gro: add UDP GRO and VXLAN UDP GRO support
diff mbox series

Message ID 20200701064800.222400-1-yang_y_yi@163.com
State Superseded
Delegated to: Thomas Monjalon
Headers show
Series
  • gro: add UDP GRO and VXLAN UDP GRO support
Related show

Checks

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

Commit Message

yang_y_yi July 1, 2020, 6:48 a.m. UTC
From: Yi Yang <yangyi01@inspur.com>

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

Signed-off-by: Yi Yang <yangyi01@inspur.com>
---
 lib/librte_gro/Makefile         |   2 +
 lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
 lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
 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        | 192 +++++++++++---
 lib/librte_gro/rte_gro.h        |   8 +-
 8 files changed, 1617 insertions(+), 34 deletions(-)
 create mode 100644 lib/librte_gro/gro_udp4.c
 create mode 100644 lib/librte_gro/gro_udp4.h
 create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
 create mode 100644 lib/librte_gro/gro_vxlan_udp4.h

Comments

Hu, Jiayu Sept. 1, 2020, 4:27 a.m. UTC | #1
Hi Yi,

This patch supports UDP and VxLAN/UDP, but both are in one patch.
It's too large, and please split it into small patches.

Thanks,
Jiayu

> -----Original Message-----
> From: yang_y_yi@163.com <yang_y_yi@163.com>
> Sent: Wednesday, July 1, 2020 2:48 PM
> To: dev@dpdk.org
> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
> yangyi01@inspur.com; yang_y_yi@163.com
> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
> 
> From: Yi Yang <yangyi01@inspur.com>
> 
> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM
> UDP performance when VM is enabled UFO or GSO, GRO
> must be supported if GSO, UFO or VXLAN 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.
> 
> Signed-off-by: Yi Yang <yangyi01@inspur.com>
> ---
>  lib/librte_gro/Makefile         |   2 +
>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
>  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        | 192 +++++++++++---
>  lib/librte_gro/rte_gro.h        |   8 +-
>  8 files changed, 1617 insertions(+), 34 deletions(-)
>  create mode 100644 lib/librte_gro/gro_udp4.c
>  create mode 100644 lib/librte_gro/gro_udp4.h
>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
> +
> +
> +/*
> + * 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);
> +	}

Need to clear MF bit for non-last fragments, and we also need to clear offset value.

> +}
> +
> +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 udp_dl, 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;
> +
> +	/*
> +	 * Don't process the packet whose UDP header length is not equal
> +	 * to 20.
> +	 */
> +	if (unlikely(pkt->l4_len != UDP_HDRLEN))
> +		return -1;

UDP header is fixed 8-byte. No need to check here.

> +
> +	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 + pkt->l4_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.
> +	 */
> +	udp_dl = pkt->pkt_len - hdr_len;
> +	if (udp_dl <= 0)
> +		return -1;

Udp_dl is unit16_t which will not be negative.

> +
> +	ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;
yang_y_yi Sept. 1, 2020, 6:10 a.m. UTC | #2
At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:
>Hi Yi,
>
>This patch supports UDP and VxLAN/UDP, but both are in one patch.
>It's too large, and please split it into small patches.

Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.

>
>Thanks,
>Jiayu
>
>> -----Original Message-----
>> From: yang_y_yi@163.com <yang_y_yi@163.com>
>> Sent: Wednesday, July 1, 2020 2:48 PM
>> To: dev@dpdk.org
>> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
>> yangyi01@inspur.com; yang_y_yi@163.com
>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
>> 
>> From: Yi Yang <yangyi01@inspur.com>
>> 
>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM
>> UDP performance when VM is enabled UFO or GSO, GRO
>> must be supported if GSO, UFO or VXLAN 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.
>> 
>> Signed-off-by: Yi Yang <yangyi01@inspur.com>
>> ---
>>  lib/librte_gro/Makefile         |   2 +
>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
>>  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        | 192 +++++++++++---
>>  lib/librte_gro/rte_gro.h        |   8 +-
>>  8 files changed, 1617 insertions(+), 34 deletions(-)
>>  create mode 100644 lib/librte_gro/gro_udp4.c
>>  create mode 100644 lib/librte_gro/gro_udp4.h
>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
>> +
>> +
>> +/*
>> + * 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);
>> +	}
>
>Need to clear MF bit for non-last fragments, and we also need to clear offset value.

For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.

>
>> +}
>> +
>> +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 udp_dl, 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;
>> +
>> +	/*
>> +	 * Don't process the packet whose UDP header length is not equal
>> +	 * to 20.
>> +	 */
>> +	if (unlikely(pkt->l4_len != UDP_HDRLEN))
>> +		return -1;
>
>UDP header is fixed 8-byte. No need to check here.

Agree, will remove it in v2.

>
>> +
>> +	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 + pkt->l4_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.
>> +	 */
>> +	udp_dl = pkt->pkt_len - hdr_len;
>> +	if (udp_dl <= 0)
>> +		return -1;
>
>Udp_dl is unit16_t which will not be negative.

Good catch, I should use int16_t here, will do it in  v2.

>
>> +
>> +	ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;
yang_y_yi Sept. 1, 2020, 8:42 a.m. UTC | #3
Jiayu, BTW, after I check it again, I think udp header length check is necessary, it is actually a sanity check io order to ensure it is indeed a udp packet, gro_tcp4.c did same thing.

At 2020-09-01 14:10:41, "yang_y_yi" <yang_y_yi@163.com> wrote:
>At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:
>>Hi Yi,
>>
>>This patch supports UDP and VxLAN/UDP, but both are in one patch.
>>It's too large, and please split it into small patches.
>
>Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.
>
>>
>>Thanks,
>>Jiayu
>>
>>> -----Original Message-----
>>> From: yang_y_yi@163.com <yang_y_yi@163.com>
>>> Sent: Wednesday, July 1, 2020 2:48 PM
>>> To: dev@dpdk.org
>>> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
>>> yangyi01@inspur.com; yang_y_yi@163.com
>>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
>>> 
>>> From: Yi Yang <yangyi01@inspur.com>
>>> 
>>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM
>>> UDP performance when VM is enabled UFO or GSO, GRO
>>> must be supported if GSO, UFO or VXLAN 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.
>>> 
>>> Signed-off-by: Yi Yang <yangyi01@inspur.com>
>>> ---
>>>  lib/librte_gro/Makefile         |   2 +
>>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
>>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
>>>  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        | 192 +++++++++++---
>>>  lib/librte_gro/rte_gro.h        |   8 +-
>>>  8 files changed, 1617 insertions(+), 34 deletions(-)
>>>  create mode 100644 lib/librte_gro/gro_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_udp4.h
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
>>> +
>>> +
>>> +/*
>>> + * 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);
>>> +	}
>>
>>Need to clear MF bit for non-last fragments, and we also need to clear offset value.
>
>For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.
>
>>
>>> +}
>>> +
>>> +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 udp_dl, 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;
>>> +
>>> +	/*
>>> +	 * Don't process the packet whose UDP header length is not equal
>>> +	 * to 20.
>>> +	 */
>>> +	if (unlikely(pkt->l4_len != UDP_HDRLEN))
>>> +		return -1;
>>
>>UDP header is fixed 8-byte. No need to check here.
>
>Agree, will remove it in v2.
>
>>
>>> +
>>> +	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 + pkt->l4_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.
>>> +	 */
>>> +	udp_dl = pkt->pkt_len - hdr_len;
>>> +	if (udp_dl <= 0)
>>> +		return -1;
>>
>>Udp_dl is unit16_t which will not be negative.
>
>Good catch, I should use int16_t here, will do it in  v2.
>
>>
>>> +
>>> +	ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;
>
Hu, Jiayu Sept. 2, 2020, 5:44 a.m. UTC | #4
Yi,

Packet type is checked by mbuf->packet_type field, and input
packets should provide correct packet_type value. TCP GRO
only process TCP packets whose header length is between
20 and 60 bytes. So we check l4_len.

From: yang_y_yi <yang_y_yi@163.com>
Sent: Tuesday, September 1, 2020 4:43 PM
To: Hu, Jiayu <jiayu.hu@intel.com>
Cc: dev@dpdk.org; thomas@monjalon.net; yangyi01@inspur.com
Subject: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

Jiayu, BTW, after I check it again, I think udp header length check is necessary, it is actually a sanity check io order to ensure it is indeed a udp packet, gro_tcp4.c did same thing.

At 2020-09-01 14:10:41, "yang_y_yi" <yang_y_yi@163.com<mailto:yang_y_yi@163.com>> wrote:

>At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>> wrote:

>>Hi Yi,

>>

>>This patch supports UDP and VxLAN/UDP, but both are in one patch.

>>It's too large, and please split it into small patches.

>

>Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.

>

>>

>>Thanks,

>>Jiayu

>>

>>> -----Original Message-----

>>> From: yang_y_yi@163.com<mailto:yang_y_yi@163.com> <yang_y_yi@163.com<mailto:yang_y_yi@163.com>>

>>> Sent: Wednesday, July 1, 2020 2:48 PM

>>> To: dev@dpdk.org<mailto:dev@dpdk.org>

>>> Cc: Hu, Jiayu <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>>; thomas@monjalon.net<mailto:thomas@monjalon.net>;

>>> yangyi01@inspur.com<mailto:yangyi01@inspur.com>; yang_y_yi@163.com<mailto:yang_y_yi@163.com>

>>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

>>>

>>> From: Yi Yang <yangyi01@inspur.com<mailto:yangyi01@inspur.com>>

>>>

>>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM

>>> UDP performance when VM is enabled UFO or GSO, GRO

>>> must be supported if GSO, UFO or VXLAN 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.

>>>

>>> Signed-off-by: Yi Yang <yangyi01@inspur.com<mailto:yangyi01@inspur.com>>

>>> ---

>>>  lib/librte_gro/Makefile         |   2 +

>>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++

>>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++

>>>  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        | 192 +++++++++++---

>>>  lib/librte_gro/rte_gro.h        |   8 +-

>>>  8 files changed, 1617 insertions(+), 34 deletions(-)

>>>  create mode 100644 lib/librte_gro/gro_udp4.c

>>>  create mode 100644 lib/librte_gro/gro_udp4.h

>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c

>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h

>>> +

>>> +

>>> +/*

>>> + * 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);

>>> +  }

>>

>>Need to clear MF bit for non-last fragments, and we also need to clear offset value.

>

>For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.

>

>>

>>> +}

>>> +

>>> +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 udp_dl, 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;

>>> +

>>> +  /*

>>> +   * Don't process the packet whose UDP header length is not equal

>>> +   * to 20.

>>> +   */

>>> +  if (unlikely(pkt->l4_len != UDP_HDRLEN))

>>> +         return -1;

>>

>>UDP header is fixed 8-byte. No need to check here.

>

>Agree, will remove it in v2.

>

>>

>>> +

>>> +  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 + pkt->l4_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.

>>> +   */

>>> +  udp_dl = pkt->pkt_len - hdr_len;

>>> +  if (udp_dl <= 0)

>>> +         return -1;

>>

>>Udp_dl is unit16_t which will not be negative.

>

>Good catch, I should use int16_t here, will do it in  v2.

>

>>

>>> +

>>> +  ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;

>
yang_y_yi Sept. 2, 2020, 5:57 a.m. UTC | #5
Jiayu, TCP header length is variable if there is TCP option, it is usually 20 if no TCP option, but correct value must be between 20 and 60 (including 20 and 60), I think we can't assume l4 header length has been set correctly if packet_type is set correctly, this is my point. I think it will be better if we can add a rte_gro_rx_prepare as rte_eth_tx_prepare. GRO can't work normally only if one of all the related fields isn't set correctly. So I don't think such sanity check is a bad thing.


At 2020-09-02 13:44:56, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:

Yi,

 

Packet type is checked by mbuf->packet_type field, and input

packets should provide correct packet_type value. TCP GRO

only process TCP packets whose header length is between

20 and 60 bytes. So we check l4_len.

 

From: yang_y_yi <yang_y_yi@163.com>
Sent: Tuesday, September 1, 2020 4:43 PM
To: Hu, Jiayu <jiayu.hu@intel.com>
Cc: dev@dpdk.org; thomas@monjalon.net; yangyi01@inspur.com
Subject: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

 

Jiayu, BTW, after I check it again, I think udp header length check is necessary, it is actually a sanity check io order to ensure it is indeed a udp packet, gro_tcp4.c did same thing.

At 2020-09-01 14:10:41, "yang_y_yi" <yang_y_yi@163.com> wrote:
>At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:
>>Hi Yi,
>> 
>>This patch supports UDP and VxLAN/UDP, but both are in one patch.
>>It's too large, and please split it into small patches.
> 
>Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.
> 
>> 
>>Thanks,
>>Jiayu
>> 
>>> -----Original Message-----
>>> From: yang_y_yi@163.com <yang_y_yi@163.com>
>>> Sent: Wednesday, July 1, 2020 2:48 PM
>>> To: dev@dpdk.org
>>> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
>>> yangyi01@inspur.com; yang_y_yi@163.com
>>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
>>> 
>>> From: Yi Yang <yangyi01@inspur.com>
>>> 
>>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM
>>> UDP performance when VM is enabled UFO or GSO, GRO
>>> must be supported if GSO, UFO or VXLAN 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.
>>> 
>>> Signed-off-by: Yi Yang <yangyi01@inspur.com>
>>> ---
>>>  lib/librte_gro/Makefile         |   2 +
>>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
>>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
>>>  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        | 192 +++++++++++---
>>>  lib/librte_gro/rte_gro.h        |   8 +-
>>>  8 files changed, 1617 insertions(+), 34 deletions(-)
>>>  create mode 100644 lib/librte_gro/gro_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_udp4.h
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
>>> +
>>> +
>>> +/*
>>> + * 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);
>>> +  }
>> 
>>Need to clear MF bit for non-last fragments, and we also need to clear offset value.
> 
>For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.
> 
>> 
>>> +}
>>> +
>>> +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 udp_dl, 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;
>>> +
>>> +  /*
>>> +   * Don't process the packet whose UDP header length is not equal
>>> +   * to 20.
>>> +   */
>>> +  if (unlikely(pkt->l4_len != UDP_HDRLEN))
>>> +         return -1;
>> 
>>UDP header is fixed 8-byte. No need to check here.
> 
>Agree, will remove it in v2.
> 
>> 
>>> +
>>> +  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 + pkt->l4_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.
>>> +   */
>>> +  udp_dl = pkt->pkt_len - hdr_len;
>>> +  if (udp_dl <= 0)
>>> +         return -1;
>> 
>>Udp_dl is unit16_t which will not be negative.
> 
>Good catch, I should use int16_t here, will do it in  v2.
> 
>> 
>>> +
>>> +  ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;
>
Hu, Jiayu Sept. 2, 2020, 6:26 a.m. UTC | #6
GRO lib requires users to provide correct mbuf->l2_len/packet_type etc..
This is for avoiding parsing packet headers. If we believe users give correct
packet_type, we also should believe l2_len/l4_len etc. are correct. Otherwise,
we need to get layer 4 header length from ipv4 header, rather than mbuf->l4_len.

rte_gro_rx_prepare() is a good way to do sanity check or prepare l2_len etc. fields,
but this function should be optional, IMO. Either user or rte_gro_rx_prepare() provides
correct l2_len etc. value.

Thanks,
Jiayu
From: yang_y_yi <yang_y_yi@163.com>
Sent: Wednesday, September 2, 2020 1:58 PM
To: Hu, Jiayu <jiayu.hu@intel.com>
Cc: dev@dpdk.org; thomas@monjalon.net; yangyi01@inspur.com
Subject: Re:RE: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
Importance: High

Jiayu, TCP header length is variable if there is TCP option, it is usually 20 if no TCP option, but correct value must be between 20 and 60 (including 20 and 60), I think we can't assume l4 header length has been set correctly if packet_type is set correctly, this is my point. I think it will be better if we can add a rte_gro_rx_prepare as rte_eth_tx_prepare. GRO can't work normally only if one of all the related fields isn't set correctly. So I don't think such sanity check is a bad thing.

At 2020-09-02 13:44:56, "Hu, Jiayu" <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>> wrote:
Yi,

Packet type is checked by mbuf->packet_type field, and input
packets should provide correct packet_type value. TCP GRO
only process TCP packets whose header length is between
20 and 60 bytes. So we check l4_len.

From: yang_y_yi <yang_y_yi@163.com<mailto:yang_y_yi@163.com>>
Sent: Tuesday, September 1, 2020 4:43 PM
To: Hu, Jiayu <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>>
Cc: dev@dpdk.org<mailto:dev@dpdk.org>; thomas@monjalon.net<mailto:thomas@monjalon.net>; yangyi01@inspur.com<mailto:yangyi01@inspur.com>
Subject: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

Jiayu, BTW, after I check it again, I think udp header length check is necessary, it is actually a sanity check io order to ensure it is indeed a udp packet, gro_tcp4.c did same thing.

At 2020-09-01 14:10:41, "yang_y_yi" <yang_y_yi@163.com<mailto:yang_y_yi@163.com>> wrote:

>At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>> wrote:

>>Hi Yi,

>>

>>This patch supports UDP and VxLAN/UDP, but both are in one patch.

>>It's too large, and please split it into small patches.

>

>Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.

>

>>

>>Thanks,

>>Jiayu

>>

>>> -----Original Message-----

>>> From: yang_y_yi@163.com<mailto:yang_y_yi@163.com> <yang_y_yi@163.com<mailto:yang_y_yi@163.com>>

>>> Sent: Wednesday, July 1, 2020 2:48 PM

>>> To: dev@dpdk.org<mailto:dev@dpdk.org>

>>> Cc: Hu, Jiayu <jiayu.hu@intel.com<mailto:jiayu.hu@intel.com>>; thomas@monjalon.net<mailto:thomas@monjalon.net>;

>>> yangyi01@inspur.com<mailto:yangyi01@inspur.com>; yang_y_yi@163.com<mailto:yang_y_yi@163.com>

>>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

>>>

>>> From: Yi Yang <yangyi01@inspur.com<mailto:yangyi01@inspur.com>>

>>>

>>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM

>>> UDP performance when VM is enabled UFO or GSO, GRO

>>> must be supported if GSO, UFO or VXLAN 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.

>>>

>>> Signed-off-by: Yi Yang <yangyi01@inspur.com<mailto:yangyi01@inspur.com>>

>>> ---

>>>  lib/librte_gro/Makefile         |   2 +

>>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++

>>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++

>>>  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        | 192 +++++++++++---

>>>  lib/librte_gro/rte_gro.h        |   8 +-

>>>  8 files changed, 1617 insertions(+), 34 deletions(-)

>>>  create mode 100644 lib/librte_gro/gro_udp4.c

>>>  create mode 100644 lib/librte_gro/gro_udp4.h

>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c

>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h

>>> +

>>> +

>>> +/*

>>> + * 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);

>>> +  }

>>

>>Need to clear MF bit for non-last fragments, and we also need to clear offset value.

>

>For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.

>

>>

>>> +}

>>> +

>>> +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 udp_dl, 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;

>>> +

>>> +  /*

>>> +   * Don't process the packet whose UDP header length is not equal

>>> +   * to 20.

>>> +   */

>>> +  if (unlikely(pkt->l4_len != UDP_HDRLEN))

>>> +         return -1;

>>

>>UDP header is fixed 8-byte. No need to check here.

>

>Agree, will remove it in v2.

>

>>

>>> +

>>> +  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 + pkt->l4_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.

>>> +   */

>>> +  udp_dl = pkt->pkt_len - hdr_len;

>>> +  if (udp_dl <= 0)

>>> +         return -1;

>>

>>Udp_dl is unit16_t which will not be negative.

>

>Good catch, I should use int16_t here, will do it in  v2.

>

>>

>>> +

>>> +  ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;

>
yang_y_yi Sept. 2, 2020, 9:31 a.m. UTC | #7
Thanks Jiayu, I have removed it and sent out v3, please help ack if no more comments.


At 2020-09-02 14:26:37, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:

GRO lib requires users to provide correct mbuf->l2_len/packet_type etc..

This is for avoiding parsing packet headers. If we believe users give correct

packet_type, we also should believe l2_len/l4_len etc. are correct. Otherwise,

we need to get layer 4 header length from ipv4 header, rather than mbuf->l4_len.

 

rte_gro_rx_prepare() is a good way to do sanity check or prepare l2_len etc. fields,

but this function should be optional, IMO. Either user or rte_gro_rx_prepare() provides

correct l2_len etc. value.

 

Thanks,

Jiayu

From: yang_y_yi <yang_y_yi@163.com>
Sent: Wednesday, September 2, 2020 1:58 PM
To: Hu, Jiayu <jiayu.hu@intel.com>
Cc: dev@dpdk.org; thomas@monjalon.net; yangyi01@inspur.com
Subject: Re:RE: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
Importance: High

 

Jiayu, TCP header length is variable if there is TCP option, it is usually 20 if no TCP option, but correct value must be between 20 and 60 (including 20 and 60), I think we can't assume l4 header length has been set correctly if packet_type is set correctly, this is my point. I think it will be better if we can add a rte_gro_rx_prepare as rte_eth_tx_prepare. GRO can't work normally only if one of all the related fields isn't set correctly. So I don't think such sanity check is a bad thing.

At 2020-09-02 13:44:56, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:

Yi,

 

Packet type is checked by mbuf->packet_type field, and input

packets should provide correct packet_type value. TCP GRO

only process TCP packets whose header length is between

20 and 60 bytes. So we check l4_len.

 

From: yang_y_yi <yang_y_yi@163.com>
Sent: Tuesday, September 1, 2020 4:43 PM
To: Hu, Jiayu <jiayu.hu@intel.com>
Cc:dev@dpdk.org; thomas@monjalon.net; yangyi01@inspur.com
Subject: Re:Re: [dpdk-dev] [PATCH] gro: add UDP GRO and VXLAN UDP GRO support

 

Jiayu, BTW, after I check it again, I think udp header length check is necessary, it is actually a sanity check io order to ensure it is indeed a udp packet, gro_tcp4.c did same thing.

At 2020-09-01 14:10:41, "yang_y_yi" <yang_y_yi@163.com> wrote:
>At 2020-09-01 12:27:29, "Hu, Jiayu" <jiayu.hu@intel.com> wrote:
>>Hi Yi,
>> 
>>This patch supports UDP and VxLAN/UDP, but both are in one patch.
>>It's too large, and please split it into small patches.
> 
>Jiayu, thank you so much for your great review , I'll send v2 to split it into two patches and fix your comments. Detailed replies for comments embedded, please check them.
> 
>> 
>>Thanks,
>>Jiayu
>> 
>>> -----Original Message-----
>>> From: yang_y_yi@163.com <yang_y_yi@163.com>
>>> Sent: Wednesday, July 1, 2020 2:48 PM
>>> To: dev@dpdk.org
>>> Cc: Hu, Jiayu <jiayu.hu@intel.com>; thomas@monjalon.net;
>>> yangyi01@inspur.com; yang_y_yi@163.com
>>> Subject: [PATCH] gro: add UDP GRO and VXLAN UDP GRO support
>>> 
>>> From: Yi Yang <yangyi01@inspur.com>
>>> 
>>> UDP GRO and VXLAN UDP GRO can help improve VM-to-VM
>>> UDP performance when VM is enabled UFO or GSO, GRO
>>> must be supported if GSO, UFO or VXLAN 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.
>>> 
>>> Signed-off-by: Yi Yang <yangyi01@inspur.com>
>>> ---
>>>  lib/librte_gro/Makefile         |   2 +
>>>  lib/librte_gro/gro_udp4.c       | 443 ++++++++++++++++++++++++++++++++
>>>  lib/librte_gro/gro_udp4.h       | 296 +++++++++++++++++++++
>>>  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        | 192 +++++++++++---
>>>  lib/librte_gro/rte_gro.h        |   8 +-
>>>  8 files changed, 1617 insertions(+), 34 deletions(-)
>>>  create mode 100644 lib/librte_gro/gro_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_udp4.h
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.c
>>>  create mode 100644 lib/librte_gro/gro_vxlan_udp4.h
>>> +
>>> +
>>> +/*
>>> + * 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);
>>> +  }
>> 
>>Need to clear MF bit for non-last fragments, and we also need to clear offset value.
> 
>For non-last fragment, MF (More Fragment) bit is necessary, why do you think we need to clear MF bit for it? Only last fragment should clear MF bit. offset value must be set correctly because it is a IP fragment.
> 
>> 
>>> +}
>>> +
>>> +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 udp_dl, 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;
>>> +
>>> +  /*
>>> +   * Don't process the packet whose UDP header length is not equal
>>> +   * to 20.
>>> +   */
>>> +  if (unlikely(pkt->l4_len != UDP_HDRLEN))
>>> +         return -1;
>> 
>>UDP header is fixed 8-byte. No need to check here.
> 
>Agree, will remove it in v2.
> 
>> 
>>> +
>>> +  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 + pkt->l4_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.
>>> +   */
>>> +  udp_dl = pkt->pkt_len - hdr_len;
>>> +  if (udp_dl <= 0)
>>> +         return -1;
>> 
>>Udp_dl is unit16_t which will not be negative.
> 
>Good catch, I should use int16_t here, will do it in  v2.
> 
>> 
>>> +
>>> +  ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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;
>

Patch
diff mbox series

diff --git a/lib/librte_gro/Makefile b/lib/librte_gro/Makefile
index e848687..30dd8c7 100644
--- a/lib/librte_gro/Makefile
+++ b/lib/librte_gro/Makefile
@@ -15,7 +15,9 @@  EXPORT_MAP := rte_gro_version.map
 # source files
 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_udp4.c b/lib/librte_gro/gro_udp4.c
new file mode 100644
index 0000000..30175e9
--- /dev/null
+++ b/lib/librte_gro/gro_udp4.c
@@ -0,0 +1,443 @@ 
+/* 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,
+		uint16_t ip_id)
+{
+	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].ip_id = ip_id;
+	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;
+	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 udp_dl, 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;
+
+	/*
+	 * 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 *);
+	ipv4_hdr = (struct rte_ipv4_hdr *)((char *)eth_hdr + pkt->l2_len);
+	hdr_len = pkt->l2_len + pkt->l3_len + pkt->l4_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.
+	 */
+	udp_dl = pkt->pkt_len - hdr_len;
+	if (udp_dl <= 0)
+		return -1;
+
+	ip_dl = rte_be_to_cpu_16(ipv4_hdr->total_length) - 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, ip_id);
+		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 = udp_check_neighbor(&(tbl->items[cur_idx]),
+				frag_offset, ip_id, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp4_packets(&(tbl->items[cur_idx]),
+						pkt, cmp, frag_offset,
+						is_last_frag, ip_id, 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,
+						ip_id) ==
+					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, ip_id);
+		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, ip_id)
+			== 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;
+	uint16_t ip_id;
+	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;
+		ip_id = tbl->items[item_idx].ip_id;
+		cmp = udp_check_neighbor(&(tbl->items[start_idx]),
+					frag_offset, ip_id, ip_dl, 0);
+		if (cmp) {
+			if (merge_two_udp4_packets(
+					&(tbl->items[start_idx]),
+					pkt, cmp, frag_offset,
+					is_last_frag, ip_id, 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..d765650
--- /dev/null
+++ b/lib/librte_gro/gro_udp4.h
@@ -0,0 +1,296 @@ 
+/* 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>
+#include <rte_vxlan.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
+
+#define UDP_HDRLEN 8
+
+/* 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;
+	/* IPv4 ID of the packet */
+	uint16_t ip_id;
+	/* the number of merged packets */
+	uint16_t nb_merged;
+	/* Indicate if IPv4 ID can be ignored */
+	uint8_t is_atomic;
+};
+
+/*
+ * 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 ip_id,
+		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);
+		/* update IP ID to the larger value */
+		item->ip_id = ip_id;
+	} else {
+		lastseg = rte_pktmbuf_lastseg(pkt);
+		lastseg->next = item->firstseg;
+		item->firstseg = pkt;
+		/* update sent_seq to the smaller value */
+		item->frag_offset = frag_offset;
+		item->ip_id = ip_id;
+	}
+	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
+udp_check_neighbor(struct gro_udp4_item *item,
+		uint16_t frag_offset,
+		uint16_t ip_id,
+		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) &&
+		(ip_id == item->ip_id))
+		/* append the new packet */
+		return 1;
+	else if ((frag_offset + ip_dl == item->frag_offset) &&
+			(ip_id == item->ip_id))
+		/* 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/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 501668c..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_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 6618f4d..6295fbb 100644
--- a/lib/librte_gro/rte_gro.c
+++ b/lib/librte_gro/rte_gro.c
@@ -9,7 +9,9 @@ 
 
 #include "rte_gro.h"
 #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,
@@ -18,17 +20,23 @@ 
 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, 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_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_vxlan_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 +48,17 @@ 
 		     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
  * used to merge packets, for different GRO types. Before using
@@ -123,20 +142,34 @@  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 */
-	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} };
+	/* 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_tcp_tbl;
+	struct gro_vxlan_tcp4_flow vxlan_tcp_flows[RTE_GRO_MAX_BURST_ITEM_NUM];
+	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_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)) == 0))
+					RTE_GRO_TCP_IPV4 |
+					RTE_GRO_IPV4_VXLAN_UDP_IPV4 |
+					RTE_GRO_UDP_IPV4)) == 0))
 		return nb_pkts;
 
 	/* Get the maximum number of packets */
@@ -146,15 +179,28 @@  struct gro_ctx {
 
 	if (param->gro_types & RTE_GRO_IPV4_VXLAN_TCP_IPV4) {
 		for (i = 0; i < item_num; i++)
-			vxlan_flows[i].start_index = INVALID_ARRAY_INDEX;
-
-		vxlan_tbl.flows = vxlan_flows;
-		vxlan_tbl.items = vxlan_items;
-		vxlan_tbl.flow_num = 0;
-		vxlan_tbl.item_num = 0;
-		vxlan_tbl.max_flow_num = item_num;
-		vxlan_tbl.max_item_num = item_num;
-		do_vxlan_gro = 1;
+			vxlan_tcp_flows[i].start_index = INVALID_ARRAY_INDEX;
+
+		vxlan_tcp_tbl.flows = vxlan_tcp_flows;
+		vxlan_tcp_tbl.items = vxlan_tcp_items;
+		vxlan_tcp_tbl.flow_num = 0;
+		vxlan_tcp_tbl.item_num = 0;
+		vxlan_tcp_tbl.max_flow_num = item_num;
+		vxlan_tcp_tbl.max_item_num = item_num;
+		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) {
@@ -170,14 +216,38 @@  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
 		 * will be flushed from the tables.
 		 */
 		if (IS_IPV4_VXLAN_TCP4_PKT(pkts[i]->packet_type) &&
-				do_vxlan_gro) {
-			ret = gro_vxlan_tcp4_reassemble(pkts[i], &vxlan_tbl, 0);
+				do_vxlan_tcp_gro) {
+			ret = gro_vxlan_tcp4_reassemble(pkts[i],
+							&vxlan_tcp_tbl, 0);
+			if (ret > 0)
+				/* Merge successfully */
+				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--;
@@ -191,27 +261,49 @@  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,
+		if (do_vxlan_tcp_gro) {
+			i = gro_vxlan_tcp4_tbl_timeout_flush(&vxlan_tcp_tbl,
 					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);
 		}
+
+		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;
@@ -224,29 +316,42 @@  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_tcp_tbl, *vxlan_udp_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_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)) == 0))
+					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_tbl = gro_ctx->tbls[RTE_GRO_IPV4_VXLAN_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;
-	do_vxlan_gro = (gro_ctx->gro_types & RTE_GRO_IPV4_VXLAN_TCP_IPV4) ==
+	do_vxlan_tcp_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;
+	do_vxlan_udp_gro = (gro_ctx->gro_types & RTE_GRO_IPV4_VXLAN_UDP_IPV4) ==
+		RTE_GRO_IPV4_VXLAN_UDP_IPV4;
 
 	current_time = rte_rdtsc();
 
 	for (i = 0; i < nb_pkts; i++) {
 		if (IS_IPV4_VXLAN_TCP4_PKT(pkts[i]->packet_type) &&
-				do_vxlan_gro) {
-			if (gro_vxlan_tcp4_reassemble(pkts[i], vxlan_tbl,
+				do_vxlan_tcp_gro) {
+			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) &&
@@ -254,6 +359,11 @@  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 +385,7 @@  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 +393,15 @@  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 ((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. */
@@ -291,7 +409,17 @@  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);
+		left_nb_out = max_nb_out - num;
 	}
 
 	return num;
diff --git a/lib/librte_gro/rte_gro.h b/lib/librte_gro/rte_gro.h
index 8d781b5..9f9ed49 100644
--- a/lib/librte_gro/rte_gro.h
+++ b/lib/librte_gro/rte_gro.h
@@ -31,7 +31,13 @@ 
 /**< 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 */
+#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