rxrpc: Rewrite the data and ack handling code

Rewrite the data and ack handling code such that:

 (1) Parsing of received ACK and ABORT packets and the distribution and the
     filing of DATA packets happens entirely within the data_ready context
     called from the UDP socket.  This allows us to process and discard ACK
     and ABORT packets much more quickly (they're no longer stashed on a
     queue for a background thread to process).

 (2) We avoid calling skb_clone(), pskb_pull() and pskb_trim().  We instead
     keep track of the offset and length of the content of each packet in
     the sk_buff metadata.  This means we don't do any allocation in the
     receive path.

 (3) Jumbo DATA packet parsing is now done in data_ready context.  Rather
     than cloning the packet once for each subpacket and pulling/trimming
     it, we file the packet multiple times with an annotation for each
     indicating which subpacket is there.  From that we can directly
     calculate the offset and length.

 (4) A call's receive queue can be accessed without taking locks (memory
     barriers do have to be used, though).

 (5) Incoming calls are set up from preallocated resources and immediately
     made live.  They can than have packets queued upon them and ACKs
     generated.  If insufficient resources exist, DATA packet #1 is given a
     BUSY reply and other DATA packets are discarded).

 (6) sk_buffs no longer take a ref on their parent call.

To make this work, the following changes are made:

 (1) Each call's receive buffer is now a circular buffer of sk_buff
     pointers (rxtx_buffer) rather than a number of sk_buff_heads spread
     between the call and the socket.  This permits each sk_buff to be in
     the buffer multiple times.  The receive buffer is reused for the
     transmit buffer.

 (2) A circular buffer of annotations (rxtx_annotations) is kept parallel
     to the data buffer.  Transmission phase annotations indicate whether a
     buffered packet has been ACK'd or not and whether it needs
     retransmission.

     Receive phase annotations indicate whether a slot holds a whole packet
     or a jumbo subpacket and, if the latter, which subpacket.  They also
     note whether the packet has been decrypted in place.

 (3) DATA packet window tracking is much simplified.  Each phase has just
     two numbers representing the window (rx_hard_ack/rx_top and
     tx_hard_ack/tx_top).

     The hard_ack number is the sequence number before base of the window,
     representing the last packet the other side says it has consumed.
     hard_ack starts from 0 and the first packet is sequence number 1.

     The top number is the sequence number of the highest-numbered packet
     residing in the buffer.  Packets between hard_ack+1 and top are
     soft-ACK'd to indicate they've been received, but not yet consumed.

     Four macros, before(), before_eq(), after() and after_eq() are added
     to compare sequence numbers within the window.  This allows for the
     top of the window to wrap when the hard-ack sequence number gets close
     to the limit.

     Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also
     to indicate when rx_top and tx_top point at the packets with the
     LAST_PACKET bit set, indicating the end of the phase.

 (4) Calls are queued on the socket 'receive queue' rather than packets.
     This means that we don't need have to invent dummy packets to queue to
     indicate abnormal/terminal states and we don't have to keep metadata
     packets (such as ABORTs) around

 (5) The offset and length of a (sub)packet's content are now passed to
     the verify_packet security op.  This is currently expected to decrypt
     the packet in place and validate it.

     However, there's now nowhere to store the revised offset and length of
     the actual data within the decrypted blob (there may be a header and
     padding to skip) because an sk_buff may represent multiple packets, so
     a locate_data security op is added to retrieve these details from the
     sk_buff content when needed.

 (6) recvmsg() now has to handle jumbo subpackets, where each subpacket is
     individually secured and needs to be individually decrypted.  The code
     to do this is broken out into rxrpc_recvmsg_data() and shared with the
     kernel API.  It now iterates over the call's receive buffer rather
     than walking the socket receive queue.

Additional changes:

 (1) The timers are condensed to a single timer that is set for the soonest
     of three timeouts (delayed ACK generation, DATA retransmission and
     call lifespan).

 (2) Transmission of ACK and ABORT packets is effected immediately from
     process-context socket ops/kernel API calls that cause them instead of
     them being punted off to a background work item.  The data_ready
     handler still has to defer to the background, though.

 (3) A shutdown op is added to the AF_RXRPC socket so that the AFS
     filesystem can shut down the socket and flush its own work items
     before closing the socket to deal with any in-progress service calls.

Future additional changes that will need to be considered:

 (1) Make sure that a call doesn't hog the front of the queue by receiving
     data from the network as fast as userspace is consuming it to the
     exclusion of other calls.

 (2) Transmit delayed ACKs from within recvmsg() when we've consumed
     sufficiently more packets to avoid the background work item needing to
     run.

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

Author: dhowells

fs/afs/rxrpc.c

@@ -55,10 +55,8 @@ static const struct afs_call_type afs_RXCMxxxx = {
 	.abort_to_error	= afs_abort_to_error,
 };
 
-static void afs_collect_incoming_call(struct work_struct *);
 static void afs_charge_preallocation(struct work_struct *);
 
-static DECLARE_WORK(afs_collect_incoming_call_work, afs_collect_incoming_call);
 static DECLARE_WORK(afs_charge_preallocation_work, afs_charge_preallocation);
 
 static int afs_wait_atomic_t(atomic_t *p)
@@ -143,6 +141,8 @@ void afs_close_socket(void)
 			 TASK_UNINTERRUPTIBLE);
 	_debug("no outstanding calls");
 
+	flush_workqueue(afs_async_calls);
+	kernel_sock_shutdown(afs_socket, SHUT_RDWR);
 	flush_workqueue(afs_async_calls);
 	sock_release(afs_socket);
 
@@ -602,51 +602,6 @@ static void afs_process_async_call(struct work_struct *work)
 	_leave("");
 }
 
-/*
- * accept the backlog of incoming calls
- */
-static void afs_collect_incoming_call(struct work_struct *work)
-{
-	struct rxrpc_call *rxcall;
-	struct afs_call *call = NULL;
-
-	_enter("");
-
-	do {
-		if (!call) {
-			call = kzalloc(sizeof(struct afs_call), GFP_KERNEL);
-			if (!call) {
-				rxrpc_kernel_reject_call(afs_socket);
-				return;
-			}
-
-			INIT_WORK(&call->async_work, afs_process_async_call);
-			call->wait_mode = &afs_async_incoming_call;
-			call->type = &afs_RXCMxxxx;
-			init_waitqueue_head(&call->waitq);
-			call->state = AFS_CALL_AWAIT_OP_ID;
-
-			_debug("CALL %p{%s} [%d]",
-			       call, call->type->name,
-			       atomic_read(&afs_outstanding_calls));
-			atomic_inc(&afs_outstanding_calls);
-		}
-
-		rxcall = rxrpc_kernel_accept_call(afs_socket,
-						  (unsigned long)call,
-						  afs_wake_up_async_call);
-		if (!IS_ERR(rxcall)) {
-			call->rxcall = rxcall;
-			call->need_attention = true;
-			queue_work(afs_async_calls, &call->async_work);
-			call = NULL;
-		}
-	} while (!call);
-
-	if (call)
-		afs_free_call(call);
-}
-
 static void afs_rx_attach(struct rxrpc_call *rxcall, unsigned long user_call_ID)
 {
 	struct afs_call *call = (struct afs_call *)user_call_ID;
@@ -704,7 +659,7 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall,
 static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall,
 			    unsigned long user_call_ID)
 {
-	queue_work(afs_wq, &afs_collect_incoming_call_work);
+	atomic_inc(&afs_outstanding_calls);
 	queue_work(afs_wq, &afs_charge_preallocation_work);
 }
 

include/net/af_rxrpc.h

@@ -42,9 +42,6 @@ int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
 void rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, const char *);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
-struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long,
-					    rxrpc_notify_rx_t);
-int rxrpc_kernel_reject_call(struct socket *);
 void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
 			   struct sockaddr_rxrpc *);
 int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,

include/rxrpc/packet.h

@@ -133,6 +133,13 @@ struct rxrpc_ackpacket {
 
 } __packed;
 
+/* Some ACKs refer to specific packets and some are general and can be updated. */
+#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED)	|	\
+			      (1 << RXRPC_ACK_PING_RESPONSE)	|	\
+			      (1 << RXRPC_ACK_DELAY)		|	\
+			      (1 << RXRPC_ACK_IDLE))
+
+
 /*
  * ACK packets can have a further piece of information tagged on the end
  */

net/rxrpc/af_rxrpc.c

@@ -155,15 +155,15 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 	}
 
 	if (rx->srx.srx_service) {
-		write_lock_bh(&local->services_lock);
+		write_lock(&local->services_lock);
 		hlist_for_each_entry(prx, &local->services, listen_link) {
 			if (prx->srx.srx_service == rx->srx.srx_service)
 				goto service_in_use;
 		}
 
 		rx->local = local;
 		hlist_add_head_rcu(&rx->listen_link, &local->services);
-		write_unlock_bh(&local->services_lock);
+		write_unlock(&local->services_lock);
 
 		rx->sk.sk_state = RXRPC_SERVER_BOUND;
 	} else {
@@ -176,7 +176,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 	return 0;
 
 service_in_use:
-	write_unlock_bh(&local->services_lock);
+	write_unlock(&local->services_lock);
 	rxrpc_put_local(local);
 	ret = -EADDRINUSE;
 error_unlock:
@@ -515,15 +515,16 @@ static int rxrpc_setsockopt(struct socket *sock, int level, int optname,
 static unsigned int rxrpc_poll(struct file *file, struct socket *sock,
 			       poll_table *wait)
 {
-	unsigned int mask;
 	struct sock *sk = sock->sk;
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	unsigned int mask;
 
 	sock_poll_wait(file, sk_sleep(sk), wait);
 	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
 	 * queue */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!list_empty(&rx->recvmsg_q))
 		mask |= POLLIN | POLLRDNORM;
 
 	/* the socket is writable if there is space to add new data to the
@@ -575,15 +576,51 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
 	rx->calls = RB_ROOT;
 
 	INIT_HLIST_NODE(&rx->listen_link);
-	INIT_LIST_HEAD(&rx->secureq);
-	INIT_LIST_HEAD(&rx->acceptq);
+	spin_lock_init(&rx->incoming_lock);
+	INIT_LIST_HEAD(&rx->sock_calls);
+	INIT_LIST_HEAD(&rx->to_be_accepted);
+	INIT_LIST_HEAD(&rx->recvmsg_q);
+	rwlock_init(&rx->recvmsg_lock);
 	rwlock_init(&rx->call_lock);
 	memset(&rx->srx, 0, sizeof(rx->srx));
 
 	_leave(" = 0 [%p]", rx);
 	return 0;
 }
 
+/*
+ * Kill all the calls on a socket and shut it down.
+ */
+static int rxrpc_shutdown(struct socket *sock, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct rxrpc_sock *rx = rxrpc_sk(sk);
+	int ret = 0;
+
+	_enter("%p,%d", sk, flags);
+
+	if (flags != SHUT_RDWR)
+		return -EOPNOTSUPP;
+	if (sk->sk_state == RXRPC_CLOSE)
+		return -ESHUTDOWN;
+
+	lock_sock(sk);
+
+	spin_lock_bh(&sk->sk_receive_queue.lock);
+	if (sk->sk_state < RXRPC_CLOSE) {
+		sk->sk_state = RXRPC_CLOSE;
+		sk->sk_shutdown = SHUTDOWN_MASK;
+	} else {
+		ret = -ESHUTDOWN;
+	}
+	spin_unlock_bh(&sk->sk_receive_queue.lock);
+
+	rxrpc_discard_prealloc(rx);
+
+	release_sock(sk);
+	return ret;
+}
+
 /*
  * RxRPC socket destructor
  */
@@ -623,9 +660,9 @@ static int rxrpc_release_sock(struct sock *sk)
 	ASSERTCMP(rx->listen_link.next, !=, LIST_POISON1);
 
 	if (!hlist_unhashed(&rx->listen_link)) {
-		write_lock_bh(&rx->local->services_lock);
+		write_lock(&rx->local->services_lock);
 		hlist_del_rcu(&rx->listen_link);
-		write_unlock_bh(&rx->local->services_lock);
+		write_unlock(&rx->local->services_lock);
 	}
 
 	/* try to flush out this socket */
@@ -678,7 +715,7 @@ static const struct proto_ops rxrpc_rpc_ops = {
 	.poll		= rxrpc_poll,
 	.ioctl		= sock_no_ioctl,
 	.listen		= rxrpc_listen,
-	.shutdown	= sock_no_shutdown,
+	.shutdown	= rxrpc_shutdown,
 	.setsockopt	= rxrpc_setsockopt,
 	.getsockopt	= sock_no_getsockopt,
 	.sendmsg	= rxrpc_sendmsg,