Merge branch 'for-5.11/elecom' into for-linus

- support for EX-G M-XGL20DLBK device, from YOSHIOKA Takuma

18 files changed, 468 insertions, 257 deletions

diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 5b79cdceefa0..887b673f6223 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -18,8 +18,10 @@
 static unsigned __read_mostly afs_cell_gc_delay = 10;
 static unsigned __read_mostly afs_cell_min_ttl = 10 * 60;
 static unsigned __read_mostly afs_cell_max_ttl = 24 * 60 * 60;
+static atomic_t cell_debug_id;
 
-static void afs_manage_cell(struct work_struct *);
+static void afs_queue_cell_manager(struct afs_net *);
+static void afs_manage_cell_work(struct work_struct *);
 
 static void afs_dec_cells_outstanding(struct afs_net *net)
 {
@@ -37,19 +39,22 @@ static void afs_set_cell_timer(struct afs_net *net, time64_t delay)
 		atomic_inc(&net->cells_outstanding);
 		if (timer_reduce(&net->cells_timer, jiffies + delay * HZ))
 			afs_dec_cells_outstanding(net);
+	} else {
+		afs_queue_cell_manager(net);
 	}
 }
 
 /*
- * Look up and get an activation reference on a cell record under RCU
- * conditions.  The caller must hold the RCU read lock.
+ * Look up and get an activation reference on a cell record.  The caller must
+ * hold net->cells_lock at least read-locked.
  */
-struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
-				     const char *name, unsigned int namesz)
+static struct afs_cell *afs_find_cell_locked(struct afs_net *net,
+					     const char *name, unsigned int namesz,
+					     enum afs_cell_trace reason)
 {
 	struct afs_cell *cell = NULL;
 	struct rb_node *p;
-	int n, seq = 0, ret = 0;
+	int n;
 
 	_enter("%*.*s", namesz, namesz, name);
 
@@ -58,61 +63,48 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,
 	if (namesz > AFS_MAXCELLNAME)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	do {
-		/* Unfortunately, rbtree walking doesn't give reliable results
-		 * under just the RCU read lock, so we have to check for
-		 * changes.
-		 */
-		if (cell)
-			afs_put_cell(net, cell);
-		cell = NULL;
-		ret = -ENOENT;
-
-		read_seqbegin_or_lock(&net->cells_lock, &seq);
-
-		if (!name) {
-			cell = rcu_dereference_raw(net->ws_cell);
-			if (cell) {
-				afs_get_cell(cell);
-				ret = 0;
-				break;
-			}
-			ret = -EDESTADDRREQ;
-			continue;
-		}
+	if (!name) {
+		cell = net->ws_cell;
+		if (!cell)
+			return ERR_PTR(-EDESTADDRREQ);
+		goto found;
+	}
 
-		p = rcu_dereference_raw(net->cells.rb_node);
-		while (p) {
-			cell = rb_entry(p, struct afs_cell, net_node);
-
-			n = strncasecmp(cell->name, name,
-					min_t(size_t, cell->name_len, namesz));
-			if (n == 0)
-				n = cell->name_len - namesz;
-			if (n < 0) {
-				p = rcu_dereference_raw(p->rb_left);
-			} else if (n > 0) {
-				p = rcu_dereference_raw(p->rb_right);
-			} else {
-				if (atomic_inc_not_zero(&cell->usage)) {
-					ret = 0;
-					break;
-				}
-				/* We want to repeat the search, this time with
-				 * the lock properly locked.
-				 */
-			}
-			cell = NULL;
-		}
+	p = net->cells.rb_node;
+	while (p) {
+		cell = rb_entry(p, struct afs_cell, net_node);
 
-	} while (need_seqretry(&net->cells_lock, seq));
+		n = strncasecmp(cell->name, name,
+				min_t(size_t, cell->name_len, namesz));
+		if (n == 0)
+			n = cell->name_len - namesz;
+		if (n < 0)
+			p = p->rb_left;
+		else if (n > 0)
+			p = p->rb_right;
+		else
+			goto found;
+	}
 
-	done_seqretry(&net->cells_lock, seq);
+	return ERR_PTR(-ENOENT);
 
-	if (ret != 0 && cell)
-		afs_put_cell(net, cell);
+found:
+	return afs_use_cell(cell, reason);
+}
 
-	return ret == 0 ? cell : ERR_PTR(ret);
+/*
+ * Look up and get an activation reference on a cell record.
+ */
+struct afs_cell *afs_find_cell(struct afs_net *net,
+			       const char *name, unsigned int namesz,
+			       enum afs_cell_trace reason)
+{
+	struct afs_cell *cell;
+
+	down_read(&net->cells_lock);
+	cell = afs_find_cell_locked(net, name, namesz, reason);
+	up_read(&net->cells_lock);
+	return cell;
 }
 
 /*
@@ -166,8 +158,9 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 		cell->name[i] = tolower(name[i]);
 	cell->name[i] = 0;
 
-	atomic_set(&cell->usage, 2);
-	INIT_WORK(&cell->manager, afs_manage_cell);
+	atomic_set(&cell->ref, 1);
+	atomic_set(&cell->active, 0);
+	INIT_WORK(&cell->manager, afs_manage_cell_work);
 	cell->volumes = RB_ROOT;
 	INIT_HLIST_HEAD(&cell->proc_volumes);
 	seqlock_init(&cell->volume_lock);
@@ -206,6 +199,9 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net,
 	cell->dns_source = vllist->source;
 	cell->dns_status = vllist->status;
 	smp_store_release(&cell->dns_lookup_count, 1); /* vs source/status */
+	atomic_inc(&net->cells_outstanding);
+	cell->debug_id = atomic_inc_return(&cell_debug_id);
+	trace_afs_cell(cell->debug_id, 1, 0, afs_cell_trace_alloc);
 
 	_leave(" = %p", cell);
 	return cell;
@@ -245,9 +241,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	_enter("%s,%s", name, vllist);
 
 	if (!excl) {
-		rcu_read_lock();
-		cell = afs_lookup_cell_rcu(net, name, namesz);
-		rcu_read_unlock();
+		cell = afs_find_cell(net, name, namesz, afs_cell_trace_use_lookup);
 		if (!IS_ERR(cell))
 			goto wait_for_cell;
 	}
@@ -268,7 +262,7 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 	/* Find the insertion point and check to see if someone else added a
 	 * cell whilst we were allocating.
 	 */
-	write_seqlock(&net->cells_lock);
+	down_write(&net->cells_lock);
 
 	pp = &net->cells.rb_node;
 	parent = NULL;
@@ -290,23 +284,26 @@ struct afs_cell *afs_lookup_cell(struct afs_net *net,
 
 	cell = candidate;
 	candidate = NULL;
+	atomic_set(&cell->active, 2);
+	trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 2, afs_cell_trace_insert);
 	rb_link_node_rcu(&cell->net_node, parent, pp);
 	rb_insert_color(&cell->net_node, &net->cells);
-	atomic_inc(&net->cells_outstanding);
-	write_sequnlock(&net->cells_lock);
+	up_write(&net->cells_lock);
 
-	queue_work(afs_wq, &cell->manager);
+	afs_queue_cell(cell, afs_cell_trace_get_queue_new);
 
 wait_for_cell:
+	trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), atomic_read(&cell->active),
+		       afs_cell_trace_wait);
 	_debug("wait_for_cell");
 	wait_var_event(&cell->state,
 		       ({
 			       state = smp_load_acquire(&cell->state); /* vs error */
-			       state == AFS_CELL_ACTIVE || state == AFS_CELL_FAILED;
+			       state == AFS_CELL_ACTIVE || state == AFS_CELL_REMOVED;
 		       }));
 
 	/* Check the state obtained from the wait check. */
-	if (state == AFS_CELL_FAILED) {
+	if (state == AFS_CELL_REMOVED) {
 		ret = cell->error;
 		goto error;
 	}
@@ -320,16 +317,17 @@ cell_already_exists:
 	if (excl) {
 		ret = -EEXIST;
 	} else {
-		afs_get_cell(cursor);
+		afs_use_cell(cursor, afs_cell_trace_use_lookup);
 		ret = 0;
 	}
-	write_sequnlock(&net->cells_lock);
-	kfree(candidate);
+	up_write(&net->cells_lock);
+	if (candidate)
+		afs_put_cell(candidate, afs_cell_trace_put_candidate);
 	if (ret == 0)
 		goto wait_for_cell;
 	goto error_noput;
 error:
-	afs_put_cell(net, cell);
+	afs_unuse_cell(net, cell, afs_cell_trace_unuse_lookup);
 error_noput:
 	_leave(" = %d [error]", ret);
 	return ERR_PTR(ret);
@@ -374,15 +372,16 @@ int afs_cell_init(struct afs_net *net, const char *rootcell)
 	}
 
 	if (!test_and_set_bit(AFS_CELL_FL_NO_GC, &new_root->flags))
-		afs_get_cell(new_root);
+		afs_use_cell(new_root, afs_cell_trace_use_pin);
 
 	/* install the new cell */
-	write_seqlock(&net->cells_lock);
-	old_root = rcu_access_pointer(net->ws_cell);
-	rcu_assign_pointer(net->ws_cell, new_root);
-	write_sequnlock(&net->cells_lock);
+	down_write(&net->cells_lock);
+	afs_see_cell(new_root, afs_cell_trace_see_ws);
+	old_root = net->ws_cell;
+	net->ws_cell = new_root;
+	up_write(&net->cells_lock);
 
-	afs_put_cell(net, old_root);
+	afs_unuse_cell(net, old_root, afs_cell_trace_unuse_ws);
 	_leave(" = 0");
 	return 0;
 }
@@ -488,18 +487,22 @@ out_wake:
 static void afs_cell_destroy(struct rcu_head *rcu)
 {
 	struct afs_cell *cell = container_of(rcu, struct afs_cell, rcu);
+	struct afs_net *net = cell->net;
+	int u;
 
 	_enter("%p{%s}", cell, cell->name);
 
-	ASSERTCMP(atomic_read(&cell->usage), ==, 0);
+	u = atomic_read(&cell->ref);
+	ASSERTCMP(u, ==, 0);
+	trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), afs_cell_trace_free);
 
-	afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root);
-	afs_put_vlserverlist(cell->net, rcu_access_pointer(cell->vl_servers));
-	afs_put_cell(cell->net, cell->alias_of);
+	afs_put_vlserverlist(net, rcu_access_pointer(cell->vl_servers));
+	afs_unuse_cell(net, cell->alias_of, afs_cell_trace_unuse_alias);
 	key_put(cell->anonymous_key);
 	kfree(cell->name);
 	kfree(cell);
 
+	afs_dec_cells_outstanding(net);
 	_leave(" [destroyed]");
 }
 
@@ -532,18 +535,63 @@ void afs_cells_timer(struct timer_list *timer)
 /*
  * Get a reference on a cell record.
  */
-struct afs_cell *afs_get_cell(struct afs_cell *cell)
+struct afs_cell *afs_get_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
-	atomic_inc(&cell->usage);
+	int u;
+
+	if (atomic_read(&cell->ref) <= 0)
+		BUG();
+
+	u = atomic_inc_return(&cell->ref);
+	trace_afs_cell(cell->debug_id, u, atomic_read(&cell->active), reason);
 	return cell;
 }
 
 /*
  * Drop a reference on a cell record.
  */
-void afs_put_cell(struct afs_net *net, struct afs_cell *cell)
+void afs_put_cell(struct afs_cell *cell, enum afs_cell_trace reason)
 {
+	if (cell) {
+		unsigned int debug_id = cell->debug_id;
+		unsigned int u, a;
+
+		a = atomic_read(&cell->active);
+		u = atomic_dec_return(&cell->ref);
+		trace_afs_cell(debug_id, u, a, reason);
+		if (u == 0) {
+			a = atomic_read(&cell->active);
+			WARN(a != 0, "Cell active count %u > 0\n", a);
+			call_rcu(&cell->rcu, afs_cell_destroy);
+		}
+	}
+}
+
+/*
+ * Note a cell becoming more active.
+ */
+struct afs_cell *afs_use_cell(struct afs_cell *cell, enum afs_cell_trace reason)
+{
+	int u, a;
+
+	if (atomic_read(&cell->ref) <= 0)
+		BUG();
+
+	u = atomic_read(&cell->ref);
+	a = atomic_inc_return(&cell->active);
+	trace_afs_cell(cell->debug_id, u, a, reason);
+	return cell;
+}
+
+/*
+ * Record a cell becoming less active.  When the active counter reaches 1, it
+ * is scheduled for destruction, but may get reactivated.
+ */
+void afs_unuse_cell(struct afs_net *net, struct afs_cell *cell, enum afs_cell_trace reason)
+{
+	unsigned int debug_id;
 	time64_t now, expire_delay;
+	int u, a;
 
 	if (!cell)
 		return;
@@ -556,11 +604,36 @@ void afs_put_cell(struct afs_net *net, struct afs_cell *cell)
 	if (cell->vl_servers->nr_servers)
 		expire_delay = afs_cell_gc_delay;
 
-	if (atomic_dec_return(&cell->usage) > 1)
-		return;
+	debug_id = cell->debug_id;
+	u = atomic_read(&cell->ref);
+	a = atomic_dec_return(&cell->active);
+	trace_afs_cell(debug_id, u, a, reason);
+	WARN_ON(a == 0);
+	if (a == 1)
+		/* 'cell' may now be garbage collected. */
+		afs_set_cell_timer(net, expire_delay);
+}
+
+/*
+ * Note that a cell has been seen.
+ */
+void afs_see_cell(struct afs_cell *cell, enum afs_cell_trace reason)
+{
+	int u, a;
+
+	u = atomic_read(&cell->ref);
+	a = atomic_read(&cell->active);
+	trace_afs_cell(cell->debug_id, u, a, reason);
+}
 
-	/* 'cell' may now be garbage collected. */
-	afs_set_cell_timer(net, expire_delay);
+/*
+ * Queue a cell for management, giving the workqueue a ref to hold.
+ */
+void afs_queue_cell(struct afs_cell *cell, enum afs_cell_trace reason)
+{
+	afs_get_cell(cell, reason);
+	if (!queue_work(afs_wq, &cell->manager))
+		afs_put_cell(cell, afs_cell_trace_put_queue_fail);
 }
 
 /*
@@ -660,12 +733,10 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell)
  * Manage a cell record, initialising and destroying it, maintaining its DNS
  * records.
  */
-static void afs_manage_cell(struct work_struct *work)
+static void afs_manage_cell(struct afs_cell *cell)
 {
-	struct afs_cell *cell = container_of(work, struct afs_cell, manager);
 	struct afs_net *net = cell->net;
-	bool deleted;
-	int ret, usage;
+	int ret, active;
 
 	_enter("%s", cell->name);
 
@@ -674,14 +745,19 @@ again:
 	switch (cell->state) {
 	case AFS_CELL_INACTIVE:
 	case AFS_CELL_FAILED:
-		write_seqlock(&net->cells_lock);
-		usage = 1;
-		deleted = atomic_try_cmpxchg_relaxed(&cell->usage, &usage, 0);
-		if (deleted)
+		down_write(&net->cells_lock);
+		active = 1;
+		if (atomic_try_cmpxchg_relaxed(&cell->active, &active, 0)) {
 			rb_erase(&cell->net_node, &net->cells);
-		write_sequnlock(&net->cells_lock);
-		if (deleted)
+			trace_afs_cell(cell->debug_id, atomic_read(&cell->ref), 0,
+				       afs_cell_trace_unuse_delete);
+			smp_store_release(&cell->state, AFS_CELL_REMOVED);
+		}
+		up_write(&net->cells_lock);
+		if (cell->state == AFS_CELL_REMOVED) {
+			wake_up_var(&cell->state);
 			goto final_destruction;
+		}
 		if (cell->state == AFS_CELL_FAILED)
 			goto done;
 		smp_store_release(&cell->state, AFS_CELL_UNSET);
@@ -703,7 +779,7 @@ again:
 		goto again;
 
 	case AFS_CELL_ACTIVE:
-		if (atomic_read(&cell->usage) > 1) {
+		if (atomic_read(&cell->active) > 1) {
 			if (test_and_clear_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags)) {
 				ret = afs_update_cell(cell);
 				if (ret < 0)
@@ -716,13 +792,16 @@ again:
 		goto again;
 
 	case AFS_CELL_DEACTIVATING:
-		if (atomic_read(&cell->usage) > 1)
+		if (atomic_read(&cell->active) > 1)
 			goto reverse_deactivation;
 		afs_deactivate_cell(net, cell);
 		smp_store_release(&cell->state, AFS_CELL_INACTIVE);
 		wake_up_var(&cell->state);
 		goto again;
 
+	case AFS_CELL_REMOVED:
+		goto done;
+
 	default:
 		break;
 	}
@@ -748,9 +827,18 @@ done:
 	return;
 
 final_destruction:
-	call_rcu(&cell->rcu, afs_cell_destroy);
-	afs_dec_cells_outstanding(net);
-	_leave(" [destruct %d]", atomic_read(&net->cells_outstanding));
+	/* The root volume is pinning the cell */
+	afs_put_volume(cell->net, cell->root_volume, afs_volume_trace_put_cell_root);
+	cell->root_volume = NULL;
+	afs_put_cell(cell, afs_cell_trace_put_destroy);
+}
+
+static void afs_manage_cell_work(struct work_struct *work)
+{
+	struct afs_cell *cell = container_of(work, struct afs_cell, manager);
+
+	afs_manage_cell(cell);
+	afs_put_cell(cell, afs_cell_trace_put_queue_work);
 }
 
 /*
@@ -779,26 +867,29 @@ void afs_manage_cells(struct work_struct *work)
 	 * lack of use and cells whose DNS results have expired and dispatch
 	 * their managers.
 	 */
-	read_seqlock_excl(&net->cells_lock);
+	down_read(&net->cells_lock);
 
 	for (cursor = rb_first(&net->cells); cursor; cursor = rb_next(cursor)) {
 		struct afs_cell *cell =
 			rb_entry(cursor, struct afs_cell, net_node);
-		unsigned usage;
+		unsigned active;
 		bool sched_cell = false;
 
-		usage = atomic_read(&cell->usage);
-		_debug("manage %s %u", cell->name, usage);
+		active = atomic_read(&cell->active);
+		trace_afs_cell(cell->debug_id, atomic_read(&cell->ref),
+			       active, afs_cell_trace_manage);
 
-		ASSERTCMP(usage, >=, 1);
+		ASSERTCMP(active, >=, 1);
 
 		if (purging) {
-			if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags))
-				usage = atomic_dec_return(&cell->usage);
-			ASSERTCMP(usage, ==, 1);
+			if (test_and_clear_bit(AFS_CELL_FL_NO_GC, &cell->flags)) {
+				active = atomic_dec_return(&cell->active);
+				trace_afs_cell(cell->debug_id, atomic_read(&cell->ref),
+					       active, afs_cell_trace_unuse_pin);
+			}
 		}
 
-		if (usage == 1) {
+		if (active == 1) {
 			struct afs_vlserver_list *vllist;
 			time64_t expire_at = cell->last_inactive;
 
@@ -821,10 +912,10 @@ void afs_manage_cells(struct work_struct *work)
 		}
 
 		if (sched_cell)
-			queue_work(afs_wq, &cell->manager);
+			afs_queue_cell(cell, afs_cell_trace_get_queue_manage);
 	}
 
-	read_sequnlock_excl(&net->cells_lock);
+	up_read(&net->cells_lock);
 
 	/* Update the timer on the way out.  We have to pass an increment on
 	 * cells_outstanding in the namespace that we are in to the timer or
@@ -854,11 +945,11 @@ void afs_cell_purge(struct afs_net *net)
 
 	_enter("");
 
-	write_seqlock(&net->cells_lock);
-	ws = rcu_access_pointer(net->ws_cell);
-	RCU_INIT_POINTER(net->ws_cell, NULL);
-	write_sequnlock(&net->cells_lock);
-	afs_put_cell(net, ws);
+	down_write(&net->cells_lock);
+	ws = net->ws_cell;
+	net->ws_cell = NULL;
+	up_write(&net->cells_lock);
+	afs_unuse_cell(net, ws, afs_cell_trace_unuse_ws);
 
 	_debug("del timer");
 	if (del_timer_sync(&net->cells_timer))
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 1d2e61e0ab04..9068d5578a26 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -281,8 +281,7 @@ retry:
 			if (ret < 0)
 				goto error;
 
-			set_page_private(req->pages[i], 1);
-			SetPagePrivate(req->pages[i]);
+			attach_page_private(req->pages[i], (void *)1);
 			unlock_page(req->pages[i]);
 			i++;
 		} else {
@@ -824,6 +823,7 @@ static struct inode *afs_do_lookup(struct inode *dir, struct dentry *dentry,
 				vp->cb_break_before = afs_calc_vnode_cb_break(vnode);
 				vp->vnode = vnode;
 				vp->put_vnode = true;
+				vp->speculative = true; /* vnode not locked */
 			}
 		}
 	}
@@ -1975,8 +1975,7 @@ static int afs_dir_releasepage(struct page *page, gfp_t gfp_flags)
 
 	_enter("{{%llx:%llu}[%lu]}", dvnode->fid.vid, dvnode->fid.vnode, page->index);
 
-	set_page_private(page, 0);
-	ClearPagePrivate(page);
+	detach_page_private(page);
 
 	/* The directory will need reloading. */
 	if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &dvnode->flags))
@@ -2003,8 +2002,6 @@ static void afs_dir_invalidatepage(struct page *page, unsigned int offset,
 		afs_stat_v(dvnode, n_inval);
 
 	/* we clean up only if the entire page is being invalidated */
-	if (offset == 0 && length == PAGE_SIZE) {
-		set_page_private(page, 0);
-		ClearPagePrivate(page);
-	}
+	if (offset == 0 && length == PAGE_SIZE)
+		detach_page_private(page);
 }
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index b108528bf010..2ffe09abae7f 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -243,10 +243,8 @@ void afs_edit_dir_add(struct afs_vnode *vnode,
 						   index, gfp);
 			if (!page)
 				goto error;
-			if (!PagePrivate(page)) {
-				set_page_private(page, 1);
-				SetPagePrivate(page);
-			}
+			if (!PagePrivate(page))
+				attach_page_private(page, (void *)1);
 			dir_page = kmap(page);
 		}
 
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 7b784af604fd..db832cc931c8 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -123,9 +123,9 @@ static int afs_probe_cell_name(struct dentry *dentry)
 		len--;
 	}
 
-	cell = afs_lookup_cell_rcu(net, name, len);
+	cell = afs_find_cell(net, name, len, afs_cell_trace_use_probe);
 	if (!IS_ERR(cell)) {
-		afs_put_cell(net, cell);
+		afs_unuse_cell(net, cell, afs_cell_trace_unuse_probe);
 		return 0;
 	}
 
@@ -179,7 +179,6 @@ static struct dentry *afs_lookup_atcell(struct dentry *dentry)
 	struct afs_cell *cell;
 	struct afs_net *net = afs_d2net(dentry);
 	struct dentry *ret;
-	unsigned int seq = 0;
 	char *name;
 	int len;
 
@@ -191,17 +190,13 @@ static struct dentry *afs_lookup_atcell(struct dentry *dentry)
 	if (!name)
 		goto out_p;
 
-	rcu_read_lock();
-	do {
-		read_seqbegin_or_lock(&net->cells_lock, &seq);
-		cell = rcu_dereference_raw(net->ws_cell);
-		if (cell) {
-			len = cell->name_len;
-			memcpy(name, cell->name, len + 1);
-		}
-	} while (need_seqretry(&net->cells_lock, seq));
-	done_seqretry(&net->cells_lock, seq);
-	rcu_read_unlock();
+	down_read(&net->cells_lock);
+	cell = net->ws_cell;
+	if (cell) {
+		len = cell->name_len;
+		memcpy(name, cell->name, len + 1);
+	}
+	up_read(&net->cells_lock);
 
 	ret = ERR_PTR(-ENOENT);
 	if (!cell)
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 371d1488cc54..85f5adf21aa0 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -33,6 +33,7 @@ const struct file_operations afs_file_operations = {
 	.write_iter	= afs_file_write,
 	.mmap		= afs_file_mmap,
 	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
 	.fsync		= afs_fsync,
 	.lock		= afs_lock,
 	.flock		= afs_flock,
@@ -601,6 +602,63 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
 }
 
 /*
+ * Adjust the dirty region of the page on truncation or full invalidation,
+ * getting rid of the markers altogether if the region is entirely invalidated.
+ */
+static void afs_invalidate_dirty(struct page *page, unsigned int offset,
+				 unsigned int length)
+{
+	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+	unsigned long priv;
+	unsigned int f, t, end = offset + length;
+
+	priv = page_private(page);
+
+	/* we clean up only if the entire page is being invalidated */
+	if (offset == 0 && length == thp_size(page))
+		goto full_invalidate;
+
+	 /* If the page was dirtied by page_mkwrite(), the PTE stays writable
+	  * and we don't get another notification to tell us to expand it
+	  * again.
+	  */
+	if (afs_is_page_dirty_mmapped(priv))
+		return;
+
+	/* We may need to shorten the dirty region */
+	f = afs_page_dirty_from(priv);
+	t = afs_page_dirty_to(priv);
+
+	if (t <= offset || f >= end)
+		return; /* Doesn't overlap */
+
+	if (f < offset && t > end)
+		return; /* Splits the dirty region - just absorb it */
+
+	if (f >= offset && t <= end)
+		goto undirty;
+
+	if (f < offset)
+		t = offset;
+	else
+		f = end;
+	if (f == t)
+		goto undirty;
+
+	priv = afs_page_dirty(f, t);
+	set_page_private(page, priv);
+	trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page->index, priv);
+	return;
+
+undirty:
+	trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page->index, priv);
+	clear_page_dirty_for_io(page);
+full_invalidate:
+	priv = (unsigned long)detach_page_private(page);
+	trace_afs_page_dirty(vnode, tracepoint_string("inval"), page->index, priv);
+}
+
+/*
  * invalidate part or all of a page
  * - release a page and clean up its private data if offset is 0 (indicating
  *   the entire page)
@@ -608,31 +666,23 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
 static void afs_invalidatepage(struct page *page, unsigned int offset,
 			       unsigned int length)
 {
-	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
-	unsigned long priv;
-
 	_enter("{%lu},%u,%u", page->index, offset, length);
 
 	BUG_ON(!PageLocked(page));
 
+#ifdef CONFIG_AFS_FSCACHE
 	/* we clean up only if the entire page is being invalidated */
 	if (offset == 0 && length == PAGE_SIZE) {
-#ifdef CONFIG_AFS_FSCACHE
 		if (PageFsCache(page)) {
 			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
 			fscache_wait_on_page_write(vnode->cache, page);
 			fscache_uncache_page(vnode->cache, page);
 		}
+	}
 #endif
 
-		if (PagePrivate(page)) {
-			priv = page_private(page);
-			trace_afs_page_dirty(vnode, tracepoint_string("inval"),
-					     page->index, priv);
-			set_page_private(page, 0);
-			ClearPagePrivate(page);
-		}
-	}
+	if (PagePrivate(page))
+		afs_invalidate_dirty(page, offset, length);
 
 	_leave("");
 }
@@ -660,11 +710,9 @@ static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 #endif
 
 	if (PagePrivate(page)) {
-		priv = page_private(page);
+		priv = (unsigned long)detach_page_private(page);
 		trace_afs_page_dirty(vnode, tracepoint_string("rel"),
 				     page->index, priv);
-		set_page_private(page, 0);
-		ClearPagePrivate(page);
 	}
 
 	/* indicate that the page can be released */
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 0fe8844b4bee..b0d7b892090d 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -294,6 +294,13 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
 			op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
 		}
 	} else if (vp->scb.have_status) {
+		if (vp->dv_before + vp->dv_delta != vp->scb.status.data_version &&
+		    vp->speculative)
+			/* Ignore the result of a speculative bulk status fetch
+			 * if it splits around a modification op, thereby
+			 * appearing to regress the data version.
+			 */
+			goto out;
 		afs_apply_status(op, vp);
 		if (vp->scb.have_cb)
 			afs_apply_callback(op, vp);
@@ -305,6 +312,7 @@ void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *v
 		}
 	}
 
+out:
 	write_sequnlock(&vnode->cb_lock);
 
 	if (vp->scb.have_status)
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index e5f0446f27e5..0d150a29e39e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -263,11 +263,11 @@ struct afs_net {
 
 	/* Cell database */
 	struct rb_root		cells;
-	struct afs_cell __rcu	*ws_cell;
+	struct afs_cell		*ws_cell;
 	struct work_struct	cells_manager;
 	struct timer_list	cells_timer;
 	atomic_t		cells_outstanding;
-	seqlock_t		cells_lock;
+	struct rw_semaphore	cells_lock;
 	struct mutex		cells_alias_lock;
 
 	struct mutex		proc_cells_lock;
@@ -326,6 +326,7 @@ enum afs_cell_state {
 	AFS_CELL_DEACTIVATING,
 	AFS_CELL_INACTIVE,
 	AFS_CELL_FAILED,
+	AFS_CELL_REMOVED,
 };
 
 /*
@@ -363,7 +364,8 @@ struct afs_cell {
 #endif
 	time64_t		dns_expiry;	/* Time AFSDB/SRV record expires */
 	time64_t		last_inactive;	/* Time of last drop of usage count */
-	atomic_t		usage;
+	atomic_t		ref;		/* Struct refcount */
+	atomic_t		active;		/* Active usage counter */
 	unsigned long		flags;
 #define AFS_CELL_FL_NO_GC	0		/* The cell was added manually, don't auto-gc */
 #define AFS_CELL_FL_DO_LOOKUP	1		/* DNS lookup requested */
@@ -373,6 +375,7 @@ struct afs_cell {
 	enum dns_record_source	dns_source:8;	/* Latest source of data from lookup */
 	enum dns_lookup_status	dns_status:8;	/* Latest status of data from lookup */
 	unsigned int		dns_lookup_count; /* Counter of DNS lookups */
+	unsigned int		debug_id;
 
 	/* The volumes belonging to this cell */
 	struct rb_root		volumes;	/* Tree of volumes on this server */
@@ -752,6 +755,7 @@ struct afs_vnode_param {
 	bool			update_ctime:1;	/* Need to update the ctime */
 	bool			set_size:1;	/* Must update i_size */
 	bool			op_unlinked:1;	/* True if file was unlinked by op */
+	bool			speculative:1;	/* T if speculative status fetch (no vnode lock) */
 };
 
 /*
@@ -809,6 +813,7 @@ struct afs_operation {
 			pgoff_t		last;		/* last page in mapping to deal with */
 			unsigned	first_offset;	/* offset into mapping[first] */
 			unsigned	last_to;	/* amount of mapping[last] */
+			bool		laundering;	/* Laundering page, PG_writeback not set */
 		} store;
 		struct {
 			struct iattr	*attr;
@@ -854,6 +859,62 @@ struct afs_vnode_cache_aux {
 	u64			data_version;
 } __packed;
 
+/*
+ * We use page->private to hold the amount of the page that we've written to,
+ * splitting the field into two parts.  However, we need to represent a range
+ * 0...PAGE_SIZE, so we reduce the resolution if the size of the page
+ * exceeds what we can encode.
+ */
+#ifdef CONFIG_64BIT
+#define __AFS_PAGE_PRIV_MASK	0x7fffffffUL
+#define __AFS_PAGE_PRIV_SHIFT	32
+#define __AFS_PAGE_PRIV_MMAPPED	0x80000000UL
+#else
+#define __AFS_PAGE_PRIV_MASK	0x7fffUL
+#define __AFS_PAGE_PRIV_SHIFT	16
+#define __AFS_PAGE_PRIV_MMAPPED	0x8000UL
+#endif
+
+static inline unsigned int afs_page_dirty_resolution(void)
+{
+	int shift = PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1);
+	return (shift > 0) ? shift : 0;
+}
+
+static inline size_t afs_page_dirty_from(unsigned long priv)
+{
+	unsigned long x = priv & __AFS_PAGE_PRIV_MASK;
+
+	/* The lower bound is inclusive */
+	return x << afs_page_dirty_resolution();
+}
+
+static inline size_t afs_page_dirty_to(unsigned long priv)
+{
+	unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK;
+
+	/* The upper bound is immediately beyond the region */
+	return (x + 1) << afs_page_dirty_resolution();
+}
+
+static inline unsigned long afs_page_dirty(size_t from, size_t to)
+{
+	unsigned int res = afs_page_dirty_resolution();
+	from >>= res;
+	to = (to - 1) >> res;
+	return (to << __AFS_PAGE_PRIV_SHIFT) | from;
+}
+
+static inline unsigned long afs_page_dirty_mmapped(unsigned long priv)
+{
+	return priv | __AFS_PAGE_PRIV_MMAPPED;
+}
+
+static inline bool afs_is_page_dirty_mmapped(unsigned long priv)
+{
+	return priv & __AFS_PAGE_PRIV_MMAPPED;
+}
+
 #include <trace/events/afs.h>
 
 /*****************************************************************************/
@@ -917,11 +978,16 @@ static inline bool afs_cb_is_broken(unsigned int cb_break,
  * cell.c
  */
 extern int afs_cell_init(struct afs_net *, const char *);
-extern struct afs_cell *afs_lookup_cell_rcu(struct afs_net *, const char *, unsigned);
+extern struct afs_cell *afs_find_cell(struct afs_net *, const char *, unsigned,
+				      enum afs_cell_trace);
 extern struct afs_cell *afs_lookup_cell(struct afs_net *, const char *, unsigned,
 					const char *, bool);
-extern struct afs_cell *afs_get_cell(struct afs_cell *);
-extern void afs_put_cell(struct afs_net *, struct afs_cell *);
+extern struct afs_cell *afs_use_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_unuse_cell(struct afs_net *, struct afs_cell *, enum afs_cell_trace);
+extern struct afs_cell *afs_get_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_see_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_put_cell(struct afs_cell *, enum afs_cell_trace);
+extern void afs_queue_cell(struct afs_cell *, enum afs_cell_trace);
 extern void afs_manage_cells(struct work_struct *);
 extern void afs_cells_timer(struct timer_list *);
 extern void __net_exit afs_cell_purge(struct afs_net *);
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 31b472f7c734..accdd8970e7c 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -78,7 +78,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	mutex_init(&net->socket_mutex);
 
 	net->cells = RB_ROOT;
-	seqlock_init(&net->cells_lock);
+	init_rwsem(&net->cells_lock);
 	INIT_WORK(&net->cells_manager, afs_manage_cells);
 	timer_setup(&net->cells_timer, afs_cells_timer, 0);
 
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 79bc5f1338ed..052dab2f5c03 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -88,7 +88,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		ctx->force = true;
 	}
 	if (ctx->cell) {
-		afs_put_cell(ctx->net, ctx->cell);
+		afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_mntpt);
 		ctx->cell = NULL;
 	}
 	if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
@@ -124,7 +124,7 @@ static int afs_mntpt_set_params(struct fs_context *fc, struct dentry *mntpt)
 		char *buf;
 
 		if (src_as->cell)
-			ctx->cell = afs_get_cell(src_as->cell);
+			ctx->cell = afs_use_cell(src_as->cell, afs_cell_trace_use_mntpt);
 
 		if (size < 2 || size > PAGE_SIZE - 1)
 			return -EINVAL;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index e8babb62ed44..065a28bfa3f1 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -38,7 +38,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v)
 
 	if (v == SEQ_START_TOKEN) {
 		/* display header on line 1 */
-		seq_puts(m, "USE    TTL SV ST NAME\n");
+		seq_puts(m, "USE ACT    TTL SV ST NAME\n");
 		return 0;
 	}
 
@@ -46,10 +46,11 @@ static int afs_proc_cells_show(struct seq_file *m, void *v)
 	vllist = rcu_dereference(cell->vl_servers);
 
 	/* display one cell per line on subsequent lines */
-	seq_printf(m, "%3u %6lld %2u %2u %s\n",
-		   atomic_read(&cell->usage),
+	seq_printf(m, "%3u %3u %6lld %2u %2u %s\n",
+		   atomic_read(&cell->ref),
+		   atomic_read(&cell->active),
 		   cell->dns_expiry - ktime_get_real_seconds(),
-		   vllist->nr_servers,
+		   vllist ? vllist->nr_servers : 0,
 		   cell->state,
 		   cell->name);
 	return 0;
@@ -128,7 +129,7 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size)
 		}
 
 		if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags))
-			afs_put_cell(net, cell);
+			afs_unuse_cell(net, cell, afs_cell_trace_unuse_no_pin);
 	} else {
 		goto inval;
 	}
@@ -154,13 +155,11 @@ static int afs_proc_rootcell_show(struct seq_file *m, void *v)
 	struct afs_net *net;
 
 	net = afs_seq2net_single(m);
-	if (rcu_access_pointer(net->ws_cell)) {
-		rcu_read_lock();
-		cell = rcu_dereference(net->ws_cell);
-		if (cell)
-			seq_printf(m, "%s\n", cell->name);
-		rcu_read_unlock();
-	}
+	down_read(&net->cells_lock);
+	cell = net->ws_cell;
+	if (cell)
+		seq_printf(m, "%s\n", cell->name);
+	up_read(&net->cells_lock);
 	return 0;
 }
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index e82e452e2612..684a2b02b9ff 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -550,7 +550,12 @@ void afs_manage_servers(struct work_struct *work)
 
 		_debug("manage %pU %u", &server->uuid, active);
 
-		ASSERTIFCMP(purging, active, ==, 0);
+		if (purging) {
+			trace_afs_server(server, atomic_read(&server->ref),
+					 active, afs_server_trace_purging);
+			if (active != 0)
+				pr_notice("Can't purge s=%08x\n", server->debug_id);
+		}
 
 		if (active == 0) {
 			time64_t expire_at = server->unuse_time;
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 3a40ee752c1e..6c5900df6aa5 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -294,7 +294,8 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param)
 			       cellnamesz, cellnamesz, cellname ?: "");
 			return PTR_ERR(cell);
 		}
-		afs_put_cell(ctx->net, ctx->cell);
+		afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_parse);
+		afs_see_cell(cell, afs_cell_trace_see_source);
 		ctx->cell = cell;
 	}
 
@@ -389,8 +390,9 @@ static int afs_validate_fc(struct fs_context *fc)
 				_debug("switch to alias");
 				key_put(ctx->key);
 				ctx->key = NULL;
-				cell = afs_get_cell(ctx->cell->alias_of);
-				afs_put_cell(ctx->net, ctx->cell);
+				cell = afs_use_cell(ctx->cell->alias_of,
+						    afs_cell_trace_use_fc_alias);
+				afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc);
 				ctx->cell = cell;
 				goto reget_key;
 			}
@@ -507,7 +509,7 @@ static struct afs_super_info *afs_alloc_sbi(struct fs_context *fc)
 		if (ctx->dyn_root) {
 			as->dyn_root = true;
 		} else {
-			as->cell = afs_get_cell(ctx->cell);
+			as->cell = afs_use_cell(ctx->cell, afs_cell_trace_use_sbi);
 			as->volume = afs_get_volume(ctx->volume,
 						    afs_volume_trace_get_alloc_sbi);
 		}
@@ -520,7 +522,7 @@ static void afs_destroy_sbi(struct afs_super_info *as)
 	if (as) {
 		struct afs_net *net = afs_net(as->net_ns);
 		afs_put_volume(net, as->volume, afs_volume_trace_put_destroy_sbi);
-		afs_put_cell(net, as->cell);
+		afs_unuse_cell(net, as->cell, afs_cell_trace_unuse_sbi);
 		put_net(as->net_ns);
 		kfree(as);
 	}
@@ -606,7 +608,7 @@ static void afs_free_fc(struct fs_context *fc)
 
 	afs_destroy_sbi(fc->s_fs_info);
 	afs_put_volume(ctx->net, ctx->volume, afs_volume_trace_put_free_fc);
-	afs_put_cell(ctx->net, ctx->cell);
+	afs_unuse_cell(ctx->net, ctx->cell, afs_cell_trace_unuse_fc);
 	key_put(ctx->key);
 	kfree(ctx);
 }
@@ -633,9 +635,7 @@ static int afs_init_fs_context(struct fs_context *fc)
 	ctx->net = afs_net(fc->net_ns);
 
 	/* Default to the workstation cell. */
-	rcu_read_lock();
-	cell = afs_lookup_cell_rcu(ctx->net, NULL, 0);
-	rcu_read_unlock();
+	cell = afs_find_cell(ctx->net, NULL, 0, afs_cell_trace_use_fc);
 	if (IS_ERR(cell))
 		cell = NULL;
 	ctx->cell = cell;
diff --git a/fs/afs/vl_alias.c b/fs/afs/vl_alias.c
index 5082ef04e99c..f04a80e4f5c3 100644
--- a/fs/afs/vl_alias.c
+++ b/fs/afs/vl_alias.c
@@ -177,7 +177,7 @@ static int afs_compare_cell_roots(struct afs_cell *cell)
 
 is_alias:
 	rcu_read_unlock();
-	cell->alias_of = afs_get_cell(p);
+	cell->alias_of = afs_use_cell(p, afs_cell_trace_use_alias);
 	return 1;
 }
 
@@ -247,18 +247,18 @@ static int afs_query_for_alias(struct afs_cell *cell, struct key *key)
 			continue;
 		if (p->root_volume)
 			continue; /* Ignore cells that have a root.cell volume. */
-		afs_get_cell(p);
+		afs_use_cell(p, afs_cell_trace_use_check_alias);
 		mutex_unlock(&cell->net->proc_cells_lock);
 
 		if (afs_query_for_alias_one(cell, key, p) != 0)
 			goto is_alias;
 
 		if (mutex_lock_interruptible(&cell->net->proc_cells_lock) < 0) {
-			afs_put_cell(cell->net, p);
+			afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias);
 			return -ERESTARTSYS;
 		}
 
-		afs_put_cell(cell->net, p);
+		afs_unuse_cell(cell->net, p, afs_cell_trace_unuse_check_alias);
 	}
 
 	mutex_unlock(&cell->net->proc_cells_lock);
diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c
index c0458c903b31..488e58490b16 100644
--- a/fs/afs/vl_rotate.c
+++ b/fs/afs/vl_rotate.c
@@ -45,7 +45,7 @@ static bool afs_start_vl_iteration(struct afs_vl_cursor *vc)
 	    cell->dns_expiry <= ktime_get_real_seconds()) {
 		dns_lookup_count = smp_load_acquire(&cell->dns_lookup_count);
 		set_bit(AFS_CELL_FL_DO_LOOKUP, &cell->flags);
-		queue_work(afs_wq, &cell->manager);
+		afs_queue_cell(cell, afs_cell_trace_get_queue_dns);
 
 		if (cell->dns_source == DNS_RECORD_UNAVAILABLE) {
 			if (wait_var_event_interruptible(
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 9bc0509e3634..f84194b791d3 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -83,7 +83,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 
 	volume->vid		= vldb->vid[params->type];
 	volume->update_at	= ktime_get_real_seconds() + afs_volume_record_life;
-	volume->cell		= afs_get_cell(params->cell);
+	volume->cell		= afs_get_cell(params->cell, afs_cell_trace_get_vol);
 	volume->type		= params->type;
 	volume->type_force	= params->force;
 	volume->name_len	= vldb->name_len;
@@ -106,7 +106,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params,
 	return volume;
 
 error_1:
-	afs_put_cell(params->net, volume->cell);
+	afs_put_cell(volume->cell, afs_cell_trace_put_vol);
 	kfree(volume);
 error_0:
 	return ERR_PTR(ret);
@@ -228,7 +228,7 @@ static void afs_destroy_volume(struct afs_net *net, struct afs_volume *volume)
 
 	afs_remove_volume_from_cell(volume);
 	afs_put_serverlist(net, rcu_access_pointer(volume->servers));
-	afs_put_cell(net, volume->cell);
+	afs_put_cell(volume->cell, afs_cell_trace_put_vol);
 	trace_afs_volume(volume->vid, atomic_read(&volume->usage),
 			 afs_volume_trace_free);
 	kfree_rcu(volume, rcu);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index da12abd6db21..c9195fc67fd8 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -76,7 +76,7 @@ static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
  */
 int afs_write_begin(struct file *file, struct address_space *mapping,
 		    loff_t pos, unsigned len, unsigned flags,
-		    struct page **pagep, void **fsdata)
+		    struct page **_page, void **fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	struct page *page;
@@ -90,11 +90,6 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 	_enter("{%llx:%llu},{%lx},%u,%u",
 	       vnode->fid.vid, vnode->fid.vnode, index, from, to);
 
-	/* We want to store information about how much of a page is altered in
-	 * page->private.
-	 */
-	BUILD_BUG_ON(PAGE_SIZE > 32768 && sizeof(page->private) < 8);
-
 	page = grab_cache_page_write_begin(mapping, index, flags);
 	if (!page)
 		return -ENOMEM;
@@ -110,9 +105,6 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		SetPageUptodate(page);
 	}
 
-	/* page won't leak in error case: it eventually gets cleaned off LRU */
-	*pagep = page;
-
 try_again:
 	/* See if this page is already partially written in a way that we can
 	 * merge the new write with.
@@ -120,8 +112,8 @@ try_again:
 	t = f = 0;
 	if (PagePrivate(page)) {
 		priv = page_private(page);
-		f = priv & AFS_PRIV_MAX;
-		t = priv >> AFS_PRIV_SHIFT;
+		f = afs_page_dirty_from(priv);
+		t = afs_page_dirty_to(priv);
 		ASSERTCMP(f, <=, t);
 	}
 
@@ -138,21 +130,9 @@ try_again:
 		if (!test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags) &&
 		    (to < f || from > t))
 			goto flush_conflicting_write;
-		if (from < f)
-			f = from;
-		if (to > t)
-			t = to;
-	} else {
-		f = from;
-		t = to;
 	}
 
-	priv = (unsigned long)t << AFS_PRIV_SHIFT;
-	priv |= f;
-	trace_afs_page_dirty(vnode, tracepoint_string("begin"),
-			     page->index, priv);
-	SetPagePrivate(page);
-	set_page_private(page, priv);
+	*_page = page;
 	_leave(" = 0");
 	return 0;
 
@@ -162,17 +142,18 @@ try_again:
 flush_conflicting_write:
 	_debug("flush conflict");
 	ret = write_one_page(page);
-	if (ret < 0) {
-		_leave(" = %d", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error;
 
 	ret = lock_page_killable(page);
-	if (ret < 0) {
-		_leave(" = %d", ret);
-		return ret;
-	}
+	if (ret < 0)
+		goto error;
 	goto try_again;
+
+error:
+	put_page(page);
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
@@ -184,12 +165,18 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
 	struct key *key = afs_file_key(file);
+	unsigned long priv;
+	unsigned int f, from = pos & (PAGE_SIZE - 1);
+	unsigned int t, to = from + copied;
 	loff_t i_size, maybe_i_size;
-	int ret;
+	int ret = 0;
 
 	_enter("{%llx:%llu},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
 
+	if (copied == 0)
+		goto out;
+
 	maybe_i_size = pos + copied;
 
 	i_size = i_size_read(&vnode->vfs_inode);
@@ -215,6 +202,25 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		SetPageUptodate(page);
 	}
 
+	if (PagePrivate(page)) {
+		priv = page_private(page);
+		f = afs_page_dirty_from(priv);
+		t = afs_page_dirty_to(priv);
+		if (from < f)
+			f = from;
+		if (to > t)
+			t = to;
+		priv = afs_page_dirty(f, t);
+		set_page_private(page, priv);
+		trace_afs_page_dirty(vnode, tracepoint_string("dirty+"),
+				     page->index, priv);
+	} else {
+		priv = afs_page_dirty(from, to);
+		attach_page_private(page, (void *)priv);
+		trace_afs_page_dirty(vnode, tracepoint_string("dirty"),
+				     page->index, priv);
+	}
+
 	set_page_dirty(page);
 	if (PageDirty(page))
 		_debug("dirtied");
@@ -334,10 +340,9 @@ static void afs_pages_written_back(struct afs_vnode *vnode,
 		ASSERTCMP(pv.nr, ==, count);
 
 		for (loop = 0; loop < count; loop++) {
-			priv = page_private(pv.pages[loop]);
+			priv = (unsigned long)detach_page_private(pv.pages[loop]);
 			trace_afs_page_dirty(vnode, tracepoint_string("clear"),
 					     pv.pages[loop]->index, priv);
-			set_page_private(pv.pages[loop], 0);
 			end_page_writeback(pv.pages[loop]);
 		}
 		first += count;
@@ -396,7 +401,8 @@ static void afs_store_data_success(struct afs_operation *op)
 	op->ctime = op->file[0].scb.status.mtime_client;
 	afs_vnode_commit_status(op, &op->file[0]);
 	if (op->error == 0) {
-		afs_pages_written_back(vnode, op->store.first, op->store.last);
+		if (!op->store.laundering)
+			afs_pages_written_back(vnode, op->store.first, op->store.last);
 		afs_stat_v(vnode, n_stores);
 		atomic_long_add((op->store.last * PAGE_SIZE + op->store.last_to) -
 				(op->store.first * PAGE_SIZE + op->store.first_offset),
@@ -415,7 +421,7 @@ static const struct afs_operation_ops afs_store_data_operation = {
  */
 static int afs_store_data(struct address_space *mapping,
 			  pgoff_t first, pgoff_t last,
-			  unsigned offset, unsigned to)
+			  unsigned offset, unsigned to, bool laundering)
 {
 	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
 	struct afs_operation *op;
@@ -448,6 +454,7 @@ static int afs_store_data(struct address_space *mapping,
 	op->store.last = last;
 	op->store.first_offset = offset;
 	op->store.last_to = to;
+	op->store.laundering = laundering;
 	op->mtime = vnode->vfs_inode.i_mtime;
 	op->flags |= AFS_OPERATION_UNINTR;
 	op->ops = &afs_store_data_operation;
@@ -509,8 +516,8 @@ static int afs_write_back_from_locked_page(struct address_space *mapping,
 	 */
 	start = primary_page->index;
 	priv = page_private(primary_page);
-	offset = priv & AFS_PRIV_MAX;
-	to = priv >> AFS_PRIV_SHIFT;
+	offset = afs_page_dirty_from(priv);
+	to = afs_page_dirty_to(priv);
 	trace_afs_page_dirty(vnode, tracepoint_string("store"),
 			     primary_page->index, priv);
 
@@ -555,8 +562,8 @@ static int afs_write_back_from_locked_page(struct address_space *mapping,
 			}
 
 			priv = page_private(page);
-			f = priv & AFS_PRIV_MAX;
-			t = priv >> AFS_PRIV_SHIFT;
+			f = afs_page_dirty_from(priv);
+			t = afs_page_dirty_to(priv);
 			if (f != 0 &&
 			    !test_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags)) {
 				unlock_page(page);
@@ -601,7 +608,7 @@ no_more:
 	if (end > i_size)
 		to = i_size & ~PAGE_MASK;
 
-	ret = afs_store_data(mapping, first, last, offset, to);
+	ret = afs_store_data(mapping, first, last, offset, to, false);
 	switch (ret) {
 	case 0:
 		ret = count;
@@ -857,12 +864,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
 	 */
 	wait_on_page_writeback(vmf->page);
 
-	priv = (unsigned long)PAGE_SIZE << AFS_PRIV_SHIFT; /* To */
-	priv |= 0; /* From */
+	priv = afs_page_dirty(0, PAGE_SIZE);
+	priv = afs_page_dirty_mmapped(priv);
 	trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"),
 			     vmf->page->index, priv);
-	SetPagePrivate(vmf->page);
-	set_page_private(vmf->page, priv);
+	if (PagePrivate(vmf->page))
+		set_page_private(vmf->page, priv);
+	else
+		attach_page_private(vmf->page, (void *)priv);
 	file_update_time(file);
 
 	sb_end_pagefault(inode->i_sb);
@@ -915,19 +924,18 @@ int afs_launder_page(struct page *page)
 		f = 0;
 		t = PAGE_SIZE;
 		if (PagePrivate(page)) {
-			f = priv & AFS_PRIV_MAX;
-			t = priv >> AFS_PRIV_SHIFT;
+			f = afs_page_dirty_from(priv);
+			t = afs_page_dirty_to(priv);
 		}
 
 		trace_afs_page_dirty(vnode, tracepoint_string("launder"),
 				     page->index, priv);
-		ret = afs_store_data(mapping, page->index, page->index, t, f);
+		ret = afs_store_data(mapping, page->index, page->index, t, f, true);
 	}
 
+	priv = (unsigned long)detach_page_private(page);
 	trace_afs_page_dirty(vnode, tracepoint_string("laundered"),
 			     page->index, priv);
-	set_page_private(page, 0);
-	ClearPagePrivate(page);
 
 #ifdef CONFIG_AFS_FSCACHE
 	if (PageFsCache(page)) {
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
index 84f3c4f57531..95c573dcda11 100644
--- a/fs/afs/xattr.c
+++ b/fs/afs/xattr.c
@@ -85,7 +85,7 @@ static int afs_xattr_get_acl(const struct xattr_handler *handler,
 			if (acl->size <= size)
 				memcpy(buffer, acl->data, acl->size);
 			else
-				op->error = -ERANGE;
+				ret = -ERANGE;
 		}
 	}
 
@@ -148,11 +148,6 @@ static const struct xattr_handler afs_xattr_afs_acl_handler = {
 	.set    = afs_xattr_set_acl,
 };
 
-static void yfs_acl_put(struct afs_operation *op)
-{
-	yfs_free_opaque_acl(op->yacl);
-}
-
 static const struct afs_operation_ops yfs_fetch_opaque_acl_operation = {
 	.issue_yfs_rpc	= yfs_fs_fetch_opaque_acl,
 	.success	= afs_acl_success,
@@ -246,7 +241,7 @@ error:
 static const struct afs_operation_ops yfs_store_opaque_acl2_operation = {
 	.issue_yfs_rpc	= yfs_fs_store_opaque_acl2,
 	.success	= afs_acl_success,
-	.put		= yfs_acl_put,
+	.put		= afs_acl_put,
 };
 
 /*
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 3b1239b7e90d..bd787e71a657 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -1990,6 +1990,7 @@ void yfs_fs_store_opaque_acl2(struct afs_operation *op)
 	memcpy(bp, acl->data, acl->size);
 	if (acl->size != size)
 		memset((void *)bp + acl->size, 0, size - acl->size);
+	bp += size / sizeof(__be32);
 	yfs_check_req(call, bp);
 
 	trace_afs_make_fs_call(call, &vp->fid);