diff options
Diffstat (limited to 'fs')
51 files changed, 501 insertions, 236 deletions
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 8fc41705c7cd..961a12dc6dc8 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -170,7 +170,6 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi, mutex_unlock(&sbi->wq_mutex); - if (autofs4_write(sbi, pipe, &pkt, pktsz)) switch (ret = autofs4_write(sbi, pipe, &pkt, pktsz)) { case 0: break; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index ab69dcb70e8a..1b468250e947 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1440,6 +1440,29 @@ static int __close_session(struct ceph_mds_client *mdsc, return request_close_session(mdsc, session); } +static bool drop_negative_children(struct dentry *dentry) +{ + struct dentry *child; + bool all_negative = true; + + if (!d_is_dir(dentry)) + goto out; + + spin_lock(&dentry->d_lock); + list_for_each_entry(child, &dentry->d_subdirs, d_child) { + if (d_really_is_positive(child)) { + all_negative = false; + break; + } + } + spin_unlock(&dentry->d_lock); + + if (all_negative) + shrink_dcache_parent(dentry); +out: + return all_negative; +} + /* * Trim old(er) caps. * @@ -1490,16 +1513,27 @@ static int trim_caps_cb(struct inode *inode, struct ceph_cap *cap, void *arg) if ((used | wanted) & ~oissued & mine) goto out; /* we need these caps */ - session->s_trim_caps--; if (oissued) { /* we aren't the only cap.. just remove us */ __ceph_remove_cap(cap, true); + session->s_trim_caps--; } else { + struct dentry *dentry; /* try dropping referring dentries */ spin_unlock(&ci->i_ceph_lock); - d_prune_aliases(inode); - dout("trim_caps_cb %p cap %p pruned, count now %d\n", - inode, cap, atomic_read(&inode->i_count)); + dentry = d_find_any_alias(inode); + if (dentry && drop_negative_children(dentry)) { + int count; + dput(dentry); + d_prune_aliases(inode); + count = atomic_read(&inode->i_count); + if (count == 1) + session->s_trim_caps--; + dout("trim_caps_cb %p cap %p pruned, count now %d\n", + inode, cap, count); + } else { + dput(dentry); + } return 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index e06740436b92..ed88ab8a4774 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1406,7 +1406,8 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses, } while (rc == -EAGAIN); if (rc) { - cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); + if (rc != -ENOENT) + cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc); goto out; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5331631386a2..01346b8b6edb 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2678,27 +2678,27 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, cifs_small_buf_release(req); rsp = (struct smb2_read_rsp *)rsp_iov.iov_base; - shdr = get_sync_hdr(rsp); - if (shdr->Status == STATUS_END_OF_FILE) { + if (rc) { + if (rc != -ENODATA) { + cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); + cifs_dbg(VFS, "Send error in read = %d\n", rc); + } free_rsp_buf(resp_buftype, rsp_iov.iov_base); - return 0; + return rc == -ENODATA ? 0 : rc; } - if (rc) { - cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); - cifs_dbg(VFS, "Send error in read = %d\n", rc); - } else { - *nbytes = le32_to_cpu(rsp->DataLength); - if ((*nbytes > CIFS_MAX_MSGSIZE) || - (*nbytes > io_parms->length)) { - cifs_dbg(FYI, "bad length %d for count %d\n", - *nbytes, io_parms->length); - rc = -EIO; - *nbytes = 0; - } + *nbytes = le32_to_cpu(rsp->DataLength); + if ((*nbytes > CIFS_MAX_MSGSIZE) || + (*nbytes > io_parms->length)) { + cifs_dbg(FYI, "bad length %d for count %d\n", + *nbytes, io_parms->length); + rc = -EIO; + *nbytes = 0; } + shdr = get_sync_hdr(rsp); + if (*buf) { memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes); free_rsp_buf(resp_buftype, rsp_iov.iov_base); diff --git a/fs/cramfs/Kconfig b/fs/cramfs/Kconfig index f937082f3244..58e2fe40b2a0 100644 --- a/fs/cramfs/Kconfig +++ b/fs/cramfs/Kconfig @@ -34,6 +34,7 @@ config CRAMFS_BLOCKDEV config CRAMFS_MTD bool "Support CramFs image directly mapped in physical memory" depends on CRAMFS && MTD + depends on CRAMFS=m || MTD=y default y if !CRAMFS_BLOCKDEV help This option allows the CramFs driver to load data directly from @@ -627,8 +627,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, if (pfn != pmd_pfn(*pmdp)) goto unlock_pmd; - if (!pmd_dirty(*pmdp) - && !pmd_access_permitted(*pmdp, WRITE)) + if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp)) goto unlock_pmd; flush_cache_page(vma, address, pfn); diff --git a/fs/exec.c b/fs/exec.c index 6be2aa0ab26f..5688b5e1b937 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1216,15 +1216,14 @@ killed: return -EAGAIN; } -char *get_task_comm(char *buf, struct task_struct *tsk) +char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { - /* buf must be at least sizeof(tsk->comm) in size */ task_lock(tsk); - strncpy(buf, tsk->comm, sizeof(tsk->comm)); + strncpy(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } -EXPORT_SYMBOL_GPL(get_task_comm); +EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable @@ -1340,15 +1339,10 @@ void setup_new_exec(struct linux_binprm * bprm) * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid - * races from other threads changing the limits. This also - * must be protected from races with prlimit() calls. + * needing to clean up the change on failure. */ - task_lock(current->group_leader); if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM) current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM; - if (current->signal->rlim[RLIMIT_STACK].rlim_max > _STK_LIM) - current->signal->rlim[RLIMIT_STACK].rlim_max = _STK_LIM; - task_unlock(current->group_leader); } arch_pick_mmap_layout(current->mm); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 07bca11749d4..c941251ac0c0 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4722,6 +4722,7 @@ retry: EXT4_INODE_EOFBLOCKS); } ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); ret2 = ext4_journal_stop(handle); if (ret2) break; diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index b4267d72f249..b32cf263750d 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -816,6 +816,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir, #ifdef CONFIG_EXT4_FS_POSIX_ACL struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT); + if (IS_ERR(p)) + return ERR_CAST(p); if (p) { int acl_size = p->a_count * sizeof(ext4_acl_entry); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7df2c5644e59..534a9130f625 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -149,6 +149,15 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, */ int ext4_inode_is_fast_symlink(struct inode *inode) { + if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { + int ea_blocks = EXT4_I(inode)->i_file_acl ? + EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; + + if (ext4_has_inline_data(inode)) + return 0; + + return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); + } return S_ISLNK(inode->i_mode) && inode->i_size && (inode->i_size < EXT4_N_BLOCKS * 4); } diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 798b3ac680db..e750d68fbcb5 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1399,6 +1399,10 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, "falling back\n")); } nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb); + if (!nblocks) { + ret = NULL; + goto cleanup_and_exit; + } start = EXT4_I(dir)->i_dir_start_lookup; if (start >= nblocks) start = 0; diff --git a/fs/namespace.c b/fs/namespace.c index e158ec6b527b..9d1374ab6e06 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2826,6 +2826,7 @@ long do_mount(const char *dev_name, const char __user *dir_name, SB_DIRSYNC | SB_SILENT | SB_POSIXACL | + SB_LAZYTIME | SB_I_VERSION); if (flags & MS_REMOUNT) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 0ac2fb1c6b63..b9129e2befea 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -291,12 +291,23 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat const struct sockaddr *sap = data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); +again: list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; /* Don't match clients that failed to initialise properly */ if (clp->cl_cons_state < 0) continue; + /* If a client is still initializing then we need to wait */ + if (clp->cl_cons_state > NFS_CS_READY) { + refcount_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + nfs_wait_client_init_complete(clp); + nfs_put_client(clp); + spin_lock(&nn->nfs_client_lock); + goto again; + } + /* Different NFS versions cannot share the same nfs_client */ if (clp->rpc_ops != data->nfs_mod->rpc_ops) continue; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 12bbab0becb4..65a7e5da508c 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -404,15 +404,19 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp, if (error < 0) goto error; - if (!nfs4_has_session(clp)) - nfs_mark_client_ready(clp, NFS_CS_READY); - error = nfs4_discover_server_trunking(clp, &old); if (error < 0) goto error; - if (clp != old) + if (clp != old) { clp->cl_preserve_clid = true; + /* + * Mark the client as having failed initialization so other + * processes walking the nfs_client_list in nfs_match_client() + * won't try to use it. + */ + nfs_mark_client_ready(clp, -EPERM); + } nfs_put_client(clp); clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags); return old; @@ -539,6 +543,9 @@ int nfs40_walk_client_list(struct nfs_client *new, spin_lock(&nn->nfs_client_lock); list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) { + if (pos == new) + goto found; + status = nfs4_match_client(pos, new, &prev, nn); if (status < 0) goto out_unlock; @@ -559,6 +566,7 @@ int nfs40_walk_client_list(struct nfs_client *new, * way that a SETCLIENTID_CONFIRM to pos can succeed is * if new and pos point to the same server: */ +found: refcount_inc(&pos->cl_count); spin_unlock(&nn->nfs_client_lock); @@ -572,6 +580,7 @@ int nfs40_walk_client_list(struct nfs_client *new, case 0: nfs4_swap_callback_idents(pos, new); pos->cl_confirm = new->cl_confirm; + nfs_mark_client_ready(pos, NFS_CS_READY); prev = NULL; *result = pos; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5b5f464f6f2a..4a379d7918f2 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1890,6 +1890,8 @@ int nfs_commit_inode(struct inode *inode, int how) if (res) error = nfs_generic_commit_list(inode, &head, how, &cinfo); nfs_commit_end(cinfo.mds); + if (res == 0) + return res; if (error < 0) goto out_error; if (!may_wait) diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 697f8ae7792d..f650e475d8f0 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -60,6 +60,9 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) gi->gid[i] = exp->ex_anon_gid; else gi->gid[i] = rqgi->gid[i]; + + /* Each thread allocates its own gi, no race */ + groups_sort(gi); } } else { gi = get_group_info(rqgi); diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index cbfc196e5dc5..5ac415466861 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -24,6 +24,16 @@ config OVERLAY_FS_REDIRECT_DIR an overlay which has redirects on a kernel that doesn't support this feature will have unexpected results. +config OVERLAY_FS_REDIRECT_ALWAYS_FOLLOW + bool "Overlayfs: follow redirects even if redirects are turned off" + default y + depends on OVERLAY_FS + help + Disable this to get a possibly more secure configuration, but that + might not be backward compatible with previous kernels. + + For more information, see Documentation/filesystems/overlayfs.txt + config OVERLAY_FS_INDEX bool "Overlayfs: turn on inodes index feature by default" depends on OVERLAY_FS diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index e13921824c70..f9788bc116a8 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -887,7 +887,8 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) spin_unlock(&dentry->d_lock); } else { kfree(redirect); - pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err); + pr_warn_ratelimited("overlayfs: failed to set redirect (%i)\n", + err); /* Fall back to userspace copy-up */ err = -EXDEV; } diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index 625ed8066570..beb945e1963c 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -435,7 +435,7 @@ int ovl_verify_index(struct dentry *index, struct ovl_path *lower, /* Check if index is orphan and don't warn before cleaning it */ if (d_inode(index)->i_nlink == 1 && - ovl_get_nlink(index, origin.dentry, 0) == 0) + ovl_get_nlink(origin.dentry, index, 0) == 0) err = -ENOENT; dput(origin.dentry); @@ -681,6 +681,22 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, if (d.stop) break; + /* + * Following redirects can have security consequences: it's like + * a symlink into the lower layer without the permission checks. + * This is only a problem if the upper layer is untrusted (e.g + * comes from an USB drive). This can allow a non-readable file + * or directory to become readable. + * + * Only following redirects when redirects are enabled disables + * this attack vector when not necessary. + */ + err = -EPERM; + if (d.redirect && !ofs->config.redirect_follow) { + pr_warn_ratelimited("overlay: refusing to follow redirect for (%pd2)\n", dentry); + goto out_put; + } + if (d.redirect && d.redirect[0] == '/' && poe != roe) { poe = roe; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 13eab09a6b6f..b489099ccd49 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -180,7 +180,7 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry) static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode) { struct dentry *ret = vfs_tmpfile(dentry, mode, 0); - int err = IS_ERR(ret) ? PTR_ERR(ret) : 0; + int err = PTR_ERR_OR_ZERO(ret); pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err); return ret; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index 752bab645879..9d0bc03bf6e4 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -14,6 +14,8 @@ struct ovl_config { char *workdir; bool default_permissions; bool redirect_dir; + bool redirect_follow; + const char *redirect_mode; bool index; }; diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c index 0daa4354fec4..8c98578d27a1 100644 --- a/fs/overlayfs/readdir.c +++ b/fs/overlayfs/readdir.c @@ -499,7 +499,7 @@ out: return err; fail: - pr_warn_ratelimited("overlay: failed to look up (%s) for ino (%i)\n", + pr_warn_ratelimited("overlayfs: failed to look up (%s) for ino (%i)\n", p->name, err); goto out; } @@ -663,7 +663,10 @@ static int ovl_iterate_real(struct file *file, struct dir_context *ctx) return PTR_ERR(rdt.cache); } - return iterate_dir(od->realfile, &rdt.ctx); + err = iterate_dir(od->realfile, &rdt.ctx); + ctx->pos = rdt.ctx.pos; + + return err; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 288d20f9a55a..76440feb79f6 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -33,6 +33,13 @@ module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644); MODULE_PARM_DESC(ovl_redirect_dir_def, "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(ovl_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(ovl_index_def, @@ -232,6 +239,7 @@ static void ovl_free_fs(struct ovl_fs *ofs) kfree(ofs->config.lowerdir); kfree(ofs->config.upperdir); kfree(ofs->config.workdir); + kfree(ofs->config.redirect_mode); if (ofs->creator_cred) put_cred(ofs->creator_cred); kfree(ofs); @@ -244,6 +252,7 @@ static void ovl_put_super(struct super_block *sb) ovl_free_fs(ofs); } +/* Sync real dirty inodes in upper filesystem (if it exists) */ static int ovl_sync_fs(struct super_block *sb, int wait) { struct ovl_fs *ofs = sb->s_fs_info; @@ -252,14 +261,24 @@ static int ovl_sync_fs(struct super_block *sb, int wait) if (!ofs->upper_mnt) return 0; - upper_sb = ofs->upper_mnt->mnt_sb; - if (!upper_sb->s_op->sync_fs) + + /* + * If this is a sync(2) call or an emergency sync, all the super blocks + * will be iterated, including upper_sb, so no need to do anything. + * + * If this is a syncfs(2) call, then we do need to call + * sync_filesystem() on upper_sb, but enough if we do it when being + * called with wait == 1. + */ + if (!wait) return 0; - /* real inodes have already been synced by sync_filesystem(ovl_sb) */ + upper_sb = ofs->upper_mnt->mnt_sb; + down_read(&upper_sb->s_umount); - ret = upper_sb->s_op->sync_fs(upper_sb, wait); + ret = sync_filesystem(upper_sb); up_read(&upper_sb->s_umount); + return ret; } @@ -295,6 +314,11 @@ static bool ovl_force_readonly(struct ovl_fs *ofs) return (!ofs->upper_mnt || !ofs->workdir); } +static const char *ovl_redirect_mode_def(void) +{ + return ovl_redirect_dir_def ? "on" : "off"; +} + /** * ovl_show_options * @@ -313,12 +337,10 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry) } if (ofs->config.default_permissions) seq_puts(m, ",default_permissions"); - if (ofs->config.redirect_dir != ovl_redirect_dir_def) - seq_printf(m, ",redirect_dir=%s", - ofs->config.redirect_dir ? "on" : "off"); + if (strcmp(ofs->config.redirect_mode, ovl_redirect_mode_def()) != 0) + seq_printf(m, ",redirect_dir=%s", ofs->config.redirect_mode); if (ofs->config.index != ovl_index_def) - seq_printf(m, ",index=%s", - ofs->config.index ? "on" : "off"); + seq_printf(m, ",index=%s", ofs->config.index ? "on" : "off"); return 0; } @@ -348,8 +370,7 @@ enum { OPT_UPPERDIR, OPT_WORKDIR, OPT_DEFAULT_PERMISSIONS, - OPT_REDIRECT_DIR_ON, - OPT_REDIRECT_DIR_OFF, + OPT_REDIRECT_DIR, OPT_INDEX_ON, OPT_INDEX_OFF, OPT_ERR, @@ -360,8 +381,7 @@ static const match_table_t ovl_tokens = { {OPT_UPPERDIR, "upperdir=%s"}, {OPT_WORKDIR, "workdir=%s"}, {OPT_DEFAULT_PERMISSIONS, "default_permissions"}, - {OPT_REDIRECT_DIR_ON, "redirect_dir=on"}, - {OPT_REDIRECT_DIR_OFF, "redirect_dir=off"}, + {OPT_REDIRECT_DIR, "redirect_dir=%s"}, {OPT_INDEX_ON, "index=on"}, {OPT_INDEX_OFF, "index=off"}, {OPT_ERR, NULL} @@ -390,10 +410,37 @@ static char *ovl_next_opt(char **s) return sbegin; } +static int ovl_parse_redirect_mode(struct ovl_config *config, const char *mode) +{ + if (strcmp(mode, "on") == 0) { + config->redirect_dir = true; + /* + * Does not make sense to have redirect creation without + * redirect following. + */ + config->redirect_follow = true; + } else if (strcmp(mode, "follow") == 0) { + config->redirect_follow = true; + } else if (strcmp(mode, "off") == 0) { + if (ovl_redirect_always_follow) + config->redirect_follow = true; + } else if (strcmp(mode, "nofollow") != 0) { + pr_err("overlayfs: bad mount option \"redirect_dir=%s\"\n", + mode); + return -EINVAL; + } + + return 0; +} + static int ovl_parse_opt(char *opt, struct ovl_config *config) { char *p; + config->redirect_mode = kstrdup(ovl_redirect_mode_def(), GFP_KERNEL); + if (!config->redirect_mode) + return -ENOMEM; + while ((p = ovl_next_opt(&opt)) != NULL) { int token; substring_t args[MAX_OPT_ARGS]; @@ -428,12 +475,11 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->default_permissions = true; break; - case OPT_REDIRECT_DIR_ON: - config->redirect_dir = true; - break; - - case OPT_REDIRECT_DIR_OFF: - config->redirect_dir = false; + case OPT_REDIRECT_DIR: + kfree(config->redirect_mode); + config->redirect_mode = match_strdup(&args[0]); + if (!config->redirect_mode) + return -ENOMEM; break; case OPT_INDEX_ON: @@ -458,7 +504,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config) config->workdir = NULL; } - return 0; + return ovl_parse_redirect_mode(config, config->redirect_mode); } #define OVL_WORKDIR_NAME "work" @@ -1160,7 +1206,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) if (!cred) goto out_err; - ofs->config.redirect_dir = ovl_redirect_dir_def; ofs->config.index = ovl_index_def; err = ovl_parse_opt((char *) data, &ofs->config); if (err) diff --git a/fs/super.c b/fs/super.c index d4e33e8f1e6f..7ff1349609e4 100644 --- a/fs/super.c +++ b/fs/super.c @@ -191,6 +191,24 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); + init_rwsem(&s->s_umount); + lockdep_set_class(&s->s_umount, &type->s_umount_key); + /* + * sget() can have s_umount recursion. + * + * When it cannot find a suitable sb, it allocates a new + * one (this one), and tries again to find a suitable old + * one. + * + * In case that succeeds, it will acquire the s_umount + * lock of the old one. Since these are clearly distrinct + * locks, and this object isn't exposed yet, there's no + * risk of deadlocks. + * + * Annotate this by putting this lock in a different + * subclass. + */ + down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; @@ -218,25 +236,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, goto fail; if (list_lru_init_memcg(&s->s_inode_lru)) goto fail; - - init_rwsem(&s->s_umount); - lockdep_set_class(&s->s_umount, &type->s_umount_key); - /* - * sget() can have s_umount recursion. - * - * When it cannot find a suitable sb, it allocates a new - * one (this one), and tries again to find a suitable old - * one. - * - * In case that succeeds, it will acquire the s_umount - * lock of the old one. Since these are clearly distrinct - * locks, and this object isn't exposed yet, there's no - * risk of deadlocks. - * - * Annotate this by putting this lock in a different - * subclass. - */ - down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 0da80019a917..83ed7715f856 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -702,7 +702,7 @@ xfs_alloc_ag_vextent( ASSERT(args->agbno % args->alignment == 0); /* if not file data, insert new block into the reverse map btree */ - if (args->oinfo.oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) { error = xfs_rmap_alloc(args->tp, args->agbp, args->agno, args->agbno, args->len, &args->oinfo); if (error) @@ -1682,7 +1682,7 @@ xfs_free_ag_extent( bno_cur = cnt_cur = NULL; mp = tp->t_mountp; - if (oinfo->oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(oinfo)) { error = xfs_rmap_free(tp, agbp, agno, bno, len, oinfo); if (error) goto error0; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 6249c92671de..a76914db72ef 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -212,6 +212,7 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; + struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_defer_ops dfops; struct xfs_trans_res tres; @@ -327,9 +328,16 @@ xfs_attr_set( * GROT: another possible req'mt for a double-split btree op. */ xfs_defer_init(args.dfops, args.firstblock); - error = xfs_attr_shortform_to_leaf(&args); + error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); if (error) goto out_defer_cancel; + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args.trans, leaf_bp); + xfs_defer_bjoin(args.dfops, leaf_bp); xfs_defer_ijoin(args.dfops, dp); error = xfs_defer_finish(&args.trans, args.dfops); if (error) @@ -337,13 +345,14 @@ xfs_attr_set( /* * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf. + * transaction to add the new attribute to the leaf, which + * means that we have to hold & join the leaf buffer here too. */ - error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; - + xfs_trans_bjoin(args.trans, leaf_bp); + leaf_bp = NULL; } if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -374,8 +383,9 @@ xfs_attr_set( out_defer_cancel: xfs_defer_cancel(&dfops); - args.trans = NULL; out: + if (leaf_bp) + xfs_trans_brelse(args.trans, leaf_bp); if (args.trans) xfs_trans_cancel(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 53cc8b986eac..601eaa36f1ad 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -735,10 +735,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args) } /* - * Convert from using the shortform to the leaf. + * Convert from using the shortform to the leaf. On success, return the + * buffer so that we can keep it locked until we're totally done with it. */ int -xfs_attr_shortform_to_leaf(xfs_da_args_t *args) +xfs_attr_shortform_to_leaf( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) { xfs_inode_t *dp; xfs_attr_shortform_t *sf; @@ -818,7 +821,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } error = 0; - + *leaf_bp = bp; out: kmem_free(tmpbuffer); return error; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index f7dda0c237b0..894124efb421 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -48,7 +48,8 @@ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); -int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); +int xfs_attr_shortform_to_leaf(struct xfs_da_args *args, + struct xfs_buf **leaf_bp); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1210f684d3c2..1bddbba6b80c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5136,7 +5136,7 @@ __xfs_bunmapi( * blowing out the transaction with a mix of EFIs and reflink * adjustments. */ - if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); else max_len = len; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 072ebfe1d6ae..087fea02c389 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -249,6 +249,10 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE); + /* Hold the (previously bjoin'd) buffer locked across the roll. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) + xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]); + trace_xfs_defer_trans_roll((*tp)->t_mountp, dop); /* Roll the transaction. */ @@ -264,6 +268,12 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0); + /* Rejoin the buffers and dirty them so the log moves forward. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) { + xfs_trans_bjoin(*tp, dop->dop_bufs[i]); + xfs_trans_bhold(*tp, dop->dop_bufs[i]); + } + return error; } @@ -295,6 +305,31 @@ xfs_defer_ijoin( } } + ASSERT(0); + return -EFSCORRUPTED; +} + +/* + * Add this buffer to the deferred op. Each joined buffer is relogged + * each time we roll the transaction. + */ +int +xfs_defer_bjoin( + struct xfs_defer_ops *dop, + struct xfs_buf *bp) +{ + int i; + + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) { + if (dop->dop_bufs[i] == bp) + return 0; + else if (dop->dop_bufs[i] == NULL) { + dop->dop_bufs[i] = bp; + return 0; + } + } + + ASSERT(0); return -EFSCORRUPTED; } @@ -493,9 +528,7 @@ xfs_defer_init( struct xfs_defer_ops *dop, xfs_fsblock_t *fbp) { - dop->dop_committed = false; - dop->dop_low = false; - memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes)); + memset(dop, 0, sizeof(struct xfs_defer_ops)); *fbp = NULLFSBLOCK; INIT_LIST_HEAD(&dop->dop_intake); INIT_LIST_HEAD(&dop->dop_pending); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index d4f046dd44bd..045beacdd37d 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -59,6 +59,7 @@ enum xfs_defer_ops_type { }; #define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ +#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */ struct xfs_defer_ops { bool dop_committed; /* did any trans commit? */ @@ -66,8 +67,9 @@ struct xfs_defer_ops { struct list_head dop_intake; /* unlogged pending work */ struct list_head dop_pending; /* logged pending work */ - /* relog these inodes with each roll */ + /* relog these with each roll */ struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES]; + struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS]; }; void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, @@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp); /* Description of a deferred type. */ struct xfs_defer_op_type { diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index de3f04a98656..3b57ef0f2f76 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -920,8 +920,7 @@ STATIC xfs_agnumber_t xfs_ialloc_ag_select( xfs_trans_t *tp, /* transaction pointer */ xfs_ino_t parent, /* parent directory inode number */ - umode_t mode, /* bits set to indicate file type */ - int okalloc) /* ok to allocate more space */ + umode_t mode) /* bits set to indicate file type */ { xfs_agnumber_t agcount; /* number of ag's in the filesystem */ xfs_agnumber_t agno; /* current ag number */ @@ -978,9 +977,6 @@ xfs_ialloc_ag_select( return agno; } - if (!okalloc) - goto nextag; - if (!pag->pagf_init) { error = xfs_alloc_pagf_init(mp, tp, agno, flags); if (error) @@ -1680,7 +1676,6 @@ xfs_dialloc( struct xfs_trans *tp, xfs_ino_t parent, umode_t mode, - int okalloc, struct xfs_buf **IO_agbp, xfs_ino_t *inop) { @@ -1692,6 +1687,7 @@ xfs_dialloc( int noroom = 0; xfs_agnumber_t start_agno; struct xfs_perag *pag; + int okalloc = 1; if (*IO_agbp) { /* @@ -1707,7 +1703,7 @@ xfs_dialloc( * We do not have an agbp, so select an initial allocation * group for inode allocation. */ - start_agno = xfs_ialloc_ag_select(tp, parent, mode, okalloc); + start_agno = xfs_ialloc_ag_select(tp, parent, mode); if (start_agno == NULLAGNUMBER) { *inop = NULLFSINO; return 0; diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h index d2bdcd5e7312..66a8de0b1caa 100644 --- a/fs/xfs/libxfs/xfs_ialloc.h +++ b/fs/xfs/libxfs/xfs_ialloc.h @@ -81,7 +81,6 @@ xfs_dialloc( struct xfs_trans *tp, /* transaction pointer */ xfs_ino_t parent, /* parent inode (directory) */ umode_t mode, /* mode bits for new inode */ - int okalloc, /* ok to allocate more space */ struct xfs_buf **agbp, /* buf for a.g. inode header */ xfs_ino_t *inop); /* inode number allocated */ diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 89bf16b4d937..b0f31791c7e6 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -632,8 +632,6 @@ xfs_iext_insert( struct xfs_iext_leaf *new = NULL; int nr_entries, i; - trace_xfs_iext_insert(ip, cur, state, _RET_IP_); - if (ifp->if_height == 0) xfs_iext_alloc_root(ifp, cur); else if (ifp->if_height == 1) @@ -661,6 +659,8 @@ xfs_iext_insert( xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); + trace_xfs_iext_insert(ip, cur, state, _RET_IP_); + if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 585b35d34142..c40d26763075 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1488,27 +1488,12 @@ __xfs_refcount_cow_alloc( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Add refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_ALLOC, dfops); - if (error) - return error; - - /* Add rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_alloc_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* @@ -1521,27 +1506,12 @@ __xfs_refcount_cow_free( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Remove refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_FREE, dfops); - if (error) - return error; - - /* Remove rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_free_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* Record a CoW staging extent in the refcount btree. */ @@ -1552,11 +1522,19 @@ xfs_refcount_alloc_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; - return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, + error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, fsb, len); + if (error) + return error; + + /* Add rmap entry */ + return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ @@ -1567,9 +1545,17 @@ xfs_refcount_free_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; + /* Remove rmap entry */ + error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + if (error) + return error; + return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW, fsb, len); } diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index dd019cee1b3b..50db920ceeeb 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -368,6 +368,51 @@ xfs_rmap_lookup_le_range( } /* + * Perform all the relevant owner checks for a removal op. If we're doing an + * unknown-owner removal then we have no owner information to check. + */ +static int +xfs_rmap_free_check_owner( + struct xfs_mount *mp, + uint64_t ltoff, + struct xfs_rmap_irec *rec, + xfs_fsblock_t bno, + xfs_filblks_t len, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + int error = 0; + + if (owner == XFS_RMAP_OWN_UNKNOWN) + return 0; + + /* Make sure the unwritten flag matches. */ + XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == + (rec->rm_flags & XFS_RMAP_UNWRITTEN), out); + + /* Make sure the owner matches what we expect to find in the tree. */ + XFS_WANT_CORRUPTED_GOTO(mp, owner == rec->rm_owner, out); + + /* Check the offset, if necessary. */ + if (XFS_RMAP_NON_INODE_OWNER(owner)) + goto out; + + if (flags & XFS_RMAP_BMBT_BLOCK) { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_flags & XFS_RMAP_BMBT_BLOCK, + out); + } else { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_offset <= offset, out); + XFS_WANT_CORRUPTED_GOTO(mp, + ltoff + rec->rm_blockcount >= offset + len, + out); + } + +out: + return error; +} + +/* * Find the extent in the rmap btree and remove it. * * The record we find should always be an exact match for the extent that we're @@ -444,33 +489,40 @@ xfs_rmap_unmap( goto out_done; } - /* Make sure the unwritten flag matches. */ - XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == - (ltrec.rm_flags & XFS_RMAP_UNWRITTEN), out_error); + /* + * If we're doing an unknown-owner removal for EFI recovery, we expect + * to find the full range in the rmapbt or nothing at all. If we + * don't find any rmaps overlapping either end of the range, we're + * done. Hopefully this means that the EFI creator already queued + * (and finished) a RUI to remove the rmap. + */ + if (owner == XFS_RMAP_OWN_UNKNOWN && + ltrec.rm_startblock + ltrec.rm_blockcount <= bno) { + struct xfs_rmap_irec rtrec; + + error = xfs_btree_increment(cur, 0, &i); + if (error) + goto out_error; + if (i == 0) + goto out_done; + error = xfs_rmap_get_rec(cur, &rtrec, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error); + if (rtrec.rm_startblock >= bno + len) + goto out_done; + } /* Make sure the extent we found covers the entire freeing range. */ XFS_WANT_CORRUPTED_GOTO(mp, ltrec.rm_startblock <= bno && - ltrec.rm_startblock + ltrec.rm_blockcount >= - bno + len, out_error); + ltrec.rm_startblock + ltrec.rm_blockcount >= + bno + len, out_error); - /* Make sure the owner matches what we expect to find in the tree. */ - XFS_WANT_CORRUPTED_GOTO(mp, owner == ltrec.rm_owner || - XFS_RMAP_NON_INODE_OWNER(owner), out_error); - - /* Check the offset, if necessary. */ - if (!XFS_RMAP_NON_INODE_OWNER(owner)) { - if (flags & XFS_RMAP_BMBT_BLOCK) { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_flags & XFS_RMAP_BMBT_BLOCK, - out_error); - } else { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_offset <= offset, out_error); - XFS_WANT_CORRUPTED_GOTO(mp, - ltoff + ltrec.rm_blockcount >= offset + len, - out_error); - } - } + /* Check owner information. */ + error = xfs_rmap_free_check_owner(mp, ltoff, <rec, bno, len, owner, + offset, flags); + if (error) + goto out_error; if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) { /* exact match, simply remove the record from rmap tree */ @@ -664,6 +716,7 @@ xfs_rmap_map( flags |= XFS_RMAP_UNWRITTEN; trace_xfs_rmap_map(mp, cur->bc_private.a.agno, bno, len, unwritten, oinfo); + ASSERT(!xfs_rmap_should_skip_owner_update(oinfo)); /* * For the initial lookup, look for an exact match or the left-adjacent diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 466ede637080..0fcd5b1ba729 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -61,7 +61,21 @@ static inline void xfs_rmap_skip_owner_update( struct xfs_owner_info *oi) { - oi->oi_owner = XFS_RMAP_OWN_UNKNOWN; + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_NULL); +} + +static inline bool +xfs_rmap_should_skip_owner_update( + struct xfs_owner_info *oi) +{ + return oi->oi_owner == XFS_RMAP_OWN_NULL; +} + +static inline void +xfs_rmap_any_owner_update( + struct xfs_owner_info *oi) +{ + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_UNKNOWN); } /* Reverse mapping functions. */ diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 9c42c4efd01e..ab3aef2ae823 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -46,7 +46,6 @@ #include "scrub/scrub.h" #include "scrub/common.h" #include "scrub/trace.h" -#include "scrub/scrub.h" #include "scrub/btree.h" /* diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c index 472080e75788..86daed0e3a45 100644 --- a/fs/xfs/scrub/trace.c +++ b/fs/xfs/scrub/trace.c @@ -26,7 +26,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_trans.h" diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 44f8c5451210..64da90655e95 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -538,7 +538,7 @@ xfs_efi_recover( return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); - xfs_rmap_skip_owner_update(&oinfo); + xfs_rmap_any_owner_update(&oinfo); for (i = 0; i < efip->efi_format.efi_nextents; i++) { extp = &efip->efi_format.efi_extents[i]; error = xfs_trans_free_extent(tp, efdp, extp->ext_start, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 8f22fc579dbb..60a2e128cb6a 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -571,6 +571,11 @@ xfs_growfs_data_private( * this doesn't actually exist in the rmap btree. */ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL); + error = xfs_rmap_free(tp, bp, agno, + be32_to_cpu(agf->agf_length) - new, + new, &oinfo); + if (error) + goto error0; error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno, be32_to_cpu(agf->agf_length) - new), diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 43005fbe8b1e..3861d61fb265 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -870,7 +870,7 @@ xfs_eofblocks_worker( * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default). * (We'll just piggyback on the post-EOF prealloc space workqueue.) */ -STATIC void +void xfs_queue_cowblocks( struct xfs_mount *mp) { @@ -1536,8 +1536,23 @@ xfs_inode_free_quota_eofblocks( return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks); } +static inline unsigned long +xfs_iflag_for_tag( + int tag) +{ + switch (tag) { + case XFS_ICI_EOFBLOCKS_TAG: + return XFS_IEOFBLOCKS; + case XFS_ICI_COWBLOCKS_TAG: + return XFS_ICOWBLOCKS; + default: + ASSERT(0); + return 0; + } +} + static void -__xfs_inode_set_eofblocks_tag( +__xfs_inode_set_blocks_tag( xfs_inode_t *ip, void (*execute)(struct xfs_mount *mp), void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, @@ -1552,10 +1567,10 @@ __xfs_inode_set_eofblocks_tag( * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ - if (ip->i_flags & XFS_IEOFBLOCKS) + if (ip->i_flags & xfs_iflag_for_tag(tag)) return; spin_lock(&ip->i_flags_lock); - ip->i_flags |= XFS_IEOFBLOCKS; + ip->i_flags |= xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1587,13 +1602,13 @@ xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_eofblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks, trace_xfs_perag_set_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } static void -__xfs_inode_clear_eofblocks_tag( +__xfs_inode_clear_blocks_tag( xfs_inode_t *ip, void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, int error, unsigned long caller_ip), @@ -1603,7 +1618,7 @@ __xfs_inode_clear_eofblocks_tag( struct xfs_perag *pag; spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~XFS_IEOFBLOCKS; + ip->i_flags &= ~xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1630,7 +1645,7 @@ xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } @@ -1724,7 +1739,7 @@ xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks, trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1734,6 +1749,6 @@ xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index bff4d85e5498..d4a77588eca1 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -81,6 +81,7 @@ void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip); int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *); int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip); void xfs_cowblocks_worker(struct work_struct *); +void xfs_queue_cowblocks(struct xfs_mount *); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 801274126648..6f95bdb408ce 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -749,7 +749,6 @@ xfs_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, - int okalloc, xfs_buf_t **ialloc_context, xfs_inode_t **ipp) { @@ -765,7 +764,7 @@ xfs_ialloc( * Call the space management code to pick * the on-disk inode to be allocated. */ - error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc, + error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, ialloc_context, &ino); if (error) return error; @@ -957,7 +956,6 @@ xfs_dir_ialloc( xfs_nlink_t nlink, dev_t rdev, prid_t prid, /* project id */ - int okalloc, /* ok to allocate new space */ xfs_inode_t **ipp, /* pointer to inode; it will be locked. */ int *committed) @@ -988,8 +986,8 @@ xfs_dir_ialloc( * transaction commit so that no other process can steal * the inode(s) that we've just allocated. */ - code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, okalloc, - &ialloc_context, &ip); + code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, &ialloc_context, + &ip); /* * Return an error if we were unable to allocate a new inode. @@ -1061,7 +1059,7 @@ xfs_dir_ialloc( * this call should always succeed. */ code = xfs_ialloc(tp, dp, mode, nlink, rdev, prid, - okalloc, &ialloc_context, &ip); + &ialloc_context, &ip); /* * If we get an error at this point, return to the caller @@ -1182,11 +1180,6 @@ xfs_create( xfs_flush_inodes(mp); error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); } - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1203,19 +1196,13 @@ xfs_create( if (error) goto out_trans_cancel; - if (!resblks) { - error = xfs_dir_canenter(tp, dp, name); - if (error) - goto out_trans_cancel; - } - /* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry * pointing to itself. */ - error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip, + NULL); if (error) goto out_trans_cancel; @@ -1340,11 +1327,6 @@ xfs_create_tmpfile( tres = &M_RES(mp)->tr_create_tmpfile; error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp); - if (error == -ENOSPC) { - /* No space at all so try a "no-allocation" reservation */ - resblks = 0; - error = xfs_trans_alloc(mp, tres, 0, 0, 0, &tp); - } if (error) goto out_release_inode; @@ -1353,8 +1335,7 @@ xfs_create_tmpfile( if (error) goto out_trans_cancel; - error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, - prid, resblks > 0, &ip, NULL); + error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, prid, &ip, NULL); if (error) goto out_trans_cancel; @@ -1506,6 +1487,24 @@ xfs_link( return error; } +/* Clear the reflink flag and the cowblocks tag if possible. */ +static void +xfs_itruncate_clear_reflink_flags( + struct xfs_inode *ip) +{ + struct xfs_ifork *dfork; + struct xfs_ifork *cfork; + + if (!xfs_is_reflink_inode(ip)) + return; + dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK); + if (dfork->if_bytes == 0 && cfork->if_bytes == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (cfork->if_bytes == 0) + xfs_inode_clear_cowblocks_tag(ip); +} + /* * Free up the underlying blocks past new_size. The new size must be smaller * than the current size. This routine can be used both for the attribute and @@ -1602,15 +1601,7 @@ xfs_itruncate_extents( if (error) goto out; - /* - * Clear the reflink flag if there are no data fork blocks and - * there are no extents staged in the cow fork. - */ - if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { - if (ip->i_d.di_nblocks == 0) - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; - xfs_inode_clear_cowblocks_tag(ip); - } + xfs_itruncate_clear_reflink_flags(ip); /* * Always re-log the inode so that our permanent transaction can keep diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index cc13c3763721..d383e392ec9d 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -232,6 +232,7 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) * log recovery to replay a bmap operation on the inode. */ #define XFS_IRECOVERY (1 << 11) +#define XFS_ICOWBLOCKS (1 << 12)/* has the cowblocks tag set */ /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during @@ -428,7 +429,7 @@ xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip); xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip); int xfs_dir_ialloc(struct xfs_trans **, struct xfs_inode *, umode_t, - xfs_nlink_t, dev_t, prid_t, int, + xfs_nlink_t, dev_t, prid_t, struct xfs_inode **, int *); /* from xfs_file.c */ diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 33eb4fb2e3fd..7ab52a8bc0a9 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1213,7 +1213,7 @@ xfs_xattr_iomap_begin( ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL); error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, - &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK); + &nimaps, XFS_BMAPI_ATTRFORK); out_unlock: xfs_iunlock(ip, lockmode); diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 010a13a201aa..ec952dfad359 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -793,8 +793,8 @@ xfs_qm_qino_alloc( return error; if (need_alloc) { - error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, 1, ip, - &committed); + error = xfs_dir_ialloc(&tp, NULL, S_IFREG, 1, 0, 0, ip, + &committed); if (error) { xfs_trans_cancel(tp); return error; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cc041a29eb70..47aea2e82c26 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -49,8 +49,6 @@ #include "xfs_alloc.h" #include "xfs_quota_defs.h" #include "xfs_quota.h" -#include "xfs_btree.h" -#include "xfs_bmap_btree.h" #include "xfs_reflink.h" #include "xfs_iomap.h" #include "xfs_rmap_btree.h" @@ -456,6 +454,8 @@ retry: if (error) goto out_bmap_cancel; + xfs_inode_set_cowblocks_tag(ip); + /* Finish up. */ error = xfs_defer_finish(&tp, &dfops); if (error) @@ -492,8 +492,9 @@ xfs_reflink_find_cow_mapping( struct xfs_iext_cursor icur; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); - ASSERT(xfs_is_reflink_inode(ip)); + if (!xfs_is_reflink_inode(ip)) + return false; offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got)) return false; @@ -612,6 +613,9 @@ xfs_reflink_cancel_cow_blocks( /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); + } else { + /* Didn't do anything, push cursor back. */ + xfs_iext_prev(ifp, &icur); } next_extent: if (!xfs_iext_get_extent(ifp, &icur, &got)) @@ -727,7 +731,7 @@ xfs_reflink_end_cow( (unsigned int)(end_fsb - offset_fsb), XFS_DATA_FORK); error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write, - resblks, 0, 0, &tp); + resblks, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; @@ -1293,6 +1297,17 @@ xfs_reflink_remap_range( trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + /* + * Clear out post-eof preallocations because we don't have page cache + * backing the delayed allocations and they'll never get freed on + * their own. + */ + if (xfs_can_free_eofblocks(dest, true)) { + ret = xfs_free_eofblocks(dest); + if (ret) + goto out_unlock; + } + /* Set flags and remap blocks. */ ret = xfs_reflink_set_inode_flag(src, dest); if (ret) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 5122d3021117..1dacccc367f8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1360,6 +1360,7 @@ xfs_fs_remount( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } + xfs_queue_cowblocks(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1369,6 +1370,14 @@ xfs_fs_remount( /* rw -> ro */ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) { + /* Get rid of any leftover CoW reservations... */ + cancel_delayed_work_sync(&mp->m_cowblocks_work); + error = xfs_icache_free_cowblocks(mp, NULL); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + /* Free the per-AG metadata reservation pool. */ error = xfs_fs_unreserve_ag_blocks(mp); if (error) { diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 68d3ca2c4968..2e9e793a8f9d 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -232,11 +232,6 @@ xfs_symlink( resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks); error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, resblks, 0, 0, &tp); - if (error == -ENOSPC && fs_blocks == 0) { - resblks = 0; - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_symlink, 0, 0, 0, - &tp); - } if (error) goto out_release_inode; @@ -260,14 +255,6 @@ xfs_symlink( goto out_trans_cancel; /* - * Check for ability to enter directory entry, if no space reserved. - */ - if (!resblks) { - error = xfs_dir_canenter(tp, dp, link_name); - if (error) - goto out_trans_cancel; - } - /* * Initialize the bmap freelist prior to calling either * bmapi or the directory create code. */ @@ -277,7 +264,7 @@ xfs_symlink( * Allocate an inode for the symlink. */ error = xfs_dir_ialloc(&tp, dp, S_IFLNK | (mode & ~S_IFMT), 1, 0, - prid, resblks > 0, &ip, NULL); + prid, &ip, NULL); if (error) goto out_trans_cancel; diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c index 5d95fe348294..35f3546b6af5 100644 --- a/fs/xfs/xfs_trace.c +++ b/fs/xfs/xfs_trace.c @@ -24,7 +24,6 @@ #include "xfs_mount.h" #include "xfs_defer.h" #include "xfs_da_format.h" -#include "xfs_defer.h" #include "xfs_inode.h" #include "xfs_btree.h" #include "xfs_da_btree.h" |