diff mbox series

[V3,2/2] gro: add VXLAN UDP GRO support

Message ID 20200902092643.49924-3-yang_y_yi@163.com (mailing list archive)
State Superseded, archived
Delegated to: Ferruh Yigit
Headers show
Series gro: add UDP GRO and VXLAN UDP GRO support | expand

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation success Compilation OK
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-testing success Testing PASS
ci/iol-intel-Performance success Performance Testing PASS
ci/travis-robot success Travis build: passed
ci/iol-intel-Functional success Functional Testing PASS
ci/iol-broadcom-Performance success Performance Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS

Commit Message

yang_y_yi Sept. 2, 2020, 9:26 a.m. UTC
From: Yi Yang <yangyi01@inspur.com>

VXLAN UDP GRO can help improve VM-to-VM UDP performance
when VM is enabled UFO or GSO, GRO must be supported if
GSO or UFO is enabled, otherwise, performance gain will
be hurt.

With this enabled in DPDK, OVS DPDK can leverage it to
improve VM-to-VM UDP performance, this will make sure
IP fragments will be reassembled once it is received
from physical NIC. It is very helpful in OVS DPDK VXLAN
TSO case.

Signed-off-by: Yi Yang <yangyi01@inspur.com>
---
 lib/librte_gro/Makefile         |   1 +
 lib/librte_gro/gro_vxlan_udp4.c | 556 ++++++++++++++++++++++++++++++++++++++++
 lib/librte_gro/gro_vxlan_udp4.h | 152 +++++++++++
 lib/librte_gro/meson.build      |   2 +-
 lib/librte_gro/rte_gro.c        |  75 +++++-
 lib/librte_gro/rte_gro.h        |   3 +
 6 files changed, 782 insertions(+), 7 deletions(-)
 create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
 create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
diff mbox series

Patch

diff --git a/lib/librte_gro/Makefile b/lib/librte_gro/Makefile
index 41ec29e..30dd8c7 100644
--- a/lib/librte_gro/Makefile
+++ b/lib/librte_gro/Makefile
@@ -17,6 +17,7 @@  SRCS-$(CONFIG_RTE_LIBRTE_GRO) += rte_gro.c
 SRCS-$(CONFIG_RTE_LIBRTE_GRO) += gro_tcp4.c
 SRCS-$(CONFIG_RTE_LIBRTE_GRO) += gro_udp4.c
 SRCS-$(CONFIG_RTE_LIBRTE_GRO) += gro_vxlan_tcp4.c
+SRCS-$(CONFIG_RTE_LIBRTE_GRO) += gro_vxlan_udp4.c
 
 # install this header file
 SYMLINK-$(CONFIG_RTE_LIBRTE_GRO)-include += rte_gro.h
diff --git a/lib/librte_gro/gro_vxlan_udp4.c b/lib/librte_gro/gro_vxlan_udp4.c
new file mode 100644
index 0000000..a66eaf0
--- /dev/null
+++ b/lib/librte_gro/gro_vxlan_udp4.c
@@ -0,0 +1,556 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Inspur Corporation
+ */
+
+#include <rte_malloc.h>
+#include <rte_mbuf.h>
+#include <rte_cycles.h>
+#include <rte_ethdev.h>
+#include <rte_udp.h>
+
+#include "gro_vxlan_udp4.h"
+
+void *
+gro_vxlan_udp4_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow)
+{
+	struct gro_vxlan_udp4_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_VXLAN_UDP4_TBL_MAX_ITEM_NUM);
+
+	if (entries_num == 0)
+		return NULL;
+
+	tbl = rte_zmalloc_socket(__func__,
+			sizeof(struct gro_vxlan_udp4_tbl),
+			RTE_CACHE_LINE_SIZE,
+			socket_id);
+	if (tbl == NULL)
+		return NULL;
+
+	size = sizeof(struct gro_vxlan_udp4_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_vxlan_udp4_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;
+	}
+
+	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_vxlan_udp4_tbl_destroy(void *tbl)
+{
+	struct gro_vxlan_udp4_tbl *vxlan_tbl = tbl;
+
+	if (vxlan_tbl) {
+		rte_free(vxlan_tbl->items);
+		rte_free(vxlan_tbl->flows);
+	}
+	rte_free(vxlan_tbl);
+}
+
+static inline uint32_t
+find_an_empty_item(struct gro_vxlan_udp4_tbl *tbl)
+{
+	uint32_t max_item_num = tbl->max_item_num, i;
+
+	for (i = 0; i < max_item_num; i++)
+		if (tbl->items[i].inner_item.firstseg == NULL)
+			return i;
+	return INVALID_ARRAY_INDEX;
+}
+
+static inline uint32_t
+find_an_empty_flow(struct gro_vxlan_udp4_tbl *tbl)
+{
+	uint32_t max_flow_num = tbl->max_flow_num, i;
+
+	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_vxlan_udp4_tbl *tbl,
+		struct rte_mbuf *pkt,
+		uint64_t start_time,
+		uint32_t prev_idx,
+		uint16_t frag_offset,
+		uint8_t is_last_frag,
+		uint16_t outer_ip_id,
+		uint16_t ip_id,
+		uint8_t outer_is_atomic)
+{
+	uint32_t item_idx;
+
+	item_idx = find_an_empty_item(tbl);
+	if (unlikely(item_idx == INVALID_ARRAY_INDEX))
+		return INVALID_ARRAY_INDEX;
+
+	tbl->items[item_idx].inner_item.firstseg = pkt;
+	tbl->items[item_idx].inner_item.lastseg = rte_pktmbuf_lastseg(pkt);
+	tbl->items[item_idx].inner_item.start_time = start_time;
+	tbl->items[item_idx].inner_item.next_pkt_idx = INVALID_ARRAY_INDEX;
+	tbl->items[item_idx].inner_item.frag_offset = frag_offset;
+	tbl->items[item_idx].inner_item.is_last_frag = is_last_frag;
+	tbl->items[item_idx].inner_item.ip_id = ip_id;
+	tbl->items[item_idx].inner_item.nb_merged = 1;
+	tbl->items[item_idx].outer_ip_id = outer_ip_id;
+	tbl->items[item_idx].outer_is_atomic = outer_is_atomic;
+	tbl->item_num++;
+
+	/* If the previous packet exists, chain the new one with it. */
+	if (prev_idx != INVALID_ARRAY_INDEX) {
+		tbl->items[item_idx].inner_item.next_pkt_idx =
+			tbl->items[prev_idx].inner_item.next_pkt_idx;
+		tbl->items[prev_idx].inner_item.next_pkt_idx = item_idx;
+	}
+
+	return item_idx;
+}
+
+static inline uint32_t
+delete_item(struct gro_vxlan_udp4_tbl *tbl,
+		uint32_t item_idx,
+		uint32_t prev_item_idx)
+{
+	uint32_t next_idx = tbl->items[item_idx].inner_item.next_pkt_idx;
+
+	/* NULL indicates an empty item. */
+	tbl->items[item_idx].inner_item.firstseg = NULL;
+	tbl->item_num--;
+	if (prev_item_idx != INVALID_ARRAY_INDEX)
+		tbl->items[prev_item_idx].inner_item.next_pkt_idx = next_idx;
+
+	return next_idx;
+}
+
+static inline uint32_t
+insert_new_flow(struct gro_vxlan_udp4_tbl *tbl,
+		struct vxlan_udp4_flow_key *src,
+		uint32_t item_idx)
+{
+	struct vxlan_udp4_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->inner_key.eth_saddr),
+			&(dst->inner_key.eth_saddr));
+	rte_ether_addr_copy(&(src->inner_key.eth_daddr),
+			&(dst->inner_key.eth_daddr));
+	dst->inner_key.ip_src_addr = src->inner_key.ip_src_addr;
+	dst->inner_key.ip_dst_addr = src->inner_key.ip_dst_addr;
+	dst->inner_key.ip_id = src->inner_key.ip_id;
+
+	dst->vxlan_hdr.vx_flags = src->vxlan_hdr.vx_flags;
+	dst->vxlan_hdr.vx_vni = src->vxlan_hdr.vx_vni;
+	rte_ether_addr_copy(&(src->outer_eth_saddr), &(dst->outer_eth_saddr));
+	rte_ether_addr_copy(&(src->outer_eth_daddr), &(dst->outer_eth_daddr));
+	dst->outer_ip_src_addr = src->outer_ip_src_addr;
+	dst->outer_ip_dst_addr = src->outer_ip_dst_addr;
+	dst->outer_src_port = src->outer_src_port;
+	dst->outer_dst_port = src->outer_dst_port;
+
+	tbl->flows[flow_idx].start_index = item_idx;
+	tbl->flow_num++;
+
+	return flow_idx;
+}
+
+static inline int
+is_same_vxlan_udp4_flow(struct vxlan_udp4_flow_key k1,
+		struct vxlan_udp4_flow_key k2)
+{
+	/* src port is changing, so shouldn't use it for flow check */
+	return (rte_is_same_ether_addr(&k1.outer_eth_saddr,
+					&k2.outer_eth_saddr) &&
+			rte_is_same_ether_addr(&k1.outer_eth_daddr,
+				&k2.outer_eth_daddr) &&
+			(k1.outer_ip_src_addr == k2.outer_ip_src_addr) &&
+			(k1.outer_ip_dst_addr == k2.outer_ip_dst_addr) &&
+			(k1.outer_dst_port == k2.outer_dst_port) &&
+			(k1.vxlan_hdr.vx_flags == k2.vxlan_hdr.vx_flags) &&
+			(k1.vxlan_hdr.vx_vni == k2.vxlan_hdr.vx_vni) &&
+			is_same_udp4_flow(k1.inner_key, k2.inner_key));
+}
+
+static inline int
+udp_check_vxlan_neighbor(struct gro_vxlan_udp4_item *item,
+		uint16_t frag_offset,
+		uint16_t ip_id,
+		uint16_t ip_dl)
+{
+	struct rte_mbuf *pkt = item->inner_item.firstseg;
+	int cmp;
+	uint16_t l2_offset;
+	int ret = 0;
+
+	l2_offset = pkt->outer_l2_len + pkt->outer_l3_len;
+	cmp = udp_check_neighbor(&item->inner_item, frag_offset, ip_id,
+			ip_dl, l2_offset);
+	/* VXLAN outer IP ID is out of order, so don't touch it and
+	 * don't compare it.
+	 */
+	if (cmp > 0)
+		/* Append the new packet. */
+		ret = 1;
+	else if (cmp < 0)
+		/* Prepend the new packet. */
+		ret = -1;
+
+	return ret;
+}
+
+static inline int
+merge_two_vxlan_udp4_packets(struct gro_vxlan_udp4_item *item,
+		struct rte_mbuf *pkt,
+		int cmp,
+		uint16_t frag_offset,
+		uint8_t is_last_frag,
+		uint16_t ip_id)
+{
+	if (merge_two_udp4_packets(&item->inner_item, pkt, cmp, frag_offset,
+				is_last_frag, ip_id,
+				pkt->outer_l2_len + pkt->outer_l3_len)) {
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void
+update_vxlan_header(struct gro_vxlan_udp4_item *item)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_udp_hdr *udp_hdr;
+	struct rte_mbuf *pkt = item->inner_item.firstseg;
+	uint16_t len;
+	uint16_t frag_offset;
+
+	/* Update the outer IPv4 header. */
+	len = pkt->pkt_len - pkt->outer_l2_len;
+	ipv4_hdr = (struct rte_ipv4_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
+			pkt->outer_l2_len);
+	ipv4_hdr->total_length = rte_cpu_to_be_16(len);
+
+	/* Update the outer UDP header. */
+	len -= pkt->outer_l3_len;
+	udp_hdr = (struct rte_udp_hdr *)((char *)ipv4_hdr + pkt->outer_l3_len);
+	udp_hdr->dgram_len = rte_cpu_to_be_16(len);
+
+	/* Update the inner IPv4 header. */
+	len -= pkt->l2_len;
+	ipv4_hdr = (struct rte_ipv4_hdr *)((char *)udp_hdr + pkt->l2_len);
+	ipv4_hdr->total_length = rte_cpu_to_be_16(len);
+
+	/* Clear MF bit if it is last fragment */
+	if (item->inner_item.is_last_frag) {
+		frag_offset = rte_be_to_cpu_16(ipv4_hdr->fragment_offset);
+		ipv4_hdr->fragment_offset =
+			rte_cpu_to_be_16(frag_offset & ~RTE_IPV4_HDR_MF_FLAG);
+	}
+}
+
+int32_t
+gro_vxlan_udp4_reassemble(struct rte_mbuf *pkt,
+		struct gro_vxlan_udp4_tbl *tbl,
+		uint64_t start_time)
+{
+	struct rte_ether_hdr *outer_eth_hdr, *eth_hdr;
+	struct rte_ipv4_hdr *outer_ipv4_hdr, *ipv4_hdr;
+	struct rte_udp_hdr *udp_hdr;
+	struct rte_vxlan_hdr *vxlan_hdr;
+	uint16_t frag_offset;
+	uint8_t is_last_frag;
+	int16_t ip_dl;
+	uint16_t outer_ip_id, ip_id;
+	uint8_t outer_is_atomic;
+
+	struct vxlan_udp4_flow_key key;
+	uint32_t cur_idx, prev_idx, item_idx;
+	uint32_t i, max_flow_num, remaining_flow_num;
+	int cmp;
+	uint16_t hdr_len;
+	uint8_t find;
+
+	outer_eth_hdr = rte_pktmbuf_mtod(pkt, struct rte_ether_hdr *);
+	outer_ipv4_hdr = (struct rte_ipv4_hdr *)((char *)outer_eth_hdr +
+			pkt->outer_l2_len);
+
+	udp_hdr = (struct rte_udp_hdr *)((char *)outer_ipv4_hdr +
+			pkt->outer_l3_len);
+	vxlan_hdr = (struct rte_vxlan_hdr *)((char *)udp_hdr +
+			sizeof(struct rte_udp_hdr));
+	eth_hdr = (struct rte_ether_hdr *)((char *)vxlan_hdr +
+			sizeof(struct rte_vxlan_hdr));
+	/* l2_len = outer udp hdr len + vxlan hdr len + inner l2 len */
+	ipv4_hdr = (struct rte_ipv4_hdr *)((char *)udp_hdr + pkt->l2_len);
+
+	/*
+	 * Don't process the packet which has non-fragment inner IP.
+	 */
+	if (!is_ipv4_fragment(ipv4_hdr))
+		return -1;
+
+	hdr_len = pkt->outer_l2_len + pkt->outer_l3_len + pkt->l2_len +
+		pkt->l3_len;
+	/*
+	 * Don't process the packet whose payload length is less than or
+	 * equal to 0.
+	 */
+	ip_dl = pkt->pkt_len - hdr_len;
+	if (ip_dl <= 0)
+		return -1;
+
+	/*
+	 * Save IPv4 ID for the packet whose DF bit is 0. For the packet
+	 * whose DF bit is 1, IPv4 ID is ignored.
+	 */
+	frag_offset = rte_be_to_cpu_16(outer_ipv4_hdr->fragment_offset);
+	outer_is_atomic =
+		((frag_offset & RTE_IPV4_HDR_DF_FLAG) == RTE_IPV4_HDR_DF_FLAG);
+	outer_ip_id = outer_is_atomic ? 0 :
+		rte_be_to_cpu_16(outer_ipv4_hdr->packet_id);
+	ip_id = rte_be_to_cpu_16(ipv4_hdr->packet_id);
+	frag_offset = rte_be_to_cpu_16(ipv4_hdr->fragment_offset);
+	is_last_frag = ((frag_offset & RTE_IPV4_HDR_MF_FLAG) == 0) ? 1 : 0;
+	frag_offset = (uint16_t)(frag_offset & RTE_IPV4_HDR_OFFSET_MASK) << 3;
+
+	rte_ether_addr_copy(&(eth_hdr->s_addr), &(key.inner_key.eth_saddr));
+	rte_ether_addr_copy(&(eth_hdr->d_addr), &(key.inner_key.eth_daddr));
+	key.inner_key.ip_src_addr = ipv4_hdr->src_addr;
+	key.inner_key.ip_dst_addr = ipv4_hdr->dst_addr;
+	key.inner_key.ip_id = ip_id;
+
+	key.vxlan_hdr.vx_flags = vxlan_hdr->vx_flags;
+	key.vxlan_hdr.vx_vni = vxlan_hdr->vx_vni;
+	rte_ether_addr_copy(&(outer_eth_hdr->s_addr), &(key.outer_eth_saddr));
+	rte_ether_addr_copy(&(outer_eth_hdr->d_addr), &(key.outer_eth_daddr));
+	key.outer_ip_src_addr = outer_ipv4_hdr->src_addr;
+	key.outer_ip_dst_addr = outer_ipv4_hdr->dst_addr;
+	key.outer_src_port = udp_hdr->src_port;
+	key.outer_dst_port = udp_hdr->dst_port;
+
+	/* 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_vxlan_udp4_flow(tbl->flows[i].key, key)) {
+				find = 1;
+				break;
+			}
+			remaining_flow_num--;
+		}
+	}
+
+	/*
+	 * Can't 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, outer_ip_id,
+				ip_id, outer_is_atomic);
+		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 inserted 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. */
+	cur_idx = tbl->flows[i].start_index;
+	prev_idx = cur_idx;
+	do {
+		cmp = udp_check_vxlan_neighbor(&(tbl->items[cur_idx]),
+				frag_offset, ip_id, ip_dl);
+		if (cmp) {
+			if (merge_two_vxlan_udp4_packets(
+						&(tbl->items[cur_idx]),
+						pkt, cmp, frag_offset,
+						is_last_frag, ip_id)) {
+				return 1;
+			}
+			/*
+			 * Can't merge two packets, as the packet
+			 * length will be greater than the max value.
+			 * Insert the packet into the flow.
+			 */
+			if (insert_new_item(tbl, pkt, start_time, prev_idx,
+						frag_offset, is_last_frag,
+						outer_ip_id, ip_id,
+						outer_is_atomic) ==
+					INVALID_ARRAY_INDEX)
+				return -1;
+			return 0;
+		}
+
+		/* Ensure inserted items are ordered by frag_offset */
+		if (frag_offset
+			< tbl->items[cur_idx].inner_item.frag_offset) {
+			break;
+		}
+
+		prev_idx = cur_idx;
+		cur_idx = tbl->items[cur_idx].inner_item.next_pkt_idx;
+	} while (cur_idx != INVALID_ARRAY_INDEX);
+
+	/* Can't find neighbor. Insert 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, outer_ip_id,
+				ip_id, outer_is_atomic);
+		if (item_idx == INVALID_ARRAY_INDEX)
+			return -1;
+		tbl->items[item_idx].inner_item.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, outer_ip_id, ip_id,
+				outer_is_atomic) == INVALID_ARRAY_INDEX)
+			return -1;
+	}
+
+	return 0;
+}
+
+static int
+gro_vxlan_udp4_merge_items(struct gro_vxlan_udp4_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;
+	uint16_t ip_id;
+	uint32_t item_idx;
+	uint16_t hdr_len;
+
+	item_idx = tbl->items[start_idx].inner_item.next_pkt_idx;
+	while (item_idx != INVALID_ARRAY_INDEX) {
+		pkt = tbl->items[item_idx].inner_item.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].inner_item.frag_offset;
+		is_last_frag = tbl->items[item_idx].inner_item.is_last_frag;
+		ip_id = tbl->items[item_idx].inner_item.ip_id;
+		cmp = udp_check_vxlan_neighbor(&(tbl->items[start_idx]),
+					frag_offset, ip_id, ip_dl);
+		if (cmp) {
+			if (merge_two_vxlan_udp4_packets(
+					&(tbl->items[start_idx]),
+					pkt, cmp, frag_offset,
+					is_last_frag, ip_id)) {
+				item_idx = delete_item(tbl, item_idx,
+							INVALID_ARRAY_INDEX);
+				tbl->items[start_idx].inner_item.next_pkt_idx
+					= item_idx;
+			} else {
+				return 0;
+			}
+		} else {
+			return 0;
+		}
+	}
+
+	return 0;
+}
+
+uint16_t
+gro_vxlan_udp4_tbl_timeout_flush(struct gro_vxlan_udp4_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].inner_item.start_time <=
+					flush_timestamp) {
+				gro_vxlan_udp4_merge_items(tbl, j);
+				out[k++] = tbl->items[j].inner_item.firstseg;
+				if (tbl->items[j].inner_item.nb_merged > 1)
+					update_vxlan_header(&(tbl->items[j]));
+				/*
+				 * Delete the item and get the next packet
+				 * index.
+				 */
+				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 the flow won't be
+				 * timeout. Go to check other flows.
+				 */
+				break;
+		}
+	}
+	return k;
+}
+
+uint32_t
+gro_vxlan_udp4_tbl_pkt_count(void *tbl)
+{
+	struct gro_vxlan_udp4_tbl *gro_tbl = tbl;
+
+	if (gro_tbl)
+		return gro_tbl->item_num;
+
+	return 0;
+}
diff --git a/lib/librte_gro/gro_vxlan_udp4.h b/lib/librte_gro/gro_vxlan_udp4.h
new file mode 100644
index 0000000..a16e327
--- /dev/null
+++ b/lib/librte_gro/gro_vxlan_udp4.h
@@ -0,0 +1,152 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Inspur Corporation
+ */
+
+#ifndef _GRO_VXLAN_UDP4_H_
+#define _GRO_VXLAN_UDP4_H_
+
+#include "gro_udp4.h"
+
+#define GRO_VXLAN_UDP4_TBL_MAX_ITEM_NUM (1024UL * 1024UL)
+
+/* Header fields representing a VxLAN flow */
+struct vxlan_udp4_flow_key {
+	struct udp4_flow_key inner_key;
+	struct rte_vxlan_hdr vxlan_hdr;
+
+	struct rte_ether_addr outer_eth_saddr;
+	struct rte_ether_addr outer_eth_daddr;
+
+	uint32_t outer_ip_src_addr;
+	uint32_t outer_ip_dst_addr;
+
+	/* Outer UDP ports */
+	uint16_t outer_src_port;
+	uint16_t outer_dst_port;
+
+};
+
+struct gro_vxlan_udp4_flow {
+	struct vxlan_udp4_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_vxlan_udp4_item {
+	struct gro_udp4_item inner_item;
+	/* IPv4 ID in the outer IPv4 header */
+	uint16_t outer_ip_id;
+	/* Indicate if outer IPv4 ID can be ignored */
+	uint8_t outer_is_atomic;
+};
+
+/*
+ * VxLAN (with an outer IPv4 header and an inner UDP/IPv4 packet)
+ * reassembly table structure
+ */
+struct gro_vxlan_udp4_tbl {
+	/* item array */
+	struct gro_vxlan_udp4_item *items;
+	/* flow array */
+	struct gro_vxlan_udp4_flow *flows;
+	/* current item number */
+	uint32_t item_num;
+	/* current flow number */
+	uint32_t flow_num;
+	/* the maximum item number */
+	uint32_t max_item_num;
+	/* the maximum flow number */
+	uint32_t max_flow_num;
+};
+
+/**
+ * This function creates a VxLAN reassembly table for VxLAN packets
+ * which have an outer IPv4 header and an inner UDP/IPv4 packet.
+ *
+ * @param socket_id
+ *  Socket index for allocating the table
+ * @param max_flow_num
+ *  The maximum number of flows in the 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_vxlan_udp4_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow);
+
+/**
+ * This function destroys a VxLAN reassembly table.
+ *
+ * @param tbl
+ *  Pointer pointing to the VxLAN reassembly table
+ */
+void gro_vxlan_udp4_tbl_destroy(void *tbl);
+
+/**
+ * This function merges a VxLAN packet which has an outer IPv4 header and
+ * an inner UDP/IPv4 packet. It does not process the packet which does not
+ * have payload.
+ *
+ * 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 there is no available space in the table.
+ *
+ * @param pkt
+ *  Packet to reassemble
+ * @param tbl
+ *  Pointer pointing to the VxLAN 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_vxlan_udp4_reassemble(struct rte_mbuf *pkt,
+		struct gro_vxlan_udp4_tbl *tbl,
+		uint64_t start_time);
+
+/**
+ * This function flushes timeout packets in the VxLAN reassembly table,
+ * and without updating checksums.
+ *
+ * @param tbl
+ *  Pointer pointing to a VxLAN GRO table
+ * @param flush_timestamp
+ *  This function flushes 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_vxlan_udp4_tbl_timeout_flush(struct gro_vxlan_udp4_tbl *tbl,
+		uint64_t flush_timestamp,
+		struct rte_mbuf **out,
+		uint16_t nb_out);
+
+/**
+ * This function returns the number of the packets in a VxLAN
+ * reassembly table.
+ *
+ * @param tbl
+ *  Pointer pointing to the VxLAN reassembly table
+ *
+ * @return
+ *  The number of packets in the table
+ */
+uint32_t gro_vxlan_udp4_tbl_pkt_count(void *tbl);
+#endif
diff --git a/lib/librte_gro/meson.build b/lib/librte_gro/meson.build
index 0d18dc2..ea8b45c 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')
+sources = files('rte_gro.c', 'gro_tcp4.c', 'gro_udp4.c', 'gro_vxlan_tcp4.c', 'gro_vxlan_udp4.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 da849f7..6295fbb 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_udp4.h"
 #include "gro_vxlan_tcp4.h"
+#include "gro_vxlan_udp4.h"
 
 typedef void *(*gro_tbl_create_fn)(uint16_t socket_id,
 		uint16_t max_flow_num,
@@ -20,14 +21,14 @@ 
 
 static gro_tbl_create_fn tbl_create_fn[RTE_GRO_TYPE_MAX_NUM] = {
 		gro_tcp4_tbl_create, gro_vxlan_tcp4_tbl_create,
-		gro_udp4_tbl_create, NULL};
+		gro_udp4_tbl_create, gro_vxlan_udp4_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_udp4_tbl_destroy, gro_vxlan_udp4_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_udp4_tbl_pkt_count, gro_vxlan_udp4_tbl_pkt_count,
 			NULL};
 
 #define IS_IPV4_TCP_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
@@ -47,6 +48,16 @@ 
 		     RTE_PTYPE_INNER_L3_IPV4_EXT | \
 		     RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN)) != 0))
 
+#define IS_IPV4_VXLAN_UDP4_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
+		((ptype & RTE_PTYPE_L4_UDP) == RTE_PTYPE_L4_UDP) && \
+		((ptype & RTE_PTYPE_TUNNEL_VXLAN) == \
+		 RTE_PTYPE_TUNNEL_VXLAN) && \
+		 ((ptype & RTE_PTYPE_INNER_L4_UDP) == \
+		  RTE_PTYPE_INNER_L4_UDP) && \
+		  (((ptype & RTE_PTYPE_INNER_L3_MASK) & \
+		    (RTE_PTYPE_INNER_L3_IPV4 | \
+		     RTE_PTYPE_INNER_L3_IPV4_EXT | \
+		     RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN)) != 0))
 
 /*
  * GRO context structure. It keeps the table structures, which are
@@ -142,14 +153,22 @@  struct gro_ctx {
 	struct gro_vxlan_tcp4_item vxlan_tcp_items[RTE_GRO_MAX_BURST_ITEM_NUM]
 			= {{{0}, 0, 0} };
 
+	/* Allocate a reassembly table for VXLAN UDP GRO */
+	struct gro_vxlan_udp4_tbl vxlan_udp_tbl;
+	struct gro_vxlan_udp4_flow vxlan_udp_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
+	struct gro_vxlan_udp4_item vxlan_udp_items[RTE_GRO_MAX_BURST_ITEM_NUM]
+			= {{{0}, 0, 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;
+	uint8_t do_tcp4_gro = 0, do_vxlan_tcp_gro = 0, do_udp4_gro = 0,
+		do_vxlan_udp_gro = 0;
 
 	if (unlikely((param->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
 					RTE_GRO_TCP_IPV4 |
+					RTE_GRO_IPV4_VXLAN_UDP_IPV4 |
 					RTE_GRO_UDP_IPV4)) == 0))
 		return nb_pkts;
 
@@ -171,6 +190,19 @@  struct gro_ctx {
 		do_vxlan_tcp_gro = 1;
 	}
 
+	if (param->gro_types & RTE_GRO_IPV4_VXLAN_UDP_IPV4) {
+		for (i = 0; i < item_num; i++)
+			vxlan_udp_flows[i].start_index = INVALID_ARRAY_INDEX;
+
+		vxlan_udp_tbl.flows = vxlan_udp_flows;
+		vxlan_udp_tbl.items = vxlan_udp_items;
+		vxlan_udp_tbl.flow_num = 0;
+		vxlan_udp_tbl.item_num = 0;
+		vxlan_udp_tbl.max_flow_num = item_num;
+		vxlan_udp_tbl.max_item_num = item_num;
+		do_vxlan_udp_gro = 1;
+	}
+
 	if (param->gro_types & RTE_GRO_TCP_IPV4) {
 		for (i = 0; i < item_num; i++)
 			tcp_flows[i].start_index = INVALID_ARRAY_INDEX;
@@ -212,6 +244,15 @@  struct gro_ctx {
 				nb_after_gro--;
 			else if (ret < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV4_VXLAN_UDP4_PKT(pkts[i]->packet_type) &&
+				do_vxlan_udp_gro) {
+			ret = gro_vxlan_udp4_reassemble(pkts[i],
+							&vxlan_udp_tbl, 0);
+			if (ret > 0)
+				/* Merge successfully */
+				nb_after_gro--;
+			else if (ret < 0)
+				unprocess_pkts[unprocess_num++] = pkts[i];
 		} else if (IS_IPV4_TCP_PKT(pkts[i]->packet_type) &&
 				do_tcp4_gro) {
 			ret = gro_tcp4_reassemble(pkts[i], &tcp_tbl, 0);
@@ -241,6 +282,12 @@  struct gro_ctx {
 					0, pkts, nb_pkts);
 		}
 
+		if (do_vxlan_udp_gro) {
+			i += gro_vxlan_udp4_tbl_timeout_flush(&vxlan_udp_tbl,
+					0, &pkts[i], nb_pkts - i);
+
+		}
+
 		if (do_tcp4_gro) {
 			i += gro_tcp4_tbl_timeout_flush(&tcp_tbl, 0,
 					&pkts[i], nb_pkts - i);
@@ -269,19 +316,21 @@  struct gro_ctx {
 {
 	struct rte_mbuf *unprocess_pkts[nb_pkts];
 	struct gro_ctx *gro_ctx = ctx;
-	void *tcp_tbl, *udp_tbl, *vxlan_tcp_tbl;
+	void *tcp_tbl, *udp_tbl, *vxlan_tcp_tbl, *vxlan_udp_tbl;
 	uint64_t current_time;
 	uint16_t i, unprocess_num = 0;
-	uint8_t do_tcp4_gro, do_vxlan_tcp_gro, do_udp4_gro;
+	uint8_t do_tcp4_gro, do_vxlan_tcp_gro, do_udp4_gro, do_vxlan_udp_gro;
 
 	if (unlikely((gro_ctx->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
 					RTE_GRO_TCP_IPV4 |
+					RTE_GRO_IPV4_VXLAN_UDP_IPV4 |
 					RTE_GRO_UDP_IPV4)) == 0))
 		return nb_pkts;
 
 	tcp_tbl = gro_ctx->tbls[RTE_GRO_TCP_IPV4_INDEX];
 	vxlan_tcp_tbl = gro_ctx->tbls[RTE_GRO_IPV4_VXLAN_TCP_IPV4_INDEX];
 	udp_tbl = gro_ctx->tbls[RTE_GRO_UDP_IPV4_INDEX];
+	vxlan_udp_tbl = gro_ctx->tbls[RTE_GRO_IPV4_VXLAN_UDP_IPV4_INDEX];
 
 	do_tcp4_gro = (gro_ctx->gro_types & RTE_GRO_TCP_IPV4) ==
 		RTE_GRO_TCP_IPV4;
@@ -289,6 +338,8 @@  struct gro_ctx {
 		RTE_GRO_IPV4_VXLAN_TCP_IPV4;
 	do_udp4_gro = (gro_ctx->gro_types & RTE_GRO_UDP_IPV4) ==
 		RTE_GRO_UDP_IPV4;
+	do_vxlan_udp_gro = (gro_ctx->gro_types & RTE_GRO_IPV4_VXLAN_UDP_IPV4) ==
+		RTE_GRO_IPV4_VXLAN_UDP_IPV4;
 
 	current_time = rte_rdtsc();
 
@@ -298,6 +349,11 @@  struct gro_ctx {
 			if (gro_vxlan_tcp4_reassemble(pkts[i], vxlan_tcp_tbl,
 						current_time) < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV4_VXLAN_UDP4_PKT(pkts[i]->packet_type) &&
+				do_vxlan_udp_gro) {
+			if (gro_vxlan_udp4_reassemble(pkts[i], vxlan_udp_tbl,
+						current_time) < 0)
+				unprocess_pkts[unprocess_num++] = pkts[i];
 		} else if (IS_IPV4_TCP_PKT(pkts[i]->packet_type) &&
 				do_tcp4_gro) {
 			if (gro_tcp4_reassemble(pkts[i], tcp_tbl,
@@ -341,6 +397,13 @@  struct gro_ctx {
 		left_nb_out = max_nb_out - num;
 	}
 
+	if ((gro_types & RTE_GRO_IPV4_VXLAN_UDP_IPV4) && max_nb_out > 0) {
+		num += gro_vxlan_udp4_tbl_timeout_flush(gro_ctx->tbls[
+				RTE_GRO_IPV4_VXLAN_UDP_IPV4_INDEX],
+				flush_timestamp, &out[num], left_nb_out);
+		left_nb_out = max_nb_out - num;
+	}
+
 	/* If no available space in 'out', stop flushing. */
 	if ((gro_types & RTE_GRO_TCP_IPV4) && max_nb_out > 0) {
 		num += gro_tcp4_tbl_timeout_flush(
diff --git a/lib/librte_gro/rte_gro.h b/lib/librte_gro/rte_gro.h
index 470f3ed..9f9ed49 100644
--- a/lib/librte_gro/rte_gro.h
+++ b/lib/librte_gro/rte_gro.h
@@ -35,6 +35,9 @@ 
 #define RTE_GRO_UDP_IPV4_INDEX 2
 #define RTE_GRO_UDP_IPV4 (1ULL << RTE_GRO_UDP_IPV4_INDEX)
 /**< UDP/IPv4 GRO flag */
+#define RTE_GRO_IPV4_VXLAN_UDP_IPV4_INDEX 3
+#define RTE_GRO_IPV4_VXLAN_UDP_IPV4 (1ULL << RTE_GRO_IPV4_VXLAN_UDP_IPV4_INDEX)
+/**< VxLAN UDP/IPv4 GRO flag. */
 
 /**
  * Structure used to create GRO context objects or used to pass