diff options
Diffstat (limited to 'fs')
89 files changed, 913 insertions, 548 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 43dea3b00c29..8a2562e3a316 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1075,8 +1075,6 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, if (fc->ac.error < 0) return; - d_drop(new_dentry); - inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key, newfid, newstatus, newcb, fc->cbi); if (IS_ERR(inode)) { @@ -1090,7 +1088,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); afs_vnode_commit_status(fc, vnode, 0); - d_add(new_dentry, inode); + d_instantiate(new_dentry, inode); } /* diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index d049cb459742..fde6b4d4121e 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -61,8 +61,11 @@ void afs_fileserver_probe_result(struct afs_call *call) afs_io_error(call, afs_io_error_fs_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -132,12 +135,14 @@ out: static int afs_do_probe_fileserver(struct afs_net *net, struct afs_server *server, struct key *key, - unsigned int server_index) + unsigned int server_index, + struct afs_error *_e) { struct afs_addr_cursor ac = { .index = 0, }; - int ret; + bool in_progress = false; + int err; _enter("%pU", &server->uuid); @@ -151,15 +156,17 @@ static int afs_do_probe_fileserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - ret = afs_fs_get_capabilities(net, server, &ac, key, server_index, + err = afs_fs_get_capabilities(net, server, &ac, key, server_index, true); - if (ret != -EINPROGRESS) { - afs_fs_probe_done(server); - return ret; - } + if (err == -EINPROGRESS) + in_progress = true; + else + afs_prioritise_error(_e, err, ac.abort_code); } - return 0; + if (!in_progress) + afs_fs_probe_done(server); + return in_progress; } /* @@ -169,21 +176,23 @@ int afs_probe_fileservers(struct afs_net *net, struct key *key, struct afs_server_list *list) { struct afs_server *server; - int i, ret; + struct afs_error e; + bool in_progress = false; + int i; + e.error = 0; + e.responded = false; for (i = 0; i < list->nr_servers; i++) { server = list->servers[i].server; if (test_bit(AFS_SERVER_FL_PROBED, &server->flags)) continue; - if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags)) { - ret = afs_do_probe_fileserver(net, server, key, i); - if (ret) - return ret; - } + if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags) && + afs_do_probe_fileserver(net, server, key, i, &e)) + in_progress = true; } - return 0; + return in_progress ? 0 : e.error; } /* diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 4c6d8e1112c2..6b17d3620414 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -382,7 +382,7 @@ void afs_zap_data(struct afs_vnode *vnode) int afs_validate(struct afs_vnode *vnode, struct key *key) { time64_t now = ktime_get_real_seconds(); - bool valid = false; + bool valid; int ret; _enter("{v={%llx:%llu} fl=%lx},%x", @@ -402,15 +402,21 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->cb_v_break = vnode->volume->cb_v_break; valid = false; } else if (vnode->status.type == AFS_FTYPE_DIR && - test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) && - vnode->cb_expires_at - 10 > now) { - valid = true; - } else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && - vnode->cb_expires_at - 10 > now) { + (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) || + vnode->cb_expires_at - 10 <= now)) { + valid = false; + } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) || + vnode->cb_expires_at - 10 <= now) { + valid = false; + } else { valid = true; } } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { valid = true; + } else { + vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; + vnode->cb_v_break = vnode->volume->cb_v_break; + valid = false; } read_sequnlock_excl(&vnode->cb_lock); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5da3b09b7518..8871b9e8645f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -696,6 +696,14 @@ struct afs_interface { }; /* + * Error prioritisation and accumulation. + */ +struct afs_error { + short error; /* Accumulated error */ + bool responded; /* T if server responded */ +}; + +/* * Cursor for iterating over a server's address list. */ struct afs_addr_cursor { @@ -1015,6 +1023,7 @@ static inline void __afs_stat(atomic_t *s) * misc.c */ extern int afs_abort_to_error(u32); +extern void afs_prioritise_error(struct afs_error *, int, u32); /* * mntpt.c diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 700a5fa7f4ec..bbb1fd51b019 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -118,3 +118,55 @@ int afs_abort_to_error(u32 abort_code) default: return -EREMOTEIO; } } + +/* + * Select the error to report from a set of errors. + */ +void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code) +{ + switch (error) { + case 0: + return; + default: + if (e->error == -ETIMEDOUT || + e->error == -ETIME) + return; + case -ETIMEDOUT: + case -ETIME: + if (e->error == -ENOMEM || + e->error == -ENONET) + return; + case -ENOMEM: + case -ENONET: + if (e->error == -ERFKILL) + return; + case -ERFKILL: + if (e->error == -EADDRNOTAVAIL) + return; + case -EADDRNOTAVAIL: + if (e->error == -ENETUNREACH) + return; + case -ENETUNREACH: + if (e->error == -EHOSTUNREACH) + return; + case -EHOSTUNREACH: + if (e->error == -EHOSTDOWN) + return; + case -EHOSTDOWN: + if (e->error == -ECONNREFUSED) + return; + case -ECONNREFUSED: + if (e->error == -ECONNRESET) + return; + case -ECONNRESET: /* Responded, but call expired. */ + if (e->responded) + return; + e->error = error; + return; + + case -ECONNABORTED: + e->responded = true; + e->error = afs_abort_to_error(abort_code); + return; + } +} diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 00504254c1c2..c3ae324781f8 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -136,7 +136,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) struct afs_addr_list *alist; struct afs_server *server; struct afs_vnode *vnode = fc->vnode; - u32 rtt, abort_code; + struct afs_error e; + u32 rtt; int error = fc->ac.error, i; _enter("%lx[%d],%lx[%d],%d,%d", @@ -306,8 +307,11 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) if (fc->error != -EDESTADDRREQ) goto iterate_address; /* Fall through */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: _debug("no conn"); fc->error = error; @@ -446,50 +450,15 @@ no_more_servers: if (fc->flags & AFS_FS_CURSOR_VBUSY) goto restart_from_beginning; - abort_code = 0; - error = -EDESTADDRREQ; + e.error = -EDESTADDRREQ; + e.responded = false; for (i = 0; i < fc->server_list->nr_servers; i++) { struct afs_server *s = fc->server_list->servers[i].server; - int probe_error = READ_ONCE(s->probe.error); - switch (probe_error) { - case 0: - continue; - default: - if (error == -ETIMEDOUT || - error == -ETIME) - continue; - case -ETIMEDOUT: - case -ETIME: - if (error == -ENOMEM || - error == -ENONET) - continue; - case -ENOMEM: - case -ENONET: - if (error == -ENETUNREACH) - continue; - case -ENETUNREACH: - if (error == -EHOSTUNREACH) - continue; - case -EHOSTUNREACH: - if (error == -ECONNREFUSED) - continue; - case -ECONNREFUSED: - if (error == -ECONNRESET) - continue; - case -ECONNRESET: /* Responded, but call expired. */ - if (error == -ECONNABORTED) - continue; - case -ECONNABORTED: - abort_code = s->probe.abort_code; - error = probe_error; - continue; - } + afs_prioritise_error(&e, READ_ONCE(s->probe.error), + s->probe.abort_code); } - if (error == -ECONNABORTED) - error = afs_abort_to_error(abort_code); - failed_set_error: fc->error = error; failed: @@ -553,8 +522,11 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) _leave(" = f [abort]"); return false; + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -633,6 +605,7 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc) struct afs_net *net = afs_v2net(fc->vnode); if (fc->error == -EDESTADDRREQ || + fc->error == -EADDRNOTAVAIL || fc->error == -ENETUNREACH || fc->error == -EHOSTUNREACH) afs_dump_edestaddrreq(fc); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 59970886690f..a7b44863d502 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -576,6 +576,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, { signed long rtt2, timeout; long ret; + bool stalled = false; u64 rtt; u32 life, last_life; @@ -609,12 +610,20 @@ static long afs_wait_for_call_to_complete(struct afs_call *call, life = rxrpc_kernel_check_life(call->net->socket, call->rxcall); if (timeout == 0 && - life == last_life && signal_pending(current)) + life == last_life && signal_pending(current)) { + if (stalled) break; + __set_current_state(TASK_RUNNING); + rxrpc_kernel_probe_life(call->net->socket, call->rxcall); + timeout = rtt2; + stalled = true; + continue; + } if (life != last_life) { timeout = rtt2; last_life = life; + stalled = false; } timeout = schedule_timeout(timeout); diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index c0f616bd70cb..f0b032976487 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -61,8 +61,11 @@ void afs_vlserver_probe_result(struct afs_call *call) afs_io_error(call, afs_io_error_vl_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -129,15 +132,17 @@ out: * Probe all of a vlserver's addresses to find out the best route and to * query its capabilities. */ -static int afs_do_probe_vlserver(struct afs_net *net, - struct afs_vlserver *server, - struct key *key, - unsigned int server_index) +static bool afs_do_probe_vlserver(struct afs_net *net, + struct afs_vlserver *server, + struct key *key, + unsigned int server_index, + struct afs_error *_e) { struct afs_addr_cursor ac = { .index = 0, }; - int ret; + bool in_progress = false; + int err; _enter("%s", server->name); @@ -151,15 +156,17 @@ static int afs_do_probe_vlserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - ret = afs_vl_get_capabilities(net, &ac, key, server, + err = afs_vl_get_capabilities(net, &ac, key, server, server_index, true); - if (ret != -EINPROGRESS) { - afs_vl_probe_done(server); - return ret; - } + if (err == -EINPROGRESS) + in_progress = true; + else + afs_prioritise_error(_e, err, ac.abort_code); } - return 0; + if (!in_progress) + afs_vl_probe_done(server); + return in_progress; } /* @@ -169,21 +176,23 @@ int afs_send_vl_probes(struct afs_net *net, struct key *key, struct afs_vlserver_list *vllist) { struct afs_vlserver *server; - int i, ret; + struct afs_error e; + bool in_progress = false; + int i; + e.error = 0; + e.responded = false; for (i = 0; i < vllist->nr_servers; i++) { server = vllist->servers[i].server; if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags)) continue; - if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags)) { - ret = afs_do_probe_vlserver(net, server, key, i); - if (ret) - return ret; - } + if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags) && + afs_do_probe_vlserver(net, server, key, i, &e)) + in_progress = true; } - return 0; + return in_progress ? 0 : e.error; } /* diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index b64a284b99d2..7adde83a0648 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -71,8 +71,9 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) { struct afs_addr_list *alist; struct afs_vlserver *vlserver; + struct afs_error e; u32 rtt; - int error = vc->ac.error, abort_code, i; + int error = vc->ac.error, i; _enter("%lx[%d],%lx[%d],%d,%d", vc->untried, vc->index, @@ -119,8 +120,11 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) goto failed; } + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -235,50 +239,15 @@ no_more_servers: if (vc->flags & AFS_VL_CURSOR_RETRY) goto restart_from_beginning; - abort_code = 0; - error = -EDESTADDRREQ; + e.error = -EDESTADDRREQ; + e.responded = false; for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; - int probe_error = READ_ONCE(s->probe.error); - switch (probe_error) { - case 0: - continue; - default: - if (error == -ETIMEDOUT || - error == -ETIME) - continue; - case -ETIMEDOUT: - case -ETIME: - if (error == -ENOMEM || - error == -ENONET) - continue; - case -ENOMEM: - case -ENONET: - if (error == -ENETUNREACH) - continue; - case -ENETUNREACH: - if (error == -EHOSTUNREACH) - continue; - case -EHOSTUNREACH: - if (error == -ECONNREFUSED) - continue; - case -ECONNREFUSED: - if (error == -ECONNRESET) - continue; - case -ECONNRESET: /* Responded, but call expired. */ - if (error == -ECONNABORTED) - continue; - case -ECONNABORTED: - abort_code = s->probe.abort_code; - error = probe_error; - continue; - } + afs_prioritise_error(&e, READ_ONCE(s->probe.error), + s->probe.abort_code); } - if (error == -ECONNABORTED) - error = afs_abort_to_error(abort_code); - failed_set_error: vc->error = error; failed: @@ -341,6 +310,7 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc) struct afs_net *net = vc->cell->net; if (vc->error == -EDESTADDRREQ || + vc->error == -EADDRNOTAVAIL || vc->error == -ENETUNREACH || vc->error == -EHOSTUNREACH) afs_vl_dump_edestaddrreq(vc); @@ -1438,6 +1438,7 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb) ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); + fput(req->ki_filp); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 80953528572d..68f322f600a0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3163,6 +3163,9 @@ void btrfs_destroy_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b0ab41da91d1..6d776717d8b3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -477,9 +477,9 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; while (1) { + clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE, mirror_num); if (!ret) { @@ -493,15 +493,6 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, break; } - /* - * This buffer's crc is fine, but its contents are corrupted, so - * there is no reason to read the other copies, they won't be - * any less wrong. - */ - if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) || - ret == -EUCLEAN) - break; - num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); if (num_copies == 1) @@ -1664,9 +1655,8 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - do { + while (1) { again = 0; /* Make the cleaner go to sleep early. */ @@ -1715,42 +1705,16 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -3931,6 +3895,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3958,9 +3929,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); @@ -4359,13 +4329,23 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, unpin = pinned_extents; again: while (1) { + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, NULL); - if (ret) + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } clear_extent_dirty(unpin, start, end); btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a3c22e16509b..58e93bce3036 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2089,6 +2089,30 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* + * Before we acquired the inode's lock, someone may have dirtied more + * pages in the target range. We need to make sure that writeback for + * any such pages does not start while we are logging the inode, because + * if it does, any of the following might happen when we are not doing a + * full inode sync: + * + * 1) We log an extent after its writeback finishes but before its + * checksums are added to the csum tree, leading to -EIO errors + * when attempting to read the extent after a log replay. + * + * 2) We can end up logging an extent before its writeback finishes. + * Therefore after the log replay we will have a file extent item + * pointing to an unwritten extent (and no data checksums as well). + * + * So trigger writeback for any eventual new dirty pages and then we + * wait for all ordered extents to complete below. + */ + ret = start_ordered_ops(inode, start, end); + if (ret) { + inode_unlock(inode); + goto out; + } + + /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaciton open. */ diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4ba0aedc878b..74aa552f4793 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -75,7 +75,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); - inode = btrfs_iget(fs_info->sb, &location, root, NULL); + inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path); + btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; @@ -838,6 +839,25 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, path->search_commit_root = 1; path->skip_locking = 1; + /* + * We must pass a path with search_commit_root set to btrfs_iget in + * order to avoid a deadlock when allocating extents for the tree root. + * + * When we are COWing an extent buffer from the tree root, when looking + * for a free extent, at extent-tree.c:find_free_extent(), we can find + * block group without its free space cache loaded. When we find one + * we must load its space cache which requires reading its free space + * cache's inode item from the root tree. If this inode item is located + * in the same leaf that we started COWing before, then we end up in + * deadlock on the extent buffer (trying to read lock it when we + * previously write locked it). + * + * It's safe to read the inode item using the commit root because + * block groups, once loaded, stay in memory forever (until they are + * removed) as well as their space caches once loaded. New block groups + * once created get their ->cached field set to BTRFS_CACHE_FINISHED so + * we will never try to read their inode item while the fs is mounted. + */ inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3df5b52278c..9ea4c6f0352f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1531,12 +1531,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) { + if (cur_offset <= end && cow_start == (u64)-1) cow_start = cur_offset; - cur_offset = end; - } if (cow_start != (u64)-1) { + cur_offset = end; ret = cow_file_range(inode, locked_page, cow_start, end, end, page_started, nr_written, 1, NULL); if (ret) @@ -3570,10 +3569,11 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static int btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode, + struct btrfs_path *in_path) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_path *path; + struct btrfs_path *path = in_path; struct extent_buffer *leaf; struct btrfs_inode_item *inode_item; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -3589,15 +3589,18 @@ static int btrfs_read_locked_inode(struct inode *inode) if (!ret) filled = true; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); if (ret) { - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); return ret; } @@ -3722,7 +3725,8 @@ cache_acl: btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); } - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); if (!maybe_acls) cache_no_acl(inode); @@ -5644,8 +5648,9 @@ static struct inode *btrfs_iget_locked(struct super_block *s, /* Get an inode object given its location and corresponding root. * Returns in *is_new if the inode was read from disk */ -struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new) +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path) { struct inode *inode; @@ -5656,7 +5661,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, if (inode->i_state & I_NEW) { int ret; - ret = btrfs_read_locked_inode(inode); + ret = btrfs_read_locked_inode(inode, path); if (!ret) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5678,6 +5683,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return inode; } +struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new) +{ + return btrfs_iget_path(s, location, root, new, NULL); +} + static struct inode *new_simple_dir(struct super_block *s, struct btrfs_key *key, struct btrfs_root *root) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3ca6943827ef..802a628e9f7d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3488,6 +3488,8 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; len = round_down(i_size_read(src), sz) - loff; + if (len == 0) + return 0; olen = len; } } @@ -4257,9 +4259,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 45868fd76209..f70825af6438 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2659,7 +2659,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, int i; u64 *i_qgroups; struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *quota_root = fs_info->quota_root; + struct btrfs_root *quota_root; struct btrfs_qgroup *srcgroup; struct btrfs_qgroup *dstgroup; u32 level_size = 0; @@ -2669,6 +2669,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) goto out; + quota_root = fs_info->quota_root; if (!quota_root) { ret = -EINVAL; goto out; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 924116f654a1..a3f75b8926d4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3959,6 +3959,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) restart: if (update_backref_cache(trans, &rc->backref_cache)) { btrfs_end_transaction(trans); + trans = NULL; continue; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 094cc1444a90..5be83b5a1b43 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3340,7 +3340,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m) kfree(m); } -static void tail_append_pending_moves(struct pending_dir_move *moves, +static void tail_append_pending_moves(struct send_ctx *sctx, + struct pending_dir_move *moves, struct list_head *stack) { if (list_empty(&moves->list)) { @@ -3351,6 +3352,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves, list_add_tail(&moves->list, stack); list_splice_tail(&list, stack); } + if (!RB_EMPTY_NODE(&moves->node)) { + rb_erase(&moves->node, &sctx->pending_dir_moves); + RB_CLEAR_NODE(&moves->node); + } } static int apply_children_dir_moves(struct send_ctx *sctx) @@ -3365,7 +3370,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) return 0; INIT_LIST_HEAD(&stack); - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); while (!list_empty(&stack)) { pm = list_first_entry(&stack, struct pending_dir_move, list); @@ -3376,7 +3381,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) goto out; pm = get_pending_dir_moves(sctx, parent_ino); if (pm) - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); } return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b362b45dd757..645fc81e2a94 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1916,7 +1916,7 @@ restore: } /* Used to sort the devices by max_avail(descending sort) */ -static int btrfs_cmp_device_free_bytes(const void *dev_info1, +static inline int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2) { if (((struct btrfs_device_info *)dev_info1)->max_avail > @@ -1945,8 +1945,8 @@ static inline void btrfs_descending_sort_devices( * The helper to calc the free space on the devices that can be used to store * file data. */ -static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, - u64 *free_bytes) +static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, + u64 *free_bytes) { struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; @@ -2237,6 +2237,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, vol = memdup_user((void __user *)arg, sizeof(*vol)); if (IS_ERR(vol)) return PTR_ERR(vol); + vol->name[BTRFS_PATH_NAME_MAX] = '\0'; switch (cmd) { case BTRFS_IOC_SCAN_DEV: diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index cab0b1f1f741..1a4e2b101ef2 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -389,13 +389,11 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, /* * Here we don't really care about alignment since extent allocator can - * handle it. We care more about the size, as if one block group is - * larger than maximum size, it's must be some obvious corruption. + * handle it. We care more about the size. */ - if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) { + if (key->offset == 0) { block_group_err(fs_info, leaf, slot, - "invalid block group size, have %llu expect (0, %llu]", - key->offset, BTRFS_MAX_DATA_CHUNK_SIZE); + "invalid block group size 0"); return -EUCLEAN; } @@ -440,7 +438,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) { block_group_err(fs_info, leaf, slot, -"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx", +"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, BTRFS_BLOCK_GROUP_SYSTEM, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index e07f3376b7df..a5ce99a6c936 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4396,6 +4396,23 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { + /* + * Skip extents outside our logging range. It's important to do + * it for correctness because if we don't ignore them, we may + * log them before their ordered extent completes, and therefore + * we could log them without logging their respective checksums + * (the checksum items are added to the csum tree at the very + * end of btrfs_finish_ordered_io()). Also leave such extents + * outside of our range in the list, since we may have another + * ranged fsync in the near future that needs them. If an extent + * outside our range corresponds to a hole, log it to avoid + * leaving gaps between extents (fsck will complain when we are + * not using the NO_HOLES feature). + */ + if ((em->start > end || em->start + em->len <= start) && + em->block_start != EXTENT_MAP_HOLE) + continue; + list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 95983c744164..1645fcfd9691 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -244,11 +244,13 @@ wait_for_old_object: ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)); - cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_retry); + cache->cache.ops->put_object(&xobject->fscache, + (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_retry); goto try_again; requeue: - cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); + cache->cache.ops->put_object(&xobject->fscache, + (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; } @@ -336,7 +338,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache, try_again: /* first step is to make up a grave dentry in the graveyard */ sprintf(nbuffer, "%08x%08x", - (uint32_t) get_seconds(), + (uint32_t) ktime_get_real_seconds(), (uint32_t) atomic_inc_return(&cache->gravecounter)); /* do the multiway lock magic */ diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 40f7595aad10..8a577409d030 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -535,7 +535,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -608,7 +611,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -962,11 +968,8 @@ void cachefiles_uncache_page(struct fscache_object *_object, struct page *page) __releases(&object->fscache.cookie->lock) { struct cachefiles_object *object; - struct cachefiles_cache *cache; object = container_of(_object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); _enter("%p,{%lu}", object, page->index); diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 0a29a00aed2e..511e6c68156a 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -135,7 +135,8 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object, struct dentry *dentry = object->dentry; int ret; - ASSERT(dentry); + if (!dentry) + return -ESTALE; _enter("%p,#%d", object, auxdata->len); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index b5ecd6f50360..4e9a7cc488da 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -563,8 +563,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root) seq_puts(m, ",noacl"); #endif - if (fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) - seq_puts(m, ",nocopyfrom"); + if ((fsopt->flags & CEPH_MOUNT_OPT_NOCOPYFROM) == 0) + seq_puts(m, ",copyfrom"); if (fsopt->mds_namespace) seq_show_option(m, "mds_namespace", fsopt->mds_namespace); diff --git a/fs/ceph/super.h b/fs/ceph/super.h index c005a5400f2e..79a265ba9200 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -42,7 +42,9 @@ #define CEPH_MOUNT_OPT_NOQUOTADF (1<<13) /* no root dir quota in statfs */ #define CEPH_MOUNT_OPT_NOCOPYFROM (1<<14) /* don't use RADOS 'copy-from' op */ -#define CEPH_MOUNT_OPT_DEFAULT CEPH_MOUNT_OPT_DCACHE +#define CEPH_MOUNT_OPT_DEFAULT \ + (CEPH_MOUNT_OPT_DCACHE | \ + CEPH_MOUNT_OPT_NOCOPYFROM) #define ceph_set_mount_opt(fsc, opt) \ (fsc)->mount_options->flags |= CEPH_MOUNT_OPT_##opt; diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index abcd78e332fe..85dadb93c992 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -133,7 +133,7 @@ config CIFS_XATTR config CIFS_POSIX bool "CIFS POSIX Extensions" - depends on CIFS_XATTR + depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY && CIFS_XATTR help Enabling this option will cause the cifs client to attempt to negotiate a newer dialect with servers, such as Samba 3.0.5 diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 3713d22b95a7..907e85d65bb4 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -174,7 +174,7 @@ cifs_bp_rename_retry: cifs_dbg(FYI, "using cifs_sb prepath <%s>\n", cifs_sb->prepath); memcpy(full_path+dfsplen+1, cifs_sb->prepath, pplen-1); - full_path[dfsplen] = '\\'; + full_path[dfsplen] = dirsep; for (i = 0; i < pplen-1; i++) if (full_path[dfsplen+1+i] == '/') full_path[dfsplen+1+i] = CIFS_DIR_SEP(cifs_sb); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 74c33d5fafc8..c9bc56b1baac 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2541,14 +2541,13 @@ static int cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, struct cifs_aio_ctx *ctx) { - int wait_retry = 0; unsigned int wsize, credits; int rc; struct TCP_Server_Info *server = tlink_tcon(wdata->cfile->tlink)->ses->server; /* - * Try to resend this wdata, waiting for credits up to 3 seconds. + * Wait for credits to resend this wdata. * Note: we are attempting to resend the whole wdata not in segments */ do { @@ -2556,19 +2555,13 @@ cifs_resend_wdata(struct cifs_writedata *wdata, struct list_head *wdata_list, server, wdata->bytes, &wsize, &credits); if (rc) - break; + goto out; if (wsize < wdata->bytes) { add_credits_and_wake_if(server, credits, 0); msleep(1000); - wait_retry++; } - } while (wsize < wdata->bytes && wait_retry < 3); - - if (wsize < wdata->bytes) { - rc = -EBUSY; - goto out; - } + } while (wsize < wdata->bytes); rc = -EAGAIN; while (rc == -EAGAIN) { @@ -3234,14 +3227,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata, struct list_head *rdata_list, struct cifs_aio_ctx *ctx) { - int wait_retry = 0; unsigned int rsize, credits; int rc; struct TCP_Server_Info *server = tlink_tcon(rdata->cfile->tlink)->ses->server; /* - * Try to resend this rdata, waiting for credits up to 3 seconds. + * Wait for credits to resend this rdata. * Note: we are attempting to resend the whole rdata not in segments */ do { @@ -3249,24 +3241,13 @@ static int cifs_resend_rdata(struct cifs_readdata *rdata, &rsize, &credits); if (rc) - break; + goto out; if (rsize < rdata->bytes) { add_credits_and_wake_if(server, credits, 0); msleep(1000); - wait_retry++; } - } while (rsize < rdata->bytes && wait_retry < 3); - - /* - * If we can't find enough credits to send this rdata - * release the rdata and return failure, this will pass - * whatever I/O amount we have finished to VFS. - */ - if (rsize < rdata->bytes) { - rc = -EBUSY; - goto out; - } + } while (rsize < rdata->bytes); rc = -EAGAIN; while (rc == -EAGAIN) { @@ -98,12 +98,6 @@ static void *dax_make_entry(pfn_t pfn, unsigned long flags) return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT)); } -static void *dax_make_page_entry(struct page *page) -{ - pfn_t pfn = page_to_pfn_t(page); - return dax_make_entry(pfn, PageHead(page) ? DAX_PMD : 0); -} - static bool dax_is_locked(void *entry) { return xa_to_value(entry) & DAX_LOCKED; @@ -116,12 +110,12 @@ static unsigned int dax_entry_order(void *entry) return 0; } -static int dax_is_pmd_entry(void *entry) +static unsigned long dax_is_pmd_entry(void *entry) { return xa_to_value(entry) & DAX_PMD; } -static int dax_is_pte_entry(void *entry) +static bool dax_is_pte_entry(void *entry) { return !(xa_to_value(entry) & DAX_PMD); } @@ -222,9 +216,8 @@ static void *get_unlocked_entry(struct xa_state *xas) ewait.wait.func = wake_exceptional_entry_func; for (;;) { - entry = xas_load(xas); - if (!entry || xa_is_internal(entry) || - WARN_ON_ONCE(!xa_is_value(entry)) || + entry = xas_find_conflict(xas); + if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) || !dax_is_locked(entry)) return entry; @@ -239,6 +232,34 @@ static void *get_unlocked_entry(struct xa_state *xas) } } +/* + * The only thing keeping the address space around is the i_pages lock + * (it's cycled in clear_inode() after removing the entries from i_pages) + * After we call xas_unlock_irq(), we cannot touch xas->xa. + */ +static void wait_entry_unlocked(struct xa_state *xas, void *entry) +{ + struct wait_exceptional_entry_queue ewait; + wait_queue_head_t *wq; + + init_wait(&ewait.wait); + ewait.wait.func = wake_exceptional_entry_func; + + wq = dax_entry_waitqueue(xas, entry, &ewait.key); + prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); + xas_unlock_irq(xas); + schedule(); + finish_wait(wq, &ewait.wait); + + /* + * Entry lock waits are exclusive. Wake up the next waiter since + * we aren't sure we will acquire the entry lock and thus wake + * the next waiter up on unlock. + */ + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &ewait.key); +} + static void put_unlocked_entry(struct xa_state *xas, void *entry) { /* If we were the only waiter woken, wake the next one */ @@ -255,6 +276,7 @@ static void dax_unlock_entry(struct xa_state *xas, void *entry) { void *old; + BUG_ON(dax_is_locked(entry)); xas_reset(xas); xas_lock_irq(xas); old = xas_store(xas, entry); @@ -352,16 +374,27 @@ static struct page *dax_busy_page(void *entry) return NULL; } -bool dax_lock_mapping_entry(struct page *page) +/* + * dax_lock_mapping_entry - Lock the DAX entry corresponding to a page + * @page: The page whose entry we want to lock + * + * Context: Process context. + * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could + * not be locked. + */ +dax_entry_t dax_lock_page(struct page *page) { XA_STATE(xas, NULL, 0); void *entry; + /* Ensure page->mapping isn't freed while we look at it */ + rcu_read_lock(); for (;;) { struct address_space *mapping = READ_ONCE(page->mapping); - if (!dax_mapping(mapping)) - return false; + entry = NULL; + if (!mapping || !dax_mapping(mapping)) + break; /* * In the device-dax case there's no need to lock, a @@ -370,8 +403,9 @@ bool dax_lock_mapping_entry(struct page *page) * otherwise we would not have a valid pfn_to_page() * translation. */ + entry = (void *)~0UL; if (S_ISCHR(mapping->host->i_mode)) - return true; + break; xas.xa = &mapping->i_pages; xas_lock_irq(&xas); @@ -382,20 +416,20 @@ bool dax_lock_mapping_entry(struct page *page) xas_set(&xas, page->index); entry = xas_load(&xas); if (dax_is_locked(entry)) { - entry = get_unlocked_entry(&xas); - /* Did the page move while we slept? */ - if (dax_to_pfn(entry) != page_to_pfn(page)) { - xas_unlock_irq(&xas); - continue; - } + rcu_read_unlock(); + wait_entry_unlocked(&xas, entry); + rcu_read_lock(); + continue; } dax_lock_entry(&xas, entry); xas_unlock_irq(&xas); - return true; + break; } + rcu_read_unlock(); + return (dax_entry_t)entry; } -void dax_unlock_mapping_entry(struct page *page) +void dax_unlock_page(struct page *page, dax_entry_t cookie) { struct address_space *mapping = page->mapping; XA_STATE(xas, &mapping->i_pages, page->index); @@ -403,7 +437,7 @@ void dax_unlock_mapping_entry(struct page *page) if (S_ISCHR(mapping->host->i_mode)) return; - dax_unlock_entry(&xas, dax_make_page_entry(page)); + dax_unlock_entry(&xas, (void *)cookie); } /* @@ -445,11 +479,9 @@ static void *grab_mapping_entry(struct xa_state *xas, retry: xas_lock_irq(xas); entry = get_unlocked_entry(xas); - if (xa_is_internal(entry)) - goto fallback; if (entry) { - if (WARN_ON_ONCE(!xa_is_value(entry))) { + if (!xa_is_value(entry)) { xas_set_err(xas, EIO); goto out_unlock; } @@ -1628,8 +1660,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order) /* Did we race with someone splitting entry or so? */ if (!entry || (order == 0 && !dax_is_pte_entry(entry)) || - (order == PMD_ORDER && (xa_is_internal(entry) || - !dax_is_pmd_entry(entry)))) { + (order == PMD_ORDER && !dax_is_pmd_entry(entry))) { put_unlocked_entry(&xas, entry); xas_unlock_irq(&xas); trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf, diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 645158dc33f1..c69927bed4ef 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -77,7 +77,7 @@ static bool dentry_connected(struct dentry *dentry) struct dentry *parent = dget_parent(dentry); dput(dentry); - if (IS_ROOT(dentry)) { + if (dentry == parent) { dput(parent); return false; } @@ -147,6 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + err = PTR_ERR(tmp); goto out_err; } if (tmp != dentry) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index cb91baa4275d..eb11502e3fcd 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -892,6 +892,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_magic != EXT2_SUPER_MAGIC) goto cantfind_ext2; + opts.s_mount_opt = 0; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); if (def_mount_opts & EXT2_DEFM_DEBUG) diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 62d9a659a8ff..dd8f10db82e9 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -612,9 +612,9 @@ skip_replace: } cleanup: - brelse(bh); if (!(bh && header == HDR(bh))) kfree(header); + brelse(bh); up_write(&EXT2_I(inode)->xattr_sem); return error; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 05f01fbd9c7f..22a9d8159720 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5835,9 +5835,10 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { + put_bh(iloc->bh); return -EIO; - + } if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 17adcb16a9c8..437f71fe83ae 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -126,6 +126,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || @@ -2811,7 +2812,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ebbc663d0798..a5efee34415f 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -459,16 +459,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", first_cluster, first_cluster - start, count2); ext4_set_bits(bh->b_data, first_cluster - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; @@ -605,7 +607,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -618,9 +619,9 @@ handle_bb: ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -635,18 +636,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -685,7 +684,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; @@ -873,6 +871,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); @@ -924,6 +923,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -939,8 +939,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } @@ -1124,8 +1122,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -2023,7 +2023,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) @@ -2059,6 +2059,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a221f1cdf704..53ff6c2a26ed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4075,6 +4075,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -4094,14 +4102,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); @@ -4510,6 +4510,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index f36fc5d5b257..7643d52c776c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1031,10 +1031,8 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, inode_lock(ea_inode); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); - if (ret) { - iloc.bh = NULL; + if (ret) goto out; - } ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; @@ -1080,12 +1078,10 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); - iloc.bh = NULL; if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: - brelse(iloc.bh); inode_unlock(ea_inode); return ret; } @@ -1388,6 +1384,12 @@ retry: bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); + if (!bh) { + WARN_ON_ONCE(1); + EXT4_ERROR_INODE(ea_inode, + "ext4_getblk() return bh = NULL"); + return -EFSCORRUPTED; + } ret = ext4_journal_get_write_access(handle, bh); if (ret) goto out; @@ -2276,8 +2278,10 @@ static struct buffer_head *ext4_xattr_get_block(struct inode *inode) if (!bh) return ERR_PTR(-EIO); error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); return ERR_PTR(error); + } return bh; } @@ -2397,6 +2401,8 @@ retry_inode: error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; @@ -2617,6 +2623,8 @@ out: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); @@ -2696,7 +2704,6 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; - struct buffer_head *bh; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; @@ -2737,13 +2744,17 @@ retry: * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { + struct buffer_head *bh; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); error = -EIO; if (!bh) goto cleanup; error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); goto cleanup; + } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 9edc920f651f..6d9cb1719de5 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -730,6 +730,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob if (awaken) wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) + wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); + /* Prevent a race with our last child, which has to signal EV_CLEARED * before dropping our spinlock. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index ae813e609932..a5e516a40e7a 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -165,9 +165,13 @@ static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) static void fuse_drop_waiting(struct fuse_conn *fc) { - if (fc->connected) { - atomic_dec(&fc->num_waiting); - } else if (atomic_dec_and_test(&fc->num_waiting)) { + /* + * lockess check of fc->connected is okay, because atomic_dec_and_test() + * provides a memory barrier mached with the one in fuse_wait_aborted() + * to ensure no wake-up is missed. + */ + if (atomic_dec_and_test(&fc->num_waiting) && + !READ_ONCE(fc->connected)) { /* wake up aborters */ wake_up_all(&fc->blocked_waitq); } @@ -1768,8 +1772,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.args[1].size = total_len; err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique); - if (err) + if (err) { fuse_retrieve_end(fc, req); + fuse_put_request(fc, req); + } return err; } @@ -2219,6 +2225,8 @@ EXPORT_SYMBOL_GPL(fuse_abort_conn); void fuse_wait_aborted(struct fuse_conn *fc) { + /* matches implicit memory barrier in fuse_drop_waiting() */ + smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 47395b0c3b35..e909678afa2d 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1119,8 +1119,10 @@ static int fuse_permission(struct inode *inode, int mask) if (fc->default_permissions || ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))) { struct fuse_inode *fi = get_fuse_inode(inode); + u32 perm_mask = STATX_MODE | STATX_UID | STATX_GID; - if (time_before64(fi->i_time, get_jiffies_64())) { + if (perm_mask & READ_ONCE(fi->inval_mask) || + time_before64(fi->i_time, get_jiffies_64())) { refreshed = true; err = fuse_perm_getattr(inode, mask); @@ -1241,7 +1243,7 @@ static int fuse_dir_open(struct inode *inode, struct file *file) static int fuse_dir_release(struct inode *inode, struct file *file) { - fuse_release_common(file, FUSE_RELEASEDIR); + fuse_release_common(file, true); return 0; } @@ -1249,7 +1251,25 @@ static int fuse_dir_release(struct inode *inode, struct file *file) static int fuse_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync) { - return fuse_fsync_common(file, start, end, datasync, 1); + struct inode *inode = file->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); + int err; + + if (is_bad_inode(inode)) + return -EIO; + + if (fc->no_fsyncdir) + return 0; + + inode_lock(inode); + err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNCDIR); + if (err == -ENOSYS) { + fc->no_fsyncdir = 1; + err = 0; + } + inode_unlock(inode); + + return err; } static long fuse_dir_ioctl(struct file *file, unsigned int cmd, diff --git a/fs/fuse/file.c b/fs/fuse/file.c index cc2121b37bf5..ffaffe18352a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -89,12 +89,12 @@ static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req) iput(req->misc.release.inode); } -static void fuse_file_put(struct fuse_file *ff, bool sync) +static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir) { if (refcount_dec_and_test(&ff->count)) { struct fuse_req *req = ff->reserved_req; - if (ff->fc->no_open) { + if (ff->fc->no_open && !isdir) { /* * Drop the release request when client does not * implement 'open' @@ -247,10 +247,11 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode) req->in.args[0].value = inarg; } -void fuse_release_common(struct file *file, int opcode) +void fuse_release_common(struct file *file, bool isdir) { struct fuse_file *ff = file->private_data; struct fuse_req *req = ff->reserved_req; + int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE; fuse_prepare_release(ff, file->f_flags, opcode); @@ -272,7 +273,7 @@ void fuse_release_common(struct file *file, int opcode) * synchronous RELEASE is allowed (and desirable) in this case * because the server can be trusted not to screw up. */ - fuse_file_put(ff, ff->fc->destroy_req != NULL); + fuse_file_put(ff, ff->fc->destroy_req != NULL, isdir); } static int fuse_open(struct inode *inode, struct file *file) @@ -288,7 +289,7 @@ static int fuse_release(struct inode *inode, struct file *file) if (fc->writeback_cache) write_inode_now(inode, 1); - fuse_release_common(file, FUSE_RELEASE); + fuse_release_common(file, false); /* return value is ignored by VFS */ return 0; @@ -302,7 +303,7 @@ void fuse_sync_release(struct fuse_file *ff, int flags) * iput(NULL) is a no-op and since the refcount is 1 and everything's * synchronous, we are fine with not doing igrab() here" */ - fuse_file_put(ff, true); + fuse_file_put(ff, true, false); } EXPORT_SYMBOL_GPL(fuse_sync_release); @@ -441,13 +442,30 @@ static int fuse_flush(struct file *file, fl_owner_t id) } int fuse_fsync_common(struct file *file, loff_t start, loff_t end, - int datasync, int isdir) + int datasync, int opcode) { struct inode *inode = file->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; FUSE_ARGS(args); struct fuse_fsync_in inarg; + + memset(&inarg, 0, sizeof(inarg)); + inarg.fh = ff->fh; + inarg.fsync_flags = datasync ? 1 : 0; + args.in.h.opcode = opcode; + args.in.h.nodeid = get_node_id(inode); + args.in.numargs = 1; + args.in.args[0].size = sizeof(inarg); + args.in.args[0].value = &inarg; + return fuse_simple_request(fc, &args); +} + +static int fuse_fsync(struct file *file, loff_t start, loff_t end, + int datasync) +{ + struct inode *inode = file->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); int err; if (is_bad_inode(inode)) @@ -479,34 +497,18 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, if (err) goto out; - if ((!isdir && fc->no_fsync) || (isdir && fc->no_fsyncdir)) + if (fc->no_fsync) goto out; - memset(&inarg, 0, sizeof(inarg)); - inarg.fh = ff->fh; - inarg.fsync_flags = datasync ? 1 : 0; - args.in.h.opcode = isdir ? FUSE_FSYNCDIR : FUSE_FSYNC; - args.in.h.nodeid = get_node_id(inode); - args.in.numargs = 1; - args.in.args[0].size = sizeof(inarg); - args.in.args[0].value = &inarg; - err = fuse_simple_request(fc, &args); + err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNC); if (err == -ENOSYS) { - if (isdir) - fc->no_fsyncdir = 1; - else - fc->no_fsync = 1; + fc->no_fsync = 1; err = 0; } out: inode_unlock(inode); - return err; -} -static int fuse_fsync(struct file *file, loff_t start, loff_t end, - int datasync) -{ - return fuse_fsync_common(file, start, end, datasync, 0); + return err; } void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos, @@ -807,7 +809,7 @@ static void fuse_readpages_end(struct fuse_conn *fc, struct fuse_req *req) put_page(page); } if (req->ff) - fuse_file_put(req->ff, false); + fuse_file_put(req->ff, false, false); } static void fuse_send_readpages(struct fuse_req *req, struct file *file) @@ -1460,7 +1462,7 @@ static void fuse_writepage_free(struct fuse_conn *fc, struct fuse_req *req) __free_page(req->pages[i]); if (req->ff) - fuse_file_put(req->ff, false); + fuse_file_put(req->ff, false, false); } static void fuse_writepage_finish(struct fuse_conn *fc, struct fuse_req *req) @@ -1619,7 +1621,7 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc) ff = __fuse_write_file_get(fc, fi); err = fuse_flush_times(inode, ff); if (ff) - fuse_file_put(ff, 0); + fuse_file_put(ff, false, false); return err; } @@ -1940,7 +1942,7 @@ static int fuse_writepages(struct address_space *mapping, err = 0; } if (data.ff) - fuse_file_put(data.ff, false); + fuse_file_put(data.ff, false, false); kfree(data.orig_pages); out: @@ -2924,10 +2926,12 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } if (io->async) { + bool blocking = io->blocking; + fuse_aio_complete(io, ret < 0 ? ret : 0, -1); /* we have a non-extending, async request, so return */ - if (!io->blocking) + if (!blocking) return -EIOCBQUEUED; wait_for_completion(&wait); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e9f712e81c7d..2f2c92e6f8cb 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -822,13 +822,13 @@ void fuse_sync_release(struct fuse_file *ff, int flags); /** * Send RELEASE or RELEASEDIR request */ -void fuse_release_common(struct file *file, int opcode); +void fuse_release_common(struct file *file, bool isdir); /** * Send FSYNC or FSYNCDIR request */ int fuse_fsync_common(struct file *file, loff_t start, loff_t end, - int datasync, int isdir); + int datasync, int opcode); /** * Notify poll wakeup diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 0b94b23b02d4..568abed20eb2 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -115,7 +115,7 @@ static void fuse_i_callback(struct rcu_head *head) static void fuse_destroy_inode(struct inode *inode) { struct fuse_inode *fi = get_fuse_inode(inode); - if (S_ISREG(inode->i_mode)) { + if (S_ISREG(inode->i_mode) && !is_bad_inode(inode)) { WARN_ON(!list_empty(&fi->write_files)); WARN_ON(!list_empty(&fi->queued_writes)); } @@ -1068,6 +1068,7 @@ void fuse_dev_free(struct fuse_dev *fud) fuse_conn_put(fc); } + kfree(fud->pq.processing); kfree(fud); } EXPORT_SYMBOL_GPL(fuse_dev_free); diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index a683d9b27d76..9a4a15d646eb 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -826,7 +826,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = gfs2_meta_inode_buffer(ip, &dibh); if (ret) goto unlock; - iomap->private = dibh; + mp->mp_bh[0] = dibh; if (gfs2_is_stuffed(ip)) { if (flags & IOMAP_WRITE) { @@ -863,9 +863,6 @@ unstuff: len = lblock_stop - lblock + 1; iomap->length = len << inode->i_blkbits; - get_bh(dibh); - mp->mp_bh[0] = dibh; - height = ip->i_height; while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height]) height++; @@ -898,8 +895,6 @@ out: iomap->bdev = inode->i_sb->s_bdev; unlock: up_read(&ip->i_rw_mutex); - if (ret && dibh) - brelse(dibh); return ret; do_alloc: @@ -980,9 +975,9 @@ static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos, static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, loff_t length, unsigned flags, - struct iomap *iomap) + struct iomap *iomap, + struct metapath *mp) { - struct metapath mp = { .mp_aheight = 1, }; struct gfs2_inode *ip = GFS2_I(inode); struct gfs2_sbd *sdp = GFS2_SB(inode); unsigned int data_blocks = 0, ind_blocks = 0, rblocks; @@ -996,9 +991,9 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, unstuff = gfs2_is_stuffed(ip) && pos + length > gfs2_max_stuffed_size(ip); - ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); + ret = gfs2_iomap_get(inode, pos, length, flags, iomap, mp); if (ret) - goto out_release; + goto out_unlock; alloc_required = unstuff || iomap->type == IOMAP_HOLE; @@ -1013,7 +1008,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_quota_lock_check(ip, &ap); if (ret) - goto out_release; + goto out_unlock; ret = gfs2_inplace_reserve(ip, &ap); if (ret) @@ -1038,17 +1033,15 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, ret = gfs2_unstuff_dinode(ip, NULL); if (ret) goto out_trans_end; - release_metapath(&mp); - brelse(iomap->private); - iomap->private = NULL; + release_metapath(mp); ret = gfs2_iomap_get(inode, iomap->offset, iomap->length, - flags, iomap, &mp); + flags, iomap, mp); if (ret) goto out_trans_end; } if (iomap->type == IOMAP_HOLE) { - ret = gfs2_iomap_alloc(inode, iomap, flags, &mp); + ret = gfs2_iomap_alloc(inode, iomap, flags, mp); if (ret) { gfs2_trans_end(sdp); gfs2_inplace_release(ip); @@ -1056,7 +1049,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos, goto out_qunlock; } } - release_metapath(&mp); if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip)) iomap->page_done = gfs2_iomap_journaled_page_done; return 0; @@ -1069,10 +1061,7 @@ out_trans_fail: out_qunlock: if (alloc_required) gfs2_quota_unlock(ip); -out_release: - if (iomap->private) - brelse(iomap->private); - release_metapath(&mp); +out_unlock: gfs2_write_unlock(inode); return ret; } @@ -1088,10 +1077,10 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, trace_gfs2_iomap_start(ip, pos, length, flags); if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) { - ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap); + ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp); } else { ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp); - release_metapath(&mp); + /* * Silently fall back to buffered I/O for stuffed files or if * we've hot a hole (see gfs2_file_direct_write). @@ -1100,6 +1089,11 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length, iomap->type != IOMAP_MAPPED) ret = -ENOTBLK; } + if (!ret) { + get_bh(mp.mp_bh[0]); + iomap->private = mp.mp_bh[0]; + } + release_metapath(&mp); trace_gfs2_iomap_end(ip, iomap, ret); return ret; } @@ -1908,10 +1902,16 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length) if (ret < 0) goto out; - /* issue read-ahead on metadata */ - if (mp.mp_aheight > 1) { - for (; ret > 1; ret--) { - metapointer_range(&mp, mp.mp_aheight - ret, + /* On the first pass, issue read-ahead on metadata. */ + if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) { + unsigned int height = mp.mp_aheight - 1; + + /* No read-ahead for data blocks. */ + if (mp.mp_aheight - 1 == strip_h) + height--; + + for (; height >= mp.mp_aheight - ret; height--) { + metapointer_range(&mp, height, start_list, start_aligned, end_list, end_aligned, &start, &end); diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index ffe3032b1043..b08a530433ad 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -733,6 +733,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp) if (gl) { glock_clear_object(gl, rgd); + gfs2_rgrp_brelse(rgd); gfs2_glock_put(gl); } @@ -1174,7 +1175,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd) * @rgd: the struct gfs2_rgrpd describing the RG to read in * * Read in all of a Resource Group's header and bitmap blocks. - * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps. + * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps. * * Returns: errno */ diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 98b96ffb95ed..19017d296173 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -338,13 +338,14 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 236efe51eca6..66774f4cb4fd 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -466,14 +466,15 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/inode.c b/fs/inode.c index 9e198f00b64c..35d2108d567c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,8 +730,11 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* recently referenced inodes get one more pass */ - if (inode->i_state & I_REFERENCED) { + /* + * Recently referenced inodes and inodes with many attached pages + * get one more pass. + */ + if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; diff --git a/fs/iomap.c b/fs/iomap.c index 64ce240217a1..5bc172f3dfe8 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + + /* + * migrate_page_move_mapping() assumes that pages with private data have + * their count elevated by 1. + */ + get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -132,6 +138,7 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); + put_page(page); kfree(iop); } @@ -142,13 +149,14 @@ static void iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp) { + loff_t orig_pos = *pos; + loff_t isize = i_size_read(inode); unsigned block_bits = inode->i_blkbits; unsigned block_size = (1 << block_bits); unsigned poff = offset_in_page(*pos); unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length); unsigned first = poff >> block_bits; unsigned last = (poff + plen - 1) >> block_bits; - unsigned end = offset_in_page(i_size_read(inode)) >> block_bits; /* * If the block size is smaller than the page size we need to check the @@ -183,8 +191,12 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop, * handle both halves separately so that we properly zero data in the * page cache for blocks that are entirely outside of i_size. */ - if (first <= end && last > end) - plen -= (last - end) * block_size; + if (orig_pos <= isize && orig_pos + length > isize) { + unsigned end = offset_in_page(isize - 1) >> block_bits; + + if (first <= end && last > end) + plen -= (last - end) * block_size; + } *offp = poff; *lenp = plen; @@ -1580,7 +1592,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, struct bio *bio; bool need_zeroout = false; bool use_fua = false; - int nr_pages, ret; + int nr_pages, ret = 0; size_t copied = 0; if ((pos | length | align) & ((1 << blkbits) - 1)) @@ -1596,12 +1608,13 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, if (iomap->flags & IOMAP_F_NEW) { need_zeroout = true; - } else { + } else if (iomap->type == IOMAP_MAPPED) { /* - * Use a FUA write if we need datasync semantics, this - * is a pure data IO that doesn't require any metadata - * updates and the underlying device supports FUA. This - * allows us to avoid cache flushes on IO completion. + * Use a FUA write if we need datasync semantics, this is a pure + * data IO that doesn't require any metadata updates (including + * after IO completion such as unwritten extent conversion) and + * the underlying device supports FUA. This allows us to avoid + * cache flushes on IO completion. */ if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) && (dio->flags & IOMAP_DIO_WRITE_FUA) && @@ -1644,8 +1657,14 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, ret = bio_iov_iter_get_pages(bio, &iter); if (unlikely(ret)) { + /* + * We have to stop part way through an IO. We must fall + * through to the sub-block tail zeroing here, otherwise + * this short IO may expose stale data in the tail of + * the block we haven't written data to. + */ bio_put(bio); - return copied ? copied : ret; + goto zero_tail; } n = bio->bi_iter.bi_size; @@ -1676,13 +1695,21 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, dio->submit.cookie = submit_bio(bio); } while (nr_pages); - if (need_zeroout) { + /* + * We need to zeroout the tail of a sub-block write if the extent type + * requires zeroing or the write extends beyond EOF. If we don't zero + * the block tail in the latter case, we can expose stale data via mmap + * reads of the EOF block. + */ +zero_tail: + if (need_zeroout || + ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { /* zero out from the end of the write to the end of the block */ pad = pos & (fs_block_size - 1); if (pad) iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); } - return copied; + return copied ? copied : ret; } static loff_t diff --git a/fs/namespace.c b/fs/namespace.c index 98d27da43304..a7f91265ea67 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -695,9 +695,6 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry) hlist_for_each_entry(mp, chain, m_hash) { if (mp->m_dentry == dentry) { - /* might be worth a WARN_ON() */ - if (d_unlinked(dentry)) - return ERR_PTR(-ENOENT); mp->m_count++; return mp; } @@ -711,6 +708,9 @@ static struct mountpoint *get_mountpoint(struct dentry *dentry) int ret; if (d_mountpoint(dentry)) { + /* might be worth a WARN_ON() */ + if (d_unlinked(dentry)) + return ERR_PTR(-ENOENT); mountpoint: read_seqlock_excl(&mount_lock); mp = lookup_mountpoint(dentry); @@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1728,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1782,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index fa515d5ea5ba..315967354954 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -66,7 +66,7 @@ __be32 nfs4_callback_getattr(void *argp, void *resp, out_iput: rcu_read_unlock(); trace_nfs4_cb_getattr(cps->clp, &args->fh, inode, -ntohl(res->status)); - iput(inode); + nfs_iput_and_deactive(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res->status)); return res->status; @@ -108,7 +108,7 @@ __be32 nfs4_callback_recall(void *argp, void *resp, } trace_nfs4_cb_recall(cps->clp, &args->fh, inode, &args->stateid, -ntohl(res)); - iput(inode); + nfs_iput_and_deactive(inode); out: dprintk("%s: exit with status = %d\n", __func__, ntohl(res)); return res; @@ -686,20 +686,24 @@ __be32 nfs4_callback_offload(void *data, void *dummy, { struct cb_offloadargs *args = data; struct nfs_server *server; - struct nfs4_copy_state *copy; + struct nfs4_copy_state *copy, *tmp_copy; bool found = false; + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + if (!copy) + return htonl(NFS4ERR_SERVERFAULT); + spin_lock(&cps->clp->cl_lock); rcu_read_lock(); list_for_each_entry_rcu(server, &cps->clp->cl_superblocks, client_link) { - list_for_each_entry(copy, &server->ss_copies, copies) { + list_for_each_entry(tmp_copy, &server->ss_copies, copies) { if (memcmp(args->coa_stateid.other, - copy->stateid.other, + tmp_copy->stateid.other, sizeof(args->coa_stateid.other))) continue; - nfs4_copy_cb_args(copy, args); - complete(©->completion); + nfs4_copy_cb_args(tmp_copy, args); + complete(&tmp_copy->completion); found = true; goto out; } @@ -707,15 +711,11 @@ __be32 nfs4_callback_offload(void *data, void *dummy, out: rcu_read_unlock(); if (!found) { - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); - if (!copy) { - spin_unlock(&cps->clp->cl_lock); - return htonl(NFS4ERR_SERVERFAULT); - } memcpy(©->stateid, &args->coa_stateid, NFS4_STATEID_SIZE); nfs4_copy_cb_args(copy, args); list_add_tail(©->copies, &cps->clp->pending_cb_stateids); - } + } else + kfree(copy); spin_unlock(&cps->clp->cl_lock); return 0; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 07b839560576..6ec2f78c1e19 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -850,16 +850,23 @@ nfs_delegation_find_inode_server(struct nfs_server *server, const struct nfs_fh *fhandle) { struct nfs_delegation *delegation; - struct inode *res = NULL; + struct inode *freeme, *res = NULL; list_for_each_entry_rcu(delegation, &server->delegations, super_list) { spin_lock(&delegation->lock); if (delegation->inode != NULL && nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { - res = igrab(delegation->inode); + freeme = igrab(delegation->inode); + if (freeme && nfs_sb_active(freeme->i_sb)) + res = freeme; spin_unlock(&delegation->lock); if (res != NULL) return res; + if (freeme) { + rcu_read_unlock(); + iput(freeme); + rcu_read_lock(); + } return ERR_PTR(-EAGAIN); } spin_unlock(&delegation->lock); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index aa12c3063bae..33824a0a57bf 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -98,8 +98,11 @@ struct nfs_direct_req { struct pnfs_ds_commit_info ds_cinfo; /* Storage for cinfo */ struct work_struct work; int flags; + /* for write */ #define NFS_ODIRECT_DO_COMMIT (1) /* an unstable reply was received */ #define NFS_ODIRECT_RESCHED_WRITES (2) /* write verification failed */ + /* for read */ +#define NFS_ODIRECT_SHOULD_DIRTY (3) /* dirty user-space page after read */ struct nfs_writeverf verf; /* unstable write verifier */ }; @@ -412,7 +415,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr) struct nfs_page *req = nfs_list_entry(hdr->pages.next); struct page *page = req->wb_page; - if (!PageCompound(page) && bytes < hdr->good_bytes) + if (!PageCompound(page) && bytes < hdr->good_bytes && + (dreq->flags == NFS_ODIRECT_SHOULD_DIRTY)) set_page_dirty(page); bytes += req->wb_bytes; nfs_list_remove_request(req); @@ -587,6 +591,9 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter) if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; + if (iter_is_iovec(iter)) + dreq->flags = NFS_ODIRECT_SHOULD_DIRTY; + nfs_start_io_direct(inode); NFS_I(inode)->read_io += count; diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 86bcba40ca61..310d7500f665 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1361,12 +1361,7 @@ static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data) task)) return; - if (ff_layout_read_prepare_common(task, hdr)) - return; - - if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, - hdr->args.lock_context, FMODE_READ) == -EIO) - rpc_exit(task, -EIO); /* lost lock, terminate I/O */ + ff_layout_read_prepare_common(task, hdr); } static void ff_layout_read_call_done(struct rpc_task *task, void *data) @@ -1542,12 +1537,7 @@ static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data) task)) return; - if (ff_layout_write_prepare_common(task, hdr)) - return; - - if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context, - hdr->args.lock_context, FMODE_WRITE) == -EIO) - rpc_exit(task, -EIO); /* lost lock, terminate I/O */ + ff_layout_write_prepare_common(task, hdr); } static void ff_layout_write_call_done(struct rpc_task *task, void *data) @@ -1742,6 +1732,11 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) fh = nfs4_ff_layout_select_ds_fh(lseg, idx); if (fh) hdr->args.fh = fh; + + if (vers == 4 && + !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid)) + goto out_failed; + /* * Note that if we ever decide to split across DSes, * then we may need to handle dense-like offsets. @@ -1804,6 +1799,10 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) if (fh) hdr->args.fh = fh; + if (vers == 4 && + !nfs4_ff_layout_select_ds_stateid(lseg, idx, &hdr->args.stateid)) + goto out_failed; + /* * Note that if we ever decide to split across DSes, * then we may need to handle dense-like offsets. diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h index 411798346e48..de50a342d5a5 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.h +++ b/fs/nfs/flexfilelayout/flexfilelayout.h @@ -215,6 +215,10 @@ unsigned int ff_layout_fetch_ds_ioerr(struct pnfs_layout_hdr *lo, unsigned int maxnum); struct nfs_fh * nfs4_ff_layout_select_ds_fh(struct pnfs_layout_segment *lseg, u32 mirror_idx); +int +nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg, + u32 mirror_idx, + nfs4_stateid *stateid); struct nfs4_pnfs_ds * nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 74d8d5352438..d23347389626 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -370,6 +370,25 @@ out: return fh; } +int +nfs4_ff_layout_select_ds_stateid(struct pnfs_layout_segment *lseg, + u32 mirror_idx, + nfs4_stateid *stateid) +{ + struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, mirror_idx); + + if (!ff_layout_mirror_valid(lseg, mirror, false)) { + pr_err_ratelimited("NFS: %s: No data server for mirror offset index %d\n", + __func__, mirror_idx); + goto out; + } + + nfs4_stateid_copy(stateid, &mirror->stateid); + return 1; +out: + return 0; +} + /** * nfs4_ff_layout_prepare_ds - prepare a DS connection for an RPC call * @lseg: the layout segment we're operating on diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index ac5b784a1de0..fed06fd9998d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -137,31 +137,32 @@ static int handle_async_copy(struct nfs42_copy_res *res, struct file *dst, nfs4_stateid *src_stateid) { - struct nfs4_copy_state *copy; + struct nfs4_copy_state *copy, *tmp_copy; int status = NFS4_OK; bool found_pending = false; struct nfs_open_context *ctx = nfs_file_open_context(dst); + copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); + if (!copy) + return -ENOMEM; + spin_lock(&server->nfs_client->cl_lock); - list_for_each_entry(copy, &server->nfs_client->pending_cb_stateids, + list_for_each_entry(tmp_copy, &server->nfs_client->pending_cb_stateids, copies) { - if (memcmp(&res->write_res.stateid, ©->stateid, + if (memcmp(&res->write_res.stateid, &tmp_copy->stateid, NFS4_STATEID_SIZE)) continue; found_pending = true; - list_del(©->copies); + list_del(&tmp_copy->copies); break; } if (found_pending) { spin_unlock(&server->nfs_client->cl_lock); + kfree(copy); + copy = tmp_copy; goto out; } - copy = kzalloc(sizeof(struct nfs4_copy_state), GFP_NOFS); - if (!copy) { - spin_unlock(&server->nfs_client->cl_lock); - return -ENOMEM; - } memcpy(©->stateid, &res->write_res.stateid, NFS4_STATEID_SIZE); init_completion(©->completion); copy->parent_state = ctx->state; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 8d59c9655ec4..1b994b527518 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -41,6 +41,8 @@ enum nfs4_client_state { NFS4CLNT_MOVED, NFS4CLNT_LEASE_MOVED, NFS4CLNT_DELEGATION_EXPIRED, + NFS4CLNT_RUN_MANAGER, + NFS4CLNT_DELEGRETURN_RUNNING, }; #define NFS4_RENEW_TIMEOUT 0x01 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 62ae0fd345ad..d8decf2ec48f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1210,6 +1210,7 @@ void nfs4_schedule_state_manager(struct nfs_client *clp) struct task_struct *task; char buf[INET6_ADDRSTRLEN + sizeof("-manager") + 1]; + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) return; __module_get(THIS_MODULE); @@ -2503,6 +2504,7 @@ static void nfs4_state_manager(struct nfs_client *clp) /* Ensure exclusive access to NFSv4 state */ do { + clear_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { section = "purge state"; status = nfs4_purge_lease(clp); @@ -2593,19 +2595,24 @@ static void nfs4_state_manager(struct nfs_client *clp) } nfs4_end_drain_session(clp); - if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { - nfs_client_return_marked_delegations(clp); - continue; + nfs4_clear_state_manager_bit(clp); + + if (!test_and_set_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state)) { + if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) { + nfs_client_return_marked_delegations(clp); + set_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state); + } + clear_bit(NFS4CLNT_DELEGRETURN_RUNNING, &clp->cl_state); } - nfs4_clear_state_manager_bit(clp); /* Did we race with an attempt to give us more work? */ - if (clp->cl_state == 0) - break; + if (!test_bit(NFS4CLNT_RUN_MANAGER, &clp->cl_state)) + return; if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0) - break; - } while (refcount_read(&clp->cl_count) > 1); - return; + return; + } while (refcount_read(&clp->cl_count) > 1 && !signalled()); + goto out_drain; + out_error: if (strlen(section)) section_sep = ": "; @@ -2613,6 +2620,7 @@ out_error: " with error %d\n", section_sep, section, clp->cl_hostname, -status); ssleep(1); +out_drain: nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index edff074d38c7..d505990dac7c 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1038,6 +1038,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { __be32 status; + if (!cstate->save_fh.fh_dentry) + return nfserr_nofilehandle; + status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); if (status) { diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index de99db518571..f2129a5d9f23 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -266,9 +266,7 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, return; if (nbh == NULL) { /* blocksize == pagesize */ - xa_lock_irq(&btnc->i_pages); - __xa_erase(&btnc->i_pages, newkey); - xa_unlock_irq(&btnc->i_pages); + xa_erase_irq(&btnc->i_pages, newkey); unlock_page(ctxt->bh->b_page); } else brelse(nbh); diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 5769cf3ff035..e08a6647267b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -115,12 +115,12 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info, continue; mark = iter_info->marks[type]; /* - * if the event is for a child and this inode doesn't care about - * events on the child, don't send it! + * If the event is for a child and this mark doesn't care about + * events on a child, don't send it! */ - if (type == FSNOTIFY_OBJ_TYPE_INODE && - (event_mask & FS_EVENT_ON_CHILD) && - !(mark->mask & FS_EVENT_ON_CHILD)) + if (event_mask & FS_EVENT_ON_CHILD && + (type != FSNOTIFY_OBJ_TYPE_INODE || + !(mark->mask & FS_EVENT_ON_CHILD))) continue; marks_mask |= mark->mask; diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 2172ba516c61..d2c34900ae05 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -167,9 +167,9 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask parent = dget_parent(dentry); p_inode = parent->d_inode; - if (unlikely(!fsnotify_inode_watches_children(p_inode))) + if (unlikely(!fsnotify_inode_watches_children(p_inode))) { __fsnotify_update_child_dentry_flags(p_inode); - else if (p_inode->i_fsnotify_mask & mask) { + } else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) { struct name_snapshot name; /* we are notifying a parent so come up with the new mask which @@ -339,6 +339,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, sb = mnt->mnt.mnt_sb; mnt_or_sb_mask = mnt->mnt_fsnotify_mask | sb->s_fsnotify_mask; } + /* An event "on child" is not intended for a mount/sb mark */ + if (mask & FS_EVENT_ON_CHILD) + mnt_or_sb_mask = 0; /* * Optimization: srcu_read_lock() has a memory barrier which can diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index da578ad4c08f..eb1ce30412dc 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2411,8 +2411,16 @@ static int ocfs2_dio_end_io(struct kiocb *iocb, /* this io's submitter should not have unlocked this before we could */ BUG_ON(!ocfs2_iocb_is_rw_locked(iocb)); - if (bytes > 0 && private) - ret = ocfs2_dio_end_io_write(inode, private, offset, bytes); + if (bytes <= 0) + mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld", + (long long)bytes); + if (private) { + if (bytes > 0) + ret = ocfs2_dio_end_io_write(inode, private, offset, + bytes); + else + ocfs2_dio_free_write_ctx(inode, private); + } ocfs2_iocb_clear_rw_locked(iocb); diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h index 308ea0eb35fd..a396096a5099 100644 --- a/fs/ocfs2/cluster/masklog.h +++ b/fs/ocfs2/cluster/masklog.h @@ -178,6 +178,15 @@ do { \ ##__VA_ARGS__); \ } while (0) +#define mlog_ratelimited(mask, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(_rs, \ + DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + if (__ratelimit(&_rs)) \ + mlog(mask, fmt, ##__VA_ARGS__); \ +} while (0) + #define mlog_errno(st) ({ \ int _st = (st); \ if (_st != -ERESTARTSYS && _st != -EINTR && \ diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 9f88188060db..4bf8d5854b27 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -125,10 +125,10 @@ check_err: check_gen: if (handle->ih_generation != inode->i_generation) { - iput(inode); trace_ocfs2_get_dentry_generation((unsigned long long)blkno, handle->ih_generation, inode->i_generation); + iput(inode); result = ERR_PTR(-ESTALE); goto bail; } diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 3f1685d7d43b..1565dd8e8856 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -157,18 +157,14 @@ out: } /* - * lock allocators, and reserving appropriate number of bits for - * meta blocks and data clusters. - * - * in some cases, we don't need to reserve clusters, just let data_ac - * be NULL. + * lock allocator, and reserve appropriate number of bits for + * meta blocks. */ -static int ocfs2_lock_allocators_move_extents(struct inode *inode, +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode, struct ocfs2_extent_tree *et, u32 clusters_to_move, u32 extents_to_split, struct ocfs2_alloc_context **meta_ac, - struct ocfs2_alloc_context **data_ac, int extra_blocks, int *credits) { @@ -193,13 +189,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, goto out; } - if (data_ac) { - ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac); - if (ret) { - mlog_errno(ret); - goto out; - } - } *credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el); @@ -259,10 +248,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1, - &context->meta_ac, - &context->data_ac, - extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + *len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; @@ -285,6 +274,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } + /* + * Make sure ocfs2_reserve_cluster is called after + * __ocfs2_flush_truncate_log, otherwise, dead lock may happen. + * + * If ocfs2_reserve_cluster is called + * before __ocfs2_flush_truncate_log, dead lock on global bitmap + * may happen. + * + */ + ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac); + if (ret) { + mlog_errno(ret); + goto out_unlock_mutex; + } + handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -617,9 +621,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1, - &context->meta_ac, - NULL, extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index c6289147c787..82c129bfe58d 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -651,6 +651,18 @@ static int ovl_symlink(struct inode *dir, struct dentry *dentry, return ovl_create_object(dentry, S_IFLNK, 0, link); } +static int ovl_set_link_redirect(struct dentry *dentry) +{ + const struct cred *old_cred; + int err; + + old_cred = ovl_override_creds(dentry->d_sb); + err = ovl_set_redirect(dentry, false); + revert_creds(old_cred); + + return err; +} + static int ovl_link(struct dentry *old, struct inode *newdir, struct dentry *new) { @@ -670,7 +682,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir, goto out_drop_write; if (ovl_is_metacopy_dentry(old)) { - err = ovl_set_redirect(old, false); + err = ovl_set_link_redirect(old); if (err) goto out_drop_write; } diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c index 8fa37cd7818a..54e5d17d7f3e 100644 --- a/fs/overlayfs/export.c +++ b/fs/overlayfs/export.c @@ -754,9 +754,8 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb, goto out; } - /* Otherwise, get a connected non-upper dir or disconnected non-dir */ - if (d_is_dir(origin.dentry) && - (origin.dentry->d_flags & DCACHE_DISCONNECTED)) { + /* Find origin.dentry again with ovl_acceptable() layer check */ + if (d_is_dir(origin.dentry)) { dput(origin.dentry); origin.dentry = NULL; err = ovl_check_origin_fh(ofs, fh, true, NULL, &stack); @@ -769,6 +768,7 @@ static struct dentry *ovl_lower_fh_to_d(struct super_block *sb, goto out_err; } + /* Get a connected non-upper dir or disconnected non-dir */ dentry = ovl_get_dentry(sb, NULL, &origin, index); out: diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 6bcc9dedc342..3b7ed5d2279c 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -286,22 +286,13 @@ int ovl_permission(struct inode *inode, int mask) if (err) return err; - /* No need to do any access on underlying for special files */ - if (special_file(realinode->i_mode)) - return 0; - - /* No need to access underlying for execute */ - mask &= ~MAY_EXEC; - if ((mask & (MAY_READ | MAY_WRITE)) == 0) - return 0; - - /* Lower files get copied up, so turn write access into read */ - if (!upperinode && mask & MAY_WRITE) { + old_cred = ovl_override_creds(inode->i_sb); + if (!upperinode && + !special_file(realinode->i_mode) && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); + /* Make sure mounter can read file for copy up later */ mask |= MAY_READ; } - - old_cred = ovl_override_creds(inode->i_sb); err = inode_permission(realinode, mask); revert_creds(old_cred); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index ffcff6516e89..e02a9039b5ea 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -816,17 +816,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we - * have to handle dumps, we must have at least record_size buffer. And - * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be - * ZERO_SIZE_PTR). + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). */ - if (cxt->console_size) - cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */ - cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize); - cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore buffer\n"); + pr_err("cannot allocate pstore crash dump buffer\n"); err = -ENOMEM; goto fail_clear; } diff --git a/fs/read_write.c b/fs/read_write.c index bfcb4ced5664..58f30537c47a 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1956,7 +1956,7 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct inode *inode_out = file_inode(file_out); loff_t ret; - WARN_ON_ONCE(remap_flags); + WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP); if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; @@ -2094,17 +2094,18 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) off = same->src_offset; len = same->src_length; - ret = -EISDIR; if (S_ISDIR(src->i_mode)) - goto out; + return -EISDIR; - ret = -EINVAL; if (!S_ISREG(src->i_mode)) - goto out; + return -EINVAL; + + if (!file->f_op->remap_file_range) + return -EOPNOTSUPP; ret = remap_verify_area(file, off, len, false); if (ret < 0) - goto out; + return ret; ret = 0; if (off + len > i_size_read(src)) @@ -2147,10 +2148,8 @@ next_fdput: fdput(dst_fd); next_loop: if (fatal_signal_pending(current)) - goto out; + break; } - -out: return ret; } EXPORT_SYMBOL(vfs_dedupe_file_range); diff --git a/fs/splice.c b/fs/splice.c index 3553f1956508..de2ede048473 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -945,11 +945,16 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd, sd->flags &= ~SPLICE_F_NONBLOCK; more = sd->flags & SPLICE_F_MORE; + WARN_ON_ONCE(pipe->nrbufs != 0); + while (len) { size_t read_len; loff_t pos = sd->pos, prev_pos = pos; - ret = do_splice_to(in, &pos, pipe, len, flags); + /* Don't try to read more the pipe has space for. */ + read_len = min_t(size_t, len, + (pipe->buffers - pipe->nrbufs) << PAGE_SHIFT); + ret = do_splice_to(in, &pos, pipe, read_len, flags); if (unlikely(ret <= 0)) goto out_release; diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 499a20a5a010..273736f41be3 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait) } } brelse(bh); - return 0; + return err; } int sysv_write_inode(struct inode *inode, struct writeback_control *wbc) diff --git a/fs/udf/super.c b/fs/udf/super.c index 8f2f56d9a1bb..e3d684ea3203 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -827,16 +827,20 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) ret = udf_dstrCS0toChar(sb, outstr, 31, pvoldesc->volIdent, 32); - if (ret < 0) - goto out_bh; - - strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); + if (ret < 0) { + strcpy(UDF_SB(sb)->s_volume_ident, "InvalidName"); + pr_warn("incorrect volume identification, setting to " + "'InvalidName'\n"); + } else { + strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); + } udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident); ret = udf_dstrCS0toChar(sb, outstr, 127, pvoldesc->volSetIdent, 128); - if (ret < 0) + if (ret < 0) { + ret = 0; goto out_bh; - + } outstr[ret] = 0; udf_debug("volSetIdent[] = '%s'\n", outstr); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 45234791fec2..5fcfa96463eb 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -351,6 +351,11 @@ try_again: return u_len; } +/* + * Convert CS0 dstring to output charset. Warning: This function may truncate + * input string if it is too long as it is used for informational strings only + * and it is better to truncate the string than to refuse mounting a media. + */ int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len) { @@ -359,9 +364,12 @@ int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len, if (i_len > 0) { s_len = ocu_i[i_len - 1]; if (s_len >= i_len) { - pr_err("incorrect dstring lengths (%d/%d)\n", - s_len, i_len); - return -EINVAL; + pr_warn("incorrect dstring lengths (%d/%d)," + " truncating\n", s_len, i_len); + s_len = i_len - 1; + /* 2-byte encoding? Need to round properly... */ + if (ocu_i[0] == 16) + s_len -= (s_len - 1) & 2; } } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 356d2b8568c1..7a85e609fc27 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1361,6 +1361,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, ret = -EINVAL; if (!vma_can_userfault(cur)) goto out_unlock; + + /* + * UFFDIO_COPY will fill file holes even without + * PROT_WRITE. This check enforces that if this is a + * MAP_SHARED, the process has write permission to the backing + * file. If VM_MAYWRITE is set it also enforces that on a + * MAP_SHARED vma: there is no F_WRITE_SEAL and no further + * F_WRITE_SEAL can be taken until the vma is destroyed. + */ + ret = -EPERM; + if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) + goto out_unlock; + /* * If this vma contains ending address, and huge pages * check alignment. @@ -1406,6 +1419,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, BUG_ON(!vma_can_userfault(vma)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this @@ -1560,6 +1574,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, if (!vma->vm_userfaultfd_ctx.ctx) goto skip; + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); + if (vma->vm_start > start) start = vma->vm_start; vma_end = min(end, vma->vm_end); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 74d7228e755b..19e921d1586f 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1694,10 +1694,13 @@ xfs_bmap_add_extent_delay_real( case BMAP_LEFT_FILLING | BMAP_RIGHT_FILLING | BMAP_RIGHT_CONTIG: /* * Filling in all of a previously delayed allocation extent. - * The right neighbor is contiguous, the left is not. + * The right neighbor is contiguous, the left is not. Take care + * with delay -> unwritten extent allocation here because the + * delalloc record we are overwriting is always written. */ PREV.br_startblock = new->br_startblock; PREV.br_blockcount += RIGHT.br_blockcount; + PREV.br_state = new->br_state; xfs_iext_next(ifp, &bma->icur); xfs_iext_remove(bma->ip, &bma->icur, state); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 34c6d7bd4d18..bbdae2b4559f 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -330,7 +330,7 @@ xfs_btree_sblock_verify_crc( if (xfs_sb_version_hascrc(&mp->m_sb)) { if (!xfs_log_check_lsn(mp, be64_to_cpu(block->bb_u.s.bb_lsn))) - return __this_address; + return false; return xfs_buf_verify_cksum(bp, XFS_BTREE_SBLOCK_CRC_OFF); } diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c index 86c50208a143..7fbf8af0b159 100644 --- a/fs/xfs/libxfs/xfs_ialloc_btree.c +++ b/fs/xfs/libxfs/xfs_ialloc_btree.c @@ -538,15 +538,18 @@ xfs_inobt_rec_check_count( static xfs_extlen_t xfs_inobt_max_size( - struct xfs_mount *mp) + struct xfs_mount *mp, + xfs_agnumber_t agno) { + xfs_agblock_t agblocks = xfs_ag_block_count(mp, agno); + /* Bail out if we're uninitialized, which can happen in mkfs. */ if (mp->m_inobt_mxr[0] == 0) return 0; return xfs_btree_calc_size(mp->m_inobt_mnr, - (uint64_t)mp->m_sb.sb_agblocks * mp->m_sb.sb_inopblock / - XFS_INODES_PER_CHUNK); + (uint64_t)agblocks * mp->m_sb.sb_inopblock / + XFS_INODES_PER_CHUNK); } static int @@ -594,7 +597,7 @@ xfs_finobt_calc_reserves( if (error) return error; - *ask += xfs_inobt_max_size(mp); + *ask += xfs_inobt_max_size(mp, agno); *used += tree_len; return 0; } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 5d263dfdb3bc..1ee8c5539fa4 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1042,7 +1042,7 @@ out_trans_cancel: goto out_unlock; } -static int +int xfs_flush_unmap_range( struct xfs_inode *ip, xfs_off_t offset, @@ -1126,9 +1126,9 @@ xfs_free_file_space( * page could be mmap'd and iomap_zero_range doesn't do that for us. * Writeback of the eof page will do this, albeit clumsily. */ - if (offset + len >= XFS_ISIZE(ip) && ((offset + len) & PAGE_MASK)) { + if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) { error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - (offset + len) & ~PAGE_MASK, LLONG_MAX); + round_down(offset + len, PAGE_SIZE), LLONG_MAX); } return error; @@ -1195,13 +1195,7 @@ xfs_prepare_shift( * Writeback and invalidate cache for the remainder of the file as we're * about to shift down every extent from offset to EOF. */ - error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, offset, -1); - if (error) - return error; - error = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, - offset >> PAGE_SHIFT, -1); - if (error) - return error; + error = xfs_flush_unmap_range(ip, offset, XFS_ISIZE(ip)); /* * Clean out anything hanging around in the cow fork now that diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 87363d136bb6..7a78229cf1a7 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -80,4 +80,7 @@ int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip, int whichfork, xfs_extnum_t *nextents, xfs_filblks_t *count); +int xfs_flush_unmap_range(struct xfs_inode *ip, xfs_off_t offset, + xfs_off_t len); + #endif /* __XFS_BMAP_UTIL_H__ */ diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 12d8455bfbb2..010db5f8fb00 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1233,9 +1233,23 @@ xfs_buf_iodone( } /* - * Requeue a failed buffer for writeback + * Requeue a failed buffer for writeback. * - * Return true if the buffer has been re-queued properly, false otherwise + * We clear the log item failed state here as well, but we have to be careful + * about reference counts because the only active reference counts on the buffer + * may be the failed log items. Hence if we clear the log item failed state + * before queuing the buffer for IO we can release all active references to + * the buffer and free it, leading to use after free problems in + * xfs_buf_delwri_queue. It makes no difference to the buffer or log items which + * order we process them in - the buffer is locked, and we own the buffer list + * so nothing on them is going to change while we are performing this action. + * + * Hence we can safely queue the buffer for IO before we clear the failed log + * item state, therefore always having an active reference to the buffer and + * avoiding the transient zero-reference state that leads to use-after-free. + * + * Return true if the buffer was added to the buffer list, false if it was + * already on the buffer list. */ bool xfs_buf_resubmit_failed_buffers( @@ -1243,16 +1257,16 @@ xfs_buf_resubmit_failed_buffers( struct list_head *buffer_list) { struct xfs_log_item *lip; + bool ret; + + ret = xfs_buf_delwri_queue(bp, buffer_list); /* - * Clear XFS_LI_FAILED flag from all items before resubmit - * - * XFS_LI_FAILED set/clear is protected by ail_lock, caller this + * XFS_LI_FAILED set/clear is protected by ail_lock, caller of this * function already have it acquired */ list_for_each_entry(lip, &bp->b_li_list, li_bio_list) xfs_clear_li_failed(lip); - /* Add this buffer back to the delayed write list */ - return xfs_buf_delwri_queue(bp, buffer_list); + return ret; } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 53c9ab8fb777..e47425071e65 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -920,7 +920,7 @@ out_unlock: } -loff_t +STATIC loff_t xfs_file_remap_range( struct file *file_in, loff_t pos_in, diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 73a1d77ec187..3091e4bc04ef 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -40,7 +40,7 @@ xfs_fill_statvfs_from_dquot( statp->f_files = limit; statp->f_ffree = (statp->f_files > dqp->q_res_icount) ? - (statp->f_ffree - dqp->q_res_icount) : 0; + (statp->f_files - dqp->q_res_icount) : 0; } } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index ecdb086bc23e..322a852ce284 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -296,6 +296,7 @@ xfs_reflink_reserve_cow( if (error) return error; + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); trace_xfs_reflink_cow_alloc(ip, &got); return 0; } @@ -1351,10 +1352,19 @@ xfs_reflink_remap_prep( if (ret) goto out_unlock; - /* Zap any page cache for the destination file's range. */ - truncate_inode_pages_range(&inode_out->i_data, - round_down(pos_out, PAGE_SIZE), - round_up(pos_out + *len, PAGE_SIZE) - 1); + /* + * If pos_out > EOF, we may have dirtied blocks between EOF and + * pos_out. In that case, we need to extend the flush and unmap to cover + * from EOF to the end of the copy length. + */ + if (pos_out > XFS_ISIZE(dest)) { + loff_t flen = *len + (pos_out - XFS_ISIZE(dest)); + ret = xfs_flush_unmap_range(dest, XFS_ISIZE(dest), flen); + } else { + ret = xfs_flush_unmap_range(dest, pos_out, *len); + } + if (ret) + goto out_unlock; return 1; out_unlock: diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 3043e5ed6495..8a6532aae779 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -280,7 +280,10 @@ DECLARE_EVENT_CLASS(xfs_buf_class, ), TP_fast_assign( __entry->dev = bp->b_target->bt_dev; - __entry->bno = bp->b_bn; + if (bp->b_bn == XFS_BUF_DADDR_NULL) + __entry->bno = bp->b_maps[0].bm_bn; + else + __entry->bno = bp->b_bn; __entry->nblks = bp->b_length; __entry->hold = atomic_read(&bp->b_hold); __entry->pincount = atomic_read(&bp->b_pin_count); |