[dpdk-dev] [PATCH v4] net/iavf: support flex desc metadata extraction

Jeff Guo jia.guo at intel.com
Wed Sep 23 17:36:09 CEST 2020


Enable metadata extraction for flexible descriptors in AVF, that would
allow network function directly get metadata without additional parsing
which would reduce the CPU cost for VFs. The enabling metadata
extractions involve the metadata of VLAN/IPv4/IPv6/IPv6-FLOW/TCP/MPLS
flexible descriptors, and the VF could negotiate the capability of
the flexible descriptor with PF and correspondingly configure the
specific offload at receiving queues.

Signed-off-by: Jeff Guo <jia.guo at intel.com>
---
v4:
add flex desc type in rx queue for handling vector path
handle ovs flex type

v3:
export these global symbols into .map

v2:
remove makefile change and modify the rxdid handling
---
 doc/guides/rel_notes/release_20_11.rst    |   6 +
 drivers/net/iavf/iavf.h                   |  25 +-
 drivers/net/iavf/iavf_ethdev.c            | 399 ++++++++++++++++++++++
 drivers/net/iavf/iavf_rxtx.c              | 284 +++++++++++++--
 drivers/net/iavf/iavf_rxtx.h              | 234 +++++++------
 drivers/net/iavf/iavf_rxtx_vec_common.h   |   3 +
 drivers/net/iavf/iavf_vchnl.c             |  22 +-
 drivers/net/iavf/meson.build              |   2 +
 drivers/net/iavf/rte_pmd_iavf.h           | 250 ++++++++++++++
 drivers/net/iavf/rte_pmd_iavf_version.map |  13 +
 10 files changed, 1091 insertions(+), 147 deletions(-)
 create mode 100644 drivers/net/iavf/rte_pmd_iavf.h

diff --git a/doc/guides/rel_notes/release_20_11.rst b/doc/guides/rel_notes/release_20_11.rst
index d4a66d045..054424d94 100644
--- a/doc/guides/rel_notes/release_20_11.rst
+++ b/doc/guides/rel_notes/release_20_11.rst
@@ -62,6 +62,12 @@ New Features
   * Added support for non-zero priorities for group 0 flows
   * Added support for VXLAN decap combined with VLAN pop
 
+* **Updated Intel iavf driver.**
+
+  Updated iavf PMD with new features and improvements, including:
+
+  * Added support for flexible descriptor metadata extraction.
+
 
 Removed Items
 -------------
diff --git a/drivers/net/iavf/iavf.h b/drivers/net/iavf/iavf.h
index 3198d85b3..44e28df56 100644
--- a/drivers/net/iavf/iavf.h
+++ b/drivers/net/iavf/iavf.h
@@ -119,7 +119,7 @@ struct iavf_info {
 	struct virtchnl_vf_resource *vf_res; /* VF resource */
 	struct virtchnl_vsi_resource *vsi_res; /* LAN VSI */
 	uint64_t supported_rxdid;
-
+	uint8_t *flex_desc; /* flexible descriptor type for all queues */
 	volatile enum virtchnl_ops pend_cmd; /* pending command not finished */
 	uint32_t cmd_retval; /* return value of the cmd response from PF */
 	uint8_t *aq_resp; /* buffer to store the adminq response from PF */
@@ -153,6 +153,28 @@ struct iavf_info {
 
 #define IAVF_MAX_PKT_TYPE 1024
 
+#define IAVF_MAX_QUEUE_NUM  2048
+
+enum iavf_flex_desc_type {
+	IAVF_FLEX_DESC_NONE,
+	IAVF_FLEX_DESC_VLAN,
+	IAVF_FLEX_DESC_IPV4,
+	IAVF_FLEX_DESC_IPV6,
+	IAVF_FLEX_DESC_IPV6_FLOW,
+	IAVF_FLEX_DESC_TCP,
+	IAVF_FLEX_DESC_OVS,
+	IAVF_FLEX_DESC_IP_OFFSET,
+	IAVF_FLEX_DESC_MAX,
+};
+
+/**
+ * Cache devargs parse result.
+ */
+struct iavf_devargs {
+	uint8_t flex_desc_dflt;
+	uint8_t flex_desc[IAVF_MAX_QUEUE_NUM];
+};
+
 /* Structure to store private data for each VF instance. */
 struct iavf_adapter {
 	struct iavf_hw hw;
@@ -166,6 +188,7 @@ struct iavf_adapter {
 	const uint32_t *ptype_tbl;
 	bool stopped;
 	uint16_t fdir_ref_cnt;
+	struct iavf_devargs devargs;
 };
 
 /* IAVF_DEV_PRIVATE_TO */
diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 440da7d76..e057fd875 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+++ b/drivers/net/iavf/iavf_ethdev.c
@@ -28,6 +28,49 @@
 #include "iavf.h"
 #include "iavf_rxtx.h"
 #include "iavf_generic_flow.h"
+#include "rte_pmd_iavf.h"
+
+/* devargs */
+#define IAVF_FLEX_DESC_ARG         "flex_desc"
+
+static const char * const iavf_valid_args[] = {
+	IAVF_FLEX_DESC_ARG,
+	NULL
+};
+
+static const struct rte_mbuf_dynfield iavf_flex_desc_metadata_param = {
+	.name = "iavf_dynfield_flex_desc_metadata",
+	.size = sizeof(uint32_t),
+	.align = __alignof__(uint32_t),
+	.flags = 0,
+};
+
+struct iavf_flex_desc_xtr_ol {
+	const struct rte_mbuf_dynflag param;
+	uint64_t *ol_flag;
+	bool required;
+};
+
+static struct iavf_flex_desc_xtr_ol iavf_flex_desc_xtr_params[] = {
+	[IAVF_FLEX_DESC_VLAN] = {
+		.param = { .name = "iavf_dynflag_flex_desc_vlan" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_vlan_mask },
+	[IAVF_FLEX_DESC_IPV4] = {
+		.param = { .name = "iavf_dynflag_flex_desc_ipv4" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_ipv4_mask },
+	[IAVF_FLEX_DESC_IPV6] = {
+		.param = { .name = "iavf_dynflag_flex_desc_ipv6" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_ipv6_mask },
+	[IAVF_FLEX_DESC_IPV6_FLOW] = {
+		.param = { .name = "iavf_dynflag_flex_desc_ipv6_flow" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask },
+	[IAVF_FLEX_DESC_TCP] = {
+		.param = { .name = "iavf_dynflag_flex_desc_tcp" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_tcp_mask },
+	[IAVF_FLEX_DESC_IP_OFFSET] = {
+		.param = { .name = "ice_dynflag_flex_desc_ip_offset" },
+		.ol_flag = &rte_net_iavf_dynflag_flex_desc_ip_offset_mask },
+};
 
 static int iavf_dev_configure(struct rte_eth_dev *dev);
 static int iavf_dev_start(struct rte_eth_dev *dev);
@@ -1213,6 +1256,354 @@ iavf_check_vf_reset_done(struct iavf_hw *hw)
 	return 0;
 }
 
+static int
+iavf_lookup_flex_desc_type(const char *flex_name)
+{
+	static struct {
+		const char *name;
+		enum iavf_flex_desc_type type;
+	} flex_type_map[] = {
+		{ "vlan",      IAVF_FLEX_DESC_VLAN      },
+		{ "ipv4",      IAVF_FLEX_DESC_IPV4      },
+		{ "ipv6",      IAVF_FLEX_DESC_IPV6      },
+		{ "ipv6_flow", IAVF_FLEX_DESC_IPV6_FLOW },
+		{ "tcp",       IAVF_FLEX_DESC_TCP       },
+		{ "ovs",       IAVF_FLEX_DESC_OVS       },
+		{ "ip_offset", IAVF_FLEX_DESC_IP_OFFSET },
+	};
+	uint32_t i;
+
+	for (i = 0; i < RTE_DIM(flex_type_map); i++) {
+		if (strcmp(flex_name, flex_type_map[i].name) == 0)
+			return flex_type_map[i].type;
+	}
+
+	PMD_DRV_LOG(ERR, "wrong flex_desc type, "
+		    "it should be: vlan|ipv4|ipv6|ipv6_flow|tcp|ovs|ip_offset");
+
+	return -1;
+}
+
+/**
+ * Parse elem, the elem could be single number/range or '(' ')' group
+ * 1) A single number elem, it's just a simple digit. e.g. 9
+ * 2) A single range elem, two digits with a '-' between. e.g. 2-6
+ * 3) A group elem, combines multiple 1) or 2) with '( )'. e.g (0,2-4,6)
+ *    Within group elem, '-' used for a range separator;
+ *                       ',' used for a single number.
+ */
+static int
+iavf_parse_queue_set(const char *input, int flex_type,
+		     struct iavf_devargs *devargs)
+{
+	const char *str = input;
+	char *end = NULL;
+	uint32_t min, max;
+	uint32_t idx;
+
+	while (isblank(*str))
+		str++;
+
+	if (!isdigit(*str) && *str != '(')
+		return -1;
+
+	/* process single number or single range of number */
+	if (*str != '(') {
+		errno = 0;
+		idx = strtoul(str, &end, 10);
+		if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
+			return -1;
+
+		while (isblank(*end))
+			end++;
+
+		min = idx;
+		max = idx;
+
+		/* process single <number>-<number> */
+		if (*end == '-') {
+			end++;
+			while (isblank(*end))
+				end++;
+			if (!isdigit(*end))
+				return -1;
+
+			errno = 0;
+			idx = strtoul(end, &end, 10);
+			if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
+				return -1;
+
+			max = idx;
+			while (isblank(*end))
+				end++;
+		}
+
+		if (*end != ':')
+			return -1;
+
+		for (idx = RTE_MIN(min, max);
+		     idx <= RTE_MAX(min, max); idx++)
+			devargs->flex_desc[idx] = flex_type;
+
+		return 0;
+	}
+
+	/* process set within bracket */
+	str++;
+	while (isblank(*str))
+		str++;
+	if (*str == '\0')
+		return -1;
+
+	min = IAVF_MAX_QUEUE_NUM;
+	do {
+		/* go ahead to the first digit */
+		while (isblank(*str))
+			str++;
+		if (!isdigit(*str))
+			return -1;
+
+		/* get the digit value */
+		errno = 0;
+		idx = strtoul(str, &end, 10);
+		if (errno || !end || idx >= IAVF_MAX_QUEUE_NUM)
+			return -1;
+
+		/* go ahead to separator '-',',' and ')' */
+		while (isblank(*end))
+			end++;
+		if (*end == '-') {
+			if (min == IAVF_MAX_QUEUE_NUM)
+				min = idx;
+			else /* avoid continuous '-' */
+				return -1;
+		} else if (*end == ',' || *end == ')') {
+			max = idx;
+			if (min == IAVF_MAX_QUEUE_NUM)
+				min = idx;
+
+			for (idx = RTE_MIN(min, max);
+			     idx <= RTE_MAX(min, max); idx++)
+				devargs->flex_desc[idx] = flex_type;
+
+			min = IAVF_MAX_QUEUE_NUM;
+		} else {
+			return -1;
+		}
+
+		str = end + 1;
+	} while (*end != ')' && *end != '\0');
+
+	return 0;
+}
+
+static int
+iavf_parse_queue_flex_desc(const char *queues, struct iavf_devargs *devargs)
+{
+	const char *queue_start;
+	uint32_t idx;
+	int flex_type;
+	char flex_name[32];
+
+	while (isblank(*queues))
+		queues++;
+
+	if (*queues != '[') {
+		flex_type = iavf_lookup_flex_desc_type(queues);
+		if (flex_type < 0)
+			return -1;
+
+		devargs->flex_desc_dflt = flex_type;
+
+		return 0;
+	}
+
+	queues++;
+	do {
+		while (isblank(*queues))
+			queues++;
+		if (*queues == '\0')
+			return -1;
+
+		queue_start = queues;
+
+		/* go across a complete bracket */
+		if (*queue_start == '(') {
+			queues += strcspn(queues, ")");
+			if (*queues != ')')
+				return -1;
+		}
+
+		/* scan the separator ':' */
+		queues += strcspn(queues, ":");
+		if (*queues++ != ':')
+			return -1;
+		while (isblank(*queues))
+			queues++;
+
+		for (idx = 0; ; idx++) {
+			if (isblank(queues[idx]) ||
+			    queues[idx] == ',' ||
+			    queues[idx] == ']' ||
+			    queues[idx] == '\0')
+				break;
+
+			if (idx > sizeof(flex_name) - 2)
+				return -1;
+
+			flex_name[idx] = queues[idx];
+		}
+		flex_name[idx] = '\0';
+		flex_type = iavf_lookup_flex_desc_type(flex_name);
+		if (flex_type < 0)
+			return -1;
+
+		queues += idx;
+
+		while (isblank(*queues) || *queues == ',' || *queues == ']')
+			queues++;
+
+		if (iavf_parse_queue_set(queue_start, flex_type, devargs) < 0)
+			return -1;
+	} while (*queues != '\0');
+
+	return 0;
+}
+
+static int
+iavf_handle_flex_desc_arg(__rte_unused const char *key, const char *value,
+			  void *extra_args)
+{
+	struct iavf_devargs *devargs = extra_args;
+
+	if (!value || !extra_args)
+		return -EINVAL;
+
+	if (iavf_parse_queue_flex_desc(value, devargs) < 0) {
+		PMD_DRV_LOG(ERR, "the flex_desc's parameter is wrong : '%s'",
+			    value);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int iavf_parse_devargs(struct rte_eth_dev *dev)
+{
+	struct iavf_adapter *ad =
+		IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+	struct rte_devargs *devargs = dev->device->devargs;
+	struct rte_kvargs *kvlist;
+	int ret;
+
+	if (!devargs)
+		return 0;
+
+	kvlist = rte_kvargs_parse(devargs->args, iavf_valid_args);
+	if (!kvlist) {
+		PMD_INIT_LOG(ERR, "invalid kvargs key\n");
+		return -EINVAL;
+	}
+
+	ad->devargs.flex_desc_dflt = IAVF_FLEX_DESC_NONE;
+	memset(ad->devargs.flex_desc, IAVF_FLEX_DESC_NONE,
+	       sizeof(ad->devargs.flex_desc));
+
+	ret = rte_kvargs_process(kvlist, IAVF_FLEX_DESC_ARG,
+				 &iavf_handle_flex_desc_arg, &ad->devargs);
+	if (ret)
+		goto bail;
+
+bail:
+	rte_kvargs_free(kvlist);
+	return ret;
+}
+
+static void
+iavf_init_flex_desc(struct rte_eth_dev *dev)
+{
+	struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
+	struct iavf_adapter *ad =
+			IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
+	const struct iavf_flex_desc_xtr_ol *xtr_ol;
+	bool flex_desc_enable = false;
+	int offset;
+	uint16_t i;
+
+	vf->flex_desc = rte_zmalloc("vf flex desc",
+				    vf->vsi_res->num_queue_pairs, 0);
+	if (unlikely(!(vf->flex_desc))) {
+		PMD_DRV_LOG(ERR, "no memory for setting up flex_desc's table");
+		return;
+	}
+
+	for (i = 0; i < vf->vsi_res->num_queue_pairs; i++) {
+		vf->flex_desc[i] = ad->devargs.flex_desc[i] !=
+					IAVF_FLEX_DESC_NONE ?
+					ad->devargs.flex_desc[i] :
+					ad->devargs.flex_desc_dflt;
+
+		if (vf->flex_desc[i] != IAVF_FLEX_DESC_NONE) {
+			/* no metadata extraction for OVS */
+			if (vf->flex_desc[i] != IAVF_FLEX_DESC_OVS) {
+				uint8_t tp = vf->flex_desc[i];
+
+				iavf_flex_desc_xtr_params[tp].required = true;
+			}
+
+			flex_desc_enable = true;
+		}
+	}
+
+	if (likely(!flex_desc_enable))
+		return;
+
+	offset = rte_mbuf_dynfield_register(&iavf_flex_desc_metadata_param);
+	if (unlikely(offset == -1)) {
+		PMD_DRV_LOG(ERR,
+			    "failed to extract flex_desc metadata, error %d",
+			    -rte_errno);
+		return;
+	}
+
+	PMD_DRV_LOG(DEBUG,
+		    "flex_desc extraction metadata offset in mbuf is : %d",
+		    offset);
+	rte_net_iavf_dynfield_flex_desc_metadata_offs = offset;
+
+	for (i = 0; i < RTE_DIM(iavf_flex_desc_xtr_params); i++) {
+		xtr_ol = &iavf_flex_desc_xtr_params[i];
+
+		uint8_t rxdid = iavf_flex_desc_type_to_rxdid((uint8_t)i);
+
+		if (!xtr_ol->required)
+			continue;
+
+		if (!(vf->supported_rxdid & BIT(rxdid))) {
+			PMD_DRV_LOG(ERR,
+				    "rxdid[%u] is not supported in hardware",
+				    rxdid);
+			rte_net_iavf_dynfield_flex_desc_metadata_offs = -1;
+			break;
+		}
+
+		offset = rte_mbuf_dynflag_register(&xtr_ol->param);
+		if (unlikely(offset == -1)) {
+			PMD_DRV_LOG(ERR,
+				    "failed to register extraction offload '%s', error %d",
+				    xtr_ol->param.name, -rte_errno);
+
+			rte_net_iavf_dynfield_flex_desc_metadata_offs = -1;
+			break;
+		}
+
+		PMD_DRV_LOG(DEBUG,
+			    "flex_desc extraction offload '%s' offset in mbuf is : %d",
+			    xtr_ol->param.name, offset);
+		*xtr_ol->ol_flag = 1ULL << offset;
+	}
+}
+
 static int
 iavf_init_vf(struct rte_eth_dev *dev)
 {
@@ -1222,6 +1613,12 @@ iavf_init_vf(struct rte_eth_dev *dev)
 	struct iavf_hw *hw = IAVF_DEV_PRIVATE_TO_HW(dev->data->dev_private);
 	struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
 
+	err = iavf_parse_devargs(dev);
+	if (err) {
+		PMD_INIT_LOG(ERR, "Failed to parse devargs");
+		goto err;
+	}
+
 	err = iavf_set_mac_type(hw);
 	if (err) {
 		PMD_INIT_LOG(ERR, "set_mac_type failed: %d", err);
@@ -1287,6 +1684,8 @@ iavf_init_vf(struct rte_eth_dev *dev)
 
 	vf->vf_reset = false;
 
+	iavf_init_flex_desc(dev);
+
 	return 0;
 err_rss:
 	rte_free(vf->rss_key);
diff --git a/drivers/net/iavf/iavf_rxtx.c b/drivers/net/iavf/iavf_rxtx.c
index 05a7dd898..ec6609178 100644
--- a/drivers/net/iavf/iavf_rxtx.c
+++ b/drivers/net/iavf/iavf_rxtx.c
@@ -26,6 +26,36 @@
 
 #include "iavf.h"
 #include "iavf_rxtx.h"
+#include "rte_pmd_iavf.h"
+
+/* Offset of mbuf dynamic field for flexible descriptor's extraction data */
+int rte_net_iavf_dynfield_flex_desc_metadata_offs = -1;
+
+/* Mask of mbuf dynamic flags for flexible descriptor's type */
+uint64_t rte_net_iavf_dynflag_flex_desc_vlan_mask;
+uint64_t rte_net_iavf_dynflag_flex_desc_ipv4_mask;
+uint64_t rte_net_iavf_dynflag_flex_desc_ipv6_mask;
+uint64_t rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask;
+uint64_t rte_net_iavf_dynflag_flex_desc_tcp_mask;
+uint64_t rte_net_iavf_dynflag_flex_desc_ip_offset_mask;
+
+uint8_t
+iavf_flex_desc_type_to_rxdid(uint8_t flex_type)
+{
+	static uint8_t rxdid_map[] = {
+		[IAVF_FLEX_DESC_NONE]      = IAVF_RXDID_COMMS_GENERIC,
+		[IAVF_FLEX_DESC_VLAN]      = IAVF_RXDID_COMMS_AUX_VLAN,
+		[IAVF_FLEX_DESC_IPV4]      = IAVF_RXDID_COMMS_AUX_IPV4,
+		[IAVF_FLEX_DESC_IPV6]      = IAVF_RXDID_COMMS_AUX_IPV6,
+		[IAVF_FLEX_DESC_IPV6_FLOW] = IAVF_RXDID_COMMS_AUX_IPV6_FLOW,
+		[IAVF_FLEX_DESC_TCP]       = IAVF_RXDID_COMMS_AUX_TCP,
+		[IAVF_FLEX_DESC_OVS]       = IAVF_RXDID_COMMS_OVS_1,
+		[IAVF_FLEX_DESC_IP_OFFSET] = IAVF_RXDID_COMMS_AUX_IP_OFFSET,
+	};
+
+	return flex_type < RTE_DIM(rxdid_map) ?
+				rxdid_map[flex_type] : IAVF_RXDID_COMMS_GENERIC;
+}
 
 static inline int
 check_rx_thresh(uint16_t nb_desc, uint16_t thresh)
@@ -294,6 +324,160 @@ static const struct iavf_txq_ops def_txq_ops = {
 	.release_mbufs = release_txq_mbufs,
 };
 
+static inline void
+iavf_rxd_to_pkt_fields_by_comms_ovs(__rte_unused struct iavf_rx_queue *rxq,
+				    struct rte_mbuf *mb,
+				    volatile union iavf_rx_flex_desc *rxdp)
+{
+	volatile struct iavf_32b_rx_flex_desc_comms_ovs *desc =
+			(volatile struct iavf_32b_rx_flex_desc_comms_ovs *)rxdp;
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	uint16_t stat_err;
+#endif
+
+	if (desc->flow_id != 0xFFFFFFFF) {
+		mb->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+		mb->hash.fdir.hi = rte_le_to_cpu_32(desc->flow_id);
+	}
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	stat_err = rte_le_to_cpu_16(desc->status_error0);
+	if (likely(stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_S))) {
+		mb->ol_flags |= PKT_RX_RSS_HASH;
+		mb->hash.rss = rte_le_to_cpu_32(desc->rss_hash);
+	}
+#endif
+}
+
+static inline void
+iavf_rxd_to_pkt_fields_by_comms_aux_v1(struct iavf_rx_queue *rxq,
+				       struct rte_mbuf *mb,
+				       volatile union iavf_rx_flex_desc *rxdp)
+{
+	volatile struct iavf_32b_rx_flex_desc_comms *desc =
+			(volatile struct iavf_32b_rx_flex_desc_comms *)rxdp;
+	uint16_t stat_err;
+
+	stat_err = rte_le_to_cpu_16(desc->status_error0);
+	if (likely(stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_S))) {
+		mb->ol_flags |= PKT_RX_RSS_HASH;
+		mb->hash.rss = rte_le_to_cpu_32(desc->rss_hash);
+	}
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	if (desc->flow_id != 0xFFFFFFFF) {
+		mb->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+		mb->hash.fdir.hi = rte_le_to_cpu_32(desc->flow_id);
+	}
+
+	if (rxq->xtr_ol_flag) {
+		uint32_t metadata = 0;
+
+		stat_err = rte_le_to_cpu_16(desc->status_error1);
+
+		if (stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS1_XTRMD4_VALID_S))
+			metadata = rte_le_to_cpu_16(desc->flex_ts.flex.aux0);
+
+		if (stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS1_XTRMD5_VALID_S))
+			metadata |=
+				rte_le_to_cpu_16(desc->flex_ts.flex.aux1) << 16;
+
+		if (metadata) {
+			mb->ol_flags |= rxq->xtr_ol_flag;
+
+			*RTE_NET_IAVF_DYNF_FLEX_DESC_METADATA(mb) = metadata;
+		}
+	}
+#endif
+}
+
+static inline void
+iavf_rxd_to_pkt_fields_by_comms_aux_v2(struct iavf_rx_queue *rxq,
+				       struct rte_mbuf *mb,
+				       volatile union iavf_rx_flex_desc *rxdp)
+{
+	volatile struct iavf_32b_rx_flex_desc_comms *desc =
+			(volatile struct iavf_32b_rx_flex_desc_comms *)rxdp;
+	uint16_t stat_err;
+
+	stat_err = rte_le_to_cpu_16(desc->status_error0);
+	if (likely(stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_S))) {
+		mb->ol_flags |= PKT_RX_RSS_HASH;
+		mb->hash.rss = rte_le_to_cpu_32(desc->rss_hash);
+	}
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	if (desc->flow_id != 0xFFFFFFFF) {
+		mb->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
+		mb->hash.fdir.hi = rte_le_to_cpu_32(desc->flow_id);
+	}
+
+	if (rxq->xtr_ol_flag) {
+		uint32_t metadata = 0;
+
+		if (desc->flex_ts.flex.aux0 != 0xFFFF)
+			metadata = rte_le_to_cpu_16(desc->flex_ts.flex.aux0);
+		else if (desc->flex_ts.flex.aux1 != 0xFFFF)
+			metadata = rte_le_to_cpu_16(desc->flex_ts.flex.aux1);
+
+		if (metadata) {
+			mb->ol_flags |= rxq->xtr_ol_flag;
+
+			*RTE_NET_IAVF_DYNF_FLEX_DESC_METADATA(mb) = metadata;
+		}
+	}
+#endif
+}
+
+static void
+iavf_select_rxd_to_pkt_fields_handler(struct iavf_rx_queue *rxq, uint32_t rxdid)
+{
+	switch (rxdid) {
+	case IAVF_RXDID_COMMS_AUX_VLAN:
+		rxq->xtr_ol_flag = rte_net_iavf_dynflag_flex_desc_vlan_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v1;
+		break;
+	case IAVF_RXDID_COMMS_AUX_IPV4:
+		rxq->xtr_ol_flag = rte_net_iavf_dynflag_flex_desc_ipv4_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v1;
+		break;
+	case IAVF_RXDID_COMMS_AUX_IPV6:
+		rxq->xtr_ol_flag = rte_net_iavf_dynflag_flex_desc_ipv6_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v1;
+		break;
+	case IAVF_RXDID_COMMS_AUX_IPV6_FLOW:
+		rxq->xtr_ol_flag =
+			rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v1;
+		break;
+	case IAVF_RXDID_COMMS_AUX_TCP:
+		rxq->xtr_ol_flag = rte_net_iavf_dynflag_flex_desc_tcp_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v1;
+		break;
+	case IAVF_RXDID_COMMS_AUX_IP_OFFSET:
+		rxq->xtr_ol_flag =
+			rte_net_iavf_dynflag_flex_desc_ip_offset_mask;
+		rxq->rxd_to_pkt_fields =
+			iavf_rxd_to_pkt_fields_by_comms_aux_v2;
+		break;
+	case IAVF_RXDID_COMMS_OVS_1:
+		rxq->rxd_to_pkt_fields = iavf_rxd_to_pkt_fields_by_comms_ovs;
+		break;
+	default:
+		/* update this according to the RXDID for FLEX_DESC_NONE */
+		rxq->rxd_to_pkt_fields = iavf_rxd_to_pkt_fields_by_comms_ovs;
+		break;
+	}
+
+	if (!rte_net_iavf_dynf_flex_desc_metadata_avail())
+		rxq->xtr_ol_flag = 0;
+}
+
 int
 iavf_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
 		       uint16_t nb_desc, unsigned int socket_id,
@@ -309,6 +493,7 @@ iavf_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
 	struct iavf_rx_queue *rxq;
 	const struct rte_memzone *mz;
 	uint32_t ring_size;
+	uint8_t flex_desc;
 	uint16_t len;
 	uint16_t rx_free_thresh;
 
@@ -346,14 +531,18 @@ iavf_dev_rx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
 		return -ENOMEM;
 	}
 
-	if (vf->vf_res->vf_cap_flags &
-	    VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC &&
-	    vf->supported_rxdid & BIT(IAVF_RXDID_COMMS_OVS_1)) {
-		rxq->rxdid = IAVF_RXDID_COMMS_OVS_1;
+	if (vf->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) {
+		flex_desc = vf->flex_desc ? vf->flex_desc[queue_idx] :
+				IAVF_FLEX_DESC_NONE;
+		rxq->rxdid = iavf_flex_desc_type_to_rxdid(flex_desc);
+		rxq->flex_desc = flex_desc;
 	} else {
 		rxq->rxdid = IAVF_RXDID_LEGACY_1;
+		rxq->flex_desc = IAVF_FLEX_DESC_NONE;
 	}
 
+	iavf_select_rxd_to_pkt_fields_handler(rxq, rxq->rxdid);
+
 	rxq->mp = mp;
 	rxq->nb_rx_desc = nb_desc;
 	rxq->rx_free_thresh = rx_free_thresh;
@@ -715,6 +904,45 @@ iavf_stop_queues(struct rte_eth_dev *dev)
 	}
 }
 
+#define IAVF_RX_FLEX_ERR0_BITS	\
+	((1 << IAVF_RX_FLEX_DESC_STATUS0_HBO_S) |	\
+	 (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |	\
+	 (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_L4E_S) |	\
+	 (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S) |	\
+	 (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_S) |	\
+	 (1 << IAVF_RX_FLEX_DESC_STATUS0_RXE_S))
+
+/* Rx L3/L4 checksum */
+static inline uint64_t
+iavf_rxd_error_to_pkt_flags(uint16_t stat_err0)
+{
+	uint64_t flags = 0;
+
+	/* check if HW has decoded the packet and checksum */
+	if (unlikely(!(stat_err0 & (1 << IAVF_RX_FLEX_DESC_STATUS0_L3L4P_S))))
+		return 0;
+
+	if (likely(!(stat_err0 & IAVF_RX_FLEX_ERR0_BITS))) {
+		flags |= (PKT_RX_IP_CKSUM_GOOD | PKT_RX_L4_CKSUM_GOOD);
+		return flags;
+	}
+
+	if (unlikely(stat_err0 & (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_IPE_S)))
+		flags |= PKT_RX_IP_CKSUM_BAD;
+	else
+		flags |= PKT_RX_IP_CKSUM_GOOD;
+
+	if (unlikely(stat_err0 & (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_L4E_S)))
+		flags |= PKT_RX_L4_CKSUM_BAD;
+	else
+		flags |= PKT_RX_L4_CKSUM_GOOD;
+
+	if (unlikely(stat_err0 & (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_EIPE_S)))
+		flags |= PKT_RX_EIP_CKSUM_BAD;
+
+	return flags;
+}
+
 static inline void
 iavf_rxd_to_vlan_tci(struct rte_mbuf *mb, volatile union iavf_rx_desc *rxdp)
 {
@@ -740,6 +968,21 @@ iavf_flex_rxd_to_vlan_tci(struct rte_mbuf *mb,
 	} else {
 		mb->vlan_tci = 0;
 	}
+
+#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+	if (rte_le_to_cpu_16(rxdp->wb.status_error1) &
+	    (1 << IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S)) {
+		mb->ol_flags |= PKT_RX_QINQ_STRIPPED | PKT_RX_QINQ |
+				PKT_RX_VLAN_STRIPPED | PKT_RX_VLAN;
+		mb->vlan_tci_outer = mb->vlan_tci;
+		mb->vlan_tci = rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd);
+		PMD_RX_LOG(DEBUG, "Descriptor l2tag2_1: %u, l2tag2_2: %u",
+			   rte_le_to_cpu_16(rxdp->wb.l2tag2_1st),
+			   rte_le_to_cpu_16(rxdp->wb.l2tag2_2nd));
+	} else {
+		mb->vlan_tci_outer = 0;
+	}
+#endif
 }
 
 /* Translate the rx descriptor status and error fields to pkt flags */
@@ -804,30 +1047,6 @@ iavf_rxd_build_fdir(volatile union iavf_rx_desc *rxdp, struct rte_mbuf *mb)
 	return flags;
 }
 
-
-/* Translate the rx flex descriptor status to pkt flags */
-static inline void
-iavf_rxd_to_pkt_fields(struct rte_mbuf *mb,
-		       volatile union iavf_rx_flex_desc *rxdp)
-{
-	volatile struct iavf_32b_rx_flex_desc_comms_ovs *desc =
-			(volatile struct iavf_32b_rx_flex_desc_comms_ovs *)rxdp;
-#ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
-	uint16_t stat_err;
-
-	stat_err = rte_le_to_cpu_16(desc->status_error0);
-	if (likely(stat_err & (1 << IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_S))) {
-		mb->ol_flags |= PKT_RX_RSS_HASH;
-		mb->hash.rss = rte_le_to_cpu_32(desc->rss_hash);
-	}
-#endif
-
-	if (desc->flow_id != 0xFFFFFFFF) {
-		mb->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
-		mb->hash.fdir.hi = rte_le_to_cpu_32(desc->flow_id);
-	}
-}
-
 #define IAVF_RX_FLEX_ERR0_BITS	\
 	((1 << IAVF_RX_FLEX_DESC_STATUS0_HBO_S) |	\
 	 (1 << IAVF_RX_FLEX_DESC_STATUS0_XSUM_IPE_S) |	\
@@ -1082,7 +1301,7 @@ iavf_recv_pkts_flex_rxd(void *rx_queue,
 		rxm->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M &
 			rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)];
 		iavf_flex_rxd_to_vlan_tci(rxm, &rxd);
-		iavf_rxd_to_pkt_fields(rxm, &rxd);
+		rxq->rxd_to_pkt_fields(rxq, rxm, &rxd);
 		pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0);
 		rxm->ol_flags |= pkt_flags;
 
@@ -1223,7 +1442,7 @@ iavf_recv_scattered_pkts_flex_rxd(void *rx_queue, struct rte_mbuf **rx_pkts,
 		first_seg->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M &
 			rte_le_to_cpu_16(rxd.wb.ptype_flex_flags0)];
 		iavf_flex_rxd_to_vlan_tci(first_seg, &rxd);
-		iavf_rxd_to_pkt_fields(first_seg, &rxd);
+		rxq->rxd_to_pkt_fields(rxq, first_seg, &rxd);
 		pkt_flags = iavf_flex_rxd_error_to_pkt_flags(rx_stat_err0);
 
 		first_seg->ol_flags |= pkt_flags;
@@ -1460,7 +1679,7 @@ iavf_rx_scan_hw_ring_flex_rxd(struct iavf_rx_queue *rxq)
 			mb->packet_type = ptype_tbl[IAVF_RX_FLEX_DESC_PTYPE_M &
 				rte_le_to_cpu_16(rxdp[j].wb.ptype_flex_flags0)];
 			iavf_flex_rxd_to_vlan_tci(mb, &rxdp[j]);
-			iavf_rxd_to_pkt_fields(mb, &rxdp[j]);
+			rxq->rxd_to_pkt_fields(rxq, mb, &rxdp[j]);
 			stat_err0 = rte_le_to_cpu_16(rxdp[j].wb.status_error0);
 			pkt_flags = iavf_flex_rxd_error_to_pkt_flags(stat_err0);
 
@@ -1652,7 +1871,7 @@ rx_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	if (rxq->rx_nb_avail)
 		return iavf_rx_fill_from_stage(rxq, rx_pkts, nb_pkts);
 
-	if (rxq->rxdid == IAVF_RXDID_COMMS_OVS_1)
+	if (rxq->rxdid >= IAVF_RXDID_FLEX_NIC && rxq->rxdid <= IAVF_RXDID_LAST)
 		nb_rx = (uint16_t)iavf_rx_scan_hw_ring_flex_rxd(rxq);
 	else
 		nb_rx = (uint16_t)iavf_rx_scan_hw_ring(rxq);
@@ -2100,6 +2319,7 @@ iavf_set_rx_function(struct rte_eth_dev *dev)
 	struct iavf_adapter *adapter =
 		IAVF_DEV_PRIVATE_TO_ADAPTER(dev->data->dev_private);
 	struct iavf_info *vf = IAVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
+
 #ifdef RTE_ARCH_X86
 	struct iavf_rx_queue *rxq;
 	int i;
diff --git a/drivers/net/iavf/iavf_rxtx.h b/drivers/net/iavf/iavf_rxtx.h
index 59625a979..577df3c1b 100644
--- a/drivers/net/iavf/iavf_rxtx.h
+++ b/drivers/net/iavf/iavf_rxtx.h
@@ -57,110 +57,6 @@
 #define IAVF_TX_OFFLOAD_NOTSUP_MASK \
 		(PKT_TX_OFFLOAD_MASK ^ IAVF_TX_OFFLOAD_MASK)
 
-/* HW desc structure, both 16-byte and 32-byte types are supported */
-#ifdef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
-#define iavf_rx_desc iavf_16byte_rx_desc
-#define iavf_rx_flex_desc iavf_16b_rx_flex_desc
-#else
-#define iavf_rx_desc iavf_32byte_rx_desc
-#define iavf_rx_flex_desc iavf_32b_rx_flex_desc
-#endif
-
-struct iavf_rxq_ops {
-	void (*release_mbufs)(struct iavf_rx_queue *rxq);
-};
-
-struct iavf_txq_ops {
-	void (*release_mbufs)(struct iavf_tx_queue *txq);
-};
-
-/* Structure associated with each Rx queue. */
-struct iavf_rx_queue {
-	struct rte_mempool *mp;       /* mbuf pool to populate Rx ring */
-	const struct rte_memzone *mz; /* memzone for Rx ring */
-	volatile union iavf_rx_desc *rx_ring; /* Rx ring virtual address */
-	uint64_t rx_ring_phys_addr;   /* Rx ring DMA address */
-	struct rte_mbuf **sw_ring;     /* address of SW ring */
-	uint16_t nb_rx_desc;          /* ring length */
-	uint16_t rx_tail;             /* current value of tail */
-	volatile uint8_t *qrx_tail;   /* register address of tail */
-	uint16_t rx_free_thresh;      /* max free RX desc to hold */
-	uint16_t nb_rx_hold;          /* number of held free RX desc */
-	struct rte_mbuf *pkt_first_seg; /* first segment of current packet */
-	struct rte_mbuf *pkt_last_seg;  /* last segment of current packet */
-	struct rte_mbuf fake_mbuf;      /* dummy mbuf */
-	uint8_t rxdid;
-
-	/* used for VPMD */
-	uint16_t rxrearm_nb;       /* number of remaining to be re-armed */
-	uint16_t rxrearm_start;    /* the idx we start the re-arming from */
-	uint64_t mbuf_initializer; /* value to init mbufs */
-
-	/* for rx bulk */
-	uint16_t rx_nb_avail;      /* number of staged packets ready */
-	uint16_t rx_next_avail;    /* index of next staged packets */
-	uint16_t rx_free_trigger;  /* triggers rx buffer allocation */
-	struct rte_mbuf *rx_stage[IAVF_RX_MAX_BURST * 2]; /* store mbuf */
-
-	uint16_t port_id;        /* device port ID */
-	uint8_t crc_len;        /* 0 if CRC stripped, 4 otherwise */
-	uint8_t fdir_enabled;   /* 0 if FDIR disabled, 1 when enabled */
-	uint16_t queue_id;      /* Rx queue index */
-	uint16_t rx_buf_len;    /* The packet buffer size */
-	uint16_t rx_hdr_len;    /* The header buffer size */
-	uint16_t max_pkt_len;   /* Maximum packet length */
-	struct iavf_vsi *vsi; /**< the VSI this queue belongs to */
-
-	bool q_set;             /* if rx queue has been configured */
-	bool rx_deferred_start; /* don't start this queue in dev start */
-	const struct iavf_rxq_ops *ops;
-};
-
-struct iavf_tx_entry {
-	struct rte_mbuf *mbuf;
-	uint16_t next_id;
-	uint16_t last_id;
-};
-
-/* Structure associated with each TX queue. */
-struct iavf_tx_queue {
-	const struct rte_memzone *mz;  /* memzone for Tx ring */
-	volatile struct iavf_tx_desc *tx_ring; /* Tx ring virtual address */
-	uint64_t tx_ring_phys_addr;    /* Tx ring DMA address */
-	struct iavf_tx_entry *sw_ring;  /* address array of SW ring */
-	uint16_t nb_tx_desc;           /* ring length */
-	uint16_t tx_tail;              /* current value of tail */
-	volatile uint8_t *qtx_tail;    /* register address of tail */
-	/* number of used desc since RS bit set */
-	uint16_t nb_used;
-	uint16_t nb_free;
-	uint16_t last_desc_cleaned;    /* last desc have been cleaned*/
-	uint16_t free_thresh;
-	uint16_t rs_thresh;
-
-	uint16_t port_id;
-	uint16_t queue_id;
-	uint64_t offloads;
-	uint16_t next_dd;              /* next to set RS, for VPMD */
-	uint16_t next_rs;              /* next to check DD,  for VPMD */
-
-	bool q_set;                    /* if rx queue has been configured */
-	bool tx_deferred_start;        /* don't start this queue in dev start */
-	const struct iavf_txq_ops *ops;
-};
-
-/* Offload features */
-union iavf_tx_offload {
-	uint64_t data;
-	struct {
-		uint64_t l2_len:7; /* L2 (MAC) Header Length. */
-		uint64_t l3_len:9; /* L3 (IP) Header Length. */
-		uint64_t l4_len:8; /* L4 Header Length. */
-		uint64_t tso_segsz:16; /* TCP TSO segment size */
-		/* uint64_t unused : 24; */
-	};
-};
-
 /* Rx Flex Descriptors
  * These descriptors are used instead of the legacy version descriptors
  */
@@ -331,6 +227,7 @@ enum iavf_rxdid {
 	IAVF_RXDID_COMMS_AUX_TCP	= 21,
 	IAVF_RXDID_COMMS_OVS_1		= 22,
 	IAVF_RXDID_COMMS_OVS_2		= 23,
+	IAVF_RXDID_COMMS_AUX_IP_OFFSET	= 25,
 	IAVF_RXDID_LAST			= 63,
 };
 
@@ -355,12 +252,139 @@ enum iavf_rx_flex_desc_status_error_0_bits {
 	IAVF_RX_FLEX_DESC_STATUS0_LAST /* this entry must be last!!! */
 };
 
+enum iavf_rx_flex_desc_status_error_1_bits {
+	/* Note: These are predefined bit offsets */
+	IAVF_RX_FLEX_DESC_STATUS1_CPM_S = 0, /* 4 bits */
+	IAVF_RX_FLEX_DESC_STATUS1_NAT_S = 4,
+	IAVF_RX_FLEX_DESC_STATUS1_CRYPTO_S = 5,
+	/* [10:6] reserved */
+	IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_S = 11,
+	IAVF_RX_FLEX_DESC_STATUS1_XTRMD2_VALID_S = 12,
+	IAVF_RX_FLEX_DESC_STATUS1_XTRMD3_VALID_S = 13,
+	IAVF_RX_FLEX_DESC_STATUS1_XTRMD4_VALID_S = 14,
+	IAVF_RX_FLEX_DESC_STATUS1_XTRMD5_VALID_S = 15,
+	IAVF_RX_FLEX_DESC_STATUS1_LAST /* this entry must be last!!! */
+};
+
 /* for iavf_32b_rx_flex_desc.ptype_flex_flags0 member */
 #define IAVF_RX_FLEX_DESC_PTYPE_M	(0x3FF) /* 10-bits */
 
 /* for iavf_32b_rx_flex_desc.pkt_len member */
 #define IAVF_RX_FLX_DESC_PKT_LEN_M	(0x3FFF) /* 14-bits */
 
+/* HW desc structure, both 16-byte and 32-byte types are supported */
+#ifdef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
+#define iavf_rx_desc iavf_16byte_rx_desc
+#define iavf_rx_flex_desc iavf_16b_rx_flex_desc
+#else
+#define iavf_rx_desc iavf_32byte_rx_desc
+#define iavf_rx_flex_desc iavf_32b_rx_flex_desc
+#endif
+
+typedef void (*iavf_rxd_to_pkt_fields_t)(struct iavf_rx_queue *rxq,
+				struct rte_mbuf *mb,
+				volatile union iavf_rx_flex_desc *rxdp);
+
+struct iavf_rxq_ops {
+	void (*release_mbufs)(struct iavf_rx_queue *rxq);
+};
+
+struct iavf_txq_ops {
+	void (*release_mbufs)(struct iavf_tx_queue *txq);
+};
+
+/* Structure associated with each Rx queue. */
+struct iavf_rx_queue {
+	struct rte_mempool *mp;       /* mbuf pool to populate Rx ring */
+	const struct rte_memzone *mz; /* memzone for Rx ring */
+	volatile union iavf_rx_desc *rx_ring; /* Rx ring virtual address */
+	uint64_t rx_ring_phys_addr;   /* Rx ring DMA address */
+	struct rte_mbuf **sw_ring;     /* address of SW ring */
+	uint16_t nb_rx_desc;          /* ring length */
+	uint16_t rx_tail;             /* current value of tail */
+	volatile uint8_t *qrx_tail;   /* register address of tail */
+	uint16_t rx_free_thresh;      /* max free RX desc to hold */
+	uint16_t nb_rx_hold;          /* number of held free RX desc */
+	struct rte_mbuf *pkt_first_seg; /* first segment of current packet */
+	struct rte_mbuf *pkt_last_seg;  /* last segment of current packet */
+	struct rte_mbuf fake_mbuf;      /* dummy mbuf */
+	uint8_t rxdid;
+
+	/* used for VPMD */
+	uint16_t rxrearm_nb;       /* number of remaining to be re-armed */
+	uint16_t rxrearm_start;    /* the idx we start the re-arming from */
+	uint64_t mbuf_initializer; /* value to init mbufs */
+
+	/* for rx bulk */
+	uint16_t rx_nb_avail;      /* number of staged packets ready */
+	uint16_t rx_next_avail;    /* index of next staged packets */
+	uint16_t rx_free_trigger;  /* triggers rx buffer allocation */
+	struct rte_mbuf *rx_stage[IAVF_RX_MAX_BURST * 2]; /* store mbuf */
+
+	uint16_t port_id;        /* device port ID */
+	uint8_t crc_len;        /* 0 if CRC stripped, 4 otherwise */
+	uint8_t fdir_enabled;   /* 0 if FDIR disabled, 1 when enabled */
+	uint16_t queue_id;      /* Rx queue index */
+	uint16_t rx_buf_len;    /* The packet buffer size */
+	uint16_t rx_hdr_len;    /* The header buffer size */
+	uint16_t max_pkt_len;   /* Maximum packet length */
+	struct iavf_vsi *vsi; /**< the VSI this queue belongs to */
+
+	bool q_set;             /* if rx queue has been configured */
+	bool rx_deferred_start; /* don't start this queue in dev start */
+	const struct iavf_rxq_ops *ops;
+	uint8_t flex_desc; /* flexible descriptor type */
+	uint64_t xtr_ol_flag;
+		/* flexible descriptor metadata extraction offload flag */
+	iavf_rxd_to_pkt_fields_t rxd_to_pkt_fields;
+				/* handle flexible descriptor by RXDID */
+};
+
+struct iavf_tx_entry {
+	struct rte_mbuf *mbuf;
+	uint16_t next_id;
+	uint16_t last_id;
+};
+
+/* Structure associated with each TX queue. */
+struct iavf_tx_queue {
+	const struct rte_memzone *mz;  /* memzone for Tx ring */
+	volatile struct iavf_tx_desc *tx_ring; /* Tx ring virtual address */
+	uint64_t tx_ring_phys_addr;    /* Tx ring DMA address */
+	struct iavf_tx_entry *sw_ring;  /* address array of SW ring */
+	uint16_t nb_tx_desc;           /* ring length */
+	uint16_t tx_tail;              /* current value of tail */
+	volatile uint8_t *qtx_tail;    /* register address of tail */
+	/* number of used desc since RS bit set */
+	uint16_t nb_used;
+	uint16_t nb_free;
+	uint16_t last_desc_cleaned;    /* last desc have been cleaned*/
+	uint16_t free_thresh;
+	uint16_t rs_thresh;
+
+	uint16_t port_id;
+	uint16_t queue_id;
+	uint64_t offloads;
+	uint16_t next_dd;              /* next to set RS, for VPMD */
+	uint16_t next_rs;              /* next to check DD,  for VPMD */
+
+	bool q_set;                    /* if rx queue has been configured */
+	bool tx_deferred_start;        /* don't start this queue in dev start */
+	const struct iavf_txq_ops *ops;
+};
+
+/* Offload features */
+union iavf_tx_offload {
+	uint64_t data;
+	struct {
+		uint64_t l2_len:7; /* L2 (MAC) Header Length. */
+		uint64_t l3_len:9; /* L3 (IP) Header Length. */
+		uint64_t l4_len:8; /* L4 Header Length. */
+		uint64_t tso_segsz:16; /* TCP TSO segment size */
+		/* uint64_t unused : 24; */
+	};
+};
+
 int iavf_dev_rx_queue_setup(struct rte_eth_dev *dev,
 			   uint16_t queue_idx,
 			   uint16_t nb_desc,
@@ -438,6 +462,8 @@ int iavf_tx_vec_dev_check(struct rte_eth_dev *dev);
 int iavf_rxq_vec_setup(struct iavf_rx_queue *rxq);
 int iavf_txq_vec_setup(struct iavf_tx_queue *txq);
 
+uint8_t iavf_flex_desc_type_to_rxdid(uint8_t xtr_type);
+
 const uint32_t *iavf_get_default_ptype_table(void);
 
 static inline
diff --git a/drivers/net/iavf/iavf_rxtx_vec_common.h b/drivers/net/iavf/iavf_rxtx_vec_common.h
index 25bb502de..58cce7a9d 100644
--- a/drivers/net/iavf/iavf_rxtx_vec_common.h
+++ b/drivers/net/iavf/iavf_rxtx_vec_common.h
@@ -224,6 +224,9 @@ iavf_rx_vec_queue_default(struct iavf_rx_queue *rxq)
 	if (rxq->nb_rx_desc % rxq->rx_free_thresh)
 		return -1;
 
+	if (rxq->flex_desc != IAVF_FLEX_DESC_NONE)
+		return -1;
+
 	return 0;
 }
 
diff --git a/drivers/net/iavf/iavf_vchnl.c b/drivers/net/iavf/iavf_vchnl.c
index 76f8e38d1..7981dfa30 100644
--- a/drivers/net/iavf/iavf_vchnl.c
+++ b/drivers/net/iavf/iavf_vchnl.c
@@ -647,25 +647,27 @@ iavf_configure_queues(struct iavf_adapter *adapter)
 
 #ifndef RTE_LIBRTE_IAVF_16BYTE_RX_DESC
 		if (vf->vf_res->vf_cap_flags &
-			VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC &&
-			vf->supported_rxdid & BIT(IAVF_RXDID_COMMS_OVS_1)) {
-			vc_qp->rxq.rxdid = IAVF_RXDID_COMMS_OVS_1;
-			PMD_DRV_LOG(NOTICE, "request RXDID == %d in "
-					"Queue[%d]", vc_qp->rxq.rxdid, i);
+		    VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC &&
+		    vf->supported_rxdid & BIT(rxq[i]->rxdid)) {
+			vc_qp->rxq.rxdid = rxq[i]->rxdid;
+			PMD_DRV_LOG(NOTICE, "request RXDID[%d] in Queue[%d]",
+				    vc_qp->rxq.rxdid, i);
 		} else {
+			PMD_DRV_LOG(NOTICE, "RXDID[%d] is not supported, "
+				    "request default RXDID[%d] in Queue[%d]",
+				    rxq[i]->rxdid, IAVF_RXDID_LEGACY_1, i);
 			vc_qp->rxq.rxdid = IAVF_RXDID_LEGACY_1;
-			PMD_DRV_LOG(NOTICE, "request RXDID == %d in "
-					"Queue[%d]", vc_qp->rxq.rxdid, i);
 		}
 #else
 		if (vf->vf_res->vf_cap_flags &
 			VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC &&
 			vf->supported_rxdid & BIT(IAVF_RXDID_LEGACY_0)) {
 			vc_qp->rxq.rxdid = IAVF_RXDID_LEGACY_0;
-			PMD_DRV_LOG(NOTICE, "request RXDID == %d in "
-					"Queue[%d]", vc_qp->rxq.rxdid, i);
+			PMD_DRV_LOG(NOTICE, "request RXDID[%d] in Queue[%d]",
+				    vc_qp->rxq.rxdid, i);
 		} else {
-			PMD_DRV_LOG(ERR, "RXDID == 0 is not supported");
+			PMD_DRV_LOG(ERR, "RXDID[%d] is not supported",
+				    IAVF_RXDID_LEGACY_0);
 			return -1;
 		}
 #endif
diff --git a/drivers/net/iavf/meson.build b/drivers/net/iavf/meson.build
index a3fad363d..cd5159332 100644
--- a/drivers/net/iavf/meson.build
+++ b/drivers/net/iavf/meson.build
@@ -35,3 +35,5 @@ if arch_subdir == 'x86'
 		objs += iavf_avx2_lib.extract_objects('iavf_rxtx_vec_avx2.c')
 	endif
 endif
+
+install_headers('rte_pmd_iavf.h')
diff --git a/drivers/net/iavf/rte_pmd_iavf.h b/drivers/net/iavf/rte_pmd_iavf.h
new file mode 100644
index 000000000..dddb4340a
--- /dev/null
+++ b/drivers/net/iavf/rte_pmd_iavf.h
@@ -0,0 +1,250 @@
+/* SPDX-Liavfnse-Identifier: BSD-3-Clause
+ * Copyright(c) 2019 Intel Corporation
+ */
+
+#ifndef _RTE_PMD_IAVF_H_
+#define _RTE_PMD_IAVF_H_
+
+/**
+ * @file rte_pmd_iavf.h
+ *
+ * iavf PMD specific functions.
+ *
+ * @b EXPERIMENTAL: this API may change, or be removed, without prior notiavf
+ *
+ */
+
+#include <stdio.h>
+#include <rte_mbuf.h>
+#include <rte_mbuf_dyn.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+/**
+ * The supported network flexible descriptor's extraction metadata format.
+ */
+union rte_net_iavf_flex_desc_metadata {
+	uint32_t metadata;
+
+	struct {
+		uint16_t data0;
+		uint16_t data1;
+	} raw;
+
+	struct {
+		uint16_t stag_vid:12,
+			 stag_dei:1,
+			 stag_pcp:3;
+		uint16_t ctag_vid:12,
+			 ctag_dei:1,
+			 ctag_pcp:3;
+	} vlan;
+
+	struct {
+		uint16_t protocol:8,
+			 ttl:8;
+		uint16_t tos:8,
+			 ihl:4,
+			 version:4;
+	} ipv4;
+
+	struct {
+		uint16_t hoplimit:8,
+			 nexthdr:8;
+		uint16_t flowhi4:4,
+			 tc:8,
+			 version:4;
+	} ipv6;
+
+	struct {
+		uint16_t flowlo16;
+		uint16_t flowhi4:4,
+			 tc:8,
+			 version:4;
+	} ipv6_flow;
+
+	struct {
+		uint16_t fin:1,
+			 syn:1,
+			 rst:1,
+			 psh:1,
+			 ack:1,
+			 urg:1,
+			 ece:1,
+			 cwr:1,
+			 res1:4,
+			 doff:4;
+		uint16_t rsvd;
+	} tcp;
+
+	uint32_t ip_ofs;
+};
+
+/* Offset of mbuf dynamic field for flexible descriptor's extraction data */
+extern int rte_net_iavf_dynfield_flex_desc_metadata_offs;
+
+/* Mask of mbuf dynamic flags for flexible descriptor's extraction type */
+extern uint64_t rte_net_iavf_dynflag_flex_desc_vlan_mask;
+extern uint64_t rte_net_iavf_dynflag_flex_desc_ipv4_mask;
+extern uint64_t rte_net_iavf_dynflag_flex_desc_ipv6_mask;
+extern uint64_t rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask;
+extern uint64_t rte_net_iavf_dynflag_flex_desc_tcp_mask;
+extern uint64_t rte_net_iavf_dynflag_flex_desc_ip_offset_mask;
+
+/**
+ * The mbuf dynamic field pointer for flexible descriptor's extraction metadata.
+ */
+#define RTE_NET_IAVF_DYNF_FLEX_DESC_METADATA(m) \
+	RTE_MBUF_DYNFIELD((m), \
+			  rte_net_iavf_dynfield_flex_desc_metadata_offs, \
+			  uint32_t *)
+
+/**
+ * The mbuf dynamic flag for VLAN protocol extraction metadata, it is valid
+ * when dev_args 'flex_desc' has 'vlan' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_VLAN \
+	(rte_net_iavf_dynflag_flex_desc_vlan_mask)
+
+/**
+ * The mbuf dynamic flag for IPv4 protocol extraction metadata, it is valid
+ * when dev_args 'flex_desc' has 'ipv4' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV4 \
+	(rte_net_iavf_dynflag_flex_desc_ipv4_mask)
+
+/**
+ * The mbuf dynamic flag for IPv6 protocol extraction metadata, it is valid
+ * when dev_args 'flex_desc' has 'ipv6' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV6 \
+	(rte_net_iavf_dynflag_flex_desc_ipv6_mask)
+
+/**
+ * The mbuf dynamic flag for IPv6 with flow protocol extraction metadata, it is
+ * valid when dev_args 'flex_desc' has 'ipv6_flow' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV6_FLOW \
+	(rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask)
+
+/**
+ * The mbuf dynamic flag for TCP protocol extraction metadata, it is valid
+ * when dev_args 'flex_desc' has 'tcp' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_TCP \
+	(rte_net_iavf_dynflag_flex_desc_tcp_mask)
+
+/**
+ * The mbuf dynamic flag for IP_OFFSET extraction metadata, it is valid
+ * when dev_args 'flex_desc' has 'ip_offset' specified.
+ */
+#define RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IP_OFFSET \
+	(rte_net_iavf_dynflag_flex_desc_ip_offset_mask)
+
+/**
+ * Check if mbuf dynamic field for flexible descriptor's extraction metadata
+ * is registered.
+ *
+ * @return
+ *   True if registered, false otherwise.
+ */
+__rte_experimental
+static __rte_always_inline int
+rte_net_iavf_dynf_flex_desc_metadata_avail(void)
+{
+	return rte_net_iavf_dynfield_flex_desc_metadata_offs != -1;
+}
+
+/**
+ * Get the mbuf dynamic field for flexible descriptor's extraction metadata.
+ *
+ * @param m
+ *    The pointer to the mbuf.
+ * @return
+ *   The saved protocol extraction metadata.
+ */
+__rte_experimental
+static __rte_always_inline uint32_t
+rte_net_iavf_dynf_flex_desc_metadata_get(struct rte_mbuf *m)
+{
+	return *RTE_NET_IAVF_DYNF_FLEX_DESC_METADATA(m);
+}
+
+/**
+ * Dump the mbuf dynamic field for flexible descriptor's extraction metadata.
+ *
+ * @param m
+ *    The pointer to the mbuf.
+ */
+__rte_experimental
+static inline void
+rte_net_iavf_dump_flex_desc_metadata(struct rte_mbuf *m)
+{
+	union rte_net_iavf_flex_desc_metadata data;
+
+	if (!rte_net_iavf_dynf_flex_desc_metadata_avail())
+		return;
+
+	data.metadata = rte_net_iavf_dynf_flex_desc_metadata_get(m);
+
+	if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_VLAN)
+		printf(" - Flexible descriptor's Metadata: [0x%04x:0x%04x],"
+		       "vlan,stag=%u:%u:%u,ctag=%u:%u:%u",
+		       data.raw.data0, data.raw.data1,
+		       data.vlan.stag_pcp,
+		       data.vlan.stag_dei,
+		       data.vlan.stag_vid,
+		       data.vlan.ctag_pcp,
+		       data.vlan.ctag_dei,
+		       data.vlan.ctag_vid);
+	else if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV4)
+		printf(" - Flexible descriptor's Metadata: [0x%04x:0x%04x],"
+		       "ipv4,ver=%u,hdrlen=%u,tos=%u,ttl=%u,proto=%u",
+		       data.raw.data0, data.raw.data1,
+		       data.ipv4.version,
+		       data.ipv4.ihl,
+		       data.ipv4.tos,
+		       data.ipv4.ttl,
+		       data.ipv4.protocol);
+	else if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV6)
+		printf(" - Flexible descriptor's Metadata: [0x%04x:0x%04x],"
+		       "ipv6,ver=%u,tc=%u,flow_hi4=0x%x,nexthdr=%u,hoplimit=%u",
+		       data.raw.data0, data.raw.data1,
+		       data.ipv6.version,
+		       data.ipv6.tc,
+		       data.ipv6.flowhi4,
+		       data.ipv6.nexthdr,
+		       data.ipv6.hoplimit);
+	else if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IPV6_FLOW)
+		printf(" - Flexible descriptor's Metadata: [0x%04x:0x%04x],"
+		       "ipv6_flow,ver=%u,tc=%u,flow=0x%x%04x",
+		       data.raw.data0, data.raw.data1,
+		       data.ipv6_flow.version,
+		       data.ipv6_flow.tc,
+		       data.ipv6_flow.flowhi4,
+		       data.ipv6_flow.flowlo16);
+	else if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_TCP)
+		printf(" - Flexible descriptor's Metadata: [0x%04x:0x%04x],"
+		       "tcp,doff=%u,flags=%s%s%s%s%s%s%s%s",
+		       data.raw.data0, data.raw.data1,
+		       data.tcp.doff,
+		       data.tcp.cwr ? "C" : "",
+		       data.tcp.ece ? "E" : "",
+		       data.tcp.urg ? "U" : "",
+		       data.tcp.ack ? "A" : "",
+		       data.tcp.psh ? "P" : "",
+		       data.tcp.rst ? "R" : "",
+		       data.tcp.syn ? "S" : "",
+		       data.tcp.fin ? "F" : "");
+	else if (m->ol_flags & RTE_IAVF_PKT_RX_DYNF_FLEX_DESC_IP_OFFSET)
+		printf(" - Flexible descriptor's Extraction: ip_offset=%u",
+		       data.ip_ofs);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_PMD_IAVF_H_ */
diff --git a/drivers/net/iavf/rte_pmd_iavf_version.map b/drivers/net/iavf/rte_pmd_iavf_version.map
index 4a76d1d52..6c821c88d 100644
--- a/drivers/net/iavf/rte_pmd_iavf_version.map
+++ b/drivers/net/iavf/rte_pmd_iavf_version.map
@@ -1,3 +1,16 @@
 DPDK_21 {
 	local: *;
 };
+
+EXPERIMENTAL {
+        global:
+
+        # added in 20.11
+        rte_net_iavf_dynfield_flex_desc_metadata_offs;
+        rte_net_iavf_dynflag_flex_desc_vlan_mask;
+        rte_net_iavf_dynflag_flex_desc_ipv4_mask;
+        rte_net_iavf_dynflag_flex_desc_ipv6_mask;
+        rte_net_iavf_dynflag_flex_desc_ipv6_flow_mask;
+        rte_net_iavf_dynflag_flex_desc_tcp_mask;
+        rte_net_iavf_dynflag_flex_desc_ip_offset_mask;
+};
-- 
2.20.1



More information about the dev mailing list