Re: [PATCH v7 2/4] ethdev: introduce protocol hdr based buffer split

[Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>]

On 10/2/22 00:05, Yuan Wang wrote:
> Currently, Rx buffer split supports length based split. With Rx queue
> offload RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT enabled and Rx packet segment
> configured, PMD will be able to split the received packets into
> multiple segments.
> 
> However, length based buffer split is not suitable for NICs that do split
> based on protocol headers. Given an arbitrarily variable length in Rx
> packet segment, it is almost impossible to pass a fixed protocol header to
> driver. Besides, the existence of tunneling results in the composition of
> a packet is various, which makes the situation even worse.
> 
> This patch extends current buffer split to support protocol header based
> buffer split. A new proto_hdr field is introduced in the reserved field
> of rte_eth_rxseg_split structure to specify protocol header. The proto_hdr
> field defines the split position of packet, splitting will always happen
> after the protocol header defined in the Rx packet segment. When Rx queue
> offload RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT is enabled and corresponding
> protocol header is configured, driver will split the ingress packets into
> multiple segments.
> 
> Examples for proto_hdr field defines:
> To split after ETH-IPV4-UDP, it should be defined as
> RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_L4_UDP
> 
> For inner ETH-IPV4-UDP, it should be defined as
> RTE_PTYPE_TUNNEL_GRENAT | RTE_PTYPE_INNER_L2_ETHER |
> RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN | RTE_PTYPE_INNER_L4_UDP
> 
> struct rte_eth_rxseg_split {
>          struct rte_mempool *mp; /* memory pools to allocate segment from */
>          uint16_t length; /* segment maximal data length,
>                              configures split point */
>          uint16_t offset; /* data offset from beginning
>                              of mbuf data buffer */
>          /**
> 	 * Proto_hdr defines a bit mask of the protocol sequence as
>           * RTE_PTYPE_*, configures split point. The last RTE_PTYPE*
>           * in the mask indicates the split position.
> 	 * For non-tunneling packets, the complete protocol sequence
>           * should be defined.
> 	 * For tunneling packets, for simplicity, only the tunnel and
>           * inner protocol sequence should be defined.
> 	 */
>          uint32_t proto_hdr;
> };
> 
> If protocol header split can be supported by a PMD, the
> rte_eth_buffer_split_get_supported_hdr_ptypes function can
> be use to obtain a list of these protocol headers.
> 
> For example, let's suppose we configured the Rx queue with the
> following segments:
>          seg0 - pool0, proto_hdr0=RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4,
>                 off0=2B
>          seg1 - pool1, proto_hdr1=RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4
>                 | RTE_PTYPE_L4_UDP, off1=128B
>          seg2 - pool2, off1=0B
> 
> The packet consists of ETH_IPV4_UDP_PAYLOAD will be split like
> following:
>          seg0 - ipv4 header @ RTE_PKTMBUF_HEADROOM + 2 in mbuf from pool0
>          seg1 - udp header @ 128 in mbuf from pool1
>          seg2 - payload @ 0 in mbuf from pool2
> 
> Note: NIC will only do split when the packets exactly match all the
> protocol headers in the segments. For example, if ARP packets received
> with above config, the NIC won't do split for ARP packets since
> it does not contains ipv4 header and udp header. These packets will be put
> into the last valid mempool, with zero offset.
> 
> Now buffer split can be configured in two modes. For length based
> buffer split, the mp, length, offset field in Rx packet segment should
> be configured, while the proto_hdr field will be ignored.
> For protocol header based buffer split, the mp, offset, proto_hdr field
> in Rx packet segment should be configured, while the length field will
> be ignored.
> 
> The split limitations imposed by underlying driver is reported in the
> rte_eth_dev_info->rx_seg_capa field. The memory attributes for the split
> parts may differ either, dpdk memory and external memory, respectively.
> 
> Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
> Signed-off-by: Xuan Ding <xuan.ding@intel.com>
> Signed-off-by: Wenxuan Wu <wenxuanx.wu@intel.com>

I apologize for delay with review. Overall LGTM now. See few
notes below.

> ---
>   doc/guides/rel_notes/release_22_11.rst |  7 +++
>   lib/ethdev/rte_ethdev.c                | 74 ++++++++++++++++++++++----
>   lib/ethdev/rte_ethdev.h                | 29 +++++++++-
>   3 files changed, 98 insertions(+), 12 deletions(-)
> 
> diff --git a/doc/guides/rel_notes/release_22_11.rst b/doc/guides/rel_notes/release_22_11.rst
> index 6a7474a3d6..510869c73a 100644
> --- a/doc/guides/rel_notes/release_22_11.rst
> +++ b/doc/guides/rel_notes/release_22_11.rst
> @@ -101,6 +101,13 @@ New Features
>     * Added ``rte_eth_buffer_split_get_supported_hdr_ptypes()``, to get supported
>       header protocols of a PMD to split.
>   
> +* **Added protocol header based buffer split.**
> +
> +  * Ethdev: The ``reserved`` field in the ``rte_eth_rxseg_split`` structure is
> +    replaced with ``proto_hdr`` to support protocol header based buffer split.
> +    User can choose length or protocol header to configure buffer split
> +    according to NIC's capability.
> +

It should be grouped together with other ethdev features.

>   
>   Removed Items
>   -------------
> diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
> index 1f0a7f8f3f..27ec19faed 100644
> --- a/lib/ethdev/rte_ethdev.c
> +++ b/lib/ethdev/rte_ethdev.c
> @@ -1649,9 +1649,10 @@ rte_eth_dev_is_removed(uint16_t port_id)
>   }
>   
>   static int
> -rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
> -			     uint16_t n_seg, uint32_t *mbp_buf_size,
> -			     const struct rte_eth_dev_info *dev_info)
> +rte_eth_rx_queue_check_split(uint16_t port_id,
> +			const struct rte_eth_rxseg_split *rx_seg,
> +			uint16_t n_seg, uint32_t *mbp_buf_size,
> +			const struct rte_eth_dev_info *dev_info)
>   {
>   	const struct rte_eth_rxseg_capa *seg_capa = &dev_info->rx_seg_capa;
>   	struct rte_mempool *mp_first;
> @@ -1674,6 +1675,7 @@ rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
>   		struct rte_mempool *mpl = rx_seg[seg_idx].mp;
>   		uint32_t length = rx_seg[seg_idx].length;
>   		uint32_t offset = rx_seg[seg_idx].offset;
> +		uint32_t proto_hdr = rx_seg[seg_idx].proto_hdr;
>   
>   		if (mpl == NULL) {
>   			RTE_ETHDEV_LOG(ERR, "null mempool pointer\n");
> @@ -1707,13 +1709,63 @@ rte_eth_rx_queue_check_split(const struct rte_eth_rxseg_split *rx_seg,
>   		}
>   		offset += seg_idx != 0 ? 0 : RTE_PKTMBUF_HEADROOM;
>   		*mbp_buf_size = rte_pktmbuf_data_room_size(mpl);
> -		length = length != 0 ? length : *mbp_buf_size;
> -		if (*mbp_buf_size < length + offset) {
> -			RTE_ETHDEV_LOG(ERR,
> -				       "%s mbuf_data_room_size %u < %u (segment length=%u + segment offset=%u)\n",
> -				       mpl->name, *mbp_buf_size,
> -				       length + offset, length, offset);
> -			return -EINVAL;
> +
> +		if (proto_hdr > 0) {
> +			/* Split based on protocol headers. */

Isn't safer here to ensure that segment length is set to 0?
Just to protect agains misusage etc.

> +
> +			/* skip the payload */

Sorry, it is confusing. What do you mean here?

> +			if (proto_hdr == RTE_PTYPE_ALL_MASK)
> +				continue;
> +
> +			int ptype_cnt;
> +
> +			ptype_cnt = rte_eth_buffer_split_get_supported_hdr_ptypes(port_id, NULL, 0);
> +			if (ptype_cnt <= 0) {
> +				RTE_ETHDEV_LOG(ERR,
> +					"Port %u failed to supported buffer split header protocols\n",
> +					port_id);
> +				return -EINVAL;
> +			}
> +
> +			uint32_t ptypes[ptype_cnt];
> +			int i;

First of all do no mix code and variable declaration.
It significantly complicates code reading.
Second creation of an array on stack based on function
return value is very dangerours from security point of
view - potential stack overflow and corresponding
vulnerabilities.

> +
> +			ptype_cnt = rte_eth_buffer_split_get_supported_hdr_ptypes(port_id,
> +										ptypes, ptype_cnt);
> +			if (ptype_cnt < 0) {
> +				RTE_ETHDEV_LOG(ERR,
> +					"Port %u failed to supported buffer split header protocols\n",
> +					port_id);
> +				return -EINVAL;
> +			}
> +
> +			for (i = 0; i < ptype_cnt; i++)
> +				if (ptypes[i] == proto_hdr)
> +					break;
> +			if (i == ptype_cnt) {
> +				RTE_ETHDEV_LOG(ERR,
> +					"Requested Rx split header protocols 0x%x is not supported.\n",
> +					proto_hdr);
> +				return -EINVAL;
> +			}
> +
> +			if (*mbp_buf_size < offset) {

The check is obviously insufficient, but I agree that it should
be driver reponsibility to do extra checks for required space
in mbuf.

> +				RTE_ETHDEV_LOG(ERR,
> +						"%s mbuf_data_room_size %u < %u segment offset)\n",
> +						mpl->name, *mbp_buf_size,
> +						offset);
> +				return -EINVAL;
> +			}
> +		} else {
> +			/* Split at fixed length. */
> +			length = length != 0 ? length : *mbp_buf_size;
> +			if (*mbp_buf_size < length + offset) {
> +				RTE_ETHDEV_LOG(ERR,
> +					"%s mbuf_data_room_size %u < %u (segment length=%u + segment offset=%u)\n",
> +					mpl->name, *mbp_buf_size,
> +					length + offset, length, offset);
> +				return -EINVAL;
> +			}
>   		}
>   	}
>   	return 0;
> @@ -1793,7 +1845,7 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
>   		n_seg = rx_conf->rx_nseg;
>   
>   		if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
> -			ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
> +			ret = rte_eth_rx_queue_check_split(port_id, rx_seg, n_seg,
>   							   &mbp_buf_size,
>   							   &dev_info);
>   			if (ret != 0)
> diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
> index cf14e04010..a5f9647bd3 100644
> --- a/lib/ethdev/rte_ethdev.h
> +++ b/lib/ethdev/rte_ethdev.h
> @@ -994,6 +994,9 @@ struct rte_eth_txmode {
>    *   specified in the first array element, the second buffer, from the
>    *   pool in the second element, and so on.
>    *
> + * - The proto_hdrs in the elements define the split position of
> + *   received packets.
> + *
>    * - The offsets from the segment description elements specify
>    *   the data offset from the buffer beginning except the first mbuf.
>    *   The first segment offset is added with RTE_PKTMBUF_HEADROOM.
> @@ -1015,12 +1018,36 @@ struct rte_eth_txmode {
>    *     - pool from the last valid element
>    *     - the buffer size from this pool
>    *     - zero offset
> + *
> + * - Length based buffer split:
> + *     - mp, length, offset should be configured.
> + *     - The proto_hdr field will be ignored.

Looking at the code above I think proto_hdr must be 0.

> + *
> + * - Protocol header based buffer split:
> + *     - mp, offset, proto_hdr should be configured.
> + *     - The length field will be ignored.

I'd require length to be 0 to avoid misusage of the API.

> + *
> + * - For Protocol header based buffer split, if the received packets
> + *   don't exactly match all protocol headers in the elements, packets
> + *   will not be split.
> + *   These packets will be put into:
> + *     - pool from the last valid element
> + *     - the buffer size from this pool
> + *     - zero offset

Shoundl't be check that dataroom in the last segment mempool
is sufficient for up to MTU packet if Rx scatter is disabled?

>    */
>   struct rte_eth_rxseg_split {
>   	struct rte_mempool *mp; /**< Memory pool to allocate segment from. */
>   	uint16_t length; /**< Segment data length, configures split point. */
>   	uint16_t offset; /**< Data offset from beginning of mbuf data buffer. */
> -	uint32_t reserved; /**< Reserved field. */
> +	/**
> +	 * Proto_hdr defines a bit mask of the protocol sequence as RTE_PTYPE_*,
> +	 * configures split point. The last RTE_PTYPE* in the mask indicates the
> +	 * split position.
> +	 * For non-tunneling packets, the complete protocol sequence should be defined.
> +	 * For tunneling packets, for simplicity, only the tunnel and inner
> +	 * protocol sequence should be defined.
> +	 */
> +	uint32_t proto_hdr;
>   };
>   
>   /**