[v4 1/3] ethdev: introduce protocol type based header split

[wenxuanx.wu@intel.com]

From: Xuan Ding <xuan.ding@intel.com>

Header split consists of splitting a received packet into two separate
regions based on the packet content. The split happens after the
packet header and before the packet payload. Splitting is usually between
the packet header that can be posted to a dedicated buffer and the packet
payload that can be posted to a different buffer.

Currently, Rx buffer split supports length and offset based packet split.
Although header split is a subset of buffer split, configuring buffer
split based on length is not suitable for NICs that do split based on
header protocol types. Because tunneling makes the conversion from length
to protocol type impossible.

This patch extends the current buffer split to support protocol type and
offset based header split. A new proto field is introduced in the
rte_eth_rxseg_split structure reserved field to specify header protocol
type. With Rx offload flag RTE_ETH_RX_OFFLOAD_HEADER_SPLIT enabled and
protocol type configured, PMD will split the ingress packets into two
separate regions. Currently, both inner and outer L2/L3/L4 level header
split can be supported.

For example, let's suppose we configured the Rx queue with the
following segments:
    seg0 - pool0, off0=2B
    seg1 - pool1, off1=128B

With header split type configured with RTE_ETH_RX_HEADER_SPLIT_UDP,
the packet consists of MAC_IP_UDP_PAYLOAD will be split like following:
    seg0 - udp header @ RTE_PKTMBUF_HEADROOM + 2 in mbuf from pool0
    seg1 - payload @ 128 in mbuf from pool1

The memory attributes for the split parts may differ either - for example
the mempool0 and mempool1 belong to dpdk memory and external memory,
respectively.

Signed-off-by: Xuan Ding <xuan.ding@intel.com>
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Signed-off-by: Wenxuan Wu <wenxuanx.wu@intel.com>
Reviewed-by: Qi Zhang <qi.z.zhang@intel.com>
---
 lib/ethdev/rte_ethdev.c | 34 ++++++++++++++++++++++-------
 lib/ethdev/rte_ethdev.h | 48 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 72 insertions(+), 10 deletions(-)

diff --git a/lib/ethdev/rte_ethdev.c b/lib/ethdev/rte_ethdev.c
index 29a3d80466..29adcdc2f0 100644
--- a/lib/ethdev/rte_ethdev.c
+++ b/lib/ethdev/rte_ethdev.c
@@ -1661,6 +1661,7 @@ 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;
+		uint16_t proto = rx_seg[seg_idx].proto;
 
 		if (mpl == NULL) {
 			RTE_ETHDEV_LOG(ERR, "null mempool pointer\n");
@@ -1694,13 +1695,29 @@ 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 == RTE_ETH_RX_HEADER_SPLIT_NONE) {
+			/* Check buffer split. */
+			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;
+			}
+		} else {
+			/* Check header split. */
+			if (length != 0) {
+				RTE_ETHDEV_LOG(ERR, "segment length should be set to zero in header split\n");
+				return -EINVAL;
+			}
+			if (*mbp_buf_size < offset) {
+				RTE_ETHDEV_LOG(ERR,
+					"%s mbuf_data_room_size %u < %u segment offset)\n",
+					mpl->name, *mbp_buf_size,
+					offset);
+				return -EINVAL;
+			}
 		}
 	}
 	return 0;
@@ -1778,7 +1795,8 @@ rte_eth_rx_queue_setup(uint16_t port_id, uint16_t rx_queue_id,
 		rx_seg = (const struct rte_eth_rxseg_split *)rx_conf->rx_seg;
 		n_seg = rx_conf->rx_nseg;
 
-		if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT) {
+		if (rx_conf->offloads & RTE_ETH_RX_OFFLOAD_BUFFER_SPLIT ||
+			rx_conf->offloads & RTE_ETH_RX_OFFLOAD_HEADER_SPLIT) {
 			ret = rte_eth_rx_queue_check_split(rx_seg, n_seg,
 							   &mbp_buf_size,
 							   &dev_info);
diff --git a/lib/ethdev/rte_ethdev.h b/lib/ethdev/rte_ethdev.h
index 04cff8ee10..e8371b98ed 100644
--- a/lib/ethdev/rte_ethdev.h
+++ b/lib/ethdev/rte_ethdev.h
@@ -1197,12 +1197,31 @@ struct rte_eth_txmode {
  *     - pool from the last valid element
  *     - the buffer size from this pool
  *     - zero offset
+ *
+ * Header split is a subset of buffer split. The split happens after the
+ * packet header and before the packet payload. For PMDs that do not
+ * support header split configuration by length, the location of the split
+ * needs to be specified by the header protocol type. While for buffer split,
+ * this field should not be configured.
+ *
+ * If RTE_ETH_RX_OFFLOAD_HEADER_SPLIT flag is set in offloads field,
+ * the PMD will split the received packets into two separate regions:
+ * - The header buffer will be allocated from the memory pool,
+ *   specified in the first array element, the second buffer, from the
+ *   pool in the second element.
+ *
+ * - The lengths do not need to be configured in header split.
+ *
+ * - 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.
  */
 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. */
+	uint16_t proto; /**< header protocol type, configures header split point. */
+	uint16_t reserved; /**< Reserved field. */
 };
 
 /**
@@ -1212,7 +1231,7 @@ struct rte_eth_rxseg_split {
  * A common structure used to describe Rx packet segment properties.
  */
 union rte_eth_rxseg {
-	/* The settings for buffer split offload. */
+	/* The settings for buffer split and header split offload. */
 	struct rte_eth_rxseg_split split;
 	/* The other features settings should be added here. */
 };
@@ -1664,6 +1683,31 @@ struct rte_eth_conf {
 			     RTE_ETH_RX_OFFLOAD_QINQ_STRIP)
 #define DEV_RX_OFFLOAD_VLAN RTE_DEPRECATED(DEV_RX_OFFLOAD_VLAN) RTE_ETH_RX_OFFLOAD_VLAN
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this enum may change without prior notice.
+ * This enum indicates the header split protocol type
+ */
+enum rte_eth_rx_header_split_protocol_type {
+	RTE_ETH_RX_HEADER_SPLIT_NONE = 0,
+	RTE_ETH_RX_HEADER_SPLIT_MAC,
+	RTE_ETH_RX_HEADER_SPLIT_IPV4,
+	RTE_ETH_RX_HEADER_SPLIT_IPV6,
+	RTE_ETH_RX_HEADER_SPLIT_L3,
+	RTE_ETH_RX_HEADER_SPLIT_TCP,
+	RTE_ETH_RX_HEADER_SPLIT_UDP,
+	RTE_ETH_RX_HEADER_SPLIT_SCTP,
+	RTE_ETH_RX_HEADER_SPLIT_L4,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_MAC,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_IPV4,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_IPV6,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_L3,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_TCP,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_UDP,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_SCTP,
+	RTE_ETH_RX_HEADER_SPLIT_INNER_L4,
+};
+
 /*
  * If new Rx offload capabilities are defined, they also must be
  * mentioned in rte_rx_offload_names in rte_ethdev.c file.
-- 
2.17.1