cae..2f0057e04934 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -975,13 +975,13 @@ static int ext4_fc_flush_data(journal_t *journal) int ret = 0; list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_submit_inode_data(journal, ei->jinode); + ret = jbd2_submit_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_wait_inode_data(journal, ei->jinode); + ret = jbd2_wait_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } @@ -1613,19 +1613,21 @@ static int ext4_fc_replay_inode(struct super_block *sb, /* Immediately update the inode on disk. */ ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); if (ret) - goto out; + goto out_brelse; ret = sync_dirty_buffer(iloc.bh); if (ret) - goto out; + goto out_brelse; ret = ext4_mark_inode_used(sb, ino); if (ret) - goto out; + goto out_brelse; /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); - return -EFSCORRUPTED; + inode = NULL; + ret = -EFSCORRUPTED; + goto out_brelse; } /* @@ -1642,13 +1644,14 @@ static int ext4_fc_replay_inode(struct super_block *sb, ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode)); ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); sync_dirty_buffer(iloc.bh); +out_brelse: brelse(iloc.bh); out: iput(inode); if (!ret) blkdev_issue_flush(sb->s_bdev); - return 0; + return ret; } /* diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index e476c6de3074..bd8f230fa507 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -83,11 +83,23 @@ static int ext4_fsync_nojournal(struct file *file, loff_t start, loff_t end, int datasync, bool *needs_barrier) { struct inode *inode = file->f_inode; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + }; int ret; ret = generic_buffers_fsync_noflush(file, start, end, datasync); - if (!ret) - ret = ext4_sync_parent(inode); + if (ret) + return ret; + + /* Force writeout of inode table buffer to disk */ + ret = ext4_write_inode(inode, &wbc); + if (ret) + return ret; + + ret = ext4_sync_parent(inode); + if (test_opt(inode->i_sb, BARRIER)) *needs_barrier = true; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b20a1bf866ab..b1bc1950c9f0 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -686,6 +686,12 @@ static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino) if (unlikely(!gdp)) return 0; + /* Inode was never used in this filesystem? */ + if (ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT) || + ino >= EXT4_INODES_PER_GROUP(sb) - ext4_itable_unused_count(sb, gdp))) + return 0; + bh = sb_find_get_block(sb, ext4_inode_table(sb, gdp) + (ino / inodes_per_block)); if (!bh || !buffer_uptodate(bh)) diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 1f6bc05593df..408677fa8196 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -522,7 +522,15 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio) goto out; len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode)); - BUG_ON(len > PAGE_SIZE); + + if (len > PAGE_SIZE) { + ext4_error_inode(inode, __func__, __LINE__, 0, + "inline size %zu exceeds PAGE_SIZE", len); + ret = -EFSCORRUPTED; + brelse(iloc.bh); + goto out; + } + kaddr = kmap_local_folio(folio, 0); ret = ext4_read_inline_data(inode, kaddr, len, &iloc); kaddr = folio_zero_tail(folio, len, kaddr + len); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 396dc3a5d16b..1123d995494b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -128,6 +128,8 @@ void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { + struct jbd2_inode *jinode = READ_ONCE(EXT4_I(inode)->jinode); + trace_ext4_begin_ordered_truncate(inode, new_size); /* * If jinode is zero, then we never opened the file for @@ -135,10 +137,10 @@ static inline int ext4_begin_ordered_truncate(struct inode *inode, * jbd2_journal_begin_ordered_truncate() since there's no * outstanding writes we need to flush. */ - if (!EXT4_I(inode)->jinode) + if (!jinode) return 0; return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode), - EXT4_I(inode)->jinode, + jinode, new_size); } @@ -184,6 +186,14 @@ void ext4_evict_inode(struct inode *inode) if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) ext4_evict_ea_inode(inode); if (inode->i_nlink) { + /* + * If there's dirty page will lead to data loss, user + * could see stale data. + */ + if (unlikely(!ext4_emergency_state(inode->i_sb) && + mapping_tagged(&inode->i_data, PAGECACHE_TAG_DIRTY))) + ext4_warning_inode(inode, "data will be lost"); + truncate_inode_pages_final(&inode->i_data); goto no_delete; @@ -4451,8 +4461,13 @@ int ext4_inode_attach_jinode(struct inode *inode) spin_unlock(&inode->i_lock); return -ENOMEM; } - ei->jinode = jinode; - jbd2_journal_init_jbd_inode(ei->jinode, inode); + jbd2_journal_init_jbd_inode(jinode, inode); + /* + * Publish ->jinode only after it is fully initialized so that + * readers never observe a partially initialized jbd2_inode. + */ + smp_wmb(); + WRITE_ONCE(ei->jinode, jinode); jinode = NULL; } spin_unlock(&inode->i_lock); @@ -5401,18 +5416,36 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, inode->i_op = &ext4_encrypted_symlink_inode_operations; } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; - if (inode->i_size == 0 || - inode->i_size >= sizeof(ei->i_data) || - strnlen((char *)ei->i_data, inode->i_size + 1) != - inode->i_size) { - ext4_error_inode(inode, function, line, 0, - "invalid fast symlink length %llu", - (unsigned long long)inode->i_size); - ret = -EFSCORRUPTED; - goto bad_inode; + + /* + * Orphan cleanup can see inodes with i_size == 0 + * and i_data uninitialized. Skip size checks in + * that case. This is safe because the first thing + * ext4_evict_inode() does for fast symlinks is + * clearing of i_data and i_size. + */ + if ((EXT4_SB(sb)->s_mount_state & EXT4_ORPHAN_FS)) { + if (inode->i_nlink != 0) { + ext4_error_inode(inode, function, line, 0, + "invalid orphan symlink nlink %d", + inode->i_nlink); + ret = -EFSCORRUPTED; + goto bad_inode; + } + } else { + if (inode->i_size == 0 || + inode->i_size >= sizeof(ei->i_data) || + strnlen((char *)ei->i_data, inode->i_size + 1) != + inode->i_size) { + ext4_error_inode(inode, function, line, 0, + "invalid fast symlink length %llu", + (unsigned long long)inode->i_size); + ret = -EFSCORRUPTED; + goto bad_inode; + } + inode_set_cached_link(inode, (char *)ei->i_data, + inode->i_size); } - inode_set_cached_link(inode, (char *)ei->i_data, - inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; } @@ -5849,6 +5882,18 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_size == inode->i_size) inc_ivers = false; + /* + * If file has inline data but new size exceeds inline capacity, + * convert to extent-based storage first to prevent inconsistent + * state (inline flag set but size exceeds inline capacity). + */ + if (ext4_has_inline_data(inode) && + attr->ia_size > EXT4_I(inode)->i_inline_size) { + error = ext4_convert_inline_data(inode); + if (error) + goto err_out; + } + if (shrink) { if (ext4_should_order_data(inode)) { error = ext4_begin_ordered_truncate(inode, diff --git a/fs/ext4/mballoc-test.c b/fs/ext4/mballoc-test.c index 9fbdf6a09489..6f5bfbb0e8a4 100644 --- a/fs/ext4/mballoc-test.c +++ b/fs/ext4/mballoc-test.c @@ -8,6 +8,7 @@ #include <linux/random.h> #include "ext4.h" +#include "mballoc.h" struct mbt_grp_ctx { struct buffer_head bitmap_bh; @@ -336,7 +337,7 @@ ext4_mb_mark_context_stub(handle_t *handle, struct super_block *sb, bool state, if (state) mb_set_bits(bitmap_bh->b_data, blkoff, len); else - mb_clear_bits(bitmap_bh->b_data, blkoff, len); + mb_clear_bits_test(bitmap_bh->b_data, blkoff, len); return 0; } @@ -413,14 +414,14 @@ static void test_new_blocks_simple(struct kunit *test) /* get block at goal */ ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ar.goal, found, "failed to alloc block at goal, expected %llu found %llu", ar.goal, found); /* get block after goal in goal group */ ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ar.goal + EXT4_C2B(sbi, 1), found, "failed to alloc block after goal in goal group, expected %llu found %llu", ar.goal + 1, found); @@ -428,7 +429,7 @@ static void test_new_blocks_simple(struct kunit *test) /* get block after goal group */ mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ext4_group_first_block_no(sb, goal_group + 1), found, "failed to alloc block after goal group, expected %llu found %llu", @@ -438,7 +439,7 @@ static void test_new_blocks_simple(struct kunit *test) for (i = goal_group; i < ext4_get_groups_count(sb); i++) mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_EQ_MSG(test, ext4_group_first_block_no(sb, 0) + EXT4_C2B(sbi, 1), found, "failed to alloc block before goal group, expected %llu found %llu", @@ -448,7 +449,7 @@ static void test_new_blocks_simple(struct kunit *test) for (i = 0; i < ext4_get_groups_count(sb); i++) mbt_ctx_mark_used(sb, i, 0, EXT4_CLUSTERS_PER_GROUP(sb)); ar.goal = ext4_group_first_block_no(sb, goal_group); - found = ext4_mb_new_blocks_simple(&ar, &err); + found = ext4_mb_new_blocks_simple_test(&ar, &err); KUNIT_ASSERT_NE_MSG(test, err, 0, "unexpectedly get block when no block is available"); } @@ -492,16 +493,16 @@ validate_free_blocks_simple(struct kunit *test, struct super_block *sb, continue; bitmap = mbt_ctx_bitmap(sb, i); - bit = mb_find_next_zero_bit(bitmap, max, 0); + bit = mb_find_next_zero_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ_MSG(test, bit, max, "free block on unexpected group %d", i); } bitmap = mbt_ctx_bitmap(sb, goal_group); - bit = mb_find_next_zero_bit(bitmap, max, 0); + bit = mb_find_next_zero_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ(test, bit, start); - bit = mb_find_next_bit(bitmap, max, bit + 1); + bit = mb_find_next_bit_test(bitmap, max, bit + 1); KUNIT_ASSERT_EQ(test, bit, start + len); } @@ -524,7 +525,7 @@ test_free_blocks_simple_range(struct kunit *test, ext4_group_t goal_group, block = ext4_group_first_block_no(sb, goal_group) + EXT4_C2B(sbi, start); - ext4_free_blocks_simple(inode, block, len); + ext4_free_blocks_simple_test(inode, block, len); validate_free_blocks_simple(test, sb, goal_group, start, len); mbt_ctx_mark_used(sb, goal_group, 0, EXT4_CLUSTERS_PER_GROUP(sb)); } @@ -566,15 +567,15 @@ test_mark_diskspace_used_range(struct kunit *test, bitmap = mbt_ctx_bitmap(sb, TEST_GOAL_GROUP); memset(bitmap, 0, sb->s_blocksize); - ret = ext4_mb_mark_diskspace_used(ac, NULL); + ret = ext4_mb_mark_diskspace_used_test(ac, NULL); KUNIT_ASSERT_EQ(test, ret, 0); max = EXT4_CLUSTERS_PER_GROUP(sb); - i = mb_find_next_bit(bitmap, max, 0); + i = mb_find_next_bit_test(bitmap, max, 0); KUNIT_ASSERT_EQ(test, i, start); - i = mb_find_next_zero_bit(bitmap, max, i + 1); + i = mb_find_next_zero_bit_test(bitmap, max, i + 1); KUNIT_ASSERT_EQ(test, i, start + len); - i = mb_find_next_bit(bitmap, max, i + 1); + i = mb_find_next_bit_test(bitmap, max, i + 1); KUNIT_ASSERT_EQ(test, max, i); } @@ -617,54 +618,54 @@ static void mbt_generate_buddy(struct super_block *sb, void *buddy, max = EXT4_CLUSTERS_PER_GROUP(sb); bb_h = buddy + sbi->s_mb_offsets[1]; - off = mb_find_next_zero_bit(bb, max, 0); + off = mb_find_next_zero_bit_test(bb, max, 0); grp->bb_first_free = off; while (off < max) { grp->bb_counters[0]++; grp->bb_free++; - if (!(off & 1) && !mb_test_bit(off + 1, bb)) { + if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) { grp->bb_free++; grp->bb_counters[0]--; - mb_clear_bit(off >> 1, bb_h); + mb_clear_bit_test(off >> 1, bb_h); grp->bb_counters[1]++; grp->bb_largest_free_order = 1; off++; } - off = mb_find_next_zero_bit(bb, max, off + 1); + off = mb_find_next_zero_bit_test(bb, max, off + 1); } for (order = 1; order < MB_NUM_ORDERS(sb) - 1; order++) { bb = buddy + sbi->s_mb_offsets[order]; bb_h = buddy + sbi->s_mb_offsets[order + 1]; max = max >> 1; - off = mb_find_next_zero_bit(bb, max, 0); + off = mb_find_next_zero_bit_test(bb, max, 0); while (off < max) { - if (!(off & 1) && !mb_test_bit(off + 1, bb)) { + if (!(off & 1) && !mb_test_bit_test(off + 1, bb)) { mb_set_bits(bb, off, 2); grp->bb_counters[order] -= 2; - mb_clear_bit(off >> 1, bb_h); + mb_clear_bit_test(off >> 1, bb_h); grp->bb_counters[order + 1]++; grp->bb_largest_free_order = order + 1; off++; } - off = mb_find_next_zero_bit(bb, max, off + 1); + off = mb_find_next_zero_bit_test(bb, max, off + 1); } } max = EXT4_CLUSTERS_PER_GROUP(sb); - off = mb_find_next_zero_bit(bitmap, max, 0); + off = mb_find_next_zero_bit_test(bitmap, max, 0); while (off < max) { grp->bb_fragments++; - off = mb_find_next_bit(bitmap, max, off + 1); + off = mb_find_next_bit_test(bitmap, max, off + 1); if (off + 1 >= max) break; - off = mb_find_next_zero_bit(bitmap, max, off + 1); + off = mb_find_next_zero_bit_test(bitmap, max, off + 1); } } @@ -706,7 +707,7 @@ do_test_generate_buddy(struct kunit *test, struct super_block *sb, void *bitmap, /* needed by validation in ext4_mb_generate_buddy */ ext4_grp->bb_free = mbt_grp->bb_free; memset(ext4_buddy, 0xff, sb->s_blocksize); - ext4_mb_generate_buddy(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP, + ext4_mb_generate_buddy_test(sb, ext4_buddy, bitmap, TEST_GOAL_GROUP, ext4_grp); KUNIT_ASSERT_EQ(test, memcmp(mbt_buddy, ext4_buddy, sb->s_blocksize), @@ -760,7 +761,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b, ex.fe_group = TEST_GOAL_GROUP; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(e4b, &ex); + mb_mark_used_test(e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); mb_set_bits(bitmap, start, len); @@ -769,7 +770,7 @@ test_mb_mark_used_range(struct kunit *test, struct ext4_buddy *e4b, memset(buddy, 0xff, sb->s_blocksize); for (i = 0; i < MB_NUM_ORDERS(sb); i++) grp->bb_counters[i] = 0; - ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp); + ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp); KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize), 0); @@ -798,7 +799,7 @@ static void test_mb_mark_used(struct kunit *test) bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); grp->bb_free = EXT4_CLUSTERS_PER_GROUP(sb); @@ -809,7 +810,7 @@ static void test_mb_mark_used(struct kunit *test) test_mb_mark_used_range(test, &e4b, ranges[i].start, ranges[i].len, bitmap, buddy, grp); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } static void @@ -825,16 +826,16 @@ test_mb_free_blocks_range(struct kunit *test, struct ext4_buddy *e4b, return; ext4_lock_group(sb, e4b->bd_group); - mb_free_blocks(NULL, e4b, start, len); + mb_free_blocks_test(NULL, e4b, start, len); ext4_unlock_group(sb, e4b->bd_group); - mb_clear_bits(bitmap, start, len); + mb_clear_bits_test(bitmap, start, len); /* bypass bb_free validatoin in ext4_mb_generate_buddy */ grp->bb_free += len; memset(buddy, 0xff, sb->s_blocksize); for (i = 0; i < MB_NUM_ORDERS(sb); i++) grp->bb_counters[i] = 0; - ext4_mb_generate_buddy(sb, buddy, bitmap, 0, grp); + ext4_mb_generate_buddy_test(sb, buddy, bitmap, 0, grp); KUNIT_ASSERT_EQ(test, memcmp(buddy, e4b->bd_buddy, sb->s_blocksize), 0); @@ -865,7 +866,7 @@ static void test_mb_free_blocks(struct kunit *test) bb_counters[MB_NUM_ORDERS(sb)]), GFP_KERNEL); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, grp); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); ex.fe_start = 0; @@ -873,7 +874,7 @@ static void test_mb_free_blocks(struct kunit *test) ex.fe_group = TEST_GOAL_GROUP; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(&e4b, &ex); + mb_mark_used_test(&e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); grp->bb_free = 0; @@ -886,7 +887,7 @@ static void test_mb_free_blocks(struct kunit *test) test_mb_free_blocks_range(test, &e4b, ranges[i].start, ranges[i].len, bitmap, buddy, grp); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } #define COUNT_FOR_ESTIMATE 100000 @@ -904,7 +905,7 @@ static void test_mb_mark_used_cost(struct kunit *test) if (sb->s_blocksize > PAGE_SIZE) kunit_skip(test, "blocksize exceeds pagesize"); - ret = ext4_mb_load_buddy(sb, TEST_GOAL_GROUP, &e4b); + ret = ext4_mb_load_buddy_test(sb, TEST_GOAL_GROUP, &e4b); KUNIT_ASSERT_EQ(test, ret, 0); ex.fe_group = TEST_GOAL_GROUP; @@ -918,7 +919,7 @@ static void test_mb_mark_used_cost(struct kunit *test) ex.fe_start = ranges[i].start; ex.fe_len = ranges[i].len; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_mark_used(&e4b, &ex); + mb_mark_used_test(&e4b, &ex); ext4_unlock_group(sb, TEST_GOAL_GROUP); } end = jiffies; @@ -929,14 +930,14 @@ static void test_mb_mark_used_cost(struct kunit *test) continue; ext4_lock_group(sb, TEST_GOAL_GROUP); - mb_free_blocks(NULL, &e4b, ranges[i].start, + mb_free_blocks_test(NULL, &e4b, ranges[i].start, ranges[i].len); ext4_unlock_group(sb, TEST_GOAL_GROUP); } } kunit_info(test, "costed jiffies %lu\n", all); - ext4_mb_unload_buddy(&e4b); + ext4_mb_unload_buddy_test(&e4b); } static const struct mbt_ext4_block_layout mbt_test_layouts[] = { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 20e9fdaf4301..bb58eafb87bc 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1199,6 +1199,8 @@ static int ext4_mb_scan_groups(struct ext4_allocation_context *ac) /* searching for the right group start from the goal value specified */ start = ac->ac_g_ex.fe_group; + if (start >= ngroups) + start = 0; ac->ac_prefetch_grp = start; ac->ac_prefetch_nr = 0; @@ -2443,8 +2445,12 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, return 0; err = ext4_mb_load_buddy(ac->ac_sb, group, e4b); - if (err) + if (err) { + if (EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info) && + !(ac->ac_flags & EXT4_MB_HINT_GOAL_ONLY)) + return 0; return err; + } ext4_lock_group(ac->ac_sb, group); if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) @@ -3580,9 +3586,7 @@ err_freebuddy: rcu_read_unlock(); iput(sbi->s_buddy_cache); err_freesgi: - rcu_read_lock(); - kvfree(rcu_dereference(sbi->s_group_info)); - rcu_read_unlock(); + kvfree(rcu_access_pointer(sbi->s_group_info)); return -ENOMEM; } @@ -3889,15 +3893,14 @@ void ext4_mb_release(struct super_block *sb) struct kmem_cache *cachep = get_groupinfo_cache(sb->s_blocksize_bits); int count; - if (test_opt(sb, DISCARD)) { - /* - * wait the discard work to drain all of ext4_free_data - */ - flush_work(&sbi->s_discard_work); - WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); - } + /* + * wait the discard work to drain all of ext4_free_data + */ + flush_work(&sbi->s_discard_work); + WARN_ON_ONCE(!list_empty(&sbi->s_discard_list)); - if (sbi->s_group_info) { + group_info = rcu_access_pointer(sbi->s_group_info); + if (group_info) { for (i = 0; i < ngroups; i++) { cond_resched(); grinfo = ext4_get_group_info(sb, i); @@ -3915,12 +3918,9 @@ void ext4_mb_release(struct super_block *sb) num_meta_group_infos = (ngroups + EXT4_DESC_PER_BLOCK(sb) - 1) >> EXT4_DESC_PER_BLOCK_BITS(sb); - rcu_read_lock(); - group_info = rcu_dereference(sbi->s_group_info); for (i = 0; i < num_meta_group_infos; i++) kfree(group_info[i]); kvfree(group_info); - rcu_read_unlock(); } ext4_mb_avg_fragment_size_destroy(sbi); ext4_mb_largest_free_orders_destroy(sbi); @@ -4084,7 +4084,7 @@ void ext4_exit_mballoc(void) #define EXT4_MB_BITMAP_MARKED_CHECK 0x0001 #define EXT4_MB_SYNC_UPDATE 0x0002 -static int +int ext4_mb_mark_context(handle_t *handle, struct super_block *sb, bool state, ext4_group_t group, ext4_grpblk_t blkoff, ext4_grpblk_t len, int flags, ext4_grpblk_t *ret_changed) @@ -7188,6 +7188,102 @@ out_unload: return error; } -#ifdef CONFIG_EXT4_KUNIT_TESTS -#include "mballoc-test.c" +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +void mb_clear_bits_test(void *bm, int cur, int len) +{ + mb_clear_bits(bm, cur, len); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bits_test); + +ext4_fsblk_t +ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar, + int *errp) +{ + return ext4_mb_new_blocks_simple(ar, errp); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_new_blocks_simple_test); + +int mb_find_next_zero_bit_test(void *addr, int max, int start) +{ + return mb_find_next_zero_bit(addr, max, start); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_zero_bit_test); + +int mb_find_next_bit_test(void *addr, int max, int start) +{ + return mb_find_next_bit(addr, max, start); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_find_next_bit_test); + +void mb_clear_bit_test(int bit, void *addr) +{ + mb_clear_bit(bit, addr); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_clear_bit_test); + +int mb_test_bit_test(int bit, void *addr) +{ + return mb_test_bit(bit, addr); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_test_bit_test); + +int ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac, + handle_t *handle) +{ + return ext4_mb_mark_diskspace_used(ac, handle); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_diskspace_used_test); + +int mb_mark_used_test(struct ext4_buddy *e4b, struct ext4_free_extent *ex) +{ + return mb_mark_used(e4b, ex); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_mark_used_test); + +void ext4_mb_generate_buddy_test(struct super_block *sb, void *buddy, + void *bitmap, ext4_group_t group, + struct ext4_group_info *grp) +{ + ext4_mb_generate_buddy(sb, buddy, bitmap, group, grp); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_generate_buddy_test); + +int ext4_mb_load_buddy_test(struct super_block *sb, ext4_group_t group, + struct ext4_buddy *e4b) +{ + return ext4_mb_load_buddy(sb, group, e4b); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_load_buddy_test); + +void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b) +{ + ext4_mb_unload_buddy(e4b); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_unload_buddy_test); + +void mb_free_blocks_test(struct inode *inode, struct ext4_buddy *e4b, + int first, int count) +{ + mb_free_blocks(inode, e4b, first, count); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_free_blocks_test); + +void ext4_free_blocks_simple_test(struct inode *inode, ext4_fsblk_t block, + unsigned long count) +{ + return ext4_free_blocks_simple(inode, block, count); +} +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_blocks_simple_test); + +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_wait_block_bitmap); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_init); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_desc); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_count_free_clusters); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_get_group_info); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_free_group_clusters_set); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_release); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_read_block_bitmap_nowait); +EXPORT_SYMBOL_FOR_EXT4_TEST(mb_set_bits); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_fc_init_inode); +EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_mb_mark_context); #endif diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 15a049f05d04..39333ce72cbd 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -270,4 +270,34 @@ ext4_mballoc_query_range( ext4_mballoc_query_range_fn formatter, void *priv); +extern int ext4_mb_mark_context(handle_t *handle, + struct super_block *sb, bool state, + ext4_group_t group, ext4_grpblk_t blkoff, + ext4_grpblk_t len, int flags, + ext4_grpblk_t *ret_changed); +#if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) +extern void mb_clear_bits_test(void *bm, int cur, int len); +extern ext4_fsblk_t +ext4_mb_new_blocks_simple_test(struct ext4_allocation_request *ar, + int *errp); +extern int mb_find_next_zero_bit_test(void *addr, int max, int start); +extern int mb_find_next_bit_test(void *addr, int max, int start); +extern void mb_clear_bit_test(int bit, void *addr); +extern int mb_test_bit_test(int bit, void *addr); +extern int +ext4_mb_mark_diskspace_used_test(struct ext4_allocation_context *ac, + handle_t *handle); +extern int mb_mark_used_test(struct ext4_buddy *e4b, + struct ext4_free_extent *ex); +extern void ext4_mb_generate_buddy_test(struct super_block *sb, + void *buddy, void *bitmap, ext4_group_t group, + struct ext4_group_info *grp); +extern int ext4_mb_load_buddy_test(struct super_block *sb, + ext4_group_t group, struct ext4_buddy *e4b); +extern void ext4_mb_unload_buddy_test(struct ext4_buddy *e4b); +extern void mb_free_blocks_test(struct inode *inode, + struct ext4_buddy *e4b, int first, int count); +extern void ext4_free_blocks_simple_test(struct inode *inode, + ext4_fsblk_t block, unsigned long count); +#endif #endif diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index a8c95eee91b7..39fe50b3c662 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -524,9 +524,15 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio, nr_to_submit++; } while ((bh = bh->b_this_page) != head); - /* Nothing to submit? Just unlock the folio... */ - if (!nr_to_submit) + if (!nr_to_submit) { + /* + * We have nothing to submit. Just cycle the folio through + * writeback state to properly update xarray tags. + */ + __folio_start_writeback(folio, keep_towrite); + folio_end_writeback(folio); return 0; + } bh = head = folio_buffers(folio); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 43f680c750ae..a34efb44e73d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1254,12 +1254,10 @@ static void ext4_group_desc_free(struct ext4_sb_info *sbi) struct buffer_head **group_desc; int i; - rcu_read_lock(); - group_desc = rcu_dereference(sbi->s_group_desc); + group_desc = rcu_access_pointer(sbi->s_group_desc); for (i = 0; i < sbi->s_gdb_count; i++) brelse(group_desc[i]); kvfree(group_desc); - rcu_read_unlock(); } static void ext4_flex_groups_free(struct ext4_sb_info *sbi) @@ -1267,14 +1265,12 @@ static void ext4_flex_groups_free(struct ext4_sb_info *sbi) struct flex_groups **flex_groups; int i; - rcu_read_lock(); - flex_groups = rcu_dereference(sbi->s_flex_groups); + flex_groups = rcu_access_pointer(sbi->s_flex_groups); if (flex_groups) { for (i = 0; i < sbi->s_flex_groups_allocated; i++) kvfree(flex_groups[i]); kvfree(flex_groups); } - rcu_read_unlock(); } static void ext4_put_super(struct super_block *sb) @@ -1527,6 +1523,27 @@ void ext4_clear_inode(struct inode *inode) invalidate_inode_buffers(inode); clear_inode(inode); ext4_discard_preallocations(inode); + /* + * We must remove the inode from the hash before ext4_free_inode() + * clears the bit in inode bitmap as otherwise another process reusing + * the inode will block in insert_inode_hash() waiting for inode + * eviction to complete while holding transaction handle open, but + * ext4_evict_inode() still running for that inode could block waiting + * for transaction commit if the inode is marked as IS_SYNC => deadlock. + * + * Removing the inode from the hash here is safe. There are two cases + * to consider: + * 1) The inode still has references to it (i_nlink > 0). In that case + * we are keeping the inode and once we remove the inode from the hash, + * iget() can create the new inode structure for the same inode number + * and we are fine with that as all IO on behalf of the inode is + * finished. + * 2) We are deleting the inode (i_nlink == 0). In that case inode + * number cannot be reused until ext4_free_inode() clears the bit in + * the inode bitmap, at which point all IO is done and reuse is fine + * again. + */ + remove_inode_hash(inode); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -3633,6 +3650,13 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) "extents feature\n"); return 0; } + if (ext4_has_feature_bigalloc(sb) && + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { + ext4_msg(sb, KERN_WARNING, + "bad geometry: bigalloc file system with non-zero " + "first_data_block\n"); + return 0; + } #if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2) if (!readonly && (ext4_has_feature_quota(sb) || @@ -5403,6 +5427,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) timer_setup(&sbi->s_err_report, print_daily_error_info, 0); spin_lock_init(&sbi->s_error_lock); + mutex_init(&sbi->s_error_notify_mutex); INIT_WORK(&sbi->s_sb_upd_work, update_super_work); err = ext4_group_desc_init(sb, es, logical_sb_block, &first_not_zeroed); diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index b87d7bdab06a..923b375e017f 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -597,7 +597,10 @@ static const struct kobj_type ext4_feat_ktype = { void ext4_notify_error_sysfs(struct ext4_sb_info *sbi) { - sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); + mutex_lock(&sbi->s_error_notify_mutex); + if (sbi->s_kobj.state_in_sysfs) + sysfs_notify(&sbi->s_kobj, NULL, "errors_count"); + mutex_unlock(&sbi->s_error_notify_mutex); } static struct kobject *ext4_root; @@ -610,8 +613,10 @@ int ext4_register_sysfs(struct super_block *sb) int err; init_completion(&sbi->s_kobj_unregister); + mutex_lock(&sbi->s_error_notify_mutex); err = kobject_init_and_add(&sbi->s_kobj, &ext4_sb_ktype, ext4_root, "%s", sb->s_id); + mutex_unlock(&sbi->s_error_notify_mutex); if (err) { kobject_put(&sbi->s_kobj); wait_for_completion(&sbi->s_kobj_unregister); @@ -644,7 +649,10 @@ void ext4_unregister_sysfs(struct super_block *sb) if (sbi->s_proc) remove_proc_subtree(sb->s_id, ext4_proc_root); + + mutex_lock(&sbi->s_error_notify_mutex); kobject_del(&sbi->s_kobj); + mutex_unlock(&sbi->s_error_notify_mutex); } int __init ext4_init_sysfs(void) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 7c75ed7e8979..3c75ee025bda 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1711,6 +1711,19 @@ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, } } +static bool __sync_lazytime(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (!(inode_state_read(inode) & I_DIRTY_TIME)) { + spin_unlock(&inode->i_lock); + return false; + } + inode_state_clear(inode, I_DIRTY_TIME); + spin_unlock(&inode->i_lock); + inode->i_op->sync_lazytime(inode); + return true; +} + bool sync_lazytime(struct inode *inode) { if (!(inode_state_read_once(inode) & I_DIRTY_TIME)) @@ -1718,9 +1731,8 @@ bool sync_lazytime(struct inode *inode) trace_writeback_lazytime(inode); if (inode->i_op->sync_lazytime) - inode->i_op->sync_lazytime(inode); - else - mark_inode_dirty_sync(inode); + return __sync_lazytime(inode); + mark_inode_dirty_sync(inode); return true; } @@ -2775,13 +2787,8 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. - * - * If the mapping does not have data integrity semantics, - * there's no need to wait for the writeout to complete, as the - * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || - mapping_no_data_integrity(mapping)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); @@ -2916,6 +2923,17 @@ void sync_inodes_sb(struct super_block *sb) */ if (bdi == &noop_backing_dev_info) return; + + /* + * If the superblock has SB_I_NO_DATA_INTEGRITY set, there's no need to + * wait for the writeout to complete, as the filesystem cannot guarantee + * data persistence on sync. Just kick off writeback and return. + */ + if (sb->s_iflags & SB_I_NO_DATA_INTEGRITY) { + wakeup_flusher_threads_bdi(bdi, WB_REASON_SYNC); + return; + } + WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ diff --git a/fs/fuse/file.c b/fs/fuse/file.c index b1bb7153cb78..676fd9856bfb 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3201,10 +3201,8 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) { + if (fc->writeback_cache) mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); - mapping_set_no_data_integrity(&inode->i_data); - } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index e57b8af06be9..c795abe47a4f 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1709,6 +1709,7 @@ static void fuse_sb_defaults(struct super_block *sb) sb->s_export_op = &fuse_export_operations; sb->s_iflags |= SB_I_IMA_UNVERIFIABLE_SIGNATURE; sb->s_iflags |= SB_I_NOIDMAP; + sb->s_iflags |= SB_I_NO_DATA_INTEGRITY; if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c index fc045f2e4c45..edd908183058 100644 --- a/fs/iomap/bio.c +++ b/fs/iomap/bio.c @@ -8,7 +8,10 @@ #include "internal.h" #include "trace.h" -static void iomap_read_end_io(struct bio *bio) +static DEFINE_SPINLOCK(failed_read_lock); +static struct bio_list failed_read_list = BIO_EMPTY_LIST; + +static void __iomap_read_end_io(struct bio *bio) { int error = blk_status_to_errno(bio->bi_status); struct folio_iter fi; @@ -18,6 +21,52 @@ static void iomap_read_end_io(struct bio *bio) bio_put(bio); } +static void +iomap_fail_reads( + struct work_struct *work) +{ + struct bio *bio; + struct bio_list tmp = BIO_EMPTY_LIST; + unsigned long flags; + + spin_lock_irqsave(&failed_read_lock, flags); + bio_list_merge_init(&tmp, &failed_read_list); + spin_unlock_irqrestore(&failed_read_lock, flags); + + while ((bio = bio_list_pop(&tmp)) != NULL) { + __iomap_read_end_io(bio); + cond_resched(); + } +} + +static DECLARE_WORK(failed_read_work, iomap_fail_reads); + +static void iomap_fail_buffered_read(struct bio *bio) +{ + unsigned long flags; + + /* + * Bounce I/O errors to a workqueue to avoid nested i_lock acquisitions + * in the fserror code. The caller no longer owns the bio reference + * after the spinlock drops. + */ + spin_lock_irqsave(&failed_read_lock, flags); + if (bio_list_empty(&failed_read_list)) + WARN_ON_ONCE(!schedule_work(&failed_read_work)); + bio_list_add(&failed_read_list, bio); + spin_unlock_irqrestore(&failed_read_lock, flags); +} + +static void iomap_read_end_io(struct bio *bio) +{ + if (bio->bi_status) { + iomap_fail_buffered_read(bio); + return; + } + + __iomap_read_end_io(bio); +} + static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx) { struct bio *bio = ctx->read_ctx; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 00f0efaf12b2..92a831cf4bf1 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -514,6 +514,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, loff_t length = iomap_length(iter); struct folio *folio = ctx->cur_folio; size_t folio_len = folio_size(folio); + struct iomap_folio_state *ifs; size_t poff, plen; loff_t pos_diff; int ret; @@ -525,7 +526,7 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, return iomap_iter_advance(iter, length); } - ifs_alloc(iter->inode, folio, iter->flags); + ifs = ifs_alloc(iter->inode, folio, iter->flags); length = min_t(loff_t, length, folio_len - offset_in_folio(folio, pos)); while (length) { @@ -560,11 +561,15 @@ static int iomap_read_folio_iter(struct iomap_iter *iter, *bytes_submitted += plen; /* - * If the entire folio has been read in by the IO - * helper, then the helper owns the folio and will end - * the read on it. + * Hand off folio ownership to the IO helper when: + * 1) The entire folio has been submitted for IO, or + * 2) There is no ifs attached to the folio + * + * Case (2) occurs when 1 << i_blkbits matches the folio + * size but the underlying filesystem or block device + * uses a smaller granularity for IO. */ - if (*bytes_submitted == folio_len) + if (*bytes_submitted == folio_len || !ifs) ctx->cur_folio = NULL; } diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index de89c5bef607..1508e2f54462 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -267,7 +267,15 @@ restart: */ BUFFER_TRACE(bh, "queue"); get_bh(bh); - J_ASSERT_BH(bh, !buffer_jwrite(bh)); + if (WARN_ON_ONCE(buffer_jwrite(bh))) { + put_bh(bh); /* drop the ref we just took */ + spin_unlock(&journal->j_list_lock); + /* Clean up any previously batched buffers */ + if (batch_count) + __flush_batch(journal, &batch_count); + jbd2_journal_abort(journal, -EFSCORRUPTED); + return -EFSCORRUPTED; + } journal->j_chkpt_bhs[batch_count++] = bh; transaction->t_chp_stats.cs_written++; transaction->t_checkpoint_list = jh->b_cpnext; @@ -325,7 +333,10 @@ int jbd2_cleanup_journal_tail(journal_t *journal) if (!jbd2_journal_get_log_tail(journal, &first_tid, &blocknr)) return 1; - J_ASSERT(blocknr != 0); + if (WARN_ON_ONCE(blocknr == 0)) { + jbd2_journal_abort(journal, -EFSCORRUPTED); + return -EFSCORRUPTED; + } /* * We need to make sure that any blocks that were recently written out diff --git a/fs/mpage.c b/fs/mpage.c index 7dae5afc2b9e..b3d9f231a04a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -646,17 +646,24 @@ out: } /** - * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them + * __mpage_writepages - walk the list of dirty pages of the given address space + * & writepage() all of them * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @get_block: the filesystem's block mapper function. + * @write_folio: handler to call for each folio before calling + * mpage_write_folio() * * This is a library function, which implements the writepages() - * address_space_operation. + * address_space_operation. It calls @write_folio handler for each folio. If + * the handler returns value > 0, it calls mpage_write_folio() to do the + * folio writeback. */ int -mpage_writepages(struct address_space *mapping, - struct writeback_control *wbc, get_block_t get_block) +__mpage_writepages(struct address_space *mapping, + struct writeback_control *wbc, get_block_t get_block, + int (*write_folio)(struct folio *folio, + struct writeback_control *wbc)) { struct mpage_data mpd = { .get_block = get_block, @@ -666,11 +673,22 @@ mpage_writepages(struct address_space *mapping, int error; blk_start_plug(&plug); - while ((folio = writeback_iter(mapping, wbc, folio, &error))) + while ((folio = writeback_iter(mapping, wbc, folio, &error))) { + if (write_folio) { + error = write_folio(folio, wbc); + /* + * == 0 means folio is handled, < 0 means error. In + * both cases hand back control to writeback_iter() + */ + if (error <= 0) + continue; + /* Let mpage_write_folio() handle the folio. */ + } error = mpage_write_folio(wbc, folio, &mpd); + } if (mpd.bio) mpage_bio_submit_write(mpd.bio); blk_finish_plug(&plug); return error; } -EXPORT_SYMBOL(mpage_writepages); +EXPORT_SYMBOL(__mpage_writepages); diff --git a/fs/namei.c b/fs/namei.c index 58f715f7657e..9e5500dad14f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -2437,8 +2437,14 @@ inside: EXPORT_SYMBOL(hashlen_string); /* - * Calculate the length and hash of the path component, and - * return the length as the result. + * hash_name - Calculate the length and hash of the path component + * @nd: the path resolution state + * @name: the pathname to read the component from + * @lastword: if the component fits in a single word, LAST_WORD_IS_DOT, + * LAST_WORD_IS_DOTDOT, or some other value depending on whether the + * component is '.', '..', or something else. Otherwise, @lastword is 0. + * + * Returns: a pointer to the terminating '/' or NUL character in @name. */ static inline const char *hash_name(struct nameidata *nd, const char *name, diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index 88a0d801525f..a8c0d86118c5 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -171,9 +171,8 @@ static void netfs_queue_read(struct netfs_io_request *rreq, spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index a498ee8d6674..f72e6da88cca 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -71,9 +71,8 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index dd1451bf7543..f9ab69de3e29 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -111,7 +111,6 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); subreq = stream->construct; stream->construct = NULL; - stream->front = NULL; } /* Check if (re-)preparation failed. */ @@ -186,10 +185,18 @@ static int netfs_unbuffered_write(struct netfs_io_request *wreq) stream->sreq_max_segs = INT_MAX; netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); - stream->prepare_write(subreq); - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_stat(&netfs_n_wh_retry_write_subreq); + if (stream->prepare_write) { + stream->prepare_write(subreq); + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); + } else { + struct iov_iter source; + + netfs_reset_iter(subreq); + source = subreq->io_iter; + netfs_reissue_write(stream, subreq, &source); + } } netfs_unbuffered_write_done(wreq); diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 72a435e5fc6d..154a14bb2d7f 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -143,6 +143,47 @@ static size_t netfs_limit_bvec(const struct iov_iter *iter, size_t start_offset, } /* + * Select the span of a kvec iterator we're going to use. Limit it by both + * maximum size and maximum number of segments. Returns the size of the span + * in bytes. + */ +static size_t netfs_limit_kvec(const struct iov_iter *iter, size_t start_offset, + size_t max_size, size_t max_segs) +{ + const struct kvec *kvecs = iter->kvec; + unsigned int nkv = iter->nr_segs, ix = 0, nsegs = 0; + size_t len, span = 0, n = iter->count; + size_t skip = iter->iov_offset + start_offset; + + if (WARN_ON(!iov_iter_is_kvec(iter)) || + WARN_ON(start_offset > n) || + n == 0) + return 0; + + while (n && ix < nkv && skip) { + len = kvecs[ix].iov_len; + if (skip < len) + break; + skip -= len; + n -= len; + ix++; + } + + while (n && ix < nkv) { + len = min3(n, kvecs[ix].iov_len - skip, max_size); + span += len; + nsegs++; + ix++; + if (span >= max_size || nsegs >= max_segs) + break; + skip = 0; + n -= len; + } + + return min(span, max_size); +} + +/* * Select the span of an xarray iterator we're going to use. Limit it by both * maximum size and maximum number of segments. It is assumed that segments * can be larger than a page in size, provided they're physically contiguous. @@ -245,6 +286,8 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, return netfs_limit_bvec(iter, start_offset, max_size, max_segs); if (iov_iter_is_xarray(iter)) return netfs_limit_xarray(iter, start_offset, max_size, max_segs); + if (iov_iter_is_kvec(iter)) + return netfs_limit_kvec(iter, start_offset, max_size, max_segs); BUG(); } EXPORT_SYMBOL(netfs_limit_iter); diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index 137f0e28a44c..e5f6665b3341 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -205,7 +205,8 @@ reassess: * in progress. The issuer thread may be adding stuff to the tail * whilst we're doing this. */ - front = READ_ONCE(stream->front); + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { size_t transferred; @@ -301,7 +302,6 @@ reassess: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&rreq->lock); netfs_put_subrequest(remove, notes & ABANDON_SREQ ? diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 7793ba5e3e8f..cca9ac43c077 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -93,8 +93,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) from->start, from->transferred, from->len); if (test_bit(NETFS_SREQ_FAILED, &from->flags) || - !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) + !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags)) { + subreq = from; goto abandon; + } list_for_each_continue(next, &stream->subrequests) { subreq = list_entry(next, struct netfs_io_subrequest, rreq_link); @@ -178,6 +180,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) if (subreq == to) break; } + subreq = NULL; continue; } diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index 8e6264f62a8f..d0e23bc42445 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -107,7 +107,6 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) spin_lock(&rreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); trace_netfs_sreq(subreq, netfs_sreq_trace_added); - stream->front = subreq; /* Store list pointers before active flag */ smp_store_release(&stream->active, true); spin_unlock(&rreq->lock); diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 83eb3dc1adf8..b194447f4b11 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -228,7 +228,8 @@ reassess_streams: if (!smp_load_acquire(&stream->active)) continue; - front = stream->front; + front = list_first_entry_or_null(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); while (front) { trace_netfs_collect_sreq(wreq, front); //_debug("sreq [%x] %llx %zx/%zx", @@ -279,7 +280,6 @@ reassess_streams: list_del_init(&front->rreq_link); front = list_first_entry_or_null(&stream->subrequests, struct netfs_io_subrequest, rreq_link); - stream->front = front; spin_unlock(&wreq->lock); netfs_put_subrequest(remove, notes & SAW_FAILURE ? diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 437268f65640..2db688f94125 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -206,9 +206,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, spin_lock(&wreq->lock); list_add_tail(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - stream->front = subreq; if (!stream->active) { - stream->collected_to = stream->front->start; + stream->collected_to = subreq->start; /* Write list pointers before active flag */ smp_store_release(&stream->active, true); } diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 758611ee4475..13cb60b52bd6 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -1146,15 +1146,15 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, return -EOVERFLOW; /* - * With metacopy disabled, we fsync after final metadata copyup, for + * With "fsync=strict", we fsync after final metadata copyup, for * both regular files and directories to get atomic copyup semantics * on filesystems that do not use strict metadata ordering (e.g. ubifs). * - * With metacopy enabled we want to avoid fsync on all meta copyup + * By default, we want to avoid fsync on all meta copyup, because * that will hurt performance of workloads such as chown -R, so we * only fsync on data copyup as legacy behavior. */ - ctx.metadata_fsync = !OVL_FS(dentry->d_sb)->config.metacopy && + ctx.metadata_fsync = ovl_should_sync_metadata(OVL_FS(dentry->d_sb)) && (S_ISREG(ctx.stat.mode) || S_ISDIR(ctx.stat.mode)); ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index cad2055ebf18..63b299bf12f7 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -99,6 +99,12 @@ enum { OVL_VERITY_REQUIRE, }; +enum { + OVL_FSYNC_VOLATILE, + OVL_FSYNC_AUTO, + OVL_FSYNC_STRICT, +}; + /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: @@ -656,6 +662,21 @@ static inline bool ovl_xino_warn(struct ovl_fs *ofs) return ofs->config.xino == OVL_XINO_ON; } +static inline bool ovl_should_sync(struct ovl_fs *ofs) +{ + return ofs->config.fsync_mode != OVL_FSYNC_VOLATILE; +} + +static inline bool ovl_should_sync_metadata(struct ovl_fs *ofs) +{ + return ofs->config.fsync_mode == OVL_FSYNC_STRICT; +} + +static inline bool ovl_is_volatile(struct ovl_config *config) +{ + return config->fsync_mode == OVL_FSYNC_VOLATILE; +} + /* * To avoid regressions in existing setups with overlay lower offline changes, * we allow lower changes only if none of the new features are used. diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 1d4828dbcf7a..80cad4ea96a3 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -18,7 +18,7 @@ struct ovl_config { int xino; bool metacopy; bool userxattr; - bool ovl_volatile; + int fsync_mode; }; struct ovl_sb { @@ -120,11 +120,6 @@ static inline struct ovl_fs *OVL_FS(struct super_block *sb) return (struct ovl_fs *)sb->s_fs_info; } -static inline bool ovl_should_sync(struct ovl_fs *ofs) -{ - return !ofs->config.ovl_volatile; -} - static inline unsigned int ovl_numlower(struct ovl_entry *oe) { return oe ? oe->__numlower : 0; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 8111b437ae5d..c93fcaa45d4a 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -58,6 +58,7 @@ enum ovl_opt { Opt_xino, Opt_metacopy, Opt_verity, + Opt_fsync, Opt_volatile, Opt_override_creds, }; @@ -140,6 +141,23 @@ static int ovl_verity_mode_def(void) return OVL_VERITY_OFF; } +static const struct constant_table ovl_parameter_fsync[] = { + { "volatile", OVL_FSYNC_VOLATILE }, + { "auto", OVL_FSYNC_AUTO }, + { "strict", OVL_FSYNC_STRICT }, + {} +}; + +static const char *ovl_fsync_mode(struct ovl_config *config) +{ + return ovl_parameter_fsync[config->fsync_mode].name; +} + +static int ovl_fsync_mode_def(void) +{ + return OVL_FSYNC_AUTO; +} + const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_string_empty("lowerdir", Opt_lowerdir), fsparam_file_or_string("lowerdir+", Opt_lowerdir_add), @@ -155,6 +173,7 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { fsparam_enum("xino", Opt_xino, ovl_parameter_xino), fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), fsparam_enum("verity", Opt_verity, ovl_parameter_verity), + fsparam_enum("fsync", Opt_fsync, ovl_parameter_fsync), fsparam_flag("volatile", Opt_volatile), fsparam_flag_no("override_creds", Opt_override_creds), {} @@ -665,8 +684,11 @@ static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) case Opt_verity: config->verity_mode = result.uint_32; break; + case Opt_fsync: + config->fsync_mode = result.uint_32; + break; case Opt_volatile: - config->ovl_volatile = true; + config->fsync_mode = OVL_FSYNC_VOLATILE; break; case Opt_userxattr: config->userxattr = true; @@ -800,6 +822,7 @@ int ovl_init_fs_context(struct fs_context *fc) ofs->config.nfs_export = ovl_nfs_export_def; ofs->config.xino = ovl_xino_def(); ofs->config.metacopy = ovl_metacopy_def; + ofs->config.fsync_mode = ovl_fsync_mode_def(); fc->s_fs_info = ofs; fc->fs_private = ctx; @@ -870,9 +893,9 @@ int ovl_fs_params_verify(const struct ovl_fs_context *ctx, config->index = false; } - if (!config->upperdir && config->ovl_volatile) { + if (!config->upperdir && ovl_is_volatile(config)) { pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n"); - config->ovl_volatile = false; + config->fsync_mode = ovl_fsync_mode_def(); } if (!config->upperdir && config->uuid == OVL_UUID_ON) { @@ -1070,8 +1093,8 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config)); if (ofs->config.metacopy != ovl_metacopy_def) seq_printf(m, ",metacopy=%s", str_on_off(ofs->config.metacopy)); - if (ofs->config.ovl_volatile) - seq_puts(m, ",volatile"); + if (ofs->config.fsync_mode != ovl_fsync_mode_def()) + seq_printf(m, ",fsync=%s", ovl_fsync_mode(&ofs->config)); if (ofs->config.userxattr) seq_puts(m, ",userxattr"); if (ofs->config.verity_mode != ovl_verity_mode_def()) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index d4c12feec039..0822987cfb51 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -776,7 +776,7 @@ static int ovl_make_workdir(struct super_block *sb, struct ovl_fs *ofs, * For volatile mount, create a incompat/volatile/dirty file to keep * track of it. */ - if (ofs->config.ovl_volatile) { + if (ovl_is_volatile(&ofs->config)) { err = ovl_create_volatile_dirty(ofs); if (err < 0) { pr_err("Failed to create volatile/dirty file.\n"); diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 3f1b763a8bb4..2ea769f311c3 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -85,7 +85,10 @@ int ovl_can_decode_fh(struct super_block *sb) if (!exportfs_can_decode_fh(sb->s_export_op)) return 0; - return sb->s_export_op->encode_fh ? -1 : FILEID_INO32_GEN; + if (sb->s_export_op->encode_fh == generic_encode_ino32_fh) + return FILEID_INO32_GEN; + + return -1; } struct dentry *ovl_indexdir(struct super_block *sb) diff --git a/fs/smb/client/Makefile b/fs/smb/client/Makefile index 26b6105f04d1..1a6e1e1c9764 100644 --- a/fs/smb/client/Makefile +++ b/fs/smb/client/Makefile @@ -48,8 +48,8 @@ cifs-$(CONFIG_CIFS_COMPRESSION) += compress.o compress/lz77.o # Build the SMB2 error mapping table from smb2status.h # $(obj)/smb2_mapping_table.c: $(src)/../common/smb2status.h \ - $(src)/gen_smb2_mapping - $(call cmd,gen_smb2_mapping) + $(src)/gen_smb2_mapping FORCE + $(call if_changed,gen_smb2_mapping) $(obj)/smb2maperror.o: $(obj)/smb2_mapping_table.c @@ -58,4 +58,5 @@ quiet_cmd_gen_smb2_mapping = GEN $@ obj-$(CONFIG_SMB_KUNIT_TESTS) += smb2maperror_test.o -clean-files += smb2_mapping_table.c +# Let Kbuild handle tracking and cleaning +targets += smb2_mapping_table.c diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 393a4ae47cc1..9b2bb8764a80 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -82,11 +82,19 @@ static void lease_del_list(struct oplock_info *opinfo) spin_unlock(&lb->lb_lock); } -static void lb_add(struct lease_table *lb) +static struct lease_table *alloc_lease_table(struct oplock_info *opinfo) { - write_lock(&lease_list_lock); - list_add(&lb->l_entry, &lease_table_list); - write_unlock(&lease_list_lock); + struct lease_table *lb; + + lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP); + if (!lb) + return NULL; + + memcpy(lb->client_guid, opinfo->conn->ClientGUID, + SMB2_CLIENT_GUID_SIZE); + INIT_LIST_HEAD(&lb->lease_list); + spin_lock_init(&lb->lb_lock); + return lb; } static int alloc_lease(struct oplock_info *opinfo, struct lease_ctx_info *lctx) @@ -1042,34 +1050,27 @@ static void copy_lease(struct oplock_info *op1, struct oplock_info *op2) lease2->version = lease1->version; } -static int add_lease_global_list(struct oplock_info *opinfo) +static void add_lease_global_list(struct oplock_info *opinfo, + struct lease_table *new_lb) { struct lease_table *lb; - read_lock(&lease_list_lock); + write_lock(&lease_list_lock); list_for_each_entry(lb, &lease_table_list, l_entry) { if (!memcmp(lb->client_guid, opinfo->conn->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { opinfo->o_lease->l_lb = lb; lease_add_list(opinfo); - read_unlock(&lease_list_lock); - return 0; + write_unlock(&lease_list_lock); + kfree(new_lb); + return; } } - read_unlock(&lease_list_lock); - lb = kmalloc_obj(struct lease_table, KSMBD_DEFAULT_GFP); - if (!lb) - return -ENOMEM; - - memcpy(lb->client_guid, opinfo->conn->ClientGUID, - SMB2_CLIENT_GUID_SIZE); - INIT_LIST_HEAD(&lb->lease_list); - spin_lock_init(&lb->lb_lock); - opinfo->o_lease->l_lb = lb; + opinfo->o_lease->l_lb = new_lb; lease_add_list(opinfo); - lb_add(lb); - return 0; + list_add(&new_lb->l_entry, &lease_table_list); + write_unlock(&lease_list_lock); } static void set_oplock_level(struct oplock_info *opinfo, int level, @@ -1189,6 +1190,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid, int err = 0; struct oplock_info *opinfo = NULL, *prev_opinfo = NULL; struct ksmbd_inode *ci = fp->f_ci; + struct lease_table *new_lb = NULL; bool prev_op_has_lease; __le32 prev_op_state = 0; @@ -1291,21 +1293,37 @@ set_lev: set_oplock_level(opinfo, req_op_level, lctx); out: - opinfo_count_inc(fp); - opinfo_add(opinfo, fp); - + /* + * Set o_fp before any publication so that concurrent readers + * (e.g. find_same_lease_key() on the lease list) that + * dereference opinfo->o_fp don't hit a NULL pointer. + * + * Keep the original publication order so concurrent opens can + * still observe the in-flight grant via ci->m_op_list, but make + * everything after opinfo_add() no-fail by preallocating any new + * lease_table first. + */ + opinfo->o_fp = fp; if (opinfo->is_lease) { - err = add_lease_global_list(opinfo); - if (err) + new_lb = alloc_lease_table(opinfo); + if (!new_lb) { + err = -ENOMEM; goto err_out; + } } + opinfo_count_inc(fp); + opinfo_add(opinfo, fp); + + if (opinfo->is_lease) + add_lease_global_list(opinfo, new_lb); + rcu_assign_pointer(fp->f_opinfo, opinfo); - opinfo->o_fp = fp; return 0; err_out: - __free_opinfo(opinfo); + kfree(new_lb); + opinfo_put(opinfo); return err; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 9c44e71e3c3b..6fb7a795ff5d 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1939,8 +1939,14 @@ out_err: if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION) try_delay = true; - sess->last_active = jiffies; - sess->state = SMB2_SESSION_EXPIRED; + /* + * For binding requests, session belongs to another + * connection. Do not expire it. + */ + if (!(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { + sess->last_active = jiffies; + sess->state = SMB2_SESSION_EXPIRED; + } ksmbd_user_session_put(sess); work->sess = NULL; if (try_delay) { @@ -4446,8 +4452,9 @@ int smb2_query_dir(struct ksmbd_work *work) d_info.wptr = (char *)rsp->Buffer; d_info.rptr = (char *)rsp->Buffer; d_info.out_buf_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_directory_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (d_info.out_buf_len < 0) { rc = -EINVAL; goto err_out; @@ -4714,8 +4721,9 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, } buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (buf_free_len < 0) return -EINVAL; @@ -4932,7 +4940,8 @@ static int get_file_all_info(struct ksmbd_work *work, int conv_len; char *filename; u64 time; - int ret; + int ret, buf_free_len, filename_len; + struct smb2_query_info_req *req = ksmbd_req_buf_next(work); if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n", @@ -4944,6 +4953,16 @@ static int get_file_all_info(struct ksmbd_work *work, if (IS_ERR(filename)) return PTR_ERR(filename); + filename_len = strlen(filename); + buf_free_len = smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer) + + offsetof(struct smb2_file_all_info, FileName), + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < (filename_len + 1) * 2) { + kfree(filename); + return -EINVAL; + } + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); if (ret) { @@ -4987,7 +5006,8 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Mode = fp->coption; file_info->AlignmentRequirement = 0; conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename, - PATH_MAX, conn->local_nls, 0); + min(filename_len, PATH_MAX), + conn->local_nls, 0); conv_len *= 2; file_info->FileNameLength = cpu_to_le32(conv_len); rsp->OutputBufferLength = @@ -5041,8 +5061,9 @@ static int get_file_stream_info(struct ksmbd_work *work, file_info = (struct smb2_file_stream_info *)rsp->Buffer; buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); + smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_query_info_rsp, Buffer), + le32_to_cpu(req->OutputBufferLength)); if (buf_free_len < 0) goto out; @@ -7586,14 +7607,15 @@ retry: rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL); skip: if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) { + locks_free_lock(flock); + kfree(smb_lock); if (!rc) { ksmbd_debug(SMB, "File unlocked\n"); } else if (rc == -ENOENT) { rsp->hdr.Status = STATUS_NOT_LOCKED; + err = rc; goto out; } - locks_free_lock(flock); - kfree(smb_lock); } else { if (rc == FILE_LOCK_DEFERRED) { void **argv; @@ -7662,6 +7684,9 @@ skip: spin_unlock(&work->conn->llist_lock); ksmbd_debug(SMB, "successful in taking lock\n"); } else { + locks_free_lock(flock); + kfree(smb_lock); + err = rc; goto out; } } @@ -7692,13 +7717,17 @@ out: struct file_lock *rlock = NULL; rlock = smb_flock_init(filp); - rlock->c.flc_type = F_UNLCK; - rlock->fl_start = smb_lock->start; - rlock->fl_end = smb_lock->end; + if (rlock) { + rlock->c.flc_type = F_UNLCK; + rlock->fl_start = smb_lock->start; + rlock->fl_end = smb_lock->end; - rc = vfs_lock_file(filp, F_SETLK, rlock, NULL); - if (rc) - pr_err("rollback unlock fail : %d\n", rc); + rc = vfs_lock_file(filp, F_SETLK, rlock, NULL); + if (rc) + pr_err("rollback unlock fail : %d\n", rc); + } else { + pr_err("rollback unlock alloc failed\n"); + } list_del(&smb_lock->llist); spin_lock(&work->conn->llist_lock); @@ -7708,7 +7737,8 @@ out: spin_unlock(&work->conn->llist_lock); locks_free_lock(smb_lock->fl); - locks_free_lock(rlock); + if (rlock) + locks_free_lock(rlock); kfree(smb_lock); } out2: @@ -8191,8 +8221,9 @@ int smb2_ioctl(struct ksmbd_work *work) buffer = (char *)req + le32_to_cpu(req->InputOffset); cnt_code = le32_to_cpu(req->CtlCode); - ret = smb2_calc_max_out_buf_len(work, 48, - le32_to_cpu(req->MaxOutputResponse)); + ret = smb2_calc_max_out_buf_len(work, + offsetof(struct smb2_ioctl_rsp, Buffer), + le32_to_cpu(req->MaxOutputResponse)); if (ret < 0) { rsp->hdr.Status = STATUS_INVALID_PARAMETER; goto out; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 7fae8002344a..23e894092dab 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -181,22 +181,23 @@ static void udf_write_failed(struct address_space *mapping, loff_t to) } } -static int udf_adinicb_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int udf_handle_page_wb(struct folio *folio, + struct writeback_control *wbc) { - struct inode *inode = mapping->host; + struct inode *inode = folio->mapping->host; struct udf_inode_info *iinfo = UDF_I(inode); - struct folio *folio = NULL; - int error = 0; - while ((folio = writeback_iter(mapping, wbc, folio, &error))) { - BUG_ON(!folio_test_locked(folio)); - BUG_ON(folio->index != 0); - memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, - 0, i_size_read(inode)); - folio_unlock(folio); - } + /* + * Inodes in the normal format are handled by the generic code. This + * check is race-free as the folio lock protects us from inode type + * conversion. + */ + if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) + return 1; + memcpy_from_file_folio(iinfo->i_data + iinfo->i_lenEAttr, folio, + 0, i_size_read(inode)); + folio_unlock(folio); mark_inode_dirty(inode); return 0; } @@ -204,12 +205,8 @@ static int udf_adinicb_writepages(struct address_space *mapping, static int udf_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct inode *inode = mapping->host; - struct udf_inode_info *iinfo = UDF_I(inode); - - if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) - return udf_adinicb_writepages(mapping, wbc); - return mpage_writepages(mapping, wbc, udf_get_block_wb); + return __mpage_writepages(mapping, wbc, udf_get_block_wb, + udf_handle_page_wb); } static void udf_adinicb_read_folio(struct folio *folio) diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h index 8244305949de..67fd9c75ac3f 100644 --- a/fs/xfs/libxfs/xfs_attr.h +++ b/fs/xfs/libxfs/xfs_attr.h @@ -55,7 +55,8 @@ struct xfs_attr_list_context { struct xfs_trans *tp; struct xfs_inode *dp; /* inode */ struct xfs_attrlist_cursor_kern cursor; /* position in list */ - void *buffer; /* output buffer */ + /* output buffer */ + void *buffer __counted_by_ptr(bufsize); /* * Abort attribute list iteration if non-zero. Can be used to pass diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 47f48ae555c0..2b78041e8672 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -1416,6 +1416,28 @@ xfs_attr3_leaf_create( } /* + * Reinitialize an existing attr fork block as an empty leaf, and attach + * the buffer to tp. + */ +int +xfs_attr3_leaf_init( + struct xfs_trans *tp, + struct xfs_inode *dp, + xfs_dablk_t blkno) +{ + struct xfs_buf *bp = NULL; + struct xfs_da_args args = { + .trans = tp, + .dp = dp, + .owner = dp->i_ino, + .geo = dp->i_mount->m_attr_geo, + }; + + ASSERT(tp != NULL); + + return xfs_attr3_leaf_create(&args, blkno, &bp); +} +/* * Split the leaf node, rebalance, then add the new entry. * * Returns 0 if the entry was added, 1 if a further split is needed or a diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index aca46da2bc50..72639efe6ac3 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -87,6 +87,9 @@ int xfs_attr3_leaf_list_int(struct xfs_buf *bp, /* * Routines used for shrinking the Btree. */ + +int xfs_attr3_leaf_init(struct xfs_trans *tp, struct xfs_inode *dp, + xfs_dablk_t blkno); int xfs_attr3_leaf_toosmall(struct xfs_da_state *state, int *retval); void xfs_attr3_leaf_unbalance(struct xfs_da_state *state, struct xfs_da_state_blk *drop_blk, diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 09d4c17b3e7b..ad801b7bd2dd 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -1506,21 +1506,20 @@ xfs_da3_fixhashpath( } /* - * Remove an entry from an intermediate node. + * Internal implementation to remove an entry from an intermediate node. */ STATIC void -xfs_da3_node_remove( - struct xfs_da_state *state, - struct xfs_da_state_blk *drop_blk) +__xfs_da3_node_remove( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_da_geometry *geo, + struct xfs_da_state_blk *drop_blk) { struct xfs_da_intnode *node; struct xfs_da3_icnode_hdr nodehdr; struct xfs_da_node_entry *btree; int index; int tmp; - struct xfs_inode *dp = state->args->dp; - - trace_xfs_da_node_remove(state->args); node = drop_blk->bp->b_addr; xfs_da3_node_hdr_from_disk(dp->i_mount, &nodehdr, node); @@ -1536,17 +1535,17 @@ xfs_da3_node_remove( tmp = nodehdr.count - index - 1; tmp *= (uint)sizeof(xfs_da_node_entry_t); memmove(&btree[index], &btree[index + 1], tmp); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, + xfs_trans_log_buf(tp, drop_blk->bp, XFS_DA_LOGRANGE(node, &btree[index], tmp)); index = nodehdr.count - 1; } memset(&btree[index], 0, sizeof(xfs_da_node_entry_t)); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, + xfs_trans_log_buf(tp, drop_blk->bp, XFS_DA_LOGRANGE(node, &btree[index], sizeof(btree[index]))); nodehdr.count -= 1; xfs_da3_node_hdr_to_disk(dp->i_mount, node, &nodehdr); - xfs_trans_log_buf(state->args->trans, drop_blk->bp, - XFS_DA_LOGRANGE(node, &node->hdr, state->args->geo->node_hdr_size)); + xfs_trans_log_buf(tp, drop_blk->bp, + XFS_DA_LOGRANGE(node, &node->hdr, geo->node_hdr_size)); /* * Copy the last hash value from the block to propagate upwards. @@ -1555,6 +1554,38 @@ xfs_da3_node_remove( } /* + * Remove an entry from an intermediate node. + */ +STATIC void +xfs_da3_node_remove( + struct xfs_da_state *state, + struct xfs_da_state_blk *drop_blk) +{ + trace_xfs_da_node_remove(state->args); + + __xfs_da3_node_remove(state->args->trans, state->args->dp, + state->args->geo, drop_blk); +} + +/* + * Remove an entry from an intermediate attr node at the specified index. + */ +void +xfs_attr3_node_entry_remove( + struct xfs_trans *tp, + struct xfs_inode *dp, + struct xfs_buf *bp, + int index) +{ + struct xfs_da_state_blk blk = { + .index = index, + .bp = bp, + }; + + __xfs_da3_node_remove(tp, dp, dp->i_mount->m_attr_geo, &blk); +} + +/* * Unbalance the elements between two intermediate nodes, * move all Btree elements from one node into another. */ diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h index 354d5d65043e..afcf2d3c7a21 100644 --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -184,6 +184,8 @@ int xfs_da3_split(xfs_da_state_t *state); int xfs_da3_join(xfs_da_state_t *state); void xfs_da3_fixhashpath(struct xfs_da_state *state, struct xfs_da_state_path *path_to_to_fix); +void xfs_attr3_node_entry_remove(struct xfs_trans *tp, struct xfs_inode *dp, + struct xfs_buf *bp, int index); /* * Routines used for finding things in the Btree. diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c index 1d25bd5b892e..222812fe202c 100644 --- a/fs/xfs/scrub/quota.c +++ b/fs/xfs/scrub/quota.c @@ -171,8 +171,10 @@ xchk_quota_item( error = xchk_quota_item_bmap(sc, dq, offset); xchk_iunlock(sc, XFS_ILOCK_SHARED); - if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) + if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, offset, &error)) { + mutex_unlock(&dq->q_qlock); return error; + } /* * Warn if the hard limits are larger than the fs. diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 39ea651cbb75..286c5f5e0544 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -972,20 +972,12 @@ TRACE_EVENT(xfile_create, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) - __array(char, pathname, MAXNAMELEN) ), TP_fast_assign( - char *path; - __entry->ino = file_inode(xf->file)->i_ino; - path = file_path(xf->file, __entry->pathname, MAXNAMELEN); - if (IS_ERR(path)) - strncpy(__entry->pathname, "(unknown)", - sizeof(__entry->pathname)); ), - TP_printk("xfino 0x%lx path '%s'", - __entry->ino, - __entry->pathname) + TP_printk("xfino 0x%lx", + __entry->ino) ); TRACE_EVENT(xfile_destroy, diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index 92331991f9fd..a5b69c0fbfd0 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -140,7 +140,7 @@ xfs_attr3_node_inactive( xfs_daddr_t parent_blkno, child_blkno; struct xfs_buf *child_bp; struct xfs_da3_icnode_hdr ichdr; - int error, i; + int error; /* * Since this code is recursive (gasp!) we must protect ourselves. @@ -152,7 +152,7 @@ xfs_attr3_node_inactive( return -EFSCORRUPTED; } - xfs_da3_node_hdr_from_disk(dp->i_mount, &ichdr, bp->b_addr); + xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr); parent_blkno = xfs_buf_daddr(bp); if (!ichdr.count) { xfs_trans_brelse(*trans, bp); @@ -167,7 +167,7 @@ xfs_attr3_node_inactive( * over the leaves removing all of them. If this is higher up * in the tree, recurse downward. */ - for (i = 0; i < ichdr.count; i++) { + while (ichdr.count > 0) { /* * Read the subsidiary block to see what we have to work with. * Don't do this in a transaction. This is a depth-first @@ -218,29 +218,32 @@ xfs_attr3_node_inactive( xfs_trans_binval(*trans, child_bp); child_bp = NULL; + error = xfs_da3_node_read_mapped(*trans, dp, + parent_blkno, &bp, XFS_ATTR_FORK); + if (error) + return error; + /* - * If we're not done, re-read the parent to get the next - * child block number. + * Remove entry from parent node, prevents being indexed to. */ - if (i + 1 < ichdr.count) { - struct xfs_da3_icnode_hdr phdr; + xfs_attr3_node_entry_remove(*trans, dp, bp, 0); + + xfs_da3_node_hdr_from_disk(mp, &ichdr, bp->b_addr); + bp = NULL; - error = xfs_da3_node_read_mapped(*trans, dp, - parent_blkno, &bp, XFS_ATTR_FORK); + if (ichdr.count > 0) { + /* + * If we're not done, get the next child block number. + */ + child_fsb = be32_to_cpu(ichdr.btree[0].before); + + /* + * Atomically commit the whole invalidate stuff. + */ + error = xfs_trans_roll_inode(trans, dp); if (error) return error; - xfs_da3_node_hdr_from_disk(dp->i_mount, &phdr, - bp->b_addr); - child_fsb = be32_to_cpu(phdr.btree[i + 1].before); - xfs_trans_brelse(*trans, bp); - bp = NULL; } - /* - * Atomically commit the whole invalidate stuff. - */ - error = xfs_trans_roll_inode(trans, dp); - if (error) - return error; } return 0; @@ -257,10 +260,8 @@ xfs_attr3_root_inactive( struct xfs_trans **trans, struct xfs_inode *dp) { - struct xfs_mount *mp = dp->i_mount; struct xfs_da_blkinfo *info; struct xfs_buf *bp; - xfs_daddr_t blkno; int error; /* @@ -272,7 +273,6 @@ xfs_attr3_root_inactive( error = xfs_da3_node_read(*trans, dp, 0, &bp, XFS_ATTR_FORK); if (error) return error; - blkno = xfs_buf_daddr(bp); /* * Invalidate the tree, even if the "tree" is only a single leaf block. @@ -283,10 +283,26 @@ xfs_attr3_root_inactive( case cpu_to_be16(XFS_DA_NODE_MAGIC): case cpu_to_be16(XFS_DA3_NODE_MAGIC): error = xfs_attr3_node_inactive(trans, dp, bp, 1); + /* + * Empty root node block are not allowed, convert it to leaf. + */ + if (!error) + error = xfs_attr3_leaf_init(*trans, dp, 0); + if (!error) + error = xfs_trans_roll_inode(trans, dp); break; case cpu_to_be16(XFS_ATTR_LEAF_MAGIC): case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC): error = xfs_attr3_leaf_inactive(trans, dp, bp); + /* + * Reinit the leaf before truncating extents so that a crash + * mid-truncation leaves an empty leaf rather than one with + * entries that may reference freed remote value blocks. + */ + if (!error) + error = xfs_attr3_leaf_init(*trans, dp, 0); + if (!error) + error = xfs_trans_roll_inode(trans, dp); break; default: xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK); @@ -295,21 +311,6 @@ xfs_attr3_root_inactive( xfs_trans_brelse(*trans, bp); break; } - if (error) - return error; - - /* - * Invalidate the incore copy of the root block. - */ - error = xfs_trans_get_buf(*trans, mp->m_ddev_targp, blkno, - XFS_FSB_TO_BB(mp, mp->m_attr_geo->fsbcount), 0, &bp); - if (error) - return error; - xfs_trans_binval(*trans, bp); /* remove from cache */ - /* - * Commit the invalidate and start the next transaction. - */ - error = xfs_trans_roll_inode(trans, dp); return error; } @@ -328,6 +329,7 @@ xfs_attr_inactive( { struct xfs_trans *trans; struct xfs_mount *mp; + struct xfs_buf *bp; int lock_mode = XFS_ILOCK_SHARED; int error = 0; @@ -363,10 +365,27 @@ xfs_attr_inactive( * removal below. */ if (dp->i_af.if_nextents > 0) { + /* + * Invalidate and truncate all blocks but leave the root block. + */ error = xfs_attr3_root_inactive(&trans, dp); if (error) goto out_cancel; + error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, + XFS_FSB_TO_B(mp, mp->m_attr_geo->fsbcount)); + if (error) + goto out_cancel; + + /* + * Invalidate and truncate the root block and ensure that the + * operation is completed within a single transaction. + */ + error = xfs_da_get_buf(trans, dp, 0, &bp, XFS_ATTR_FORK); + if (error) + goto out_cancel; + + xfs_trans_binval(trans, bp); error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0); if (error) goto out_cancel; diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index 354472bf45f1..deab14f31b38 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -653,7 +653,6 @@ xfs_attri_recover_work( break; } if (error) { - xfs_irele(ip); XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attrp, sizeof(*attrp)); return ERR_PTR(-EFSCORRUPTED); @@ -1047,8 +1046,8 @@ xlog_recover_attri_commit_pass2( break; case XFS_ATTRI_OP_FLAGS_SET: case XFS_ATTRI_OP_FLAGS_REPLACE: - /* Log item, attr name, attr value */ - if (item->ri_total != 3) { + /* Log item, attr name, optional attr value */ + if (item->ri_total != 2 + !!attri_formatp->alfi_value_len) { XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, attri_formatp, len); return -EFSCORRUPTED; @@ -1132,52 +1131,6 @@ xlog_recover_attri_commit_pass2( return -EFSCORRUPTED; } - switch (op) { - case XFS_ATTRI_OP_FLAGS_REMOVE: - /* Regular remove operations operate only on names. */ - if (attr_value != NULL || value_len != 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - fallthrough; - case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE: - case XFS_ATTRI_OP_FLAGS_PPTR_SET: - case XFS_ATTRI_OP_FLAGS_SET: - case XFS_ATTRI_OP_FLAGS_REPLACE: - /* - * Regular xattr set/remove/replace operations require a name - * and do not take a newname. Values are optional for set and - * replace. - * - * Name-value set/remove operations must have a name, do not - * take a newname, and can take a value. - */ - if (attr_name == NULL || name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - break; - case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE: - /* - * Name-value replace operations require the caller to - * specify the old and new names and values explicitly. - * Values are optional. - */ - if (attr_name == NULL || name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - if (attr_new_name == NULL || new_name_len == 0) { - XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - attri_formatp, len); - return -EFSCORRUPTED; - } - break; - } - /* * Memory alloc failure will cause replay to abort. We attach the * name/value buffer to the recovered incore log item and drop our diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 491e2a7053a3..65a0e69c3d08 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -125,6 +125,7 @@ xfs_qm_dquot_logitem_push( struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_buf *bp; + struct xfs_ail *ailp = lip->li_ailp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -153,7 +154,7 @@ xfs_qm_dquot_logitem_push( goto out_unlock; } - spin_unlock(&lip->li_ailp->ail_lock); + spin_unlock(&ailp->ail_lock); error = xfs_dquot_use_attached_buf(dqp, &bp); if (error == -EAGAIN) { @@ -172,9 +173,13 @@ xfs_qm_dquot_logitem_push( rval = XFS_ITEM_FLUSHING; } xfs_buf_relse(bp); + /* + * The buffer no longer protects the log item from reclaim, so + * do not reference lip after this point. + */ out_relock_ail: - spin_lock(&lip->li_ailp->ail_lock); + spin_lock(&ailp->ail_lock); out_unlock: mutex_unlock(&dqp->q_qlock); return rval; diff --git a/fs/xfs/xfs_handle.c b/fs/xfs/xfs_handle.c index d1291ca15239..2b8617ae7ec2 100644 --- a/fs/xfs/xfs_handle.c +++ b/fs/xfs/xfs_handle.c @@ -443,8 +443,8 @@ xfs_ioc_attr_list( context.dp = dp; context.resynch = 1; context.attr_filter = xfs_attr_filter(flags); - context.buffer = buffer; context.bufsize = round_down(bufsize, sizeof(uint32_t)); + context.buffer = buffer; context.firstu = context.bufsize; context.put_listent = xfs_ioc_attr_put_listent; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 50c0404f9064..beaa26ec62da 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1048,7 +1048,8 @@ xfs_itruncate_extents_flags( xfs_assert_ilocked(ip, XFS_ILOCK_EXCL); if (icount_read(VFS_I(ip))) xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL); - ASSERT(new_size <= XFS_ISIZE(ip)); + if (whichfork == XFS_DATA_FORK) + ASSERT(new_size <= XFS_ISIZE(ip)); ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); ASSERT(ip->i_itemp != NULL); ASSERT(ip->i_itemp->ili_lock_flags == 0); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index 8913036b8024..4ae81eed0442 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -746,6 +746,7 @@ xfs_inode_item_push( struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; struct xfs_buf *bp = lip->li_buf; + struct xfs_ail *ailp = lip->li_ailp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -771,7 +772,7 @@ xfs_inode_item_push( if (!xfs_buf_trylock(bp)) return XFS_ITEM_LOCKED; - spin_unlock(&lip->li_ailp->ail_lock); + spin_unlock(&ailp->ail_lock); /* * We need to hold a reference for flushing the cluster buffer as it may @@ -795,7 +796,11 @@ xfs_inode_item_push( rval = XFS_ITEM_LOCKED; } - spin_lock(&lip->li_ailp->ail_lock); + /* + * The buffer no longer protects the log item from reclaim, so + * do not reference lip after this point. + */ + spin_lock(&ailp->ail_lock); return rval; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 9c295abd0a0a..ef1ea8a1238c 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -608,8 +608,9 @@ xfs_unmount_check( * have been retrying in the background. This will prevent never-ending * retries in AIL pushing from hanging the unmount. * - * Finally, we can push the AIL to clean all the remaining dirty objects, then - * reclaim the remaining inodes that are still in memory at this point in time. + * Stop inodegc and background reclaim before pushing the AIL so that they + * are not running while the AIL is being flushed. Then push the AIL to + * clean all the remaining dirty objects and reclaim the remaining inodes. */ static void xfs_unmount_flush_inodes( @@ -621,9 +622,9 @@ xfs_unmount_flush_inodes( xfs_set_unmounting(mp); - xfs_ail_push_all_sync(mp->m_ail); xfs_inodegc_stop(mp); cancel_delayed_work_sync(&mp->m_reclaim_work); + xfs_ail_push_all_sync(mp->m_ail); xfs_reclaim_inodes(mp); xfs_health_unmount(mp); xfs_healthmon_unmount(mp); diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 813e5a9f57eb..5e8190fe2be9 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -56,6 +56,7 @@ #include <linux/tracepoint.h> struct xfs_agf; +struct xfs_ail; struct xfs_alloc_arg; struct xfs_attr_list_context; struct xfs_buf_log_item; @@ -1650,16 +1651,43 @@ TRACE_EVENT(xfs_log_force, DEFINE_EVENT(xfs_log_item_class, name, \ TP_PROTO(struct xfs_log_item *lip), \ TP_ARGS(lip)) -DEFINE_LOG_ITEM_EVENT(xfs_ail_push); -DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned); -DEFINE_LOG_ITEM_EVENT(xfs_ail_locked); -DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin); DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort); DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort); +DECLARE_EVENT_CLASS(xfs_ail_push_class, + TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), + TP_ARGS(ailp, type, flags, lsn), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(uint, type) + __field(unsigned long, flags) + __field(xfs_lsn_t, lsn) + ), + TP_fast_assign( + __entry->dev = ailp->ail_log->l_mp->m_super->s_dev; + __entry->type = type; + __entry->flags = flags; + __entry->lsn = lsn; + ), + TP_printk("dev %d:%d lsn %d/%d type %s flags %s", + MAJOR(__entry->dev), MINOR(__entry->dev), + CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn), + __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), + __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) +) + +#define DEFINE_AIL_PUSH_EVENT(name) \ +DEFINE_EVENT(xfs_ail_push_class, name, \ + TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), \ + TP_ARGS(ailp, type, flags, lsn)) +DEFINE_AIL_PUSH_EVENT(xfs_ail_push); +DEFINE_AIL_PUSH_EVENT(xfs_ail_pinned); +DEFINE_AIL_PUSH_EVENT(xfs_ail_locked); +DEFINE_AIL_PUSH_EVENT(xfs_ail_flushing); + DECLARE_EVENT_CLASS(xfs_ail_class, TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn), TP_ARGS(lip, old_lsn, new_lsn), @@ -5091,23 +5119,16 @@ TRACE_EVENT(xmbuf_create, TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) - __array(char, pathname, MAXNAMELEN) ), TP_fast_assign( - char *path; struct file *file = btp->bt_file; __entry->dev = btp->bt_mount->m_super->s_dev; __entry->ino = file_inode(file)->i_ino; - path = file_path(file, __entry->pathname, MAXNAMELEN); - if (IS_ERR(path)) - strncpy(__entry->pathname, "(unknown)", - sizeof(__entry->pathname)); ), - TP_printk("dev %d:%d xmino 0x%lx path '%s'", + TP_printk("dev %d:%d xmino 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->ino, - __entry->pathname) + __entry->ino) ); TRACE_EVENT(xmbuf_free, diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 923729af4206..99a9bf3762b7 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -365,6 +365,12 @@ xfsaild_resubmit_item( return XFS_ITEM_SUCCESS; } +/* + * Push a single log item from the AIL. + * + * @lip may have been released and freed by the time this function returns, + * so callers must not dereference the log item afterwards. + */ static inline uint xfsaild_push_item( struct xfs_ail *ailp, @@ -458,6 +464,74 @@ xfs_ail_calc_push_target( return target_lsn; } +static void +xfsaild_process_logitem( + struct xfs_ail *ailp, + struct xfs_log_item *lip, + int *stuck, + int *flushing) +{ + struct xfs_mount *mp = ailp->ail_log->l_mp; + uint type = lip->li_type; + unsigned long flags = lip->li_flags; + xfs_lsn_t item_lsn = lip->li_lsn; + int lock_result; + + /* + * Note that iop_push may unlock and reacquire the AIL lock. We + * rely on the AIL cursor implementation to be able to deal with + * the dropped lock. + * + * The log item may have been freed by the push, so it must not + * be accessed or dereferenced below this line. + */ + lock_result = xfsaild_push_item(ailp, lip); + switch (lock_result) { + case XFS_ITEM_SUCCESS: + XFS_STATS_INC(mp, xs_push_ail_success); + trace_xfs_ail_push(ailp, type, flags, item_lsn); + + ailp->ail_last_pushed_lsn = item_lsn; + break; + + case XFS_ITEM_FLUSHING: + /* + * The item or its backing buffer is already being + * flushed. The typical reason for that is that an + * inode buffer is locked because we already pushed the + * updates to it as part of inode clustering. + * + * We do not want to stop flushing just because lots + * of items are already being flushed, but we need to + * re-try the flushing relatively soon if most of the + * AIL is being flushed. + */ + XFS_STATS_INC(mp, xs_push_ail_flushing); + trace_xfs_ail_flushing(ailp, type, flags, item_lsn); + + (*flushing)++; + ailp->ail_last_pushed_lsn = item_lsn; + break; + + case XFS_ITEM_PINNED: + XFS_STATS_INC(mp, xs_push_ail_pinned); + trace_xfs_ail_pinned(ailp, type, flags, item_lsn); + + (*stuck)++; + ailp->ail_log_flush++; + break; + case XFS_ITEM_LOCKED: + XFS_STATS_INC(mp, xs_push_ail_locked); + trace_xfs_ail_locked(ailp, type, flags, item_lsn); + + (*stuck)++; + break; + default: + ASSERT(0); + break; + } +} + static long xfsaild_push( struct xfs_ail *ailp) @@ -505,62 +579,11 @@ xfsaild_push( lsn = lip->li_lsn; while ((XFS_LSN_CMP(lip->li_lsn, ailp->ail_target) <= 0)) { - int lock_result; if (test_bit(XFS_LI_FLUSHING, &lip->li_flags)) goto next_item; - /* - * Note that iop_push may unlock and reacquire the AIL lock. We - * rely on the AIL cursor implementation to be able to deal with - * the dropped lock. - */ - lock_result = xfsaild_push_item(ailp, lip); - switch (lock_result) { - case XFS_ITEM_SUCCESS: - XFS_STATS_INC(mp, xs_push_ail_success); - trace_xfs_ail_push(lip); - - ailp->ail_last_pushed_lsn = lsn; - break; - - case XFS_ITEM_FLUSHING: - /* - * The item or its backing buffer is already being - * flushed. The typical reason for that is that an - * inode buffer is locked because we already pushed the - * updates to it as part of inode clustering. - * - * We do not want to stop flushing just because lots - * of items are already being flushed, but we need to - * re-try the flushing relatively soon if most of the - * AIL is being flushed. - */ - XFS_STATS_INC(mp, xs_push_ail_flushing); - trace_xfs_ail_flushing(lip); - - flushing++; - ailp->ail_last_pushed_lsn = lsn; - break; - - case XFS_ITEM_PINNED: - XFS_STATS_INC(mp, xs_push_ail_pinned); - trace_xfs_ail_pinned(lip); - - stuck++; - ailp->ail_log_flush++; - break; - case XFS_ITEM_LOCKED: - XFS_STATS_INC(mp, xs_push_ail_locked); - trace_xfs_ail_locked(lip); - - stuck++; - break; - default: - ASSERT(0); - break; - } - + xfsaild_process_logitem(ailp, lip, &stuck, &flushing); count++; /* diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 8bbd4ec567f8..5ead3976d511 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -183,10 +183,9 @@ xfs_verify_iosize( min_not_zero(SZ_1M, me->me_max_io_size); BUILD_BUG_ON(BBSHIFT != SECTOR_SHIFT); - ASSERT(BBTOB(bbcount) >= bdev_logical_block_size(btp->bt_bdev)); + ASSERT(BBTOB(bbcount) >= btp->bt_logical_sectorsize); - return clamp(iosize, bdev_logical_block_size(btp->bt_bdev), - BBTOB(bbcount)); + return clamp(iosize, btp->bt_logical_sectorsize, BBTOB(bbcount)); } /* Allocate as much memory as we can get for verification buffer. */ @@ -218,8 +217,8 @@ xfs_verify_media_error( unsigned int bio_bbcount, blk_status_t bio_status) { - trace_xfs_verify_media_error(mp, me, btp->bt_bdev->bd_dev, daddr, - bio_bbcount, bio_status); + trace_xfs_verify_media_error(mp, me, btp->bt_dev, daddr, bio_bbcount, + bio_status); /* * Pass any error, I/O or otherwise, up to the caller if we didn't @@ -280,7 +279,7 @@ xfs_verify_media( btp = mp->m_ddev_targp; break; case XFS_DEV_LOG: - if (mp->m_logdev_targp->bt_bdev != mp->m_ddev_targp->bt_bdev) + if (mp->m_logdev_targp != mp->m_ddev_targp) btp = mp->m_logdev_targp; break; case XFS_DEV_RT: @@ -299,7 +298,7 @@ xfs_verify_media( /* start and end have to be aligned to the lba size */ if (!IS_ALIGNED(BBTOB(me->me_start_daddr | me->me_end_daddr), - bdev_logical_block_size(btp->bt_bdev))) + btp->bt_logical_sectorsize)) return -EINVAL; /* @@ -331,8 +330,7 @@ xfs_verify_media( if (!folio) return -ENOMEM; - trace_xfs_verify_media(mp, me, btp->bt_bdev->bd_dev, daddr, bbcount, - folio); + trace_xfs_verify_media(mp, me, btp->bt_dev, daddr, bbcount, folio); bio = bio_alloc(btp->bt_bdev, 1, REQ_OP_READ, GFP_KERNEL); if (!bio) { @@ -400,7 +398,7 @@ out_folio: * an operational error. */ me->me_start_daddr = daddr; - trace_xfs_verify_media_end(mp, me, btp->bt_bdev->bd_dev); + trace_xfs_verify_media_end(mp, me, btp->bt_dev); return 0; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index a735f16d9cd8..544213067d59 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -332,8 +332,8 @@ xfs_vn_listxattr( memset(&context, 0, sizeof(context)); context.dp = XFS_I(inode); context.resynch = 1; - context.buffer = size ? data : NULL; context.bufsize = size; + context.buffer = size ? data : NULL; context.firstu = context.bufsize; context.put_listent = xfs_xattr_put_listent; |