diff options
Diffstat (limited to 'fs')
47 files changed, 572 insertions, 298 deletions
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index b177fd3b1eb3..be5768949cb1 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -655,6 +655,8 @@ const struct file_operations v9fs_cached_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -667,6 +669,8 @@ const struct file_operations v9fs_cached_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -678,6 +682,8 @@ const struct file_operations v9fs_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -690,6 +696,8 @@ const struct file_operations v9fs_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = generic_file_readonly_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; @@ -701,6 +709,8 @@ const struct file_operations v9fs_mmap_file_operations = { .release = v9fs_dir_release, .lock = v9fs_file_lock, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync, }; @@ -713,5 +723,7 @@ const struct file_operations v9fs_mmap_file_operations_dotl = { .lock = v9fs_file_lock_dotl, .flock = v9fs_file_flock_dotl, .mmap = v9fs_mmap_file_mmap, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, .fsync = v9fs_file_fsync_dotl, }; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 1bb5b9d7f0a2..9068d5578a26 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -823,6 +823,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry, vp->cb_break_before = afs_calc_vnode_cb_break(vnode); vp->vnode = vnode; vp->put_vnode = true; + vp->speculative = true; /* vnode not locked */ } } } diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 0fe8844b4bee..b0d7b892090d 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -294,6 +294,13 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v op->flags &= ~AFS_OPERATION_DIR_CONFLICT; } } else if (vp->scb.have_status) { + if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version && + vp->speculative) + /* Ignore the result of a speculative bulk status fetch + * if it splits around a modification op, thereby + * appearing to regress the data version. + */ + goto out; afs_apply_status(op, vp); if (vp->scb.have_cb) afs_apply_callback(op, vp); @@ -305,6 +312,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v } } +out: write_sequnlock(&vnode->cb_lock); if (vp->scb.have_status) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 14d5d75f4b6e..0d150a29e39e 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -755,6 +755,7 @@ struct afs_vnode_param { bool update_ctime:1; /* Need to update the ctime */ bool set_size:1; /* Must update i_size */ bool op_unlinked:1; /* True if file was unlinked by op */ + bool speculative:1; /* T if speculative status fetch (no vnode lock) */ }; /* diff --git a/fs/afs/write.c b/fs/afs/write.c index 50371207f327..c9195fc67fd8 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -169,11 +169,14 @@ int afs_write_end(struct file *file, struct address_space *mapping, unsigned int f, from = pos & (PAGE_SIZE - 1); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; - int ret; + int ret = 0; _enter("{%llx:%llu},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + if (copied == 0) + goto out; + maybe_i_size = pos + copied; i_size = i_size_read(&vnode->vfs_inode); @@ -1572,7 +1572,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { - __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); + sb_start_write(file_inode(file)->i_sb); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0378933d163c..0b29bdb25105 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -878,7 +878,10 @@ struct btrfs_fs_info { */ struct ulist *qgroup_ulist; - /* protect user change for quota operations */ + /* + * Protect user change for quota operations. If a transaction is needed, + * it must be started before locking this lock. + */ struct mutex qgroup_ioctl_lock; /* list of dirty qgroups to be written at next commit */ diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 87355a38a654..4373da7bcc0d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -452,46 +452,6 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages) } } -static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, - const u64 start, - const u64 len, - struct extent_state **cached_state) -{ - u64 search_start = start; - const u64 end = start + len - 1; - - while (search_start < end) { - const u64 search_len = end - search_start + 1; - struct extent_map *em; - u64 em_len; - int ret = 0; - - em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); - if (IS_ERR(em)) - return PTR_ERR(em); - - if (em->block_start != EXTENT_MAP_HOLE) - goto next; - - em_len = em->len; - if (em->start < search_start) - em_len -= search_start - em->start; - if (em_len > search_len) - em_len = search_len; - - ret = set_extent_bit(&inode->io_tree, search_start, - search_start + em_len - 1, - EXTENT_DELALLOC_NEW, - NULL, cached_state, GFP_NOFS); -next: - search_start = extent_map_end(em); - free_extent_map(em); - if (ret) - return ret; - } - return 0; -} - /* * after copy_from_user, pages need to be dirtied and we need to make * sure holes are created between the current EOF and the start of @@ -528,23 +488,6 @@ int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages, EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached); - if (!btrfs_is_free_space_inode(inode)) { - if (start_pos >= isize && - !(inode->flags & BTRFS_INODE_PREALLOC)) { - /* - * There can't be any extents following eof in this case - * so just set the delalloc new bit for the range - * directly. - */ - extra_bits |= EXTENT_DELALLOC_NEW; - } else { - err = btrfs_find_new_delalloc_bytes(inode, start_pos, - num_bytes, cached); - if (err) - return err; - } - } - err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block, extra_bits, cached); if (err) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index da58c58ef9aa..7e8d8169779d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2253,11 +2253,69 @@ static int add_pending_csums(struct btrfs_trans_handle *trans, return 0; } +static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode, + const u64 start, + const u64 len, + struct extent_state **cached_state) +{ + u64 search_start = start; + const u64 end = start + len - 1; + + while (search_start < end) { + const u64 search_len = end - search_start + 1; + struct extent_map *em; + u64 em_len; + int ret = 0; + + em = btrfs_get_extent(inode, NULL, 0, search_start, search_len); + if (IS_ERR(em)) + return PTR_ERR(em); + + if (em->block_start != EXTENT_MAP_HOLE) + goto next; + + em_len = em->len; + if (em->start < search_start) + em_len -= search_start - em->start; + if (em_len > search_len) + em_len = search_len; + + ret = set_extent_bit(&inode->io_tree, search_start, + search_start + em_len - 1, + EXTENT_DELALLOC_NEW, + NULL, cached_state, GFP_NOFS); +next: + search_start = extent_map_end(em); + free_extent_map(em); + if (ret) + return ret; + } + return 0; +} + int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state) { WARN_ON(PAGE_ALIGNED(end)); + + if (start >= i_size_read(&inode->vfs_inode) && + !(inode->flags & BTRFS_INODE_PREALLOC)) { + /* + * There can't be any extents following eof in this case so just + * set the delalloc new bit for the range directly. + */ + extra_bits |= EXTENT_DELALLOC_NEW; + } else { + int ret; + + ret = btrfs_find_new_delalloc_bytes(inode, start, + end + 1 - start, + cached_state); + if (ret) + return ret; + } + return set_extent_delalloc(&inode->io_tree, start, end, extra_bits, cached_state); } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 77c54749f432..87bd37b70738 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/workqueue.h> #include <linux/btrfs.h> +#include <linux/sched/mm.h> #include "ctree.h" #include "transaction.h" @@ -497,13 +498,13 @@ next2: break; } out: + btrfs_free_path(path); fs_info->qgroup_flags |= flags; if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)) clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN && ret >= 0) ret = qgroup_rescan_init(fs_info, rescan_progress, 0); - btrfs_free_path(path); if (ret < 0) { ulist_free(fs_info->qgroup_ulist); @@ -936,6 +937,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) struct btrfs_key found_key; struct btrfs_qgroup *qgroup = NULL; struct btrfs_trans_handle *trans = NULL; + struct ulist *ulist = NULL; int ret = 0; int slot; @@ -943,8 +945,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) if (fs_info->quota_root) goto out; - fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL); - if (!fs_info->qgroup_ulist) { + ulist = ulist_alloc(GFP_KERNEL); + if (!ulist) { ret = -ENOMEM; goto out; } @@ -952,6 +954,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) ret = btrfs_sysfs_add_qgroups(fs_info); if (ret < 0) goto out; + + /* + * Unlock qgroup_ioctl_lock before starting the transaction. This is to + * avoid lock acquisition inversion problems (reported by lockdep) between + * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we + * start a transaction. + * After we started the transaction lock qgroup_ioctl_lock again and + * check if someone else created the quota root in the meanwhile. If so, + * just return success and release the transaction handle. + * + * Also we don't need to worry about someone else calling + * btrfs_sysfs_add_qgroups() after we unlock and getting an error because + * that function returns 0 (success) when the sysfs entries already exist. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + /* * 1 for quota root item * 1 for BTRFS_QGROUP_STATUS item @@ -961,12 +979,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info) * would be a lot of overkill. */ trans = btrfs_start_transaction(tree_root, 2); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); trans = NULL; goto out; } + if (fs_info->quota_root) + goto out; + + fs_info->qgroup_ulist = ulist; + ulist = NULL; + /* * initially create the quota tree */ @@ -1124,11 +1150,14 @@ out: if (ret) { ulist_free(fs_info->qgroup_ulist); fs_info->qgroup_ulist = NULL; - if (trans) - btrfs_end_transaction(trans); btrfs_sysfs_del_qgroups(fs_info); } mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + ulist_free(ulist); return ret; } @@ -1141,19 +1170,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) goto out; + mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item * * We should also reserve enough items for the quota tree deletion in * btrfs_clean_quota_tree but this is not done. + * + * Also, we must always start a transaction without holding the mutex + * qgroup_ioctl_lock, see btrfs_quota_enable(). */ trans = btrfs_start_transaction(fs_info->tree_root, 1); + + mutex_lock(&fs_info->qgroup_ioctl_lock); if (IS_ERR(trans)) { ret = PTR_ERR(trans); + trans = NULL; goto out; } + if (!fs_info->quota_root) + goto out; + clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); @@ -1167,13 +1206,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) ret = btrfs_clean_quota_tree(trans, quota_root); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } ret = btrfs_del_root(trans, "a_root->root_key); if (ret) { btrfs_abort_transaction(trans, ret); - goto end_trans; + goto out; } list_del("a_root->dirty_list); @@ -1185,10 +1224,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_put_root(quota_root); -end_trans: - ret = btrfs_end_transaction(trans); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); + if (ret && trans) + btrfs_end_transaction(trans); + else if (trans) + ret = btrfs_end_transaction(trans); + return ret; } @@ -1324,13 +1366,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup *member; struct btrfs_qgroup_list *list; struct ulist *tmp; + unsigned int nofs_flag; int ret = 0; /* Check the level of src and dst first */ if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) return -EINVAL; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -1387,10 +1433,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, struct btrfs_qgroup_list *list; struct ulist *tmp; bool found = false; + unsigned int nofs_flag; int ret = 0; int ret2; + /* We hold a transaction handle open, must do a NOFS allocation. */ + nofs_flag = memalloc_nofs_save(); tmp = ulist_alloc(GFP_KERNEL); + memalloc_nofs_restore(nofs_flag); if (!tmp) return -ENOMEM; @@ -3512,6 +3562,7 @@ static int try_flush_qgroup(struct btrfs_root *root) { struct btrfs_trans_handle *trans; int ret; + bool can_commit = true; /* * We don't want to run flush again and again, so if there is a running @@ -3523,6 +3574,20 @@ static int try_flush_qgroup(struct btrfs_root *root) return 0; } + /* + * If current process holds a transaction, we shouldn't flush, as we + * assume all space reservation happens before a transaction handle is + * held. + * + * But there are cases like btrfs_delayed_item_reserve_metadata() where + * we try to reserve space with one transction handle already held. + * In that case we can't commit transaction, but at least try to end it + * and hope the started data writes can free some space. + */ + if (current->journal_info && + current->journal_info != BTRFS_SEND_TRANS_STUB) + can_commit = false; + ret = btrfs_start_delalloc_snapshot(root); if (ret < 0) goto out; @@ -3534,7 +3599,10 @@ static int try_flush_qgroup(struct btrfs_root *root) goto out; } - ret = btrfs_commit_transaction(trans); + if (can_commit) + ret = btrfs_commit_transaction(trans); + else + ret = btrfs_end_transaction(trans); out: clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state); wake_up(&root->qgroup_flush_wait); diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index e6719f7db386..04022069761d 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -983,7 +983,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE >> 1, (BTRFS_MAX_EXTENT_SIZE >> 1) + sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1050,7 +1051,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, BTRFS_MAX_EXTENT_SIZE + sectorsize, BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1082,7 +1084,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) /* Empty */ ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); if (ret) { test_err("clear_extent_bit returned %d", ret); goto out; @@ -1097,7 +1100,8 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize) out: if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, - EXTENT_DELALLOC | EXTENT_UPTODATE, 0, 0, NULL); + EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | + EXTENT_UPTODATE, 0, 0, NULL); iput(inode); btrfs_free_dummy_root(root); btrfs_free_dummy_fs_info(fs_info); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 8784b74f5232..ea2bb4cb5890 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1068,6 +1068,7 @@ static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key, "invalid root item size, have %u expect %zu or %u", btrfs_item_size_nr(leaf, slot), sizeof(ri), btrfs_legacy_root_item_size()); + return -EUCLEAN; } /* @@ -1423,6 +1424,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, "invalid item size, have %u expect aligned to %zu for key type %u", btrfs_item_size_nr(leaf, slot), sizeof(*dref), key->type); + return -EUCLEAN; } if (!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize)) { generic_err(leaf, slot, @@ -1451,6 +1453,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, extent_err(leaf, slot, "invalid extent data backref offset, have %llu expect aligned to %u", offset, leaf->fs_info->sectorsize); + return -EUCLEAN; } } return 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a6406b3b8c2b..78637665166e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -940,7 +940,13 @@ static noinline struct btrfs_device *device_list_add(const char *path, if (device->bdev != path_bdev) { bdput(path_bdev); mutex_unlock(&fs_devices->device_list_mutex); - btrfs_warn_in_rcu(device->fs_info, + /* + * device->fs_info may not be reliable here, so + * pass in a NULL instead. This avoids a + * possible use-after-free when the fs_info and + * fs_info->sb are already torn down. + */ + btrfs_warn_in_rcu(NULL, "duplicate device %s devid %llu generation %llu scanned by %s (%d)", path, devid, found_transid, current->comm, diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 23b21e943652..ef4784e72b1d 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1266,6 +1266,7 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc); } else if (mode_from_special_sid) { rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, true); + kfree(pntsd); } else { /* get approximated mode from ACL */ rc = parse_sec_desc(cifs_sb, pntsd, acllen, fattr, false); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c38156f324dd..28c1459fb0fc 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -876,6 +876,8 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); + cancel_delayed_work_sync(&server->echo); + spin_lock(&GlobalMid_Lock); server->tcpStatus = CifsExiting; spin_unlock(&GlobalMid_Lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 504766cb6c19..dab94f67c988 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -264,7 +264,7 @@ smb2_revert_current_mid(struct TCP_Server_Info *server, const unsigned int val) } static struct mid_q_entry * -smb2_find_mid(struct TCP_Server_Info *server, char *buf) +__smb2_find_mid(struct TCP_Server_Info *server, char *buf, bool dequeue) { struct mid_q_entry *mid; struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)buf; @@ -281,6 +281,10 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) (mid->mid_state == MID_REQUEST_SUBMITTED) && (mid->command == shdr->Command)) { kref_get(&mid->refcount); + if (dequeue) { + list_del_init(&mid->qhead); + mid->mid_flags |= MID_DELETED; + } spin_unlock(&GlobalMid_Lock); return mid; } @@ -289,6 +293,18 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf) return NULL; } +static struct mid_q_entry * +smb2_find_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, false); +} + +static struct mid_q_entry * +smb2_find_dequeue_mid(struct TCP_Server_Info *server, char *buf) +{ + return __smb2_find_mid(server, buf, true); +} + static void smb2_dump_detail(void *buf, struct TCP_Server_Info *server) { @@ -4356,7 +4372,8 @@ init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size, static int handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, char *buf, unsigned int buf_len, struct page **pages, - unsigned int npages, unsigned int page_data_size) + unsigned int npages, unsigned int page_data_size, + bool is_offloaded) { unsigned int data_offset; unsigned int data_len; @@ -4378,7 +4395,8 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (server->ops->is_session_expired && server->ops->is_session_expired(buf)) { - cifs_reconnect(server); + if (!is_offloaded) + cifs_reconnect(server); return -1; } @@ -4402,7 +4420,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: server returned error %d\n", __func__, rdata->result); /* normal error on read response */ - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return 0; } @@ -4426,7 +4447,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4442,21 +4466,30 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n", __func__, data_offset); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } if (data_len > page_data_size - pad_len) { /* data_len is corrupt -- discard frame */ rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } rdata->result = init_read_bvec(pages, npages, page_data_size, cur_off, &bvec); if (rdata->result != 0) { - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4471,7 +4504,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); rdata->result = -EIO; - dequeue_mid(mid, rdata->result); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_MALFORMED; + else + dequeue_mid(mid, rdata->result); return 0; } @@ -4482,7 +4518,10 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, if (length < 0) return length; - dequeue_mid(mid, false); + if (is_offloaded) + mid->mid_state = MID_RESPONSE_RECEIVED; + else + dequeue_mid(mid, false); return length; } @@ -4511,15 +4550,34 @@ static void smb2_decrypt_offload(struct work_struct *work) } dw->server->lstrp = jiffies; - mid = smb2_find_mid(dw->server, dw->buf); + mid = smb2_find_dequeue_mid(dw->server, dw->buf); if (mid == NULL) cifs_dbg(FYI, "mid not found\n"); else { mid->decrypted = true; rc = handle_read_data(dw->server, mid, dw->buf, dw->server->vals->read_rsp_size, - dw->ppages, dw->npages, dw->len); - mid->callback(mid); + dw->ppages, dw->npages, dw->len, + true); + if (rc >= 0) { +#ifdef CONFIG_CIFS_STATS2 + mid->when_received = jiffies; +#endif + mid->callback(mid); + } else { + spin_lock(&GlobalMid_Lock); + if (dw->server->tcpStatus == CifsNeedReconnect) { + mid->mid_state = MID_RETRY_NEEDED; + spin_unlock(&GlobalMid_Lock); + mid->callback(mid); + } else { + mid->mid_state = MID_REQUEST_SUBMITTED; + mid->mid_flags &= ~(MID_DELETED); + list_add_tail(&mid->qhead, + &dw->server->pending_mid_q); + spin_unlock(&GlobalMid_Lock); + } + } cifs_mid_q_entry_release(mid); } @@ -4622,7 +4680,7 @@ non_offloaded_decrypt: (*mid)->decrypted = true; rc = handle_read_data(server, *mid, buf, server->vals->read_rsp_size, - pages, npages, len); + pages, npages, len, false); } free_pages: @@ -4765,7 +4823,7 @@ smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid) char *buf = server->large_buf ? server->bigbuf : server->smallbuf; return handle_read_data(server, mid, buf, server->pdu_size, - NULL, 0, 0); + NULL, 0, 0, false); } static int diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index e27e255d40dd..36b2ece43403 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -339,8 +339,8 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EAGAIN; if (signal_pending(current)) { - cifs_dbg(FYI, "signal is pending before sending any data\n"); - return -EINTR; + cifs_dbg(FYI, "signal pending before send request\n"); + return -ERESTARTSYS; } /* cork the socket */ diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 89bffa82ed74..c57bebfa48fe 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -74,7 +74,7 @@ int fscrypt_select_encryption_impl(struct fscrypt_info *ci) int i; /* The file must need contents encryption, not filenames encryption */ - if (!fscrypt_needs_contents_encryption(inode)) + if (!S_ISREG(inode->i_mode)) return 0; /* The crypto mode must have a blk-crypto counterpart */ diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 96c0c86f3fff..0297ad95eb5c 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -7,6 +7,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/ctype.h> +#include <linux/kmemleak.h> #include <linux/slab.h> #include <linux/uuid.h> @@ -103,6 +104,7 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, var->var.VariableName[i] = '\0'; inode->i_private = var; + kmemleak_ignore(var); err = efivar_entry_add(var, &efivarfs_list); if (err) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1b399cafb15a..65ecaf96d0a4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1231,13 +1231,13 @@ struct ext4_inode_info { blocks */ #define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated file systems */ -#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */ -#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */ - #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly specified journal checksum */ #define EXT4_MOUNT2_JOURNAL_FAST_COMMIT 0x00000010 /* Journal fast commit */ +#define EXT4_MOUNT2_DAX_NEVER 0x00000020 /* Do not allow Direct Access */ +#define EXT4_MOUNT2_DAX_INODE 0x00000040 /* For printing options only */ + #define clear_opt(sb, opt) EXT4_SB(sb)->s_mount_opt &= \ ~EXT4_MOUNT_##opt @@ -2695,7 +2695,8 @@ void ext4_insert_dentry(struct inode *inode, struct ext4_filename *fname); static inline void ext4_update_dx_flag(struct inode *inode) { - if (!ext4_has_feature_dir_index(inode->i_sb)) { + if (!ext4_has_feature_dir_index(inode->i_sb) && + ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { /* ext4_iget() should have caught this... */ WARN_ON_ONCE(ext4_has_feature_metadata_csum(inode->i_sb)); ext4_clear_inode_flag(inode, EXT4_INODE_INDEX); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c3b864588a0b..94472044f4c1 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -289,18 +289,7 @@ void ext4_superblock_csum_set(struct super_block *sb) if (!ext4_has_metadata_csum(sb)) return; - /* - * Locking the superblock prevents the scenario - * where: - * 1) a first thread pauses during checksum calculation. - * 2) a second thread updates the superblock, recalculates - * the checksum, and updates s_checksum - * 3) the first thread resumes and finishes its checksum calculation - * and updates s_checksum with a potentially stale or torn value. - */ - lock_buffer(EXT4_SB(sb)->s_sbh); es->s_checksum = ext4_superblock_csum(sb, es); - unlock_buffer(EXT4_SB(sb)->s_sbh); } ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, @@ -2649,10 +2638,6 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, } else if (test_opt2(sb, DAX_INODE)) { SEQ_OPTS_PUTS("dax=inode"); } - - if (test_opt2(sb, JOURNAL_FAST_COMMIT)) - SEQ_OPTS_PUTS("fast_commit"); - ext4_show_quota_options(seq, sb); return 0; } diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 9cd2ecad07db..cc4f987687f3 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -77,7 +77,7 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock, if (error) return error; if (!buffer_mapped(bh_result)) - return -EIO; + return -ENODATA; return 0; } diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 8dff9cbd0a87..62d9081d1e26 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -1301,12 +1301,8 @@ int gfs2_block_map(struct inode *inode, sector_t lblock, trace_gfs2_bmap(ip, bh_map, lblock, create, 1); ret = gfs2_iomap_get(inode, pos, length, flags, &iomap, &mp); - if (!ret && iomap.type == IOMAP_HOLE) { - if (create) - ret = gfs2_iomap_alloc(inode, &iomap, &mp); - else - ret = -ENODATA; - } + if (create && !ret && iomap.type == IOMAP_HOLE) + ret = gfs2_iomap_alloc(inode, &iomap, &mp); release_metapath(&mp); if (ret) goto out; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index d98a2e5dab9f..35a6fd103761 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1035,6 +1035,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, gl->gl_node.next = NULL; gl->gl_flags = 0; gl->gl_name = name; + lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass); gl->gl_lockref.count = 1; gl->gl_state = LM_ST_UNLOCKED; gl->gl_target = LM_ST_UNLOCKED; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index 6c1432d78dce..3faa421568b0 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -245,7 +245,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) static void gfs2_rgrp_go_dump(struct seq_file *seq, struct gfs2_glock *gl, const char *fs_id_buf) { - struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); + struct gfs2_rgrpd *rgd = gl->gl_object; if (rgd) gfs2_rgrp_dump(seq, rgd, fs_id_buf); @@ -571,7 +571,19 @@ static int freeze_go_sync(struct gfs2_glock *gl) int error = 0; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; - if (gl->gl_req == LM_ST_EXCLUSIVE && !gfs2_withdrawn(sdp)) { + /* + * We need to check gl_state == LM_ST_SHARED here and not gl_req == + * LM_ST_EXCLUSIVE. That's because when any node does a freeze, + * all the nodes should have the freeze glock in SH mode and they all + * call do_xmote: One for EX and the others for UN. They ALL must + * freeze locally, and they ALL must queue freeze work. The freeze_work + * calls freeze_func, which tries to reacquire the freeze glock in SH, + * effectively waiting for the thaw on the node who holds it in EX. + * Once thawed, the work func acquires the freeze glock in + * SH and everybody goes back to thawed. + */ + if (gl->gl_state == LM_ST_SHARED && !gfs2_withdrawn(sdp) && + !test_bit(SDF_NORECOVERY, &sdp->sd_flags)) { atomic_set(&sdp->sd_freeze_state, SFS_STARTING_FREEZE); error = freeze_super(sdp->sd_vfs); if (error) { @@ -770,6 +782,7 @@ const struct gfs2_glock_operations gfs2_iopen_glops = { .go_callback = iopen_go_callback, .go_demote_ok = iopen_go_demote_ok, .go_flags = GLOF_LRU | GLOF_NONDISK, + .go_subclass = 1, }; const struct gfs2_glock_operations gfs2_flock_glops = { diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index d7707307f4b1..f8858d995b24 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -247,6 +247,7 @@ struct gfs2_glock_operations { const char *fs_id_buf); void (*go_callback)(struct gfs2_glock *gl, bool remote); void (*go_free)(struct gfs2_glock *gl); + const int go_subclass; const int go_type; const unsigned long go_flags; #define GLOF_ASPACE 1 /* address space attached */ diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 077ccb1b3ccc..65ae4fc28ede 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -150,6 +150,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* @@ -180,8 +182,6 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (unlikely(error)) goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_glock_put(io_gl); io_gl = NULL; @@ -725,13 +725,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, flush_delayed_work(&ip->i_gl->gl_work); glock_set_object(ip->i_gl, ip); - error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; + gfs2_cancel_delete_work(io_gl); + glock_set_object(io_gl, ip); + + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); + if (error) + goto fail_gunlock2; error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_free_inode; + goto fail_gunlock2; if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -740,18 +746,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, init_dinode(dip, ip, symname); gfs2_trans_end(sdp); - error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (error) - goto fail_free_inode; - BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags)); error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); if (error) goto fail_gunlock2; - gfs2_cancel_delete_work(ip->i_iopen_gh.gh_gl); - glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); insert_inode_hash(inode); @@ -803,6 +803,7 @@ fail_gunlock3: gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { @@ -2116,6 +2117,25 @@ loff_t gfs2_seek_hole(struct file *file, loff_t offset) return vfs_setpos(file, ret, inode->i_sb->s_maxbytes); } +static int gfs2_update_time(struct inode *inode, struct timespec64 *time, + int flags) +{ + struct gfs2_inode *ip = GFS2_I(inode); + struct gfs2_glock *gl = ip->i_gl; + struct gfs2_holder *gh; + int error; + + gh = gfs2_glock_is_locked_by_me(gl); + if (gh && !gfs2_glock_is_held_excl(gl)) { + gfs2_glock_dq(gh); + gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, gh); + error = gfs2_glock_nq(gh); + if (error) + return error; + } + return generic_update_time(inode, time, flags); +} + const struct inode_operations gfs2_file_iops = { .permission = gfs2_permission, .setattr = gfs2_setattr, @@ -2124,6 +2144,7 @@ const struct inode_operations gfs2_file_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, }; const struct inode_operations gfs2_dir_iops = { @@ -2143,6 +2164,7 @@ const struct inode_operations gfs2_dir_iops = { .fiemap = gfs2_fiemap, .get_acl = gfs2_get_acl, .set_acl = gfs2_set_acl, + .update_time = gfs2_update_time, .atomic_open = gfs2_atomic_open, }; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 9133b3178677..2e9314091c81 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -132,6 +132,8 @@ __acquires(&sdp->sd_ail_lock) spin_unlock(&sdp->sd_ail_lock); ret = generic_writepages(mapping, wbc); spin_lock(&sdp->sd_ail_lock); + if (ret == -ENODATA) /* if a jdata write into a new hole */ + ret = 0; /* ignore it */ if (ret || wbc->nr_to_write <= 0) break; return -EBUSY; diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 92d799a193b8..5e8eef9990e3 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -985,6 +985,10 @@ static int gfs2_ri_update(struct gfs2_inode *ip) if (error < 0) return error; + if (RB_EMPTY_ROOT(&sdp->sd_rindex_tree)) { + fs_err(sdp, "no resource groups found in the file system.\n"); + return -ENOENT; + } set_rgrp_preferences(sdp); sdp->sd_rindex_uptodate = 1; @@ -2529,13 +2533,13 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type) rbm.rgd = rgd; error = gfs2_rbm_from_block(&rbm, no_addr); - if (WARN_ON_ONCE(error)) - goto fail; - - if (gfs2_testbit(&rbm, false) != type) - error = -ESTALE; + if (!WARN_ON_ONCE(error)) { + if (gfs2_testbit(&rbm, false) != type) + error = -ESTALE; + } gfs2_glock_dq_uninit(&rgd_gh); + fail: return error; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 8018c7076b25..1023f7b44cea 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -205,6 +205,7 @@ struct fixed_file_ref_node { struct list_head file_list; struct fixed_file_data *file_data; struct llist_node llist; + bool done; }; struct fixed_file_data { @@ -478,6 +479,7 @@ struct io_sr_msg { struct io_open { struct file *file; int dfd; + bool ignore_nonblock; struct filename *filename; struct open_how how; unsigned long nofile; @@ -1311,22 +1313,6 @@ static bool io_grab_identity(struct io_kiocb *req) return false; req->work.flags |= IO_WQ_WORK_FSIZE; } - - if (!(req->work.flags & IO_WQ_WORK_FILES) && - (def->work_flags & IO_WQ_WORK_FILES) && - !(req->flags & REQ_F_NO_FILE_TABLE)) { - if (id->files != current->files || - id->nsproxy != current->nsproxy) - return false; - atomic_inc(&id->files->count); - get_nsproxy(id->nsproxy); - req->flags |= REQ_F_INFLIGHT; - - spin_lock_irq(&ctx->inflight_lock); - list_add(&req->inflight_entry, &ctx->inflight_list); - spin_unlock_irq(&ctx->inflight_lock); - req->work.flags |= IO_WQ_WORK_FILES; - } #ifdef CONFIG_BLK_CGROUP if (!(req->work.flags & IO_WQ_WORK_BLKCG) && (def->work_flags & IO_WQ_WORK_BLKCG)) { @@ -1368,6 +1354,21 @@ static bool io_grab_identity(struct io_kiocb *req) } spin_unlock(¤t->fs->lock); } + if (!(req->work.flags & IO_WQ_WORK_FILES) && + (def->work_flags & IO_WQ_WORK_FILES) && + !(req->flags & REQ_F_NO_FILE_TABLE)) { + if (id->files != current->files || + id->nsproxy != current->nsproxy) + return false; + atomic_inc(&id->files->count); + get_nsproxy(id->nsproxy); + req->flags |= REQ_F_INFLIGHT; + + spin_lock_irq(&ctx->inflight_lock); + list_add(&req->inflight_entry, &ctx->inflight_list); + spin_unlock_irq(&ctx->inflight_lock); + req->work.flags |= IO_WQ_WORK_FILES; + } return true; } @@ -2577,7 +2578,6 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) } end_req: req_set_fail_links(req); - io_req_complete(req, ret); return false; } #endif @@ -3192,7 +3192,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, rw->free_iovec = iovec; rw->bytes_done = 0; /* can only be fixed buffers, no need to do anything */ - if (iter->type == ITER_BVEC) + if (iov_iter_is_bvec(iter)) return; if (!iovec) { unsigned iov_off = 0; @@ -3547,8 +3547,7 @@ static int io_write(struct io_kiocb *req, bool force_nonblock, * we return to userspace. */ if (req->flags & REQ_F_ISREG) { - __sb_start_write(file_inode(req->file)->i_sb, - SB_FREEZE_WRITE, true); + sb_start_write(file_inode(req->file)->i_sb); __sb_writers_release(file_inode(req->file)->i_sb, SB_FREEZE_WRITE); } @@ -3796,6 +3795,7 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return ret; } req->open.nofile = rlimit(RLIMIT_NOFILE); + req->open.ignore_nonblock = false; req->flags |= REQ_F_NEED_CLEANUP; return 0; } @@ -3839,7 +3839,7 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) struct file *file; int ret; - if (force_nonblock) + if (force_nonblock && !req->open.ignore_nonblock) return -EAGAIN; ret = build_open_flags(&req->open.how, &op); @@ -3854,6 +3854,21 @@ static int io_openat2(struct io_kiocb *req, bool force_nonblock) if (IS_ERR(file)) { put_unused_fd(ret); ret = PTR_ERR(file); + /* + * A work-around to ensure that /proc/self works that way + * that it should - if we get -EOPNOTSUPP back, then assume + * that proc_self_get_link() failed us because we're in async + * context. We should be safe to retry this from the task + * itself with force_nonblock == false set, as it should not + * block on lookup. Would be nice to know this upfront and + * avoid the async dance, but doesn't seem feasible. + */ + if (ret == -EOPNOTSUPP && io_wq_current_is_worker()) { + req->open.ignore_nonblock = true; + refcount_inc(&req->refs); + io_req_task_queue(req); + return 0; + } } else { fsnotify_open(file); fd_install(ret, file); @@ -6958,9 +6973,7 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) return -ENXIO; spin_lock(&data->lock); - if (!list_empty(&data->ref_list)) - ref_node = list_first_entry(&data->ref_list, - struct fixed_file_ref_node, node); + ref_node = data->node; spin_unlock(&data->lock); if (ref_node) percpu_ref_kill(&ref_node->refs); @@ -7309,10 +7322,6 @@ static void __io_file_put_work(struct fixed_file_ref_node *ref_node) kfree(pfile); } - spin_lock(&file_data->lock); - list_del(&ref_node->node); - spin_unlock(&file_data->lock); - percpu_ref_exit(&ref_node->refs); kfree(ref_node); percpu_ref_put(&file_data->refs); @@ -7339,17 +7348,32 @@ static void io_file_put_work(struct work_struct *work) static void io_file_data_ref_zero(struct percpu_ref *ref) { struct fixed_file_ref_node *ref_node; + struct fixed_file_data *data; struct io_ring_ctx *ctx; - bool first_add; + bool first_add = false; int delay = HZ; ref_node = container_of(ref, struct fixed_file_ref_node, refs); - ctx = ref_node->file_data->ctx; + data = ref_node->file_data; + ctx = data->ctx; - if (percpu_ref_is_dying(&ctx->file_data->refs)) + spin_lock(&data->lock); + ref_node->done = true; + + while (!list_empty(&data->ref_list)) { + ref_node = list_first_entry(&data->ref_list, + struct fixed_file_ref_node, node); + /* recycle ref nodes in order */ + if (!ref_node->done) + break; + list_del(&ref_node->node); + first_add |= llist_add(&ref_node->llist, &ctx->file_put_llist); + } + spin_unlock(&data->lock); + + if (percpu_ref_is_dying(&data->refs)) delay = 0; - first_add = llist_add(&ref_node->llist, &ctx->file_put_llist); if (!delay) mod_delayed_work(system_wq, &ctx->file_put_work, 0); else if (first_add) @@ -7373,6 +7397,7 @@ static struct fixed_file_ref_node *alloc_fixed_file_ref_node( INIT_LIST_HEAD(&ref_node->node); INIT_LIST_HEAD(&ref_node->file_list); ref_node->file_data = ctx->file_data; + ref_node->done = false; return ref_node; } @@ -7468,7 +7493,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, file_data->node = ref_node; spin_lock(&file_data->lock); - list_add(&ref_node->node, &file_data->ref_list); + list_add_tail(&ref_node->node, &file_data->ref_list); spin_unlock(&file_data->lock); percpu_ref_get(&file_data->refs); return ret; @@ -7627,7 +7652,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, if (needs_switch) { percpu_ref_kill(&data->node->refs); spin_lock(&data->lock); - list_add(&ref_node->node, &data->ref_list); + list_add_tail(&ref_node->node, &data->ref_list); data->node = ref_node; spin_unlock(&data->lock); percpu_ref_get(&ctx->file_data->refs); @@ -9226,7 +9251,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, * to a power-of-two, if it isn't already. We do NOT impose * any cq vs sq ring sizing. */ - if (p->cq_entries < p->sq_entries) + if (!p->cq_entries) return -EINVAL; if (p->cq_entries > IORING_MAX_CQ_ENTRIES) { if (!(p->flags & IORING_SETUP_CLAMP)) @@ -9234,6 +9259,8 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, p->cq_entries = IORING_MAX_CQ_ENTRIES; } p->cq_entries = roundup_pow_of_two(p->cq_entries); + if (p->cq_entries < p->sq_entries) + return -EINVAL; } else { p->cq_entries = 2 * p->sq_entries; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0c3d5e3b24b2..188f79d76988 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -566,12 +566,14 @@ static int __jbd2_journal_force_commit(journal_t *journal) } /** - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. + * jbd2_journal_force_commit_nested - Force and wait upon a commit if the + * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. + * + * This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { @@ -582,7 +584,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal) } /** - * int journal_force_commit() - force any uncommitted transactions + * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction @@ -1881,7 +1883,7 @@ static int load_superblock(journal_t *journal) /** - * int jbd2_journal_load() - Read journal from disk. + * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain @@ -1951,7 +1953,7 @@ recovery_error: } /** - * void jbd2_journal_destroy() - Release a journal_t structure. + * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the @@ -2028,7 +2030,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features() - Check if features specified are used. + * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2063,7 +2065,7 @@ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, } /** - * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2126,7 +2128,7 @@ jbd2_journal_initialize_fast_commit(journal_t *journal) } /** - * int jbd2_journal_set_features() - Mark a given journal feature in the superblock + * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -2217,7 +2219,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, } /* - * jbd2_journal_clear_features () - Clear a given journal feature in the + * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features @@ -2246,7 +2248,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_flush () - Flush journal + * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * * Flush all data for a given journal to disk and empty the journal. @@ -2321,7 +2323,7 @@ out: } /** - * int jbd2_journal_wipe() - Wipe journal contents + * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * @@ -2362,7 +2364,7 @@ int jbd2_journal_wipe(journal_t *journal, int write) } /** - * void jbd2_journal_abort () - Shutdown the journal immediately. + * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. @@ -2453,7 +2455,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) } /** - * int jbd2_journal_errno () - returns the journal's error state. + * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last @@ -2477,7 +2479,7 @@ int jbd2_journal_errno(journal_t *journal) } /** - * int jbd2_journal_clear_err () - clears the journal's error state + * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly @@ -2497,7 +2499,7 @@ int jbd2_journal_clear_err(journal_t *journal) } /** - * void jbd2_journal_ack_err() - Ack journal err. + * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index d54f04674e8e..9396666b7314 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -519,7 +519,7 @@ EXPORT_SYMBOL(jbd2__journal_start); /** - * handle_t *jbd2_journal_start() - Obtain a new handle. + * jbd2_journal_start() - Obtain a new handle. * @journal: Journal to start transaction on. * @nblocks: number of block buffer we might modify * @@ -566,7 +566,7 @@ void jbd2_journal_free_reserved(handle_t *handle) EXPORT_SYMBOL(jbd2_journal_free_reserved); /** - * int jbd2_journal_start_reserved() - start reserved handle + * jbd2_journal_start_reserved() - start reserved handle * @handle: handle to start * @type: for handle statistics * @line_no: for handle statistics @@ -620,7 +620,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, EXPORT_SYMBOL(jbd2_journal_start_reserved); /** - * int jbd2_journal_extend() - extend buffer credits. + * jbd2_journal_extend() - extend buffer credits. * @handle: handle to 'extend' * @nblocks: nr blocks to try to extend by. * @revoke_records: number of revoke records to try to extend by. @@ -745,7 +745,7 @@ static void stop_this_handle(handle_t *handle) } /** - * int jbd2_journal_restart() - restart a handle . + * jbd2__journal_restart() - restart a handle . * @handle: handle to restart * @nblocks: nr credits requested * @revoke_records: number of revoke record credits requested @@ -815,7 +815,7 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) EXPORT_SYMBOL(jbd2_journal_restart); /** - * void jbd2_journal_lock_updates () - establish a transaction barrier. + * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. * * This locks out any further updates from being started, and blocks @@ -874,7 +874,7 @@ void jbd2_journal_lock_updates(journal_t *journal) } /** - * void jbd2_journal_unlock_updates (journal_t* journal) - release barrier + * jbd2_journal_unlock_updates () - release barrier * @journal: Journal to release the barrier on. * * Release a transaction barrier obtained with jbd2_journal_lock_updates(). @@ -1182,7 +1182,8 @@ out: } /** - * int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update. + * jbd2_journal_get_write_access() - notify intent to modify a buffer + * for metadata (not data) update. * @handle: transaction to add buffer modifications to * @bh: bh to be used for metadata writes * @@ -1226,7 +1227,7 @@ int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh) * unlocked buffer beforehand. */ /** - * int jbd2_journal_get_create_access () - notify intent to use newly created bh + * jbd2_journal_get_create_access () - notify intent to use newly created bh * @handle: transaction to new buffer to * @bh: new buffer. * @@ -1306,7 +1307,7 @@ out: } /** - * int jbd2_journal_get_undo_access() - Notify intent to modify metadata with + * jbd2_journal_get_undo_access() - Notify intent to modify metadata with * non-rewindable consequences * @handle: transaction * @bh: buffer to undo @@ -1383,7 +1384,7 @@ out: } /** - * void jbd2_journal_set_triggers() - Add triggers for commit writeout + * jbd2_journal_set_triggers() - Add triggers for commit writeout * @bh: buffer to trigger on * @type: struct jbd2_buffer_trigger_type containing the trigger(s). * @@ -1425,7 +1426,7 @@ void jbd2_buffer_abort_trigger(struct journal_head *jh, } /** - * int jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata + * jbd2_journal_dirty_metadata() - mark a buffer as containing dirty metadata * @handle: transaction to add buffer to. * @bh: buffer to mark * @@ -1593,7 +1594,7 @@ out: } /** - * void jbd2_journal_forget() - bforget() for potentially-journaled buffers. + * jbd2_journal_forget() - bforget() for potentially-journaled buffers. * @handle: transaction handle * @bh: bh to 'forget' * @@ -1762,7 +1763,7 @@ drop: } /** - * int jbd2_journal_stop() - complete a transaction + * jbd2_journal_stop() - complete a transaction * @handle: transaction to complete. * * All done for a particular handle. @@ -2080,7 +2081,7 @@ out: } /** - * int jbd2_journal_try_to_free_buffers() - try to free page buffers. + * jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free * @@ -2411,7 +2412,7 @@ zap_buffer_unlocked: } /** - * void jbd2_journal_invalidatepage() + * jbd2_journal_invalidatepage() * @journal: journal to use for flush... * @page: page to flush * @offset: start of the range to invalidate diff --git a/fs/libfs.c b/fs/libfs.c index fc34361c1489..7124c2e8df2f 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -959,7 +959,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { struct simple_attr *attr; - u64 val; + unsigned long long val; size_t size; ssize_t ret; @@ -977,7 +977,9 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, goto out; attr->set_buf[size] = '\0'; - val = simple_strtoll(attr->set_buf, NULL, 0); + ret = kstrtoull(attr->set_buf, 0, &val); + if (ret) + goto out; ret = attr->set(attr->data, val); if (ret == 0) ret = len; /* on success, claim we got the whole input */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index a960ec3a569a..8d3ad5ef2925 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -178,6 +178,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, struct inode *inode = d_inode(dentry); struct dentry *parent; bool parent_watched = dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED; + bool parent_needed, parent_interested; __u32 p_mask; struct inode *p_inode = NULL; struct name_snapshot name; @@ -193,7 +194,8 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, return 0; parent = NULL; - if (!parent_watched && !fsnotify_event_needs_parent(inode, mnt, mask)) + parent_needed = fsnotify_event_needs_parent(inode, mnt, mask); + if (!parent_watched && !parent_needed) goto notify; /* Does parent inode care about events on children? */ @@ -205,17 +207,17 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, /* * Include parent/name in notification either if some notification - * groups require parent info (!parent_watched case) or the parent is - * interested in this event. + * groups require parent info or the parent is interested in this event. */ - if (!parent_watched || (mask & p_mask & ALL_FSNOTIFY_EVENTS)) { + parent_interested = mask & p_mask & ALL_FSNOTIFY_EVENTS; + if (parent_needed || parent_interested) { /* When notifying parent, child should be passed as data */ WARN_ON_ONCE(inode != fsnotify_data_inode(data, data_type)); /* Notify both parent and child with child name info */ take_dentry_name_snapshot(&name, dentry); file_name = &name.name; - if (parent_watched) + if (parent_interested) mask |= FS_EVENT_ON_CHILD; } diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1d91dd1e8711..2febc76e9de7 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1713,6 +1713,7 @@ static void ocfs2_inode_init_once(void *data) oi->ip_blkno = 0ULL; oi->ip_clusters = 0; + oi->ip_next_orphan = NULL; ocfs2_resv_init_once(&oi->ip_la_data_resv); diff --git a/fs/proc/self.c b/fs/proc/self.c index 72cd69bcaf4a..cc71ce3466dc 100644 --- a/fs/proc/self.c +++ b/fs/proc/self.c @@ -16,6 +16,13 @@ static const char *proc_self_get_link(struct dentry *dentry, pid_t tgid = task_tgid_nr_ns(current, ns); char *name; + /* + * Not currently supported. Once we can inherit all of struct pid, + * we can allow this. + */ + if (current->flags & PF_KTHREAD) + return ERR_PTR(-EOPNOTSUPP); + if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ diff --git a/fs/super.c b/fs/super.c index a51c2083cd6b..98bb0629ee10 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1631,55 +1631,6 @@ int super_setup_bdi(struct super_block *sb) } EXPORT_SYMBOL(super_setup_bdi); -/* - * This is an internal function, please use sb_end_{write,pagefault,intwrite} - * instead. - */ -void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} -EXPORT_SYMBOL(__sb_end_write); - -/* - * This is an internal function, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -int __sb_start_write(struct super_block *sb, int level, bool wait) -{ - bool force_trylock = false; - int ret = 1; - -#ifdef CONFIG_LOCKDEP - /* - * We want lockdep to tell us about possible deadlocks with freezing - * but it's it bit tricky to properly instrument it. Getting a freeze - * protection works as getting a read lock but there are subtle - * problems. XFS for example gets freeze protection on internal level - * twice in some cases, which is OK only because we already hold a - * freeze protection also on higher level. Due to these cases we have - * to use wait == F (trylock mode) which must not fail. - */ - if (wait) { - int i; - - for (i = 0; i < level - 1; i++) - if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) { - force_trylock = true; - break; - } - } -#endif - if (wait && !force_trylock) - percpu_down_read(sb->s_writers.rw_sem + level-1); - else - ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1); - - WARN_ON(force_trylock && !ret); - return ret; -} -EXPORT_SYMBOL(__sb_start_write); - /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index bb128db220ac..d6ef69ab1c67 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -515,7 +515,7 @@ xfs_attr_copy_value( *========================================================================*/ /* - * Query whether the requested number of additional bytes of extended + * Query whether the total requested number of attr fork bytes of extended * attribute space will be able to fit inline. * * Returns zero if not, else the di_forkoff fork offset to be used in the @@ -535,6 +535,12 @@ xfs_attr_shortform_bytesfit( int maxforkoff; int offset; + /* + * Check if the new size could fit at all first: + */ + if (bytes > XFS_LITINO(mp)) + return 0; + /* rounded down */ offset = (XFS_LITINO(mp) - bytes) >> 3; diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 340c83f76c80..2668ebe02865 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -1514,7 +1514,7 @@ xfs_rmap_convert_shared( * record for our insertion point. This will also give us the record for * start block contiguity tests. */ - error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, flags, + error = xfs_rmap_lookup_le_range(cur, bno, owner, offset, oldext, &PREV, &i); if (error) goto done; diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c index 955302e7cdde..fed56d213a3f 100644 --- a/fs/xfs/scrub/bmap.c +++ b/fs/xfs/scrub/bmap.c @@ -113,6 +113,8 @@ xchk_bmap_get_rmap( if (info->whichfork == XFS_ATTR_FORK) rflags |= XFS_RMAP_ATTR_FORK; + if (irec->br_state == XFS_EXT_UNWRITTEN) + rflags |= XFS_RMAP_UNWRITTEN; /* * CoW staging extents are owned (on disk) by the refcountbt, so @@ -216,13 +218,13 @@ xchk_bmap_xref_rmap( * which doesn't track unwritten state. */ if (owner != XFS_RMAP_OWN_COW && - irec->br_state == XFS_EXT_UNWRITTEN && - !(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) + !!(irec->br_state == XFS_EXT_UNWRITTEN) != + !!(rmap.rm_flags & XFS_RMAP_UNWRITTEN)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); - if (info->whichfork == XFS_ATTR_FORK && - !(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) + if (!!(info->whichfork == XFS_ATTR_FORK) != + !!(rmap.rm_flags & XFS_RMAP_ATTR_FORK)) xchk_fblock_xref_set_corrupt(info->sc, info->whichfork, irec->br_startoff); if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK) diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c index f52a7b8256f9..debf392e0515 100644 --- a/fs/xfs/scrub/btree.c +++ b/fs/xfs/scrub/btree.c @@ -452,32 +452,41 @@ xchk_btree_check_minrecs( int level, struct xfs_btree_block *block) { - unsigned int numrecs; - int ok_level; - - numrecs = be16_to_cpu(block->bb_numrecs); + struct xfs_btree_cur *cur = bs->cur; + unsigned int root_level = cur->bc_nlevels - 1; + unsigned int numrecs = be16_to_cpu(block->bb_numrecs); /* More records than minrecs means the block is ok. */ - if (numrecs >= bs->cur->bc_ops->get_minrecs(bs->cur, level)) + if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) return; /* - * Certain btree blocks /can/ have fewer than minrecs records. Any - * level greater than or equal to the level of the highest dedicated - * btree block are allowed to violate this constraint. - * - * For a btree rooted in a block, the btree root can have fewer than - * minrecs records. If the btree is rooted in an inode and does not - * store records in the root, the direct children of the root and the - * root itself can have fewer than minrecs records. + * For btrees rooted in the inode, it's possible that the root block + * contents spilled into a regular ondisk block because there wasn't + * enough space in the inode root. The number of records in that + * child block might be less than the standard minrecs, but that's ok + * provided that there's only one direct child of the root. */ - ok_level = bs->cur->bc_nlevels - 1; - if (bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) - ok_level--; - if (level >= ok_level) + if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && + level == cur->bc_nlevels - 2) { + struct xfs_btree_block *root_block; + struct xfs_buf *root_bp; + int root_maxrecs; + + root_block = xfs_btree_get_block(cur, root_level, &root_bp); + root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level); + if (be16_to_cpu(root_block->bb_numrecs) != 1 || + numrecs <= root_maxrecs) + xchk_btree_set_corrupt(bs->sc, cur, level); return; + } - xchk_btree_set_corrupt(bs->sc, bs->cur, level); + /* + * Otherwise, only the root level is allowed to have fewer than minrecs + * records or keyptrs. + */ + if (level < root_level) + xchk_btree_set_corrupt(bs->sc, cur, level); } /* diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index 7c432997edad..b045e95c2ea7 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -558,14 +558,27 @@ xchk_directory_leaf1_bestfree( /* Check all the bestfree entries. */ for (i = 0; i < bestcount; i++, bestp++) { best = be16_to_cpu(*bestp); - if (best == NULLDATAOFF) - continue; error = xfs_dir3_data_read(sc->tp, sc->ip, - i * args->geo->fsbcount, 0, &dbp); + xfs_dir2_db_to_da(args->geo, i), + XFS_DABUF_MAP_HOLE_OK, + &dbp); if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error)) break; - xchk_directory_check_freesp(sc, lblk, dbp, best); + + if (!dbp) { + if (best != NULLDATAOFF) { + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, + lblk); + break; + } + continue; + } + + if (best == NULLDATAOFF) + xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk); + else + xchk_directory_check_freesp(sc, lblk, dbp, best); xfs_trans_brelse(sc->tp, dbp); if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) break; diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index beaeb6fa3119..dd672e6bbc75 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -170,7 +170,6 @@ xchk_refcountbt_process_rmap_fragments( */ INIT_LIST_HEAD(&worklist); rbno = NULLAGBLOCK; - nr = 1; /* Make sure the fragments actually /are/ in agbno order. */ bno = 0; @@ -184,15 +183,14 @@ xchk_refcountbt_process_rmap_fragments( * Find all the rmaps that start at or before the refc extent, * and put them on the worklist. */ + nr = 0; list_for_each_entry_safe(frag, n, &refchk->fragments, list) { - if (frag->rm.rm_startblock > refchk->bno) - goto done; + if (frag->rm.rm_startblock > refchk->bno || nr > target_nr) + break; bno = frag->rm.rm_startblock + frag->rm.rm_blockcount; if (bno < rbno) rbno = bno; list_move_tail(&frag->list, &worklist); - if (nr == target_nr) - break; nr++; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 3abb8b9d6f4c..7b9ff824e82d 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -706,6 +706,23 @@ relock: return 0; } +/* + * Check that the imap we are going to return to the caller spans the entire + * range that the caller requested for the IO. + */ +static bool +imap_spans_range( + struct xfs_bmbt_irec *imap, + xfs_fileoff_t offset_fsb, + xfs_fileoff_t end_fsb) +{ + if (imap->br_startoff > offset_fsb) + return false; + if (imap->br_startoff + imap->br_blockcount < end_fsb) + return false; + return true; +} + static int xfs_direct_write_iomap_begin( struct inode *inode, @@ -766,6 +783,18 @@ xfs_direct_write_iomap_begin( if (imap_needs_alloc(inode, flags, &imap, nimaps)) goto allocate_blocks; + /* + * NOWAIT IO needs to span the entire requested IO with a single map so + * that we avoid partial IO failures due to the rest of the IO range not + * covered by this map triggering an EAGAIN condition when it is + * subsequently mapped and aborting the IO. + */ + if ((flags & IOMAP_NOWAIT) && + !imap_spans_range(&imap, offset_fsb, end_fsb)) { + error = -EAGAIN; + goto out_unlock; + } + xfs_iunlock(ip, lockmode); trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap); return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags); diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c index 233dcc8784db..2a45138831e3 100644 --- a/fs/xfs/xfs_iwalk.c +++ b/fs/xfs/xfs_iwalk.c @@ -55,6 +55,9 @@ struct xfs_iwalk_ag { /* Where do we start the traversal? */ xfs_ino_t startino; + /* What was the last inode number we saw when iterating the inobt? */ + xfs_ino_t lastino; + /* Array of inobt records we cache. */ struct xfs_inobt_rec_incore *recs; @@ -301,6 +304,9 @@ xfs_iwalk_ag_start( if (XFS_IS_CORRUPT(mp, *has_more != 1)) return -EFSCORRUPTED; + iwag->lastino = XFS_AGINO_TO_INO(mp, agno, + irec->ir_startino + XFS_INODES_PER_CHUNK - 1); + /* * If the LE lookup yielded an inobt record before the cursor position, * skip it and see if there's another one after it. @@ -347,15 +353,17 @@ xfs_iwalk_run_callbacks( struct xfs_mount *mp = iwag->mp; struct xfs_trans *tp = iwag->tp; struct xfs_inobt_rec_incore *irec; - xfs_agino_t restart; + xfs_agino_t next_agino; int error; + next_agino = XFS_INO_TO_AGINO(mp, iwag->lastino) + 1; + ASSERT(iwag->nr_recs > 0); /* Delete cursor but remember the last record we cached... */ xfs_iwalk_del_inobt(tp, curpp, agi_bpp, 0); irec = &iwag->recs[iwag->nr_recs - 1]; - restart = irec->ir_startino + XFS_INODES_PER_CHUNK - 1; + ASSERT(next_agino == irec->ir_startino + XFS_INODES_PER_CHUNK); error = xfs_iwalk_ag_recs(iwag); if (error) @@ -372,7 +380,7 @@ xfs_iwalk_run_callbacks( if (error) return error; - return xfs_inobt_lookup(*curpp, restart, XFS_LOOKUP_GE, has_more); + return xfs_inobt_lookup(*curpp, next_agino, XFS_LOOKUP_GE, has_more); } /* Walk all inodes in a single AG, from @iwag->startino to the end of the AG. */ @@ -396,6 +404,7 @@ xfs_iwalk_ag( while (!error && has_more) { struct xfs_inobt_rec_incore *irec; + xfs_ino_t rec_fsino; cond_resched(); if (xfs_pwork_want_abort(&iwag->pwork)) @@ -407,6 +416,15 @@ xfs_iwalk_ag( if (error || !has_more) break; + /* Make sure that we always move forward. */ + rec_fsino = XFS_AGINO_TO_INO(mp, agno, irec->ir_startino); + if (iwag->lastino != NULLFSINO && + XFS_IS_CORRUPT(mp, iwag->lastino >= rec_fsino)) { + error = -EFSCORRUPTED; + goto out; + } + iwag->lastino = rec_fsino + XFS_INODES_PER_CHUNK - 1; + /* No allocated inodes in this chunk; skip it. */ if (iwag->skip_empty && irec->ir_freecount == irec->ir_count) { error = xfs_btree_increment(cur, 0, &has_more); @@ -535,6 +553,7 @@ xfs_iwalk( .trim_start = 1, .skip_empty = 1, .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; @@ -623,6 +642,7 @@ xfs_iwalk_threaded( iwag->data = data; iwag->startino = startino; iwag->sz_recs = xfs_iwalk_prefetch(inode_records); + iwag->lastino = NULLFSINO; xfs_pwork_queue(&pctl, &iwag->pwork); startino = XFS_AGINO_TO_INO(mp, agno + 1, 0); if (flags & XFS_INOBT_WALK_SAME_AG) @@ -696,6 +716,7 @@ xfs_inobt_walk( .startino = startino, .sz_recs = xfs_inobt_walk_prefetch(inobt_records), .pwork = XFS_PWORK_SINGLE_THREADED, + .lastino = NULLFSINO, }; xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, startino); int error; diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 150ee5cb8645..7110507a2b6b 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -194,20 +194,25 @@ xfs_initialize_perag( } pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL); - if (!pag) + if (!pag) { + error = -ENOMEM; goto out_unwind_new_pags; + } pag->pag_agno = index; pag->pag_mount = mp; spin_lock_init(&pag->pag_ici_lock); INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC); - if (xfs_buf_hash_init(pag)) + + error = xfs_buf_hash_init(pag); + if (error) goto out_free_pag; init_waitqueue_head(&pag->pagb_wait); spin_lock_init(&pag->pagb_lock); pag->pagb_count = 0; pag->pagb_tree = RB_ROOT; - if (radix_tree_preload(GFP_NOFS)) + error = radix_tree_preload(GFP_NOFS); + if (error) goto out_hash_destroy; spin_lock(&mp->m_perag_lock); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index b101feb2aab4..f3082a957d5e 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -134,7 +134,7 @@ xfs_fs_map_blocks( goto out_unlock; error = invalidate_inode_pages2(inode->i_mapping); if (WARN_ON_ONCE(error)) - return error; + goto out_unlock; end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + length); offset_fsb = XFS_B_TO_FSBT(mp, offset); |