[dpdk-dev] [PATCH v2 1/3] gso: support UDP/IPv4 fragmentation

[Jiayu Hu <jiayu.hu@intel.com>]

This patch adds GSO support for UDP/IPv4 packets. Supported packets
may include a single VLAN tag. UDP/IPv4 GSO doesn't check if input
packets have correct checksums, and doesn't update checksums for
output packets (the responsibility for this lies with the application).
Additionally, UDP/IPv4 GSO doesn't process IP fragmented packets.

UDP/IPv4 GSO uses two chained MBUFs, one direct MBUF and one indrect
MBUF, to organize an output packet. The direct MBUF stores the packet
header, while the indirect mbuf simply points to a location within the
original packet's payload. Consequently, use of UDP GSO requires
multi-segment MBUF support in the TX functions of the NIC driver.

If a packet is GSO'd, UDP/IPv4 GSO reduces its MBUF refcnt by 1. As a
result, when all of its GSOed segments are freed, the packet is freed
automatically.

Signed-off-by: Jiayu Hu <jiayu.hu@intel.com>
---
 lib/librte_gso/Makefile     |  1 +
 lib/librte_gso/gso_common.h |  3 ++
 lib/librte_gso/gso_udp4.c   | 81 +++++++++++++++++++++++++++++++++++++++++++++
 lib/librte_gso/gso_udp4.h   | 42 +++++++++++++++++++++++
 lib/librte_gso/rte_gso.c    | 24 +++++++++++---
 lib/librte_gso/rte_gso.h    |  6 +++-
 6 files changed, 151 insertions(+), 6 deletions(-)
 create mode 100644 lib/librte_gso/gso_udp4.c
 create mode 100644 lib/librte_gso/gso_udp4.h

diff --git a/lib/librte_gso/Makefile b/lib/librte_gso/Makefile
index 3648ec0..1fac53a 100644
--- a/lib/librte_gso/Makefile
+++ b/lib/librte_gso/Makefile
@@ -19,6 +19,7 @@ SRCS-$(CONFIG_RTE_LIBRTE_GSO) += rte_gso.c
 SRCS-$(CONFIG_RTE_LIBRTE_GSO) += gso_common.c
 SRCS-$(CONFIG_RTE_LIBRTE_GSO) += gso_tcp4.c
 SRCS-$(CONFIG_RTE_LIBRTE_GSO) += gso_tunnel_tcp4.c
+SRCS-$(CONFIG_RTE_LIBRTE_GSO) += gso_udp4.c
 
 # install this header file
 SYMLINK-$(CONFIG_RTE_LIBRTE_GSO)-include += rte_gso.h
diff --git a/lib/librte_gso/gso_common.h b/lib/librte_gso/gso_common.h
index 5ca5974..6cd764f 100644
--- a/lib/librte_gso/gso_common.h
+++ b/lib/librte_gso/gso_common.h
@@ -31,6 +31,9 @@
 		(PKT_TX_TCP_SEG | PKT_TX_IPV4 | PKT_TX_OUTER_IPV4 | \
 		 PKT_TX_TUNNEL_GRE))
 
+#define IS_IPV4_UDP(flag) (((flag) & (PKT_TX_UDP_SEG | PKT_TX_IPV4)) == \
+		(PKT_TX_UDP_SEG | PKT_TX_IPV4))
+
 /**
  * Internal function which updates the UDP header of a packet, following
  * segmentation. This is required to update the header's datagram length field.
diff --git a/lib/librte_gso/gso_udp4.c b/lib/librte_gso/gso_udp4.c
new file mode 100644
index 0000000..a3db329
--- /dev/null
+++ b/lib/librte_gso/gso_udp4.c
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#include "gso_common.h"
+#include "gso_udp4.h"
+
+#define IPV4_HDR_MF_BIT (1U << 13)
+
+static inline void
+update_ipv4_udp_headers(struct rte_mbuf *pkt, struct rte_mbuf **segs,
+		uint16_t nb_segs)
+{
+	struct ipv4_hdr *ipv4_hdr;
+	uint16_t frag_offset = 0, is_mf;
+	uint16_t l2_hdrlen = pkt->l2_len, l3_hdrlen = pkt->l3_len;
+	uint16_t tail_idx = nb_segs - 1, length, i;
+
+	/*
+	 * Update IP header fields for output segments. Specifically,
+	 * keep the same IP id, update fragment offset and total
+	 * length.
+	 */
+	for (i = 0; i < nb_segs; i++) {
+		ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(segs[i],
+					char *) + l2_hdrlen);
+		length = segs[i]->pkt_len - l2_hdrlen;
+		ipv4_hdr->total_length = rte_cpu_to_be_16(length);
+
+		is_mf = i < tail_idx ? IPV4_HDR_MF_BIT : 0;
+		ipv4_hdr->fragment_offset =
+			rte_cpu_to_be_16(frag_offset | is_mf);
+		frag_offset += ((length - l3_hdrlen) >> 3);
+	}
+}
+
+int
+gso_udp4_segment(struct rte_mbuf *pkt,
+		uint16_t gso_size,
+		struct rte_mempool *direct_pool,
+		struct rte_mempool *indirect_pool,
+		struct rte_mbuf **pkts_out,
+		uint16_t nb_pkts_out)
+{
+	struct ipv4_hdr *ipv4_hdr;
+	uint16_t pyld_unit_size, hdr_offset;
+	uint16_t frag_off;
+	int ret;
+
+	/* Don't process the fragmented packet */
+	ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
+			pkt->l2_len);
+	frag_off = rte_be_to_cpu_16(ipv4_hdr->fragment_offset);
+	if (unlikely(IS_FRAGMENTED(frag_off))) {
+		pkts_out[0] = pkt;
+		return 1;
+	}
+
+	/*
+	 * UDP fragmentation is the same as IP fragmentation.
+	 * Except the first one, other output packets just have l2
+	 * and l3 headers.
+	 */
+	hdr_offset = pkt->l2_len + pkt->l3_len;
+
+	/* Don't process the packet without data. */
+	if (unlikely(hdr_offset + pkt->l4_len >= pkt->pkt_len)) {
+		pkts_out[0] = pkt;
+		return 1;
+	}
+
+	pyld_unit_size = gso_size - hdr_offset;
+
+	/* Segment the payload */
+	ret = gso_do_segment(pkt, hdr_offset, pyld_unit_size, direct_pool,
+			indirect_pool, pkts_out, nb_pkts_out);
+	if (ret > 1)
+		update_ipv4_udp_headers(pkt, pkts_out, ret);
+
+	return ret;
+}
diff --git a/lib/librte_gso/gso_udp4.h b/lib/librte_gso/gso_udp4.h
new file mode 100644
index 0000000..b2a2908
--- /dev/null
+++ b/lib/librte_gso/gso_udp4.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2018 Intel Corporation
+ */
+
+#ifndef _GSO_UDP4_H_
+#define _GSO_UDP4_H_
+
+#include <stdint.h>
+#include <rte_mbuf.h>
+
+/**
+ * Segment an UDP/IPv4 packet. This function doesn't check if the input
+ * packet has correct checksums, and doesn't update checksums for output
+ * GSO segments. Furthermore, it doesn't process IP fragment packets.
+ *
+ * @param pkt
+ *  The packet mbuf to segment.
+ * @param gso_size
+ *  The max length of a GSO segment, measured in bytes.
+ * @param direct_pool
+ *  MBUF pool used for allocating direct buffers for output segments.
+ * @param indirect_pool
+ *  MBUF pool used for allocating indirect buffers for output segments.
+ * @param pkts_out
+ *  Pointer array used to store the MBUF addresses of output GSO
+ *  segments, when the function succeeds. If the memory space in
+ *  pkts_out is insufficient, it fails and returns -EINVAL.
+ * @param nb_pkts_out
+ *  The max number of items that 'pkts_out' can keep.
+ *
+ * @return
+ *   - The number of GSO segments filled in pkts_out on success.
+ *   - Return -ENOMEM if run out of memory in MBUF pools.
+ *   - Return -EINVAL for invalid parameters.
+ */
+int gso_udp4_segment(struct rte_mbuf *pkt,
+		uint16_t gso_size,
+		struct rte_mempool *direct_pool,
+		struct rte_mempool *indirect_pool,
+		struct rte_mbuf **pkts_out,
+		uint16_t nb_pkts_out);
+#endif
diff --git a/lib/librte_gso/rte_gso.c b/lib/librte_gso/rte_gso.c
index a44e3d4..751b5b6 100644
--- a/lib/librte_gso/rte_gso.c
+++ b/lib/librte_gso/rte_gso.c
@@ -11,6 +11,17 @@
 #include "gso_common.h"
 #include "gso_tcp4.h"
 #include "gso_tunnel_tcp4.h"
+#include "gso_udp4.h"
+
+#define ILLEGAL_UDP_GSO_CTX(ctx) \
+	((((ctx)->gso_types & DEV_TX_OFFLOAD_UDP_TSO) == 0) || \
+	 (ctx)->gso_size < RTE_GSO_UDP_SEG_SIZE_MIN)
+
+#define ILLEGAL_TCP_GSO_CTX(ctx) \
+	((((ctx)->gso_types & (DEV_TX_OFFLOAD_TCP_TSO | \
+		DEV_TX_OFFLOAD_VXLAN_TNL_TSO | \
+		DEV_TX_OFFLOAD_GRE_TNL_TSO)) == 0) || \
+		(ctx)->gso_size < RTE_GSO_SEG_SIZE_MIN)
 
 int
 rte_gso_segment(struct rte_mbuf *pkt,
@@ -27,14 +38,12 @@ rte_gso_segment(struct rte_mbuf *pkt,
 
 	if (pkt == NULL || pkts_out == NULL || gso_ctx == NULL ||
 			nb_pkts_out < 1 ||
-			gso_ctx->gso_size < RTE_GSO_SEG_SIZE_MIN ||
-			((gso_ctx->gso_types & (DEV_TX_OFFLOAD_TCP_TSO |
-			DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
-			DEV_TX_OFFLOAD_GRE_TNL_TSO)) == 0))
+			(ILLEGAL_UDP_GSO_CTX(gso_ctx) &&
+			 ILLEGAL_TCP_GSO_CTX(gso_ctx)))
 		return -EINVAL;
 
 	if (gso_ctx->gso_size >= pkt->pkt_len) {
-		pkt->ol_flags &= (~PKT_TX_TCP_SEG);
+		pkt->ol_flags &= (~(PKT_TX_TCP_SEG | PKT_TX_UDP_SEG));
 		pkts_out[0] = pkt;
 		return 1;
 	}
@@ -59,6 +68,11 @@ rte_gso_segment(struct rte_mbuf *pkt,
 		ret = gso_tcp4_segment(pkt, gso_size, ipid_delta,
 				direct_pool, indirect_pool,
 				pkts_out, nb_pkts_out);
+	} else if (IS_IPV4_UDP(pkt->ol_flags) &&
+			(gso_ctx->gso_types & DEV_TX_OFFLOAD_UDP_TSO)) {
+		pkt->ol_flags &= (~PKT_TX_UDP_SEG);
+		ret = gso_udp4_segment(pkt, gso_size, direct_pool,
+				indirect_pool, pkts_out, nb_pkts_out);
 	} else {
 		/* unsupported packet, skip */
 		pkts_out[0] = pkt;
diff --git a/lib/librte_gso/rte_gso.h b/lib/librte_gso/rte_gso.h
index f4abd61..a626a11 100644
--- a/lib/librte_gso/rte_gso.h
+++ b/lib/librte_gso/rte_gso.h
@@ -17,10 +17,14 @@ extern "C" {
 #include <stdint.h>
 #include <rte_mbuf.h>
 
-/* Minimum GSO segment size. */
+/* Minimum GSO segment size for TCP based packets. */
 #define RTE_GSO_SEG_SIZE_MIN (sizeof(struct ether_hdr) + \
 		sizeof(struct ipv4_hdr) + sizeof(struct tcp_hdr) + 1)
 
+/* Minimum GSO segment size for UDP based packets. */
+#define RTE_GSO_UDP_SEG_SIZE_MIN (sizeof(struct ether_hdr) + \
+		sizeof(struct ipv4_hdr) + sizeof(struct udp_hdr) + 1)
+
 /* GSO flags for rte_gso_ctx. */
 #define RTE_GSO_FLAG_IPID_FIXED (1ULL << 0)
 /**< Use fixed IP ids for output GSO segments. Setting
-- 
2.7.4