rxrpc: Fix races between skb free, ACK generation and replying

Inside the kafs filesystem it is possible to occasionally have a call
processed and terminated before we've had a chance to check whether we need
to clean up the rx queue for that call because afs_send_simple_reply() ends
the call when it is done, but this is done in a workqueue item that might
happen to run to completion before afs_deliver_to_call() completes.

Further, it is possible for rxrpc_kernel_send_data() to be called to send a
reply before the last request-phase data skb is released.  The rxrpc skb
destructor is where the ACK processing is done and the call state is
advanced upon release of the last skb.  ACK generation is also deferred to
a work item because it's possible that the skb destructor is not called in
a context where kernel_sendmsg() can be invoked.

To this end, the following changes are made:

 (1) kernel_rxrpc_data_consumed() is added.  This should be called whenever
     an skb is emptied so as to crank the ACK and call states.  This does
     not release the skb, however.  kernel_rxrpc_free_skb() must now be
     called to achieve that.  These together replace
     rxrpc_kernel_data_delivered().

 (2) kernel_rxrpc_data_consumed() is wrapped by afs_data_consumed().

     This makes afs_deliver_to_call() easier to work as the skb can simply
     be discarded unconditionally here without trying to work out what the
     return value of the ->deliver() function means.

     The ->deliver() functions can, via afs_data_complete(),
     afs_transfer_reply() and afs_extract_data() mark that an skb has been
     consumed (thereby cranking the state) without the need to
     conditionally free the skb to make sure the state is correct on an
     incoming call for when the call processor tries to send the reply.

 (3) rxrpc_recvmsg() now has to call kernel_rxrpc_data_consumed() when it
     has finished with a packet and MSG_PEEK isn't set.

 (4) rxrpc_packet_destructor() no longer calls rxrpc_hard_ACK_data().

     Because of this, we no longer need to clear the destructor and put the
     call before we free the skb in cases where we don't want the ACK/call
     state to be cranked.

 (5) The ->deliver() call-type callbacks are made to return -EAGAIN rather
     than 0 if they expect more data (afs_extract_data() returns -EAGAIN to
     the delivery function already), and the caller is now responsible for
     producing an abort if that was the last packet.

 (6) There are many bits of unmarshalling code where:

 		ret = afs_extract_data(call, skb, last, ...);
		switch (ret) {
		case 0:		break;
		case -EAGAIN:	return 0;
		default:	return ret;
		}

     is to be found.  As -EAGAIN can now be passed back to the caller, we
     now just return if ret < 0:

 		ret = afs_extract_data(call, skb, last, ...);
		if (ret < 0)
			return ret;

 (7) Checks for trailing data and empty final data packets has been
     consolidated as afs_data_complete().  So:

		if (skb->len > 0)
			return -EBADMSG;
		if (!last)
			return 0;

     becomes:

		ret = afs_data_complete(call, skb, last);
		if (ret < 0)
			return ret;

 (8) afs_transfer_reply() now checks the amount of data it has against the
     amount of data desired and the amount of data in the skb and returns
     an error to induce an abort if we don't get exactly what we want.

Without these changes, the following oops can occasionally be observed,
particularly if some printks are inserted into the delivery path:

general protection fault: 0000 [#1] SMP
Modules linked in: kafs(E) af_rxrpc(E) [last unloaded: af_rxrpc]
CPU: 0 PID: 1305 Comm: kworker/u8:3 Tainted: G            E   4.7.0-fsdevel+ #1303
Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014
Workqueue: kafsd afs_async_workfn [kafs]
task: ffff88040be041c0 ti: ffff88040c070000 task.ti: ffff88040c070000
RIP: 0010:[<ffffffff8108fd3c>]  [<ffffffff8108fd3c>] __lock_acquire+0xcf/0x15a1
RSP: 0018:ffff88040c073bc0  EFLAGS: 00010002
RAX: 6b6b6b6b6b6b6b6b RBX: 0000000000000000 RCX: ffff88040d29a710
RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88040d29a710
RBP: ffff88040c073c70 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: ffff88040be041c0 R15: ffffffff814c928f
FS:  0000000000000000(0000) GS:ffff88041fa00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fa4595f4750 CR3: 0000000001c14000 CR4: 00000000001406f0
Stack:
 0000000000000006 000000000be04930 0000000000000000 ffff880400000000
 ffff880400000000 ffffffff8108f847 ffff88040be041c0 ffffffff81050446
 ffff8803fc08a920 ffff8803fc08a958 ffff88040be041c0 ffff88040c073c38
Call Trace:
 [<ffffffff8108f847>] ? mark_held_locks+0x5e/0x74
 [<ffffffff81050446>] ? __local_bh_enable_ip+0x9b/0xa1
 [<ffffffff8108f9ca>] ? trace_hardirqs_on_caller+0x16d/0x189
 [<ffffffff810915f4>] lock_acquire+0x122/0x1b6
 [<ffffffff810915f4>] ? lock_acquire+0x122/0x1b6
 [<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
 [<ffffffff81609dbf>] _raw_spin_lock_irqsave+0x35/0x49
 [<ffffffff814c928f>] ? skb_dequeue+0x18/0x61
 [<ffffffff814c928f>] skb_dequeue+0x18/0x61
 [<ffffffffa009aa92>] afs_deliver_to_call+0x344/0x39d [kafs]
 [<ffffffffa009ab37>] afs_process_async_call+0x4c/0xd5 [kafs]
 [<ffffffffa0099e9c>] afs_async_workfn+0xe/0x10 [kafs]
 [<ffffffff81063a3a>] process_one_work+0x29d/0x57c
 [<ffffffff81064ac2>] worker_thread+0x24a/0x385
 [<ffffffff81064878>] ? rescuer_thread+0x2d0/0x2d0
 [<ffffffff810696f5>] kthread+0xf3/0xfb
 [<ffffffff8160a6ff>] ret_from_fork+0x1f/0x40
 [<ffffffff81069602>] ? kthread_create_on_node+0x1cf/0x1cf

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/rxrpc.txt

@@ -790,13 +790,12 @@ The kernel interface functions are as follows:
      Data messages can have their contents extracted with the usual bunch of
      socket buffer manipulation functions.  A data message can be determined to
      be the last one in a sequence with rxrpc_kernel_is_data_last().  When a
-     data message has been used up, rxrpc_kernel_data_delivered() should be
-     called on it..
+     data message has been used up, rxrpc_kernel_data_consumed() should be
+     called on it.
 
-     Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose
-     of.  It is possible to get extra refs on all types of message for later
-     freeing, but this may pin the state of a call until the message is finally
-     freed.
+     Messages should be handled to rxrpc_kernel_free_skb() to dispose of.  It
+     is possible to get extra refs on all types of message for later freeing,
+     but this may pin the state of a call until the message is finally freed.
 
  (*) Accept an incoming call.
 
@@ -821,12 +820,14 @@ The kernel interface functions are as follows:
      Other errors may be returned if the call had been aborted (-ECONNABORTED)
      or had timed out (-ETIME).
 
- (*) Record the delivery of a data message and free it.
+ (*) Record the delivery of a data message.
 
-	void rxrpc_kernel_data_delivered(struct sk_buff *skb);
+	void rxrpc_kernel_data_consumed(struct rxrpc_call *call,
+					struct sk_buff *skb);
 
-     This is used to record a data message as having been delivered and to
-     update the ACK state for the call.  The socket buffer will be freed.
+     This is used to record a data message as having been consumed and to
+     update the ACK state for the call.  The message must still be passed to
+     rxrpc_kernel_free_skb() for disposal by the caller.
 
  (*) Free a message.
 

fs/afs/cmservice.c

@@ -189,11 +189,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 	case 1:
 		_debug("extract FID count");
 		ret = afs_extract_data(call, skb, last, &call->tmp, 4);
-		switch (ret) {
-		case 0:		break;
-		case -EAGAIN:	return 0;
-		default:	return ret;
-		}
+		if (ret < 0)
+			return ret;
 
 		call->count = ntohl(call->tmp);
 		_debug("FID count: %u", call->count);
@@ -210,11 +207,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 		_debug("extract FID array");
 		ret = afs_extract_data(call, skb, last, call->buffer,
 				       call->count * 3 * 4);
-		switch (ret) {
-		case 0:		break;
-		case -EAGAIN:	return 0;
-		default:	return ret;
-		}
+		if (ret < 0)
+			return ret;
 
 		_debug("unmarshall FID array");
 		call->request = kcalloc(call->count,
@@ -239,11 +233,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 	case 3:
 		_debug("extract CB count");
 		ret = afs_extract_data(call, skb, last, &call->tmp, 4);
-		switch (ret) {
-		case 0:		break;
-		case -EAGAIN:	return 0;
-		default:	return ret;
-		}
+		if (ret < 0)
+			return ret;
 
 		tmp = ntohl(call->tmp);
 		_debug("CB count: %u", tmp);
@@ -258,11 +249,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 		_debug("extract CB array");
 		ret = afs_extract_data(call, skb, last, call->request,
 				       call->count * 3 * 4);
-		switch (ret) {
-		case 0:		break;
-		case -EAGAIN:	return 0;
-		default:	return ret;
-		}
+		if (ret < 0)
+			return ret;
 
 		_debug("unmarshall CB array");
 		cb = call->request;
@@ -278,9 +266,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 		call->unmarshall++;
 
 	case 5:
-		_debug("trailer");
-		if (skb->len != 0)
-			return -EBADMSG;
+		ret = afs_data_complete(call, skb, last);
+		if (ret < 0)
+			return ret;
 
 		/* Record that the message was unmarshalled successfully so
 		 * that the call destructor can know do the callback breaking
@@ -294,8 +282,6 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 		break;
 	}
 
-	if (!last)
-		return 0;
 
 	call->state = AFS_CALL_REPLYING;
 
@@ -335,13 +321,13 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call,
 {
 	struct afs_server *server;
 	struct in_addr addr;
+	int ret;
 
 	_enter(",{%u},%d", skb->len, last);
 
-	if (skb->len > 0)
-		return -EBADMSG;
-	if (!last)
-		return 0;
+	ret = afs_data_complete(call, skb, last);
+	if (ret < 0)
+		return ret;
 
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
@@ -371,8 +357,10 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call,
 
 	_enter(",{%u},%d", skb->len, last);
 
+	/* There are some arguments that we ignore */
+	afs_data_consumed(call, skb);
 	if (!last)
-		return 0;
+		return -EAGAIN;
 
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
@@ -408,12 +396,13 @@ static void SRXAFSCB_Probe(struct work_struct *work)
 static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb,
 				bool last)
 {
+	int ret;
+
 	_enter(",{%u},%d", skb->len, last);
 
-	if (skb->len > 0)
-		return -EBADMSG;
-	if (!last)
-		return 0;
+	ret = afs_data_complete(call, skb, last);
+	if (ret < 0)
+		return ret;
 
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
@@ -460,10 +449,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
 
 	_enter("{%u},{%u},%d", call->unmarshall, skb->len, last);
 
-	if (skb->len > 0)
-		return -EBADMSG;
-	if (!last)
-		return 0;
+	ret = afs_data_complete(call, skb, last);
+	if (ret < 0)
+		return ret;
 
 	switch (call->unmarshall) {
 	case 0:
@@ -509,8 +497,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb,
 		break;
 	}
 
-	if (!last)
-		return 0;
+	ret = afs_data_complete(call, skb, last);
+	if (ret < 0)
+		return ret;
 
 	call->state = AFS_CALL_REPLYING;
 
@@ -588,12 +577,13 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call,
 						 struct sk_buff *skb, bool last)
 {
+	int ret;
+
 	_enter(",{%u},%d", skb->len, last);
 
-	if (skb->len > 0)
-		return -EBADMSG;
-	if (!last)
-		return 0;
+	ret = afs_data_complete(call, skb, last);
+	if (ret < 0)
+		return ret;
 
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;