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, 11 insertions, 24 deletions

diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index f8d8079dc058..b4b6a3664dda 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -12,7 +12,6 @@
 #ifndef _NET_RXRPC_H
 #define _NET_RXRPC_H
 
-#include <linux/skbuff.h>
 #include <linux/rxrpc.h>
 
 struct key;
@@ -20,38 +19,26 @@ struct sock;
 struct socket;
 struct rxrpc_call;
 
-/*
- * the mark applied to socket buffers that may be intercepted
- */
-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 */
-};
+typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *,
+				  unsigned long);
+typedef void (*rxrpc_notify_new_call_t)(struct sock *);
 
-typedef void (*rxrpc_interceptor_t)(struct sock *, unsigned long,
-				    struct sk_buff *);
-void rxrpc_kernel_intercept_rx_messages(struct socket *, rxrpc_interceptor_t);
+void rxrpc_kernel_new_call_notification(struct socket *,
+					rxrpc_notify_new_call_t);
 struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
 					   struct sockaddr_rxrpc *,
 					   struct key *,
 					   unsigned long,
-					   gfp_t);
+					   gfp_t,
+					   rxrpc_notify_rx_t);
 int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t);
-void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *);
+int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
+			   void *, size_t, size_t *, bool, u32 *);
 void rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, u32);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
-bool rxrpc_kernel_is_data_last(struct sk_buff *);
-u32 rxrpc_kernel_get_abort_code(struct sk_buff *);
-int rxrpc_kernel_get_error_number(struct sk_buff *);
-void rxrpc_kernel_free_skb(struct sk_buff *);
-struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long);
+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 *);