diff mbox series

[Intel-wired-lan,iwl-next,v4,09/12] iavf: refactor iavf_clean_rx_irq to support legacy and flex descriptors

Message ID 20240410121706.6223-10-mateusz.polchlopek@intel.com (mailing list archive)
State Superseded
Delegated to: Netdev Maintainers
Headers show
Series Add support for Rx timestamping for both ice and iavf drivers. | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Guessed tree name to be net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 942 this patch: 942
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 5 maintainers not CCed: pabeni@redhat.com jesse.brandeburg@intel.com kuba@kernel.org edumazet@google.com richardcochran@gmail.com
netdev/build_clang success Errors and warnings before: 953 this patch: 953
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 953 this patch: 953
netdev/checkpatch warning WARNING: line length of 83 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 119 this patch: 119
netdev/source_inline success Was 0 now: 0

Commit Message

Mateusz Polchlopek April 10, 2024, 12:17 p.m. UTC
From: Jacob Keller <jacob.e.keller@intel.com>

Using VIRTCHNL_VF_OFFLOAD_FLEX_DESC, the iAVF driver is capable of
negotiating to enable the advanced flexible descriptor layout. Add the
flexible NIC layout (RXDID=2) as a member of the Rx descriptor union.

Also add bit position definitions for the status and error indications
that are needed.

The iavf_clean_rx_irq function needs to extract a few fields from the Rx
descriptor, including the size, rx_ptype, and vlan_tag.
Move the extraction to a separate function that decodes the fields into
a structure. This will reduce the burden for handling multiple
descriptor types by keeping the relevant extraction logic in one place.

To support handling an additional descriptor format with minimal code
duplication, refactor Rx checksum handling so that the general logic
is separated from the bit calculations. Introduce an iavf_rx_desc_decoded
structure which holds the relevant bits decoded from the Rx descriptor.
This will enable implementing flexible descriptor handling without
duplicating the general logic twice.

Introduce an iavf_extract_flex_rx_fields, iavf_flex_rx_hash, and
iavf_flex_rx_csum functions which operate on the flexible NIC descriptor
format instead of the legacy 32 byte format. Based on the negotiated
RXDID, select the correct function for processing the Rx descriptors.

With this change, the Rx hot path should be functional when using either
the default legacy 32byte format or when we switch to the flexible NIC
layout.

Modify the Rx hot path to add support for the flexible descriptor
format and add request enabling Rx timestamps for all queues.

As in ice, make sure we bump the checksum level if the hardware detected
a packet type which could have an outer checksum. This is important
because hardware only verifies the inner checksum.

Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_txrx.c   | 354 +++++++++++++-----
 drivers/net/ethernet/intel/iavf/iavf_txrx.h   |   8 +
 drivers/net/ethernet/intel/iavf/iavf_type.h   | 149 ++++++--
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |   5 +
 4 files changed, 390 insertions(+), 126 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 32bb604a1382..e2f46e29945f 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -972,27 +972,33 @@  bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 	return true;
 }
 
+/* iavf_rx_csum_decoded
+ *
+ * Checksum offload bits decoded from the receive descriptor.
+ */
+struct iavf_rx_csum_decoded {
+	u8 l3l4p : 1;
+	u8 ipe : 1;
+	u8 eipe : 1;
+	u8 eudpe : 1;
+	u8 ipv6exadd : 1;
+	u8 l4e : 1;
+	u8 pprs : 1;
+	u8 nat : 1;
+};
+
 /**
- * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_csum - Indicate in skb if hw indicated a good checksum
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
+ * @ptype: decoded ptype information
+ * @csum_bits: decoded Rx descriptor information
  **/
-static void iavf_rx_checksum(struct iavf_vsi *vsi,
-			     struct sk_buff *skb,
-			     union iavf_rx_desc *rx_desc)
+static void iavf_rx_csum(struct iavf_vsi *vsi, struct sk_buff *skb,
+			 struct iavf_rx_ptype_decoded *ptype,
+			 struct iavf_rx_csum_decoded *csum_bits)
 {
-	struct iavf_rx_ptype_decoded decoded;
-	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
-	u8 ptype;
-	u64 qword;
-
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-	decoded = decode_rx_desc_ptype(ptype);
 
 	skb->ip_summed = CHECKSUM_NONE;
 
@@ -1003,42 +1009,45 @@  static void iavf_rx_checksum(struct iavf_vsi *vsi,
 		return;
 
 	/* did the hardware decode the packet and checksum? */
-	if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (!csum_bits->l3l4p)
 		return;
 
 	/* both known and outer_ip must be set for the below code to work */
-	if (!(decoded.known && decoded.outer_ip))
+	if (!(ptype->known && ptype->outer_ip))
 		return;
 
-	ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4);
-	ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
-	       (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6);
+	ipv4 = (ptype->outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
+		(ptype->outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4);
+	ipv6 = (ptype->outer_ip == IAVF_RX_PTYPE_OUTER_IP) &&
+		(ptype->outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6);
 
-	if (ipv4 &&
-	    (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
-			 BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
+	if (ipv4 && (csum_bits->ipe || csum_bits->eipe))
 		goto checksum_fail;
 
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (ipv6 &&
-	    rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
-		/* don't increment checksum err here, non-fatal err */
+	if (ipv6 && csum_bits->ipv6exadd)
 		return;
 
 	/* there was some L4 error, count error and punt packet to the stack */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
+	if (csum_bits->l4e)
 		goto checksum_fail;
 
 	/* handle packets that were not able to be checksummed due
 	 * to arrival speed, in this case the stack can compute
 	 * the csum.
 	 */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
+	if (csum_bits->pprs)
 		return;
 
+	/* If there is an outer header present that might contain a checksum
+	 * we need to bump the checksum level by 1 to reflect the fact that
+	 * we are indicating we validated the inner checksum.
+	 */
+	if (ptype->tunnel_type >= IAVF_RX_PTYPE_TUNNEL_IP_GRENAT)
+		skb->csum_level = 1;
+
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
-	switch (decoded.inner_prot) {
+	switch (ptype->inner_prot) {
 	case IAVF_RX_PTYPE_INNER_PROT_TCP:
 	case IAVF_RX_PTYPE_INNER_PROT_UDP:
 	case IAVF_RX_PTYPE_INNER_PROT_SCTP:
@@ -1054,13 +1063,89 @@  static void iavf_rx_checksum(struct iavf_vsi *vsi,
 	vsi->back->hw_csum_rx_error++;
 }
 
+/**
+ * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good cksum
+ * @vsi: the VSI we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ **/
+static void iavf_legacy_rx_csum(struct iavf_vsi *vsi,
+				struct sk_buff *skb,
+				union iavf_rx_desc *rx_desc)
+{
+	struct iavf_rx_csum_decoded csum_bits;
+	struct iavf_rx_ptype_decoded decoded;
+	u32 rx_error;
+	u64 qword;
+	u16 ptype;
+
+	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
+	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
+	decoded = decode_rx_desc_ptype(ptype);
+
+	csum_bits.ipe = FIELD_GET(IAVF_RX_DESC_ERROR_IPE_MASK, rx_error);
+	csum_bits.eipe = FIELD_GET(IAVF_RX_DESC_ERROR_EIPE_MASK, rx_error);
+	csum_bits.l4e = FIELD_GET(IAVF_RX_DESC_ERROR_L4E_MASK, rx_error);
+	csum_bits.pprs = FIELD_GET(IAVF_RX_DESC_ERROR_PPRS_MASK, rx_error);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RX_DESC_STATUS_L3L4P_MASK, rx_error);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RX_DESC_STATUS_IPV6EXADD_MASK,
+					rx_error);
+	csum_bits.nat = 0;
+	csum_bits.eudpe = 0;
+
+	iavf_rx_csum(vsi, skb, &decoded, &csum_bits);
+}
+
+/**
+ * iavf_flex_rx_csum - Indicate in skb if hw indicated a good cksum
+ * @vsi: the VSI we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ **/
+static void iavf_flex_rx_csum(struct iavf_vsi *vsi, struct sk_buff *skb,
+			      union iavf_rx_desc *rx_desc)
+{
+	struct iavf_rx_csum_decoded csum_bits;
+	struct iavf_rx_ptype_decoded decoded;
+	u16 rx_status0, ptype;
+
+	rx_status0 = le16_to_cpu(rx_desc->flex_wb.status_error0);
+	ptype = FIELD_GET(IAVF_RX_FLEX_DESC_PTYPE_M,
+			  le16_to_cpu(rx_desc->flex_wb.ptype_flexi_flags0));
+	decoded = decode_rx_desc_ptype(ptype);
+
+	csum_bits.ipe = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_XSUM_IPE_M,
+				  rx_status0);
+	csum_bits.eipe = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_XSUM_EIPE_M,
+				   rx_status0);
+	csum_bits.l4e = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_XSUM_L4E_M,
+				  rx_status0);
+	csum_bits.eudpe = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_M,
+				    rx_status0);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_L3L4P_M,
+				    rx_status0);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS0_IPV6EXADD_M,
+					rx_status0);
+	csum_bits.nat = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS1_NAT_M, rx_status0);
+	csum_bits.pprs = 0;
+
+	iavf_rx_csum(vsi, skb, &decoded, &csum_bits);
+}
+
 /**
  * iavf_ptype_to_htype - get a hash type
  * @ptype: the ptype value from the descriptor
  *
  * Returns a hash type to be used by skb_set_hash
  **/
-static int iavf_ptype_to_htype(u8 ptype)
+static int iavf_ptype_to_htype(u16 ptype)
 {
 	struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype);
 
@@ -1078,21 +1163,21 @@  static int iavf_ptype_to_htype(u8 ptype)
 }
 
 /**
- * iavf_rx_hash - set the hash value in the skb
+ * iavf_legacy_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
  * @rx_desc: specific descriptor
  * @skb: skb currently being received and modified
  * @rx_ptype: Rx packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
  **/
-static void iavf_rx_hash(struct iavf_ring *ring,
-			 union iavf_rx_desc *rx_desc,
-			 struct sk_buff *skb,
-			 u8 rx_ptype)
+static void iavf_legacy_rx_hash(struct iavf_ring *ring,
+				union iavf_rx_desc *rx_desc,
+				struct sk_buff *skb, u8 rx_ptype)
 {
+	const __le64 rss_mask = cpu_to_le64(IAVF_RX_DESC_STATUS_FLTSTAT_MASK);
 	u32 hash;
-	const __le64 rss_mask =
-		cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
-			    IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
 	if (!(ring->netdev->features & NETIF_F_RXHASH))
 		return;
@@ -1103,6 +1188,33 @@  static void iavf_rx_hash(struct iavf_ring *ring,
 	}
 }
 
+/**
+ * iavf_flex_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @rx_desc: specific descriptor
+ * @skb: skb currently being received and modified
+ * @rx_ptype: Rx packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ **/
+static void iavf_flex_rx_hash(struct iavf_ring *ring,
+			      union iavf_rx_desc *rx_desc,
+			      struct sk_buff *skb, u16 rx_ptype)
+{
+	__le16 status0;
+
+	if (!(ring->netdev->features & NETIF_F_RXHASH))
+		return;
+
+	status0 = rx_desc->flex_wb.status_error0;
+	if (status0 & cpu_to_le16(IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_M)) {
+		u32 hash = le32_to_cpu(rx_desc->flex_wb.rss_hash);
+
+		skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype));
+	}
+}
+
 /**
  * iavf_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: rx descriptor ring packet is being transacted on
@@ -1114,14 +1226,19 @@  static void iavf_rx_hash(struct iavf_ring *ring,
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  **/
-static void
-iavf_process_skb_fields(struct iavf_ring *rx_ring,
-			union iavf_rx_desc *rx_desc, struct sk_buff *skb,
-			u8 rx_ptype)
+static void iavf_process_skb_fields(struct iavf_ring *rx_ring,
+				    union iavf_rx_desc *rx_desc,
+				    struct sk_buff *skb, u16 rx_ptype)
 {
-	iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE) {
+		iavf_legacy_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+
+		iavf_legacy_rx_csum(rx_ring->vsi, skb, rx_desc);
+	} else {
+		iavf_flex_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
 
-	iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
+		iavf_flex_rx_csum(rx_ring->vsi, skb, rx_desc);
+	}
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
@@ -1448,7 +1565,7 @@  static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
 /**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
+ * @fields: Rx descriptor extracted fields
  * @skb: Current socket buffer containing buffer in progress
  *
  * This function updates next to clean.  If the buffer is an EOP buffer
@@ -1457,7 +1574,7 @@  static void iavf_put_rx_buffer(struct iavf_ring *rx_ring,
  * that this is in fact a non-EOP buffer.
  **/
 static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
-			    union iavf_rx_desc *rx_desc,
+			    struct iavf_rx_extracted *fields,
 			    struct sk_buff *skb)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
@@ -1469,8 +1586,7 @@  static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	prefetch(IAVF_RX_DESC(rx_ring, ntc));
 
 	/* if we are the last buffer then there is nothing else to do */
-#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
-	if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
+	if (likely(fields->end_of_packet))
 		return false;
 
 	rx_ring->rx_stats.non_eop_descs++;
@@ -1478,6 +1594,92 @@  static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	return true;
 }
 
+/**
+ * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ * @fields: storage for extracted values
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ */
+static void iavf_extract_legacy_rx_fields(struct iavf_ring *rx_ring,
+					  union iavf_rx_desc *rx_desc,
+					  struct iavf_rx_extracted *fields)
+{
+	u64 qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+
+	fields->size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+	fields->rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
+
+	if (qword & IAVF_RX_DESC_STATUS_L2TAG1P_MASK &&
+	    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
+		fields->vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
+
+	if (rx_desc->wb.qword2.ext_status &
+	    cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
+	    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
+		fields->vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+
+	fields->end_of_packet = FIELD_GET(IAVF_RX_DESC_STATUS_EOF_MASK, qword);
+	fields->rxe = FIELD_GET(BIT(IAVF_RXD_QW1_ERROR_SHIFT), qword);
+}
+
+/**
+ * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ * @fields: storage for extracted values
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+static void iavf_extract_flex_rx_fields(struct iavf_ring *rx_ring,
+					union iavf_rx_desc *rx_desc,
+					struct iavf_rx_extracted *fields)
+{
+	__le16 status0, status1, flexi_flags0;
+
+	fields->size = FIELD_GET(IAVF_RX_FLEX_DESC_PKT_LEN_M,
+				 le16_to_cpu(rx_desc->flex_wb.pkt_len));
+
+	flexi_flags0 = rx_desc->flex_wb.ptype_flexi_flags0;
+
+	fields->rx_ptype = FIELD_GET(IAVF_RX_FLEX_DESC_PTYPE_M,
+				     le16_to_cpu(flexi_flags0));
+
+	status0 = rx_desc->flex_wb.status_error0;
+	if (status0 & cpu_to_le16(IAVF_RX_FLEX_DESC_STATUS0_L2TAG1P_M) &&
+	    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
+		fields->vlan_tag = le16_to_cpu(rx_desc->flex_wb.l2tag1);
+
+	status1 = rx_desc->flex_wb.status_error1;
+	if (status1 & cpu_to_le16(IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_M) &&
+	    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
+		fields->vlan_tag = le16_to_cpu(rx_desc->flex_wb.l2tag2_2nd);
+
+	fields->end_of_packet = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS_ERR0_EOP_BIT,
+					  le16_to_cpu(status0));
+	fields->rxe = FIELD_GET(IAVF_RX_FLEX_DESC_STATUS_ERR0_RXE_BIT,
+				le16_to_cpu(status0));
+}
+
+static void iavf_extract_rx_fields(struct iavf_ring *rx_ring,
+				   union iavf_rx_desc *rx_desc,
+				   struct iavf_rx_extracted *fields)
+{
+	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE)
+		iavf_extract_legacy_rx_fields(rx_ring, rx_desc, fields);
+	else
+		iavf_extract_flex_rx_fields(rx_ring, rx_desc, fields);
+}
+
 /**
  * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
@@ -1498,12 +1700,9 @@  static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
+		struct iavf_rx_extracted fields = {};
 		struct iavf_rx_buffer *rx_buffer;
 		union iavf_rx_desc *rx_desc;
-		unsigned int size;
-		u16 vlan_tag = 0;
-		u8 rx_ptype;
-		u64 qword;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1514,39 +1713,32 @@  static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 
 		rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then the length will be non-zero
-		 */
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-
 		/* This memory barrier is needed to keep us from reading
 		 * any other fields out of the rx_desc until we have
 		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
-#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
-		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+		if (!iavf_test_staterr(rx_desc, IAVF_RX_DESC_STATUS_DD_MASK))
 			break;
 
-		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+		iavf_extract_rx_fields(rx_ring, rx_desc, &fields);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
-		rx_buffer = iavf_get_rx_buffer(rx_ring, size);
+		rx_buffer = iavf_get_rx_buffer(rx_ring, fields.size);
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(rx_ring, rx_buffer, skb, size);
+			iavf_add_rx_frag(rx_ring, rx_buffer, skb, fields.size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = iavf_build_skb(rx_ring, rx_buffer, size);
+			skb = iavf_build_skb(rx_ring, rx_buffer, fields.size);
 		else
-			skb = iavf_construct_skb(rx_ring, rx_buffer, size);
+			skb = iavf_construct_skb(rx_ring, rx_buffer,
+						 fields.size);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buff_failed++;
-			if (rx_buffer && size)
+			if (rx_buffer && fields.size)
 				rx_buffer->pagecnt_bias++;
 			break;
 		}
@@ -1554,15 +1746,14 @@  static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		iavf_put_rx_buffer(rx_ring, rx_buffer);
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb))
+		if (iavf_is_non_eop(rx_ring, &fields, skb))
 			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set, and
-		 * what we are doing here is actually checking
-		 * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
-		 * the error field
+		/* RXE field in descriptor is an indication of the MAC errors
+		 * (like CRC, alignment, oversize etc). If it is set then iavf
+		 * should finish.
 		 */
-		if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
+		if (unlikely(fields.rxe)) {
 			dev_kfree_skb_any(skb);
 			skb = NULL;
 			continue;
@@ -1576,22 +1767,11 @@  static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
 		/* populate checksum, VLAN, and protocol */
-		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
-		if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
-		    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
-		if (rx_desc->wb.qword2.ext_status &
-		    cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
-		    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.rx_ptype);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
-		iavf_receive_skb(rx_ring, skb, vlan_tag);
+		iavf_receive_skb(rx_ring, skb, fields.vlan_tag);
 		skb = NULL;
 
 		/* update budget accounting */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 97055c63e866..67e51b4883bc 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -170,6 +170,14 @@  static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
 		  cpu_to_le64(stat_err_bits));
 }
 
+struct iavf_rx_extracted {
+	unsigned int size;
+	u16 vlan_tag;
+	u16 rx_ptype;
+	u8 end_of_packet:1;
+	u8 rxe:1;
+};
+
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IAVF_RX_INCREMENT(r, i) \
 	do {					\
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index 2b6a207fa441..e80d1f7b3052 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -208,6 +208,45 @@  union iavf_16byte_rx_desc {
 	} wb;  /* writeback */
 };
 
+/* Rx Flex Descriptor NIC Profile
+ * RxDID Profile ID 2
+ * Flex-field 0: RSS hash lower 16-bits
+ * Flex-field 1: RSS hash upper 16-bits
+ * Flex-field 2: Flow ID lower 16-bits
+ * Flex-field 3: Flow ID higher 16-bits
+ * Flex-field 4: reserved, VLAN ID taken from L2Tag
+ */
+struct iavf_32byte_rx_flex_wb {
+	/* Qword 0 */
+	u8 rxdid;
+	u8 mir_id_umb_cast;
+	__le16 ptype_flexi_flags0;
+	__le16 pkt_len;
+	__le16 hdr_len_sph_flex_flags1;
+
+	/* Qword 1 */
+	__le16 status_error0;
+	__le16 l2tag1;
+	__le32 rss_hash;
+
+	/* Qword 2 */
+	__le16 status_error1;
+	u8 flexi_flags2;
+	u8 ts_low;
+	__le16 l2tag2_1st;
+	__le16 l2tag2_2nd;
+
+	/* Qword 3 */
+	__le32 flow_id;
+	union {
+		struct {
+			__le16 rsvd;
+			__le16 flow_id_ipv6;
+		} flex;
+		__le32 ts_high;
+	} flex_ts;
+};
+
 union iavf_32byte_rx_desc {
 	struct {
 		__le64  pkt_addr; /* Packet buffer address */
@@ -255,35 +294,34 @@  union iavf_32byte_rx_desc {
 			} hi_dword;
 		} qword3;
 	} wb;  /* writeback */
-};
+	struct iavf_32byte_rx_flex_wb flex_wb;
+};
+
+/* Note: These are predefined bit offsets */
+#define IAVF_RX_DESC_STATUS_DD_MASK		BIT(0)
+#define IAVF_RX_DESC_STATUS_EOF_MASK		BIT(1)
+#define IAVF_RX_DESC_STATUS_L2TAG1P_MASK	BIT(2)
+#define IAVF_RX_DESC_STATUS_L3L4P_MASK		BIT(3)
+#define IAVF_RX_DESC_STATUS_CRCP_MASK		BIT(4)
+#define IAVF_RX_DESC_STATUS_TSYNINDX_MASK	GENMASK_ULL(6, 5)
+#define IAVF_RX_DESC_STATUS_TSYNVALID_MASK	BIT(7)
+/* Note: Bit 8 is reserved in X710 and XL710 */
+#define IAVF_RX_DESC_STATUS_EXT_UDP_0_MASK	BIT(8)
+#define IAVF_RX_DESC_STATUS_UMBCAST_MASK	GENMASK_ULL(10, 9)
+#define IAVF_RX_DESC_STATUS_FLM_MASK		BIT(11)
+#define IAVF_RX_DESC_STATUS_FLTSTAT_MASK	GENMASK_ULL(13, 12)
+#define IAVF_RX_DESC_STATUS_LPBK_MASK		BIT(14)
+#define IAVF_RX_DESC_STATUS_IPV6EXADD_MASK	BIT(15)
+#define IAVF_RX_DESC_STATUS_RESERVED_MASK	GENMASK_ULL(17, 16)
+/* Note: For non-tunnel packets INT_UDP_0 is the right status for
+ * UDP header
+ */
+#define IAVF_RX_DESC_STATUS_INT_UDP_0_MASK	BIT(18)
 
-enum iavf_rx_desc_status_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_STATUS_DD_SHIFT		= 0,
-	IAVF_RX_DESC_STATUS_EOF_SHIFT		= 1,
-	IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT	= 2,
-	IAVF_RX_DESC_STATUS_L3L4P_SHIFT		= 3,
-	IAVF_RX_DESC_STATUS_CRCP_SHIFT		= 4,
-	IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT	= 5, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT	= 7,
-	/* Note: Bit 8 is reserved in X710 and XL710 */
-	IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT	= 8,
-	IAVF_RX_DESC_STATUS_UMBCAST_SHIFT	= 9, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_FLM_SHIFT		= 11,
-	IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT	= 12, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_LPBK_SHIFT		= 14,
-	IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
-	IAVF_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	/* Note: For non-tunnel packets INT_UDP_0 is the right status for
-	 * UDP header
-	 */
-	IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT	= 18,
-	IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
+#define IAVF_RX_FLEX_DESC_STATUS_ERR0_EOP_BIT	BIT(1)
+#define IAVF_RX_FLEX_DESC_STATUS_ERR0_RXE_BIT	BIT(10)
 
-#define IAVF_RXD_QW1_STATUS_SHIFT	0
-#define IAVF_RXD_QW1_STATUS_MASK	((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
-					 << IAVF_RXD_QW1_STATUS_SHIFT)
+#define IAVF_RXD_QW1_STATUS_MASK		(BIT(19) - 1)
 
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK  (0x3UL << \
@@ -303,18 +341,16 @@  enum iavf_rx_desc_fltstat_values {
 #define IAVF_RXD_QW1_ERROR_SHIFT	19
 #define IAVF_RXD_QW1_ERROR_MASK		(0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
 
-enum iavf_rx_desc_error_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_ERROR_RXE_SHIFT		= 0,
-	IAVF_RX_DESC_ERROR_RECIPE_SHIFT		= 1,
-	IAVF_RX_DESC_ERROR_HBO_SHIFT		= 2,
-	IAVF_RX_DESC_ERROR_L3L4E_SHIFT		= 3, /* 3 BITS */
-	IAVF_RX_DESC_ERROR_IPE_SHIFT		= 3,
-	IAVF_RX_DESC_ERROR_L4E_SHIFT		= 4,
-	IAVF_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
-	IAVF_RX_DESC_ERROR_PPRS_SHIFT		= 7
-};
+/* Note: These are predefined bit offsets */
+#define IAVF_RX_DESC_ERROR_RXE_MASK		BIT(0)
+#define IAVF_RX_DESC_ERROR_RECIPE_MASK		BIT(1)
+#define IAVF_RX_DESC_ERROR_HBO_MASK		BIT(2)
+#define IAVF_RX_DESC_ERROR_L3L4E_MASK		GENMASK_ULL(5, 3)
+#define IAVF_RX_DESC_ERROR_IPE_MASK		BIT(3)
+#define IAVF_RX_DESC_ERROR_L4E_MASK		BIT(4)
+#define IAVF_RX_DESC_ERROR_EIPE_MASK		BIT(5)
+#define IAVF_RX_DESC_ERROR_OVERSIZE_MASK	BIT(6)
+#define IAVF_RX_DESC_ERROR_PPRS_MASK		BIT(7)
 
 enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_NONE		= 0,
@@ -327,6 +363,41 @@  enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 #define IAVF_RXD_QW1_PTYPE_SHIFT	30
 #define IAVF_RXD_QW1_PTYPE_MASK		(0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
 
+/* for iavf_32byte_rx_flex_wb.ptype_flexi_flags0 member */
+#define IAVF_RX_FLEX_DESC_PTYPE_M      (0x3FF) /* 10-bits */
+
+/* for iavf_32byte_rx_flex_wb.pkt_length member */
+#define IAVF_RX_FLEX_DESC_PKT_LEN_M    (0x3FFF) /* 14-bits */
+
+/* Note: These are predefined bit offsets */
+#define IAVF_RX_FLEX_DESC_STATUS0_DD_M			BIT(0)
+#define IAVF_RX_FLEX_DESC_STATUS0_EOF_M			BIT(1)
+#define IAVF_RX_FLEX_DESC_STATUS0_HBO_M			BIT(2)
+#define IAVF_RX_FLEX_DESC_STATUS0_L3L4P_M		BIT(3)
+#define IAVF_RX_FLEX_DESC_STATUS0_XSUM_IPE_M		BIT(4)
+#define IAVF_RX_FLEX_DESC_STATUS0_XSUM_L4E_M		BIT(5)
+#define IAVF_RX_FLEX_DESC_STATUS0_XSUM_EIPE_M		BIT(6)
+#define IAVF_RX_FLEX_DESC_STATUS0_XSUM_EUDPE_M		BIT(7)
+#define IAVF_RX_FLEX_DESC_STATUS0_LPBK_M		BIT(8)
+#define IAVF_RX_FLEX_DESC_STATUS0_IPV6EXADD_M		BIT(9)
+#define IAVF_RX_FLEX_DESC_STATUS0_RXE_M			BIT(10)
+#define IAVF_RX_FLEX_DESC_STATUS0_CRCP_			BIT(11)
+#define IAVF_RX_FLEX_DESC_STATUS0_RSS_VALID_M		BIT(12)
+#define IAVF_RX_FLEX_DESC_STATUS0_L2TAG1P_M		BIT(13)
+#define IAVF_RX_FLEX_DESC_STATUS0_XTRMD0_VALID_M	BIT(14)
+#define IAVF_RX_FLEX_DESC_STATUS0_XTRMD1_VALID_M	BIT(15)
+
+/* Note: These are predefined bit offsets */
+#define IAVF_RX_FLEX_DESC_STATUS1_CPM_M			(0xFULL) /* 4 bits */
+#define IAVF_RX_FLEX_DESC_STATUS1_NAT_M			BIT(4)
+#define IAVF_RX_FLEX_DESC_STATUS1_CRYPTO_M		BIT(5)
+/* [10:6] reserved */
+#define IAVF_RX_FLEX_DESC_STATUS1_L2TAG2P_M		BIT(11)
+#define IAVF_RX_FLEX_DESC_STATUS1_XTRMD2_VALID_M	BIT(12)
+#define IAVF_RX_FLEX_DESC_STATUS1_XTRMD3_VALID_M	BIT(13)
+#define IAVF_RX_FLEX_DESC_STATUS1_XTRMD4_VALID_M	BIT(14)
+#define IAVF_RX_FLEX_DESC_STATUS1_XTRMD5_VALID_M	BIT(15)
+
 /* Packet type non-ip values */
 enum iavf_rx_l2_ptype {
 	IAVF_RX_PTYPE_L2_RESERVED			= 0,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index fde8b4bf56fb..0e005ae993ee 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -397,6 +397,7 @@  void iavf_configure_queues(struct iavf_adapter *adapter)
 	int i, max_frame = adapter->vf_res->max_mtu;
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
+	u8 rx_flags = 0;
 	size_t len;
 
 	if (max_frame > IAVF_MAX_RXBUFFER || !max_frame)
@@ -414,6 +415,9 @@  void iavf_configure_queues(struct iavf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))
+		rx_flags |= VIRTCHNL_PTP_RX_TSTAMP;
+
 	/* Limit maximum frame size when jumbo frames is not enabled */
 	if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) &&
 	    (adapter->netdev->mtu <= ETH_DATA_LEN))
@@ -443,6 +447,7 @@  void iavf_configure_queues(struct iavf_adapter *adapter)
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
+		vqpi->rxq.flags = rx_flags;
 		vqpi++;
 	}