FS-Cache: Exclusive op submission can BUG if there's been an I/O error

The function to submit an exclusive op (fscache_submit_exclusive_op()) can BUG
if there's been an I/O error because it may see the parent cache object in an
unexpected state.  It should only BUG if there hasn't been an I/O error.

In this case the problem was produced by remounting the cache partition to be
R/O.  The EROFS state was detected and the cache was aborted, but not
everything handled the aborting correctly.

SysRq : Emergency Remount R/O
EXT4-fs (sda6): re-mounted. Opts: (null)
Emergency Remount complete
CacheFiles: I/O Error: Failed to update xattr with error -30
FS-Cache: Cache cachefiles stopped due to I/O error
------------[ cut here ]------------
kernel BUG at fs/fscache/operation.c:128!
invalid opcode: 0000 [#1] SMP 
CPU 0 
Modules linked in: cachefiles nfs fscache auth_rpcgss nfs_acl lockd sunrpc

Pid: 6612, comm: kworker/u:2 Not tainted 3.1.0-rc8-fsdevel+ #1093                  /DG965RY
RIP: 0010:[<ffffffffa00739c0>]  [<ffffffffa00739c0>] fscache_submit_exclusive_op+0x2ad/0x2c2 [fscache]
RSP: 0018:ffff880000853d40  EFLAGS: 00010206
RAX: ffff880038ac72a8 RBX: ffff8800181f2260 RCX: ffffffff81f2b2b0
RDX: 0000000000000001 RSI: ffffffff8179a478 RDI: ffff8800181f2280
RBP: ffff880000853d60 R08: 0000000000000002 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000001 R12: ffff880038ac7268
R13: ffff8800181f2280 R14: ffff88003a359190 R15: 000000010122b162
FS:  0000000000000000(0000) GS:ffff88003bc00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 00000034cc4a77f0 CR3: 0000000010e96000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process kworker/u:2 (pid: 6612, threadinfo ffff880000852000, task ffff880014c3c040)
Stack:
 ffff8800181f2260 ffff8800181f2310 ffff880038ac7268 ffff8800181f2260
 ffff880000853dc0 ffffffffa0072375 ffff880037ecfe00 ffff88003a359198
 ffff880000853dc0 0000000000000246 0000000000000000 ffff88000a91d308
Call Trace:
 [<ffffffffa0072375>] fscache_object_work_func+0x792/0xe65 [fscache]
 [<ffffffff81047e44>] process_one_work+0x1eb/0x37f
 [<ffffffff81047de6>] ? process_one_work+0x18d/0x37f
 [<ffffffffa0071be3>] ? fscache_enqueue_dependents+0xd8/0xd8 [fscache]
 [<ffffffff810482e4>] worker_thread+0x15a/0x21a
 [<ffffffff8104818a>] ? rescuer_thread+0x188/0x188
 [<ffffffff8104bf96>] kthread+0x7f/0x87
 [<ffffffff813ad6f4>] kernel_thread_helper+0x4/0x10
 [<ffffffff81026b98>] ? finish_task_switch+0x45/0xc0
 [<ffffffff813abd1d>] ? retint_restore_args+0xe/0xe
 [<ffffffff8104bf17>] ? __init_kthread_worker+0x53/0x53
 [<ffffffff813ad6f0>] ? gs_change+0xb/0xb


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

fs/fscache/internal.h

@@ -288,6 +288,7 @@ extern const struct file_operations fscache_stats_fops;
 static inline void fscache_raise_event(struct fscache_object *object,
 				       unsigned event)
 {
+	BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS);
 	if (!test_and_set_bit(event, &object->events) &&
 	    test_bit(event, &object->event_mask))
 		fscache_enqueue_object(object);

fs/fscache/object.c

@@ -103,6 +103,7 @@ static void fscache_object_state_machine(struct fscache_object *object)
 {
 	enum fscache_object_state new_state;
 	struct fscache_cookie *cookie;
+	int event;
 
 	ASSERT(object != NULL);
 
@@ -275,7 +276,8 @@ static void fscache_object_state_machine(struct fscache_object *object)
 
 	/* determine the transition from a lookup state */
 lookup_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
@@ -292,7 +294,8 @@ lookup_transit:
 
 	/* determine the transition from an active state */
 active_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
@@ -314,7 +317,8 @@ active_transit:
 
 	/* determine the transition from a terminal state */
 terminal_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 		new_state = FSCACHE_OBJECT_WITHDRAWING;
 		goto change_state;
@@ -347,8 +351,8 @@ done:
 
 unsupported_event:
 	printk(KERN_ERR "FS-Cache:"
-	       " Unsupported event %lx [mask %lx] in state %s\n",
-	       object->events, object->event_mask,
+	       " Unsupported event %d [%lx/%lx] in state %s\n",
+	       event, object->events, object->event_mask,
 	       fscache_object_states[object->state]);
 	BUG();
 }
@@ -945,7 +949,7 @@ static void fscache_invalidate_object(struct fscache_object *object)
 
 	spin_lock(&cookie->lock);
 	if (fscache_submit_exclusive_op(object, op) < 0)
-		BUG();
+		goto submit_op_failed;
 	spin_unlock(&cookie->lock);
 	fscache_put_operation(op);
 
@@ -960,4 +964,11 @@ static void fscache_invalidate_object(struct fscache_object *object)
 	 */
 	fscache_invalidation_complete(cookie);
 	_leave("");
+	return;
+
+submit_op_failed:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+	_leave(" [EIO]");
 }

fs/fscache/operation.c

@@ -84,6 +84,8 @@ static void fscache_run_op(struct fscache_object *object,
 int fscache_submit_exclusive_op(struct fscache_object *object,
 				struct fscache_operation *op)
 {
+	int ret;
+
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
 	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
@@ -116,6 +118,7 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
 		/* need to issue a new write op after this */
 		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		ret = 0;
 	} else if (object->state == FSCACHE_OBJECT_CREATING) {
 		op->object = object;
 		object->n_ops++;
@@ -123,13 +126,17 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		atomic_inc(&op->usage);
 		list_add_tail(&op->pend_link, &object->pending_ops);
 		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
 	} else {
-		/* not allowed to submit ops in any other state */
-		BUG();
+		/* If we're in any other state, there must have been an I/O
+		 * error of some nature.
+		 */
+		ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
+		ret = -EIO;
 	}
 
 	spin_unlock(&object->lock);
-	return 0;
+	return ret;
 }
 
 /*