[xdp-hints] [PATCH bpf-next 00/15] new kfunc XDP hints and ice implementation

[xdp-hints] [PATCH bpf-next 00/15] new kfunc XDP hints and ice implementation

[Larysa Zaremba]

This series introduces XDP hints support into ice driver and adds new kfunc
hints that utilize hardware capabilities.

- patches 01-04 refactors driver descriptor to skb fields processing code,
  making it more reusable without changing any behavior.

- patches 05-08 add support add support for existing hints (timestamp and 
  hash) in ice driver.

- patches 09-12 introduce new kfunc hints, namely 2 VLAN tag hints 
  (ctag & stag separately) and "checksum level", which is basically
  a CHECKSUM_UNNECESSARY indicator. Then those hints are implemented in
  ice driver.

- patches 13-15 adjust xdp_hw_metadata to account for new hints.

- in particular, patch 14 lifts the limitation on data_meta size to be
  32 or lower, because all the information that needs to be passed into
  AF_XDP from XDP in xdp_hw_metadata no longer fits into 32 bytes.

Aleksander Lobakin (1):
  net, xdp: allow metadata > 32

Larysa Zaremba (14):
  ice: make RX hash reading code more reusable
  ice: make RX HW timestamp reading code more reusable
  ice: make RX checksum checking code more reusable
  ice: Make ptype internal to descriptor info processing
  ice: Introduce ice_xdp_buff
  ice: Support HW timestamp hint
  ice: Support RX hash XDP hint
  ice: Support XDP hints in AF_XDP ZC mode
  xdp: Add VLAN tag hint
  ice: Implement VLAN tag hint
  xdp: Add checksum level hint
  ice: Implement checksum level hint
  selftests/bpf: Allow VLAN packets in xdp_hw_metadata
  selftests/bpf: Add flags and new hints to xdp_hw_metadata

 Documentation/networking/xdp-rx-metadata.rst  |  14 +-
 drivers/net/ethernet/intel/ice/ice.h          |   2 +
 .../net/ethernet/intel/ice/ice_lan_tx_rx.h    | 412 +++++++++---------
 drivers/net/ethernet/intel/ice/ice_main.c     |   1 +
 drivers/net/ethernet/intel/ice/ice_ptp.c      |  23 +-
 drivers/net/ethernet/intel/ice/ice_ptp.h      |  18 +-
 drivers/net/ethernet/intel/ice/ice_txrx.c     |  13 +-
 drivers/net/ethernet/intel/ice/ice_txrx.h     |  23 +-
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 311 +++++++++++--
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h |  13 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c      |  16 +-
 include/linux/netdevice.h                     |   3 +
 include/linux/skbuff.h                        |  13 +-
 include/net/xdp.h                             |  16 +-
 kernel/bpf/offload.c                          |   6 +
 net/core/xdp.c                                |  36 ++
 .../selftests/bpf/progs/xdp_hw_metadata.c     |  49 ++-
 tools/testing/selftests/bpf/xdp_hw_metadata.c |  29 +-
 tools/testing/selftests/bpf/xdp_metadata.h    |  36 +-
 19 files changed, 738 insertions(+), 296 deletions(-)

-- 
2.35.3

[xdp-hints] [PATCH 01/15] ice: make RX hash reading code more reusable

[Larysa Zaremba]

Previously, we only needed RX hash in skb path,
hence all related code was written with skb in mind.
But with the addition of XDP hints via kfuncs to the ice driver,
the same logic will be needed in .xmo_() callbacks.

Separate generic process of reading RX hash from a descriptor
into a separate function.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 38 +++++++++++++------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index c8322fb6f2b3..fc67bbf600af 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -63,28 +63,44 @@ static enum pkt_hash_types ice_ptype_to_htype(u16 ptype)
 }
 
 /**
- * ice_rx_hash - set the hash value in the skb
+ * ice_copy_rx_hash_from_desc - copy hash value from descriptor to address
+ * @rx_desc: specific descriptor
+ * @dst: address to copy hash value to
+ *
+ * Returns true, if valid hash has been copied into the destination address.
+ */
+static bool
+ice_copy_rx_hash_from_desc(union ice_32b_rx_flex_desc *rx_desc, u32 *dst)
+{
+	struct ice_32b_rx_flex_desc_nic *nic_mdid;
+
+	if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
+		return false;
+
+	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	*dst = le32_to_cpu(nic_mdid->rss_hash);
+	return true;
+}
+
+/**
+ * ice_rx_hash_to_skb - set the hash value in the skb
  * @rx_ring: descriptor ring
  * @rx_desc: specific descriptor
  * @skb: pointer to current skb
  * @rx_ptype: the ptype value from the descriptor
  */
 static void
-ice_rx_hash(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc,
-	    struct sk_buff *skb, u16 rx_ptype)
+ice_rx_hash_to_skb(struct ice_rx_ring *rx_ring,
+		   union ice_32b_rx_flex_desc *rx_desc,
+		   struct sk_buff *skb, u16 rx_ptype)
 {
-	struct ice_32b_rx_flex_desc_nic *nic_mdid;
 	u32 hash;
 
 	if (!(rx_ring->netdev->features & NETIF_F_RXHASH))
 		return;
 
-	if (rx_desc->wb.rxdid != ICE_RXDID_FLEX_NIC)
-		return;
-
-	nic_mdid = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
-	hash = le32_to_cpu(nic_mdid->rss_hash);
-	skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
+	if (ice_copy_rx_hash_from_desc(rx_desc, &hash))
+		skb_set_hash(skb, hash, ice_ptype_to_htype(rx_ptype));
 }
 
 /**
@@ -186,7 +202,7 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
 		       struct sk_buff *skb, u16 ptype)
 {
-	ice_rx_hash(rx_ring, rx_desc, skb, ptype);
+	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
 
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
-- 
2.35.3

[xdp-hints] [PATCH 02/15] ice: make RX HW timestamp reading code more reusable

[Larysa Zaremba]

Previously, we only needed RX HW timestamp in skb path,
hence all related code was written with skb in mind.
But with the addition of XDP hints via kfuncs to the ice driver,
the same logic will be needed in .xmo_() callbacks.

Put generic process of reading RX HW timestamp from a descriptor
into a separate function.
Move skb-related code into another source file.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c      | 23 +++++++---------
 drivers/net/ethernet/intel/ice/ice_ptp.h      | 18 ++++++++-----
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 27 ++++++++++++++++++-
 3 files changed, 48 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index ac6f06f9a2ed..c90ce91f11ab 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2142,30 +2142,28 @@ int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr)
 }
 
 /**
- * ice_ptp_rx_hwtstamp - Check for an Rx timestamp
+ * ice_ptp_copy_rx_hwts_from_desc - Check for an Rx timestamp
  * @rx_ring: Ring to get the VSI info
  * @rx_desc: Receive descriptor
- * @skb: Particular skb to send timestamp with
+ * @dst: Address to put RX timestamp to
  *
- * The driver receives a notification in the receive descriptor with timestamp.
- * The timestamp is in ns, so we must convert the result first.
+ * If function returns true, dst contains a valid RX timestamp in ns.
  */
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb)
+bool ice_ptp_copy_rx_hwts_from_desc(struct ice_rx_ring *rx_ring,
+				    union ice_32b_rx_flex_desc *rx_desc,
+				    u64 *dst)
 {
-	struct skb_shared_hwtstamps *hwtstamps;
 	u64 ts_ns, cached_time;
 	u32 ts_high;
 
 	if (!(rx_desc->wb.time_stamp_low & ICE_PTP_TS_VALID))
-		return;
+		return false;
 
 	cached_time = READ_ONCE(rx_ring->cached_phctime);
 
 	/* Do not report a timestamp if we don't have a cached PHC time */
 	if (!cached_time)
-		return;
+		return false;
 
 	/* Use ice_ptp_extend_32b_ts directly, using the ring-specific cached
 	 * PHC value, rather than accessing the PF. This also allows us to
@@ -2176,9 +2174,8 @@ ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
 	ts_high = le32_to_cpu(rx_desc->wb.flex_ts.ts_high);
 	ts_ns = ice_ptp_extend_32b_ts(cached_time, ts_high);
 
-	hwtstamps = skb_hwtstamps(skb);
-	memset(hwtstamps, 0, sizeof(*hwtstamps));
-	hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
+	*dst = ts_ns;
+	return true;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 9cda2f43e0e5..509ea9570276 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -259,9 +259,9 @@ int ice_get_ptp_clock_index(struct ice_pf *pf);
 s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
 bool ice_ptp_process_ts(struct ice_pf *pf);
 
-void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb);
+bool ice_ptp_copy_rx_hwts_from_desc(struct ice_rx_ring *rx_ring,
+				    union ice_32b_rx_flex_desc *rx_desc,
+				    u64 *dst);
 void ice_ptp_reset(struct ice_pf *pf);
 void ice_ptp_prepare_for_reset(struct ice_pf *pf);
 void ice_ptp_init(struct ice_pf *pf);
@@ -294,9 +294,15 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 {
 	return true;
 }
-static inline void
-ice_ptp_rx_hwtstamp(struct ice_rx_ring *rx_ring,
-		    union ice_32b_rx_flex_desc *rx_desc, struct sk_buff *skb) { }
+
+static inline bool
+ice_ptp_copy_rx_hwts_from_desc(struct ice_rx_ring *rx_ring,
+			       union ice_32b_rx_flex_desc *rx_desc,
+			       u64 *dst)
+{
+	return false;
+}
+
 static inline void ice_ptp_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_prepare_for_reset(struct ice_pf *pf) { }
 static inline void ice_ptp_init(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index fc67bbf600af..1aab79dc8915 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -186,6 +186,31 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	ring->vsi->back->hw_csum_rx_error++;
 }
 
+/**
+ * ice_ptp_rx_hwts_to_skb - Put RX timestamp into skb, if available
+ * @rx_ring: Ring to get the VSI info
+ * @rx_desc: Receive descriptor
+ * @skb: Particular skb to send timestamp with
+ *
+ * The driver receives a notification in the receive descriptor with timestamp.
+ * The timestamp is in ns, so we must convert the result first.
+ */
+static void
+ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring,
+		       union ice_32b_rx_flex_desc *rx_desc,
+		       struct sk_buff *skb)
+{
+	struct skb_shared_hwtstamps *hwtstamps;
+	u64 ts_ns;
+
+	if (!ice_ptp_copy_rx_hwts_from_desc(rx_ring, rx_desc, &ts_ns))
+		return;
+
+	hwtstamps = skb_hwtstamps(skb);
+	memset(hwtstamps, 0, sizeof(*hwtstamps));
+	hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
+}
+
 /**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: Rx descriptor ring packet is being transacted on
@@ -210,7 +235,7 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
 
 	if (rx_ring->ptp_rx)
-		ice_ptp_rx_hwtstamp(rx_ring, rx_desc, skb);
+		ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb);
 }
 
 /**
-- 
2.35.3

[xdp-hints] [PATCH 03/15] ice: make RX checksum checking code more reusable

[Larysa Zaremba]

Previously, we only needed RX checksum flags in skb path,
hence all related code was written with skb in mind.
But with the addition of XDP hints via kfuncs to the ice driver,
the same logic will be needed in .xmo_() callbacks.

Put generic process of determining checksum status into
a separate function.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 71 ++++++++++++-------
 1 file changed, 46 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1aab79dc8915..6a4fd3f3fc0a 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -104,17 +104,17 @@ ice_rx_hash_to_skb(struct ice_rx_ring *rx_ring,
 }
 
 /**
- * ice_rx_csum - Indicate in skb if checksum is good
- * @ring: the ring we care about
- * @skb: skb currently being received and modified
+ * ice_rx_csum_checked - Indicates, whether hardware has checked the checksum
  * @rx_desc: the receive descriptor
  * @ptype: the packet type decoded by hardware
+ * @csum_lvl_dst: address to put checksum level into
+ * @ring: ring for error stats, can be NULL
  *
- * skb->protocol must be set before this function is called
+ * Returns true, if hardware has checked the checksum.
  */
-static void
-ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
-	    union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+static bool
+ice_rx_csum_checked(union ice_32b_rx_flex_desc *rx_desc, u16 ptype,
+		    u8 *csum_lvl_dst, struct ice_rx_ring *ring)
 {
 	struct ice_rx_ptype_decoded decoded;
 	u16 rx_status0, rx_status1;
@@ -125,20 +125,12 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 
 	decoded = ice_decode_rx_desc_ptype(ptype);
 
-	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
-	skb->ip_summed = CHECKSUM_NONE;
-	skb_checksum_none_assert(skb);
-
-	/* check if Rx checksum is enabled */
-	if (!(ring->netdev->features & NETIF_F_RXCSUM))
-		return;
-
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
-		return;
+		return false;
 
 	if (!(decoded.known && decoded.outer_ip))
-		return;
+		return false;
 
 	ipv4 = (decoded.outer_ip == ICE_RX_PTYPE_OUTER_IP) &&
 	       (decoded.outer_ip_ver == ICE_RX_PTYPE_OUTER_IPV4);
@@ -168,22 +160,51 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	 * we are indicating we validated the inner checksum.
 	 */
 	if (decoded.tunnel_type >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT)
-		skb->csum_level = 1;
+		*csum_lvl_dst = 1;
 
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
 	switch (decoded.inner_prot) {
 	case ICE_RX_PTYPE_INNER_PROT_TCP:
 	case ICE_RX_PTYPE_INNER_PROT_UDP:
 	case ICE_RX_PTYPE_INNER_PROT_SCTP:
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		break;
-	default:
-		break;
+		return true;
 	}
-	return;
+
+	return false;
 
 checksum_fail:
-	ring->vsi->back->hw_csum_rx_error++;
+	if (ring)
+		ring->vsi->back->hw_csum_rx_error++;
+
+	return false;
+}
+
+/**
+ * ice_rx_csum_into_skb - Indicate in skb if checksum is good
+ * @ring: the ring we care about
+ * @skb: skb currently being received and modified
+ * @rx_desc: the receive descriptor
+ * @ptype: the packet type decoded by hardware
+ */
+static void
+ice_rx_csum_into_skb(struct ice_rx_ring *ring, struct sk_buff *skb,
+		     union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
+{
+	u8 csum_level = 0;
+
+	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
+	skb->ip_summed = CHECKSUM_NONE;
+	skb_checksum_none_assert(skb);
+
+	/* check if Rx checksum is enabled */
+	if (!(ring->netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (!ice_rx_csum_checked(rx_desc, ptype, &csum_level, ring))
+		return;
+
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	skb->csum_level = csum_level;
 }
 
 /**
@@ -232,7 +253,7 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
 
-	ice_rx_csum(rx_ring, skb, rx_desc, ptype);
+	ice_rx_csum_into_skb(rx_ring, skb, rx_desc, ptype);
 
 	if (rx_ring->ptp_rx)
 		ice_ptp_rx_hwts_to_skb(rx_ring, rx_desc, skb);
-- 
2.35.3

[xdp-hints] [PATCH 04/15] ice: Make ptype internal to descriptor info processing

[Larysa Zaremba]

Currently, rx_ptype variable is used only as an argument
to ice_process_skb_fields() and is computed
just before the function call.

Therefore, there is no reason to pass this value as an argument.
Instead, remove this argument and compute the value directly inside
ice_process_skb_fields() function.

Also, separate its calculation into a short function, so the code
can later be reused in .xmo_() callbacks.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c     |  6 +-----
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 15 +++++++++++++--
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h |  2 +-
 drivers/net/ethernet/intel/ice/ice_xsk.c      |  2 +-
 4 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 4fcf2d07eb85..c9bb77da0861 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1181,7 +1181,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		unsigned int size;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
-		u16 rx_ptype;
 
 		/* get the Rx desc from Rx ring based on 'next_to_clean' */
 		rx_desc = ICE_RX_DESC(rx_ring, ntc);
@@ -1286,10 +1285,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
-		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
-			ICE_RX_FLEX_DESC_PTYPE_M;
-
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
 
 		ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb);
 		/* send completed skb up the stack */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 6a4fd3f3fc0a..2515f5f7a2b6 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -232,12 +232,21 @@ ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring,
 	hwtstamps->hwtstamp = ns_to_ktime(ts_ns);
 }
 
+/**
+ * ice_get_ptype - Read HW packet type from the descriptor
+ * @rx_desc: RX descriptor
+ */
+static u16 ice_get_ptype(union ice_32b_rx_flex_desc *rx_desc)
+{
+	return le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
+	       ICE_RX_FLEX_DESC_PTYPE_M;
+}
+
 /**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: Rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @ptype: the packet type decoded by hardware
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
@@ -246,8 +255,10 @@ ice_ptp_rx_hwts_to_skb(struct ice_rx_ring *rx_ring,
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u16 ptype)
+		       struct sk_buff *skb)
 {
+	u16 ptype = ice_get_ptype(rx_desc);
+
 	ice_rx_hash_to_skb(rx_ring, rx_desc, skb, ptype);
 
 	/* modifies the skb - consumes the enet header */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index 115969ecdf7b..e1d49e1235b3 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -148,7 +148,7 @@ void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val);
 void
 ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       union ice_32b_rx_flex_desc *rx_desc,
-		       struct sk_buff *skb, u16 ptype);
+		       struct sk_buff *skb);
 void
 ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
 #endif /* !_ICE_TXRX_LIB_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index d1e489da7363..3b80aed5d47a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -857,7 +857,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) &
 				       ICE_RX_FLEX_DESC_PTYPE_M;
 
-		ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
+		ice_process_skb_fields(rx_ring, rx_desc, skb);
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-- 
2.35.3

[xdp-hints] [PATCH 05/15] ice: Introduce ice_xdp_buff

[Larysa Zaremba]

In order to use XDP hints via kfuncs we need to put
RX descriptor and ring pointers just next to xdp_buff.
Same as in hints implementations in other drivers, we archieve
this through putting xdp_buff into a child structure.

Currently, xdp_buff is stored in the ring structure,
so replace it with union that includes child structure.
This way enough memory is available while existing XDP code
remains isolated from hints.

Size of the new child structure (ice_xdp_buff) is 72 bytes,
therefore it does not fit into a single cache line.
To at least place union at the start of cache line, move 'next'
field from CL3 to CL1, as it isn't used often.

Placing union at the start of cache line makes at least xdp_buff
and descriptor fit into a single CL,
ring pointer is used less often, so it can spill into the next CL.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c     |  7 ++++--
 drivers/net/ethernet/intel/ice/ice_txrx.h     | 23 ++++++++++++++++---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.h | 11 +++++++++
 3 files changed, 36 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c9bb77da0861..ca21a71749b6 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -557,13 +557,14 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
  * @rx_buf: Rx buffer to store the XDP action
+ * @eop_desc: Last descriptor in packet to read metadata from
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static void
 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	    struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
-	    struct ice_rx_buf *rx_buf)
+	    struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc)
 {
 	unsigned int ret = ICE_XDP_PASS;
 	u32 act;
@@ -571,6 +572,8 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	if (!xdp_prog)
 		goto exit;
 
+	ice_xdp_set_meta_srcs(xdp, eop_desc, rx_ring);
+
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 	switch (act) {
 	case XDP_PASS:
@@ -1240,7 +1243,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf);
+		ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc);
 		if (rx_buf->act == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index fff0efe28373..f1ac2eb974f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -260,6 +260,15 @@ enum ice_rx_dtype {
 	ICE_RX_DTYPE_SPLIT_ALWAYS	= 2,
 };
 
+struct ice_xdp_buff {
+	struct xdp_buff xdp_buff;
+	union ice_32b_rx_flex_desc *eop_desc;	/* Required for all metadata */
+	/* End of the 1st cache line */
+	struct ice_rx_ring *rx_ring;
+};
+
+static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0);
+
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
@@ -301,7 +310,6 @@ enum ice_dynamic_itr {
 /* descriptor ring, associated with a VSI */
 struct ice_rx_ring {
 	/* CL1 - 1st cacheline starts here */
-	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	void *desc;			/* Descriptor ring memory */
 	struct device *dev;		/* Used for DMA mapping */
 	struct net_device *netdev;	/* netdev ring maps to */
@@ -313,12 +321,19 @@ struct ice_rx_ring {
 	u16 count;			/* Number of descriptors */
 	u16 reg_idx;			/* HW register index of the ring */
 	u16 next_to_alloc;
-	/* CL2 - 2nd cacheline starts here */
+
 	union {
 		struct ice_rx_buf *rx_buf;
 		struct xdp_buff **xdp_buf;
 	};
-	struct xdp_buff xdp;
+	/* CL2 - 2nd cacheline starts here
+	 * Size of ice_xdp_buff is 72 bytes,
+	 * so it spills into CL3
+	 */
+	union {
+		struct ice_xdp_buff xdp_ext;
+		struct xdp_buff xdp;
+	};
 	/* CL3 - 3rd cacheline starts here */
 	struct bpf_prog *xdp_prog;
 	u16 rx_offset;
@@ -328,6 +343,8 @@ struct ice_rx_ring {
 	u16 next_to_clean;
 	u16 first_desc;
 
+	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
+
 	/* stats structs */
 	struct ice_ring_stats *ring_stats;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
index e1d49e1235b3..2835a8348237 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h
@@ -151,4 +151,15 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring,
 		       struct sk_buff *skb);
 void
 ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag);
+
+static inline void
+ice_xdp_set_meta_srcs(struct xdp_buff *xdp,
+		      union ice_32b_rx_flex_desc *eop_desc,
+		      struct ice_rx_ring *rx_ring)
+{
+	struct ice_xdp_buff *xdp_ext = (struct ice_xdp_buff *)xdp;
+
+	xdp_ext->eop_desc = eop_desc;
+	xdp_ext->rx_ring = rx_ring;
+}
 #endif /* !_ICE_TXRX_LIB_H_ */
-- 
2.35.3

[xdp-hints] [PATCH 06/15] ice: Support HW timestamp hint

[Larysa Zaremba]

Use previously refactored code and create a function
that allows XDP code to read HW timestamp.

HW timestamp is the first supported hint in the driver,
so also add xdp_metadata_ops.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h          |  2 ++
 drivers/net/ethernet/intel/ice/ice_main.c     |  1 +
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 22 +++++++++++++++++++
 3 files changed, 25 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index aa32111afd6e..ba1bb8392db1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -962,4 +962,6 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags);
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
+
+extern const struct xdp_metadata_ops ice_xdp_md_ops;
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a1f7c8edc22f..cda6c4a80737 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3378,6 +3378,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
 
 	netdev->netdev_ops = &ice_netdev_ops;
 	netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
+	netdev->xdp_metadata_ops = &ice_xdp_md_ops;
 	ice_set_ethtool_ops(netdev);
 
 	if (vsi->type != ICE_VSI_PF)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 2515f5f7a2b6..e9589cadf811 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -537,3 +537,25 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res,
 			spin_unlock(&xdp_ring->tx_lock);
 	}
 }
+
+/**
+ * ice_xdp_rx_hw_ts - HW timestamp XDP hint handler
+ * @ctx: XDP buff pointer
+ * @ts_ns: destination address
+ *
+ * Copy HW timestamp (if available) to the destination address.
+ */
+static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	if (!ice_ptp_copy_rx_hwts_from_desc(xdp_ext->rx_ring,
+					    xdp_ext->eop_desc, ts_ns))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+const struct xdp_metadata_ops ice_xdp_md_ops = {
+	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+};
-- 
2.35.3

[xdp-hints] [PATCH 07/15] ice: Support RX hash XDP hint

[Larysa Zaremba]

RX hash XDP hint requests both hash value and type.
Type is XDP-specific, so we need a separate way to map
these values to the hardware ptypes, so create a lookup table.

Instead of creating a new long list, reuse contents
of ice_decode_rx_desc_ptype[] through preprocessor.

Current hash type enum does not contain ICMP packet type,
but ice devices support it, so also add a new type into core code.

Then use previously refactored code and create a function
that allows XDP code to read RX hash.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 .../net/ethernet/intel/ice/ice_lan_tx_rx.h    | 412 +++++++++---------
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c |  72 +++
 include/net/xdp.h                             |   3 +
 3 files changed, 283 insertions(+), 204 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 89f986a75cc8..d384ddfcb83e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -673,6 +673,212 @@ struct ice_tlan_ctx {
  *      Use the enum ice_rx_l2_ptype to decode the packet type
  * ENDIF
  */
+#define ICE_PTYPES								\
+	/* L2 Packet types */							\
+	ICE_PTT_UNUSED_ENTRY(0),						\
+	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),			\
+	ICE_PTT_UNUSED_ENTRY(2),						\
+	ICE_PTT_UNUSED_ENTRY(3),						\
+	ICE_PTT_UNUSED_ENTRY(4),						\
+	ICE_PTT_UNUSED_ENTRY(5),						\
+	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),			\
+	ICE_PTT_UNUSED_ENTRY(8),						\
+	ICE_PTT_UNUSED_ENTRY(9),						\
+	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),		\
+	ICE_PTT_UNUSED_ENTRY(12),						\
+	ICE_PTT_UNUSED_ENTRY(13),						\
+	ICE_PTT_UNUSED_ENTRY(14),						\
+	ICE_PTT_UNUSED_ENTRY(15),						\
+	ICE_PTT_UNUSED_ENTRY(16),						\
+	ICE_PTT_UNUSED_ENTRY(17),						\
+	ICE_PTT_UNUSED_ENTRY(18),						\
+	ICE_PTT_UNUSED_ENTRY(19),						\
+	ICE_PTT_UNUSED_ENTRY(20),						\
+	ICE_PTT_UNUSED_ENTRY(21),						\
+										\
+	/* Non Tunneled IPv4 */							\
+	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(25),						\
+	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv4 */							\
+	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(32),						\
+	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> IPv6 */							\
+	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(39),						\
+	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT */							\
+	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv4 */						\
+	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(47),						\
+	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> IPv6 */						\
+	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(54),						\
+	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv4 --> GRE/NAT --> MAC */						\
+	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */					\
+	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(62),						\
+	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */					\
+	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(69),						\
+	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 --> GRE/NAT --> MAC/VLAN */					\
+	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(77),						\
+	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(84),						\
+	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* Non Tunneled IPv6 */							\
+	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),		\
+	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(91),						\
+	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),		\
+	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),		\
+	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv4 */							\
+	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(98),						\
+	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> IPv6 */							\
+	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(105),						\
+	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT */							\
+	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv4 */						\
+	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),		\
+	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),		\
+	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(113),						\
+	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),		\
+	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),		\
+	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> IPv6 */						\
+	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),		\
+	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),		\
+	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),		\
+	ICE_PTT_UNUSED_ENTRY(120),						\
+	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),		\
+	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),		\
+	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),		\
+										\
+	/* IPv6 --> GRE/NAT -> MAC */						\
+	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */					\
+	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(128),						\
+	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */					\
+	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(135),						\
+	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN */					\
+	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */				\
+	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),	\
+	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),	\
+	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(143),						\
+	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),	\
+	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),	\
+	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),	\
+										\
+	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */				\
+	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),	\
+	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),	\
+	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),	\
+	ICE_PTT_UNUSED_ENTRY(150),						\
+	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),	\
+	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),	\
+	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+
+#define ICE_NUM_DEFINED_PTYPES	154
 
 /* macro to make the table lines short, use explicit indexing with [PTYPE] */
 #define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
@@ -695,212 +901,10 @@ struct ice_tlan_ctx {
 
 /* Lookup table mapping in the 10-bit HW PTYPE to the bit field for decoding */
 static const struct ice_rx_ptype_decoded ice_ptype_lkup[BIT(10)] = {
-	/* L2 Packet types */
-	ICE_PTT_UNUSED_ENTRY(0),
-	ICE_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2),
-	ICE_PTT_UNUSED_ENTRY(2),
-	ICE_PTT_UNUSED_ENTRY(3),
-	ICE_PTT_UNUSED_ENTRY(4),
-	ICE_PTT_UNUSED_ENTRY(5),
-	ICE_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(8),
-	ICE_PTT_UNUSED_ENTRY(9),
-	ICE_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE),
-	ICE_PTT_UNUSED_ENTRY(12),
-	ICE_PTT_UNUSED_ENTRY(13),
-	ICE_PTT_UNUSED_ENTRY(14),
-	ICE_PTT_UNUSED_ENTRY(15),
-	ICE_PTT_UNUSED_ENTRY(16),
-	ICE_PTT_UNUSED_ENTRY(17),
-	ICE_PTT_UNUSED_ENTRY(18),
-	ICE_PTT_UNUSED_ENTRY(19),
-	ICE_PTT_UNUSED_ENTRY(20),
-	ICE_PTT_UNUSED_ENTRY(21),
-
-	/* Non Tunneled IPv4 */
-	ICE_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(25),
-	ICE_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv4 */
-	ICE_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(32),
-	ICE_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> IPv6 */
-	ICE_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(39),
-	ICE_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT */
-	ICE_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> IPv4 */
-	ICE_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(47),
-	ICE_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> IPv6 */
-	ICE_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(54),
-	ICE_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC */
-	ICE_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 --> GRE/NAT --> MAC --> IPv4 */
-	ICE_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(62),
-	ICE_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT -> MAC --> IPv6 */
-	ICE_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(69),
-	ICE_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv4 --> GRE/NAT --> MAC/VLAN */
-	ICE_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(77),
-	ICE_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(84),
-	ICE_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
-
-	/* Non Tunneled IPv6 */
-	ICE_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3),
-	ICE_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(91),
-	ICE_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP,  PAY4),
-	ICE_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4),
-	ICE_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv4 */
-	ICE_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(98),
-	ICE_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> IPv6 */
-	ICE_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(105),
-	ICE_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT */
-	ICE_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> IPv4 */
-	ICE_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(113),
-	ICE_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> IPv6 */
-	ICE_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(120),
-	ICE_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC */
-	ICE_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv4 */
-	ICE_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(128),
-	ICE_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC -> IPv6 */
-	ICE_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(135),
-	ICE_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN */
-	ICE_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */
-	ICE_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3),
-	ICE_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3),
-	ICE_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(143),
-	ICE_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP,  PAY4),
-	ICE_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4),
-	ICE_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4),
-
-	/* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */
-	ICE_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3),
-	ICE_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3),
-	ICE_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP,  PAY4),
-	ICE_PTT_UNUSED_ENTRY(150),
-	ICE_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP,  PAY4),
-	ICE_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4),
-	ICE_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4),
+	ICE_PTYPES
 
 	/* unused entries */
-	[154 ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
+	[ICE_NUM_DEFINED_PTYPES ... 1023] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }
 };
 
 static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index e9589cadf811..1caa73644e7b 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -556,6 +556,78 @@ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns)
 	return 0;
 }
 
+/* Define a ptype index -> XDP hash type lookup table.
+ * It uses the same ptype definitions as ice_decode_rx_desc_ptype[],
+ * avoiding possible copy-paste errors.
+ */
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+#define ICE_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\
+	[PTYPE] = XDP_RSS_L3_##OUTER_IP_VER | XDP_RSS_L4_##I | XDP_RSS_TYPE_##PL
+
+#define ICE_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = 0
+
+/* A few supplementary definitions for when XDP hash types do not coincide
+ * with what can be generated from ptype definitions
+ * by means of preprocessor concatenation.
+ */
+#define XDP_RSS_L3_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_L4_NONE		XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY2	XDP_RSS_TYPE_L2
+#define XDP_RSS_TYPE_PAY3	XDP_RSS_TYPE_NONE
+#define XDP_RSS_TYPE_PAY4	XDP_RSS_L4
+
+static const enum xdp_rss_hash_type
+ice_ptype_to_xdp_hash[ICE_NUM_DEFINED_PTYPES] = {
+	ICE_PTYPES
+};
+
+#undef XDP_RSS_L3_NONE
+#undef XDP_RSS_L4_NONE
+#undef XDP_RSS_TYPE_PAY2
+#undef XDP_RSS_TYPE_PAY3
+#undef XDP_RSS_TYPE_PAY4
+
+#undef ICE_PTT
+#undef ICE_PTT_UNUSED_ENTRY
+
+/**
+ * ice_xdp_rx_hash_type - Get XDP-specific hash type from the RX descriptor
+ * @eop_desc: End of Packet descriptor
+ */
+static enum xdp_rss_hash_type
+ice_xdp_rx_hash_type(union ice_32b_rx_flex_desc *eop_desc)
+{
+	u16 ptype = ice_get_ptype(eop_desc);
+
+	if (unlikely(ptype >= ICE_NUM_DEFINED_PTYPES))
+		return 0;
+
+	return ice_ptype_to_xdp_hash[ptype];
+}
+
+/**
+ * ice_xdp_rx_hash - RX hash XDP hint handler
+ * @ctx: XDP buff pointer
+ * @hash: hash destination address
+ * @rss_type: XDP hash type destination address
+ *
+ * Copy RX hash (if available) and its type to the destination address.
+ */
+static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+
+	*rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc);
+	if (!ice_copy_rx_hash_from_desc(xdp_ext->eop_desc, hash))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
+	.xmo_rx_hash			= ice_xdp_rx_hash,
 };
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d1c5381fc95f..6381560efae2 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -417,6 +417,7 @@ enum xdp_rss_hash_type {
 	XDP_RSS_L4_UDP		= BIT(5),
 	XDP_RSS_L4_SCTP		= BIT(6),
 	XDP_RSS_L4_IPSEC	= BIT(7), /* L4 based hash include IPSEC SPI */
+	XDP_RSS_L4_ICMP		= BIT(8),
 
 	/* Second part: RSS hash type combinations used for driver HW mapping */
 	XDP_RSS_TYPE_NONE            = 0,
@@ -432,11 +433,13 @@ enum xdp_rss_hash_type {
 	XDP_RSS_TYPE_L4_IPV4_UDP     = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV4_SCTP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV4_IPSEC   = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV4_ICMP    = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP,
 	XDP_RSS_TYPE_L4_IPV6_UDP     = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP,
 	XDP_RSS_TYPE_L4_IPV6_SCTP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP,
 	XDP_RSS_TYPE_L4_IPV6_IPSEC   = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC,
+	XDP_RSS_TYPE_L4_IPV6_ICMP    = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_ICMP,
 
 	XDP_RSS_TYPE_L4_IPV6_TCP_EX  = XDP_RSS_TYPE_L4_IPV6_TCP  | XDP_RSS_L3_DYNHDR,
 	XDP_RSS_TYPE_L4_IPV6_UDP_EX  = XDP_RSS_TYPE_L4_IPV6_UDP  | XDP_RSS_L3_DYNHDR,
-- 
2.35.3

[xdp-hints] [PATCH 08/15] ice: Support XDP hints in AF_XDP ZC mode

[Larysa Zaremba]

In AF_XDP ZC, xdp_buff is not stored on ring,
instead it is provided by xsk_pool.
Space for metadata sources right after such buffers was already reserved
in commit 94ecc5ca4dbf ("xsk: Add cb area to struct xdp_buff_xsk").
This makes the implementation rather straightforward.

Update AF_XDP ZC packet processing to support XDP hints.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 3b80aed5d47a..7f5ce3529666 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -708,16 +708,25 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
  * @xdp: xdp_buff used as input to the XDP program
  * @xdp_prog: XDP program to run
  * @xdp_ring: ring to be used for XDP_TX action
+ * @rx_desc: packet descriptor
  *
  * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
  */
 static int
 ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
+	       struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
+	       union ice_32b_rx_flex_desc *rx_desc)
 {
 	int err, result = ICE_XDP_PASS;
 	u32 act;
 
+	/* We can safely convert xdp_buff_xsk to ice_xdp_buff,
+	 * because there are XSK_PRIV_MAX bytes reserved in xdp_buff_xsk
+	 * right after xdp_buff, for our private use.
+	 * Macro insures we do not go above the limit.
+	 */
+	XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff);
+	ice_xdp_set_meta_srcs(xdp, rx_desc, rx_ring);
 	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
 	if (likely(act == XDP_REDIRECT)) {
@@ -816,7 +825,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		xsk_buff_set_size(xdp, size);
 		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring,
+					 rx_desc);
 		if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
 			xdp_xmit |= xdp_res;
 		} else if (xdp_res == ICE_XDP_EXIT) {
-- 
2.35.3

[xdp-hints] [PATCH 09/15] xdp: Add VLAN tag hint

[Larysa Zaremba]

Implement functionality that enables drivers to expose VLAN tag
to XDP code.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 Documentation/networking/xdp-rx-metadata.rst | 11 ++++++++-
 include/linux/netdevice.h                    |  2 ++
 include/net/xdp.h                            |  4 ++++
 kernel/bpf/offload.c                         |  4 ++++
 net/core/xdp.c                               | 24 ++++++++++++++++++++
 5 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 25ce72af81c2..73a78029c596 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -18,7 +18,16 @@ Currently, the following kfuncs are supported. In the future, as more
 metadata is supported, this set will grow:
 
 .. kernel-doc:: net/core/xdp.c
-   :identifiers: bpf_xdp_metadata_rx_timestamp bpf_xdp_metadata_rx_hash
+   :identifiers: bpf_xdp_metadata_rx_timestamp
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_hash
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_ctag
+
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_stag
 
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08fbd4622ccf..fdae37fe11f5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1655,6 +1655,8 @@ struct xdp_metadata_ops {
 	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
 	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
 			       enum xdp_rss_hash_type *rss_type);
+	int	(*xmo_rx_ctag)(const struct xdp_md *ctx, u16 *vlan_tag);
+	int	(*xmo_rx_stag)(const struct xdp_md *ctx, u16 *vlan_tag);
 };
 
 /**
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 6381560efae2..2db7439fc60f 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -389,6 +389,10 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   bpf_xdp_metadata_rx_timestamp) \
 	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_HASH, \
 			   bpf_xdp_metadata_rx_hash) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CTAG, \
+			   bpf_xdp_metadata_rx_ctag) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_STAG, \
+			   bpf_xdp_metadata_rx_stag) \
 
 enum {
 #define XDP_METADATA_KFUNC(name, _) name,
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index d9c9f45e3529..2c6b6e82cfac 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -848,6 +848,10 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
 		p = ops->xmo_rx_timestamp;
 	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_HASH))
 		p = ops->xmo_rx_hash;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_CTAG))
+		p = ops->xmo_rx_ctag;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_STAG))
+		p = ops->xmo_rx_stag;
 out:
 	up_read(&bpf_devs_lock);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 41e5ca8643ec..eff21501609f 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -738,6 +738,30 @@ __bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_ctag - Read XDP packet inner vlan tag.
+ * @ctx: XDP context pointer.
+ * @vlan_tag: Return value pointer.
+ *
+ * Returns 0 on success or ``-errno`` on error.
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_ctag(const struct xdp_md *ctx, u16 *vlan_tag)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * bpf_xdp_metadata_rx_stag - Read XDP packet outer vlan tag.
+ * @ctx: XDP context pointer.
+ * @vlan_tag: Return value pointer.
+ *
+ * Returns 0 on success or ``-errno`` on error.
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_stag(const struct xdp_md *ctx, u16 *vlan_tag)
+{
+	return -EOPNOTSUPP;
+}
+
 __diag_pop();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
-- 
2.35.3

[xdp-hints] [PATCH 10/15] ice: Implement VLAN tag hint

[Larysa Zaremba]

Implement .xmo_rx_vlan_tag callback to allow XDP code to read
packet's VLAN tag.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 1caa73644e7b..39547feb6106 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -627,7 +627,51 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash,
 	return 0;
 }
 
+/**
+ * ice_xdp_rx_ctag - VLAN tag XDP hint handler
+ * @ctx: XDP buff pointer
+ * @vlan_tag: destination address
+ *
+ * Copy VLAN tag (if was stripped) to the destination address.
+ */
+static int ice_xdp_rx_ctag(const struct xdp_md *ctx, u16 *vlan_tag)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	netdev_features_t features;
+
+	features = xdp_ext->rx_ring->netdev->features;
+
+	if (!(features & NETIF_F_HW_VLAN_CTAG_RX))
+		return -EINVAL;
+
+	*vlan_tag = ice_get_vlan_tag_from_rx_desc(xdp_ext->eop_desc);
+	return 0;
+}
+
+/**
+ * ice_xdp_rx_stag - VLAN s-tag XDP hint handler
+ * @ctx: XDP buff pointer
+ * @vlan_tag: destination address
+ *
+ * Copy VLAN s-tag (if was stripped) to the destination address.
+ */
+static int ice_xdp_rx_stag(const struct xdp_md *ctx, u16 *vlan_tag)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	netdev_features_t features;
+
+	features = xdp_ext->rx_ring->netdev->features;
+
+	if (!(features & NETIF_F_HW_VLAN_STAG_RX))
+		return -EINVAL;
+
+	*vlan_tag = ice_get_vlan_tag_from_rx_desc(xdp_ext->eop_desc);
+	return 0;
+}
+
 const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
 	.xmo_rx_hash			= ice_xdp_rx_hash,
+	.xmo_rx_ctag			= ice_xdp_rx_ctag,
+	.xmo_rx_stag			= ice_xdp_rx_stag,
 };
-- 
2.35.3

[xdp-hints] [PATCH 11/15] xdp: Add checksum level hint

[Larysa Zaremba]

Implement functionality that enables drivers to expose to XDP code,
whether checksums was checked and on what level.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 Documentation/networking/xdp-rx-metadata.rst |  3 +++
 include/linux/netdevice.h                    |  1 +
 include/net/xdp.h                            |  2 ++
 kernel/bpf/offload.c                         |  2 ++
 net/core/xdp.c                               | 12 ++++++++++++
 5 files changed, 20 insertions(+)

diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst
index 73a78029c596..f74f0e283097 100644
--- a/Documentation/networking/xdp-rx-metadata.rst
+++ b/Documentation/networking/xdp-rx-metadata.rst
@@ -29,6 +29,9 @@ metadata is supported, this set will grow:
 .. kernel-doc:: net/core/xdp.c
    :identifiers: bpf_xdp_metadata_rx_stag
 
+.. kernel-doc:: net/core/xdp.c
+   :identifiers: bpf_xdp_metadata_rx_csum_lvl
+
 An XDP program can use these kfuncs to read the metadata into stack
 variables for its own consumption. Or, to pass the metadata on to other
 consumers, an XDP program can store it into the metadata area carried
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fdae37fe11f5..ddade3a15366 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1657,6 +1657,7 @@ struct xdp_metadata_ops {
 			       enum xdp_rss_hash_type *rss_type);
 	int	(*xmo_rx_ctag)(const struct xdp_md *ctx, u16 *vlan_tag);
 	int	(*xmo_rx_stag)(const struct xdp_md *ctx, u16 *vlan_tag);
+	int	(*xmo_rx_csum_lvl)(const struct xdp_md *ctx, u8 *csum_level);
 };
 
 /**
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 2db7439fc60f..0fbd25616241 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -393,6 +393,8 @@ void xdp_attachment_setup(struct xdp_attachment_info *info,
 			   bpf_xdp_metadata_rx_ctag) \
 	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_STAG, \
 			   bpf_xdp_metadata_rx_stag) \
+	XDP_METADATA_KFUNC(XDP_METADATA_KFUNC_RX_CSUM_LVL, \
+			   bpf_xdp_metadata_rx_csum_lvl) \
 
 enum {
 #define XDP_METADATA_KFUNC(name, _) name,
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 2c6b6e82cfac..8bd54fb4ac63 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -852,6 +852,8 @@ void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id)
 		p = ops->xmo_rx_ctag;
 	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_STAG))
 		p = ops->xmo_rx_stag;
+	else if (func_id == bpf_xdp_metadata_kfunc_id(XDP_METADATA_KFUNC_RX_CSUM_LVL))
+		p = ops->xmo_rx_csum_lvl;
 out:
 	up_read(&bpf_devs_lock);
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index eff21501609f..7dd45fd62983 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -762,6 +762,18 @@ __bpf_kfunc int bpf_xdp_metadata_rx_stag(const struct xdp_md *ctx, u16 *vlan_tag
 	return -EOPNOTSUPP;
 }
 
+/**
+ * bpf_xdp_metadata_rx_csum_lvl - Get depth at which HW has checked the checksum.
+ * @ctx: XDP context pointer.
+ * @csum_level: Return value pointer.
+ *
+ * Returns 0 on success (HW has checked the checksum) or ``-errno`` on error.
+ */
+__bpf_kfunc int bpf_xdp_metadata_rx_csum_lvl(const struct xdp_md *ctx, u8 *csum_level)
+{
+	return -EOPNOTSUPP;
+}
+
 __diag_pop();
 
 BTF_SET8_START(xdp_metadata_kfunc_ids)
-- 
2.35.3

[xdp-hints] [PATCH 12/15] ice: Implement checksum level hint

[Larysa Zaremba]

Implement .xmo_rx_csum_lvl callback to allow XDP code to determine,
whether checksum was checked by hardware and on what level.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 24 ++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 39547feb6106..6a3ec925f20d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -161,6 +161,8 @@ ice_rx_csum_checked(union ice_32b_rx_flex_desc *rx_desc, u16 ptype,
 	 */
 	if (decoded.tunnel_type >= ICE_RX_PTYPE_TUNNEL_IP_GRENAT)
 		*csum_lvl_dst = 1;
+	else
+		*csum_lvl_dst = 0;
 
 	/* Only report checksum unnecessary for TCP, UDP, or SCTP */
 	switch (decoded.inner_prot) {
@@ -190,7 +192,7 @@ static void
 ice_rx_csum_into_skb(struct ice_rx_ring *ring, struct sk_buff *skb,
 		     union ice_32b_rx_flex_desc *rx_desc, u16 ptype)
 {
-	u8 csum_level = 0;
+	u8 csum_level;
 
 	/* Start with CHECKSUM_NONE and by default csum_level = 0 */
 	skb->ip_summed = CHECKSUM_NONE;
@@ -669,9 +671,29 @@ static int ice_xdp_rx_stag(const struct xdp_md *ctx, u16 *vlan_tag)
 	return 0;
 }
 
+/**
+ * ice_xdp_rx_csum_lvl - Get level, at which HW has checked the checksum
+ * @ctx: XDP buff pointer
+ * @csum_lvl: destination address
+ *
+ * Copy HW checksum level (if was checked) to the destination address.
+ */
+static int ice_xdp_rx_csum_lvl(const struct xdp_md *ctx, u8 *csum_lvl)
+{
+	const struct ice_xdp_buff *xdp_ext = (void *)ctx;
+	u16 ptype = ice_get_ptype(xdp_ext->eop_desc);
+
+	if (!ice_rx_csum_checked(xdp_ext->eop_desc, ptype, csum_lvl,
+				 xdp_ext->rx_ring))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 const struct xdp_metadata_ops ice_xdp_md_ops = {
 	.xmo_rx_timestamp		= ice_xdp_rx_hw_ts,
 	.xmo_rx_hash			= ice_xdp_rx_hash,
 	.xmo_rx_ctag			= ice_xdp_rx_ctag,
 	.xmo_rx_stag			= ice_xdp_rx_stag,
+	.xmo_rx_csum_lvl		= ice_xdp_rx_csum_lvl,
 };
-- 
2.35.3

[xdp-hints] [PATCH 13/15] selftests/bpf: Allow VLAN packets in xdp_hw_metadata

[Larysa Zaremba]

Make VLAN c-tag and s-tag XDP hint testing more convenient
by not skipping VLAN-ed packets.

Allow both 802.1ad and 802.1Q headers.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 tools/testing/selftests/bpf/progs/xdp_hw_metadata.c | 9 ++++++++-
 tools/testing/selftests/bpf/xdp_metadata.h          | 8 ++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index b2dfd7066c6e..f95f82a8b449 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -26,15 +26,22 @@ int rx(struct xdp_md *ctx)
 {
 	void *data, *data_meta, *data_end;
 	struct ipv6hdr *ip6h = NULL;
-	struct ethhdr *eth = NULL;
 	struct udphdr *udp = NULL;
 	struct iphdr *iph = NULL;
 	struct xdp_meta *meta;
+	struct ethhdr *eth;
 	int err;
 
 	data = (void *)(long)ctx->data;
 	data_end = (void *)(long)ctx->data_end;
 	eth = data;
+
+	if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021AD))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
+	if (eth + 1 < data_end && eth->h_proto == bpf_htons(ETH_P_8021Q))
+		eth = (void *)eth + sizeof(struct vlan_hdr);
+
 	if (eth + 1 < data_end) {
 		if (eth->h_proto == bpf_htons(ETH_P_IP)) {
 			iph = (void *)(eth + 1);
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 938a729bd307..6664893c2c77 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -9,6 +9,14 @@
 #define ETH_P_IPV6 0x86DD
 #endif
 
+#ifndef ETH_P_8021Q
+#define ETH_P_8021Q 0x8100
+#endif
+
+#ifndef ETH_P_8021AD
+#define ETH_P_8021AD 0x88A8
+#endif
+
 struct xdp_meta {
 	__u64 rx_timestamp;
 	__u64 xdp_timestamp;
-- 
2.35.3

[xdp-hints] [PATCH 14/15] net, xdp: allow metadata > 32

[Larysa Zaremba]

From: Aleksander Lobakin <aleksander.lobakin@intel.com>

When using XDP hints, metadata sometimes has to be much bigger
than 32 bytes. Relax the restriction, allow metadata larger than 32 bytes
and make __skb_metadata_differs() work with bigger lengths.

Now size of metadata is only limited by the fact it is stored as u8
in skb_shared_info, so maximum possible value is 255. Other important
conditions, such as having enough space for xdp_frame building, are already
checked in bpf_xdp_adjust_meta().

The requirement of having its length aligned to 4 bytes is still
valid.

Signed-off-by: Aleksander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 include/linux/skbuff.h | 13 ++++++++-----
 include/net/xdp.h      |  7 ++++++-
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 8ddb4af1a501..afcd372aecdf 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4219,10 +4219,13 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 {
 	const void *a = skb_metadata_end(skb_a);
 	const void *b = skb_metadata_end(skb_b);
-	/* Using more efficient varaiant than plain call to memcmp(). */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
 	u64 diffs = 0;
 
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    BITS_PER_LONG != 64)
+		goto slow;
+
+	/* Using more efficient variant than plain call to memcmp(). */
 	switch (meta_len) {
 #define __it(x, op) (x -= sizeof(u##op))
 #define __it_diff(a, b, op) (*(u##op *)__it(a, op)) ^ (*(u##op *)__it(b, op))
@@ -4242,11 +4245,11 @@ static inline bool __skb_metadata_differs(const struct sk_buff *skb_a,
 		fallthrough;
 	case  4: diffs |= __it_diff(a, b, 32);
 		break;
+	default:
+slow:
+		return memcmp(a - meta_len, b - meta_len, meta_len);
 	}
 	return diffs;
-#else
-	return memcmp(a - meta_len, b - meta_len, meta_len);
-#endif
 }
 
 static inline bool skb_metadata_differs(const struct sk_buff *skb_a,
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 0fbd25616241..f48723250c7c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -370,7 +370,12 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 
 static inline bool xdp_metalen_invalid(unsigned long metalen)
 {
-	return (metalen & (sizeof(__u32) - 1)) || (metalen > 32);
+	typeof(metalen) meta_max;
+
+	meta_max = type_max(typeof_member(struct skb_shared_info, meta_len));
+	BUILD_BUG_ON(!__builtin_constant_p(meta_max));
+
+	return !IS_ALIGNED(metalen, sizeof(u32)) || metalen > meta_max;
 }
 
 struct xdp_attachment_info {
-- 
2.35.3

[xdp-hints] [PATCH 15/15] selftests/bpf: Add flags and new hints to xdp_hw_metadata

[Larysa Zaremba]

Add hints added in the previous patches (VLAN tags and checksum level)
to the xdp_hw_metadata program.

Also, to make metadata layout more straightforward, add flags field
to pass information about validity of every separate hint separately.

Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
---
 .../selftests/bpf/progs/xdp_hw_metadata.c     | 40 ++++++++++++++++---
 tools/testing/selftests/bpf/xdp_hw_metadata.c | 29 +++++++++++---
 tools/testing/selftests/bpf/xdp_metadata.h    | 28 ++++++++++++-
 3 files changed, 85 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
index f95f82a8b449..97bad79ce4ca 100644
--- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c
@@ -20,6 +20,12 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx,
 					 __u64 *timestamp) __ksym;
 extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
 				    enum xdp_rss_hash_type *rss_type) __ksym;
+extern int bpf_xdp_metadata_rx_ctag(const struct xdp_md *ctx,
+				    __u16 *vlan_tag) __ksym;
+extern int bpf_xdp_metadata_rx_stag(const struct xdp_md *ctx,
+				    __u16 *vlan_tag) __ksym;
+extern int bpf_xdp_metadata_rx_csum_lvl(const struct xdp_md *ctx,
+					__u8 *csum_level) __ksym;
 
 SEC("xdp")
 int rx(struct xdp_md *ctx)
@@ -83,15 +89,39 @@ int rx(struct xdp_md *ctx)
 		return XDP_PASS;
 	}
 
+	meta->hint_valid = 0;
+
 	err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp);
-	if (!err)
+	if (err) {
+		meta->rx_timestamp_err = err;
+	} else {
+		meta->hint_valid |= XDP_META_FIELD_TS;
 		meta->xdp_timestamp = bpf_ktime_get_tai_ns();
-	else
-		meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
+	}
 
 	err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type);
-	if (err < 0)
-		meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */
+	if (err)
+		meta->rx_hash_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_RSS;
+
+	err = bpf_xdp_metadata_rx_ctag(ctx, &meta->rx_ctag);
+	if (err)
+		meta->rx_ctag_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_CTAG;
+
+	err = bpf_xdp_metadata_rx_stag(ctx, &meta->rx_stag);
+	if (err)
+		meta->rx_stag_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_STAG;
+
+	err = bpf_xdp_metadata_rx_csum_lvl(ctx, &meta->rx_csum_lvl);
+	if (err)
+		meta->rx_csum_err = err;
+	else
+		meta->hint_valid |= XDP_META_FIELD_CSUM_LVL;
 
 	__sync_add_and_fetch(&pkts_redir, 1);
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 613321eb84c1..efcabe68f64b 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -156,15 +156,16 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 
 	meta = data - sizeof(*meta);
 
-	if (meta->rx_hash_err < 0)
-		printf("No rx_hash err=%d\n", meta->rx_hash_err);
-	else
+	if (meta->hint_valid & XDP_META_FIELD_RSS)
 		printf("rx_hash: 0x%X with RSS type:0x%X\n",
 		       meta->rx_hash, meta->rx_hash_type);
+	else
+		printf("No rx_hash, err=%d\n", meta->rx_hash_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_TS) {
+		printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
+		       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
 
-	printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
-	       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
-	if (meta->rx_timestamp) {
 		__u64 usr_clock = gettime(clock_id);
 		__u64 xdp_clock = meta->xdp_timestamp;
 		__s64 delta_X = xdp_clock - meta->rx_timestamp;
@@ -179,8 +180,24 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 		       usr_clock, (double)usr_clock / NANOSEC_PER_SEC,
 		       (double)delta_X2U / NANOSEC_PER_SEC,
 		       (double)delta_X2U / 1000);
+	} else {
+		printf("No rx_timestamp, err=%d\n", meta->rx_timestamp_err);
 	}
 
+	if (meta->hint_valid & XDP_META_FIELD_CTAG)
+		printf("rx_ctag: %u\n", meta->rx_ctag);
+	else
+		printf("No rx_ctag, err=%d\n", meta->rx_ctag_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_STAG)
+		printf("rx_stag: %u\n", meta->rx_stag);
+	else
+		printf("No rx_stag, err=%d\n", meta->rx_stag_err);
+
+	if (meta->hint_valid & XDP_META_FIELD_CSUM_LVL)
+		printf("Checksum was checked at level %u\n", meta->rx_csum_lvl);
+	else
+		printf("Checksum was not checked, err=%d\n", meta->rx_csum_err);
 }
 
 static void verify_skb_metadata(int fd)
diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h
index 6664893c2c77..7c0267a8918a 100644
--- a/tools/testing/selftests/bpf/xdp_metadata.h
+++ b/tools/testing/selftests/bpf/xdp_metadata.h
@@ -17,12 +17,38 @@
 #define ETH_P_8021AD 0x88A8
 #endif
 
+#define BIT(nr)			(1 << (nr))
+
+enum xdp_meta_field {
+	XDP_META_FIELD_TS	= BIT(0),
+	XDP_META_FIELD_RSS	= BIT(1),
+	XDP_META_FIELD_CTAG	= BIT(2),
+	XDP_META_FIELD_STAG	= BIT(3),
+	XDP_META_FIELD_CSUM_LVL	= BIT(4),
+};
+
 struct xdp_meta {
-	__u64 rx_timestamp;
+	union {
+		__u64 rx_timestamp;
+		__s32 rx_timestamp_err;
+	};
 	__u64 xdp_timestamp;
 	__u32 rx_hash;
 	union {
 		__u32 rx_hash_type;
 		__s32 rx_hash_err;
 	};
+	union {
+		__u16 rx_ctag;
+		__s32 rx_ctag_err;
+	};
+	union {
+		__u16 rx_stag;
+		__s32 rx_stag_err;
+	};
+	union {
+		__u8 rx_csum_lvl;
+		__s32 rx_csum_err;
+	};
+	enum xdp_meta_field hint_valid;
 };
-- 
2.35.3