[dpdk-dev] [PATCH] ip_frag: fix ipv6 when MTU sizes not aligned to 8 bytes

[Chas Williams <3chas3@gmail.com>]

From: Chas Williams <chas3@att.com>

The same issue was fixed on for the ipv4 version of this routine in
commit 8d4d3a4f7337 ("ip_frag: handle MTU sizes not aligned to 8 bytes").
Briefly, the size of an ipv6 header is always 40 bytes.  With an MTU of
1500, this will never produce a multiple of 8 bytes for the frag_size
and this routine can never succeed. Since RTE_ASSERTS are disabled by
default, this failure is tpyically ignored.

To fix this, round down to the nearest 8 bytes and use this when
producing the fragments.

Fixes: 0aa31d7a5929 ("ip_frag: add IPv6 fragmentation support")

Signed-off-by: Chas Williams <chas3@att.com>
---
 lib/librte_ip_frag/rte_ip_frag.h            |  1 +
 lib/librte_ip_frag/rte_ipv6_fragmentation.c | 18 +++++++++++-------
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/lib/librte_ip_frag/rte_ip_frag.h b/lib/librte_ip_frag/rte_ip_frag.h
index a4ccaf9d1..04fd9df52 100644
--- a/lib/librte_ip_frag/rte_ip_frag.h
+++ b/lib/librte_ip_frag/rte_ip_frag.h
@@ -115,6 +115,7 @@ struct rte_ip_frag_tbl {
 #define	RTE_IPV6_EHDR_MF_MASK			1
 #define	RTE_IPV6_EHDR_FO_SHIFT			3
 #define	RTE_IPV6_EHDR_FO_MASK			(~((1 << RTE_IPV6_EHDR_FO_SHIFT) - 1))
+#define	RTE_IPV6_EHDR_FO_ALIGN			(1 << RTE_IPV6_EHDR_FO_SHIFT)
 
 #define RTE_IPV6_FRAG_USED_MASK			\
 	(RTE_IPV6_EHDR_MF_MASK | RTE_IPV6_EHDR_FO_MASK)
diff --git a/lib/librte_ip_frag/rte_ipv6_fragmentation.c b/lib/librte_ip_frag/rte_ipv6_fragmentation.c
index 62a7e4e83..b9437eb11 100644
--- a/lib/librte_ip_frag/rte_ipv6_fragmentation.c
+++ b/lib/librte_ip_frag/rte_ipv6_fragmentation.c
@@ -77,11 +77,14 @@ rte_ipv6_fragment_packet(struct rte_mbuf *pkt_in,
 	uint32_t out_pkt_pos, in_seg_data_pos;
 	uint32_t more_in_segs;
 	uint16_t fragment_offset, frag_size;
+	uint64_t frag_bytes_remaining;
 
-	frag_size = (uint16_t)(mtu_size - sizeof(struct ipv6_hdr));
-
-	/* Fragment size should be a multiple of 8. */
-	RTE_ASSERT((frag_size & ~RTE_IPV6_EHDR_FO_MASK) == 0);
+	/*
+	 * Ensure the IP payload length of all fragments (except the
+	 * the last fragment) are a multiple of 8 bytes per RFC2460.
+	 */
+	frag_size = RTE_ALIGN_FLOOR(mtu_size - sizeof(struct ipv6_hdr),
+				    RTE_IPV6_EHDR_FO_ALIGN);
 
 	/* Check that pkts_out is big enough to hold all fragments */
 	if (unlikely (frag_size * nb_pkts_out <
@@ -111,6 +114,7 @@ rte_ipv6_fragment_packet(struct rte_mbuf *pkt_in,
 		/* Reserve space for the IP header that will be built later */
 		out_pkt->data_len = sizeof(struct ipv6_hdr) + sizeof(struct ipv6_extension_fragment);
 		out_pkt->pkt_len  = sizeof(struct ipv6_hdr) + sizeof(struct ipv6_extension_fragment);
+		frag_bytes_remaining = frag_size;
 
 		out_seg_prev = out_pkt;
 		more_out_segs = 1;
@@ -130,7 +134,7 @@ rte_ipv6_fragment_packet(struct rte_mbuf *pkt_in,
 
 			/* Prepare indirect buffer */
 			rte_pktmbuf_attach(out_seg, in_seg);
-			len = mtu_size - out_pkt->pkt_len;
+			len = frag_bytes_remaining;
 			if (len > (in_seg->data_len - in_seg_data_pos)) {
 				len = in_seg->data_len - in_seg_data_pos;
 			}
@@ -140,11 +144,11 @@ rte_ipv6_fragment_packet(struct rte_mbuf *pkt_in,
 			    out_pkt->pkt_len);
 			out_pkt->nb_segs += 1;
 			in_seg_data_pos += len;
+			frag_bytes_remaining -= len;
 
 			/* Current output packet (i.e. fragment) done ? */
-			if (unlikely(out_pkt->pkt_len >= mtu_size)) {
+			if (unlikely(frag_bytes_remaining == 0))
 				more_out_segs = 0;
-			}
 
 			/* Current input segment done ? */
 			if (unlikely(in_seg_data_pos == in_seg->data_len)) {
-- 
2.14.4