[dpdk-dev] [PATCH v1 5/8] gro: support UDP/IPv6

[yang_y_yi@163.com]

From: Yi Yang <yangyi01@inspur.com>

UDP/IPv6 GRO can help improve UDP/IPv6 performance.

With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to-VM UDP/IPv6 performance, it will merge
small adjacent UDP/IPv6 fragments to a big UDP/IPv6 packet
immediate after they are received from a physical NIC. It
is very helpful in OVS DPDK VLAN use case.

Signed-off-by: Yi Yang <yangyi01@inspur.com>
---
 .../prog_guide/generic_receive_offload_lib.rst     |   6 +-
 doc/guides/rel_notes/release_21_02.rst             |   5 +
 lib/librte_gro/gro_udp6.c                          | 487 +++++++++++++++++++++
 lib/librte_gro/gro_udp6.h                          | 284 ++++++++++++
 lib/librte_gro/meson.build                         |   2 +-
 lib/librte_gro/rte_gro.c                           |  72 ++-
 lib/librte_gro/rte_gro.h                           |   3 +
 7 files changed, 847 insertions(+), 12 deletions(-)
 create mode 100644 lib/librte_gro/gro_udp6.c
 create mode 100644 lib/librte_gro/gro_udp6.h

diff --git a/doc/guides/prog_guide/generic_receive_offload_lib.rst b/doc/guides/prog_guide/generic_receive_offload_lib.rst
index 0efade3..0ea3076 100644
--- a/doc/guides/prog_guide/generic_receive_offload_lib.rst
+++ b/doc/guides/prog_guide/generic_receive_offload_lib.rst
@@ -31,9 +31,9 @@ fragmentation is possible (i.e., DF==0). Additionally, it complies RFC
 6864 to process the IPv4 ID field.
 
 Currently, the GRO library provides GRO supports for TCP/IPv4, UDP/IPv4,
-and TCP/IPv6 packets as well as VxLAN packets which contain an outer IPv4
-header and an inner TCP/IPv4, UDP/IPv4 or TCP/IPv6 packet or an outer IPv6
-header and an inner TCP/IPv4 or TCP/IPv6 packet.
+UDP/IPv6, and TCP/IPv6 packets as well as VxLAN packets which contain an
+outer IPv4 header and an inner TCP/IPv4, UDP/IPv4 or TCP/IPv6 packet or
+an outer IPv6 header and an inner TCP/IPv4 or TCP/IPv6 packet.
 
 Two Sets of API
 ---------------
diff --git a/doc/guides/rel_notes/release_21_02.rst b/doc/guides/rel_notes/release_21_02.rst
index a5bc2f1..d8974b7 100644
--- a/doc/guides/rel_notes/release_21_02.rst
+++ b/doc/guides/rel_notes/release_21_02.rst
@@ -75,6 +75,11 @@ New Features
    Added TCP/IPv6 GRO support for IPv6 VXLAN packets, this enabled TCP/IPv6
    GRO support for IPv6 VXLAN use case.
 
+* **Added UDP/IPv6 GRO support for non-VXLAN packets.**
+
+   Added UDP/IPv6 GRO support for non-VXLAN packets, this enabled UDP/IPv6
+   GRO support for IPv6 VLAN use case.
+
 Removed Items
 -------------
 
diff --git a/lib/librte_gro/gro_udp6.c b/lib/librte_gro/gro_udp6.c
new file mode 100644
index 0000000..193cf2e
--- /dev/null
+++ b/lib/librte_gro/gro_udp6.c
@@ -0,0 +1,487 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Inspur Corporation
+ */
+
+#include <rte_malloc.h>
+#include <rte_mbuf.h>
+#include <rte_cycles.h>
+#include <rte_ethdev.h>
+#include <rte_ip.h>
+
+#include "gro_udp6.h"
+
+void *
+gro_udp6_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow)
+{
+	struct gro_udp6_tbl *tbl;
+	size_t size;
+	uint32_t entries_num, i;
+
+	entries_num = max_flow_num * max_item_per_flow;
+	entries_num = RTE_MIN(entries_num, GRO_UDP6_TBL_MAX_ITEM_NUM);
+
+	if (entries_num == 0)
+		return NULL;
+
+	tbl = rte_zmalloc_socket(__func__,
+			sizeof(struct gro_udp6_tbl),
+			RTE_CACHE_LINE_SIZE,
+			socket_id);
+	if (tbl == NULL)
+		return NULL;
+
+	size = sizeof(struct gro_udp6_item) * entries_num;
+	tbl->items = rte_zmalloc_socket(__func__,
+			size,
+			RTE_CACHE_LINE_SIZE,
+			socket_id);
+	if (tbl->items == NULL) {
+		rte_free(tbl);
+		return NULL;
+	}
+	tbl->max_item_num = entries_num;
+
+	size = sizeof(struct gro_udp6_flow) * entries_num;
+	tbl->flows = rte_zmalloc_socket(__func__,
+			size,
+			RTE_CACHE_LINE_SIZE,
+			socket_id);
+	if (tbl->flows == NULL) {
+		rte_free(tbl->items);
+		rte_free(tbl);
+		return NULL;
+	}
+	/* INVALID_ARRAY_INDEX indicates an empty flow */
+	for (i = 0; i < entries_num; i++)
+		tbl->flows[i].start_index = INVALID_ARRAY_INDEX;
+	tbl->max_flow_num = entries_num;
+
+	return tbl;
+}
+
+void
+gro_udp6_tbl_destroy(void *tbl)
+{
+	struct gro_udp6_tbl *udp6_tbl = tbl;
+
+	if (udp6_tbl) {
+		rte_free(udp6_tbl->items);
+		rte_free(udp6_tbl->flows);
+	}
+	rte_free(udp6_tbl);
+}
+
+static inline uint32_t
+find_an_empty_item(struct gro_udp6_tbl *tbl)
+{
+	uint32_t i;
+	uint32_t max_item_num = tbl->max_item_num;
+
+	for (i = 0; i < max_item_num; i++)
+		if (tbl->items[i].firstseg == NULL)
+			return i;
+	return INVALID_ARRAY_INDEX;
+}
+
+static inline uint32_t
+find_an_empty_flow(struct gro_udp6_tbl *tbl)
+{
+	uint32_t i;
+	uint32_t max_flow_num = tbl->max_flow_num;
+
+	for (i = 0; i < max_flow_num; i++)
+		if (tbl->flows[i].start_index == INVALID_ARRAY_INDEX)
+			return i;
+	return INVALID_ARRAY_INDEX;
+}
+
+static inline uint32_t
+insert_new_item(struct gro_udp6_tbl *tbl,
+		struct rte_mbuf *pkt,
+		uint64_t start_time,
+		uint32_t prev_idx,
+		uint16_t frag_offset,
+		uint8_t is_last_frag)
+{
+	uint32_t item_idx;
+
+	item_idx = find_an_empty_item(tbl);
+	if (item_idx == INVALID_ARRAY_INDEX)
+		return INVALID_ARRAY_INDEX;
+
+	tbl->items[item_idx].firstseg = pkt;
+	tbl->items[item_idx].lastseg = rte_pktmbuf_lastseg(pkt);
+	tbl->items[item_idx].start_time = start_time;
+	tbl->items[item_idx].next_pkt_idx = INVALID_ARRAY_INDEX;
+	tbl->items[item_idx].frag_offset = frag_offset;
+	tbl->items[item_idx].is_last_frag = is_last_frag;
+	tbl->items[item_idx].nb_merged = 1;
+	tbl->item_num++;
+
+	/* if the previous packet exists, chain them together. */
+	if (prev_idx != INVALID_ARRAY_INDEX) {
+		tbl->items[item_idx].next_pkt_idx =
+			tbl->items[prev_idx].next_pkt_idx;
+		tbl->items[prev_idx].next_pkt_idx = item_idx;
+	}
+
+	return item_idx;
+}
+
+static inline uint32_t
+delete_item(struct gro_udp6_tbl *tbl, uint32_t item_idx,
+		uint32_t prev_item_idx)
+{
+	uint32_t next_idx = tbl->items[item_idx].next_pkt_idx;
+
+	/* NULL indicates an empty item */
+	tbl->items[item_idx].firstseg = NULL;
+	tbl->item_num--;
+	if (prev_item_idx != INVALID_ARRAY_INDEX)
+		tbl->items[prev_item_idx].next_pkt_idx = next_idx;
+
+	return next_idx;
+}
+
+/* Copy IPv6 addr */
+static inline void gro_ipv6_addr_copy(const uint8_t *ipv6_from,
+				      uint8_t *ipv6_to)
+{
+	const uint64_t *from_words = (const uint64_t *)ipv6_from;
+	uint64_t *to_words   = (uint64_t *)ipv6_to;
+
+	to_words[0] = from_words[0];
+	to_words[1] = from_words[1];
+}
+
+static inline uint32_t
+insert_new_flow(struct gro_udp6_tbl *tbl,
+		struct udp6_flow_key *src,
+		uint32_t item_idx)
+{
+	struct udp6_flow_key *dst;
+	uint32_t flow_idx;
+
+	flow_idx = find_an_empty_flow(tbl);
+	if (unlikely(flow_idx == INVALID_ARRAY_INDEX))
+		return INVALID_ARRAY_INDEX;
+
+	dst = &(tbl->flows[flow_idx].key);
+
+	rte_ether_addr_copy(&(src->eth_saddr), &(dst->eth_saddr));
+	rte_ether_addr_copy(&(src->eth_daddr), &(dst->eth_daddr));
+	gro_ipv6_addr_copy(src->ip_saddr, dst->ip_saddr);
+	gro_ipv6_addr_copy(src->ip_daddr, dst->ip_daddr);
+	dst->ip_id = src->ip_id;
+
+	tbl->flows[flow_idx].start_index = item_idx;
+	tbl->flow_num++;
+
+	return flow_idx;
+}
+
+static inline uint16_t
+get_ipv6_frag_offset(struct rte_ipv6_fragment_ext *ipv6_frag_hdr)
+{
+	return ((rte_be_to_cpu_16(ipv6_frag_hdr->frag_data) >> 3) * 8);
+}
+
+static inline uint8_t
+is_last_ipv6_frag(struct rte_ipv6_fragment_ext *ipv6_frag_hdr)
+{
+	return (rte_be_to_cpu_16(ipv6_frag_hdr->frag_data) & 0x0001);
+}
+
+/*
+ * update the packet length for the flushed packet.
+ */
+static inline void
+update_header(struct gro_udp6_item *item)
+{
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_mbuf *pkt = item->firstseg;
+	struct rte_ipv6_fragment_ext *ipv6_frag_hdr;
+	size_t fh_len = sizeof(*ipv6_frag_hdr);
+
+	ipv6_hdr = (struct rte_ipv6_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
+			pkt->l2_len);
+	/* Note: payload_len includes extension headers and upper layers
+	 * data, but l3_len also includes extension headers, so need to
+	 * add length of extension headers if they exist.
+	 */
+	ipv6_hdr->payload_len = rte_cpu_to_be_16(pkt->pkt_len -
+			pkt->l2_len - pkt->l3_len);
+
+	/* Remove fragment extension header or clear MF flag */
+	if (item->is_last_frag && (ipv6_hdr->proto == IPPROTO_FRAGMENT)) {
+		uint16_t ip_ofs;
+
+		ipv6_frag_hdr = (struct rte_ipv6_fragment_ext *)(ipv6_hdr + 1);
+		ip_ofs = get_ipv6_frag_offset(ipv6_frag_hdr);
+		if (ip_ofs == 0) {
+			ipv6_hdr->proto = ipv6_frag_hdr->next_header;
+			pkt->l3_len -= fh_len;
+
+			/* Remove IPv6 fragment extension header */
+			memmove(rte_pktmbuf_mtod_offset(pkt, char *, fh_len),
+				rte_pktmbuf_mtod(pkt, char*),
+				pkt->outer_l2_len + pkt->outer_l3_len +
+					pkt->l2_len + pkt->l3_len);
+			rte_pktmbuf_adj(pkt, fh_len);
+		} else {
+			/* clear MF flag */
+			ipv6_frag_hdr->frag_data = rte_cpu_to_be_16(
+				(rte_be_to_cpu_16(ipv6_frag_hdr->frag_data) &
+					0xFFFE));
+			ipv6_hdr->payload_len += fh_len;
+		}
+	}
+}
+
+int32_t
+gro_udp6_reassemble(struct rte_mbuf *pkt,
+		struct gro_udp6_tbl *tbl,
+		uint64_t start_time)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv6_hdr *ipv6_hdr;
+	struct rte_ipv6_fragment_ext *ipv6_frag_hdr;
+	uint16_t fh_len = sizeof(*ipv6_frag_hdr);
+	uint16_t ip_dl;
+	uint32_t ip_id;
+	uint16_t hdr_len;
+	uint16_t frag_offset = 0;
+	uint8_t is_last_frag;
+
+	struct udp6_flow_key key;
+	uint32_t cur_idx, prev_idx, item_idx;
+	uint32_t i, max_flow_num, remaining_flow_num;
+	int cmp;
+	uint8_t find;
+
+	/*
+	 * Don't process the packet whose UDP header length is not equal
+	 * to 20.
+	 */
+	if (unlikely(pkt->l4_len != UDP_HDRLEN))
+		return -1;
+
+	eth_hdr = rte_pktmbuf_mtod(pkt, struct rte_ether_hdr *);
+	ipv6_hdr = (struct rte_ipv6_hdr *)((char *)eth_hdr + pkt->l2_len);
+
+	/* Note: l3_len includes length of extension headers */
+	hdr_len = pkt->l2_len + pkt->l3_len;
+
+	/*
+	 * Don't process non-fragment packet.
+	 */
+	if (ipv6_hdr->proto != IPPROTO_FRAGMENT)
+		return -1;
+
+	/*
+	 * Don't process the packet whose payload length is less than or
+	 * equal to 0.
+	 */
+	if (pkt->pkt_len <= hdr_len)
+		return -1;
+
+	ipv6_frag_hdr = (struct rte_ipv6_fragment_ext *)(ipv6_hdr + 1);
+	ip_dl = rte_be_to_cpu_16(ipv6_hdr->payload_len) - fh_len;
+	ip_id = rte_be_to_cpu_32(ipv6_frag_hdr->id);
+	frag_offset = get_ipv6_frag_offset(ipv6_frag_hdr);
+	is_last_frag = is_last_ipv6_frag(ipv6_frag_hdr);
+
+	rte_ether_addr_copy(&(eth_hdr->s_addr), &(key.eth_saddr));
+	rte_ether_addr_copy(&(eth_hdr->d_addr), &(key.eth_daddr));
+	gro_ipv6_addr_copy(ipv6_hdr->src_addr, key.ip_saddr);
+	gro_ipv6_addr_copy(ipv6_hdr->dst_addr, key.ip_daddr);
+	key.ip_id = ip_id;
+
+	/* Search for a matched flow. */
+	max_flow_num = tbl->max_flow_num;
+	remaining_flow_num = tbl->flow_num;
+	find = 0;
+	for (i = 0; i < max_flow_num && remaining_flow_num; i++) {
+		if (tbl->flows[i].start_index != INVALID_ARRAY_INDEX) {
+			if (is_same_udp6_flow(tbl->flows[i].key, key)) {
+				find = 1;
+				break;
+			}
+			remaining_flow_num--;
+		}
+	}
+
+	/*
+	 * Fail to find a matched flow. Insert a new flow and store the
+	 * packet into the flow.
+	 */
+	if (find == 0) {
+		item_idx = insert_new_item(tbl, pkt, start_time,
+				INVALID_ARRAY_INDEX, frag_offset,
+				is_last_frag);
+		if (item_idx == INVALID_ARRAY_INDEX)
+			return -1;
+		if (insert_new_flow(tbl, &key, item_idx) ==
+				INVALID_ARRAY_INDEX) {
+			/*
+			 * Fail to insert a new flow, so delete the
+			 * stored packet.
+			 */
+			delete_item(tbl, item_idx, INVALID_ARRAY_INDEX);
+			return -1;
+		}
+		return 0;
+	}
+
+	/*
+	 * Check all packets in the flow and try to find a neighbor for
+	 * the input packet.
+	 */
+	cur_idx = tbl->flows[i].start_index;
+	prev_idx = cur_idx;
+	do {
+		cmp = udp6_check_neighbor(&(tbl->items[cur_idx]),
+				frag_offset, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp6_packets(&(tbl->items[cur_idx]),
+						pkt, cmp, frag_offset,
+						is_last_frag, 0))
+				return 1;
+			/*
+			 * Fail to merge the two packets, as the packet
+			 * length is greater than the max value. Store
+			 * the packet into the flow.
+			 */
+			if (insert_new_item(tbl, pkt, start_time, prev_idx,
+						frag_offset, is_last_frag) ==
+					INVALID_ARRAY_INDEX)
+				return -1;
+			return 0;
+		}
+
+		/* Ensure inserted items are ordered by frag_offset */
+		if (frag_offset
+			< tbl->items[cur_idx].frag_offset) {
+			break;
+		}
+
+		prev_idx = cur_idx;
+		cur_idx = tbl->items[cur_idx].next_pkt_idx;
+	} while (cur_idx != INVALID_ARRAY_INDEX);
+
+	/* Fail to find a neighbor, so store the packet into the flow. */
+	if (cur_idx == tbl->flows[i].start_index) {
+		/* Insert it before the first packet of the flow */
+		item_idx = insert_new_item(tbl, pkt, start_time,
+				INVALID_ARRAY_INDEX, frag_offset,
+				is_last_frag);
+		if (item_idx == INVALID_ARRAY_INDEX)
+			return -1;
+		tbl->items[item_idx].next_pkt_idx = cur_idx;
+		tbl->flows[i].start_index = item_idx;
+	} else {
+		if (insert_new_item(tbl, pkt, start_time, prev_idx,
+			frag_offset, is_last_frag) == INVALID_ARRAY_INDEX)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int
+gro_udp6_merge_items(struct gro_udp6_tbl *tbl,
+			   uint32_t start_idx)
+{
+	uint16_t frag_offset;
+	uint8_t is_last_frag;
+	int16_t ip_dl;
+	struct rte_mbuf *pkt;
+	int cmp;
+	uint32_t item_idx;
+	uint16_t hdr_len;
+
+	item_idx = tbl->items[start_idx].next_pkt_idx;
+	while (item_idx != INVALID_ARRAY_INDEX) {
+		pkt = tbl->items[item_idx].firstseg;
+		hdr_len = pkt->outer_l2_len + pkt->outer_l3_len + pkt->l2_len +
+			pkt->l3_len;
+		ip_dl = pkt->pkt_len - hdr_len;
+		frag_offset = tbl->items[item_idx].frag_offset;
+		is_last_frag = tbl->items[item_idx].is_last_frag;
+		cmp = udp6_check_neighbor(&(tbl->items[start_idx]),
+					frag_offset, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp6_packets(
+					&(tbl->items[start_idx]),
+					pkt, cmp, frag_offset,
+					is_last_frag, 0)) {
+				item_idx = delete_item(tbl, item_idx,
+							INVALID_ARRAY_INDEX);
+				tbl->items[start_idx].next_pkt_idx
+					= item_idx;
+			} else {
+				return 0;
+			}
+		} else {
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+uint16_t
+gro_udp6_tbl_timeout_flush(struct gro_udp6_tbl *tbl,
+		uint64_t flush_timestamp,
+		struct rte_mbuf **out,
+		uint16_t nb_out)
+{
+	uint16_t k = 0;
+	uint32_t i, j;
+	uint32_t max_flow_num = tbl->max_flow_num;
+
+	for (i = 0; i < max_flow_num; i++) {
+		if (unlikely(tbl->flow_num == 0))
+			return k;
+
+		j = tbl->flows[i].start_index;
+		while (j != INVALID_ARRAY_INDEX) {
+			if (tbl->items[j].start_time <= flush_timestamp) {
+				gro_udp6_merge_items(tbl, j);
+				out[k++] = tbl->items[j].firstseg;
+				if (tbl->items[j].nb_merged > 1)
+					update_header(&(tbl->items[j]));
+				/*
+				 * Delete the packet and get the next
+				 * packet in the flow.
+				 */
+				j = delete_item(tbl, j, INVALID_ARRAY_INDEX);
+				tbl->flows[i].start_index = j;
+				if (j == INVALID_ARRAY_INDEX)
+					tbl->flow_num--;
+
+				if (unlikely(k == nb_out))
+					return k;
+			} else
+				/*
+				 * The left packets in this flow won't be
+				 * timeout. Go to check other flows.
+				 */
+				break;
+		}
+	}
+	return k;
+}
+
+uint32_t
+gro_udp6_tbl_pkt_count(void *tbl)
+{
+	struct gro_udp6_tbl *gro_tbl = tbl;
+
+	if (gro_tbl)
+		return gro_tbl->item_num;
+
+	return 0;
+}
diff --git a/lib/librte_gro/gro_udp6.h b/lib/librte_gro/gro_udp6.h
new file mode 100644
index 0000000..92696e4
--- /dev/null
+++ b/lib/librte_gro/gro_udp6.h
@@ -0,0 +1,284 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2021 Inspur Corporation
+ */
+
+#ifndef _GRO_UDP6_H_
+#define _GRO_UDP6_H_
+
+#include <rte_ip.h>
+#include <rte_udp.h>
+#include <rte_vxlan.h>
+
+#define INVALID_ARRAY_INDEX 0xffffffffUL
+#define GRO_UDP6_TBL_MAX_ITEM_NUM (1024UL * 1024UL)
+
+/*
+ * The max length of a IPv6 packet, which includes the length of the L3
+ * header, the L4 header and the data payload.
+ */
+#define MAX_IPV6_PKT_LENGTH UINT16_MAX
+
+#define UDP_HDRLEN 8
+
+/* Header fields representing a UDP/IPv6 flow */
+struct udp6_flow_key {
+	struct rte_ether_addr eth_saddr;
+	struct rte_ether_addr eth_daddr;
+	uint8_t ip_saddr[16];
+	uint8_t ip_daddr[16];
+
+	/* IP fragment for UDP does not contain UDP header
+	 * except the first one. But IP ID must be same.
+	 * ip_id of fragment is 32 bit for IPv6
+	 */
+	uint32_t ip_id;
+};
+
+struct gro_udp6_flow {
+	struct udp6_flow_key key;
+	/*
+	 * The index of the first packet in the flow.
+	 * INVALID_ARRAY_INDEX indicates an empty flow.
+	 */
+	uint32_t start_index;
+};
+
+struct gro_udp6_item {
+	/*
+	 * The first MBUF segment of the packet. If the value
+	 * is NULL, it means the item is empty.
+	 */
+	struct rte_mbuf *firstseg;
+	/* The last MBUF segment of the packet */
+	struct rte_mbuf *lastseg;
+	/*
+	 * The time when the first packet is inserted into the table.
+	 * This value won't be updated, even if the packet is merged
+	 * with other packets.
+	 */
+	uint64_t start_time;
+	/*
+	 * next_pkt_idx is used to chain the packets that
+	 * are in the same flow but can't be merged together
+	 * (e.g. caused by packet reordering).
+	 */
+	uint32_t next_pkt_idx;
+	/* offset of IP fragment packet */
+	uint16_t frag_offset;
+	/* is last IP fragment? */
+	uint8_t is_last_frag;
+	/* the number of merged packets */
+	uint16_t nb_merged;
+};
+
+/*
+ * UDP/IPv6 reassembly table structure.
+ */
+struct gro_udp6_tbl {
+	/* item array */
+	struct gro_udp6_item *items;
+	/* flow array */
+	struct gro_udp6_flow *flows;
+	/* current item number */
+	uint32_t item_num;
+	/* current flow num */
+	uint32_t flow_num;
+	/* item array size */
+	uint32_t max_item_num;
+	/* flow array size */
+	uint32_t max_flow_num;
+};
+
+/**
+ * This function creates a UDP/IPv6 reassembly table.
+ *
+ * @param socket_id
+ *  Socket index for allocating the UDP/IPv6 reassemble table
+ * @param max_flow_num
+ *  The maximum number of flows in the UDP/IPv6 GRO table
+ * @param max_item_per_flow
+ *  The maximum number of packets per flow
+ *
+ * @return
+ *  - Return the table pointer on success.
+ *  - Return NULL on failure.
+ */
+void *gro_udp6_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow);
+
+/**
+ * This function destroys a UDP/IPv6 reassembly table.
+ *
+ * @param tbl
+ *  Pointer pointing to the UDP/IPv6 reassembly table.
+ */
+void gro_udp6_tbl_destroy(void *tbl);
+
+/**
+ * This function merges a UDP/IPv6 packet.
+ *
+ * This function does not check if the packet has correct checksums and
+ * does not re-calculate checksums for the merged packet. It returns the
+ * packet if it isn't UDP fragment or there is no available space in
+ * the table.
+ *
+ * @param pkt
+ *  Packet to reassemble
+ * @param tbl
+ *  Pointer pointing to the UDP/IPv6 reassembly table
+ * @start_time
+ *  The time when the packet is inserted into the table
+ *
+ * @return
+ *  - Return a positive value if the packet is merged.
+ *  - Return zero if the packet isn't merged but stored in the table.
+ *  - Return a negative value for invalid parameters or no available
+ *    space in the table.
+ */
+int32_t gro_udp6_reassemble(struct rte_mbuf *pkt,
+		struct gro_udp6_tbl *tbl,
+		uint64_t start_time);
+
+/**
+ * This function flushes timeout packets in a UDP/IPv6 reassembly table,
+ * and without updating checksums.
+ *
+ * @param tbl
+ *  UDP/IPv6 reassembly table pointer
+ * @param flush_timestamp
+ *  Flush packets which are inserted into the table before or at the
+ *  flush_timestamp.
+ * @param out
+ *  Pointer array used to keep flushed packets
+ * @param nb_out
+ *  The element number in 'out'. It also determines the maximum number of
+ *  packets that can be flushed finally.
+ *
+ * @return
+ *  The number of flushed packets
+ */
+uint16_t gro_udp6_tbl_timeout_flush(struct gro_udp6_tbl *tbl,
+		uint64_t flush_timestamp,
+		struct rte_mbuf **out,
+		uint16_t nb_out);
+
+/**
+ * This function returns the number of the packets in a UDP/IPv6
+ * reassembly table.
+ *
+ * @param tbl
+ *  UDP/IPv6 reassembly table pointer
+ *
+ * @return
+ *  The number of packets in the table
+ */
+uint32_t gro_udp6_tbl_pkt_count(void *tbl);
+
+#ifndef _GRO_TCP6_H_
+static inline int rte_is_same_ipv6_addr(const uint8_t *ipv6_a1,
+					const uint8_t *ipv6_a2)
+{
+	const uint64_t *w1 = (const uint64_t *)ipv6_a1;
+	const uint64_t *w2 = (const uint64_t *)ipv6_a2;
+
+	return ((w1[0] ^ w2[0]) | (w1[1] ^ w2[1])) == 0;
+}
+#endif
+
+/*
+ * Check if two UDP/IPv6 packets belong to the same flow.
+ */
+static inline int
+is_same_udp6_flow(struct udp6_flow_key k1, struct udp6_flow_key k2)
+{
+	return (rte_is_same_ether_addr(&k1.eth_saddr, &k2.eth_saddr) &&
+			rte_is_same_ether_addr(&k1.eth_daddr, &k2.eth_daddr) &&
+			rte_is_same_ipv6_addr(k1.ip_saddr, k2.ip_saddr) &&
+			rte_is_same_ipv6_addr(k1.ip_daddr, k2.ip_daddr) &&
+			(k1.ip_id == k2.ip_id));
+}
+
+/*
+ * Merge two UDP/IPv6 packets without updating checksums.
+ * If cmp is larger than 0, append the new packet to the
+ * original packet. Otherwise, pre-pend the new packet to
+ * the original packet.
+ */
+static inline int
+merge_two_udp6_packets(struct gro_udp6_item *item,
+		struct rte_mbuf *pkt,
+		int cmp,
+		uint16_t frag_offset,
+		uint8_t is_last_frag,
+		uint16_t l2_offset)
+{
+	struct rte_mbuf *pkt_head, *pkt_tail, *lastseg;
+	uint16_t hdr_len, l2_len;
+	uint32_t ip_len;
+
+	if (cmp > 0) {
+		pkt_head = item->firstseg;
+		pkt_tail = pkt;
+	} else {
+		pkt_head = pkt;
+		pkt_tail = item->firstseg;
+	}
+
+	/* check if the IPv6 packet length is greater than the max value */
+	hdr_len = l2_offset + pkt_head->l2_len + pkt_head->l3_len;
+	l2_len = l2_offset > 0 ? pkt_head->outer_l2_len : pkt_head->l2_len;
+	ip_len = pkt_head->pkt_len - l2_len
+		 + pkt_tail->pkt_len - hdr_len;
+	if (unlikely(ip_len > MAX_IPV6_PKT_LENGTH))
+		return 0;
+
+	/* remove the packet header for the tail packet */
+	rte_pktmbuf_adj(pkt_tail, hdr_len);
+
+	/* chain two packets together */
+	if (cmp > 0) {
+		item->lastseg->next = pkt;
+		item->lastseg = rte_pktmbuf_lastseg(pkt);
+	} else {
+		lastseg = rte_pktmbuf_lastseg(pkt);
+		lastseg->next = item->firstseg;
+		item->firstseg = pkt;
+		item->frag_offset = frag_offset;
+	}
+	item->nb_merged++;
+	if (is_last_frag)
+		item->is_last_frag = is_last_frag;
+
+	/* update MBUF metadata for the merged packet */
+	pkt_head->nb_segs += pkt_tail->nb_segs;
+	pkt_head->pkt_len += pkt_tail->pkt_len;
+
+	return 1;
+}
+
+/*
+ * Check if two UDP/IPv6 packets are neighbors.
+ */
+static inline int
+udp6_check_neighbor(struct gro_udp6_item *item,
+		uint16_t frag_offset,
+		uint16_t ip_dl,
+		uint16_t l2_offset)
+{
+	struct rte_mbuf *pkt_orig = item->firstseg;
+	uint16_t len;
+
+	/* check if the two packets are neighbors */
+	len = pkt_orig->pkt_len - l2_offset - pkt_orig->l2_len -
+		pkt_orig->l3_len;
+	if (frag_offset == item->frag_offset + len)
+		/* append the new packet */
+		return 1;
+	else if (frag_offset + ip_dl == item->frag_offset)
+		/* pre-pend the new packet */
+		return -1;
+
+	return 0;
+}
+#endif
diff --git a/lib/librte_gro/meson.build b/lib/librte_gro/meson.build
index 3eff89c..7939081 100644
--- a/lib/librte_gro/meson.build
+++ b/lib/librte_gro/meson.build
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: BSD-3-Clause
 # Copyright(c) 2017 Intel Corporation
 
-sources = files('rte_gro.c', 'gro_tcp4.c', 'gro_udp4.c', 'gro_vxlan_tcp4.c', 'gro_vxlan_udp4.c', 'gro_tcp6.c', 'gro_vxlan_tcp6.c', 'gro_vxlan6_tcp4.c', 'gro_vxlan6_tcp6.c')
+sources = files('rte_gro.c', 'gro_tcp4.c', 'gro_udp4.c', 'gro_vxlan_tcp4.c', 'gro_vxlan_udp4.c', 'gro_tcp6.c', 'gro_vxlan_tcp6.c', 'gro_vxlan6_tcp4.c', 'gro_vxlan6_tcp6.c', 'gro_udp6.c')
 headers = files('rte_gro.h')
 deps += ['ethdev']
diff --git a/lib/librte_gro/rte_gro.c b/lib/librte_gro/rte_gro.c
index 0c5584e..13b38cc 100644
--- a/lib/librte_gro/rte_gro.c
+++ b/lib/librte_gro/rte_gro.c
@@ -11,6 +11,7 @@
 #include "gro_tcp4.h"
 #include "gro_tcp6.h"
 #include "gro_udp4.h"
+#include "gro_udp6.h"
 #include "gro_vxlan6_tcp4.h"
 #include "gro_vxlan6_tcp6.h"
 #include "gro_vxlan_tcp4.h"
@@ -28,21 +29,21 @@
 		gro_udp4_tbl_create, gro_vxlan_udp4_tbl_create,
 		gro_tcp6_tbl_create, gro_vxlan_tcp6_tbl_create,
 		gro_vxlan6_tcp4_tbl_create, gro_vxlan6_tcp6_tbl_create,
-		NULL};
+		gro_udp6_tbl_create, NULL};
 static gro_tbl_destroy_fn tbl_destroy_fn[RTE_GRO_TYPE_MAX_NUM] = {
 			gro_tcp4_tbl_destroy, gro_vxlan_tcp4_tbl_destroy,
 			gro_udp4_tbl_destroy, gro_vxlan_udp4_tbl_destroy,
 			gro_tcp6_tbl_destroy, gro_vxlan_tcp6_tbl_destroy,
 			gro_vxlan6_tcp4_tbl_destroy,
 			gro_vxlan6_tcp6_tbl_destroy,
-			NULL};
+			gro_udp6_tbl_destroy, NULL};
 static gro_tbl_pkt_count_fn tbl_pkt_count_fn[RTE_GRO_TYPE_MAX_NUM] = {
 			gro_tcp4_tbl_pkt_count, gro_vxlan_tcp4_tbl_pkt_count,
 			gro_udp4_tbl_pkt_count, gro_vxlan_udp4_tbl_pkt_count,
 			gro_tcp6_tbl_pkt_count, gro_vxlan_tcp6_tbl_pkt_count,
 			gro_vxlan6_tcp4_tbl_pkt_count,
 			gro_vxlan6_tcp6_tbl_pkt_count,
-			NULL};
+			gro_udp6_tbl_pkt_count, NULL};
 
 #define IS_IPV4_TCP_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
 		((ptype & RTE_PTYPE_L4_TCP) == RTE_PTYPE_L4_TCP) && \
@@ -121,6 +122,10 @@
 		 ((ptype & RTE_PTYPE_INNER_L3_MASK) == \
 		  RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN)))
 
+#define IS_IPV6_UDP_PKT(ptype) (RTE_ETH_IS_IPV6_HDR(ptype) && \
+		((ptype & RTE_PTYPE_L4_UDP) == RTE_PTYPE_L4_UDP) && \
+		(RTE_ETH_IS_TUNNEL_PKT(ptype) == 0))
+
 /*
  * GRO context structure. It keeps the table structures, which are
  * used to merge packets, for different GRO types. Before using
@@ -246,13 +251,19 @@ struct gro_ctx {
 	struct gro_vxlan6_tcp6_item
 		vxlan6_tcp6_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{{0}} };
 
+	/* allocate a reassembly table for UDP/IPv6 GRO */
+	struct gro_udp6_tbl udp6_tbl;
+	struct gro_udp6_flow udp6_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
+	struct gro_udp6_item udp6_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{0} };
+
 	struct rte_mbuf *unprocess_pkts[nb_pkts];
 	uint32_t item_num;
 	int32_t ret;
 	uint16_t i, unprocess_num = 0, nb_after_gro = nb_pkts;
 	uint8_t do_tcp4_gro = 0, do_vxlan_tcp_gro = 0, do_udp4_gro = 0,
 		do_vxlan_udp_gro = 0, do_tcp6_gro = 0, do_vxlan_tcp6_gro = 0,
-		do_vxlan6_tcp4_gro = 0, do_vxlan6_tcp6_gro = 0;
+		do_vxlan6_tcp4_gro = 0, do_vxlan6_tcp6_gro = 0,
+		do_udp6_gro = 0;
 
 	if (unlikely((param->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
 					RTE_GRO_TCP_IPV4 |
@@ -261,7 +272,8 @@ struct gro_ctx {
 					RTE_GRO_TCP_IPV6 |
 					RTE_GRO_IPV4_VXLAN_TCP_IPV6 |
 					RTE_GRO_IPV6_VXLAN_TCP_IPV4 |
-					RTE_GRO_IPV6_VXLAN_TCP_IPV6)) == 0))
+					RTE_GRO_IPV6_VXLAN_TCP_IPV6 |
+					RTE_GRO_UDP_IPV6)) == 0))
 		return nb_pkts;
 
 	/* Get the maximum number of packets */
@@ -373,6 +385,19 @@ struct gro_ctx {
 		do_vxlan6_tcp6_gro = 1;
 	}
 
+	if (param->gro_types & RTE_GRO_UDP_IPV6) {
+		for (i = 0; i < item_num; i++)
+			udp6_flows[i].start_index = INVALID_ARRAY_INDEX;
+
+		udp6_tbl.flows = udp6_flows;
+		udp6_tbl.items = udp6_items;
+		udp6_tbl.flow_num = 0;
+		udp6_tbl.item_num = 0;
+		udp6_tbl.max_flow_num = item_num;
+		udp6_tbl.max_item_num = item_num;
+		do_udp6_gro = 1;
+	}
+
 	for (i = 0; i < nb_pkts; i++) {
 		/*
 		 * The timestamp is ignored, since all packets
@@ -447,6 +472,14 @@ struct gro_ctx {
 				nb_after_gro--;
 			else if (ret < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV6_UDP_PKT(pkts[i]->packet_type) &&
+				do_udp6_gro) {
+			ret = gro_udp6_reassemble(pkts[i], &udp6_tbl, 0);
+			if (ret > 0)
+				/* merge successfully */
+				nb_after_gro--;
+			else if (ret < 0)
+				unprocess_pkts[unprocess_num++] = pkts[i];
 		} else
 			unprocess_pkts[unprocess_num++] = pkts[i];
 	}
@@ -496,6 +529,11 @@ struct gro_ctx {
 					0, &pkts[i], nb_pkts - i);
 		}
 
+		if (do_udp6_gro) {
+			i += gro_udp6_tbl_timeout_flush(&udp6_tbl, 0,
+					&pkts[i], nb_pkts - i);
+		}
+
 		/* Copy unprocessed packets */
 		if (unprocess_num > 0) {
 			memcpy(&pkts[i], unprocess_pkts,
@@ -516,12 +554,13 @@ struct gro_ctx {
 	struct rte_mbuf *unprocess_pkts[nb_pkts];
 	struct gro_ctx *gro_ctx = ctx;
 	void *tcp_tbl, *udp_tbl, *vxlan_tcp_tbl, *vxlan_udp_tbl, *tcp6_tbl,
-		*vxlan_tcp6_tbl, *vxlan6_tcp4_tbl, *vxlan6_tcp6_tbl;
+		*vxlan_tcp6_tbl, *vxlan6_tcp4_tbl, *vxlan6_tcp6_tbl,
+		*udp6_tbl;
 	uint64_t current_time;
 	uint16_t i, unprocess_num = 0;
 	uint8_t do_tcp4_gro, do_vxlan_tcp_gro, do_udp4_gro, do_vxlan_udp_gro,
 		do_tcp6_gro, do_vxlan_tcp6_gro, do_vxlan6_tcp4_gro,
-		do_vxlan6_tcp6_gro;
+		do_vxlan6_tcp6_gro, do_udp6_gro;
 
 	if (unlikely((gro_ctx->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
 					RTE_GRO_TCP_IPV4 |
@@ -530,7 +569,8 @@ struct gro_ctx {
 					RTE_GRO_TCP_IPV6 |
 					RTE_GRO_IPV4_VXLAN_TCP_IPV6 |
 					RTE_GRO_IPV6_VXLAN_TCP_IPV4 |
-					RTE_GRO_IPV6_VXLAN_TCP_IPV6)) == 0))
+					RTE_GRO_IPV6_VXLAN_TCP_IPV6 |
+					RTE_GRO_UDP_IPV6)) == 0))
 		return nb_pkts;
 
 	tcp_tbl = gro_ctx->tbls[RTE_GRO_TCP_IPV4_INDEX];
@@ -541,6 +581,7 @@ struct gro_ctx {
 	vxlan_tcp6_tbl = gro_ctx->tbls[RTE_GRO_IPV4_VXLAN_TCP_IPV6_INDEX];
 	vxlan6_tcp4_tbl = gro_ctx->tbls[RTE_GRO_IPV6_VXLAN_TCP_IPV4_INDEX];
 	vxlan6_tcp6_tbl = gro_ctx->tbls[RTE_GRO_IPV6_VXLAN_TCP_IPV6_INDEX];
+	udp6_tbl = gro_ctx->tbls[RTE_GRO_UDP_IPV6_INDEX];
 
 	do_tcp4_gro = (gro_ctx->gro_types & RTE_GRO_TCP_IPV4) ==
 		RTE_GRO_TCP_IPV4;
@@ -558,6 +599,8 @@ struct gro_ctx {
 				== RTE_GRO_IPV6_VXLAN_TCP_IPV4;
 	do_vxlan6_tcp6_gro = (gro_ctx->gro_types & RTE_GRO_IPV6_VXLAN_TCP_IPV6)
 				== RTE_GRO_IPV6_VXLAN_TCP_IPV6;
+	do_udp6_gro = (gro_ctx->gro_types & RTE_GRO_UDP_IPV6) ==
+		RTE_GRO_UDP_IPV6;
 
 	current_time = rte_rdtsc();
 
@@ -602,6 +645,11 @@ struct gro_ctx {
 			if (gro_vxlan6_tcp6_reassemble(pkts[i], vxlan6_tcp6_tbl,
 						current_time) < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV6_UDP_PKT(pkts[i]->packet_type) &&
+				do_udp6_gro) {
+			if (gro_udp6_reassemble(pkts[i], udp6_tbl,
+						current_time) < 0)
+				unprocess_pkts[unprocess_num++] = pkts[i];
 		} else
 			unprocess_pkts[unprocess_num++] = pkts[i];
 	}
@@ -685,6 +733,14 @@ struct gro_ctx {
 		num += gro_vxlan6_tcp6_tbl_timeout_flush(gro_ctx->tbls[
 				RTE_GRO_IPV6_VXLAN_TCP_IPV6_INDEX],
 				flush_timestamp, &out[num], left_nb_out);
+		left_nb_out = max_nb_out - num;
+	}
+
+	if ((gro_types & RTE_GRO_UDP_IPV6) && left_nb_out > 0) {
+		num += gro_udp6_tbl_timeout_flush(
+				gro_ctx->tbls[RTE_GRO_UDP_IPV6_INDEX],
+				flush_timestamp,
+				&out[num], left_nb_out);
 	}
 
 	return num;
diff --git a/lib/librte_gro/rte_gro.h b/lib/librte_gro/rte_gro.h
index cb0895f..94ed3d3 100644
--- a/lib/librte_gro/rte_gro.h
+++ b/lib/librte_gro/rte_gro.h
@@ -50,6 +50,9 @@
 #define RTE_GRO_IPV6_VXLAN_TCP_IPV6_INDEX 7
 #define RTE_GRO_IPV6_VXLAN_TCP_IPV6 (1ULL << RTE_GRO_IPV6_VXLAN_TCP_IPV6_INDEX)
 /**< IPv6 VxLAN TCP/IPv6 GRO flag. */
+#define RTE_GRO_UDP_IPV6_INDEX 8
+#define RTE_GRO_UDP_IPV6 (1ULL << RTE_GRO_UDP_IPV6_INDEX)
+/**< UDP/IPv6 GRO flag */
 
 /**
  * Structure used to create GRO context objects or used to pass
-- 
1.8.3.1