[dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add PTYPE to DEV_RX_OFFLOAD_* flags.

Currently, most of the NICs already support PTYPE parsing and update
the mbuf->packet_type through an internal lookup table, but there is
no way to disable the lookup if the application is not intrested in
ptypes returned by `rte_eth_dev_get_supported_ptypes`.

Pavan Nikhilesh (3):
  ethdev: add ptype as an Rx offload
  net: update Rx offload capabilities
  examples: add Rx ptype offload

 doc/guides/nics/features.rst                    |  3 +++
 drivers/net/atlantic/atl_ethdev.c               |  3 ++-
 drivers/net/bnxt/bnxt_ethdev.c                  |  3 ++-
 drivers/net/cxgbe/cxgbe.h                       |  3 ++-
 drivers/net/dpaa/dpaa_ethdev.c                  |  3 ++-
 drivers/net/dpaa2/dpaa2_ethdev.c                |  3 ++-
 drivers/net/e1000/em_rxtx.c                     |  3 ++-
 drivers/net/e1000/igb_rxtx.c                    |  3 ++-
 drivers/net/enetc/enetc_ethdev.c                |  3 ++-
 drivers/net/enic/enic_res.c                     |  3 ++-
 drivers/net/failsafe/failsafe_ops.c             |  6 ++++--
 drivers/net/fm10k/fm10k_ethdev.c                | 15 ++++++++-------
 drivers/net/i40e/i40e_ethdev.c                  |  3 ++-
 drivers/net/iavf/iavf_ethdev.c                  |  3 ++-
 drivers/net/ice/ice_ethdev.c                    |  3 ++-
 drivers/net/ixgbe/ixgbe_rxtx.c                  |  3 ++-
 drivers/net/mlx4/mlx4_rxq.c                     |  3 ++-
 drivers/net/mlx5/mlx5_rxq.c                     |  3 ++-
 drivers/net/mvneta/mvneta_ethdev.h              |  3 ++-
 drivers/net/mvpp2/mrvl_ethdev.c                 |  3 ++-
 drivers/net/netvsc/hn_rndis.c                   |  3 ++-
 drivers/net/nfp/nfp_net.c                       |  3 ++-
 drivers/net/octeontx/octeontx_ethdev.h          |  3 ++-
 drivers/net/octeontx2/otx2_ethdev.c             |  5 +++++
 drivers/net/octeontx2/otx2_ethdev.h             | 15 ++++++++-------
 drivers/net/qede/qede_ethdev.c                  |  3 ++-
 drivers/net/tap/rte_eth_tap.c                   |  3 ++-
 drivers/net/thunderx/nicvf_ethdev.h             |  3 ++-
 drivers/net/vmxnet3/vmxnet3_ethdev.c            |  3 ++-
 examples/ip_fragmentation/main.c                |  7 +++++++
 examples/l3fwd-power/main.c                     |  8 ++++++++
 examples/l3fwd/main.c                           |  9 +++++++++
 examples/performance-thread/l3fwd-thread/main.c |  9 +++++++++
 examples/tep_termination/vxlan_setup.c          |  1 +
 lib/librte_ethdev/rte_ethdev.h                  |  1 +
 35 files changed, 111 insertions(+), 40 deletions(-)

--
2.17.1

[dpdk-dev] [RFC 1/3] ethdev: add ptype as an Rx offload

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add ptype to DEV_RX_OFFLOAD_* flags which can be used to enable/disable
packet type parsing.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 doc/guides/nics/features.rst   | 3 +++
 lib/librte_ethdev/rte_ethdev.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/doc/guides/nics/features.rst b/doc/guides/nics/features.rst
index 6f8cac2c8..6b222b270 100644
--- a/doc/guides/nics/features.rst
+++ b/doc/guides/nics/features.rst
@@ -662,6 +662,9 @@ Packet type parsing
 
 Supports packet type parsing and returns a list of supported types.
 
+* **[uses]       rte_eth_rxconf,rte_eth_rxmpde**: ``offloads:DEV_RX_OFFLOAD_PTYPE``.
+* **[provides]   mbuf**: ``mbuf.packet_type``.
+* **[provides]   rte_eth_dev_info**: ``rx_offload_capa,rx_queue_offload_capa:DEV_RX_OFFLOAD_PTYPE``.
 * **[implements] eth_dev_ops**: ``dev_supported_ptypes_get``.
 * **[related]    API**: ``rte_eth_dev_get_supported_ptypes()``.
 
diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h
index dc6596bc9..888b766d4 100644
--- a/lib/librte_ethdev/rte_ethdev.h
+++ b/lib/librte_ethdev/rte_ethdev.h
@@ -1013,6 +1013,7 @@ struct rte_eth_conf {
 #define DEV_RX_OFFLOAD_KEEP_CRC		0x00010000
 #define DEV_RX_OFFLOAD_SCTP_CKSUM	0x00020000
 #define DEV_RX_OFFLOAD_OUTER_UDP_CKSUM  0x00040000
+#define DEV_RX_OFFLOAD_PTYPE		0x00080000
 
 #define DEV_RX_OFFLOAD_CHECKSUM (DEV_RX_OFFLOAD_IPV4_CKSUM | \
 				 DEV_RX_OFFLOAD_UDP_CKSUM | \
-- 
2.17.1

[dpdk-dev] [RFC 2/3] net: update Rx offload capabilities

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add DEV_RX_OFFLOAD_PTYPE flag for all supported NICs.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 drivers/net/atlantic/atl_ethdev.c      |  3 ++-
 drivers/net/bnxt/bnxt_ethdev.c         |  3 ++-
 drivers/net/cxgbe/cxgbe.h              |  3 ++-
 drivers/net/dpaa/dpaa_ethdev.c         |  3 ++-
 drivers/net/dpaa2/dpaa2_ethdev.c       |  3 ++-
 drivers/net/e1000/em_rxtx.c            |  3 ++-
 drivers/net/e1000/igb_rxtx.c           |  3 ++-
 drivers/net/enetc/enetc_ethdev.c       |  3 ++-
 drivers/net/enic/enic_res.c            |  3 ++-
 drivers/net/failsafe/failsafe_ops.c    |  6 ++++--
 drivers/net/fm10k/fm10k_ethdev.c       | 15 ++++++++-------
 drivers/net/i40e/i40e_ethdev.c         |  3 ++-
 drivers/net/iavf/iavf_ethdev.c         |  3 ++-
 drivers/net/ice/ice_ethdev.c           |  3 ++-
 drivers/net/ixgbe/ixgbe_rxtx.c         |  3 ++-
 drivers/net/mlx4/mlx4_rxq.c            |  3 ++-
 drivers/net/mlx5/mlx5_rxq.c            |  3 ++-
 drivers/net/mvneta/mvneta_ethdev.h     |  3 ++-
 drivers/net/mvpp2/mrvl_ethdev.c        |  3 ++-
 drivers/net/netvsc/hn_rndis.c          |  3 ++-
 drivers/net/nfp/nfp_net.c              |  3 ++-
 drivers/net/octeontx/octeontx_ethdev.h |  3 ++-
 drivers/net/octeontx2/otx2_ethdev.c    |  5 +++++
 drivers/net/octeontx2/otx2_ethdev.h    | 15 ++++++++-------
 drivers/net/qede/qede_ethdev.c         |  3 ++-
 drivers/net/tap/rte_eth_tap.c          |  3 ++-
 drivers/net/thunderx/nicvf_ethdev.h    |  3 ++-
 drivers/net/vmxnet3/vmxnet3_ethdev.c   |  3 ++-
 28 files changed, 73 insertions(+), 40 deletions(-)

diff --git a/drivers/net/atlantic/atl_ethdev.c b/drivers/net/atlantic/atl_ethdev.c
index 3c1b349df..d3ae1fb1e 100644
--- a/drivers/net/atlantic/atl_ethdev.c
+++ b/drivers/net/atlantic/atl_ethdev.c
@@ -168,7 +168,8 @@ static struct rte_pci_driver rte_atl_pmd = {
 			| DEV_RX_OFFLOAD_TCP_CKSUM \
 			| DEV_RX_OFFLOAD_JUMBO_FRAME \
 			| DEV_RX_OFFLOAD_MACSEC_STRIP \
-			| DEV_RX_OFFLOAD_VLAN_FILTER)
+			| DEV_RX_OFFLOAD_VLAN_FILTER \
+			| DEV_RX_OFFLOAD_PTYPE)
 
 #define ATL_TX_OFFLOADS (DEV_TX_OFFLOAD_VLAN_INSERT \
 			| DEV_TX_OFFLOAD_IPV4_CKSUM \
diff --git a/drivers/net/bnxt/bnxt_ethdev.c b/drivers/net/bnxt/bnxt_ethdev.c
index 25a345cd4..fda0bf176 100644
--- a/drivers/net/bnxt/bnxt_ethdev.c
+++ b/drivers/net/bnxt/bnxt_ethdev.c
@@ -160,7 +160,8 @@ static const struct rte_pci_id bnxt_pci_id_map[] = {
 				     DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM | \
 				     DEV_RX_OFFLOAD_JUMBO_FRAME | \
 				     DEV_RX_OFFLOAD_KEEP_CRC | \
-				     DEV_RX_OFFLOAD_TCP_LRO)
+				     DEV_RX_OFFLOAD_TCP_LRO | \
+				     DEV_RX_OFFLOAD_PTYPE)
 
 static int bnxt_vlan_offload_set_op(struct rte_eth_dev *dev, int mask);
 static void bnxt_print_link_info(struct rte_eth_dev *eth_dev);
diff --git a/drivers/net/cxgbe/cxgbe.h b/drivers/net/cxgbe/cxgbe.h
index 3f97fa58b..6315192ab 100644
--- a/drivers/net/cxgbe/cxgbe.h
+++ b/drivers/net/cxgbe/cxgbe.h
@@ -47,7 +47,8 @@
 			   DEV_RX_OFFLOAD_UDP_CKSUM | \
 			   DEV_RX_OFFLOAD_TCP_CKSUM | \
 			   DEV_RX_OFFLOAD_JUMBO_FRAME | \
-			   DEV_RX_OFFLOAD_SCATTER)
+			   DEV_RX_OFFLOAD_SCATTER | \
+			   DEV_RX_OFFLOAD_PTYPE)
 
 
 #define CXGBE_DEVARG_KEEP_OVLAN "keep_ovlan"
diff --git a/drivers/net/dpaa/dpaa_ethdev.c b/drivers/net/dpaa/dpaa_ethdev.c
index 7154fb9b4..960783116 100644
--- a/drivers/net/dpaa/dpaa_ethdev.c
+++ b/drivers/net/dpaa/dpaa_ethdev.c
@@ -49,7 +49,8 @@
 /* Supported Rx offloads */
 static uint64_t dev_rx_offloads_sup =
 		DEV_RX_OFFLOAD_JUMBO_FRAME |
-		DEV_RX_OFFLOAD_SCATTER;
+		DEV_RX_OFFLOAD_SCATTER |
+		DEV_RX_OFFLOAD_PTYPE;
 
 /* Rx offloads which cannot be disabled */
 static uint64_t dev_rx_offloads_nodis =
diff --git a/drivers/net/dpaa2/dpaa2_ethdev.c b/drivers/net/dpaa2/dpaa2_ethdev.c
index dd6a78f9f..a1c8ad95c 100644
--- a/drivers/net/dpaa2/dpaa2_ethdev.c
+++ b/drivers/net/dpaa2/dpaa2_ethdev.c
@@ -38,7 +38,8 @@ static uint64_t dev_rx_offloads_sup =
 		DEV_RX_OFFLOAD_TCP_CKSUM |
 		DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM |
 		DEV_RX_OFFLOAD_VLAN_FILTER |
-		DEV_RX_OFFLOAD_JUMBO_FRAME;
+		DEV_RX_OFFLOAD_JUMBO_FRAME |
+		DEV_RX_OFFLOAD_PTYPE;
 
 /* Rx offloads which cannot be disabled */
 static uint64_t dev_rx_offloads_nodis =
diff --git a/drivers/net/e1000/em_rxtx.c b/drivers/net/e1000/em_rxtx.c
index 6f40b45a3..c556e11af 100644
--- a/drivers/net/e1000/em_rxtx.c
+++ b/drivers/net/e1000/em_rxtx.c
@@ -1373,7 +1373,8 @@ em_get_rx_port_offloads_capa(struct rte_eth_dev *dev)
 		DEV_RX_OFFLOAD_UDP_CKSUM   |
 		DEV_RX_OFFLOAD_TCP_CKSUM   |
 		DEV_RX_OFFLOAD_KEEP_CRC    |
-		DEV_RX_OFFLOAD_SCATTER;
+		DEV_RX_OFFLOAD_SCATTER     |
+		DEV_RX_OFFLOAD_PTYPE;
 	if (max_rx_pktlen > RTE_ETHER_MAX_LEN)
 		rx_offload_capa |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 
diff --git a/drivers/net/e1000/igb_rxtx.c b/drivers/net/e1000/igb_rxtx.c
index c5606de5d..f082bb9f1 100644
--- a/drivers/net/e1000/igb_rxtx.c
+++ b/drivers/net/e1000/igb_rxtx.c
@@ -1646,7 +1646,8 @@ igb_get_rx_port_offloads_capa(struct rte_eth_dev *dev)
 			  DEV_RX_OFFLOAD_TCP_CKSUM   |
 			  DEV_RX_OFFLOAD_JUMBO_FRAME |
 			  DEV_RX_OFFLOAD_KEEP_CRC    |
-			  DEV_RX_OFFLOAD_SCATTER;
+			  DEV_RX_OFFLOAD_SCATTER     |
+			  DEV_RX_OFFLOAD_PTYPE;
 
 	return rx_offload_capa;
 }
diff --git a/drivers/net/enetc/enetc_ethdev.c b/drivers/net/enetc/enetc_ethdev.c
index 6c5501acb..b6613922b 100644
--- a/drivers/net/enetc/enetc_ethdev.c
+++ b/drivers/net/enetc/enetc_ethdev.c
@@ -167,7 +167,8 @@ enetc_dev_infos_get(struct rte_eth_dev *dev __rte_unused,
 		 DEV_RX_OFFLOAD_UDP_CKSUM |
 		 DEV_RX_OFFLOAD_TCP_CKSUM |
 		 DEV_RX_OFFLOAD_KEEP_CRC |
-		 DEV_RX_OFFLOAD_JUMBO_FRAME);
+		 DEV_RX_OFFLOAD_JUMBO_FRAME |
+		 DEV_RX_OFFLOAD_PTYPE);
 }
 
 static int
diff --git a/drivers/net/enic/enic_res.c b/drivers/net/enic/enic_res.c
index 9405e1933..395dccb5d 100644
--- a/drivers/net/enic/enic_res.c
+++ b/drivers/net/enic/enic_res.c
@@ -198,7 +198,8 @@ int enic_get_vnic_config(struct enic *enic)
 		DEV_RX_OFFLOAD_VLAN_STRIP |
 		DEV_RX_OFFLOAD_IPV4_CKSUM |
 		DEV_RX_OFFLOAD_UDP_CKSUM |
-		DEV_RX_OFFLOAD_TCP_CKSUM;
+		DEV_RX_OFFLOAD_TCP_CKSUM |
+		DEV_RX_OFFLOAD_PTYPE;
 	enic->tx_offload_mask =
 		PKT_TX_IPV6 |
 		PKT_TX_IPV4 |
diff --git a/drivers/net/failsafe/failsafe_ops.c b/drivers/net/failsafe/failsafe_ops.c
index 96e05d4dc..b6f73a5fb 100644
--- a/drivers/net/failsafe/failsafe_ops.c
+++ b/drivers/net/failsafe/failsafe_ops.c
@@ -895,7 +895,8 @@ fs_dev_infos_get(struct rte_eth_dev *dev,
 		DEV_RX_OFFLOAD_JUMBO_FRAME |
 		DEV_RX_OFFLOAD_SCATTER |
 		DEV_RX_OFFLOAD_TIMESTAMP |
-		DEV_RX_OFFLOAD_SECURITY;
+		DEV_RX_OFFLOAD_SECURITY |
+		DEV_RX_OFFLOAD_PTYPE;
 
 	infos->rx_queue_offload_capa =
 		DEV_RX_OFFLOAD_VLAN_STRIP |
@@ -912,7 +913,8 @@ fs_dev_infos_get(struct rte_eth_dev *dev,
 		DEV_RX_OFFLOAD_JUMBO_FRAME |
 		DEV_RX_OFFLOAD_SCATTER |
 		DEV_RX_OFFLOAD_TIMESTAMP |
-		DEV_RX_OFFLOAD_SECURITY;
+		DEV_RX_OFFLOAD_SECURITY |
+		DEV_RX_OFFLOAD_PTYPE;
 
 	infos->tx_offload_capa =
 		DEV_TX_OFFLOAD_MULTI_SEGS |
diff --git a/drivers/net/fm10k/fm10k_ethdev.c b/drivers/net/fm10k/fm10k_ethdev.c
index db4d72129..ed07dae2a 100644
--- a/drivers/net/fm10k/fm10k_ethdev.c
+++ b/drivers/net/fm10k/fm10k_ethdev.c
@@ -1791,13 +1791,14 @@ static uint64_t fm10k_get_rx_port_offloads_capa(struct rte_eth_dev *dev)
 {
 	RTE_SET_USED(dev);
 
-	return  (uint64_t)(DEV_RX_OFFLOAD_VLAN_STRIP  |
-			   DEV_RX_OFFLOAD_VLAN_FILTER |
-			   DEV_RX_OFFLOAD_IPV4_CKSUM  |
-			   DEV_RX_OFFLOAD_UDP_CKSUM   |
-			   DEV_RX_OFFLOAD_TCP_CKSUM   |
-			   DEV_RX_OFFLOAD_JUMBO_FRAME |
-			   DEV_RX_OFFLOAD_HEADER_SPLIT);
+	return  (uint64_t)(DEV_RX_OFFLOAD_VLAN_STRIP   |
+			   DEV_RX_OFFLOAD_VLAN_FILTER  |
+			   DEV_RX_OFFLOAD_IPV4_CKSUM   |
+			   DEV_RX_OFFLOAD_UDP_CKSUM    |
+			   DEV_RX_OFFLOAD_TCP_CKSUM    |
+			   DEV_RX_OFFLOAD_JUMBO_FRAME  |
+			   DEV_RX_OFFLOAD_HEADER_SPLIT |
+			   DEV_RX_OFFLOAD_PTYPE);
 }
 
 static int
diff --git a/drivers/net/i40e/i40e_ethdev.c b/drivers/net/i40e/i40e_ethdev.c
index 4e40b7ab5..75f219b17 100644
--- a/drivers/net/i40e/i40e_ethdev.c
+++ b/drivers/net/i40e/i40e_ethdev.c
@@ -3511,7 +3511,8 @@ i40e_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 		DEV_RX_OFFLOAD_SCATTER |
 		DEV_RX_OFFLOAD_VLAN_EXTEND |
 		DEV_RX_OFFLOAD_VLAN_FILTER |
-		DEV_RX_OFFLOAD_JUMBO_FRAME;
+		DEV_RX_OFFLOAD_JUMBO_FRAME |
+		DEV_RX_OFFLOAD_PTYPE;
 
 	dev_info->tx_queue_offload_capa = DEV_TX_OFFLOAD_MBUF_FAST_FREE;
 	dev_info->tx_offload_capa =
diff --git a/drivers/net/iavf/iavf_ethdev.c b/drivers/net/iavf/iavf_ethdev.c
index 8f3907378..7cf71ecd4 100644
--- a/drivers/net/iavf/iavf_ethdev.c
+++ b/drivers/net/iavf/iavf_ethdev.c
@@ -517,7 +517,8 @@ iavf_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 		DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM |
 		DEV_RX_OFFLOAD_SCATTER |
 		DEV_RX_OFFLOAD_JUMBO_FRAME |
-		DEV_RX_OFFLOAD_VLAN_FILTER;
+		DEV_RX_OFFLOAD_VLAN_FILTER |
+		DEV_RX_OFFLOAD_PTYPE;
 	dev_info->tx_offload_capa =
 		DEV_TX_OFFLOAD_VLAN_INSERT |
 		DEV_TX_OFFLOAD_QINQ_INSERT |
diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index 8c60a988a..28e3c6f8f 100644
--- a/drivers/net/ice/ice_ethdev.c
+++ b/drivers/net/ice/ice_ethdev.c
@@ -2118,7 +2118,8 @@ ice_dev_info_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 		DEV_RX_OFFLOAD_JUMBO_FRAME |
 		DEV_RX_OFFLOAD_KEEP_CRC |
 		DEV_RX_OFFLOAD_SCATTER |
-		DEV_RX_OFFLOAD_VLAN_FILTER;
+		DEV_RX_OFFLOAD_VLAN_FILTER |
+		DEV_RX_OFFLOAD_PTYPE;
 	dev_info->tx_offload_capa =
 		DEV_TX_OFFLOAD_VLAN_INSERT |
 		DEV_TX_OFFLOAD_TCP_TSO |
diff --git a/drivers/net/ixgbe/ixgbe_rxtx.c b/drivers/net/ixgbe/ixgbe_rxtx.c
index edcfa60ce..942454cb4 100644
--- a/drivers/net/ixgbe/ixgbe_rxtx.c
+++ b/drivers/net/ixgbe/ixgbe_rxtx.c
@@ -2872,7 +2872,8 @@ ixgbe_get_rx_port_offloads(struct rte_eth_dev *dev)
 		   DEV_RX_OFFLOAD_KEEP_CRC    |
 		   DEV_RX_OFFLOAD_JUMBO_FRAME |
 		   DEV_RX_OFFLOAD_VLAN_FILTER |
-		   DEV_RX_OFFLOAD_SCATTER;
+		   DEV_RX_OFFLOAD_SCATTER     |
+		   DEV_RX_OFFLOAD_PTYPE;
 
 	if (hw->mac.type == ixgbe_mac_82598EB)
 		offloads |= DEV_RX_OFFLOAD_VLAN_STRIP;
diff --git a/drivers/net/mlx4/mlx4_rxq.c b/drivers/net/mlx4/mlx4_rxq.c
index f45c1ff85..e915a7c6f 100644
--- a/drivers/net/mlx4/mlx4_rxq.c
+++ b/drivers/net/mlx4/mlx4_rxq.c
@@ -685,7 +685,8 @@ mlx4_get_rx_queue_offloads(struct mlx4_priv *priv)
 {
 	uint64_t offloads = DEV_RX_OFFLOAD_SCATTER |
 			    DEV_RX_OFFLOAD_KEEP_CRC |
-			    DEV_RX_OFFLOAD_JUMBO_FRAME;
+			    DEV_RX_OFFLOAD_JUMBO_FRAME |
+			    DEV_RX_OFFLOAD_PTYPE;
 
 	if (priv->hw_csum)
 		offloads |= DEV_RX_OFFLOAD_CHECKSUM;
diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
index a1fdeef2a..c3c35a7c1 100644
--- a/drivers/net/mlx5/mlx5_rxq.c
+++ b/drivers/net/mlx5/mlx5_rxq.c
@@ -368,7 +368,8 @@ mlx5_get_rx_queue_offloads(struct rte_eth_dev *dev)
 	struct mlx5_dev_config *config = &priv->config;
 	uint64_t offloads = (DEV_RX_OFFLOAD_SCATTER |
 			     DEV_RX_OFFLOAD_TIMESTAMP |
-			     DEV_RX_OFFLOAD_JUMBO_FRAME);
+			     DEV_RX_OFFLOAD_JUMBO_FRAME |
+			     DEV_RX_OFFLOAD_PTYPE);
 
 	if (config->hw_fcs_strip)
 		offloads |= DEV_RX_OFFLOAD_KEEP_CRC;
diff --git a/drivers/net/mvneta/mvneta_ethdev.h b/drivers/net/mvneta/mvneta_ethdev.h
index ef8067790..cee859679 100644
--- a/drivers/net/mvneta/mvneta_ethdev.h
+++ b/drivers/net/mvneta/mvneta_ethdev.h
@@ -55,7 +55,8 @@
 
 /** Rx offloads capabilities */
 #define MVNETA_RX_OFFLOADS (DEV_RX_OFFLOAD_JUMBO_FRAME | \
-			    DEV_RX_OFFLOAD_CHECKSUM)
+			    DEV_RX_OFFLOAD_CHECKSUM |    \
+			    DEV_RX_OFFLOAD_PTYPE)
 
 /** Tx offloads capabilities */
 #define MVNETA_TX_OFFLOAD_CHECKSUM (DEV_TX_OFFLOAD_IPV4_CKSUM | \
diff --git a/drivers/net/mvpp2/mrvl_ethdev.c b/drivers/net/mvpp2/mrvl_ethdev.c
index 810a703fc..e5dd96fa6 100644
--- a/drivers/net/mvpp2/mrvl_ethdev.c
+++ b/drivers/net/mvpp2/mrvl_ethdev.c
@@ -60,7 +60,8 @@
 /** Port Rx offload capabilities */
 #define MRVL_RX_OFFLOADS (DEV_RX_OFFLOAD_VLAN_FILTER | \
 			  DEV_RX_OFFLOAD_JUMBO_FRAME | \
-			  DEV_RX_OFFLOAD_CHECKSUM)
+			  DEV_RX_OFFLOAD_CHECKSUM | \
+			  DEV_RX_OFFLOAD_PTYPE)
 
 /** Port Tx offloads capabilities */
 #define MRVL_TX_OFFLOADS (DEV_TX_OFFLOAD_IPV4_CKSUM | \
diff --git a/drivers/net/netvsc/hn_rndis.c b/drivers/net/netvsc/hn_rndis.c
index a67bc7a79..13a9da90f 100644
--- a/drivers/net/netvsc/hn_rndis.c
+++ b/drivers/net/netvsc/hn_rndis.c
@@ -897,7 +897,8 @@ int hn_rndis_get_offload(struct hn_data *hv,
 	    == HN_NDIS_LSOV2_CAP_IP6)
 		dev_info->tx_offload_capa |= DEV_TX_OFFLOAD_TCP_TSO;
 
-	dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP;
+	dev_info->rx_offload_capa = DEV_RX_OFFLOAD_VLAN_STRIP |
+				    DEV_RX_OFFLOAD_PTYPE;
 
 	if (hwcaps.ndis_csum.ndis_ip4_rxcsum & NDIS_RXCSUM_CAP_IP4)
 		dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_IPV4_CKSUM;
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/nfp/nfp_net.c
index f1a3ef2f9..ce27ac763 100644
--- a/drivers/net/nfp/nfp_net.c
+++ b/drivers/net/nfp/nfp_net.c
@@ -1226,7 +1226,8 @@ nfp_net_infos_get(struct rte_eth_dev *dev, struct rte_eth_dev_info *dev_info)
 					     DEV_RX_OFFLOAD_UDP_CKSUM |
 					     DEV_RX_OFFLOAD_TCP_CKSUM;
 
-	dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_JUMBO_FRAME;
+	dev_info->rx_offload_capa |= DEV_RX_OFFLOAD_JUMBO_FRAME |
+				     DEV_RX_OFFLOAD_PTYPE;
 
 	if (hw->cap & NFP_NET_CFG_CTRL_TXVLAN)
 		dev_info->tx_offload_capa = DEV_TX_OFFLOAD_VLAN_INSERT;
diff --git a/drivers/net/octeontx/octeontx_ethdev.h b/drivers/net/octeontx/octeontx_ethdev.h
index fd2e99edf..20703977e 100644
--- a/drivers/net/octeontx/octeontx_ethdev.h
+++ b/drivers/net/octeontx/octeontx_ethdev.h
@@ -29,7 +29,8 @@
 #define OCTEONTX_MAX_BGX_PORTS			4
 #define OCTEONTX_MAX_LMAC_PER_BGX		4
 
-#define OCTEONTX_RX_OFFLOADS			DEV_RX_OFFLOAD_CHECKSUM
+#define OCTEONTX_RX_OFFLOADS			(DEV_RX_OFFLOAD_CHECKSUM | \
+						 DEV_RX_OFFLOAD_PTYPE)
 #define OCTEONTX_TX_OFFLOADS			DEV_TX_OFFLOAD_MT_LOCKFREE
 
 static inline struct octeontx_nic *
diff --git a/drivers/net/octeontx2/otx2_ethdev.c b/drivers/net/octeontx2/otx2_ethdev.c
index b84128fef..ca01bf081 100644
--- a/drivers/net/octeontx2/otx2_ethdev.c
+++ b/drivers/net/octeontx2/otx2_ethdev.c
@@ -590,6 +590,11 @@ nix_rx_offload_flags(struct rte_eth_dev *eth_dev)
 	if ((dev->rx_offloads & DEV_RX_OFFLOAD_TIMESTAMP))
 		flags |= NIX_RX_OFFLOAD_TSTAMP_F;
 
+	if ((dev->rx_offloads & DEV_RX_OFFLOAD_PTYPE))
+		flags |= NIX_RX_OFFLOAD_PTYPE_F;
+	else
+		flags &= ~NIX_RX_OFFLOAD_PTYPE_F;
+
 	return flags;
 }
 
diff --git a/drivers/net/octeontx2/otx2_ethdev.h b/drivers/net/octeontx2/otx2_ethdev.h
index 7b15d6bc8..2eeb07c9c 100644
--- a/drivers/net/octeontx2/otx2_ethdev.h
+++ b/drivers/net/octeontx2/otx2_ethdev.h
@@ -122,8 +122,8 @@
 	DEV_TX_OFFLOAD_MT_LOCKFREE	| \
 	DEV_TX_OFFLOAD_VLAN_INSERT	| \
 	DEV_TX_OFFLOAD_QINQ_INSERT	| \
-	DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM | \
-	DEV_TX_OFFLOAD_OUTER_UDP_CKSUM  | \
+	DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM	| \
+	DEV_TX_OFFLOAD_OUTER_UDP_CKSUM	| \
 	DEV_TX_OFFLOAD_TCP_CKSUM	| \
 	DEV_TX_OFFLOAD_UDP_CKSUM	| \
 	DEV_TX_OFFLOAD_SCTP_CKSUM	| \
@@ -136,11 +136,12 @@
 	DEV_RX_OFFLOAD_OUTER_IPV4_CKSUM | \
 	DEV_RX_OFFLOAD_SCATTER		| \
 	DEV_RX_OFFLOAD_JUMBO_FRAME	| \
-	DEV_RX_OFFLOAD_OUTER_UDP_CKSUM | \
-	DEV_RX_OFFLOAD_VLAN_STRIP | \
-	DEV_RX_OFFLOAD_VLAN_FILTER | \
-	DEV_RX_OFFLOAD_QINQ_STRIP | \
-	DEV_RX_OFFLOAD_TIMESTAMP)
+	DEV_RX_OFFLOAD_OUTER_UDP_CKSUM	| \
+	DEV_RX_OFFLOAD_VLAN_STRIP	| \
+	DEV_RX_OFFLOAD_VLAN_FILTER	| \
+	DEV_RX_OFFLOAD_QINQ_STRIP	| \
+	DEV_RX_OFFLOAD_TIMESTAMP	| \
+	DEV_RX_OFFLOAD_PTYPE)
 
 #define NIX_DEFAULT_RSS_CTX_GROUP  0
 #define NIX_DEFAULT_RSS_MCAM_IDX  -1
diff --git a/drivers/net/qede/qede_ethdev.c b/drivers/net/qede/qede_ethdev.c
index 528b33e8c..2af69416b 100644
--- a/drivers/net/qede/qede_ethdev.c
+++ b/drivers/net/qede/qede_ethdev.c
@@ -1291,7 +1291,8 @@ qede_dev_info_get(struct rte_eth_dev *eth_dev,
 				     DEV_RX_OFFLOAD_SCATTER	|
 				     DEV_RX_OFFLOAD_JUMBO_FRAME |
 				     DEV_RX_OFFLOAD_VLAN_FILTER |
-				     DEV_RX_OFFLOAD_VLAN_STRIP);
+				     DEV_RX_OFFLOAD_VLAN_STRIP  |
+				     DEV_RX_OFFLOAD_PTYPE);
 	dev_info->rx_queue_offload_capa = 0;
 
 	/* TX offloads are on a per-packet basis, so it is applicable
diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c
index 64bd04911..21307d9b9 100644
--- a/drivers/net/tap/rte_eth_tap.c
+++ b/drivers/net/tap/rte_eth_tap.c
@@ -336,7 +336,8 @@ tap_rx_offload_get_queue_capa(void)
 	return DEV_RX_OFFLOAD_SCATTER |
 	       DEV_RX_OFFLOAD_IPV4_CKSUM |
 	       DEV_RX_OFFLOAD_UDP_CKSUM |
-	       DEV_RX_OFFLOAD_TCP_CKSUM;
+	       DEV_RX_OFFLOAD_TCP_CKSUM |
+	       DEV_RX_OFFLOAD_PTYPE;
 }
 
 /* Callback to handle the rx burst of packets to the correct interface and
diff --git a/drivers/net/thunderx/nicvf_ethdev.h b/drivers/net/thunderx/nicvf_ethdev.h
index c0bfbf848..6b1e433d2 100644
--- a/drivers/net/thunderx/nicvf_ethdev.h
+++ b/drivers/net/thunderx/nicvf_ethdev.h
@@ -41,7 +41,8 @@
 	DEV_RX_OFFLOAD_CHECKSUM    | \
 	DEV_RX_OFFLOAD_VLAN_STRIP  | \
 	DEV_RX_OFFLOAD_JUMBO_FRAME | \
-	DEV_RX_OFFLOAD_SCATTER)
+	DEV_RX_OFFLOAD_SCATTER     | \
+	DEV_RX_OFFLOAD_PTYPE)
 
 #define NICVF_DEFAULT_RX_FREE_THRESH    224
 #define NICVF_DEFAULT_TX_FREE_THRESH    224
diff --git a/drivers/net/vmxnet3/vmxnet3_ethdev.c b/drivers/net/vmxnet3/vmxnet3_ethdev.c
index 57feb3773..2276c811a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethdev.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethdev.c
@@ -58,7 +58,8 @@
 	 DEV_RX_OFFLOAD_UDP_CKSUM |	\
 	 DEV_RX_OFFLOAD_TCP_CKSUM |	\
 	 DEV_RX_OFFLOAD_TCP_LRO |	\
-	 DEV_RX_OFFLOAD_JUMBO_FRAME)
+	 DEV_RX_OFFLOAD_JUMBO_FRAME |   \
+	 DEV_RX_OFFLOAD_PTYPE)
 
 static int eth_vmxnet3_dev_init(struct rte_eth_dev *eth_dev);
 static int eth_vmxnet3_dev_uninit(struct rte_eth_dev *eth_dev);
-- 
2.17.1

[dpdk-dev] [RFC 3/3] examples: add Rx ptype offload

[pbhagavatula]

From: Pavan Nikhilesh <pbhagavatula@marvell.com>

Add DEV_RX_OFFLOAD_PTYPE as a offload requirement for applicable
examples.

Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
---
 examples/ip_fragmentation/main.c                | 7 +++++++
 examples/l3fwd-power/main.c                     | 8 ++++++++
 examples/l3fwd/main.c                           | 9 +++++++++
 examples/performance-thread/l3fwd-thread/main.c | 9 +++++++++
 examples/tep_termination/vxlan_setup.c          | 1 +
 5 files changed, 34 insertions(+)

diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c
index 324d60773..2a9895542 100644
--- a/examples/ip_fragmentation/main.c
+++ b/examples/ip_fragmentation/main.c
@@ -904,6 +904,13 @@ main(int argc, char **argv)
 
 		/* limit the frame size to the maximum supported by NIC */
 		rte_eth_dev_info_get(portid, &dev_info);
+
+		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE)
+			local_port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_PTYPE;
+
+		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
+			local_port_conf.txmode.offloads |=
+				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
 		local_port_conf.rxmode.max_rx_pkt_len = RTE_MIN(
 		    dev_info.max_rx_pktlen,
 		    local_port_conf.rxmode.max_rx_pkt_len);
diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
index fd8d9528f..875d60c06 100644
--- a/examples/l3fwd-power/main.c
+++ b/examples/l3fwd-power/main.c
@@ -2261,6 +2261,14 @@ main(int argc, char **argv)
 		dev_rxq_num = dev_info.max_rx_queues;
 		dev_txq_num = dev_info.max_tx_queues;
 
+		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
+			if (!parse_ptype)
+				port_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_PTYPE;
+		} else {
+			parse_ptype = 1;
+		}
+
 		nb_rx_queue = get_port_n_rx_queues(portid);
 		if (nb_rx_queue > dev_rxq_num)
 			rte_exit(EXIT_FAILURE,
diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
index 3800bad19..dfee880a0 100644
--- a/examples/l3fwd/main.c
+++ b/examples/l3fwd/main.c
@@ -875,6 +875,15 @@ main(int argc, char **argv)
 			nb_rx_queue, (unsigned)n_tx_queue );
 
 		rte_eth_dev_info_get(portid, &dev_info);
+
+		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
+			if (!parse_ptype)
+				local_port_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_PTYPE;
+		} else {
+			parse_ptype = 1;
+		}
+
 		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
 			local_port_conf.txmode.offloads |=
 				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
diff --git a/examples/performance-thread/l3fwd-thread/main.c b/examples/performance-thread/l3fwd-thread/main.c
index 49d942407..f033326be 100644
--- a/examples/performance-thread/l3fwd-thread/main.c
+++ b/examples/performance-thread/l3fwd-thread/main.c
@@ -3560,6 +3560,15 @@ main(int argc, char **argv)
 		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
 			nb_rx_queue, (unsigned)n_tx_queue);
 		rte_eth_dev_info_get(portid, &dev_info);
+
+		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
+			if (!parse_ptype_on)
+				port_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_PTYPE;
+		} else {
+			parse_ptype_on = 1;
+		}
+
 		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
 			local_port_conf.txmode.offloads |=
 				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
diff --git a/examples/tep_termination/vxlan_setup.c b/examples/tep_termination/vxlan_setup.c
index 9a0880002..3d2acecd5 100644
--- a/examples/tep_termination/vxlan_setup.c
+++ b/examples/tep_termination/vxlan_setup.c
@@ -69,6 +69,7 @@ uint8_t tep_filter_type[] = {RTE_TUNNEL_FILTER_IMAC_TENID,
 static struct rte_eth_conf port_conf = {
 	.rxmode = {
 		.split_hdr_size = 0,
+		.offloads = DEV_RX_OFFLOAD_PTYPE,
 	},
 	.txmode = {
 		.mq_mode = ETH_MQ_TX_NONE,
-- 
2.17.1

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Hemant Agrawal]

> 
> Add PTYPE to DEV_RX_OFFLOAD_* flags.
> 
> Currently, most of the NICs already support PTYPE parsing and update the
> mbuf->packet_type through an internal lookup table, but there is no way to
> disable the lookup if the application is not intrested in ptypes returned by
> `rte_eth_dev_get_supported_ptypes`.
> 
[Hemant]  it will also mean introducing another check in datapath, if the application has asked for PTYPE offload - copy the results to mbuf->packet_type otherwise don't do it. 

Your second patch is incomplete in the sense that it only adds the capability. But it does not disable the lookups? 

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Pavan Nikhilesh Bhagavatula]

>-----Original Message-----
>From: Hemant Agrawal <hemant.agrawal@nxp.com>
>Sent: Tuesday, August 6, 2019 1:49 PM
>To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>Jacob Kollanukkaran <jerinj@marvell.com>
>Cc: dev@dpdk.org
>Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>
>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
>>
>> Currently, most of the NICs already support PTYPE parsing and update
>the
>> mbuf->packet_type through an internal lookup table, but there is no
>way to
>> disable the lookup if the application is not intrested in ptypes
>returned by
>> `rte_eth_dev_get_supported_ptypes`.
>>
>[Hemant]  it will also mean introducing another check in datapath, if the
>application has asked for PTYPE offload - copy the results to mbuf-
>>packet_type otherwise don't do it.
>

I think that having the check would give better performance than loading ptype table to L1 
doing  a lookup and copying it to mbuf when the application doesn't need it.

>Your second patch is incomplete in the sense that it only adds the
>capability. But it does not disable the lookups?

It is upto the maintainer of the PMD to disable the lookup in data path. If there is a scope of optimization 
then they could do it. There is no harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
I was hesitant to touch data path as it would be impossible to verify performance effect on all NICs.

Re: [dpdk-dev] [RFC 1/3] ethdev: add ptype as an Rx offload

[Andrew Rybchenko]

On 8/6/19 11:02 AM, pbhagavatula@marvell.com wrote:
> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>
> Add ptype to DEV_RX_OFFLOAD_* flags which can be used to enable/disable
> packet type parsing.
>
> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>

I like the idea. I think there are few more Rx features which
lack Rx offload bit:
  - delivery of RSS hash in mbuf (it is not always required when
    RSS is used to distribute packets across Rx queues)
  - maybe Rx mark, since it is an extra information which could
    be passed by NIC to CPU and it is better to know in advance
    at Rx queue setup if it should be requested and processed

API breakage should be considered here. I think it is OK to
introduce it in the next release cycle in a dummy way which
does not affect packet type delivery for existing PMDs
(i.e. add offload capability and advertise in PMD, but do not
take it into account when Rx mbuf is filled in) and
submit deprecation notice that it may be taken into account
by PMDs in 20.02 to avoid packet type delivery if the offload
is not requested. It will allow applications to make transition
smoother.

Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Andrew Rybchenko]

On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:
>
>> -----Original Message-----
>> From: Hemant Agrawal <hemant.agrawal@nxp.com>
>> Sent: Tuesday, August 6, 2019 1:49 PM
>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>> Jacob Kollanukkaran <jerinj@marvell.com>
>> Cc: dev@dpdk.org
>> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
>>>
>>> Currently, most of the NICs already support PTYPE parsing and update
>> the
>>> mbuf->packet_type through an internal lookup table, but there is no
>> way to
>>> disable the lookup if the application is not intrested in ptypes
>> returned by
>>> `rte_eth_dev_get_supported_ptypes`.
>>>
>> [Hemant]  it will also mean introducing another check in datapath, if the
>> application has asked for PTYPE offload - copy the results to mbuf-
>>> packet_type otherwise don't do it.
> I think that having the check would give better performance than loading ptype table to L1
> doing  a lookup and copying it to mbuf when the application doesn't need it.

Anyway, if PMD decides that it is better to always provide packet type
information - there is no harm. Basically if the offload is not requested
it makes packet_type undefined in mbuf.

>> Your second patch is incomplete in the sense that it only adds the
>> capability. But it does not disable the lookups?
> It is upto the maintainer of the PMD to disable the lookup in data path. If there is a scope of optimization
> then they could do it. There is no harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
> I was hesitant to touch data path as it would be impossible to verify performance effect on all NICs.

I think it is the right way to approach it especially taking transition 
into account.

Re: [dpdk-dev] [RFC 3/3] examples: add Rx ptype offload

[Ananyev, Konstantin]

> -----Original Message-----
> From: pbhagavatula@marvell.com [mailto:pbhagavatula@marvell.com]
> Sent: Tuesday, August 6, 2019 9:02 AM
> To: jerinj@marvell.com; Ananyev, Konstantin <konstantin.ananyev@intel.com>; Hunt, David <david.hunt@intel.com>; Kovacevic, Marko
> <marko.kovacevic@intel.com>; Ori Kam <orika@mellanox.com>; Richardson, Bruce <bruce.richardson@intel.com>; De Lara Guarch, Pablo
> <pablo.de.lara.guarch@intel.com>; Nicolau, Radu <radu.nicolau@intel.com>; Akhil Goyal <akhil.goyal@nxp.com>; Kantecki, Tomasz
> <tomasz.kantecki@intel.com>; Mcnamara, John <john.mcnamara@intel.com>; Van Haaren, Harry <harry.van.haaren@intel.com>; Li,
> Xiaoyun <xiaoyun.li@intel.com>
> Cc: dev@dpdk.org; Pavan Nikhilesh <pbhagavatula@marvell.com>
> Subject: [dpdk-dev] [RFC 3/3] examples: add Rx ptype offload
> 
> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> 
> Add DEV_RX_OFFLOAD_PTYPE as a offload requirement for applicable
> examples.
> 
> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
> ---
>  examples/ip_fragmentation/main.c                | 7 +++++++
>  examples/l3fwd-power/main.c                     | 8 ++++++++
>  examples/l3fwd/main.c                           | 9 +++++++++
>  examples/performance-thread/l3fwd-thread/main.c | 9 +++++++++
>  examples/tep_termination/vxlan_setup.c          | 1 +
>  5 files changed, 34 insertions(+)
> 
> diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c
> index 324d60773..2a9895542 100644
> --- a/examples/ip_fragmentation/main.c
> +++ b/examples/ip_fragmentation/main.c
> @@ -904,6 +904,13 @@ main(int argc, char **argv)
> 
>  		/* limit the frame size to the maximum supported by NIC */
>  		rte_eth_dev_info_get(portid, &dev_info);
> +
> +		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE)
> +			local_port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_PTYPE;
> +
> +		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
> +			local_port_conf.txmode.offloads |=
> +				DEV_TX_OFFLOAD_MBUF_FAST_FREE;

I didn't look at the rest of the patch series yet, but these 3 lines above seems wrong.
and not related to that subject. 
Probably something wrong with your merge process.
Check
commit ed553e3db4a84af0ddac0d898476333d61adb93a
Author: Sunil Kumar Kori <skori@marvell.com>
Date:   Thu Jul 25 13:54:10 2019 +0530

    examples/ip_frag: remove Tx fast free offload flag


>  		local_port_conf.rxmode.max_rx_pkt_len = RTE_MIN(
>  		    dev_info.max_rx_pktlen,
>  		    local_port_conf.rxmode.max_rx_pkt_len);
> diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
> index fd8d9528f..875d60c06 100644
> --- a/examples/l3fwd-power/main.c
> +++ b/examples/l3fwd-power/main.c
> @@ -2261,6 +2261,14 @@ main(int argc, char **argv)
>  		dev_rxq_num = dev_info.max_rx_queues;
>  		dev_txq_num = dev_info.max_tx_queues;
> 
> +		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
> +			if (!parse_ptype)
> +				port_conf.rxmode.offloads |=
> +					DEV_RX_OFFLOAD_PTYPE;
> +		} else {
> +			parse_ptype = 1;
> +		}
> +
>  		nb_rx_queue = get_port_n_rx_queues(portid);
>  		if (nb_rx_queue > dev_rxq_num)
>  			rte_exit(EXIT_FAILURE,
> diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
> index 3800bad19..dfee880a0 100644
> --- a/examples/l3fwd/main.c
> +++ b/examples/l3fwd/main.c
> @@ -875,6 +875,15 @@ main(int argc, char **argv)
>  			nb_rx_queue, (unsigned)n_tx_queue );
> 
>  		rte_eth_dev_info_get(portid, &dev_info);
> +
> +		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
> +			if (!parse_ptype)
> +				local_port_conf.rxmode.offloads |=
> +					DEV_RX_OFFLOAD_PTYPE;
> +		} else {
> +			parse_ptype = 1;
> +		}
> +
>  		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
>  			local_port_conf.txmode.offloads |=
>  				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
> diff --git a/examples/performance-thread/l3fwd-thread/main.c b/examples/performance-thread/l3fwd-thread/main.c
> index 49d942407..f033326be 100644
> --- a/examples/performance-thread/l3fwd-thread/main.c
> +++ b/examples/performance-thread/l3fwd-thread/main.c
> @@ -3560,6 +3560,15 @@ main(int argc, char **argv)
>  		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
>  			nb_rx_queue, (unsigned)n_tx_queue);
>  		rte_eth_dev_info_get(portid, &dev_info);
> +
> +		if (dev_info.rx_offload_capa & DEV_RX_OFFLOAD_PTYPE) {
> +			if (!parse_ptype_on)
> +				port_conf.rxmode.offloads |=
> +					DEV_RX_OFFLOAD_PTYPE;
> +		} else {
> +			parse_ptype_on = 1;
> +		}
> +
>  		if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
>  			local_port_conf.txmode.offloads |=
>  				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
> diff --git a/examples/tep_termination/vxlan_setup.c b/examples/tep_termination/vxlan_setup.c
> index 9a0880002..3d2acecd5 100644
> --- a/examples/tep_termination/vxlan_setup.c
> +++ b/examples/tep_termination/vxlan_setup.c
> @@ -69,6 +69,7 @@ uint8_t tep_filter_type[] = {RTE_TUNNEL_FILTER_IMAC_TENID,
>  static struct rte_eth_conf port_conf = {
>  	.rxmode = {
>  		.split_hdr_size = 0,
> +		.offloads = DEV_RX_OFFLOAD_PTYPE,
>  	},
>  	.txmode = {
>  		.mq_mode = ETH_MQ_TX_NONE,
> --
> 2.17.1

Re: [dpdk-dev] [RFC 3/3] examples: add Rx ptype offload

[Pavan Nikhilesh Bhagavatula]

>-----Original Message-----
>From: Ananyev, Konstantin <konstantin.ananyev@intel.com>
>Sent: Tuesday, August 6, 2019 2:50 PM
>To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>Jacob Kollanukkaran <jerinj@marvell.com>; Hunt, David
><david.hunt@intel.com>; Kovacevic, Marko
><marko.kovacevic@intel.com>; Ori Kam <orika@mellanox.com>;
>Richardson, Bruce <bruce.richardson@intel.com>; De Lara Guarch,
>Pablo <pablo.de.lara.guarch@intel.com>; Nicolau, Radu
><radu.nicolau@intel.com>; Akhil Goyal <akhil.goyal@nxp.com>;
>Kantecki, Tomasz <tomasz.kantecki@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Van Haaren, Harry
><harry.van.haaren@intel.com>; Li, Xiaoyun <xiaoyun.li@intel.com>
>Cc: dev@dpdk.org
>Subject: RE: [dpdk-dev] [RFC 3/3] examples: add Rx ptype offload
>> -----Original Message-----
>> From: pbhagavatula@marvell.com
>[mailto:pbhagavatula@marvell.com]
>> Sent: Tuesday, August 6, 2019 9:02 AM
>> To: jerinj@marvell.com; Ananyev, Konstantin
><konstantin.ananyev@intel.com>; Hunt, David
><david.hunt@intel.com>; Kovacevic, Marko
>> <marko.kovacevic@intel.com>; Ori Kam <orika@mellanox.com>;
>Richardson, Bruce <bruce.richardson@intel.com>; De Lara Guarch,
>Pablo
>> <pablo.de.lara.guarch@intel.com>; Nicolau, Radu
><radu.nicolau@intel.com>; Akhil Goyal <akhil.goyal@nxp.com>;
>Kantecki, Tomasz
>> <tomasz.kantecki@intel.com>; Mcnamara, John
><john.mcnamara@intel.com>; Van Haaren, Harry
><harry.van.haaren@intel.com>; Li,
>> Xiaoyun <xiaoyun.li@intel.com>
>> Cc: dev@dpdk.org; Pavan Nikhilesh <pbhagavatula@marvell.com>
>> Subject: [dpdk-dev] [RFC 3/3] examples: add Rx ptype offload
>>
>> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>
>> Add DEV_RX_OFFLOAD_PTYPE as a offload requirement for applicable
>> examples.
>>
>> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
>> ---
>>  examples/ip_fragmentation/main.c                | 7 +++++++
>>  examples/l3fwd-power/main.c                     | 8 ++++++++
>>  examples/l3fwd/main.c                           | 9 +++++++++
>>  examples/performance-thread/l3fwd-thread/main.c | 9 +++++++++
>>  examples/tep_termination/vxlan_setup.c          | 1 +
>>  5 files changed, 34 insertions(+)
>>
>> diff --git a/examples/ip_fragmentation/main.c
>b/examples/ip_fragmentation/main.c
>> index 324d60773..2a9895542 100644
>> --- a/examples/ip_fragmentation/main.c
>> +++ b/examples/ip_fragmentation/main.c
>> @@ -904,6 +904,13 @@ main(int argc, char **argv)
>>
>>  		/* limit the frame size to the maximum supported by
>NIC */
>>  		rte_eth_dev_info_get(portid, &dev_info);
>> +
>> +		if (dev_info.rx_offload_capa &
>DEV_RX_OFFLOAD_PTYPE)
>> +			local_port_conf.rxmode.offloads |=
>DEV_RX_OFFLOAD_PTYPE;
>> +
>> +		if (dev_info.tx_offload_capa &
>DEV_TX_OFFLOAD_MBUF_FAST_FREE)
>> +			local_port_conf.txmode.offloads |=
>> +				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
>
>I didn't look at the rest of the patch series yet, but these 3 lines above
>seems wrong.
>and not related to that subject.
>Probably something wrong with your merge process.

Ack. I will remove it in the next version.

>Check
>commit ed553e3db4a84af0ddac0d898476333d61adb93a
>Author: Sunil Kumar Kori <skori@marvell.com>
>Date:   Thu Jul 25 13:54:10 2019 +0530
>
>    examples/ip_frag: remove Tx fast free offload flag
>
>
>>  		local_port_conf.rxmode.max_rx_pkt_len = RTE_MIN(
>>  		    dev_info.max_rx_pktlen,
>>  		    local_port_conf.rxmode.max_rx_pkt_len);
>> diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-
>power/main.c
>> index fd8d9528f..875d60c06 100644
>> --- a/examples/l3fwd-power/main.c
>> +++ b/examples/l3fwd-power/main.c
>> @@ -2261,6 +2261,14 @@ main(int argc, char **argv)
>>  		dev_rxq_num = dev_info.max_rx_queues;
>>  		dev_txq_num = dev_info.max_tx_queues;
>>
>> +		if (dev_info.rx_offload_capa &
>DEV_RX_OFFLOAD_PTYPE) {
>> +			if (!parse_ptype)
>> +				port_conf.rxmode.offloads |=
>> +					DEV_RX_OFFLOAD_PTYPE;
>> +		} else {
>> +			parse_ptype = 1;
>> +		}
>> +
>>  		nb_rx_queue = get_port_n_rx_queues(portid);
>>  		if (nb_rx_queue > dev_rxq_num)
>>  			rte_exit(EXIT_FAILURE,
>> diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
>> index 3800bad19..dfee880a0 100644
>> --- a/examples/l3fwd/main.c
>> +++ b/examples/l3fwd/main.c
>> @@ -875,6 +875,15 @@ main(int argc, char **argv)
>>  			nb_rx_queue, (unsigned)n_tx_queue );
>>
>>  		rte_eth_dev_info_get(portid, &dev_info);
>> +
>> +		if (dev_info.rx_offload_capa &
>DEV_RX_OFFLOAD_PTYPE) {
>> +			if (!parse_ptype)
>> +				local_port_conf.rxmode.offloads |=
>> +					DEV_RX_OFFLOAD_PTYPE;
>> +		} else {
>> +			parse_ptype = 1;
>> +		}
>> +
>>  		if (dev_info.tx_offload_capa &
>DEV_TX_OFFLOAD_MBUF_FAST_FREE)
>>  			local_port_conf.txmode.offloads |=
>>  				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
>> diff --git a/examples/performance-thread/l3fwd-thread/main.c
>b/examples/performance-thread/l3fwd-thread/main.c
>> index 49d942407..f033326be 100644
>> --- a/examples/performance-thread/l3fwd-thread/main.c
>> +++ b/examples/performance-thread/l3fwd-thread/main.c
>> @@ -3560,6 +3560,15 @@ main(int argc, char **argv)
>>  		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
>>  			nb_rx_queue, (unsigned)n_tx_queue);
>>  		rte_eth_dev_info_get(portid, &dev_info);
>> +
>> +		if (dev_info.rx_offload_capa &
>DEV_RX_OFFLOAD_PTYPE) {
>> +			if (!parse_ptype_on)
>> +				port_conf.rxmode.offloads |=
>> +					DEV_RX_OFFLOAD_PTYPE;
>> +		} else {
>> +			parse_ptype_on = 1;
>> +		}
>> +
>>  		if (dev_info.tx_offload_capa &
>DEV_TX_OFFLOAD_MBUF_FAST_FREE)
>>  			local_port_conf.txmode.offloads |=
>>  				DEV_TX_OFFLOAD_MBUF_FAST_FREE;
>> diff --git a/examples/tep_termination/vxlan_setup.c
>b/examples/tep_termination/vxlan_setup.c
>> index 9a0880002..3d2acecd5 100644
>> --- a/examples/tep_termination/vxlan_setup.c
>> +++ b/examples/tep_termination/vxlan_setup.c
>> @@ -69,6 +69,7 @@ uint8_t tep_filter_type[] =
>{RTE_TUNNEL_FILTER_IMAC_TENID,
>>  static struct rte_eth_conf port_conf = {
>>  	.rxmode = {
>>  		.split_hdr_size = 0,
>> +		.offloads = DEV_RX_OFFLOAD_PTYPE,
>>  	},
>>  	.txmode = {
>>  		.mq_mode = ETH_MQ_TX_NONE,
>> --
>> 2.17.1

Re: [dpdk-dev] [EXT] Re: [RFC 1/3] ethdev: add ptype as an Rx offload

[Pavan Nikhilesh Bhagavatula]

>-----Original Message-----
>From: Andrew Rybchenko <arybchenko@solarflare.com>
>Sent: Tuesday, August 6, 2019 2:30 PM
>To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>Jacob Kollanukkaran <jerinj@marvell.com>; John McNamara
><john.mcnamara@intel.com>; Marko Kovacevic
><marko.kovacevic@intel.com>; Thomas Monjalon
><thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>
>Cc: dev@dpdk.org
>Subject: [EXT] Re: [dpdk-dev] [RFC 1/3] ethdev: add ptype as an Rx
>offload
>
>External Email
>
>----------------------------------------------------------------------
>On 8/6/19 11:02 AM, pbhagavatula@marvell.com wrote:
>> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>
>> Add ptype to DEV_RX_OFFLOAD_* flags which can be used to
>enable/disable
>> packet type parsing.
>>
>> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
>
>I like the idea. I think there are few more Rx features which
>lack Rx offload bit:
>  - delivery of RSS hash in mbuf (it is not always required when
>    RSS is used to distribute packets across Rx queues)

Especially when applications use custom hash functions to store flows.

>  - maybe Rx mark, since it is an extra information which could
>    be passed by NIC to CPU and it is better to know in advance
>    at Rx queue setup if it should be requested and processed

Are you referring to RTE_FLOW_ACTION_TYPE_MARK?

>
>API breakage should be considered here. I think it is OK to
>introduce it in the next release cycle in a dummy way which
>does not affect packet type delivery for existing PMDs
>(i.e. add offload capability and advertise in PMD, but do not
>take it into account when Rx mbuf is filled in) and
>submit deprecation notice that it may be taken into account
>by PMDs in 20.02 to avoid packet type delivery if the offload
>is not requested. It will allow applications to make transition
>smoother.

Couldn’t agree with you more. I could extend the current RFC to include 
RSS and RX mark as we would be modifying the same offload fields across 
all drivers. Easier for PMD maintainers too.

>
>Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>

Re: [dpdk-dev] [EXT] Re: [RFC 1/3] ethdev: add ptype as an Rx offload

[Stephen Hemminger]

On Tue, 6 Aug 2019 14:31:43 +0000
Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com> wrote:

> >-----Original Message-----
> >From: Andrew Rybchenko <arybchenko@solarflare.com>
> >Sent: Tuesday, August 6, 2019 2:30 PM
> >To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
> >Jacob Kollanukkaran <jerinj@marvell.com>; John McNamara
> ><john.mcnamara@intel.com>; Marko Kovacevic
> ><marko.kovacevic@intel.com>; Thomas Monjalon
> ><thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>
> >Cc: dev@dpdk.org
> >Subject: [EXT] Re: [dpdk-dev] [RFC 1/3] ethdev: add ptype as an Rx
> >offload
> >
> >External Email
> >
> >----------------------------------------------------------------------
> >On 8/6/19 11:02 AM, pbhagavatula@marvell.com wrote:  
> >> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
> >>
> >> Add ptype to DEV_RX_OFFLOAD_* flags which can be used to  
> >enable/disable  
> >> packet type parsing.
> >>
> >> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>  
> >
> >I like the idea. I think there are few more Rx features which
> >lack Rx offload bit:
> >  - delivery of RSS hash in mbuf (it is not always required when
> >    RSS is used to distribute packets across Rx queues)  
> 
> Especially when applications use custom hash functions to store flows.
> 
> >  - maybe Rx mark, since it is an extra information which could
> >    be passed by NIC to CPU and it is better to know in advance
> >    at Rx queue setup if it should be requested and processed  
> 
> Are you referring to RTE_FLOW_ACTION_TYPE_MARK?
> 
> >
> >API breakage should be considered here. I think it is OK to
> >introduce it in the next release cycle in a dummy way which
> >does not affect packet type delivery for existing PMDs
> >(i.e. add offload capability and advertise in PMD, but do not
> >take it into account when Rx mbuf is filled in) and
> >submit deprecation notice that it may be taken into account
> >by PMDs in 20.02 to avoid packet type delivery if the offload
> >is not requested. It will allow applications to make transition
> >smoother.  
> 
> Couldn’t agree with you more. I could extend the current RFC to include 
> RSS and RX mark as we would be modifying the same offload fields across 
> all drivers. Easier for PMD maintainers too.
> 
> >
> >Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>  
> 

I would rather the ptype offload be always on and handled in software
for drivers that don't do it.

Re: [dpdk-dev] [EXT] Re: [RFC 1/3] ethdev: add ptype as an Rx offload

[Andrew Rybchenko]

On 8/6/19 6:45 PM, Stephen Hemminger wrote:
> On Tue, 6 Aug 2019 14:31:43 +0000
> Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com> wrote:
>
>>> -----Original Message-----
>>> From: Andrew Rybchenko <arybchenko@solarflare.com>
>>> Sent: Tuesday, August 6, 2019 2:30 PM
>>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>>> Jacob Kollanukkaran <jerinj@marvell.com>; John McNamara
>>> <john.mcnamara@intel.com>; Marko Kovacevic
>>> <marko.kovacevic@intel.com>; Thomas Monjalon
>>> <thomas@monjalon.net>; Ferruh Yigit <ferruh.yigit@intel.com>
>>> Cc: dev@dpdk.org
>>> Subject: [EXT] Re: [dpdk-dev] [RFC 1/3] ethdev: add ptype as an Rx
>>> offload
>>>
>>> External Email
>>>
>>> ----------------------------------------------------------------------
>>> On 8/6/19 11:02 AM, pbhagavatula@marvell.com wrote:
>>>> From: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>>>
>>>> Add ptype to DEV_RX_OFFLOAD_* flags which can be used to
>>> enable/disable
>>>> packet type parsing.
>>>>
>>>> Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
>>> I like the idea. I think there are few more Rx features which
>>> lack Rx offload bit:
>>>   - delivery of RSS hash in mbuf (it is not always required when
>>>     RSS is used to distribute packets across Rx queues)
>> Especially when applications use custom hash functions to store flows.
>>
>>>   - maybe Rx mark, since it is an extra information which could
>>>     be passed by NIC to CPU and it is better to know in advance
>>>     at Rx queue setup if it should be requested and processed
>> Are you referring to RTE_FLOW_ACTION_TYPE_MARK?
>>
>>> API breakage should be considered here. I think it is OK to
>>> introduce it in the next release cycle in a dummy way which
>>> does not affect packet type delivery for existing PMDs
>>> (i.e. add offload capability and advertise in PMD, but do not
>>> take it into account when Rx mbuf is filled in) and
>>> submit deprecation notice that it may be taken into account
>>> by PMDs in 20.02 to avoid packet type delivery if the offload
>>> is not requested. It will allow applications to make transition
>>> smoother.
>> Couldn’t agree with you more. I could extend the current RFC to include
>> RSS and RX mark as we would be modifying the same offload fields across
>> all drivers. Easier for PMD maintainers too.
>>
>>> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
> I would rather the ptype offload be always on and handled in software
> for drivers that don't do it.

It sounds like wasting of CPU cycle for nothing in some cases.
Also where should software stop? There are various tunnels etc.
If application is unhappy with supported classification provided
by the driver, it can always use software parser if really required.

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Stephen Hemminger]

On Tue, 6 Aug 2019 12:06:35 +0300
Andrew Rybchenko <arybchenko@solarflare.com> wrote:

> On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:
> >  
> >> -----Original Message-----
> >> From: Hemant Agrawal <hemant.agrawal@nxp.com>
> >> Sent: Tuesday, August 6, 2019 1:49 PM
> >> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
> >> Jacob Kollanukkaran <jerinj@marvell.com>
> >> Cc: dev@dpdk.org
> >> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload  
> >>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
> >>>
> >>> Currently, most of the NICs already support PTYPE parsing and update  
> >> the  
> >>> mbuf->packet_type through an internal lookup table, but there is no  
> >> way to  
> >>> disable the lookup if the application is not intrested in ptypes  
> >> returned by  
> >>> `rte_eth_dev_get_supported_ptypes`.
> >>>  
> >> [Hemant]  it will also mean introducing another check in datapath, if the
> >> application has asked for PTYPE offload - copy the results to mbuf-  
> >>> packet_type otherwise don't do it.  
> > I think that having the check would give better performance than loading ptype table to L1
> > doing  a lookup and copying it to mbuf when the application doesn't need it.  
> 
> Anyway, if PMD decides that it is better to always provide packet type
> information - there is no harm. Basically if the offload is not requested
> it makes packet_type undefined in mbuf.
> 
> >> Your second patch is incomplete in the sense that it only adds the
> >> capability. But it does not disable the lookups?  
> > It is upto the maintainer of the PMD to disable the lookup in data path. If there is a scope of optimization
> > then they could do it. There is no harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
> > I was hesitant to touch data path as it would be impossible to verify performance effect on all NICs.  
> 
> I think it is the right way to approach it especially taking transition 
> into account.
> 

With hardline API policy, this has to fail on compile for old applications.
You can't magically assume that applications using ptype will set new feature.

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Andrew Rybchenko]

On 8/7/19 6:22 PM, Stephen Hemminger wrote:
> On Wed, 7 Aug 2019 11:32:35 +0300
> Andrew Rybchenko <arybchenko@solarflare.com> wrote:
> 
>> On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
>>>> -----Original Message-----
>>>> From: Stephen Hemminger <stephen@networkplumber.org>
>>>> Sent: Wednesday, August 7, 2019 4:45 AM
>>>> To: Andrew Rybchenko <arybchenko@solarflare.com>
>>>> Cc: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Hemant
>>>> Agrawal <hemant.agrawal@nxp.com>; Jerin Jacob Kollanukkaran
>>>> <jerinj@marvell.com>; dev@dpdk.org
>>>> Subject: [EXT] Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>>>
>>>> On Tue, 6 Aug 2019 12:06:35 +0300
>>>> Andrew Rybchenko <arybchenko@solarflare.com> wrote:
>>>>   
>>>>> On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:
>>>>>>> -----Original Message-----
>>>>>>> From: Hemant Agrawal <hemant.agrawal@nxp.com>
>>>>>>> Sent: Tuesday, August 6, 2019 1:49 PM
>>>>>>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>>>>>>> Jacob Kollanukkaran <jerinj@marvell.com>
>>>>>>> Cc: dev@dpdk.org
>>>>>>> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>>>>>>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
>>>>>>>>
>>>>>>>> Currently, most of the NICs already support PTYPE parsing and
>>>>>>>> update
>>>>>>> the
>>>>>>>> mbuf->packet_type through an internal lookup table, but there is
>>>>>>>> mbuf->no
>>>>>>> way to
>>>>>>>> disable the lookup if the application is not intrested in ptypes
>>>>>>> returned by
>>>>>>>> `rte_eth_dev_get_supported_ptypes`.
>>>>>>>>   
>>>>>>> [Hemant]  it will also mean introducing another check in datapath,
>>>>>>> if the application has asked for PTYPE offload - copy the results
>>>>>>> to mbuf-
>>>>>>>> packet_type otherwise don't do it.
>>>>>> I think that having the check would give better performance than
>>>>>> loading ptype table to L1 doing  a lookup and copying it to mbuf when the
>>>> application doesn't need it.
>>>>> Anyway, if PMD decides that it is better to always provide packet type
>>>>> information - there is no harm. Basically if the offload is not
>>>>> requested it makes packet_type undefined in mbuf.
>>>>>   
>>>>>>> Your second patch is incomplete in the sense that it only adds the
>>>>>>> capability. But it does not disable the lookups?
>>>>>> It is upto the maintainer of the PMD to disable the lookup in data
>>>>>> path. If there is a scope of optimization then they could do it. There is no
>>>> harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
>>>>>> I was hesitant to touch data path as it would be impossible to verify
>>>> performance effect on all NICs.
>>>>> I think it is the right way to approach it especially taking
>>>>> transition into account.
>>>>>   
>>>> With hardline API policy, this has to fail on compile for old applications.
>>
>> Stephen, could you explain a bit more why.
> 
> Existing releases packets will be received with ptype for hardware that
> supports it. We should not require users to change their application to
> continue to get mbufs with ptype.  If your change would break that, and
> require application to change; then your change should break the API in
> a hard way that causes compile rather than runtime failure.

Many thanks, I got it.

> The best solution would be to just keep old applications running and compiling
> without breaking anything. That means ptype should still be received.
> 
> If (as an optimization) you want to allow application to turn of getting
> ptype; then that would be a useful. Probably best done at the port level
> as part of configuration.

I see, but it contradicts to the existing practice that offloads should
be disabled by default and a way to enable should be provided.
May be techboard should discuss it and make a decision (covering RSS
hash information and Rx mark mentioned in my review notes).

>>> Not specific to this API change. That's is the propriety any new symbol addition
>>> to the code base.
>>>
>>> Planning to make this API change available fromv19.11 LTS.
>>
>> The only way to to require applications to enable PTYPE offload to get
>> ptypes in mbuf since 19.11 LTS is to have deprecation notice in 19.08.
>>
>>>> You can't magically assume that applications using ptype will set new feature.
>>> When OFFLOAD flags got introduced, we decided to disable all offloads by default.
>>> So, need to add positive logic here to enable offload instead of enable something by
>>> Default and disable if required to get have synergy with other offloads.
>>>
>>> Will update the release note as usual to document the change.
>>> Since there is NO ABI change, IMO, we don't need deprecation notice.
>>
>> Sorry, but it is a behaviour change. Before an application does not need
>> to enable ptype offload, but now it is required. It means that application
>> will be broken and, therefore, it requires deprecation notice.
> 
> The DPDK development community has to make not breaking applications
> a higher priority than adding marginal enhancements

Fair, but where is marginal enhancements boundary?

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Stephen Hemminger]

On Wed, 7 Aug 2019 11:32:35 +0300
Andrew Rybchenko <arybchenko@solarflare.com> wrote:

> On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
> >> -----Original Message-----
> >> From: Stephen Hemminger <stephen@networkplumber.org>
> >> Sent: Wednesday, August 7, 2019 4:45 AM
> >> To: Andrew Rybchenko <arybchenko@solarflare.com>
> >> Cc: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Hemant
> >> Agrawal <hemant.agrawal@nxp.com>; Jerin Jacob Kollanukkaran
> >> <jerinj@marvell.com>; dev@dpdk.org
> >> Subject: [EXT] Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
> >>
> >> On Tue, 6 Aug 2019 12:06:35 +0300
> >> Andrew Rybchenko <arybchenko@solarflare.com> wrote:
> >>  
> >>> On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:  
> >>>>> -----Original Message-----
> >>>>> From: Hemant Agrawal <hemant.agrawal@nxp.com>
> >>>>> Sent: Tuesday, August 6, 2019 1:49 PM
> >>>>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
> >>>>> Jacob Kollanukkaran <jerinj@marvell.com>
> >>>>> Cc: dev@dpdk.org
> >>>>> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload  
> >>>>>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
> >>>>>>
> >>>>>> Currently, most of the NICs already support PTYPE parsing and
> >>>>>> update  
> >>>>> the  
> >>>>>> mbuf->packet_type through an internal lookup table, but there is
> >>>>>> mbuf->no  
> >>>>> way to  
> >>>>>> disable the lookup if the application is not intrested in ptypes  
> >>>>> returned by  
> >>>>>> `rte_eth_dev_get_supported_ptypes`.
> >>>>>>  
> >>>>> [Hemant]  it will also mean introducing another check in datapath,
> >>>>> if the application has asked for PTYPE offload - copy the results
> >>>>> to mbuf-  
> >>>>>> packet_type otherwise don't do it.  
> >>>> I think that having the check would give better performance than
> >>>> loading ptype table to L1 doing  a lookup and copying it to mbuf when the  
> >> application doesn't need it.  
> >>> Anyway, if PMD decides that it is better to always provide packet type
> >>> information - there is no harm. Basically if the offload is not
> >>> requested it makes packet_type undefined in mbuf.
> >>>  
> >>>>> Your second patch is incomplete in the sense that it only adds the
> >>>>> capability. But it does not disable the lookups?  
> >>>> It is upto the maintainer of the PMD to disable the lookup in data
> >>>> path. If there is a scope of optimization then they could do it. There is no  
> >> harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.  
> >>>> I was hesitant to touch data path as it would be impossible to verify  
> >> performance effect on all NICs.  
> >>> I think it is the right way to approach it especially taking
> >>> transition into account.
> >>>  
> >> With hardline API policy, this has to fail on compile for old applications.  
> 
> Stephen, could you explain a bit more why.

Existing releases packets will be received with ptype for hardware that
supports it. We should not require users to change their application to
continue to get mbufs with ptype.  If your change would break that, and
require application to change; then your change should break the API in
a hard way that causes compile rather than runtime failure.

The best solution would be to just keep old applications running and compiling
without breaking anything. That means ptype should still be received.

If (as an optimization) you want to allow application to turn of getting
ptype; then that would be a useful. Probably best done at the port level
as part of configuration.

> 
> > Not specific to this API change. That's is the propriety any new symbol addition
> > to the code base.
> >
> > Planning to make this API change available fromv19.11 LTS.  
> 
> The only way to to require applications to enable PTYPE offload to get
> ptypes in mbuf since 19.11 LTS is to have deprecation notice in 19.08.
> 
> >> You can't magically assume that applications using ptype will set new feature.  
> > When OFFLOAD flags got introduced, we decided to disable all offloads by default.
> > So, need to add positive logic here to enable offload instead of enable something by
> > Default and disable if required to get have synergy with other offloads.
> >
> > Will update the release note as usual to document the change.
> > Since there is NO ABI change, IMO, we don't need deprecation notice.  
> 
> Sorry, but it is a behaviour change. Before an application does not need
> to enable ptype offload, but now it is required. It means that application
> will be broken and, therefore, it requires deprecation notice.

The DPDK development community has to make not breaking applications
a higher priority than adding marginal enhancements

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Andrew Rybchenko]

On 8/7/19 5:04 AM, Jerin Jacob Kollanukkaran wrote:
>> -----Original Message-----
>> From: Stephen Hemminger <stephen@networkplumber.org>
>> Sent: Wednesday, August 7, 2019 4:45 AM
>> To: Andrew Rybchenko <arybchenko@solarflare.com>
>> Cc: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Hemant
>> Agrawal <hemant.agrawal@nxp.com>; Jerin Jacob Kollanukkaran
>> <jerinj@marvell.com>; dev@dpdk.org
>> Subject: [EXT] Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>
>> On Tue, 6 Aug 2019 12:06:35 +0300
>> Andrew Rybchenko <arybchenko@solarflare.com> wrote:
>>
>>> On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:
>>>>> -----Original Message-----
>>>>> From: Hemant Agrawal <hemant.agrawal@nxp.com>
>>>>> Sent: Tuesday, August 6, 2019 1:49 PM
>>>>> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
>>>>> Jacob Kollanukkaran <jerinj@marvell.com>
>>>>> Cc: dev@dpdk.org
>>>>> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
>>>>>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
>>>>>>
>>>>>> Currently, most of the NICs already support PTYPE parsing and
>>>>>> update
>>>>> the
>>>>>> mbuf->packet_type through an internal lookup table, but there is
>>>>>> mbuf->no
>>>>> way to
>>>>>> disable the lookup if the application is not intrested in ptypes
>>>>> returned by
>>>>>> `rte_eth_dev_get_supported_ptypes`.
>>>>>>
>>>>> [Hemant]  it will also mean introducing another check in datapath,
>>>>> if the application has asked for PTYPE offload - copy the results
>>>>> to mbuf-
>>>>>> packet_type otherwise don't do it.
>>>> I think that having the check would give better performance than
>>>> loading ptype table to L1 doing  a lookup and copying it to mbuf when the
>> application doesn't need it.
>>> Anyway, if PMD decides that it is better to always provide packet type
>>> information - there is no harm. Basically if the offload is not
>>> requested it makes packet_type undefined in mbuf.
>>>
>>>>> Your second patch is incomplete in the sense that it only adds the
>>>>> capability. But it does not disable the lookups?
>>>> It is upto the maintainer of the PMD to disable the lookup in data
>>>> path. If there is a scope of optimization then they could do it. There is no
>> harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
>>>> I was hesitant to touch data path as it would be impossible to verify
>> performance effect on all NICs.
>>> I think it is the right way to approach it especially taking
>>> transition into account.
>>>
>> With hardline API policy, this has to fail on compile for old applications.

Stephen, could you explain a bit more why.

> Not specific to this API change. That's is the propriety any new symbol addition
> to the code base.
>
> Planning to make this API change available fromv19.11 LTS.

The only way to to require applications to enable PTYPE offload to get
ptypes in mbuf since 19.11 LTS is to have deprecation notice in 19.08.

>> You can't magically assume that applications using ptype will set new feature.
> When OFFLOAD flags got introduced, we decided to disable all offloads by default.
> So, need to add positive logic here to enable offload instead of enable something by
> Default and disable if required to get have synergy with other offloads.
>
> Will update the release note as usual to document the change.
> Since there is NO ABI change, IMO, we don't need deprecation notice.

Sorry, but it is a behaviour change. Before an application does not need
to enable ptype offload, but now it is required. It means that application
will be broken and, therefore, it requires deprecation notice.

Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload

[Jerin Jacob Kollanukkaran]

> -----Original Message-----
> From: Stephen Hemminger <stephen@networkplumber.org>
> Sent: Wednesday, August 7, 2019 4:45 AM
> To: Andrew Rybchenko <arybchenko@solarflare.com>
> Cc: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Hemant
> Agrawal <hemant.agrawal@nxp.com>; Jerin Jacob Kollanukkaran
> <jerinj@marvell.com>; dev@dpdk.org
> Subject: [EXT] Re: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
> 
> On Tue, 6 Aug 2019 12:06:35 +0300
> Andrew Rybchenko <arybchenko@solarflare.com> wrote:
> 
> > On 8/6/19 11:47 AM, Pavan Nikhilesh Bhagavatula wrote:
> > >
> > >> -----Original Message-----
> > >> From: Hemant Agrawal <hemant.agrawal@nxp.com>
> > >> Sent: Tuesday, August 6, 2019 1:49 PM
> > >> To: Pavan Nikhilesh Bhagavatula <pbhagavatula@marvell.com>; Jerin
> > >> Jacob Kollanukkaran <jerinj@marvell.com>
> > >> Cc: dev@dpdk.org
> > >> Subject: RE: [dpdk-dev] [RFC 0/3] ethdev: add ptype as Rx offload
> > >>> Add PTYPE to DEV_RX_OFFLOAD_* flags.
> > >>>
> > >>> Currently, most of the NICs already support PTYPE parsing and
> > >>> update
> > >> the
> > >>> mbuf->packet_type through an internal lookup table, but there is
> > >>> mbuf->no
> > >> way to
> > >>> disable the lookup if the application is not intrested in ptypes
> > >> returned by
> > >>> `rte_eth_dev_get_supported_ptypes`.
> > >>>
> > >> [Hemant]  it will also mean introducing another check in datapath,
> > >> if the application has asked for PTYPE offload - copy the results
> > >> to mbuf-
> > >>> packet_type otherwise don't do it.
> > > I think that having the check would give better performance than
> > > loading ptype table to L1 doing  a lookup and copying it to mbuf when the
> application doesn't need it.
> >
> > Anyway, if PMD decides that it is better to always provide packet type
> > information - there is no harm. Basically if the offload is not
> > requested it makes packet_type undefined in mbuf.
> >
> > >> Your second patch is incomplete in the sense that it only adds the
> > >> capability. But it does not disable the lookups?
> > > It is upto the maintainer of the PMD to disable the lookup in data
> > > path. If there is a scope of optimization then they could do it. There is no
> harm in exposing  PTYPE even RX_OFFLOAD_PTYPE is not enabled.
> > > I was hesitant to touch data path as it would be impossible to verify
> performance effect on all NICs.
> >
> > I think it is the right way to approach it especially taking
> > transition into account.
> >
> 
> With hardline API policy, this has to fail on compile for old applications.

Not specific to this API change. That's is the propriety any new symbol addition
to the code base.

Planning to make this API change available from v19.11 LTS.

> You can't magically assume that applications using ptype will set new feature.

When OFFLOAD flags got introduced, we decided to disable all offloads by default.
So, need to add positive logic here to enable offload instead of enable something by
Default and disable if required to get have synergy with other offloads.

Will update the release note as usual to document the change. 
Since there is NO ABI change, IMO, we don't need deprecation notice.