[v6,1/3] gro: add UDP/IPv4 GRO support
diff mbox series

Message ID 20200917034959.194372-2-yang_y_yi@163.com
State Superseded, archived
Delegated to: Thomas Monjalon
Headers show
Series
  • gro: add UDP/IPv4 GRO and VXLAN UDP/IPv4 GRO support
Related show

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

yang_y_yi Sept. 17, 2020, 3:49 a.m. UTC
From: Yi Yang <yangyi01@inspur.com>

UDP/IPv4 GRO can help improve VM-to-VM UDP performance
when UFO or GSO is enabled in VM, GRO must be supported
if UFO or GSO is enabled, otherwise, performance can't
get big improvement if only GSO is there.

With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to-VM UDP performance, it will reassemble
UDP fragments 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>
---
 lib/librte_gro/gro_udp4.c  | 430 +++++++++++++++++++++++++++++++++++++++++++++
 lib/librte_gro/gro_udp4.h  | 281 +++++++++++++++++++++++++++++
 lib/librte_gro/meson.build |   2 +-
 lib/librte_gro/rte_gro.c   |  92 ++++++++--
 lib/librte_gro/rte_gro.h   |   5 +-
 5 files changed, 794 insertions(+), 16 deletions(-)
 create mode 100644 lib/librte_gro/gro_udp4.c
 create mode 100644 lib/librte_gro/gro_udp4.h

Comments

Hu, Jiayu Sept. 21, 2020, 6:21 a.m. UTC | #1
> -----Original Message-----
> From: yang_y_yi@163.com <yang_y_yi@163.com>
> Sent: Thursday, September 17, 2020 11:50 AM
> To: dev@dpdk.org
> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
> yangyi01@inspur.com; yang_y_yi@163.com
> Subject: [PATCH v6 1/3] gro: add UDP/IPv4 GRO support
> 
> From: Yi Yang <yangyi01@inspur.com>
> 
> UDP/IPv4 GRO can help improve VM-to-VM UDP performance
> when UFO or GSO is enabled in VM, GRO must be supported
> if UFO or GSO is enabled, otherwise, performance can't
> get big improvement if only GSO is there.
> 
> With this enabled in DPDK, OVS DPDK can leverage it
> to improve VM-to-VM UDP performance, it will reassemble
> UDP fragments 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>

Acked-by: Jiayu Hu <jiayu.hu@intel.com>

> ---
>  lib/librte_gro/gro_udp4.c  | 430
> +++++++++++++++++++++++++++++++++++++++++++++
>  lib/librte_gro/gro_udp4.h  | 281 +++++++++++++++++++++++++++++
>  lib/librte_gro/meson.build |   2 +-
>  lib/librte_gro/rte_gro.c   |  92 ++++++++--
>  lib/librte_gro/rte_gro.h   |   5 +-
>  5 files changed, 794 insertions(+), 16 deletions(-)
>  create mode 100644 lib/librte_gro/gro_udp4.c
>  create mode 100644 lib/librte_gro/gro_udp4.h
>

Patch
diff mbox series

diff --git a/lib/librte_gro/gro_udp4.c b/lib/librte_gro/gro_udp4.c
new file mode 100644
index 0000000..061e7b0
--- /dev/null
+++ b/lib/librte_gro/gro_udp4.c
@@ -0,0 +1,430 @@ 
+/* 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 "gro_udp4.h"
+
+void *
+gro_udp4_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow)
+{
+	struct gro_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_UDP4_TBL_MAX_ITEM_NUM);
+
+	if (entries_num == 0)
+		return NULL;
+
+	tbl = rte_zmalloc_socket(__func__,
+			sizeof(struct gro_udp4_tbl),
+			RTE_CACHE_LINE_SIZE,
+			socket_id);
+	if (tbl == NULL)
+		return NULL;
+
+	size = sizeof(struct gro_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_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;
+	}
+	/* 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_udp4_tbl_destroy(void *tbl)
+{
+	struct gro_udp4_tbl *udp_tbl = tbl;
+
+	if (udp_tbl) {
+		rte_free(udp_tbl->items);
+		rte_free(udp_tbl->flows);
+	}
+	rte_free(udp_tbl);
+}
+
+static inline uint32_t
+find_an_empty_item(struct gro_udp4_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_udp4_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_udp4_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 (unlikely(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_udp4_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;
+}
+
+static inline uint32_t
+insert_new_flow(struct gro_udp4_tbl *tbl,
+		struct udp4_flow_key *src,
+		uint32_t item_idx)
+{
+	struct 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->eth_saddr), &(dst->eth_saddr));
+	rte_ether_addr_copy(&(src->eth_daddr), &(dst->eth_daddr));
+	dst->ip_src_addr = src->ip_src_addr;
+	dst->ip_dst_addr = src->ip_dst_addr;
+	dst->ip_id = src->ip_id;
+
+	tbl->flows[flow_idx].start_index = item_idx;
+	tbl->flow_num++;
+
+	return flow_idx;
+}
+
+/*
+ * update the packet length for the flushed packet.
+ */
+static inline void
+update_header(struct gro_udp4_item *item)
+{
+	struct rte_ipv4_hdr *ipv4_hdr;
+	struct rte_mbuf *pkt = item->firstseg;
+	uint16_t frag_offset;
+
+	ipv4_hdr = (struct rte_ipv4_hdr *)(rte_pktmbuf_mtod(pkt, char *) +
+			pkt->l2_len);
+	ipv4_hdr->total_length = rte_cpu_to_be_16(pkt->pkt_len -
+			pkt->l2_len);
+
+	/* Clear MF bit if it is last fragment */
+	if (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_udp4_reassemble(struct rte_mbuf *pkt,
+		struct gro_udp4_tbl *tbl,
+		uint64_t start_time)
+{
+	struct rte_ether_hdr *eth_hdr;
+	struct rte_ipv4_hdr *ipv4_hdr;
+	uint16_t ip_dl;
+	uint16_t ip_id, hdr_len;
+	uint16_t frag_offset = 0;
+	uint8_t is_last_frag;
+
+	struct udp4_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;
+
+	eth_hdr = rte_pktmbuf_mtod(pkt, struct rte_ether_hdr *);
+	ipv4_hdr = (struct rte_ipv4_hdr *)((char *)eth_hdr + pkt->l2_len);
+	hdr_len = pkt->l2_len + pkt->l3_len;
+
+	/*
+	 * Don't process non-fragment packet.
+	 */
+	if (!is_ipv4_fragment(ipv4_hdr))
+		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;
+
+	ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length);
+	if (ip_dl <= pkt->l3_len)
+		return -1;
+
+	ip_dl -= pkt->l3_len;
+	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.eth_saddr));
+	rte_ether_addr_copy(&(eth_hdr->d_addr), &(key.eth_daddr));
+	key.ip_src_addr = ipv4_hdr->src_addr;
+	key.ip_dst_addr = ipv4_hdr->dst_addr;
+	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_udp4_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 (unlikely(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 = udp4_check_neighbor(&(tbl->items[cur_idx]),
+				frag_offset, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp4_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 (unlikely(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_udp4_merge_items(struct gro_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;
+	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->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 = udp4_check_neighbor(&(tbl->items[start_idx]),
+					frag_offset, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp4_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_udp4_tbl_timeout_flush(struct gro_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].start_time <= flush_timestamp) {
+				gro_udp4_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_udp4_tbl_pkt_count(void *tbl)
+{
+	struct gro_udp4_tbl *gro_tbl = tbl;
+
+	if (gro_tbl)
+		return gro_tbl->item_num;
+
+	return 0;
+}
diff --git a/lib/librte_gro/gro_udp4.h b/lib/librte_gro/gro_udp4.h
new file mode 100644
index 0000000..0a078e4
--- /dev/null
+++ b/lib/librte_gro/gro_udp4.h
@@ -0,0 +1,281 @@ 
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2020 Inspur Corporation
+ */
+
+#ifndef _GRO_UDP4_H_
+#define _GRO_UDP4_H_
+
+#include <rte_ip.h>
+#include <rte_udp.h>
+
+#define INVALID_ARRAY_INDEX 0xffffffffUL
+#define GRO_UDP4_TBL_MAX_ITEM_NUM (1024UL * 1024UL)
+
+/*
+ * The max length of a IPv4 packet, which includes the length of the L3
+ * header, the L4 header and the data payload.
+ */
+#define MAX_IPV4_PKT_LENGTH UINT16_MAX
+
+/* Header fields representing a UDP/IPv4 flow */
+struct udp4_flow_key {
+	struct rte_ether_addr eth_saddr;
+	struct rte_ether_addr eth_daddr;
+	uint32_t ip_src_addr;
+	uint32_t ip_dst_addr;
+
+	/* IP fragment for UDP does not contain UDP header
+	 * except the first one. But IP ID must be same.
+	 */
+	uint16_t ip_id;
+};
+
+struct gro_udp4_flow {
+	struct 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_udp4_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/IPv4 reassembly table structure.
+ */
+struct gro_udp4_tbl {
+	/* item array */
+	struct gro_udp4_item *items;
+	/* flow array */
+	struct gro_udp4_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/IPv4 reassembly table.
+ *
+ * @param socket_id
+ *  Socket index for allocating the UDP/IPv4 reassemble table
+ * @param max_flow_num
+ *  The maximum number of flows in the UDP/IPv4 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_udp4_tbl_create(uint16_t socket_id,
+		uint16_t max_flow_num,
+		uint16_t max_item_per_flow);
+
+/**
+ * This function destroys a UDP/IPv4 reassembly table.
+ *
+ * @param tbl
+ *  Pointer pointing to the UDP/IPv4 reassembly table.
+ */
+void gro_udp4_tbl_destroy(void *tbl);
+
+/**
+ * This function merges a UDP/IPv4 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/IPv4 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_udp4_reassemble(struct rte_mbuf *pkt,
+		struct gro_udp4_tbl *tbl,
+		uint64_t start_time);
+
+/**
+ * This function flushes timeout packets in a UDP/IPv4 reassembly table,
+ * and without updating checksums.
+ *
+ * @param tbl
+ *  UDP/IPv4 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_udp4_tbl_timeout_flush(struct gro_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 UDP/IPv4
+ * reassembly table.
+ *
+ * @param tbl
+ *  UDP/IPv4 reassembly table pointer
+ *
+ * @return
+ *  The number of packets in the table
+ */
+uint32_t gro_udp4_tbl_pkt_count(void *tbl);
+
+/*
+ * Check if two UDP/IPv4 packets belong to the same flow.
+ */
+static inline int
+is_same_udp4_flow(struct udp4_flow_key k1, struct udp4_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) &&
+			(k1.ip_src_addr == k2.ip_src_addr) &&
+			(k1.ip_dst_addr == k2.ip_dst_addr) &&
+			(k1.ip_id == k2.ip_id));
+}
+
+/*
+ * Merge two UDP/IPv4 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_udp4_packets(struct gro_udp4_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 IPv4 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_IPV4_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/IPv4 packets are neighbors.
+ */
+static inline int
+udp4_check_neighbor(struct gro_udp4_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;
+}
+
+static inline int
+is_ipv4_fragment(const struct rte_ipv4_hdr *hdr)
+{
+	uint16_t flag_offset, ip_flag, ip_ofs;
+
+	flag_offset = rte_be_to_cpu_16(hdr->fragment_offset);
+	ip_ofs = (uint16_t)(flag_offset & RTE_IPV4_HDR_OFFSET_MASK);
+	ip_flag = (uint16_t)(flag_offset & RTE_IPV4_HDR_MF_FLAG);
+
+	return ip_flag != 0 || ip_ofs  != 0;
+}
+#endif
diff --git a/lib/librte_gro/meson.build b/lib/librte_gro/meson.build
index 501668c..0d18dc2 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_vxlan_tcp4.c')
+sources = files('rte_gro.c', 'gro_tcp4.c', 'gro_udp4.c', 'gro_vxlan_tcp4.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 6618f4d..f623230 100644
--- a/lib/librte_gro/rte_gro.c
+++ b/lib/librte_gro/rte_gro.c
@@ -9,6 +9,7 @@ 
 
 #include "rte_gro.h"
 #include "gro_tcp4.h"
+#include "gro_udp4.h"
 #include "gro_vxlan_tcp4.h"
 
 typedef void *(*gro_tbl_create_fn)(uint16_t socket_id,
@@ -18,17 +19,23 @@ 
 typedef uint32_t (*gro_tbl_pkt_count_fn)(void *tbl);
 
 static gro_tbl_create_fn tbl_create_fn[RTE_GRO_TYPE_MAX_NUM] = {
-		gro_tcp4_tbl_create, gro_vxlan_tcp4_tbl_create, NULL};
+		gro_tcp4_tbl_create, gro_vxlan_tcp4_tbl_create,
+		gro_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,
 			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,
 			NULL};
 
 #define IS_IPV4_TCP_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
 		((ptype & RTE_PTYPE_L4_TCP) == RTE_PTYPE_L4_TCP))
 
+#define IS_IPV4_UDP_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
+		((ptype & RTE_PTYPE_L4_UDP) == RTE_PTYPE_L4_UDP))
+
 #define IS_IPV4_VXLAN_TCP4_PKT(ptype) (RTE_ETH_IS_IPV4_HDR(ptype) && \
 		((ptype & RTE_PTYPE_L4_UDP) == RTE_PTYPE_L4_UDP) && \
 		((ptype & RTE_PTYPE_TUNNEL_VXLAN) == \
@@ -40,6 +47,7 @@ 
 		     RTE_PTYPE_INNER_L3_IPV4_EXT | \
 		     RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN)) != 0))
 
+
 /*
  * GRO context structure. It keeps the table structures, which are
  * used to merge packets, for different GRO types. Before using
@@ -123,20 +131,26 @@  struct gro_ctx {
 	struct gro_tcp4_flow tcp_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
 	struct gro_tcp4_item tcp_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{0} };
 
-	/* Allocate a reassembly table for VXLAN GRO */
+	/* allocate a reassembly table for UDP/IPv4 GRO */
+	struct gro_udp4_tbl udp_tbl;
+	struct gro_udp4_flow udp_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
+	struct gro_udp4_item udp_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {{0} };
+
+	/* Allocate a reassembly table for VXLAN TCP GRO */
 	struct gro_vxlan_tcp4_tbl vxlan_tbl;
 	struct gro_vxlan_tcp4_flow vxlan_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
-	struct gro_vxlan_tcp4_item vxlan_items[RTE_GRO_MAX_BURST_ITEM_NUM] = {
-		{{0}, 0, 0} };
+	struct gro_vxlan_tcp4_item vxlan_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_gro = 0;
+	uint8_t do_tcp4_gro = 0, do_vxlan_gro = 0, do_udp4_gro = 0;
 
 	if (unlikely((param->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
-					RTE_GRO_TCP_IPV4)) == 0))
+					RTE_GRO_TCP_IPV4 |
+					RTE_GRO_UDP_IPV4)) == 0))
 		return nb_pkts;
 
 	/* Get the maximum number of packets */
@@ -170,6 +184,20 @@  struct gro_ctx {
 		do_tcp4_gro = 1;
 	}
 
+	if (param->gro_types & RTE_GRO_UDP_IPV4) {
+		for (i = 0; i < item_num; i++)
+			udp_flows[i].start_index = INVALID_ARRAY_INDEX;
+
+		udp_tbl.flows = udp_flows;
+		udp_tbl.items = udp_items;
+		udp_tbl.flow_num = 0;
+		udp_tbl.item_num = 0;
+		udp_tbl.max_flow_num = item_num;
+		udp_tbl.max_item_num = item_num;
+		do_udp4_gro = 1;
+	}
+
+
 	for (i = 0; i < nb_pkts; i++) {
 		/*
 		 * The timestamp is ignored, since all packets
@@ -177,7 +205,8 @@  struct gro_ctx {
 		 */
 		if (IS_IPV4_VXLAN_TCP4_PKT(pkts[i]->packet_type) &&
 				do_vxlan_gro) {
-			ret = gro_vxlan_tcp4_reassemble(pkts[i], &vxlan_tbl, 0);
+			ret = gro_vxlan_tcp4_reassemble(pkts[i],
+							&vxlan_tbl, 0);
 			if (ret > 0)
 				/* Merge successfully */
 				nb_after_gro--;
@@ -191,27 +220,43 @@  struct gro_ctx {
 				nb_after_gro--;
 			else if (ret < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV4_UDP_PKT(pkts[i]->packet_type) &&
+				do_udp4_gro) {
+			ret = gro_udp4_reassemble(pkts[i], &udp_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];
 	}
 
-	if (nb_after_gro < nb_pkts) {
+	if ((nb_after_gro < nb_pkts)
+		 || (unprocess_num < nb_pkts)) {
 		i = 0;
 		/* Flush all packets from the tables */
 		if (do_vxlan_gro) {
 			i = gro_vxlan_tcp4_tbl_timeout_flush(&vxlan_tbl,
 					0, pkts, nb_pkts);
 		}
+
 		if (do_tcp4_gro) {
 			i += gro_tcp4_tbl_timeout_flush(&tcp_tbl, 0,
 					&pkts[i], nb_pkts - i);
 		}
+
+		if (do_udp4_gro) {
+			i += gro_udp4_tbl_timeout_flush(&udp_tbl, 0,
+					&pkts[i], nb_pkts - i);
+		}
 		/* Copy unprocessed packets */
 		if (unprocess_num > 0) {
 			memcpy(&pkts[i], unprocess_pkts,
 					sizeof(struct rte_mbuf *) *
 					unprocess_num);
 		}
+		nb_after_gro = i + unprocess_num;
 	}
 
 	return nb_after_gro;
@@ -224,22 +269,26 @@  struct gro_ctx {
 {
 	struct rte_mbuf *unprocess_pkts[nb_pkts];
 	struct gro_ctx *gro_ctx = ctx;
-	void *tcp_tbl, *vxlan_tbl;
+	void *tcp_tbl, *udp_tbl, *vxlan_tbl;
 	uint64_t current_time;
 	uint16_t i, unprocess_num = 0;
-	uint8_t do_tcp4_gro, do_vxlan_gro;
+	uint8_t do_tcp4_gro, do_vxlan_gro, do_udp4_gro;
 
 	if (unlikely((gro_ctx->gro_types & (RTE_GRO_IPV4_VXLAN_TCP_IPV4 |
-					RTE_GRO_TCP_IPV4)) == 0))
+					RTE_GRO_TCP_IPV4 |
+					RTE_GRO_UDP_IPV4)) == 0))
 		return nb_pkts;
 
 	tcp_tbl = gro_ctx->tbls[RTE_GRO_TCP_IPV4_INDEX];
 	vxlan_tbl = gro_ctx->tbls[RTE_GRO_IPV4_VXLAN_TCP_IPV4_INDEX];
+	udp_tbl = gro_ctx->tbls[RTE_GRO_UDP_IPV4_INDEX];
 
 	do_tcp4_gro = (gro_ctx->gro_types & RTE_GRO_TCP_IPV4) ==
 		RTE_GRO_TCP_IPV4;
 	do_vxlan_gro = (gro_ctx->gro_types & RTE_GRO_IPV4_VXLAN_TCP_IPV4) ==
 		RTE_GRO_IPV4_VXLAN_TCP_IPV4;
+	do_udp4_gro = (gro_ctx->gro_types & RTE_GRO_UDP_IPV4) ==
+		RTE_GRO_UDP_IPV4;
 
 	current_time = rte_rdtsc();
 
@@ -254,6 +303,11 @@  struct gro_ctx {
 			if (gro_tcp4_reassemble(pkts[i], tcp_tbl,
 						current_time) < 0)
 				unprocess_pkts[unprocess_num++] = pkts[i];
+		} else if (IS_IPV4_UDP_PKT(pkts[i]->packet_type) &&
+				do_udp4_gro) {
+			if (gro_udp4_reassemble(pkts[i], udp_tbl,
+						current_time) < 0)
+				unprocess_pkts[unprocess_num++] = pkts[i];
 		} else
 			unprocess_pkts[unprocess_num++] = pkts[i];
 	}
@@ -275,6 +329,7 @@  struct gro_ctx {
 	struct gro_ctx *gro_ctx = ctx;
 	uint64_t flush_timestamp;
 	uint16_t num = 0;
+	uint16_t left_nb_out = max_nb_out;
 
 	gro_types = gro_types & gro_ctx->gro_types;
 	flush_timestamp = rte_rdtsc() - timeout_cycles;
@@ -282,8 +337,8 @@  struct gro_ctx {
 	if (gro_types & RTE_GRO_IPV4_VXLAN_TCP_IPV4) {
 		num = gro_vxlan_tcp4_tbl_timeout_flush(gro_ctx->tbls[
 				RTE_GRO_IPV4_VXLAN_TCP_IPV4_INDEX],
-				flush_timestamp, out, max_nb_out);
-		max_nb_out -= num;
+				flush_timestamp, out, left_nb_out);
+		left_nb_out = max_nb_out - num;
 	}
 
 	/* If no available space in 'out', stop flushing. */
@@ -291,7 +346,16 @@  struct gro_ctx {
 		num += gro_tcp4_tbl_timeout_flush(
 				gro_ctx->tbls[RTE_GRO_TCP_IPV4_INDEX],
 				flush_timestamp,
-				&out[num], max_nb_out);
+				&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_UDP_IPV4) && max_nb_out > 0) {
+		num += gro_udp4_tbl_timeout_flush(
+				gro_ctx->tbls[RTE_GRO_UDP_IPV4_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 8d781b5..470f3ed 100644
--- a/lib/librte_gro/rte_gro.h
+++ b/lib/librte_gro/rte_gro.h
@@ -31,7 +31,10 @@ 
 /**< TCP/IPv4 GRO flag */
 #define RTE_GRO_IPV4_VXLAN_TCP_IPV4_INDEX 1
 #define RTE_GRO_IPV4_VXLAN_TCP_IPV4 (1ULL << RTE_GRO_IPV4_VXLAN_TCP_IPV4_INDEX)
-/**< VxLAN GRO flag. */
+/**< VxLAN TCP/IPv4 GRO flag. */
+#define RTE_GRO_UDP_IPV4_INDEX 2
+#define RTE_GRO_UDP_IPV4 (1ULL << RTE_GRO_UDP_IPV4_INDEX)
+/**< UDP/IPv4 GRO flag */
 
 /**
  * Structure used to create GRO context objects or used to pass