diff options
Diffstat (limited to 'fs')
76 files changed, 942 insertions, 493 deletions
diff --git a/fs/afs/file.c b/fs/afs/file.c index cb6ad61eec3b..afe4b803f84b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -514,8 +514,9 @@ static void afs_add_open_mmap(struct afs_vnode *vnode) if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) { down_write(&vnode->volume->cell->fs_open_mmaps_lock); - list_add_tail(&vnode->cb_mmap_link, - &vnode->volume->cell->fs_open_mmaps); + if (list_empty(&vnode->cb_mmap_link)) + list_add_tail(&vnode->cb_mmap_link, + &vnode->volume->cell->fs_open_mmaps); up_write(&vnode->volume->cell->fs_open_mmaps_lock); } diff --git a/fs/afs/super.c b/fs/afs/super.c index d110def8aa8e..34c68724c98b 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -667,6 +667,7 @@ static void afs_i_init_once(void *_vnode) INIT_LIST_HEAD(&vnode->pending_locks); INIT_LIST_HEAD(&vnode->granted_locks); INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work); + INIT_LIST_HEAD(&vnode->cb_mmap_link); seqlock_init(&vnode->cb_lock); } @@ -181,8 +181,9 @@ struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; - bool done; bool cancelled; + bool work_scheduled; + bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; @@ -1619,6 +1620,51 @@ static void aio_poll_put_work(struct work_struct *work) iocb_put(iocb); } +/* + * Safely lock the waitqueue which the request is on, synchronizing with the + * case where the ->poll() provider decides to free its waitqueue early. + * + * Returns true on success, meaning that req->head->lock was locked, req->wait + * is on req->head, and an RCU read lock was taken. Returns false if the + * request was already removed from its waitqueue (which might no longer exist). + */ +static bool poll_iocb_lock_wq(struct poll_iocb *req) +{ + wait_queue_head_t *head; + + /* + * While we hold the waitqueue lock and the waitqueue is nonempty, + * wake_up_pollfree() will wait for us. However, taking the waitqueue + * lock in the first place can race with the waitqueue being freed. + * + * We solve this as eventpoll does: by taking advantage of the fact that + * all users of wake_up_pollfree() will RCU-delay the actual free. If + * we enter rcu_read_lock() and see that the pointer to the queue is + * non-NULL, we can then lock it without the memory being freed out from + * under us, then check whether the request is still on the queue. + * + * Keep holding rcu_read_lock() as long as we hold the queue lock, in + * case the caller deletes the entry from the queue, leaving it empty. + * In that case, only RCU prevents the queue memory from being freed. + */ + rcu_read_lock(); + head = smp_load_acquire(&req->head); + if (head) { + spin_lock(&head->lock); + if (!list_empty(&req->wait.entry)) + return true; + spin_unlock(&head->lock); + } + rcu_read_unlock(); + return false; +} + +static void poll_iocb_unlock_wq(struct poll_iocb *req) +{ + spin_unlock(&req->head->lock); + rcu_read_unlock(); +} + static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); @@ -1638,14 +1684,27 @@ static void aio_poll_complete_work(struct work_struct *work) * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); - if (!mask && !READ_ONCE(req->cancelled)) { - add_wait_queue(req->head, &req->wait); - spin_unlock_irq(&ctx->ctx_lock); - return; - } + if (poll_iocb_lock_wq(req)) { + if (!mask && !READ_ONCE(req->cancelled)) { + /* + * The request isn't actually ready to be completed yet. + * Reschedule completion if another wakeup came in. + */ + if (req->work_need_resched) { + schedule_work(&req->work); + req->work_need_resched = false; + } else { + req->work_scheduled = false; + } + poll_iocb_unlock_wq(req); + spin_unlock_irq(&ctx->ctx_lock); + return; + } + list_del_init(&req->wait.entry); + poll_iocb_unlock_wq(req); + } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); @@ -1657,13 +1716,14 @@ static int aio_poll_cancel(struct kiocb *iocb) struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; - spin_lock(&req->head->lock); - WRITE_ONCE(req->cancelled, true); - if (!list_empty(&req->wait.entry)) { - list_del_init(&req->wait.entry); - schedule_work(&aiocb->poll.work); - } - spin_unlock(&req->head->lock); + if (poll_iocb_lock_wq(req)) { + WRITE_ONCE(req->cancelled, true); + if (!req->work_scheduled) { + schedule_work(&aiocb->poll.work); + req->work_scheduled = true; + } + poll_iocb_unlock_wq(req); + } /* else, the request was force-cancelled by POLLFREE already */ return 0; } @@ -1680,21 +1740,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (mask && !(mask & req->events)) return 0; - list_del_init(&req->wait.entry); - - if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { + /* + * Complete the request inline if possible. This requires that three + * conditions be met: + * 1. An event mask must have been passed. If a plain wakeup was done + * instead, then mask == 0 and we have to call vfs_poll() to get + * the events, so inline completion isn't possible. + * 2. The completion work must not have already been scheduled. + * 3. ctx_lock must not be busy. We have to use trylock because we + * already hold the waitqueue lock, so this inverts the normal + * locking order. Use irqsave/irqrestore because not all + * filesystems (e.g. fuse) call this function with IRQs disabled, + * yet IRQs have to be disabled before ctx_lock is obtained. + */ + if (mask && !req->work_scheduled && + spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; - /* - * Try to complete the iocb inline if we can. Use - * irqsave/irqrestore because not all filesystems (e.g. fuse) - * call this function with IRQs disabled and because IRQs - * have to be disabled before ctx_lock is obtained. - */ + list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); - req->done = true; - if (iocb->ki_eventfd && eventfd_signal_allowed()) { + if (iocb->ki_eventfd && !eventfd_signal_allowed()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); @@ -1703,7 +1769,43 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, if (iocb) iocb_put(iocb); } else { - schedule_work(&req->work); + /* + * Schedule the completion work if needed. If it was already + * scheduled, record that another wakeup came in. + * + * Don't remove the request from the waitqueue here, as it might + * not actually be complete yet (we won't know until vfs_poll() + * is called), and we must not miss any wakeups. POLLFREE is an + * exception to this; see below. + */ + if (req->work_scheduled) { + req->work_need_resched = true; + } else { + schedule_work(&req->work); + req->work_scheduled = true; + } + + /* + * If the waitqueue is being freed early but we can't complete + * the request inline, we have to tear down the request as best + * we can. That means immediately removing the request from its + * waitqueue and preventing all further accesses to the + * waitqueue via the request. We also need to schedule the + * completion work (done above). Also mark the request as + * cancelled, to potentially skip an unneeded call to ->poll(). + */ + if (mask & POLLFREE) { + WRITE_ONCE(req->cancelled, true); + list_del_init(&req->wait.entry); + + /* + * Careful: this *must* be the last step, since as soon + * as req->head is NULL'ed out, the request can be + * completed and freed, since aio_poll_complete_work() + * will no longer need to take the waitqueue lock. + */ + smp_store_release(&req->head, NULL); + } } return 1; } @@ -1711,6 +1813,7 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; + bool queued; int error; }; @@ -1721,11 +1824,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ - if (unlikely(pt->iocb->poll.head)) { + if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } + pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); @@ -1750,12 +1854,14 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; - req->done = false; req->cancelled = false; + req->work_scheduled = false; + req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; + apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ @@ -1764,23 +1870,35 @@ static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); - if (likely(req->head)) { - spin_lock(&req->head->lock); - if (unlikely(list_empty(&req->wait.entry))) { - if (apt.error) + if (likely(apt.queued)) { + bool on_queue = poll_iocb_lock_wq(req); + + if (!on_queue || req->work_scheduled) { + /* + * aio_poll_wake() already either scheduled the async + * completion work, or completed the request inline. + */ + if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { + /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { + /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); - } else if (!req->done) { /* actually waiting for an event */ + } else if (on_queue) { + /* + * Actually waiting for an event, so add the request to + * active_reqs so that it can be cancelled if needed. + */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } - spin_unlock(&req->head->lock); + if (on_queue) + poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); diff --git a/fs/attr.c b/fs/attr.c index 473d21b3a86d..66899b6e9bd8 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -35,7 +35,7 @@ static bool chown_ok(struct user_namespace *mnt_userns, kuid_t uid) { kuid_t kuid = i_uid_into_mnt(mnt_userns, inode); - if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, kuid)) + if (uid_eq(current_fsuid(), kuid) && uid_eq(uid, inode->i_uid)) return true; if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; @@ -62,7 +62,7 @@ static bool chgrp_ok(struct user_namespace *mnt_userns, { kgid_t kgid = i_gid_into_mnt(mnt_userns, inode); if (uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)) && - (in_group_p(gid) || gid_eq(gid, kgid))) + (in_group_p(gid) || gid_eq(gid, inode->i_gid))) return true; if (capable_wrt_inode_uidgid(mnt_userns, inode, CAP_CHOWN)) return true; diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 309516e6a968..43c89952b7d2 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -234,6 +234,13 @@ static void run_ordered_work(struct __btrfs_workqueue *wq, ordered_list); if (!test_bit(WORK_DONE_BIT, &work->flags)) break; + /* + * Orders all subsequent loads after reading WORK_DONE_BIT, + * paired with the smp_mb__before_atomic in btrfs_work_helper + * this guarantees that the ordered function will see all + * updates from ordinary work function. + */ + smp_rmb(); /* * we are going to call the ordered done function, but @@ -317,6 +324,13 @@ static void btrfs_work_helper(struct work_struct *normal_work) thresh_exec_hook(wq); work->func(work); if (need_order) { + /* + * Ensures all memory accesses done in the work function are + * ordered before setting the WORK_DONE_BIT. Ensuring the thread + * which is going to executed the ordered work sees them. + * Pairs with the smp_rmb in run_ordered_work. + */ + smp_mb__before_atomic(); set_bit(WORK_DONE_BIT, &work->flags); run_ordered_work(wq, work); } else { diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index c3983bdaf4b8..f704339c6b86 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -463,8 +463,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, BUG_ON(ret < 0); rcu_assign_pointer(root->node, cow); - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -485,8 +485,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } } - btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + btrfs_free_tree_block(trans, btrfs_root_id(root), buf, + parent_start, last_ref); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -927,7 +927,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); /* once for the root ptr */ free_extent_buffer_stale(mid); return 0; @@ -986,7 +986,8 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(right); del_ptr(root, path, level + 1, pslot + 1); root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), right, + 0, 1); free_extent_buffer_stale(right); right = NULL; } else { @@ -1031,7 +1032,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, btrfs_tree_unlock(mid); del_ptr(root, path, level + 1, pslot); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1); free_extent_buffer_stale(mid); mid = NULL; } else { @@ -4032,7 +4033,7 @@ static noinline void btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); atomic_inc(&leaf->refs); - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1); free_extent_buffer_stale(leaf); } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7553e9dc5f93..5fe5eccb3c87 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2257,6 +2257,11 @@ static inline bool btrfs_root_dead(const struct btrfs_root *root) return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0; } +static inline u64 btrfs_root_id(const struct btrfs_root *root) +{ + return root->root_key.objectid; +} + /* struct btrfs_root_backup */ BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup, tree_root, 64); @@ -2719,7 +2724,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, u64 empty_size, enum btrfs_lock_nesting nest); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref); int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index 2059d1504149..40c4d6ba3fb9 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -143,10 +143,13 @@ int btrfs_check_data_free_space(struct btrfs_inode *inode, /* Use new btrfs_qgroup_reserve_data to reserve precious data space. */ ret = btrfs_qgroup_reserve_data(inode, reserved, start, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space_noquota(fs_info, len); - else + extent_changeset_free(*reserved); + *reserved = NULL; + } else { ret = 0; + } return ret; } @@ -452,8 +455,11 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode, if (ret < 0) return ret; ret = btrfs_delalloc_reserve_metadata(inode, len); - if (ret < 0) + if (ret < 0) { btrfs_free_reserved_data_space(inode, *reserved, start, len); + extent_changeset_free(*reserved); + *reserved = NULL; + } return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59c3be8c1f4c..b3f2e2232326 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1732,6 +1732,14 @@ again: } return root; fail: + /* + * If our caller provided us an anonymous device, then it's his + * responsability to free it in case we fail. So we have to set our + * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() + * and once again by our caller. + */ + if (anon_dev) + root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); } @@ -3978,11 +3986,23 @@ static void btrfs_end_empty_barrier(struct bio *bio) */ static void write_dev_flush(struct btrfs_device *device) { - struct request_queue *q = bdev_get_queue(device->bdev); struct bio *bio = device->flush_bio; +#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY + /* + * When a disk has write caching disabled, we skip submission of a bio + * with flush and sync requests before writing the superblock, since + * it's not needed. However when the integrity checker is enabled, this + * results in reports that there are metadata blocks referred by a + * superblock that were not properly flushed. So don't skip the bio + * submission only when the integrity checker is enabled for the sake + * of simplicity, since this is a debug tool and not meant for use in + * non-debug builds. + */ + struct request_queue *q = bdev_get_queue(device->bdev); if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) return; +#endif bio_reset(bio); bio->bi_end_io = btrfs_end_empty_barrier; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3fd736a02c1e..25ef6e3fd306 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3275,20 +3275,20 @@ out_delayed_unlock: } void btrfs_free_tree_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, + u64 root_id, struct extent_buffer *buf, u64 parent, int last_ref) { - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_ref generic_ref = { 0 }; int ret; btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF, buf->start, buf->len, parent); btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), - root->root_key.objectid, 0, false); + root_id, 0, false); - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { btrfs_ref_tree_mod(fs_info, &generic_ref); ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL); BUG_ON(ret); /* -ENOMEM */ @@ -3298,7 +3298,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_block_group *cache; bool must_pin = false; - if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { + if (root_id != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); if (!ret) { btrfs_redirty_list_add(trans->transaction, buf); @@ -5472,7 +5472,8 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, goto owner_mismatch; } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); + btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent, + wc->refs[level] == 1); out: wc->refs[level] = 0; wc->flags[level] = 0; @@ -6051,6 +6052,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) int dev_ret = 0; int ret = 0; + if (range->start == U64_MAX) + return -EINVAL; + /* * Check range overflow if range->len is set. * The default range->len is U64_MAX. diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4e03a6d3aa32..9234d96a7fd5 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4314,6 +4314,20 @@ static void set_btree_ioerr(struct page *page, struct extent_buffer *eb) return; /* + * A read may stumble upon this buffer later, make sure that it gets an + * error and knows there was an error. + */ + clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); + + /* + * We need to set the mapping with the io error as well because a write + * error will flip the file system readonly, and then syncfs() will + * return a 0 because we are readonly if we don't modify the err seq for + * the superblock. + */ + mapping_set_error(page->mapping, -EIO); + + /* * If we error out, we should add back the dirty_metadata_bytes * to make it consistent. */ @@ -6597,6 +6611,14 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num) if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; + /* + * We could have had EXTENT_BUFFER_UPTODATE cleared by the write + * operation, which could potentially still be in flight. In this case + * we simply want to return an error. + */ + if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) + return -EIO; + if (eb->fs_info->sectorsize < PAGE_SIZE) return read_extent_buffer_subpage(eb, wait, mirror_num); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index a33bca94d133..3abec44c6255 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -1256,8 +1256,8 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info) btrfs_tree_lock(free_space_root->node); btrfs_clean_tree_block(free_space_root->node); btrfs_tree_unlock(free_space_root->node); - btrfs_free_tree_block(trans, free_space_root, free_space_root->node, - 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(free_space_root), + free_space_root->node, 0, 1); btrfs_put_root(free_space_root); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fb8cc9642ac4..edfecfe62b4b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -617,11 +617,13 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, * Since we don't abort the transaction in this case, free the * tree block so that we don't leak space and leave the * filesystem in an inconsistent state (an extent item in the - * extent tree without backreferences). Also no need to have - * the tree block locked since it is not in any tree at this - * point, so no other task can find it and use it. + * extent tree with a backreference for a root that does not + * exists). */ - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_tree_lock(leaf); + btrfs_clean_tree_block(leaf); + btrfs_tree_unlock(leaf); + btrfs_free_tree_block(trans, objectid, leaf, 0, 1); free_extent_buffer(leaf); goto fail; } @@ -3187,10 +3189,8 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg) return -EPERM; vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) { - ret = PTR_ERR(vol_args); - goto out; - } + if (IS_ERR(vol_args)) + return PTR_ERR(vol_args); if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) { ret = -EOPNOTSUPP; @@ -3985,6 +3985,10 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg) bool need_unlock; /* for mut. excl. ops lock */ int ret; + if (!arg) + btrfs_warn(fs_info, + "IOC_BALANCE ioctl (v1) is deprecated and will be removed in kernel 5.18"); + if (!capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 65cb0766e62d..0fb90cbe7669 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -125,6 +125,7 @@ static inline size_t read_compress_length(const char *buf) static int copy_compressed_data_to_page(char *compressed_data, size_t compressed_size, struct page **out_pages, + unsigned long max_nr_page, u32 *cur_out, const u32 sectorsize) { @@ -133,6 +134,9 @@ static int copy_compressed_data_to_page(char *compressed_data, struct page *cur_page; char *kaddr; + if ((*cur_out / PAGE_SIZE) >= max_nr_page) + return -E2BIG; + /* * We never allow a segment header crossing sector boundary, previous * run should ensure we have enough space left inside the sector. @@ -161,6 +165,10 @@ static int copy_compressed_data_to_page(char *compressed_data, orig_out + compressed_size - *cur_out); kunmap(cur_page); + + if ((*cur_out / PAGE_SIZE) >= max_nr_page) + return -E2BIG; + cur_page = out_pages[*cur_out / PAGE_SIZE]; /* Allocate a new page */ if (!cur_page) { @@ -203,6 +211,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, const u32 sectorsize = btrfs_sb(mapping->host->i_sb)->sectorsize; struct page *page_in = NULL; char *sizes_ptr; + const unsigned long max_nr_page = *out_pages; int ret = 0; /* Points to the file offset of input data */ u64 cur_in = start; @@ -210,6 +219,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, u32 cur_out = 0; u32 len = *total_out; + ASSERT(max_nr_page > 0); *out_pages = 0; *total_out = 0; *total_in = 0; @@ -248,7 +258,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, } ret = copy_compressed_data_to_page(workspace->cbuf, out_len, - pages, &cur_out, sectorsize); + pages, max_nr_page, + &cur_out, sectorsize); if (ret < 0) goto out; @@ -279,6 +290,8 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping, *total_out = cur_out; *total_in = cur_in - start; out: + if (page_in) + put_page(page_in); *out_pages = DIV_ROUND_UP(cur_out, PAGE_SIZE); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index db680f5be745..6c037f1252b7 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1219,7 +1219,8 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) btrfs_tree_lock(quota_root->node); btrfs_clean_tree_block(quota_root->node); btrfs_tree_unlock(quota_root->node); - btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1); + btrfs_free_tree_block(trans, btrfs_root_id(quota_root), + quota_root->node, 0, 1); btrfs_put_root(quota_root); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 12ceb14a1141..d20166336557 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -334,7 +334,8 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id, key.offset = ref_id; again: ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1); - BUG_ON(ret < 0); + if (ret < 0) + goto out; if (ret == 0) { leaf = path->nodes[0]; ref = btrfs_item_ptr(leaf, path->slots[0], diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index cf82ea6f54fb..8f6ceea33969 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -73,8 +73,8 @@ struct scrub_page { u64 physical_for_dev_replace; atomic_t refs; u8 mirror_num; - int have_csum:1; - int io_error:1; + unsigned int have_csum:1; + unsigned int io_error:1; u8 csum[BTRFS_CSUM_SIZE]; struct scrub_recover *recover; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 8ab33caf016f..6993dcdba6f1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1181,6 +1181,7 @@ again: parent_objectid, victim_name, victim_name_len); if (ret < 0) { + kfree(victim_name); return ret; } else if (!ret) { ret = -ENOENT; @@ -2908,6 +2909,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans, path->nodes[*level]->len); if (ret) return ret; + btrfs_redirty_list_add(trans->transaction, + next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -2988,6 +2991,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans, next->start, next->len); if (ret) goto out; + btrfs_redirty_list_add(trans->transaction, next); } else { if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags)) clear_extent_buffer_dirty(next); @@ -3438,8 +3442,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans, EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT); extent_io_tree_release(&log->log_csum_range); - if (trans && log->node) - btrfs_redirty_list_add(trans->transaction, log->node); btrfs_put_root(log); } @@ -3976,6 +3978,7 @@ search: goto done; } if (btrfs_header_generation(path->nodes[0]) != trans->transid) { + ctx->last_dir_item_offset = min_key.offset; ret = overwrite_item(trans, log, dst_path, path->nodes[0], path->slots[0], &min_key); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 61ac57bcbf1a..fd0ced829edb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1370,8 +1370,10 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, bytenr_orig = btrfs_sb_offset(0); ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr); - if (ret) - return ERR_PTR(ret); + if (ret) { + device = ERR_PTR(ret); + goto error_bdev_put; + } disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig); if (IS_ERR(disk_super)) { @@ -7559,6 +7561,19 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) fs_info->fs_devices->total_rw_bytes = 0; /* + * Lockdep complains about possible circular locking dependency between + * a disk's open_mutex (struct gendisk.open_mutex), the rw semaphores + * used for freeze procection of a fs (struct super_block.s_writers), + * which we take when starting a transaction, and extent buffers of the + * chunk tree if we call read_one_dev() while holding a lock on an + * extent buffer of the chunk tree. Since we are mounting the filesystem + * and at this point there can't be any concurrent task modifying the + * chunk tree, to keep it simple, just skip locking on the chunk tree. + */ + ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); + path->skip_locking = 1; + + /* * Read all device items, and then all the chunk items. All * device items are found before any chunk item (their object id * is smaller than the lowest possible object id for a chunk @@ -7583,10 +7598,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) goto error; break; } - /* - * The nodes on level 1 are not locked but we don't need to do - * that during mount time as nothing else can access the tree - */ node = path->nodes[1]; if (node) { if (last_ra_node != node->start) { @@ -7614,7 +7625,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info) * requirement for chunk allocation, see the comment on * top of btrfs_chunk_alloc() for details. */ - ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags)); chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); ret = read_one_chunk(&found_key, leaf, chunk); if (ret) diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 67d932d70798..678a29469511 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1860,6 +1860,7 @@ int btrfs_zone_finish(struct btrfs_block_group *block_group) block_group->alloc_offset = block_group->zone_capacity; block_group->free_space_ctl->free_space = 0; btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH, @@ -1942,6 +1943,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical, u64 len ASSERT(block_group->alloc_offset == block_group->zone_capacity); ASSERT(block_group->free_space_ctl->free_space == 0); btrfs_clear_treelog_bg(block_group); + btrfs_clear_data_reloc_bg(block_group); spin_unlock(&block_group->lock); map = block_group->physical_map; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index b9460b6fb76f..c447fa2e2d1f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4350,7 +4350,7 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb); int bits = (fmode << 1) | 1; - bool is_opened = false; + bool already_opened = false; int i; if (count == 1) @@ -4358,19 +4358,19 @@ void ceph_get_fmode(struct ceph_inode_info *ci, int fmode, int count) spin_lock(&ci->i_ceph_lock); for (i = 0; i < CEPH_FILE_MODE_BITS; i++) { - if (bits & (1 << i)) - ci->i_nr_by_mode[i] += count; - /* - * If any of the mode ref is larger than 1, + * If any of the mode ref is larger than 0, * that means it has been already opened by * others. Just skip checking the PIN ref. */ - if (i && ci->i_nr_by_mode[i] > 1) - is_opened = true; + if (i && ci->i_nr_by_mode[i]) + already_opened = true; + + if (bits & (1 << i)) + ci->i_nr_by_mode[i] += count; } - if (!is_opened) + if (!already_opened) percpu_counter_inc(&mdsc->metric.opened_inodes); spin_unlock(&ci->i_ceph_lock); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 02a0a0fd9ccd..c138e8126286 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -605,13 +605,25 @@ static int ceph_finish_async_create(struct inode *dir, struct dentry *dentry, in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino); in.cap.flags = CEPH_CAP_FLAG_AUTH; in.ctime = in.mtime = in.atime = iinfo.btime; - in.mode = cpu_to_le32((u32)mode); in.truncate_seq = cpu_to_le32(1); in.truncate_size = cpu_to_le64(-1ULL); in.xattr_version = cpu_to_le64(1); in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid())); - in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ? - dir->i_gid : current_fsgid())); + if (dir->i_mode & S_ISGID) { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid)); + + /* Directories always inherit the setgid bit. */ + if (S_ISDIR(mode)) + mode |= S_ISGID; + else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) && + !in_group_p(dir->i_gid) && + !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID)) + mode &= ~S_ISGID; + } else { + in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid())); + } + in.mode = cpu_to_le32((u32)mode); + in.nlink = cpu_to_le32(1); in.max_size = cpu_to_le64(lo->stripe_unit); @@ -847,7 +859,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, ssize_t ret; u64 off = iocb->ki_pos; u64 len = iov_iter_count(to); - u64 i_size; + u64 i_size = i_size_read(inode); dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len, (file->f_flags & O_DIRECT) ? "O_DIRECT" : ""); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 250aad330a10..c30eefc0ac19 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3683,7 +3683,7 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; char *path; - int pathlen, err; + int pathlen = 0, err; u64 pathbase; u64 snap_follows; @@ -3703,7 +3703,6 @@ static int reconnect_caps_cb(struct inode *inode, struct ceph_cap *cap, } } else { path = NULL; - pathlen = 0; pathbase = 0; } diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index 12bde7bfda86..23a1ed2fb769 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -393,26 +393,14 @@ static void cifs_put_swn_reg(struct cifs_swn_reg *swnreg) static int cifs_swn_resource_state_changed(struct cifs_swn_reg *swnreg, const char *name, int state) { - int i; - switch (state) { case CIFS_SWN_RESOURCE_STATE_UNAVAILABLE: cifs_dbg(FYI, "%s: resource name '%s' become unavailable\n", __func__, name); - for (i = 0; i < swnreg->tcon->ses->chan_count; i++) { - spin_lock(&GlobalMid_Lock); - if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting) - swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); - } + cifs_ses_mark_for_reconnect(swnreg->tcon->ses); break; case CIFS_SWN_RESOURCE_STATE_AVAILABLE: cifs_dbg(FYI, "%s: resource name '%s' become available\n", __func__, name); - for (i = 0; i < swnreg->tcon->ses->chan_count; i++) { - spin_lock(&GlobalMid_Lock); - if (swnreg->tcon->ses->chans[i].server->tcpStatus != CifsExiting) - swnreg->tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); - } + cifs_ses_mark_for_reconnect(swnreg->tcon->ses); break; case CIFS_SWN_RESOURCE_STATE_UNKNOWN: cifs_dbg(FYI, "%s: resource name '%s' changed to unknown state\n", __func__, name); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index b50da1901ebd..9e5d9e192ef0 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -152,5 +152,5 @@ extern struct dentry *cifs_smb3_do_mount(struct file_system_type *fs_type, extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.33" +#define CIFS_VERSION "2.34" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f3073a62ce57..4f5a3e857df4 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -599,6 +599,7 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) bool is_server_using_iface(struct TCP_Server_Info *server, struct cifs_server_iface *iface); bool is_ses_using_iface(struct cifs_ses *ses, struct cifs_server_iface *iface); +void cifs_ses_mark_for_reconnect(struct cifs_ses *ses); void extract_unc_hostname(const char *unc, const char **h, size_t *len); int copy_path_name(char *dst, const char *src); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 82577a7a5bb1..1060164b984a 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1271,10 +1271,8 @@ static int match_server(struct TCP_Server_Info *server, struct smb3_fs_context * { struct sockaddr *addr = (struct sockaddr *)&ctx->dstaddr; - if (ctx->nosharesock) { - server->nosharesock = true; + if (ctx->nosharesock) return 0; - } /* this server does not share socket */ if (server->nosharesock) @@ -1438,6 +1436,9 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, goto out_err; } + if (ctx->nosharesock) + tcp_ses->nosharesock = true; + tcp_ses->ops = ctx->ops; tcp_ses->vals = ctx->vals; cifs_set_net_ns(tcp_ses, get_net(current->nsproxy->net_ns)); @@ -1452,8 +1453,10 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx, tcp_ses->max_in_flight = 0; tcp_ses->credits = 1; if (primary_server) { + spin_lock(&cifs_tcp_ses_lock); ++primary_server->srv_count; tcp_ses->primary_server = primary_server; + spin_unlock(&cifs_tcp_ses_lock); } init_waitqueue_head(&tcp_ses->response_q); init_waitqueue_head(&tcp_ses->request_q); @@ -1559,6 +1562,10 @@ smbd_connected: /* fscache server cookies are based on primary channel only */ if (!CIFS_SERVER_IS_CHAN(tcp_ses)) cifs_fscache_get_client_cookie(tcp_ses); +#ifdef CONFIG_CIFS_FSCACHE + else + tcp_ses->fscache = tcp_ses->primary_server->fscache; +#endif /* CONFIG_CIFS_FSCACHE */ /* queue echo request delayed work */ queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval); @@ -3043,12 +3050,6 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } - /* - * The cookie is initialized from volume info returned above. - * Inside cifs_fscache_get_super_cookie it checks - * that we do not get super cookie twice. - */ - cifs_fscache_get_super_cookie(tcon); } /* @@ -3063,6 +3064,13 @@ static int mount_get_conns(struct mount_ctx *mnt_ctx) (cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx))) cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx); + /* + * The cookie is initialized from volume info returned above. + * Inside cifs_fscache_get_super_cookie it checks + * that we do not get super cookie twice. + */ + cifs_fscache_get_super_cookie(tcon); + out: mnt_ctx->server = server; mnt_ctx->ses = ses; @@ -3423,6 +3431,7 @@ static int connect_dfs_root(struct mount_ctx *mnt_ctx, struct dfs_cache_tgt_list */ mount_put_conns(mnt_ctx); mount_get_dfs_conns(mnt_ctx); + set_root_ses(mnt_ctx); full_path = build_unc_path_to_root(ctx, cifs_sb, true); if (IS_ERR(full_path)) @@ -4111,18 +4120,6 @@ cifs_prune_tlinks(struct work_struct *work) } #ifdef CONFIG_CIFS_DFS_UPCALL -static void mark_tcon_tcp_ses_for_reconnect(struct cifs_tcon *tcon) -{ - int i; - - for (i = 0; i < tcon->ses->chan_count; i++) { - spin_lock(&GlobalMid_Lock); - if (tcon->ses->chans[i].server->tcpStatus != CifsExiting) - tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); - } -} - /* Update dfs referral path of superblock */ static int update_server_fullpath(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb, const char *target) @@ -4299,7 +4296,7 @@ static int tree_connect_dfs_target(const unsigned int xid, struct cifs_tcon *tco */ if (rc && server->current_fullpath != server->origin_fullpath) { server->current_fullpath = server->origin_fullpath; - mark_tcon_tcp_ses_for_reconnect(tcon); + cifs_ses_mark_for_reconnect(tcon->ses); } dfs_cache_free_tgts(tl); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 5c1259d2eeac..e9b0fa2a9614 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1355,12 +1355,7 @@ static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cach } cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__); - for (i = 0; i < tcon->ses->chan_count; i++) { - spin_lock(&GlobalMid_Lock); - if (tcon->ses->chans[i].server->tcpStatus != CifsExiting) - tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect; - spin_unlock(&GlobalMid_Lock); - } + cifs_ses_mark_for_reconnect(tcon->ses); } /* Refresh dfs referral of tcon and mark it for reconnect if needed */ diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6a179ae753c1..e3ed25dc6f3f 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -435,6 +435,42 @@ out: } /* + * Remove duplicate path delimiters. Windows is supposed to do that + * but there are some bugs that prevent rename from working if there are + * multiple delimiters. + * + * Returns a sanitized duplicate of @path. The caller is responsible for + * cleaning up the original. + */ +#define IS_DELIM(c) ((c) == '/' || (c) == '\\') +static char *sanitize_path(char *path) +{ + char *cursor1 = path, *cursor2 = path; + + /* skip all prepended delimiters */ + while (IS_DELIM(*cursor1)) + cursor1++; + + /* copy the first letter */ + *cursor2 = *cursor1; + + /* copy the remainder... */ + while (*(cursor1++)) { + /* ... skipping all duplicated delimiters */ + if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2)) + continue; + *(++cursor2) = *cursor1; + } + + /* if the last character is a delimiter, skip it */ + if (IS_DELIM(*(cursor2 - 1))) + cursor2--; + + *(cursor2) = '\0'; + return kstrdup(path, GFP_KERNEL); +} + +/* * Parse a devname into substrings and populate the ctx->UNC and ctx->prepath * fields with the result. Returns 0 on success and an error otherwise * (e.g. ENOMEM or EINVAL) @@ -493,7 +529,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = kstrdup(pos, GFP_KERNEL); + ctx->prepath = sanitize_path(pos); if (!ctx->prepath) return -ENOMEM; diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 7e409a38a2d7..003c5f1f4dfb 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -16,14 +16,7 @@ * Key layout of CIFS server cache index object */ struct cifs_server_key { - struct { - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; - struct in6_addr ipv6_addr; - }; + __u64 conn_id; } __packed; /* @@ -31,42 +24,23 @@ struct cifs_server_key { */ void cifs_fscache_get_client_cookie(struct TCP_Server_Info *server) { - const struct sockaddr *sa = (struct sockaddr *) &server->dstaddr; - const struct sockaddr_in *addr = (struct sockaddr_in *) sa; - const struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) sa; struct cifs_server_key key; - uint16_t key_len = sizeof(key.hdr); - - memset(&key, 0, sizeof(key)); /* - * Should not be a problem as sin_family/sin6_family overlays - * sa_family field + * Check if cookie was already initialized so don't reinitialize it. + * In the future, as we integrate with newer fscache features, + * we may want to instead add a check if cookie has changed */ - key.hdr.family = sa->sa_family; - switch (sa->sa_family) { - case AF_INET: - key.hdr.port = addr->sin_port; - key.ipv4_addr = addr->sin_addr; - key_len += sizeof(key.ipv4_addr); - break; - - case AF_INET6: - key.hdr.port = addr6->sin6_port; - key.ipv6_addr = addr6->sin6_addr; - key_len += sizeof(key.ipv6_addr); - break; - - default: - cifs_dbg(VFS, "Unknown network family '%d'\n", sa->sa_family); - server->fscache = NULL; + if (server->fscache) return; - } + + memset(&key, 0, sizeof(key)); + key.conn_id = server->conn_id; server->fscache = fscache_acquire_cookie(cifs_fscache_netfs.primary_index, &cifs_fscache_server_index_def, - &key, key_len, + &key, sizeof(key), NULL, 0, server, 0, true); cifs_dbg(FYI, "%s: (0x%p/0x%p)\n", @@ -92,7 +66,7 @@ void cifs_fscache_get_super_cookie(struct cifs_tcon *tcon) * In the future, as we integrate with newer fscache features, * we may want to instead add a check if cookie has changed */ - if (tcon->fscache == NULL) + if (tcon->fscache) return; sharename = extract_sharename(tcon->treeName); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 82848412ad85..279622e4eb1c 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1356,11 +1356,6 @@ iget_no_retry: goto out; } -#ifdef CONFIG_CIFS_FSCACHE - /* populate tcon->resource_id */ - tcon->resource_id = CIFS_I(inode)->uniqueid; -#endif - if (rc && tcon->pipe) { cifs_dbg(FYI, "ipc connection - fake read inode\n"); spin_lock(&inode->i_lock); @@ -1375,7 +1370,6 @@ iget_no_retry: iget_failed(inode); inode = ERR_PTR(rc); } - out: kfree(path); free_xid(xid); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 2c10b186ed6e..035dc3e245dc 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -95,9 +95,9 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) } if (!(ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { - cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname); ses->chan_max = 1; spin_unlock(&ses->chan_lock); + cifs_dbg(VFS, "server %s does not support multichannel\n", ses->server->hostname); return 0; } spin_unlock(&ses->chan_lock); @@ -222,6 +222,7 @@ cifs_ses_add_channel(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses, /* Auth */ ctx.domainauto = ses->domainAuto; ctx.domainname = ses->domainName; + ctx.server_hostname = ses->server->hostname; ctx.username = ses->user_name; ctx.password = ses->password; ctx.sectype = ses->sectype; @@ -318,6 +319,19 @@ out: return rc; } +/* Mark all session channels for reconnect */ +void cifs_ses_mark_for_reconnect(struct cifs_ses *ses) +{ + int i; + + for (i = 0; i < ses->chan_count; i++) { + spin_lock(&GlobalMid_Lock); + if (ses->chans[i].server->tcpStatus != CifsExiting) + ses->chans[i].server->tcpStatus = CifsNeedReconnect; + spin_unlock(&GlobalMid_Lock); + } +} + static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB) { __u32 capabilities = 0; @@ -576,8 +590,8 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, { unsigned int tioffset; /* challenge message target info area */ unsigned int tilen; /* challenge message target info area length */ - CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr; + __u32 server_flags; if (blob_len < sizeof(CHALLENGE_MESSAGE)) { cifs_dbg(VFS, "challenge blob len %d too small\n", blob_len); @@ -595,12 +609,37 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return -EINVAL; } + server_flags = le32_to_cpu(pblob->NegotiateFlags); + cifs_dbg(FYI, "%s: negotiate=0x%08x challenge=0x%08x\n", __func__, + ses->ntlmssp->client_flags, server_flags); + + if ((ses->ntlmssp->client_flags & (NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_SIGN)) && + (!(server_flags & NTLMSSP_NEGOTIATE_56) && !(server_flags & NTLMSSP_NEGOTIATE_128))) { + cifs_dbg(VFS, "%s: requested signing/encryption but server did not return either 56-bit or 128-bit session key size\n", + __func__); + return -EINVAL; + } + if (!(server_flags & NTLMSSP_NEGOTIATE_NTLM) && !(server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) { + cifs_dbg(VFS, "%s: server does not seem to support either NTLMv1 or NTLMv2\n", __func__); + return -EINVAL; + } + if (ses->server->sign && !(server_flags & NTLMSSP_NEGOTIATE_SIGN)) { + cifs_dbg(VFS, "%s: forced packet signing but server does not seem to support it\n", + __func__); + return -EOPNOTSUPP; + } + if ((ses->ntlmssp->client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) && + !(server_flags & NTLMSSP_NEGOTIATE_KEY_XCH)) + pr_warn_once("%s: authentication has been weakened as server does not support key exchange\n", + __func__); + + ses->ntlmssp->server_flags = server_flags; + memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE); - /* BB we could decode pblob->NegotiateFlags; some may be useful */ /* In particular we can examine sign flags */ /* BB spec says that if AvId field of MsvAvTimestamp is populated then we must set the MIC field of the AUTHENTICATE_MESSAGE */ - ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags); + tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset); tilen = le16_to_cpu(pblob->TargetInfoArray.Length); if (tioffset > blob_len || tioffset + tilen > blob_len) { @@ -707,13 +746,13 @@ int build_ntlmssp_negotiate_blob(unsigned char **pbuffer, flags = NTLMSSP_NEGOTIATE_56 | NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL; - if (server->sign) - flags |= NTLMSSP_NEGOTIATE_SIGN; + NTLMSSP_NEGOTIATE_ALWAYS_SIGN | NTLMSSP_NEGOTIATE_SEAL | + NTLMSSP_NEGOTIATE_SIGN; if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess) flags |= NTLMSSP_NEGOTIATE_KEY_XCH; tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE); + ses->ntlmssp->client_flags = flags; sec_blob->NegotiateFlags = cpu_to_le32(flags); /* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */ @@ -765,15 +804,8 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8); sec_blob->MessageType = NtLmAuthenticate; - flags = NTLMSSP_NEGOTIATE_56 | - NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO | - NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE | - NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC | - NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; - if (ses->server->sign) - flags |= NTLMSSP_NEGOTIATE_SIGN; - if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) - flags |= NTLMSSP_NEGOTIATE_KEY_XCH; + flags = ses->ntlmssp->server_flags | NTLMSSP_REQUEST_TARGET | + NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED; tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE); sec_blob->NegotiateFlags = cpu_to_le32(flags); @@ -820,9 +852,9 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer, *pbuffer, &tmp, nls_cp); - if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) || - (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) - && !calc_seckey(ses)) { + if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) && + (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) && + !calc_seckey(ses)) { memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE); sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer); sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2f5f2c4c6183..8b3670388cda 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -142,7 +142,7 @@ static int smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon, struct TCP_Server_Info *server) { - int rc; + int rc = 0; struct nls_table *nls_codepage; struct cifs_ses *ses; int retries; diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c index 84da2c280012..ec9a1d780dc1 100644 --- a/fs/erofs/utils.c +++ b/fs/erofs/utils.c @@ -150,7 +150,7 @@ static bool erofs_try_to_release_workgroup(struct erofs_sb_info *sbi, * however in order to avoid some race conditions, add a * DBG_BUGON to observe this in advance. */ - DBG_BUGON(xa_erase(&sbi->managed_pslots, grp->index) != grp); + DBG_BUGON(__xa_erase(&sbi->managed_pslots, grp->index) != grp); /* last refcount should be connected with its managed pslot. */ erofs_workgroup_unfreeze(grp, 0); @@ -165,15 +165,19 @@ static unsigned long erofs_shrink_workstation(struct erofs_sb_info *sbi, unsigned int freed = 0; unsigned long index; + xa_lock(&sbi->managed_pslots); xa_for_each(&sbi->managed_pslots, index, grp) { /* try to shrink each valid workgroup */ if (!erofs_try_to_release_workgroup(sbi, grp)) continue; + xa_unlock(&sbi->managed_pslots); ++freed; if (!--nr_shrink) - break; + return freed; + xa_lock(&sbi->managed_pslots); } + xa_unlock(&sbi->managed_pslots); return freed; } diff --git a/fs/file.c b/fs/file.c index 8627dacfc424..97d212a9b814 100644 --- a/fs/file.c +++ b/fs/file.c @@ -841,24 +841,68 @@ void do_close_on_exec(struct files_struct *files) spin_unlock(&files->file_lock); } +static inline struct file *__fget_files_rcu(struct files_struct *files, + unsigned int fd, fmode_t mask, unsigned int refs) +{ + for (;;) { + struct file *file; + struct fdtable *fdt = rcu_dereference_raw(files->fdt); + struct file __rcu **fdentry; + + if (unlikely(fd >= fdt->max_fds)) + return NULL; + + fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds); + file = rcu_dereference_raw(*fdentry); + if (unlikely(!file)) + return NULL; + + if (unlikely(file->f_mode & mask)) + return NULL; + + /* + * Ok, we have a file pointer. However, because we do + * this all locklessly under RCU, we may be racing with + * that file being closed. + * + * Such a race can take two forms: + * + * (a) the file ref already went down to zero, + * and get_file_rcu_many() fails. Just try + * again: + */ + if (unlikely(!get_file_rcu_many(file, refs))) + continue; + + /* + * (b) the file table entry has changed under us. + * Note that we don't need to re-check the 'fdt->fd' + * pointer having changed, because it always goes + * hand-in-hand with 'fdt'. + * + * If so, we need to put our refs and try again. + */ + if (unlikely(rcu_dereference_raw(files->fdt) != fdt) || + unlikely(rcu_dereference_raw(*fdentry) != file)) { + fput_many(file, refs); + continue; + } + + /* + * Ok, we have a ref to the file, and checked that it + * still exists. + */ + return file; + } +} + static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask, unsigned int refs) { struct file *file; rcu_read_lock(); -loop: - file = files_lookup_fd_rcu(files, fd); - if (file) { - /* File object ref couldn't be taken. - * dup2() atomicity guarantee is the reason - * we loop to catch the new file (or NULL pointer) - */ - if (file->f_mode & mask) - file = NULL; - else if (!get_file_rcu_many(file, refs)) - goto loop; - } + file = __fget_files_rcu(files, fd, mask, refs); rcu_read_unlock(); return file; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 79f7eda49e06..cd54a529460d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -847,17 +847,17 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep) replace_page_cache_page(oldpage, newpage); + get_page(newpage); + + if (!(buf->flags & PIPE_BUF_FLAG_LRU)) + lru_cache_add(newpage); + /* * Release while we have extra ref on stolen page. Otherwise * anon_pipe_buf_release() might think the page can be reused. */ pipe_buf_release(cs->pipe, buf); - get_page(newpage); - - if (!(buf->flags & PIPE_BUF_FLAG_LRU)) - lru_cache_add(newpage); - err = 0; spin_lock(&cs->req->waitq.lock); if (test_bit(FR_ABORTED, &cs->req->flags)) diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 7235d539e969..d67108489148 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -940,7 +940,7 @@ do_alloc: else if (height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); else - iomap->length = size - pos; + iomap->length = size - iomap->offset; } else if (flags & IOMAP_WRITE) { u64 alloc_size; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index adafaaf7d24d..3e718cfc19a7 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -773,8 +773,8 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, size_t *prev_count, size_t *window_size) { - char __user *p = i->iov[0].iov_base + i->iov_offset; size_t count = iov_iter_count(i); + char __user *p; int pages = 1; if (likely(!count)) @@ -787,14 +787,14 @@ static inline bool should_fault_in_pages(ssize_t ret, struct iov_iter *i, if (*prev_count != count || !*window_size) { int pages, nr_dirtied; - pages = min_t(int, BIO_MAX_VECS, - DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE)); + pages = min_t(int, BIO_MAX_VECS, DIV_ROUND_UP(count, PAGE_SIZE)); nr_dirtied = max(current->nr_dirtied_pause - current->nr_dirtied, 1); pages = min(pages, nr_dirtied); } *prev_count = count; + p = i->iov[0].iov_base + i->iov_offset; *window_size = (size_t)PAGE_SIZE * pages - offset_in_page(p); return true; } @@ -1013,6 +1013,7 @@ static ssize_t gfs2_file_buffered_write(struct kiocb *iocb, struct gfs2_sbd *sdp = GFS2_SB(inode); struct gfs2_holder *statfs_gh = NULL; size_t prev_count = 0, window_size = 0; + size_t orig_count = iov_iter_count(from); size_t read = 0; ssize_t ret; @@ -1057,6 +1058,7 @@ retry_under_glock: if (inode == sdp->sd_rindex) gfs2_glock_dq_uninit(statfs_gh); + from->count = orig_count - read; if (should_fault_in_pages(ret, from, &prev_count, &window_size)) { size_t leftover; @@ -1064,6 +1066,7 @@ retry_under_glock: leftover = fault_in_iov_iter_readable(from, window_size); gfs2_holder_disallow_demote(gh); if (leftover != window_size) { + from->count = min(from->count, window_size - leftover); if (!gfs2_holder_queued(gh)) { if (read) goto out_uninit; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 19f38aee1b61..44a7a4288956 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -411,14 +411,14 @@ static void do_error(struct gfs2_glock *gl, const int ret) static void demote_incompat_holders(struct gfs2_glock *gl, struct gfs2_holder *new_gh) { - struct gfs2_holder *gh; + struct gfs2_holder *gh, *tmp; /* * Demote incompatible holders before we make ourselves eligible. * (This holder may or may not allow auto-demoting, but we don't want * to demote the new holder before it's even granted.) */ - list_for_each_entry(gh, &gl->gl_holders, gh_list) { + list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) { /* * Since holders are at the front of the list, we stop when we * find the first non-holder. @@ -496,7 +496,7 @@ again: * Since we unlock the lockref lock, we set a flag to indicate * instantiate is in progress. */ - if (test_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) { + if (test_and_set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags)) { wait_on_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG, TASK_UNINTERRUPTIBLE); /* @@ -509,14 +509,10 @@ again: goto again; } - set_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); - ret = glops->go_instantiate(gh); if (!ret) clear_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags); - clear_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); - smp_mb__after_atomic(); - wake_up_bit(&gl->gl_flags, GLF_INSTANTIATE_IN_PROG); + clear_and_wake_up_bit(GLF_INSTANTIATE_IN_PROG, &gl->gl_flags); return ret; } @@ -1861,7 +1857,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs) void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) { - struct gfs2_holder mock_gh = { .gh_gl = gl, .gh_state = state, }; unsigned long delay = 0; unsigned long holdtime; unsigned long now = jiffies; @@ -1894,8 +1889,13 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state) * keep the glock until the last strong holder is done with it. */ if (!find_first_strong_holder(gl)) { - if (state == LM_ST_UNLOCKED) - mock_gh.gh_state = LM_ST_EXCLUSIVE; + struct gfs2_holder mock_gh = { + .gh_gl = gl, + .gh_state = (state == LM_ST_UNLOCKED) ? + LM_ST_EXCLUSIVE : state, + .gh_iflags = BIT(HIF_HOLDER) + }; + demote_incompat_holders(gl, &mock_gh); } handle_callback(gl, state, delay, true); diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 6424b903e885..89905f4f29bb 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -40,37 +40,6 @@ static const struct inode_operations gfs2_file_iops; static const struct inode_operations gfs2_dir_iops; static const struct inode_operations gfs2_symlink_iops; -static int iget_test(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - return GFS2_I(inode)->i_no_addr == no_addr; -} - -static int iget_set(struct inode *inode, void *opaque) -{ - u64 no_addr = *(u64 *)opaque; - - GFS2_I(inode)->i_no_addr = no_addr; - inode->i_ino = no_addr; - return 0; -} - -static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr) -{ - struct inode *inode; - -repeat: - inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); - if (!inode) - return inode; - if (is_bad_inode(inode)) { - iput(inode); - goto repeat; - } - return inode; -} - /** * gfs2_set_iop - Sets inode operations * @inode: The inode with correct i_mode filled in @@ -104,6 +73,22 @@ static void gfs2_set_iop(struct inode *inode) } } +static int iget_test(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + return GFS2_I(inode)->i_no_addr == no_addr; +} + +static int iget_set(struct inode *inode, void *opaque) +{ + u64 no_addr = *(u64 *)opaque; + + GFS2_I(inode)->i_no_addr = no_addr; + inode->i_ino = no_addr; + return 0; +} + /** * gfs2_inode_lookup - Lookup an inode * @sb: The super block @@ -132,12 +117,11 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, { struct inode *inode; struct gfs2_inode *ip; - struct gfs2_glock *io_gl = NULL; struct gfs2_holder i_gh; int error; gfs2_holder_mark_uninitialized(&i_gh); - inode = gfs2_iget(sb, no_addr); + inode = iget5_locked(sb, no_addr, iget_test, iget_set, &no_addr); if (!inode) return ERR_PTR(-ENOMEM); @@ -145,22 +129,16 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (inode->i_state & I_NEW) { struct gfs2_sbd *sdp = GFS2_SB(inode); + struct gfs2_glock *io_gl; error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (unlikely(error)) goto fail; - flush_delayed_work(&ip->i_gl->gl_work); - - error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); - if (unlikely(error)) - goto fail; - if (blktype != GFS2_BLKST_UNLINKED) - gfs2_cancel_delete_work(io_gl); if (type == DT_UNKNOWN || blktype != GFS2_BLKST_FREE) { /* * The GL_SKIP flag indicates to skip reading the inode - * block. We read the inode with gfs2_inode_refresh + * block. We read the inode when instantiating it * after possibly checking the block type. */ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, @@ -181,24 +159,31 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, } } - glock_set_object(ip->i_gl, ip); set_bit(GLF_INSTANTIATE_NEEDED, &ip->i_gl->gl_flags); - error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); + + error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (unlikely(error)) goto fail; - glock_set_object(ip->i_iopen_gh.gh_gl, ip); + if (blktype != GFS2_BLKST_UNLINKED) + gfs2_cancel_delete_work(io_gl); + error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh); gfs2_glock_put(io_gl); - io_gl = NULL; + if (unlikely(error)) + goto fail; /* Lowest possible timestamp; will be overwritten in gfs2_dinode_in. */ inode->i_atime.tv_sec = 1LL << (8 * sizeof(inode->i_atime.tv_sec) - 1); inode->i_atime.tv_nsec = 0; + glock_set_object(ip->i_gl, ip); + if (type == DT_UNKNOWN) { /* Inode glock must be locked already */ error = gfs2_instantiate(&i_gh); - if (error) + if (error) { + glock_clear_object(ip->i_gl, ip); goto fail; + } } else { ip->i_no_formal_ino = no_formal_ino; inode->i_mode = DT2IF(type); @@ -206,31 +191,23 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type, if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); + glock_set_object(ip->i_iopen_gh.gh_gl, ip); gfs2_set_iop(inode); + unlock_new_inode(inode); } if (no_formal_ino && ip->i_no_formal_ino && no_formal_ino != ip->i_no_formal_ino) { - error = -ESTALE; - if (inode->i_state & I_NEW) - goto fail; iput(inode); - return ERR_PTR(error); + return ERR_PTR(-ESTALE); } - if (inode->i_state & I_NEW) - unlock_new_inode(inode); - return inode; fail: - if (gfs2_holder_initialized(&ip->i_iopen_gh)) { - glock_clear_object(ip->i_iopen_gh.gh_gl, ip); + if (gfs2_holder_initialized(&ip->i_iopen_gh)) gfs2_glock_dq_uninit(&ip->i_iopen_gh); - } - if (io_gl) - gfs2_glock_put(io_gl); if (gfs2_holder_initialized(&i_gh)) gfs2_glock_dq_uninit(&i_gh); iget_failed(inode); @@ -730,18 +707,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl); if (error) goto fail_free_inode; - flush_delayed_work(&ip->i_gl->gl_work); error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) goto fail_free_inode; gfs2_cancel_delete_work(io_gl); + error = insert_inode_locked4(inode, ip->i_no_addr, iget_test, &ip->i_no_addr); + BUG_ON(error); + error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1); if (error) goto fail_gunlock2; - glock_set_object(ip->i_gl, ip); error = gfs2_trans_begin(sdp, blocks, 0); if (error) goto fail_gunlock2; @@ -757,9 +735,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, if (error) goto fail_gunlock2; + glock_set_object(ip->i_gl, ip); glock_set_object(io_gl, ip); gfs2_set_iop(inode); - insert_inode_hash(inode); free_vfs_inode = 0; /* After this point, the inode is no longer considered free. Any failures need to undo @@ -801,17 +779,17 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs + 1); gfs2_glock_put(io_gl); gfs2_qa_put(dip); + unlock_new_inode(inode); return error; fail_gunlock3: + glock_clear_object(ip->i_gl, ip); glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); fail_gunlock2: - glock_clear_object(io_gl, ip); gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { - glock_clear_object(ip->i_gl, ip); if (free_vfs_inode) /* else evict will do the put for us */ gfs2_glock_put(ip->i_gl); } @@ -829,7 +807,10 @@ fail_gunlock: mark_inode_dirty(inode); set_bit(free_vfs_inode ? GIF_FREE_VFS_INODE : GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags); - iput(inode); + if (inode->i_state & I_NEW) + iget_failed(inode); + else + iput(inode); } if (gfs2_holder_initialized(ghs + 1)) gfs2_glock_dq_uninit(ghs + 1); diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 5b121371508a..0f93e8beca4d 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1402,13 +1402,6 @@ out: gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); - if (ip->i_gl) { - glock_clear_object(ip->i_gl, ip); - wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); - gfs2_glock_add_to_lru(ip->i_gl); - gfs2_glock_put_eventually(ip->i_gl); - ip->i_gl = NULL; - } if (gfs2_holder_initialized(&ip->i_iopen_gh)) { struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl; @@ -1421,6 +1414,13 @@ out: gfs2_holder_uninit(&ip->i_iopen_gh); gfs2_glock_put_eventually(gl); } + if (ip->i_gl) { + glock_clear_object(ip->i_gl, ip); + wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE); + gfs2_glock_add_to_lru(ip->i_gl); + gfs2_glock_put_eventually(ip->i_gl); + ip->i_gl = NULL; + } } static struct inode *gfs2_alloc_inode(struct super_block *sb) diff --git a/fs/inode.c b/fs/inode.c index 3eba0940ffcf..6b80a51129d5 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -180,8 +180,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; - if (sb->s_type->fs_flags & FS_THP_SUPPORT) - __set_bit(AS_THP_SUPPORT, &mapping->flags); mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS diff --git a/fs/io-wq.c b/fs/io-wq.c index 88202de519f6..5c4f582d6549 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -142,6 +142,7 @@ static bool io_acct_cancel_pending_work(struct io_wqe *wqe, struct io_wqe_acct *acct, struct io_cb_cancel_data *match); static void create_worker_cb(struct callback_head *cb); +static void io_wq_cancel_tw_create(struct io_wq *wq); static bool io_worker_get(struct io_worker *worker) { @@ -357,12 +358,22 @@ static bool io_queue_worker_create(struct io_worker *worker, test_and_set_bit_lock(0, &worker->create_state)) goto fail_release; + atomic_inc(&wq->worker_refs); init_task_work(&worker->create_work, func); worker->create_index = acct->index; if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { - clear_bit_unlock(0, &worker->create_state); + /* + * EXIT may have been set after checking it above, check after + * adding the task_work and remove any creation item if it is + * now set. wq exit does that too, but we can have added this + * work item after we canceled in io_wq_exit_workers(). + */ + if (test_bit(IO_WQ_BIT_EXIT, &wq->state)) + io_wq_cancel_tw_create(wq); + io_worker_ref_put(wq); return true; } + io_worker_ref_put(wq); clear_bit_unlock(0, &worker->create_state); fail_release: io_worker_release(worker); @@ -384,7 +395,9 @@ static void io_wqe_dec_running(struct io_worker *worker) if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) { atomic_inc(&acct->nr_running); atomic_inc(&wqe->wq->worker_refs); + raw_spin_unlock(&wqe->lock); io_queue_worker_create(worker, acct, create_worker_cb); + raw_spin_lock(&wqe->lock); } } @@ -714,6 +727,13 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data) static inline bool io_should_retry_thread(long err) { + /* + * Prevent perpetual task_work retry, if the task (or its group) is + * exiting. + */ + if (fatal_signal_pending(current)) + return false; + switch (err) { case -EAGAIN: case -ERESTARTSYS: @@ -1191,13 +1211,9 @@ void io_wq_exit_start(struct io_wq *wq) set_bit(IO_WQ_BIT_EXIT, &wq->state); } -static void io_wq_exit_workers(struct io_wq *wq) +static void io_wq_cancel_tw_create(struct io_wq *wq) { struct callback_head *cb; - int node; - - if (!wq->task) - return; while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; @@ -1205,6 +1221,16 @@ static void io_wq_exit_workers(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); } +} + +static void io_wq_exit_workers(struct io_wq *wq) +{ + int node; + + if (!wq->task) + return; + + io_wq_cancel_tw_create(wq); rcu_read_lock(); for_each_node(node) { diff --git a/fs/io_uring.c b/fs/io_uring.c index b07196b4511c..fb2a0cb4aaf8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1278,6 +1278,7 @@ static void io_refs_resurrect(struct percpu_ref *ref, struct completion *compl) static bool io_match_task(struct io_kiocb *head, struct task_struct *task, bool cancel_all) + __must_hold(&req->ctx->timeout_lock) { struct io_kiocb *req; @@ -1293,6 +1294,44 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, return false; } +static bool io_match_linked(struct io_kiocb *head) +{ + struct io_kiocb *req; + + io_for_each_link(req, head) { + if (req->flags & REQ_F_INFLIGHT) + return true; + } + return false; +} + +/* + * As io_match_task() but protected against racing with linked timeouts. + * User must not hold timeout_lock. + */ +static bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task, + bool cancel_all) +{ + bool matched; + + if (task && head->task != task) + return false; + if (cancel_all) + return true; + + if (head->flags & REQ_F_LINK_TIMEOUT) { + struct io_ring_ctx *ctx = head->ctx; + + /* protect against races with linked timeouts */ + spin_lock_irq(&ctx->timeout_lock); + matched = io_match_linked(head); + spin_unlock_irq(&ctx->timeout_lock); + } else { + matched = io_match_linked(head); + } + return matched; +} + static inline bool req_has_async_data(struct io_kiocb *req) { return req->flags & REQ_F_ASYNC_DATA; @@ -1502,10 +1541,10 @@ static void io_prep_async_link(struct io_kiocb *req) if (req->flags & REQ_F_LINK_TIMEOUT) { struct io_ring_ctx *ctx = req->ctx; - spin_lock(&ctx->completion_lock); + spin_lock_irq(&ctx->timeout_lock); io_for_each_link(cur, req) io_prep_async_work(cur); - spin_unlock(&ctx->completion_lock); + spin_unlock_irq(&ctx->timeout_lock); } else { io_for_each_link(cur, req) io_prep_async_work(cur); @@ -2852,9 +2891,13 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; kiocb->ki_pos = READ_ONCE(sqe->off); - if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = file->f_pos; + if (kiocb->ki_pos == -1) { + if (!(file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = file->f_pos; + } else { + kiocb->ki_pos = 0; + } } kiocb->ki_flags = iocb_flags(file); ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); @@ -4327,6 +4370,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, kfree(nxt); if (++i == nbufs) return i; + cond_resched(); } i++; kfree(buf); @@ -5704,7 +5748,7 @@ static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, list = &ctx->cancel_hash[i]; hlist_for_each_entry_safe(req, tmp, list, hash_node) { - if (io_match_task(req, tsk, cancel_all)) + if (io_match_task_safe(req, tsk, cancel_all)) posted += io_poll_remove_one(req); } } @@ -6156,6 +6200,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) return -EFAULT; + if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) + return -EINVAL; + data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode); @@ -6880,10 +6927,11 @@ static inline struct file *io_file_get(struct io_ring_ctx *ctx, static void io_req_task_link_timeout(struct io_kiocb *req, bool *locked) { struct io_kiocb *prev = req->timeout.prev; - int ret; + int ret = -ENOENT; if (prev) { - ret = io_try_cancel_userdata(req, prev->user_data); + if (!(req->task->flags & PF_EXITING)) + ret = io_try_cancel_userdata(req, prev->user_data); io_req_complete_post(req, ret ?: -ETIME, 0); io_put_req(prev); } else { @@ -9255,10 +9303,8 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) struct io_buffer *buf; unsigned long index; - xa_for_each(&ctx->io_buffers, index, buf) { + xa_for_each(&ctx->io_buffers, index, buf) __io_remove_buffers(ctx, buf, index, -1U); - cond_resched(); - } } static void io_req_caches_free(struct io_ring_ctx *ctx) @@ -9562,19 +9608,8 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); struct io_task_cancel *cancel = data; - bool ret; - if (!cancel->all && (req->flags & REQ_F_LINK_TIMEOUT)) { - struct io_ring_ctx *ctx = req->ctx; - - /* protect against races with linked timeouts */ - spin_lock(&ctx->completion_lock); - ret = io_match_task(req, cancel->task, cancel->all); - spin_unlock(&ctx->completion_lock); - } else { - ret = io_match_task(req, cancel->task, cancel->all); - } - return ret; + return io_match_task_safe(req, cancel->task, cancel->all); } static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, @@ -9586,7 +9621,7 @@ static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, spin_lock(&ctx->completion_lock); list_for_each_entry_reverse(de, &ctx->defer_list, list) { - if (io_match_task(de->req, task, cancel_all)) { + if (io_match_task_safe(de->req, task, cancel_all)) { list_cut_position(&list, &ctx->defer_list, &de->list); break; } @@ -9764,7 +9799,7 @@ static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) } if (wq) { /* - * Must be after io_uring_del_task_file() (removes nodes under + * Must be after io_uring_del_tctx_node() (removes nodes under * uring_lock) to avoid race with io_uring_try_cancel_iowq(). */ io_wq_put_and_exit(wq); @@ -9793,7 +9828,7 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task) /* * Find any io_uring ctx that this task has registered or done IO on, and cancel - * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation. + * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation. */ static __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) @@ -9835,8 +9870,10 @@ static __cold void io_uring_cancel_generic(bool cancel_all, cancel_all); } - prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE); + prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE); + io_run_task_work(); io_uring_drop_tctx_refs(current); + /* * If we've seen completions, retry without waiting. This * avoids a race where a completion comes in before we did diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76..71a36ae120ee 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -205,7 +205,16 @@ struct iomap_readpage_ctx { struct readahead_control *rac; }; -static loff_t iomap_read_inline_data(const struct iomap_iter *iter, +/** + * iomap_read_inline_data - copy inline data into the page cache + * @iter: iteration structure + * @page: page to copy to + * + * Copy the inline data in @iter into @page and zero out the rest of the page. + * Only a single IOMAP_INLINE extent is allowed at the end of each file. + * Returns zero for success to complete the read, or the usual negative errno. + */ +static int iomap_read_inline_data(const struct iomap_iter *iter, struct page *page) { const struct iomap *iomap = iomap_iter_srcmap(iter); @@ -214,7 +223,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter, void *addr; if (PageUptodate(page)) - return PAGE_SIZE - poff; + return 0; if (WARN_ON_ONCE(size > PAGE_SIZE - poff)) return -EIO; @@ -231,7 +240,7 @@ static loff_t iomap_read_inline_data(const struct iomap_iter *iter, memset(addr + size, 0, PAGE_SIZE - poff - size); kunmap_local(addr); iomap_set_range_uptodate(page, poff, PAGE_SIZE - poff); - return PAGE_SIZE - poff; + return 0; } static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter, @@ -257,7 +266,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter, sector_t sector; if (iomap->type == IOMAP_INLINE) - return min(iomap_read_inline_data(iter, page), length); + return iomap_read_inline_data(iter, page); /* zero post-eof blocks as the page may be mapped */ iop = iomap_page_create(iter->inode, page); @@ -370,6 +379,8 @@ static loff_t iomap_readahead_iter(const struct iomap_iter *iter, ctx->cur_page_in_bio = false; } ret = iomap_readpage_iter(iter, ctx, done); + if (ret <= 0) + return ret; } return done; @@ -580,15 +591,10 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos, static int iomap_write_begin_inline(const struct iomap_iter *iter, struct page *page) { - int ret; - /* needs more work for the tailpacking case; disable for now */ if (WARN_ON_ONCE(iomap_iter_srcmap(iter)->offset != 0)) return -EIO; - ret = iomap_read_inline_data(iter, page); - if (ret < 0) - return ret; - return 0; + return iomap_read_inline_data(iter, page); } static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos, diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c index 8317f7ca402b..5052be9261d9 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/ksmbd/ndr.c @@ -148,7 +148,7 @@ static int ndr_read_int16(struct ndr *n, __u16 *value) static int ndr_read_int32(struct ndr *n, __u32 *value) { if (n->offset + sizeof(__u32) > n->length) - return 0; + return -EINVAL; if (value) *value = le32_to_cpu(*(__le32 *)ndr_get_field(n)); diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c index 0a5d8450e835..02a44d28bdaf 100644 --- a/fs/ksmbd/smb2ops.c +++ b/fs/ksmbd/smb2ops.c @@ -271,9 +271,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn) if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_LEASES) conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING; - if (conn->cipher_type) - conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; - if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 121f8e8c70ac..b8b3a4c28b74 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -915,6 +915,25 @@ static void decode_encrypt_ctxt(struct ksmbd_conn *conn, } } +/** + * smb3_encryption_negotiated() - checks if server and client agreed on enabling encryption + * @conn: smb connection + * + * Return: true if connection should be encrypted, else false + */ +static bool smb3_encryption_negotiated(struct ksmbd_conn *conn) +{ + if (!conn->ops->generate_encryptionkey) + return false; + + /* + * SMB 3.0 and 3.0.2 dialects use the SMB2_GLOBAL_CAP_ENCRYPTION flag. + * SMB 3.1.1 uses the cipher_type field. + */ + return (conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) || + conn->cipher_type; +} + static void decode_compress_ctxt(struct ksmbd_conn *conn, struct smb2_compression_capabilities_context *pneg_ctxt) { @@ -1469,8 +1488,7 @@ static int ntlm_authenticate(struct ksmbd_work *work) (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) sess->sign = true; - if (conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION && - conn->ops->generate_encryptionkey && + if (smb3_encryption_negotiated(conn) && !(req->Flags & SMB2_SESSION_REQ_FLAG_BINDING)) { rc = conn->ops->generate_encryptionkey(sess); if (rc) { @@ -1559,8 +1577,7 @@ static int krb5_authenticate(struct ksmbd_work *work) (req->SecurityMode & SMB2_NEGOTIATE_SIGNING_REQUIRED)) sess->sign = true; - if ((conn->vals->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) && - conn->ops->generate_encryptionkey) { + if (smb3_encryption_negotiated(conn)) { retval = conn->ops->generate_encryptionkey(sess); if (retval) { ksmbd_debug(SMB, @@ -1697,8 +1714,10 @@ int smb2_sess_setup(struct ksmbd_work *work) negblob_off = le16_to_cpu(req->SecurityBufferOffset); negblob_len = le16_to_cpu(req->SecurityBufferLength); if (negblob_off < offsetof(struct smb2_sess_setup_req, Buffer) || - negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) - return -EINVAL; + negblob_len < offsetof(struct negotiate_message, NegotiateFlags)) { + rc = -EINVAL; + goto out_err; + } negblob = (struct negotiate_message *)((char *)&req->hdr.ProtocolId + negblob_off); @@ -2960,6 +2979,10 @@ int smb2_open(struct ksmbd_work *work) &pntsd_size, &fattr); posix_acl_release(fattr.cf_acls); posix_acl_release(fattr.cf_dacls); + if (rc) { + kfree(pntsd); + goto err_out; + } rc = ksmbd_vfs_set_sd_xattr(conn, user_ns, @@ -4457,6 +4480,12 @@ static void get_file_stream_info(struct ksmbd_work *work, &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; + buf_free_len = + smb2_calc_max_out_buf_len(work, 8, + le32_to_cpu(req->OutputBufferLength)); + if (buf_free_len < 0) + goto out; + xattr_list_len = ksmbd_vfs_listxattr(path->dentry, &xattr_list); if (xattr_list_len < 0) { goto out; @@ -4465,12 +4494,6 @@ static void get_file_stream_info(struct ksmbd_work *work, goto out; } - buf_free_len = - smb2_calc_max_out_buf_len(work, 8, - le32_to_cpu(req->OutputBufferLength)); - if (buf_free_len < 0) - goto out; - while (idx < xattr_list_len) { stream_name = xattr_list + idx; streamlen = strlen(stream_name); @@ -4496,8 +4519,10 @@ static void get_file_stream_info(struct ksmbd_work *work, ":%s", &stream_name[XATTR_NAME_STREAM_LEN]); next = sizeof(struct smb2_file_stream_info) + streamlen * 2; - if (next > buf_free_len) + if (next > buf_free_len) { + kfree(stream_buf); break; + } file_info = (struct smb2_file_stream_info *)&rsp->Buffer[nbytes]; streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName, @@ -4514,6 +4539,7 @@ static void get_file_stream_info(struct ksmbd_work *work, file_info->NextEntryOffset = cpu_to_le32(next); } +out: if (!S_ISDIR(stat.mode) && buf_free_len >= sizeof(struct smb2_file_stream_info) + 7 * 2) { file_info = (struct smb2_file_stream_info *) @@ -4522,14 +4548,13 @@ static void get_file_stream_info(struct ksmbd_work *work, "::$DATA", 7, conn->local_nls, 0); streamlen *= 2; file_info->StreamNameLength = cpu_to_le32(streamlen); - file_info->StreamSize = 0; - file_info->StreamAllocationSize = 0; + file_info->StreamSize = cpu_to_le64(stat.size); + file_info->StreamAllocationSize = cpu_to_le64(stat.blocks << 9); nbytes += sizeof(struct smb2_file_stream_info) + streamlen; } /* last entry offset should be 0 */ file_info->NextEntryOffset = 0; -out: kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); @@ -5068,7 +5093,7 @@ static int smb2_get_info_sec(struct ksmbd_work *work, if (addition_info & ~(OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO | PROTECTED_DACL_SECINFO | UNPROTECTED_DACL_SECINFO)) { - pr_err("Unsupported addition info: 0x%x)\n", + ksmbd_debug(SMB, "Unsupported addition info: 0x%x)\n", addition_info); pntsd->revision = cpu_to_le16(1); diff --git a/fs/namespace.c b/fs/namespace.c index 659a8f39c61a..b696543adab8 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4263,12 +4263,11 @@ SYSCALL_DEFINE5(mount_setattr, int, dfd, const char __user *, path, return err; err = user_path_at(dfd, path, kattr.lookup_flags, &target); - if (err) - return err; - - err = do_mount_setattr(&target, &kattr); + if (!err) { + err = do_mount_setattr(&target, &kattr); + path_put(&target); + } finish_mount_kattr(&kattr); - path_put(&target); return err; } diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 9320a42dfaf9..75c76cbb27cc 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -354,16 +354,11 @@ static void netfs_rreq_write_to_cache_work(struct work_struct *work) netfs_rreq_do_write_to_cache(rreq); } -static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq, - bool was_async) +static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq) { - if (was_async) { - rreq->work.func = netfs_rreq_write_to_cache_work; - if (!queue_work(system_unbound_wq, &rreq->work)) - BUG(); - } else { - netfs_rreq_do_write_to_cache(rreq); - } + rreq->work.func = netfs_rreq_write_to_cache_work; + if (!queue_work(system_unbound_wq, &rreq->work)) + BUG(); } /* @@ -558,7 +553,7 @@ again: wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS); if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags)) - return netfs_rreq_write_to_cache(rreq, was_async); + return netfs_rreq_write_to_cache(rreq); netfs_rreq_completed(rreq, was_async); } @@ -960,7 +955,7 @@ int netfs_readpage(struct file *file, rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) - ops->cleanup(netfs_priv, folio_file_mapping(folio)); + ops->cleanup(folio_file_mapping(folio), netfs_priv); folio_unlock(folio); return -ENOMEM; } @@ -1008,8 +1003,8 @@ out: } EXPORT_SYMBOL(netfs_readpage); -/** - * netfs_skip_folio_read - prep a folio for writing without reading first +/* + * Prepare a folio for writing without reading first * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write @@ -1191,7 +1186,7 @@ have_folio: goto error; have_folio_no_wait: if (netfs_priv) - ops->cleanup(netfs_priv, mapping); + ops->cleanup(mapping, netfs_priv); *_folio = folio; _leave(" = 0"); return 0; @@ -1202,7 +1197,7 @@ error: folio_unlock(folio); folio_put(folio); if (netfs_priv) - ops->cleanup(netfs_priv, mapping); + ops->cleanup(mapping, netfs_priv); _leave(" = %d", ret); return ret; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index dd53704c3f40..fda530d5e764 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -219,6 +219,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) NFS_INO_DATA_INVAL_DEFER); else if (nfsi->cache_validity & NFS_INO_INVALID_DATA) nfsi->cache_validity &= ~NFS_INO_DATA_INVAL_DEFER; + trace_nfs_set_cache_invalid(inode, 0); } EXPORT_SYMBOL_GPL(nfs_set_cache_invalid); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 08355b66e7cb..8b21ff1be717 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -289,7 +289,9 @@ static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len) loff_t newsize = pos + len; loff_t end = newsize - 1; - truncate_pagecache_range(inode, pos, end); + WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping, + pos >> PAGE_SHIFT, end >> PAGE_SHIFT)); + spin_lock(&inode->i_lock); if (newsize > i_size_read(inode)) i_size_write(inode, newsize); diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c index c8bad735e4c1..271e5f92ed01 100644 --- a/fs/nfs/nfs42xdr.c +++ b/fs/nfs/nfs42xdr.c @@ -1434,8 +1434,7 @@ static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp, status = decode_clone(xdr); if (status) goto out; - status = decode_getfattr(xdr, res->dst_fattr, res->server); - + decode_getfattr(xdr, res->dst_fattr, res->server); out: res->rpc_status = status; return status; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ecc4594299d6..f63dfa01001c 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1998,6 +1998,10 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) dprintk("%s: exit with error %d for server %s\n", __func__, -EPROTONOSUPPORT, clp->cl_hostname); return -EPROTONOSUPPORT; + case -ENOSPC: + if (clp->cl_cons_state == NFS_CS_SESSION_INITING) + nfs_mark_client_ready(clp, -EIO); + return -EIO; case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery * in nfs4_exchange_id */ default: diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 21dac847f1e4..b3aee261801e 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -162,6 +162,7 @@ DEFINE_NFS_INODE_EVENT_DONE(nfs_writeback_inode_exit); DEFINE_NFS_INODE_EVENT(nfs_fsync_enter); DEFINE_NFS_INODE_EVENT_DONE(nfs_fsync_exit); DEFINE_NFS_INODE_EVENT(nfs_access_enter); +DEFINE_NFS_INODE_EVENT_DONE(nfs_set_cache_invalid); TRACE_EVENT(nfs_access_exit, TP_PROTO( diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 4418517f6f12..15dac36ca852 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -438,22 +438,19 @@ nfsd3_proc_link(struct svc_rqst *rqstp) static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, struct nfsd3_readdirres *resp, - int count) + u32 count) { struct xdr_buf *buf = &resp->dirlist; struct xdr_stream *xdr = &resp->xdr; - count = min_t(u32, count, svc_max_payload(rqstp)); + count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp)); memset(buf, 0, sizeof(*buf)); /* Reserve room for the NULL ptr & eof flag (-2 words) */ buf->buflen = count - XDR_UNIT * 2; buf->pages = rqstp->rq_next_page; - while (count > 0) { - rqstp->rq_next_page++; - count -= PAGE_SIZE; - } + rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; /* This is xdr_init_encode(), but it assumes that * the head kvec has already been consumed. */ @@ -462,7 +459,7 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp, xdr->page_ptr = buf->pages; xdr->iov = NULL; xdr->p = page_address(*buf->pages); - xdr->end = xdr->p + (PAGE_SIZE >> 2); + xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); xdr->rqst = NULL; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 6fedc49726bf..c634483d85d2 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -2156,6 +2156,7 @@ static struct notifier_block nfsd4_cld_block = { int register_cld_notifier(void) { + WARN_ON(!nfsd_net_id); return rpc_pipefs_notifier_register(&nfsd4_cld_block); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index bfad94c70b84..1956d377d1a6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -1207,6 +1207,11 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) return 0; } +static bool delegation_hashed(struct nfs4_delegation *dp) +{ + return !(list_empty(&dp->dl_perfile)); +} + static bool unhash_delegation_locked(struct nfs4_delegation *dp) { @@ -1214,7 +1219,7 @@ unhash_delegation_locked(struct nfs4_delegation *dp) lockdep_assert_held(&state_lock); - if (list_empty(&dp->dl_perfile)) + if (!delegation_hashed(dp)) return false; dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; @@ -4598,7 +4603,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); - if (dp->dl_time == 0) { + if (delegation_hashed(dp) && dp->dl_time == 0) { dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index b2a1d969a172..5a93a5db4fb0 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -288,11 +288,8 @@ nfsd4_decode_bitmap4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen) p = xdr_inline_decode(argp->xdr, count << 2); if (!p) return nfserr_bad_xdr; - i = 0; - while (i < count) - bmval[i++] = be32_to_cpup(p++); - while (i < bmlen) - bmval[i++] = 0; + for (i = 0; i < bmlen; i++) + bmval[i] = (i < count) ? be32_to_cpup(p++) : 0; return nfs_ok; } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index af8531c3854a..51a49e0cfe37 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1521,12 +1521,9 @@ static int __init init_nfsd(void) int retval; printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n"); - retval = register_cld_notifier(); - if (retval) - return retval; retval = nfsd4_init_slabs(); if (retval) - goto out_unregister_notifier; + return retval; retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; @@ -1545,9 +1542,14 @@ static int __init init_nfsd(void) goto out_free_exports; retval = register_pernet_subsys(&nfsd_net_ops); if (retval < 0) + goto out_free_filesystem; + retval = register_cld_notifier(); + if (retval) goto out_free_all; return 0; out_free_all: + unregister_pernet_subsys(&nfsd_net_ops); +out_free_filesystem: unregister_filesystem(&nfsd_fs_type); out_free_exports: remove_proc_entry("fs/nfs/exports", NULL); @@ -1561,13 +1563,12 @@ out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: nfsd4_free_slabs(); -out_unregister_notifier: - unregister_cld_notifier(); return retval; } static void __exit exit_nfsd(void) { + unregister_cld_notifier(); unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); remove_proc_entry("fs/nfs/exports", NULL); @@ -1577,7 +1578,6 @@ static void __exit exit_nfsd(void) nfsd4_free_slabs(); nfsd4_exit_pnfs(); unregister_filesystem(&nfsd_fs_type); - unregister_cld_notifier(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index eea5b59b6a6c..de282f3273c5 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -556,17 +556,17 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp) static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, struct nfsd_readdirres *resp, - int count) + u32 count) { struct xdr_buf *buf = &resp->dirlist; struct xdr_stream *xdr = &resp->xdr; - count = min_t(u32, count, PAGE_SIZE); + count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp)); memset(buf, 0, sizeof(*buf)); /* Reserve room for the NULL ptr & eof flag (-2 words) */ - buf->buflen = count - sizeof(__be32) * 2; + buf->buflen = count - XDR_UNIT * 2; buf->pages = rqstp->rq_next_page; rqstp->rq_next_page++; @@ -577,7 +577,7 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp, xdr->page_ptr = buf->pages; xdr->iov = NULL; xdr->p = page_address(*buf->pages); - xdr->end = xdr->p + (PAGE_SIZE >> 2); + xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE); xdr->rqst = NULL; } diff --git a/fs/ntfs/Kconfig b/fs/ntfs/Kconfig index 1667a7e590d8..f93e69a61283 100644 --- a/fs/ntfs/Kconfig +++ b/fs/ntfs/Kconfig @@ -52,6 +52,7 @@ config NTFS_DEBUG config NTFS_RW bool "NTFS write support" depends on NTFS_FS + depends on PAGE_SIZE_LESS_THAN_64KB help This enables the partial, but safe, write support in the NTFS driver. diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 30a3b66f475a..509f85148fee 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -154,9 +154,13 @@ ssize_t read_from_oldmem(char *buf, size_t count, nr_bytes = count; /* If pfn is not ram, return zeros for sparse dump files */ - if (!pfn_is_ram(pfn)) - memset(buf, 0, nr_bytes); - else { + if (!pfn_is_ram(pfn)) { + tmp = 0; + if (!userbuf) + memset(buf, 0, nr_bytes); + else if (clear_user(buf, nr_bytes)) + tmp = -EFAULT; + } else { if (encrypted) tmp = copy_oldmem_page_encrypted(pfn, buf, nr_bytes, @@ -165,12 +169,12 @@ ssize_t read_from_oldmem(char *buf, size_t count, else tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - - if (tmp < 0) { - up_read(&vmcore_cb_rwsem); - return tmp; - } } + if (tmp < 0) { + up_read(&vmcore_cb_rwsem); + return tmp; + } + *ppos += nr_bytes; count -= nr_bytes; buf += nr_bytes; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 5d1fbaffd66a..4ae0cfcd15f2 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -309,7 +309,7 @@ static int __init __best_effort_init(void) if (ret) kfree(best_effort_dev); else - pr_info("attached %s (%zu) (no dedicated panic_write!)\n", + pr_info("attached %s (%lu) (no dedicated panic_write!)\n", blkdev, best_effort_dev->zone.total_size); return ret; diff --git a/fs/signalfd.c b/fs/signalfd.c index 040e1cf90528..65ce0e72e7b9 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -35,17 +35,7 @@ void signalfd_cleanup(struct sighand_struct *sighand) { - wait_queue_head_t *wqh = &sighand->signalfd_wqh; - /* - * The lockless check can race with remove_wait_queue() in progress, - * but in this case its caller should run under rcu_read_lock() and - * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return. - */ - if (likely(!waitqueue_active(wqh))) - return; - - /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */ - wake_up_poll(wqh, EPOLLHUP | POLLFREE); + wake_up_pollfree(&sighand->signalfd_wqh); } struct signalfd_ctx { diff --git a/fs/smbfs_common/cifs_arc4.c b/fs/smbfs_common/cifs_arc4.c index 85ba15a60b13..043e4cb839fa 100644 --- a/fs/smbfs_common/cifs_arc4.c +++ b/fs/smbfs_common/cifs_arc4.c @@ -72,16 +72,3 @@ void cifs_arc4_crypt(struct arc4_ctx *ctx, u8 *out, const u8 *in, unsigned int l ctx->y = y; } EXPORT_SYMBOL_GPL(cifs_arc4_crypt); - -static int __init -init_smbfs_common(void) -{ - return 0; -} -static void __init -exit_smbfs_common(void) -{ -} - -module_init(init_smbfs_common) -module_exit(exit_smbfs_common) diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index 925a621b432e..3616839c5c4b 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -161,6 +161,77 @@ struct tracefs_fs_info { struct tracefs_mount_opts mount_opts; }; +static void change_gid(struct dentry *dentry, kgid_t gid) +{ + if (!dentry->d_inode) + return; + dentry->d_inode->i_gid = gid; +} + +/* + * Taken from d_walk, but without he need for handling renames. + * Nothing can be renamed while walking the list, as tracefs + * does not support renames. This is only called when mounting + * or remounting the file system, to set all the files to + * the given gid. + */ +static void set_gid(struct dentry *parent, kgid_t gid) +{ + struct dentry *this_parent; + struct list_head *next; + + this_parent = parent; + spin_lock(&this_parent->d_lock); + + change_gid(this_parent, gid); +repeat: + next = this_parent->d_subdirs.next; +resume: + while (next != &this_parent->d_subdirs) { + struct list_head *tmp = next; + struct dentry *dentry = list_entry(tmp, struct dentry, d_child); + next = tmp->next; + + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + + change_gid(dentry, gid); + + if (!list_empty(&dentry->d_subdirs)) { + spin_unlock(&this_parent->d_lock); + spin_release(&dentry->d_lock.dep_map, _RET_IP_); + this_parent = dentry; + spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_); + goto repeat; + } + spin_unlock(&dentry->d_lock); + } + /* + * All done at this level ... ascend and resume the search. + */ + rcu_read_lock(); +ascend: + if (this_parent != parent) { + struct dentry *child = this_parent; + this_parent = child->d_parent; + + spin_unlock(&child->d_lock); + spin_lock(&this_parent->d_lock); + + /* go into the first sibling still alive */ + do { + next = child->d_child.next; + if (next == &this_parent->d_subdirs) + goto ascend; + child = list_entry(next, struct dentry, d_child); + } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)); + rcu_read_unlock(); + goto resume; + } + rcu_read_unlock(); + spin_unlock(&this_parent->d_lock); + return; +} + static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) { substring_t args[MAX_OPT_ARGS]; @@ -193,6 +264,7 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) if (!gid_valid(gid)) return -EINVAL; opts->gid = gid; + set_gid(tracefs_mount->mnt_root, gid); break; case Opt_mode: if (match_octal(&args[0], &option)) @@ -414,6 +486,8 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode, inode->i_mode = mode; inode->i_fop = fops ? fops : &tracefs_file_operations; inode->i_private = data; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; d_instantiate(dentry, inode); fsnotify_create(dentry->d_parent->d_inode, dentry); return end_creating(dentry); @@ -436,6 +510,8 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent, inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP; inode->i_op = ops; inode->i_fop = &simple_dir_operations; + inode->i_uid = d_inode(dentry->d_parent)->i_uid; + inode->i_gid = d_inode(dentry->d_parent)->i_gid; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); diff --git a/fs/udf/dir.c b/fs/udf/dir.c index 70abdfad2df1..42e3e551fa4c 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -31,6 +31,7 @@ #include <linux/mm.h> #include <linux/slab.h> #include <linux/bio.h> +#include <linux/iversion.h> #include "udf_i.h" #include "udf_sb.h" @@ -43,7 +44,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) struct fileIdentDesc *fi = NULL; struct fileIdentDesc cfi; udf_pblk_t block, iblock; - loff_t nf_pos; + loff_t nf_pos, emit_pos = 0; int flen; unsigned char *fname = NULL, *copy_name = NULL; unsigned char *nameptr; @@ -57,6 +58,7 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) int i, num, ret = 0; struct extent_position epos = { NULL, 0, {0, 0} }; struct super_block *sb = dir->i_sb; + bool pos_valid = false; if (ctx->pos == 0) { if (!dir_emit_dot(file, ctx)) @@ -67,6 +69,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) if (nf_pos >= size) goto out; + /* + * Something changed since last readdir (either lseek was called or dir + * changed)? We need to verify the position correctly points at the + * beginning of some dir entry so that the directory parsing code does + * not get confused. Since UDF does not have any reliable way of + * identifying beginning of dir entry (names are under user control), + * we need to scan the directory from the beginning. + */ + if (!inode_eq_iversion(dir, file->f_version)) { + emit_pos = nf_pos; + nf_pos = 0; + } else { + pos_valid = true; + } + fname = kmalloc(UDF_NAME_LEN, GFP_NOFS); if (!fname) { ret = -ENOMEM; @@ -122,13 +139,21 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) while (nf_pos < size) { struct kernel_lb_addr tloc; + loff_t cur_pos = nf_pos; - ctx->pos = (nf_pos >> 2) + 1; + /* Update file position only if we got past the current one */ + if (nf_pos >= emit_pos) { + ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; + } fi = udf_fileident_read(dir, &nf_pos, &fibh, &cfi, &epos, &eloc, &elen, &offset); if (!fi) goto out; + /* Still not at offset where user asked us to read from? */ + if (cur_pos < emit_pos) + continue; liu = le16_to_cpu(cfi.lengthOfImpUse); lfi = cfi.lengthFileIdent; @@ -186,8 +211,11 @@ static int udf_readdir(struct file *file, struct dir_context *ctx) } /* end while */ ctx->pos = (nf_pos >> 2) + 1; + pos_valid = true; out: + if (pos_valid) + file->f_version = inode_query_iversion(dir); if (fibh.sbh != fibh.ebh) brelse(fibh.ebh); brelse(fibh.sbh); diff --git a/fs/udf/namei.c b/fs/udf/namei.c index caeef08efed2..0ed4861b038f 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> +#include <linux/iversion.h> static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) @@ -134,6 +135,8 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi, mark_buffer_dirty_inode(fibh->ebh, inode); mark_buffer_dirty_inode(fibh->sbh, inode); } + inode_inc_iversion(inode); + return 0; } diff --git a/fs/udf/super.c b/fs/udf/super.c index 34247fba6df9..f26b5e0b84b6 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -57,6 +57,7 @@ #include <linux/crc-itu-t.h> #include <linux/log2.h> #include <asm/byteorder.h> +#include <linux/iversion.h> #include "udf_sb.h" #include "udf_i.h" @@ -149,6 +150,7 @@ static struct inode *udf_alloc_inode(struct super_block *sb) init_rwsem(&ei->i_data_sem); ei->cached_extent.lstart = -1; spin_lock_init(&ei->i_extent_cache_lock); + inode_set_iversion(&ei->vfs_inode, 1); return &ei->vfs_inode; } diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index fbc9d816882c..23523b802539 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1077,21 +1077,18 @@ xfs_attr_node_hasname( state = xfs_da_state_alloc(args); if (statep != NULL) - *statep = NULL; + *statep = state; /* * Search to see if name exists, and get back a pointer to it. */ error = xfs_da3_node_lookup_int(state, &retval); - if (error) { - xfs_da_state_free(state); - return error; - } + if (error) + retval = error; - if (statep != NULL) - *statep = state; - else + if (!statep) xfs_da_state_free(state); + return retval; } @@ -1112,7 +1109,7 @@ xfs_attr_node_addname_find_attr( */ retval = xfs_attr_node_hasname(args, &dac->da_state); if (retval != -ENOATTR && retval != -EEXIST) - return retval; + goto error; if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE)) goto error; @@ -1337,7 +1334,7 @@ int xfs_attr_node_removename_setup( error = xfs_attr_node_hasname(args, state); if (error != -EEXIST) - return error; + goto out; error = 0; ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index e1472004170e..da4af2142a2b 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -289,22 +289,6 @@ xfs_perag_clear_inode_tag( trace_xfs_perag_clear_inode_tag(mp, pag->pag_agno, tag, _RET_IP_); } -static inline void -xfs_inew_wait( - struct xfs_inode *ip) -{ - wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT); - DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT); - - do { - prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); - if (!xfs_iflags_test(ip, XFS_INEW)) - break; - schedule(); - } while (true); - finish_wait(wq, &wait.wq_entry); -} - /* * When we recycle a reclaimable inode, we need to re-initialise the VFS inode * part of the structure. This is made more complex by the fact we store @@ -368,18 +352,13 @@ xfs_iget_recycle( ASSERT(!rwsem_is_locked(&inode->i_rwsem)); error = xfs_reinit_inode(mp, inode); if (error) { - bool wake; - /* * Re-initializing the inode failed, and we are in deep * trouble. Try to re-add it to the reclaim list. */ rcu_read_lock(); spin_lock(&ip->i_flags_lock); - wake = !!__xfs_iflags_test(ip, XFS_INEW); ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM); - if (wake) - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); ASSERT(ip->i_flags & XFS_IRECLAIMABLE); spin_unlock(&ip->i_flags_lock); rcu_read_unlock(); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 64b9bf334806..6771f357ad2c 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -3122,7 +3122,6 @@ xfs_rename( * appropriately. */ if (flags & RENAME_WHITEOUT) { - ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE))); error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip); if (error) return error; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index e635a3d64cba..c447bf04205a 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -231,8 +231,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) #define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */ #define XFS_ISTALE (1 << 1) /* inode has been staled */ #define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */ -#define __XFS_INEW_BIT 3 /* inode has just been allocated */ -#define XFS_INEW (1 << __XFS_INEW_BIT) +#define XFS_INEW (1 << 3) /* inode has just been allocated */ #define XFS_IPRESERVE_DM_FIELDS (1 << 4) /* has legacy DMAPI fields set */ #define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */ #define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */ @@ -492,7 +491,6 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip) xfs_iflags_clear(ip, XFS_INEW); barrier(); unlock_new_inode(VFS_I(ip)); - wake_up_bit(&ip->i_flags, __XFS_INEW_BIT); } static inline void xfs_setup_existing_inode(struct xfs_inode *ip) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e21459f9923a..778b57b1f020 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1765,7 +1765,10 @@ static int xfs_remount_ro( struct xfs_mount *mp) { - int error; + struct xfs_icwalk icw = { + .icw_flags = XFS_ICWALK_FLAG_SYNC, + }; + int error; /* * Cancel background eofb scanning so it cannot race with the final @@ -1773,8 +1776,13 @@ xfs_remount_ro( */ xfs_blockgc_stop(mp); - /* Get rid of any leftover CoW reservations... */ - error = xfs_blockgc_free_space(mp, NULL); + /* + * Clear out all remaining COW staging extents and speculative post-EOF + * preallocations so that we don't leave inodes requiring inactivation + * cleanups during reclaim on a read-only mount. We must process every + * cached inode, so this requires a synchronous cache scan. + */ + error = xfs_blockgc_free_space(mp, &icw); if (error) { xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 259ee2bda492..b76dfb310ab6 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1787,5 +1787,6 @@ static void __exit zonefs_exit(void) MODULE_AUTHOR("Damien Le Moal"); MODULE_DESCRIPTION("Zone file system for zoned block devices"); MODULE_LICENSE("GPL"); +MODULE_ALIAS_FS("zonefs"); module_init(zonefs_init); module_exit(zonefs_exit); |