Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

No conflicts.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

24 files changed, 438 insertions, 138 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);
 }
 
diff --git a/fs/aio.c b/fs/aio.c
index 9c81cf611d65..f6f1cbffef9e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -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/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/extent-tree.c b/fs/btrfs/extent-tree.c
index 3fd736a02c1e..fc4895e6a62c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6051,6 +6051,9 @@ 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..3258b6f01e85 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.
 	 */
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 92138ac2a4e2..2b84846ed934 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3187,10 +3187,8 @@ 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;
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/tree-log.c b/fs/btrfs/tree-log.c
index 8ab33caf016f..3e6f14e13918 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2908,6 +2908,8 @@ 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 +2990,7 @@ 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 +3441,6 @@ 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);
 }
 
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/sess.c b/fs/cifs/sess.c
index af63548eaf26..035dc3e245dc 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -590,8 +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);
@@ -609,12 +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) {
@@ -721,13 +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 */
@@ -779,15 +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);
@@ -834,9 +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/file.c b/fs/file.c
index ad4a8bf3cf10..97d212a9b814 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -841,28 +841,68 @@ void do_close_on_exec(struct files_struct *files)
 	spin_unlock(&files->file_lock);
 }
 
-static struct file *__fget_files(struct files_struct *files, unsigned int fd,
-				 fmode_t mask, unsigned int refs)
+static inline struct file *__fget_files_rcu(struct files_struct *files,
+	unsigned int fd, fmode_t mask, unsigned int refs)
 {
-	struct file *file;
+	for (;;) {
+		struct file *file;
+		struct fdtable *fdt = rcu_dereference_raw(files->fdt);
+		struct file __rcu **fdentry;
 
-	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 (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 (file->f_mode & mask)
-			file = NULL;
-		else if (!get_file_rcu_many(file, refs))
-			goto loop;
-		else if (files_lookup_fd_raw(files, fd) != file) {
+		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);
-			goto loop;
+			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();
+	file = __fget_files_rcu(files, fd, mask, refs);
 	rcu_read_unlock();
 
 	return file;
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 50cf9f92da36..8d2bb818a3bb 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);
@@ -1198,13 +1209,9 @@ 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;
@@ -1212,6 +1219,16 @@ 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 c4f217613f56..d5ab0e9a3f29 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -9824,7 +9824,7 @@ 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)
@@ -9866,8 +9866,10 @@ 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/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/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/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/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;