rxrpc: Don't expose skbs to in-kernel users [ver #2]

Don't expose skbs to in-kernel users, such as the AFS filesystem, but
instead provide a notification hook the indicates that a call needs
attention and another that indicates that there's a new call to be
collected.

This makes the following possibilities more achievable:

 (1) Call refcounting can be made simpler if skbs don't hold refs to calls.

 (2) skbs referring to non-data events will be able to be freed much sooner
     rather than being queued for AFS to pick up as rxrpc_kernel_recv_data
     will be able to consult the call state.

 (3) We can shortcut the receive phase when a call is remotely aborted
     because we don't have to go through all the packets to get to the one
     cancelling the operation.

 (4) It makes it easier to do encryption/decryption directly between AFS's
     buffers and sk_buffs.

 (5) Encryption/decryption can more easily be done in the AFS's thread
     contexts - usually that of the userspace process that issued a syscall
     - rather than in one of rxrpc's background threads on a workqueue.

 (6) AFS will be able to wait synchronously on a call inside AF_RXRPC.

To make this work, the following interface function has been added:

     int rxrpc_kernel_recv_data(
		struct socket *sock, struct rxrpc_call *call,
		void *buffer, size_t bufsize, size_t *_offset,
		bool want_more, u32 *_abort_code);

This is the recvmsg equivalent.  It allows the caller to find out about the
state of a specific call and to transfer received data into a buffer
piecemeal.

afs_extract_data() and rxrpc_kernel_recv_data() now do all the extraction
logic between them.  They don't wait synchronously yet because the socket
lock needs to be dealt with.

Five interface functions have been removed:

	rxrpc_kernel_is_data_last()
    	rxrpc_kernel_get_abort_code()
    	rxrpc_kernel_get_error_number()
    	rxrpc_kernel_free_skb()
    	rxrpc_kernel_data_consumed()

As a temporary hack, sk_buffs going to an in-kernel call are queued on the
rxrpc_call struct (->knlrecv_queue) rather than being handed over to the
in-kernel user.  To process the queue internally, a temporary function,
temp_deliver_data() has been added.  This will be replaced with common code
between the rxrpc_recvmsg() path and the kernel_rxrpc_recv_data() path in a
future patch.

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

1 files changed, 21 insertions, 2 deletions

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 0c320b2b7b43..4e86d248dc5e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -40,6 +40,20 @@ struct rxrpc_crypt {
 struct rxrpc_connection;
 
 /*
+ * Mark applied to socket buffers.
+ */
+enum rxrpc_skb_mark {
+	RXRPC_SKB_MARK_DATA,		/* data message */
+	RXRPC_SKB_MARK_FINAL_ACK,	/* final ACK received message */
+	RXRPC_SKB_MARK_BUSY,		/* server busy message */
+	RXRPC_SKB_MARK_REMOTE_ABORT,	/* remote abort message */
+	RXRPC_SKB_MARK_LOCAL_ABORT,	/* local abort message */
+	RXRPC_SKB_MARK_NET_ERROR,	/* network error message */
+	RXRPC_SKB_MARK_LOCAL_ERROR,	/* local error message */
+	RXRPC_SKB_MARK_NEW_CALL,	/* local error message */
+};
+
+/*
  * sk_state for RxRPC sockets
  */
 enum {
@@ -57,7 +71,7 @@ enum {
 struct rxrpc_sock {
 	/* WARNING: sk has to be the first member */
 	struct sock		sk;
-	rxrpc_interceptor_t	interceptor;	/* kernel service Rx interceptor function */
+	rxrpc_notify_new_call_t	notify_new_call; /* Func to notify of new call */
 	struct rxrpc_local	*local;		/* local endpoint */
 	struct list_head	listen_link;	/* link in the local endpoint's listen list */
 	struct list_head	secureq;	/* calls awaiting connection security clearance */
@@ -367,6 +381,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_EXPECT_OOS,		/* expect out of sequence packets */
 	RXRPC_CALL_IS_SERVICE,		/* Call is service call */
 	RXRPC_CALL_EXPOSED,		/* The call was exposed to the world */
+	RXRPC_CALL_RX_NO_MORE,		/* Don't indicate MSG_MORE from recvmsg() */
 };
 
 /*
@@ -441,6 +456,7 @@ struct rxrpc_call {
 	struct timer_list	resend_timer;	/* Tx resend timer */
 	struct work_struct	destroyer;	/* call destroyer */
 	struct work_struct	processor;	/* packet processor and ACK generator */
+	rxrpc_notify_rx_t	notify_rx;	/* kernel service Rx notification function */
 	struct list_head	link;		/* link in master call list */
 	struct list_head	chan_wait_link;	/* Link in conn->waiting_calls */
 	struct hlist_node	error_link;	/* link in error distribution list */
@@ -448,6 +464,7 @@ struct rxrpc_call {
 	struct rb_node		sock_node;	/* node in socket call tree */
 	struct sk_buff_head	rx_queue;	/* received packets */
 	struct sk_buff_head	rx_oos_queue;	/* packets received out of sequence */
+	struct sk_buff_head	knlrecv_queue;	/* Queue for kernel_recv [TODO: replace this] */
 	struct sk_buff		*tx_pending;	/* Tx socket buffer being filled */
 	wait_queue_head_t	waitq;		/* Wait queue for channel or Tx */
 	__be32			crypto_buf[2];	/* Temporary packet crypto buffer */
@@ -512,7 +529,8 @@ extern struct workqueue_struct *rxrpc_workqueue;
  * call_accept.c
  */
 void rxrpc_accept_incoming_calls(struct rxrpc_local *);
-struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long);
+struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long,
+				     rxrpc_notify_rx_t);
 int rxrpc_reject_call(struct rxrpc_sock *);
 
 /*
@@ -874,6 +892,7 @@ int rxrpc_init_server_conn_security(struct rxrpc_connection *);
 /*
  * skbuff.c
  */
+void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *);
 void rxrpc_packet_destructor(struct sk_buff *);
 void rxrpc_new_skb(struct sk_buff *);
 void rxrpc_see_skb(struct sk_buff *);