afs: Overhaul cell database management

Overhaul the way that the in-kernel AFS client keeps track of cells in the
following manner:

 (1) Cells are now held in an rbtree to make walking them quicker and RCU
     managed (though this is probably overkill).

 (2) Cells now have a manager work item that:

     (A) Looks after fetching and refreshing the VL server list.

     (B) Manages cell record lifetime, including initialising and
     	 destruction.

     (B) Manages cell record caching whereby threads are kept around for a
     	 certain time after last use and then destroyed.

     (C) Manages the FS-Cache index cookie for a cell.  It is not permitted
     	 for a cookie to be in use twice, so we have to be careful to not
     	 allow a new cell record to exist at the same time as an old record
     	 of the same name.

 (3) Each AFS network namespace is given a manager work item that manages
     the cells within it, maintaining a single timer to prod cells into
     updating their DNS records.

     This uses the reduce_timer() facility to make the timer expire at the
     soonest timed event that needs happening.

 (4) When a module is being unloaded, cells and cell managers are now
     counted out using dec_after_work() to make sure the module text is
     pinned until after the data structures have been cleaned up.

 (5) Each cell's VL server list is now protected by a seqlock rather than a
     semaphore.

Signed-off-by: David Howells <dhowells@redhat.com>

fs/afs/internal.h

@@ -207,13 +207,14 @@ struct afs_net {
 	atomic_t		nr_superblocks;
 
 	/* Cell database */
-	struct list_head	cells;
+	struct rb_root		cells;
 	struct afs_cell		*ws_cell;
-	rwlock_t		cells_lock;
-	struct rw_semaphore	cells_sem;
-	wait_queue_head_t	cells_freeable_wq;
+	struct work_struct	cells_manager;
+	struct timer_list	cells_timer;
+	atomic_t		cells_outstanding;
+	seqlock_t		cells_lock;
 
-	struct rw_semaphore	proc_cells_sem;
+	spinlock_t		proc_cells_lock;
 	struct list_head	proc_cells;
 
 	/* Volume location database */
@@ -242,14 +243,26 @@ struct afs_net {
 
 extern struct afs_net __afs_net;// Dummy AFS network namespace; TODO: replace with real netns
 
+enum afs_cell_state {
+	AFS_CELL_UNSET,
+	AFS_CELL_ACTIVATING,
+	AFS_CELL_ACTIVE,
+	AFS_CELL_DEACTIVATING,
+	AFS_CELL_INACTIVE,
+	AFS_CELL_FAILED,
+};
+
 /*
  * AFS cell record
  */
 struct afs_cell {
-	atomic_t		usage;
-	struct list_head	link;		/* main cell list link */
-	struct afs_net		*net;		/* The network namespace */
+	union {
+		struct rcu_head	rcu;
+		struct rb_node	net_node;	/* Node in net->cells */
+	};
+	struct afs_net		*net;
 	struct key		*anonymous_key;	/* anonymous user key for this cell */
+	struct work_struct	manager;	/* Manager for init/deinit/dns */
 	struct list_head	proc_link;	/* /proc cell list link */
 #ifdef CONFIG_AFS_FSCACHE
 	struct fscache_cookie	*cache;		/* caching cookie */
@@ -262,12 +275,26 @@ struct afs_cell {
 	/* volume location record management */
 	struct rw_semaphore	vl_sem;		/* volume management serialisation semaphore */
 	struct list_head	vl_list;	/* cell's active VL record list */
+	time64_t		dns_expiry;	/* Time AFSDB/SRV record expires */
+	time64_t		last_inactive;	/* Time of last drop of usage count */
+	atomic_t		usage;
+	unsigned long		flags;
+#define AFS_CELL_FL_NOT_READY	0		/* The cell record is not ready for use */
+#define AFS_CELL_FL_NO_GC	1		/* The cell was added manually, don't auto-gc */
+#define AFS_CELL_FL_NOT_FOUND	2		/* Permanent DNS error */
+#define AFS_CELL_FL_DNS_FAIL	3		/* Failed to access DNS */
+	enum afs_cell_state	state;
+	short			error;
+
 	spinlock_t		vl_lock;	/* vl_list lock */
+
+	/* VLDB server list. */
+	seqlock_t		vl_addrs_lock;
 	unsigned short		vl_naddrs;	/* number of VL servers in addr list */
 	unsigned short		vl_curr_svix;	/* current server index */
 	struct sockaddr_rxrpc	vl_addrs[AFS_CELL_MAX_ADDRS];	/* cell VL server addresses */
-
-	char			name[0];	/* cell name - must go last */
+	u8			name_len;	/* Length of name */
+	char			name[64 + 1];	/* Cell name, case-flattened and NUL-padded */
 };
 
 /*
@@ -494,17 +521,20 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest
 /*
  * cell.c
  */
-static inline struct afs_cell *afs_get_cell(struct afs_cell *cell)
+ static inline struct afs_cell *afs_get_cell(struct afs_cell *cell)
 {
 	if (cell)
 		atomic_inc(&cell->usage);
 	return cell;
 }
-extern int afs_cell_init(struct afs_net *, char *);
-extern struct afs_cell *afs_cell_create(struct afs_net *, const char *, unsigned, char *, bool);
-extern struct afs_cell *afs_cell_lookup(struct afs_net *, const char *, unsigned, bool);
-extern struct afs_cell *afs_grab_cell(struct afs_cell *);
+
+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_lookup_cell(struct afs_net *, const char *, unsigned,
+					const char *, bool);
 extern void afs_put_cell(struct afs_net *, struct afs_cell *);
+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 *);
 
 /*

fs/afs/main.c

@@ -46,12 +46,15 @@ static int __net_init afs_net_init(struct afs_net *net)
 
 	INIT_WORK(&net->charge_preallocation_work, afs_charge_preallocation);
 	mutex_init(&net->socket_mutex);
-	INIT_LIST_HEAD(&net->cells);
-	rwlock_init(&net->cells_lock);
-	init_rwsem(&net->cells_sem);
-	init_waitqueue_head(&net->cells_freeable_wq);
-	init_rwsem(&net->proc_cells_sem);
+
+	net->cells = RB_ROOT;
+	seqlock_init(&net->cells_lock);
+	INIT_WORK(&net->cells_manager, afs_manage_cells);
+	timer_setup(&net->cells_timer, afs_cells_timer, 0);
+
+	spin_lock_init(&net->proc_cells_lock);
 	INIT_LIST_HEAD(&net->proc_cells);
+
 	INIT_LIST_HEAD(&net->vl_updates);
 	INIT_LIST_HEAD(&net->vl_graveyard);
 	INIT_DELAYED_WORK(&net->vl_reaper, afs_vlocation_reaper);
@@ -83,11 +86,14 @@ static int __net_init afs_net_init(struct afs_net *net)
 	return 0;
 
 error_open_socket:
+	net->live = false;
 	afs_vlocation_purge(net);
 	afs_cell_purge(net);
 error_cell_init:
+	net->live = false;
 	afs_proc_cleanup(net);
 error_proc:
+	net->live = false;
 	return ret;
 }
 

fs/afs/proc.c

@@ -186,7 +186,7 @@ static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos)
 {
 	struct afs_net *net = afs_seq2net(m);
 
-	down_read(&net->proc_cells_sem);
+	rcu_read_lock();
 	return seq_list_start_head(&net->proc_cells, *_pos);
 }
 
@@ -205,9 +205,7 @@ static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos)
  */
 static void afs_proc_cells_stop(struct seq_file *m, void *v)
 {
-	struct afs_net *net = afs_seq2net(m);
-
-	up_read(&net->proc_cells_sem);
+	rcu_read_unlock();
 }
 
 /*
@@ -225,8 +223,7 @@ static int afs_proc_cells_show(struct seq_file *m, void *v)
 	}
 
 	/* display one cell per line on subsequent lines */
-	seq_printf(m, "%3d %s\n",
-		   atomic_read(&cell->usage), cell->name);
+	seq_printf(m, "%3u %s\n", atomic_read(&cell->usage), cell->name);
 	return 0;
 }
 
@@ -279,13 +276,13 @@ static ssize_t afs_proc_cells_write(struct file *file, const char __user *buf,
 	if (strcmp(kbuf, "add") == 0) {
 		struct afs_cell *cell;
 
-		cell = afs_cell_create(net, name, strlen(name), args, false);
+		cell = afs_lookup_cell(net, name, strlen(name), args, true);
 		if (IS_ERR(cell)) {
 			ret = PTR_ERR(cell);
 			goto done;
 		}
 
-		afs_put_cell(net, cell);
+		set_bit(AFS_CELL_FL_NO_GC, &cell->flags);
 		printk("kAFS: Added new cell '%s'\n", name);
 	} else {
 		goto inval;
@@ -354,7 +351,7 @@ int afs_proc_cell_setup(struct afs_net *net, struct afs_cell *cell)
 {
 	struct proc_dir_entry *dir;
 
-	_enter("%p{%s}", cell, cell->name);
+	_enter("%p{%s},%p", cell, cell->name, net->proc_afs);
 
 	dir = proc_mkdir(cell->name, net->proc_afs);
 	if (!dir)

fs/afs/super.c

@@ -200,10 +200,11 @@ static int afs_parse_options(struct afs_mount_params *params,
 		token = match_token(p, afs_options_list, args);
 		switch (token) {
 		case afs_opt_cell:
-			cell = afs_cell_lookup(params->net,
+			rcu_read_lock();
+			cell = afs_lookup_cell_rcu(params->net,
 						   args[0].from,
-					       args[0].to - args[0].from,
-					       false);
+						   args[0].to - args[0].from);
+			rcu_read_unlock();
 			if (IS_ERR(cell))
 				return PTR_ERR(cell);
 			afs_put_cell(params->net, params->cell);
@@ -308,7 +309,8 @@ static int afs_parse_device_name(struct afs_mount_params *params,
 
 	/* lookup the cell record */
 	if (cellname || !params->cell) {
-		cell = afs_cell_lookup(params->net, cellname, cellnamesz, true);
+		cell = afs_lookup_cell(params->net, cellname, cellnamesz,
+				       NULL, false);
 		if (IS_ERR(cell)) {
 			printk(KERN_ERR "kAFS: unable to lookup cell '%*.*s'\n",
 			       cellnamesz, cellnamesz, cellname ?: "");

fs/afs/xattr.c

@@ -45,7 +45,7 @@ static int afs_xattr_get_cell(const struct xattr_handler *handler,
 	struct afs_cell *cell = vnode->volume->cell;
 	size_t namelen;
 
-	namelen = strlen(cell->name);
+	namelen = cell->name_len;
 	if (size == 0)
 		return namelen;
 	if (namelen > size)