diff options
Diffstat (limited to 'fs')
60 files changed, 783 insertions, 385 deletions
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c index af3db0a7ae4da..7ea6f0b43b950 100644 --- a/fs/btrfs/bio.c +++ b/fs/btrfs/bio.c @@ -358,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio) INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work); queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work); } else { - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) btrfs_record_physical_zoned(bbio); btrfs_bio_end_io(bbio, bbio->bio.bi_status); } @@ -401,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio) else bio->bi_status = BLK_STS_OK; - if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status) + if (bio_is_zone_append(bio) && !bio->bi_status) stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; btrfs_bio_end_io(bbio, bbio->bio.bi_status); @@ -415,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio) if (bio->bi_status) { atomic_inc(&stripe->bioc->error); btrfs_log_dev_io_error(bio, stripe->dev); - } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) { + } else if (bio_is_zone_append(bio)) { stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; } @@ -652,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length) map_length = min(map_length, bbio->fs_info->max_zone_append_size); sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits, &nr_segs, map_length); - if (sector_offset) - return sector_offset << SECTOR_SHIFT; + if (sector_offset) { + /* + * bio_split_rw_at() could split at a size smaller than our + * sectorsize and thus cause unaligned I/Os. Fix that by + * always rounding down to the nearest boundary. + */ + return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize); + } return map_length; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 307dedf95c706..2c341956a01ce 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi } /* + * Return the generation this root started with. + * + * Every normal root that is created with root->root_key.offset set to it's + * originating generation. If it is a snapshot it is the generation when the + * snapshot was created. + * + * However for TREE_RELOC roots root_key.offset is the objectid of the owning + * tree root. Thankfully we copy the root item of the owning tree root, which + * has it's last_snapshot set to what we would have root_key.offset set to, so + * return that if this is a TREE_RELOC root. + */ +static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root) +{ + if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID) + return btrfs_root_last_snapshot(&root->root_item); + return root->root_key.offset; +} + +/* * Structure that conveys information about an extent that is going to replace * all the extents in a file range. */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index bd09dd3ad1a0a..3c6f7fecbb9aa 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control * * reference to it. */ generation = btrfs_node_ptr_generation(eb, slot); - if (!wc->update_ref || generation <= root->root_key.offset) + if (!wc->update_ref || generation <= btrfs_root_origin_generation(root)) return false; /* @@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans, goto reada; if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) + generation <= btrfs_root_origin_generation(root)) continue; /* We don't lock the tree block, it's OK to be racy here */ @@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans, * for the subtree */ if (wc->stage == UPDATE_BACKREF && - generation <= root->root_key.offset) { + generation <= btrfs_root_origin_generation(root)) { wc->lookup_info = 1; return 1; } diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 148d8cefa40ee..dfeee033f31fb 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf, dref_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_extent_data_ref_count(leaf, dref); break; /* Contains parent bytenr and ref count */ @@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf, inline_offset, fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data ref count, should have non-zero value"); + return -EUCLEAN; + } inline_refs += btrfs_shared_data_ref_count(leaf, sref); break; case BTRFS_EXTENT_OWNER_REF_KEY: @@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf, { u32 expect_item_size = 0; - if (key->type == BTRFS_SHARED_DATA_REF_KEY) + if (key->type == BTRFS_SHARED_DATA_REF_KEY) { + struct btrfs_shared_data_ref *sref; + + sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); + if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) { + extent_err(leaf, slot, + "invalid shared data backref count, should have non-zero value"); + return -EUCLEAN; + } + expect_item_size = sizeof(struct btrfs_shared_data_ref); + } if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) { generic_err(leaf, slot, @@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf, offset, leaf->fs_info->sectorsize); return -EUCLEAN; } + if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) { + extent_err(leaf, slot, + "invalid extent data backref count, should have non-zero value"); + return -EUCLEAN; + } } return 0; } diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 586446e02ef72..ec23da8405ff8 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -51,7 +51,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, * * VariableName-12345678-1234-1234-1234-1234567891bc */ -bool efivarfs_valid_name(const char *str, int len) +static bool efivarfs_valid_name(const char *str, int len) { const char *s = str + len - EFI_VARIABLE_GUID_LEN; diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index d71d2e08422f0..74f0602a9e016 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -60,7 +60,6 @@ bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; -extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, const struct inode *dir, int mode, dev_t dev, bool is_removable); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index a929f1b613be8..beba15673be8d 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -144,9 +144,6 @@ static int efivarfs_d_hash(const struct dentry *dentry, struct qstr *qstr) const unsigned char *s = qstr->name; unsigned int len = qstr->len; - if (!efivarfs_valid_name(s, len)) - return -EINVAL; - while (len-- > EFI_VARIABLE_GUID_LEN) hash = partial_name_hash(*s++, hash); diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 1c49f8962021f..0cd6b5c4df985 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -56,10 +56,10 @@ void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) buf->file = NULL; if (erofs_is_fileio_mode(sbi)) { - buf->file = sbi->fdev; /* some fs like FUSE needs it */ + buf->file = sbi->dif0.file; /* some fs like FUSE needs it */ buf->mapping = buf->file->f_mapping; } else if (erofs_is_fscache_mode(sb)) - buf->mapping = sbi->s_fscache->inode->i_mapping; + buf->mapping = sbi->dif0.fscache->inode->i_mapping; else buf->mapping = sb->s_bdev->bd_mapping; } @@ -179,19 +179,13 @@ out: } static void erofs_fill_from_devinfo(struct erofs_map_dev *map, - struct erofs_device_info *dif) + struct super_block *sb, struct erofs_device_info *dif) { + map->m_sb = sb; + map->m_dif = dif; map->m_bdev = NULL; - map->m_fp = NULL; - if (dif->file) { - if (S_ISBLK(file_inode(dif->file)->i_mode)) - map->m_bdev = file_bdev(dif->file); - else - map->m_fp = dif->file; - } - map->m_daxdev = dif->dax_dev; - map->m_dax_part_off = dif->dax_part_off; - map->m_fscache = dif->fscache; + if (dif->file && S_ISBLK(file_inode(dif->file)->i_mode)) + map->m_bdev = file_bdev(dif->file); } int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) @@ -201,12 +195,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) erofs_off_t startoff, length; int id; - map->m_bdev = sb->s_bdev; - map->m_daxdev = EROFS_SB(sb)->dax_dev; - map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; - map->m_fscache = EROFS_SB(sb)->s_fscache; - map->m_fp = EROFS_SB(sb)->fdev; - + erofs_fill_from_devinfo(map, sb, &EROFS_SB(sb)->dif0); + map->m_bdev = sb->s_bdev; /* use s_bdev for the primary device */ if (map->m_deviceid) { down_read(&devs->rwsem); dif = idr_find(&devs->tree, map->m_deviceid - 1); @@ -219,7 +209,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); up_read(&devs->rwsem); } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); @@ -232,7 +222,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - erofs_fill_from_devinfo(map, dif); + erofs_fill_from_devinfo(map, sb, dif); break; } } @@ -302,7 +292,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->offset = map.m_la; if (flags & IOMAP_DAX) - iomap->dax_dev = mdev.m_daxdev; + iomap->dax_dev = mdev.m_dif->dax_dev; else iomap->bdev = mdev.m_bdev; iomap->length = map.m_llen; @@ -331,7 +321,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->type = IOMAP_MAPPED; iomap->addr = mdev.m_pa; if (flags & IOMAP_DAX) - iomap->addr += mdev.m_dax_part_off; + iomap->addr += mdev.m_dif->dax_part_off; } return 0; } diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c index 3af96b1e2c2aa..33f8539dda4ae 100644 --- a/fs/erofs/fileio.c +++ b/fs/erofs/fileio.c @@ -9,6 +9,7 @@ struct erofs_fileio_rq { struct bio_vec bvecs[BIO_MAX_VECS]; struct bio bio; struct kiocb iocb; + struct super_block *sb; }; struct erofs_fileio { @@ -52,8 +53,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq) rq->iocb.ki_pos = rq->bio.bi_iter.bi_sector << SECTOR_SHIFT; rq->iocb.ki_ioprio = get_current_ioprio(); rq->iocb.ki_complete = erofs_fileio_ki_complete; - rq->iocb.ki_flags = (rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) ? - IOCB_DIRECT : 0; + if (test_opt(&EROFS_SB(rq->sb)->opt, DIRECT_IO) && + rq->iocb.ki_filp->f_mode & FMODE_CAN_ODIRECT) + rq->iocb.ki_flags = IOCB_DIRECT; iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt, rq->bio.bi_iter.bi_size); ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter); @@ -67,7 +69,8 @@ static struct erofs_fileio_rq *erofs_fileio_rq_alloc(struct erofs_map_dev *mdev) GFP_KERNEL | __GFP_NOFAIL); bio_init(&rq->bio, NULL, rq->bvecs, BIO_MAX_VECS, REQ_OP_READ); - rq->iocb.ki_filp = mdev->m_fp; + rq->iocb.ki_filp = mdev->m_dif->file; + rq->sb = mdev->m_sb; return rq; } diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index fda16eedafb57..ce3d8737df85d 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -198,7 +198,7 @@ struct bio *erofs_fscache_bio_alloc(struct erofs_map_dev *mdev) io = kmalloc(sizeof(*io), GFP_KERNEL | __GFP_NOFAIL); bio_init(&io->bio, NULL, io->bvecs, BIO_MAX_VECS, REQ_OP_READ); - io->io.private = mdev->m_fscache->cookie; + io->io.private = mdev->m_dif->fscache->cookie; io->io.end_io = erofs_fscache_bio_endio; refcount_set(&io->io.ref, 1); return &io->bio; @@ -316,7 +316,7 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_rq *req) if (!io) return -ENOMEM; iov_iter_xarray(&io->iter, ITER_DEST, &mapping->i_pages, pos, count); - ret = erofs_fscache_read_io_async(mdev.m_fscache->cookie, + ret = erofs_fscache_read_io_async(mdev.m_dif->fscache->cookie, mdev.m_pa + (pos - map.m_la), io); erofs_fscache_req_io_put(io); @@ -657,7 +657,7 @@ int erofs_fscache_register_fs(struct super_block *sb) if (IS_ERR(fscache)) return PTR_ERR(fscache); - sbi->s_fscache = fscache; + sbi->dif0.fscache = fscache; return 0; } @@ -665,14 +665,14 @@ void erofs_fscache_unregister_fs(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - erofs_fscache_unregister_cookie(sbi->s_fscache); + erofs_fscache_unregister_cookie(sbi->dif0.fscache); if (sbi->domain) erofs_fscache_domain_put(sbi->domain); else fscache_relinquish_volume(sbi->volume, NULL, false); - sbi->s_fscache = NULL; + sbi->dif0.fscache = NULL; sbi->volume = NULL; sbi->domain = NULL; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1c847c30a918f..686d835eb533a 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -107,6 +107,7 @@ struct erofs_xattr_prefix_item { }; struct erofs_sb_info { + struct erofs_device_info dif0; struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP /* list for all registered superblocks, mainly for shrinker */ @@ -124,13 +125,9 @@ struct erofs_sb_info { struct erofs_sb_lz4_info lz4; #endif /* CONFIG_EROFS_FS_ZIP */ - struct file *fdev; struct inode *packed_inode; struct erofs_dev_context *devs; - struct dax_device *dax_dev; - u64 dax_part_off; u64 total_blocks; - u32 primarydevice_blocks; u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR @@ -166,7 +163,6 @@ struct erofs_sb_info { /* fscache support */ struct fscache_volume *volume; - struct erofs_fscache *s_fscache; struct erofs_domain *domain; char *fsid; char *domain_id; @@ -180,6 +176,7 @@ struct erofs_sb_info { #define EROFS_MOUNT_POSIX_ACL 0x00000020 #define EROFS_MOUNT_DAX_ALWAYS 0x00000040 #define EROFS_MOUNT_DAX_NEVER 0x00000080 +#define EROFS_MOUNT_DIRECT_IO 0x00000100 #define clear_opt(opt, option) ((opt)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(opt, option) ((opt)->mount_opt |= EROFS_MOUNT_##option) @@ -187,7 +184,7 @@ struct erofs_sb_info { static inline bool erofs_is_fileio_mode(struct erofs_sb_info *sbi) { - return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->fdev; + return IS_ENABLED(CONFIG_EROFS_FS_BACKED_BY_FILE) && sbi->dif0.file; } static inline bool erofs_is_fscache_mode(struct super_block *sb) @@ -357,11 +354,9 @@ enum { }; struct erofs_map_dev { - struct erofs_fscache *m_fscache; + struct super_block *m_sb; + struct erofs_device_info *m_dif; struct block_device *m_bdev; - struct dax_device *m_daxdev; - struct file *m_fp; - u64 m_dax_part_off; erofs_off_t m_pa; unsigned int m_deviceid; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index c235a8e4315ea..f5956474bfdea 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -203,7 +203,7 @@ static int erofs_scan_devices(struct super_block *sb, struct erofs_device_info *dif; int id, err = 0; - sbi->total_blocks = sbi->primarydevice_blocks; + sbi->total_blocks = sbi->dif0.blocks; if (!erofs_sb_has_device_table(sbi)) ondisk_extradevs = 0; else @@ -307,7 +307,7 @@ static int erofs_read_superblock(struct super_block *sb) sbi->sb_size); goto out; } - sbi->primarydevice_blocks = le32_to_cpu(dsb->blocks); + sbi->dif0.blocks = le32_to_cpu(dsb->blocks); sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); @@ -364,14 +364,8 @@ static void erofs_default_options(struct erofs_sb_info *sbi) } enum { - Opt_user_xattr, - Opt_acl, - Opt_cache_strategy, - Opt_dax, - Opt_dax_enum, - Opt_device, - Opt_fsid, - Opt_domain_id, + Opt_user_xattr, Opt_acl, Opt_cache_strategy, Opt_dax, Opt_dax_enum, + Opt_device, Opt_fsid, Opt_domain_id, Opt_directio, Opt_err }; @@ -398,6 +392,7 @@ static const struct fs_parameter_spec erofs_fs_parameters[] = { fsparam_string("device", Opt_device), fsparam_string("fsid", Opt_fsid), fsparam_string("domain_id", Opt_domain_id), + fsparam_flag_no("directio", Opt_directio), {} }; @@ -511,6 +506,16 @@ static int erofs_fc_parse_param(struct fs_context *fc, errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; #endif + case Opt_directio: +#ifdef CONFIG_EROFS_FS_BACKED_BY_FILE + if (result.boolean) + set_opt(&sbi->opt, DIRECT_IO); + else + clear_opt(&sbi->opt, DIRECT_IO); +#else + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); +#endif + break; default: return -ENOPARAM; } @@ -602,9 +607,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return -EINVAL; } - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, - &sbi->dax_part_off, - NULL, NULL); + sbi->dif0.dax_dev = fs_dax_get_by_bdev(sb->s_bdev, + &sbi->dif0.dax_part_off, NULL, NULL); } err = erofs_read_superblock(sb); @@ -627,7 +631,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) } if (test_opt(&sbi->opt, DAX_ALWAYS)) { - if (!sbi->dax_dev) { + if (!sbi->dif0.dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); } else if (sbi->blkszbits != PAGE_SHIFT) { @@ -703,16 +707,18 @@ static int erofs_fc_get_tree(struct fs_context *fc) GET_TREE_BDEV_QUIET_LOOKUP : 0); #ifdef CONFIG_EROFS_FS_BACKED_BY_FILE if (ret == -ENOTBLK) { + struct file *file; + if (!fc->source) return invalf(fc, "No source specified"); - sbi->fdev = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); - if (IS_ERR(sbi->fdev)) - return PTR_ERR(sbi->fdev); + file = filp_open(fc->source, O_RDONLY | O_LARGEFILE, 0); + if (IS_ERR(file)) + return PTR_ERR(file); + sbi->dif0.file = file; - if (S_ISREG(file_inode(sbi->fdev)->i_mode) && - sbi->fdev->f_mapping->a_ops->read_folio) + if (S_ISREG(file_inode(sbi->dif0.file)->i_mode) && + sbi->dif0.file->f_mapping->a_ops->read_folio) return get_tree_nodev(fc, erofs_fc_fill_super); - fput(sbi->fdev); } #endif return ret; @@ -763,19 +769,24 @@ static void erofs_free_dev_context(struct erofs_dev_context *devs) kfree(devs); } -static void erofs_fc_free(struct fs_context *fc) +static void erofs_sb_free(struct erofs_sb_info *sbi) { - struct erofs_sb_info *sbi = fc->s_fs_info; - - if (!sbi) - return; - erofs_free_dev_context(sbi->devs); kfree(sbi->fsid); kfree(sbi->domain_id); + if (sbi->dif0.file) + fput(sbi->dif0.file); kfree(sbi); } +static void erofs_fc_free(struct fs_context *fc) +{ + struct erofs_sb_info *sbi = fc->s_fs_info; + + if (sbi) /* free here if an error occurs before transferring to sb */ + erofs_sb_free(sbi); +} + static const struct fs_context_operations erofs_context_ops = { .parse_param = erofs_fc_parse_param, .get_tree = erofs_fc_get_tree, @@ -809,19 +820,14 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi = EROFS_SB(sb); - if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || sbi->fdev) + if ((IS_ENABLED(CONFIG_EROFS_FS_ONDEMAND) && sbi->fsid) || + sbi->dif0.file) kill_anon_super(sb); else kill_block_super(sb); - - erofs_free_dev_context(sbi->devs); - fs_put_dax(sbi->dax_dev, NULL); + fs_put_dax(sbi->dif0.dax_dev, NULL); erofs_fscache_unregister_fs(sb); - kfree(sbi->fsid); - kfree(sbi->domain_id); - if (sbi->fdev) - fput(sbi->fdev); - kfree(sbi); + erofs_sb_free(sbi); sb->s_fs_info = NULL; } @@ -947,6 +953,8 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) seq_puts(seq, ",dax=always"); if (test_opt(opt, DAX_NEVER)) seq_puts(seq, ",dax=never"); + if (erofs_is_fileio_mode(sbi) && test_opt(opt, DIRECT_IO)) + seq_puts(seq, ",directio"); #ifdef CONFIG_EROFS_FS_ONDEMAND if (sbi->fsid) seq_printf(seq, ",fsid=%s", sbi->fsid); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 01f1475054874..19ef4ff2a1345 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1792,9 +1792,9 @@ drain_io: erofs_fscache_submit_bio(bio); else submit_bio(bio); - if (memstall) - psi_memstall_leave(&pflags); } + if (memstall) + psi_memstall_leave(&pflags); /* * although background is preferred, no one is pending for submission. diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index 75704f58ecfa9..0dd65cefce33e 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -230,9 +230,10 @@ void erofs_shrinker_unregister(struct super_block *sb) struct erofs_sb_info *const sbi = EROFS_SB(sb); mutex_lock(&sbi->umount_mutex); - /* clean up all remaining pclusters in memory */ - z_erofs_shrink_scan(sbi, ~0UL); - + while (!xa_empty(&sbi->managed_pslots)) { + z_erofs_shrink_scan(sbi, ~0UL); + cond_resched(); + } spin_lock(&erofs_sb_list_lock); list_del(&sbi->list); spin_unlock(&erofs_sb_list_lock); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index c9f9b6e979648..9d96b833015c8 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -2043,6 +2043,7 @@ exit_cifs(void) destroy_workqueue(decrypt_wq); destroy_workqueue(fileinfo_put_wq); destroy_workqueue(serverclose_wq); + destroy_workqueue(cfid_put_wq); destroy_workqueue(cifsiod_wq); cifs_proc_clean(); } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 668098d3b108e..f146e06c97eb6 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1947,6 +1947,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } + netfs_wait_for_outstanding_io(inode); cifs_close_deferred_file_under_dentry(tcon, full_path); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & @@ -2464,8 +2465,10 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, } cifs_close_deferred_file_under_dentry(tcon, from_name); - if (d_inode(target_dentry) != NULL) + if (d_inode(target_dentry) != NULL) { + netfs_wait_for_outstanding_io(d_inode(target_dentry)); cifs_close_deferred_file_under_dentry(tcon, to_name); + } rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 50b1aba200089..d88b41133e00c 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -676,7 +676,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf return -ENOMEM; symname_utf16_len = utf8s_to_utf16s(buf->PathBuffer, symname_utf8_len, UTF16_LITTLE_ENDIAN, - symname_utf16, symname_utf8_len * 2); + (wchar_t *) symname_utf16, symname_utf8_len * 2); if (symname_utf16_len < 0) { kfree(symname_utf16); return symname_utf16_len; diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 0bb77f9ec6861..3306fb6551368 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -488,11 +488,11 @@ cifs_ses_add_channel(struct cifs_ses *ses, if (iface->sockaddr.ss_family == AF_INET) cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI4)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv4->sin_addr); else cifs_dbg(FYI, "adding channel to ses %p (speed:%zu bps rdma:%s ip:%pI6)\n", - ses, iface->speed, iface->rdma_capable ? "yes" : "no", + ses, iface->speed, str_yes_no(iface->rdma_capable), &ipv6->sin6_addr); /* diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 1d1ffd0acaca2..2a5b4a96bf993 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -1016,6 +1016,8 @@ static int ksmbd_get_encryption_key(struct ksmbd_work *work, __u64 ses_id, ses_enc_key = enc ? sess->smb3encryptionkey : sess->smb3decryptionkey; + if (enc) + ksmbd_user_session_get(sess); memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); return 0; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index c14dd72e1b301..f8a40f65db6ae 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -70,7 +70,6 @@ struct ksmbd_conn *ksmbd_conn_alloc(void) atomic_set(&conn->req_running, 0); atomic_set(&conn->r_count, 0); atomic_set(&conn->refcnt, 1); - atomic_set(&conn->mux_smb_requests, 0); conn->total_credits = 1; conn->outstanding_credits = 0; @@ -120,8 +119,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; + atomic_inc(&conn->req_running); if (requests_queue) { - atomic_inc(&conn->req_running); spin_lock(&conn->request_lock); list_add_tail(&work->request_entry, requests_queue); spin_unlock(&conn->request_lock); @@ -132,11 +131,14 @@ void ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + atomic_dec(&conn->req_running); + if (waitqueue_active(&conn->req_running_q)) + wake_up(&conn->req_running_q); + if (list_empty(&work->request_entry) && list_empty(&work->async_request_entry)) return; - atomic_dec(&conn->req_running); spin_lock(&conn->request_lock); list_del_init(&work->request_entry); spin_unlock(&conn->request_lock); @@ -308,7 +310,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size, max_allowed_pdu_size; + unsigned int pdu_size, max_allowed_pdu_size, max_req; char hdr_buf[4] = {0,}; int size; @@ -318,6 +320,7 @@ int ksmbd_conn_handler_loop(void *p) if (t->ops->prepare && t->ops->prepare(t)) goto out; + max_req = server_conf.max_inflight_req; conn->last_active = jiffies; set_freezable(); while (ksmbd_conn_alive(conn)) { @@ -327,6 +330,13 @@ int ksmbd_conn_handler_loop(void *p) kvfree(conn->request_buf); conn->request_buf = NULL; +recheck: + if (atomic_read(&conn->req_running) + 1 > max_req) { + wait_event_interruptible(conn->req_running_q, + atomic_read(&conn->req_running) < max_req); + goto recheck; + } + size = t->ops->read(t, hdr_buf, sizeof(hdr_buf), -1); if (size != sizeof(hdr_buf)) break; diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 8ddd5a3c7bafb..b379ae4fdcdff 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -107,7 +107,6 @@ struct ksmbd_conn { __le16 signing_algorithm; bool binding; atomic_t refcnt; - atomic_t mux_smb_requests; }; struct ksmbd_conn_ops { diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index df92d746e89ca..71c6939dfbf13 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -263,8 +263,10 @@ struct ksmbd_session *ksmbd_session_lookup(struct ksmbd_conn *conn, down_read(&conn->session_lock); sess = xa_load(&conn->sessions, id); - if (sess) + if (sess) { sess->last_active = jiffies; + ksmbd_user_session_get(sess); + } up_read(&conn->session_lock); return sess; } @@ -275,6 +277,8 @@ struct ksmbd_session *ksmbd_session_lookup_slowpath(unsigned long long id) down_read(&sessions_table_lock); sess = __session_lookup(id); + if (sess) + ksmbd_user_session_get(sess); up_read(&sessions_table_lock); return sess; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 930d7566b52ef..601e7fcbcf1e6 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -241,14 +241,14 @@ send: if (work->tcon) ksmbd_tree_connect_put(work->tcon); smb3_preauth_hash_rsp(work); - if (work->sess) - ksmbd_user_session_put(work->sess); if (work->sess && work->sess->enc && work->encrypted && conn->ops->encrypt_resp) { rc = conn->ops->encrypt_resp(work); if (rc < 0) conn->ops->set_rsp_status(work, STATUS_DATA_ERROR); } + if (work->sess) + ksmbd_user_session_put(work->sess); ksmbd_conn_write(work); } @@ -270,7 +270,6 @@ static void handle_ksmbd_work(struct work_struct *wk) ksmbd_conn_try_dequeue_request(work); ksmbd_free_work_struct(work); - atomic_dec(&conn->mux_smb_requests); /* * Checking waitqueue to dropping pending requests on * disconnection. waitqueue_active is safe because it @@ -300,11 +299,6 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) if (err) return 0; - if (atomic_inc_return(&conn->mux_smb_requests) >= conn->vals->max_credits) { - atomic_dec_return(&conn->mux_smb_requests); - return -ENOSPC; - } - work = ksmbd_alloc_work_struct(); if (!work) { pr_err("allocation for work failed\n"); @@ -367,6 +361,7 @@ static int server_conf_init(void) server_conf.auth_mechs |= KSMBD_AUTH_KRB5 | KSMBD_AUTH_MSKRB5; #endif + server_conf.max_inflight_req = SMB2_MAX_CREDITS; return 0; } diff --git a/fs/smb/server/server.h b/fs/smb/server/server.h index 4fc529335271f..94187628ff089 100644 --- a/fs/smb/server/server.h +++ b/fs/smb/server/server.h @@ -42,6 +42,7 @@ struct ksmbd_server_config { struct smb_sid domain_sid; unsigned int auth_mechs; unsigned int max_connections; + unsigned int max_inflight_req; char *conf[SERVER_CONF_WORK_GROUP + 1]; struct task_struct *dh_task; diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4f539eeadbb0d..23e21845f9286 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -67,8 +67,10 @@ static inline bool check_session_id(struct ksmbd_conn *conn, u64 id) return false; sess = ksmbd_session_lookup_all(conn, id); - if (sess) + if (sess) { + ksmbd_user_session_put(sess); return true; + } pr_err("Invalid user session id: %llu\n", id); return false; } @@ -605,10 +607,8 @@ int smb2_check_user_session(struct ksmbd_work *work) /* Check for validity of user session */ work->sess = ksmbd_session_lookup_all(conn, sess_id); - if (work->sess) { - ksmbd_user_session_get(work->sess); + if (work->sess) return 1; - } ksmbd_debug(SMB, "Invalid user session, Uid %llu\n", sess_id); return -ENOENT; } @@ -1097,6 +1097,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) return rc; } + ksmbd_conn_lock(conn); smb2_buf_len = get_rfc1002_len(work->request_buf); smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); if (smb2_neg_size > smb2_buf_len) { @@ -1247,6 +1248,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) ksmbd_conn_set_need_negotiate(conn); err_out: + ksmbd_conn_unlock(conn); if (rc) rsp->hdr.Status = STATUS_INSUFFICIENT_RESOURCES; @@ -1701,29 +1703,35 @@ int smb2_sess_setup(struct ksmbd_work *work) if (conn->dialect != sess->dialect) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (!(req->hdr.Flags & SMB2_FLAGS_SIGNED)) { rc = -EINVAL; + ksmbd_user_session_put(sess); goto out_err; } if (strncmp(conn->ClientGUID, sess->ClientGUID, SMB2_CLIENT_GUID_SIZE)) { rc = -ENOENT; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_IN_PROGRESS) { rc = -EACCES; + ksmbd_user_session_put(sess); goto out_err; } if (sess->state == SMB2_SESSION_EXPIRED) { rc = -EFAULT; + ksmbd_user_session_put(sess); goto out_err; } + ksmbd_user_session_put(sess); if (ksmbd_conn_need_reconnect(conn)) { rc = -EFAULT; @@ -1731,7 +1739,8 @@ int smb2_sess_setup(struct ksmbd_work *work) goto out_err; } - if (ksmbd_session_lookup(conn, sess_id)) { + sess = ksmbd_session_lookup(conn, sess_id); + if (!sess) { rc = -EACCES; goto out_err; } @@ -1742,7 +1751,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = true; - ksmbd_user_session_get(sess); } else if ((conn->dialect < SMB30_PROT_ID || server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) && (req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { @@ -1769,7 +1777,6 @@ int smb2_sess_setup(struct ksmbd_work *work) } conn->binding = false; - ksmbd_user_session_get(sess); } work->sess = sess; @@ -2197,9 +2204,9 @@ err_out: int smb2_session_logoff(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_logoff_req *req; struct smb2_logoff_rsp *rsp; - struct ksmbd_session *sess; u64 sess_id; int err; @@ -2221,11 +2228,6 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_close_session_fds(work); ksmbd_conn_wait_idle(conn); - /* - * Re-lookup session to validate if session is deleted - * while waiting request complete - */ - sess = ksmbd_session_lookup_all(conn, sess_id); if (ksmbd_tree_conn_session_logoff(sess)) { ksmbd_debug(SMB, "Invalid tid %d\n", req->hdr.Id.SyncId.TreeId); rsp->hdr.Status = STATUS_NETWORK_NAME_DELETED; @@ -4228,6 +4230,7 @@ static bool __query_dir(struct dir_context *ctx, const char *name, int namlen, /* dot and dotdot entries are already reserved */ if (!strcmp(".", name) || !strcmp("..", name)) return true; + d_info->num_scan++; if (ksmbd_share_veto_filename(priv->work->tcon->share_conf, name)) return true; if (!match_pattern(name, namlen, priv->search_pattern)) @@ -4390,9 +4393,18 @@ int smb2_query_dir(struct ksmbd_work *work) query_dir_private.info_level = req->FileInformationClass; dir_fp->readdir_data.private = &query_dir_private; set_ctx_actor(&dir_fp->readdir_data.ctx, __query_dir); - +again: + d_info.num_scan = 0; rc = iterate_dir(dir_fp->filp, &dir_fp->readdir_data.ctx); /* + * num_entry can be 0 if the directory iteration stops before reaching + * the end of the directory and no file is matched with the search + * pattern. + */ + if (rc >= 0 && !d_info.num_entry && d_info.num_scan && + d_info.out_buf_len > 0) + goto again; + /* * req->OutputBufferLength is too small to contain even one entry. * In this case, it immediately returns OutputBufferLength 0 to client. */ @@ -6016,15 +6028,13 @@ static int set_file_basic_info(struct ksmbd_file *fp, attrs.ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); } - attrs.ia_valid |= ATTR_CTIME; if (file_info->ChangeTime) - attrs.ia_ctime = ksmbd_NTtimeToUnix(file_info->ChangeTime); - else - attrs.ia_ctime = inode_get_ctime(inode); + inode_set_ctime_to_ts(inode, + ksmbd_NTtimeToUnix(file_info->ChangeTime)); if (file_info->LastWriteTime) { attrs.ia_mtime = ksmbd_NTtimeToUnix(file_info->LastWriteTime); - attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); + attrs.ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET | ATTR_CTIME); } if (file_info->Attributes) { @@ -6066,8 +6076,6 @@ static int set_file_basic_info(struct ksmbd_file *fp, return -EACCES; inode_lock(inode); - inode_set_ctime_to_ts(inode, attrs.ia_ctime); - attrs.ia_valid &= ~ATTR_CTIME; rc = notify_change(idmap, dentry, &attrs, NULL); inode_unlock(inode); } @@ -8982,6 +8990,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) le64_to_cpu(tr_hdr->SessionId)); return -ECONNABORTED; } + ksmbd_user_session_put(sess); iov[0].iov_base = buf; iov[0].iov_len = sizeof(struct smb2_transform_hdr) + 4; diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 48cda3350e5a2..befaf42b84cc3 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -319,8 +319,11 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) init_smb2_max_write_size(req->smb2_max_write); if (req->smb2_max_trans) init_smb2_max_trans_size(req->smb2_max_trans); - if (req->smb2_max_credits) + if (req->smb2_max_credits) { init_smb2_max_credits(req->smb2_max_credits); + server_conf.max_inflight_req = + req->smb2_max_credits; + } if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); diff --git a/fs/smb/server/vfs.h b/fs/smb/server/vfs.h index cb76f4b5bafe8..06903024a2d88 100644 --- a/fs/smb/server/vfs.h +++ b/fs/smb/server/vfs.h @@ -43,6 +43,7 @@ struct ksmbd_dir_info { char *rptr; int name_len; int out_buf_len; + int num_scan; int num_entry; int data_count; int last_entry_offset; diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 2b5fc5fd16435..68ee1c299c25f 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -3557,14 +3557,31 @@ xfs_btree_insrec( xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS); /* - * If we just inserted into a new tree block, we have to - * recalculate nkey here because nkey is out of date. + * Update btree keys to reflect the newly added record or keyptr. + * There are three cases here to be aware of. Normally, all we have to + * do is walk towards the root, updating keys as necessary. * - * Otherwise we're just updating an existing block (having shoved - * some records into the new tree block), so use the regular key - * update mechanism. + * If the caller had us target a full block for the insertion, we dealt + * with that by calling the _make_block_unfull function. If the + * "make unfull" function splits the block, it'll hand us back the key + * and pointer of the new block. We haven't yet added the new block to + * the next level up, so if we decide to add the new record to the new + * block (bp->b_bn != old_bn), we have to update the caller's pointer + * so that the caller adds the new block with the correct key. + * + * However, there is a third possibility-- if the selected block is the + * root block of an inode-rooted btree and cannot be expanded further, + * the "make unfull" function moves the root block contents to a new + * block and updates the root block to point to the new block. In this + * case, no block pointer is passed back because the block has already + * been added to the btree. In this case, we need to use the regular + * key update function, just like the first case. This is critical for + * overlapping btrees, because the high key must be updated to reflect + * the entire tree, not just the subtree accessible through the first + * child of the root (which is now two levels down from the root). */ - if (bp && xfs_buf_daddr(bp) != old_bn) { + if (!xfs_btree_ptr_is_null(cur, &nptr) && + bp && xfs_buf_daddr(bp) != old_bn) { xfs_btree_get_keys(cur, block, lkey); } else if (xfs_btree_needs_key_update(cur, optr)) { error = xfs_btree_update_keys(cur, level); @@ -5144,7 +5161,7 @@ xfs_btree_count_blocks_helper( int level, void *data) { - xfs_extlen_t *blocks = data; + xfs_filblks_t *blocks = data; (*blocks)++; return 0; @@ -5154,7 +5171,7 @@ xfs_btree_count_blocks_helper( int xfs_btree_count_blocks( struct xfs_btree_cur *cur, - xfs_extlen_t *blocks) + xfs_filblks_t *blocks) { *blocks = 0; return xfs_btree_visit_blocks(cur, xfs_btree_count_blocks_helper, diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 3b739459ebb0f..c5bff273cae25 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -484,7 +484,7 @@ typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level, int xfs_btree_visit_blocks(struct xfs_btree_cur *cur, xfs_btree_visit_blocks_fn fn, unsigned int flags, void *data); -int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks); +int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_filblks_t *blocks); union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n, struct xfs_btree_block *block); diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 9b34896dd1a32..6f270d8f4270c 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -744,6 +744,7 @@ xfs_finobt_count_blocks( { struct xfs_buf *agbp = NULL; struct xfs_btree_cur *cur; + xfs_filblks_t blocks; int error; error = xfs_ialloc_read_agi(pag, tp, 0, &agbp); @@ -751,9 +752,10 @@ xfs_finobt_count_blocks( return error; cur = xfs_finobt_init_cursor(pag, tp, agbp); - error = xfs_btree_count_blocks(cur, tree_blocks); + error = xfs_btree_count_blocks(cur, &blocks); xfs_btree_del_cursor(cur, error); xfs_trans_brelse(tp, agbp); + *tree_blocks = blocks; return error; } diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index e74bb059f24fa..4f3bfc884aff2 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -496,7 +496,7 @@ xfs_rtginode_create( error = xfs_metadir_create(&upd, S_IFREG); if (error) - return error; + goto out_cancel; xfs_rtginode_lockdep_setup(upd.ip, rtg_rgno(rtg), type); diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a809513a290cf..3b5623611eba0 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -494,12 +494,13 @@ xfs_validate_sb_common( return -EINVAL; } - if (!sbp->sb_spino_align || - sbp->sb_spino_align > sbp->sb_inoalignmt || - (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0) { + if (sbp->sb_spino_align && + (sbp->sb_spino_align > sbp->sb_inoalignmt || + (sbp->sb_inoalignmt % sbp->sb_spino_align) != 0)) { xfs_warn(mp, - "Sparse inode alignment (%u) is invalid.", - sbp->sb_spino_align); +"Sparse inode alignment (%u) is invalid, must be integer factor of (%u).", + sbp->sb_spino_align, + sbp->sb_inoalignmt); return -EINVAL; } } else if (sbp->sb_spino_align) { diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c index f228127a88ff2..fb47a76ead18c 100644 --- a/fs/xfs/libxfs/xfs_symlink_remote.c +++ b/fs/xfs/libxfs/xfs_symlink_remote.c @@ -92,8 +92,10 @@ xfs_symlink_verify( struct xfs_mount *mp = bp->b_mount; struct xfs_dsymlink_hdr *dsl = bp->b_addr; + /* no verification of non-crc buffers */ if (!xfs_has_crc(mp)) - return __this_address; + return NULL; + if (!xfs_verify_magic(bp, dsl->sl_magic)) return __this_address; if (!uuid_equal(&dsl->sl_uuid, &mp->m_sb.sb_meta_uuid)) diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c index 61f80a6410c73..9f8c312dfd3c8 100644 --- a/fs/xfs/scrub/agheader.c +++ b/fs/xfs/scrub/agheader.c @@ -60,6 +60,32 @@ xchk_superblock_xref( } /* + * Calculate the ondisk superblock size in bytes given the feature set of the + * mounted filesystem (aka the primary sb). This is subtlely different from + * the logic in xfs_repair, which computes the size of a secondary sb given the + * featureset listed in the secondary sb. + */ +STATIC size_t +xchk_superblock_ondisk_size( + struct xfs_mount *mp) +{ + if (xfs_has_metadir(mp)) + return offsetofend(struct xfs_dsb, sb_pad); + if (xfs_has_metauuid(mp)) + return offsetofend(struct xfs_dsb, sb_meta_uuid); + if (xfs_has_crc(mp)) + return offsetofend(struct xfs_dsb, sb_lsn); + if (xfs_sb_version_hasmorebits(&mp->m_sb)) + return offsetofend(struct xfs_dsb, sb_bad_features2); + if (xfs_has_logv2(mp)) + return offsetofend(struct xfs_dsb, sb_logsunit); + if (xfs_has_sector(mp)) + return offsetofend(struct xfs_dsb, sb_logsectsize); + /* only support dirv2 or more recent */ + return offsetofend(struct xfs_dsb, sb_dirblklog); +} + +/* * Scrub the filesystem superblock. * * Note: We do /not/ attempt to check AG 0's superblock. Mount is @@ -75,6 +101,7 @@ xchk_superblock( struct xfs_buf *bp; struct xfs_dsb *sb; struct xfs_perag *pag; + size_t sblen; xfs_agnumber_t agno; uint32_t v2_ok; __be32 features_mask; @@ -145,8 +172,11 @@ xchk_superblock( xchk_block_set_preen(sc, bp); if (xfs_has_metadir(sc->mp)) { - if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) - xchk_block_set_preen(sc, bp); + if (sb->sb_rbmino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rsumino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); } else { if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino)) xchk_block_set_preen(sc, bp); @@ -229,7 +259,13 @@ xchk_superblock( * sb_icount, sb_ifree, sb_fdblocks, sb_frexents */ - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_uquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + + if (sb->sb_gquotino != cpu_to_be64(0)) + xchk_block_set_preen(sc, bp); + } else { if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino)) xchk_block_set_preen(sc, bp); @@ -281,15 +317,8 @@ xchk_superblock( if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok))) xchk_block_set_corrupt(sc, bp); - if (xfs_has_metadir(mp)) { - if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) - xchk_block_set_corrupt(sc, bp); - if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) - xchk_block_set_preen(sc, bp); - } else { - if (sb->sb_features2 != sb->sb_bad_features2) - xchk_block_set_preen(sc, bp); - } + if (sb->sb_features2 != sb->sb_bad_features2) + xchk_block_set_preen(sc, bp); } /* Check sb_features2 flags that are set at mkfs time. */ @@ -351,7 +380,10 @@ xchk_superblock( if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align)) xchk_block_set_corrupt(sc, bp); - if (!xfs_has_metadir(mp)) { + if (xfs_has_metadir(mp)) { + if (sb->sb_pquotino != cpu_to_be64(0)) + xchk_block_set_corrupt(sc, bp); + } else { if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino)) xchk_block_set_preen(sc, bp); } @@ -366,16 +398,25 @@ xchk_superblock( } if (xfs_has_metadir(mp)) { + if (sb->sb_metadirino != cpu_to_be64(mp->m_sb.sb_metadirino)) + xchk_block_set_preen(sc, bp); + if (sb->sb_rgcount != cpu_to_be32(mp->m_sb.sb_rgcount)) xchk_block_set_corrupt(sc, bp); if (sb->sb_rgextents != cpu_to_be32(mp->m_sb.sb_rgextents)) xchk_block_set_corrupt(sc, bp); + + if (sb->sb_rgblklog != mp->m_sb.sb_rgblklog) + xchk_block_set_corrupt(sc, bp); + + if (memchr_inv(sb->sb_pad, 0, sizeof(sb->sb_pad))) + xchk_block_set_corrupt(sc, bp); } /* Everything else must be zero. */ - if (memchr_inv(sb + 1, 0, - BBTOB(bp->b_length) - sizeof(struct xfs_dsb))) + sblen = xchk_superblock_ondisk_size(mp); + if (memchr_inv((char *)sb + sblen, 0, BBTOB(bp->b_length) - sblen)) xchk_block_set_corrupt(sc, bp); xchk_superblock_xref(sc, bp); @@ -458,7 +499,7 @@ xchk_agf_xref_btreeblks( { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; struct xfs_mount *mp = sc->mp; - xfs_agblock_t blocks; + xfs_filblks_t blocks; xfs_agblock_t btreeblks; int error; @@ -507,7 +548,7 @@ xchk_agf_xref_refcblks( struct xfs_scrub *sc) { struct xfs_agf *agf = sc->sa.agf_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; if (!sc->sa.refc_cur) @@ -840,7 +881,7 @@ xchk_agi_xref_fiblocks( struct xfs_scrub *sc) { struct xfs_agi *agi = sc->sa.agi_bp->b_addr; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error = 0; if (!xfs_has_inobtcounts(sc->mp)) diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c index 0fad0baaba2f6..b45d2b32051a6 100644 --- a/fs/xfs/scrub/agheader_repair.c +++ b/fs/xfs/scrub/agheader_repair.c @@ -256,7 +256,7 @@ xrep_agf_calc_from_btrees( struct xfs_agf *agf = agf_bp->b_addr; struct xfs_mount *mp = sc->mp; xfs_agblock_t btreeblks; - xfs_agblock_t blocks; + xfs_filblks_t blocks; int error; /* Update the AGF counters from the bnobt. */ @@ -946,7 +946,7 @@ xrep_agi_calc_from_btrees( if (error) goto err; if (xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; error = xfs_btree_count_blocks(cur, &blocks); if (error) @@ -959,7 +959,7 @@ xrep_agi_calc_from_btrees( agi->agi_freecount = cpu_to_be32(freecount); if (xfs_has_finobt(mp) && xfs_has_inobtcounts(mp)) { - xfs_agblock_t blocks; + xfs_filblks_t blocks; cur = xfs_finobt_init_cursor(sc->sa.pag, sc->tp, agi_bp); error = xfs_btree_count_blocks(cur, &blocks); diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c index 4a50f8e000409..ca23cf4db6c5e 100644 --- a/fs/xfs/scrub/fscounters.c +++ b/fs/xfs/scrub/fscounters.c @@ -261,7 +261,7 @@ xchk_fscount_btreeblks( struct xchk_fscounters *fsc, xfs_agnumber_t agno) { - xfs_extlen_t blocks; + xfs_filblks_t blocks; int error; error = xchk_ag_init_existing(sc, agno, &sc->sa); diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c index ce86bdad37fa4..ccc6ca5934ca6 100644 --- a/fs/xfs/scrub/health.c +++ b/fs/xfs/scrub/health.c @@ -71,7 +71,8 @@ /* Map our scrub type to a sick mask and a set of health update functions. */ enum xchk_health_group { - XHG_FS = 1, + XHG_NONE = 1, + XHG_FS, XHG_AG, XHG_INO, XHG_RTGROUP, @@ -83,6 +84,7 @@ struct xchk_health_map { }; static const struct xchk_health_map type_to_health_flag[XFS_SCRUB_TYPE_NR] = { + [XFS_SCRUB_TYPE_PROBE] = { XHG_NONE, 0 }, [XFS_SCRUB_TYPE_SB] = { XHG_AG, XFS_SICK_AG_SB }, [XFS_SCRUB_TYPE_AGF] = { XHG_AG, XFS_SICK_AG_AGF }, [XFS_SCRUB_TYPE_AGFL] = { XHG_AG, XFS_SICK_AG_AGFL }, @@ -133,7 +135,7 @@ xchk_mark_healthy_if_clean( { if (!(sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT))) - sc->sick_mask |= mask; + sc->healthy_mask |= mask; } /* @@ -189,6 +191,7 @@ xchk_update_health( { struct xfs_perag *pag; struct xfs_rtgroup *rtg; + unsigned int mask = sc->sick_mask; bool bad; /* @@ -203,50 +206,56 @@ xchk_update_health( return; } - if (!sc->sick_mask) - return; - bad = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT | XFS_SCRUB_OFLAG_XCORRUPT)); + if (!bad) + mask |= sc->healthy_mask; switch (type_to_health_flag[sc->sm->sm_type].group) { + case XHG_NONE: + break; case XHG_AG: + if (!mask) + return; pag = xfs_perag_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(pag_group(pag), sc->sick_mask); + xfs_group_mark_corrupt(pag_group(pag), mask); else - xfs_group_mark_healthy(pag_group(pag), sc->sick_mask); + xfs_group_mark_healthy(pag_group(pag), mask); xfs_perag_put(pag); break; case XHG_INO: if (!sc->ip) return; - if (bad) { - unsigned int mask = sc->sick_mask; - - /* - * If we're coming in for repairs then we don't want - * sickness flags to propagate to the incore health - * status if the inode gets inactivated before we can - * fix it. - */ - if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) - mask |= XFS_SICK_INO_FORGET; + /* + * If we're coming in for repairs then we don't want sickness + * flags to propagate to the incore health status if the inode + * gets inactivated before we can fix it. + */ + if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) + mask |= XFS_SICK_INO_FORGET; + if (!mask) + return; + if (bad) xfs_inode_mark_corrupt(sc->ip, mask); - } else - xfs_inode_mark_healthy(sc->ip, sc->sick_mask); + else + xfs_inode_mark_healthy(sc->ip, mask); break; case XHG_FS: + if (!mask) + return; if (bad) - xfs_fs_mark_corrupt(sc->mp, sc->sick_mask); + xfs_fs_mark_corrupt(sc->mp, mask); else - xfs_fs_mark_healthy(sc->mp, sc->sick_mask); + xfs_fs_mark_healthy(sc->mp, mask); break; case XHG_RTGROUP: + if (!mask) + return; rtg = xfs_rtgroup_get(sc->mp, sc->sm->sm_agno); if (bad) - xfs_group_mark_corrupt(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_corrupt(rtg_group(rtg), mask); else - xfs_group_mark_healthy(rtg_group(rtg), sc->sick_mask); + xfs_group_mark_healthy(rtg_group(rtg), mask); xfs_rtgroup_put(rtg); break; default: diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index abad54c3621d4..4dc7c83dc08a4 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -650,8 +650,8 @@ xchk_iallocbt_xref_rmap_btreeblks( struct xfs_scrub *sc) { xfs_filblks_t blocks; - xfs_extlen_t inobt_blocks = 0; - xfs_extlen_t finobt_blocks = 0; + xfs_filblks_t inobt_blocks = 0; + xfs_filblks_t finobt_blocks = 0; int error; if (!sc->sa.ino_cur || !sc->sa.rmap_cur || diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c index b78db65134651..c678cba1ffc3f 100644 --- a/fs/xfs/scrub/metapath.c +++ b/fs/xfs/scrub/metapath.c @@ -171,23 +171,13 @@ static int xchk_setup_metapath_quotadir( struct xfs_scrub *sc) { - struct xfs_trans *tp; - struct xfs_inode *dp = NULL; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; - error = xfs_dqinode_load_parent(tp, &dp); - xfs_trans_cancel(tp); - if (error) - return error; + if (!qi || !qi->qi_dirip) + return -ENOENT; - error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, - kasprintf(GFP_KERNEL, "quota"), dp); - xfs_irele(dp); - return error; + return xchk_setup_metapath_scan(sc, sc->mp->m_metadirip, + kstrdup("quota", GFP_KERNEL), qi->qi_dirip); } /* Scan a quota inode under the /quota directory. */ @@ -196,37 +186,31 @@ xchk_setup_metapath_dqinode( struct xfs_scrub *sc, xfs_dqtype_t type) { - struct xfs_trans *tp = NULL; - struct xfs_inode *dp = NULL; + struct xfs_quotainfo *qi = sc->mp->m_quotainfo; struct xfs_inode *ip = NULL; - const char *path; - int error; - - error = xfs_trans_alloc_empty(sc->mp, &tp); - if (error) - return error; - error = xfs_dqinode_load_parent(tp, &dp); - if (error) - goto out_cancel; - - error = xfs_dqinode_load(tp, dp, type, &ip); - if (error) - goto out_dp; - - xfs_trans_cancel(tp); - tp = NULL; + if (!qi) + return -ENOENT; - path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type)); - error = xchk_setup_metapath_scan(sc, dp, path, ip); + switch (type) { + case XFS_DQTYPE_USER: + ip = qi->qi_uquotaip; + break; + case XFS_DQTYPE_GROUP: + ip = qi->qi_gquotaip; + break; + case XFS_DQTYPE_PROJ: + ip = qi->qi_pquotaip; + break; + default: + ASSERT(0); + return -EINVAL; + } + if (!ip) + return -ENOENT; - xfs_irele(ip); -out_dp: - xfs_irele(dp); -out_cancel: - if (tp) - xfs_trans_cancel(tp); - return error; + return xchk_setup_metapath_scan(sc, qi->qi_dirip, + kstrdup(xfs_dqinode_path(type), GFP_KERNEL), ip); } #else # define xchk_setup_metapath_quotadir(...) (-ENOENT) diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index 2b6be75e94241..1c5e45cc64190 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -491,7 +491,7 @@ xchk_refcount_xref_rmap( struct xfs_scrub *sc, xfs_filblks_t cow_blocks) { - xfs_extlen_t refcbt_blocks = 0; + xfs_filblks_t refcbt_blocks = 0; xfs_filblks_t blocks; int error; diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h index a7fda3e2b0137..5dbbe93cb49bf 100644 --- a/fs/xfs/scrub/scrub.h +++ b/fs/xfs/scrub/scrub.h @@ -184,6 +184,12 @@ struct xfs_scrub { */ unsigned int sick_mask; + /* + * Clear these XFS_SICK_* flags but only if the scan is ok. Useful for + * removing ZAPPED flags after a repair. + */ + unsigned int healthy_mask; + /* next time we want to cond_resched() */ struct xchk_relax relax; diff --git a/fs/xfs/scrub/symlink_repair.c b/fs/xfs/scrub/symlink_repair.c index d015a86ef460f..953ce7be78dc2 100644 --- a/fs/xfs/scrub/symlink_repair.c +++ b/fs/xfs/scrub/symlink_repair.c @@ -36,6 +36,7 @@ #include "scrub/tempfile.h" #include "scrub/tempexch.h" #include "scrub/reap.h" +#include "scrub/health.h" /* * Symbolic Link Repair @@ -233,7 +234,7 @@ xrep_symlink_salvage( * target zapped flag. */ if (buflen == 0) { - sc->sick_mask |= XFS_SICK_INO_SYMLINK_ZAPPED; + xchk_mark_healthy_if_clean(sc, XFS_SICK_INO_SYMLINK_ZAPPED); sprintf(target_buf, DUMMY_TARGET); } diff --git a/fs/xfs/scrub/tempfile.c b/fs/xfs/scrub/tempfile.c index 4b7f7860e37ec..2d7ca7e1bbca0 100644 --- a/fs/xfs/scrub/tempfile.c +++ b/fs/xfs/scrub/tempfile.c @@ -184,11 +184,18 @@ out_release_dquots: } /* + * Move sc->tempip from the regular directory tree to the metadata directory + * tree if sc->ip is part of the metadata directory tree and tempip has an + * eligible file mode. + * * Temporary files have to be created before we even know which inode we're * going to scrub, so we assume that they will be part of the regular directory * tree. If it turns out that we're actually scrubbing a file from the * metadata directory tree, we have to subtract the temp file from the root - * dquots and detach the dquots. + * dquots and detach the dquots prior to setting the METADATA iflag. However, + * the scrub setup functions grab sc->ip and create sc->tempip before we + * actually get around to checking if the file mode is the right type for the + * scrubber. */ int xrep_tempfile_adjust_directory_tree( @@ -204,6 +211,9 @@ xrep_tempfile_adjust_directory_tree( if (!sc->ip || !xfs_is_metadir_inode(sc->ip)) return 0; + if (!S_ISDIR(VFS_I(sc->tempip)->i_mode) && + !S_ISREG(VFS_I(sc->tempip)->i_mode)) + return 0; xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -223,6 +233,7 @@ xrep_tempfile_adjust_directory_tree( if (error) goto out_ilock; + xfs_iflags_set(sc->tempip, XFS_IRECOVERY); xfs_qm_dqdetach(sc->tempip); out_ilock: xrep_tempfile_iunlock(sc); @@ -246,6 +257,8 @@ xrep_tempfile_remove_metadir( ASSERT(sc->tp == NULL); + xfs_iflags_clear(sc->tempip, XFS_IRECOVERY); + xfs_ilock(sc->tempip, XFS_IOLOCK_EXCL); sc->temp_ilock_flags |= XFS_IOLOCK_EXCL; @@ -945,10 +958,13 @@ xrep_is_tempfile( /* * Files in the metadata directory tree also have S_PRIVATE set and - * IOP_XATTR unset, so we must distinguish them separately. + * IOP_XATTR unset, so we must distinguish them separately. We (ab)use + * the IRECOVERY flag to mark temporary metadir inodes knowing that the + * end of log recovery clears IRECOVERY, so the only ones that can + * exist during online repair are the ones we create. */ if (xfs_has_metadir(mp) && (ip->i_diflags2 & XFS_DIFLAG2_METADATA)) - return false; + return __xfs_iflags_test(ip, XFS_IRECOVERY); if (IS_PRIVATE(inode) && !(inode->i_opflags & IOP_XATTR)) return true; diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h index 9b38f5ad1eaf0..d2ae7e93acb08 100644 --- a/fs/xfs/scrub/trace.h +++ b/fs/xfs/scrub/trace.h @@ -605,7 +605,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error, TP_fast_assign( xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level); __entry->dev = sc->mp->m_super->s_dev; - __entry->ino = sc->ip->i_ino; + __entry->ino = cur->bc_ino.ip->i_ino; __entry->whichfork = cur->bc_ino.whichfork; __entry->type = sc->sm->sm_type; __assign_str(name); diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a59bbe767a7dc..0836fea2d6d81 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -103,7 +103,7 @@ xfs_bmap_count_blocks( struct xfs_mount *mp = ip->i_mount; struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork); struct xfs_btree_cur *cur; - xfs_extlen_t btblocks = 0; + xfs_filblks_t btblocks = 0; int error; *nextents = 0; diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c index ff982d983989b..f11d475898f28 100644 --- a/fs/xfs/xfs_dquot.c +++ b/fs/xfs/xfs_dquot.c @@ -69,6 +69,30 @@ xfs_dquot_mark_sick( } /* + * Detach the dquot buffer if it's still attached, because we can get called + * through dqpurge after a log shutdown. Caller must hold the dqflock or have + * otherwise isolated the dquot. + */ +void +xfs_dquot_detach_buf( + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_buf *bp = NULL; + + spin_lock(&qlip->qli_lock); + if (qlip->qli_item.li_buf) { + bp = qlip->qli_item.li_buf; + qlip->qli_item.li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) { + list_del_init(&qlip->qli_item.li_bio_list); + xfs_buf_rele(bp); + } +} + +/* * This is called to free all the memory associated with a dquot */ void @@ -76,6 +100,7 @@ xfs_qm_dqdestroy( struct xfs_dquot *dqp) { ASSERT(list_empty(&dqp->q_lru)); + ASSERT(dqp->q_logitem.qli_item.li_buf == NULL); kvfree(dqp->q_logitem.qli_item.li_lv_shadow); mutex_destroy(&dqp->q_qlock); @@ -1142,9 +1167,11 @@ static void xfs_qm_dqflush_done( struct xfs_log_item *lip) { - struct xfs_dq_logitem *qip = (struct xfs_dq_logitem *)lip; - struct xfs_dquot *dqp = qip->qli_dquot; + struct xfs_dq_logitem *qlip = + container_of(lip, struct xfs_dq_logitem, qli_item); + struct xfs_dquot *dqp = qlip->qli_dquot; struct xfs_ail *ailp = lip->li_ailp; + struct xfs_buf *bp = NULL; xfs_lsn_t tail_lsn; /* @@ -1156,12 +1183,12 @@ xfs_qm_dqflush_done( * holding the lock before removing the dquot from the AIL. */ if (test_bit(XFS_LI_IN_AIL, &lip->li_flags) && - ((lip->li_lsn == qip->qli_flush_lsn) || + (lip->li_lsn == qlip->qli_flush_lsn || test_bit(XFS_LI_FAILED, &lip->li_flags))) { spin_lock(&ailp->ail_lock); xfs_clear_li_failed(lip); - if (lip->li_lsn == qip->qli_flush_lsn) { + if (lip->li_lsn == qlip->qli_flush_lsn) { /* xfs_ail_update_finish() drops the AIL lock */ tail_lsn = xfs_ail_delete_one(ailp, lip); xfs_ail_update_finish(ailp, tail_lsn); @@ -1171,6 +1198,20 @@ xfs_qm_dqflush_done( } /* + * If this dquot hasn't been dirtied since initiating the last dqflush, + * release the buffer reference. We already unlinked this dquot item + * from the buffer. + */ + spin_lock(&qlip->qli_lock); + if (!qlip->qli_dirty) { + bp = lip->li_buf; + lip->li_buf = NULL; + } + spin_unlock(&qlip->qli_lock); + if (bp) + xfs_buf_rele(bp); + + /* * Release the dq's flush lock since we're done with it. */ xfs_dqfunlock(dqp); @@ -1196,7 +1237,7 @@ xfs_buf_dquot_io_fail( spin_lock(&bp->b_mount->m_ail->ail_lock); list_for_each_entry(lip, &bp->b_li_list, li_bio_list) - xfs_set_li_failed(lip, bp); + set_bit(XFS_LI_FAILED, &lip->li_flags); spin_unlock(&bp->b_mount->m_ail->ail_lock); } @@ -1239,6 +1280,111 @@ xfs_qm_dqflush_check( } /* + * Get the buffer containing the on-disk dquot. + * + * Requires dquot flush lock, will clear the dirty flag, delete the quota log + * item from the AIL, and shut down the system if something goes wrong. + */ +static int +xfs_dquot_read_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_mount *mp = dqp->q_mount; + struct xfs_buf *bp = NULL; + int error; + + error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen, 0, + &bp, &xfs_dquot_buf_ops); + if (xfs_metadata_is_sick(error)) + xfs_dquot_mark_sick(dqp); + if (error) + goto out_abort; + + *bpp = bp; + return 0; + +out_abort: + dqp->q_flags &= ~XFS_DQFLAG_DIRTY; + xfs_trans_ail_delete(&dqp->q_logitem.qli_item, 0); + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; +} + +/* + * Attach a dquot buffer to this dquot to avoid allocating a buffer during a + * dqflush, since dqflush can be called from reclaim context. + */ +int +xfs_dquot_attach_buf( + struct xfs_trans *tp, + struct xfs_dquot *dqp) +{ + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; + int error; + + spin_lock(&qlip->qli_lock); + if (!lip->li_buf) { + struct xfs_buf *bp = NULL; + + spin_unlock(&qlip->qli_lock); + error = xfs_dquot_read_buf(tp, dqp, &bp); + if (error) + return error; + + /* + * Attach the dquot to the buffer so that the AIL does not have + * to read the dquot buffer to push this item. + */ + xfs_buf_hold(bp); + spin_lock(&qlip->qli_lock); + lip->li_buf = bp; + xfs_trans_brelse(tp, bp); + } + qlip->qli_dirty = true; + spin_unlock(&qlip->qli_lock); + + return 0; +} + +/* + * Get a new reference the dquot buffer attached to this dquot for a dqflush + * operation. + * + * Returns 0 and a NULL bp if none was attached to the dquot; 0 and a locked + * bp; or -EAGAIN if the buffer could not be locked. + */ +int +xfs_dquot_use_attached_buf( + struct xfs_dquot *dqp, + struct xfs_buf **bpp) +{ + struct xfs_buf *bp = dqp->q_logitem.qli_item.li_buf; + + /* + * A NULL buffer can happen if the dquot dirty flag was set but the + * filesystem shut down before transaction commit happened. In that + * case we're not going to flush anyway. + */ + if (!bp) { + ASSERT(xfs_is_shutdown(dqp->q_mount)); + + *bpp = NULL; + return 0; + } + + if (!xfs_buf_trylock(bp)) + return -EAGAIN; + + xfs_buf_hold(bp); + *bpp = bp; + return 0; +} + +/* * Write a modified dquot to disk. * The dquot must be locked and the flush lock too taken by caller. * The flush lock will not be unlocked until the dquot reaches the disk, @@ -1249,11 +1395,11 @@ xfs_qm_dqflush_check( int xfs_qm_dqflush( struct xfs_dquot *dqp, - struct xfs_buf **bpp) + struct xfs_buf *bp) { struct xfs_mount *mp = dqp->q_mount; - struct xfs_log_item *lip = &dqp->q_logitem.qli_item; - struct xfs_buf *bp; + struct xfs_dq_logitem *qlip = &dqp->q_logitem; + struct xfs_log_item *lip = &qlip->qli_item; struct xfs_dqblk *dqblk; xfs_failaddr_t fa; int error; @@ -1263,28 +1409,12 @@ xfs_qm_dqflush( trace_xfs_dqflush(dqp); - *bpp = NULL; - xfs_qm_dqunpin_wait(dqp); - /* - * Get the buffer containing the on-disk dquot - */ - error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno, - mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK, - &bp, &xfs_dquot_buf_ops); - if (error == -EAGAIN) - goto out_unlock; - if (xfs_metadata_is_sick(error)) - xfs_dquot_mark_sick(dqp); - if (error) - goto out_abort; - fa = xfs_qm_dqflush_check(dqp); if (fa) { xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS", dqp->q_id, fa); - xfs_buf_relse(bp); xfs_dquot_mark_sick(dqp); error = -EFSCORRUPTED; goto out_abort; @@ -1299,8 +1429,15 @@ xfs_qm_dqflush( */ dqp->q_flags &= ~XFS_DQFLAG_DIRTY; - xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn, - &dqp->q_logitem.qli_item.li_lsn); + /* + * We hold the dquot lock, so nobody can dirty it while we're + * scheduling the write out. Clear the dirty-since-flush flag. + */ + spin_lock(&qlip->qli_lock); + qlip->qli_dirty = false; + spin_unlock(&qlip->qli_lock); + + xfs_trans_ail_copy_lsn(mp->m_ail, &qlip->qli_flush_lsn, &lip->li_lsn); /* * copy the lsn into the on-disk dquot now while we have the in memory @@ -1312,7 +1449,7 @@ xfs_qm_dqflush( * of a dquot without an up-to-date CRC getting to disk. */ if (xfs_has_crc(mp)) { - dqblk->dd_lsn = cpu_to_be64(dqp->q_logitem.qli_item.li_lsn); + dqblk->dd_lsn = cpu_to_be64(lip->li_lsn); xfs_update_cksum((char *)dqblk, sizeof(struct xfs_dqblk), XFS_DQUOT_CRC_OFF); } @@ -1322,7 +1459,7 @@ xfs_qm_dqflush( * the AIL and release the flush lock once the dquot is synced to disk. */ bp->b_flags |= _XBF_DQUOTS; - list_add_tail(&dqp->q_logitem.qli_item.li_bio_list, &bp->b_li_list); + list_add_tail(&lip->li_bio_list, &bp->b_li_list); /* * If the buffer is pinned then push on the log so we won't @@ -1334,14 +1471,12 @@ xfs_qm_dqflush( } trace_xfs_dqflush_done(dqp); - *bpp = bp; return 0; out_abort: dqp->q_flags &= ~XFS_DQFLAG_DIRTY; xfs_trans_ail_delete(lip, 0); xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); -out_unlock: xfs_dqfunlock(dqp); return error; } diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h index d73d179df0095..c617bac75361b 100644 --- a/fs/xfs/xfs_dquot.h +++ b/fs/xfs/xfs_dquot.h @@ -214,7 +214,7 @@ void xfs_dquot_to_disk(struct xfs_disk_dquot *ddqp, struct xfs_dquot *dqp); #define XFS_DQ_IS_DIRTY(dqp) ((dqp)->q_flags & XFS_DQFLAG_DIRTY) void xfs_qm_dqdestroy(struct xfs_dquot *dqp); -int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf **bpp); +int xfs_qm_dqflush(struct xfs_dquot *dqp, struct xfs_buf *bp); void xfs_qm_dqunpin_wait(struct xfs_dquot *dqp); void xfs_qm_adjust_dqtimers(struct xfs_dquot *d); void xfs_qm_adjust_dqlimits(struct xfs_dquot *d); @@ -237,6 +237,10 @@ void xfs_dqlockn(struct xfs_dqtrx *q); void xfs_dquot_set_prealloc_limits(struct xfs_dquot *); +int xfs_dquot_attach_buf(struct xfs_trans *tp, struct xfs_dquot *dqp); +int xfs_dquot_use_attached_buf(struct xfs_dquot *dqp, struct xfs_buf **bpp); +void xfs_dquot_detach_buf(struct xfs_dquot *dqp); + static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp) { xfs_dqlock(dqp); diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c index 7d19091215b08..271b195ebb932 100644 --- a/fs/xfs/xfs_dquot_item.c +++ b/fs/xfs/xfs_dquot_item.c @@ -123,8 +123,9 @@ xfs_qm_dquot_logitem_push( __releases(&lip->li_ailp->ail_lock) __acquires(&lip->li_ailp->ail_lock) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; - struct xfs_buf *bp = lip->li_buf; + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + struct xfs_buf *bp; uint rval = XFS_ITEM_SUCCESS; int error; @@ -155,14 +156,25 @@ xfs_qm_dquot_logitem_push( spin_unlock(&lip->li_ailp->ail_lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + rval = XFS_ITEM_LOCKED; + goto out_relock_ail; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend does it on + * success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { if (!xfs_buf_delwri_queue(bp, buffer_list)) rval = XFS_ITEM_FLUSHING; - xfs_buf_relse(bp); - } else if (error == -EAGAIN) - rval = XFS_ITEM_LOCKED; + } + xfs_buf_relse(bp); +out_relock_ail: spin_lock(&lip->li_ailp->ail_lock); out_unlock: xfs_dqunlock(dqp); @@ -195,12 +207,10 @@ xfs_qm_dquot_logitem_committing( } #ifdef DEBUG_EXPENSIVE -static int -xfs_qm_dquot_logitem_precommit( - struct xfs_trans *tp, - struct xfs_log_item *lip) +static void +xfs_qm_dquot_logitem_precommit_check( + struct xfs_dquot *dqp) { - struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot; struct xfs_mount *mp = dqp->q_mount; struct xfs_disk_dquot ddq = { }; xfs_failaddr_t fa; @@ -216,13 +226,24 @@ xfs_qm_dquot_logitem_precommit( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); ASSERT(fa == NULL); } - - return 0; } #else -# define xfs_qm_dquot_logitem_precommit NULL +# define xfs_qm_dquot_logitem_precommit_check(...) ((void)0) #endif +static int +xfs_qm_dquot_logitem_precommit( + struct xfs_trans *tp, + struct xfs_log_item *lip) +{ + struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip); + struct xfs_dquot *dqp = qlip->qli_dquot; + + xfs_qm_dquot_logitem_precommit_check(dqp); + + return xfs_dquot_attach_buf(tp, dqp); +} + static const struct xfs_item_ops xfs_dquot_item_ops = { .iop_size = xfs_qm_dquot_logitem_size, .iop_precommit = xfs_qm_dquot_logitem_precommit, @@ -247,5 +268,7 @@ xfs_qm_dquot_logitem_init( xfs_log_item_init(dqp->q_mount, &lp->qli_item, XFS_LI_DQUOT, &xfs_dquot_item_ops); + spin_lock_init(&lp->qli_lock); lp->qli_dquot = dqp; + lp->qli_dirty = false; } diff --git a/fs/xfs/xfs_dquot_item.h b/fs/xfs/xfs_dquot_item.h index 794710c244749..d66e52807d76d 100644 --- a/fs/xfs/xfs_dquot_item.h +++ b/fs/xfs/xfs_dquot_item.h @@ -14,6 +14,13 @@ struct xfs_dq_logitem { struct xfs_log_item qli_item; /* common portion */ struct xfs_dquot *qli_dquot; /* dquot ptr */ xfs_lsn_t qli_flush_lsn; /* lsn at last flush */ + + /* + * We use this spinlock to coordinate access to the li_buf pointer in + * the log item and the qli_dirty flag. + */ + spinlock_t qli_lock; + bool qli_dirty; /* dirtied since last flush? */ }; void xfs_qm_dquot_logitem_init(struct xfs_dquot *dqp); diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index 9ab05ad224d12..265c424498933 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -854,7 +854,7 @@ xfs_ioc_start_commit( struct xfs_commit_range __user *argp) { struct xfs_commit_range args = { }; - struct timespec64 ts; + struct kstat kstat = { }; struct xfs_commit_range_fresh *kern_f; struct xfs_commit_range_fresh __user *user_f; struct inode *inode2 = file_inode(file); @@ -871,12 +871,12 @@ xfs_ioc_start_commit( memcpy(&kern_f->fsid, ip2->i_mount->m_fixedfsid, sizeof(xfs_fsid_t)); xfs_ilock(ip2, lockflags); - ts = inode_get_ctime(inode2); - kern_f->file2_ctime = ts.tv_sec; - kern_f->file2_ctime_nsec = ts.tv_nsec; - ts = inode_get_mtime(inode2); - kern_f->file2_mtime = ts.tv_sec; - kern_f->file2_mtime_nsec = ts.tv_nsec; + /* Force writing of a distinct ctime if any writes happen. */ + fill_mg_cmtime(&kstat, STATX_CTIME | STATX_MTIME, inode2); + kern_f->file2_ctime = kstat.ctime.tv_sec; + kern_f->file2_ctime_nsec = kstat.ctime.tv_nsec; + kern_f->file2_mtime = kstat.mtime.tv_sec; + kern_f->file2_mtime_nsec = kstat.mtime.tv_nsec; kern_f->file2_ino = ip2->i_ino; kern_f->file2_gen = inode2->i_generation; kern_f->magic = XCR_FRESH_MAGIC; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 4a0b7de4f7aed..9a435b1ff2647 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1242,6 +1242,14 @@ out_unlock: xfs_iunlock2_remapping(src, dest); if (ret) trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + /* + * If the caller did not set CAN_SHORTEN, then it is not prepared to + * handle partial results -- either the whole remap succeeds, or we + * must say why it did not. In this case, any error should be returned + * to the caller. + */ + if (ret && remapped < len && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) + return ret; return remapped > 0 ? remapped : ret; } diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 82f2e0dd22499..3290dd8524a69 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -163,7 +163,8 @@ struct xfs_getfsmap_info { xfs_daddr_t next_daddr; /* next daddr we expect */ /* daddr of low fsmap key when we're using the rtbitmap */ xfs_daddr_t low_daddr; - xfs_daddr_t end_daddr; /* daddr of high fsmap key */ + /* daddr of high fsmap key, or the last daddr on the device */ + xfs_daddr_t end_daddr; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ /* @@ -387,8 +388,8 @@ xfs_getfsmap_group_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) - frec->start_daddr = info->end_daddr; + if (info->last) + frec->start_daddr = info->end_daddr + 1; else frec->start_daddr = xfs_gbno_to_daddr(xg, startblock); @@ -736,11 +737,10 @@ xfs_getfsmap_rtdev_rtbitmap_helper( * we calculated from userspace's high key to synthesize the record. * Note that if the btree query found a mapping, there won't be a gap. */ - if (info->last && info->end_daddr != XFS_BUF_DADDR_NULL) { - frec.start_daddr = info->end_daddr; - } else { + if (info->last) + frec.start_daddr = info->end_daddr + 1; + else frec.start_daddr = xfs_rtb_to_daddr(mp, start_rtb); - } frec.len_daddr = XFS_FSB_TO_BB(mp, rtbcount); return xfs_getfsmap_helper(tp, info, &frec); @@ -933,7 +933,10 @@ xfs_getfsmap( struct xfs_trans *tp = NULL; struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; - struct xfs_getfsmap_info info = { NULL }; + struct xfs_getfsmap_info info = { + .fsmap_recs = fsmap_recs, + .head = head, + }; bool use_rmap; int i; int error = 0; @@ -998,9 +1001,6 @@ xfs_getfsmap( info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; - info.end_daddr = XFS_BUF_DADDR_NULL; - info.fsmap_recs = fsmap_recs; - info.head = head; /* For each device we support... */ for (i = 0; i < XFS_GETFSMAP_DEVS; i++) { @@ -1013,17 +1013,23 @@ xfs_getfsmap( break; /* - * If this device number matches the high key, we have - * to pass the high key to the handler to limit the - * query results. If the device number exceeds the - * low key, zero out the low key so that we get - * everything from the beginning. + * If this device number matches the high key, we have to pass + * the high key to the handler to limit the query results, and + * set the end_daddr so that we can synthesize records at the + * end of the query range or device. */ if (handlers[i].dev == head->fmh_keys[1].fmr_device) { dkeys[1] = head->fmh_keys[1]; info.end_daddr = min(handlers[i].nr_sectors - 1, dkeys[1].fmr_physical); + } else { + info.end_daddr = handlers[i].nr_sectors - 1; } + + /* + * If the device number exceeds the low key, zero out the low + * key so that we get everything from the beginning. + */ if (handlers[i].dev > head->fmh_keys[0].fmr_device) memset(&dkeys[0], 0, sizeof(struct xfs_fsmap)); diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b0de3d924d4c1..1648dc5a80688 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -231,7 +231,7 @@ xfs_iflags_clear(xfs_inode_t *ip, unsigned long flags) } static inline int -__xfs_iflags_test(xfs_inode_t *ip, unsigned long flags) +__xfs_iflags_test(const struct xfs_inode *ip, unsigned long flags) { return (ip->i_flags & flags); } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 61ee110b47d7d..dc8b1010d4d33 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -148,17 +148,29 @@ xfs_qm_dqpurge( * We don't care about getting disk errors here. We need * to purge this dquot anyway, so we go ahead regardless. */ - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (error == -EAGAIN) { + xfs_dqfunlock(dqp); + dqp->q_flags &= ~XFS_DQFLAG_FREEING; + goto out_unlock; + } + if (!bp) + goto out_funlock; + + /* + * dqflush completes dqflock on error, and the bwrite ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (!error) { error = xfs_bwrite(bp); xfs_buf_relse(bp); - } else if (error == -EAGAIN) { - dqp->q_flags &= ~XFS_DQFLAG_FREEING; - goto out_unlock; } xfs_dqflock(dqp); } + xfs_dquot_detach_buf(dqp); +out_funlock: ASSERT(atomic_read(&dqp->q_pincount) == 0); ASSERT(xlog_is_shutdown(dqp->q_logitem.qli_item.li_log) || !test_bit(XFS_LI_IN_AIL, &dqp->q_logitem.qli_item.li_flags)); @@ -241,6 +253,10 @@ xfs_qm_destroy_quotainos( xfs_irele(qi->qi_pquotaip); qi->qi_pquotaip = NULL; } + if (qi->qi_dirip) { + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; + } } /* @@ -490,7 +506,17 @@ xfs_qm_dquot_isolate( /* we have to drop the LRU lock to flush the dquot */ spin_unlock(&lru->lock); - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); + if (!bp || error == -EAGAIN) { + xfs_dqfunlock(dqp); + goto out_unlock_dirty; + } + + /* + * dqflush completes dqflock on error, and the delwri ioend + * does it on success. + */ + error = xfs_qm_dqflush(dqp, bp); if (error) goto out_unlock_dirty; @@ -498,6 +524,8 @@ xfs_qm_dquot_isolate( xfs_buf_relse(bp); goto out_unlock_dirty; } + + xfs_dquot_detach_buf(dqp); xfs_dqfunlock(dqp); /* @@ -646,8 +674,7 @@ xfs_qm_init_timelimits( static int xfs_qm_load_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { struct xfs_trans *tp; int error; @@ -656,7 +683,7 @@ xfs_qm_load_metadir_qinos( if (error) return error; - error = xfs_dqinode_load_parent(tp, dpp); + error = xfs_dqinode_load_parent(tp, &qi->qi_dirip); if (error == -ENOENT) { /* no quota dir directory, but we'll create one later */ error = 0; @@ -666,21 +693,21 @@ xfs_qm_load_metadir_qinos( goto out_trans; if (XFS_IS_UQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_USER, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_GQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_GROUP, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error && error != -ENOENT) goto out_trans; } if (XFS_IS_PQUOTA_ON(mp)) { - error = xfs_dqinode_load(tp, *dpp, XFS_DQTYPE_PROJ, + error = xfs_dqinode_load(tp, qi->qi_dirip, XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error && error != -ENOENT) goto out_trans; @@ -696,34 +723,40 @@ out_trans: STATIC int xfs_qm_create_metadir_qinos( struct xfs_mount *mp, - struct xfs_quotainfo *qi, - struct xfs_inode **dpp) + struct xfs_quotainfo *qi) { int error; - if (!*dpp) { - error = xfs_dqinode_mkdir_parent(mp, dpp); + if (!qi->qi_dirip) { + error = xfs_dqinode_mkdir_parent(mp, &qi->qi_dirip); if (error && error != -EEXIST) return error; + /* + * If the /quotas dirent points to an inode that isn't + * loadable, qi_dirip will be NULL but mkdir_parent will return + * -EEXIST. In this case the metadir is corrupt, so bail out. + */ + if (XFS_IS_CORRUPT(mp, qi->qi_dirip == NULL)) + return -EFSCORRUPTED; } if (XFS_IS_UQUOTA_ON(mp) && !qi->qi_uquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_USER, - &qi->qi_uquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_USER, &qi->qi_uquotaip); if (error) return error; } if (XFS_IS_GQUOTA_ON(mp) && !qi->qi_gquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_GROUP, - &qi->qi_gquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_GROUP, &qi->qi_gquotaip); if (error) return error; } if (XFS_IS_PQUOTA_ON(mp) && !qi->qi_pquotaip) { - error = xfs_dqinode_metadir_create(*dpp, XFS_DQTYPE_PROJ, - &qi->qi_pquotaip); + error = xfs_dqinode_metadir_create(qi->qi_dirip, + XFS_DQTYPE_PROJ, &qi->qi_pquotaip); if (error) return error; } @@ -768,7 +801,6 @@ xfs_qm_init_metadir_qinos( struct xfs_mount *mp) { struct xfs_quotainfo *qi = mp->m_quotainfo; - struct xfs_inode *dp = NULL; int error; if (!xfs_has_quota(mp)) { @@ -777,20 +809,22 @@ xfs_qm_init_metadir_qinos( return error; } - error = xfs_qm_load_metadir_qinos(mp, qi, &dp); + error = xfs_qm_load_metadir_qinos(mp, qi); if (error) goto out_err; - error = xfs_qm_create_metadir_qinos(mp, qi, &dp); + error = xfs_qm_create_metadir_qinos(mp, qi); if (error) goto out_err; - xfs_irele(dp); + /* The only user of the quota dir inode is online fsck */ +#if !IS_ENABLED(CONFIG_XFS_ONLINE_SCRUB) + xfs_irele(qi->qi_dirip); + qi->qi_dirip = NULL; +#endif return 0; out_err: xfs_qm_destroy_quotainos(mp->m_quotainfo); - if (dp) - xfs_irele(dp); return error; } @@ -1304,6 +1338,10 @@ xfs_qm_quotacheck_dqadjust( return error; } + error = xfs_dquot_attach_buf(NULL, dqp); + if (error) + return error; + trace_xfs_dqadjust(dqp); /* @@ -1486,11 +1524,17 @@ xfs_qm_flush_one( goto out_unlock; } - error = xfs_qm_dqflush(dqp, &bp); + error = xfs_dquot_use_attached_buf(dqp, &bp); if (error) goto out_unlock; + if (!bp) { + error = -EFSCORRUPTED; + goto out_unlock; + } - xfs_buf_delwri_queue(bp, buffer_list); + error = xfs_qm_dqflush(dqp, bp); + if (!error) + xfs_buf_delwri_queue(bp, buffer_list); xfs_buf_relse(bp); out_unlock: xfs_dqunlock(dqp); diff --git a/fs/xfs/xfs_qm.h b/fs/xfs/xfs_qm.h index e919c7f62f578..35b64bc3a7a86 100644 --- a/fs/xfs/xfs_qm.h +++ b/fs/xfs/xfs_qm.h @@ -55,6 +55,7 @@ struct xfs_quotainfo { struct xfs_inode *qi_uquotaip; /* user quota inode */ struct xfs_inode *qi_gquotaip; /* group quota inode */ struct xfs_inode *qi_pquotaip; /* project quota inode */ + struct xfs_inode *qi_dirip; /* quota metadir */ struct list_lru qi_lru; int qi_dquots; struct mutex qi_quotaofflock;/* to serialize quotaoff */ diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h index fa1317cc396c9..d7565462af3dc 100644 --- a/fs/xfs/xfs_quota.h +++ b/fs/xfs/xfs_quota.h @@ -101,7 +101,8 @@ extern void xfs_trans_free_dqinfo(struct xfs_trans *); extern void xfs_trans_mod_dquot_byino(struct xfs_trans *, struct xfs_inode *, uint, int64_t); extern void xfs_trans_apply_dquot_deltas(struct xfs_trans *); -extern void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *); +void xfs_trans_unreserve_and_mod_dquots(struct xfs_trans *tp, + bool already_locked); int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force); extern int xfs_trans_reserve_quota_bydquots(struct xfs_trans *, @@ -173,7 +174,7 @@ static inline void xfs_trans_mod_dquot_byino(struct xfs_trans *tp, { } #define xfs_trans_apply_dquot_deltas(tp) -#define xfs_trans_unreserve_and_mod_dquots(tp) +#define xfs_trans_unreserve_and_mod_dquots(tp, a) static inline int xfs_trans_reserve_quota_nblks(struct xfs_trans *tp, struct xfs_inode *ip, int64_t dblocks, int64_t rblocks, bool force) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 0cb534d71119a..fcfa6e0eb3ad2 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -1827,7 +1827,7 @@ xfs_rtallocate_rtg( * For an allocation to an empty file at offset 0, pick an extent that * will space things out in the rt area. */ - if (bno_hint) + if (bno_hint != NULLFSBLOCK) start = xfs_rtb_to_rtx(args.mp, bno_hint); else if (!xfs_has_rtgroups(args.mp) && initial_user_data) start = xfs_rtpick_extent(args.rtg, tp, maxlen); diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 30fbed27cf05c..4cd25717c9d13 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -860,29 +860,17 @@ __xfs_trans_commit( trace_xfs_trans_commit(tp, _RET_IP_); - error = xfs_trans_run_precommits(tp); - if (error) { - if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) - xfs_defer_cancel(tp); - goto out_unreserve; - } - /* - * Finish deferred items on final commit. Only permanent transactions - * should ever have deferred ops. + * Commit per-transaction changes that are not already tracked through + * log items. This can add dirty log items to the transaction. */ - WARN_ON_ONCE(!list_empty(&tp->t_dfops) && - !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); - if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) { - error = xfs_defer_finish_noroll(&tp); - if (error) - goto out_unreserve; + if (tp->t_flags & XFS_TRANS_SB_DIRTY) + xfs_trans_apply_sb_deltas(tp); + xfs_trans_apply_dquot_deltas(tp); - /* Run precommits from final tx in defer chain. */ - error = xfs_trans_run_precommits(tp); - if (error) - goto out_unreserve; - } + error = xfs_trans_run_precommits(tp); + if (error) + goto out_unreserve; /* * If there is nothing to be logged by the transaction, @@ -907,13 +895,6 @@ __xfs_trans_commit( ASSERT(tp->t_ticket != NULL); - /* - * If we need to update the superblock, then do it now. - */ - if (tp->t_flags & XFS_TRANS_SB_DIRTY) - xfs_trans_apply_sb_deltas(tp); - xfs_trans_apply_dquot_deltas(tp); - xlog_cil_commit(log, tp, &commit_seq, regrant); xfs_trans_free(tp); @@ -939,7 +920,7 @@ out_unreserve: * the dqinfo portion to be. All that means is that we have some * (non-persistent) quota reservations that need to be unreserved. */ - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, true); if (tp->t_ticket) { if (regrant && !xlog_is_shutdown(log)) xfs_log_ticket_regrant(log, tp->t_ticket); @@ -958,6 +939,20 @@ int xfs_trans_commit( struct xfs_trans *tp) { + /* + * Finish deferred items on final commit. Only permanent transactions + * should ever have deferred ops. + */ + WARN_ON_ONCE(!list_empty(&tp->t_dfops) && + !(tp->t_flags & XFS_TRANS_PERM_LOG_RES)); + if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) { + int error = xfs_defer_finish_noroll(&tp); + if (error) { + xfs_trans_cancel(tp); + return error; + } + } + return __xfs_trans_commit(tp, false); } @@ -1019,7 +1014,7 @@ xfs_trans_cancel( } #endif xfs_trans_unreserve_and_mod_sb(tp); - xfs_trans_unreserve_and_mod_dquots(tp); + xfs_trans_unreserve_and_mod_dquots(tp, false); if (tp->t_ticket) { xfs_log_ticket_ungrant(log, tp->t_ticket); @@ -1435,5 +1430,8 @@ done: out_cancel: xfs_trans_cancel(tp); + xfs_iunlock(dp, XFS_ILOCK_EXCL); + if (dp != ip) + xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; } diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 8ede9d099d1fe..f56d62dced97b 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -360,7 +360,7 @@ xfsaild_resubmit_item( /* protected by ail_lock */ list_for_each_entry(lip, &bp->b_li_list, li_bio_list) { - if (bp->b_flags & _XBF_INODES) + if (bp->b_flags & (_XBF_INODES | _XBF_DQUOTS)) clear_bit(XFS_LI_FAILED, &lip->li_flags); else xfs_clear_li_failed(lip); diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c index 481ba3dc9f190..713b6d243e563 100644 --- a/fs/xfs/xfs_trans_dquot.c +++ b/fs/xfs/xfs_trans_dquot.c @@ -606,6 +606,24 @@ xfs_trans_apply_dquot_deltas( ASSERT(dqp->q_blk.reserved >= dqp->q_blk.count); ASSERT(dqp->q_ino.reserved >= dqp->q_ino.count); ASSERT(dqp->q_rtb.reserved >= dqp->q_rtb.count); + + /* + * We've applied the count changes and given back + * whatever reservation we didn't use. Zero out the + * dqtrx fields. + */ + qtrx->qt_blk_res = 0; + qtrx->qt_bcount_delta = 0; + qtrx->qt_delbcnt_delta = 0; + + qtrx->qt_rtblk_res = 0; + qtrx->qt_rtblk_res_used = 0; + qtrx->qt_rtbcount_delta = 0; + qtrx->qt_delrtb_delta = 0; + + qtrx->qt_ino_res = 0; + qtrx->qt_ino_res_used = 0; + qtrx->qt_icount_delta = 0; } } } @@ -642,7 +660,8 @@ xfs_trans_unreserve_and_mod_dquots_hook( */ void xfs_trans_unreserve_and_mod_dquots( - struct xfs_trans *tp) + struct xfs_trans *tp, + bool already_locked) { int i, j; struct xfs_dquot *dqp; @@ -671,10 +690,12 @@ xfs_trans_unreserve_and_mod_dquots( * about the number of blocks used field, or deltas. * Also we don't bother to zero the fields. */ - locked = false; + locked = already_locked; if (qtrx->qt_blk_res) { - xfs_dqlock(dqp); - locked = true; + if (!locked) { + xfs_dqlock(dqp); + locked = true; + } dqp->q_blk.reserved -= (xfs_qcnt_t)qtrx->qt_blk_res; } @@ -695,7 +716,7 @@ xfs_trans_unreserve_and_mod_dquots( dqp->q_rtb.reserved -= (xfs_qcnt_t)qtrx->qt_rtblk_res; } - if (locked) + if (locked && !already_locked) xfs_dqunlock(dqp); } |