tipc: message reassembly using fragment chain

When the first fragment of a long data data message is received on a link, a
reassembly buffer large enough to hold the data from this and all subsequent
fragments of the message is allocated. The payload of each new fragment is
copied into this buffer upon arrival. When the last fragment is received, the
reassembled message is delivered upwards to the port/socket layer.

Not only is this an inefficient approach, but it may also cause bursts of
reassembly failures in low memory situations. since we may fail to allocate
the necessary large buffer in the first place. Furthermore, after 100 subsequent
such failures the link will be reset, something that in reality aggravates the
situation.

To remedy this problem, this patch introduces a different approach. Instead of
allocating a big reassembly buffer, we now append the arriving fragments
to a reassembly chain on the link, and deliver the whole chain up to the
socket layer once the last fragment has been received. This is safe because
the retransmission layer of a TIPC link always delivers packets in strict
uninterrupted order, to the reassembly layer as to all other upper layers.
Hence there can never be more than one fragment chain pending reassembly at
any given time in a link, and we can trust (but still verify) that the
fragments will be chained up in the correct order.

Signed-off-by: Erik Hugne <erik.hugne@ericsson.com>
Reviewed-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 14 insertions, 6 deletions

diff --git a/net/tipc/link.h b/net/tipc/link.h
index 55cf8554a08b..8a6c1026644d 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -41,6 +41,12 @@
 #include "node.h"
 
 /*
+ * Link reassembly status codes
+ */
+#define LINK_REASM_ERROR	-1
+#define LINK_REASM_COMPLETE	1
+
+/*
  * Out-of-range value for link sequence numbers
  */
 #define INVALID_LINK_SEQ 0x10000
@@ -134,7 +140,8 @@ struct tipc_stats {
  * @next_out: ptr to first unsent outbound message in queue
  * @waiting_ports: linked list of ports waiting for link congestion to abate
  * @long_msg_seq_no: next identifier to use for outbound fragmented messages
- * @defragm_buf: list of partially reassembled inbound message fragments
+ * @reasm_head: list head of partially reassembled inbound message fragments
+ * @reasm_tail: last fragment received
  * @stats: collects statistics regarding link activity
  */
 struct tipc_link {
@@ -196,9 +203,10 @@ struct tipc_link {
 	struct sk_buff *next_out;
 	struct list_head waiting_ports;
 
-	/* Fragmentation/defragmentation */
+	/* Fragmentation/reassembly */
 	u32 long_msg_seq_no;
-	struct sk_buff *defragm_buf;
+	struct sk_buff *reasm_head;
+	struct sk_buff *reasm_tail;
 
 	/* Statistics */
 	struct tipc_stats stats;
@@ -229,9 +237,9 @@ int tipc_link_send_sections_fast(struct tipc_port *sender,
 				 struct iovec const *msg_sect,
 				 unsigned int len, u32 destnode);
 void tipc_link_recv_bundle(struct sk_buff *buf);
-int  tipc_link_recv_fragment(struct sk_buff **pending,
-			     struct sk_buff **fb,
-			     struct tipc_msg **msg);
+int  tipc_link_recv_fragment(struct sk_buff **reasm_head,
+			     struct sk_buff **reasm_tail,
+			     struct sk_buff **fbuf);
 void tipc_link_send_proto_msg(struct tipc_link *l_ptr, u32 msg_typ, int prob,
 			      u32 gap, u32 tolerance, u32 priority,
 			      u32 acked_mtu);