[PATCH v3] ip_frag: add IPv4 fragment copy packet API

[Morten Brørup]

> From: Huichao Cai [mailto:chcchc88 at 163.com]
> Sent: Friday, 22 July 2022 15.02
> To: dev at dpdk.org
> Cc: konstantin.v.ananyev at yandex.ru
> Subject: [PATCH v3] ip_frag: add IPv4 fragment copy packet API
> 
> Some NIC drivers support MBUF_FAST_FREE(Device supports optimization
> for fast release of mbufs. When set application must guarantee that
> per-queue all mbufs comes from the same mempool and has refcnt = 1)
> offload. In order to adapt to this offload function, add this API.
> Add some test data for this API.
> 
> Signed-off-by: Huichao Cai <chcchc88 at 163.com>
> ---
>  app/test/test_ipfrag.c               |   8 +-
>  lib/ip_frag/rte_ip_frag.h            |  27 +++++
>  lib/ip_frag/rte_ipv4_fragmentation.c | 208
> +++++++++++++++++++++++++++++++++++
>  lib/ip_frag/version.map              |   1 +
>  4 files changed, 243 insertions(+), 1 deletion(-)
> 
> diff --git a/app/test/test_ipfrag.c b/app/test/test_ipfrag.c
> index ba0ffd0..bb7c4d3 100644
> --- a/app/test/test_ipfrag.c
> +++ b/app/test/test_ipfrag.c
> @@ -418,10 +418,16 @@ static void ut_teardown(void)
>  		}
> 
>  		if (tests[i].ipv == 4)
> -			len = rte_ipv4_fragment_packet(b, pkts_out, BURST,
> +			if (i % 2)
> +				len = rte_ipv4_fragment_packet(b, pkts_out,
> BURST,
>  						       tests[i].mtu_size,
>  						       direct_pool,
>  						       indirect_pool);
> +			else
> +				len = rte_ipv4_fragment_copy_packet(b,
> pkts_out,
> +						       BURST,
> +						       tests[i].mtu_size,
> +						       pkt_pool);
>  		else if (tests[i].ipv == 6)
>  			len = rte_ipv6_fragment_packet(b, pkts_out, BURST,
>  						       tests[i].mtu_size,
> diff --git a/lib/ip_frag/rte_ip_frag.h b/lib/ip_frag/rte_ip_frag.h
> index 7d2abe1..c2a7e1e 100644
> --- a/lib/ip_frag/rte_ip_frag.h
> +++ b/lib/ip_frag/rte_ip_frag.h
> @@ -179,6 +179,33 @@ int32_t rte_ipv4_fragment_packet(struct rte_mbuf
> *pkt_in,
>  			struct rte_mempool *pool_indirect);
> 
>  /**
> + * IPv4 fragmentation by copy.
> + *
> + * This function implements the fragmentation of IPv4 packets by copy.
> + *
> + * @param pkt_in
> + *   The input packet.
> + * @param pkts_out
> + *   Array storing the output fragments.
> + * @param mtu_size
> + *   Size in bytes of the Maximum Transfer Unit (MTU) for the outgoing
> IPv4
> + *   datagrams. This value includes the size of the IPv4 header.
> + * @param pool_direct
> + *   MBUF pool used for allocating direct buffers for the output
> fragments.
> + * @return
> + *   Upon successful completion - number of output fragments placed
> + *   in the pkts_out array.
> + *   Otherwise - (-1) * errno.
> + */
> +__rte_experimental
> +int32_t
> +rte_ipv4_fragment_copy_packet(struct rte_mbuf *pkt_in,
> +	struct rte_mbuf **pkts_out,
> +	uint16_t nb_pkts_out,
> +	uint16_t mtu_size,
> +	struct rte_mempool *pool_direct);
> +
> +/**
>   * This function implements reassembly of fragmented IPv4 packets.
>   * Incoming mbufs should have its l2_len/l3_len fields setup
> correctly.
>   *
> diff --git a/lib/ip_frag/rte_ipv4_fragmentation.c
> b/lib/ip_frag/rte_ipv4_fragmentation.c
> index 27a8ad2..cb15781 100644
> --- a/lib/ip_frag/rte_ipv4_fragmentation.c
> +++ b/lib/ip_frag/rte_ipv4_fragmentation.c
> @@ -83,6 +83,48 @@ static inline uint16_t
> __create_ipopt_frag_hdr(uint8_t *iph,
>  	return ipopt_len;
>  }
> 
> +static struct rte_mbuf *
> +__copy_to_pktmbuf(char *src, struct rte_mbuf *m_head,
> +	struct rte_mbuf *m_tail, struct rte_mempool *mp, uint32_t len)
> +{
> +	struct rte_mbuf *m_last, **prev;
> +
> +	m_last = m_tail;
> +	prev = &m_last->next;
> +	while (len > 0) {
> +		uint32_t copy_len;
> +
> +		/* current buffer is full, chain a new one */
> +		if (unlikely(rte_pktmbuf_tailroom(m_last) == 0)) {
> +			m_last = rte_pktmbuf_alloc(mp);
> +			if (unlikely(m_last == NULL))
> +				return NULL;
> +
> +			++m_head->nb_segs;
> +			*prev = m_last;
> +			prev = &m_last->next;
> +		}

I think that MBUF_FAST_FREE also requires non-segmented packets, although this requirement is missing in the documentation. I have asked Olivier (as MBUF maintainer) to confirm this requirement [1].

[1] http://inbox.dpdk.org/dev/98CBD80474FA8B44BF855DF32C47DC35D871C5@smartserver.smartshare.dk/

> +
> +		/*
> +		 * copy the min of data in len
> +		 * vs space available in output (m_last)
> +		 */
> +		copy_len = RTE_MIN(rte_pktmbuf_tailroom(m_last), len);
> +
> +		/* append from seg to m_last */
> +		memcpy(rte_pktmbuf_mtod_offset(m_last, char *, m_last-
> >data_len),
> +			src, copy_len);
> +
> +		/* update offsets and lengths */
> +		m_last->data_len += copy_len;
> +		m_head->pkt_len += copy_len;
> +		src += copy_len;
> +		len -= copy_len;
> +	}
> +
> +	return m_last;
> +}
> +
>  /**
>   * IPv4 fragmentation.
>   *