[PATCH net v6 02/10] rxrpc: Fix packet encryption error handling

[David Howells]

In rxrpc_send_data(), if ->secure_packet() returns an error, the code
currently just jumps to out: and returns the error to the app on the
assumption that any error returned by this is automatically fatal for the
call, and may even have corrupted the transmission queue - but leaving it
to userspace to deal with.  Nothing stops the application from retrying the
sendmsg(), which will try to encrypt the buffer again, and might succeed
with a corrupt buffer.

Fix rxrpc_send_data() in the following ways:

 (1) If -ENOMEM is returned, assume we never got as far as the encryption
     and that the operation is retryable.  In which case, jump to
     maybe_error_rewind and, if we've copied data into the last packet,
     remove a byte from it so that we don't tell the caller that we've
     completed the transmission phase.

 (2) If any other error occurs, set the TX_ERROR flag on the call and
     return that error directly; on all subsequent attempts to add data to
     the call, return -EIO.  The app must then abort the call to get rid of
     it (this allows the app to choose the abort code to use).

Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Closes: https://sashiko.dev/#/patchset/20260702144919.172295-1-dhowells%40redhat.com
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
cc: Marc Dionne <marc.dionne@xxxxxxxxxxxx>
cc: Eric Dumazet <edumazet@xxxxxxxxxx>
cc: "David S. Miller" <davem@xxxxxxxxxxxxx>
cc: Jakub Kicinski <kuba@xxxxxxxxxx>
cc: Paolo Abeni <pabeni@xxxxxxxxxx>
cc: Simon Horman <horms@xxxxxxxxxx>
cc: linux-afs@xxxxxxxxxxxxxxxxxxx
cc: stable@xxxxxxxxxx
---
 fs/afs/rxrpc.c               | 22 +++++++++------
 include/trace/events/rxrpc.h |  1 +
 net/rxrpc/ar-internal.h      |  1 +
 net/rxrpc/sendmsg.c          | 53 ++++++++++++++++++++++++++++--------
 4 files changed, 57 insertions(+), 20 deletions(-)

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index d82916657a3d..b435f4b2da7f 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -412,21 +412,25 @@ void afs_make_call(struct afs_call *call, gfp_t gfp)
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= MSG_WAITALL | (call->write_iter ? MSG_MORE : 0);
 
-	ret = rxrpc_kernel_send_data(call->net->socket, rxcall,
-				     &msg, call->request_size,
-				     afs_notify_end_request_tx);
-	if (ret < 0)
-		goto error_do_abort;
+	do {
+		ret = rxrpc_kernel_send_data(call->net->socket, rxcall,
+					     &msg, call->request_size,
+					     afs_notify_end_request_tx);
+		if (ret < 0)
+			goto error_do_abort;
+	} while (iov_iter_count(&msg.msg_iter) > 0);
 
 	if (call->write_iter) {
 		msg.msg_iter = *call->write_iter;
 		msg.msg_flags &= ~MSG_MORE;
 		trace_afs_send_data(call, &msg);
 
-		ret = rxrpc_kernel_send_data(call->net->socket,
-					     call->rxcall, &msg,
-					     iov_iter_count(&msg.msg_iter),
-					     afs_notify_end_request_tx);
+		do {
+			ret = rxrpc_kernel_send_data(call->net->socket,
+						     call->rxcall, &msg,
+						     iov_iter_count(&msg.msg_iter),
+						     afs_notify_end_request_tx);
+		} while (iov_iter_count(&msg.msg_iter) > 0);
 		*call->write_iter = msg.msg_iter;
 
 		trace_afs_sent_data(call, &msg, ret);
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 704a10de6670..8f3e3967885a 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -148,6 +148,7 @@
 	EM(rxrpc_eproto_wrong_security,		"wrong-sec")		\
 	EM(rxrpc_recvmsg_excess_data,		"recvmsg-excess")	\
 	EM(rxrpc_recvmsg_short_data,		"recvmsg-short")	\
+	EM(rxrpc_sendmsg_tx_error,		"tx-error")		\
 	E_(rxrpc_sendmsg_late_send,		"sendmsg-late")
 
 #define rxrpc_call_poke_traces \
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 865f05fe37ab..a6f830c1621f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -642,6 +642,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_TX_LAST,		/* Last packet in Tx buffer (at rxtx_top) */
 	RXRPC_CALL_TX_ALL_ACKED,	/* Last packet has been hard-acked */
 	RXRPC_CALL_TX_NO_MORE,		/* No more data to transmit (MSG_MORE deasserted) */
+	RXRPC_CALL_TX_ERROR,		/* Terminal error; call needs abort */
 	RXRPC_CALL_SEND_PING,		/* A ping will need to be sent */
 	RXRPC_CALL_RETRANS_TIMEOUT,	/* Retransmission due to timeout occurred */
 	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 4c754f78ece9..5ea10dc497a7 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -330,13 +330,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	bool more = msg->msg_flags & MSG_MORE;
 	int ret, copied = 0;
 
-	if (test_bit(RXRPC_CALL_TX_NO_MORE, &call->flags)) {
-		trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
-				  call->cid, call->call_id, call->rx_consumed,
-				  0, -EPROTO);
-		return -EPROTO;
-	}
-
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	ret = rxrpc_wait_to_be_connected(call, &timeo);
@@ -353,6 +346,19 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
 reload:
+	if (unlikely(test_bit(RXRPC_CALL_TX_NO_MORE, &call->flags))) {
+		trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send,
+				  call->cid, call->call_id, call->rx_consumed,
+				  0, -EPROTO);
+		return -EPROTO;
+	}
+	if (unlikely(test_bit(RXRPC_CALL_TX_ERROR, &call->flags))) {
+		trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_tx_error,
+				  call->cid, call->call_id, call->rx_consumed,
+				  0, -EIO);
+		return -EIO;
+	}
+
 	txb = call->tx_pending;
 	call->tx_pending = NULL;
 	if (txb)
@@ -440,12 +446,21 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 		/* add the packet to the send queue if it's now full */
 		if (!txb->space ||
 		    (msg_data_left(msg) == 0 && !more)) {
-			if (msg_data_left(msg) == 0 && !more)
-				txb->flags |= RXRPC_LAST_PACKET;
-
+			/* Do any required crypto.  If this fails, it could
+			 * have corrupted the txbuf content with a partial
+			 * encrypt.  Assume that ENOMEM is retryable, but
+			 * everything else is terminal.
+			 */
 			ret = call->security->secure_packet(call, txb);
-			if (ret < 0)
+			if (ret < 0) {
+				if (ret == -ENOMEM)
+					goto maybe_error_rewind;
+				set_bit(RXRPC_CALL_TX_ERROR, &call->flags);
 				goto out;
+			}
+
+			if (msg_data_left(msg) == 0 && !more)
+				txb->flags |= RXRPC_LAST_PACKET;
 			rxrpc_queue_packet(rx, call, txb, notify_end_tx);
 			txb = NULL;
 		}
@@ -463,6 +478,22 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 	_leave(" = %d", call->error);
 	return call->error;
 
+maybe_error_rewind:
+	/* If we got a retryable error after copying all the supplied data into
+	 * the last packet, we need to rewind as much as we can so the caller
+	 * knows they need to retry the sendmsg.
+	 */
+	if (copied && !more && !msg_data_left(msg)) {
+		unsigned int rewind_by = umin(copied, txb->len);
+
+		txb->space  += rewind_by;
+		txb->len    -= rewind_by;
+		txb->offset -= rewind_by;
+		copied      -= rewind_by;
+		if (call->tx_total_len != -1)
+			call->tx_total_len += rewind_by;
+		iov_iter_revert(&msg->msg_iter, rewind_by);
+	}
 maybe_error:
 	if (copied) {
 		if (rxrpc_call_is_complete(call) &&