diff options
Diffstat (limited to 'fs')
97 files changed, 3197 insertions, 1836 deletions
diff --git a/fs/afs/write.c b/fs/afs/write.c index 9c7fd6fd8095..e1c45341719b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -413,17 +413,19 @@ static int afs_store_data(struct afs_vnode *vnode, struct iov_iter *iter, loff_t afs_op_set_vnode(op, 0, vnode); op->file[0].dv_delta = 1; op->file[0].modification = true; - op->store.write_iter = iter; op->store.pos = pos; op->store.size = size; - op->store.i_size = max(pos + size, vnode->netfs.remote_i_size); op->store.laundering = laundering; - op->mtime = vnode->netfs.inode.i_mtime; op->flags |= AFS_OPERATION_UNINTR; op->ops = &afs_store_data_operation; try_next_key: afs_begin_vnode_operation(op); + + op->store.write_iter = iter; + op->store.i_size = max(pos + size, vnode->netfs.remote_i_size); + op->mtime = vnode->netfs.inode.i_mtime; + afs_wait_for_operation(op); switch (op->error) { diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 6bb251a4d613..59cbfb80edbd 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -187,16 +187,42 @@ static void ceph_netfs_expand_readahead(struct netfs_io_request *rreq) struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_file_layout *lo = &ci->i_layout; + unsigned long max_pages = inode->i_sb->s_bdi->ra_pages; + loff_t end = rreq->start + rreq->len, new_end; + struct ceph_netfs_request_data *priv = rreq->netfs_priv; + unsigned long max_len; u32 blockoff; - u64 blockno; - /* Expand the start downward */ - blockno = div_u64_rem(rreq->start, lo->stripe_unit, &blockoff); - rreq->start = blockno * lo->stripe_unit; - rreq->len += blockoff; + if (priv) { + /* Readahead is disabled by posix_fadvise POSIX_FADV_RANDOM */ + if (priv->file_ra_disabled) + max_pages = 0; + else + max_pages = priv->file_ra_pages; + + } - /* Now, round up the length to the next block */ - rreq->len = roundup(rreq->len, lo->stripe_unit); + /* Readahead is disabled */ + if (!max_pages) + return; + + max_len = max_pages << PAGE_SHIFT; + + /* + * Try to expand the length forward by rounding up it to the next + * block, but do not exceed the file size, unless the original + * request already exceeds it. + */ + new_end = min(round_up(end, lo->stripe_unit), rreq->i_size); + if (new_end > end && new_end <= rreq->start + max_len) + rreq->len = new_end - rreq->start; + + /* Try to expand the start downward */ + div_u64_rem(rreq->start, lo->stripe_unit, &blockoff); + if (rreq->len + blockoff <= max_len) { + rreq->start -= blockoff; + rreq->len += blockoff; + } } static bool ceph_netfs_clamp_length(struct netfs_io_subrequest *subreq) @@ -362,18 +388,28 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) { struct inode *inode = rreq->inode; int got = 0, want = CEPH_CAP_FILE_CACHE; + struct ceph_netfs_request_data *priv; int ret = 0; if (rreq->origin != NETFS_READAHEAD) return 0; + priv = kzalloc(sizeof(*priv), GFP_NOFS); + if (!priv) + return -ENOMEM; + if (file) { struct ceph_rw_context *rw_ctx; struct ceph_file_info *fi = file->private_data; + priv->file_ra_pages = file->f_ra.ra_pages; + priv->file_ra_disabled = file->f_mode & FMODE_RANDOM; + rw_ctx = ceph_find_rw_context(fi); - if (rw_ctx) + if (rw_ctx) { + rreq->netfs_priv = priv; return 0; + } } /* @@ -383,27 +419,40 @@ static int ceph_init_request(struct netfs_io_request *rreq, struct file *file) ret = ceph_try_get_caps(inode, CEPH_CAP_FILE_RD, want, true, &got); if (ret < 0) { dout("start_read %p, error getting cap\n", inode); - return ret; + goto out; } if (!(got & want)) { dout("start_read %p, no cache cap\n", inode); - return -EACCES; + ret = -EACCES; + goto out; + } + if (ret == 0) { + ret = -EACCES; + goto out; } - if (ret == 0) - return -EACCES; - rreq->netfs_priv = (void *)(uintptr_t)got; - return 0; + priv->caps = got; + rreq->netfs_priv = priv; + +out: + if (ret < 0) + kfree(priv); + + return ret; } static void ceph_netfs_free_request(struct netfs_io_request *rreq) { - struct ceph_inode_info *ci = ceph_inode(rreq->inode); - int got = (uintptr_t)rreq->netfs_priv; + struct ceph_netfs_request_data *priv = rreq->netfs_priv; + + if (!priv) + return; - if (got) - ceph_put_cap_refs(ci, got); + if (priv->caps) + ceph_put_cap_refs(ceph_inode(rreq->inode), priv->caps); + kfree(priv); + rreq->netfs_priv = NULL; } const struct netfs_request_ops ceph_netfs_ops = { diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 2321e5ddb664..e2bb0d0072da 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -3109,6 +3109,12 @@ static void __ceph_put_cap_refs(struct ceph_inode_info *ci, int had, } if (had & CEPH_CAP_FILE_WR) { if (--ci->i_wr_ref == 0) { + /* + * The Fb caps will always be took and released + * together with the Fw caps. + */ + WARN_ON_ONCE(ci->i_wb_ref); + last++; check_flushsnaps = true; if (ci->i_wrbuffer_ref_head == 0 && @@ -3560,6 +3566,15 @@ static void handle_cap_grant(struct inode *inode, } BUG_ON(cap->issued & ~cap->implemented); + /* don't let check_caps skip sending a response to MDS for revoke msgs */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + cap->mds_wanted = 0; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } + if (extra_info->inline_version > 0 && extra_info->inline_version >= ci->i_inline_version) { ci->i_inline_version = extra_info->inline_version; @@ -4086,6 +4101,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, struct cap_extra_info extra_info = {}; bool queue_trunc; bool close_sessions = false; + bool do_cap_release = false; dout("handle_caps from mds%d\n", session->s_mds); @@ -4192,17 +4208,14 @@ void ceph_handle_caps(struct ceph_mds_session *session, if (!inode) { dout(" i don't have ino %llx\n", vino.ino); - if (op == CEPH_CAP_OP_IMPORT) { - cap = ceph_get_cap(mdsc, NULL); - cap->cap_ino = vino.ino; - cap->queue_release = 1; - cap->cap_id = le64_to_cpu(h->cap_id); - cap->mseq = mseq; - cap->seq = seq; - cap->issue_seq = seq; - spin_lock(&session->s_cap_lock); - __ceph_queue_cap_release(session, cap); - spin_unlock(&session->s_cap_lock); + switch (op) { + case CEPH_CAP_OP_IMPORT: + case CEPH_CAP_OP_REVOKE: + case CEPH_CAP_OP_GRANT: + do_cap_release = true; + break; + default: + break; } goto flush_cap_releases; } @@ -4252,6 +4265,14 @@ void ceph_handle_caps(struct ceph_mds_session *session, inode, ceph_ino(inode), ceph_snap(inode), session->s_mds); spin_unlock(&ci->i_ceph_lock); + switch (op) { + case CEPH_CAP_OP_REVOKE: + case CEPH_CAP_OP_GRANT: + do_cap_release = true; + break; + default: + break; + } goto flush_cap_releases; } @@ -4302,6 +4323,18 @@ flush_cap_releases: * along for the mds (who clearly thinks we still have this * cap). */ + if (do_cap_release) { + cap = ceph_get_cap(mdsc, NULL); + cap->cap_ino = vino.ino; + cap->queue_release = 1; + cap->cap_id = le64_to_cpu(h->cap_id); + cap->mseq = mseq; + cap->seq = seq; + cap->issue_seq = seq; + spin_lock(&session->s_cap_lock); + __ceph_queue_cap_release(session, cap); + spin_unlock(&session->s_cap_lock); + } ceph_flush_cap_releases(mdsc, session); goto done; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index cb67ac821f0e..4a2b39d9a61a 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -886,7 +886,8 @@ static int ceph_mknod(struct mnt_idmap *idmap, struct inode *dir, set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_args.mknod.mode = cpu_to_le32(mode); req->r_args.mknod.rdev = cpu_to_le32(rdev); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (as_ctx.pagelist) { req->r_pagelist = as_ctx.pagelist; @@ -953,7 +954,8 @@ static int ceph_symlink(struct mnt_idmap *idmap, struct inode *dir, set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_dentry = dget(dentry); req->r_num_caps = 2; - req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (as_ctx.pagelist) { req->r_pagelist = as_ctx.pagelist; @@ -1022,7 +1024,8 @@ static int ceph_mkdir(struct mnt_idmap *idmap, struct inode *dir, ihold(dir); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); req->r_args.mkdir.mode = cpu_to_le32(mode); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (as_ctx.pagelist) { req->r_pagelist = as_ctx.pagelist; @@ -1079,7 +1082,7 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir, req->r_parent = dir; ihold(dir); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; /* release LINK_SHARED on source inode (mds will lock it) */ req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; @@ -1218,7 +1221,7 @@ retry: req->r_num_caps = 2; req->r_parent = dir; ihold(dir); - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; req->r_inode_drop = ceph_drop_caps_for_unlink(inode); @@ -1320,9 +1323,9 @@ static int ceph_rename(struct mnt_idmap *idmap, struct inode *old_dir, req->r_parent = new_dir; ihold(new_dir); set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); - req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_XATTR_EXCL; req->r_old_dentry_unless = CEPH_CAP_FILE_EXCL; - req->r_dentry_drop = CEPH_CAP_FILE_SHARED; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; /* release LINK_RDCACHE on source inode (mds will lock it) */ req->r_old_inode_drop = CEPH_CAP_LINK_SHARED | CEPH_CAP_LINK_EXCL; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b1925232dc08..63efe5389783 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -791,7 +791,8 @@ retry: if (flags & O_CREAT) { struct ceph_file_layout lo; - req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL; + req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL | + CEPH_CAP_XATTR_EXCL; req->r_dentry_unless = CEPH_CAP_FILE_EXCL; if (as_ctx.pagelist) { req->r_pagelist = as_ctx.pagelist; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 4c0f22acf53d..66048a86c480 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -645,6 +645,7 @@ bad: err = -EIO; out_bad: pr_err("mds parse_reply err %d\n", err); + ceph_msg_dump(msg); return err; } @@ -3538,6 +3539,7 @@ static void handle_forward(struct ceph_mds_client *mdsc, bad: pr_err("mdsc_handle_forward decode error err=%d\n", err); + ceph_msg_dump(msg); } static int __decode_session_metadata(void **p, void *end, @@ -5258,6 +5260,7 @@ void ceph_mdsc_handle_fsmap(struct ceph_mds_client *mdsc, struct ceph_msg *msg) bad: pr_err("error decoding fsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); err_out: mutex_lock(&mdsc->mutex); mdsc->mdsmap_err = err; @@ -5326,6 +5329,7 @@ bad_unlock: bad: pr_err("error decoding mdsmap %d. Shutting down mount.\n", err); ceph_umount_begin(mdsc->fsc->sb); + ceph_msg_dump(msg); return; } diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c index c47347d2e84e..cce78d769f55 100644 --- a/fs/ceph/metric.c +++ b/fs/ceph/metric.c @@ -36,6 +36,14 @@ static bool ceph_mdsc_send_metrics(struct ceph_mds_client *mdsc, s32 items = 0; s32 len; + /* Do not send the metrics until the MDS rank is ready */ + mutex_lock(&mdsc->mutex); + if (ceph_mdsmap_get_state(mdsc->mdsmap, s->s_mds) != CEPH_MDS_STATE_ACTIVE) { + mutex_unlock(&mdsc->mutex); + return false; + } + mutex_unlock(&mdsc->mutex); + len = sizeof(*head) + sizeof(*cap) + sizeof(*read) + sizeof(*write) + sizeof(*meta) + sizeof(*dlease) + sizeof(*files) + sizeof(*icaps) + sizeof(*inodes) + sizeof(*rsize) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 2e73ba62bd7a..343d738448dc 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -675,14 +675,17 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, return 0; } - /* Fb cap still in use, delay it */ - if (ci->i_wb_ref) { + /* + * Defer flushing the capsnap if the dirty buffer not flushed yet. + * And trigger to flush the buffer immediately. + */ + if (ci->i_wrbuffer_ref) { dout("%s %p %llx.%llx cap_snap %p snapc %p %llu %s s=%llu " "used WRBUFFER, delaying\n", __func__, inode, ceph_vinop(inode), capsnap, capsnap->context, capsnap->context->seq, ceph_cap_string(capsnap->dirty), capsnap->size); - capsnap->writing = 1; + ceph_queue_writeback(inode); return 0; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index d24bf0db5234..3bfddf34d488 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -451,6 +451,19 @@ struct ceph_inode_info { unsigned long i_work_mask; }; +struct ceph_netfs_request_data { + int caps; + + /* + * Maximum size of a file readahead request. + * The fadvise could update the bdi's default ra_pages. + */ + unsigned int file_ra_pages; + + /* Set it if fadvise disables file readahead entirely */ + bool file_ra_disabled; +}; + static inline struct ceph_inode_info * ceph_inode(const struct inode *inode) { diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 1f971c880dde..b7711888dd17 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -940,15 +940,6 @@ static const struct file_operations fops_str_wo = { * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. - * - * This function will return a pointer to a dentry if it succeeds. This - * pointer must be passed to the debugfs_remove() function when the file is - * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be - * returned. - * - * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will - * be returned. */ void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value) diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 64b3860f50ee..8fd3b7f9fb88 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -30,12 +30,9 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io, unsigned char reason) { f2fs_build_fault_attr(sbi, 0, 0); - set_ckpt_flags(sbi, CP_ERROR_FLAG); - if (!end_io) { + if (!end_io) f2fs_flush_merged_writes(sbi); - - f2fs_handle_stop(sbi, reason); - } + f2fs_handle_critical_error(sbi, reason, end_io); } /* diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 11653fa79289..236d890f560b 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -55,6 +55,7 @@ struct f2fs_compress_ops { int (*init_decompress_ctx)(struct decompress_io_ctx *dic); void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); + bool (*is_level_valid)(int level); }; static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -308,17 +309,25 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool lz4_is_level_valid(int lvl) +{ +#ifdef CONFIG_F2FS_FS_LZ4HC + return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL); +#else + return lvl == 0; +#endif +} + static const struct f2fs_compress_ops f2fs_lz4_ops = { .init_compress_ctx = lz4_init_compress_ctx, .destroy_compress_ctx = lz4_destroy_compress_ctx, .compress_pages = lz4_compress_pages, .decompress_pages = lz4_decompress_pages, + .is_level_valid = lz4_is_level_valid, }; #endif #ifdef CONFIG_F2FS_FS_ZSTD -#define F2FS_ZSTD_DEFAULT_CLEVEL 1 - static int zstd_init_compress_ctx(struct compress_ctx *cc) { zstd_parameters params; @@ -327,6 +336,7 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) unsigned int workspace_size; unsigned char level = F2FS_I(cc->inode)->i_compress_level; + /* Need to remain this for backward compatibility */ if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; @@ -477,6 +487,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool zstd_is_level_valid(int lvl) +{ + return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel(); +} + static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_compress_ctx = zstd_init_compress_ctx, .destroy_compress_ctx = zstd_destroy_compress_ctx, @@ -484,6 +499,7 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_decompress_ctx = zstd_init_decompress_ctx, .destroy_decompress_ctx = zstd_destroy_decompress_ctx, .decompress_pages = zstd_decompress_pages, + .is_level_valid = zstd_is_level_valid, }; #endif @@ -542,6 +558,16 @@ bool f2fs_is_compress_backend_ready(struct inode *inode) return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } +bool f2fs_is_compress_level_valid(int alg, int lvl) +{ + const struct f2fs_compress_ops *cops = f2fs_cops[alg]; + + if (cops->is_level_valid) + return cops->is_level_valid(lvl); + + return lvl == 0; +} + static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); @@ -743,8 +769,8 @@ void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) ret = -EFSCORRUPTED; /* Avoid f2fs_commit_super in irq context */ - if (in_task) - f2fs_save_errors(sbi, ERROR_FAIL_DECOMPRESSION); + if (!in_task) + f2fs_handle_error_async(sbi, ERROR_FAIL_DECOMPRESSION); else f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION); goto out_release; @@ -1215,6 +1241,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, unsigned int last_index = cc->cluster_size - 1; loff_t psize; int i, err; + bool quota_inode = IS_NOQUOTA(inode); /* we should bypass data pages to proceed the kworker jobs */ if (unlikely(f2fs_cp_error(sbi))) { @@ -1222,7 +1249,7 @@ static int f2fs_write_compressed_pages(struct compress_ctx *cc, goto out_free; } - if (IS_NOQUOTA(inode)) { + if (quota_inode) { /* * We need to wait for node_write to avoid block allocation during * checkpoint. This can only happen to quota writes which can cause @@ -1344,7 +1371,7 @@ unlock_continue: set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); f2fs_put_dnode(&dn); - if (IS_NOQUOTA(inode)) + if (quota_inode) f2fs_up_read(&sbi->node_write); else f2fs_unlock_op(sbi); @@ -1370,7 +1397,7 @@ out_put_cic: out_put_dnode: f2fs_put_dnode(&dn); out_unlock_op: - if (IS_NOQUOTA(inode)) + if (quota_inode) f2fs_up_read(&sbi->node_write); else f2fs_unlock_op(sbi); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7165b1202f53..5882afe71d82 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -383,6 +383,17 @@ static void f2fs_write_end_io(struct bio *bio) bio_put(bio); } +#ifdef CONFIG_BLK_DEV_ZONED +static void f2fs_zone_write_end_io(struct bio *bio) +{ + struct f2fs_bio_info *io = (struct f2fs_bio_info *)bio->bi_private; + + bio->bi_private = io->bi_private; + complete(&io->zone_wait); + f2fs_write_end_io(bio); +} +#endif + struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, sector_t *sector) { @@ -639,6 +650,11 @@ int f2fs_init_write_merge_io(struct f2fs_sb_info *sbi) INIT_LIST_HEAD(&sbi->write_io[i][j].io_list); INIT_LIST_HEAD(&sbi->write_io[i][j].bio_list); init_f2fs_rwsem(&sbi->write_io[i][j].bio_list_lock); +#ifdef CONFIG_BLK_DEV_ZONED + init_completion(&sbi->write_io[i][j].zone_wait); + sbi->write_io[i][j].zone_pending_bio = NULL; + sbi->write_io[i][j].bi_private = NULL; +#endif } } @@ -965,6 +981,26 @@ alloc_new: return 0; } +#ifdef CONFIG_BLK_DEV_ZONED +static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr) +{ + int devi = 0; + + if (f2fs_is_multi_device(sbi)) { + devi = f2fs_target_device_index(sbi, blkaddr); + if (blkaddr < FDEV(devi).start_blk || + blkaddr > FDEV(devi).end_blk) { + f2fs_err(sbi, "Invalid block %x", blkaddr); + return false; + } + blkaddr -= FDEV(devi).start_blk; + } + return bdev_zoned_model(FDEV(devi).bdev) == BLK_ZONED_HM && + f2fs_blkz_is_seq(sbi, devi, blkaddr) && + (blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1); +} +#endif + void f2fs_submit_page_write(struct f2fs_io_info *fio) { struct f2fs_sb_info *sbi = fio->sbi; @@ -975,6 +1011,16 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) f2fs_bug_on(sbi, is_read_io(fio->op)); f2fs_down_write(&io->io_rwsem); + +#ifdef CONFIG_BLK_DEV_ZONED + if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) { + wait_for_completion_io(&io->zone_wait); + bio_put(io->zone_pending_bio); + io->zone_pending_bio = NULL; + io->bi_private = NULL; + } +#endif + next: if (fio->in_list) { spin_lock(&io->io_lock); @@ -1038,6 +1084,18 @@ skip: if (fio->in_list) goto next; out: +#ifdef CONFIG_BLK_DEV_ZONED + if (f2fs_sb_has_blkzoned(sbi) && btype < META && + is_end_zone_blkaddr(sbi, fio->new_blkaddr)) { + bio_get(io->bio); + reinit_completion(&io->zone_wait); + io->bi_private = io->bio->bi_private; + io->bio->bi_private = io; + io->bio->bi_end_io = f2fs_zone_write_end_io; + io->zone_pending_bio = io->bio; + __submit_merged_bio(io); + } +#endif if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); @@ -2173,7 +2231,6 @@ submit_and_realloc: f2fs_update_iostat(F2FS_I_SB(inode), NULL, FS_DATA_READ_IO, F2FS_BLKSIZE); *last_block_in_bio = block_nr; - goto out; out: *bio_ret = bio; return ret; @@ -2775,6 +2832,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, loff_t psize = (loff_t)(page->index + 1) << PAGE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; + bool quota_inode = IS_NOQUOTA(inode); int err = 0; struct f2fs_io_info fio = { .sbi = sbi, @@ -2807,6 +2865,10 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, if (S_ISDIR(inode->i_mode) && !is_sbi_flag_set(sbi, SBI_IS_CLOSE)) goto redirty_out; + + /* keep data pages in remount-ro mode */ + if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) + goto redirty_out; goto out; } @@ -2832,19 +2894,19 @@ write: goto out; /* Dentry/quota blocks are controlled by checkpoint */ - if (S_ISDIR(inode->i_mode) || IS_NOQUOTA(inode)) { + if (S_ISDIR(inode->i_mode) || quota_inode) { /* * We need to wait for node_write to avoid block allocation during * checkpoint. This can only happen to quota writes which can cause * the below discard race condition. */ - if (IS_NOQUOTA(inode)) + if (quota_inode) f2fs_down_read(&sbi->node_write); fio.need_lock = LOCK_DONE; err = f2fs_do_write_data_page(&fio); - if (IS_NOQUOTA(inode)) + if (quota_inode) f2fs_up_read(&sbi->node_write); goto done; @@ -4067,7 +4129,6 @@ const struct address_space_operations f2fs_dblock_aops = { .migrate_folio = filemap_migrate_folio, .invalidate_folio = f2fs_invalidate_folio, .release_folio = f2fs_release_folio, - .direct_IO = noop_direct_IO, .bmap = f2fs_bmap, .swap_activate = f2fs_swap_activate, .swap_deactivate = f2fs_swap_deactivate, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 887e55988450..d635c58cf5a3 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -775,8 +775,15 @@ int f2fs_add_dentry(struct inode *dir, const struct f2fs_filename *fname, { int err = -EAGAIN; - if (f2fs_has_inline_dentry(dir)) + if (f2fs_has_inline_dentry(dir)) { + /* + * Should get i_xattr_sem to keep the lock order: + * i_xattr_sem -> inode_page lock used by f2fs_setxattr. + */ + f2fs_down_read(&F2FS_I(dir)->i_xattr_sem); err = f2fs_add_inline_entry(dir, fname, inode, ino, mode); + f2fs_up_read(&F2FS_I(dir)->i_xattr_sem); + } if (err == -EAGAIN) err = f2fs_add_regular_entry(dir, fname, inode, ino, mode); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index d211ee89c158..c7cb2177b252 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -80,34 +80,34 @@ extern const char *f2fs_fault_name[FAULT_MAX]; /* * For mount options */ -#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000002 -#define F2FS_MOUNT_DISCARD 0x00000004 -#define F2FS_MOUNT_NOHEAP 0x00000008 -#define F2FS_MOUNT_XATTR_USER 0x00000010 -#define F2FS_MOUNT_POSIX_ACL 0x00000020 -#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040 -#define F2FS_MOUNT_INLINE_XATTR 0x00000080 -#define F2FS_MOUNT_INLINE_DATA 0x00000100 -#define F2FS_MOUNT_INLINE_DENTRY 0x00000200 -#define F2FS_MOUNT_FLUSH_MERGE 0x00000400 -#define F2FS_MOUNT_NOBARRIER 0x00000800 -#define F2FS_MOUNT_FASTBOOT 0x00001000 -#define F2FS_MOUNT_READ_EXTENT_CACHE 0x00002000 -#define F2FS_MOUNT_DATA_FLUSH 0x00008000 -#define F2FS_MOUNT_FAULT_INJECTION 0x00010000 -#define F2FS_MOUNT_USRQUOTA 0x00080000 -#define F2FS_MOUNT_GRPQUOTA 0x00100000 -#define F2FS_MOUNT_PRJQUOTA 0x00200000 -#define F2FS_MOUNT_QUOTA 0x00400000 -#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00800000 -#define F2FS_MOUNT_RESERVE_ROOT 0x01000000 -#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x02000000 -#define F2FS_MOUNT_NORECOVERY 0x04000000 -#define F2FS_MOUNT_ATGC 0x08000000 -#define F2FS_MOUNT_MERGE_CHECKPOINT 0x10000000 -#define F2FS_MOUNT_GC_MERGE 0x20000000 -#define F2FS_MOUNT_COMPRESS_CACHE 0x40000000 -#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x80000000 +#define F2FS_MOUNT_DISABLE_ROLL_FORWARD 0x00000001 +#define F2FS_MOUNT_DISCARD 0x00000002 +#define F2FS_MOUNT_NOHEAP 0x00000004 +#define F2FS_MOUNT_XATTR_USER 0x00000008 +#define F2FS_MOUNT_POSIX_ACL 0x00000010 +#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000020 +#define F2FS_MOUNT_INLINE_XATTR 0x00000040 +#define F2FS_MOUNT_INLINE_DATA 0x00000080 +#define F2FS_MOUNT_INLINE_DENTRY 0x00000100 +#define F2FS_MOUNT_FLUSH_MERGE 0x00000200 +#define F2FS_MOUNT_NOBARRIER 0x00000400 +#define F2FS_MOUNT_FASTBOOT 0x00000800 +#define F2FS_MOUNT_READ_EXTENT_CACHE 0x00001000 +#define F2FS_MOUNT_DATA_FLUSH 0x00002000 +#define F2FS_MOUNT_FAULT_INJECTION 0x00004000 +#define F2FS_MOUNT_USRQUOTA 0x00008000 +#define F2FS_MOUNT_GRPQUOTA 0x00010000 +#define F2FS_MOUNT_PRJQUOTA 0x00020000 +#define F2FS_MOUNT_QUOTA 0x00040000 +#define F2FS_MOUNT_INLINE_XATTR_SIZE 0x00080000 +#define F2FS_MOUNT_RESERVE_ROOT 0x00100000 +#define F2FS_MOUNT_DISABLE_CHECKPOINT 0x00200000 +#define F2FS_MOUNT_NORECOVERY 0x00400000 +#define F2FS_MOUNT_ATGC 0x00800000 +#define F2FS_MOUNT_MERGE_CHECKPOINT 0x01000000 +#define F2FS_MOUNT_GC_MERGE 0x02000000 +#define F2FS_MOUNT_COMPRESS_CACHE 0x04000000 +#define F2FS_MOUNT_AGE_EXTENT_CACHE 0x08000000 #define F2FS_OPTION(sbi) ((sbi)->mount_opt) #define clear_opt(sbi, option) (F2FS_OPTION(sbi).opt &= ~F2FS_MOUNT_##option) @@ -162,6 +162,7 @@ struct f2fs_mount_info { int fs_mode; /* fs mode: LFS or ADAPTIVE */ int bggc_mode; /* bggc mode: off, on or sync */ int memory_mode; /* memory mode */ + int errors; /* errors parameter */ int discard_unit; /* * discard command's offset/size should * be aligned to this unit: block, @@ -185,21 +186,21 @@ struct f2fs_mount_info { unsigned char noextensions[COMPRESS_EXT_NUM][F2FS_EXTENSION_LEN]; /* extensions */ }; -#define F2FS_FEATURE_ENCRYPT 0x0001 -#define F2FS_FEATURE_BLKZONED 0x0002 -#define F2FS_FEATURE_ATOMIC_WRITE 0x0004 -#define F2FS_FEATURE_EXTRA_ATTR 0x0008 -#define F2FS_FEATURE_PRJQUOTA 0x0010 -#define F2FS_FEATURE_INODE_CHKSUM 0x0020 -#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x0040 -#define F2FS_FEATURE_QUOTA_INO 0x0080 -#define F2FS_FEATURE_INODE_CRTIME 0x0100 -#define F2FS_FEATURE_LOST_FOUND 0x0200 -#define F2FS_FEATURE_VERITY 0x0400 -#define F2FS_FEATURE_SB_CHKSUM 0x0800 -#define F2FS_FEATURE_CASEFOLD 0x1000 -#define F2FS_FEATURE_COMPRESSION 0x2000 -#define F2FS_FEATURE_RO 0x4000 +#define F2FS_FEATURE_ENCRYPT 0x00000001 +#define F2FS_FEATURE_BLKZONED 0x00000002 +#define F2FS_FEATURE_ATOMIC_WRITE 0x00000004 +#define F2FS_FEATURE_EXTRA_ATTR 0x00000008 +#define F2FS_FEATURE_PRJQUOTA 0x00000010 +#define F2FS_FEATURE_INODE_CHKSUM 0x00000020 +#define F2FS_FEATURE_FLEXIBLE_INLINE_XATTR 0x00000040 +#define F2FS_FEATURE_QUOTA_INO 0x00000080 +#define F2FS_FEATURE_INODE_CRTIME 0x00000100 +#define F2FS_FEATURE_LOST_FOUND 0x00000200 +#define F2FS_FEATURE_VERITY 0x00000400 +#define F2FS_FEATURE_SB_CHKSUM 0x00000800 +#define F2FS_FEATURE_CASEFOLD 0x00001000 +#define F2FS_FEATURE_COMPRESSION 0x00002000 +#define F2FS_FEATURE_RO 0x00004000 #define __F2FS_HAS_FEATURE(raw_super, mask) \ ((raw_super->feature & cpu_to_le32(mask)) != 0) @@ -1175,6 +1176,7 @@ enum iostat_type { /* other */ FS_DISCARD_IO, /* discard */ FS_FLUSH_IO, /* flush */ + FS_ZONE_RESET_IO, /* zone reset */ NR_IO_TYPE, }; @@ -1217,6 +1219,11 @@ struct f2fs_bio_info { struct bio *bio; /* bios to merge */ sector_t last_block_in_bio; /* last block number */ struct f2fs_io_info fio; /* store buffered io info. */ +#ifdef CONFIG_BLK_DEV_ZONED + struct completion zone_wait; /* condition value for the previous open zone to close */ + struct bio *zone_pending_bio; /* pending bio for the previous zone */ + void *bi_private; /* previous bi_private for pending bio */ +#endif struct f2fs_rwsem io_rwsem; /* blocking op for bio */ spinlock_t io_lock; /* serialize DATA/NODE IOs */ struct list_head io_list; /* track fios */ @@ -1370,6 +1377,12 @@ enum { MEMORY_MODE_LOW, /* memory mode for low memry devices */ }; +enum errors_option { + MOUNT_ERRORS_READONLY, /* remount fs ro on errors */ + MOUNT_ERRORS_CONTINUE, /* continue on errors */ + MOUNT_ERRORS_PANIC, /* panic on errors */ +}; + static inline int f2fs_test_bit(unsigned int nr, char *addr); static inline void f2fs_set_bit(unsigned int nr, char *addr); static inline void f2fs_clear_bit(unsigned int nr, char *addr); @@ -1427,6 +1440,8 @@ struct compress_data { #define F2FS_COMPRESSED_PAGE_MAGIC 0xF5F2C000 +#define F2FS_ZSTD_DEFAULT_CLEVEL 1 + #define COMPRESS_LEVEL_OFFSET 8 /* compress context */ @@ -1721,8 +1736,14 @@ struct f2fs_sb_info { struct workqueue_struct *post_read_wq; /* post read workqueue */ - unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */ - spinlock_t error_lock; /* protect errors array */ + /* + * If we are in irq context, let's update error information into + * on-disk superblock in the work. + */ + struct work_struct s_error_work; + unsigned char errors[MAX_F2FS_ERRORS]; /* error flags */ + unsigned char stop_reason[MAX_STOP_REASON]; /* stop reason */ + spinlock_t error_lock; /* protect errors/stop_reason array */ bool error_dirty; /* errors of sb is dirty */ struct kmem_cache *inline_xattr_slab; /* inline xattr entry */ @@ -2941,6 +2962,8 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr) #define F2FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define F2FS_CASEFOLD_FL 0x40000000 /* Casefolded file */ +#define F2FS_QUOTA_DEFAULT_FL (F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL) + /* Flags that should be inherited by new inodes from their parent. */ #define F2FS_FL_INHERITED (F2FS_SYNC_FL | F2FS_NODUMP_FL | F2FS_NOATIME_FL | \ F2FS_DIRSYNC_FL | F2FS_PROJINHERIT_FL | \ @@ -3394,6 +3417,8 @@ static inline int get_inline_xattr_addrs(struct inode *inode) ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) +#define F2FS_MIN_EXTRA_ATTR_SIZE (sizeof(__le32)) + #define F2FS_TOTAL_EXTRA_ATTR_SIZE \ (offsetof(struct f2fs_inode, i_extra_end) - \ offsetof(struct f2fs_inode, i_extra_isize)) \ @@ -3432,7 +3457,6 @@ static inline bool __is_valid_data_blkaddr(block_t blkaddr) * file.c */ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); -void f2fs_truncate_data_blocks(struct dnode_of_data *dn); int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate_blocks(struct inode *inode, u64 from, bool lock); int f2fs_truncate(struct inode *inode); @@ -3541,9 +3565,11 @@ int f2fs_enable_quota_files(struct f2fs_sb_info *sbi, bool rdonly); int f2fs_quota_sync(struct super_block *sb, int type); loff_t max_file_blocks(struct inode *inode); void f2fs_quota_off_umount(struct super_block *sb); -void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason); void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag); +void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason, + bool irq_context); void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error); +void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error); int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover); int f2fs_sync_fs(struct super_block *sb, int sync); int f2fs_sanity_check_ckpt(struct f2fs_sb_info *sbi); @@ -3815,7 +3841,7 @@ void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi); block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode); int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control); void f2fs_build_gc_manager(struct f2fs_sb_info *sbi); -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count); +int f2fs_resize_fs(struct file *filp, __u64 block_count); int __init f2fs_create_garbage_collection_cache(void); void f2fs_destroy_garbage_collection_cache(void); /* victim selection function for cleaning and SSR */ @@ -4213,6 +4239,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); +bool f2fs_is_compress_level_valid(int alg, int lvl); int __init f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); @@ -4277,6 +4304,7 @@ static inline bool f2fs_is_compress_backend_ready(struct inode *inode) /* not support compression */ return false; } +static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } static inline struct page *f2fs_compress_control_page(struct page *page) { WARN_ON_ONCE(1); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 2435111a8532..093039dee992 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -149,8 +149,6 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf) zero_user_segment(page, offset, PAGE_SIZE); } set_page_dirty(page); - if (!PageUptodate(page)) - SetPageUptodate(page); f2fs_update_iostat(sbi, inode, APP_MAPPED_IO, F2FS_BLKSIZE); f2fs_update_time(sbi, REQ_TIME); @@ -546,7 +544,8 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) if (err) return err; - filp->f_mode |= FMODE_NOWAIT; + filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC; + filp->f_mode |= FMODE_CAN_ODIRECT; return dquot_file_open(inode, filp); } @@ -627,11 +626,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) dn->ofs_in_node, nr_free); } -void f2fs_truncate_data_blocks(struct dnode_of_data *dn) -{ - f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); -} - static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { @@ -2225,7 +2219,6 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) ret = 0; f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); trace_f2fs_shutdown(sbi, in, ret); } return ret; @@ -2238,7 +2231,6 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (ret) goto out; f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); thaw_bdev(sb->s_bdev); break; case F2FS_GOING_DOWN_METASYNC: @@ -2247,16 +2239,13 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) if (ret) goto out; f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_NOSYNC: f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_METAFLUSH: f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_SHUTDOWN); - set_sbi_flag(sbi, SBI_IS_SHUTDOWN); break; case F2FS_GOING_DOWN_NEED_FSCK: set_sbi_flag(sbi, SBI_NEED_FSCK); @@ -2593,6 +2582,11 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi, inode_lock(inode); + if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) { + err = -EINVAL; + goto unlock_out; + } + /* if in-place-update policy is enabled, don't waste time here */ set_inode_flag(inode, FI_OPU_WRITE); if (f2fs_should_update_inplace(inode, NULL)) { @@ -2717,6 +2711,7 @@ clear_out: clear_inode_flag(inode, FI_SKIP_WRITES); out: clear_inode_flag(inode, FI_OPU_WRITE); +unlock_out: inode_unlock(inode); if (!err) range->len = (u64)total << PAGE_SHIFT; @@ -2876,6 +2871,17 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, f2fs_up_write(&F2FS_I(dst)->i_gc_rwsem[WRITE]); out_src: f2fs_up_write(&F2FS_I(src)->i_gc_rwsem[WRITE]); + if (ret) + goto out_unlock; + + src->i_mtime = src->i_ctime = current_time(src); + f2fs_mark_inode_dirty_sync(src, false); + if (src != dst) { + dst->i_mtime = dst->i_ctime = current_time(dst); + f2fs_mark_inode_dirty_sync(dst, false); + } + f2fs_update_time(sbi, REQ_TIME); + out_unlock: if (src != dst) inode_unlock(dst); @@ -3278,7 +3284,7 @@ static int f2fs_ioc_resize_fs(struct file *filp, unsigned long arg) sizeof(block_count))) return -EFAULT; - return f2fs_resize_fs(sbi, block_count); + return f2fs_resize_fs(filp, block_count); } static int f2fs_ioc_enable_verity(struct file *filp, unsigned long arg) @@ -3375,18 +3381,29 @@ out: return err; } -static int f2fs_get_compress_blocks(struct file *filp, unsigned long arg) +static int f2fs_get_compress_blocks(struct inode *inode, __u64 *blocks) { - struct inode *inode = file_inode(filp); - __u64 blocks; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) return -EINVAL; - blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks); + *blocks = atomic_read(&F2FS_I(inode)->i_compr_blocks); + + return 0; +} + +static int f2fs_ioc_get_compress_blocks(struct file *filp, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + __u64 blocks; + int ret; + + ret = f2fs_get_compress_blocks(inode, &blocks); + if (ret < 0) + return ret; + return put_user(blocks, (u64 __user *)arg); } @@ -3455,7 +3472,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) int ret; int writecount; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3468,7 +3485,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3488,13 +3505,15 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg) if (ret) goto out; + if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) { + ret = -EPERM; + goto out; + } + set_inode_flag(inode, FI_COMPRESS_RELEASED); inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, true); - if (!atomic_read(&F2FS_I(inode)->i_compr_blocks)) - goto out; - f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); @@ -3625,7 +3644,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) unsigned int reserved_blocks = 0; int ret; - if (!f2fs_sb_has_compression(F2FS_I_SB(inode))) + if (!f2fs_sb_has_compression(sbi)) return -EOPNOTSUPP; if (!f2fs_compressed_file(inode)) @@ -3641,7 +3660,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) goto out; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -4035,7 +4054,7 @@ static int f2fs_ioc_decompress_file(struct file *filp) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); @@ -4110,7 +4129,7 @@ static int f2fs_ioc_compress_file(struct file *filp) if (!f2fs_compressed_file(inode)) return -EINVAL; - f2fs_balance_fs(F2FS_I_SB(inode), true); + f2fs_balance_fs(sbi, true); file_start_write(filp); inode_lock(inode); @@ -4238,7 +4257,7 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FS_IOC_SETFSLABEL: return f2fs_ioc_setfslabel(filp, arg); case F2FS_IOC_GET_COMPRESS_BLOCKS: - return f2fs_get_compress_blocks(filp, arg); + return f2fs_ioc_get_compress_blocks(filp, arg); case F2FS_IOC_RELEASE_COMPRESS_BLOCKS: return f2fs_release_compress_blocks(filp, arg); case F2FS_IOC_RESERVE_COMPRESS_BLOCKS: diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 61c5f9d26018..01effd3fcb6c 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -59,7 +59,7 @@ static int gc_thread_func(void *data) if (gc_th->gc_wake) gc_th->gc_wake = false; - if (try_to_freeze()) { + if (try_to_freeze() || f2fs_readonly(sbi->sb)) { stat_other_skip_bggc_count(sbi); continue; } @@ -1797,7 +1797,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control) { int gc_type = gc_control->init_gc_type; unsigned int segno = gc_control->victim_segno; - int sec_freed = 0, seg_freed = 0, total_freed = 0; + int sec_freed = 0, seg_freed = 0, total_freed = 0, total_sec_freed = 0; int ret = 0; struct cp_control cpc; struct gc_inode_list gc_list = { @@ -1842,6 +1842,8 @@ gc_more: ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; + /* Reset due to checkpoint */ + sec_freed = 0; } } @@ -1866,15 +1868,17 @@ retry: gc_control->should_migrate_blocks); total_freed += seg_freed; - if (seg_freed == f2fs_usable_segs_in_sec(sbi, segno)) + if (seg_freed == f2fs_usable_segs_in_sec(sbi, segno)) { sec_freed++; + total_sec_freed++; + } if (gc_type == FG_GC) { sbi->cur_victim_sec = NULL_SEGNO; if (has_enough_free_secs(sbi, sec_freed, 0)) { if (!gc_control->no_bg_gc && - sec_freed < gc_control->nr_free_secs) + total_sec_freed < gc_control->nr_free_secs) goto go_gc_more; goto stop; } @@ -1901,6 +1905,8 @@ retry: ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; + /* Reset due to checkpoint */ + sec_freed = 0; } go_gc_more: segno = NULL_SEGNO; @@ -1913,7 +1919,7 @@ stop: if (gc_type == FG_GC) f2fs_unpin_all_sections(sbi, true); - trace_f2fs_gc_end(sbi->sb, ret, total_freed, sec_freed, + trace_f2fs_gc_end(sbi->sb, ret, total_freed, total_sec_freed, get_pages(sbi, F2FS_DIRTY_NODES), get_pages(sbi, F2FS_DIRTY_DENTS), get_pages(sbi, F2FS_DIRTY_IMETA), @@ -1927,7 +1933,7 @@ stop: put_gc_inode(&gc_list); if (gc_control->err_gc_skipped && !ret) - ret = sec_freed ? 0 : -EAGAIN; + ret = total_sec_freed ? 0 : -EAGAIN; return ret; } @@ -2099,8 +2105,9 @@ static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) } } -int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) +int f2fs_resize_fs(struct file *filp, __u64 block_count) { + struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 old_block_count, shrunk_blocks; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; unsigned int secs; @@ -2138,12 +2145,18 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) return -EINVAL; } + err = mnt_want_write_file(filp); + if (err) + return err; + shrunk_blocks = old_block_count - block_count; secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); /* stop other GC */ - if (!f2fs_down_write_trylock(&sbi->gc_lock)) - return -EAGAIN; + if (!f2fs_down_write_trylock(&sbi->gc_lock)) { + err = -EAGAIN; + goto out_drop_write; + } /* stop CP to protect MAIN_SEC in free_segment_range */ f2fs_lock_op(sbi); @@ -2163,10 +2176,20 @@ int f2fs_resize_fs(struct f2fs_sb_info *sbi, __u64 block_count) out_unlock: f2fs_unlock_op(sbi); f2fs_up_write(&sbi->gc_lock); +out_drop_write: + mnt_drop_write_file(filp); if (err) return err; - freeze_super(sbi->sb); + err = freeze_super(sbi->sb); + if (err) + return err; + + if (f2fs_readonly(sbi->sb)) { + thaw_super(sbi->sb); + return -EROFS; + } + f2fs_down_write(&sbi->gc_lock); f2fs_down_write(&sbi->cp_global_sem); diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index cf4327ad106c..09e986b050c6 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -10,6 +10,8 @@ #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/sched/mm.h> +#include <linux/lz4.h> +#include <linux/zstd.h> #include "f2fs.h" #include "node.h" @@ -202,6 +204,80 @@ void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, struct page *page) ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page)); } +static bool sanity_check_compress_inode(struct inode *inode, + struct f2fs_inode *ri) +{ + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); + unsigned char clevel; + + if (ri->i_compress_algorithm >= COMPRESS_MAX) { + f2fs_warn(sbi, + "%s: inode (ino=%lx) has unsupported compress algorithm: %u, run fsck to fix", + __func__, inode->i_ino, ri->i_compress_algorithm); + goto err; + } + if (le64_to_cpu(ri->i_compr_blocks) > + SECTOR_TO_BLOCK(inode->i_blocks)) { + f2fs_warn(sbi, + "%s: inode (ino=%lx) has inconsistent i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix", + __func__, inode->i_ino, le64_to_cpu(ri->i_compr_blocks), + SECTOR_TO_BLOCK(inode->i_blocks)); + goto err; + } + if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE || + ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) { + f2fs_warn(sbi, + "%s: inode (ino=%lx) has unsupported log cluster size: %u, run fsck to fix", + __func__, inode->i_ino, ri->i_log_cluster_size); + goto err; + } + + clevel = le16_to_cpu(ri->i_compress_flag) >> + COMPRESS_LEVEL_OFFSET; + switch (ri->i_compress_algorithm) { + case COMPRESS_LZO: +#ifdef CONFIG_F2FS_FS_LZO + if (clevel) + goto err_level; +#endif + break; + case COMPRESS_LZORLE: +#ifdef CONFIG_F2FS_FS_LZORLE + if (clevel) + goto err_level; +#endif + break; + case COMPRESS_LZ4: +#ifdef CONFIG_F2FS_FS_LZ4 +#ifdef CONFIG_F2FS_FS_LZ4HC + if (clevel && + (clevel < LZ4HC_MIN_CLEVEL || clevel > LZ4HC_MAX_CLEVEL)) + goto err_level; +#else + if (clevel) + goto err_level; +#endif +#endif + break; + case COMPRESS_ZSTD: +#ifdef CONFIG_F2FS_FS_ZSTD + if (clevel < zstd_min_clevel() || clevel > zstd_max_clevel()) + goto err_level; +#endif + break; + default: + goto err_level; + } + + return true; +err_level: + f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported compress level: %u, run fsck to fix", + __func__, inode->i_ino, clevel); +err: + set_sbi_flag(sbi, SBI_NEED_FSCK); + return false; +} + static bool sanity_check_inode(struct inode *inode, struct page *node_page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); @@ -225,41 +301,77 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } - if (f2fs_sb_has_flexible_inline_xattr(sbi) - && !f2fs_has_extra_attr(inode)) { + if (f2fs_has_extra_attr(inode)) { + if (!f2fs_sb_has_extra_attr(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off", + __func__, inode->i_ino); + return false; + } + if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE || + fi->i_extra_isize < F2FS_MIN_EXTRA_ATTR_SIZE || + fi->i_extra_isize % sizeof(__le32)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, max: %zu", + __func__, inode->i_ino, fi->i_extra_isize, + F2FS_TOTAL_EXTRA_ATTR_SIZE); + return false; + } + if (f2fs_sb_has_flexible_inline_xattr(sbi) && + f2fs_has_inline_xattr(inode) && + (!fi->i_inline_xattr_size || + fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %zu", + __func__, inode->i_ino, fi->i_inline_xattr_size, + MAX_INLINE_XATTR_SIZE); + return false; + } + if (f2fs_sb_has_compression(sbi) && + fi->i_flags & F2FS_COMPR_FL && + F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, + i_compress_flag)) { + if (!sanity_check_compress_inode(inode, ri)) + return false; + } + } else if (f2fs_sb_has_flexible_inline_xattr(sbi)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_warn(sbi, "%s: corrupted inode ino=%lx, run fsck to fix.", __func__, inode->i_ino); return false; } - if (f2fs_has_extra_attr(inode) && - !f2fs_sb_has_extra_attr(sbi)) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) is with extra_attr, but extra_attr feature is off", - __func__, inode->i_ino); - return false; - } - - if (fi->i_extra_isize > F2FS_TOTAL_EXTRA_ATTR_SIZE || - fi->i_extra_isize % sizeof(__le32)) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_extra_isize: %d, max: %zu", - __func__, inode->i_ino, fi->i_extra_isize, - F2FS_TOTAL_EXTRA_ATTR_SIZE); - return false; - } - - if (f2fs_has_extra_attr(inode) && - f2fs_sb_has_flexible_inline_xattr(sbi) && - f2fs_has_inline_xattr(inode) && - (!fi->i_inline_xattr_size || - fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) has corrupted i_inline_xattr_size: %d, max: %zu", - __func__, inode->i_ino, fi->i_inline_xattr_size, - MAX_INLINE_XATTR_SIZE); - return false; + if (!f2fs_sb_has_extra_attr(sbi)) { + if (f2fs_sb_has_project_quota(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", + __func__, inode->i_ino, F2FS_FEATURE_PRJQUOTA); + return false; + } + if (f2fs_sb_has_inode_chksum(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", + __func__, inode->i_ino, F2FS_FEATURE_INODE_CHKSUM); + return false; + } + if (f2fs_sb_has_flexible_inline_xattr(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", + __func__, inode->i_ino, F2FS_FEATURE_FLEXIBLE_INLINE_XATTR); + return false; + } + if (f2fs_sb_has_inode_crtime(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", + __func__, inode->i_ino, F2FS_FEATURE_INODE_CRTIME); + return false; + } + if (f2fs_sb_has_compression(sbi)) { + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_warn(sbi, "%s: corrupted inode ino=%lx, wrong feature flag: %u, run fsck to fix.", + __func__, inode->i_ino, F2FS_FEATURE_COMPRESSION); + return false; + } } if (f2fs_sanity_check_inline_data(inode)) { @@ -283,39 +395,6 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page) return false; } - if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) && - fi->i_flags & F2FS_COMPR_FL && - F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, - i_log_cluster_size)) { - if (ri->i_compress_algorithm >= COMPRESS_MAX) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported " - "compress algorithm: %u, run fsck to fix", - __func__, inode->i_ino, - ri->i_compress_algorithm); - return false; - } - if (le64_to_cpu(ri->i_compr_blocks) > - SECTOR_TO_BLOCK(inode->i_blocks)) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) has inconsistent " - "i_compr_blocks:%llu, i_blocks:%llu, run fsck to fix", - __func__, inode->i_ino, - le64_to_cpu(ri->i_compr_blocks), - SECTOR_TO_BLOCK(inode->i_blocks)); - return false; - } - if (ri->i_log_cluster_size < MIN_COMPRESS_LOG_SIZE || - ri->i_log_cluster_size > MAX_COMPRESS_LOG_SIZE) { - set_sbi_flag(sbi, SBI_NEED_FSCK); - f2fs_warn(sbi, "%s: inode (ino=%lx) has unsupported " - "log cluster size: %u, run fsck to fix", - __func__, inode->i_ino, - ri->i_log_cluster_size); - return false; - } - } - return true; } @@ -442,7 +521,7 @@ static int do_read_inode(struct inode *inode) if (f2fs_has_extra_attr(inode) && f2fs_sb_has_compression(sbi) && (fi->i_flags & F2FS_COMPR_FL)) { if (F2FS_FITS_IN_INODE(ri, fi->i_extra_isize, - i_log_cluster_size)) { + i_compress_flag)) { unsigned short compress_flag; atomic_set(&fi->i_compr_blocks, @@ -680,7 +759,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) if (f2fs_sb_has_compression(F2FS_I_SB(inode)) && F2FS_FITS_IN_INODE(ri, F2FS_I(inode)->i_extra_isize, - i_log_cluster_size)) { + i_compress_flag)) { unsigned short compress_flag; ri->i_compr_blocks = diff --git a/fs/f2fs/iostat.c b/fs/f2fs/iostat.c index 3d5bfb1ad585..f8703038e1d8 100644 --- a/fs/f2fs/iostat.c +++ b/fs/f2fs/iostat.c @@ -80,6 +80,7 @@ int __maybe_unused iostat_info_seq_show(struct seq_file *seq, void *offset) seq_puts(seq, "[OTHER]\n"); IOSTAT_INFO_SHOW("fs discard", FS_DISCARD_IO); IOSTAT_INFO_SHOW("fs flush", FS_FLUSH_IO); + IOSTAT_INFO_SHOW("fs zone reset", FS_ZONE_RESET_IO); return 0; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index ad597b417fea..bee0568888da 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -23,7 +23,7 @@ #include <trace/events/f2fs.h> static inline bool is_extension_exist(const unsigned char *s, const char *sub, - bool tmp_ext) + bool tmp_ext, bool tmp_dot) { size_t slen = strlen(s); size_t sublen = strlen(sub); @@ -49,13 +49,27 @@ static inline bool is_extension_exist(const unsigned char *s, const char *sub, for (i = 1; i < slen - sublen; i++) { if (s[i] != '.') continue; - if (!strncasecmp(s + i + 1, sub, sublen)) - return true; + if (!strncasecmp(s + i + 1, sub, sublen)) { + if (!tmp_dot) + return true; + if (i == slen - sublen - 1 || s[i + 1 + sublen] == '.') + return true; + } } return false; } +static inline bool is_temperature_extension(const unsigned char *s, const char *sub) +{ + return is_extension_exist(s, sub, true, false); +} + +static inline bool is_compress_extension(const unsigned char *s, const char *sub) +{ + return is_extension_exist(s, sub, true, true); +} + int f2fs_update_extension_list(struct f2fs_sb_info *sbi, const char *name, bool hot, bool set) { @@ -148,7 +162,7 @@ static void set_compress_new_inode(struct f2fs_sb_info *sbi, struct inode *dir, cold_count = le32_to_cpu(sbi->raw_super->extension_count); hot_count = sbi->raw_super->hot_ext_count; for (i = cold_count; i < cold_count + hot_count; i++) - if (is_extension_exist(name, extlist[i], false)) + if (is_temperature_extension(name, extlist[i])) break; f2fs_up_read(&sbi->sb_lock); if (i < (cold_count + hot_count)) @@ -156,12 +170,12 @@ static void set_compress_new_inode(struct f2fs_sb_info *sbi, struct inode *dir, /* Don't compress unallowed extension. */ for (i = 0; i < noext_cnt; i++) - if (is_extension_exist(name, noext[i], false)) + if (is_compress_extension(name, noext[i])) return; /* Compress wanting extension. */ for (i = 0; i < ext_cnt; i++) { - if (is_extension_exist(name, ext[i], false)) { + if (is_compress_extension(name, ext[i])) { set_compress_context(inode); return; } @@ -189,7 +203,7 @@ static void set_file_temperature(struct f2fs_sb_info *sbi, struct inode *inode, cold_count = le32_to_cpu(sbi->raw_super->extension_count); hot_count = sbi->raw_super->hot_ext_count; for (i = 0; i < cold_count + hot_count; i++) - if (is_extension_exist(name, extlist[i], true)) + if (is_temperature_extension(name, extlist[i])) break; f2fs_up_read(&sbi->sb_lock); @@ -576,8 +590,8 @@ out_splice: } #endif new = d_splice_alias(inode, dentry); - err = PTR_ERR_OR_ZERO(new); - trace_f2fs_lookup_end(dir, dentry, ino, !new ? -ENOENT : err); + trace_f2fs_lookup_end(dir, !IS_ERR_OR_NULL(new) ? new : dentry, + ino, IS_ERR(new) ? PTR_ERR(new) : err); return new; out_iput: iput(inode); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index bd1dad523796..ee2e1dd64f25 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -925,6 +925,7 @@ static int truncate_node(struct dnode_of_data *dn) static int truncate_dnode(struct dnode_of_data *dn) { + struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *page; int err; @@ -932,19 +933,30 @@ static int truncate_dnode(struct dnode_of_data *dn) return 1; /* get direct node */ - page = f2fs_get_node_page(F2FS_I_SB(dn->inode), dn->nid); + page = f2fs_get_node_page(sbi, dn->nid); if (PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); + if (IS_INODE(page) || ino_of_node(page) != dn->inode->i_ino) { + f2fs_err(sbi, "incorrect node reference, ino: %lu, nid: %u, ino_of_node: %u", + dn->inode->i_ino, dn->nid, ino_of_node(page)); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_INVALID_NODE_REFERENCE); + f2fs_put_page(page, 1); + return -EFSCORRUPTED; + } + /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; - f2fs_truncate_data_blocks(dn); + f2fs_truncate_data_blocks_range(dn, ADDRS_PER_BLOCK(dn->inode)); err = truncate_node(dn); - if (err) + if (err) { + f2fs_put_page(page, 1); return err; + } return 1; } @@ -1596,6 +1608,9 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, trace_f2fs_writepage(page, NODE); if (unlikely(f2fs_cp_error(sbi))) { + /* keep node pages in remount-ro mode */ + if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) + goto redirty_out; ClearPageUptodate(page); dec_page_count(sbi, F2FS_DIRTY_NODES); unlock_page(page); @@ -2063,7 +2078,6 @@ int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, struct list_head *head = &sbi->fsync_node_list; unsigned long flags; unsigned int cur_seq_id = 0; - int ret2, ret = 0; while (seq_id && cur_seq_id < seq_id) { spin_lock_irqsave(&sbi->fsync_node_lock, flags); @@ -2084,16 +2098,9 @@ int f2fs_wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, f2fs_wait_on_page_writeback(page, NODE, true, false); put_page(page); - - if (ret) - break; } - ret2 = filemap_check_errors(NODE_MAPPING(sbi)); - if (!ret) - ret = ret2; - - return ret; + return filemap_check_errors(NODE_MAPPING(sbi)); } static int f2fs_write_node_pages(struct address_space *mapping, @@ -3065,7 +3072,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; - struct nat_entry_set *setvec[SETVEC_SIZE]; + struct nat_entry_set *setvec[NAT_VEC_SIZE]; struct nat_entry_set *set, *tmp; unsigned int found; nid_t set_idx = 0; @@ -3098,7 +3105,7 @@ int f2fs_flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) remove_nats_in_journal(sbi); while ((found = __gang_lookup_nat_set(nm_i, - set_idx, SETVEC_SIZE, setvec))) { + set_idx, NAT_VEC_SIZE, setvec))) { unsigned idx; set_idx = setvec[found - 1]->set + 1; @@ -3319,8 +3326,9 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; - struct nat_entry *natvec[NATVEC_SIZE]; - struct nat_entry_set *setvec[SETVEC_SIZE]; + void *vec[NAT_VEC_SIZE]; + struct nat_entry **natvec = (struct nat_entry **)vec; + struct nat_entry_set **setvec = (struct nat_entry_set **)vec; nid_t nid = 0; unsigned int found; @@ -3343,7 +3351,7 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) /* destroy nat cache */ f2fs_down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, - nid, NATVEC_SIZE, natvec))) { + nid, NAT_VEC_SIZE, natvec))) { unsigned idx; nid = nat_get_nid(natvec[found - 1]) + 1; @@ -3359,8 +3367,9 @@ void f2fs_destroy_node_manager(struct f2fs_sb_info *sbi) /* destroy nat set cache */ nid = 0; + memset(vec, 0, sizeof(void *) * NAT_VEC_SIZE); while ((found = __gang_lookup_nat_set(nm_i, - nid, SETVEC_SIZE, setvec))) { + nid, NAT_VEC_SIZE, setvec))) { unsigned idx; nid = setvec[found - 1]->set + 1; diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h index 906fb67a99da..5bd16a95eef8 100644 --- a/fs/f2fs/node.h +++ b/fs/f2fs/node.h @@ -35,8 +35,7 @@ #define DEF_RF_NODE_BLOCKS 0 /* vector size for gang look-up from nat cache that consists of radix tree */ -#define NATVEC_SIZE 64 -#define SETVEC_SIZE 32 +#define NAT_VEC_SIZE 32 /* return value for read_node_page */ #define LOCKED_PAGE 1 diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 58c1a0096f7d..4e7d4ceeb084 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -360,21 +360,63 @@ static unsigned int adjust_por_ra_blocks(struct f2fs_sb_info *sbi, return ra_blocks; } +/* Detect looped node chain with Floyd's cycle detection algorithm. */ +static int sanity_check_node_chain(struct f2fs_sb_info *sbi, block_t blkaddr, + block_t *blkaddr_fast, bool *is_detecting) +{ + unsigned int ra_blocks = RECOVERY_MAX_RA_BLOCKS; + struct page *page = NULL; + int i; + + if (!*is_detecting) + return 0; + + for (i = 0; i < 2; i++) { + if (!f2fs_is_valid_blkaddr(sbi, *blkaddr_fast, META_POR)) { + *is_detecting = false; + return 0; + } + + page = f2fs_get_tmp_page(sbi, *blkaddr_fast); + if (IS_ERR(page)) + return PTR_ERR(page); + + if (!is_recoverable_dnode(page)) { + f2fs_put_page(page, 1); + *is_detecting = false; + return 0; + } + + ra_blocks = adjust_por_ra_blocks(sbi, ra_blocks, *blkaddr_fast, + next_blkaddr_of_node(page)); + + *blkaddr_fast = next_blkaddr_of_node(page); + f2fs_put_page(page, 1); + + f2fs_ra_meta_pages_cond(sbi, *blkaddr_fast, ra_blocks); + } + + if (*blkaddr_fast == blkaddr) { + f2fs_notice(sbi, "%s: Detect looped node chain on blkaddr:%u." + " Run fsck to fix it.", __func__, blkaddr); + return -EINVAL; + } + return 0; +} + static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, bool check_only) { struct curseg_info *curseg; struct page *page = NULL; - block_t blkaddr; - unsigned int loop_cnt = 0; - unsigned int ra_blocks = RECOVERY_MAX_RA_BLOCKS; - unsigned int free_blocks = MAIN_SEGS(sbi) * sbi->blocks_per_seg - - valid_user_blocks(sbi); + block_t blkaddr, blkaddr_fast; + bool is_detecting = true; int err = 0; /* get node pages in the current segment */ curseg = CURSEG_I(sbi, CURSEG_WARM_NODE); blkaddr = NEXT_FREE_BLKADDR(sbi, curseg); + blkaddr_fast = blkaddr; while (1) { struct fsync_inode_entry *entry; @@ -418,10 +460,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, quota_inode); if (IS_ERR(entry)) { err = PTR_ERR(entry); - if (err == -ENOENT) { - err = 0; + if (err == -ENOENT) goto next; - } f2fs_put_page(page, 1); break; } @@ -431,25 +471,14 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head, if (IS_INODE(page) && is_dent_dnode(page)) entry->last_dentry = blkaddr; next: - /* sanity check in order to detect looped node chain */ - if (++loop_cnt >= free_blocks || - blkaddr == next_blkaddr_of_node(page)) { - f2fs_notice(sbi, "%s: detect looped node chain, blkaddr:%u, next:%u", - __func__, blkaddr, - next_blkaddr_of_node(page)); - f2fs_put_page(page, 1); - err = -EINVAL; - break; - } - - ra_blocks = adjust_por_ra_blocks(sbi, ra_blocks, blkaddr, - next_blkaddr_of_node(page)); - /* check next segment */ blkaddr = next_blkaddr_of_node(page); f2fs_put_page(page, 1); - f2fs_ra_meta_pages_cond(sbi, blkaddr, ra_blocks); + err = sanity_check_node_chain(sbi, blkaddr, &blkaddr_fast, + &is_detecting); + if (err) + break; } return err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 6db410f1bb8c..0457d620011f 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1196,6 +1196,45 @@ static void __init_discard_policy(struct f2fs_sb_info *sbi, static void __update_discard_tree_range(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t lstart, block_t start, block_t len); + +#ifdef CONFIG_BLK_DEV_ZONED +static void __submit_zone_reset_cmd(struct f2fs_sb_info *sbi, + struct discard_cmd *dc, blk_opf_t flag, + struct list_head *wait_list, + unsigned int *issued) +{ + struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info; + struct block_device *bdev = dc->bdev; + struct bio *bio = bio_alloc(bdev, 0, REQ_OP_ZONE_RESET | flag, GFP_NOFS); + unsigned long flags; + + trace_f2fs_issue_reset_zone(bdev, dc->di.start); + + spin_lock_irqsave(&dc->lock, flags); + dc->state = D_SUBMIT; + dc->bio_ref++; + spin_unlock_irqrestore(&dc->lock, flags); + + if (issued) + (*issued)++; + + atomic_inc(&dcc->queued_discard); + dc->queued++; + list_move_tail(&dc->list, wait_list); + + /* sanity check on discard range */ + __check_sit_bitmap(sbi, dc->di.lstart, dc->di.lstart + dc->di.len); + + bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(dc->di.start); + bio->bi_private = dc; + bio->bi_end_io = f2fs_submit_discard_endio; + submit_bio(bio); + + atomic_inc(&dcc->issued_discard); + f2fs_update_iostat(sbi, NULL, FS_ZONE_RESET_IO, dc->di.len * F2FS_BLKSIZE); +} +#endif + /* this function is copied from blkdev_issue_discard from block/blk-lib.c */ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, struct discard_policy *dpolicy, @@ -1217,6 +1256,13 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi, if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) return 0; +#ifdef CONFIG_BLK_DEV_ZONED + if (f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(bdev)) { + __submit_zone_reset_cmd(sbi, dc, flag, wait_list, issued); + return 0; + } +#endif + trace_f2fs_issue_discard(bdev, dc->di.start, dc->di.len); lstart = dc->di.lstart; @@ -1461,6 +1507,19 @@ static void __update_discard_tree_range(struct f2fs_sb_info *sbi, } } +#ifdef CONFIG_BLK_DEV_ZONED +static void __queue_zone_reset_cmd(struct f2fs_sb_info *sbi, + struct block_device *bdev, block_t blkstart, block_t lblkstart, + block_t blklen) +{ + trace_f2fs_queue_reset_zone(bdev, blkstart); + + mutex_lock(&SM_I(sbi)->dcc_info->cmd_lock); + __insert_discard_cmd(sbi, bdev, lblkstart, blkstart, blklen); + mutex_unlock(&SM_I(sbi)->dcc_info->cmd_lock); +} +#endif + static void __queue_discard_cmd(struct f2fs_sb_info *sbi, struct block_device *bdev, block_t blkstart, block_t blklen) { @@ -1724,6 +1783,19 @@ static void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr) mutex_lock(&dcc->cmd_lock); dc = __lookup_discard_cmd(sbi, blkaddr); +#ifdef CONFIG_BLK_DEV_ZONED + if (dc && f2fs_sb_has_blkzoned(sbi) && bdev_is_zoned(dc->bdev)) { + /* force submit zone reset */ + if (dc->state == D_PREP) + __submit_zone_reset_cmd(sbi, dc, REQ_SYNC, + &dcc->wait_list, NULL); + dc->ref++; + mutex_unlock(&dcc->cmd_lock); + /* wait zone reset */ + __wait_one_discard_bio(sbi, dc); + return; + } +#endif if (dc) { if (dc->state == D_PREP) { __punch_discard_cmd(sbi, dc, blkaddr); @@ -1876,9 +1948,15 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi, blkstart, blklen); return -EIO; } - trace_f2fs_issue_reset_zone(bdev, blkstart); - return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, - sector, nr_sects, GFP_NOFS); + + if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) { + trace_f2fs_issue_reset_zone(bdev, blkstart); + return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET, + sector, nr_sects, GFP_NOFS); + } + + __queue_zone_reset_cmd(sbi, bdev, blkstart, lblkstart, blklen); + return 0; } /* For conventional zones, use regular discard if supported */ @@ -2115,7 +2193,7 @@ find_next: len = next_pos - cur_pos; if (f2fs_sb_has_blkzoned(sbi) || - (force && len < cpc->trim_minlen)) + !force || len < cpc->trim_minlen) goto skip; f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos, @@ -4768,17 +4846,17 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi, { unsigned int wp_segno, wp_blkoff, zone_secno, zone_segno, segno; block_t zone_block, wp_block, last_valid_block; - unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT; int i, s, b, ret; struct seg_entry *se; if (zone->type != BLK_ZONE_TYPE_SEQWRITE_REQ) return 0; - wp_block = fdev->start_blk + (zone->wp >> log_sectors_per_block); + wp_block = fdev->start_blk + (zone->wp >> sbi->log_sectors_per_block); wp_segno = GET_SEGNO(sbi, wp_block); wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno); - zone_block = fdev->start_blk + (zone->start >> log_sectors_per_block); + zone_block = fdev->start_blk + (zone->start >> + sbi->log_sectors_per_block); zone_segno = GET_SEGNO(sbi, zone_block); zone_secno = GET_SEC_FROM_SEG(sbi, zone_segno); @@ -4811,39 +4889,52 @@ static int check_zone_write_pointer(struct f2fs_sb_info *sbi, } /* - * If last valid block is beyond the write pointer, report the - * inconsistency. This inconsistency does not cause write error - * because the zone will not be selected for write operation until - * it get discarded. Just report it. + * The write pointer matches with the valid blocks or + * already points to the end of the zone. */ - if (last_valid_block >= wp_block) { - f2fs_notice(sbi, "Valid block beyond write pointer: " - "valid block[0x%x,0x%x] wp[0x%x,0x%x]", - GET_SEGNO(sbi, last_valid_block), - GET_BLKOFF_FROM_SEG0(sbi, last_valid_block), - wp_segno, wp_blkoff); + if ((last_valid_block + 1 == wp_block) || + (zone->wp == zone->start + zone->len)) return 0; - } - /* - * If there is no valid block in the zone and if write pointer is - * not at zone start, reset the write pointer. - */ - if (last_valid_block + 1 == zone_block && zone->wp != zone->start) { + if (last_valid_block + 1 == zone_block) { + /* + * If there is no valid block in the zone and if write pointer + * is not at zone start, reset the write pointer. + */ f2fs_notice(sbi, "Zone without valid block has non-zero write " "pointer. Reset the write pointer: wp[0x%x,0x%x]", wp_segno, wp_blkoff); ret = __f2fs_issue_discard_zone(sbi, fdev->bdev, zone_block, - zone->len >> log_sectors_per_block); - if (ret) { + zone->len >> sbi->log_sectors_per_block); + if (ret) f2fs_err(sbi, "Discard zone failed: %s (errno=%d)", fdev->path, ret); - return ret; - } + + return ret; } - return 0; + /* + * If there are valid blocks and the write pointer doesn't + * match with them, we need to report the inconsistency and + * fill the zone till the end to close the zone. This inconsistency + * does not cause write error because the zone will not be selected + * for write operation until it get discarded. + */ + f2fs_notice(sbi, "Valid blocks are not aligned with write pointer: " + "valid block[0x%x,0x%x] wp[0x%x,0x%x]", + GET_SEGNO(sbi, last_valid_block), + GET_BLKOFF_FROM_SEG0(sbi, last_valid_block), + wp_segno, wp_blkoff); + + ret = blkdev_issue_zeroout(fdev->bdev, zone->wp, + zone->len - (zone->wp - zone->start), + GFP_NOFS, 0); + if (ret) + f2fs_err(sbi, "Fill up zone failed: %s (errno=%d)", + fdev->path, ret); + + return ret; } static struct f2fs_dev_info *get_target_zoned_dev(struct f2fs_sb_info *sbi, @@ -4876,7 +4967,6 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) struct blk_zone zone; unsigned int cs_section, wp_segno, wp_blkoff, wp_sector_off; block_t cs_zone_block, wp_block; - unsigned int log_sectors_per_block = sbi->log_blocksize - SECTOR_SHIFT; sector_t zone_sector; int err; @@ -4888,8 +4978,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) return 0; /* report zone for the sector the curseg points to */ - zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) - << log_sectors_per_block; + zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) << + sbi->log_sectors_per_block; err = blkdev_report_zones(zbd->bdev, zone_sector, 1, report_one_zone_cb, &zone); if (err != 1) { @@ -4901,10 +4991,10 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) if (zone.type != BLK_ZONE_TYPE_SEQWRITE_REQ) return 0; - wp_block = zbd->start_blk + (zone.wp >> log_sectors_per_block); + wp_block = zbd->start_blk + (zone.wp >> sbi->log_sectors_per_block); wp_segno = GET_SEGNO(sbi, wp_block); wp_blkoff = wp_block - START_BLOCK(sbi, wp_segno); - wp_sector_off = zone.wp & GENMASK(log_sectors_per_block - 1, 0); + wp_sector_off = zone.wp & GENMASK(sbi->log_sectors_per_block - 1, 0); if (cs->segno == wp_segno && cs->next_blkoff == wp_blkoff && wp_sector_off == 0) @@ -4931,8 +5021,8 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) if (!zbd) return 0; - zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) - << log_sectors_per_block; + zone_sector = (sector_t)(cs_zone_block - zbd->start_blk) << + sbi->log_sectors_per_block; err = blkdev_report_zones(zbd->bdev, zone_sector, 1, report_one_zone_cb, &zone); if (err != 1) { @@ -4950,7 +5040,7 @@ static int fix_curseg_write_pointer(struct f2fs_sb_info *sbi, int type) "Reset the zone: curseg[0x%x,0x%x]", type, cs->segno, cs->next_blkoff); err = __f2fs_issue_discard_zone(sbi, zbd->bdev, cs_zone_block, - zone.len >> log_sectors_per_block); + zone.len >> sbi->log_sectors_per_block); if (err) { f2fs_err(sbi, "Discard zone failed: %s (errno=%d)", zbd->path, err); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index e34197a70dc1..ca31163da00a 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -164,6 +164,7 @@ enum { Opt_discard_unit, Opt_memory_mode, Opt_age_extent_cache, + Opt_errors, Opt_err, }; @@ -243,6 +244,7 @@ static match_table_t f2fs_tokens = { {Opt_discard_unit, "discard_unit=%s"}, {Opt_memory_mode, "memory=%s"}, {Opt_age_extent_cache, "age_extent_cache"}, + {Opt_errors, "errors=%s"}, {Opt_err, NULL}, }; @@ -587,14 +589,12 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) { #ifdef CONFIG_F2FS_FS_LZ4HC unsigned int level; -#endif if (strlen(str) == 3) { - F2FS_OPTION(sbi).compress_level = 0; + F2FS_OPTION(sbi).compress_level = LZ4HC_DEFAULT_CLEVEL; return 0; } -#ifdef CONFIG_F2FS_FS_LZ4HC str += 3; if (str[0] != ':') { @@ -604,7 +604,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) { + if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) { f2fs_info(sbi, "invalid lz4hc compress level: %d", level); return -EINVAL; } @@ -612,6 +612,10 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) F2FS_OPTION(sbi).compress_level = level; return 0; #else + if (strlen(str) == 3) { + F2FS_OPTION(sbi).compress_level = 0; + return 0; + } f2fs_info(sbi, "kernel doesn't support lz4hc compression"); return -EINVAL; #endif @@ -625,7 +629,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) int len = 4; if (strlen(str) == len) { - F2FS_OPTION(sbi).compress_level = 0; + F2FS_OPTION(sbi).compress_level = F2FS_ZSTD_DEFAULT_CLEVEL; return 0; } @@ -638,7 +642,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (!level || level > zstd_max_clevel()) { + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } @@ -1268,6 +1272,25 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) case Opt_age_extent_cache: set_opt(sbi, AGE_EXTENT_CACHE); break; + case Opt_errors: + name = match_strdup(&args[0]); + if (!name) + return -ENOMEM; + if (!strcmp(name, "remount-ro")) { + F2FS_OPTION(sbi).errors = + MOUNT_ERRORS_READONLY; + } else if (!strcmp(name, "continue")) { + F2FS_OPTION(sbi).errors = + MOUNT_ERRORS_CONTINUE; + } else if (!strcmp(name, "panic")) { + F2FS_OPTION(sbi).errors = + MOUNT_ERRORS_PANIC; + } else { + kfree(name); + return -EINVAL; + } + kfree(name); + break; default: f2fs_err(sbi, "Unrecognized mount option \"%s\" or missing value", p); @@ -1340,7 +1363,7 @@ default_check: return -EINVAL; } - min_size = sizeof(struct f2fs_xattr_header) / sizeof(__le32); + min_size = MIN_INLINE_XATTR_SIZE; max_size = MAX_INLINE_XATTR_SIZE; if (F2FS_OPTION(sbi).inline_xattr_size < min_size || @@ -1550,6 +1573,7 @@ static void f2fs_put_super(struct super_block *sb) { struct f2fs_sb_info *sbi = F2FS_SB(sb); int i; + int err = 0; bool done; /* unregister procfs/sysfs entries in advance to avoid race case */ @@ -1576,7 +1600,7 @@ static void f2fs_put_super(struct super_block *sb) struct cp_control cpc = { .reason = CP_UMOUNT, }; - f2fs_write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); } /* be sure to wait for any on-going discard commands */ @@ -1585,7 +1609,7 @@ static void f2fs_put_super(struct super_block *sb) struct cp_control cpc = { .reason = CP_UMOUNT | CP_TRIMMED, }; - f2fs_write_checkpoint(sbi, &cpc); + err = f2fs_write_checkpoint(sbi, &cpc); } /* @@ -1602,6 +1626,19 @@ static void f2fs_put_super(struct super_block *sb) f2fs_wait_on_all_pages(sbi, F2FS_WB_CP_DATA); + if (err) { + truncate_inode_pages_final(NODE_MAPPING(sbi)); + truncate_inode_pages_final(META_MAPPING(sbi)); + } + + for (i = 0; i < NR_COUNT_TYPE; i++) { + if (!get_pages(sbi, i)) + continue; + f2fs_err(sbi, "detect filesystem reference count leak during " + "umount, type: %d, count: %lld", i, get_pages(sbi, i)); + f2fs_bug_on(sbi, 1); + } + f2fs_bug_on(sbi, sbi->fsync_node_num); f2fs_destroy_compress_inode(sbi); @@ -1622,6 +1659,9 @@ static void f2fs_put_super(struct super_block *sb) f2fs_destroy_node_manager(sbi); f2fs_destroy_segment_manager(sbi); + /* flush s_error_work before sbi destroy */ + flush_work(&sbi->s_error_work); + f2fs_destroy_post_read_wq(sbi); kvfree(sbi->ckpt); @@ -2052,12 +2092,32 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root) else if (F2FS_OPTION(sbi).memory_mode == MEMORY_MODE_LOW) seq_printf(seq, ",memory=%s", "low"); + if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_READONLY) + seq_printf(seq, ",errors=%s", "remount-ro"); + else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE) + seq_printf(seq, ",errors=%s", "continue"); + else if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC) + seq_printf(seq, ",errors=%s", "panic"); + return 0; } -static void default_options(struct f2fs_sb_info *sbi) +static void default_options(struct f2fs_sb_info *sbi, bool remount) { /* init some FS parameters */ + if (!remount) { + set_opt(sbi, READ_EXTENT_CACHE); + clear_opt(sbi, DISABLE_CHECKPOINT); + + if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) + set_opt(sbi, DISCARD); + + if (f2fs_sb_has_blkzoned(sbi)) + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; + else + F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; + } + if (f2fs_sb_has_readonly(sbi)) F2FS_OPTION(sbi).active_logs = NR_CURSEG_RO_TYPE; else @@ -2080,29 +2140,23 @@ static void default_options(struct f2fs_sb_info *sbi) } F2FS_OPTION(sbi).bggc_mode = BGGC_MODE_ON; F2FS_OPTION(sbi).memory_mode = MEMORY_MODE_NORMAL; + F2FS_OPTION(sbi).errors = MOUNT_ERRORS_CONTINUE; sbi->sb->s_flags &= ~SB_INLINECRYPT; set_opt(sbi, INLINE_XATTR); set_opt(sbi, INLINE_DATA); set_opt(sbi, INLINE_DENTRY); - set_opt(sbi, READ_EXTENT_CACHE); set_opt(sbi, NOHEAP); - clear_opt(sbi, DISABLE_CHECKPOINT); set_opt(sbi, MERGE_CHECKPOINT); F2FS_OPTION(sbi).unusable_cap = 0; sbi->sb->s_flags |= SB_LAZYTIME; if (!f2fs_is_readonly(sbi)) set_opt(sbi, FLUSH_MERGE); - if (f2fs_hw_support_discard(sbi) || f2fs_hw_should_discard(sbi)) - set_opt(sbi, DISCARD); - if (f2fs_sb_has_blkzoned(sbi)) { + if (f2fs_sb_has_blkzoned(sbi)) F2FS_OPTION(sbi).fs_mode = FS_MODE_LFS; - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_SECTION; - } else { + else F2FS_OPTION(sbi).fs_mode = FS_MODE_ADAPTIVE; - F2FS_OPTION(sbi).discard_unit = DISCARD_UNIT_BLOCK; - } #ifdef CONFIG_F2FS_FS_XATTR set_opt(sbi, XATTR_USER); @@ -2274,13 +2328,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data) clear_sbi_flag(sbi, SBI_NEED_SB_WRITE); } - default_options(sbi); + default_options(sbi, true); /* parse mount options */ err = parse_options(sb, data, true); if (err) goto restore_opts; + /* flush outstanding errors before changing fs state */ + flush_work(&sbi->s_error_work); + /* * Previous and new state of filesystem is RO, * so skip checking GC and FLUSH_MERGE conditions. @@ -2713,6 +2770,7 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, { struct inode *qf_inode; unsigned long qf_inum; + unsigned long qf_flag = F2FS_QUOTA_DEFAULT_FL; int err; BUG_ON(!f2fs_sb_has_quota_ino(F2FS_SB(sb))); @@ -2728,7 +2786,15 @@ static int f2fs_quota_enable(struct super_block *sb, int type, int format_id, } /* Don't account quota for quota files to avoid recursion */ + inode_lock(qf_inode); qf_inode->i_flags |= S_NOQUOTA; + + if ((F2FS_I(qf_inode)->i_flags & qf_flag) != qf_flag) { + F2FS_I(qf_inode)->i_flags |= qf_flag; + f2fs_set_inode_flags(qf_inode); + } + inode_unlock(qf_inode); + err = dquot_load_quota_inode(qf_inode, type, format_id, flags); iput(qf_inode); return err; @@ -2859,18 +2925,29 @@ static int f2fs_quota_on(struct super_block *sb, int type, int format_id, return -EBUSY; } + if (path->dentry->d_sb != sb) + return -EXDEV; + err = f2fs_quota_sync(sb, type); if (err) return err; - err = dquot_quota_on(sb, type, format_id, path); + inode = d_inode(path->dentry); + + err = filemap_fdatawrite(inode->i_mapping); if (err) return err; - inode = d_inode(path->dentry); + err = filemap_fdatawait(inode->i_mapping); + if (err) + return err; + + err = dquot_quota_on(sb, type, format_id, path); + if (err) + return err; inode_lock(inode); - F2FS_I(inode)->i_flags |= F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL; + F2FS_I(inode)->i_flags |= F2FS_QUOTA_DEFAULT_FL; f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -2895,7 +2972,7 @@ static int __f2fs_quota_off(struct super_block *sb, int type) goto out_put; inode_lock(inode); - F2FS_I(inode)->i_flags &= ~(F2FS_NOATIME_FL | F2FS_IMMUTABLE_FL); + F2FS_I(inode)->i_flags &= ~F2FS_QUOTA_DEFAULT_FL; f2fs_set_inode_flags(inode); inode_unlock(inode); f2fs_mark_inode_dirty_sync(inode, false); @@ -3926,55 +4003,73 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover) return err; } -void f2fs_handle_stop(struct f2fs_sb_info *sbi, unsigned char reason) +static void save_stop_reason(struct f2fs_sb_info *sbi, unsigned char reason) +{ + unsigned long flags; + + spin_lock_irqsave(&sbi->error_lock, flags); + if (sbi->stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0)) + sbi->stop_reason[reason]++; + spin_unlock_irqrestore(&sbi->error_lock, flags); +} + +static void f2fs_record_stop_reason(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); + unsigned long flags; int err; f2fs_down_write(&sbi->sb_lock); - if (raw_super->s_stop_reason[reason] < GENMASK(BITS_PER_BYTE - 1, 0)) - raw_super->s_stop_reason[reason]++; + spin_lock_irqsave(&sbi->error_lock, flags); + if (sbi->error_dirty) { + memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors, + MAX_F2FS_ERRORS); + sbi->error_dirty = false; + } + memcpy(raw_super->s_stop_reason, sbi->stop_reason, MAX_STOP_REASON); + spin_unlock_irqrestore(&sbi->error_lock, flags); err = f2fs_commit_super(sbi, false); - if (err) - f2fs_err(sbi, "f2fs_commit_super fails to record reason:%u err:%d", - reason, err); + f2fs_up_write(&sbi->sb_lock); + if (err) + f2fs_err(sbi, "f2fs_commit_super fails to record err:%d", err); } void f2fs_save_errors(struct f2fs_sb_info *sbi, unsigned char flag) { - spin_lock(&sbi->error_lock); + unsigned long flags; + + spin_lock_irqsave(&sbi->error_lock, flags); if (!test_bit(flag, (unsigned long *)sbi->errors)) { set_bit(flag, (unsigned long *)sbi->errors); sbi->error_dirty = true; } - spin_unlock(&sbi->error_lock); + spin_unlock_irqrestore(&sbi->error_lock, flags); } static bool f2fs_update_errors(struct f2fs_sb_info *sbi) { + unsigned long flags; bool need_update = false; - spin_lock(&sbi->error_lock); + spin_lock_irqsave(&sbi->error_lock, flags); if (sbi->error_dirty) { memcpy(F2FS_RAW_SUPER(sbi)->s_errors, sbi->errors, MAX_F2FS_ERRORS); sbi->error_dirty = false; need_update = true; } - spin_unlock(&sbi->error_lock); + spin_unlock_irqrestore(&sbi->error_lock, flags); return need_update; } -void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error) +static void f2fs_record_errors(struct f2fs_sb_info *sbi, unsigned char error) { int err; - f2fs_save_errors(sbi, error); - f2fs_down_write(&sbi->sb_lock); if (!f2fs_update_errors(sbi)) @@ -3988,6 +4083,83 @@ out_unlock: f2fs_up_write(&sbi->sb_lock); } +void f2fs_handle_error(struct f2fs_sb_info *sbi, unsigned char error) +{ + f2fs_save_errors(sbi, error); + f2fs_record_errors(sbi, error); +} + +void f2fs_handle_error_async(struct f2fs_sb_info *sbi, unsigned char error) +{ + f2fs_save_errors(sbi, error); + + if (!sbi->error_dirty) + return; + if (!test_bit(error, (unsigned long *)sbi->errors)) + return; + schedule_work(&sbi->s_error_work); +} + +static bool system_going_down(void) +{ + return system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF + || system_state == SYSTEM_RESTART; +} + +void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason, + bool irq_context) +{ + struct super_block *sb = sbi->sb; + bool shutdown = reason == STOP_CP_REASON_SHUTDOWN; + bool continue_fs = !shutdown && + F2FS_OPTION(sbi).errors == MOUNT_ERRORS_CONTINUE; + + set_ckpt_flags(sbi, CP_ERROR_FLAG); + + if (!f2fs_hw_is_readonly(sbi)) { + save_stop_reason(sbi, reason); + + if (irq_context && !shutdown) + schedule_work(&sbi->s_error_work); + else + f2fs_record_stop_reason(sbi); + } + + /* + * We force ERRORS_RO behavior when system is rebooting. Otherwise we + * could panic during 'reboot -f' as the underlying device got already + * disabled. + */ + if (F2FS_OPTION(sbi).errors == MOUNT_ERRORS_PANIC && + !shutdown && !system_going_down() && + !is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN)) + panic("F2FS-fs (device %s): panic forced after error\n", + sb->s_id); + + if (shutdown) + set_sbi_flag(sbi, SBI_IS_SHUTDOWN); + + /* continue filesystem operators if errors=continue */ + if (continue_fs || f2fs_readonly(sb)) + return; + + f2fs_warn(sbi, "Remounting filesystem read-only"); + /* + * Make sure updated value of ->s_mount_flags will be visible before + * ->s_flags update + */ + smp_wmb(); + sb->s_flags |= SB_RDONLY; +} + +static void f2fs_record_error_work(struct work_struct *work) +{ + struct f2fs_sb_info *sbi = container_of(work, + struct f2fs_sb_info, s_error_work); + + f2fs_record_stop_reason(sbi); +} + static int f2fs_scan_devices(struct f2fs_sb_info *sbi) { struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); @@ -4220,14 +4392,16 @@ try_onemore: sb->s_fs_info = sbi; sbi->raw_super = raw_super; + INIT_WORK(&sbi->s_error_work, f2fs_record_error_work); memcpy(sbi->errors, raw_super->s_errors, MAX_F2FS_ERRORS); + memcpy(sbi->stop_reason, raw_super->s_stop_reason, MAX_STOP_REASON); /* precompute checksum seed for metadata */ if (f2fs_sb_has_inode_chksum(sbi)) sbi->s_chksum_seed = f2fs_chksum(sbi, ~0, raw_super->uuid, sizeof(raw_super->uuid)); - default_options(sbi); + default_options(sbi, false); /* parse mount options */ options = kstrdup((const char *)data, GFP_KERNEL); if (data && !options) { @@ -4617,6 +4791,8 @@ free_sm: f2fs_destroy_segment_manager(sbi); stop_ckpt_thread: f2fs_stop_ckpt_thread(sbi); + /* flush s_error_work before sbi destroy */ + flush_work(&sbi->s_error_work); f2fs_destroy_post_read_wq(sbi); free_devices: destroy_device_list(sbi); diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 8ea05340bad9..48b7e0073884 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -842,68 +842,160 @@ static struct f2fs_attr f2fs_attr_##_name = { \ #define F2FS_GENERAL_RO_ATTR(name) \ static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL) -#define F2FS_STAT_ATTR(_struct_type, _struct_name, _name, _elname) \ -static struct f2fs_attr f2fs_attr_##_name = { \ - .attr = {.name = __stringify(_name), .mode = 0444 }, \ - .show = f2fs_sbi_show, \ - .struct_type = _struct_type, \ - .offset = offsetof(struct _struct_name, _elname), \ -} +#ifdef CONFIG_F2FS_STAT_FS +#define STAT_INFO_RO_ATTR(name, elname) \ + F2FS_RO_ATTR(STAT_INFO, f2fs_stat_info, name, elname) +#endif -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_urgent_sleep_time, - urgent_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time); -F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle, gc_mode); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_urgent, gc_mode); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_discard_request, max_discard_request); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, min_discard_issue_time, min_discard_issue_time); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, mid_discard_issue_time, mid_discard_issue_time); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_discard_issue_time, max_discard_issue_time); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_io_aware_gran, discard_io_aware_gran); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_urgent_util, discard_urgent_util); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, discard_granularity, discard_granularity); -F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_ordered_discard, max_ordered_discard); -F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_seq_blocks, min_seq_blocks); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks); -F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ssr_sections, min_ssr_sections); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio); -F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, max_roll_forward_node_blocks, max_rf_node_blocks); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, migration_granularity, migration_granularity); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, discard_idle_interval, - interval_time[DISCARD_TIME]); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_idle_interval, interval_time[GC_TIME]); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, - umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); -#ifdef CONFIG_F2FS_IOSTAT -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_enable, iostat_enable); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, iostat_period_ms, iostat_period_ms); +#define GC_THREAD_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, name, elname) + +#define SM_INFO_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, name, elname) + +#define SM_INFO_GENERAL_RW_ATTR(elname) \ + SM_INFO_RW_ATTR(elname, elname) + +#define DCC_INFO_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, name, elname) + +#define DCC_INFO_GENERAL_RW_ATTR(elname) \ + DCC_INFO_RW_ATTR(elname, elname) + +#define NM_INFO_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, name, elname) + +#define NM_INFO_GENERAL_RW_ATTR(elname) \ + NM_INFO_RW_ATTR(elname, elname) + +#define F2FS_SBI_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, name, elname) + +#define F2FS_SBI_GENERAL_RW_ATTR(elname) \ + F2FS_SBI_RW_ATTR(elname, elname) + +#define F2FS_SBI_GENERAL_RO_ATTR(elname) \ + F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, elname, elname) + +#ifdef CONFIG_F2FS_FAULT_INJECTION +#define FAULT_INFO_GENERAL_RW_ATTR(type, elname) \ + F2FS_RW_ATTR(type, f2fs_fault_info, elname, elname) #endif -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, readdir_ra, readdir_ra); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_io_bytes, max_io_bytes); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_pin_file_thresh, gc_pin_file_threshold); + +#define RESERVED_BLOCKS_GENERAL_RW_ATTR(elname) \ + F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, elname, elname) + +#define CPRC_INFO_GENERAL_RW_ATTR(elname) \ + F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, elname, elname) + +#define ATGC_INFO_RW_ATTR(name, elname) \ + F2FS_RW_ATTR(ATGC_INFO, atgc_management, name, elname) + +/* GC_THREAD ATTR */ +GC_THREAD_RW_ATTR(gc_urgent_sleep_time, urgent_sleep_time); +GC_THREAD_RW_ATTR(gc_min_sleep_time, min_sleep_time); +GC_THREAD_RW_ATTR(gc_max_sleep_time, max_sleep_time); +GC_THREAD_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time); + +/* SM_INFO ATTR */ +SM_INFO_RW_ATTR(reclaim_segments, rec_prefree_segments); +SM_INFO_GENERAL_RW_ATTR(ipu_policy); +SM_INFO_GENERAL_RW_ATTR(min_ipu_util); +SM_INFO_GENERAL_RW_ATTR(min_fsync_blocks); +SM_INFO_GENERAL_RW_ATTR(min_seq_blocks); +SM_INFO_GENERAL_RW_ATTR(min_hot_blocks); +SM_INFO_GENERAL_RW_ATTR(min_ssr_sections); + +/* DCC_INFO ATTR */ +DCC_INFO_RW_ATTR(max_small_discards, max_discards); +DCC_INFO_GENERAL_RW_ATTR(max_discard_request); +DCC_INFO_GENERAL_RW_ATTR(min_discard_issue_time); +DCC_INFO_GENERAL_RW_ATTR(mid_discard_issue_time); +DCC_INFO_GENERAL_RW_ATTR(max_discard_issue_time); +DCC_INFO_GENERAL_RW_ATTR(discard_io_aware_gran); +DCC_INFO_GENERAL_RW_ATTR(discard_urgent_util); +DCC_INFO_GENERAL_RW_ATTR(discard_granularity); +DCC_INFO_GENERAL_RW_ATTR(max_ordered_discard); + +/* NM_INFO ATTR */ +NM_INFO_RW_ATTR(max_roll_forward_node_blocks, max_rf_node_blocks); +NM_INFO_GENERAL_RW_ATTR(ram_thresh); +NM_INFO_GENERAL_RW_ATTR(ra_nid_pages); +NM_INFO_GENERAL_RW_ATTR(dirty_nats_ratio); + +/* F2FS_SBI ATTR */ F2FS_RW_ATTR(F2FS_SBI, f2fs_super_block, extension_list, extension_list); +F2FS_SBI_RW_ATTR(gc_idle, gc_mode); +F2FS_SBI_RW_ATTR(gc_urgent, gc_mode); +F2FS_SBI_RW_ATTR(cp_interval, interval_time[CP_TIME]); +F2FS_SBI_RW_ATTR(idle_interval, interval_time[REQ_TIME]); +F2FS_SBI_RW_ATTR(discard_idle_interval, interval_time[DISCARD_TIME]); +F2FS_SBI_RW_ATTR(gc_idle_interval, interval_time[GC_TIME]); +F2FS_SBI_RW_ATTR(umount_discard_timeout, interval_time[UMOUNT_DISCARD_TIMEOUT]); +F2FS_SBI_RW_ATTR(gc_pin_file_thresh, gc_pin_file_threshold); +F2FS_SBI_RW_ATTR(gc_reclaimed_segments, gc_reclaimed_segs); +F2FS_SBI_GENERAL_RW_ATTR(max_victim_search); +F2FS_SBI_GENERAL_RW_ATTR(migration_granularity); +F2FS_SBI_GENERAL_RW_ATTR(dir_level); +#ifdef CONFIG_F2FS_IOSTAT +F2FS_SBI_GENERAL_RW_ATTR(iostat_enable); +F2FS_SBI_GENERAL_RW_ATTR(iostat_period_ms); +#endif +F2FS_SBI_GENERAL_RW_ATTR(readdir_ra); +F2FS_SBI_GENERAL_RW_ATTR(max_io_bytes); +F2FS_SBI_GENERAL_RW_ATTR(data_io_flag); +F2FS_SBI_GENERAL_RW_ATTR(node_io_flag); +F2FS_SBI_GENERAL_RW_ATTR(gc_remaining_trials); +F2FS_SBI_GENERAL_RW_ATTR(seq_file_ra_mul); +F2FS_SBI_GENERAL_RW_ATTR(gc_segment_mode); +F2FS_SBI_GENERAL_RW_ATTR(max_fragment_chunk); +F2FS_SBI_GENERAL_RW_ATTR(max_fragment_hole); +#ifdef CONFIG_F2FS_FS_COMPRESSION +F2FS_SBI_GENERAL_RW_ATTR(compr_written_block); +F2FS_SBI_GENERAL_RW_ATTR(compr_saved_block); +F2FS_SBI_GENERAL_RW_ATTR(compr_new_inode); +F2FS_SBI_GENERAL_RW_ATTR(compress_percent); +F2FS_SBI_GENERAL_RW_ATTR(compress_watermark); +#endif +/* atomic write */ +F2FS_SBI_GENERAL_RO_ATTR(current_atomic_write); +F2FS_SBI_GENERAL_RW_ATTR(peak_atomic_write); +F2FS_SBI_GENERAL_RW_ATTR(committed_atomic_block); +F2FS_SBI_GENERAL_RW_ATTR(revoked_atomic_block); +/* block age extent cache */ +F2FS_SBI_GENERAL_RW_ATTR(hot_data_age_threshold); +F2FS_SBI_GENERAL_RW_ATTR(warm_data_age_threshold); +F2FS_SBI_GENERAL_RW_ATTR(last_age_weight); +#ifdef CONFIG_BLK_DEV_ZONED +F2FS_SBI_GENERAL_RO_ATTR(unusable_blocks_per_sec); +#endif + +/* STAT_INFO ATTR */ +#ifdef CONFIG_F2FS_STAT_FS +STAT_INFO_RO_ATTR(cp_foreground_calls, cp_count); +STAT_INFO_RO_ATTR(cp_background_calls, bg_cp_count); +STAT_INFO_RO_ATTR(gc_foreground_calls, call_count); +STAT_INFO_RO_ATTR(gc_background_calls, bg_gc); +#endif + +/* FAULT_INFO ATTR */ #ifdef CONFIG_F2FS_FAULT_INJECTION -F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate); -F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type); +FAULT_INFO_GENERAL_RW_ATTR(FAULT_INFO_RATE, inject_rate); +FAULT_INFO_GENERAL_RW_ATTR(FAULT_INFO_TYPE, inject_type); #endif -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, data_io_flag, data_io_flag); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, node_io_flag, node_io_flag); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_remaining_trials, gc_remaining_trials); -F2FS_RW_ATTR(CPRC_INFO, ckpt_req_control, ckpt_thread_ioprio, ckpt_thread_ioprio); + +/* RESERVED_BLOCKS ATTR */ +RESERVED_BLOCKS_GENERAL_RW_ATTR(reserved_blocks); + +/* CPRC_INFO ATTR */ +CPRC_INFO_GENERAL_RW_ATTR(ckpt_thread_ioprio); + +/* ATGC_INFO ATTR */ +ATGC_INFO_RW_ATTR(atgc_candidate_ratio, candidate_ratio); +ATGC_INFO_RW_ATTR(atgc_candidate_count, max_candidate_count); +ATGC_INFO_RW_ATTR(atgc_age_weight, age_weight); +ATGC_INFO_RW_ATTR(atgc_age_threshold, age_threshold); + F2FS_GENERAL_RO_ATTR(dirty_segments); F2FS_GENERAL_RO_ATTR(free_segments); F2FS_GENERAL_RO_ATTR(ovp_segments); @@ -917,10 +1009,6 @@ F2FS_GENERAL_RO_ATTR(main_blkaddr); F2FS_GENERAL_RO_ATTR(pending_discard); F2FS_GENERAL_RO_ATTR(gc_mode); #ifdef CONFIG_F2FS_STAT_FS -F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_foreground_calls, cp_count); -F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, cp_background_calls, bg_cp_count); -F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_foreground_calls, call_count); -F2FS_STAT_ATTR(STAT_INFO, f2fs_stat_info, gc_background_calls, bg_gc); F2FS_GENERAL_RO_ATTR(moved_blocks_background); F2FS_GENERAL_RO_ATTR(moved_blocks_foreground); F2FS_GENERAL_RO_ATTR(avg_vblocks); @@ -935,8 +1023,6 @@ F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif /* CONFIG_FS_ENCRYPTION */ #ifdef CONFIG_BLK_DEV_ZONED F2FS_FEATURE_RO_ATTR(block_zoned); -F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, unusable_blocks_per_sec, - unusable_blocks_per_sec); #endif F2FS_FEATURE_RO_ATTR(atomic_write); F2FS_FEATURE_RO_ATTR(extra_attr); @@ -956,37 +1042,9 @@ F2FS_FEATURE_RO_ATTR(casefold); F2FS_FEATURE_RO_ATTR(readonly); #ifdef CONFIG_F2FS_FS_COMPRESSION F2FS_FEATURE_RO_ATTR(compression); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_written_block, compr_written_block); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_saved_block, compr_saved_block); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compr_new_inode, compr_new_inode); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compress_percent, compress_percent); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, compress_watermark, compress_watermark); #endif F2FS_FEATURE_RO_ATTR(pin_file); -/* For ATGC */ -F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_candidate_ratio, candidate_ratio); -F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_candidate_count, max_candidate_count); -F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_weight, age_weight); -F2FS_RW_ATTR(ATGC_INFO, atgc_management, atgc_age_threshold, age_threshold); - -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, seq_file_ra_mul, seq_file_ra_mul); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_segment_mode, gc_segment_mode); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, gc_reclaimed_segments, gc_reclaimed_segs); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_chunk, max_fragment_chunk); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_fragment_hole, max_fragment_hole); - -/* For atomic write */ -F2FS_RO_ATTR(F2FS_SBI, f2fs_sb_info, current_atomic_write, current_atomic_write); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, peak_atomic_write, peak_atomic_write); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, committed_atomic_block, committed_atomic_block); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, revoked_atomic_block, revoked_atomic_block); - -/* For block age extent cache */ -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, hot_data_age_threshold, hot_data_age_threshold); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, warm_data_age_threshold, warm_data_age_threshold); -F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, last_age_weight, last_age_weight); - #define ATTR_LIST(name) (&f2fs_attr_##name.attr) static struct attribute *f2fs_attrs[] = { ATTR_LIST(gc_urgent_sleep_time), @@ -1386,12 +1444,19 @@ int __init f2fs_init_sysfs(void) ret = kobject_init_and_add(&f2fs_feat, &f2fs_feat_ktype, NULL, "features"); - if (ret) { - kobject_put(&f2fs_feat); - kset_unregister(&f2fs_kset); - } else { - f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + if (ret) + goto put_kobject; + + f2fs_proc_root = proc_mkdir("fs/f2fs", NULL); + if (!f2fs_proc_root) { + ret = -ENOMEM; + goto put_kobject; } + + return 0; +put_kobject: + kobject_put(&f2fs_feat); + kset_unregister(&f2fs_kset); return ret; } @@ -1430,23 +1495,24 @@ int f2fs_register_sysfs(struct f2fs_sb_info *sbi) if (err) goto put_feature_list_kobj; - if (f2fs_proc_root) - sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root); + if (!sbi->s_proc) { + err = -ENOMEM; + goto put_feature_list_kobj; + } - if (sbi->s_proc) { - proc_create_single_data("segment_info", 0444, sbi->s_proc, + proc_create_single_data("segment_info", 0444, sbi->s_proc, segment_info_seq_show, sb); - proc_create_single_data("segment_bits", 0444, sbi->s_proc, + proc_create_single_data("segment_bits", 0444, sbi->s_proc, segment_bits_seq_show, sb); #ifdef CONFIG_F2FS_IOSTAT - proc_create_single_data("iostat_info", 0444, sbi->s_proc, + proc_create_single_data("iostat_info", 0444, sbi->s_proc, iostat_info_seq_show, sb); #endif - proc_create_single_data("victim_bits", 0444, sbi->s_proc, + proc_create_single_data("victim_bits", 0444, sbi->s_proc, victim_bits_seq_show, sb); - proc_create_single_data("discard_plist_info", 0444, sbi->s_proc, + proc_create_single_data("discard_plist_info", 0444, sbi->s_proc, discard_plist_seq_show, sb); - } return 0; put_feature_list_kobj: kobject_put(&sbi->s_feature_list_kobj); @@ -1462,8 +1528,7 @@ put_sb_kobj: void f2fs_unregister_sysfs(struct f2fs_sb_info *sbi) { - if (sbi->s_proc) - remove_proc_subtree(sbi->sb->s_id, f2fs_proc_root); + remove_proc_subtree(sbi->sb->s_id, f2fs_proc_root); kobject_put(&sbi->s_stat_kobj); wait_for_completion(&sbi->s_stat_kobj_unregister); diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index 213805d3592c..476b186b90a6 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -528,10 +528,12 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name, if (len > F2FS_NAME_LEN) return -ERANGE; - f2fs_down_read(&F2FS_I(inode)->i_xattr_sem); + if (!ipage) + f2fs_down_read(&F2FS_I(inode)->i_xattr_sem); error = lookup_all_xattrs(inode, ipage, index, len, name, &entry, &base_addr, &base_size, &is_inline); - f2fs_up_read(&F2FS_I(inode)->i_xattr_sem); + if (!ipage) + f2fs_up_read(&F2FS_I(inode)->i_xattr_sem); if (error) return error; diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h index 416d652774a3..b1811c392e6f 100644 --- a/fs/f2fs/xattr.h +++ b/fs/f2fs/xattr.h @@ -83,6 +83,7 @@ struct f2fs_xattr_entry { sizeof(struct f2fs_xattr_header) - \ sizeof(struct f2fs_xattr_entry)) +#define MIN_INLINE_XATTR_SIZE (sizeof(struct f2fs_xattr_header) / sizeof(__le32)) #define MAX_INLINE_XATTR_SIZE \ (DEF_ADDRS_PER_INODE - \ F2FS_TOTAL_EXTRA_ATTR_SIZE / sizeof(__le32) - \ diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 1c407eba1e30..ae49256b7c8c 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -432,10 +432,10 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page) if (error) return error; - kaddr = kmap_atomic(page); + kaddr = kmap_local_page(page); memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); memset(kaddr + dsize, 0, PAGE_SIZE - dsize); - kunmap_atomic(kaddr); + kunmap_local(kaddr); flush_dcache_page(page); brelse(dibh); SetPageUptodate(page); @@ -489,18 +489,18 @@ int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos, unsigned copied = 0; unsigned amt; struct page *page; - void *p; do { + page = read_cache_page(mapping, index, gfs2_read_folio, NULL); + if (IS_ERR(page)) { + if (PTR_ERR(page) == -EINTR) + continue; + return PTR_ERR(page); + } amt = size - copied; if (offset + size > PAGE_SIZE) amt = PAGE_SIZE - offset; - page = read_cache_page(mapping, index, gfs2_read_folio, NULL); - if (IS_ERR(page)) - return PTR_ERR(page); - p = kmap_atomic(page); - memcpy(buf + copied, p + offset, amt); - kunmap_atomic(p); + memcpy_from_page(buf + copied, page, offset, amt); put_page(page); copied += amt; index++; @@ -751,7 +751,6 @@ static const struct address_space_operations gfs2_aops = { .release_folio = iomap_release_folio, .invalidate_folio = iomap_invalidate_folio, .bmap = gfs2_bmap, - .direct_IO = noop_direct_IO, .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_page = generic_error_remove_page, diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index c739b258a2d9..8d611fbcf0bd 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1729,8 +1729,8 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) if (offset >= maxsize) { /* - * The starting point lies beyond the allocated meta-data; - * there are no blocks do deallocate. + * The starting point lies beyond the allocated metadata; + * there are no blocks to deallocate. */ return 0; } diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index f146447eac63..1bf3c4453516 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -630,6 +630,9 @@ int gfs2_open_common(struct inode *inode, struct file *file) ret = generic_file_open(inode, file); if (ret) return ret; + + if (!gfs2_is_jdata(GFS2_I(inode))) + file->f_mode |= FMODE_CAN_ODIRECT; } fp = kzalloc(sizeof(struct gfs2_file), GFP_NOFS); @@ -1030,8 +1033,8 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, } gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, gh); -retry: if (should_fault_in_pages(from, iocb, &prev_count, &window_size)) { +retry: window_size -= fault_in_iov_iter_readable(from, window_size); if (!window_size) { ret = -EFAULT; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 5adc7d85dbf3..1438e7465e30 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -145,8 +145,8 @@ static void gfs2_glock_dealloc(struct rcu_head *rcu) * * We need to allow some glocks to be enqueued, dequeued, promoted, and demoted * when we're withdrawn. For example, to maintain metadata integrity, we should - * disallow the use of inode and rgrp glocks when withdrawn. Other glocks, like - * iopen or the transaction glocks may be safely used because none of their + * disallow the use of inode and rgrp glocks when withdrawn. Other glocks like + * the iopen or freeze glock may be safely used because none of their * metadata goes through the journal. So in general, we should disallow all * glocks that are journaled, and allow all the others. One exception is: * we need to allow our active journal to be promoted and demoted so others diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 01d433ed6ce7..54319328b16b 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -236,7 +236,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) truncate_inode_pages_range(mapping, start, end); } -static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl, +static void gfs2_rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf) { struct gfs2_rgrpd *rgd = gl->gl_object; @@ -536,72 +536,53 @@ static int inode_go_held(struct gfs2_holder *gh) * */ -static void inode_go_dump(struct seq_file *seq, struct gfs2_glock *gl, +static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf) { struct gfs2_inode *ip = gl->gl_object; - struct inode *inode; - unsigned long nrpages; + const struct inode *inode = &ip->i_inode; if (ip == NULL) return; - inode = &ip->i_inode; - xa_lock_irq(&inode->i_data.i_pages); - nrpages = inode->i_data.nrpages; - xa_unlock_irq(&inode->i_data.i_pages); - gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu " "p:%lu\n", fs_id_buf, (unsigned long long)ip->i_no_formal_ino, (unsigned long long)ip->i_no_addr, - IF2DT(ip->i_inode.i_mode), ip->i_flags, + IF2DT(inode->i_mode), ip->i_flags, (unsigned int)ip->i_diskflags, - (unsigned long long)i_size_read(inode), nrpages); + (unsigned long long)i_size_read(inode), + inode->i_data.nrpages); } /** - * freeze_go_sync - promote/demote the freeze glock + * freeze_go_callback - A cluster node is requesting a freeze * @gl: the glock + * @remote: true if this came from a different cluster node */ -static int freeze_go_sync(struct gfs2_glock *gl) +static void freeze_go_callback(struct gfs2_glock *gl, bool remote) { - int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct super_block *sb = sdp->sd_vfs; + + if (!remote || + gl->gl_state != LM_ST_SHARED || + gl->gl_demote_state != LM_ST_UNLOCKED) + return; /* - * We need to check gl_state == LM_ST_SHARED here and not gl_req == - * LM_ST_EXCLUSIVE. That's because when any node does a freeze, - * all the nodes should have the freeze glock in SH mode and they all - * call do_xmote: One for EX and the others for UN. They ALL must - * freeze locally, and they ALL must queue freeze work. The freeze_work - * calls freeze_func, which tries to reacquire the freeze glock in SH, - * effectively waiting for the thaw on the node who holds it in EX. - * Once thawed, the work func acquires the freeze glock in - * SH and everybody goes back to thawed. + * Try to get an active super block reference to prevent racing with + * unmount (see trylock_super()). But note that unmount isn't the only + * place where a write lock on s_umount is taken, and we can fail here + * because of things like remount as well. */ - if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && - !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) { - atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); - error = freeze_super(sdp->sd_vfs); - if (error) { - fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", - error); - if (gfs2_withdrawn(sdp)) { - atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); - return 0; - } - gfs2_assert_withdraw(sdp, 0); - } - queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work); - if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) - gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE | - GFS2_LFC_FREEZE_GO_SYNC); - else /* read-only mounts */ - atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); + if (down_read_trylock(&sb->s_umount)) { + atomic_inc(&sb->s_active); + up_read(&sb->s_umount); + if (!queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work)) + deactivate_super(sb); } - return 0; } /** @@ -761,9 +742,9 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = { }; const struct gfs2_glock_operations gfs2_freeze_glops = { - .go_sync = freeze_go_sync, .go_xmote_bh = freeze_go_xmote_bh, .go_demote_ok = freeze_go_demote_ok, + .go_callback = freeze_go_callback, .go_type = LM_TYPE_NONDISK, .go_flags = GLOF_NONDISK, }; diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 79485329118b..04f2d78e8658 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -221,7 +221,7 @@ struct gfs2_glock_operations { int (*go_demote_ok) (const struct gfs2_glock *gl); int (*go_instantiate) (struct gfs2_glock *gl); int (*go_held)(struct gfs2_holder *gh); - void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl, + void (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); void (*go_free)(struct gfs2_glock *gl); @@ -600,7 +600,7 @@ enum { SDF_RORECOVERY = 7, /* read only recovery */ SDF_SKIP_DLM_UNLOCK = 8, SDF_FORCE_AIL_FLUSH = 9, - SDF_FS_FROZEN = 10, + SDF_FREEZE_INITIATOR = 10, SDF_WITHDRAWING = 11, /* Will withdraw eventually */ SDF_WITHDRAW_IN_PROG = 12, /* Withdraw is in progress */ SDF_REMOTE_WITHDRAW = 13, /* Performing remote recovery */ @@ -608,12 +608,7 @@ enum { withdrawing */ SDF_DEACTIVATING = 15, SDF_EVICTING = 16, -}; - -enum gfs2_freeze_state { - SFS_UNFROZEN = 0, - SFS_STARTING_FREEZE = 1, - SFS_FROZEN = 2, + SDF_FROZEN = 17, }; #define GFS2_FSNAME_LEN 256 @@ -841,7 +836,6 @@ struct gfs2_sbd { /* For quiescing the filesystem */ struct gfs2_holder sd_freeze_gh; - atomic_t sd_freeze_state; struct mutex sd_freeze_mutex; char sd_fsname[GFS2_FSNAME_LEN + 3 * sizeof(int) + 2]; diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c index 71911bf9ab34..54911294687c 100644 --- a/fs/gfs2/lock_dlm.c +++ b/fs/gfs2/lock_dlm.c @@ -296,10 +296,8 @@ static void gdlm_put_lock(struct gfs2_glock *gl) struct lm_lockstruct *ls = &sdp->sd_lockstruct; int error; - if (gl->gl_lksb.sb_lkid == 0) { - gfs2_glock_free(gl); - return; - } + if (gl->gl_lksb.sb_lkid == 0) + goto out_free; clear_bit(GLF_BLOCKING, &gl->gl_flags); gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT); @@ -307,17 +305,13 @@ static void gdlm_put_lock(struct gfs2_glock *gl) gfs2_update_request_times(gl); /* don't want to call dlm if we've unmounted the lock protocol */ - if (test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) { - gfs2_glock_free(gl); - return; - } + if (test_bit(DFL_UNMOUNT, &ls->ls_recover_flags)) + goto out_free; /* don't want to skip dlm_unlock writing the lvb when lock has one */ if (test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags) && - !gl->gl_lksb.sb_lvbptr) { - gfs2_glock_free(gl); - return; - } + !gl->gl_lksb.sb_lvbptr) + goto out_free; again: error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK, @@ -331,8 +325,11 @@ again: fs_err(sdp, "gdlm_unlock %x,%llx err=%d\n", gl->gl_name.ln_type, (unsigned long long)gl->gl_name.ln_number, error); - return; } + return; + +out_free: + gfs2_glock_free(gl); } static void gdlm_cancel(struct gfs2_glock *gl) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index d750d1128bed..aa568796207c 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -914,9 +914,8 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, static void log_write_header(struct gfs2_sbd *sdp, u32 flags) { blk_opf_t op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC; - enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); - gfs2_assert_withdraw(sdp, (state != SFS_FROZEN)); + gfs2_assert_withdraw(sdp, !test_bit(SDF_FROZEN, &sdp->sd_flags)); if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) { gfs2_ordered_wait(sdp); @@ -1036,7 +1035,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) { struct gfs2_trans *tr = NULL; unsigned int reserved_blocks = 0, used_blocks = 0; - enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); + bool frozen = test_bit(SDF_FROZEN, &sdp->sd_flags); unsigned int first_log_head; unsigned int reserved_revokes = 0; @@ -1067,7 +1066,7 @@ repeat: if (tr) { sdp->sd_log_tr = NULL; tr->tr_first = first_log_head; - if (unlikely (state == SFS_FROZEN)) { + if (unlikely(frozen)) { if (gfs2_assert_withdraw_delayed(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new)) goto out_withdraw; @@ -1092,7 +1091,7 @@ repeat: if (flags & GFS2_LOG_HEAD_FLUSH_SHUTDOWN) clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); - if (unlikely(state == SFS_FROZEN)) + if (unlikely(frozen)) if (gfs2_assert_withdraw_delayed(sdp, !reserved_revokes)) goto out_withdraw; @@ -1136,8 +1135,6 @@ repeat: if (flags & (GFS2_LOG_HEAD_FLUSH_SHUTDOWN | GFS2_LOG_HEAD_FLUSH_FREEZE)) gfs2_log_shutdown(sdp); - if (flags & GFS2_LOG_HEAD_FLUSH_FREEZE) - atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); } out_end: diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 1902413d5d12..251322b01631 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -427,10 +427,11 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, { struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); struct gfs2_log_header_host lh; - void *kaddr = kmap_atomic(page); + void *kaddr; unsigned int offset; bool ret = false; + kaddr = kmap_local_page(page); for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { if (lh.lh_sequence >= head->lh_sequence) @@ -441,7 +442,7 @@ static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, } } } - kunmap_atomic(kaddr); + kunmap_local(kaddr); return ret; } @@ -626,11 +627,11 @@ static void gfs2_check_magic(struct buffer_head *bh) __be32 *ptr; clear_buffer_escaped(bh); - kaddr = kmap_atomic(bh->b_page); + kaddr = kmap_local_page(bh->b_page); ptr = kaddr + bh_offset(bh); if (*ptr == cpu_to_be32(GFS2_MAGIC)) set_buffer_escaped(bh); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } static int blocknr_cmp(void *priv, const struct list_head *a, @@ -696,14 +697,12 @@ static void gfs2_before_commit(struct gfs2_sbd *sdp, unsigned int limit, lock_buffer(bd2->bd_bh); if (buffer_escaped(bd2->bd_bh)) { - void *kaddr; + void *p; + page = mempool_alloc(gfs2_page_pool, GFP_NOIO); - ptr = page_address(page); - kaddr = kmap_atomic(bd2->bd_bh->b_page); - memcpy(ptr, kaddr + bh_offset(bd2->bd_bh), - bd2->bd_bh->b_size); - kunmap_atomic(kaddr); - *(__be32 *)ptr = 0; + p = page_address(page); + memcpy_from_page(p, page, bh_offset(bd2->bd_bh), bd2->bd_bh->b_size); + *(__be32 *)p = 0; clear_buffer_escaped(bd2->bd_bh); unlock_buffer(bd2->bd_bh); brelse(bd2->bd_bh); diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index cd962985b058..8a27957dbfee 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -135,7 +135,6 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb) init_rwsem(&sdp->sd_log_flush_lock); atomic_set(&sdp->sd_log_in_flight, 0); init_waitqueue_head(&sdp->sd_log_flush_wait); - atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); mutex_init(&sdp->sd_freeze_mutex); return sdp; @@ -434,7 +433,7 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh, error = gfs2_glock_get(sdp, GFS2_FREEZE_LOCK, &gfs2_freeze_glops, CREATE, &sdp->sd_freeze_gl); if (error) { - fs_err(sdp, "can't create transaction glock: %d\n", error); + fs_err(sdp, "can't create freeze glock: %d\n", error); goto fail_rename; } @@ -1140,7 +1139,6 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) int silent = fc->sb_flags & SB_SILENT; struct gfs2_sbd *sdp; struct gfs2_holder mount_gh; - struct gfs2_holder freeze_gh; int error; sdp = init_sbd(sb); @@ -1269,15 +1267,15 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc) } } - error = gfs2_freeze_lock(sdp, &freeze_gh, 0); + error = gfs2_freeze_lock_shared(sdp); if (error) goto fail_per_node; if (!sb_rdonly(sb)) error = gfs2_make_fs_rw(sdp); - gfs2_freeze_unlock(&freeze_gh); if (error) { + gfs2_freeze_unlock(&sdp->sd_freeze_gh); if (sdp->sd_quotad_process) kthread_stop(sdp->sd_quotad_process); sdp->sd_quotad_process = NULL; @@ -1590,12 +1588,6 @@ static int gfs2_reconfigure(struct fs_context *fc) fc->sb_flags |= SB_RDONLY; if ((sb->s_flags ^ fc->sb_flags) & SB_RDONLY) { - struct gfs2_holder freeze_gh; - - error = gfs2_freeze_lock(sdp, &freeze_gh, 0); - if (error) - return -EINVAL; - if (fc->sb_flags & SB_RDONLY) { gfs2_make_fs_ro(sdp); } else { @@ -1603,7 +1595,6 @@ static int gfs2_reconfigure(struct fs_context *fc) if (error) errorfc(fc, "unable to remount read-write"); } - gfs2_freeze_unlock(&freeze_gh); } sdp->sd_args = *newargs; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 1ed17226d9ed..704192b73605 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -75,6 +75,9 @@ #define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT) #define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1) +#define QC_CHANGE 0 +#define QC_SYNC 1 + /* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */ /* -> sd_bitmap_lock */ static DEFINE_SPINLOCK(qd_lock); @@ -470,7 +473,6 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp) spin_unlock(&qd_lock); if (qd) { - gfs2_assert_warn(sdp, qd->qd_change_sync); error = bh_get(qd); if (error) { clear_bit(QDF_LOCKED, &qd->qd_flags); @@ -591,6 +593,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) || gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags))) { error = -EIO; + gfs2_qa_put(ip); goto out; } @@ -661,7 +664,7 @@ static int sort_qd(const void *a, const void *b) return 0; } -static void do_qc(struct gfs2_quota_data *qd, s64 change) +static void do_qc(struct gfs2_quota_data *qd, s64 change, int qc_type) { struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode); @@ -686,16 +689,18 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change) qd->qd_change = x; spin_unlock(&qd_lock); - if (!x) { + if (qc_type == QC_CHANGE) { + if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) { + qd_hold(qd); + slot_hold(qd); + } + } else { gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags)); clear_bit(QDF_CHANGE, &qd->qd_flags); qc->qc_flags = 0; qc->qc_id = 0; slot_put(qd); qd_put(qd); - } else if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) { - qd_hold(qd); - slot_hold(qd); } if (change < 0) /* Reset quiet flag if we freed some blocks */ @@ -711,7 +716,6 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, struct address_space *mapping = inode->i_mapping; struct page *page; struct buffer_head *bh; - void *kaddr; u64 blk; unsigned bsize = sdp->sd_sb.sb_bsize, bnum = 0, boff = 0; unsigned to_write = bytes, pg_off = off; @@ -763,10 +767,8 @@ static int gfs2_write_buf_to_page(struct gfs2_inode *ip, unsigned long index, } /* Write to the page, now that we have setup the buffer(s) */ - kaddr = kmap_atomic(page); - memcpy(kaddr + off, buf, bytes); + memcpy_to_page(page, off, buf, bytes); flush_dcache_page(page); - kunmap_atomic(kaddr); unlock_page(page); put_page(page); @@ -955,7 +957,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda) if (error) goto out_end_trans; - do_qc(qd, -qd->qd_change_sync); + do_qc(qd, -qd->qd_change_sync, QC_SYNC); set_bit(QDF_REFRESH, &qd->qd_flags); } @@ -1281,7 +1283,7 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if (qid_eq(qd->qd_id, make_kqid_uid(uid)) || qid_eq(qd->qd_id, make_kqid_gid(gid))) { - do_qc(qd, change); + do_qc(qd, change, QC_CHANGE); } } } diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 2bb085a72e8e..9c7a9f640bad 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -404,7 +404,7 @@ void gfs2_recover_func(struct work_struct *work) struct gfs2_inode *ip = GFS2_I(jd->jd_inode); struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); struct gfs2_log_header_host head; - struct gfs2_holder j_gh, ji_gh, thaw_gh; + struct gfs2_holder j_gh, ji_gh; ktime_t t_start, t_jlck, t_jhd, t_tlck, t_rep; int ro = 0; unsigned int pass; @@ -420,10 +420,10 @@ void gfs2_recover_func(struct work_struct *work) if (sdp->sd_args.ar_spectator) goto fail; if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) { - fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n", + fs_info(sdp, "jid=%u: Trying to acquire journal glock...\n", jd->jd_jid); jlocked = 1; - /* Acquire the journal lock so we can do recovery */ + /* Acquire the journal glock so we can do recovery */ error = gfs2_glock_nq_num(sdp, jd->jd_jid, &gfs2_journal_glops, LM_ST_EXCLUSIVE, @@ -465,14 +465,14 @@ void gfs2_recover_func(struct work_struct *work) ktime_ms_delta(t_jhd, t_jlck)); if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) { - fs_info(sdp, "jid=%u: Acquiring the transaction lock...\n", - jd->jd_jid); - - /* Acquire a shared hold on the freeze lock */ + mutex_lock(&sdp->sd_freeze_mutex); - error = gfs2_freeze_lock(sdp, &thaw_gh, LM_FLAG_PRIORITY); - if (error) + if (test_bit(SDF_FROZEN, &sdp->sd_flags)) { + mutex_unlock(&sdp->sd_freeze_mutex); + fs_warn(sdp, "jid=%u: Can't replay: filesystem " + "is frozen\n", jd->jd_jid); goto fail_gunlock_ji; + } if (test_bit(SDF_RORECOVERY, &sdp->sd_flags)) { ro = 1; @@ -496,7 +496,7 @@ void gfs2_recover_func(struct work_struct *work) fs_warn(sdp, "jid=%u: Can't replay: read-only block " "device\n", jd->jd_jid); error = -EROFS; - goto fail_gunlock_thaw; + goto fail_gunlock_nofreeze; } t_tlck = ktime_get(); @@ -514,7 +514,7 @@ void gfs2_recover_func(struct work_struct *work) lops_after_scan(jd, error, pass); if (error) { up_read(&sdp->sd_log_flush_lock); - goto fail_gunlock_thaw; + goto fail_gunlock_nofreeze; } } @@ -522,7 +522,7 @@ void gfs2_recover_func(struct work_struct *work) clean_journal(jd, &head); up_read(&sdp->sd_log_flush_lock); - gfs2_freeze_unlock(&thaw_gh); + mutex_unlock(&sdp->sd_freeze_mutex); t_rep = ktime_get(); fs_info(sdp, "jid=%u: Journal replayed in %lldms [jlck:%lldms, " "jhead:%lldms, tlck:%lldms, replay:%lldms]\n", @@ -543,8 +543,8 @@ void gfs2_recover_func(struct work_struct *work) fs_info(sdp, "jid=%u: Done\n", jd->jd_jid); goto done; -fail_gunlock_thaw: - gfs2_freeze_unlock(&thaw_gh); +fail_gunlock_nofreeze: + mutex_unlock(&sdp->sd_freeze_mutex); fail_gunlock_ji: if (jlocked) { gfs2_glock_dq_uninit(&ji_gh); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 3b9b76e980ad..9308190895c8 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -2584,8 +2584,8 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip) gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh); gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data); - rgrp_unlock_local(rgd); be32_add_cpu(&rgd->rd_rgl->rl_unlinked, -1); + rgrp_unlock_local(rgd); gfs2_statfs_change(sdp, 0, +1, -1); trace_gfs2_block_alloc(ip, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a84bf6444bba..9f4d5d6549ee 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -332,7 +332,12 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp) struct lfcc *lfcc; LIST_HEAD(list); struct gfs2_log_header_host lh; - int error; + int error, error2; + + /* + * Grab all the journal glocks in SH mode. We are *probably* doing + * that to prevent recovery. + */ list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { lfcc = kmalloc(sizeof(struct lfcc), GFP_KERNEL); @@ -349,11 +354,13 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp) list_add(&lfcc->list, &list); } + gfs2_freeze_unlock(&sdp->sd_freeze_gh); + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_EXCLUSIVE, LM_FLAG_NOEXP | GL_NOPID, &sdp->sd_freeze_gh); if (error) - goto out; + goto relock_shared; list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) { error = gfs2_jdesc_check(jd); @@ -368,8 +375,14 @@ static int gfs2_lock_fs_check_clean(struct gfs2_sbd *sdp) } } - if (error) - gfs2_freeze_unlock(&sdp->sd_freeze_gh); + if (!error) + goto out; /* success */ + + gfs2_freeze_unlock(&sdp->sd_freeze_gh); + +relock_shared: + error2 = gfs2_freeze_lock_shared(sdp); + gfs2_assert_withdraw(sdp, !error2); out: while (!list_empty(&list)) { @@ -463,7 +476,7 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc) * @flags: The type of dirty * * Unfortunately it can be called under any combination of inode - * glock and transaction lock, so we have to check carefully. + * glock and freeze glock, so we have to check carefully. * * At the moment this deals only with atime - it should be possible * to expand that role in future, once a review of the locking has @@ -615,6 +628,8 @@ restart: /* Release stuff */ + gfs2_freeze_unlock(&sdp->sd_freeze_gh); + iput(sdp->sd_jindex); iput(sdp->sd_statfs_inode); iput(sdp->sd_rindex); @@ -669,59 +684,109 @@ static int gfs2_sync_fs(struct super_block *sb, int wait) return sdp->sd_log_error; } -void gfs2_freeze_func(struct work_struct *work) +static int gfs2_freeze_locally(struct gfs2_sbd *sdp) { - int error; - struct gfs2_holder freeze_gh; - struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_freeze_work); struct super_block *sb = sdp->sd_vfs; + int error; - atomic_inc(&sb->s_active); - error = gfs2_freeze_lock(sdp, &freeze_gh, 0); - if (error) { - gfs2_assert_withdraw(sdp, 0); - } else { - atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN); - error = thaw_super(sb); - if (error) { - fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n", - error); - gfs2_assert_withdraw(sdp, 0); + error = freeze_super(sb); + if (error) + return error; + + if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { + gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_FREEZE | + GFS2_LFC_FREEZE_GO_SYNC); + if (gfs2_withdrawn(sdp)) { + thaw_super(sb); + return -EIO; } - gfs2_freeze_unlock(&freeze_gh); } + return 0; +} + +static int gfs2_do_thaw(struct gfs2_sbd *sdp) +{ + struct super_block *sb = sdp->sd_vfs; + int error; + + error = gfs2_freeze_lock_shared(sdp); + if (error) + goto fail; + error = thaw_super(sb); + if (!error) + return 0; + +fail: + fs_info(sdp, "GFS2: couldn't thaw filesystem: %d\n", error); + gfs2_assert_withdraw(sdp, 0); + return error; +} + +void gfs2_freeze_func(struct work_struct *work) +{ + struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_freeze_work); + struct super_block *sb = sdp->sd_vfs; + int error; + + mutex_lock(&sdp->sd_freeze_mutex); + error = -EBUSY; + if (test_bit(SDF_FROZEN, &sdp->sd_flags)) + goto freeze_failed; + + error = gfs2_freeze_locally(sdp); + if (error) + goto freeze_failed; + + gfs2_freeze_unlock(&sdp->sd_freeze_gh); + set_bit(SDF_FROZEN, &sdp->sd_flags); + + error = gfs2_do_thaw(sdp); + if (error) + goto out; + + clear_bit(SDF_FROZEN, &sdp->sd_flags); + goto out; + +freeze_failed: + fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", error); + +out: + mutex_unlock(&sdp->sd_freeze_mutex); deactivate_super(sb); - clear_bit_unlock(SDF_FS_FROZEN, &sdp->sd_flags); - wake_up_bit(&sdp->sd_flags, SDF_FS_FROZEN); - return; } /** - * gfs2_freeze - prevent further writes to the filesystem + * gfs2_freeze_super - prevent further writes to the filesystem * @sb: the VFS structure for the filesystem * */ -static int gfs2_freeze(struct super_block *sb) +static int gfs2_freeze_super(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; int error; - mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) { - error = -EBUSY; + if (!mutex_trylock(&sdp->sd_freeze_mutex)) + return -EBUSY; + error = -EBUSY; + if (test_bit(SDF_FROZEN, &sdp->sd_flags)) goto out; - } for (;;) { - if (gfs2_withdrawn(sdp)) { - error = -EINVAL; + error = gfs2_freeze_locally(sdp); + if (error) { + fs_info(sdp, "GFS2: couldn't freeze filesystem: %d\n", + error); goto out; } error = gfs2_lock_fs_check_clean(sdp); if (!error) - break; + break; /* success */ + + error = gfs2_do_thaw(sdp); + if (error) + goto out; if (error == -EBUSY) fs_err(sdp, "waiting for recovery before freeze\n"); @@ -735,32 +800,58 @@ static int gfs2_freeze(struct super_block *sb) fs_err(sdp, "retrying...\n"); msleep(1000); } - set_bit(SDF_FS_FROZEN, &sdp->sd_flags); + out: + if (!error) { + set_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags); + set_bit(SDF_FROZEN, &sdp->sd_flags); + } mutex_unlock(&sdp->sd_freeze_mutex); return error; } /** - * gfs2_unfreeze - reallow writes to the filesystem + * gfs2_thaw_super - reallow writes to the filesystem * @sb: the VFS structure for the filesystem * */ -static int gfs2_unfreeze(struct super_block *sb) +static int gfs2_thaw_super(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; + int error; - mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || - !gfs2_holder_initialized(&sdp->sd_freeze_gh)) { - mutex_unlock(&sdp->sd_freeze_mutex); - return -EINVAL; + if (!mutex_trylock(&sdp->sd_freeze_mutex)) + return -EBUSY; + error = -EINVAL; + if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags)) + goto out; + + gfs2_freeze_unlock(&sdp->sd_freeze_gh); + + error = gfs2_do_thaw(sdp); + + if (!error) { + clear_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags); + clear_bit(SDF_FROZEN, &sdp->sd_flags); } +out: + mutex_unlock(&sdp->sd_freeze_mutex); + return error; +} + +void gfs2_thaw_freeze_initiator(struct super_block *sb) +{ + struct gfs2_sbd *sdp = sb->s_fs_info; + + mutex_lock(&sdp->sd_freeze_mutex); + if (!test_bit(SDF_FREEZE_INITIATOR, &sdp->sd_flags)) + goto out; gfs2_freeze_unlock(&sdp->sd_freeze_gh); + +out: mutex_unlock(&sdp->sd_freeze_mutex); - return wait_on_bit(&sdp->sd_flags, SDF_FS_FROZEN, TASK_INTERRUPTIBLE); } /** @@ -1004,7 +1095,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) { struct gfs2_sbd *sdp = root->d_sb->s_fs_info; struct gfs2_args *args = &sdp->sd_args; - int val; + unsigned int logd_secs, statfs_slow, statfs_quantum, quota_quantum; + + spin_lock(&sdp->sd_tune.gt_spin); + logd_secs = sdp->sd_tune.gt_logd_secs; + quota_quantum = sdp->sd_tune.gt_quota_quantum; + statfs_quantum = sdp->sd_tune.gt_statfs_quantum; + statfs_slow = sdp->sd_tune.gt_statfs_slow; + spin_unlock(&sdp->sd_tune.gt_spin); if (is_ancestor(root, sdp->sd_master_dir)) seq_puts(s, ",meta"); @@ -1059,17 +1157,14 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root) } if (args->ar_discard) seq_puts(s, ",discard"); - val = sdp->sd_tune.gt_logd_secs; - if (val != 30) - seq_printf(s, ",commit=%d", val); - val = sdp->sd_tune.gt_statfs_quantum; - if (val != 30) - seq_printf(s, ",statfs_quantum=%d", val); - else if (sdp->sd_tune.gt_statfs_slow) + if (logd_secs != 30) + seq_printf(s, ",commit=%d", logd_secs); + if (statfs_quantum != 30) + seq_printf(s, ",statfs_quantum=%d", statfs_quantum); + else if (statfs_slow) seq_puts(s, ",statfs_quantum=0"); - val = sdp->sd_tune.gt_quota_quantum; - if (val != 60) - seq_printf(s, ",quota_quantum=%d", val); + if (quota_quantum != 60) + seq_printf(s, ",quota_quantum=%d", quota_quantum); if (args->ar_statfs_percent) seq_printf(s, ",statfs_percent=%d", args->ar_statfs_percent); if (args->ar_errors != GFS2_ERRORS_DEFAULT) { @@ -1131,9 +1226,7 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip) return -EIO; } - error = gfs2_rindex_update(sdp); - if (error) - return error; + gfs2_rindex_update(sdp); error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (error) @@ -1334,9 +1427,6 @@ static int evict_unlinked_inode(struct inode *inode) goto out; } - if (ip->i_gl) - gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino); - /* * As soon as we clear the bitmap for the dinode, gfs2_create_inode() * can get called to recreate it, or even gfs2_inode_lookup() if the @@ -1350,6 +1440,9 @@ static int evict_unlinked_inode(struct inode *inode) */ ret = gfs2_dinode_dealloc(ip); + if (!ret && ip->i_gl) + gfs2_inode_remember_delete(ip->i_gl, ip->i_no_formal_ino); + out: return ret; } @@ -1528,8 +1621,8 @@ const struct super_operations gfs2_super_ops = { .evict_inode = gfs2_evict_inode, .put_super = gfs2_put_super, .sync_fs = gfs2_sync_fs, - .freeze_super = gfs2_freeze, - .thaw_super = gfs2_unfreeze, + .freeze_super = gfs2_freeze_super, + .thaw_super = gfs2_thaw_super, .statfs = gfs2_statfs, .drop_inode = gfs2_drop_inode, .show_options = gfs2_show_options, diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h index 58d13fd77aed..bba58629bc45 100644 --- a/fs/gfs2/super.h +++ b/fs/gfs2/super.h @@ -46,6 +46,7 @@ extern void gfs2_statfs_change_out(const struct gfs2_statfs_change_host *sc, extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh); extern int gfs2_statfs_sync(struct super_block *sb, int type); extern void gfs2_freeze_func(struct work_struct *work); +extern void gfs2_thaw_freeze_initiator(struct super_block *sb); extern void free_local_statfs_inodes(struct gfs2_sbd *sdp); extern struct inode *find_local_statfs_inode(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index 454dc2ff8b5e..2dfbe2f188dd 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -82,6 +82,7 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf) "RO Recovery: %d\n" "Skip DLM Unlock: %d\n" "Force AIL Flush: %d\n" + "FS Freeze Initiator: %d\n" "FS Frozen: %d\n" "Withdrawing: %d\n" "Withdraw In Prog: %d\n" @@ -111,7 +112,8 @@ static ssize_t status_show(struct gfs2_sbd *sdp, char *buf) test_bit(SDF_RORECOVERY, &f), test_bit(SDF_SKIP_DLM_UNLOCK, &f), test_bit(SDF_FORCE_AIL_FLUSH, &f), - test_bit(SDF_FS_FROZEN, &f), + test_bit(SDF_FREEZE_INITIATOR, &f), + test_bit(SDF_FROZEN, &f), test_bit(SDF_WITHDRAWING, &f), test_bit(SDF_WITHDRAW_IN_PROG, &f), test_bit(SDF_REMOTE_WITHDRAW, &f), diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c index 63fec11ef2ce..ec1631257978 100644 --- a/fs/gfs2/trans.c +++ b/fs/gfs2/trans.c @@ -233,7 +233,6 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) struct gfs2_bufdata *bd; struct gfs2_meta_header *mh; struct gfs2_trans *tr = current->journal_info; - enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); lock_buffer(bh); if (buffer_pinned(bh)) { @@ -267,7 +266,7 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh) (unsigned long long)bd->bd_bh->b_blocknr); BUG(); } - if (unlikely(state == SFS_FROZEN)) { + if (unlikely(test_bit(SDF_FROZEN, &sdp->sd_flags))) { fs_info(sdp, "GFS2:adding buf while frozen\n"); gfs2_assert_withdraw(sdp, 0); } diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 7a6aeffcdf5c..dac22b1c1a2e 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -93,21 +93,18 @@ out_unlock: } /** - * gfs2_freeze_lock - hold the freeze glock + * gfs2_freeze_lock_shared - hold the freeze glock * @sdp: the superblock - * @freeze_gh: pointer to the requested holder - * @caller_flags: any additional flags needed by the caller */ -int gfs2_freeze_lock(struct gfs2_sbd *sdp, struct gfs2_holder *freeze_gh, - int caller_flags) +int gfs2_freeze_lock_shared(struct gfs2_sbd *sdp) { - int flags = LM_FLAG_NOEXP | GL_EXACT | caller_flags; int error; - error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, flags, - freeze_gh); - if (error && error != GLR_TRYFAILED) - fs_err(sdp, "can't lock the freeze lock: %d\n", error); + error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, + LM_FLAG_NOEXP | GL_EXACT, + &sdp->sd_freeze_gh); + if (error) + fs_err(sdp, "can't lock the freeze glock: %d\n", error); return error; } @@ -124,7 +121,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) struct gfs2_inode *ip; struct gfs2_glock *i_gl; u64 no_formal_ino; - int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); int ret = 0; int tries; @@ -152,24 +148,18 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) */ clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags); if (!sb_rdonly(sdp->sd_vfs)) { - struct gfs2_holder freeze_gh; - - gfs2_holder_mark_uninitialized(&freeze_gh); - if (sdp->sd_freeze_gl && - !gfs2_glock_is_locked_by_me(sdp->sd_freeze_gl)) { - ret = gfs2_freeze_lock(sdp, &freeze_gh, - log_write_allowed ? 0 : LM_FLAG_TRY); - if (ret == GLR_TRYFAILED) - ret = 0; - } - if (!ret) - gfs2_make_fs_ro(sdp); + bool locked = mutex_trylock(&sdp->sd_freeze_mutex); + + gfs2_make_fs_ro(sdp); + + if (locked) + mutex_unlock(&sdp->sd_freeze_mutex); + /* * Dequeue any pending non-system glock holders that can no * longer be granted because the file system is withdrawn. */ gfs2_gl_dq_holders(sdp); - gfs2_freeze_unlock(&freeze_gh); } if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ @@ -187,15 +177,8 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) } sdp->sd_jinode_gh.gh_flags |= GL_NOCACHE; gfs2_glock_dq(&sdp->sd_jinode_gh); - if (test_bit(SDF_FS_FROZEN, &sdp->sd_flags)) { - /* Make sure gfs2_unfreeze works if partially-frozen */ - flush_work(&sdp->sd_freeze_work); - atomic_set(&sdp->sd_freeze_state, SFS_FROZEN); - thaw_super(sdp->sd_vfs); - } else { - wait_on_bit(&i_gl->gl_flags, GLF_DEMOTE, - TASK_UNINTERRUPTIBLE); - } + gfs2_thaw_freeze_initiator(sdp->sd_vfs); + wait_on_bit(&i_gl->gl_flags, GLF_DEMOTE, TASK_UNINTERRUPTIBLE); /* * holder_uninit to force glock_put, to force dlm to let go diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h index 78ec190f4155..cdb839529175 100644 --- a/fs/gfs2/util.h +++ b/fs/gfs2/util.h @@ -149,8 +149,7 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, extern int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, bool verbose); -extern int gfs2_freeze_lock(struct gfs2_sbd *sdp, - struct gfs2_holder *freeze_gh, int caller_flags); +extern int gfs2_freeze_lock_shared(struct gfs2_sbd *sdp); extern void gfs2_freeze_unlock(struct gfs2_holder *freeze_gh); #define gfs2_io_error(sdp) \ diff --git a/fs/inode.c b/fs/inode.c index d37fad91c8da..8fefb69e1f84 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1156,8 +1156,10 @@ lock: */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { - WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); - WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); + if (inode1) + WARN_ON_ONCE(S_ISDIR(inode1->i_mode)); + if (inode2) + WARN_ON_ONCE(S_ISDIR(inode2->i_mode)); lock_two_inodes(inode1, inode2, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 45b6919903e6..5a1a4af9d3d2 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -655,7 +655,9 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out3: + spin_lock(&kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); + spin_unlock(&kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: diff --git a/fs/namei.c b/fs/namei.c index 91171da719c5..e56ff39a79bc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -4874,8 +4874,7 @@ int vfs_rename(struct renamedata *rd) d_exchange(old_dentry, new_dentry); } out: - if (source) - inode_unlock(source); + inode_unlock(source); if (target) inode_unlock(target); dput(new_dentry); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 95d7d8790bc3..f69c451018e3 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1623,6 +1623,20 @@ static int fanotify_events_supported(struct fsnotify_group *group, return -EINVAL; /* + * mount and sb marks are not allowed on kernel internal pseudo fs, + * like pipe_mnt, because that would subscribe to events on all the + * anonynous pipes in the system. + * + * SB_NOUSER covers all of the internal pseudo fs whose objects are not + * exposed to user's mount namespace, but there are other SB_KERNMOUNT + * fs, like nsfs, debugfs, for which the value of allowing sb and mount + * mark is questionable. For now we leave them alone. + */ + if (mark_type != FAN_MARK_INODE && + path->mnt->mnt_sb->s_flags & SB_NOUSER) + return -EINVAL; + + /* * We shouldn't have allowed setting dirent events and the directory * flags FAN_ONDIR and FAN_EVENT_ON_CHILD in mask of non-dir inode, * but because we always allowed it, error only when using new APIs. diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 0b8bc66377db..a9d82bbb4729 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -573,7 +573,7 @@ add_alloc_in_same_attr_seg: sbi, run, vcn, lcn, to_allocate, &pre_alloc, is_mft ? ALLOCATE_MFT : ALLOCATE_DEF, &alen, is_mft ? 0 : - (sbi->record_size - + (sbi->record_size - le32_to_cpu(rec->used) + 8) / 3 + 1, diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index c0c6bcbc8c05..42631b31adf1 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +80,7 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS); + le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); if (!le) { err = -ENOMEM; goto out; @@ -375,8 +375,7 @@ bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le) * al_delete_le - Delete first le from the list which matches its parameters. */ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, - const __le16 *name, size_t name_len, - const struct MFT_REF *ref) + const __le16 *name, u8 name_len, const struct MFT_REF *ref) { u16 size; struct ATTR_LIST_ENTRY *le; diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 9a6c6a09d70c..107e808e06ea 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -287,8 +287,8 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, /* Check bits before 'bit'. */ ib = wnd->zone_bit == wnd->zone_end || bit < wnd->zone_end ? - 0 : - wnd->zone_end; + 0 : + wnd->zone_end; while (bit > ib && wnd_is_free_hlp(wnd, bit - 1, 1)) { bit -= 1; @@ -298,8 +298,8 @@ static void wnd_add_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len, /* Check bits after 'end_in'. */ ib = wnd->zone_bit == wnd->zone_end || end_in > wnd->zone_bit ? - wnd->nbits : - wnd->zone_bit; + wnd->nbits : + wnd->zone_bit; while (end_in < ib && wnd_is_free_hlp(wnd, end_in, 1)) { end_in += 1; @@ -418,7 +418,7 @@ static void wnd_remove_free_ext(struct wnd_bitmap *wnd, size_t bit, size_t len) n3 = rb_first(&wnd->count_tree); wnd->extent_max = n3 ? rb_entry(n3, struct e_node, count.node)->count.key : - 0; + 0; return; } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 9be3e8edf4f3..1d6c824246c4 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -179,7 +179,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) { int err = 0; struct address_space *mapping = inode->i_mapping; - u32 blocksize = 1 << inode->i_blkbits; + u32 blocksize = i_blocksize(inode); pgoff_t idx = vbo >> PAGE_SHIFT; u32 from = vbo & (PAGE_SIZE - 1); pgoff_t idx_end = (vbo_to + PAGE_SIZE - 1) >> PAGE_SHIFT; @@ -192,7 +192,7 @@ static int ntfs_zero_range(struct inode *inode, u64 vbo, u64 vbo_to) for (; idx < idx_end; idx += 1, from = 0) { page_off = (loff_t)idx << PAGE_SHIFT; to = (page_off + PAGE_SIZE) > vbo_to ? (vbo_to - page_off) : - PAGE_SIZE; + PAGE_SIZE; iblock = page_off >> inode->i_blkbits; page = find_or_create_page(mapping, idx, @@ -1078,7 +1078,7 @@ static ssize_t ntfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) goto out; ret = is_compressed(ni) ? ntfs_compress_write(iocb, from) : - __generic_file_write_iter(iocb, from); + __generic_file_write_iter(iocb, from); out: inode_unlock(inode); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 2bfcf1a989c9..16bd9faa2d28 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -77,7 +77,7 @@ struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni) attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) : - NULL; + NULL; } /* @@ -92,7 +92,7 @@ struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni) attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) : - NULL; + NULL; } /* @@ -236,6 +236,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, return attr; out: + ntfs_inode_err(&ni->vfs_inode, "failed to parse mft record"); ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); return NULL; } @@ -384,7 +385,7 @@ bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) * ni_remove_attr - Remove all attributes for the given type/name/id. */ int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, - const __le16 *name, size_t name_len, bool base_only, + const __le16 *name, u8 name_len, bool base_only, const __le16 *id) { int err; @@ -517,6 +518,9 @@ out: */ static int ni_repack(struct ntfs_inode *ni) { +#if 1 + return 0; +#else int err = 0; struct ntfs_sb_info *sbi = ni->mi.sbi; struct mft_inode *mi, *mi_p = NULL; @@ -639,6 +643,7 @@ static int ni_repack(struct ntfs_inode *ni) run_close(&run); return err; +#endif } /* @@ -813,10 +818,8 @@ int ni_create_attr_list(struct ntfs_inode *ni) * Looks like one record_size is always enough. */ le = kmalloc(al_aligned(rs), GFP_NOFS); - if (!le) { - err = -ENOMEM; - goto out; - } + if (!le) + return -ENOMEM; mi_get_ref(&ni->mi, &le->ref); ni->attr_list.le = le; @@ -865,15 +868,16 @@ int ni_create_attr_list(struct ntfs_inode *ni) if (to_free > free_b) { err = -EINVAL; - goto out1; + goto out; } } /* Allocate child MFT. */ err = ntfs_look_free_mft(sbi, &rno, is_mft, ni, &mi); if (err) - goto out1; + goto out; + err = -EINVAL; /* Call mi_remove_attr() in reverse order to keep pointers 'arr_move' valid. */ while (to_free > 0) { struct ATTRIB *b = arr_move[--nb]; @@ -882,7 +886,8 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), b->name_len, asize, name_off); - WARN_ON(!attr); + if (!attr) + goto out; mi_get_ref(mi, &le_b[nb]->ref); le_b[nb]->id = attr->id; @@ -892,17 +897,20 @@ int ni_create_attr_list(struct ntfs_inode *ni) attr->id = le_b[nb]->id; /* Remove from primary record. */ - WARN_ON(!mi_remove_attr(NULL, &ni->mi, b)); + if (!mi_remove_attr(NULL, &ni->mi, b)) + goto out; if (to_free <= asize) break; to_free -= asize; - WARN_ON(!nb); + if (!nb) + goto out; } attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); - WARN_ON(!attr); + if (!attr) + goto out; attr->non_res = 0; attr->flags = 0; @@ -916,14 +924,12 @@ int ni_create_attr_list(struct ntfs_inode *ni) ni->attr_list.dirty = false; mark_inode_dirty(&ni->vfs_inode); - goto out; + return 0; -out1: +out: kfree(ni->attr_list.le); ni->attr_list.le = NULL; ni->attr_list.size = 0; - -out: return err; } @@ -1638,14 +1644,13 @@ int ni_delete_all(struct ntfs_inode *ni) * Return: File name attribute by its value. */ struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, - const struct cpu_str *uni, + const struct le_str *uni, const struct MFT_REF *home_dir, struct mft_inode **mi, struct ATTR_LIST_ENTRY **le) { struct ATTRIB *attr = NULL; struct ATTR_FILE_NAME *fname; - struct le_str *fns; if (le) *le = NULL; @@ -1669,10 +1674,9 @@ next: if (uni->len != fname->name_len) goto next; - fns = (struct le_str *)&fname->name_len; - if (ntfs_cmp_names_cpu(uni, fns, NULL, false)) + if (ntfs_cmp_names(uni->name, uni->len, fname->name, uni->len, NULL, + false)) goto next; - return fname; } @@ -1757,8 +1761,8 @@ int ni_new_attr_flags(struct ntfs_inode *ni, enum FILE_ATTRIBUTE new_fa) /* Resize nonresident empty attribute in-place only. */ new_asize = (new_aflags & (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED)) ? - (SIZEOF_NONRESIDENT_EX + 8) : - (SIZEOF_NONRESIDENT + 8); + (SIZEOF_NONRESIDENT_EX + 8) : + (SIZEOF_NONRESIDENT + 8); if (!mi_resize_attr(mi, attr, new_asize - le32_to_cpu(attr->size))) return -EOPNOTSUPP; @@ -2910,7 +2914,7 @@ int ni_remove_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, /* Find name in record. */ mi_get_ref(&dir_ni->mi, &de_name->home); - fname = ni_fname_name(ni, (struct cpu_str *)&de_name->name_len, + fname = ni_fname_name(ni, (struct le_str *)&de_name->name_len, &de_name->home, &mi, &le); if (!fname) return -ENOENT; @@ -3160,8 +3164,8 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, __le64 valid_le; dup->alloc_size = is_attr_ext(attr) ? - attr->nres.total_size : - attr->nres.alloc_size; + attr->nres.total_size : + attr->nres.alloc_size; dup->data_size = attr->nres.data_size; if (new_valid > data_size) diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 57762c5fe68b..12f28cdf5c83 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -828,8 +828,8 @@ static inline struct RESTART_TABLE *extend_rsttbl(struct RESTART_TABLE *tbl, memcpy(rt + 1, tbl + 1, esize * used); rt->free_goal = free_goal == ~0u ? - cpu_to_le32(~0u) : - cpu_to_le32(sizeof(struct RESTART_TABLE) + + cpu_to_le32(~0u) : + cpu_to_le32(sizeof(struct RESTART_TABLE) + free_goal * esize); if (tbl->first_free) { @@ -1090,8 +1090,8 @@ static inline u64 base_lsn(struct ntfs_log *log, << log->file_data_bits) + ((((is_log_record_end(hdr) && h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn)) ? - le16_to_cpu(hdr->record_hdr.next_record_off) : - log->page_size) + + le16_to_cpu(hdr->record_hdr.next_record_off) : + log->page_size) + lsn) >> 3); @@ -1299,8 +1299,8 @@ static void log_init_pg_hdr(struct ntfs_log *log, u32 sys_page_size, log->clst_per_page = 1; log->first_page = major_ver >= 2 ? - 0x22 * page_size : - ((sys_page_size << 1) + (page_size << 1)); + 0x22 * page_size : + ((sys_page_size << 1) + (page_size << 1)); log->major_ver = major_ver; log->minor_ver = minor_ver; } @@ -1513,8 +1513,8 @@ static u32 current_log_avail(struct ntfs_log *log) * If there is no oldest lsn then start at the first page of the file. */ oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN) ? - log->first_page : - (log->oldest_lsn_off & ~log->sys_page_mask); + log->first_page : + (log->oldest_lsn_off & ~log->sys_page_mask); /* * We will use the next log page offset to compute the next free page. @@ -1522,9 +1522,9 @@ static u32 current_log_avail(struct ntfs_log *log) * If we are at the first page then use the end of the file. */ next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL) ? - log->next_page + log->page_size : + log->next_page + log->page_size : log->next_page == log->first_page ? log->l_size : - log->next_page; + log->next_page; /* If the two offsets are the same then there is no available space. */ if (oldest_off == next_free_off) @@ -1535,8 +1535,8 @@ static u32 current_log_avail(struct ntfs_log *log) */ free_bytes = oldest_off < next_free_off ? - log->total_avail_pages - (next_free_off - oldest_off) : - oldest_off - next_free_off; + log->total_avail_pages - (next_free_off - oldest_off) : + oldest_off - next_free_off; free_bytes >>= log->page_bits; return free_bytes * log->reserved; @@ -1671,7 +1671,7 @@ next_tail: best_lsn1 = first_tail ? base_lsn(log, first_tail, first_file_off) : 0; best_lsn2 = second_tail ? base_lsn(log, second_tail, second_file_off) : - 0; + 0; if (first_tail && second_tail) { if (best_lsn1 > best_lsn2) { @@ -1767,7 +1767,7 @@ tail_read: page_cnt = page_pos = 1; curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off) : - log->next_page; + log->next_page; wrapped_file = curpage_off == log->first_page && @@ -1826,8 +1826,8 @@ use_cur_page: ((lsn_cur >> log->file_data_bits) + ((curpage_off < (lsn_to_vbo(log, lsn_cur) & ~log->page_mask)) ? - 1 : - 0)) != expected_seq) { + 1 : + 0)) != expected_seq) { goto check_tail; } @@ -2643,8 +2643,8 @@ static inline bool check_index_root(const struct ATTRIB *attr, const struct INDEX_ROOT *root = resident_data(attr); u8 index_bits = le32_to_cpu(root->index_block_size) >= sbi->cluster_size ? - sbi->cluster_bits : - SECTOR_SHIFT; + sbi->cluster_bits : + SECTOR_SHIFT; u8 block_clst = root->index_block_clst; if (le32_to_cpu(attr->res.data_size) < sizeof(struct INDEX_ROOT) || @@ -3861,9 +3861,9 @@ check_restart_area: /* If we have a valid page then grab a pointer to the restart area. */ ra2 = rst_info.valid_page ? - Add2Ptr(rst_info.r_page, + Add2Ptr(rst_info.r_page, le16_to_cpu(rst_info.r_page->ra_off)) : - NULL; + NULL; if (rst_info.chkdsk_was_run || (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) { diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 28cc421102e5..33afee0f5559 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -9,6 +9,7 @@ #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/kernel.h> +#include <linux/nls.h> #include "debug.h" #include "ntfs.h" @@ -173,12 +174,12 @@ int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, fo = le16_to_cpu(rhdr->fix_off); fn = simple ? ((bytes >> SECTOR_SHIFT) + 1) : - le16_to_cpu(rhdr->fix_num); + le16_to_cpu(rhdr->fix_num); /* Check errors. */ if ((fo & 1) || fo + fn * sizeof(short) > SECTOR_SIZE || !fn-- || fn * SECTOR_SIZE > bytes) { - return -EINVAL; /* Native chkntfs returns ok! */ + return -E_NTFS_CORRUPT; } /* Get fixup pointer. */ @@ -1661,7 +1662,8 @@ int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, return 0; } -struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) +struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, + enum RECORD_FLAG flag) { int err = 0; struct super_block *sb = sbi->sb; @@ -1673,8 +1675,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) ni = ntfs_i(inode); - err = mi_format_new(&ni->mi, sbi, rno, dir ? RECORD_FLAG_DIR : 0, - false); + err = mi_format_new(&ni->mi, sbi, rno, flag, false); if (err) goto out; @@ -1937,7 +1938,7 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) break; sii_e = (struct NTFS_DE_SII *)ne; - if (le16_to_cpu(ne->view.data_size) < SIZEOF_SECURITY_HDR) + if (le16_to_cpu(ne->view.data_size) < sizeof(sii_e->sec_hdr)) continue; next_id = le32_to_cpu(sii_e->sec_id) + 1; @@ -1998,18 +1999,18 @@ int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, goto out; t32 = le32_to_cpu(sii_e->sec_hdr.size); - if (t32 < SIZEOF_SECURITY_HDR) { + if (t32 < sizeof(struct SECURITY_HDR)) { err = -EINVAL; goto out; } - if (t32 > SIZEOF_SECURITY_HDR + 0x10000) { + if (t32 > sizeof(struct SECURITY_HDR) + 0x10000) { /* Looks like too big security. 0x10000 - is arbitrary big number. */ err = -EFBIG; goto out; } - *size = t32 - SIZEOF_SECURITY_HDR; + *size = t32 - sizeof(struct SECURITY_HDR); p = kmalloc(*size, GFP_NOFS); if (!p) { @@ -2023,14 +2024,14 @@ int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, if (err) goto out; - if (memcmp(&d_security, &sii_e->sec_hdr, SIZEOF_SECURITY_HDR)) { + if (memcmp(&d_security, &sii_e->sec_hdr, sizeof(d_security))) { err = -EINVAL; goto out; } err = ntfs_read_run_nb(sbi, &ni->file.run, le64_to_cpu(sii_e->sec_hdr.off) + - SIZEOF_SECURITY_HDR, + sizeof(struct SECURITY_HDR), p, *size, NULL); if (err) goto out; @@ -2069,7 +2070,7 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi, struct NTFS_DE_SDH sdh_e; struct NTFS_DE_SII sii_e; struct SECURITY_HDR *d_security; - u32 new_sec_size = size_sd + SIZEOF_SECURITY_HDR; + u32 new_sec_size = size_sd + sizeof(struct SECURITY_HDR); u32 aligned_sec_size = ALIGN(new_sec_size, 16); struct SECURITY_KEY hash_key; struct ntfs_fnd *fnd_sdh = NULL; @@ -2207,14 +2208,14 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi, /* Fill SII entry. */ sii_e.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_SII, sec_hdr)); - sii_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR); + sii_e.de.view.data_size = cpu_to_le16(sizeof(struct SECURITY_HDR)); sii_e.de.view.res = 0; - sii_e.de.size = cpu_to_le16(SIZEOF_SII_DIRENTRY); + sii_e.de.size = cpu_to_le16(sizeof(struct NTFS_DE_SII)); sii_e.de.key_size = cpu_to_le16(sizeof(d_security->key.sec_id)); sii_e.de.flags = 0; sii_e.de.res = 0; sii_e.sec_id = d_security->key.sec_id; - memcpy(&sii_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR); + memcpy(&sii_e.sec_hdr, d_security, sizeof(struct SECURITY_HDR)); err = indx_insert_entry(indx_sii, ni, &sii_e.de, NULL, NULL, 0); if (err) @@ -2223,7 +2224,7 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi, /* Fill SDH entry. */ sdh_e.de.view.data_off = cpu_to_le16(offsetof(struct NTFS_DE_SDH, sec_hdr)); - sdh_e.de.view.data_size = cpu_to_le16(SIZEOF_SECURITY_HDR); + sdh_e.de.view.data_size = cpu_to_le16(sizeof(struct SECURITY_HDR)); sdh_e.de.view.res = 0; sdh_e.de.size = cpu_to_le16(SIZEOF_SDH_DIRENTRY); sdh_e.de.key_size = cpu_to_le16(sizeof(sdh_e.key)); @@ -2231,7 +2232,7 @@ int ntfs_insert_security(struct ntfs_sb_info *sbi, sdh_e.de.res = 0; sdh_e.key.hash = d_security->key.hash; sdh_e.key.sec_id = d_security->key.sec_id; - memcpy(&sdh_e.sec_hdr, d_security, SIZEOF_SECURITY_HDR); + memcpy(&sdh_e.sec_hdr, d_security, sizeof(struct SECURITY_HDR)); sdh_e.magic[0] = cpu_to_le16('I'); sdh_e.magic[1] = cpu_to_le16('I'); @@ -2522,7 +2523,8 @@ out: /* * run_deallocate - Deallocate clusters. */ -int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim) +int run_deallocate(struct ntfs_sb_info *sbi, const struct runs_tree *run, + bool trim) { CLST lcn, len; size_t idx = 0; @@ -2578,13 +2580,13 @@ static inline bool name_has_forbidden_chars(const struct le_str *fname) return false; } -static inline bool is_reserved_name(struct ntfs_sb_info *sbi, +static inline bool is_reserved_name(const struct ntfs_sb_info *sbi, const struct le_str *fname) { int port_digit; const __le16 *name = fname->name; int len = fname->len; - u16 *upcase = sbi->upcase; + const u16 *upcase = sbi->upcase; /* check for 3 chars reserved names (device names) */ /* name by itself or with any extension is forbidden */ @@ -2618,3 +2620,60 @@ bool valid_windows_name(struct ntfs_sb_info *sbi, const struct le_str *fname) return !name_has_forbidden_chars(fname) && !is_reserved_name(sbi, fname); } + +/* + * ntfs_set_label - updates current ntfs label. + */ +int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len) +{ + int err; + struct ATTRIB *attr; + struct ntfs_inode *ni = sbi->volume.ni; + const u8 max_ulen = 0x80; /* TODO: use attrdef to get maximum length */ + /* Allocate PATH_MAX bytes. */ + struct cpu_str *uni = __getname(); + + if (!uni) + return -ENOMEM; + + err = ntfs_nls_to_utf16(sbi, label, len, uni, (PATH_MAX - 2) / 2, + UTF16_LITTLE_ENDIAN); + if (err < 0) + goto out; + + if (uni->len > max_ulen) { + ntfs_warn(sbi->sb, "new label is too long"); + err = -EFBIG; + goto out; + } + + ni_lock(ni); + + /* Ignore any errors. */ + ni_remove_attr(ni, ATTR_LABEL, NULL, 0, false, NULL); + + err = ni_insert_resident(ni, uni->len * sizeof(u16), ATTR_LABEL, NULL, + 0, &attr, NULL, NULL); + if (err < 0) + goto unlock_out; + + /* write new label in on-disk struct. */ + memcpy(resident_data(attr), uni->name, uni->len * sizeof(u16)); + + /* update cached value of current label. */ + if (len >= ARRAY_SIZE(sbi->volume.label)) + len = ARRAY_SIZE(sbi->volume.label) - 1; + memcpy(sbi->volume.label, label, len); + sbi->volume.label[len] = 0; + mark_inode_dirty_sync(&ni->vfs_inode); + +unlock_out: + ni_unlock(ni); + + if (!err) + err = _ni_write_inode(&ni->vfs_inode, 0); + +out: + __putname(uni); + return err; +}
\ No newline at end of file diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 0a48d2d67219..124c6e822623 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -432,8 +432,8 @@ next_run: nbits = 8 * (data_size - vbo); ok = nbits > from ? - (*fn)((ulong *)bh->b_data, from, nbits, ret) : - false; + (*fn)((ulong *)bh->b_data, from, nbits, ret) : + false; put_bh(bh); if (ok) { @@ -1113,6 +1113,12 @@ ok: *node = in; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); + ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + if (ib != in->index) kfree(ib); @@ -1676,8 +1682,8 @@ static int indx_insert_into_root(struct ntfs_index *indx, struct ntfs_inode *ni, /* Create alloc and bitmap attributes (if not). */ err = run_is_empty(&indx->alloc_run) ? - indx_create_allocate(indx, ni, &new_vbn) : - indx_add_allocate(indx, ni, &new_vbn); + indx_create_allocate(indx, ni, &new_vbn) : + indx_add_allocate(indx, ni, &new_vbn); /* Layout of record may be changed, so rescan root. */ root = indx_get_root(indx, ni, &attr, &mi); @@ -1868,8 +1874,8 @@ indx_insert_into_buffer(struct ntfs_index *indx, struct ntfs_inode *ni, (*indx->cmp)(new_de + 1, le16_to_cpu(new_de->key_size), up_e + 1, le16_to_cpu(up_e->key_size), ctx) < 0 ? - hdr2 : - hdr1, + hdr2 : + hdr1, new_de, NULL, ctx); indx_mark_used(indx, ni, new_vbn >> indx->idx2vbn_bits); @@ -2340,7 +2346,7 @@ int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, re, ctx, fnd->level - 1, fnd) : - indx_insert_into_root(indx, ni, re, e, + indx_insert_into_root(indx, ni, re, e, ctx, fnd, 0); kfree(re); diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index 6c560245eef4..dc7e7ab701c6 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -263,7 +263,7 @@ next_attr: goto next_attr; run = ino == MFT_REC_BITMAP ? &sbi->used.bitmap.run : - &ni->file.run; + &ni->file.run; break; case ATTR_ROOT: @@ -291,8 +291,8 @@ next_attr: goto out; mode = sb->s_root ? - (S_IFDIR | (0777 & sbi->options->fs_dmask_inv)) : - (S_IFDIR | 0777); + (S_IFDIR | (0777 & sbi->options->fs_dmask_inv)) : + (S_IFDIR | 0777); goto next_attr; case ATTR_ALLOC: @@ -450,7 +450,7 @@ end_enum: inode->i_op = &ntfs_file_inode_operations; inode->i_fop = &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : - &ntfs_aops; + &ntfs_aops; if (ino != MFT_REC_MFT) init_rwsem(&ni->file.run_lock); } else if (S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || @@ -787,7 +787,7 @@ static ssize_t ntfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ret = blockdev_direct_IO(iocb, inode, iter, wr ? ntfs_get_block_direct_IO_W : - ntfs_get_block_direct_IO_R); + ntfs_get_block_direct_IO_R); if (ret > 0) end = vbo + ret; @@ -1191,11 +1191,11 @@ out: * - ntfs_symlink * - ntfs_mkdir * - ntfs_atomic_open - * + * * NOTE: if fnd != NULL (ntfs_atomic_open) then @dir is locked */ -struct inode *ntfs_create_inode(struct mnt_idmap *idmap, - struct inode *dir, struct dentry *dentry, +struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, struct ntfs_fnd *fnd) @@ -1309,7 +1309,7 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, if (err) goto out2; - ni = ntfs_new_inode(sbi, ino, fa & FILE_ATTRIBUTE_DIRECTORY); + ni = ntfs_new_inode(sbi, ino, S_ISDIR(mode) ? RECORD_FLAG_DIR : 0); if (IS_ERR(ni)) { err = PTR_ERR(ni); ni = NULL; @@ -1437,8 +1437,7 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, root = Add2Ptr(attr, sizeof(I30_NAME) + SIZEOF_RESIDENT); memcpy(root, dir_root, offsetof(struct INDEX_ROOT, ihdr)); - root->ihdr.de_off = - cpu_to_le32(sizeof(struct INDEX_HDR)); // 0x10 + root->ihdr.de_off = cpu_to_le32(sizeof(struct INDEX_HDR)); root->ihdr.used = cpu_to_le32(sizeof(struct INDEX_HDR) + sizeof(struct NTFS_DE)); root->ihdr.total = root->ihdr.used; @@ -1605,7 +1604,7 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, inode->i_op = &ntfs_file_inode_operations; inode->i_fop = &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : - &ntfs_aops; + &ntfs_aops; init_rwsem(&ni->file.run_lock); } else { inode->i_op = &ntfs_special_inode_operations; diff --git a/fs/ntfs3/lznt.c b/fs/ntfs3/lznt.c index 61e161c7c567..4aae598d6d88 100644 --- a/fs/ntfs3/lznt.c +++ b/fs/ntfs3/lznt.c @@ -297,7 +297,7 @@ next: struct lznt *get_lznt_ctx(int level) { struct lznt *r = kzalloc(level ? offsetof(struct lznt, hash) : - sizeof(struct lznt), + sizeof(struct lznt), GFP_NOFS); if (r) @@ -393,8 +393,8 @@ ssize_t decompress_lznt(const void *cmpr, size_t cmpr_size, void *unc, } else { /* This chunk does not contain compressed data. */ unc_use = unc_chunk + LZNT_CHUNK_SIZE > unc_end ? - unc_end - unc_chunk : - LZNT_CHUNK_SIZE; + unc_end - unc_chunk : + LZNT_CHUNK_SIZE; if (cmpr_chunk + sizeof(chunk_hdr) + unc_use > cmpr_end) { diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index 9736b1e4a0f6..70f8c859e0ad 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -109,8 +109,8 @@ static int ntfs_create(struct mnt_idmap *idmap, struct inode *dir, { struct inode *inode; - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, - 0, NULL, 0, NULL); + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFREG | mode, 0, + NULL, 0, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; } @@ -125,8 +125,8 @@ static int ntfs_mknod(struct mnt_idmap *idmap, struct inode *dir, { struct inode *inode; - inode = ntfs_create_inode(idmap, dir, dentry, NULL, mode, rdev, - NULL, 0, NULL); + inode = ntfs_create_inode(idmap, dir, dentry, NULL, mode, rdev, NULL, 0, + NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; } @@ -199,8 +199,8 @@ static int ntfs_symlink(struct mnt_idmap *idmap, struct inode *dir, u32 size = strlen(symname); struct inode *inode; - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, - 0, symname, size, NULL); + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFLNK | 0777, 0, + symname, size, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; } @@ -213,8 +213,8 @@ static int ntfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, { struct inode *inode; - inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, - 0, NULL, 0, NULL); + inode = ntfs_create_inode(idmap, dir, dentry, NULL, S_IFDIR | mode, 0, + NULL, 0, NULL); return IS_ERR(inode) ? PTR_ERR(inode) : 0; } @@ -422,19 +422,10 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, * fnd contains tree's path to insert to. * If fnd is not NULL then dir is locked. */ - - /* - * Unfortunately I don't know how to get here correct 'struct nameidata *nd' - * or 'struct mnt_idmap *idmap'. - * See atomic_open in fs/namei.c. - * This is why xfstest/633 failed. - * Looks like ntfs_atomic_open must accept 'struct mnt_idmap *idmap' as argument. - */ - - inode = ntfs_create_inode(&nop_mnt_idmap, dir, dentry, uni, mode, 0, - NULL, 0, fnd); + inode = ntfs_create_inode(mnt_idmap(file->f_path.mnt), dir, dentry, uni, + mode, 0, NULL, 0, fnd); err = IS_ERR(inode) ? PTR_ERR(inode) : - finish_open(file, dentry, ntfs_file_open); + finish_open(file, dentry, ntfs_file_open); dput(d); out2: diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 90151e56c122..98b76d1b09e7 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -95,11 +95,10 @@ enum RECORD_NUM { MFT_REC_BITMAP = 6, MFT_REC_BOOT = 7, MFT_REC_BADCLUST = 8, - //MFT_REC_QUOTA = 9, - MFT_REC_SECURE = 9, // NTFS 3.0 + MFT_REC_SECURE = 9, MFT_REC_UPCASE = 10, - MFT_REC_EXTEND = 11, // NTFS 3.0 - MFT_REC_RESERVED = 11, + MFT_REC_EXTEND = 11, + MFT_REC_RESERVED = 12, MFT_REC_FREE = 16, MFT_REC_USER = 24, }; @@ -109,7 +108,6 @@ enum ATTR_TYPE { ATTR_STD = cpu_to_le32(0x10), ATTR_LIST = cpu_to_le32(0x20), ATTR_NAME = cpu_to_le32(0x30), - // ATTR_VOLUME_VERSION on Nt4 ATTR_ID = cpu_to_le32(0x40), ATTR_SECURE = cpu_to_le32(0x50), ATTR_LABEL = cpu_to_le32(0x60), @@ -118,7 +116,6 @@ enum ATTR_TYPE { ATTR_ROOT = cpu_to_le32(0x90), ATTR_ALLOC = cpu_to_le32(0xA0), ATTR_BITMAP = cpu_to_le32(0xB0), - // ATTR_SYMLINK on Nt4 ATTR_REPARSE = cpu_to_le32(0xC0), ATTR_EA_INFO = cpu_to_le32(0xD0), ATTR_EA = cpu_to_le32(0xE0), @@ -144,6 +141,7 @@ enum FILE_ATTRIBUTE { FILE_ATTRIBUTE_ENCRYPTED = cpu_to_le32(0x00004000), FILE_ATTRIBUTE_VALID_FLAGS = cpu_to_le32(0x00007fb7), FILE_ATTRIBUTE_DIRECTORY = cpu_to_le32(0x10000000), + FILE_ATTRIBUTE_INDEX = cpu_to_le32(0x20000000) }; static_assert(sizeof(enum FILE_ATTRIBUTE) == 4); @@ -266,7 +264,7 @@ enum RECORD_FLAG { RECORD_FLAG_IN_USE = cpu_to_le16(0x0001), RECORD_FLAG_DIR = cpu_to_le16(0x0002), RECORD_FLAG_SYSTEM = cpu_to_le16(0x0004), - RECORD_FLAG_UNKNOWN = cpu_to_le16(0x0008), + RECORD_FLAG_INDEX = cpu_to_le16(0x0008), }; /* MFT Record structure. */ @@ -290,6 +288,15 @@ struct MFT_REC { #define MFTRECORD_FIXUP_OFFSET_1 offsetof(struct MFT_REC, res) #define MFTRECORD_FIXUP_OFFSET_3 offsetof(struct MFT_REC, fixups) +/* + * define MFTRECORD_FIXUP_OFFSET as MFTRECORD_FIXUP_OFFSET_3 (0x30) + * to format new mft records with bigger header (as current ntfs.sys does) + * + * define MFTRECORD_FIXUP_OFFSET as MFTRECORD_FIXUP_OFFSET_1 (0x2A) + * to format new mft records with smaller header (as old ntfs.sys did) + * Both variants are valid. + */ +#define MFTRECORD_FIXUP_OFFSET MFTRECORD_FIXUP_OFFSET_1 static_assert(MFTRECORD_FIXUP_OFFSET_1 == 0x2A); static_assert(MFTRECORD_FIXUP_OFFSET_3 == 0x30); @@ -331,18 +338,18 @@ struct ATTR_NONRESIDENT { __le64 svcn; // 0x10: Starting VCN of this segment. __le64 evcn; // 0x18: End VCN of this segment. __le16 run_off; // 0x20: Offset to packed runs. - // Unit of Compression size for this stream, expressed - // as a log of the cluster size. + // Unit of Compression size for this stream, expressed + // as a log of the cluster size. // - // 0 means file is not compressed - // 1, 2, 3, and 4 are potentially legal values if the - // stream is compressed, however the implementation - // may only choose to use 4, or possibly 3. Note - // that 4 means cluster size time 16. If convenient - // the implementation may wish to accept a - // reasonable range of legal values here (1-5?), - // even if the implementation only generates - // a smaller set of values itself. + // 0 means file is not compressed + // 1, 2, 3, and 4 are potentially legal values if the + // stream is compressed, however the implementation + // may only choose to use 4, or possibly 3. + // Note that 4 means cluster size time 16. + // If convenient the implementation may wish to accept a + // reasonable range of legal values here (1-5?), + // even if the implementation only generates + // a smaller set of values itself. u8 c_unit; // 0x22: u8 res1[5]; // 0x23: __le64 alloc_size; // 0x28: The allocated size of attribute in bytes. @@ -836,16 +843,22 @@ static_assert(sizeof(struct ATTR_DEF_ENTRY) == 0xa0); /* Object ID (0x40) */ struct OBJECT_ID { struct GUID ObjId; // 0x00: Unique Id assigned to file. - struct GUID BirthVolumeId; // 0x10: Birth Volume Id is the Object Id of the Volume on. - // which the Object Id was allocated. It never changes. - struct GUID BirthObjectId; // 0x20: Birth Object Id is the first Object Id that was - // ever assigned to this MFT Record. I.e. If the Object Id - // is changed for some reason, this field will reflect the - // original value of the Object Id. - struct GUID DomainId; // 0x30: Domain Id is currently unused but it is intended to be - // used in a network environment where the local machine is - // part of a Windows 2000 Domain. This may be used in a Windows - // 2000 Advanced Server managed domain. + + // Birth Volume Id is the Object Id of the Volume on. + // which the Object Id was allocated. It never changes. + struct GUID BirthVolumeId; //0x10: + + // Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + struct GUID BirthObjectId; // 0x20: + + // Domain Id is currently unused but it is intended to be + // used in a network environment where the local machine is + // part of a Windows 2000 Domain. This may be used in a Windows + // 2000 Advanced Server managed domain. + struct GUID DomainId; // 0x30: }; static_assert(sizeof(struct OBJECT_ID) == 0x40); @@ -855,32 +868,35 @@ struct NTFS_DE_O { struct NTFS_DE de; struct GUID ObjId; // 0x10: Unique Id assigned to file. struct MFT_REF ref; // 0x20: MFT record number with this file. - struct GUID BirthVolumeId; // 0x28: Birth Volume Id is the Object Id of the Volume on - // which the Object Id was allocated. It never changes. - struct GUID BirthObjectId; // 0x38: Birth Object Id is the first Object Id that was - // ever assigned to this MFT Record. I.e. If the Object Id - // is changed for some reason, this field will reflect the - // original value of the Object Id. - // This field is valid if data_size == 0x48. - struct GUID BirthDomainId; // 0x48: Domain Id is currently unused but it is intended - // to be used in a network environment where the local - // machine is part of a Windows 2000 Domain. This may be - // used in a Windows 2000 Advanced Server managed domain. + + // Birth Volume Id is the Object Id of the Volume on + // which the Object Id was allocated. It never changes. + struct GUID BirthVolumeId; // 0x28: + + // Birth Object Id is the first Object Id that was + // ever assigned to this MFT Record. I.e. If the Object Id + // is changed for some reason, this field will reflect the + // original value of the Object Id. + // This field is valid if data_size == 0x48. + struct GUID BirthObjectId; // 0x38: + + // Domain Id is currently unused but it is intended + // to be used in a network environment where the local + // machine is part of a Windows 2000 Domain. This may be + // used in a Windows 2000 Advanced Server managed domain. + struct GUID BirthDomainId; // 0x48: }; static_assert(sizeof(struct NTFS_DE_O) == 0x58); -#define NTFS_OBJECT_ENTRY_DATA_SIZE1 \ - 0x38 // struct NTFS_DE_O.BirthDomainId is not used -#define NTFS_OBJECT_ENTRY_DATA_SIZE2 \ - 0x48 // struct NTFS_DE_O.BirthDomainId is used - /* Q Directory entry structure ( rule = 0x11 ) */ struct NTFS_DE_Q { struct NTFS_DE de; __le32 owner_id; // 0x10: Unique Id assigned to file + + /* here is 0x30 bytes of user quota. NOTE: 4 byte aligned! */ __le32 Version; // 0x14: 0x02 - __le32 flags2; // 0x18: Quota flags, see above + __le32 Flags; // 0x18: Quota flags, see above __le64 BytesUsed; // 0x1C: __le64 ChangeTime; // 0x24: __le64 WarningLimit; // 0x28: @@ -888,9 +904,9 @@ struct NTFS_DE_Q { __le64 ExceededTime; // 0x3C: // SID is placed here -}; // sizeof() = 0x44 +}__packed; // sizeof() = 0x44 -#define SIZEOF_NTFS_DE_Q 0x44 +static_assert(sizeof(struct NTFS_DE_Q) == 0x44); #define SecurityDescriptorsBlockSize 0x40000 // 256K #define SecurityDescriptorMaxSize 0x20000 // 128K @@ -912,7 +928,7 @@ struct SECURITY_HDR { */ } __packed; -#define SIZEOF_SECURITY_HDR 0x14 +static_assert(sizeof(struct SECURITY_HDR) == 0x14); /* SII Directory entry structure */ struct NTFS_DE_SII { @@ -921,7 +937,8 @@ struct NTFS_DE_SII { struct SECURITY_HDR sec_hdr; // 0x14: } __packed; -#define SIZEOF_SII_DIRENTRY 0x28 +static_assert(offsetof(struct NTFS_DE_SII, sec_hdr) == 0x14); +static_assert(sizeof(struct NTFS_DE_SII) == 0x28); /* SDH Directory entry structure */ struct NTFS_DE_SDH { @@ -1155,7 +1172,7 @@ struct REPARSE_DATA_BUFFER { #define FILE_NEED_EA 0x80 // See ntifs.h /* - *FILE_NEED_EA, indicates that the file to which the EA belongs cannot be + * FILE_NEED_EA, indicates that the file to which the EA belongs cannot be * interpreted without understanding the associated extended attributes. */ struct EA_INFO { diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index eb01f7e76479..629403ede6e5 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -53,6 +53,8 @@ enum utf16_endian; #define E_NTFS_NONRESIDENT 556 /* NTFS specific error code about punch hole. */ #define E_NTFS_NOTALIGNED 557 +/* NTFS specific error code when on-disk struct is corrupted. */ +#define E_NTFS_CORRUPT 558 /* sbi->flags */ @@ -274,7 +276,7 @@ struct ntfs_sb_info { __le16 flags; // Cached current VOLUME_INFO::flags, VOLUME_FLAG_DIRTY. u8 major_ver; u8 minor_ver; - char label[65]; + char label[256]; bool real_dirty; // Real fs state. } volume; @@ -284,7 +286,6 @@ struct ntfs_sb_info { struct ntfs_inode *ni; u32 next_id; u64 next_off; - __le32 def_security_id; } security; @@ -312,6 +313,7 @@ struct ntfs_sb_info { struct ntfs_mount_options *options; struct ratelimit_state msg_ratelimit; + struct proc_dir_entry *procdir; }; /* One MFT record(usually 1024 bytes), consists of attributes. */ @@ -465,8 +467,7 @@ int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, struct ATTR_LIST_ENTRY **new_le); bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le); bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, - const __le16 *name, size_t name_len, - const struct MFT_REF *ref); + const __le16 *name, u8 name_len, const struct MFT_REF *ref); int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { @@ -525,7 +526,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, int ni_load_all_mi(struct ntfs_inode *ni); bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, - const __le16 *name, size_t name_len, bool base_only, + const __le16 *name, u8 name_len, bool base_only, const __le16 *id); int ni_create_attr_list(struct ntfs_inode *ni); int ni_expand_list(struct ntfs_inode *ni); @@ -542,7 +543,7 @@ void ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr, struct mft_inode *mi, struct ATTR_LIST_ENTRY *le); int ni_delete_all(struct ntfs_inode *ni); struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, - const struct cpu_str *uni, + const struct le_str *uni, const struct MFT_REF *home, struct mft_inode **mi, struct ATTR_LIST_ENTRY **entry); @@ -629,7 +630,7 @@ int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run); int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, u64 *lbo, u64 *bytes); struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST nRec, - bool dir); + enum RECORD_FLAG flag); extern const u8 s_default_security[0x50]; bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len); int ntfs_security_init(struct ntfs_sb_info *sbi); @@ -647,8 +648,10 @@ int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, const struct MFT_REF *ref); void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim); -int run_deallocate(struct ntfs_sb_info *sbi, struct runs_tree *run, bool trim); +int run_deallocate(struct ntfs_sb_info *sbi, const struct runs_tree *run, + bool trim); bool valid_windows_name(struct ntfs_sb_info *sbi, const struct le_str *name); +int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len); /* Globals from index.c */ int indx_used_bit(struct ntfs_index *indx, struct ntfs_inode *ni, size_t *bit); @@ -706,8 +709,8 @@ int ntfs_sync_inode(struct inode *inode); int ntfs_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2); int inode_write_data(struct inode *inode, const void *data, size_t bytes); -struct inode *ntfs_create_inode(struct mnt_idmap *idmap, - struct inode *dir, struct dentry *dentry, +struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, struct ntfs_fnd *fnd); @@ -736,7 +739,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr); // TODO: id? struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, enum ATTR_TYPE type, const __le16 *name, - size_t name_len, const __le16 *id); + u8 name_len, const __le16 *id); static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, struct ATTR_LIST_ENTRY *le) { @@ -856,12 +859,12 @@ unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase, /* globals from xattr.c */ #ifdef CONFIG_NTFS3_FS_POSIX_ACL -struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, - struct dentry *dentry, int type); +struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, + int type); int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, - struct inode *dir); + struct inode *dir); #else #define ntfs_get_acl NULL #define ntfs_set_acl NULL diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 2a281cead2bc..c12ebffc94da 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -124,7 +124,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) struct rw_semaphore *rw_lock = NULL; if (is_mounted(sbi)) { - if (!is_mft) { + if (!is_mft && mft_ni) { rw_lock = &mft_ni->file.run_lock; down_read(rw_lock); } @@ -148,7 +148,7 @@ int mi_read(struct mft_inode *mi, bool is_mft) ni_lock(mft_ni); down_write(rw_lock); } - err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, &mft_ni->file.run, + err = attr_load_runs_vcn(mft_ni, ATTR_DATA, NULL, 0, run, vbo >> sbi->cluster_bits); if (rw_lock) { up_write(rw_lock); @@ -180,6 +180,12 @@ ok: return 0; out: + if (err == -E_NTFS_CORRUPT) { + ntfs_err(sbi->sb, "mft corrupted"); + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + err = -EINVAL; + } + return err; } @@ -296,7 +302,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) */ struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, enum ATTR_TYPE type, const __le16 *name, - size_t name_len, const __le16 *id) + u8 name_len, const __le16 *id) { u32 type_in = le32_to_cpu(type); u32 atype; @@ -382,6 +388,8 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, rec->seq = cpu_to_le16(seq); rec->flags = RECORD_FLAG_IN_USE | flags; + if (MFTRECORD_FIXUP_OFFSET == MFTRECORD_FIXUP_OFFSET_3) + rec->mft_record = cpu_to_le32(rno); mi->dirty = true; diff --git a/fs/ntfs3/run.c b/fs/ntfs3/run.c index 47612d16c027..cb8cf0161177 100644 --- a/fs/ntfs3/run.c +++ b/fs/ntfs3/run.c @@ -434,8 +434,8 @@ requires_new_range: if (should_add_tail) { tail_lcn = r->lcn == SPARSE_LCN ? - SPARSE_LCN : - (r->lcn + Tovcn); + SPARSE_LCN : + (r->lcn + Tovcn); tail_vcn = r->vcn + Tovcn; tail_len = r->len - Tovcn; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 5158dd31fd97..1a02072b6b0e 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -57,6 +57,7 @@ #include <linux/minmax.h> #include <linux/module.h> #include <linux/nls.h> +#include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/statfs.h> @@ -116,8 +117,8 @@ void ntfs_inode_printk(struct inode *inode, const char *fmt, ...) /* Use static allocated buffer, if possible. */ name = atomic_dec_and_test(&s_name_buf_cnt) ? - s_name_buf : - kmalloc(sizeof(s_name_buf), GFP_NOFS); + s_name_buf : + kmalloc(sizeof(s_name_buf), GFP_NOFS); if (name) { struct dentry *de = d_find_alias(inode); @@ -257,6 +258,7 @@ enum Opt { Opt_err, }; +// clang-format off static const struct fs_parameter_spec ntfs_fs_parameters[] = { fsparam_u32("uid", Opt_uid), fsparam_u32("gid", Opt_gid), @@ -277,9 +279,13 @@ static const struct fs_parameter_spec ntfs_fs_parameters[] = { fsparam_flag_no("nocase", Opt_nocase), {} }; +// clang-format on /* * Load nls table or if @nls is utf8 then return NULL. + * + * It is good idea to use here "const char *nls". + * But load_nls accepts "char*". */ static struct nls_table *ntfs_load_nls(char *nls) { @@ -436,6 +442,103 @@ static int ntfs_fs_reconfigure(struct fs_context *fc) return 0; } +#ifdef CONFIG_PROC_FS +static struct proc_dir_entry *proc_info_root; + +/* + * ntfs3_volinfo: + * + * The content of /proc/fs/ntfs3/<dev>/volinfo + * + * ntfs3.1 + * cluster size + * number of clusters +*/ +static int ntfs3_volinfo(struct seq_file *m, void *o) +{ + struct super_block *sb = m->private; + struct ntfs_sb_info *sbi = sb->s_fs_info; + + seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver, + sbi->volume.minor_ver, sbi->cluster_size, + sbi->used.bitmap.nbits); + + return 0; +} + +static int ntfs3_volinfo_open(struct inode *inode, struct file *file) +{ + return single_open(file, ntfs3_volinfo, pde_data(inode)); +} + +/* read /proc/fs/ntfs3/<dev>/label */ +static int ntfs3_label_show(struct seq_file *m, void *o) +{ + struct super_block *sb = m->private; + struct ntfs_sb_info *sbi = sb->s_fs_info; + + seq_printf(m, "%s\n", sbi->volume.label); + + return 0; +} + +/* write /proc/fs/ntfs3/<dev>/label */ +static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + int err; + struct super_block *sb = pde_data(file_inode(file)); + struct ntfs_sb_info *sbi = sb->s_fs_info; + ssize_t ret = count; + u8 *label = kmalloc(count, GFP_NOFS); + + if (!label) + return -ENOMEM; + + if (copy_from_user(label, buffer, ret)) { + ret = -EFAULT; + goto out; + } + while (ret > 0 && label[ret - 1] == '\n') + ret -= 1; + + err = ntfs_set_label(sbi, label, ret); + + if (err < 0) { + ntfs_err(sb, "failed (%d) to write label", err); + ret = err; + goto out; + } + + *ppos += count; + ret = count; +out: + kfree(label); + return ret; +} + +static int ntfs3_label_open(struct inode *inode, struct file *file) +{ + return single_open(file, ntfs3_label_show, pde_data(inode)); +} + +static const struct proc_ops ntfs3_volinfo_fops = { + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_open = ntfs3_volinfo_open, +}; + +static const struct proc_ops ntfs3_label_fops = { + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = single_release, + .proc_open = ntfs3_label_open, + .proc_write = ntfs3_label_write, +}; + +#endif + static struct kmem_cache *ntfs_inode_cachep; static struct inode *ntfs_alloc_inode(struct super_block *sb) @@ -510,6 +613,16 @@ static void ntfs_put_super(struct super_block *sb) { struct ntfs_sb_info *sbi = sb->s_fs_info; +#ifdef CONFIG_PROC_FS + // Remove /proc/fs/ntfs3/.. + if (sbi->procdir) { + remove_proc_entry("label", sbi->procdir); + remove_proc_entry("volinfo", sbi->procdir); + remove_proc_entry(sb->s_id, proc_info_root); + sbi->procdir = NULL; + } +#endif + /* Mark rw ntfs as clear, if possible. */ ntfs_set_state(sbi, NTFS_DIRTY_CLEAR); @@ -711,9 +824,16 @@ static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot) /* * ntfs_init_from_boot - Init internal info from on-disk boot sector. + * + * NTFS mount begins from boot - special formatted 512 bytes. + * There are two boots: the first and the last 512 bytes of volume. + * The content of boot is not changed during ntfs life. + * + * NOTE: ntfs.sys checks only first (primary) boot. + * chkdsk checks both boots. */ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, - u64 dev_size) + u64 dev_size, struct NTFS_BOOT **boot2) { struct ntfs_sb_info *sbi = sb->s_fs_info; int err; @@ -724,6 +844,8 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, struct MFT_REC *rec; u16 fn, ao; u8 cluster_bits; + u32 boot_off = 0; + const char *hint = "Primary boot"; sbi->volume.blocks = dev_size >> PAGE_SHIFT; @@ -731,11 +853,12 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, if (!bh) return -EIO; +check_boot: err = -EINVAL; - boot = (struct NTFS_BOOT *)bh->b_data; + boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off); if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) { - ntfs_err(sb, "Boot's signature is not NTFS."); + ntfs_err(sb, "%s signature is not NTFS.", hint); goto out; } @@ -748,14 +871,16 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, boot->bytes_per_sector[0]; if (boot_sector_size < SECTOR_SIZE || !is_power_of_2(boot_sector_size)) { - ntfs_err(sb, "Invalid bytes per sector %u.", boot_sector_size); + ntfs_err(sb, "%s: invalid bytes per sector %u.", hint, + boot_sector_size); goto out; } /* cluster size: 512, 1K, 2K, 4K, ... 2M */ sct_per_clst = true_sectors_per_clst(boot); if ((int)sct_per_clst < 0 || !is_power_of_2(sct_per_clst)) { - ntfs_err(sb, "Invalid sectors per cluster %u.", sct_per_clst); + ntfs_err(sb, "%s: invalid sectors per cluster %u.", hint, + sct_per_clst); goto out; } @@ -771,20 +896,20 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, if (mlcn * sct_per_clst >= sectors || mlcn2 * sct_per_clst >= sectors) { ntfs_err( sb, - "Start of MFT 0x%llx (0x%llx) is out of volume 0x%llx.", - mlcn, mlcn2, sectors); + "%s: start of MFT 0x%llx (0x%llx) is out of volume 0x%llx.", + hint, mlcn, mlcn2, sectors); goto out; } sbi->record_size = record_size = boot->record_size < 0 ? 1 << (-boot->record_size) : - (u32)boot->record_size << cluster_bits; + (u32)boot->record_size << cluster_bits; sbi->record_bits = blksize_bits(record_size); sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes /* Check MFT record size. */ if (record_size < SECTOR_SIZE || !is_power_of_2(record_size)) { - ntfs_err(sb, "Invalid bytes per MFT record %u (%d).", + ntfs_err(sb, "%s: invalid bytes per MFT record %u (%d).", hint, record_size, boot->record_size); goto out; } @@ -796,18 +921,18 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, } sbi->index_size = boot->index_size < 0 ? - 1u << (-boot->index_size) : - (u32)boot->index_size << cluster_bits; + 1u << (-boot->index_size) : + (u32)boot->index_size << cluster_bits; /* Check index record size. */ if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) { - ntfs_err(sb, "Invalid bytes per index %u(%d).", sbi->index_size, - boot->index_size); + ntfs_err(sb, "%s: invalid bytes per index %u(%d).", hint, + sbi->index_size, boot->index_size); goto out; } if (sbi->index_size > MAXIMUM_BYTES_PER_INDEX) { - ntfs_err(sb, "Unsupported bytes per index %u.", + ntfs_err(sb, "%s: unsupported bytes per index %u.", hint, sbi->index_size); goto out; } @@ -834,7 +959,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, /* Compare boot's cluster and sector. */ if (sbi->cluster_size < boot_sector_size) { - ntfs_err(sb, "Invalid bytes per cluster (%u).", + ntfs_err(sb, "%s: invalid bytes per cluster (%u).", hint, sbi->cluster_size); goto out; } @@ -850,7 +975,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, } sbi->max_bytes_per_attr = - record_size - ALIGN(MFTRECORD_FIXUP_OFFSET_1, 8) - + record_size - ALIGN(MFTRECORD_FIXUP_OFFSET, 8) - ALIGN(((record_size >> SECTOR_SHIFT) * sizeof(short)), 8) - ALIGN(sizeof(enum ATTR_TYPE), 8); @@ -892,10 +1017,10 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, sbi->new_rec = rec; rec->rhdr.sign = NTFS_FILE_SIGNATURE; - rec->rhdr.fix_off = cpu_to_le16(MFTRECORD_FIXUP_OFFSET_1); + rec->rhdr.fix_off = cpu_to_le16(MFTRECORD_FIXUP_OFFSET); fn = (sbi->record_size >> SECTOR_SHIFT) + 1; rec->rhdr.fix_num = cpu_to_le16(fn); - ao = ALIGN(MFTRECORD_FIXUP_OFFSET_1 + sizeof(short) * fn, 8); + ao = ALIGN(MFTRECORD_FIXUP_OFFSET + sizeof(short) * fn, 8); rec->attr_off = cpu_to_le16(ao); rec->used = cpu_to_le32(ao + ALIGN(sizeof(enum ATTR_TYPE), 8)); rec->total = cpu_to_le32(sbi->record_size); @@ -930,7 +1055,34 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, err = 0; + if (bh->b_blocknr && !sb_rdonly(sb)) { + /* + * Alternative boot is ok but primary is not ok. + * Do not update primary boot here 'cause it may be faked boot. + * Let ntfs to be mounted and update boot later. + */ + *boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN); + } + out: + if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) { + u32 block_size = min_t(u32, sector_size, PAGE_SIZE); + u64 lbo = dev_size - sizeof(*boot); + + /* + * Try alternative boot (last sector) + */ + brelse(bh); + + sb_set_blocksize(sb, block_size); + bh = ntfs_bread(sb, lbo >> blksize_bits(block_size)); + if (!bh) + return -EINVAL; + + boot_off = lbo & (block_size - 1); + hint = "Alternative boot"; + goto check_boot; + } brelse(bh); return err; @@ -955,6 +1107,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) struct ATTR_DEF_ENTRY *t; u16 *shared; struct MFT_REF ref; + bool ro = sb_rdonly(sb); + struct NTFS_BOOT *boot2 = NULL; ref.high = 0; @@ -985,7 +1139,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* Parse boot. */ err = ntfs_init_from_boot(sb, bdev_logical_block_size(bdev), - bdev_nr_bytes(bdev)); + bdev_nr_bytes(bdev), &boot2); if (err) goto out; @@ -1035,6 +1189,10 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) sbi->volume.minor_ver = info->minor_ver; sbi->volume.flags = info->flags; sbi->volume.ni = ni; + if (info->flags & VOLUME_FLAG_DIRTY) { + sbi->volume.real_dirty = true; + ntfs_info(sb, "It is recommened to use chkdsk."); + } /* Load $MFTMirr to estimate recs_mirr. */ ref.low = cpu_to_le32(MFT_REC_MIRR); @@ -1069,21 +1227,16 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) iput(inode); - if (sbi->flags & NTFS_FLAGS_NEED_REPLAY) { - if (!sb_rdonly(sb)) { - ntfs_warn(sb, - "failed to replay log file. Can't mount rw!"); - err = -EINVAL; - goto out; - } - } else if (sbi->volume.flags & VOLUME_FLAG_DIRTY) { - if (!sb_rdonly(sb) && !options->force) { - ntfs_warn( - sb, - "volume is dirty and \"force\" flag is not set!"); - err = -EINVAL; - goto out; - } + if ((sbi->flags & NTFS_FLAGS_NEED_REPLAY) && !ro) { + ntfs_warn(sb, "failed to replay log file. Can't mount rw!"); + err = -EINVAL; + goto out; + } + + if ((sbi->volume.flags & VOLUME_FLAG_DIRTY) && !ro && !options->force) { + ntfs_warn(sb, "volume is dirty and \"force\" flag is not set!"); + err = -EINVAL; + goto out; } /* Load $MFT. */ @@ -1173,7 +1326,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) bad_len += len; bad_frags += 1; - if (sb_rdonly(sb)) + if (ro) continue; if (wnd_set_used_safe(&sbi->used.bitmap, lcn, len, &tt) || tt) { @@ -1368,6 +1521,44 @@ load_root: goto put_inode_out; } + if (boot2) { + /* + * Alternative boot is ok but primary is not ok. + * Volume is recognized as NTFS. Update primary boot. + */ + struct buffer_head *bh0 = sb_getblk(sb, 0); + if (bh0) { + if (buffer_locked(bh0)) + __wait_on_buffer(bh0); + + lock_buffer(bh0); + memcpy(bh0->b_data, boot2, sizeof(*boot2)); + set_buffer_uptodate(bh0); + mark_buffer_dirty(bh0); + unlock_buffer(bh0); + if (!sync_dirty_buffer(bh0)) + ntfs_warn(sb, "primary boot is updated"); + put_bh(bh0); + } + + kfree(boot2); + } + +#ifdef CONFIG_PROC_FS + /* Create /proc/fs/ntfs3/.. */ + if (proc_info_root) { + struct proc_dir_entry *e = proc_mkdir(sb->s_id, proc_info_root); + static_assert((S_IRUGO | S_IWUSR) == 0644); + if (e) { + proc_create_data("volinfo", S_IRUGO, e, + &ntfs3_volinfo_fops, sb); + proc_create_data("label", S_IRUGO | S_IWUSR, e, + &ntfs3_label_fops, sb); + sbi->procdir = e; + } + } +#endif + return 0; put_inode_out: @@ -1380,6 +1571,7 @@ out: put_mount_options(sbi->options); put_ntfs(sbi); sb->s_fs_info = NULL; + kfree(boot2); return err; } @@ -1473,12 +1665,14 @@ static void ntfs_fs_free(struct fs_context *fc) put_mount_options(opts); } +// clang-format off static const struct fs_context_operations ntfs_context_ops = { .parse_param = ntfs_fs_parse_param, .get_tree = ntfs_fs_get_tree, .reconfigure = ntfs_fs_reconfigure, .free = ntfs_fs_free, }; +// clang-format on /* * ntfs_init_fs_context - Initialize sbi and opts @@ -1559,6 +1753,12 @@ static int __init init_ntfs_fs(void) if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS)) pr_info("ntfs3: Read-only LZX/Xpress compression included\n"); + +#ifdef CONFIG_PROC_FS + /* Create "/proc/fs/ntfs3" */ + proc_info_root = proc_mkdir("fs/ntfs3", NULL); +#endif + err = ntfs3_init_bitmap(); if (err) return err; @@ -1590,6 +1790,12 @@ static void __exit exit_ntfs_fs(void) kmem_cache_destroy(ntfs_inode_cachep); unregister_filesystem(&ntfs_fs_type); ntfs3_exit_bitmap(); + +#ifdef CONFIG_PROC_FS + if (proc_info_root) + remove_proc_entry("fs/ntfs3", NULL); +#endif + } MODULE_LICENSE("GPL"); diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index c3de60a4543f..023f314e8950 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -24,7 +24,7 @@ static inline size_t unpacked_ea_size(const struct EA_FULL *ea) { return ea->size ? le32_to_cpu(ea->size) : - ALIGN(struct_size(ea, name, + ALIGN(struct_size(ea, name, 1 + ea->name_len + le16_to_cpu(ea->elength)), 4); @@ -141,6 +141,7 @@ static int ntfs_read_ea(struct ntfs_inode *ni, struct EA_FULL **ea, memset(Add2Ptr(ea_p, size), 0, add_bytes); + err = -EINVAL; /* Check all attributes for consistency. */ for (off = 0; off < size; off += ea_size) { const struct EA_FULL *ef = Add2Ptr(ea_p, off); @@ -214,6 +215,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, ea = Add2Ptr(ea_all, off); ea_size = unpacked_ea_size(ea); + if (!ea->name_len) + break; + if (buffer) { if (ret + ea->name_len + 1 > bytes_per_buffer) { err = -ERANGE; @@ -524,8 +528,8 @@ out: /* * ntfs_get_acl - inode_operations::get_acl */ -struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, - struct dentry *dentry, int type) +struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, + int type) { struct inode *inode = d_inode(dentry); struct ntfs_inode *ni = ntfs_i(inode); @@ -592,8 +596,7 @@ static noinline int ntfs_set_acl_ex(struct mnt_idmap *idmap, case ACL_TYPE_ACCESS: /* Do not change i_mode if we are in init_acl */ if (acl && !init_acl) { - err = posix_acl_update_mode(idmap, inode, &mode, - &acl); + err = posix_acl_update_mode(idmap, inode, &mode, &acl); if (err) return err; } @@ -816,10 +819,9 @@ out: * ntfs_setxattr - inode_operations::setxattr */ static noinline int ntfs_setxattr(const struct xattr_handler *handler, - struct mnt_idmap *idmap, - struct dentry *de, struct inode *inode, - const char *name, const void *value, - size_t size, int flags) + struct mnt_idmap *idmap, struct dentry *de, + struct inode *inode, const char *name, + const void *value, size_t size, int flags) { int err = -EINVAL; struct ntfs_inode *ni = ntfs_i(inode); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 4142d1a457ff..9402591f12aa 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -70,14 +70,6 @@ enum { OVL_XINO_ON, }; -/* The set of options that user requested explicitly via mount options */ -struct ovl_opt_set { - bool metacopy; - bool redirect; - bool nfs_export; - bool index; -}; - /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, * where: @@ -368,30 +360,6 @@ static inline bool ovl_open_flags_need_copy_up(int flags) return ((OPEN_FMODE(flags) & FMODE_WRITE) || (flags & O_TRUNC)); } - -/* params.c */ -#define OVL_MAX_STACK 500 - -struct ovl_fs_context_layer { - char *name; - struct path path; -}; - -struct ovl_fs_context { - struct path upper; - struct path work; - size_t capacity; - size_t nr; /* includes nr_data */ - size_t nr_data; - struct ovl_opt_set set; - struct ovl_fs_context_layer *lower; -}; - -int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, - bool workdir); -int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc); -void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx); - /* util.c */ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); @@ -791,3 +759,12 @@ int ovl_set_origin(struct ovl_fs *ofs, struct dentry *lower, /* export.c */ extern const struct export_operations ovl_export_operations; + +/* super.c */ +int ovl_fill_super(struct super_block *sb, struct fs_context *fc); + +/* Will this overlay be forced to mount/remount ro? */ +static inline bool ovl_force_readonly(struct ovl_fs *ofs) +{ + return (!ovl_upper_mnt(ofs) || !ofs->workdir); +} diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index d17d6b483dd0..a63160dbb0f9 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -1,12 +1,124 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/fs.h> +#include <linux/module.h> #include <linux/namei.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/posix_acl_xattr.h> +#include <linux/seq_file.h> #include <linux/xattr.h> #include "overlayfs.h" +#include "params.h" + +static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR); +module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); +MODULE_PARM_DESC(redirect_dir, + "Default to on or off for the redirect_dir feature"); + +static bool ovl_redirect_always_follow = + IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); +module_param_named(redirect_always_follow, ovl_redirect_always_follow, + bool, 0644); +MODULE_PARM_DESC(redirect_always_follow, + "Follow redirects even if redirect_dir feature is turned off"); + +static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO); +module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644); +MODULE_PARM_DESC(xino_auto, + "Auto enable xino feature"); + +static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); +module_param_named(index, ovl_index_def, bool, 0644); +MODULE_PARM_DESC(index, + "Default to on or off for the inodes index feature"); + +static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT); +module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644); +MODULE_PARM_DESC(nfs_export, + "Default to on or off for the NFS export feature"); + +static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY); +module_param_named(metacopy, ovl_metacopy_def, bool, 0644); +MODULE_PARM_DESC(metacopy, + "Default to on or off for the metadata only copy up feature"); + +enum { + Opt_lowerdir, + Opt_upperdir, + Opt_workdir, + Opt_default_permissions, + Opt_redirect_dir, + Opt_index, + Opt_uuid, + Opt_nfs_export, + Opt_userxattr, + Opt_xino, + Opt_metacopy, + Opt_volatile, +}; + +static const struct constant_table ovl_parameter_bool[] = { + { "on", true }, + { "off", false }, + {} +}; + +static const struct constant_table ovl_parameter_xino[] = { + { "off", OVL_XINO_OFF }, + { "auto", OVL_XINO_AUTO }, + { "on", OVL_XINO_ON }, + {} +}; + +const char *ovl_xino_mode(struct ovl_config *config) +{ + return ovl_parameter_xino[config->xino].name; +} + +static int ovl_xino_def(void) +{ + return ovl_xino_auto_def ? OVL_XINO_AUTO : OVL_XINO_OFF; +} + +const struct constant_table ovl_parameter_redirect_dir[] = { + { "off", OVL_REDIRECT_OFF }, + { "follow", OVL_REDIRECT_FOLLOW }, + { "nofollow", OVL_REDIRECT_NOFOLLOW }, + { "on", OVL_REDIRECT_ON }, + {} +}; + +static const char *ovl_redirect_mode(struct ovl_config *config) +{ + return ovl_parameter_redirect_dir[config->redirect_mode].name; +} + +static int ovl_redirect_mode_def(void) +{ + return ovl_redirect_dir_def ? OVL_REDIRECT_ON : + ovl_redirect_always_follow ? OVL_REDIRECT_FOLLOW : + OVL_REDIRECT_NOFOLLOW; +} + +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) + +const struct fs_parameter_spec ovl_parameter_spec[] = { + fsparam_string_empty("lowerdir", Opt_lowerdir), + fsparam_string("upperdir", Opt_upperdir), + fsparam_string("workdir", Opt_workdir), + fsparam_flag("default_permissions", Opt_default_permissions), + fsparam_enum("redirect_dir", Opt_redirect_dir, ovl_parameter_redirect_dir), + fsparam_enum("index", Opt_index, ovl_parameter_bool), + fsparam_enum("uuid", Opt_uuid, ovl_parameter_bool), + fsparam_enum("nfs_export", Opt_nfs_export, ovl_parameter_bool), + fsparam_flag("userxattr", Opt_userxattr), + fsparam_enum("xino", Opt_xino, ovl_parameter_xino), + fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), + fsparam_flag("volatile", Opt_volatile), + {} +}; static ssize_t ovl_parse_param_split_lowerdirs(char *str) { @@ -110,8 +222,8 @@ static int ovl_mount_dir(const char *name, struct path *path) return err; } -int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, - bool workdir) +static int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, + bool workdir) { int err; struct ovl_fs *ofs = fc->s_fs_info; @@ -154,7 +266,7 @@ int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, return 0; } -void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) +static void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) { for (size_t nr = 0; nr < ctx->nr; nr++) { path_put(&ctx->lower[nr].path); @@ -179,7 +291,7 @@ void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) * Append data "/lower5" as data lower layer. This requires that * there's at least one regular lower layer present. */ -int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) +static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) { int err; struct ovl_fs_context *ctx = fc->fs_private; @@ -387,3 +499,415 @@ out_err: /* Intentionally don't realloc to a smaller size. */ return err; } + +static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + int err = 0; + struct fs_parse_result result; + struct ovl_fs *ofs = fc->s_fs_info; + struct ovl_config *config = &ofs->config; + struct ovl_fs_context *ctx = fc->fs_private; + int opt; + + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { + /* + * On remount overlayfs has always ignored all mount + * options no matter if malformed or not so for + * backwards compatibility we do the same here. + */ + if (fc->oldapi) + return 0; + + /* + * Give us the freedom to allow changing mount options + * with the new mount api in the future. So instead of + * silently ignoring everything we report a proper + * error. This is only visible for users of the new + * mount api. + */ + return invalfc(fc, "No changes allowed in reconfigure"); + } + + opt = fs_parse(fc, ovl_parameter_spec, param, &result); + if (opt < 0) + return opt; + + switch (opt) { + case Opt_lowerdir: + err = ovl_parse_param_lowerdir(param->string, fc); + break; + case Opt_upperdir: + fallthrough; + case Opt_workdir: + err = ovl_parse_param_upperdir(param->string, fc, + (Opt_workdir == opt)); + break; + case Opt_default_permissions: + config->default_permissions = true; + break; + case Opt_redirect_dir: + config->redirect_mode = result.uint_32; + if (config->redirect_mode == OVL_REDIRECT_OFF) { + config->redirect_mode = ovl_redirect_always_follow ? + OVL_REDIRECT_FOLLOW : + OVL_REDIRECT_NOFOLLOW; + } + ctx->set.redirect = true; + break; + case Opt_index: + config->index = result.uint_32; + ctx->set.index = true; + break; + case Opt_uuid: + config->uuid = result.uint_32; + break; + case Opt_nfs_export: + config->nfs_export = result.uint_32; + ctx->set.nfs_export = true; + break; + case Opt_xino: + config->xino = result.uint_32; + break; + case Opt_metacopy: + config->metacopy = result.uint_32; + ctx->set.metacopy = true; + break; + case Opt_volatile: + config->ovl_volatile = true; + break; + case Opt_userxattr: + config->userxattr = true; + break; + default: + pr_err("unrecognized mount option \"%s\" or missing value\n", + param->key); + return -EINVAL; + } + + return err; +} + +static int ovl_get_tree(struct fs_context *fc) +{ + return get_tree_nodev(fc, ovl_fill_super); +} + +static inline void ovl_fs_context_free(struct ovl_fs_context *ctx) +{ + ovl_parse_param_drop_lowerdir(ctx); + path_put(&ctx->upper); + path_put(&ctx->work); + kfree(ctx->lower); + kfree(ctx); +} + +static void ovl_free(struct fs_context *fc) +{ + struct ovl_fs *ofs = fc->s_fs_info; + struct ovl_fs_context *ctx = fc->fs_private; + + /* + * ofs is stored in the fs_context when it is initialized. + * ofs is transferred to the superblock on a successful mount, + * but if an error occurs before the transfer we have to free + * it here. + */ + if (ofs) + ovl_free_fs(ofs); + + if (ctx) + ovl_fs_context_free(ctx); +} + +static int ovl_reconfigure(struct fs_context *fc) +{ + struct super_block *sb = fc->root->d_sb; + struct ovl_fs *ofs = sb->s_fs_info; + struct super_block *upper_sb; + int ret = 0; + + if (!(fc->sb_flags & SB_RDONLY) && ovl_force_readonly(ofs)) + return -EROFS; + + if (fc->sb_flags & SB_RDONLY && !sb_rdonly(sb)) { + upper_sb = ovl_upper_mnt(ofs)->mnt_sb; + if (ovl_should_sync(ofs)) { + down_read(&upper_sb->s_umount); + ret = sync_filesystem(upper_sb); + up_read(&upper_sb->s_umount); + } + } + + return ret; +} + +static const struct fs_context_operations ovl_context_ops = { + .parse_param = ovl_parse_param, + .get_tree = ovl_get_tree, + .reconfigure = ovl_reconfigure, + .free = ovl_free, +}; + +/* + * This is called during fsopen() and will record the user namespace of + * the caller in fc->user_ns since we've raised FS_USERNS_MOUNT. We'll + * need it when we actually create the superblock to verify that the + * process creating the superblock is in the same user namespace as + * process that called fsopen(). + */ +int ovl_init_fs_context(struct fs_context *fc) +{ + struct ovl_fs_context *ctx; + struct ovl_fs *ofs; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); + if (!ctx) + return -ENOMEM; + + /* + * By default we allocate for three lower layers. It's likely + * that it'll cover most users. + */ + ctx->lower = kmalloc_array(3, sizeof(*ctx->lower), GFP_KERNEL_ACCOUNT); + if (!ctx->lower) + goto out_err; + ctx->capacity = 3; + + ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); + if (!ofs) + goto out_err; + + ofs->config.redirect_mode = ovl_redirect_mode_def(); + ofs->config.index = ovl_index_def; + ofs->config.uuid = true; + ofs->config.nfs_export = ovl_nfs_export_def; + ofs->config.xino = ovl_xino_def(); + ofs->config.metacopy = ovl_metacopy_def; + + fc->s_fs_info = ofs; + fc->fs_private = ctx; + fc->ops = &ovl_context_ops; + return 0; + +out_err: + ovl_fs_context_free(ctx); + return -ENOMEM; + +} + +void ovl_free_fs(struct ovl_fs *ofs) +{ + struct vfsmount **mounts; + unsigned i; + + iput(ofs->workbasedir_trap); + iput(ofs->indexdir_trap); + iput(ofs->workdir_trap); + dput(ofs->whiteout); + dput(ofs->indexdir); + dput(ofs->workdir); + if (ofs->workdir_locked) + ovl_inuse_unlock(ofs->workbasedir); + dput(ofs->workbasedir); + if (ofs->upperdir_locked) + ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root); + + /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */ + mounts = (struct vfsmount **) ofs->layers; + for (i = 0; i < ofs->numlayer; i++) { + iput(ofs->layers[i].trap); + mounts[i] = ofs->layers[i].mnt; + kfree(ofs->layers[i].name); + } + kern_unmount_array(mounts, ofs->numlayer); + kfree(ofs->layers); + for (i = 0; i < ofs->numfs; i++) + free_anon_bdev(ofs->fs[i].pseudo_dev); + kfree(ofs->fs); + + kfree(ofs->config.upperdir); + kfree(ofs->config.workdir); + if (ofs->creator_cred) + put_cred(ofs->creator_cred); + kfree(ofs); +} + +int ovl_fs_params_verify(const struct ovl_fs_context *ctx, + struct ovl_config *config) +{ + struct ovl_opt_set set = ctx->set; + + if (ctx->nr_data > 0 && !config->metacopy) { + pr_err("lower data-only dirs require metacopy support.\n"); + return -EINVAL; + } + + /* Workdir/index are useless in non-upper mount */ + if (!config->upperdir) { + if (config->workdir) { + pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n", + config->workdir); + kfree(config->workdir); + config->workdir = NULL; + } + if (config->index && set.index) { + pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n"); + set.index = false; + } + config->index = false; + } + + if (!config->upperdir && config->ovl_volatile) { + pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n"); + config->ovl_volatile = false; + } + + /* + * This is to make the logic below simpler. It doesn't make any other + * difference, since redirect_dir=on is only used for upper. + */ + if (!config->upperdir && config->redirect_mode == OVL_REDIRECT_FOLLOW) + config->redirect_mode = OVL_REDIRECT_ON; + + /* Resolve metacopy -> redirect_dir dependency */ + if (config->metacopy && config->redirect_mode != OVL_REDIRECT_ON) { + if (set.metacopy && set.redirect) { + pr_err("conflicting options: metacopy=on,redirect_dir=%s\n", + ovl_redirect_mode(config)); + return -EINVAL; + } + if (set.redirect) { + /* + * There was an explicit redirect_dir=... that resulted + * in this conflict. + */ + pr_info("disabling metacopy due to redirect_dir=%s\n", + ovl_redirect_mode(config)); + config->metacopy = false; + } else { + /* Automatically enable redirect otherwise. */ + config->redirect_mode = OVL_REDIRECT_ON; + } + } + + /* Resolve nfs_export -> index dependency */ + if (config->nfs_export && !config->index) { + if (!config->upperdir && + config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { + pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n"); + config->nfs_export = false; + } else if (set.nfs_export && set.index) { + pr_err("conflicting options: nfs_export=on,index=off\n"); + return -EINVAL; + } else if (set.index) { + /* + * There was an explicit index=off that resulted + * in this conflict. + */ + pr_info("disabling nfs_export due to index=off\n"); + config->nfs_export = false; + } else { + /* Automatically enable index otherwise. */ + config->index = true; + } + } + + /* Resolve nfs_export -> !metacopy dependency */ + if (config->nfs_export && config->metacopy) { + if (set.nfs_export && set.metacopy) { + pr_err("conflicting options: nfs_export=on,metacopy=on\n"); + return -EINVAL; + } + if (set.metacopy) { + /* + * There was an explicit metacopy=on that resulted + * in this conflict. + */ + pr_info("disabling nfs_export due to metacopy=on\n"); + config->nfs_export = false; + } else { + /* + * There was an explicit nfs_export=on that resulted + * in this conflict. + */ + pr_info("disabling metacopy due to nfs_export=on\n"); + config->metacopy = false; + } + } + + + /* Resolve userxattr -> !redirect && !metacopy dependency */ + if (config->userxattr) { + if (set.redirect && + config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { + pr_err("conflicting options: userxattr,redirect_dir=%s\n", + ovl_redirect_mode(config)); + return -EINVAL; + } + if (config->metacopy && set.metacopy) { + pr_err("conflicting options: userxattr,metacopy=on\n"); + return -EINVAL; + } + /* + * Silently disable default setting of redirect and metacopy. + * This shall be the default in the future as well: these + * options must be explicitly enabled if used together with + * userxattr. + */ + config->redirect_mode = OVL_REDIRECT_NOFOLLOW; + config->metacopy = false; + } + + return 0; +} + +/** + * ovl_show_options + * @m: the seq_file handle + * @dentry: The dentry to query + * + * Prints the mount options for a given superblock. + * Returns zero; does not fail. + */ +int ovl_show_options(struct seq_file *m, struct dentry *dentry) +{ + struct super_block *sb = dentry->d_sb; + struct ovl_fs *ofs = sb->s_fs_info; + size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; + const struct ovl_layer *data_layers = &ofs->layers[nr_merged_lower]; + + /* ofs->layers[0] is the upper layer */ + seq_printf(m, ",lowerdir=%s", ofs->layers[1].name); + /* dump regular lower layers */ + for (nr = 2; nr < nr_merged_lower; nr++) + seq_printf(m, ":%s", ofs->layers[nr].name); + /* dump data lower layers */ + for (nr = 0; nr < ofs->numdatalayer; nr++) + seq_printf(m, "::%s", data_layers[nr].name); + if (ofs->config.upperdir) { + seq_show_option(m, "upperdir", ofs->config.upperdir); + seq_show_option(m, "workdir", ofs->config.workdir); + } + if (ofs->config.default_permissions) + seq_puts(m, ",default_permissions"); + if (ofs->config.redirect_mode != ovl_redirect_mode_def()) + seq_printf(m, ",redirect_dir=%s", + ovl_redirect_mode(&ofs->config)); + if (ofs->config.index != ovl_index_def) + seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); + if (!ofs->config.uuid) + seq_puts(m, ",uuid=off"); + if (ofs->config.nfs_export != ovl_nfs_export_def) + seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ? + "on" : "off"); + if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(ofs)) + seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config)); + if (ofs->config.metacopy != ovl_metacopy_def) + seq_printf(m, ",metacopy=%s", + ofs->config.metacopy ? "on" : "off"); + if (ofs->config.ovl_volatile) + seq_puts(m, ",volatile"); + if (ofs->config.userxattr) + seq_puts(m, ",userxattr"); + return 0; +} diff --git a/fs/overlayfs/params.h b/fs/overlayfs/params.h new file mode 100644 index 000000000000..8750da68ab2a --- /dev/null +++ b/fs/overlayfs/params.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <linux/fs_context.h> +#include <linux/fs_parser.h> + +struct ovl_fs; +struct ovl_config; + +extern const struct fs_parameter_spec ovl_parameter_spec[]; +extern const struct constant_table ovl_parameter_redirect_dir[]; + +/* The set of options that user requested explicitly via mount options */ +struct ovl_opt_set { + bool metacopy; + bool redirect; + bool nfs_export; + bool index; +}; + +#define OVL_MAX_STACK 500 + +struct ovl_fs_context_layer { + char *name; + struct path path; +}; + +struct ovl_fs_context { + struct path upper; + struct path work; + size_t capacity; + size_t nr; /* includes nr_data */ + size_t nr_data; + struct ovl_opt_set set; + struct ovl_fs_context_layer *lower; +}; + +int ovl_init_fs_context(struct fs_context *fc); +void ovl_free_fs(struct ovl_fs *ofs); +int ovl_fs_params_verify(const struct ovl_fs_context *ctx, + struct ovl_config *config); +int ovl_show_options(struct seq_file *m, struct dentry *dentry); +const char *ovl_xino_mode(struct ovl_config *config); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index c14c52560fd6..5b069f1a1e44 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -19,6 +19,7 @@ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "overlayfs.h" +#include "params.h" MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); MODULE_DESCRIPTION("Overlay filesystem"); @@ -27,38 +28,6 @@ MODULE_LICENSE("GPL"); struct ovl_dir_cache; -static bool ovl_redirect_dir_def = IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_DIR); -module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); -MODULE_PARM_DESC(redirect_dir, - "Default to on or off for the redirect_dir feature"); - -static bool ovl_redirect_always_follow = - IS_ENABLED(CONFIG_OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW); -module_param_named(redirect_always_follow, ovl_redirect_always_follow, - bool, 0644); -MODULE_PARM_DESC(redirect_always_follow, - "Follow redirects even if redirect_dir feature is turned off"); - -static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX); -module_param_named(index, ovl_index_def, bool, 0644); -MODULE_PARM_DESC(index, - "Default to on or off for the inodes index feature"); - -static bool ovl_nfs_export_def = IS_ENABLED(CONFIG_OVERLAY_FS_NFS_EXPORT); -module_param_named(nfs_export, ovl_nfs_export_def, bool, 0644); -MODULE_PARM_DESC(nfs_export, - "Default to on or off for the NFS export feature"); - -static bool ovl_xino_auto_def = IS_ENABLED(CONFIG_OVERLAY_FS_XINO_AUTO); -module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644); -MODULE_PARM_DESC(xino_auto, - "Auto enable xino feature"); - -static bool ovl_metacopy_def = IS_ENABLED(CONFIG_OVERLAY_FS_METACOPY); -module_param_named(metacopy, ovl_metacopy_def, bool, 0644); -MODULE_PARM_DESC(metacopy, - "Default to on or off for the metadata only copy up feature"); - static struct dentry *ovl_d_real(struct dentry *dentry, const struct inode *inode) { @@ -211,43 +180,6 @@ static void ovl_destroy_inode(struct inode *inode) kfree(oi->lowerdata_redirect); } -static void ovl_free_fs(struct ovl_fs *ofs) -{ - struct vfsmount **mounts; - unsigned i; - - iput(ofs->workbasedir_trap); - iput(ofs->indexdir_trap); - iput(ofs->workdir_trap); - dput(ofs->whiteout); - dput(ofs->indexdir); - dput(ofs->workdir); - if (ofs->workdir_locked) - ovl_inuse_unlock(ofs->workbasedir); - dput(ofs->workbasedir); - if (ofs->upperdir_locked) - ovl_inuse_unlock(ovl_upper_mnt(ofs)->mnt_root); - - /* Hack! Reuse ofs->layers as a vfsmount array before freeing it */ - mounts = (struct vfsmount **) ofs->layers; - for (i = 0; i < ofs->numlayer; i++) { - iput(ofs->layers[i].trap); - mounts[i] = ofs->layers[i].mnt; - kfree(ofs->layers[i].name); - } - kern_unmount_array(mounts, ofs->numlayer); - kfree(ofs->layers); - for (i = 0; i < ofs->numfs; i++) - free_anon_bdev(ofs->fs[i].pseudo_dev); - kfree(ofs->fs); - - kfree(ofs->config.upperdir); - kfree(ofs->config.workdir); - if (ofs->creator_cred) - put_cred(ofs->creator_cred); - kfree(ofs); -} - static void ovl_put_super(struct super_block *sb) { struct ovl_fs *ofs = sb->s_fs_info; @@ -323,122 +255,6 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf) return err; } -/* Will this overlay be forced to mount/remount ro? */ -static bool ovl_force_readonly(struct ovl_fs *ofs) -{ - return (!ovl_upper_mnt(ofs) || !ofs->workdir); -} - -static const struct constant_table ovl_parameter_redirect_dir[] = { - { "off", OVL_REDIRECT_OFF }, - { "follow", OVL_REDIRECT_FOLLOW }, - { "nofollow", OVL_REDIRECT_NOFOLLOW }, - { "on", OVL_REDIRECT_ON }, - {} -}; - -static const char *ovl_redirect_mode(struct ovl_config *config) -{ - return ovl_parameter_redirect_dir[config->redirect_mode].name; -} - -static int ovl_redirect_mode_def(void) -{ - return ovl_redirect_dir_def ? OVL_REDIRECT_ON : - ovl_redirect_always_follow ? OVL_REDIRECT_FOLLOW : - OVL_REDIRECT_NOFOLLOW; -} - -static const struct constant_table ovl_parameter_xino[] = { - { "off", OVL_XINO_OFF }, - { "auto", OVL_XINO_AUTO }, - { "on", OVL_XINO_ON }, - {} -}; - -static const char *ovl_xino_mode(struct ovl_config *config) -{ - return ovl_parameter_xino[config->xino].name; -} - -static inline int ovl_xino_def(void) -{ - return ovl_xino_auto_def ? OVL_XINO_AUTO : OVL_XINO_OFF; -} - -/** - * ovl_show_options - * @m: the seq_file handle - * @dentry: The dentry to query - * - * Prints the mount options for a given superblock. - * Returns zero; does not fail. - */ -static int ovl_show_options(struct seq_file *m, struct dentry *dentry) -{ - struct super_block *sb = dentry->d_sb; - struct ovl_fs *ofs = sb->s_fs_info; - size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; - const struct ovl_layer *data_layers = &ofs->layers[nr_merged_lower]; - - /* ofs->layers[0] is the upper layer */ - seq_printf(m, ",lowerdir=%s", ofs->layers[1].name); - /* dump regular lower layers */ - for (nr = 2; nr < nr_merged_lower; nr++) - seq_printf(m, ":%s", ofs->layers[nr].name); - /* dump data lower layers */ - for (nr = 0; nr < ofs->numdatalayer; nr++) - seq_printf(m, "::%s", data_layers[nr].name); - if (ofs->config.upperdir) { - seq_show_option(m, "upperdir", ofs->config.upperdir); - seq_show_option(m, "workdir", ofs->config.workdir); - } - if (ofs->config.default_permissions) - seq_puts(m, ",default_permissions"); - if (ofs->config.redirect_mode != ovl_redirect_mode_def()) - seq_printf(m, ",redirect_dir=%s", - ovl_redirect_mode(&ofs->config)); - if (ofs->config.index != ovl_index_def) - seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); - if (!ofs->config.uuid) - seq_puts(m, ",uuid=off"); - if (ofs->config.nfs_export != ovl_nfs_export_def) - seq_printf(m, ",nfs_export=%s", ofs->config.nfs_export ? - "on" : "off"); - if (ofs->config.xino != ovl_xino_def() && !ovl_same_fs(ofs)) - seq_printf(m, ",xino=%s", ovl_xino_mode(&ofs->config)); - if (ofs->config.metacopy != ovl_metacopy_def) - seq_printf(m, ",metacopy=%s", - ofs->config.metacopy ? "on" : "off"); - if (ofs->config.ovl_volatile) - seq_puts(m, ",volatile"); - if (ofs->config.userxattr) - seq_puts(m, ",userxattr"); - return 0; -} - -static int ovl_reconfigure(struct fs_context *fc) -{ - struct super_block *sb = fc->root->d_sb; - struct ovl_fs *ofs = sb->s_fs_info; - struct super_block *upper_sb; - int ret = 0; - - if (!(fc->sb_flags & SB_RDONLY) && ovl_force_readonly(ofs)) - return -EROFS; - - if (fc->sb_flags & SB_RDONLY && !sb_rdonly(sb)) { - upper_sb = ovl_upper_mnt(ofs)->mnt_sb; - if (ovl_should_sync(ofs)) { - down_read(&upper_sb->s_umount); - ret = sync_filesystem(upper_sb); - up_read(&upper_sb->s_umount); - } - } - - return ret; -} - static const struct super_operations ovl_super_operations = { .alloc_inode = ovl_alloc_inode, .free_inode = ovl_free_inode, @@ -450,262 +266,6 @@ static const struct super_operations ovl_super_operations = { .show_options = ovl_show_options, }; -enum { - Opt_lowerdir, - Opt_upperdir, - Opt_workdir, - Opt_default_permissions, - Opt_redirect_dir, - Opt_index, - Opt_uuid, - Opt_nfs_export, - Opt_userxattr, - Opt_xino, - Opt_metacopy, - Opt_volatile, -}; - -static const struct constant_table ovl_parameter_bool[] = { - { "on", true }, - { "off", false }, - {} -}; - -#define fsparam_string_empty(NAME, OPT) \ - __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) - -static const struct fs_parameter_spec ovl_parameter_spec[] = { - fsparam_string_empty("lowerdir", Opt_lowerdir), - fsparam_string("upperdir", Opt_upperdir), - fsparam_string("workdir", Opt_workdir), - fsparam_flag("default_permissions", Opt_default_permissions), - fsparam_enum("redirect_dir", Opt_redirect_dir, ovl_parameter_redirect_dir), - fsparam_enum("index", Opt_index, ovl_parameter_bool), - fsparam_enum("uuid", Opt_uuid, ovl_parameter_bool), - fsparam_enum("nfs_export", Opt_nfs_export, ovl_parameter_bool), - fsparam_flag("userxattr", Opt_userxattr), - fsparam_enum("xino", Opt_xino, ovl_parameter_xino), - fsparam_enum("metacopy", Opt_metacopy, ovl_parameter_bool), - fsparam_flag("volatile", Opt_volatile), - {} -}; - -static int ovl_parse_param(struct fs_context *fc, struct fs_parameter *param) -{ - int err = 0; - struct fs_parse_result result; - struct ovl_fs *ofs = fc->s_fs_info; - struct ovl_config *config = &ofs->config; - struct ovl_fs_context *ctx = fc->fs_private; - int opt; - - if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) { - /* - * On remount overlayfs has always ignored all mount - * options no matter if malformed or not so for - * backwards compatibility we do the same here. - */ - if (fc->oldapi) - return 0; - - /* - * Give us the freedom to allow changing mount options - * with the new mount api in the future. So instead of - * silently ignoring everything we report a proper - * error. This is only visible for users of the new - * mount api. - */ - return invalfc(fc, "No changes allowed in reconfigure"); - } - - opt = fs_parse(fc, ovl_parameter_spec, param, &result); - if (opt < 0) - return opt; - - switch (opt) { - case Opt_lowerdir: - err = ovl_parse_param_lowerdir(param->string, fc); - break; - case Opt_upperdir: - fallthrough; - case Opt_workdir: - err = ovl_parse_param_upperdir(param->string, fc, - (Opt_workdir == opt)); - break; - case Opt_default_permissions: - config->default_permissions = true; - break; - case Opt_redirect_dir: - config->redirect_mode = result.uint_32; - if (config->redirect_mode == OVL_REDIRECT_OFF) { - config->redirect_mode = ovl_redirect_always_follow ? - OVL_REDIRECT_FOLLOW : - OVL_REDIRECT_NOFOLLOW; - } - ctx->set.redirect = true; - break; - case Opt_index: - config->index = result.uint_32; - ctx->set.index = true; - break; - case Opt_uuid: - config->uuid = result.uint_32; - break; - case Opt_nfs_export: - config->nfs_export = result.uint_32; - ctx->set.nfs_export = true; - break; - case Opt_xino: - config->xino = result.uint_32; - break; - case Opt_metacopy: - config->metacopy = result.uint_32; - ctx->set.metacopy = true; - break; - case Opt_volatile: - config->ovl_volatile = true; - break; - case Opt_userxattr: - config->userxattr = true; - break; - default: - pr_err("unrecognized mount option \"%s\" or missing value\n", - param->key); - return -EINVAL; - } - - return err; -} - -static int ovl_fs_params_verify(const struct ovl_fs_context *ctx, - struct ovl_config *config) -{ - struct ovl_opt_set set = ctx->set; - - if (ctx->nr_data > 0 && !config->metacopy) { - pr_err("lower data-only dirs require metacopy support.\n"); - return -EINVAL; - } - - /* Workdir/index are useless in non-upper mount */ - if (!config->upperdir) { - if (config->workdir) { - pr_info("option \"workdir=%s\" is useless in a non-upper mount, ignore\n", - config->workdir); - kfree(config->workdir); - config->workdir = NULL; - } - if (config->index && set.index) { - pr_info("option \"index=on\" is useless in a non-upper mount, ignore\n"); - set.index = false; - } - config->index = false; - } - - if (!config->upperdir && config->ovl_volatile) { - pr_info("option \"volatile\" is meaningless in a non-upper mount, ignoring it.\n"); - config->ovl_volatile = false; - } - - /* - * This is to make the logic below simpler. It doesn't make any other - * difference, since redirect_dir=on is only used for upper. - */ - if (!config->upperdir && config->redirect_mode == OVL_REDIRECT_FOLLOW) - config->redirect_mode = OVL_REDIRECT_ON; - - /* Resolve metacopy -> redirect_dir dependency */ - if (config->metacopy && config->redirect_mode != OVL_REDIRECT_ON) { - if (set.metacopy && set.redirect) { - pr_err("conflicting options: metacopy=on,redirect_dir=%s\n", - ovl_redirect_mode(config)); - return -EINVAL; - } - if (set.redirect) { - /* - * There was an explicit redirect_dir=... that resulted - * in this conflict. - */ - pr_info("disabling metacopy due to redirect_dir=%s\n", - ovl_redirect_mode(config)); - config->metacopy = false; - } else { - /* Automatically enable redirect otherwise. */ - config->redirect_mode = OVL_REDIRECT_ON; - } - } - - /* Resolve nfs_export -> index dependency */ - if (config->nfs_export && !config->index) { - if (!config->upperdir && - config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { - pr_info("NFS export requires \"redirect_dir=nofollow\" on non-upper mount, falling back to nfs_export=off.\n"); - config->nfs_export = false; - } else if (set.nfs_export && set.index) { - pr_err("conflicting options: nfs_export=on,index=off\n"); - return -EINVAL; - } else if (set.index) { - /* - * There was an explicit index=off that resulted - * in this conflict. - */ - pr_info("disabling nfs_export due to index=off\n"); - config->nfs_export = false; - } else { - /* Automatically enable index otherwise. */ - config->index = true; - } - } - - /* Resolve nfs_export -> !metacopy dependency */ - if (config->nfs_export && config->metacopy) { - if (set.nfs_export && set.metacopy) { - pr_err("conflicting options: nfs_export=on,metacopy=on\n"); - return -EINVAL; - } - if (set.metacopy) { - /* - * There was an explicit metacopy=on that resulted - * in this conflict. - */ - pr_info("disabling nfs_export due to metacopy=on\n"); - config->nfs_export = false; - } else { - /* - * There was an explicit nfs_export=on that resulted - * in this conflict. - */ - pr_info("disabling metacopy due to nfs_export=on\n"); - config->metacopy = false; - } - } - - - /* Resolve userxattr -> !redirect && !metacopy dependency */ - if (config->userxattr) { - if (set.redirect && - config->redirect_mode != OVL_REDIRECT_NOFOLLOW) { - pr_err("conflicting options: userxattr,redirect_dir=%s\n", - ovl_redirect_mode(config)); - return -EINVAL; - } - if (config->metacopy && set.metacopy) { - pr_err("conflicting options: userxattr,metacopy=on\n"); - return -EINVAL; - } - /* - * Silently disable default setting of redirect and metacopy. - * This shall be the default in the future as well: these - * options must be explicitly enabled if used together with - * userxattr. - */ - config->redirect_mode = OVL_REDIRECT_NOFOLLOW; - config->metacopy = false; - } - - return 0; -} - #define OVL_WORKDIR_NAME "work" #define OVL_INDEXDIR_NAME "index" @@ -1758,7 +1318,7 @@ static struct dentry *ovl_get_root(struct super_block *sb, return root; } -static int ovl_fill_super(struct super_block *sb, struct fs_context *fc) +int ovl_fill_super(struct super_block *sb, struct fs_context *fc) { struct ovl_fs *ofs = sb->s_fs_info; struct ovl_fs_context *ctx = fc->fs_private; @@ -1919,92 +1479,6 @@ out_err: return err; } -static int ovl_get_tree(struct fs_context *fc) -{ - return get_tree_nodev(fc, ovl_fill_super); -} - -static inline void ovl_fs_context_free(struct ovl_fs_context *ctx) -{ - ovl_parse_param_drop_lowerdir(ctx); - path_put(&ctx->upper); - path_put(&ctx->work); - kfree(ctx->lower); - kfree(ctx); -} - -static void ovl_free(struct fs_context *fc) -{ - struct ovl_fs *ofs = fc->s_fs_info; - struct ovl_fs_context *ctx = fc->fs_private; - - /* - * ofs is stored in the fs_context when it is initialized. - * ofs is transferred to the superblock on a successful mount, - * but if an error occurs before the transfer we have to free - * it here. - */ - if (ofs) - ovl_free_fs(ofs); - - if (ctx) - ovl_fs_context_free(ctx); -} - -static const struct fs_context_operations ovl_context_ops = { - .parse_param = ovl_parse_param, - .get_tree = ovl_get_tree, - .reconfigure = ovl_reconfigure, - .free = ovl_free, -}; - -/* - * This is called during fsopen() and will record the user namespace of - * the caller in fc->user_ns since we've raised FS_USERNS_MOUNT. We'll - * need it when we actually create the superblock to verify that the - * process creating the superblock is in the same user namespace as - * process that called fsopen(). - */ -static int ovl_init_fs_context(struct fs_context *fc) -{ - struct ovl_fs_context *ctx; - struct ovl_fs *ofs; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); - if (!ctx) - return -ENOMEM; - - /* - * By default we allocate for three lower layers. It's likely - * that it'll cover most users. - */ - ctx->lower = kmalloc_array(3, sizeof(*ctx->lower), GFP_KERNEL_ACCOUNT); - if (!ctx->lower) - goto out_err; - ctx->capacity = 3; - - ofs = kzalloc(sizeof(struct ovl_fs), GFP_KERNEL); - if (!ofs) - goto out_err; - - ofs->config.redirect_mode = ovl_redirect_mode_def(); - ofs->config.index = ovl_index_def; - ofs->config.uuid = true; - ofs->config.nfs_export = ovl_nfs_export_def; - ofs->config.xino = ovl_xino_def(); - ofs->config.metacopy = ovl_metacopy_def; - - fc->s_fs_info = ofs; - fc->fs_private = ctx; - fc->ops = &ovl_context_ops; - return 0; - -out_err: - ovl_fs_context_free(ctx); - return -ENOMEM; - -} - static struct file_system_type ovl_fs_type = { .owner = THIS_MODULE, .name = "overlay", diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 5d0cf59c4926..9cb32e1a78a0 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -199,7 +199,7 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) ent->addr = (unsigned long)page_to_virt(p); ent->size = nr_pages << PAGE_SHIFT; - if (!virt_addr_valid(ent->addr)) + if (!virt_addr_valid((void *)ent->addr)) goto free_out; /* cut not-mapped area. ....from ppc-32 code. */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index ca2da713c5fe..b5808fe3469a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -2179,7 +2179,7 @@ static inline void cifs_sg_set_buf(struct sg_table *sgtable, } while (buflen); } else { sg_set_page(&sgtable->sgl[sgtable->nents++], - virt_to_page(addr), buflen, off); + virt_to_page((void *)addr), buflen, off); } } diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 223e17c16b60..2a2aec8c6112 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -2500,7 +2500,7 @@ static ssize_t smb_extract_kvec_to_rdma(struct iov_iter *iter, if (is_vmalloc_or_module_addr((void *)kaddr)) page = vmalloc_to_page((void *)kaddr); else - page = virt_to_page(kaddr); + page = virt_to_page((void *)kaddr); if (!smb_set_sge(rdma, page, off, seg)) return -EIO; diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index eeb0e3099421..138676463336 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -118,11 +118,13 @@ static int internal_create_group(struct kobject *kobj, int update, /* Updates may happen before the object has been instantiated */ if (unlikely(update && !kobj->sd)) return -EINVAL; + if (!grp->attrs && !grp->bin_attrs) { - WARN(1, "sysfs: (bin_)attrs not set by subsystem for group: %s/%s\n", - kobj->name, grp->name ?: ""); - return -EINVAL; + pr_debug("sysfs: (bin_)attrs not set by subsystem for group: %s/%s, skipping\n", + kobj->name, grp->name ?: ""); + return 0; } + kobject_get_ownership(kobj, &uid, &gid); if (grp->name) { if (update) { @@ -142,8 +144,10 @@ static int internal_create_group(struct kobject *kobj, int update, return PTR_ERR(kn); } } - } else + } else { kn = kobj->sd; + } + kernfs_get(kn); error = create_files(kn, kobj, uid, gid, grp, update); if (error) { diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index ee84835ebc66..e9cc481b4ddf 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -985,7 +985,7 @@ xfs_ag_shrink_space( goto resv_err; err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, - true); + XFS_AG_RESV_NONE, true); if (err2) goto resv_err; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index c20fe99405d8..3069194527dd 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1536,7 +1536,8 @@ xfs_alloc_ag_vextent_lastblock( */ STATIC int xfs_alloc_ag_vextent_near( - struct xfs_alloc_arg *args) + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { struct xfs_alloc_cur acur = {}; int error; /* error code */ @@ -1555,6 +1556,8 @@ xfs_alloc_ag_vextent_near( if (args->agbno > args->max_agbno) args->agbno = args->max_agbno; + /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: len = 0; @@ -1610,9 +1613,20 @@ restart: */ if (!acur.len) { if (acur.busy) { + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_near_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, - acur.busy_gen); + error = xfs_extent_busy_flush(args->tp, args->pag, + acur.busy_gen, alloc_flags); + if (error) + goto out; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; goto restart; } trace_xfs_alloc_size_neither(args); @@ -1635,22 +1649,25 @@ out: * and of the form k * prod + mod unless there's nothing that large. * Return the starting a.g. block, or NULLAGBLOCK if we can't do it. */ -STATIC int /* error */ +static int xfs_alloc_ag_vextent_size( - xfs_alloc_arg_t *args) /* allocation argument structure */ + struct xfs_alloc_arg *args, + uint32_t alloc_flags) { - struct xfs_agf *agf = args->agbp->b_addr; - struct xfs_btree_cur *bno_cur; /* cursor for bno btree */ - struct xfs_btree_cur *cnt_cur; /* cursor for cnt btree */ - int error; /* error result */ - xfs_agblock_t fbno; /* start of found freespace */ - xfs_extlen_t flen; /* length of found freespace */ - int i; /* temp status variable */ - xfs_agblock_t rbno; /* returned block number */ - xfs_extlen_t rlen; /* length of returned extent */ - bool busy; - unsigned busy_gen; + struct xfs_agf *agf = args->agbp->b_addr; + struct xfs_btree_cur *bno_cur; + struct xfs_btree_cur *cnt_cur; + xfs_agblock_t fbno; /* start of found freespace */ + xfs_extlen_t flen; /* length of found freespace */ + xfs_agblock_t rbno; /* returned block number */ + xfs_extlen_t rlen; /* length of returned extent */ + bool busy; + unsigned busy_gen; + int error; + int i; + /* Retry once quickly if we find busy extents before blocking. */ + alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH; restart: /* * Allocate and initialize a cursor for the by-size btree. @@ -1708,19 +1725,25 @@ restart: error = xfs_btree_increment(cnt_cur, 0, &i); if (error) goto error0; - if (i == 0) { - /* - * Our only valid extents must have been busy. - * Make it unbusy by forcing the log out and - * retrying. - */ - xfs_btree_del_cursor(cnt_cur, - XFS_BTREE_NOERROR); - trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, - args->pag, busy_gen); - goto restart; - } + if (i) + continue; + + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ + trace_xfs_alloc_size_busy(args); + error = xfs_extent_busy_flush(args->tp, args->pag, + busy_gen, alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + goto restart; } } @@ -1800,9 +1823,21 @@ restart: args->len = rlen; if (rlen < args->minlen) { if (busy) { - xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); + /* + * Our only valid extents must have been busy. Flush and + * retry the allocation again. If we get an -EAGAIN + * error, we're being told that a deadlock was avoided + * and the current transaction needs committing before + * the allocation can be retried. + */ trace_xfs_alloc_size_busy(args); - xfs_extent_busy_flush(args->mp, args->pag, busy_gen); + error = xfs_extent_busy_flush(args->tp, args->pag, + busy_gen, alloc_flags); + if (error) + goto error0; + + alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH; + xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR); goto restart; } goto out_nominleft; @@ -2435,23 +2470,25 @@ static int xfs_defer_agfl_block( struct xfs_trans *tp, xfs_agnumber_t agno, - xfs_fsblock_t agbno, + xfs_agblock_t agbno, struct xfs_owner_info *oinfo) { struct xfs_mount *mp = tp->t_mountp; struct xfs_extent_free_item *xefi; + xfs_fsblock_t fsbno = XFS_AGB_TO_FSB(mp, agno, agbno); ASSERT(xfs_extfree_item_cache != NULL); ASSERT(oinfo != NULL); + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno))) + return -EFSCORRUPTED; + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); - xefi->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno); + xefi->xefi_startblock = fsbno; xefi->xefi_blockcount = 1; xefi->xefi_owner = oinfo->oi_owner; - - if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock))) - return -EFSCORRUPTED; + xefi->xefi_agresv = XFS_AG_RESV_AGFL; trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); @@ -2470,6 +2507,7 @@ __xfs_free_extent_later( xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type, bool skip_discard) { struct xfs_extent_free_item *xefi; @@ -2490,6 +2528,7 @@ __xfs_free_extent_later( ASSERT(agbno + len <= mp->m_sb.sb_agblocks); #endif ASSERT(xfs_extfree_item_cache != NULL); + ASSERT(type != XFS_AG_RESV_AGFL); if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) return -EFSCORRUPTED; @@ -2498,6 +2537,7 @@ __xfs_free_extent_later( GFP_KERNEL | __GFP_NOFAIL); xefi->xefi_startblock = bno; xefi->xefi_blockcount = (xfs_extlen_t)len; + xefi->xefi_agresv = type; if (skip_discard) xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD; if (oinfo) { @@ -2568,7 +2608,7 @@ out: int /* error */ xfs_alloc_fix_freelist( struct xfs_alloc_arg *args, /* allocation argument structure */ - int flags) /* XFS_ALLOC_FLAG_... */ + uint32_t alloc_flags) { struct xfs_mount *mp = args->mp; struct xfs_perag *pag = args->pag; @@ -2584,7 +2624,7 @@ xfs_alloc_fix_freelist( ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES); if (!xfs_perag_initialised_agf(pag)) { - error = xfs_alloc_read_agf(pag, tp, flags, &agbp); + error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2600,13 +2640,13 @@ xfs_alloc_fix_freelist( */ if (xfs_perag_prefers_metadata(pag) && (args->datatype & XFS_ALLOC_USERDATA) && - (flags & XFS_ALLOC_FLAG_TRYLOCK)) { - ASSERT(!(flags & XFS_ALLOC_FLAG_FREEING)); + (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) { + ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING)); goto out_agbp_relse; } need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags | + if (!xfs_alloc_space_available(args, need, alloc_flags | XFS_ALLOC_FLAG_CHECK)) goto out_agbp_relse; @@ -2615,7 +2655,7 @@ xfs_alloc_fix_freelist( * Can fail if we're not blocking on locks, and it's held. */ if (!agbp) { - error = xfs_alloc_read_agf(pag, tp, flags, &agbp); + error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp); if (error) { /* Couldn't lock the AGF so skip this AG. */ if (error == -EAGAIN) @@ -2630,7 +2670,7 @@ xfs_alloc_fix_freelist( /* If there isn't enough total space or single-extent, reject it. */ need = xfs_alloc_min_freelist(mp, pag); - if (!xfs_alloc_space_available(args, need, flags)) + if (!xfs_alloc_space_available(args, need, alloc_flags)) goto out_agbp_relse; #ifdef DEBUG @@ -2668,11 +2708,12 @@ xfs_alloc_fix_freelist( */ memset(&targs, 0, sizeof(targs)); /* struct copy below */ - if (flags & XFS_ALLOC_FLAG_NORMAP) + if (alloc_flags & XFS_ALLOC_FLAG_NORMAP) targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE; else targs.oinfo = XFS_RMAP_OINFO_AG; - while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) { + while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) && + pag->pagf_flcount > need) { error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0); if (error) goto out_agbp_relse; @@ -2700,7 +2741,7 @@ xfs_alloc_fix_freelist( targs.resv = XFS_AG_RESV_AGFL; /* Allocate as many blocks as possible at once. */ - error = xfs_alloc_ag_vextent_size(&targs); + error = xfs_alloc_ag_vextent_size(&targs, alloc_flags); if (error) goto out_agflbp_relse; @@ -2710,7 +2751,7 @@ xfs_alloc_fix_freelist( * on a completely full ag. */ if (targs.agbno == NULLAGBLOCK) { - if (flags & XFS_ALLOC_FLAG_FREEING) + if (alloc_flags & XFS_ALLOC_FLAG_FREEING) break; goto out_agflbp_relse; } @@ -2916,6 +2957,47 @@ xfs_alloc_put_freelist( } /* + * Check that this AGF/AGI header's sequence number and length matches the AG + * number and size in fsblocks. + */ +xfs_failaddr_t +xfs_validate_ag_length( + struct xfs_buf *bp, + uint32_t seqno, + uint32_t length) +{ + struct xfs_mount *mp = bp->b_mount; + /* + * During growfs operations, the perag is not fully initialised, + * so we can't use it for any useful checking. growfs ensures we can't + * use it by using uncached buffers that don't have the perag attached + * so we can detect and avoid this problem. + */ + if (bp->b_pag && seqno != bp->b_pag->pag_agno) + return __this_address; + + /* + * Only the last AG in the filesystem is allowed to be shorter + * than the AG size recorded in the superblock. + */ + if (length != mp->m_sb.sb_agblocks) { + /* + * During growfs, the new last AG can get here before we + * have updated the superblock. Give it a pass on the seqno + * check. + */ + if (bp->b_pag && seqno != mp->m_sb.sb_agcount - 1) + return __this_address; + if (length < XFS_MIN_AG_BLOCKS) + return __this_address; + if (length > mp->m_sb.sb_agblocks) + return __this_address; + } + + return NULL; +} + +/* * Verify the AGF is consistent. * * We do not verify the AGFL indexes in the AGF are fully consistent here @@ -2934,6 +3016,9 @@ xfs_agf_verify( { struct xfs_mount *mp = bp->b_mount; struct xfs_agf *agf = bp->b_addr; + xfs_failaddr_t fa; + uint32_t agf_seqno = be32_to_cpu(agf->agf_seqno); + uint32_t agf_length = be32_to_cpu(agf->agf_length); if (xfs_has_crc(mp)) { if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid)) @@ -2945,18 +3030,26 @@ xfs_agf_verify( if (!xfs_verify_magic(bp, agf->agf_magicnum)) return __this_address; - if (!(XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) && - be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) && - be32_to_cpu(agf->agf_flfirst) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_fllast) < xfs_agfl_size(mp) && - be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp))) + if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum))) return __this_address; - if (be32_to_cpu(agf->agf_length) > mp->m_sb.sb_dblocks) + /* + * Both agf_seqno and agf_length need to validated before anything else + * block number related in the AGF or AGFL can be checked. + */ + fa = xfs_validate_ag_length(bp, agf_seqno, agf_length); + if (fa) + return fa; + + if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp)) + return __this_address; + if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp)) + return __this_address; + if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp)) return __this_address; if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) || - be32_to_cpu(agf->agf_freeblks) > be32_to_cpu(agf->agf_length)) + be32_to_cpu(agf->agf_freeblks) > agf_length) return __this_address; if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 || @@ -2967,38 +3060,28 @@ xfs_agf_verify( mp->m_alloc_maxlevels) return __this_address; - if (xfs_has_rmapbt(mp) && - (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 || - be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > - mp->m_rmap_maxlevels)) - return __this_address; - - if (xfs_has_rmapbt(mp) && - be32_to_cpu(agf->agf_rmap_blocks) > be32_to_cpu(agf->agf_length)) + if (xfs_has_lazysbcount(mp) && + be32_to_cpu(agf->agf_btreeblks) > agf_length) return __this_address; - /* - * during growfs operations, the perag is not fully initialised, - * so we can't use it for any useful checking. growfs ensures we can't - * use it by using uncached buffers that don't have the perag attached - * so we can detect and avoid this problem. - */ - if (bp->b_pag && be32_to_cpu(agf->agf_seqno) != bp->b_pag->pag_agno) - return __this_address; + if (xfs_has_rmapbt(mp)) { + if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length) + return __this_address; - if (xfs_has_lazysbcount(mp) && - be32_to_cpu(agf->agf_btreeblks) > be32_to_cpu(agf->agf_length)) - return __this_address; + if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 || + be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > + mp->m_rmap_maxlevels) + return __this_address; + } - if (xfs_has_reflink(mp) && - be32_to_cpu(agf->agf_refcount_blocks) > - be32_to_cpu(agf->agf_length)) - return __this_address; + if (xfs_has_reflink(mp)) { + if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length) + return __this_address; - if (xfs_has_reflink(mp) && - (be32_to_cpu(agf->agf_refcount_level) < 1 || - be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels)) - return __this_address; + if (be32_to_cpu(agf->agf_refcount_level) < 1 || + be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels) + return __this_address; + } return NULL; } @@ -3226,7 +3309,7 @@ xfs_alloc_vextent_check_args( static int xfs_alloc_vextent_prepare_ag( struct xfs_alloc_arg *args, - uint32_t flags) + uint32_t alloc_flags) { bool need_pag = !args->pag; int error; @@ -3235,7 +3318,7 @@ xfs_alloc_vextent_prepare_ag( args->pag = xfs_perag_get(args->mp, args->agno); args->agbp = NULL; - error = xfs_alloc_fix_freelist(args, flags); + error = xfs_alloc_fix_freelist(args, alloc_flags); if (error) { trace_xfs_alloc_vextent_nofix(args); if (need_pag) @@ -3357,6 +3440,7 @@ xfs_alloc_vextent_this_ag( { struct xfs_mount *mp = args->mp; xfs_agnumber_t minimum_agno; + uint32_t alloc_flags = 0; int error; ASSERT(args->pag != NULL); @@ -3375,9 +3459,9 @@ xfs_alloc_vextent_this_ag( return error; } - error = xfs_alloc_vextent_prepare_ag(args, 0); + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); if (!error && args->agbp) - error = xfs_alloc_ag_vextent_size(args); + error = xfs_alloc_ag_vextent_size(args, alloc_flags); return xfs_alloc_vextent_finish(args, minimum_agno, error, false); } @@ -3406,20 +3490,20 @@ xfs_alloc_vextent_iterate_ags( xfs_agnumber_t minimum_agno, xfs_agnumber_t start_agno, xfs_agblock_t target_agbno, - uint32_t flags) + uint32_t alloc_flags) { struct xfs_mount *mp = args->mp; xfs_agnumber_t restart_agno = minimum_agno; xfs_agnumber_t agno; int error = 0; - if (flags & XFS_ALLOC_FLAG_TRYLOCK) + if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) restart_agno = 0; restart: for_each_perag_wrap_range(mp, start_agno, restart_agno, mp->m_sb.sb_agcount, agno, args->pag) { args->agno = agno; - error = xfs_alloc_vextent_prepare_ag(args, flags); + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); if (error) break; if (!args->agbp) { @@ -3433,10 +3517,10 @@ restart: */ if (args->agno == start_agno && target_agbno) { args->agbno = target_agbno; - error = xfs_alloc_ag_vextent_near(args); + error = xfs_alloc_ag_vextent_near(args, alloc_flags); } else { args->agbno = 0; - error = xfs_alloc_ag_vextent_size(args); + error = xfs_alloc_ag_vextent_size(args, alloc_flags); } break; } @@ -3453,8 +3537,8 @@ restart: * constraining flags by the caller, drop them and retry the allocation * without any constraints being set. */ - if (flags) { - flags = 0; + if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) { + alloc_flags &= ~XFS_ALLOC_FLAG_TRYLOCK; restart_agno = minimum_agno; goto restart; } @@ -3482,6 +3566,7 @@ xfs_alloc_vextent_start_ag( xfs_agnumber_t start_agno; xfs_agnumber_t rotorstep = xfs_rotorstep; bool bump_rotor = false; + uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK; int error; ASSERT(args->pag == NULL); @@ -3508,7 +3593,7 @@ xfs_alloc_vextent_start_ag( start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target)); error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno, - XFS_FSB_TO_AGBNO(mp, target), XFS_ALLOC_FLAG_TRYLOCK); + XFS_FSB_TO_AGBNO(mp, target), alloc_flags); if (bump_rotor) { if (args->agno == start_agno) @@ -3535,6 +3620,7 @@ xfs_alloc_vextent_first_ag( struct xfs_mount *mp = args->mp; xfs_agnumber_t minimum_agno; xfs_agnumber_t start_agno; + uint32_t alloc_flags = XFS_ALLOC_FLAG_TRYLOCK; int error; ASSERT(args->pag == NULL); @@ -3553,7 +3639,7 @@ xfs_alloc_vextent_first_ag( start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target)); error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno, - XFS_FSB_TO_AGBNO(mp, target), 0); + XFS_FSB_TO_AGBNO(mp, target), alloc_flags); return xfs_alloc_vextent_finish(args, minimum_agno, error, true); } @@ -3606,6 +3692,7 @@ xfs_alloc_vextent_near_bno( struct xfs_mount *mp = args->mp; xfs_agnumber_t minimum_agno; bool needs_perag = args->pag == NULL; + uint32_t alloc_flags = 0; int error; if (!needs_perag) @@ -3626,9 +3713,9 @@ xfs_alloc_vextent_near_bno( if (needs_perag) args->pag = xfs_perag_grab(mp, args->agno); - error = xfs_alloc_vextent_prepare_ag(args, 0); + error = xfs_alloc_vextent_prepare_ag(args, alloc_flags); if (!error && args->agbp) - error = xfs_alloc_ag_vextent_near(args); + error = xfs_alloc_ag_vextent_near(args, alloc_flags); return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag); } @@ -3756,15 +3843,11 @@ xfs_alloc_query_range( xfs_alloc_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_alloc_query_range_info query; + union xfs_btree_irec low_brec = { .a = *low_rec }; + union xfs_btree_irec high_brec = { .a = *high_rec }; + struct xfs_alloc_query_range_info query = { .priv = priv, .fn = fn }; ASSERT(cur->bc_btnum == XFS_BTNUM_BNO); - low_brec.a = *low_rec; - high_brec.a = *high_rec; - query.priv = priv; - query.fn = fn; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_alloc_query_range_helper, &query); } diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 85ac470be0da..6bb8d295c321 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -19,11 +19,12 @@ unsigned int xfs_agfl_size(struct xfs_mount *mp); /* * Flags for xfs_alloc_fix_freelist. */ -#define XFS_ALLOC_FLAG_TRYLOCK 0x00000001 /* use trylock for buffer locking */ -#define XFS_ALLOC_FLAG_FREEING 0x00000002 /* indicate caller is freeing extents*/ -#define XFS_ALLOC_FLAG_NORMAP 0x00000004 /* don't modify the rmapbt */ -#define XFS_ALLOC_FLAG_NOSHRINK 0x00000008 /* don't shrink the freelist */ -#define XFS_ALLOC_FLAG_CHECK 0x00000010 /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYLOCK (1U << 0) /* use trylock for buffer locking */ +#define XFS_ALLOC_FLAG_FREEING (1U << 1) /* indicate caller is freeing extents*/ +#define XFS_ALLOC_FLAG_NORMAP (1U << 2) /* don't modify the rmapbt */ +#define XFS_ALLOC_FLAG_NOSHRINK (1U << 3) /* don't shrink the freelist */ +#define XFS_ALLOC_FLAG_CHECK (1U << 4) /* test only, don't modify args */ +#define XFS_ALLOC_FLAG_TRYFLUSH (1U << 5) /* don't wait in busy extent flush */ /* * Argument structure for xfs_alloc routines. @@ -195,7 +196,7 @@ int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp, struct xfs_buf **bpp); int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t, struct xfs_buf *, struct xfs_owner_info *); -int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags); +int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags); int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag, struct xfs_buf **agbp); @@ -232,7 +233,7 @@ xfs_buf_to_agfl_bno( int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, - bool skip_discard); + enum xfs_ag_resv_type type, bool skip_discard); /* * List of extents to be free "later". @@ -245,6 +246,7 @@ struct xfs_extent_free_item { xfs_extlen_t xefi_blockcount;/* number of blocks in extent */ struct xfs_perag *xefi_pag; unsigned int xefi_flags; + enum xfs_ag_resv_type xefi_agresv; }; void xfs_extent_free_get_group(struct xfs_mount *mp, @@ -259,9 +261,10 @@ xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, - const struct xfs_owner_info *oinfo) + const struct xfs_owner_info *oinfo, + enum xfs_ag_resv_type type) { - return __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, type, false); } @@ -270,4 +273,7 @@ extern struct kmem_cache *xfs_extfree_item_cache; int __init xfs_extfree_intent_init_cache(void); void xfs_extfree_intent_destroy_cache(void); +xfs_failaddr_t xfs_validate_ag_length(struct xfs_buf *bp, uint32_t seqno, + uint32_t length); + #endif /* __XFS_ALLOC_H__ */ diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index beee51ad75ce..2580ae47209a 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -2293,8 +2293,6 @@ xfs_attr3_leaf_unbalance( trace_xfs_attr_leaf_unbalance(state->args); - drop_leaf = drop_blk->bp->b_addr; - save_leaf = save_blk->bp->b_addr; xfs_attr3_leaf_hdr_from_disk(state->args->geo, &drophdr, drop_leaf); xfs_attr3_leaf_hdr_from_disk(state->args->geo, &savehdr, save_leaf); entry = xfs_attr3_leaf_entryp(drop_leaf); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index fef35696adb7..30c931b38853 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -574,7 +574,8 @@ xfs_bmap_btree_to_extents( return error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo, + XFS_AG_RESV_NONE); if (error) return error; @@ -5236,8 +5237,9 @@ xfs_bmap_del_extent_real( } else { error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, - (bflags & XFS_BMAPI_NODISCARD) || - del->br_state == XFS_EXT_UNWRITTEN); + XFS_AG_RESV_NONE, + ((bflags & XFS_BMAPI_NODISCARD) || + del->br_state == XFS_EXT_UNWRITTEN)); if (error) goto done; } diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 36564ae3084f..bf3f1b36fdd2 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -271,7 +271,8 @@ xfs_bmbt_free_block( int error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo, + XFS_AG_RESV_NONE); if (error) return error; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index 34600f94c2f4..b83e54c70906 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1853,8 +1853,8 @@ xfs_difree_inode_chunk( /* not sparse, calculate extent info directly */ return xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); + M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES, + XFS_AG_RESV_NONE); } /* holemask is only 16-bits (fits in an unsigned long) */ @@ -1899,8 +1899,8 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); error = xfs_free_extent_later(tp, - XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + XFS_AGB_TO_FSB(mp, agno, agbno), contigblk, + &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE); if (error) return error; @@ -2486,11 +2486,14 @@ xfs_ialloc_log_agi( static xfs_failaddr_t xfs_agi_verify( - struct xfs_buf *bp) + struct xfs_buf *bp) { - struct xfs_mount *mp = bp->b_mount; - struct xfs_agi *agi = bp->b_addr; - int i; + struct xfs_mount *mp = bp->b_mount; + struct xfs_agi *agi = bp->b_addr; + xfs_failaddr_t fa; + uint32_t agi_seqno = be32_to_cpu(agi->agi_seqno); + uint32_t agi_length = be32_to_cpu(agi->agi_length); + int i; if (xfs_has_crc(mp)) { if (!uuid_equal(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid)) @@ -2507,6 +2510,10 @@ xfs_agi_verify( if (!XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum))) return __this_address; + fa = xfs_validate_ag_length(bp, agi_seqno, agi_length); + if (fa) + return fa; + if (be32_to_cpu(agi->agi_level) < 1 || be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels) return __this_address; @@ -2516,15 +2523,6 @@ xfs_agi_verify( be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels)) return __this_address; - /* - * during growfs operations, the perag is not fully initialised, - * so we can't use it for any useful checking. growfs ensures we can't - * use it by using uncached buffers that don't have the perag attached - * so we can detect and avoid this problem. - */ - if (bp->b_pag && be32_to_cpu(agi->agi_seqno) != bp->b_pag->pag_agno) - return __this_address; - for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) { if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO)) continue; diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 5a945ae21b5d..9258f01c0015 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -160,8 +160,7 @@ __xfs_inobt_free_block( xfs_inobt_mod_blockcount(cur, -1); fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp)); - return xfs_free_extent(cur->bc_tp, cur->bc_ag.pag, - XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1, + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_INOBT, resv); } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index b6e21433925c..646b3fa362ad 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1152,7 +1152,8 @@ xfs_refcount_adjust_extents( cur->bc_ag.pag->pag_agno, tmp.rc_startblock); error = xfs_free_extent_later(cur->bc_tp, fsbno, - tmp.rc_blockcount, NULL); + tmp.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_error; } @@ -1213,7 +1214,8 @@ xfs_refcount_adjust_extents( cur->bc_ag.pag->pag_agno, ext.rc_startblock); error = xfs_free_extent_later(cur->bc_tp, fsbno, - ext.rc_blockcount, NULL); + ext.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_error; } @@ -1919,8 +1921,13 @@ xfs_refcount_recover_cow_leftovers( struct xfs_buf *agbp; struct xfs_refcount_recovery *rr, *n; struct list_head debris; - union xfs_btree_irec low; - union xfs_btree_irec high; + union xfs_btree_irec low = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + }; + union xfs_btree_irec high = { + .rc.rc_domain = XFS_REFC_DOMAIN_COW, + .rc.rc_startblock = -1U, + }; xfs_fsblock_t fsb; int error; @@ -1951,10 +1958,6 @@ xfs_refcount_recover_cow_leftovers( cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag); /* Find all the leftover CoW staging extents. */ - memset(&low, 0, sizeof(low)); - memset(&high, 0, sizeof(high)); - low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW; - high.rc.rc_startblock = -1U; error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); xfs_btree_del_cursor(cur, error); @@ -1981,7 +1984,8 @@ xfs_refcount_recover_cow_leftovers( /* Free the block. */ error = xfs_free_extent_later(tp, fsb, - rr->rr_rrec.rc_blockcount, NULL); + rr->rr_rrec.rc_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) goto out_trans; diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index d4afc5f4e6a5..5c3987d8dc24 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -106,19 +106,13 @@ xfs_refcountbt_free_block( struct xfs_buf *agbp = cur->bc_ag.agbp; struct xfs_agf *agf = agbp->b_addr; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); - int error; trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno, XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1); be32_add_cpu(&agf->agf_refcount_blocks, -1); xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS); - error = xfs_free_extent(cur->bc_tp, cur->bc_ag.pag, - XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1, + return xfs_free_extent_later(cur->bc_tp, fsbno, 1, &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA); - if (error) - return error; - - return error; } STATIC int diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index f4dc23b3b837..fbb0b2637463 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -2389,14 +2389,10 @@ xfs_rmap_query_range( xfs_rmap_query_range_fn fn, void *priv) { - union xfs_btree_irec low_brec; - union xfs_btree_irec high_brec; - struct xfs_rmap_query_range_info query; + union xfs_btree_irec low_brec = { .r = *low_rec }; + union xfs_btree_irec high_brec = { .r = *high_rec }; + struct xfs_rmap_query_range_info query = { .priv = priv, .fn = fn }; - low_brec.r = *low_rec; - high_brec.r = *high_rec; - query.priv = priv; - query.fn = fn; return xfs_btree_query_range(cur, &low_brec, &high_brec, xfs_rmap_query_range_helper, &query); } diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index ba0f17bc1dc0..5e174685a77c 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -412,7 +412,6 @@ xfs_validate_sb_common( sbp->sb_inodelog < XFS_DINODE_MIN_LOG || sbp->sb_inodelog > XFS_DINODE_MAX_LOG || sbp->sb_inodesize != (1 << sbp->sb_inodelog) || - sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE || sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) || XFS_FSB_TO_B(mp, sbp->sb_agblocks) < XFS_MIN_AG_BYTES || XFS_FSB_TO_B(mp, sbp->sb_agblocks) > XFS_MAX_AG_BYTES || @@ -430,6 +429,61 @@ xfs_validate_sb_common( return -EFSCORRUPTED; } + /* + * Logs that are too large are not supported at all. Reject them + * outright. Logs that are too small are tolerated on v4 filesystems, + * but we can only check that when mounting the log. Hence we skip + * those checks here. + */ + if (sbp->sb_logblocks > XFS_MAX_LOG_BLOCKS) { + xfs_notice(mp, + "Log size 0x%x blocks too large, maximum size is 0x%llx blocks", + sbp->sb_logblocks, XFS_MAX_LOG_BLOCKS); + return -EFSCORRUPTED; + } + + if (XFS_FSB_TO_B(mp, sbp->sb_logblocks) > XFS_MAX_LOG_BYTES) { + xfs_warn(mp, + "log size 0x%llx bytes too large, maximum size is 0x%llx bytes", + XFS_FSB_TO_B(mp, sbp->sb_logblocks), + XFS_MAX_LOG_BYTES); + return -EFSCORRUPTED; + } + + /* + * Do not allow filesystems with corrupted log sector or stripe units to + * be mounted. We cannot safely size the iclogs or write to the log if + * the log stripe unit is not valid. + */ + if (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT) { + if (sbp->sb_logsectsize != (1U << sbp->sb_logsectlog)) { + xfs_notice(mp, + "log sector size in bytes/log2 (0x%x/0x%x) must match", + sbp->sb_logsectsize, 1U << sbp->sb_logsectlog); + return -EFSCORRUPTED; + } + } else if (sbp->sb_logsectsize || sbp->sb_logsectlog) { + xfs_notice(mp, + "log sector size in bytes/log2 (0x%x/0x%x) are not zero", + sbp->sb_logsectsize, sbp->sb_logsectlog); + return -EFSCORRUPTED; + } + + if (sbp->sb_logsunit > 1) { + if (sbp->sb_logsunit % sbp->sb_blocksize) { + xfs_notice(mp, + "log stripe unit 0x%x bytes must be a multiple of block size", + sbp->sb_logsunit); + return -EFSCORRUPTED; + } + if (sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE) { + xfs_notice(mp, + "log stripe unit 0x%x bytes over maximum size (0x%x bytes)", + sbp->sb_logsunit, XLOG_MAX_RECORD_BSIZE); + return -EFSCORRUPTED; + } + } + /* Validate the realtime geometry; stolen from xfs_repair */ if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE || sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) { diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index f3d328e4a440..7c2fdc71e42d 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -566,20 +566,45 @@ xfs_extent_busy_clear( /* * Flush out all busy extents for this AG. + * + * If the current transaction is holding busy extents, the caller may not want + * to wait for committed busy extents to resolve. If we are being told just to + * try a flush or progress has been made since we last skipped a busy extent, + * return immediately to allow the caller to try again. + * + * If we are freeing extents, we might actually be holding the only free extents + * in the transaction busy list and the log force won't resolve that situation. + * In this case, we must return -EAGAIN to avoid a deadlock by informing the + * caller it needs to commit the busy extents it holds before retrying the + * extent free operation. */ -void +int xfs_extent_busy_flush( - struct xfs_mount *mp, + struct xfs_trans *tp, struct xfs_perag *pag, - unsigned busy_gen) + unsigned busy_gen, + uint32_t alloc_flags) { DEFINE_WAIT (wait); int error; - error = xfs_log_force(mp, XFS_LOG_SYNC); + error = xfs_log_force(tp->t_mountp, XFS_LOG_SYNC); if (error) - return; + return error; + + /* Avoid deadlocks on uncommitted busy extents. */ + if (!list_empty(&tp->t_busy)) { + if (alloc_flags & XFS_ALLOC_FLAG_TRYFLUSH) + return 0; + + if (busy_gen != READ_ONCE(pag->pagb_gen)) + return 0; + + if (alloc_flags & XFS_ALLOC_FLAG_FREEING) + return -EAGAIN; + } + /* Wait for committed busy extents to resolve. */ do { prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE); if (busy_gen != READ_ONCE(pag->pagb_gen)) @@ -588,6 +613,7 @@ xfs_extent_busy_flush( } while (1); finish_wait(&pag->pagb_wait, &wait); + return 0; } void diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index 4a118131059f..c37bf87e6781 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -51,9 +51,9 @@ bool xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno, xfs_extlen_t *len, unsigned *busy_gen); -void -xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag, - unsigned busy_gen); +int +xfs_extent_busy_flush(struct xfs_trans *tp, struct xfs_perag *pag, + unsigned busy_gen, uint32_t alloc_flags); void xfs_extent_busy_wait_all(struct xfs_mount *mp); diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index f9e36b810663..f1a5ecf099aa 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -337,6 +337,34 @@ xfs_trans_get_efd( } /* + * Fill the EFD with all extents from the EFI when we need to roll the + * transaction and continue with a new EFI. + * + * This simply copies all the extents in the EFI to the EFD rather than make + * assumptions about which extents in the EFI have already been processed. We + * currently keep the xefi list in the same order as the EFI extent list, but + * that may not always be the case. Copying everything avoids leaving a landmine + * were we fail to cancel all the extents in an EFI if the xefi list is + * processed in a different order to the extents in the EFI. + */ +static void +xfs_efd_from_efi( + struct xfs_efd_log_item *efdp) +{ + struct xfs_efi_log_item *efip = efdp->efd_efip; + uint i; + + ASSERT(efip->efi_format.efi_nextents > 0); + ASSERT(efdp->efd_next_extent < efip->efi_format.efi_nextents); + + for (i = 0; i < efip->efi_format.efi_nextents; i++) { + efdp->efd_format.efd_extents[i] = + efip->efi_format.efi_extents[i]; + } + efdp->efd_next_extent = efip->efi_format.efi_nextents; +} + +/* * Free an extent and log it to the EFD. Note that the transaction is marked * dirty regardless of whether the extent free succeeds or fails to support the * EFI/EFD lifecycle rules. @@ -365,7 +393,7 @@ xfs_trans_free_extent( agbno, xefi->xefi_blockcount); error = __xfs_free_extent(tp, xefi->xefi_pag, agbno, - xefi->xefi_blockcount, &oinfo, XFS_AG_RESV_NONE, + xefi->xefi_blockcount, &oinfo, xefi->xefi_agresv, xefi->xefi_flags & XFS_EFI_SKIP_DISCARD); /* @@ -378,6 +406,17 @@ xfs_trans_free_extent( tp->t_flags |= XFS_TRANS_DIRTY | XFS_TRANS_HAS_INTENT_DONE; set_bit(XFS_LI_DIRTY, &efdp->efd_item.li_flags); + /* + * If we need a new transaction to make progress, the caller will log a + * new EFI with the current contents. It will also log an EFD to cancel + * the existing EFI, and so we need to copy all the unprocessed extents + * in this EFI to the EFD so this works correctly. + */ + if (error == -EAGAIN) { + xfs_efd_from_efi(efdp); + return error; + } + next_extent = efdp->efd_next_extent; ASSERT(next_extent < efdp->efd_format.efd_nextents); extp = &(efdp->efd_format.efd_extents[next_extent]); @@ -495,6 +534,13 @@ xfs_extent_free_finish_item( error = xfs_trans_free_extent(tp, EFD_ITEM(done), xefi); + /* + * Don't free the XEFI if we need a new transaction to complete + * processing of it. + */ + if (error == -EAGAIN) + return error; + xfs_extent_free_put_group(xefi); kmem_cache_free(xfs_extfree_item_cache, xefi); return error; @@ -620,6 +666,7 @@ xfs_efi_item_recover( struct xfs_trans *tp; int i; int error = 0; + bool requeue_only = false; /* * First check the validity of the extents described by the @@ -644,6 +691,7 @@ xfs_efi_item_recover( for (i = 0; i < efip->efi_format.efi_nextents; i++) { struct xfs_extent_free_item fake = { .xefi_owner = XFS_RMAP_OWN_UNKNOWN, + .xefi_agresv = XFS_AG_RESV_NONE, }; struct xfs_extent *extp; @@ -652,9 +700,28 @@ xfs_efi_item_recover( fake.xefi_startblock = extp->ext_start; fake.xefi_blockcount = extp->ext_len; - xfs_extent_free_get_group(mp, &fake); - error = xfs_trans_free_extent(tp, efdp, &fake); - xfs_extent_free_put_group(&fake); + if (!requeue_only) { + xfs_extent_free_get_group(mp, &fake); + error = xfs_trans_free_extent(tp, efdp, &fake); + xfs_extent_free_put_group(&fake); + } + + /* + * If we can't free the extent without potentially deadlocking, + * requeue the rest of the extents to a new so that they get + * run again later with a new transaction context. + */ + if (error == -EAGAIN || requeue_only) { + error = xfs_free_extent_later(tp, fake.xefi_startblock, + fake.xefi_blockcount, + &XFS_RMAP_OINFO_ANY_OWNER, + fake.xefi_agresv); + if (!error) { + requeue_only = true; + continue; + } + } + if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, extp, sizeof(*extp)); diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 59e7d1a14b67..10403ba9b58f 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -160,9 +160,18 @@ struct xfs_getfsmap_info { struct xfs_buf *agf_bp; /* AGF, for refcount queries */ struct xfs_perag *pag; /* AG info, if applicable */ 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; u64 missing_owner; /* owner of holes */ u32 dev; /* device id */ - struct xfs_rmap_irec low; /* low rmap key */ + /* + * Low rmap key for the query. If low.rm_blockcount is nonzero, this + * is the second (or later) call to retrieve the recordset in pieces. + * xfs_getfsmap_rec_before_start will compare all records retrieved + * by the rmapbt query to filter out any records that start before + * the last record. + */ + struct xfs_rmap_irec low; struct xfs_rmap_irec high; /* high rmap key */ bool last; /* last extent? */ }; @@ -237,16 +246,31 @@ xfs_getfsmap_format( xfs_fsmap_from_internal(rec, xfm); } +static inline bool +xfs_getfsmap_rec_before_start( + struct xfs_getfsmap_info *info, + const struct xfs_rmap_irec *rec, + xfs_daddr_t rec_daddr) +{ + if (info->low_daddr != -1ULL) + return rec_daddr < info->low_daddr; + if (info->low.rm_blockcount) + return xfs_rmap_compare(rec, &info->low) < 0; + return false; +} + /* * Format a reverse mapping for getfsmap, having translated rm_startblock - * into the appropriate daddr units. + * into the appropriate daddr units. Pass in a nonzero @len_daddr if the + * length could be larger than rm_blockcount in struct xfs_rmap_irec. */ STATIC int xfs_getfsmap_helper( struct xfs_trans *tp, struct xfs_getfsmap_info *info, const struct xfs_rmap_irec *rec, - xfs_daddr_t rec_daddr) + xfs_daddr_t rec_daddr, + xfs_daddr_t len_daddr) { struct xfs_fsmap fmr; struct xfs_mount *mp = tp->t_mountp; @@ -256,12 +280,15 @@ xfs_getfsmap_helper( if (fatal_signal_pending(current)) return -EINTR; + if (len_daddr == 0) + len_daddr = XFS_FSB_TO_BB(mp, rec->rm_blockcount); + /* * Filter out records that start before our startpoint, if the * caller requested that. */ - if (xfs_rmap_compare(rec, &info->low) < 0) { - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + if (xfs_getfsmap_rec_before_start(info, rec, rec_daddr)) { + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -280,7 +307,7 @@ xfs_getfsmap_helper( info->head->fmh_entries++; - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -320,7 +347,7 @@ xfs_getfsmap_helper( if (error) return error; fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset); - fmr.fmr_length = XFS_FSB_TO_BB(mp, rec->rm_blockcount); + fmr.fmr_length = len_daddr; if (rec->rm_flags & XFS_RMAP_UNWRITTEN) fmr.fmr_flags |= FMR_OF_PREALLOC; if (rec->rm_flags & XFS_RMAP_ATTR_FORK) @@ -337,7 +364,7 @@ xfs_getfsmap_helper( xfs_getfsmap_format(mp, &fmr, info); out: - rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount); + rec_daddr += len_daddr; if (info->next_daddr < rec_daddr) info->next_daddr = rec_daddr; return 0; @@ -358,7 +385,7 @@ xfs_getfsmap_datadev_helper( fsb = XFS_AGB_TO_FSB(mp, cur->bc_ag.pag->pag_agno, rec->rm_startblock); rec_daddr = XFS_FSB_TO_DADDR(mp, fsb); - return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr); + return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr, 0); } /* Transform a bnobt irec into a fsmap */ @@ -382,7 +409,7 @@ xfs_getfsmap_datadev_bnobt_helper( irec.rm_offset = 0; irec.rm_flags = 0; - return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr); + return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr, 0); } /* Set rmap flags based on the getfsmap flags */ @@ -409,31 +436,25 @@ xfs_getfsmap_logdev( { struct xfs_mount *mp = tp->t_mountp; struct xfs_rmap_irec rmap; - int error; + xfs_daddr_t rec_daddr, len_daddr; + xfs_fsblock_t start_fsb, end_fsb; + uint64_t eofs; - /* Set up search keys */ - info->low.rm_startblock = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical); - info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); - error = xfs_fsmap_owner_to_rmap(&info->low, keys); - if (error) - return error; - info->low.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks); + if (keys[0].fmr_physical >= eofs) + return 0; + start_fsb = XFS_BB_TO_FSBT(mp, + keys[0].fmr_physical + keys[0].fmr_length); + end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); - error = xfs_fsmap_owner_to_rmap(&info->high, keys + 1); - if (error) - return error; - info->high.rm_startblock = -1U; - info->high.rm_owner = ULLONG_MAX; - info->high.rm_offset = ULLONG_MAX; - info->high.rm_blockcount = 0; - info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS; - info->missing_owner = XFS_FMR_OWN_FREE; + /* Adjust the low key if we are continuing from where we left off. */ + if (keys[0].fmr_length > 0) + info->low_daddr = XFS_FSB_TO_BB(mp, start_fsb); - trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low); - trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high); + trace_xfs_fsmap_low_key_linear(mp, info->dev, start_fsb); + trace_xfs_fsmap_high_key_linear(mp, info->dev, end_fsb); - if (keys[0].fmr_physical > 0) + if (start_fsb > 0) return 0; /* Fabricate an rmap entry for the external log device. */ @@ -443,7 +464,9 @@ xfs_getfsmap_logdev( rmap.rm_offset = 0; rmap.rm_flags = 0; - return xfs_getfsmap_helper(tp, info, &rmap, 0); + rec_daddr = XFS_FSB_TO_BB(mp, rmap.rm_startblock); + len_daddr = XFS_FSB_TO_BB(mp, rmap.rm_blockcount); + return xfs_getfsmap_helper(tp, info, &rmap, rec_daddr, len_daddr); } #ifdef CONFIG_XFS_RT @@ -457,72 +480,58 @@ xfs_getfsmap_rtdev_rtbitmap_helper( { struct xfs_getfsmap_info *info = priv; struct xfs_rmap_irec irec; - xfs_daddr_t rec_daddr; + xfs_rtblock_t rtbno; + xfs_daddr_t rec_daddr, len_daddr; + + rtbno = rec->ar_startext * mp->m_sb.sb_rextsize; + rec_daddr = XFS_FSB_TO_BB(mp, rtbno); + irec.rm_startblock = rtbno; + + rtbno = rec->ar_extcount * mp->m_sb.sb_rextsize; + len_daddr = XFS_FSB_TO_BB(mp, rtbno); + irec.rm_blockcount = rtbno; - irec.rm_startblock = rec->ar_startext * mp->m_sb.sb_rextsize; - rec_daddr = XFS_FSB_TO_BB(mp, irec.rm_startblock); - irec.rm_blockcount = rec->ar_extcount * mp->m_sb.sb_rextsize; irec.rm_owner = XFS_RMAP_OWN_NULL; /* "free" */ irec.rm_offset = 0; irec.rm_flags = 0; - return xfs_getfsmap_helper(tp, info, &irec, rec_daddr); + return xfs_getfsmap_helper(tp, info, &irec, rec_daddr, len_daddr); } -/* Execute a getfsmap query against the realtime device. */ +/* Execute a getfsmap query against the realtime device rtbitmap. */ STATIC int -__xfs_getfsmap_rtdev( +xfs_getfsmap_rtdev_rtbitmap( struct xfs_trans *tp, const struct xfs_fsmap *keys, - int (*query_fn)(struct xfs_trans *, - struct xfs_getfsmap_info *), struct xfs_getfsmap_info *info) { + + struct xfs_rtalloc_rec alow = { 0 }; + struct xfs_rtalloc_rec ahigh = { 0 }; struct xfs_mount *mp = tp->t_mountp; - xfs_fsblock_t start_fsb; - xfs_fsblock_t end_fsb; + xfs_rtblock_t start_rtb; + xfs_rtblock_t end_rtb; uint64_t eofs; - int error = 0; + int error; - eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks); + eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rextents * mp->m_sb.sb_rextsize); if (keys[0].fmr_physical >= eofs) return 0; - start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical); - end_fsb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); + start_rtb = XFS_BB_TO_FSBT(mp, + keys[0].fmr_physical + keys[0].fmr_length); + end_rtb = XFS_BB_TO_FSB(mp, min(eofs - 1, keys[1].fmr_physical)); - /* Set up search keys */ - info->low.rm_startblock = start_fsb; - error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); - if (error) - return error; - info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset); - info->low.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); - - info->high.rm_startblock = end_fsb; - error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]); - if (error) - return error; - info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset); - info->high.rm_blockcount = 0; - xfs_getfsmap_set_irec_flags(&info->high, &keys[1]); - - trace_xfs_fsmap_low_key(mp, info->dev, NULLAGNUMBER, &info->low); - trace_xfs_fsmap_high_key(mp, info->dev, NULLAGNUMBER, &info->high); + info->missing_owner = XFS_FMR_OWN_UNKNOWN; - return query_fn(tp, info); -} + /* Adjust the low key if we are continuing from where we left off. */ + if (keys[0].fmr_length > 0) { + info->low_daddr = XFS_FSB_TO_BB(mp, start_rtb); + if (info->low_daddr >= eofs) + return 0; + } -/* Actually query the realtime bitmap. */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap_query( - struct xfs_trans *tp, - struct xfs_getfsmap_info *info) -{ - struct xfs_rtalloc_rec alow = { 0 }; - struct xfs_rtalloc_rec ahigh = { 0 }; - struct xfs_mount *mp = tp->t_mountp; - int error; + trace_xfs_fsmap_low_key_linear(mp, info->dev, start_rtb); + trace_xfs_fsmap_high_key_linear(mp, info->dev, end_rtb); xfs_ilock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP); @@ -530,8 +539,8 @@ xfs_getfsmap_rtdev_rtbitmap_query( * Set up query parameters to return free rtextents covering the range * we want. */ - alow.ar_startext = info->low.rm_startblock; - ahigh.ar_startext = info->high.rm_startblock; + alow.ar_startext = start_rtb; + ahigh.ar_startext = end_rtb; do_div(alow.ar_startext, mp->m_sb.sb_rextsize); if (do_div(ahigh.ar_startext, mp->m_sb.sb_rextsize)) ahigh.ar_startext++; @@ -554,18 +563,6 @@ err: xfs_iunlock(mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP); return error; } - -/* Execute a getfsmap query against the realtime device rtbitmap. */ -STATIC int -xfs_getfsmap_rtdev_rtbitmap( - struct xfs_trans *tp, - const struct xfs_fsmap *keys, - struct xfs_getfsmap_info *info) -{ - info->missing_owner = XFS_FMR_OWN_UNKNOWN; - return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query, - info); -} #endif /* CONFIG_XFS_RT */ /* Execute a getfsmap query against the regular data device. */ @@ -606,9 +603,27 @@ __xfs_getfsmap_datadev( error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]); if (error) return error; - info->low.rm_blockcount = 0; + info->low.rm_blockcount = XFS_BB_TO_FSBT(mp, keys[0].fmr_length); xfs_getfsmap_set_irec_flags(&info->low, &keys[0]); + /* Adjust the low key if we are continuing from where we left off. */ + if (info->low.rm_blockcount == 0) { + /* empty */ + } else if (XFS_RMAP_NON_INODE_OWNER(info->low.rm_owner) || + (info->low.rm_flags & (XFS_RMAP_ATTR_FORK | + XFS_RMAP_BMBT_BLOCK | + XFS_RMAP_UNWRITTEN))) { + info->low.rm_startblock += info->low.rm_blockcount; + info->low.rm_owner = 0; + info->low.rm_offset = 0; + + start_fsb += info->low.rm_blockcount; + if (XFS_FSB_TO_DADDR(mp, start_fsb) >= eofs) + return 0; + } else { + info->low.rm_offset += info->low.rm_blockcount; + } + info->high.rm_startblock = -1U; info->high.rm_owner = ULLONG_MAX; info->high.rm_offset = ULLONG_MAX; @@ -659,12 +674,8 @@ __xfs_getfsmap_datadev( * Set the AG low key to the start of the AG prior to * moving on to the next AG. */ - if (pag->pag_agno == start_ag) { - info->low.rm_startblock = 0; - info->low.rm_owner = 0; - info->low.rm_offset = 0; - info->low.rm_flags = 0; - } + if (pag->pag_agno == start_ag) + memset(&info->low, 0, sizeof(info->low)); /* * If this is the last AG, report any gap at the end of it @@ -791,6 +802,19 @@ xfs_getfsmap_check_keys( struct xfs_fsmap *low_key, struct xfs_fsmap *high_key) { + if (low_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) { + if (low_key->fmr_offset) + return false; + } + if (high_key->fmr_flags != -1U && + (high_key->fmr_flags & (FMR_OF_SPECIAL_OWNER | + FMR_OF_EXTENT_MAP))) { + if (high_key->fmr_offset && high_key->fmr_offset != -1ULL) + return false; + } + if (high_key->fmr_length && high_key->fmr_length != -1ULL) + return false; + if (low_key->fmr_device > high_key->fmr_device) return false; if (low_key->fmr_device < high_key->fmr_device) @@ -834,15 +858,15 @@ xfs_getfsmap_check_keys( * ---------------- * There are multiple levels of keys and counters at work here: * xfs_fsmap_head.fmh_keys -- low and high fsmap keys passed in; - * these reflect fs-wide sector addrs. + * these reflect fs-wide sector addrs. * dkeys -- fmh_keys used to query each device; - * these are fmh_keys but w/ the low key - * bumped up by fmr_length. + * these are fmh_keys but w/ the low key + * bumped up by fmr_length. * xfs_getfsmap_info.next_daddr -- next disk addr we expect to see; this * is how we detect gaps in the fsmap records and report them. * xfs_getfsmap_info.low/high -- per-AG low/high keys computed from - * dkeys; used to query the metadata. + * dkeys; used to query the metadata. */ int xfs_getfsmap( @@ -863,6 +887,8 @@ xfs_getfsmap( if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) || !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1])) return -EINVAL; + if (!xfs_getfsmap_check_keys(&head->fmh_keys[0], &head->fmh_keys[1])) + return -EINVAL; use_rmap = xfs_has_rmapbt(mp) && has_capability_noaudit(current, CAP_SYS_ADMIN); @@ -901,26 +927,15 @@ xfs_getfsmap( * blocks could be mapped to several other files/offsets. * According to rmapbt record ordering, the minimal next * possible record for the block range is the next starting - * offset in the same inode. Therefore, bump the file offset to - * continue the search appropriately. For all other low key - * mapping types (attr blocks, metadata), bump the physical - * offset as there can be no other mapping for the same physical - * block range. + * offset in the same inode. Therefore, each fsmap backend bumps + * the file offset to continue the search appropriately. For + * all other low key mapping types (attr blocks, metadata), each + * fsmap backend bumps the physical offset as there can be no + * other mapping for the same physical block range. */ dkeys[0] = head->fmh_keys[0]; - if (dkeys[0].fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) { - dkeys[0].fmr_physical += dkeys[0].fmr_length; - dkeys[0].fmr_owner = 0; - if (dkeys[0].fmr_offset) - return -EINVAL; - } else - dkeys[0].fmr_offset += dkeys[0].fmr_length; - dkeys[0].fmr_length = 0; memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap)); - if (!xfs_getfsmap_check_keys(dkeys, &head->fmh_keys[1])) - return -EINVAL; - info.next_daddr = head->fmh_keys[0].fmr_physical + head->fmh_keys[0].fmr_length; info.fsmap_recs = fsmap_recs; @@ -960,6 +975,8 @@ xfs_getfsmap( info.dev = handlers[i].dev; info.last = false; info.pag = NULL; + info.low_daddr = -1ULL; + info.low.rm_blockcount = 0; error = handlers[i].fn(tp, dkeys, &info); if (error) break; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index fc61cc024023..79004d193e54 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -639,7 +639,6 @@ xfs_log_mount( int num_bblks) { struct xlog *log; - bool fatal = xfs_has_crc(mp); int error = 0; int min_logfsbs; @@ -663,53 +662,37 @@ xfs_log_mount( mp->m_log = log; /* - * Validate the given log space and drop a critical message via syslog - * if the log size is too small that would lead to some unexpected - * situations in transaction log space reservation stage. + * Now that we have set up the log and it's internal geometry + * parameters, we can validate the given log space and drop a critical + * message via syslog if the log size is too small. A log that is too + * small can lead to unexpected situations in transaction log space + * reservation stage. The superblock verifier has already validated all + * the other log geometry constraints, so we don't have to check those + * here. * - * Note: we can't just reject the mount if the validation fails. This - * would mean that people would have to downgrade their kernel just to - * remedy the situation as there is no way to grow the log (short of - * black magic surgery with xfs_db). + * Note: For v4 filesystems, we can't just reject the mount if the + * validation fails. This would mean that people would have to + * downgrade their kernel just to remedy the situation as there is no + * way to grow the log (short of black magic surgery with xfs_db). * - * We can, however, reject mounts for CRC format filesystems, as the + * We can, however, reject mounts for V5 format filesystems, as the * mkfs binary being used to make the filesystem should never create a * filesystem with a log that is too small. */ min_logfsbs = xfs_log_calc_minimum_size(mp); - if (mp->m_sb.sb_logblocks < min_logfsbs) { xfs_warn(mp, "Log size %d blocks too small, minimum size is %d blocks", mp->m_sb.sb_logblocks, min_logfsbs); - error = -EINVAL; - } else if (mp->m_sb.sb_logblocks > XFS_MAX_LOG_BLOCKS) { - xfs_warn(mp, - "Log size %d blocks too large, maximum size is %lld blocks", - mp->m_sb.sb_logblocks, XFS_MAX_LOG_BLOCKS); - error = -EINVAL; - } else if (XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks) > XFS_MAX_LOG_BYTES) { - xfs_warn(mp, - "log size %lld bytes too large, maximum size is %lld bytes", - XFS_FSB_TO_B(mp, mp->m_sb.sb_logblocks), - XFS_MAX_LOG_BYTES); - error = -EINVAL; - } else if (mp->m_sb.sb_logsunit > 1 && - mp->m_sb.sb_logsunit % mp->m_sb.sb_blocksize) { - xfs_warn(mp, - "log stripe unit %u bytes must be a multiple of block size", - mp->m_sb.sb_logsunit); - error = -EINVAL; - fatal = true; - } - if (error) { + /* * Log check errors are always fatal on v5; or whenever bad * metadata leads to a crash. */ - if (fatal) { + if (xfs_has_crc(mp)) { xfs_crit(mp, "AAIEEE! Log failed size checks. Abort!"); ASSERT(0); + error = -EINVAL; goto out_free_log; } xfs_crit(mp, "Log size out of supported range."); diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index c4078d0ec108..4a9bbd3fe120 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -114,7 +114,8 @@ xfs_dax_notify_ddev_failure( int error = 0; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, daddr); xfs_agnumber_t agno = XFS_FSB_TO_AGNO(mp, fsbno); - xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, daddr + bblen); + xfs_fsblock_t end_fsbno = XFS_DADDR_TO_FSB(mp, + daddr + bblen - 1); xfs_agnumber_t end_agno = XFS_FSB_TO_AGNO(mp, end_fsbno); error = xfs_trans_alloc_empty(mp, &tp); @@ -210,7 +211,7 @@ xfs_dax_notify_failure( ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1; /* Ignore the range out of filesystem area */ - if (offset + len < ddev_start) + if (offset + len - 1 < ddev_start) return -ENXIO; if (offset > ddev_end) return -ENXIO; @@ -222,8 +223,8 @@ xfs_dax_notify_failure( len -= ddev_start - offset; offset = 0; } - if (offset + len > ddev_end) - len -= ddev_end - offset; + if (offset + len - 1 > ddev_end) + len = ddev_end - offset + 1; return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len), mf_flags); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index abcc559f3c64..eb9102453aff 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -617,7 +617,8 @@ xfs_reflink_cancel_cow_blocks( del.br_blockcount); error = xfs_free_extent_later(*tpp, del.br_startblock, - del.br_blockcount, NULL); + del.br_blockcount, NULL, + XFS_AG_RESV_NONE); if (error) break; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 4db669203149..f3cc204bb4bf 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3623,6 +3623,31 @@ DEFINE_FSMAP_EVENT(xfs_fsmap_low_key); DEFINE_FSMAP_EVENT(xfs_fsmap_high_key); DEFINE_FSMAP_EVENT(xfs_fsmap_mapping); +DECLARE_EVENT_CLASS(xfs_fsmap_linear_class, + TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), + TP_ARGS(mp, keydev, bno), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(dev_t, keydev) + __field(xfs_fsblock_t, bno) + ), + TP_fast_assign( + __entry->dev = mp->m_super->s_dev; + __entry->keydev = new_decode_dev(keydev); + __entry->bno = bno; + ), + TP_printk("dev %d:%d keydev %d:%d bno 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), + MAJOR(__entry->keydev), MINOR(__entry->keydev), + __entry->bno) +) +#define DEFINE_FSMAP_LINEAR_EVENT(name) \ +DEFINE_EVENT(xfs_fsmap_linear_class, name, \ + TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \ + TP_ARGS(mp, keydev, bno)) +DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_low_key_linear); +DEFINE_FSMAP_LINEAR_EVENT(xfs_fsmap_high_key_linear); + DECLARE_EVENT_CLASS(xfs_getfsmap_class, TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap), TP_ARGS(mp, fsmap), diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 7d4109af193e..1098452e7f95 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -823,7 +823,7 @@ xfs_trans_ail_update_bulk( trace_xfs_ail_insert(lip, 0, lsn); } lip->li_lsn = lsn; - list_add(&lip->li_ail, &tmp); + list_add_tail(&lip->li_ail, &tmp); } if (!list_empty(&tmp)) |