diff options
Diffstat (limited to 'fs')
87 files changed, 1218 insertions, 1036 deletions
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 2037e7a77a37..d764236072b1 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -91,11 +91,9 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = { */ bool afs_cm_incoming_call(struct afs_call *call) { - u32 operation_id = ntohl(call->operation_ID); + _enter("{CB.OP %u}", call->operation_ID); - _enter("{CB.OP %u}", operation_id); - - switch (operation_id) { + switch (call->operation_ID) { case CBCallBack: call->type = &afs_SRXCBCallBack; return true; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 96f4d764d1a6..31c616ab9b40 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -364,7 +364,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) buffer = kmap(page); ret = afs_extract_data(call, buffer, call->count, true); - kunmap(buffer); + kunmap(page); if (ret < 0) return ret; } @@ -397,7 +397,7 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call) page = call->reply3; buffer = kmap(page); memset(buffer + call->count, 0, PAGE_SIZE - call->count); - kunmap(buffer); + kunmap(page); } _leave(" = 0 [done]"); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5497c8496055..535a38d2c1d0 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -112,7 +112,7 @@ struct afs_call { bool need_attention; /* T if RxRPC poked us */ u16 service_id; /* RxRPC service ID to call */ __be16 port; /* target UDP port */ - __be32 operation_ID; /* operation ID for an incoming call */ + u32 operation_ID; /* operation ID for an incoming call */ u32 count; /* count for use in unmarshalling */ __be32 tmp; /* place to extract temporary data */ afs_dataversion_t store_version; /* updated version expected from store */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 477928b25940..25f05a8d21b1 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -676,10 +676,11 @@ static int afs_deliver_cm_op_id(struct afs_call *call) ASSERTCMP(call->offset, <, 4); /* the operation ID forms the first four bytes of the request data */ - ret = afs_extract_data(call, &call->operation_ID, 4, true); + ret = afs_extract_data(call, &call->tmp, 4, true); if (ret < 0) return ret; + call->operation_ID = ntohl(call->tmp); call->state = AFS_CALL_AWAIT_REQUEST; call->offset = 0; @@ -1078,6 +1078,17 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2) unsigned tail, pos, head; unsigned long flags; + if (kiocb->ki_flags & IOCB_WRITE) { + struct file *file = kiocb->ki_filp; + + /* + * Tell lockdep we inherited freeze protection from submission + * thread. + */ + __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); + file_end_write(file); + } + /* * Special case handling for sync iocbs: * - events go directly into the iocb for fast handling @@ -1392,122 +1403,106 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) return -EINVAL; } -typedef ssize_t (rw_iter_op)(struct kiocb *, struct iov_iter *); - -static int aio_setup_vectored_rw(int rw, char __user *buf, size_t len, - struct iovec **iovec, - bool compat, - struct iov_iter *iter) +static int aio_setup_rw(int rw, struct iocb *iocb, struct iovec **iovec, + bool vectored, bool compat, struct iov_iter *iter) { + void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf; + size_t len = iocb->aio_nbytes; + + if (!vectored) { + ssize_t ret = import_single_range(rw, buf, len, *iovec, iter); + *iovec = NULL; + return ret; + } #ifdef CONFIG_COMPAT if (compat) - return compat_import_iovec(rw, - (struct compat_iovec __user *)buf, - len, UIO_FASTIOV, iovec, iter); + return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec, + iter); #endif - return import_iovec(rw, (struct iovec __user *)buf, - len, UIO_FASTIOV, iovec, iter); + return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter); } -/* - * aio_run_iocb: - * Performs the initial checks and io submission. - */ -static ssize_t aio_run_iocb(struct kiocb *req, unsigned opcode, - char __user *buf, size_t len, bool compat) +static inline ssize_t aio_ret(struct kiocb *req, ssize_t ret) +{ + switch (ret) { + case -EIOCBQUEUED: + return ret; + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTARTNOHAND: + case -ERESTART_RESTARTBLOCK: + /* + * There's no easy way to restart the syscall since other AIO's + * may be already running. Just fail this IO with EINTR. + */ + ret = -EINTR; + /*FALLTHRU*/ + default: + aio_complete(req, ret, 0); + return 0; + } +} + +static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored, + bool compat) { struct file *file = req->ki_filp; - ssize_t ret; - int rw; - fmode_t mode; - rw_iter_op *iter_op; struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; + ssize_t ret; - switch (opcode) { - case IOCB_CMD_PREAD: - case IOCB_CMD_PREADV: - mode = FMODE_READ; - rw = READ; - iter_op = file->f_op->read_iter; - goto rw_common; - - case IOCB_CMD_PWRITE: - case IOCB_CMD_PWRITEV: - mode = FMODE_WRITE; - rw = WRITE; - iter_op = file->f_op->write_iter; - goto rw_common; -rw_common: - if (unlikely(!(file->f_mode & mode))) - return -EBADF; - - if (!iter_op) - return -EINVAL; - - if (opcode == IOCB_CMD_PREADV || opcode == IOCB_CMD_PWRITEV) - ret = aio_setup_vectored_rw(rw, buf, len, - &iovec, compat, &iter); - else { - ret = import_single_range(rw, buf, len, iovec, &iter); - iovec = NULL; - } - if (!ret) - ret = rw_verify_area(rw, file, &req->ki_pos, - iov_iter_count(&iter)); - if (ret < 0) { - kfree(iovec); - return ret; - } - - if (rw == WRITE) - file_start_write(file); - - ret = iter_op(req, &iter); - - if (rw == WRITE) - file_end_write(file); - kfree(iovec); - break; - - case IOCB_CMD_FDSYNC: - if (!file->f_op->aio_fsync) - return -EINVAL; - - ret = file->f_op->aio_fsync(req, 1); - break; + if (unlikely(!(file->f_mode & FMODE_READ))) + return -EBADF; + if (unlikely(!file->f_op->read_iter)) + return -EINVAL; - case IOCB_CMD_FSYNC: - if (!file->f_op->aio_fsync) - return -EINVAL; + ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); + if (ret) + return ret; + ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); + if (!ret) + ret = aio_ret(req, file->f_op->read_iter(req, &iter)); + kfree(iovec); + return ret; +} - ret = file->f_op->aio_fsync(req, 0); - break; +static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored, + bool compat) +{ + struct file *file = req->ki_filp; + struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct iov_iter iter; + ssize_t ret; - default: - pr_debug("EINVAL: no operation provided\n"); + if (unlikely(!(file->f_mode & FMODE_WRITE))) + return -EBADF; + if (unlikely(!file->f_op->write_iter)) return -EINVAL; - } - if (ret != -EIOCBQUEUED) { + ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); + if (ret) + return ret; + ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); + if (!ret) { + req->ki_flags |= IOCB_WRITE; + file_start_write(file); + ret = aio_ret(req, file->f_op->write_iter(req, &iter)); /* - * There's no easy way to restart the syscall since other AIO's - * may be already running. Just fail this IO with EINTR. + * We release freeze protection in aio_complete(). Fool lockdep + * by telling it the lock got released so that it doesn't + * complain about held lock when we return to userspace. */ - if (unlikely(ret == -ERESTARTSYS || ret == -ERESTARTNOINTR || - ret == -ERESTARTNOHAND || - ret == -ERESTART_RESTARTBLOCK)) - ret = -EINTR; - aio_complete(req, ret, 0); + __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } - - return 0; + kfree(iovec); + return ret; } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, struct iocb *iocb, bool compat) { struct aio_kiocb *req; + struct file *file; ssize_t ret; /* enforce forwards compatibility on users */ @@ -1530,7 +1525,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, if (unlikely(!req)) return -EAGAIN; - req->common.ki_filp = fget(iocb->aio_fildes); + req->common.ki_filp = file = fget(iocb->aio_fildes); if (unlikely(!req->common.ki_filp)) { ret = -EBADF; goto out_put_req; @@ -1565,13 +1560,29 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, req->ki_user_iocb = user_iocb; req->ki_user_data = iocb->aio_data; - ret = aio_run_iocb(&req->common, iocb->aio_lio_opcode, - (char __user *)(unsigned long)iocb->aio_buf, - iocb->aio_nbytes, - compat); - if (ret) - goto out_put_req; + get_file(file); + switch (iocb->aio_lio_opcode) { + case IOCB_CMD_PREAD: + ret = aio_read(&req->common, iocb, false, compat); + break; + case IOCB_CMD_PWRITE: + ret = aio_write(&req->common, iocb, false, compat); + break; + case IOCB_CMD_PREADV: + ret = aio_read(&req->common, iocb, true, compat); + break; + case IOCB_CMD_PWRITEV: + ret = aio_write(&req->common, iocb, true, compat); + break; + default: + pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); + ret = -EINVAL; + break; + } + fput(file); + if (ret && ret != -EIOCBQUEUED) + goto out_put_req; return 0; out_put_req: put_reqs_available(ctx, 1); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index ccc70d96958d..d4d8b7e36b2f 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -698,7 +698,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } @@ -728,7 +728,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, comp_bio, mirror_num, 0); if (ret) { - bio->bi_error = ret; + comp_bio->bi_error = ret; bio_endio(comp_bio); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 210c94ac8818..4607af38c72e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2647,7 +2647,10 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, btrfs_free_delayed_extent_op(extent_op); if (ret) { + spin_lock(&delayed_refs->lock); locked_ref->processing = 0; + delayed_refs->num_heads_ready++; + spin_unlock(&delayed_refs->lock); btrfs_delayed_ref_unlock(locked_ref); btrfs_put_delayed_ref(ref); btrfs_debug(fs_info, "run_one_delayed_ref returned %d", diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 66a755150056..8ed05d95584a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -5569,7 +5569,7 @@ void le_bitmap_set(u8 *map, unsigned int start, int len) *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; - mask_to_set = ~(u8)0; + mask_to_set = ~0; p++; } if (len) { @@ -5589,7 +5589,7 @@ void le_bitmap_clear(u8 *map, unsigned int start, int len) *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_BYTE; - mask_to_clear = ~(u8)0; + mask_to_clear = ~0; p++; } if (len) { @@ -5679,7 +5679,7 @@ void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start, kaddr[offset] |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_BYTE; - mask_to_set = ~(u8)0; + mask_to_set = ~0; if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; @@ -5721,7 +5721,7 @@ void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start, kaddr[offset] &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_BYTE; - mask_to_clear = ~(u8)0; + mask_to_clear = ~0; if (++offset >= PAGE_SIZE && len > 0) { offset = 0; page = eb->pages[++i]; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b790bda7998..8e3a5a266917 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4605,8 +4605,8 @@ delete: BUG_ON(ret); if (btrfs_should_throttle_delayed_refs(trans, root)) btrfs_async_run_delayed_refs(root, - trans->transid, - trans->delayed_ref_updates * 2, 0); + trans->delayed_ref_updates * 2, + trans->transid, 0); if (be_nice) { if (truncate_space_check(trans, root, extent_num_bytes)) { @@ -8931,9 +8931,14 @@ again: * So even we call qgroup_free_data(), it won't decrease reserved * space. * 2) Not written to disk - * This means the reserved space should be freed here. + * This means the reserved space should be freed here. However, + * if a truncate invalidates the page (by clearing PageDirty) + * and the page is accounted for while allocating extent + * in btrfs_check_data_free_space() we let delayed_ref to + * free the entire extent. */ - btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); + if (PageDirty(page)) + btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE); if (!inode_evicting) { clear_extent_bit(tree, page_start, page_end, EXTENT_LOCKED | EXTENT_DIRTY | diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 18e1aa0f85f5..7acbd2cf6192 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3814,6 +3814,11 @@ process_slot: } btrfs_release_path(path); key.offset = next_key_min_offset; + + if (fatal_signal_pending(current)) { + ret = -EINTR; + goto out; + } } ret = 0; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 0ec8ffa37ab0..c4af0cdb783d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2728,7 +2728,14 @@ static int do_relocation(struct btrfs_trans_handle *trans, bytenr = btrfs_node_blockptr(upper->eb, slot); if (lowest) { - BUG_ON(bytenr != node->bytenr); + if (bytenr != node->bytenr) { + btrfs_err(root->fs_info, + "lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu", + bytenr, node->bytenr, slot, + upper->eb->start); + err = -EIO; + goto next; + } } else { if (node->eb->start == bytenr) goto next; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 01bc36cec26e..71261b459863 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5805,6 +5805,64 @@ static int changed_extent(struct send_ctx *sctx, int ret = 0; if (sctx->cur_ino != sctx->cmp_key->objectid) { + + if (result == BTRFS_COMPARE_TREE_CHANGED) { + struct extent_buffer *leaf_l; + struct extent_buffer *leaf_r; + struct btrfs_file_extent_item *ei_l; + struct btrfs_file_extent_item *ei_r; + + leaf_l = sctx->left_path->nodes[0]; + leaf_r = sctx->right_path->nodes[0]; + ei_l = btrfs_item_ptr(leaf_l, + sctx->left_path->slots[0], + struct btrfs_file_extent_item); + ei_r = btrfs_item_ptr(leaf_r, + sctx->right_path->slots[0], + struct btrfs_file_extent_item); + + /* + * We may have found an extent item that has changed + * only its disk_bytenr field and the corresponding + * inode item was not updated. This case happens due to + * very specific timings during relocation when a leaf + * that contains file extent items is COWed while + * relocation is ongoing and its in the stage where it + * updates data pointers. So when this happens we can + * safely ignore it since we know it's the same extent, + * but just at different logical and physical locations + * (when an extent is fully replaced with a new one, we + * know the generation number must have changed too, + * since snapshot creation implies committing the current + * transaction, and the inode item must have been updated + * as well). + * This replacement of the disk_bytenr happens at + * relocation.c:replace_file_extents() through + * relocation.c:btrfs_reloc_cow_block(). + */ + if (btrfs_file_extent_generation(leaf_l, ei_l) == + btrfs_file_extent_generation(leaf_r, ei_r) && + btrfs_file_extent_ram_bytes(leaf_l, ei_l) == + btrfs_file_extent_ram_bytes(leaf_r, ei_r) && + btrfs_file_extent_compression(leaf_l, ei_l) == + btrfs_file_extent_compression(leaf_r, ei_r) && + btrfs_file_extent_encryption(leaf_l, ei_l) == + btrfs_file_extent_encryption(leaf_r, ei_r) && + btrfs_file_extent_other_encoding(leaf_l, ei_l) == + btrfs_file_extent_other_encoding(leaf_r, ei_r) && + btrfs_file_extent_type(leaf_l, ei_l) == + btrfs_file_extent_type(leaf_r, ei_r) && + btrfs_file_extent_disk_bytenr(leaf_l, ei_l) != + btrfs_file_extent_disk_bytenr(leaf_r, ei_r) && + btrfs_file_extent_disk_num_bytes(leaf_l, ei_l) == + btrfs_file_extent_disk_num_bytes(leaf_r, ei_r) && + btrfs_file_extent_offset(leaf_l, ei_l) == + btrfs_file_extent_offset(leaf_r, ei_r) && + btrfs_file_extent_num_bytes(leaf_l, ei_l) == + btrfs_file_extent_num_bytes(leaf_r, ei_r)) + return 0; + } + inconsistent_snapshot_error(sctx, result, "extent"); return -EIO; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 528cae123dc9..3d33c4e41e5f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2713,14 +2713,12 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root, int index, int error) { struct btrfs_log_ctx *ctx; + struct btrfs_log_ctx *safe; - if (!error) { - INIT_LIST_HEAD(&root->log_ctxs[index]); - return; - } - - list_for_each_entry(ctx, &root->log_ctxs[index], list) + list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) { + list_del_init(&ctx->list); ctx->log_ret = error; + } INIT_LIST_HEAD(&root->log_ctxs[index]); } @@ -2961,13 +2959,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&root->log_mutex); out_wake_log_root: - /* - * We needn't get log_mutex here because we are sure all - * the other tasks are blocked. - */ + mutex_lock(&log_root_tree->log_mutex); btrfs_remove_all_log_ctxs(log_root_tree, index2, ret); - mutex_lock(&log_root_tree->log_mutex); log_root_tree->log_transid_committed++; atomic_set(&log_root_tree->log_commit[index2], 0); mutex_unlock(&log_root_tree->log_mutex); @@ -2978,10 +2972,8 @@ out_wake_log_root: if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) wake_up(&log_root_tree->log_commit_wait[index2]); out: - /* See above. */ - btrfs_remove_all_log_ctxs(root, index1, ret); - mutex_lock(&root->log_mutex); + btrfs_remove_all_log_ctxs(root, index1, ret); root->log_transid_committed++; atomic_set(&root->log_commit[index1], 0); mutex_unlock(&root->log_mutex); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 78180d151730..a594c7879cc2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1261,26 +1261,30 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) return -ECHILD; op = ceph_snap(dir) == CEPH_SNAPDIR ? - CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP; + CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_GETATTR; req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS); if (!IS_ERR(req)) { req->r_dentry = dget(dentry); - req->r_num_caps = 2; + req->r_num_caps = op == CEPH_MDS_OP_GETATTR ? 1 : 2; mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; if (ceph_security_xattr_wanted(dir)) mask |= CEPH_CAP_XATTR_SHARED; req->r_args.getattr.mask = mask; - req->r_locked_dir = dir; err = ceph_mdsc_do_request(mdsc, NULL, req); - if (err == 0 || err == -ENOENT) { - if (dentry == req->r_dentry) { - valid = !d_unhashed(dentry); - } else { - d_invalidate(req->r_dentry); - err = -EAGAIN; - } + switch (err) { + case 0: + if (d_really_is_positive(dentry) && + d_inode(dentry) == req->r_target_inode) + valid = 1; + break; + case -ENOENT: + if (d_really_is_negative(dentry)) + valid = 1; + /* Fallthrough */ + default: + break; } ceph_mdsc_put_request(req); dout("d_revalidate %p lookup result=%d\n", diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 7bf08825cc11..f995e3528a33 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1272,7 +1272,8 @@ again: statret = __ceph_do_getattr(inode, page, CEPH_STAT_CAP_INLINE_DATA, !!page); if (statret < 0) { - __free_page(page); + if (page) + __free_page(page); if (statret == -ENODATA) { BUG_ON(retry_op != READ_INLINE); goto again; @@ -1769,7 +1770,6 @@ const struct file_operations ceph_file_fops = { .fsync = ceph_fsync, .lock = ceph_lock, .flock = ceph_flock, - .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, .unlocked_ioctl = ceph_ioctl, .compat_ioctl = ceph_ioctl, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index bca1b49c1c4b..ef4d04647325 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1511,7 +1511,8 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req, ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir); } - if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2) { + if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 && + !(rinfo->hash_order && req->r_path2)) { /* note dir version at start of readdir so we can tell * if any dentries get dropped */ req->r_dir_release_cnt = atomic64_read(&ci->i_release_count); diff --git a/fs/ceph/super.c b/fs/ceph/super.c index a29ffce98187..b382e5910eea 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -845,6 +845,8 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc) err = ceph_fs_debugfs_init(fsc); if (err < 0) goto fail; + } else { + root = dget(fsc->sb->s_root); } fsc->mount_state = CEPH_MOUNT_MOUNTED; diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 40b703217977..febc28f9e2c2 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -16,7 +16,7 @@ static int __remove_xattr(struct ceph_inode_info *ci, struct ceph_inode_xattr *xattr); -const struct xattr_handler ceph_other_xattr_handler; +static const struct xattr_handler ceph_other_xattr_handler; /* * List of handlers for synthetic system.* attributes. Other @@ -1086,7 +1086,7 @@ static int ceph_set_xattr_handler(const struct xattr_handler *handler, return __ceph_setxattr(inode, name, value, size, flags); } -const struct xattr_handler ceph_other_xattr_handler = { +static const struct xattr_handler ceph_other_xattr_handler = { .prefix = "", /* match any name => handlers called with full name */ .get = ceph_get_xattr_handler, .set = ceph_set_xattr_handler, diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 8347c90cf483..5eb04129f938 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -808,7 +808,11 @@ calc_seckey(struct cifs_ses *ses) struct crypto_skcipher *tfm_arc4; struct scatterlist sgin, sgout; struct skcipher_request *req; - unsigned char sec_key[CIFS_SESS_KEY_SIZE]; /* a nonce */ + unsigned char *sec_key; + + sec_key = kmalloc(CIFS_SESS_KEY_SIZE, GFP_KERNEL); + if (sec_key == NULL) + return -ENOMEM; get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE); @@ -816,7 +820,7 @@ calc_seckey(struct cifs_ses *ses) if (IS_ERR(tfm_arc4)) { rc = PTR_ERR(tfm_arc4); cifs_dbg(VFS, "could not allocate crypto API arc4\n"); - return rc; + goto out; } rc = crypto_skcipher_setkey(tfm_arc4, ses->auth_key.response, @@ -854,7 +858,8 @@ calc_seckey(struct cifs_ses *ses) out_free_cipher: crypto_free_skcipher(tfm_arc4); - +out: + kfree(sec_key); return rc; } diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 3f3185febc58..e3fed9249a04 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -3427,6 +3427,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, __u16 rc = 0; struct cifs_posix_acl *cifs_acl = (struct cifs_posix_acl *)parm_data; struct posix_acl_xattr_header *local_acl = (void *)pACL; + struct posix_acl_xattr_entry *ace = (void *)(local_acl + 1); int count; int i; @@ -3453,8 +3454,7 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL, return 0; } for (i = 0; i < count; i++) { - rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], - (struct posix_acl_xattr_entry *)(local_acl + 1)); + rc = convert_ace_to_cifs_ace(&cifs_acl->ace_array[i], &ace[i]); if (rc != 0) { /* ACE not converted */ break; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index aab5227979e2..4547aeddd12b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -412,6 +412,9 @@ cifs_reconnect(struct TCP_Server_Info *server) } } while (server->tcpStatus == CifsNeedReconnect); + if (server->tcpStatus == CifsNeedNegotiate) + mod_delayed_work(cifsiod_wq, &server->echo, 0); + return rc; } @@ -421,17 +424,25 @@ cifs_echo_request(struct work_struct *work) int rc; struct TCP_Server_Info *server = container_of(work, struct TCP_Server_Info, echo.work); - unsigned long echo_interval = server->echo_interval; + unsigned long echo_interval; + + /* + * If we need to renegotiate, set echo interval to zero to + * immediately call echo service where we can renegotiate. + */ + if (server->tcpStatus == CifsNeedNegotiate) + echo_interval = 0; + else + echo_interval = server->echo_interval; /* - * We cannot send an echo if it is disabled or until the - * NEGOTIATE_PROTOCOL request is done, which is indicated by - * server->ops->need_neg() == true. Also, no need to ping if - * we got a response recently. + * We cannot send an echo if it is disabled. + * Also, no need to ping if we got a response recently. */ if (server->tcpStatus == CifsNeedReconnect || - server->tcpStatus == CifsExiting || server->tcpStatus == CifsNew || + server->tcpStatus == CifsExiting || + server->tcpStatus == CifsNew || (server->ops->can_echo && !server->ops->can_echo(server)) || time_before(jiffies, server->lstrp + echo_interval - HZ)) goto requeue_echo; @@ -442,7 +453,7 @@ cifs_echo_request(struct work_struct *work) server->hostname); requeue_echo: - queue_delayed_work(cifsiod_wq, &server->echo, echo_interval); + queue_delayed_work(cifsiod_wq, &server->echo, server->echo_interval); } static bool diff --git a/fs/coredump.c b/fs/coredump.c index 281b768000e6..eb9c92c9b20f 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1,6 +1,7 @@ #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/freezer.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> @@ -423,7 +424,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state) if (core_waiters > 0) { struct core_thread *ptr; + freezer_do_not_count(); wait_for_completion(&core_state->startup); + freezer_count(); /* * Wait for all the threads to become inactive, so that * all the thread context (extended register state, like diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 61057b7dbddb..98f87fe8f186 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -151,7 +151,10 @@ static int do_page_crypto(struct inode *inode, struct page *src_page, struct page *dest_page, gfp_t gfp_flags) { - u8 xts_tweak[FS_XTS_TWEAK_SIZE]; + struct { + __le64 index; + u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)]; + } xts_tweak; struct skcipher_request *req = NULL; DECLARE_FS_COMPLETION_RESULT(ecr); struct scatterlist dst, src; @@ -171,17 +174,15 @@ static int do_page_crypto(struct inode *inode, req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, page_crypt_complete, &ecr); - BUILD_BUG_ON(FS_XTS_TWEAK_SIZE < sizeof(index)); - memcpy(xts_tweak, &index, sizeof(index)); - memset(&xts_tweak[sizeof(index)], 0, - FS_XTS_TWEAK_SIZE - sizeof(index)); + BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE); + xts_tweak.index = cpu_to_le64(index); + memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding)); sg_init_table(&dst, 1); sg_set_page(&dst, dest_page, PAGE_SIZE, 0); sg_init_table(&src, 1); sg_set_page(&src, src_page, PAGE_SIZE, 0); - skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, - xts_tweak); + skcipher_request_set_crypt(req, &src, &dst, PAGE_SIZE, &xts_tweak); if (rw == FS_DECRYPT) res = crypto_skcipher_decrypt(req); else diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 9a28133ac3b8..9b774f4b50c8 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -39,65 +39,54 @@ static void fname_crypt_complete(struct crypto_async_request *req, int res) static int fname_encrypt(struct inode *inode, const struct qstr *iname, struct fscrypt_str *oname) { - u32 ciphertext_len; struct skcipher_request *req = NULL; DECLARE_FS_COMPLETION_RESULT(ecr); struct fscrypt_info *ci = inode->i_crypt_info; struct crypto_skcipher *tfm = ci->ci_ctfm; int res = 0; char iv[FS_CRYPTO_BLOCK_SIZE]; - struct scatterlist src_sg, dst_sg; + struct scatterlist sg; int padding = 4 << (ci->ci_flags & FS_POLICY_FLAGS_PAD_MASK); - char *workbuf, buf[32], *alloc_buf = NULL; - unsigned lim; + unsigned int lim; + unsigned int cryptlen; lim = inode->i_sb->s_cop->max_namelen(inode); if (iname->len <= 0 || iname->len > lim) return -EIO; - ciphertext_len = max(iname->len, (u32)FS_CRYPTO_BLOCK_SIZE); - ciphertext_len = round_up(ciphertext_len, padding); - ciphertext_len = min(ciphertext_len, lim); + /* + * Copy the filename to the output buffer for encrypting in-place and + * pad it with the needed number of NUL bytes. + */ + cryptlen = max_t(unsigned int, iname->len, FS_CRYPTO_BLOCK_SIZE); + cryptlen = round_up(cryptlen, padding); + cryptlen = min(cryptlen, lim); + memcpy(oname->name, iname->name, iname->len); + memset(oname->name + iname->len, 0, cryptlen - iname->len); - if (ciphertext_len <= sizeof(buf)) { - workbuf = buf; - } else { - alloc_buf = kmalloc(ciphertext_len, GFP_NOFS); - if (!alloc_buf) - return -ENOMEM; - workbuf = alloc_buf; - } + /* Initialize the IV */ + memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); - /* Allocate request */ + /* Set up the encryption request */ req = skcipher_request_alloc(tfm, GFP_NOFS); if (!req) { printk_ratelimited(KERN_ERR - "%s: crypto_request_alloc() failed\n", __func__); - kfree(alloc_buf); + "%s: skcipher_request_alloc() failed\n", __func__); return -ENOMEM; } skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, fname_crypt_complete, &ecr); + sg_init_one(&sg, oname->name, cryptlen); + skcipher_request_set_crypt(req, &sg, &sg, cryptlen, iv); - /* Copy the input */ - memcpy(workbuf, iname->name, iname->len); - if (iname->len < ciphertext_len) - memset(workbuf + iname->len, 0, ciphertext_len - iname->len); - - /* Initialize IV */ - memset(iv, 0, FS_CRYPTO_BLOCK_SIZE); - - /* Create encryption request */ - sg_init_one(&src_sg, workbuf, ciphertext_len); - sg_init_one(&dst_sg, oname->name, ciphertext_len); - skcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv); + /* Do the encryption */ res = crypto_skcipher_encrypt(req); if (res == -EINPROGRESS || res == -EBUSY) { + /* Request is being completed asynchronously; wait for it */ wait_for_completion(&ecr.completion); res = ecr.res; } - kfree(alloc_buf); skcipher_request_free(req); if (res < 0) { printk_ratelimited(KERN_ERR @@ -105,7 +94,7 @@ static int fname_encrypt(struct inode *inode, return res; } - oname->len = ciphertext_len; + oname->len = cryptlen; return 0; } diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 82f0285f5d08..67fb6d8876d0 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -185,7 +185,7 @@ int get_crypt_info(struct inode *inode) struct crypto_skcipher *ctfm; const char *cipher_str; int keysize; - u8 raw_key[FS_MAX_KEY_SIZE]; + u8 *raw_key = NULL; int res; res = fscrypt_initialize(); @@ -238,6 +238,15 @@ retry: if (res) goto out; + /* + * This cannot be a stack buffer because it is passed to the scatterlist + * crypto API as part of key derivation. + */ + res = -ENOMEM; + raw_key = kmalloc(FS_MAX_KEY_SIZE, GFP_NOFS); + if (!raw_key) + goto out; + if (fscrypt_dummy_context_enabled(inode)) { memset(raw_key, 0x42, FS_AES_256_XTS_KEY_SIZE); goto got_key; @@ -276,7 +285,8 @@ got_key: if (res) goto out; - memzero_explicit(raw_key, sizeof(raw_key)); + kzfree(raw_key); + raw_key = NULL; if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) { put_crypt_info(crypt_info); goto retry; @@ -287,7 +297,7 @@ out: if (res == -ENOKEY) res = 0; put_crypt_info(crypt_info); - memzero_explicit(raw_key, sizeof(raw_key)); + kzfree(raw_key); return res; } diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index ed115acb5dee..6865663aac69 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -109,6 +109,8 @@ int fscrypt_process_policy(struct file *filp, if (ret) return ret; + inode_lock(inode); + if (!inode_has_encryption_context(inode)) { if (!S_ISDIR(inode->i_mode)) ret = -EINVAL; @@ -127,6 +129,8 @@ int fscrypt_process_policy(struct file *filp, ret = -EINVAL; } + inode_unlock(inode); + mnt_drop_write_file(filp); return ret; } diff --git a/fs/exec.c b/fs/exec.c index 6fcfb3f7b137..4e497b9ee71e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -191,6 +191,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, { struct page *page; int ret; + unsigned int gup_flags = FOLL_FORCE; #ifdef CONFIG_STACK_GROWSUP if (write) { @@ -199,12 +200,16 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return NULL; } #endif + + if (write) + gup_flags |= FOLL_WRITE; + /* * We are doing an exec(). 'current' is the process * doing the exec and bprm->mm is the new process's mm. */ - ret = get_user_pages_remote(current, bprm->mm, pos, 1, write, - 1, &page, NULL); + ret = get_user_pages_remote(current, bprm->mm, pos, 1, gup_flags, + &page, NULL); if (ret <= 0) return NULL; diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c index 79101651fe9e..42f9a0a0c4ca 100644 --- a/fs/exofs/dir.c +++ b/fs/exofs/dir.c @@ -137,7 +137,7 @@ Espan: bad_entry: EXOFS_ERR( "ERROR [exofs_check_page]: bad entry in directory(0x%lx): %s - " - "offset=%lu, inode=0x%llu, rec_len=%d, name_len=%d\n", + "offset=%lu, inode=0x%llx, rec_len=%d, name_len=%d\n", dir->i_ino, error, (page->index<<PAGE_SHIFT)+offs, _LLU(le64_to_cpu(p->inode_no)), rec_len, p->name_len); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index d831e24dc885..41b8b44a391c 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -622,7 +622,7 @@ static int ext2_get_blocks(struct inode *inode, u32 *bno, bool *new, bool *boundary, int create) { - int err = -EIO; + int err; int offsets[4]; Indirect chain[4]; Indirect *partial; @@ -639,7 +639,7 @@ static int ext2_get_blocks(struct inode *inode, depth = ext2_block_to_path(inode,iblock,offsets,&blocks_to_boundary); if (depth == 0) - return (err); + return -EIO; partial = ext2_get_branch(inode, depth, offsets, chain, &err); /* Simplest case - block found, no allocation needed */ @@ -761,7 +761,6 @@ static int ext2_get_blocks(struct inode *inode, ext2_splice_branch(inode, iblock, partial, indirect_blks, count); mutex_unlock(&ei->truncate_mutex); got_it: - *bno = le32_to_cpu(chain[depth-1].key); if (count > blocks_to_boundary) *boundary = true; err = count; @@ -772,6 +771,8 @@ cleanup: brelse(partial->bh); partial--; } + if (err > 0) + *bno = le32_to_cpu(chain[depth-1].key); return err; } diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 02ddec6d8a7d..fdb19543af1e 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -128,12 +128,12 @@ static void debug_print_tree(struct ext4_sb_info *sbi) node = rb_first(&sbi->system_blks); while (node) { entry = rb_entry(node, struct ext4_system_zone, node); - printk("%s%llu-%llu", first ? "" : ", ", + printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ", entry->start_blk, entry->start_blk + entry->count - 1); first = 0; node = rb_next(node); } - printk("\n"); + printk(KERN_CONT "\n"); } int ext4_setup_system_zone(struct super_block *sb) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 282a51b07c57..a8a750f59621 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -235,6 +235,7 @@ struct ext4_io_submit { #define EXT4_MAX_BLOCK_SIZE 65536 #define EXT4_MIN_BLOCK_LOG_SIZE 10 #define EXT4_MAX_BLOCK_LOG_SIZE 16 +#define EXT4_MAX_CLUSTER_LOG_SIZE 30 #ifdef __KERNEL__ # define EXT4_BLOCK_SIZE(s) ((s)->s_blocksize) #else diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 3ef1df6ae9ec..1aba469f8220 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -27,16 +27,15 @@ #ifdef CONFIG_EXT4_DEBUG extern ushort ext4_mballoc_debug; -#define mb_debug(n, fmt, a...) \ - do { \ - if ((n) <= ext4_mballoc_debug) { \ - printk(KERN_DEBUG "(%s, %d): %s: ", \ - __FILE__, __LINE__, __func__); \ - printk(fmt, ## a); \ - } \ - } while (0) +#define mb_debug(n, fmt, ...) \ +do { \ + if ((n) <= ext4_mballoc_debug) { \ + printk(KERN_DEBUG "(%s, %d): %s: " fmt, \ + __FILE__, __LINE__, __func__, ##__VA_ARGS__); \ + } \ +} while (0) #else -#define mb_debug(n, fmt, a...) no_printk(fmt, ## a) +#define mb_debug(n, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif #define EXT4_MB_HISTORY_ALLOC 1 /* allocation */ diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index f92f10d4f66a..104f8bfba718 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -577,12 +577,13 @@ static inline unsigned dx_node_limit(struct inode *dir) static void dx_show_index(char * label, struct dx_entry *entries) { int i, n = dx_get_count (entries); - printk(KERN_DEBUG "%s index ", label); + printk(KERN_DEBUG "%s index", label); for (i = 0; i < n; i++) { - printk("%x->%lu ", i ? dx_get_hash(entries + i) : - 0, (unsigned long)dx_get_block(entries + i)); + printk(KERN_CONT " %x->%lu", + i ? dx_get_hash(entries + i) : 0, + (unsigned long)dx_get_block(entries + i)); } - printk("\n"); + printk(KERN_CONT "\n"); } struct stats @@ -679,7 +680,7 @@ static struct stats dx_show_leaf(struct inode *dir, } de = ext4_next_entry(de, size); } - printk("(%i)\n", names); + printk(KERN_CONT "(%i)\n", names); return (struct stats) { names, space, 1 }; } @@ -798,7 +799,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, q = entries + count - 1; while (p <= q) { m = p + (q - p) / 2; - dxtrace(printk(".")); + dxtrace(printk(KERN_CONT ".")); if (dx_get_hash(m) > hash) q = m - 1; else @@ -810,7 +811,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, at = entries; while (n--) { - dxtrace(printk(",")); + dxtrace(printk(KERN_CONT ",")); if (dx_get_hash(++at) > hash) { at--; @@ -821,7 +822,8 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } at = p - 1; - dxtrace(printk(" %x->%u\n", at == entries ? 0 : dx_get_hash(at), + dxtrace(printk(KERN_CONT " %x->%u\n", + at == entries ? 0 : dx_get_hash(at), dx_get_block(at))); frame->entries = entries; frame->at = at; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6db81fbcbaa6..52b0530c5d65 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -597,14 +597,15 @@ void __ext4_std_error(struct super_block *sb, const char *function, void __ext4_abort(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) { + struct va_format vaf; va_list args; save_error_info(sb, function, line); va_start(args, fmt); - printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: ", sb->s_id, - function, line); - vprintk(fmt, args); - printk("\n"); + vaf.fmt = fmt; + vaf.va = &args; + printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n", + sb->s_id, function, line, &vaf); va_end(args); if ((sb->s_flags & MS_RDONLY) == 0) { @@ -2715,12 +2716,12 @@ static void print_daily_error_info(unsigned long arg) es->s_first_error_func, le32_to_cpu(es->s_first_error_line)); if (es->s_first_error_ino) - printk(": inode %u", + printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_first_error_ino)); if (es->s_first_error_block) - printk(": block %llu", (unsigned long long) + printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_first_error_block)); - printk("\n"); + printk(KERN_CONT "\n"); } if (es->s_last_error_time) { printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d", @@ -2729,12 +2730,12 @@ static void print_daily_error_info(unsigned long arg) es->s_last_error_func, le32_to_cpu(es->s_last_error_line)); if (es->s_last_error_ino) - printk(": inode %u", + printk(KERN_CONT ": inode %u", le32_to_cpu(es->s_last_error_ino)); if (es->s_last_error_block) - printk(": block %llu", (unsigned long long) + printk(KERN_CONT ": block %llu", (unsigned long long) le64_to_cpu(es->s_last_error_block)); - printk("\n"); + printk(KERN_CONT "\n"); } mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */ } @@ -3564,7 +3565,15 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (blocksize < EXT4_MIN_BLOCK_SIZE || blocksize > EXT4_MAX_BLOCK_SIZE) { ext4_msg(sb, KERN_ERR, - "Unsupported filesystem blocksize %d", blocksize); + "Unsupported filesystem blocksize %d (%d log_block_size)", + blocksize, le32_to_cpu(es->s_log_block_size)); + goto failed_mount; + } + if (le32_to_cpu(es->s_log_block_size) > + (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log block size: %u", + le32_to_cpu(es->s_log_block_size)); goto failed_mount; } @@ -3696,6 +3705,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) "block size (%d)", clustersize, blocksize); goto failed_mount; } + if (le32_to_cpu(es->s_log_cluster_size) > + (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) { + ext4_msg(sb, KERN_ERR, + "Invalid log cluster size: %u", + le32_to_cpu(es->s_log_cluster_size)); + goto failed_mount; + } sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) - le32_to_cpu(es->s_log_block_size); sbi->s_clusters_per_group = diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 73bcfd41f5f2..42145be5c6b4 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -223,14 +223,18 @@ static struct attribute *ext4_attrs[] = { EXT4_ATTR_FEATURE(lazy_itable_init); EXT4_ATTR_FEATURE(batched_discard); EXT4_ATTR_FEATURE(meta_bg_resize); +#ifdef CONFIG_EXT4_FS_ENCRYPTION EXT4_ATTR_FEATURE(encryption); +#endif EXT4_ATTR_FEATURE(metadata_csum_seed); static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(lazy_itable_init), ATTR_LIST(batched_discard), ATTR_LIST(meta_bg_resize), +#ifdef CONFIG_EXT4_FS_ENCRYPTION ATTR_LIST(encryption), +#endif ATTR_LIST(metadata_csum_seed), NULL, }; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index c15d63389957..d77be9e9f535 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -61,18 +61,12 @@ #include "acl.h" #ifdef EXT4_XATTR_DEBUG -# define ea_idebug(inode, f...) do { \ - printk(KERN_DEBUG "inode %s:%lu: ", \ - inode->i_sb->s_id, inode->i_ino); \ - printk(f); \ - printk("\n"); \ - } while (0) -# define ea_bdebug(bh, f...) do { \ - printk(KERN_DEBUG "block %pg:%lu: ", \ - bh->b_bdev, (unsigned long) bh->b_blocknr); \ - printk(f); \ - printk("\n"); \ - } while (0) +# define ea_idebug(inode, fmt, ...) \ + printk(KERN_DEBUG "inode %s:%lu: " fmt "\n", \ + inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__) +# define ea_bdebug(bh, fmt, ...) \ + printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \ + bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__) #else # define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) @@ -241,7 +235,7 @@ __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, int error = -EFSCORRUPTED; if (((void *) header >= end) || - (header->h_magic != le32_to_cpu(EXT4_XATTR_MAGIC))) + (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC))) goto errout; error = ext4_xattr_check_names(entry, end, entry); errout: diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index 93985c64d8a8..6f14ee923acd 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -852,16 +852,16 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi, for (segno = start_segno; segno < end_segno; segno++) { - if (get_valid_blocks(sbi, segno, 1) == 0 || - unlikely(f2fs_cp_error(sbi))) - goto next; - /* find segment summary of victim */ sum_page = find_get_page(META_MAPPING(sbi), GET_SUM_BLOCK(sbi, segno)); - f2fs_bug_on(sbi, !PageUptodate(sum_page)); f2fs_put_page(sum_page, 0); + if (get_valid_blocks(sbi, segno, 1) == 0 || + !PageUptodate(sum_page) || + unlikely(f2fs_cp_error(sbi))) + goto next; + sum = page_address(sum_page); f2fs_bug_on(sbi, type != GET_SUM_TYPE((&sum->footer))); diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 6a4d0e5418a1..096f79997f75 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -286,6 +286,11 @@ const struct dentry_operations fuse_dentry_operations = { .d_release = fuse_dentry_release, }; +const struct dentry_operations fuse_root_dentry_operations = { + .d_init = fuse_dentry_init, + .d_release = fuse_dentry_release, +}; + int fuse_valid_type(int m) { return S_ISREG(m) || S_ISDIR(m) || S_ISLNK(m) || S_ISCHR(m) || @@ -1734,8 +1739,6 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) * This should be done on write(), truncate() and chown(). */ if (!fc->handle_killpriv) { - int kill; - /* * ia_mode calculation may have used stale i_mode. * Refresh and recalculate. @@ -1745,12 +1748,11 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr) return ret; attr->ia_mode = inode->i_mode; - kill = should_remove_suid(entry); - if (kill & ATTR_KILL_SUID) { + if (inode->i_mode & S_ISUID) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISUID; } - if (kill & ATTR_KILL_SGID) { + if ((inode->i_mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { attr->ia_valid |= ATTR_MODE; attr->ia_mode &= ~S_ISGID; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index abc66a6237fd..2401c5dabb2a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1985,6 +1985,10 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, { struct inode *inode = page->mapping->host; + /* Haven't copied anything? Skip zeroing, size extending, dirtying. */ + if (!copied) + goto unlock; + if (!PageUptodate(page)) { /* Zero any unwritten bytes at the end of the page */ size_t endoff = (pos + copied) & ~PAGE_MASK; @@ -1995,6 +1999,8 @@ static int fuse_write_end(struct file *file, struct address_space *mapping, fuse_write_update_size(inode, pos + copied); set_page_dirty(page); + +unlock: unlock_page(page); put_page(page); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 0dfbb136e59a..91307940c8ac 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -692,6 +692,7 @@ static inline u64 get_node_id(struct inode *inode) extern const struct file_operations fuse_dev_operations; extern const struct dentry_operations fuse_dentry_operations; +extern const struct dentry_operations fuse_root_dentry_operations; /** * Inode to nodeid comparison. diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 17141099f2e7..6fe6a88ecb4a 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1131,10 +1131,11 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) err = -ENOMEM; root = fuse_get_root_inode(sb, d.rootmode); + sb->s_d_op = &fuse_root_dentry_operations; root_dentry = d_make_root(root); if (!root_dentry) goto err_dev_free; - /* only now - we want root dentry with NULL ->d_op */ + /* Root dentry doesn't have .d_revalidate */ sb->s_d_op = &fuse_dentry_operations; init_req = fuse_request_alloc(0); diff --git a/fs/iomap.c b/fs/iomap.c index 013d1d36fbbf..a8ee8c33ca78 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length, struct page *page = data; int ret; - ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length, - NULL, iomap); + ret = __block_write_begin_int(page, pos, length, NULL, iomap); if (ret) return ret; @@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, } while (len > 0) { - ret = iomap_apply(inode, start, len, 0, ops, &ctx, + ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx, iomap_fiemap_actor); /* inode with no (attribute) mapping will give ENOENT */ if (ret == -ENOENT) diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index ad0c745ebad7..871c8b392099 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -687,6 +687,11 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) pri_bh = NULL; root_found: + /* We don't support read-write mounts */ + if (!(s->s_flags & MS_RDONLY)) { + error = -EACCES; + goto out_freebh; + } if (joliet_level && (pri == NULL || !opt.rock)) { /* This is the case of Joliet with the norock mount flag. @@ -1501,9 +1506,6 @@ struct inode *__isofs_iget(struct super_block *sb, static struct dentry *isofs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) { - /* We don't support read-write mounts */ - if (!(flags & MS_RDONLY)) - return ERR_PTR(-EACCES); return mount_bdev(fs_type, flags, dev_name, data, isofs_fill_super); } diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c index 98b3eb7d8eaf..0ec137310320 100644 --- a/fs/isofs/rock.c +++ b/fs/isofs/rock.c @@ -377,9 +377,9 @@ repeat: { int p; for (p = 0; p < rr->u.ER.len_id; p++) - printk("%c", rr->u.ER.data[p]); + printk(KERN_CONT "%c", rr->u.ER.data[p]); } - printk("\n"); + printk(KERN_CONT "\n"); break; case SIG('P', 'X'): inode->i_mode = isonum_733(rr->u.PX.mode); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3d8246a9faa4..e1652665bd93 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1149,6 +1149,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "file as BJ_Reserved"); spin_lock(&journal->j_list_lock); __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); + spin_unlock(&journal->j_list_lock); } else if (jh->b_transaction == journal->j_committing_transaction) { /* first access by this transaction */ jh->b_modified = 0; @@ -1156,8 +1157,8 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "set next transaction"); spin_lock(&journal->j_list_lock); jh->b_next_transaction = transaction; + spin_unlock(&journal->j_list_lock); } - spin_unlock(&journal->j_list_lock); jbd_unlock_bh_state(bh); /* diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 2bcb86e6e6ca..78219d5644e9 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -911,6 +911,7 @@ const struct file_operations kernfs_file_fops = { .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, + .fsync = noop_fsync, }; /** diff --git a/fs/locks.c b/fs/locks.c index ce93b416b490..22c5b4aa4961 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1609,6 +1609,7 @@ int fcntl_getlease(struct file *filp) ctx = smp_load_acquire(&inode->i_flctx); if (ctx && !list_empty_careful(&ctx->flc_lease)) { + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); list_for_each_entry(fl, &ctx->flc_lease, fl_list) { @@ -1618,6 +1619,8 @@ int fcntl_getlease(struct file *filp) break; } spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); + locks_dispose_list(&dispose); } return type; @@ -2529,11 +2532,14 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) if (list_empty(&ctx->flc_lease)) return; + percpu_down_read_preempt_disable(&file_rwsem); spin_lock(&ctx->flc_lock); list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) if (filp == fl->fl_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); + percpu_up_read_preempt_enable(&file_rwsem); + locks_dispose_list(&dispose); } diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 217847679f0e..2905479f214a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -344,9 +344,10 @@ static void bl_write_cleanup(struct work_struct *work) u64 start = hdr->args.offset & (loff_t)PAGE_MASK; u64 end = (hdr->args.offset + hdr->args.count + PAGE_SIZE - 1) & (loff_t)PAGE_MASK; + u64 lwb = hdr->args.offset + hdr->args.count; ext_tree_mark_written(bl, start >> SECTOR_SHIFT, - (end - start) >> SECTOR_SHIFT, end); + (end - start) >> SECTOR_SHIFT, lwb); } pnfs_ld_write_done(hdr); diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 532d8e242d4d..484bebc20bca 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -197,7 +197,7 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, } ret = -EPROTONOSUPPORT; - if (minorversion == 0) + if (!IS_ENABLED(CONFIG_NFS_V4_1) || minorversion == 0) ret = nfs4_callback_up_net(serv, net); else if (xprt->ops->bc_up) ret = xprt->ops->bc_up(serv, net); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 7555ba889d1f..ebecfb8fba06 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -314,7 +314,8 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat /* Match the full socket address */ if (!rpc_cmp_addr_port(sap, clap)) /* Match all xprt_switch full socket addresses */ - if (!rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient, + if (IS_ERR(clp->cl_rpcclient) || + !rpc_clnt_xprt_switch_has_addr(clp->cl_rpcclient, sap)) continue; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index c8162c660c44..5551e8ef67fd 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -98,7 +98,7 @@ rename_retry: return end; } namelen = strlen(base); - if (flags & NFS_PATH_CANONICAL) { + if (*end == '/') { /* Strip off excess slashes in base string */ while (namelen > 0 && base[namelen - 1] == '/') namelen--; diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 9b3a82abab07..1452177c822d 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -542,6 +542,13 @@ static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state) return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0; } +static inline bool nfs4_state_match_open_stateid_other(const struct nfs4_state *state, + const nfs4_stateid *stateid) +{ + return test_bit(NFS_OPEN_STATE, &state->flags) && + nfs4_stateid_match_other(&state->open_stateid, stateid); +} + #else #define nfs4_close_state(a, b) do { } while (0) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ad917bd72b38..241da19b7da4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1451,7 +1451,6 @@ static void nfs_resync_open_stateid_locked(struct nfs4_state *state) } static void nfs_clear_open_stateid_locked(struct nfs4_state *state, - nfs4_stateid *arg_stateid, nfs4_stateid *stateid, fmode_t fmode) { clear_bit(NFS_O_RDWR_STATE, &state->flags); @@ -1469,10 +1468,9 @@ static void nfs_clear_open_stateid_locked(struct nfs4_state *state, } if (stateid == NULL) return; - /* Handle races with OPEN */ - if (!nfs4_stateid_match_other(arg_stateid, &state->open_stateid) || - (nfs4_stateid_match_other(stateid, &state->open_stateid) && - !nfs4_stateid_is_newer(stateid, &state->open_stateid))) { + /* Handle OPEN+OPEN_DOWNGRADE races */ + if (nfs4_stateid_match_other(stateid, &state->open_stateid) && + !nfs4_stateid_is_newer(stateid, &state->open_stateid)) { nfs_resync_open_stateid_locked(state); return; } @@ -1486,7 +1484,9 @@ static void nfs_clear_open_stateid(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode) { write_seqlock(&state->seqlock); - nfs_clear_open_stateid_locked(state, arg_stateid, stateid, fmode); + /* Ignore, if the CLOSE argment doesn't match the current stateid */ + if (nfs4_state_match_open_stateid_other(state, arg_stateid)) + nfs_clear_open_stateid_locked(state, stateid, fmode); write_sequnlock(&state->seqlock); if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags)) nfs4_schedule_state_manager(state->owner->so_server->nfs_client); @@ -1545,7 +1545,7 @@ static int update_open_stateid(struct nfs4_state *state, struct nfs_client *clp = server->nfs_client; struct nfs_inode *nfsi = NFS_I(state->inode); struct nfs_delegation *deleg_cur; - nfs4_stateid freeme = {0}; + nfs4_stateid freeme = { }; int ret = 0; fmode &= (FMODE_READ|FMODE_WRITE); @@ -2564,15 +2564,23 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) static int nfs41_check_expired_locks(struct nfs4_state *state) { int status, ret = NFS_OK; - struct nfs4_lock_state *lsp; + struct nfs4_lock_state *lsp, *prev = NULL; struct nfs_server *server = NFS_SERVER(state->inode); if (!test_bit(LK_STATE_IN_USE, &state->flags)) goto out; + + spin_lock(&state->state_lock); list_for_each_entry(lsp, &state->lock_states, ls_locks) { if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) { struct rpc_cred *cred = lsp->ls_state->owner->so_cred; + atomic_inc(&lsp->ls_count); + spin_unlock(&state->state_lock); + + nfs4_put_lock_state(prev); + prev = lsp; + status = nfs41_test_and_free_expired_stateid(server, &lsp->ls_stateid, cred); @@ -2585,10 +2593,14 @@ static int nfs41_check_expired_locks(struct nfs4_state *state) set_bit(NFS_LOCK_LOST, &lsp->ls_flags); } else if (status != NFS_OK) { ret = status; - break; + nfs4_put_lock_state(prev); + goto out; } + spin_lock(&state->state_lock); } - }; + } + spin_unlock(&state->state_lock); + nfs4_put_lock_state(prev); out: return ret; } @@ -3122,7 +3134,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) } else if (is_rdwr) calldata->arg.fmode |= FMODE_READ|FMODE_WRITE; - if (!nfs4_valid_open_stateid(state)) + if (!nfs4_valid_open_stateid(state) || + test_bit(NFS_OPEN_STATE, &state->flags) == 0) call_close = 0; spin_unlock(&state->owner->so_lock); @@ -5569,6 +5582,7 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case 0: renew_lease(data->res.server, data->timestamp); + break; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_EXPIRED: @@ -5579,8 +5593,6 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) case -NFS4ERR_OLD_STATEID: case -NFS4ERR_STALE_STATEID: task->tk_status = 0; - if (data->roc) - pnfs_roc_set_barrier(data->inode, data->roc_barrier); break; default: if (nfs4_async_handle_error(task, data->res.server, @@ -5590,6 +5602,8 @@ static void nfs4_delegreturn_done(struct rpc_task *task, void *calldata) } } data->rpc_status = task->tk_status; + if (data->roc && data->rpc_status == 0) + pnfs_roc_set_barrier(data->inode, data->roc_barrier); } static void nfs4_delegreturn_release(void *calldata) diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index b62973045a3e..a61350f75c74 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -178,12 +178,14 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, __must_hold(&tbl->slot_tbl_lock) { struct nfs4_slot *slot; + int ret; slot = nfs4_lookup_slot(tbl, slotid); - if (IS_ERR(slot)) - return PTR_ERR(slot); - *seq_nr = slot->seq_nr; - return 0; + ret = PTR_ERR_OR_ZERO(slot); + if (!ret) + *seq_nr = slot->seq_nr; + + return ret; } /* @@ -196,7 +198,7 @@ static int nfs4_slot_get_seqid(struct nfs4_slot_table *tbl, u32 slotid, static bool nfs4_slot_seqid_in_use(struct nfs4_slot_table *tbl, u32 slotid, u32 seq_nr) { - u32 cur_seq; + u32 cur_seq = 0; bool ret = false; spin_lock(&tbl->slot_tbl_lock); diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 5f4281ec5f72..0959c9661662 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1547,6 +1547,7 @@ restart: ssleep(1); case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: + case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: case -NFS4ERR_RECLAIM_BAD: case -NFS4ERR_RECLAIM_CONFLICT: diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 56b2d96f9103..259ef85f435a 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -146,6 +146,8 @@ set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh, u32 id; int i; + if (fsinfo->nlayouttypes == 0) + goto out_no_driver; if (!(server->nfs_client->cl_exchange_flags & (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) { printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n", diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index b10d557f9c9e..ee36efd5aece 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -84,6 +84,8 @@ struct nfsd_net { struct list_head client_lru; struct list_head close_lru; struct list_head del_recall_lru; + + /* protected by blocked_locks_lock */ struct list_head blocked_locks_lru; struct delayed_work laundromat_work; @@ -91,6 +93,9 @@ struct nfsd_net { /* client_lock protects the client lru list and session hash table */ spinlock_t client_lock; + /* protects blocked_locks_lru */ + spinlock_t blocked_locks_lock; + struct file *rec_file; bool in_grace; const struct nfsd4_client_tracking_ops *client_tracking_ops; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 9752beb78659..4b4beaaa4eaa 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -217,7 +217,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, { struct nfsd4_blocked_lock *cur, *found = NULL; - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); @@ -226,7 +226,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, break; } } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); if (found) posix_unblock_lock(&found->nbl_lock); return found; @@ -1227,9 +1227,7 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); - - lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); @@ -1238,12 +1236,12 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) static void release_lock_stateid(struct nfs4_ol_stateid *stp) { - struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner); + struct nfs4_client *clp = stp->st_stid.sc_client; bool unhashed; - spin_lock(&oo->oo_owner.so_client->cl_lock); + spin_lock(&clp->cl_lock); unhashed = unhash_lock_stateid(stp); - spin_unlock(&oo->oo_owner.so_client->cl_lock); + spin_unlock(&clp->cl_lock); if (unhashed) nfs4_put_stid(&stp->st_stid); } @@ -4665,7 +4663,7 @@ nfs4_laundromat(struct nfsd_net *nn) * indefinitely once the lock does become free. */ BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); @@ -4678,7 +4676,7 @@ nfs4_laundromat(struct nfsd_net *nn) list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&nn->blocked_locks_lru, @@ -5439,13 +5437,13 @@ nfsd4_lm_notify(struct file_lock *fl) bool queue = false; /* An empty list means that something else is going to be using it */ - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); queue = true; } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); if (queue) nfsd4_run_cb(&nbl->nbl_cb); @@ -5868,10 +5866,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (fl_flags & FL_SLEEP) { nbl->nbl_time = jiffies; - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); } err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); @@ -5900,10 +5898,10 @@ out: if (nbl) { /* dequeue it if we queued it before */ if (fl_flags & FL_SLEEP) { - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); } @@ -6943,9 +6941,11 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->client_lru); INIT_LIST_HEAD(&nn->close_lru); INIT_LIST_HEAD(&nn->del_recall_lru); - INIT_LIST_HEAD(&nn->blocked_locks_lru); spin_lock_init(&nn->client_lock); + spin_lock_init(&nn->blocked_locks_lock); + INIT_LIST_HEAD(&nn->blocked_locks_lru); + INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); get_net(net); @@ -7063,14 +7063,14 @@ nfs4_state_shutdown_net(struct net *net) } BUG_ON(!list_empty(&reaplist)); - spin_lock(&nn->client_lock); + spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } - spin_unlock(&nn->client_lock); + spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&nn->blocked_locks_lru, diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index a18613579001..0ee19ecc982d 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1544,8 +1544,6 @@ const struct file_operations ntfs_dir_ops = { .iterate = ntfs_readdir, /* Read directory contents. */ #ifdef NTFS_RW .fsync = ntfs_dir_fsync, /* Sync a directory to disk. */ - /*.aio_fsync = ,*/ /* Sync all outstanding async - i/o operations on a kiocb. */ #endif /* NTFS_RW */ /*.ioctl = ,*/ /* Perform function on the mounted filesystem. */ diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index e7054e2ac922..3ecb9f337b7d 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -3699,7 +3699,7 @@ static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash, static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb, struct ocfs2_dx_root_block *dx_root) { - int credits = ocfs2_clusters_to_blocks(osb->sb, 2); + int credits = ocfs2_clusters_to_blocks(osb->sb, 3); credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list); credits += ocfs2_quota_trans_credits(osb->sb); diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index aeb60f791418..36795eed40b0 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -178,6 +178,8 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) len -= bytes; } + if (!error) + error = vfs_fsync(new_file, 0); fput(new_file); out_fput: fput(old_file); diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index c58f01babf30..7fb53d055537 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -270,9 +270,6 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type) if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; - if (!realinode->i_op->get_acl) - return NULL; - old_cred = ovl_override_creds(inode->i_sb); acl = get_acl(realinode, type); revert_creds(old_cred); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index bcf3965be819..0e100856c7b8 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -328,11 +328,11 @@ static struct dentry *ovl_d_real(struct dentry *dentry, if (!real) goto bug; + /* Handle recursion */ + real = d_real(real, inode, open_flags); + if (!inode || inode == d_inode(real)) return real; - - /* Handle recursion */ - return d_real(real, inode, open_flags); bug: WARN(1, "ovl_d_real(%pd4, %s:%lu): real dentry not found\n", dentry, inode ? inode->i_sb->s_id : "NULL", inode ? inode->i_ino : 0); @@ -1037,6 +1037,21 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler, posix_acl_release(acl); + /* + * Check if sgid bit needs to be cleared (actual setacl operation will + * be done with mounter's capabilities and so that won't do it for us). + */ + if (unlikely(inode->i_mode & S_ISGID) && + handler->flags == ACL_TYPE_ACCESS && + !in_group_p(inode->i_gid) && + !capable_wrt_inode_uidgid(inode, CAP_FSETID)) { + struct iattr iattr = { .ia_valid = ATTR_KILL_SGID }; + + err = ovl_setattr(dentry, &iattr); + if (err) + return err; + } + err = ovl_xattr_set(dentry, handler->name, value, size, flags); if (!err) ovl_copyattr(ovl_inode_real(inode, NULL), inode); diff --git a/fs/proc/array.c b/fs/proc/array.c index 89600fd5963d..81818adb8e9e 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -412,10 +412,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, mm = get_task_mm(task); if (mm) { vsize = task_vsize(mm); - if (permitted) { - eip = KSTK_EIP(task); - esp = KSTK_ESP(task); - } + /* + * esp and eip are intentionally zeroed out. There is no + * non-racy way to read them without freezing the task. + * Programs that need reliable values can use ptrace(2). + */ } get_task_comm(tcomm, task); diff --git a/fs/proc/base.c b/fs/proc/base.c index c2964d890c9a..ca651ac00660 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -832,6 +832,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, unsigned long addr = *ppos; ssize_t copied; char *page; + unsigned int flags; if (!mm) return 0; @@ -844,6 +845,11 @@ static ssize_t mem_rw(struct file *file, char __user *buf, if (!atomic_inc_not_zero(&mm->mm_users)) goto free; + /* Maybe we should limit FOLL_FORCE to actual ptrace users? */ + flags = FOLL_FORCE; + if (write) + flags |= FOLL_WRITE; + while (count > 0) { int this_len = min_t(int, count, PAGE_SIZE); @@ -852,7 +858,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, break; } - this_len = access_remote_vm(mm, addr, page, this_len, write); + this_len = access_remote_vm(mm, addr, page, this_len, flags); if (!this_len) { if (!copied) copied = -EIO; @@ -964,8 +970,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); - retval = access_remote_vm(mm, (env_start + src), - page, this_len, 0); + retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); if (retval <= 0) { ret = retval; @@ -1007,6 +1012,9 @@ static ssize_t auxv_read(struct file *file, char __user *buf, { struct mm_struct *mm = file->private_data; unsigned int nwords = 0; + + if (!mm) + return 0; do { nwords += 2; } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6909582ce5e5..35b92d81692f 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -266,24 +266,15 @@ static int do_maps_open(struct inode *inode, struct file *file, * /proc/PID/maps that is the stack of the main task. */ static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, int is_pid) + struct vm_area_struct *vma) { - int stack = 0; - - if (is_pid) { - stack = vma->vm_start <= vma->vm_mm->start_stack && - vma->vm_end >= vma->vm_mm->start_stack; - } else { - struct inode *inode = priv->inode; - struct task_struct *task; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) - stack = vma_is_stack_for_task(vma, task); - rcu_read_unlock(); - } - return stack; + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; } static void @@ -354,7 +345,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - if (is_stack(priv, vma, is_pid)) + if (is_stack(priv, vma)) name = "[stack]"; } @@ -1669,7 +1660,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else if (is_stack(proc_priv, vma, is_pid)) { + } else if (is_stack(proc_priv, vma)) { seq_puts(m, " stack"); } diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index faacb0c0d857..37175621e890 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -124,25 +124,17 @@ unsigned long task_statm(struct mm_struct *mm, } static int is_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, int is_pid) + struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; - int stack = 0; - - if (is_pid) { - stack = vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack; - } else { - struct inode *inode = priv->inode; - struct task_struct *task; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) - stack = vma_is_stack_for_task(vma, task); - rcu_read_unlock(); - } - return stack; + + /* + * We make no effort to guess what a given thread considers to be + * its "stack". It's not even well-defined for programs written + * languages like Go. + */ + return vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; } /* @@ -184,7 +176,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm && is_stack(priv, vma, is_pid)) { + } else if (mm && is_stack(priv, vma)) { seq_pad(m, ' '); seq_printf(m, "[stack]"); } diff --git a/fs/splice.c b/fs/splice.c index 153d4f3bd441..5a7750bd2eea 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -299,13 +299,8 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, { struct iov_iter to; struct kiocb kiocb; - loff_t isize; int idx, ret; - isize = i_size_read(in->f_mapping->host); - if (unlikely(*ppos >= isize)) - return 0; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); idx = to.idx; init_sync_kiocb(&kiocb, in); @@ -413,7 +408,8 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, if (res <= 0) return -ENOMEM; - nr_pages = res / PAGE_SIZE; + BUG_ON(dummy); + nr_pages = DIV_ROUND_UP(res, PAGE_SIZE); vec = __vec; if (nr_pages > PIPE_DEF_BUFFERS) { diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index c8f60df2733e..ca16c5d7bab1 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -439,7 +439,7 @@ static unsigned int vfs_dent_type(uint8_t type) */ static int ubifs_readdir(struct file *file, struct dir_context *ctx) { - int err; + int err = 0; struct qstr nm; union ubifs_key key; struct ubifs_dent_node *dent; @@ -541,14 +541,20 @@ out: kfree(file->private_data); file->private_data = NULL; - if (err != -ENOENT) { + if (err != -ENOENT) ubifs_err(c, "cannot find next direntry, error %d", err); - return err; - } + else + /* + * -ENOENT is a non-fatal error in this context, the TNC uses + * it to indicate that the cursor moved past the current directory + * and readdir() has to stop. + */ + err = 0; + /* 2 is a special value indicating that there are no more direntries */ ctx->pos = 2; - return 0; + return err; } /* Free saved readdir() state when the directory is closed */ @@ -1060,9 +1066,9 @@ static void unlock_4_inodes(struct inode *inode1, struct inode *inode2, mutex_unlock(&ubifs_inode(inode1)->ui_mutex); } -static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry, - unsigned int flags) +static int do_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) { struct ubifs_info *c = old_dir->i_sb->s_fs_info; struct inode *old_inode = d_inode(old_dentry); @@ -1323,7 +1329,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, return err; } -static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry, +static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { @@ -1336,7 +1342,7 @@ static int ubifs_rename2(struct inode *old_dir, struct dentry *old_dentry, if (flags & RENAME_EXCHANGE) return ubifs_xrename(old_dir, old_dentry, new_dir, new_dentry); - return ubifs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); + return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry, @@ -1387,7 +1393,7 @@ const struct inode_operations ubifs_dir_inode_operations = { .mkdir = ubifs_mkdir, .rmdir = ubifs_rmdir, .mknod = ubifs_mknod, - .rename = ubifs_rename2, + .rename = ubifs_rename, .setattr = ubifs_setattr, .getattr = ubifs_getattr, .listxattr = ubifs_listxattr, diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index 6c2f4d41ed73..d9f9615bfd71 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -172,6 +172,7 @@ out_cancel: host_ui->xattr_cnt -= 1; host_ui->xattr_size -= CALC_DENT_SIZE(nm->len); host_ui->xattr_size -= CALC_XATTR_BYTES(size); + host_ui->xattr_names -= nm->len; mutex_unlock(&host_ui->ui_mutex); out_free: make_bad_inode(inode); @@ -478,6 +479,7 @@ out_cancel: host_ui->xattr_cnt += 1; host_ui->xattr_size += CALC_DENT_SIZE(nm->len); host_ui->xattr_size += CALC_XATTR_BYTES(ui->data_len); + host_ui->xattr_names += nm->len; mutex_unlock(&host_ui->ui_mutex); ubifs_release_budget(c, &req); make_bad_inode(inode); diff --git a/fs/xattr.c b/fs/xattr.c index 3368659c471e..2d13b4e62fae 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -170,7 +170,7 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { struct inode *inode = dentry->d_inode; - int error = -EOPNOTSUPP; + int error = -EAGAIN; int issec = !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN); @@ -183,15 +183,21 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, security_inode_post_setxattr(dentry, name, value, size, flags); } - } else if (issec) { - const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; - + } else { if (unlikely(is_bad_inode(inode))) return -EIO; - error = security_inode_setsecurity(inode, suffix, value, - size, flags); - if (!error) - fsnotify_xattr(dentry); + } + if (error == -EAGAIN) { + error = -EOPNOTSUPP; + + if (issec) { + const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; + + error = security_inode_setsecurity(inode, suffix, value, + size, flags); + if (!error) + fsnotify_xattr(dentry); + } } return error; diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index c27344cf38e1..c6eb21940783 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3974,9 +3974,6 @@ xfs_bmap_remap_alloc( * allocating, so skip that check by pretending to be freeing. */ error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING); - if (error) - goto error0; -error0: xfs_perag_put(args.pag); if (error) trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_); @@ -3999,6 +3996,39 @@ xfs_bmap_alloc( return xfs_bmap_btalloc(ap); } +/* Trim extent to fit a logical block range. */ +void +xfs_trim_extent( + struct xfs_bmbt_irec *irec, + xfs_fileoff_t bno, + xfs_filblks_t len) +{ + xfs_fileoff_t distance; + xfs_fileoff_t end = bno + len; + + if (irec->br_startoff + irec->br_blockcount <= bno || + irec->br_startoff >= end) { + irec->br_blockcount = 0; + return; + } + + if (irec->br_startoff < bno) { + distance = bno - irec->br_startoff; + if (isnullstartblock(irec->br_startblock)) + irec->br_startblock = DELAYSTARTBLOCK; + if (irec->br_startblock != DELAYSTARTBLOCK && + irec->br_startblock != HOLESTARTBLOCK) + irec->br_startblock += distance; + irec->br_startoff += distance; + irec->br_blockcount -= distance; + } + + if (end < irec->br_startoff + irec->br_blockcount) { + distance = irec->br_startoff + irec->br_blockcount - end; + irec->br_blockcount -= distance; + } +} + /* * Trim the returned map to the required bounds */ @@ -4829,6 +4859,219 @@ xfs_bmap_split_indlen( return stolen; } +int +xfs_bmap_del_extent_delay( + struct xfs_inode *ip, + int whichfork, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork); + struct xfs_bmbt_irec new; + int64_t da_old, da_new, da_diff = 0; + xfs_fileoff_t del_endoff, got_endoff; + xfs_filblks_t got_indlen, new_indlen, stolen; + int error = 0, state = 0; + bool isrt; + + XFS_STATS_INC(mp, xs_del_exlist); + + isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip); + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + da_old = startblockval(got->br_startblock); + da_new = 0; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + + if (isrt) { + int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount); + + do_div(rtexts, mp->m_sb.sb_rextsize); + xfs_mod_frextents(mp, rtexts); + } + + /* + * Update the inode delalloc counter now and wait to update the + * sb counters as we might have to borrow some blocks for the + * indirect block accounting. + */ + xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0, + isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS); + ip->i_delayed_blks -= del->br_blockcount; + + if (whichfork == XFS_COW_FORK) + state |= BMAP_COWFORK; + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = got->br_blockcount - del->br_blockcount; + da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, + got->br_blockcount), da_old); + got->br_startblock = nullstartblock((int)da_new); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + * + * Distribute the original indlen reservation across the two new + * extents. Steal blocks from the deleted extent if necessary. + * Stealing blocks simply fudges the fdblocks accounting below. + * Warn if either of the new indlen reservations is zero as this + * can lead to delalloc problems. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + + got->br_blockcount = del->br_startoff - got->br_startoff; + got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount); + + new.br_blockcount = got_endoff - del_endoff; + new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount); + + WARN_ON_ONCE(!got_indlen || !new_indlen); + stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen, + del->br_blockcount); + + got->br_startblock = nullstartblock((int)got_indlen); + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_state = got->br_state; + new.br_startblock = nullstartblock((int)new_indlen); + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + + da_new = got_indlen + new_indlen - stolen; + del->br_blockcount -= stolen; + break; + } + + ASSERT(da_old >= da_new); + da_diff = da_old - da_new; + if (!isrt) + da_diff += del->br_blockcount; + if (da_diff) + xfs_mod_fdblocks(mp, da_diff, false); + return error; +} + +void +xfs_bmap_del_extent_cow( + struct xfs_inode *ip, + xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec new; + xfs_fileoff_t del_endoff, got_endoff; + int state = BMAP_COWFORK; + + XFS_STATS_INC(mp, xs_del_exlist); + + del_endoff = del->br_startoff + del->br_blockcount; + got_endoff = got->br_startoff + got->br_blockcount; + + ASSERT(*idx >= 0); + ASSERT(*idx < ifp->if_bytes / sizeof(struct xfs_bmbt_rec)); + ASSERT(del->br_blockcount > 0); + ASSERT(got->br_startoff <= del->br_startoff); + ASSERT(got_endoff >= del_endoff); + ASSERT(!isnullstartblock(got->br_startblock)); + + if (got->br_startoff == del->br_startoff) + state |= BMAP_LEFT_CONTIG; + if (got_endoff == del_endoff) + state |= BMAP_RIGHT_CONTIG; + + switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) { + case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG: + /* + * Matches the whole extent. Delete the entry. + */ + xfs_iext_remove(ip, *idx, 1, state); + --*idx; + break; + case BMAP_LEFT_CONTIG: + /* + * Deleting the first part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_startoff = del_endoff; + got->br_blockcount -= del->br_blockcount; + got->br_startblock = del->br_startblock + del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case BMAP_RIGHT_CONTIG: + /* + * Deleting the last part of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount -= del->br_blockcount; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + break; + case 0: + /* + * Deleting the middle of the extent. + */ + trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_); + got->br_blockcount = del->br_startoff - got->br_startoff; + xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got); + trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_); + + new.br_startoff = del_endoff; + new.br_blockcount = got_endoff - del_endoff; + new.br_state = got->br_state; + new.br_startblock = del->br_startblock + del->br_blockcount; + + ++*idx; + xfs_iext_insert(ip, *idx, 1, &new, state); + break; + } +} + /* * Called by xfs_bmapi to update file extent records and the btree * after removing space (or undoing a delayed allocation). @@ -5171,175 +5414,6 @@ done: return error; } -/* Remove an extent from the CoW fork. Similar to xfs_bmap_del_extent. */ -int -xfs_bunmapi_cow( - struct xfs_inode *ip, - struct xfs_bmbt_irec *del) -{ - xfs_filblks_t da_new; - xfs_filblks_t da_old; - xfs_fsblock_t del_endblock = 0; - xfs_fileoff_t del_endoff; - int delay; - struct xfs_bmbt_rec_host *ep; - int error; - struct xfs_bmbt_irec got; - xfs_fileoff_t got_endoff; - struct xfs_ifork *ifp; - struct xfs_mount *mp; - xfs_filblks_t nblks; - struct xfs_bmbt_irec new; - /* REFERENCED */ - uint qfield; - xfs_filblks_t temp; - xfs_filblks_t temp2; - int state = BMAP_COWFORK; - int eof; - xfs_extnum_t eidx; - - mp = ip->i_mount; - XFS_STATS_INC(mp, xs_del_exlist); - - ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof, - &eidx, &got, &new); - - ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp; - ASSERT((eidx >= 0) && (eidx < ifp->if_bytes / - (uint)sizeof(xfs_bmbt_rec_t))); - ASSERT(del->br_blockcount > 0); - ASSERT(got.br_startoff <= del->br_startoff); - del_endoff = del->br_startoff + del->br_blockcount; - got_endoff = got.br_startoff + got.br_blockcount; - ASSERT(got_endoff >= del_endoff); - delay = isnullstartblock(got.br_startblock); - ASSERT(isnullstartblock(del->br_startblock) == delay); - qfield = 0; - error = 0; - /* - * If deleting a real allocation, must free up the disk space. - */ - if (!delay) { - nblks = del->br_blockcount; - qfield = XFS_TRANS_DQ_BCOUNT; - /* - * Set up del_endblock and cur for later. - */ - del_endblock = del->br_startblock + del->br_blockcount; - da_old = da_new = 0; - } else { - da_old = startblockval(got.br_startblock); - da_new = 0; - nblks = 0; - } - qfield = qfield; - nblks = nblks; - - /* - * Set flag value to use in switch statement. - * Left-contig is 2, right-contig is 1. - */ - switch (((got.br_startoff == del->br_startoff) << 1) | - (got_endoff == del_endoff)) { - case 3: - /* - * Matches the whole extent. Delete the entry. - */ - xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK); - --eidx; - break; - - case 2: - /* - * Deleting the first part of the extent. - */ - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_startoff(ep, del_endoff); - temp = got.br_blockcount - del->br_blockcount; - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - xfs_bmbt_set_startblock(ep, del_endblock); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 1: - /* - * Deleting the last part of the extent. - */ - temp = got.br_blockcount - del->br_blockcount; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - if (delay) { - temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp), - da_old); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - da_new = temp; - break; - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - break; - - case 0: - /* - * Deleting the middle of the extent. - */ - temp = del->br_startoff - got.br_startoff; - trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_); - xfs_bmbt_set_blockcount(ep, temp); - new.br_startoff = del_endoff; - temp2 = got_endoff - del_endoff; - new.br_blockcount = temp2; - new.br_state = got.br_state; - if (!delay) { - new.br_startblock = del_endblock; - } else { - temp = xfs_bmap_worst_indlen(ip, temp); - xfs_bmbt_set_startblock(ep, nullstartblock((int)temp)); - temp2 = xfs_bmap_worst_indlen(ip, temp2); - new.br_startblock = nullstartblock((int)temp2); - da_new = temp + temp2; - while (da_new > da_old) { - if (temp) { - temp--; - da_new--; - xfs_bmbt_set_startblock(ep, - nullstartblock((int)temp)); - } - if (da_new == da_old) - break; - if (temp2) { - temp2--; - da_new--; - new.br_startblock = - nullstartblock((int)temp2); - } - } - } - trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_); - xfs_iext_insert(ip, eidx + 1, 1, &new, state); - ++eidx; - break; - } - - /* - * Account for change in delayed indirect blocks. - * Nothing to do for disk quota accounting here. - */ - ASSERT(da_old >= da_new); - if (da_old > da_new) - xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false); - - return error; -} - /* * Unmap (remove) blocks from a file. * If nexts is nonzero then the number of extents to remove is limited to diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index f97db7132564..7cae6ec27fa6 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -190,6 +190,8 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, #define XFS_BMAP_TRACE_EXLIST(ip,c,w) #endif +void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, + xfs_filblks_t len); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, @@ -221,7 +223,11 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, int flags, xfs_extnum_t nexts, xfs_fsblock_t *firstblock, struct xfs_defer_ops *dfops, int *done); -int xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del); +int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork, + xfs_extnum_t *idx, struct xfs_bmbt_irec *got, + struct xfs_bmbt_irec *del); +void xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx, + struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del); int xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx, xfs_extnum_t num); uint xfs_default_attroffset(struct xfs_inode *ip); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5c8e6f2ce44f..0e80993c8a59 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4826,7 +4826,7 @@ xfs_btree_calc_size( return rval; } -int +static int xfs_btree_count_blocks_helper( struct xfs_btree_cur *cur, int level, diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 613c5cf19436..5c2929f94bd3 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -199,9 +199,9 @@ xfs_defer_intake_work( struct xfs_defer_pending *dfp; list_for_each_entry(dfp, &dop->dop_intake, dfp_list) { - trace_xfs_defer_intake_work(tp->t_mountp, dfp); dfp->dfp_intent = dfp->dfp_type->create_intent(tp, dfp->dfp_count); + trace_xfs_defer_intake_work(tp->t_mountp, dfp); list_sort(tp->t_mountp, &dfp->dfp_work, dfp->dfp_type->diff_items); list_for_each(li, &dfp->dfp_work) @@ -221,21 +221,14 @@ xfs_defer_trans_abort( struct xfs_defer_pending *dfp; trace_xfs_defer_trans_abort(tp->t_mountp, dop); - /* - * If the transaction was committed, drop the intent reference - * since we're bailing out of here. The other reference is - * dropped when the intent hits the AIL. If the transaction - * was not committed, the intent is freed by the intent item - * unlock handler on abort. - */ - if (!dop->dop_committed) - return; - /* Abort intent items. */ + /* Abort intent items that don't have a done item. */ list_for_each_entry(dfp, &dop->dop_pending, dfp_list) { trace_xfs_defer_pending_abort(tp->t_mountp, dfp); - if (!dfp->dfp_done) + if (dfp->dfp_intent && !dfp->dfp_done) { dfp->dfp_type->abort_intent(dfp->dfp_intent); + dfp->dfp_intent = NULL; + } } /* Shut down FS. */ diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c index 3cc3cf767474..ac9a003dd29a 100644 --- a/fs/xfs/libxfs/xfs_dquot_buf.c +++ b/fs/xfs/libxfs/xfs_dquot_buf.c @@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc( if (mp->m_quotainfo) ndquots = mp->m_quotainfo->qi_dqperchunk; else - ndquots = xfs_calc_dquots_per_chunk( - XFS_BB_TO_FSB(mp, bp->b_length)); + ndquots = xfs_calc_dquots_per_chunk(bp->b_length); for (i = 0; i < ndquots; i++, d++) { if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk), diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f6547fc5e016..6b7579e7b60a 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -865,7 +865,6 @@ typedef struct xfs_timestamp { * padding field for v3 inodes. */ #define XFS_DINODE_MAGIC 0x494e /* 'IN' */ -#define XFS_DINODE_GOOD_VERSION(v) ((v) >= 1 && (v) <= 3) typedef struct xfs_dinode { __be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */ __be16 di_mode; /* mode and type of file */ diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 8de9a3a29589..134424fac434 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -57,6 +57,17 @@ xfs_inobp_check( } #endif +bool +xfs_dinode_good_version( + struct xfs_mount *mp, + __u8 version) +{ + if (xfs_sb_version_hascrc(&mp->m_sb)) + return version == 3; + + return version == 1 || version == 2; +} + /* * If we are doing readahead on an inode buffer, we might be in log recovery * reading an inode allocation buffer that hasn't yet been replayed, and hence @@ -91,7 +102,7 @@ xfs_inode_buf_verify( dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog)); di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) && - XFS_DINODE_GOOD_VERSION(dip->di_version); + xfs_dinode_good_version(mp, dip->di_version); if (unlikely(XFS_TEST_ERROR(!di_ok, mp, XFS_ERRTAG_ITOBP_INOTOBP, XFS_RANDOM_ITOBP_INOTOBP))) { diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 62d9d4681c8c..3cfe12a4f58a 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -74,6 +74,8 @@ void xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from); void xfs_log_dinode_to_disk(struct xfs_log_dinode *from, struct xfs_dinode *to); +bool xfs_dinode_good_version(struct xfs_mount *mp, __u8 version); + #if defined(DEBUG) void xfs_inobp_check(struct xfs_mount *, struct xfs_buf *); #else diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index a314fc7b56fa..6e4f7f900fea 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -249,6 +249,7 @@ xfs_file_dio_aio_read( struct xfs_inode *ip = XFS_I(inode); loff_t isize = i_size_read(inode); size_t count = iov_iter_count(to); + loff_t end = iocb->ki_pos + count - 1; struct iov_iter data; struct xfs_buftarg *target; ssize_t ret = 0; @@ -272,49 +273,21 @@ xfs_file_dio_aio_read( file_accessed(iocb->ki_filp); - /* - * Locking is a bit tricky here. If we take an exclusive lock for direct - * IO, we effectively serialise all new concurrent read IO to this file - * and block it behind IO that is currently in progress because IO in - * progress holds the IO lock shared. We only need to hold the lock - * exclusive to blow away the page cache, so only take lock exclusively - * if the page cache needs invalidation. This allows the normal direct - * IO case of no page cache pages to proceeed concurrently without - * serialisation. - */ xfs_rw_ilock(ip, XFS_IOLOCK_SHARED); if (mapping->nrpages) { - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); - xfs_rw_ilock(ip, XFS_IOLOCK_EXCL); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); + if (ret) + goto out_unlock; /* - * The generic dio code only flushes the range of the particular - * I/O. Because we take an exclusive lock here, this whole - * sequence is considerably more expensive for us. This has a - * noticeable performance impact for any file with cached pages, - * even when outside of the range of the particular I/O. - * - * Hence, amortize the cost of the lock against a full file - * flush and reduce the chances of repeated iolock cycles going - * forward. + * Invalidate whole pages. This can return an error if we fail + * to invalidate a page, but this should never happen on XFS. + * Warn if it does fail. */ - if (mapping->nrpages) { - ret = filemap_write_and_wait(mapping); - if (ret) { - xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); - return ret; - } - - /* - * Invalidate whole pages. This can return an error if - * we fail to invalidate a page, but this should never - * happen on XFS. Warn if it does fail. - */ - ret = invalidate_inode_pages2(mapping); - WARN_ON_ONCE(ret); - ret = 0; - } - xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); + WARN_ON_ONCE(ret); + ret = 0; } data = *to; @@ -324,8 +297,9 @@ xfs_file_dio_aio_read( iocb->ki_pos += ret; iov_iter_advance(to, ret); } - xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); +out_unlock: + xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); return ret; } @@ -570,61 +544,49 @@ xfs_file_dio_aio_write( if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL; - /* "unaligned" here means not aligned to a filesystem block */ - if ((iocb->ki_pos & mp->m_blockmask) || - ((iocb->ki_pos + count) & mp->m_blockmask)) - unaligned_io = 1; - /* - * We don't need to take an exclusive lock unless there page cache needs - * to be invalidated or unaligned IO is being executed. We don't need to - * consider the EOF extension case here because - * xfs_file_aio_write_checks() will relock the inode as necessary for - * EOF zeroing cases and fill out the new inode size as appropriate. + * Don't take the exclusive iolock here unless the I/O is unaligned to + * the file system block size. We don't need to consider the EOF + * extension case here because xfs_file_aio_write_checks() will relock + * the inode as necessary for EOF zeroing cases and fill out the new + * inode size as appropriate. */ - if (unaligned_io || mapping->nrpages) + if ((iocb->ki_pos & mp->m_blockmask) || + ((iocb->ki_pos + count) & mp->m_blockmask)) { + unaligned_io = 1; iolock = XFS_IOLOCK_EXCL; - else + } else { iolock = XFS_IOLOCK_SHARED; - xfs_rw_ilock(ip, iolock); - - /* - * Recheck if there are cached pages that need invalidate after we got - * the iolock to protect against other threads adding new pages while - * we were waiting for the iolock. - */ - if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) { - xfs_rw_iunlock(ip, iolock); - iolock = XFS_IOLOCK_EXCL; - xfs_rw_ilock(ip, iolock); } + xfs_rw_ilock(ip, iolock); + ret = xfs_file_aio_write_checks(iocb, from, &iolock); if (ret) goto out; count = iov_iter_count(from); end = iocb->ki_pos + count - 1; - /* - * See xfs_file_dio_aio_read() for why we do a full-file flush here. - */ if (mapping->nrpages) { - ret = filemap_write_and_wait(VFS_I(ip)->i_mapping); + ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end); if (ret) goto out; + /* * Invalidate whole pages. This can return an error if we fail * to invalidate a page, but this should never happen on XFS. * Warn if it does fail. */ - ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping); + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } /* * If we are doing unaligned IO, wait for all other IO to drain, - * otherwise demote the lock if we had to flush cached pages + * otherwise demote the lock if we had to take the exclusive lock + * for other reasons in xfs_file_aio_write_checks. */ if (unaligned_io) inode_dio_wait(inode); @@ -947,134 +909,6 @@ out_unlock: return error; } -/* - * Flush all file writes out to disk. - */ -static int -xfs_file_wait_for_io( - struct inode *inode, - loff_t offset, - size_t len) -{ - loff_t rounding; - loff_t ioffset; - loff_t iendoffset; - loff_t bs; - int ret; - - bs = inode->i_sb->s_blocksize; - inode_dio_wait(inode); - - rounding = max_t(xfs_off_t, bs, PAGE_SIZE); - ioffset = round_down(offset, rounding); - iendoffset = round_up(offset + len, rounding) - 1; - ret = filemap_write_and_wait_range(inode->i_mapping, ioffset, - iendoffset); - return ret; -} - -/* Hook up to the VFS reflink function */ -STATIC int -xfs_file_share_range( - struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - bool is_dedupe) -{ - struct inode *inode_in; - struct inode *inode_out; - ssize_t ret; - loff_t bs; - loff_t isize; - int same_inode; - loff_t blen; - unsigned int flags = 0; - - inode_in = file_inode(file_in); - inode_out = file_inode(file_out); - bs = inode_out->i_sb->s_blocksize; - - /* Don't touch certain kinds of inodes */ - if (IS_IMMUTABLE(inode_out)) - return -EPERM; - if (IS_SWAPFILE(inode_in) || - IS_SWAPFILE(inode_out)) - return -ETXTBSY; - - /* Reflink only works within this filesystem. */ - if (inode_in->i_sb != inode_out->i_sb) - return -EXDEV; - same_inode = (inode_in->i_ino == inode_out->i_ino); - - /* Don't reflink dirs, pipes, sockets... */ - if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) - return -EISDIR; - if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) - return -EINVAL; - if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) - return -EINVAL; - - /* Don't share DAX file data for now. */ - if (IS_DAX(inode_in) || IS_DAX(inode_out)) - return -EINVAL; - - /* Are we going all the way to the end? */ - isize = i_size_read(inode_in); - if (isize == 0) - return 0; - if (len == 0) - len = isize - pos_in; - - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + len < pos_in || pos_out + len < pos_out || - pos_in + len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - - /* Wait for the completion of any pending IOs on srcfile */ - ret = xfs_file_wait_for_io(inode_in, pos_in, len); - if (ret) - goto out; - ret = xfs_file_wait_for_io(inode_out, pos_out, len); - if (ret) - goto out; - - if (is_dedupe) - flags |= XFS_REFLINK_DEDUPE; - ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out), - pos_out, len, flags); - if (ret < 0) - goto out; - -out: - return ret; -} - STATIC ssize_t xfs_file_copy_range( struct file *file_in, @@ -1086,7 +920,7 @@ xfs_file_copy_range( { int error; - error = xfs_file_share_range(file_in, pos_in, file_out, pos_out, + error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); if (error) return error; @@ -1101,7 +935,7 @@ xfs_file_clone_range( loff_t pos_out, u64 len) { - return xfs_file_share_range(file_in, pos_in, file_out, pos_out, + return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, false); } @@ -1124,7 +958,7 @@ xfs_file_dedupe_range( if (len > XFS_MAX_DEDUPE_LEN) len = XFS_MAX_DEDUPE_LEN; - error = xfs_file_share_range(src_file, loff, dst_file, dst_loff, + error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff, len, true); if (error) return error; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 14796b744e0a..f295049db681 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1656,9 +1656,9 @@ void xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_set_eofblocks_tag(ip); + trace_xfs_inode_set_cowblocks_tag(ip); return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, - trace_xfs_perag_set_eofblocks, + trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1666,7 +1666,7 @@ void xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { - trace_xfs_inode_clear_eofblocks_tag(ip); + trace_xfs_inode_clear_cowblocks_tag(ip); return __xfs_inode_clear_eofblocks_tag(ip, - trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG); + trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d907eb9f8ef3..436e109bb01e 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay( xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx, &got, &prev); if (!eof && got.br_startoff <= offset_fsb) { + if (xfs_is_reflink_inode(ip)) { + bool shared; + + end_fsb = min(XFS_B_TO_FSB(mp, offset + count), + maxbytes_fsb); + xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb); + error = xfs_reflink_reserve_cow(ip, &got, &shared); + if (error) + goto out_unlock; + } + trace_xfs_iomap_found(ip, offset, count, 0, &got); goto done; } @@ -961,19 +972,13 @@ xfs_file_iomap_begin( struct xfs_mount *mp = ip->i_mount; struct xfs_bmbt_irec imap; xfs_fileoff_t offset_fsb, end_fsb; - bool shared, trimmed; int nimaps = 1, error = 0; + bool shared = false, trimmed = false; unsigned lockmode; if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { - error = xfs_reflink_reserve_cow_range(ip, offset, length); - if (error < 0) - return error; - } - if ((flags & IOMAP_WRITE) && !IS_DAX(inode) && !xfs_get_extsz_hint(ip)) { /* Reserve delalloc blocks for regular writeback. */ @@ -981,7 +986,16 @@ xfs_file_iomap_begin( iomap); } - lockmode = xfs_ilock_data_map_shared(ip); + /* + * COW writes will allocate delalloc space, so we need to make sure + * to take the lock exclusively here. + */ + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + lockmode = XFS_ILOCK_EXCL; + xfs_ilock(ip, XFS_ILOCK_EXCL); + } else { + lockmode = xfs_ilock_data_map_shared(ip); + } ASSERT(offset <= mp->m_super->s_maxbytes); if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes) @@ -991,16 +1005,24 @@ xfs_file_iomap_begin( error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, &nimaps, 0); - if (error) { - xfs_iunlock(ip, lockmode); - return error; + if (error) + goto out_unlock; + + if (flags & IOMAP_REPORT) { + /* Trim the mapping to the nearest shared extent boundary. */ + error = xfs_reflink_trim_around_shared(ip, &imap, &shared, + &trimmed); + if (error) + goto out_unlock; } - /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); - if (error) { - xfs_iunlock(ip, lockmode); - return error; + if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) { + error = xfs_reflink_reserve_cow(ip, &imap, &shared); + if (error) + goto out_unlock; + + end_fsb = imap.br_startoff + imap.br_blockcount; + length = XFS_FSB_TO_B(mp, end_fsb) - offset; } if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) { @@ -1039,6 +1061,9 @@ xfs_file_iomap_begin( if (shared) iomap->flags |= IOMAP_F_SHARED; return 0; +out_unlock: + xfs_iunlock(ip, lockmode); + return error; } static int diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index fc7873942bea..b341f10cf481 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1009,6 +1009,7 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: + mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 5965e9455d91..a279b4e7f5fe 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared( if (!xfs_is_reflink_inode(ip) || ISUNWRITTEN(irec) || irec->br_startblock == HOLESTARTBLOCK || - irec->br_startblock == DELAYSTARTBLOCK) { + irec->br_startblock == DELAYSTARTBLOCK || + isnullstartblock(irec->br_startblock)) { *shared = false; return 0; } @@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared( } } -/* Create a CoW reservation for a range of blocks within a file. */ -static int -__xfs_reflink_reserve_cow( +/* + * Trim the passed in imap to the next shared/unshared extent boundary, and + * if imap->br_startoff points to a shared extent reserve space for it in the + * COW fork. In this case *shared is set to true, else to false. + * + * Note that imap will always contain the block numbers for the existing blocks + * in the data fork, as the upper layers need them for read-modify-write + * operations. + */ +int +xfs_reflink_reserve_cow( struct xfs_inode *ip, - xfs_fileoff_t *offset_fsb, - xfs_fileoff_t end_fsb, - bool *skipped) + struct xfs_bmbt_irec *imap, + bool *shared) { - struct xfs_bmbt_irec got, prev, imap; - xfs_fileoff_t orig_end_fsb; - int nimaps, eof = 0, error = 0; - bool shared = false, trimmed = false; + struct xfs_bmbt_irec got, prev; + xfs_fileoff_t end_fsb, orig_end_fsb; + int eof = 0, error = 0; + bool trimmed; xfs_extnum_t idx; xfs_extlen_t align; - /* Already reserved? Skip the refcount btree access. */ - xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx, + /* + * Search the COW fork extent list first. This serves two purposes: + * first this implement the speculative preallocation using cowextisze, + * so that we also unshared block adjacent to shared blocks instead + * of just the shared blocks themselves. Second the lookup in the + * extent list is generally faster than going out to the shared extent + * tree. + */ + xfs_bmap_search_extents(ip, imap->br_startoff, XFS_COW_FORK, &eof, &idx, &got, &prev); - if (!eof && got.br_startoff <= *offset_fsb) { - end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount; - trace_xfs_reflink_cow_found(ip, &got); - goto done; - } + if (!eof && got.br_startoff <= imap->br_startoff) { + trace_xfs_reflink_cow_found(ip, imap); + xfs_trim_extent(imap, got.br_startoff, got.br_blockcount); - /* Read extent from the source file. */ - nimaps = 1; - error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, - &imap, &nimaps, 0); - if (error) - goto out_unlock; - ASSERT(nimaps == 1); + *shared = true; + return 0; + } /* Trim the mapping to the nearest shared extent boundary. */ - error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed); + error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed); if (error) - goto out_unlock; - - end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount; + return error; /* Not shared? Just report the (potentially capped) extent. */ - if (!shared) { - *skipped = true; - goto done; - } + if (!*shared) + return 0; /* * Fork all the shared blocks from our write offset until the end of @@ -278,72 +283,38 @@ __xfs_reflink_reserve_cow( */ error = xfs_qm_dqattach_locked(ip, 0); if (error) - goto out_unlock; + return error; + + end_fsb = orig_end_fsb = imap->br_startoff + imap->br_blockcount; align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip)); if (align) end_fsb = roundup_64(end_fsb, align); retry: - error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb, - end_fsb - *offset_fsb, &got, - &prev, &idx, eof); + error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff, + end_fsb - imap->br_startoff, &got, &prev, &idx, eof); switch (error) { case 0: break; case -ENOSPC: case -EDQUOT: /* retry without any preallocation */ - trace_xfs_reflink_cow_enospc(ip, &imap); + trace_xfs_reflink_cow_enospc(ip, imap); if (end_fsb != orig_end_fsb) { end_fsb = orig_end_fsb; goto retry; } /*FALLTHRU*/ default: - goto out_unlock; + return error; } if (end_fsb != orig_end_fsb) xfs_inode_set_cowblocks_tag(ip); trace_xfs_reflink_cow_alloc(ip, &got); -done: - *offset_fsb = end_fsb; -out_unlock: - return error; -} - -/* Create a CoW reservation for part of a file. */ -int -xfs_reflink_reserve_cow_range( - struct xfs_inode *ip, - xfs_off_t offset, - xfs_off_t count) -{ - struct xfs_mount *mp = ip->i_mount; - xfs_fileoff_t offset_fsb, end_fsb; - bool skipped = false; - int error; - - trace_xfs_reflink_reserve_cow_range(ip, offset, count); - - offset_fsb = XFS_B_TO_FSBT(mp, offset); - end_fsb = XFS_B_TO_FSB(mp, offset + count); - - xfs_ilock(ip, XFS_ILOCK_EXCL); - while (offset_fsb < end_fsb) { - error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb, - &skipped); - if (error) { - trace_xfs_reflink_reserve_cow_range_error(ip, error, - _RET_IP_); - break; - } - } - xfs_iunlock(ip, XFS_ILOCK_EXCL); - - return error; + return 0; } /* Allocate all CoW reservations covering a range of blocks in a file. */ @@ -358,9 +329,8 @@ __xfs_reflink_allocate_cow( struct xfs_defer_ops dfops; struct xfs_trans *tp; xfs_fsblock_t first_block; - xfs_fileoff_t next_fsb; int nimaps = 1, error; - bool skipped = false; + bool shared; xfs_defer_init(&dfops, &first_block); @@ -371,33 +341,38 @@ __xfs_reflink_allocate_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); - next_fsb = *offset_fsb; - error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped); + /* Read extent from the source file. */ + nimaps = 1; + error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb, + &imap, &nimaps, 0); + if (error) + goto out_unlock; + ASSERT(nimaps == 1); + + error = xfs_reflink_reserve_cow(ip, &imap, &shared); if (error) goto out_trans_cancel; - if (skipped) { - *offset_fsb = next_fsb; + if (!shared) { + *offset_fsb = imap.br_startoff + imap.br_blockcount; goto out_trans_cancel; } xfs_trans_ijoin(tp, ip, 0); - error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb, + error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount, XFS_BMAPI_COWFORK, &first_block, XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), &imap, &nimaps, &dfops); if (error) goto out_trans_cancel; - /* We might not have been able to map the whole delalloc extent */ - *offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb); - error = xfs_defer_finish(&tp, &dfops, NULL); if (error) goto out_trans_cancel; error = xfs_trans_commit(tp); + *offset_fsb = imap.br_startoff + imap.br_blockcount; out_unlock: xfs_iunlock(ip, XFS_ILOCK_EXCL); return error; @@ -536,58 +511,49 @@ xfs_reflink_cancel_cow_blocks( xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb) { - struct xfs_bmbt_irec irec; - xfs_filblks_t count_fsb; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; + xfs_extnum_t idx; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error = 0; - int nimaps; + int error = 0, eof = 0; if (!xfs_is_reflink_inode(ip)) return 0; - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - break; - ASSERT(nimaps == 1); - - trace_xfs_reflink_cancel_cow(ip, &irec); + xfs_bmap_search_extents(ip, offset_fsb, XFS_COW_FORK, &eof, &idx, + &got, &prev); + if (eof) + return 0; - if (irec.br_startblock == DELAYSTARTBLOCK) { - /* Free a delayed allocation. */ - xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount, - false); - ip->i_delayed_blks -= irec.br_blockcount; + while (got.br_startoff < end_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + trace_xfs_reflink_cancel_cow(ip, &del); - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); + if (isnullstartblock(del.br_startblock)) { + error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, + &idx, &got, &del); if (error) break; - } else if (irec.br_startblock == HOLESTARTBLOCK) { - /* empty */ } else { xfs_trans_ijoin(*tpp, ip, 0); xfs_defer_init(&dfops, &firstfsb); /* Free the CoW orphan record. */ error = xfs_refcount_free_cow_extent(ip->i_mount, - &dfops, irec.br_startblock, - irec.br_blockcount); + &dfops, del.br_startblock, + del.br_blockcount); if (error) break; xfs_bmap_add_free(ip->i_mount, &dfops, - irec.br_startblock, irec.br_blockcount, + del.br_startblock, del.br_blockcount, NULL); /* Update quota accounting */ xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT, - -(long)irec.br_blockcount); + -(long)del.br_blockcount); /* Roll the transaction */ error = xfs_defer_finish(tpp, &dfops, ip); @@ -597,15 +563,18 @@ xfs_reflink_cancel_cow_blocks( } /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &irec); - if (error) - break; + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); } - /* Roll on... */ - offset_fsb = irec.br_startoff + irec.br_blockcount; + if (++idx >= ifp->if_bytes / sizeof(struct xfs_bmbt_rec)) + break; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } + /* clear tag if cow fork is emptied */ + if (!ifp->if_bytes) + xfs_inode_clear_cowblocks_tag(ip); + return error; } @@ -668,25 +637,26 @@ xfs_reflink_end_cow( xfs_off_t offset, xfs_off_t count) { - struct xfs_bmbt_irec irec; - struct xfs_bmbt_irec uirec; + struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); + struct xfs_bmbt_irec got, prev, del; struct xfs_trans *tp; xfs_fileoff_t offset_fsb; xfs_fileoff_t end_fsb; - xfs_filblks_t count_fsb; xfs_fsblock_t firstfsb; struct xfs_defer_ops dfops; - int error; + int error, eof = 0; unsigned int resblks; - xfs_filblks_t ilen; xfs_filblks_t rlen; - int nimaps; + xfs_extnum_t idx; trace_xfs_reflink_end_cow(ip, offset, count); + /* No COW extents? That's easy! */ + if (ifp->if_bytes == 0) + return 0; + offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count); - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); /* Start a rolling transaction to switch the mappings */ resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK); @@ -698,72 +668,65 @@ xfs_reflink_end_cow( xfs_ilock(ip, XFS_ILOCK_EXCL); xfs_trans_ijoin(tp, ip, 0); - /* Go find the old extent in the CoW fork. */ - while (offset_fsb < end_fsb) { - /* Read extent from the source file */ - nimaps = 1; - count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb); - error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec, - &nimaps, XFS_BMAPI_COWFORK); - if (error) - goto out_cancel; - ASSERT(nimaps == 1); + xfs_bmap_search_extents(ip, end_fsb - 1, XFS_COW_FORK, &eof, &idx, + &got, &prev); - ASSERT(irec.br_startblock != DELAYSTARTBLOCK); - trace_xfs_reflink_cow_remap(ip, &irec); + /* If there is a hole at end_fsb - 1 go to the previous extent */ + if (eof || got.br_startoff > end_fsb) { + ASSERT(idx > 0); + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); + } - /* - * We can have a hole in the CoW fork if part of a directio - * write is CoW but part of it isn't. - */ - rlen = ilen = irec.br_blockcount; - if (irec.br_startblock == HOLESTARTBLOCK) + /* Walk backwards until we're out of the I/O range... */ + while (got.br_startoff + got.br_blockcount > offset_fsb) { + del = got; + xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb); + + /* Extent delete may have bumped idx forward */ + if (!del.br_blockcount) { + idx--; goto next_extent; + } + + ASSERT(!isnullstartblock(got.br_startblock)); /* Unmap the old blocks in the data fork. */ - while (rlen) { - xfs_defer_init(&dfops, &firstfsb); - error = __xfs_bunmapi(tp, ip, irec.br_startoff, - &rlen, 0, 1, &firstfsb, &dfops); - if (error) - goto out_defer; - - /* - * Trim the extent to whatever got unmapped. - * Remember, bunmapi works backwards. - */ - uirec.br_startblock = irec.br_startblock + rlen; - uirec.br_startoff = irec.br_startoff + rlen; - uirec.br_blockcount = irec.br_blockcount - rlen; - irec.br_blockcount = rlen; - trace_xfs_reflink_cow_remap_piece(ip, &uirec); + xfs_defer_init(&dfops, &firstfsb); + rlen = del.br_blockcount; + error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1, + &firstfsb, &dfops); + if (error) + goto out_defer; - /* Free the CoW orphan record. */ - error = xfs_refcount_free_cow_extent(tp->t_mountp, - &dfops, uirec.br_startblock, - uirec.br_blockcount); - if (error) - goto out_defer; + /* Trim the extent to whatever got unmapped. */ + if (rlen) { + xfs_trim_extent(&del, del.br_startoff + rlen, + del.br_blockcount - rlen); + } + trace_xfs_reflink_cow_remap(ip, &del); - /* Map the new blocks into the data fork. */ - error = xfs_bmap_map_extent(tp->t_mountp, &dfops, - ip, &uirec); - if (error) - goto out_defer; + /* Free the CoW orphan record. */ + error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops, + del.br_startblock, del.br_blockcount); + if (error) + goto out_defer; - /* Remove the mapping from the CoW fork. */ - error = xfs_bunmapi_cow(ip, &uirec); - if (error) - goto out_defer; + /* Map the new blocks into the data fork. */ + error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del); + if (error) + goto out_defer; - error = xfs_defer_finish(&tp, &dfops, ip); - if (error) - goto out_defer; - } + /* Remove the mapping from the CoW fork. */ + xfs_bmap_del_extent_cow(ip, &idx, &got, &del); + + error = xfs_defer_finish(&tp, &dfops, ip); + if (error) + goto out_defer; next_extent: - /* Roll on... */ - offset_fsb = irec.br_startoff + ilen; + if (idx < 0) + break; + xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), &got); } error = xfs_trans_commit(tp); @@ -774,7 +737,6 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); -out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: @@ -1312,19 +1274,26 @@ out_error: */ int xfs_reflink_remap_range( - struct xfs_inode *src, - xfs_off_t srcoff, - struct xfs_inode *dest, - xfs_off_t destoff, - xfs_off_t len, - unsigned int flags) + struct file *file_in, + loff_t pos_in, + struct file *file_out, + loff_t pos_out, + u64 len, + bool is_dedupe) { + struct inode *inode_in = file_inode(file_in); + struct xfs_inode *src = XFS_I(inode_in); + struct inode *inode_out = file_inode(file_out); + struct xfs_inode *dest = XFS_I(inode_out); struct xfs_mount *mp = src->i_mount; + loff_t bs = inode_out->i_sb->s_blocksize; + bool same_inode = (inode_in == inode_out); xfs_fileoff_t sfsbno, dfsbno; xfs_filblks_t fsblen; - int error; xfs_extlen_t cowextsize; - bool is_same; + loff_t isize; + ssize_t ret; + loff_t blen; if (!xfs_sb_version_hasreflink(&mp->m_sb)) return -EOPNOTSUPP; @@ -1332,17 +1301,8 @@ xfs_reflink_remap_range( if (XFS_FORCED_SHUTDOWN(mp)) return -EIO; - /* Don't reflink realtime inodes */ - if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) - return -EINVAL; - - if (flags & ~XFS_REFLINK_ALL) - return -EINVAL; - - trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff); - /* Lock both files against IO */ - if (src->i_ino == dest->i_ino) { + if (same_inode) { xfs_ilock(src, XFS_IOLOCK_EXCL); xfs_ilock(src, XFS_MMAPLOCK_EXCL); } else { @@ -1350,39 +1310,126 @@ xfs_reflink_remap_range( xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL); } + /* Don't touch certain kinds of inodes */ + ret = -EPERM; + if (IS_IMMUTABLE(inode_out)) + goto out_unlock; + + ret = -ETXTBSY; + if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) + goto out_unlock; + + + /* Don't reflink dirs, pipes, sockets... */ + ret = -EISDIR; + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + goto out_unlock; + ret = -EINVAL; + if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode)) + goto out_unlock; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + goto out_unlock; + + /* Don't reflink realtime inodes */ + if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest)) + goto out_unlock; + + /* Don't share DAX file data for now. */ + if (IS_DAX(inode_in) || IS_DAX(inode_out)) + goto out_unlock; + + /* Are we going all the way to the end? */ + isize = i_size_read(inode_in); + if (isize == 0) { + ret = 0; + goto out_unlock; + } + + if (len == 0) + len = isize - pos_in; + + /* Ensure offsets don't wrap and the input is inside i_size */ + if (pos_in + len < pos_in || pos_out + len < pos_out || + pos_in + len > isize) + goto out_unlock; + + /* Don't allow dedupe past EOF in the dest file */ + if (is_dedupe) { + loff_t disize; + + disize = i_size_read(inode_out); + if (pos_out >= disize || pos_out + len > disize) + goto out_unlock; + } + + /* If we're linking to EOF, continue to the block boundary. */ + if (pos_in + len == isize) + blen = ALIGN(isize, bs) - pos_in; + else + blen = len; + + /* Only reflink if we're aligned to block boundaries */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || + !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) + goto out_unlock; + + /* Don't allow overlapped reflink within the same file */ + if (same_inode) { + if (pos_out + blen > pos_in && pos_out < pos_in + blen) + goto out_unlock; + } + + /* Wait for the completion of any pending IOs on both files */ + inode_dio_wait(inode_in); + if (!same_inode) + inode_dio_wait(inode_out); + + ret = filemap_write_and_wait_range(inode_in->i_mapping, + pos_in, pos_in + len - 1); + if (ret) + goto out_unlock; + + ret = filemap_write_and_wait_range(inode_out->i_mapping, + pos_out, pos_out + len - 1); + if (ret) + goto out_unlock; + + trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + /* * Check that the extents are the same. */ - if (flags & XFS_REFLINK_DEDUPE) { - is_same = false; - error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest), - destoff, len, &is_same); - if (error) - goto out_error; + if (is_dedupe) { + bool is_same = false; + + ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out, + len, &is_same); + if (ret) + goto out_unlock; if (!is_same) { - error = -EBADE; - goto out_error; + ret = -EBADE; + goto out_unlock; } } - error = xfs_reflink_set_inode_flag(src, dest); - if (error) - goto out_error; + ret = xfs_reflink_set_inode_flag(src, dest); + if (ret) + goto out_unlock; /* * Invalidate the page cache so that we can clear any CoW mappings * in the destination file. */ - truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff, - PAGE_ALIGN(destoff + len) - 1); + truncate_inode_pages_range(&inode_out->i_data, pos_out, + PAGE_ALIGN(pos_out + len) - 1); - dfsbno = XFS_B_TO_FSBT(mp, destoff); - sfsbno = XFS_B_TO_FSBT(mp, srcoff); + dfsbno = XFS_B_TO_FSBT(mp, pos_out); + sfsbno = XFS_B_TO_FSBT(mp, pos_in); fsblen = XFS_B_TO_FSB(mp, len); - error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, - destoff + len); - if (error) - goto out_error; + ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen, + pos_out + len); + if (ret) + goto out_unlock; /* * Carry the cowextsize hint from src to dest if we're sharing the @@ -1390,26 +1437,24 @@ xfs_reflink_remap_range( * has a cowextsize hint, and the destination file does not. */ cowextsize = 0; - if (srcoff == 0 && len == i_size_read(VFS_I(src)) && + if (pos_in == 0 && len == i_size_read(inode_in) && (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) && - destoff == 0 && len >= i_size_read(VFS_I(dest)) && + pos_out == 0 && len >= i_size_read(inode_out) && !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)) cowextsize = src->i_d.di_cowextsize; - error = xfs_reflink_update_dest(dest, destoff + len, cowextsize); - if (error) - goto out_error; + ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize); -out_error: +out_unlock: xfs_iunlock(src, XFS_MMAPLOCK_EXCL); xfs_iunlock(src, XFS_IOLOCK_EXCL); if (src->i_ino != dest->i_ino) { xfs_iunlock(dest, XFS_MMAPLOCK_EXCL); xfs_iunlock(dest, XFS_IOLOCK_EXCL); } - if (error) - trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_); - return error; + if (ret) + trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_); + return ret; } /* diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 5dc3c8ac12aa..fad11607c9ad 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno, extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip, struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed); -extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip, - xfs_off_t offset, xfs_off_t count); +extern int xfs_reflink_reserve_cow(struct xfs_inode *ip, + struct xfs_bmbt_irec *imap, bool *shared); extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset, @@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset, extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); -#define XFS_REFLINK_DEDUPE 1 /* only reflink if contents match */ -#define XFS_REFLINK_ALL (XFS_REFLINK_DEDUPE) -extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff, - struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len, - unsigned int flags); +extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe); extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip, struct xfs_trans **tpp); extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset, diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 5f8d55d29a11..276d3023d60f 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = { }; -struct kobj_type xfs_error_cfg_ktype = { +static struct kobj_type xfs_error_cfg_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, .default_attrs = xfs_error_attrs, }; -struct kobj_type xfs_error_ktype = { +static struct kobj_type xfs_error_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, }; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ad188d3a83f3..0907752be62d 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc); -DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range); +DEFINE_RW_EVENT(xfs_reflink_reserve_cow); DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range); DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write); @@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap); -DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece); -DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); |