Skip to contentSkip to conversation

fix rx packets dropped issue

PATCH Superseded Steve Yang 12 participants 115 messages Dec 9, 2020 – Jan 25, 2021 1 message not in the archive Network drivers

lore
Share & tools
lore

Steve Yang

author
#0 lore raw

cover fix rx packets dropped issue

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU'.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Steve Yang (12):
net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set

 drivers/net/dpaa2/dpaa2_ethdev.c        |  2 +-
 drivers/net/e1000/em_ethdev.c           |  2 +-
 drivers/net/e1000/igb_ethdev.c          |  2 +-
 drivers/net/hns3/hns3_ethdev.c          |  2 +-
 drivers/net/hns3/hns3_ethdev_vf.c       |  2 +-
 drivers/net/i40e/i40e_ethdev.c          |  2 +-
 drivers/net/i40e/i40e_ethdev.h          |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c       | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c            |  2 +-
 drivers/net/i40e/i40e_rxtx.c            |  8 ++++----
 drivers/net/iavf/iavf.h                 |  1 +
 drivers/net/iavf/iavf_ethdev.c          | 10 +++++-----
 drivers/net/ice/ice_dcf_ethdev.c        |  8 ++++----
 drivers/net/ice/ice_ethdev.c            |  2 +-
 drivers/net/ice/ice_ethdev.h            |  1 +
 drivers/net/ice/ice_rxtx.c              | 10 +++++-----
 drivers/net/ipn3ke/ipn3ke_representor.c |  2 +-
 drivers/net/octeontx/octeontx_ethdev.c  |  2 +-
 drivers/net/octeontx2/otx2_ethdev_ops.c |  2 +-
 drivers/net/qede/qede_ethdev.c          |  2 +-
 drivers/net/sfc/sfc_ethdev.c            |  2 +-
 drivers/net/thunderx/nicvf_ethdev.c     |  2 +-
 22 files changed, 40 insertions(+), 37 deletions(-)
Signature · 1 line
2.17.1
author
#1 lore raw

PATCH 1/12 net/dpaa2: fix the jumbo frame flag condition for mtu set

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes e16408499412 ("net/dpaa2: configure jumbo frames")
---
 drivers/net/dpaa2/dpaa2_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/dpaa2/dpaa2_ethdev.c +1 -1
index ab6863300e..b92f4c1a7f 100644
@@ -1420,7 +1420,7 @@ dpaa2_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > DPAA2_MAX_RX_PKT_LEN)
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#2 lore raw

PATCH 2/12 net/e1000: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes ef990fb56e55 ("net/e1000: convert to new Rx offloads API")
---
 drivers/net/e1000/em_ethdev.c  | 2 +-
 drivers/net/e1000/igb_ethdev.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/e1000/em_ethdev.c +1 -1
index 8ee9422bf4..044858f567 100644
@@ -1816,7 +1816,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
drivers/net/e1000/igb_ethdev.c +1 -1
index 647aa8d995..d31964558d 100644
@@ -4369,7 +4369,7 @@ eth_igb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
Signature · 1 line
2.17.1
author
#3 lore raw

PATCH 3/12 net/hns3: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 1f5ca0b460cd ("net/hns3: support some device operations")
Fixes a5475d61fa34 ("net/hns3: support VF")
---
 drivers/net/hns3/hns3_ethdev.c    | 2 +-
 drivers/net/hns3/hns3_ethdev_vf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/hns3/hns3_ethdev.c +1 -1
index 2011378879..1a5cfd3e1f 100644
@@ -2458,7 +2458,7 @@ hns3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	rte_spinlock_lock(&hw->lock);
-	is_jumbo_frame = frame_size > RTE_ETHER_MAX_LEN ? true : false;
+	is_jumbo_frame = mtu > RTE_ETHER_MTU ? true : false;
 	frame_size = RTE_MAX(frame_size, HNS3_DEFAULT_FRAME_LEN);
 
 	/*
drivers/net/hns3/hns3_ethdev_vf.c +1 -1
index 0366b9d4dc..d47af417bf 100644
@@ -928,7 +928,7 @@ hns3vf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		rte_spinlock_unlock(&hw->lock);
 		return ret;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#4 lore raw

PATCH 4/12 net/i40e: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes c1715402df8f ("i40evf: fix jumbo frame support")
Fixes 43e5488c0ac6 ("net/i40e: support MTU configuration")
Fixes a778a1fa2e4e ("i40e: set up and initialize flow director")
Fixes c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
---
 drivers/net/i40e/i40e_ethdev.c    |  2 +-
 drivers/net/i40e/i40e_ethdev.h    |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c      |  2 +-
 drivers/net/i40e/i40e_rxtx.c      |  8 ++++----
 5 files changed, 12 insertions(+), 11 deletions(-)
drivers/net/i40e/i40e_ethdev.c +1 -1
index f54769c29d..0b5e4abb41 100644
@@ -11753,7 +11753,7 @@ i40e_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_ethdev.h +1 -0
index 696c5aaf7e..1f31a532a1 100644
@@ -281,6 +281,7 @@ struct rte_flow {
  */
 #define I40E_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + I40E_VLAN_TAG_SIZE * 2)
+#define I40E_ETH_MAX_LEN (RTE_ETHER_MTU + I40E_ETH_OVERHEAD)
 
 #define I40E_RXTX_BYTES_H_16_BIT(bytes) ((bytes) & ~I40E_48_BIT_MASK)
 #define I40E_RXTX_BYTES_L_48_BIT(bytes) ((bytes) & I40E_48_BIT_MASK)
drivers/net/i40e/i40e_ethdev_vf.c +5 -5
index c26b036b85..c2577d598c 100644
@@ -1889,22 +1889,22 @@ i40evf_rxq_init(struct rte_eth_dev *dev, struct i40e_rx_queue *rxq)
 	 * Check if the jumbo frame and maximum packet length are set correctly
 	 */
 	if (dev_data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
-				"frame is enabled", (uint32_t)RTE_ETHER_MAX_LEN,
+				"frame is enabled", (uint32_t)I40E_ETH_MAX_LEN,
 					(uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
 				"frame is disabled",
 				(uint32_t)RTE_ETHER_MIN_LEN,
-				(uint32_t)RTE_ETHER_MAX_LEN);
+				(uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
@@ -2825,7 +2825,7 @@ i40evf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_fdir.c +1 -1
index 50c0eee9f2..449b67b2a9 100644
@@ -116,7 +116,7 @@ i40e_fdir_rx_queue_init(struct i40e_rx_queue *rxq)
 #endif
 	rx_ctx.dtype = i40e_header_split_none;
 	rx_ctx.hsplit_0 = I40E_HEADER_SPLIT_NONE;
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = I40E_ETH_MAX_LEN;
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
 	rx_ctx.tphdata_ena = 1;
drivers/net/i40e/i40e_rxtx.c +4 -4
index 5df9a9df56..b8859bbff2 100644
@@ -2797,23 +2797,23 @@ i40e_rx_queue_config(struct i40e_rx_queue *rxq)
 		RTE_MIN((uint32_t)(hw->func_caps.rx_buf_chain_len *
 			rxq->rx_buf_len), data->dev_conf.rxmode.max_rx_pkt_len);
 	if (data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)I40E_ETH_MAX_LEN,
 				    (uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-			rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+			rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
Signature · 1 line
2.17.1
author
#5 lore raw

PATCH 5/12 net/iavf: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 3fd7a3719c66 ("net/avf: enable ops for MTU setting")
Fixes 69dd4c3d0898 ("net/avf: enable queue and device")
---
 drivers/net/iavf/iavf.h        |  1 +
 drivers/net/iavf/iavf_ethdev.c | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)
drivers/net/iavf/iavf.h +1 -0
index 6d5912d8c1..3328bd9327 100644
@@ -66,6 +66,7 @@
 #define IAVF_VLAN_TAG_SIZE               4
 #define IAVF_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IAVF_VLAN_TAG_SIZE * 2)
+#define IAVF_ETH_MAX_LEN (RTE_ETHER_MTU + IAVF_ETH_OVERHEAD)
 
 #define IAVF_32_BIT_WIDTH (CHAR_BIT * 4)
 #define IAVF_48_BIT_WIDTH (CHAR_BIT * 6)
drivers/net/iavf/iavf_ethdev.c +5 -5
index 7e3c26a94e..b24d801065 100644
@@ -418,23 +418,23 @@ iavf_init_rxq(struct rte_eth_dev *dev, struct iavf_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= IAVF_ETH_MAX_LEN ||
 		    max_pkt_len > IAVF_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)IAVF_ETH_MAX_LEN,
 				    (uint32_t)IAVF_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > IAVF_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)IAVF_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -1167,7 +1167,7 @@ iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#6 lore raw

PATCH 6/12 net/ice: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 84dc7a95a2d3 ("net/ice: enable flow director engine")
Fixes 1b009275e2c8 ("net/ice: add Rx queue init in DCF")
Fixes ae2bdd0219cb ("net/ice: support MTU setting")
Fixes 50370662b727 ("net/ice: support device and queue ops")
---
 drivers/net/ice/ice_dcf_ethdev.c |  8 ++++----
 drivers/net/ice/ice_ethdev.c     |  2 +-
 drivers/net/ice/ice_ethdev.h     |  1 +
 drivers/net/ice/ice_rxtx.c       | 10 +++++-----
 4 files changed, 11 insertions(+), 10 deletions(-)
drivers/net/ice/ice_dcf_ethdev.c +4 -4
index b0b2ecb0d6..e5c877805f 100644
@@ -60,23 +60,23 @@ ice_dcf_init_rxq(struct rte_eth_dev *dev, struct ice_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
drivers/net/ice/ice_ethdev.c +1 -1
index 9a5d6a559f..fc99f4bad0 100644
@@ -3904,7 +3904,7 @@ ice_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/ice/ice_ethdev.h +1 -0
index 899f446cde..2b03c59671 100644
@@ -135,6 +135,7 @@
  */
 #define ICE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + ICE_VLAN_TAG_SIZE * 2)
+#define ICE_ETH_MAX_LEN (RTE_ETHER_MTU + ICE_ETH_OVERHEAD)
 
 #define ICE_RXTX_BYTES_HIGH(bytes) ((bytes) & ~ICE_40_BIT_MASK)
 #define ICE_RXTX_BYTES_LOW(bytes) ((bytes) & ICE_40_BIT_MASK)
drivers/net/ice/ice_rxtx.c +5 -5
index 5fbd68eafc..0d9ad75782 100644
@@ -246,23 +246,23 @@ ice_program_hw_rx_queue(struct ice_rx_queue *rxq)
 				   dev->data->dev_conf.rxmode.max_rx_pkt_len);
 
 	if (rxmode->offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -701,7 +701,7 @@ ice_fdir_program_hw_rx_queue(struct ice_rx_queue *rxq)
 	rx_ctx.hbuf = rxq->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S;
 	rx_ctx.dtype = 0; /* No Header Split mode */
 	rx_ctx.dsize = 1; /* 32B descriptors */
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = ICE_ETH_MAX_LEN;
 	/* TPH: Transaction Layer Packet (TLP) processing hints */
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
Signature · 1 line
2.17.1
author
#7 lore raw

PATCH 7/12 net/ipn3ke: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 70d6b7f550f4 ("net/ipn3ke: add representor")
---
 drivers/net/ipn3ke/ipn3ke_representor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ipn3ke/ipn3ke_representor.c +1 -1
index 8a53602576..c8ca58cc4b 100644
@@ -2801,7 +2801,7 @@ ipn3ke_rpst_mtu_set(struct rte_eth_dev *ethdev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev_data->dev_conf.rxmode.offloads |=
 			(uint64_t)(DEV_RX_OFFLOAD_JUMBO_FRAME);
 	else
Signature · 1 line
2.17.1
author
#8 lore raw

PATCH 8/12 net/octeontx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 3151e6a687a3 ("net/octeontx: support MTU")
---
 drivers/net/octeontx/octeontx_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/octeontx/octeontx_ethdev.c +1 -1
index 3ee7b043fd..0b79360885 100644
@@ -552,7 +552,7 @@ octeontx_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		nic->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		nic->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#9 lore raw

PATCH 9/12 net/octeontx2: fix the jumbo frame flag condition for mtu

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")
---
 drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..170b8fbd91 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
Acked-by on v1 9/12
#10 lore raw

Re: [dpdk-dev] [EXT] [PATCH v1 09/12] net/octeontx2: fix the jumbo frame flag condition for mtu

Quoted 59 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Wednesday, December 9, 2020 8:46 AM
To: [email protected]
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Harman Kalra <[email protected]>; Jerin Jacob Kollanukkaran <[email protected]>; Nithin Kumar Dabilpuram <[email protected]>; Kiran Kumar Kokkilagadda <[email protected]>; Rasesh Mody <[email protected]>; Shahed Shaikh <[email protected]>; [email protected]; Maciej Czekaj [C] <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Sunil Kumar Kori <[email protected]>; Vamsi Krishna Attunuru <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Steve Yang <[email protected]>
Subject: [EXT] [PATCH v1 09/12] net/octeontx2: fix the jumbo frame flag condition for mtu

External Email

----------------------------------------------------------------------
The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")

---
drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-

1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..170b8fbd91 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t
 mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Quoted 2 lines

--
2.17.1

author
#11 lore raw

PATCH 10/12 net/qede: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 200645ac7909 ("net/qede: set MTU")
---
 drivers/net/qede/qede_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/qede/qede_ethdev.c +1 -1
index 549013557c..d6f0f0a493 100644
@@ -2367,7 +2367,7 @@ static int qede_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 			fp->rxq->rx_buf_size = rc;
 		}
 	}
-	if (max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#12 lore raw

PATCH 11/12 net/sfc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes ff6a1197c3b1 ("net/sfc: convert to new Rx offload API")
---
 drivers/net/sfc/sfc_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/sfc/sfc_ethdev.c +1 -1
index 93fc7baa0d..f2f5336435 100644
@@ -1017,7 +1017,7 @@ sfc_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 	 * The driver does not use it, but other PMDs update jumbo frame
 	 * flag and max_rx_pkt_len when MTU is set.
 	 */
-	if (mtu > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	}
Signature · 1 line
2.17.1
author
#13 lore raw

PATCH 12/12 net/thunderx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes 65d9804edc05 ("net/thunderx: support MTU configuration")
---
 drivers/net/thunderx/nicvf_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/thunderx/nicvf_ethdev.c +1 -1
index b6bb05e500..a13ee960ec 100644
@@ -176,7 +176,7 @@ nicvf_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 		(frame_size + 2 * VLAN_TAG_SIZE > buffsz * NIC_HW_MAX_SEGS))
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		rxmode->offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
#14 lore raw
In reply to Steve Yang

Hi, steve

What I saw is that you replace of frame size checking to mtu checking, but you still use "18" as overhead number to configure max_rx_pkt_len?

uint32_t frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;

dev->data->dev_conf.rxmode.max_rx_pkt_len = frame_size;

Quoted 80 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Wednesday, December 9, 2020 11:16 AM
To: [email protected]
Cc: [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Xing, Beilei <[email protected]>; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Zhang, Helin <[email protected]>; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Lu, Wenzhuo <[email protected]>; Pei, Andy <[email protected]>; Wei, Dan <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Yang, SteveX <[email protected]>
Subject: [PATCH v1 00/12] fix rx packets dropped issue

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU'.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Steve Yang (12):
net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set

 drivers/net/dpaa2/dpaa2_ethdev.c        |  2 +-
 drivers/net/e1000/em_ethdev.c           |  2 +-
 drivers/net/e1000/igb_ethdev.c          |  2 +-
 drivers/net/hns3/hns3_ethdev.c          |  2 +-
 drivers/net/hns3/hns3_ethdev_vf.c       |  2 +-
 drivers/net/i40e/i40e_ethdev.c          |  2 +-
 drivers/net/i40e/i40e_ethdev.h          |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c       | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c            |  2 +-
 drivers/net/i40e/i40e_rxtx.c            |  8 ++++----
 drivers/net/iavf/iavf.h                 |  1 +
 drivers/net/iavf/iavf_ethdev.c          | 10 +++++-----
 drivers/net/ice/ice_dcf_ethdev.c        |  8 ++++----
 drivers/net/ice/ice_ethdev.c            |  2 +-
 drivers/net/ice/ice_ethdev.h            |  1 +
 drivers/net/ice/ice_rxtx.c              | 10 +++++-----
 drivers/net/ipn3ke/ipn3ke_representor.c |  2 +-
drivers/net/octeontx/octeontx_ethdev.c  |  2 +-
drivers/net/octeontx2/otx2_ethdev_ops.c |  2 +-
 drivers/net/qede/qede_ethdev.c          |  2 +-
 drivers/net/sfc/sfc_ethdev.c            |  2 +-
 drivers/net/thunderx/nicvf_ethdev.c     |  2 +-
 22 files changed, 40 insertions(+), 37 deletions(-)

--
2.17.1

#15 lore raw
In reply to Steve Yang
Quoted 13 lines · Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU'.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Quoted 14 lines

Steve Yang (12):
net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set

Overall looks good to me, there is no review from the individual drivers, but if there is no objection I am for merging it soon. A few things below:

1) I see following usage not updated, can you please include them in next version:
ixgbe_set_vf_lpe
ixgbe_dev_mtu_set
cxgbe_dev_mtu_set
cxgbe_dev_rx_queue_setup
axgb_mtu_set
enetc_mtu_set
hinic_dev_set_mtu
dpaa_mtu_set
nfp_net_dev_mtu_set
lio_dev_mtu_set

2) I guess 'eth_dev' update will come as separate patch, can you please send it without waiting this set to be merged, since both are related having them both can help discussions.

Thanks,
ferruh

author
#16 lore raw

v2 cover fix rx packets dropped issue

In reply to Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

---
v2:
- defined the 'RTE_ETHER_MTU + overhead' to 'driver_ETH_MAX_LEN';
- changed the 'mtu > RTE_ETHER_MTU' to 'frame_size > driver_ETH_MAX_LEN';
---

Steve Yang (22):
ethdev: fix MTU size exceeds max rx packet length app/testpmd: fix max rx packet length for VLAN packets net/dpaa: fix the jumbo frame flag condition for mtu set net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set net/ixgbe: fix the jumbo frame flag condition net/cxgbe: fix the jumbo frame flag condition net/axgbe: fix the jumbo frame flag condition for mtu set net/enetc: fix the jumbo frame flag condition for mtu set net/hinic: fix the jumbo frame flag condition for mtu set net/nfp: fix the jumbo frame flag condition for mtu set net/liquidio: fix the jumbo frame flag condition for mtu set

 app/test-pmd/cmdline.c                    |  6 ------
 app/test-pmd/config.c                     |  2 +-
 app/test-pmd/parameters.c                 |  7 ++-----
 app/test-pmd/testpmd.c                    | 20 ++++++++++++++++++++
 drivers/net/axgbe/axgbe_ethdev.c          |  2 +-
 drivers/net/axgbe/axgbe_ethdev.h          |  6 ++++++
 drivers/net/cxgbe/cxgbe.h                 |  4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c          |  4 ++--
 drivers/net/dpaa/dpaa_ethdev.c            |  2 +-
 drivers/net/dpaa/dpaa_ethdev.h            |  4 ++++
 drivers/net/dpaa2/dpaa2_ethdev.c          |  2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h          |  4 ++++
 drivers/net/e1000/e1000_ethdev.h          |  2 +-
 drivers/net/e1000/em_ethdev.c             |  5 ++---
 drivers/net/e1000/igb_ethdev.c            |  2 +-
 drivers/net/enetc/enetc.h                 |  4 ++++
 drivers/net/enetc/enetc_ethdev.c          |  2 +-
 drivers/net/hinic/hinic_pmd_ethdev.c      |  5 ++++-
 drivers/net/hns3/hns3_ethdev.c            |  2 +-
 drivers/net/hns3/hns3_ethdev_vf.c         |  2 +-
 drivers/net/i40e/i40e_ethdev.c            |  2 +-
 drivers/net/i40e/i40e_ethdev.h            |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c         | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c              |  2 +-
 drivers/net/i40e/i40e_rxtx.c              |  8 ++++----
 drivers/net/iavf/iavf.h                   |  1 +
 drivers/net/iavf/iavf_ethdev.c            | 10 +++++-----
 drivers/net/ice/ice_dcf_ethdev.c          |  8 ++++----
 drivers/net/ice/ice_ethdev.c              |  2 +-
 drivers/net/ice/ice_ethdev.h              |  1 +
 drivers/net/ice/ice_rxtx.c                | 10 +++++-----
 drivers/net/ipn3ke/ipn3ke_ethdev.h        |  1 +
 drivers/net/ipn3ke/ipn3ke_representor.c   |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.c          |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h          |  3 +++
 drivers/net/ixgbe/ixgbe_pf.c              |  2 +-
 drivers/net/liquidio/lio_ethdev.c         |  2 +-
 drivers/net/liquidio/lio_ethdev.h         |  3 +++
 drivers/net/nfp/nfp_net.c                 |  2 +-
 drivers/net/octeontx/octeontx_ethdev.c    |  2 +-
 drivers/net/octeontx/octeontx_ethdev.h    |  1 +
 drivers/net/octeontx2/otx2_ethdev.h       |  2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c   |  2 +-
 drivers/net/qede/qede_ethdev.c            |  2 +-
 drivers/net/qede/qede_rxtx.h              |  1 +
 drivers/net/sfc/sfc_ethdev.c              |  2 +-
 drivers/net/thunderx/base/nicvf_hw_defs.h |  1 +
 drivers/net/thunderx/nicvf_ethdev.c       |  2 +-
 lib/librte_ethdev/rte_ethdev.c            | 21 ++++++++++++++++++---
 49 files changed, 130 insertions(+), 65 deletions(-)
Signature · 1 line
2.17.1
author
#17 lore raw

PATCH v2 1/22 ethdev: fix MTU size exceeds max rx packet length

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
 lib/librte_ethdev/rte_ethdev.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +18 -3
index 17ddacc78d..ff6a1e675f 100644
@@ -1292,6 +1292,7 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	struct rte_eth_dev *dev;
 	struct rte_eth_dev_info dev_info;
 	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
 	int diag;
 	int ret;
 
@@ -1323,6 +1324,15 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	if (ret != 0)
 		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu &&
+	    dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen &&
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
 	/* If number of queues specified by application for both Rx and Tx is
 	 * zero, use driver preferred values. This cannot be done individually
 	 * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,13 +1420,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 			goto rollback;
 		}
 	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+			pktlen > RTE_ETHER_MTU + overhead_len)
 			/* Use default value */
 			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
 	}
 
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
+
 	/*
 	 * If LRO is enabled, check that the maximum aggregated packet
 	 * size is supported by the configured device.
Signature · 1 line
2.17.1
#18 lore raw

Re: [dpdk-dev] [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 25 lines · Steve Yang

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
 lib/librte_ethdev/rte_ethdev.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +1 -0
index 17ddacc78d..ff6a1e675f 100644
@@ -1292,6 +1292,7 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	struct rte_eth_dev *dev;
 	struct rte_eth_dev_info dev_info;
 	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
 	int diag;
 	int ret;
 

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1328

Quoted 5 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
@@ -1323,6 +1324,15 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	if (ret != 0)
 		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu &&

First of all I'm not sure that we need to handle 0 value separately. Or it should be checked separately and trigger an error since it is a driver mis-behaviour.

If kept, it should be compared vs 0 explicitly in accordance with DPDK coding style.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1330

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
+	    dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen &&

It should be compared vs 0 explicitly in accordance with DPDK coding style.

Quoted 9 lines
lib/librte_ethdev/rte_ethdev.c +5 -0
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
 	/* If number of queues specified by application for both Rx and Tx is
 	 * zero, use driver preferred values. This cannot be done individually
 	 * as it is valid for either Tx or Rx (but not both) to be zero.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1425

Quoted 8 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
@@ -1410,13 +1420,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 			goto rollback;
 		}
 	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+			pktlen > RTE_ETHER_MTU + overhead_len)

Alignment looks misleading. Either two tabs or just 4 spaces.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1434

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +5 -1
 			/* Use default value */
 			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
 	}
 
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
+

Is it expected side effect that re-configure always resets previously set MTU. I.e.:
configure -> set_mtu -> start -> stop -> re-configure
and set MTU is lost.

Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
 	/*
 	 * If LRO is enabled, check that the maximum aggregated packet
 	 * size is supported by the configured device.
#19 lore raw

Re: [dpdk-dev] [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 29 lines · Andrew Rybchenko
Quoted 28 lines · Steve Yang

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
  lib/librte_ethdev/rte_ethdev.c | 21 ++++++++++++++++++---
  1 file changed, 18 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +1 -0
index 17ddacc78d..ff6a1e675f 100644
@@ -1292,6 +1292,7 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	struct rte_eth_dev *dev;
  	struct rte_eth_dev_info dev_info;
  	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
  	int diag;
  	int ret;
 
@@ -1323,6 +1324,15 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	if (ret != 0)
  		goto rollback;
 
Quoted 7 lines

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1328

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu &&

First of all I'm not sure that we need to handle 0 value separately. Or it should be checked separately and trigger an error since it is a driver mis-behaviour.

Agree. Most probably we can drop it, "dev_info.max_mtu != UINT16_MAX" covers the case driver doesn't provide any value.

Quoted 42 lines

If kept, it should be compared vs 0 explicitly in accordance with DPDK coding style.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1330

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
+	    dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen &&

It should be compared vs 0 explicitly in accordance with DPDK coding style.

Quoted 9 lines
lib/librte_ethdev/rte_ethdev.c +5 -0
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
  	/* If number of queues specified by application for both Rx and Tx is
  	 * zero, use driver preferred values. This cannot be done individually
  	 * as it is valid for either Tx or Rx (but not both) to be zero.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1425

Quoted 8 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
@@ -1410,13 +1420,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  			goto rollback;
  		}
  	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+			pktlen > RTE_ETHER_MTU + overhead_len)

Alignment looks misleading. Either two tabs or just 4 spaces.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1434

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +5 -1
  			/* Use default value */
  			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
  	}
 
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
+

Is it expected side effect that re-configure always resets previously set MTU. I.e.:

Quoted 3 lines
    configure -> set_mtu -> start -> stop -> re-configure

and set MTU is lost.

This is the problem of two APIs updating same/related values, when device re-configure with a given 'max_rx_pkt_len', can we know if the intentions is update to the value to new provided 'max_rx_pkt_len' or not?

For this case if user want to keep the MTU value, can read the MTU from device first and set 'max_rx_pkt_len' according it.

And we can reduce to updating the MTU in the configure() only when JUMBO frame offload is requested, that should be when the 'max_rx_pkt_len' is valid only.

Quoted 5 lines
Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
  	/*
  	 * If LRO is enabled, check that the maximum aggregated packet
  	 * size is supported by the configured device.
#20 lore raw

Re: [dpdk-dev] [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

In reply to Steve Yang
Quoted 49 lines · Steve Yang

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
  lib/librte_ethdev/rte_ethdev.c | 21 ++++++++++++++++++---
  1 file changed, 18 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +13 -2
index 17ddacc78d..ff6a1e675f 100644
@@ -1292,6 +1292,7 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	struct rte_eth_dev *dev;
  	struct rte_eth_dev_info dev_info;
  	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
  	int diag;
  	int ret;
 
@@ -1323,6 +1324,15 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	if (ret != 0)
  		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu &&
+	    dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen &&
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
  	/* If number of queues specified by application for both Rx and Tx is
  	 * zero, use driver preferred values. This cannot be done individually
  	 * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,13 +1420,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  			goto rollback;
  		}
  	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+			pktlen > RTE_ETHER_MTU + overhead_len)

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1434

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +5 -1
  			/* Use default value */
  			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
  	}
 
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
+

Hi
I think the dev->data->mtu should be updated after configured
success. So the update in this position seems unreasonable. 'max_rx_pkt_len' is only used when jumbo_frame enabled, as follows:

struct rte_eth_rxmode {
	.....
	uint32_t max_rx_pkt_len;  /**< Only used if JUMBO_FRAME enabled. */
	/** Maximum allowed size of LRO aggregated packet. */
	....};

So If DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offload, driver should configure mtu to hardware according to 'max_rx_pkt_len' and update dev->data->mtu. This seems more reasonable. And some PMD drivers are already doing this.

In addition, validity check for 'max_rx_pkt_len' in rte_eth_dev_configure API may be error. It should be greater than 'RTE_ETHER_MTU + overhead_len'. Because driver must enable DEV_RX_OFFLOAD_JUMBO_FRAME when user set mtu with greater than 1500 by 'rte_eth_dev_set_mtu' API.

What do you think?

Thanks
Lijun Ou

Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
  	/*
  	 * If LRO is enabled, check that the maximum aggregated packet
  	 * size is supported by the configured device.

A message that is not in the archive (sent off-list or not yet received): DM6PR11MB43627F10DDAFC9801816FF5BF9D00@DM6PR11MB4362.namprd11.prod.outlook.com

#22 lore raw

Re: [dpdk-dev] [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 132 lines · SteveX

Hi Lijun,

Thanks for your review. Please check my comments inline. Regards,
Steve Yang.

Quoted 107 lines

-----Original Message-----
From: oulijun <[email protected]>
Sent: Wednesday, December 30, 2020 6:20 PM
To: Yang, SteveX <[email protected]>; [email protected]
Cc: Lu, Wenzhuo <[email protected]>; Xing, Beilei <[email protected]>; Iremonger, Bernard <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Zhang, Helin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Wei, Dan <[email protected]>; Pei, Andy <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Zhao1, Wei <[email protected]>; Jiang, JunyuX <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]
Subject: Re: [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id,

Quoted 17 lines · Steve Yang

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
   lib/librte_ethdev/rte_ethdev.c | 21 ++++++++++++++++++---
   1 file changed, 18 insertions(+), 3 deletions(-)
(quoted diff) +0 -0

b/lib/librte_ethdev/rte_ethdev.c index 17ddacc78d..ff6a1e675f 100644

lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1292,6 +1292,7 @@ rte_eth_dev_configure(uint16_t port_id,

uint16_t nb_rx_q, uint16_t nb_tx_q,

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id,

Quoted 8 lines
lib/librte_ethdev/rte_ethdev.c +1 -0
   struct rte_eth_dev *dev;
   struct rte_eth_dev_info dev_info;
   struct rte_eth_conf orig_conf;
+uint16_t overhead_len;
   int diag;
   int ret;
 
@@ -1323,6 +1324,15 @@ rte_eth_dev_configure(uint16_t port_id,

uint16_t nb_rx_q, uint16_t nb_tx_q,

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,

Quoted 9 lines
lib/librte_ethdev/rte_ethdev.c +6 -0
   if (ret != 0)
   goto rollback;
 
+/* Get the real Ethernet overhead length */
+if (dev_info.max_mtu &&
+    dev_info.max_mtu != UINT16_MAX &&
+    dev_info.max_rx_pktlen &&
+    dev_info.max_rx_pktlen > dev_info.max_mtu)
+overhead_len = dev_info.max_rx_pktlen -

dev_info.max_mtu;

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1334

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
+else
+overhead_len = RTE_ETHER_HDR_LEN +

RTE_ETHER_CRC_LEN;

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id,

Quoted 5 lines
lib/librte_ethdev/rte_ethdev.c +1 -0
+
   /* If number of queues specified by application for both Rx and Tx is
    * zero, use driver preferred values. This cannot be done individually
    * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,13 +1420,18 @@ rte_eth_dev_configure(uint16_t port_id,

uint16_t nb_rx_q, uint16_t nb_tx_q,

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,

Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +0 -1
   goto rollback;
   }
   } else {
-if (dev_conf->rxmode.max_rx_pkt_len <

RTE_ETHER_MIN_LEN ||

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1414

Quoted 1 line
lib/librte_ethdev/rte_ethdev.c +0 -1
-dev_conf->rxmode.max_rx_pkt_len >

RTE_ETHER_MAX_LEN)

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,

Quoted 6 lines
lib/librte_ethdev/rte_ethdev.c +3 -1
+uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+pktlen > RTE_ETHER_MTU + overhead_len)
   /* Use default value */
   dev->data->dev_conf.rxmode.max_rx_pkt_len =
-

RTE_ETHER_MAX_LEN;

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1428

Quoted 1 line
lib/librte_ethdev/rte_ethdev.c +1 -0
+RTE_ETHER_MTU +

overhead_len;

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
   }
 
Quoted 7 lines

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1434

Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +4 -0
+/* Scale the MTU size to adapt max_rx_pkt_len */
+dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+overhead_len;
+

Hi

    I think the dev->data->mtu should be updated after configured success. So

the update in this position seems unreasonable.

Good suggestion, I've checked some PMDs, and the corresponding assignments are existed within their 'dev_configure_ops'. For example: [bnxt_ethdev.c # 1100]

```
if (rx_offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
eth_dev->data->mtu =
eth_dev->data->dev_conf.rxmode.max_rx_pkt_len -
RTE_ETHER_HDR_LEN - RTE_ETHER_CRC_LEN - VLAN_TAG_SIZE *
BNXT_NUM_VLANS;
bnxt_mtu_set_op(eth_dev, eth_dev->data->mtu);
}
```
Quoted 1 line

Hence, I will move this 'mtu' assignment to line after '(*dev->dev_ops->dev_configure)(dev)'.

There is a 'rollback' already for the similar reason.

What do you think to store the old MTU and restore it in the rollback if needed? So you don't need to change where MTU set.

Quoted 3 lines

Actually, it doesn't matter if it is the JUMBO frame, the 'mtu' must keep pace with 'max_rx_pkt_len' anytime.
E.g.: if 'mtu' is 1500, and 'max_rx_pkt_len' is set to 1510 by command line, that 'mtu' must be reduced to '1510 - 18 = 1492' in 'dev_configure' phase, even though it is not a Jumbo frame.

According to the API definition:
max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */

The concern was removing this check from the ethdev may break some PMDs that does not follow the API and use the 'max_rx_pkt_len' even if JUMBO frame offload set.

For this release, we can afford to break the PMDs implementing wrong and fix them after testing.

Quoted 22 lines
Quoted 14 lines

'max_rx_pkt_len' is only used when jumbo_frame enabled, as follows:
struct rte_eth_rxmode {
.....
uint32_t max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */
/** Maximum allowed size of LRO aggregated packet. */ ....};

So If DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offload, driver should configure mtu to hardware according to 'max_rx_pkt_len' and update dev->data->mtu. This seems more reasonable. And some PMD drivers are already doing this.

Quoted 7 lines

In addition, validity check for 'max_rx_pkt_len' in rte_eth_dev_configure API may be error. It should be greater than 'RTE_ETHER_MTU + overhead_len'.
Because driver must enable DEV_RX_OFFLOAD_JUMBO_FRAME when user set mtu
with greater than 1500 by 'rte_eth_dev_set_mtu' API.

Quoted 9 lines

I'm not sure if it is following validity check you mentioned.

Quoted 2 lines

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1425

Quoted 2 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
+if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+pktlen > RTE_ETHER_MTU + overhead_len)

If yes, no issue here, because the 'rte_eth_dev_configure' is only used for initializing device, and just gives out an initial 'max_rx_pkt_len' value by default. Once user tries to change mtu via 'set mtu', the 'max_rx_pkt_len' will be updated to expected value in the 'mtu_set' ops.
Another aspect, that is the 'disable DEV_RX_OFFLOAD_JUMBO' branch, 'max_rx_pkt_len' must be limited to effective max value for non-Jumbo frame.

In the 'disable DEV_RX_OFFLOAD_JUMBO' branch, 'max_rx_pkt_len' should be invalid according API doc as mentioned above, I guess Lijun refers to this.

Overall what about updating as following, in 'rte_eth_dev_configure()':

if (offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
// max_rx_pkt_len checks
old_mtu = mtu
mtu = max_rx_pkt_len - overhead_len
}

...

rollback:
mtu = old_mtu;

Quoted 9 lines
Quoted 9 lines

What do you think?

Thanks
Lijun Ou

Quoted 4 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
   /*
    * If LRO is enabled, check that the maximum aggregated packet
    * size is supported by the configured device.
#23 lore raw

Re: [dpdk-dev] [PATCH v2 01/22] ethdev: fix MTU size exceeds max rx packet length

In reply to a message not in the archive

On 1/6/2021 3:36 AM, Yang, SteveX wrote:

<...>

Quoted 5 lines
Quoted 5 lines
Quoted 5 lines

If max rx packet length is smaller then MTU + Ether overhead, that will drop all MTU size packets.

Update the MTU size according to the max rx packet and Ether overhead.

Can you please elaborate the explanation a little more, it is hard to understand the problem with above description.

Problem is:
"
Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one. "

Addition to above, the code reviews suggest slight difference, like dropping the ethdev check completely for non-jumbo packets, please reflect them to the commit log if changes are implemented.

Quoted 4 lines
Quoted 4 lines
Quoted 4 lines
Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

---

author
#24 lore raw

PATCH v2 2/22 app/testpmd: fix max rx packet length for VLAN packets

In reply to Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
---
 app/test-pmd/cmdline.c    |  6 ------
 app/test-pmd/config.c     |  2 +-
 app/test-pmd/parameters.c |  7 ++-----
 app/test-pmd/testpmd.c    | 20 ++++++++++++++++++++
 4 files changed, 23 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
 	RTE_ETH_FOREACH_DEV(pid) {
 		struct rte_port *port = &ports[pid];
-		uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
 		if (!strcmp(res->name, "max-pkt-len")) {
 			if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 				return;
 
 			port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-			if (res->value > RTE_ETHER_MAX_LEN)
-				rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-			else
-				rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-			port->dev_conf.rxmode.offloads = rx_offloads;
 		} else {
 			printf("Unknown parameter\n");
 			return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
 		 * device supports jumbo frame.
 		 */
 		eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-		if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+		if (mtu > RTE_ETHER_MTU) {
 			rte_port->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 			rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
 			}
 			if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
 				n = atoi(optarg);
-				if (n >= RTE_ETHER_MIN_LEN) {
+				if (n >= RTE_ETHER_MIN_LEN)
 					rx_mode.max_rx_pkt_len = (uint32_t) n;
-					if (n > RTE_ETHER_MAX_LEN)
-						rx_offloads |=
-							DEV_RX_OFFLOAD_JUMBO_FRAME;
-				} else
+				else
 					rte_exit(EXIT_FAILURE,
 						 "Invalid max-pkt-len=%d - should be > %d\n",
 						 n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +20 -0
index 33a060dffd..fdb5c3c38b 100644
@@ -1410,6 +1410,7 @@ init_config(void)
 	struct rte_gro_param gro_param;
 	uint32_t gso_types;
 	uint16_t data_size;
+	uint16_t eth_overhead;
 	bool warning = 0;
 	int k;
 	int ret;
@@ -1446,6 +1447,25 @@ init_config(void)
 			rte_exit(EXIT_FAILURE,
 				 "rte_eth_dev_info_get() failed\n");
 
+		/* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+		if (port->dev_info.max_mtu &&
+		    port->dev_info.max_mtu != UINT16_MAX &&
+		    port->dev_info.max_rx_pktlen &&
+		    port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+			eth_overhead = port->dev_info.max_rx_pktlen -
+				port->dev_info.max_mtu;
+		else
+			eth_overhead =
+				RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+		if (port->dev_conf.rxmode.max_rx_pkt_len <=
+			(uint32_t)(RTE_ETHER_MTU + eth_overhead))
+			port->dev_conf.rxmode.max_rx_pkt_len =
+					RTE_ETHER_MTU + eth_overhead;
+		else
+			port->dev_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_JUMBO_FRAME;
+
 		if (!(port->dev_info.tx_offload_capa &
 		      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
 			port->dev_conf.txmode.offloads &=
Signature · 1 line
2.17.1
#25 lore raw

Re: [dpdk-dev] [PATCH v2 02/22] app/testpmd: fix max rx packet length for VLAN packets

Quoted 14 lines · Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")

<...>

app/test-pmd/testpmd.c init_config(void) · line 1451

Quoted 6 lines
app/test-pmd/testpmd.c +2 -0
@@ -1446,6 +1447,25 @@ init_config(void)
  			rte_exit(EXIT_FAILURE,
  				 "rte_eth_dev_info_get() failed\n");
 
+		/* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+		if (port->dev_info.max_mtu &&

Similar to the ethdev comment, above check can be dropped.

Quoted 21 lines
app/test-pmd/testpmd.c +17 -0
+		    port->dev_info.max_mtu != UINT16_MAX &&
+		    port->dev_info.max_rx_pktlen &&
+		    port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+			eth_overhead = port->dev_info.max_rx_pktlen -
+				port->dev_info.max_mtu;
+		else
+			eth_overhead =
+				RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+		if (port->dev_conf.rxmode.max_rx_pkt_len <=
+			(uint32_t)(RTE_ETHER_MTU + eth_overhead))
+			port->dev_conf.rxmode.max_rx_pkt_len =
+					RTE_ETHER_MTU + eth_overhead;
+		else
+			port->dev_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_JUMBO_FRAME;
+
  		if (!(port->dev_info.tx_offload_capa &
  		      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
  			port->dev_conf.txmode.offloads &=
author
#26 lore raw

PATCH v2 3/22 net/dpaa: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 25f854197abc ("net/dpaa: support jumbo frames")
---
 drivers/net/dpaa/dpaa_ethdev.c | 2 +-
 drivers/net/dpaa/dpaa_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa/dpaa_ethdev.c +1 -1
index f00279e004..0c87c136d7 100644
@@ -184,7 +184,7 @@ dpaa_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa/dpaa_ethdev.h +4 -0
index 659bceb467..a858b1372c 100644
@@ -51,6 +51,10 @@
 #define VLAN_TAG_SIZE   4 /** < Vlan Header Length */
 #endif
 
+#define DPAA_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			  RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			  VLAN_TAG_SIZE)
+
 /* PCD frame queues */
 #define DPAA_DEFAULT_NUM_PCD_QUEUES	1
 #define DPAA_VSP_PROFILE_MAX_NUM	8
Signature · 1 line
2.17.1
author
#27 lore raw

PATCH v2 4/22 net/dpaa2: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes e16408499412 ("net/dpaa2: configure jumbo frames")
---
 drivers/net/dpaa2/dpaa2_ethdev.c | 2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa2/dpaa2_ethdev.c +1 -1
index ab6863300e..6f38da3cce 100644
@@ -1420,7 +1420,7 @@ dpaa2_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > DPAA2_MAX_RX_PKT_LEN)
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA2_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa2/dpaa2_ethdev.h +4 -0
index 8d82f74684..cacb11bd3e 100644
@@ -26,6 +26,10 @@
 
 #define DPAA2_RX_DEFAULT_NBDESC 512
 
+#define DPAA2_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			   RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			   VLAN_TAG_SIZE)
+
 /*default tc to be used for ,congestion, distribution etc configuration. */
 #define DPAA2_DEF_TC		0
 
Signature · 1 line
2.17.1
author
#28 lore raw

PATCH v2 5/22 net/e1000: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes ef990fb56e55 ("net/e1000: convert to new Rx offloads API")
---
 drivers/net/e1000/e1000_ethdev.h | 2 +-
 drivers/net/e1000/em_ethdev.c    | 5 ++---
 drivers/net/e1000/igb_ethdev.c   | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)
drivers/net/e1000/e1000_ethdev.h +1 -1
index 4755a5f333..3b4d9c3ee6 100644
@@ -97,7 +97,7 @@
  */
 #define E1000_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				VLAN_TAG_SIZE)
-
+#define E1000_ETH_MAX_LEN (RTE_ETHER_MTU + E1000_ETH_OVERHEAD)
 /*
  * Maximum number of Ring Descriptors.
  *
drivers/net/e1000/em_ethdev.c +2 -3
index 8ee9422bf4..2036c6e917 100644
@@ -1799,8 +1799,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (ret != 0)
 		return ret;
 
-	frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
-		VLAN_TAG_SIZE;
+	frame_size = mtu + E1000_ETH_OVERHEAD;
 
 	/* check that mtu is within the allowed range */
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > dev_info.max_rx_pktlen)
@@ -1816,7 +1815,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
drivers/net/e1000/igb_ethdev.c +1 -1
index 647aa8d995..dfe87508c2 100644
@@ -4369,7 +4369,7 @@ eth_igb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
Signature · 1 line
2.17.1
Acked-by on v2 5/22
#29 lore raw

Re: [dpdk-dev] [PATCH v2 05/22] net/e1000: fix the jumbo frame flag condition for mtu set

Quoted 113 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Thursday, December 17, 2020 5:23 PM
To: [email protected]
Cc: Lu, Wenzhuo <[email protected]>; Xing, Beilei <[email protected]>; Iremonger, Bernard <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Zhang, Helin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Wei, Dan <[email protected]>; Pei, Andy <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Zhao1, Wei <[email protected]>; Jiang, JunyuX <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Yang, SteveX <[email protected]>
Subject: [PATCH v2 05/22] net/e1000: fix the jumbo frame flag condition for mtu set

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes ef990fb56e55 ("net/e1000: convert to new Rx offloads API")
---
 drivers/net/e1000/e1000_ethdev.h | 2 +-
 drivers/net/e1000/em_ethdev.c    | 5 ++---
 drivers/net/e1000/igb_ethdev.c   | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)
drivers/net/e1000/e1000_ethdev.h +1 -1
index 4755a5f333..3b4d9c3ee6 100644
@@ -97,7 +97,7 @@
  */
 #define E1000_ETH_OVERHEAD (RTE_ETHER_HDR_LEN +
 RTE_ETHER_CRC_LEN + \
 				VLAN_TAG_SIZE)
-
+#define E1000_ETH_MAX_LEN (RTE_ETHER_MTU + E1000_ETH_OVERHEAD)
 /*
  * Maximum number of Ring Descriptors.

*

(quoted diff) +0 -0

b/drivers/net/e1000/em_ethdev.c index 8ee9422bf4..2036c6e917 100644

drivers/net/e1000/em_ethdev.c +1 -2
@@ -1799,8 +1799,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev,
 uint16_t mtu)
 	if (ret != 0)
 		return ret;
 
-	frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
-		VLAN_TAG_SIZE;
+	frame_size = mtu + E1000_ETH_OVERHEAD;
 
 	/* check that mtu is within the allowed range */

if (mtu < RTE_ETHER_MIN_MTU || frame_size >
dev_info.max_rx_pktlen) @@ -1816,7 +1815,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)

drivers/net/e1000/em_ethdev.c +1 -1
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
(quoted diff) +0 -0

b/drivers/net/e1000/igb_ethdev.c index 647aa8d995..dfe87508c2 100644

drivers/net/e1000/igb_ethdev.c +1 -1
@@ -4369,7 +4369,7 @@ eth_igb_mtu_set(struct rte_eth_dev *dev,
 uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;

rctl |= E1000_RCTL_LPE;
--
2.17.1

author
#30 lore raw

PATCH v2 6/22 net/hns3: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'HSN3_DEFAULT_FRAME_LEN'.

Fixes 1f5ca0b460cd ("net/hns3: support some device operations")
Fixes a5475d61fa34 ("net/hns3: support VF")
---
 drivers/net/hns3/hns3_ethdev.c    | 2 +-
 drivers/net/hns3/hns3_ethdev_vf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/hns3/hns3_ethdev.c +1 -1
index 7c34e382fb..10e0c0de46 100644
@@ -2467,7 +2467,7 @@ hns3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	rte_spinlock_lock(&hw->lock);
-	is_jumbo_frame = frame_size > RTE_ETHER_MAX_LEN ? true : false;
+	is_jumbo_frame = frame_size > HNS3_DEFAULT_FRAME_LEN ? true : false;
 	frame_size = RTE_MAX(frame_size, HNS3_DEFAULT_FRAME_LEN);
 
 	/*
drivers/net/hns3/hns3_ethdev_vf.c +1 -1
index f09cabcd82..ef03fb1c4e 100644
@@ -928,7 +928,7 @@ hns3vf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		rte_spinlock_unlock(&hw->lock);
 		return ret;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#31 lore raw

PATCH v2 7/22 net/i40e: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes c1715402df8f ("i40evf: fix jumbo frame support")
Fixes 43e5488c0ac6 ("net/i40e: support MTU configuration")
Fixes a778a1fa2e4e ("i40e: set up and initialize flow director")
Fixes c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
---
 drivers/net/i40e/i40e_ethdev.c    |  2 +-
 drivers/net/i40e/i40e_ethdev.h    |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c      |  2 +-
 drivers/net/i40e/i40e_rxtx.c      |  8 ++++----
 5 files changed, 12 insertions(+), 11 deletions(-)
drivers/net/i40e/i40e_ethdev.c +1 -1
index 2cb18ecc03..d4fcc6c853 100644
@@ -11770,7 +11770,7 @@ i40e_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_ethdev.h +1 -0
index 696c5aaf7e..1f31a532a1 100644
@@ -281,6 +281,7 @@ struct rte_flow {
  */
 #define I40E_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + I40E_VLAN_TAG_SIZE * 2)
+#define I40E_ETH_MAX_LEN (RTE_ETHER_MTU + I40E_ETH_OVERHEAD)
 
 #define I40E_RXTX_BYTES_H_16_BIT(bytes) ((bytes) & ~I40E_48_BIT_MASK)
 #define I40E_RXTX_BYTES_L_48_BIT(bytes) ((bytes) & I40E_48_BIT_MASK)
drivers/net/i40e/i40e_ethdev_vf.c +5 -5
index c26b036b85..85c65c09ee 100644
@@ -1889,22 +1889,22 @@ i40evf_rxq_init(struct rte_eth_dev *dev, struct i40e_rx_queue *rxq)
 	 * Check if the jumbo frame and maximum packet length are set correctly
 	 */
 	if (dev_data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
-				"frame is enabled", (uint32_t)RTE_ETHER_MAX_LEN,
+				"frame is enabled", (uint32_t)I40E_ETH_MAX_LEN,
 					(uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
 				"frame is disabled",
 				(uint32_t)RTE_ETHER_MIN_LEN,
-				(uint32_t)RTE_ETHER_MAX_LEN);
+				(uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
@@ -2825,7 +2825,7 @@ i40evf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_fdir.c +1 -1
index 50c0eee9f2..449b67b2a9 100644
@@ -116,7 +116,7 @@ i40e_fdir_rx_queue_init(struct i40e_rx_queue *rxq)
 #endif
 	rx_ctx.dtype = i40e_header_split_none;
 	rx_ctx.hsplit_0 = I40E_HEADER_SPLIT_NONE;
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = I40E_ETH_MAX_LEN;
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
 	rx_ctx.tphdata_ena = 1;
drivers/net/i40e/i40e_rxtx.c +4 -4
index 5df9a9df56..b8859bbff2 100644
@@ -2797,23 +2797,23 @@ i40e_rx_queue_config(struct i40e_rx_queue *rxq)
 		RTE_MIN((uint32_t)(hw->func_caps.rx_buf_chain_len *
 			rxq->rx_buf_len), data->dev_conf.rxmode.max_rx_pkt_len);
 	if (data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)I40E_ETH_MAX_LEN,
 				    (uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-			rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+			rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
Signature · 1 line
2.17.1
Acked-by on v2 7/22
#32 lore raw

Re: [dpdk-dev] [PATCH v2 07/22] net/i40e: fix the jumbo frame flag condition

Quoted 192 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Thursday, December 17, 2020 5:23 PM
To: [email protected]
Cc: Lu, Wenzhuo <[email protected]>; Xing, Beilei <[email protected]>; Iremonger, Bernard <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Zhang, Helin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Wei, Dan <[email protected]>; Pei, Andy <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Zhao1, Wei <[email protected]>; Jiang, JunyuX <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Yang, SteveX <[email protected]>
Subject: [PATCH v2 07/22] net/i40e: fix the jumbo frame flag condition

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes c1715402df8f ("i40evf: fix jumbo frame support")
Fixes 43e5488c0ac6 ("net/i40e: support MTU configuration")
Fixes a778a1fa2e4e ("i40e: set up and initialize flow director")
Fixes c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
---
 drivers/net/i40e/i40e_ethdev.c    |  2 +-
 drivers/net/i40e/i40e_ethdev.h    |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c      |  2 +-
 drivers/net/i40e/i40e_rxtx.c      |  8 ++++----
 5 files changed, 12 insertions(+), 11 deletions(-)
drivers/net/i40e/i40e_ethdev.c +1 -1
index 2cb18ecc03..d4fcc6c853 100644
@@ -11770,7 +11770,7 @@ i40e_dev_mtu_set(struct rte_eth_dev *dev,
 uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/i40e/i40e_ethdev.c +0 -0
 	else
(quoted diff) +0 -0

b/drivers/net/i40e/i40e_ethdev.h index 696c5aaf7e..1f31a532a1 100644

drivers/net/i40e/i40e_ethdev.h +1 -0
@@ -281,6 +281,7 @@ struct rte_flow {
  */
 #define I40E_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
 I40E_VLAN_TAG_SIZE * 2)
+#define I40E_ETH_MAX_LEN (RTE_ETHER_MTU + I40E_ETH_OVERHEAD)
 
 #define I40E_RXTX_BYTES_H_16_BIT(bytes) ((bytes) & ~I40E_48_BIT_MASK)

#define I40E_RXTX_BYTES_L_48_BIT(bytes) ((bytes) & I40E_48_BIT_MASK)

drivers/net/i40e/i40e_ethdev_vf.c +0 -0
index c26b036b85..85c65c09ee 100644
@@ -1889,22 +1889,22 @@ i40evf_rxq_init(struct rte_eth_dev *dev, struct
 i40e_rx_queue *rxq)
 	 * Check if the jumbo frame and maximum packet length are set

correctly

drivers/net/i40e/i40e_ethdev_vf.c +0 -0
 	 */
 	if (dev_data->dev_conf.rxmode.offloads &

DEV_RX_OFFLOAD_JUMBO_FRAME) {

drivers/net/i40e/i40e_ethdev_vf.c +1 -1
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must

be "
"larger than %u and smaller than %u, as
jumbo "

drivers/net/i40e/i40e_ethdev_vf.c +0 -1
-				"frame is enabled",

(uint32_t)RTE_ETHER_MAX_LEN,

drivers/net/i40e/i40e_ethdev_vf.c +1 -0
+				"frame is enabled",

(uint32_t)I40E_ETH_MAX_LEN,

drivers/net/i40e/i40e_ethdev_vf.c +1 -1
 					(uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must

be "
"larger than %u and smaller than %u, as
jumbo "

drivers/net/i40e/i40e_ethdev_vf.c +2 -2
 				"frame is disabled",
 				(uint32_t)RTE_ETHER_MIN_LEN,
-				(uint32_t)RTE_ETHER_MAX_LEN);
+				(uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
@@ -2825,7 +2825,7 @@ i40evf_dev_mtu_set(struct rte_eth_dev *dev,
 uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/i40e/i40e_ethdev_vf.c +0 -0
 	else
drivers/net/i40e/i40e_fdir.c index renamed from drivers/net/i40e/i40e_fdir.c +0 -0

50c0eee9f2..449b67b2a9 100644

drivers/net/i40e/i40e_fdir.c +1 -1
@@ -116,7 +116,7 @@ i40e_fdir_rx_queue_init(struct i40e_rx_queue *rxq)
 #endif
 	rx_ctx.dtype = i40e_header_split_none;
 	rx_ctx.hsplit_0 = I40E_HEADER_SPLIT_NONE;
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = I40E_ETH_MAX_LEN;
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
 	rx_ctx.tphdata_ena = 1;
drivers/net/i40e/i40e_rxtx.c index renamed from drivers/net/i40e/i40e_rxtx.c +0 -0

5df9a9df56..b8859bbff2 100644

drivers/net/i40e/i40e_rxtx.c +1 -1
@@ -2797,23 +2797,23 @@ i40e_rx_queue_config(struct i40e_rx_queue
 *rxq)
 		RTE_MIN((uint32_t)(hw->func_caps.rx_buf_chain_len *
 			rxq->rx_buf_len), data-
 >dev_conf.rxmode.max_rx_pkt_len);
 	if (data->dev_conf.rxmode.offloads &
 DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must

"

drivers/net/i40e/i40e_rxtx.c +2 -2
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)I40E_ETH_MAX_LEN,
 				    (uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-			rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+			rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must

be "

drivers/net/i40e/i40e_rxtx.c +1 -2
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
--

2.17.1

author
#33 lore raw

PATCH v2 8/22 net/iavf: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 3fd7a3719c66 ("net/avf: enable ops for MTU setting")
Fixes 69dd4c3d0898 ("net/avf: enable queue and device")
---
 drivers/net/iavf/iavf.h        |  1 +
 drivers/net/iavf/iavf_ethdev.c | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)
drivers/net/iavf/iavf.h +1 -0
index 6d5912d8c1..3328bd9327 100644
@@ -66,6 +66,7 @@
 #define IAVF_VLAN_TAG_SIZE               4
 #define IAVF_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IAVF_VLAN_TAG_SIZE * 2)
+#define IAVF_ETH_MAX_LEN (RTE_ETHER_MTU + IAVF_ETH_OVERHEAD)
 
 #define IAVF_32_BIT_WIDTH (CHAR_BIT * 4)
 #define IAVF_48_BIT_WIDTH (CHAR_BIT * 6)
drivers/net/iavf/iavf_ethdev.c +5 -5
index 7e3c26a94e..658f28d353 100644
@@ -418,23 +418,23 @@ iavf_init_rxq(struct rte_eth_dev *dev, struct iavf_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= IAVF_ETH_MAX_LEN ||
 		    max_pkt_len > IAVF_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)IAVF_ETH_MAX_LEN,
 				    (uint32_t)IAVF_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > IAVF_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)IAVF_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -1167,7 +1167,7 @@ iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IAVF_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#34 lore raw

PATCH v2 9/22 net/ice: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 84dc7a95a2d3 ("net/ice: enable flow director engine")
Fixes 1b009275e2c8 ("net/ice: add Rx queue init in DCF")
Fixes ae2bdd0219cb ("net/ice: support MTU setting")
Fixes 50370662b727 ("net/ice: support device and queue ops")
---
 drivers/net/ice/ice_dcf_ethdev.c |  8 ++++----
 drivers/net/ice/ice_ethdev.c     |  2 +-
 drivers/net/ice/ice_ethdev.h     |  1 +
 drivers/net/ice/ice_rxtx.c       | 10 +++++-----
 4 files changed, 11 insertions(+), 10 deletions(-)
drivers/net/ice/ice_dcf_ethdev.c +4 -4
index b0b2ecb0d6..e5c877805f 100644
@@ -60,23 +60,23 @@ ice_dcf_init_rxq(struct rte_eth_dev *dev, struct ice_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
drivers/net/ice/ice_ethdev.c +1 -1
index 9a5d6a559f..d25aed54b3 100644
@@ -3904,7 +3904,7 @@ ice_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ICE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/ice/ice_ethdev.h +1 -0
index 899f446cde..2b03c59671 100644
@@ -135,6 +135,7 @@
  */
 #define ICE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + ICE_VLAN_TAG_SIZE * 2)
+#define ICE_ETH_MAX_LEN (RTE_ETHER_MTU + ICE_ETH_OVERHEAD)
 
 #define ICE_RXTX_BYTES_HIGH(bytes) ((bytes) & ~ICE_40_BIT_MASK)
 #define ICE_RXTX_BYTES_LOW(bytes) ((bytes) & ICE_40_BIT_MASK)
drivers/net/ice/ice_rxtx.c +5 -5
index d052bd0f1b..c98328ce0b 100644
@@ -246,23 +246,23 @@ ice_program_hw_rx_queue(struct ice_rx_queue *rxq)
 				   dev->data->dev_conf.rxmode.max_rx_pkt_len);
 
 	if (rxmode->offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -701,7 +701,7 @@ ice_fdir_program_hw_rx_queue(struct ice_rx_queue *rxq)
 	rx_ctx.hbuf = rxq->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S;
 	rx_ctx.dtype = 0; /* No Header Split mode */
 	rx_ctx.dsize = 1; /* 32B descriptors */
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = ICE_ETH_MAX_LEN;
 	/* TPH: Transaction Layer Packet (TLP) processing hints */
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
Signature · 1 line
2.17.1
author
#35 lore raw

PATCH v2 10/22 net/ipn3ke: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 70d6b7f550f4 ("net/ipn3ke: add representor")
---
 drivers/net/ipn3ke/ipn3ke_ethdev.h      | 1 +
 drivers/net/ipn3ke/ipn3ke_representor.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/ipn3ke/ipn3ke_ethdev.h +1 -0
index 9b0cf309c8..a6815a9cca 100644
@@ -640,6 +640,7 @@ ipn3ke_tm_ops_get(struct rte_eth_dev *ethdev,
  */
 #define IPN3KE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IPN3KE_VLAN_TAG_SIZE * 2)
+#define IPN3KE_ETH_MAX_LEN (RTE_ETHER_MTU + IPN3KE_ETH_OVERHEAD)
 
 #define IPN3KE_MAC_FRAME_SIZE_MAX    9728
 #define IPN3KE_MAC_RX_FRAME_MAXLENGTH    0x00AE
drivers/net/ipn3ke/ipn3ke_representor.c +1 -1
index 8a53602576..9e15cce34f 100644
@@ -2801,7 +2801,7 @@ ipn3ke_rpst_mtu_set(struct rte_eth_dev *ethdev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IPN3KE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			(uint64_t)(DEV_RX_OFFLOAD_JUMBO_FRAME);
 	else
Signature · 1 line
2.17.1
Reviewed-by on v2 10/22
#36 lore raw

Re: [dpdk-dev] [PATCH v2 10/22] net/ipn3ke: fix the jumbo frame flag condition for mtu set

Hi,

Quoted 86 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Thursday, December 17, 2020 17:23
To: [email protected]
Cc: Lu, Wenzhuo <[email protected]>; Xing, Beilei <[email protected]>; Iremonger, Bernard <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Zhang, Helin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Wei, Dan <[email protected]>; Pei, Andy <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Zhao1, Wei <[email protected]>; Jiang, JunyuX <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Yang, SteveX <[email protected]>
Subject: [PATCH v2 10/22] net/ipn3ke: fix the jumbo frame flag condition for mtu set

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 70d6b7f550f4 ("net/ipn3ke: add representor")
---
 drivers/net/ipn3ke/ipn3ke_ethdev.h      | 1 +
 drivers/net/ipn3ke/ipn3ke_representor.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/ipn3ke/ipn3ke_ethdev.h +1 -0
index 9b0cf309c8..a6815a9cca 100644
@@ -640,6 +640,7 @@ ipn3ke_tm_ops_get(struct rte_eth_dev *ethdev,
  */
 #define IPN3KE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
 IPN3KE_VLAN_TAG_SIZE * 2)
+#define IPN3KE_ETH_MAX_LEN (RTE_ETHER_MTU +
 IPN3KE_ETH_OVERHEAD)
 

#define IPN3KE_MAC_FRAME_SIZE_MAX 9728
#define IPN3KE_MAC_RX_FRAME_MAXLENGTH 0x00AE

drivers/net/ipn3ke/ipn3ke_representor.c +1 -1
index 8a53602576..9e15cce34f 100644
@@ -2801,7 +2801,7 @@ ipn3ke_rpst_mtu_set(struct rte_eth_dev *ethdev,
 uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IPN3KE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			(uint64_t)(DEV_RX_OFFLOAD_JUMBO_FRAME);
Quoted 3 lines

else
--
2.17.1

author
#37 lore raw

PATCH v2 11/22 net/octeontx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 3151e6a687a3 ("net/octeontx: support MTU")
---
 drivers/net/octeontx/octeontx_ethdev.c | 2 +-
 drivers/net/octeontx/octeontx_ethdev.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/octeontx/octeontx_ethdev.c +1 -1
index 3ee7b043fd..81779885d5 100644
@@ -552,7 +552,7 @@ octeontx_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > OCCTX_L2_MAX_LEN)
 		nic->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		nic->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/octeontx/octeontx_ethdev.h +1 -0
index 7246fb6d1d..780a094ffa 100644
@@ -44,6 +44,7 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define OCCTX_L2_OVERHEAD	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				 OCCTX_MAX_VTAG_ACT_SIZE)
+#define OCCTX_L2_MAX_LEN	(RTE_ETHER_MTU + OCCTX_L2_OVERHEAD)
 
 /* Since HW FRS includes NPC VTAG insertion space, user has reduced FRS */
 #define OCCTX_MAX_FRS	\
Signature · 1 line
2.17.1
Acked-by on v2 11/22
#38 lore raw

Re: [dpdk-dev] [EXT] [PATCH v2 11/22] net/octeontx: fix the jumbo frame flag condition for mtu set

Quoted 8 lines · Steve Yang

External Email

----------------------------------------------------------------------
The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

Quoted 6 lines

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 3151e6a687a3 ("net/octeontx: support MTU")
Quoted 33 lines
---
 drivers/net/octeontx/octeontx_ethdev.c | 2 +-
 drivers/net/octeontx/octeontx_ethdev.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/octeontx/octeontx_ethdev.c +1 -1
index 3ee7b043fd..81779885d5 100644
@@ -552,7 +552,7 @@ octeontx_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > OCCTX_L2_MAX_LEN)
 		nic->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		nic->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/octeontx/octeontx_ethdev.h +1 -0
index 7246fb6d1d..780a094ffa 100644
@@ -44,6 +44,7 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define OCCTX_L2_OVERHEAD	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				 OCCTX_MAX_VTAG_ACT_SIZE)
+#define OCCTX_L2_MAX_LEN	(RTE_ETHER_MTU + OCCTX_L2_OVERHEAD)
 
 /* Since HW FRS includes NPC VTAG insertion space, user has reduced FRS */
 #define OCCTX_MAX_FRS	\
Signature · 1 line
2.17.1
author
#39 lore raw

PATCH v2 12/22 net/octeontx2: fix the jumbo frame flag condition for mtu

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")
---
 drivers/net/octeontx2/otx2_ethdev.h     | 2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev.h +2 -0
index 3b9871f4dc..99f0469d89 100644
@@ -51,6 +51,8 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define NIX_L2_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + 8)
+#define NIX_L2_MAX_LEN \
+	(RTE_ETHER_MTU + NIX_L2_OVERHEAD)
 
 /* HW config of frame size doesn't include FCS */
 #define NIX_MAX_HW_FRS			9212
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..963cc285ed 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIX_L2_MAX_LEN)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
Acked-by on v2 12/22
#40 lore raw

Re: [dpdk-dev] [PATCH v2 12/22] net/octeontx2: fix the jumbo frame flag condition for mtu

Quoted 45 lines · Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")
---
 drivers/net/octeontx2/otx2_ethdev.h     | 2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev.h +2 -0
index 3b9871f4dc..99f0469d89 100644
@@ -51,6 +51,8 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define NIX_L2_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + 8)
+#define NIX_L2_MAX_LEN \
+	(RTE_ETHER_MTU + NIX_L2_OVERHEAD)
 
 /* HW config of frame size doesn't include FCS */
 #define NIX_MAX_HW_FRS			9212
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..963cc285ed 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIX_L2_MAX_LEN)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
Acked-by on v2 12/22
#41 lore raw

Re: [dpdk-dev] [EXT] [PATCH v2 12/22] net/octeontx2: fix the jumbo frame flag condition for mtu

In reply to Steve Yang
Quoted 87 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Thursday, December 17, 2020 2:53 PM
To: [email protected]
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Shijith Thotton <[email protected]>; Srisivasubramanian Srinivasan <[email protected]>; [email protected]; Harman Kalra <[email protected]>; Jerin Jacob Kollanukkaran <[email protected]>; Nithin Kumar Dabilpuram <[email protected]>; Kiran Kumar Kokkilagadda <[email protected]>; Rasesh Mody <[email protected]>; Shahed Shaikh <[email protected]>; [email protected]; Maciej Czekaj [C] <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Vamsi Krishna Attunuru <[email protected]>; Sunil Kumar Kori <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Steve Yang <[email protected]>
Subject: [EXT] [PATCH v2 12/22] net/octeontx2: fix the jumbo frame flag condition for mtu

External Email

----------------------------------------------------------------------
The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")

---
drivers/net/octeontx2/otx2_ethdev.h | 2 ++
drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-

2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev.h +2 -0
index 3b9871f4dc..99f0469d89 100644
@@ -51,6 +51,8 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define NIX_L2_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + 8)
+#define NIX_L2_MAX_LEN \
+	(RTE_ETHER_MTU + NIX_L2_OVERHEAD)
 
 /* HW config of frame size doesn't include FCS */
 #define NIX_MAX_HW_FRS			9212
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..963cc285ed 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t
 mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIX_L2_MAX_LEN)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Quoted 2 lines

--
2.17.1

author
#42 lore raw

PATCH v2 13/22 net/qede: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 200645ac7909 ("net/qede: set MTU")
---
 drivers/net/qede/qede_ethdev.c | 2 +-
 drivers/net/qede/qede_rxtx.h   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/qede/qede_ethdev.c +1 -1
index 549013557c..6919378b8e 100644
@@ -2367,7 +2367,7 @@ static int qede_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 			fp->rxq->rx_buf_size = rc;
 		}
 	}
-	if (max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+	if (frame_size > QEDE_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/qede/qede_rxtx.h +1 -0
index d7ff870b20..fcb564a1bb 100644
@@ -71,6 +71,7 @@
 				 + (QEDE_LLC_SNAP_HDR_LEN) + 2)
 
 #define QEDE_MAX_ETHER_HDR_LEN	(RTE_ETHER_HDR_LEN + QEDE_ETH_OVERHEAD)
+#define QEDE_ETH_MAX_LEN	(RTE_ETHER_MTU + QEDE_MAX_ETHER_HDR_LEN)
 
 #define QEDE_RSS_OFFLOAD_ALL    (ETH_RSS_IPV4			|\
 				 ETH_RSS_NONFRAG_IPV4_TCP	|\
Signature · 1 line
2.17.1
author
#43 lore raw

PATCH v2 14/22 net/sfc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes ff6a1197c3b1 ("net/sfc: convert to new Rx offload API")
---
 drivers/net/sfc/sfc_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/sfc/sfc_ethdev.c +1 -1
index 93fc7baa0d..f2f5336435 100644
@@ -1017,7 +1017,7 @@ sfc_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 	 * The driver does not use it, but other PMDs update jumbo frame
 	 * flag and max_rx_pkt_len when MTU is set.
 	 */
-	if (mtu > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	}
Signature · 1 line
2.17.1
author
#44 lore raw

PATCH v2 15/22 net/thunderx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

Fixes 65d9804edc05 ("net/thunderx: support MTU configuration")
---
 drivers/net/thunderx/base/nicvf_hw_defs.h | 1 +
 drivers/net/thunderx/nicvf_ethdev.c       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/thunderx/base/nicvf_hw_defs.h +1 -0
index b12c8ec50a..adc8ec943d 100644
@@ -176,6 +176,7 @@
 #define NIC_HW_MAX_MTU                  (9190)
 #define NIC_HW_MAX_FRS                  (NIC_HW_MAX_MTU + NIC_HW_L2_OVERHEAD)
 #define NIC_HW_MAX_SEGS                 (12)
+#define NIC_HW_L2_MAX_LEN		(RTE_ETHER_MTU + NIC_HW_L2_OVERHEAD)
 
 /* Descriptor alignments */
 #define NICVF_RBDR_BASE_ALIGN_BYTES     (128) /* 7 bits */
drivers/net/thunderx/nicvf_ethdev.c +1 -1
index b6bb05e500..c2e7c334d4 100644
@@ -176,7 +176,7 @@ nicvf_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 		(frame_size + 2 * VLAN_TAG_SIZE > buffsz * NIC_HW_MAX_SEGS))
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIC_HW_L2_MAX_LEN)
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		rxmode->offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#45 lore raw

PATCH v2 16/22 net/ixgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Fixes 95a27b3ba5f5 ("net/ixgbe: enable jumbo frame for VF")
---
 drivers/net/ixgbe/ixgbe_ethdev.c | 2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h | 3 +++
 drivers/net/ixgbe/ixgbe_pf.c     | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)
drivers/net/ixgbe/ixgbe_ethdev.c +1 -1
index d7a1806ab8..fa0f5afd03 100644
@@ -5173,7 +5173,7 @@ ixgbe_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > IXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		hlreg0 |= IXGBE_HLREG0_JUMBOEN;
drivers/net/ixgbe/ixgbe_ethdev.h +3 -0
index 3d35ea791b..a0ce18ca24 100644
@@ -104,6 +104,9 @@
 /* The overhead from MTU to max frame size. */
 #define IXGBE_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
 
+/* The max frame size with default MTU */
+#define IXGBE_ETH_MAX_LEN  (RTE_ETHER_MTU + IXGBE_ETH_OVERHEAD)
+
 /* bit of VXLAN tunnel type | 7 bits of zeros  | 8 bits of zeros*/
 #define IXGBE_FDIR_VXLAN_TUNNEL_TYPE    0x8000
 /* bit of NVGRE tunnel type | 7 bits of zeros  | 8 bits of zeros*/
drivers/net/ixgbe/ixgbe_pf.c +1 -1
index 833863af5a..89698e8470 100644
@@ -575,7 +575,7 @@ ixgbe_set_vf_lpe(struct rte_eth_dev *dev, __rte_unused uint32_t vf, uint32_t *ms
 		   IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
 	if (max_frs < new_mtu) {
 		hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
-		if (new_mtu > RTE_ETHER_MAX_LEN) {
+		if (new_mtu > IXGBE_ETH_MAX_LEN) {
 			dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 			hlreg0 |= IXGBE_HLREG0_JUMBOEN;
Signature · 1 line
2.17.1
Acked-by on v2 16/22
#46 lore raw

Re: [dpdk-dev] [PATCH v2 16/22] net/ixgbe: fix the jumbo frame flag condition

Quoted 104 lines

-----Original Message-----
From: Steve Yang <[email protected]>
Sent: Thursday, December 17, 2020 5:23 PM
To: [email protected]
Cc: Lu, Wenzhuo <[email protected]>; Xing, Beilei <[email protected]>; Iremonger, Bernard <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Guo, Jia <[email protected]>; Wang, Haiyue <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Wu, Jingjing <[email protected]>; Yang, Qiming <[email protected]>; Zhang, Qi Z <[email protected]>; Xu, Rosen <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Yigit, Ferruh <[email protected]>; [email protected]; Ananyev, Konstantin <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Zhang, Helin <[email protected]>; [email protected]; [email protected]; Xu, Ting <[email protected]>; Li, Xiaoyun <[email protected]>; Wei, Dan <[email protected]>; Pei, Andy <[email protected]>; [email protected]; [email protected]; [email protected]; Richardson, Bruce <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Zhao1, Wei <[email protected]>; Jiang, JunyuX <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Yang, SteveX <[email protected]>
Subject: [PATCH v2 16/22] net/ixgbe: fix the jumbo frame flag condition

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Fixes 95a27b3ba5f5 ("net/ixgbe: enable jumbo frame for VF")

---
drivers/net/ixgbe/ixgbe_ethdev.c | 2 +- drivers/net/ixgbe/ixgbe_ethdev.h
| 3 +++

 drivers/net/ixgbe/ixgbe_pf.c     | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)
drivers/net/ixgbe/ixgbe_ethdev.c +1 -1
index d7a1806ab8..fa0f5afd03 100644
@@ -5173,7 +5173,7 @@ ixgbe_dev_mtu_set(struct rte_eth_dev *dev,
 uint16_t mtu)
 	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > IXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/ixgbe/ixgbe_ethdev.c +0 -0
 		hlreg0 |= IXGBE_HLREG0_JUMBOEN;
drivers/net/ixgbe/ixgbe_ethdev.h +3 -0
index 3d35ea791b..a0ce18ca24 100644
@@ -104,6 +104,9 @@
 /* The overhead from MTU to max frame size. */  #define
 IXGBE_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
 
+/* The max frame size with default MTU */ #define IXGBE_ETH_MAX_LEN
+(RTE_ETHER_MTU + IXGBE_ETH_OVERHEAD)
+
 /* bit of VXLAN tunnel type | 7 bits of zeros  | 8 bits of zeros*/
 #define IXGBE_FDIR_VXLAN_TUNNEL_TYPE    0x8000
 /* bit of NVGRE tunnel type | 7 bits of zeros  | 8 bits of zeros*/ diff --git

a/drivers/net/ixgbe/ixgbe_pf.c b/drivers/net/ixgbe/ixgbe_pf.c index 833863af5a..89698e8470 100644

drivers/net/ixgbe/ixgbe_pf.c +0 -0
@@ -575,7 +575,7 @@ ixgbe_set_vf_lpe(struct rte_eth_dev *dev,

__rte_unused uint32_t vf, uint32_t *ms
IXGBE_MHADD_MFS_MASK) >>
IXGBE_MHADD_MFS_SHIFT;

drivers/net/ixgbe/ixgbe_pf.c +1 -2
 	if (max_frs < new_mtu) {
 		hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
-		if (new_mtu > RTE_ETHER_MAX_LEN) {
+		if (new_mtu > IXGBE_ETH_MAX_LEN) {
 			dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 			hlreg0 |= IXGBE_HLREG0_JUMBOEN;
--

2.17.1

author
#47 lore raw

PATCH v2 17/22 net/cxgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 4b2eff452d2e ("cxgbe: enable jumbo frames")
Fixes 0ec33be4c857 ("cxgbe: allow to change mtu")
---
 drivers/net/cxgbe/cxgbe.h        | 4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)
drivers/net/cxgbe/cxgbe.h +4 -0
index ef62af1c3f..7c89a028bf 100644
@@ -19,6 +19,10 @@
 #define CXGBE_MAX_RX_PKTLEN (9000 + RTE_ETHER_HDR_LEN + \
 				RTE_ETHER_CRC_LEN) /* max pkt */
 
+/* The max frame size with default MTU */
+#define CXGBE_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /* Max poll time is 100 * 100msec = 10 sec */
 #define CXGBE_LINK_STATUS_POLL_MS 100 /* 100ms */
 #define CXGBE_LINK_STATUS_POLL_CNT 100 /* Max number of times to poll */
drivers/net/cxgbe/cxgbe_ethdev.c +2 -2
index 98d0362fa3..480d6f58a8 100644
@@ -300,7 +300,7 @@ int cxgbe_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -EINVAL;
 
 	/* set to jumbo mode if needed */
-	if (new_mtu > RTE_ETHER_MAX_LEN)
+	if (new_mtu > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
@@ -669,7 +669,7 @@ int cxgbe_dev_rx_queue_setup(struct rte_eth_dev *eth_dev,
 		rxq->fl.size = temp_nb_desc;
 
 	/* Set to jumbo mode if necessary */
-	if (pkt_len > RTE_ETHER_MAX_LEN)
+	if (pkt_len > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#48 lore raw

PATCH v2 18/22 net/axgbe: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes b58d8781fa1f ("net/axgbe: support setting MTU")
---
 drivers/net/axgbe/axgbe_ethdev.c | 2 +-
 drivers/net/axgbe/axgbe_ethdev.h | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)
drivers/net/axgbe/axgbe_ethdev.c +1 -1
index f524a3be96..599ae19940 100644
@@ -1489,7 +1489,7 @@ static int axgb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 				dev->data->port_id);
 		return -EBUSY;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > AXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		val = 1;
drivers/net/axgbe/axgbe_ethdev.h +6 -0
index 1481fd9ff3..a6226729fe 100644
@@ -125,6 +125,12 @@
 /* MDIO port types */
 #define AXGMAC_MAX_C22_PORT		3
 
+/* The max frame size with default MTU */
+#define AXGBE_ETH_MAX_LEN ( \
+	RTE_ETHER_MTU + \
+	RTE_ETHER_HDR_LEN + \
+	RTE_ETHER_CRC_LEN)
+
 /* Helper macro for descriptor handling
  *  Always use AXGBE_GET_DESC_DATA to access the descriptor data
  *  since the index is free-running and needs to be and-ed
Signature · 1 line
2.17.1
author
#49 lore raw

PATCH v2 19/22 net/enetc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 5d5589b0c858 ("net/enetc: support MTU update and jumbo frames")
---
 drivers/net/enetc/enetc.h        | 4 ++++
 drivers/net/enetc/enetc_ethdev.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/enetc/enetc.h +4 -0
index 14ef3bc18b..7163633bce 100644
@@ -29,6 +29,10 @@
 /* maximum frame size supported */
 #define ENETC_MAC_MAXFRM_SIZE	9600
 
+/* The max frame size with default MTU */
+#define ENETC_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /*
  * upper_32_bits - return bits 32-63 of a number
  * @n: the number we're accessing
drivers/net/enetc/enetc_ethdev.c +1 -1
index 6ff3022874..4d2c9c0474 100644
@@ -677,7 +677,7 @@ enetc_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ENETC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads &=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#50 lore raw

PATCH v2 20/22 net/hinic: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 254bd849b132 ("net/hinic: set jumbo frame offload flag")
---
 drivers/net/hinic/hinic_pmd_ethdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/hinic/hinic_pmd_ethdev.c +4 -1
index 62642354cf..5a2c171099 100644
@@ -75,6 +75,9 @@
 #define HINIC_PKTLEN_TO_MTU(pktlen)	\
 	((pktlen) - (ETH_HLEN + ETH_CRC_LEN))
 
+/* The max frame size with default MTU */
+#define HINIC_ETH_MAX_LEN (RTE_ETHER_MTU + ETH_HLEN + ETH_CRC_LEN)
+
 /* lro numer limit for one packet */
 #define HINIC_LRO_WQE_NUM_DEFAULT	8
 
@@ -1556,7 +1559,7 @@ static int hinic_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 
 	/* update max frame size */
 	frame_size = HINIC_MTU_TO_PKTLEN(mtu);
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > HINIC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#51 lore raw

PATCH v2 21/22 net/nfp: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU'.

Fixes d4a27a3b092a ("nfp: add basic features")
---
 drivers/net/nfp/nfp_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/nfp/nfp_net.c +1 -1
index 1608bf5ea1..9ea24e5bda 100644
@@ -1508,7 +1508,7 @@ nfp_net_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	/* switch to jumbo mode if needed */
-	if ((uint32_t)mtu > RTE_ETHER_MAX_LEN)
+	if ((uint32_t)mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#52 lore raw

PATCH v2 22/22 net/liquidio: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 9f1c00266d82 ("net/liquidio: add API to set MTU")
---
 drivers/net/liquidio/lio_ethdev.c | 2 +-
 drivers/net/liquidio/lio_ethdev.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)
drivers/net/liquidio/lio_ethdev.c +1 -1
index d4dd3768cd..eb0fdab45a 100644
@@ -481,7 +481,7 @@ lio_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -1;
 	}
 
-	if (frame_len > RTE_ETHER_MAX_LEN)
+	if (frame_len > LIO_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/liquidio/lio_ethdev.h +3 -0
index 74cd2fb6c6..d33be1c44d 100644
@@ -13,6 +13,9 @@
 #define LIO_LSC_TIMEOUT		100000 /* 100000us (100ms) */
 #define LIO_MAX_CMD_TIMEOUT     10000 /* 10000ms (10s) */
 
+/* The max frame size with default MTU */
+#define LIO_ETH_MAX_LEN (RTE_ETHER_MTU + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 #define LIO_DEV(_eth_dev)		((_eth_dev)->data->dev_private)
 
 /* LIO Response condition variable */
Signature · 1 line
2.17.1
#53 lore raw
In reply to Steve Yang
Quoted 34 lines · Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

---
v2:
- defined the 'RTE_ETHER_MTU + overhead' to 'driver_ETH_MAX_LEN';
- changed the 'mtu > RTE_ETHER_MTU' to 'frame_size > driver_ETH_MAX_LEN';
---

Steve Yang (22):
ethdev: fix MTU size exceeds max rx packet length app/testpmd: fix max rx packet length for VLAN packets net/dpaa: fix the jumbo frame flag condition for mtu set net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set

Quoted 8 lines

net/thunderx: fix the jumbo frame flag condition for mtu set net/ixgbe: fix the jumbo frame flag condition net/cxgbe: fix the jumbo frame flag condition net/axgbe: fix the jumbo frame flag condition for mtu set net/enetc: fix the jumbo frame flag condition for mtu set net/hinic: fix the jumbo frame flag condition for mtu set net/nfp: fix the jumbo frame flag condition for mtu set net/liquidio: fix the jumbo frame flag condition for mtu set

Driver maintainers please be aware that this set is planned to be merged for -rc1, last a few days to review changes to your driver.

author
#54 lore raw

v3 cover fix rx packets dropped issue

In reply to Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Following scopes perhaps will be impacted:
- the cases of jumbo frame related;
- the logic of 'max_rx_pkt_len' and 'mtu' related;
- the using place of 'RTE_ETHER_MAX_LEN';

---
v3:
- removed redundant if-conditions in rte_ethdev and testpmd;
- adjusted the alignment style;
- added offload check before updating mtu;
v2:
- defined the 'RTE_ETHER_MTU + overhead' to 'driver_ETH_MAX_LEN';
- changed the 'mtu > RTE_ETHER_MTU' to 'frame_size > driver_ETH_MAX_LEN';
---

Steve Yang (22):
ethdev: fix MTU size exceeds max rx packet length app/testpmd: fix max rx packet length for VLAN packets net/dpaa: fix the jumbo frame flag condition for mtu set net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set net/ixgbe: fix the jumbo frame flag condition net/cxgbe: fix the jumbo frame flag condition net/axgbe: fix the jumbo frame flag condition for mtu set net/enetc: fix the jumbo frame flag condition for mtu set net/hinic: fix the jumbo frame flag condition for mtu set net/nfp: fix the jumbo frame flag condition for mtu set net/liquidio: fix the jumbo frame flag condition for mtu set

 app/test-pmd/cmdline.c                    |  6 -----
 app/test-pmd/config.c                     |  2 +-
 app/test-pmd/parameters.c                 |  7 ++----
 app/test-pmd/testpmd.c                    | 18 +++++++++++++++
 drivers/net/axgbe/axgbe_ethdev.c          |  2 +-
 drivers/net/axgbe/axgbe_ethdev.h          |  6 +++++
 drivers/net/cxgbe/cxgbe.h                 |  4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c          |  4 ++--
 drivers/net/dpaa/dpaa_ethdev.c            |  2 +-
 drivers/net/dpaa/dpaa_ethdev.h            |  4 ++++
 drivers/net/dpaa2/dpaa2_ethdev.c          |  2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h          |  4 ++++
 drivers/net/e1000/e1000_ethdev.h          |  2 +-
 drivers/net/e1000/em_ethdev.c             |  5 ++---
 drivers/net/e1000/igb_ethdev.c            |  2 +-
 drivers/net/enetc/enetc.h                 |  4 ++++
 drivers/net/enetc/enetc_ethdev.c          |  2 +-
 drivers/net/hinic/hinic_pmd_ethdev.c      |  5 ++++-
 drivers/net/hns3/hns3_ethdev.c            |  2 +-
 drivers/net/hns3/hns3_ethdev_vf.c         |  2 +-
 drivers/net/i40e/i40e_ethdev.c            |  2 +-
 drivers/net/i40e/i40e_ethdev.h            |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c         | 10 ++++-----
 drivers/net/i40e/i40e_fdir.c              |  2 +-
 drivers/net/i40e/i40e_rxtx.c              |  8 +++----
 drivers/net/iavf/iavf.h                   |  1 +
 drivers/net/iavf/iavf_ethdev.c            | 10 ++++-----
 drivers/net/ice/ice_dcf_ethdev.c          |  8 +++----
 drivers/net/ice/ice_ethdev.c              |  2 +-
 drivers/net/ice/ice_ethdev.h              |  1 +
 drivers/net/ice/ice_rxtx.c                | 10 ++++-----
 drivers/net/ipn3ke/ipn3ke_ethdev.h        |  1 +
 drivers/net/ipn3ke/ipn3ke_representor.c   |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.c          |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h          |  3 +++
 drivers/net/ixgbe/ixgbe_pf.c              |  2 +-
 drivers/net/liquidio/lio_ethdev.c         |  2 +-
 drivers/net/liquidio/lio_ethdev.h         |  3 +++
 drivers/net/nfp/nfp_net.c                 |  2 +-
 drivers/net/octeontx/octeontx_ethdev.c    |  2 +-
 drivers/net/octeontx/octeontx_ethdev.h    |  1 +
 drivers/net/octeontx2/otx2_ethdev.h       |  2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c   |  2 +-
 drivers/net/qede/qede_ethdev.c            |  2 +-
 drivers/net/qede/qede_rxtx.h              |  1 +
 drivers/net/sfc/sfc_ethdev.c              |  2 +-
 drivers/net/thunderx/base/nicvf_hw_defs.h |  1 +
 drivers/net/thunderx/nicvf_ethdev.c       |  2 +-
 lib/librte_ethdev/rte_ethdev.c            | 27 ++++++++++++++++++++---
 49 files changed, 134 insertions(+), 65 deletions(-)
Signature · 1 line
2.17.1
author
#55 lore raw

PATCH v3 1/22 ethdev: fix MTU size exceeds max rx packet length

In reply to Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
 lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +24 -3
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	struct rte_eth_dev *dev;
 	struct rte_eth_dev_info dev_info;
 	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
 	int diag;
 	int ret;
+	uint16_t old_mtu;
 
 	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
 
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 		memcpy(&dev->data->dev_conf, dev_conf,
 		       sizeof(dev->data->dev_conf));
 
+	/* Backup mtu for rollback */
+	old_mtu = dev->data->mtu;
+
 	ret = rte_eth_dev_info_get(port_id, &dev_info);
 	if (ret != 0)
 		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
 	/* If number of queues specified by application for both Rx and Tx is
 	 * zero, use driver preferred values. This cannot be done individually
 	 * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 			goto rollback;
 		}
 	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+		    pktlen > RTE_ETHER_MTU + overhead_len)
 			/* Use default value */
 			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
+	}
+
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+		dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
 	}
 
 	/*
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	eth_dev_tx_queue_config(dev, 0);
 rollback:
 	memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf));
+	if (old_mtu != dev->data->mtu)
+		dev->data->mtu = old_mtu;
 
 	rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret);
 	return ret;
Signature · 1 line
2.17.1
#56 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 25 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

<...>

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1430

Quoted 13 lines
lib/librte_ethdev/rte_ethdev.c +4 -3
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  			goto rollback;
  		}
  	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+		    pktlen > RTE_ETHER_MTU + overhead_len)
  			/* Use default value */
  			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;

What do you think removing the above check, the else block, completely? Since the 'max_rx_pkt_len' should not be used when jumbo frame is not set.

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1437

Quoted 7 lines
lib/librte_ethdev/rte_ethdev.c +6 -0
+	}
+
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+		dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
  	}

Above if block has exact same check, why not move it above block?

#57 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 38 lines · Ferruh Yigit
Quoted 25 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,
app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522 ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496
Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

<...>

Quoted 9 lines
lib/librte_ethdev/rte_ethdev.c +2 -2
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
               goto rollback;
           }
       } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
Quoted 9 lines
Quoted 5 lines
lib/librte_ethdev/rte_ethdev.c +1 -0
+            pktlen > RTE_ETHER_MTU + overhead_len)
               /* Use default value */

              dev->data->dev_conf.rxmode.max_rx_pkt_len = -                            RTE_ETHER_MAX_LEN; +                        RTE_ETHER_MTU + overhead_len;

What do you think removing the above check, the else block, completely? Since the 'max_rx_pkt_len' should not be used when jumbo frame is not set.

As I tested removing this check is causing problem because some PMDs are using the 'max_rx_pkt_len' even jumbo frame is not set.

Perhaps better to keep it, and make a separate patch later to remove this check, after PMDs fixed.

Quoted 9 lines
Quoted 7 lines

+    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) { +        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len - +                overhead_len;
      }

Above if block has exact same check, why not move it above block?

Can you still send a new version for above change please?

#58 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 48 lines · Ferruh Yigit
Quoted 27 lines · Ferruh Yigit
Quoted 25 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

<...>

Quoted 15 lines

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1430

Quoted 13 lines
lib/librte_ethdev/rte_ethdev.c +4 -3
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
              goto rollback;
          }
      } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
              /* Use default value */
              dev->data->dev_conf.rxmode.max_rx_pkt_len =
-                            RTE_ETHER_MAX_LEN;
+                        RTE_ETHER_MTU + overhead_len;

What do you think removing the above check, the else block, completely? Since the 'max_rx_pkt_len' should not be used when jumbo frame is not set.

Quoted 3 lines

As I tested removing this check is causing problem because some PMDs are using the 'max_rx_pkt_len' even jumbo frame is not set.

Perhaps better to keep it, and make a separate patch later to remove this check, after PMDs fixed.

Hello Ferruh -
Working on fixing our PMD here. Do you want PMDs to update the JUMBO_FRAME flag based on the mtu value in dev_set_mtu(), or do you want the application to be solely responsible for it?

Thanks,
Andrew

Quoted 10 lines
Quoted 8 lines

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1437

Quoted 7 lines
lib/librte_ethdev/rte_ethdev.c +6 -0
+    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+                overhead_len;
      }

Above if block has exact same check, why not move it above block?

Can you still send a new version for above change please?

#59 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 49 lines · Andrew Boyer
Quoted 49 lines · On Jan 14, 2021, at 12:13 PM, Ferruh Yigit <[email protected]…
Quoted 43 lines · Ferruh Yigit
Quoted 25 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,
app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522 ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496
Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Signed-off-by Steve Yang <[email protected] <mailto:[email protected]>>

<...>

Quoted 11 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
 goto rollback;
 }
 } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
 /* Use default value */
Quoted 3 lines

dev->data->dev_conf.rxmode.max_rx_pkt_len =
-                            RTE_ETHER_MAX_LEN; +                        RTE_ETHER_MTU + overhead_len;

What do you think removing the above check, the else block, completely? Since the 'max_rx_pkt_len' should not be used when jumbo frame is not set.

Quoted 7 lines
Quoted 3 lines

As I tested removing this check is causing problem because some PMDs are using the 'max_rx_pkt_len' even jumbo frame is not set.

Perhaps better to keep it, and make a separate patch later to remove this check, after PMDs fixed.

Hello Ferruh -
Working on fixing our PMD here. Do you want PMDs to update the JUMBO_FRAME flag based on the mtu value in dev_set_mtu(), or do you want the application to be solely responsible for it?

Hi Andrew,

Technically JUMBO_FRAME flag is an user config and application should set it. It is application's responsibility to check the capability and set the flag when necessary.

But, after above said, many PMDs set it based on provided MTU value, if the explicitly requested MTU is bigger than the RTE_ETHER_MTU, this means user implied the JUMBO_FRAME support, for this case PMDs set the flag implicitly instead of failing.

In another thread Andrew R. & Konstantin suggested to remove the JUMBO_FRAME flag, since it is redundant and causing this kind of confusion, instead driver can decide based on requested MTU value, and driver reported 'max_mtu' value can be used by application to detect the capability. We will probably do this change, but it can be done only in the ABI break release, v21.11.

For now, PMD can set the flag itself if requested MTU > RTE_ETHER_MTU and driver supports jumbo frames.

Quoted 14 lines

Thanks,
Andrew

Quoted 10 lines
Quoted 8 lines
Quoted 7 lines

+    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) { +        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len - +                overhead_len;
}

Above if block has exact same check, why not move it above block?

Can you still send a new version for above change please?

#60 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

In reply to Steve Yang

Hi Steve
This is a very good job! But I have some question and suggestions. Please check it.

Quoted 52 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
  lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---
  1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +5 -0
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	struct rte_eth_dev *dev;
  	struct rte_eth_dev_info dev_info;
  	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
  	int diag;
  	int ret;
+	uint16_t old_mtu;
 
  	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
 
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  		memcpy(&dev->data->dev_conf, dev_conf,
  		       sizeof(dev->data->dev_conf));
 
+	/* Backup mtu for rollback */
+	old_mtu = dev->data->mtu;
+
  	ret = rte_eth_dev_info_get(port_id, &dev_info);

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1337

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -0
  	if (ret != 0)
  		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+

The Ethernet frame header length supported by each NIC may be different, which cause the difference of allowed packets size and drop you say. The diference of Ethernet frame header length have an impact for the maximum Ethernet frame length, which is a boundary value of enabling jumbo frame through the ' max_rx_pkt_len '.
However, we need to do the same thing you do above to get the overhead_len every time, which will
cause a lot of duplicate code in the framework and app. For examples, parsing and processing for '--max-pkt-len=xxx' parameter,
and " cmd_config_max_pkt_len_parsed " in testpmd, and here modifying
here dev_configure API.
It's a little redundant and troublesome.

Maybe, it is necessary for driver to directly report the supported maximum Ethernet frame length by rte_dev_info_get API. As following:

struct rte_eth_dev_info {
	xxxx
	/**
	 * The maximum Ethernet frame length supported by each
	 * driver varies with the Ethernet header length.
	 */
	uint16_t eth_max_len;
	xxxx
}

int
rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info)

{
    xxx
	dev_info->min_mtu = RTE_ETHER_MIN_MTU;
	dev_info->max_mtu = UINT16_MAX;
	dev_info->eth_max_len = RTE_ETHER_MAX_LEN;
    xxx
}

And then:
xxx_devv_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *info)

{
	xxx
	info->eth_max_len = xxx_ETHER_MAX _LEN;
	xxx
}

What do you think?

Quoted 13 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
  	/* If number of queues specified by application for both Rx and Tx is
  	 * zero, use driver preferred values. This cannot be done individually
  	 * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  			goto rollback;
  		}
  	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+		    pktlen > RTE_ETHER_MTU + overhead_len)
  			/* Use default value */

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q, · line 1437

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -1
  			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
+	}
+
+	/* Scale the MTU size to adapt max_rx_pkt_len */
+	if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+		dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
  	}

Now that we update mtu here when jumbo frame enabled. It is necessary to check validity of max_rx_pkt_len. As following:

if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
	if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen ||
		dev_conf->rxmode.max_rx_pkt_len <=  RTE_ETHER_MTU + overhead_len) {
			xxxx
		}
} else {

xxx
}

If it does not thing above, which will cause an unreasonable case. Like,
dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 1 dev_conf->rxmode.max_rx_pkt_len = 1500
overhead_len = 26
dev->data->mtu = dev_conf->rxmode.max_rx_pkt_len - overhead_len = 1500 - 26 = 1474

In fact, DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offloads when mtu > 1500.

Quoted 12 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
  	/*
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
  	eth_dev_tx_queue_config(dev, 0);
  rollback:
  	memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf));
+	if (old_mtu != dev->data->mtu)
+		dev->data->mtu = old_mtu;
 
  	rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret);
  	return ret;
#61 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 96 lines · oulijun

Hi Steve
This is a very good job! But I have some question and suggestions. Please check it.

Quoted 50 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,
app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522 ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496
Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

---
  lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---

  1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +5 -0
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
       struct rte_eth_dev *dev;
       struct rte_eth_dev_info dev_info;
       struct rte_eth_conf orig_conf;
+    uint16_t overhead_len;
       int diag;
       int ret;
+    uint16_t old_mtu;
       RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
           memcpy(&dev->data->dev_conf, dev_conf,
                  sizeof(dev->data->dev_conf));
+    /* Backup mtu for rollback */
+    old_mtu = dev->data->mtu;
+

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t · line 1336

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -0
       ret = rte_eth_dev_info_get(port_id, &dev_info);
       if (ret != 0)
           goto rollback;
+    /* Get the real Ethernet overhead length */
+    if (dev_info.max_mtu != UINT16_MAX &&
+        dev_info.max_rx_pktlen > dev_info.max_mtu)
+        overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+    else
+        overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+

The Ethernet frame header length supported by each NIC may be different, which cause the difference of allowed packets size and drop you say. The diference of Ethernet frame header length have an impact for the maximum Ethernet frame length, which is a boundary value of enabling jumbo frame through the ' max_rx_pkt_len '.
However, we need to do the same thing you do above to get the overhead_len every time, which will
cause a lot of duplicate code in the framework and app. For examples, parsing and processing for '--max-pkt-len=xxx' parameter,
 and " cmd_config_max_pkt_len_parsed " in testpmd, and here modifying here
dev_configure API.
It's a little redundant and troublesome.

Maybe, it is necessary for driver to directly report the supported maximum Ethernet frame length by rte_dev_info_get API. As following:
struct rte_eth_dev_info {
    xxxx
    /**
     * The maximum Ethernet frame length supported by each
     * driver varies with the Ethernet header length.
     */
    uint16_t eth_max_len;
    xxxx
}

int
rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info) {
    xxx
    dev_info->min_mtu = RTE_ETHER_MIN_MTU;
    dev_info->max_mtu = UINT16_MAX;
    dev_info->eth_max_len = RTE_ETHER_MAX_LEN;
    xxx
}

Quoted 8 lines

And then:
xxx_devv_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *info) {
    xxx
    info->eth_max_len = xxx_ETHER_MAX _LEN;
    xxx
}
What do you think?

Hi Lijun,

The 'max_mtu' has been added in the past to solve exact same problem, perhaps it would be better to add something like 'eth_max_len' at that time.

But as Steve mentioned we are planning to switch to more MTU based configuration, which should remove the need of the field you mentioned.

Quoted 21 lines
Quoted 21 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
       /* If number of queues specified by application for both Rx and Tx is
        * zero, use driver preferred values. This cannot be done individually
        * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
               goto rollback;
           }
       } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
               /* Use default value */

              dev->data->dev_conf.rxmode.max_rx_pkt_len = -                            RTE_ETHER_MAX_LEN;
+                        RTE_ETHER_MTU + overhead_len; +    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {

Quoted 8 lines
Quoted 3 lines

+        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len - +                overhead_len;
      }

Now that we update mtu here when jumbo frame enabled. It is necessary to check validity of max_rx_pkt_len. As following:
if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
    if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen || dev_conf->rxmode.max_rx_pkt_len <=  RTE_ETHER_MTU + overhead_len) {

It is not clear from API that if "max_rx_pkt_len <= RTE_ETHER_MTU + overhead_len" is a valid value or not, the API says:
"max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */"

But it doesn't say that when 'DEV_RX_OFFLOAD_JUMBO_FRAME' is set, 'max_rx_pkt_len' should be less then 'RTE_ETHER_MTU'

Quoted 6 lines

            xxxx
        }
} else {
        xxx
}

Quoted 7 lines

If it does not thing above, which will cause an unreasonable case. Like,
dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 1 dev_conf->rxmode.max_rx_pkt_len = 1500
overhead_len = 26
dev->data->mtu = dev_conf->rxmode.max_rx_pkt_len - overhead_len = 1500 - 26 = 1474

This looks correct, if the applicatin is requesting 'max_rx_pkt_len = 1500', the requeted MTU is 1474, if application wants an MTU as 1500, it should set the 'max_rx_pkt_len' as "1500 + overhead".

Quoted 1 line

In fact, DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offloads when mtu > 1500.

Overall the 'max_rx_pkt_len' setting is a little messy, it has been tried to fix in last release but we reverted them because of unexpected side affects.

Current long term plan is,
- Switch both 'rte_eth_dev_configure()' & 'rte_eth_dev_set_mtu()' to work on MTU values. (instead one working on frame lenght and other on MTU)
- Remove the 'DEV_RX_OFFLOAD_JUMBO_FRAME' and decide jumbo frame request by requested MTU value check
- App decide the jumbo frame capability from the 'max_mtu' check
- App calculate Ethernet overhead using 'max_mtu' and 'max_rx_pktlen'

Quoted 11 lines
Quoted 11 lines

      /*

lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
       eth_dev_tx_queue_config(dev, 0);

  rollback:
      memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf)); +    if (old_mtu != dev->data->mtu)
+        dev->data->mtu = old_mtu; rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret); return ret;

#62 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 145 lines · Ferruh Yigit
Quoted 96 lines · oulijun

Hi Steve
This is a very good job! But I have some question and suggestions. Please check it.

Quoted 50 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
  lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---
  1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +5 -0
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
      struct rte_eth_dev *dev;
      struct rte_eth_dev_info dev_info;
      struct rte_eth_conf orig_conf;
+    uint16_t overhead_len;
      int diag;
      int ret;
+    uint16_t old_mtu;
      RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
          memcpy(&dev->data->dev_conf, dev_conf,
                 sizeof(dev->data->dev_conf));
+    /* Backup mtu for rollback */
+    old_mtu = dev->data->mtu;
+

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1336

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -0
      ret = rte_eth_dev_info_get(port_id, &dev_info);
      if (ret != 0)
          goto rollback;
+    /* Get the real Ethernet overhead length */
+    if (dev_info.max_mtu != UINT16_MAX &&
+        dev_info.max_rx_pktlen > dev_info.max_mtu)
+        overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+    else
+        overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+

The Ethernet frame header length supported by each NIC may be different, which cause the difference of allowed packets size and drop you say. The diference of Ethernet frame header length have an impact for the maximum Ethernet frame length, which is a boundary value of enabling jumbo frame through the ' max_rx_pkt_len '.
However, we need to do the same thing you do above to get the overhead_len every time, which will
cause a lot of duplicate code in the framework and app. For examples, parsing and processing for '--max-pkt-len=xxx' parameter,
and " cmd_config_max_pkt_len_parsed " in testpmd, and here modifying
here dev_configure API.
It's a little redundant and troublesome.

Maybe, it is necessary for driver to directly report the supported maximum Ethernet frame length by rte_dev_info_get API. As following:

struct rte_eth_dev_info {
     xxxx
     /**
      * The maximum Ethernet frame length supported by each
      * driver varies with the Ethernet header length.
      */
     uint16_t eth_max_len;
     xxxx
}

int
rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info)

{
     xxx
     dev_info->min_mtu = RTE_ETHER_MIN_MTU;
     dev_info->max_mtu = UINT16_MAX;
     dev_info->eth_max_len = RTE_ETHER_MAX_LEN;
     xxx
}
Quoted 8 lines

And then:
xxx_devv_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *info)

{
     xxx
     info->eth_max_len = xxx_ETHER_MAX _LEN;
     xxx
}

What do you think?

Hi Lijun,

The 'max_mtu' has been added in the past to solve exact same problem, perhaps it would be better to add something like 'eth_max_len' at that time.

But as Steve mentioned we are planning to switch to more MTU based configuration, which should remove the need of the field you mentioned.

Quoted 28 lines
Quoted 16 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
      /* If number of queues specified by application for both Rx and 

Tx is
* zero, use driver preferred values. This cannot be done
individually
* as it is valid for either Tx or Rx (but not both) to be zero.

lib/librte_ethdev/rte_ethdev.c +3 -2
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
              goto rollback;
          }
      } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
              /* Use default value */

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1438

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -1
              dev->data->dev_conf.rxmode.max_rx_pkt_len =
-                            RTE_ETHER_MAX_LEN;
+                        RTE_ETHER_MTU + overhead_len;
+    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+                overhead_len;
      }

Now that we update mtu here when jumbo frame enabled. It is necessary to check validity of max_rx_pkt_len. As following:

Quoted 4 lines
if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
     if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen ||
         dev_conf->rxmode.max_rx_pkt_len <=  RTE_ETHER_MTU + 

overhead_len) {

Quoted 5 lines

It is not clear from API that if "max_rx_pkt_len <= RTE_ETHER_MTU + overhead_len" is a valid value or not, the API says:
"max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */"

But it doesn't say that when 'DEV_RX_OFFLOAD_JUMBO_FRAME' is set, 'max_rx_pkt_len' should be less then 'RTE_ETHER_MTU'

The MTU setting entry does need to be adjusted. I agree! But I think this place should be modified, and it's probably more reasonable.

Generally speaking, max_rx_pkt_len will be also updated with 'mtu + overhead_len' also when application sets mtu > 1500, which means JUMBO_FRAME is enabled. Namely, JUMBO_FRAME is enabled based on mtu > 1500 or max_rx_pkt_len > 1500 + overhead_len.
Besides, having following check for "rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 0":
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,

              goto rollback;
          }
      } else {
        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
            pktlen > RTE_ETHER_MTU + overhead_len)
              /* Use default value */
              dev->data->dev_conf.rxmode.max_rx_pkt_len =
                        RTE_ETHER_MTU + overhead_len;
}

One of check condition for the branch is "pktlen > RTE_ETHER_MTU + overhead_len ".

In view of the above two aspects, when application set DEV_RX_OFFLOAD_JUMBO_FRAME in offload, the max_rx_pkt_len must be greater than " RTE_ETHER_MTU + overhead_len "

Since DEV_RX_OFFLOAD_JUMBO_FRAME is not removed, so the check is necessary.

Quoted 47 lines
Quoted 6 lines
             xxxx
         }
} else {

xxx
}

Quoted 8 lines

If it does not thing above, which will cause an unreasonable case. Like,
dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 1 dev_conf->rxmode.max_rx_pkt_len = 1500
overhead_len = 26
dev->data->mtu = dev_conf->rxmode.max_rx_pkt_len - overhead_len = 1500
- 26 = 1474

This looks correct, if the applicatin is requesting 'max_rx_pkt_len = 1500', the requeted MTU is 1474, if application wants an MTU as 1500, it should set the 'max_rx_pkt_len' as "1500 + overhead".

Quoted 2 lines

In fact, DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offloads when mtu

Quoted 1 line

1500.

Overall the 'max_rx_pkt_len' setting is a little messy, it has been tried to fix in last release but we reverted them because of unexpected side affects.

Current long term plan is,
- Switch both 'rte_eth_dev_configure()' & 'rte_eth_dev_set_mtu()' to work on MTU values. (instead one working on frame lenght and other on MTU)
- Remove the 'DEV_RX_OFFLOAD_JUMBO_FRAME' and decide jumbo frame request by requested MTU value check
- App decide the jumbo frame capability from the 'max_mtu' check
- App calculate Ethernet overhead using 'max_mtu' and 'max_rx_pktlen'

Quoted 5 lines
Quoted 5 lines
      /*
lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
      eth_dev_tx_queue_config(dev, 0);
  rollback:
Quoted 8 lines
Quoted 8 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
      memcpy(&dev->data->dev_conf, &orig_conf, 
 sizeof(dev->data->dev_conf));
+    if (old_mtu != dev->data->mtu)
+        dev->data->mtu = old_mtu;
      rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, 
ret);
      return ret;

.

#63 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

Quoted 172 lines · oulijun
Quoted 145 lines · Ferruh Yigit
Quoted 96 lines · oulijun

Hi Steve
This is a very good job! But I have some question and suggestions. Please check it.

Quoted 50 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
---
  lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---
  1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +5 -0
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
      struct rte_eth_dev *dev;
      struct rte_eth_dev_info dev_info;
      struct rte_eth_conf orig_conf;
+    uint16_t overhead_len;
      int diag;
      int ret;
+    uint16_t old_mtu;
      RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
          memcpy(&dev->data->dev_conf, dev_conf,
                 sizeof(dev->data->dev_conf));
+    /* Backup mtu for rollback */
+    old_mtu = dev->data->mtu;
+

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1336

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -0
      ret = rte_eth_dev_info_get(port_id, &dev_info);
      if (ret != 0)
          goto rollback;
+    /* Get the real Ethernet overhead length */
+    if (dev_info.max_mtu != UINT16_MAX &&
+        dev_info.max_rx_pktlen > dev_info.max_mtu)
+        overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+    else
+        overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+

The Ethernet frame header length supported by each NIC may be different, which cause the difference of allowed packets size and drop you say. The diference of Ethernet frame header length have an impact for the maximum Ethernet frame length, which is a boundary value of enabling jumbo frame through the ' max_rx_pkt_len '.
However, we need to do the same thing you do above to get the overhead_len every time, which will
cause a lot of duplicate code in the framework and app. For examples, parsing and processing for '--max-pkt-len=xxx' parameter,
and " cmd_config_max_pkt_len_parsed " in testpmd, and here
modifying here dev_configure API.
It's a little redundant and troublesome.

Maybe, it is necessary for driver to directly report the supported maximum Ethernet frame length by rte_dev_info_get API. As following:

struct rte_eth_dev_info {
     xxxx
     /**
      * The maximum Ethernet frame length supported by each
      * driver varies with the Ethernet header length.
      */
     uint16_t eth_max_len;
     xxxx
}

int
rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info)

{
     xxx
     dev_info->min_mtu = RTE_ETHER_MIN_MTU;
     dev_info->max_mtu = UINT16_MAX;
     dev_info->eth_max_len = RTE_ETHER_MAX_LEN;
     xxx
}
Quoted 8 lines

And then:
xxx_devv_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *info)

{
     xxx
     info->eth_max_len = xxx_ETHER_MAX _LEN;
     xxx
}

What do you think?

Hi Lijun,

The 'max_mtu' has been added in the past to solve exact same problem, perhaps it would be better to add something like 'eth_max_len' at that time.

But as Steve mentioned we are planning to switch to more MTU based configuration, which should remove the need of the field you mentioned.

Quoted 28 lines
Quoted 16 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
      /* If number of queues specified by application for both Rx 

and Tx is
* zero, use driver preferred values. This cannot be done
individually
* as it is valid for either Tx or Rx (but not both) to be zero.

lib/librte_ethdev/rte_ethdev.c +3 -2
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
              goto rollback;
          }
      } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
              /* Use default value */

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, · line 1438

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -1
              dev->data->dev_conf.rxmode.max_rx_pkt_len =
-                            RTE_ETHER_MAX_LEN;
+                        RTE_ETHER_MTU + overhead_len;
+    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
+        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+                overhead_len;
      }

Now that we update mtu here when jumbo frame enabled. It is necessary to check validity of max_rx_pkt_len. As following:

Quoted 4 lines
if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
     if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen ||
         dev_conf->rxmode.max_rx_pkt_len <=  RTE_ETHER_MTU + 

overhead_len) {

Quoted 5 lines

It is not clear from API that if "max_rx_pkt_len <= RTE_ETHER_MTU + overhead_len" is a valid value or not, the API says:
"max_rx_pkt_len; /**< Only used if JUMBO_FRAME enabled. */"

But it doesn't say that when 'DEV_RX_OFFLOAD_JUMBO_FRAME' is set, 'max_rx_pkt_len' should be less then 'RTE_ETHER_MTU'

The MTU setting entry does need to be adjusted. I agree! But I think this place should be modified, and it's probably more reasonable.

Generally speaking, max_rx_pkt_len will be also updated with 'mtu + overhead_len' also when application sets mtu > 1500, which means JUMBO_FRAME is enabled. Namely, JUMBO_FRAME is enabled based on mtu > 1500 or max_rx_pkt_len > 1500 + overhead_len.
Besides, having following check for "rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 0":

lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
               goto rollback;
           }
       } else {
         uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
         if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
             pktlen > RTE_ETHER_MTU + overhead_len)
               /* Use default value */
               dev->data->dev_conf.rxmode.max_rx_pkt_len =
                         RTE_ETHER_MTU + overhead_len;
 }

One of check condition for the branch is "pktlen > RTE_ETHER_MTU + overhead_len ".

Quoted 22 lines

In view of the above two aspects, when application set DEV_RX_OFFLOAD_JUMBO_FRAME in offload, the max_rx_pkt_len must be greater than " RTE_ETHER_MTU + overhead_len "

Since DEV_RX_OFFLOAD_JUMBO_FRAME is not removed, so the check is necessary.

Quoted 18 lines
Quoted 6 lines
             xxxx
         }
} else {

xxx
}

Quoted 7 lines

If it does not thing above, which will cause an unreasonable case. Like,
dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 1 dev_conf->rxmode.max_rx_pkt_len = 1500
overhead_len = 26
dev->data->mtu = dev_conf->rxmode.max_rx_pkt_len - overhead_len = 1500 - 26 = 1474

This looks correct, if the applicatin is requesting 'max_rx_pkt_len = 1500', the requeted MTU is 1474, if application wants an MTU as 1500, it should set the 'max_rx_pkt_len' as "1500 + overhead".

Quoted 1 line

In fact, DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offloads when mtu > 1500.

Now that there are two interfaces for modifying MTU, namely, 'rte_eth_dev_configure()' & 'rte_eth_dev_set_mtu()'. They modify MTU based on 'max_rx_pkt_len' and 'mtu' value, respectively. The 'max_rx_pkt_len' field has been used
in xxx_dev_configure ops in many PMD drivers. In addition, if
'DEV_RX_OFFLOAD_JUMBO_FRAME' is set, the value of
'max_rx_pkt_len' is also verified by using max_rx_pktlen and RTE_ETHER_MTU + overhead_len in i40e and ice driver.

Currently, DEV_RX_OFFLOAD_JUMBO_FRAME has not been removed, so it is necessary and reasonable
to check 'max_rx_pkt_len' in 'rte_eth_dev_configure()'.

Please check it again. Looking forward to your reply.

Quoted 29 lines
Quoted 11 lines

Overall the 'max_rx_pkt_len' setting is a little messy, it has been tried to fix in last release but we reverted them because of unexpected side affects.

Current long term plan is,
- Switch both 'rte_eth_dev_configure()' & 'rte_eth_dev_set_mtu()' to work on MTU values. (instead one working on frame lenght and other on MTU)
- Remove the 'DEV_RX_OFFLOAD_JUMBO_FRAME' and decide jumbo frame request by requested MTU value check
- App decide the jumbo frame capability from the 'max_mtu' check
- App calculate Ethernet overhead using 'max_mtu' and 'max_rx_pktlen'

Quoted 16 lines
Quoted 5 lines
Quoted 5 lines
lib/librte_ethdev/rte_ethdev.c +0 -0
      /*
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, 
 uint16_t nb_rx_q, uint16_t nb_tx_q,
      eth_dev_tx_queue_config(dev, 0);
  rollback:
Quoted 8 lines
Quoted 8 lines
lib/librte_ethdev/rte_ethdev.c +2 -0
      memcpy(&dev->data->dev_conf, &orig_conf, 
 sizeof(dev->data->dev_conf));
+    if (old_mtu != dev->data->mtu)
+        dev->data->mtu = old_mtu;
      rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, 
dev_conf, ret);
      return ret;

.

.

#64 lore raw

Re: [dpdk-dev] [PATCH v3 01/22] ethdev: fix MTU size exceeds max rx packet length

In reply to oulijun
Quoted 168 lines · oulijun
Quoted 141 lines · Ferruh Yigit
Quoted 95 lines · oulijun

Hi Steve
This is a very good job! But I have some question and suggestions. Please check it.

Quoted 50 lines · Steve Yang

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,
app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522 ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496
Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")

---
  lib/librte_ethdev/rte_ethdev.c | 27 ++++++++++++++++++++++++---

  1 file changed, 24 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +5 -0
index 17ddacc78d..19ca4c4512 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
       struct rte_eth_dev *dev;
       struct rte_eth_dev_info dev_info;
       struct rte_eth_conf orig_conf;
+    uint16_t overhead_len;
       int diag;
       int ret;
+    uint16_t old_mtu;
       RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
           memcpy(&dev->data->dev_conf, dev_conf,
                  sizeof(dev->data->dev_conf));
+    /* Backup mtu for rollback */
+    old_mtu = dev->data->mtu;
+

lib/librte_ethdev/rte_ethdev.c rte_eth_dev_configure(uint16_t port_id, uint16_t · line 1336

Quoted 10 lines
lib/librte_ethdev/rte_ethdev.c +7 -0
       ret = rte_eth_dev_info_get(port_id, &dev_info);
       if (ret != 0)
           goto rollback;
+    /* Get the real Ethernet overhead length */
+    if (dev_info.max_mtu != UINT16_MAX &&
+        dev_info.max_rx_pktlen > dev_info.max_mtu)
+        overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+    else
+        overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+

The Ethernet frame header length supported by each NIC may be different, which cause the difference of allowed packets size and drop you say. The diference of Ethernet frame header length have an impact for the maximum Ethernet frame length, which is a boundary value of enabling jumbo frame through the ' max_rx_pkt_len '.
However, we need to do the same thing you do above to get the overhead_len every time, which will
cause a lot of duplicate code in the framework and app. For examples, parsing and processing for '--max-pkt-len=xxx' parameter, and " cmd_config_max_pkt_len_parsed " in testpmd, and here modifying here dev_configure API.
It's a little redundant and troublesome.

Maybe, it is necessary for driver to directly report the supported maximum Ethernet frame length by rte_dev_info_get API. As following:
struct rte_eth_dev_info {
     xxxx
     /**
      * The maximum Ethernet frame length supported by each
      * driver varies with the Ethernet header length.
      */
     uint16_t eth_max_len;
     xxxx
}

int
rte_eth_dev_info_get(uint16_t port_id, struct rte_eth_dev_info *dev_info) {
     xxx
     dev_info->min_mtu = RTE_ETHER_MIN_MTU;
     dev_info->max_mtu = UINT16_MAX;
     dev_info->eth_max_len = RTE_ETHER_MAX_LEN;
     xxx
}

Quoted 8 lines

And then:
xxx_devv_infos_get(struct rte_eth_dev *eth_dev, struct rte_eth_dev_info *info) {
     xxx
     info->eth_max_len = xxx_ETHER_MAX _LEN;
     xxx
}
What do you think?

Hi Lijun,

The 'max_mtu' has been added in the past to solve exact same problem, perhaps it would be better to add something like 'eth_max_len' at that time.

But as Steve mentioned we are planning to switch to more MTU based configuration, which should remove the need of the field you mentioned.

Quoted 21 lines
Quoted 21 lines
lib/librte_ethdev/rte_ethdev.c +3 -2
       /* If number of queues specified by application for both Rx and Tx is
        * zero, use driver preferred values. This cannot be done individually
        * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
               goto rollback;
           }
       } else {
-        if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-            dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+        uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+        if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+            pktlen > RTE_ETHER_MTU + overhead_len)
               /* Use default value */

              dev->data->dev_conf.rxmode.max_rx_pkt_len = -                            RTE_ETHER_MAX_LEN;
+                        RTE_ETHER_MTU + overhead_len; +    }
+
+    /* Scale the MTU size to adapt max_rx_pkt_len */
+    if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {

Quoted 8 lines
Quoted 3 lines

+        dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len - +                overhead_len;
      }

Now that we update mtu here when jumbo frame enabled. It is necessary to check validity of max_rx_pkt_len. As following:
if (dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
     if (dev_conf->rxmode.max_rx_pkt_len > dev_info.max_rx_pktlen || dev_conf->rxmode.max_rx_pkt_len <=  RTE_ETHER_MTU + overhead_len) {

Quoted 5 lines

It is not clear from API that if "max_rx_pkt_len <=  RTE_ETHER_MTU + overhead_len" is a valid value or not, the API says:
"max_rx_pkt_len;  /**< Only used if JUMBO_FRAME enabled. */"

But it doesn't say that when 'DEV_RX_OFFLOAD_JUMBO_FRAME' is set, 'max_rx_pkt_len' should be less then 'RTE_ETHER_MTU'

The MTU setting entry does need to be adjusted. I agree! But I think this place should be modified, and it's probably more reasonable.

Generally speaking, max_rx_pkt_len will be also updated with 'mtu + overhead_len' also when application sets mtu > 1500, which means JUMBO_FRAME is enabled. Namely, JUMBO_FRAME is enabled based on mtu > 1500 or max_rx_pkt_len > 1500 + overhead_len.
Besides, having following check for "rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 0":

lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1410,11 +1422,18 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
               goto rollback;
           }
       } else {
         uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
         if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
             pktlen > RTE_ETHER_MTU + overhead_len)
               /* Use default value */
               dev->data->dev_conf.rxmode.max_rx_pkt_len =
                         RTE_ETHER_MTU + overhead_len;
 }

One of check condition for the branch is "pktlen > RTE_ETHER_MTU + overhead_len ".

Quoted 2 lines

In view of the above two aspects, when application set DEV_RX_OFFLOAD_JUMBO_FRAME in offload, the max_rx_pkt_len must be greater than " RTE_ETHER_MTU + overhead_len "

Hi Lijun,

Most probably intention was like you said, but that is not implemented or documented that way.

The API doc only says 'max_rx_pkt_len' is valid only when 'JUMBO_FRAME' is set, but it doesn't say what is the valid range.

And when 'JUMBO_FRAME' is set, the check in the 'rte_eth_dev_configure()' is same from the beggining of the project, and it is between 'RTE_ETHER_MIN_LEN' to 'dev_info.max_rx_pktlen', and changing it will be the behaviour change.

So I suggest lets not add this new config restriction, but it is application's responsiblity to set/unset the 'JUMBO_FRAME' flag based on the packet size, and we can implemet this in the testpmd.

Quoted 45 lines

Since DEV_RX_OFFLOAD_JUMBO_FRAME is not removed, so the check is necessary.

Quoted 43 lines
Quoted 6 lines

             xxxx
         }
} else {
         xxx
}

Quoted 7 lines

If it does not thing above, which will cause an unreasonable case. Like,
dev_conf->rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME == 1 dev_conf->rxmode.max_rx_pkt_len = 1500
overhead_len = 26
dev->data->mtu = dev_conf->rxmode.max_rx_pkt_len - overhead_len = 1500 - 26 = 1474

This looks correct, if the applicatin is requesting 'max_rx_pkt_len = 1500', the requeted MTU is 1474, if application wants an MTU as 1500, it should set the 'max_rx_pkt_len' as "1500 + overhead".

Quoted 1 line

In fact, DEV_RX_OFFLOAD_JUMBO_FRAME is set to rxmode.offloads when mtu > 1500.

Overall the 'max_rx_pkt_len' setting is a little messy, it has been tried to fix in last release but we reverted them because of unexpected side affects.

Current long term plan is,
- Switch both 'rte_eth_dev_configure()' & 'rte_eth_dev_set_mtu()' to work on MTU values. (instead one working on frame lenght and other on MTU)
- Remove the 'DEV_RX_OFFLOAD_JUMBO_FRAME' and decide jumbo frame request by requested MTU value check
- App decide the jumbo frame capability from the 'max_mtu' check
- App calculate Ethernet overhead using 'max_mtu' and 'max_rx_pktlen'

Quoted 11 lines
Quoted 11 lines

      /*

lib/librte_ethdev/rte_ethdev.c +0 -0
@@ -1549,6 +1568,8 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t 
 nb_rx_q, uint16_t nb_tx_q,
       eth_dev_tx_queue_config(dev, 0);

  rollback:
      memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf)); +    if (old_mtu != dev->data->mtu)
+        dev->data->mtu = old_mtu; rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret); return ret;

.

author
#65 lore raw

v4 cover fix rx packets dropped issue

In reply to Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Following scopes perhaps will be impacted:
- the cases of jumbo frame related;
- the logic of 'max_rx_pkt_len' and 'mtu' related;
- the using place of 'RTE_ETHER_MAX_LEN';

---
v4:
- moved mtu assignment to the same if-true-block of jumbo frame;
v3:
- removed redundant if-conditions in rte_ethdev and testpmd;
- adjusted the alignment style;
- added offload check before updating mtu;
v2:
- defined the 'RTE_ETHER_MTU + overhead' to 'driver_ETH_MAX_LEN';
- changed the 'mtu > RTE_ETHER_MTU' to 'frame_size > driver_ETH_MAX_LEN';
---

Steve Yang (22):
ethdev: fix MTU size exceeds max rx packet length app/testpmd: fix max rx packet length for VLAN packets net/dpaa: fix the jumbo frame flag condition for mtu set net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set net/thunderx: fix the jumbo frame flag condition for mtu set net/ixgbe: fix the jumbo frame flag condition net/cxgbe: fix the jumbo frame flag condition net/axgbe: fix the jumbo frame flag condition for mtu set net/enetc: fix the jumbo frame flag condition for mtu set net/hinic: fix the jumbo frame flag condition for mtu set net/nfp: fix the jumbo frame flag condition for mtu set net/liquidio: fix the jumbo frame flag condition for mtu set

 app/test-pmd/cmdline.c                    |  6 ------
 app/test-pmd/config.c                     |  2 +-
 app/test-pmd/parameters.c                 |  7 ++-----
 app/test-pmd/testpmd.c                    | 18 ++++++++++++++++
 drivers/net/axgbe/axgbe_ethdev.c          |  2 +-
 drivers/net/axgbe/axgbe_ethdev.h          |  6 ++++++
 drivers/net/cxgbe/cxgbe.h                 |  4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c          |  4 ++--
 drivers/net/dpaa/dpaa_ethdev.c            |  2 +-
 drivers/net/dpaa/dpaa_ethdev.h            |  4 ++++
 drivers/net/dpaa2/dpaa2_ethdev.c          |  2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h          |  4 ++++
 drivers/net/e1000/e1000_ethdev.h          |  2 +-
 drivers/net/e1000/em_ethdev.c             |  5 ++---
 drivers/net/e1000/igb_ethdev.c            |  2 +-
 drivers/net/enetc/enetc.h                 |  4 ++++
 drivers/net/enetc/enetc_ethdev.c          |  2 +-
 drivers/net/hinic/hinic_pmd_ethdev.c      |  5 ++++-
 drivers/net/hns3/hns3_ethdev.c            |  2 +-
 drivers/net/hns3/hns3_ethdev_vf.c         |  2 +-
 drivers/net/i40e/i40e_ethdev.c            |  2 +-
 drivers/net/i40e/i40e_ethdev.h            |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c         | 10 ++++-----
 drivers/net/i40e/i40e_fdir.c              |  2 +-
 drivers/net/i40e/i40e_rxtx.c              |  8 ++++----
 drivers/net/iavf/iavf.h                   |  1 +
 drivers/net/iavf/iavf_ethdev.c            | 10 ++++-----
 drivers/net/ice/ice_dcf_ethdev.c          |  8 ++++----
 drivers/net/ice/ice_ethdev.c              |  2 +-
 drivers/net/ice/ice_ethdev.h              |  1 +
 drivers/net/ice/ice_rxtx.c                | 10 ++++-----
 drivers/net/ipn3ke/ipn3ke_ethdev.h        |  1 +
 drivers/net/ipn3ke/ipn3ke_representor.c   |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.c          |  2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h          |  3 +++
 drivers/net/ixgbe/ixgbe_pf.c              |  2 +-
 drivers/net/liquidio/lio_ethdev.c         |  2 +-
 drivers/net/liquidio/lio_ethdev.h         |  3 +++
 drivers/net/nfp/nfp_net.c                 |  2 +-
 drivers/net/octeontx/octeontx_ethdev.c    |  2 +-
 drivers/net/octeontx/octeontx_ethdev.h    |  1 +
 drivers/net/octeontx2/otx2_ethdev.h       |  2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c   |  2 +-
 drivers/net/qede/qede_ethdev.c            |  2 +-
 drivers/net/qede/qede_rxtx.h              |  1 +
 drivers/net/sfc/sfc_ethdev.c              |  2 +-
 drivers/net/thunderx/base/nicvf_hw_defs.h |  1 +
 drivers/net/thunderx/nicvf_ethdev.c       |  2 +-
 lib/librte_ethdev/rte_ethdev.c            | 25 ++++++++++++++++++++---
 49 files changed, 132 insertions(+), 65 deletions(-)
Signature · 1 line
2.17.1
author
#66 lore raw

PATCH v4 1/22 ethdev: fix MTU size exceeds max rx packet length

Ethdev is using default Ethernet overhead to decide if provided 'max_rx_pkt_len' value is bigger than max (non jumbo) MTU value, and limits it to MAX if it is.

Since the application/driver used Ethernet overhead is different than the ethdev one, check result is wrong.

If the driver is using Ethernet overhead bigger than the default one, the provided 'max_rx_pkt_len' is trimmed down, and in the driver when correct Ethernet overhead is used to convert back, the resulting MTU is less than the intended one, causing some packets to be dropped.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

The fix is to make ethdev use the correct Ethernet overhead for port, instead of default one.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Cc Thomas Monjalon <[email protected]>
Cc Ferruh Yigit <[email protected]>
Cc Andrew Rybchenko <[email protected]>
---
 lib/librte_ethdev/rte_ethdev.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)
lib/librte_ethdev/rte_ethdev.c +22 -3
index 17ddacc78d..71e1e9a6db 100644
@@ -1292,8 +1292,10 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	struct rte_eth_dev *dev;
 	struct rte_eth_dev_info dev_info;
 	struct rte_eth_conf orig_conf;
+	uint16_t overhead_len;
 	int diag;
 	int ret;
+	uint16_t old_mtu;
 
 	RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -ENODEV);
 
@@ -1319,10 +1321,20 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 		memcpy(&dev->data->dev_conf, dev_conf,
 		       sizeof(dev->data->dev_conf));
 
+	/* Backup mtu for rollback */
+	old_mtu = dev->data->mtu;
+
 	ret = rte_eth_dev_info_get(port_id, &dev_info);
 	if (ret != 0)
 		goto rollback;
 
+	/* Get the real Ethernet overhead length */
+	if (dev_info.max_mtu != UINT16_MAX &&
+	    dev_info.max_rx_pktlen > dev_info.max_mtu)
+		overhead_len = dev_info.max_rx_pktlen - dev_info.max_mtu;
+	else
+		overhead_len = RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
 	/* If number of queues specified by application for both Rx and Tx is
 	 * zero, use driver preferred values. This cannot be done individually
 	 * as it is valid for either Tx or Rx (but not both) to be zero.
@@ -1409,12 +1421,17 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 			ret = -EINVAL;
 			goto rollback;
 		}
+
+		/* Scale the MTU size to adapt max_rx_pkt_len */
+		dev->data->mtu = dev->data->dev_conf.rxmode.max_rx_pkt_len -
+				overhead_len;
 	} else {
-		if (dev_conf->rxmode.max_rx_pkt_len < RTE_ETHER_MIN_LEN ||
-			dev_conf->rxmode.max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+		uint16_t pktlen = dev_conf->rxmode.max_rx_pkt_len;
+		if (pktlen < RTE_ETHER_MIN_MTU + overhead_len ||
+		    pktlen > RTE_ETHER_MTU + overhead_len)
 			/* Use default value */
 			dev->data->dev_conf.rxmode.max_rx_pkt_len =
-							RTE_ETHER_MAX_LEN;
+						RTE_ETHER_MTU + overhead_len;
 	}
 
 	/*
@@ -1549,6 +1566,8 @@ rte_eth_dev_configure(uint16_t port_id, uint16_t nb_rx_q, uint16_t nb_tx_q,
 	eth_dev_tx_queue_config(dev, 0);
 rollback:
 	memcpy(&dev->data->dev_conf, &orig_conf, sizeof(dev->data->dev_conf));
+	if (old_mtu != dev->data->mtu)
+		dev->data->mtu = old_mtu;
 
 	rte_ethdev_trace_configure(port_id, nb_rx_q, nb_tx_q, dev_conf, ret);
 	return ret;
Signature · 1 line
2.17.1
author
#67 lore raw

PATCH v4 2/22 app/testpmd: fix max rx packet length for VLAN packets

In reply to Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
Cc Wenzhuo Lu <[email protected]>
Cc Beilei Xing <[email protected]>
Cc Bernard Iremonger <[email protected]>
---
 app/test-pmd/cmdline.c    |  6 ------
 app/test-pmd/config.c     |  2 +-
 app/test-pmd/parameters.c |  7 ++-----
 app/test-pmd/testpmd.c    | 18 ++++++++++++++++++
 4 files changed, 21 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
 	RTE_ETH_FOREACH_DEV(pid) {
 		struct rte_port *port = &ports[pid];
-		uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
 		if (!strcmp(res->name, "max-pkt-len")) {
 			if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 				return;
 
 			port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-			if (res->value > RTE_ETHER_MAX_LEN)
-				rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-			else
-				rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-			port->dev_conf.rxmode.offloads = rx_offloads;
 		} else {
 			printf("Unknown parameter\n");
 			return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
 		 * device supports jumbo frame.
 		 */
 		eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-		if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+		if (mtu > RTE_ETHER_MTU) {
 			rte_port->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 			rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
 			}
 			if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
 				n = atoi(optarg);
-				if (n >= RTE_ETHER_MIN_LEN) {
+				if (n >= RTE_ETHER_MIN_LEN)
 					rx_mode.max_rx_pkt_len = (uint32_t) n;
-					if (n > RTE_ETHER_MAX_LEN)
-						rx_offloads |=
-							DEV_RX_OFFLOAD_JUMBO_FRAME;
-				} else
+				else
 					rte_exit(EXIT_FAILURE,
 						 "Invalid max-pkt-len=%d - should be > %d\n",
 						 n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +18 -0
index 2b60f6c5d3..c256e719ae 100644
@@ -1410,6 +1410,7 @@ init_config(void)
 	struct rte_gro_param gro_param;
 	uint32_t gso_types;
 	uint16_t data_size;
+	uint16_t eth_overhead;
 	bool warning = 0;
 	int k;
 	int ret;
@@ -1446,6 +1447,23 @@ init_config(void)
 			rte_exit(EXIT_FAILURE,
 				 "rte_eth_dev_info_get() failed\n");
 
+		/* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+		if (port->dev_info.max_mtu != UINT16_MAX &&
+		    port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+			eth_overhead = port->dev_info.max_rx_pktlen -
+				port->dev_info.max_mtu;
+		else
+			eth_overhead =
+				RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+		if (port->dev_conf.rxmode.max_rx_pkt_len <=
+			(uint32_t)(RTE_ETHER_MTU + eth_overhead))
+			port->dev_conf.rxmode.max_rx_pkt_len =
+					RTE_ETHER_MTU + eth_overhead;
+		else
+			port->dev_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_JUMBO_FRAME;
+
 		if (!(port->dev_info.tx_offload_capa &
 		      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
 			port->dev_conf.txmode.offloads &=
Signature · 1 line
2.17.1
#68 lore raw

Re: [dpdk-dev] [PATCH v4 02/22] app/testpmd: fix max rx packet length for VLAN packets

Quoted 119 lines · Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
Cc Wenzhuo Lu <[email protected]>
Cc Beilei Xing <[email protected]>
Cc Bernard Iremonger <[email protected]>
---
 app/test-pmd/cmdline.c    |  6 ------
 app/test-pmd/config.c     |  2 +-
 app/test-pmd/parameters.c |  7 ++-----
 app/test-pmd/testpmd.c    | 18 ++++++++++++++++++
 4 files changed, 21 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
        RTE_ETH_FOREACH_DEV(pid) {
                struct rte_port *port = &ports[pid];
-               uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
                if (!strcmp(res->name, "max-pkt-len")) {
                        if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
                                return;
 
                        port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-                       if (res->value > RTE_ETHER_MAX_LEN)
-                               rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       else
-                               rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       port->dev_conf.rxmode.offloads = rx_offloads;
                } else {
                        printf("Unknown parameter\n");
                        return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
                 * device supports jumbo frame.
                 */
                eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-               if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+               if (mtu > RTE_ETHER_MTU) {
                        rte_port->dev_conf.rxmode.offloads |=
                                                DEV_RX_OFFLOAD_JUMBO_FRAME;
                        rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
                        }
                        if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
                                n = atoi(optarg);
-                               if (n >= RTE_ETHER_MIN_LEN) {
+                               if (n >= RTE_ETHER_MIN_LEN)
                                        rx_mode.max_rx_pkt_len = (uint32_t) n;
-                                       if (n > RTE_ETHER_MAX_LEN)
-                                               rx_offloads |=
-                                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
-                               } else
+                               else
                                        rte_exit(EXIT_FAILURE,
                                                 "Invalid max-pkt-len=%d - should be > %d\n",
                                                 n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +18 -1
index 2b60f6c5d3..c256e719ae 100644
@@ -1410,6 +1410,7 @@ init_config(void)
        struct rte_gro_param gro_param;
        uint32_t gso_types;
        uint16_t data_size;
+       uint16_t eth_overhead;
        bool warning = 0;
        int k;
        int ret;
@@ -1446,6 +1447,23 @@ init_config(void)
                        rte_exit(EXIT_FAILURE,
                                 "rte_eth_dev_info_get() failed\n");
 
+               /* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+               if (port->dev_info.max_mtu != UINT16_MAX &&
+                   port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+                       eth_overhead = port->dev_info.max_rx_pktlen -
+                               port->dev_info.max_mtu;
+               else
+                       eth_overhead =
+                               RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+               if (port->dev_conf.rxmode.max_rx_pkt_len <=
+                       (uint32_t)(RTE_ETHER_MTU + eth_overhead))
+                       port->dev_conf.rxmode.max_rx_pkt_len =
+                                       RTE_ETHER_MTU + eth_overhead;
+               else
+                       port->dev_conf.rxmode.offloads |=
+                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
+
                if (!(port->dev_info.tx_offload_capa &
                      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
                        port->dev_conf.txmode.offloads &=
--
Quoted 2 lines

2.17.1

Moving the setting of DEV_RX_OFFLOAD_JUMBO_FRAME from cmd_config_max_pkt_len_parsed() to init_config() doesn't seem to be correct for the case where max_rx_pkt_len is changed from the command line via "port config all max-pkt-len".

The init_config() function is only called when testpmd is started, but the DEV_RX_OFFLOAD_JUMBO_FRAME setting needs to
be recomputed whenever max_rx_pkt_len changes.

(Of course this won't matter when DEV_RX_OFFLOAD_JUMBO_FRAME is removed, which seems like a great idea, but for now this is impacting some test automation with 21.02-rc1.)

#69 lore raw

Re: [dpdk-dev] [PATCH v4 02/22] app/testpmd: fix max rx packet length for VLAN packets

Quoted 129 lines · Lance Richardson
Quoted 119 lines · Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
Cc Wenzhuo Lu <[email protected]>
Cc Beilei Xing <[email protected]>
Cc Bernard Iremonger <[email protected]>
---
 app/test-pmd/cmdline.c    |  6 ------
 app/test-pmd/config.c     |  2 +-
 app/test-pmd/parameters.c |  7 ++-----
 app/test-pmd/testpmd.c    | 18 ++++++++++++++++++
 4 files changed, 21 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
        RTE_ETH_FOREACH_DEV(pid) {
                struct rte_port *port = &ports[pid];
-               uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
                if (!strcmp(res->name, "max-pkt-len")) {
                        if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
                                return;
 
                        port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-                       if (res->value > RTE_ETHER_MAX_LEN)
-                               rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       else
-                               rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       port->dev_conf.rxmode.offloads = rx_offloads;
                } else {
                        printf("Unknown parameter\n");
                        return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
                 * device supports jumbo frame.
                 */
                eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-               if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+               if (mtu > RTE_ETHER_MTU) {
                        rte_port->dev_conf.rxmode.offloads |=
                                                DEV_RX_OFFLOAD_JUMBO_FRAME;
                        rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
                        }
                        if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
                                n = atoi(optarg);
-                               if (n >= RTE_ETHER_MIN_LEN) {
+                               if (n >= RTE_ETHER_MIN_LEN)
                                        rx_mode.max_rx_pkt_len = (uint32_t) n;
-                                       if (n > RTE_ETHER_MAX_LEN)
-                                               rx_offloads |=
-                                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
-                               } else
+                               else
                                        rte_exit(EXIT_FAILURE,
                                                 "Invalid max-pkt-len=%d - should be > %d\n",
                                                 n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +18 -1
index 2b60f6c5d3..c256e719ae 100644
@@ -1410,6 +1410,7 @@ init_config(void)
        struct rte_gro_param gro_param;
        uint32_t gso_types;
        uint16_t data_size;
+       uint16_t eth_overhead;
        bool warning = 0;
        int k;
        int ret;
@@ -1446,6 +1447,23 @@ init_config(void)
                        rte_exit(EXIT_FAILURE,
                                 "rte_eth_dev_info_get() failed\n");
 
+               /* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+               if (port->dev_info.max_mtu != UINT16_MAX &&
+                   port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+                       eth_overhead = port->dev_info.max_rx_pktlen -
+                               port->dev_info.max_mtu;
+               else
+                       eth_overhead =
+                               RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+               if (port->dev_conf.rxmode.max_rx_pkt_len <=
+                       (uint32_t)(RTE_ETHER_MTU + eth_overhead))
+                       port->dev_conf.rxmode.max_rx_pkt_len =
+                                       RTE_ETHER_MTU + eth_overhead;
+               else
+                       port->dev_conf.rxmode.offloads |=
+                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
+
                if (!(port->dev_info.tx_offload_capa &
                      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
                        port->dev_conf.txmode.offloads &=
--
Quoted 2 lines

2.17.1

Moving the setting of DEV_RX_OFFLOAD_JUMBO_FRAME from cmd_config_max_pkt_len_parsed() to init_config() doesn't seem to be correct for the case where max_rx_pkt_len is changed from the command line via "port config all max-pkt-len".

Quoted 7 lines

The init_config() function is only called when testpmd is started, but the DEV_RX_OFFLOAD_JUMBO_FRAME setting needs to
be recomputed whenever max_rx_pkt_len changes.

(Of course this won't matter when DEV_RX_OFFLOAD_JUMBO_FRAME is removed, which seems like a great idea, but for now this is impacting some test automation with 21.02-rc1.)

+Ferruh (sorry, thought he was already on this thread.)

#70 lore raw

Re: [dpdk-dev] [PATCH v4 02/22] app/testpmd: fix max rx packet length for VLAN packets

In reply to Lance Richardson
Quoted 128 lines · Lance Richardson
Quoted 119 lines · Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
Cc Wenzhuo Lu <[email protected]>
Cc Beilei Xing <[email protected]>
Cc Bernard Iremonger <[email protected]>
---
  app/test-pmd/cmdline.c    |  6 ------
  app/test-pmd/config.c     |  2 +-
  app/test-pmd/parameters.c |  7 ++-----
  app/test-pmd/testpmd.c    | 18 ++++++++++++++++++
  4 files changed, 21 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
         RTE_ETH_FOREACH_DEV(pid) {
                 struct rte_port *port = &ports[pid];
-               uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
                 if (!strcmp(res->name, "max-pkt-len")) {
                         if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
                                 return;
 
                         port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-                       if (res->value > RTE_ETHER_MAX_LEN)
-                               rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       else
-                               rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-                       port->dev_conf.rxmode.offloads = rx_offloads;
                 } else {
                         printf("Unknown parameter\n");
                         return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
                  * device supports jumbo frame.
                  */
                 eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-               if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+               if (mtu > RTE_ETHER_MTU) {
                         rte_port->dev_conf.rxmode.offloads |=
                                                 DEV_RX_OFFLOAD_JUMBO_FRAME;
                         rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
                         }
                         if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
                                 n = atoi(optarg);
-                               if (n >= RTE_ETHER_MIN_LEN) {
+                               if (n >= RTE_ETHER_MIN_LEN)
                                         rx_mode.max_rx_pkt_len = (uint32_t) n;
-                                       if (n > RTE_ETHER_MAX_LEN)
-                                               rx_offloads |=
-                                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
-                               } else
+                               else
                                         rte_exit(EXIT_FAILURE,
                                                  "Invalid max-pkt-len=%d - should be > %d\n",
                                                  n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +18 -1
index 2b60f6c5d3..c256e719ae 100644
@@ -1410,6 +1410,7 @@ init_config(void)
         struct rte_gro_param gro_param;
         uint32_t gso_types;
         uint16_t data_size;
+       uint16_t eth_overhead;
         bool warning = 0;
         int k;
         int ret;
@@ -1446,6 +1447,23 @@ init_config(void)
                         rte_exit(EXIT_FAILURE,
                                  "rte_eth_dev_info_get() failed\n");
 
+               /* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+               if (port->dev_info.max_mtu != UINT16_MAX &&
+                   port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+                       eth_overhead = port->dev_info.max_rx_pktlen -
+                               port->dev_info.max_mtu;
+               else
+                       eth_overhead =
+                               RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+               if (port->dev_conf.rxmode.max_rx_pkt_len <=
+                       (uint32_t)(RTE_ETHER_MTU + eth_overhead))
+                       port->dev_conf.rxmode.max_rx_pkt_len =
+                                       RTE_ETHER_MTU + eth_overhead;
+               else
+                       port->dev_conf.rxmode.offloads |=
+                                       DEV_RX_OFFLOAD_JUMBO_FRAME;
+
                 if (!(port->dev_info.tx_offload_capa &
                       DEV_TX_OFFLOAD_MBUF_FAST_FREE))
                         port->dev_conf.txmode.offloads &=
--
Quoted 2 lines

2.17.1

Moving the setting of DEV_RX_OFFLOAD_JUMBO_FRAME from cmd_config_max_pkt_len_parsed() to init_config() doesn't seem to be correct for the case where max_rx_pkt_len is changed from the command line via "port config all max-pkt-len".

Quoted 4 lines

The init_config() function is only called when testpmd is started, but the DEV_RX_OFFLOAD_JUMBO_FRAME setting needs to
be recomputed whenever max_rx_pkt_len changes.

Hi Lance,

You are right, there is a patch trying to fix the command, can you please review it?
https://patches.dpdk.org/project/dpdk/list/?series=14925

Quoted 4 lines

(Of course this won't matter when DEV_RX_OFFLOAD_JUMBO_FRAME is removed, which seems like a great idea, but for now this is impacting some test automation with 21.02-rc1.)

author
#71 lore raw

PATCH v4 3/22 net/dpaa: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 25f854197abc ("net/dpaa: support jumbo frames")
Cc Hemant Agrawal <[email protected]>
Cc Sachin Saxena <[email protected]>
---
 drivers/net/dpaa/dpaa_ethdev.c | 2 +-
 drivers/net/dpaa/dpaa_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa/dpaa_ethdev.c +1 -1
index f00279e004..0c87c136d7 100644
@@ -184,7 +184,7 @@ dpaa_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa/dpaa_ethdev.h +4 -0
index 659bceb467..a858b1372c 100644
@@ -51,6 +51,10 @@
 #define VLAN_TAG_SIZE   4 /** < Vlan Header Length */
 #endif
 
+#define DPAA_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			  RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			  VLAN_TAG_SIZE)
+
 /* PCD frame queues */
 #define DPAA_DEFAULT_NUM_PCD_QUEUES	1
 #define DPAA_VSP_PROFILE_MAX_NUM	8
Signature · 1 line
2.17.1
author
#72 lore raw

PATCH v4 4/22 net/dpaa2: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes e16408499412 ("net/dpaa2: configure jumbo frames")
Cc Hemant Agrawal <[email protected]>
Cc Sachin Saxena <[email protected]>
---
 drivers/net/dpaa2/dpaa2_ethdev.c | 2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa2/dpaa2_ethdev.c +1 -1
index ab6863300e..6f38da3cce 100644
@@ -1420,7 +1420,7 @@ dpaa2_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > DPAA2_MAX_RX_PKT_LEN)
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA2_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa2/dpaa2_ethdev.h +4 -0
index 8d82f74684..cacb11bd3e 100644
@@ -26,6 +26,10 @@
 
 #define DPAA2_RX_DEFAULT_NBDESC 512
 
+#define DPAA2_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			   RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			   VLAN_TAG_SIZE)
+
 /*default tc to be used for ,congestion, distribution etc configuration. */
 #define DPAA2_DEF_TC		0
 
Signature · 1 line
2.17.1
author
#73 lore raw

PATCH v4 5/22 net/e1000: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes ef990fb56e55 ("net/e1000: convert to new Rx offloads API")
Cc Jeff Guo <[email protected]>
Cc Haiyue Wang <[email protected]>
---
 drivers/net/e1000/e1000_ethdev.h | 2 +-
 drivers/net/e1000/em_ethdev.c    | 5 ++---
 drivers/net/e1000/igb_ethdev.c   | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)
drivers/net/e1000/e1000_ethdev.h +1 -1
index 4755a5f333..3b4d9c3ee6 100644
@@ -97,7 +97,7 @@
  */
 #define E1000_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				VLAN_TAG_SIZE)
-
+#define E1000_ETH_MAX_LEN (RTE_ETHER_MTU + E1000_ETH_OVERHEAD)
 /*
  * Maximum number of Ring Descriptors.
  *
drivers/net/e1000/em_ethdev.c +2 -3
index 8ee9422bf4..2036c6e917 100644
@@ -1799,8 +1799,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (ret != 0)
 		return ret;
 
-	frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
-		VLAN_TAG_SIZE;
+	frame_size = mtu + E1000_ETH_OVERHEAD;
 
 	/* check that mtu is within the allowed range */
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > dev_info.max_rx_pktlen)
@@ -1816,7 +1815,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
drivers/net/e1000/igb_ethdev.c +1 -1
index 647aa8d995..dfe87508c2 100644
@@ -4369,7 +4369,7 @@ eth_igb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
Signature · 1 line
2.17.1
author
#74 lore raw

PATCH v4 6/22 net/hns3: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'HSN3_DEFAULT_FRAME_LEN', that perhaps impacts the cases of the jumbo frame related.

Fixes 1f5ca0b460cd ("net/hns3: support some device operations")
Fixes a5475d61fa34 ("net/hns3: support VF")
Cc "Min Hu (Connor)" <[email protected]>
Cc Yisen Zhuang <[email protected]>
Cc Lijun Ou <[email protected]>
---
 drivers/net/hns3/hns3_ethdev.c    | 2 +-
 drivers/net/hns3/hns3_ethdev_vf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/hns3/hns3_ethdev.c +1 -1
index 7c34e382fb..10e0c0de46 100644
@@ -2467,7 +2467,7 @@ hns3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	rte_spinlock_lock(&hw->lock);
-	is_jumbo_frame = frame_size > RTE_ETHER_MAX_LEN ? true : false;
+	is_jumbo_frame = frame_size > HNS3_DEFAULT_FRAME_LEN ? true : false;
 	frame_size = RTE_MAX(frame_size, HNS3_DEFAULT_FRAME_LEN);
 
 	/*
drivers/net/hns3/hns3_ethdev_vf.c +1 -1
index f09cabcd82..ef03fb1c4e 100644
@@ -928,7 +928,7 @@ hns3vf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		rte_spinlock_unlock(&hw->lock);
 		return ret;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#75 lore raw

PATCH v4 7/22 net/i40e: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes c1715402df8f ("i40evf: fix jumbo frame support")
Fixes 43e5488c0ac6 ("net/i40e: support MTU configuration")
Fixes a778a1fa2e4e ("i40e: set up and initialize flow director")
Fixes c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
Cc Jeff Guo <[email protected]>
Cc Beilei Xing <[email protected]>
---
 drivers/net/i40e/i40e_ethdev.c    |  2 +-
 drivers/net/i40e/i40e_ethdev.h    |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c      |  2 +-
 drivers/net/i40e/i40e_rxtx.c      |  8 ++++----
 5 files changed, 12 insertions(+), 11 deletions(-)
drivers/net/i40e/i40e_ethdev.c +1 -1
index 14622484a0..6074d3d928 100644
@@ -11745,7 +11745,7 @@ i40e_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_ethdev.h +1 -0
index 0617fe5e65..c1c429a075 100644
@@ -283,6 +283,7 @@ struct rte_flow {
  */
 #define I40E_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + I40E_VLAN_TAG_SIZE * 2)
+#define I40E_ETH_MAX_LEN (RTE_ETHER_MTU + I40E_ETH_OVERHEAD)
 
 #define I40E_RXTX_BYTES_H_16_BIT(bytes) ((bytes) & ~I40E_48_BIT_MASK)
 #define I40E_RXTX_BYTES_L_48_BIT(bytes) ((bytes) & I40E_48_BIT_MASK)
drivers/net/i40e/i40e_ethdev_vf.c +5 -5
index dc076ae552..bca8cb80e4 100644
@@ -1899,22 +1899,22 @@ i40evf_rxq_init(struct rte_eth_dev *dev, struct i40e_rx_queue *rxq)
 	 * Check if the jumbo frame and maximum packet length are set correctly
 	 */
 	if (dev_data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
-				"frame is enabled", (uint32_t)RTE_ETHER_MAX_LEN,
+				"frame is enabled", (uint32_t)I40E_ETH_MAX_LEN,
 					(uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
 				"frame is disabled",
 				(uint32_t)RTE_ETHER_MIN_LEN,
-				(uint32_t)RTE_ETHER_MAX_LEN);
+				(uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
@@ -2836,7 +2836,7 @@ i40evf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_fdir.c +1 -1
index 0343e8b09a..f5defcf585 100644
@@ -116,7 +116,7 @@ i40e_fdir_rx_queue_init(struct i40e_rx_queue *rxq)
 #endif
 	rx_ctx.dtype = i40e_header_split_none;
 	rx_ctx.hsplit_0 = I40E_HEADER_SPLIT_NONE;
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = I40E_ETH_MAX_LEN;
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
 	rx_ctx.tphdata_ena = 1;
drivers/net/i40e/i40e_rxtx.c +4 -4
index 5df9a9df56..b8859bbff2 100644
@@ -2797,23 +2797,23 @@ i40e_rx_queue_config(struct i40e_rx_queue *rxq)
 		RTE_MIN((uint32_t)(hw->func_caps.rx_buf_chain_len *
 			rxq->rx_buf_len), data->dev_conf.rxmode.max_rx_pkt_len);
 	if (data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)I40E_ETH_MAX_LEN,
 				    (uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-			rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+			rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
Signature · 1 line
2.17.1
author
#76 lore raw

PATCH v4 8/22 net/iavf: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 3fd7a3719c66 ("net/avf: enable ops for MTU setting")
Fixes 69dd4c3d0898 ("net/avf: enable queue and device")
Cc Beilei Xing <[email protected]>
Cc Jingjing Wu <[email protected]>
---
 drivers/net/iavf/iavf.h        |  1 +
 drivers/net/iavf/iavf_ethdev.c | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)
drivers/net/iavf/iavf.h +1 -0
index af11268fe3..c934d2e614 100644
@@ -73,6 +73,7 @@
 #define IAVF_VLAN_TAG_SIZE               4
 #define IAVF_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IAVF_VLAN_TAG_SIZE * 2)
+#define IAVF_ETH_MAX_LEN (RTE_ETHER_MTU + IAVF_ETH_OVERHEAD)
 
 #define IAVF_32_BIT_WIDTH (CHAR_BIT * 4)
 #define IAVF_48_BIT_WIDTH (CHAR_BIT * 6)
drivers/net/iavf/iavf_ethdev.c +5 -5
index e22c62ed00..250ef6fc9a 100644
@@ -460,23 +460,23 @@ iavf_init_rxq(struct rte_eth_dev *dev, struct iavf_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= IAVF_ETH_MAX_LEN ||
 		    max_pkt_len > IAVF_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)IAVF_ETH_MAX_LEN,
 				    (uint32_t)IAVF_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > IAVF_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)IAVF_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -1303,7 +1303,7 @@ iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IAVF_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#77 lore raw

PATCH v4 9/22 net/ice: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 84dc7a95a2d3 ("net/ice: enable flow director engine")
Fixes 1b009275e2c8 ("net/ice: add Rx queue init in DCF")
Fixes ae2bdd0219cb ("net/ice: support MTU setting")
Fixes 50370662b727 ("net/ice: support device and queue ops")
Cc Qiming Yang <[email protected]>
Cc Qi Zhang <[email protected]>
---
 drivers/net/ice/ice_dcf_ethdev.c |  8 ++++----
 drivers/net/ice/ice_ethdev.c     |  2 +-
 drivers/net/ice/ice_ethdev.h     |  1 +
 drivers/net/ice/ice_rxtx.c       | 10 +++++-----
 4 files changed, 11 insertions(+), 10 deletions(-)
drivers/net/ice/ice_dcf_ethdev.c +4 -4
index a9e78064d4..d46734a57b 100644
@@ -60,23 +60,23 @@ ice_dcf_init_rxq(struct rte_eth_dev *dev, struct ice_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
drivers/net/ice/ice_ethdev.c +1 -1
index e2799a8eb2..ba533a78ee 100644
@@ -3912,7 +3912,7 @@ ice_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ICE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/ice/ice_ethdev.h +1 -0
index 899f446cde..2b03c59671 100644
@@ -135,6 +135,7 @@
  */
 #define ICE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + ICE_VLAN_TAG_SIZE * 2)
+#define ICE_ETH_MAX_LEN (RTE_ETHER_MTU + ICE_ETH_OVERHEAD)
 
 #define ICE_RXTX_BYTES_HIGH(bytes) ((bytes) & ~ICE_40_BIT_MASK)
 #define ICE_RXTX_BYTES_LOW(bytes) ((bytes) & ICE_40_BIT_MASK)
drivers/net/ice/ice_rxtx.c +5 -5
index d052bd0f1b..c98328ce0b 100644
@@ -246,23 +246,23 @@ ice_program_hw_rx_queue(struct ice_rx_queue *rxq)
 				   dev->data->dev_conf.rxmode.max_rx_pkt_len);
 
 	if (rxmode->offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -701,7 +701,7 @@ ice_fdir_program_hw_rx_queue(struct ice_rx_queue *rxq)
 	rx_ctx.hbuf = rxq->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S;
 	rx_ctx.dtype = 0; /* No Header Split mode */
 	rx_ctx.dsize = 1; /* 32B descriptors */
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = ICE_ETH_MAX_LEN;
 	/* TPH: Transaction Layer Packet (TLP) processing hints */
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
Signature · 1 line
2.17.1
author
#78 lore raw

PATCH v4 10/22 net/ipn3ke: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 70d6b7f550f4 ("net/ipn3ke: add representor")
Cc Rosen Xu <[email protected]>
---
 drivers/net/ipn3ke/ipn3ke_ethdev.h      | 1 +
 drivers/net/ipn3ke/ipn3ke_representor.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/ipn3ke/ipn3ke_ethdev.h +1 -0
index 9b0cf309c8..a6815a9cca 100644
@@ -640,6 +640,7 @@ ipn3ke_tm_ops_get(struct rte_eth_dev *ethdev,
  */
 #define IPN3KE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IPN3KE_VLAN_TAG_SIZE * 2)
+#define IPN3KE_ETH_MAX_LEN (RTE_ETHER_MTU + IPN3KE_ETH_OVERHEAD)
 
 #define IPN3KE_MAC_FRAME_SIZE_MAX    9728
 #define IPN3KE_MAC_RX_FRAME_MAXLENGTH    0x00AE
drivers/net/ipn3ke/ipn3ke_representor.c +1 -1
index 8a53602576..9e15cce34f 100644
@@ -2801,7 +2801,7 @@ ipn3ke_rpst_mtu_set(struct rte_eth_dev *ethdev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IPN3KE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			(uint64_t)(DEV_RX_OFFLOAD_JUMBO_FRAME);
 	else
Signature · 1 line
2.17.1
author
#79 lore raw

PATCH v4 11/22 net/octeontx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 3151e6a687a3 ("net/octeontx: support MTU")
Cc Harman Kalra <[email protected]>
---
 drivers/net/octeontx/octeontx_ethdev.c | 2 +-
 drivers/net/octeontx/octeontx_ethdev.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/octeontx/octeontx_ethdev.c +1 -1
index 3ee7b043fd..81779885d5 100644
@@ -552,7 +552,7 @@ octeontx_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > OCCTX_L2_MAX_LEN)
 		nic->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		nic->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/octeontx/octeontx_ethdev.h +1 -0
index 7246fb6d1d..780a094ffa 100644
@@ -44,6 +44,7 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define OCCTX_L2_OVERHEAD	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				 OCCTX_MAX_VTAG_ACT_SIZE)
+#define OCCTX_L2_MAX_LEN	(RTE_ETHER_MTU + OCCTX_L2_OVERHEAD)
 
 /* Since HW FRS includes NPC VTAG insertion space, user has reduced FRS */
 #define OCCTX_MAX_FRS	\
Signature · 1 line
2.17.1
author
#80 lore raw

PATCH v4 12/22 net/octeontx2: fix the jumbo frame flag condition for mtu

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")
Cc Jerin Jacob <[email protected]>
Cc Nithin Dabilpuram <[email protected]>
Cc Kiran Kumar K <[email protected]>
---
 drivers/net/octeontx2/otx2_ethdev.h     | 2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev.h +2 -0
index 3b9871f4dc..99f0469d89 100644
@@ -51,6 +51,8 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define NIX_L2_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + 8)
+#define NIX_L2_MAX_LEN \
+	(RTE_ETHER_MTU + NIX_L2_OVERHEAD)
 
 /* HW config of frame size doesn't include FCS */
 #define NIX_MAX_HW_FRS			9212
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..963cc285ed 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIX_L2_MAX_LEN)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#81 lore raw

PATCH v4 13/22 net/qede: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 200645ac7909 ("net/qede: set MTU")
Cc Rasesh Mody <[email protected]>
Cc Shahed Shaikh <[email protected]>
---
 drivers/net/qede/qede_ethdev.c | 2 +-
 drivers/net/qede/qede_rxtx.h   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/qede/qede_ethdev.c +1 -1
index 549013557c..6919378b8e 100644
@@ -2367,7 +2367,7 @@ static int qede_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 			fp->rxq->rx_buf_size = rc;
 		}
 	}
-	if (max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+	if (frame_size > QEDE_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/qede/qede_rxtx.h +1 -0
index d7ff870b20..fcb564a1bb 100644
@@ -71,6 +71,7 @@
 				 + (QEDE_LLC_SNAP_HDR_LEN) + 2)
 
 #define QEDE_MAX_ETHER_HDR_LEN	(RTE_ETHER_HDR_LEN + QEDE_ETH_OVERHEAD)
+#define QEDE_ETH_MAX_LEN	(RTE_ETHER_MTU + QEDE_MAX_ETHER_HDR_LEN)
 
 #define QEDE_RSS_OFFLOAD_ALL    (ETH_RSS_IPV4			|\
 				 ETH_RSS_NONFRAG_IPV4_TCP	|\
Signature · 1 line
2.17.1
author
#82 lore raw

PATCH v4 14/22 net/sfc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU', that perhaps impacts the cases of the jumbo frame related.

Fixes ff6a1197c3b1 ("net/sfc: convert to new Rx offload API")
Cc Andrew Rybchenko <[email protected]>
---
 drivers/net/sfc/sfc_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/sfc/sfc_ethdev.c +1 -1
index 93fc7baa0d..f2f5336435 100644
@@ -1017,7 +1017,7 @@ sfc_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 	 * The driver does not use it, but other PMDs update jumbo frame
 	 * flag and max_rx_pkt_len when MTU is set.
 	 */
-	if (mtu > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	}
Signature · 1 line
2.17.1
author
#83 lore raw

PATCH v4 15/22 net/thunderx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 65d9804edc05 ("net/thunderx: support MTU configuration")
Cc Jerin Jacob <[email protected]>
Cc Maciej Czekaj <[email protected]>
---
 drivers/net/thunderx/base/nicvf_hw_defs.h | 1 +
 drivers/net/thunderx/nicvf_ethdev.c       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/thunderx/base/nicvf_hw_defs.h +1 -0
index b12c8ec50a..adc8ec943d 100644
@@ -176,6 +176,7 @@
 #define NIC_HW_MAX_MTU                  (9190)
 #define NIC_HW_MAX_FRS                  (NIC_HW_MAX_MTU + NIC_HW_L2_OVERHEAD)
 #define NIC_HW_MAX_SEGS                 (12)
+#define NIC_HW_L2_MAX_LEN		(RTE_ETHER_MTU + NIC_HW_L2_OVERHEAD)
 
 /* Descriptor alignments */
 #define NICVF_RBDR_BASE_ALIGN_BYTES     (128) /* 7 bits */
drivers/net/thunderx/nicvf_ethdev.c +1 -1
index b6bb05e500..c2e7c334d4 100644
@@ -176,7 +176,7 @@ nicvf_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 		(frame_size + 2 * VLAN_TAG_SIZE > buffsz * NIC_HW_MAX_SEGS))
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIC_HW_L2_MAX_LEN)
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		rxmode->offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#84 lore raw

PATCH v4 16/22 net/ixgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Fixes 95a27b3ba5f5 ("net/ixgbe: enable jumbo frame for VF")
Cc Jeff Guo <[email protected]>
Cc Haiyue Wang <[email protected]>
---
 drivers/net/ixgbe/ixgbe_ethdev.c | 2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h | 3 +++
 drivers/net/ixgbe/ixgbe_pf.c     | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)
drivers/net/ixgbe/ixgbe_ethdev.c +1 -1
index d7a1806ab8..fa0f5afd03 100644
@@ -5173,7 +5173,7 @@ ixgbe_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > IXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		hlreg0 |= IXGBE_HLREG0_JUMBOEN;
drivers/net/ixgbe/ixgbe_ethdev.h +3 -0
index 3d35ea791b..a0ce18ca24 100644
@@ -104,6 +104,9 @@
 /* The overhead from MTU to max frame size. */
 #define IXGBE_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
 
+/* The max frame size with default MTU */
+#define IXGBE_ETH_MAX_LEN  (RTE_ETHER_MTU + IXGBE_ETH_OVERHEAD)
+
 /* bit of VXLAN tunnel type | 7 bits of zeros  | 8 bits of zeros*/
 #define IXGBE_FDIR_VXLAN_TUNNEL_TYPE    0x8000
 /* bit of NVGRE tunnel type | 7 bits of zeros  | 8 bits of zeros*/
drivers/net/ixgbe/ixgbe_pf.c +1 -1
index 833863af5a..89698e8470 100644
@@ -575,7 +575,7 @@ ixgbe_set_vf_lpe(struct rte_eth_dev *dev, __rte_unused uint32_t vf, uint32_t *ms
 		   IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
 	if (max_frs < new_mtu) {
 		hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
-		if (new_mtu > RTE_ETHER_MAX_LEN) {
+		if (new_mtu > IXGBE_ETH_MAX_LEN) {
 			dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 			hlreg0 |= IXGBE_HLREG0_JUMBOEN;
Signature · 1 line
2.17.1
author
#85 lore raw

PATCH v4 17/22 net/cxgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 4b2eff452d2e ("cxgbe: enable jumbo frames")
Fixes 0ec33be4c857 ("cxgbe: allow to change mtu")
Cc Rahul Lakkireddy <[email protected]>
---
 drivers/net/cxgbe/cxgbe.h        | 4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)
drivers/net/cxgbe/cxgbe.h +4 -0
index ef62af1c3f..7c89a028bf 100644
@@ -19,6 +19,10 @@
 #define CXGBE_MAX_RX_PKTLEN (9000 + RTE_ETHER_HDR_LEN + \
 				RTE_ETHER_CRC_LEN) /* max pkt */
 
+/* The max frame size with default MTU */
+#define CXGBE_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /* Max poll time is 100 * 100msec = 10 sec */
 #define CXGBE_LINK_STATUS_POLL_MS 100 /* 100ms */
 #define CXGBE_LINK_STATUS_POLL_CNT 100 /* Max number of times to poll */
drivers/net/cxgbe/cxgbe_ethdev.c +2 -2
index 98d0362fa3..480d6f58a8 100644
@@ -300,7 +300,7 @@ int cxgbe_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -EINVAL;
 
 	/* set to jumbo mode if needed */
-	if (new_mtu > RTE_ETHER_MAX_LEN)
+	if (new_mtu > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
@@ -669,7 +669,7 @@ int cxgbe_dev_rx_queue_setup(struct rte_eth_dev *eth_dev,
 		rxq->fl.size = temp_nb_desc;
 
 	/* Set to jumbo mode if necessary */
-	if (pkt_len > RTE_ETHER_MAX_LEN)
+	if (pkt_len > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#86 lore raw

PATCH v4 18/22 net/axgbe: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes b58d8781fa1f ("net/axgbe: support setting MTU")
Cc Somalapuram Amaranath <[email protected]>
---
 drivers/net/axgbe/axgbe_ethdev.c | 2 +-
 drivers/net/axgbe/axgbe_ethdev.h | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)
drivers/net/axgbe/axgbe_ethdev.c +1 -1
index ddd903680d..ebe9a2876d 100644
@@ -1490,7 +1490,7 @@ static int axgb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 				dev->data->port_id);
 		return -EBUSY;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > AXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		val = 1;
drivers/net/axgbe/axgbe_ethdev.h +6 -0
index 1481fd9ff3..a6226729fe 100644
@@ -125,6 +125,12 @@
 /* MDIO port types */
 #define AXGMAC_MAX_C22_PORT		3
 
+/* The max frame size with default MTU */
+#define AXGBE_ETH_MAX_LEN ( \
+	RTE_ETHER_MTU + \
+	RTE_ETHER_HDR_LEN + \
+	RTE_ETHER_CRC_LEN)
+
 /* Helper macro for descriptor handling
  *  Always use AXGBE_GET_DESC_DATA to access the descriptor data
  *  since the index is free-running and needs to be and-ed
Signature · 1 line
2.17.1
author
#87 lore raw

PATCH v4 19/22 net/enetc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 5d5589b0c858 ("net/enetc: support MTU update and jumbo frames")
Cc Gagandeep Singh <[email protected]>
Cc Sachin Saxena <[email protected]>
---
 drivers/net/enetc/enetc.h        | 4 ++++
 drivers/net/enetc/enetc_ethdev.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/enetc/enetc.h +4 -0
index 14ef3bc18b..7163633bce 100644
@@ -29,6 +29,10 @@
 /* maximum frame size supported */
 #define ENETC_MAC_MAXFRM_SIZE	9600
 
+/* The max frame size with default MTU */
+#define ENETC_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /*
  * upper_32_bits - return bits 32-63 of a number
  * @n: the number we're accessing
drivers/net/enetc/enetc_ethdev.c +1 -1
index 6ff3022874..4d2c9c0474 100644
@@ -677,7 +677,7 @@ enetc_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ENETC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads &=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#88 lore raw

PATCH v4 20/22 net/hinic: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 254bd849b132 ("net/hinic: set jumbo frame offload flag")
Cc Ziyang Xuan <[email protected]>
Cc Xiaoyun Wang <[email protected]>
Cc Guoyang Zhou <[email protected]>
---
 drivers/net/hinic/hinic_pmd_ethdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/hinic/hinic_pmd_ethdev.c +4 -1
index 62642354cf..5a2c171099 100644
@@ -75,6 +75,9 @@
 #define HINIC_PKTLEN_TO_MTU(pktlen)	\
 	((pktlen) - (ETH_HLEN + ETH_CRC_LEN))
 
+/* The max frame size with default MTU */
+#define HINIC_ETH_MAX_LEN (RTE_ETHER_MTU + ETH_HLEN + ETH_CRC_LEN)
+
 /* lro numer limit for one packet */
 #define HINIC_LRO_WQE_NUM_DEFAULT	8
 
@@ -1556,7 +1559,7 @@ static int hinic_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 
 	/* update max frame size */
 	frame_size = HINIC_MTU_TO_PKTLEN(mtu);
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > HINIC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#89 lore raw

PATCH v4 21/22 net/nfp: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU', that perhaps impacts the cases of the jumbo frame related.

Fixes d4a27a3b092a ("nfp: add basic features")
Cc Heinrich Kuhn <[email protected]>
---
 drivers/net/nfp/nfp_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/nfp/nfp_net.c +1 -1
index 1608bf5ea1..9ea24e5bda 100644
@@ -1508,7 +1508,7 @@ nfp_net_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	/* switch to jumbo mode if needed */
-	if ((uint32_t)mtu > RTE_ETHER_MAX_LEN)
+	if ((uint32_t)mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#90 lore raw

PATCH v4 22/22 net/liquidio: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 9f1c00266d82 ("net/liquidio: add API to set MTU")
Cc Shijith Thotton <[email protected]>
Cc Srisivasubramanian Srinivasan <[email protected]>
---
 drivers/net/liquidio/lio_ethdev.c | 2 +-
 drivers/net/liquidio/lio_ethdev.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)
drivers/net/liquidio/lio_ethdev.c +1 -1
index d4dd3768cd..eb0fdab45a 100644
@@ -481,7 +481,7 @@ lio_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -1;
 	}
 
-	if (frame_len > RTE_ETHER_MAX_LEN)
+	if (frame_len > LIO_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/liquidio/lio_ethdev.h +3 -0
index 74cd2fb6c6..d33be1c44d 100644
@@ -13,6 +13,9 @@
 #define LIO_LSC_TIMEOUT		100000 /* 100000us (100ms) */
 #define LIO_MAX_CMD_TIMEOUT     10000 /* 10000ms (10s) */
 
+/* The max frame size with default MTU */
+#define LIO_ETH_MAX_LEN (RTE_ETHER_MTU + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 #define LIO_DEV(_eth_dev)		((_eth_dev)->data->dev_private)
 
 /* LIO Response condition variable */
Signature · 1 line
2.17.1
Reviewed-by on the v4 series
#91 lore raw
In reply to Steve Yang
Quoted 52 lines · Steve Yang

The jumbo frame used the 'RTE_ETHER_MAX_LEN' as boundary condition, this fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead.

When the MTU(1500) set, the frame type of rx packet will be different if used different overhead, it will cause the consistency issue, and the normal packet will be dropped. Hence, using fixed value 'RTE_ETHER_MTU' can avoid this issue.

Like,

app     -> max_rx_pkt_len = 1500/*mtu*/ + 22/*overhead*/ = 1522
ethdev  -> 1522 > 1518/*MAX*/; max_rx_pkt_len = 1518
driver  -> MTU = 1518 - 22 = 1496

Packets with size 1497-1500 are dropped although intention is to be able to send/receive them.

Following scopes will be changed:
- 'rte_ethdev'
- 'app', e.g.: 'test-pmd';
- net PMDs which support VLAN tag(s) within overhead, e.g.: i40e;

Following scopes perhaps will be impacted:
- the cases of jumbo frame related;
- the logic of 'max_rx_pkt_len' and 'mtu' related;
- the using place of 'RTE_ETHER_MAX_LEN';

---
v4:
- moved mtu assignment to the same if-true-block of jumbo frame;
v3:
- removed redundant if-conditions in rte_ethdev and testpmd;
- adjusted the alignment style;
- added offload check before updating mtu;
v2:
- defined the 'RTE_ETHER_MTU + overhead' to 'driver_ETH_MAX_LEN';
- changed the 'mtu > RTE_ETHER_MTU' to 'frame_size > driver_ETH_MAX_LEN';
---

Steve Yang (22):
ethdev: fix MTU size exceeds max rx packet length app/testpmd: fix max rx packet length for VLAN packets net/dpaa: fix the jumbo frame flag condition for mtu set net/dpaa2: fix the jumbo frame flag condition for mtu set net/e1000: fix the jumbo frame flag condition for mtu set net/hns3: fix the jumbo frame flag condition for mtu set net/i40e: fix the jumbo frame flag condition net/iavf: fix the jumbo frame flag condition net/ice: fix the jumbo frame flag condition net/ipn3ke: fix the jumbo frame flag condition for mtu set net/octeontx: fix the jumbo frame flag condition for mtu set net/octeontx2: fix the jumbo frame flag condition for mtu net/qede: fix the jumbo frame flag condition for mtu set net/sfc: fix the jumbo frame flag condition for mtu set

Quoted 8 lines

net/thunderx: fix the jumbo frame flag condition for mtu set net/ixgbe: fix the jumbo frame flag condition net/cxgbe: fix the jumbo frame flag condition net/axgbe: fix the jumbo frame flag condition for mtu set net/enetc: fix the jumbo frame flag condition for mtu set net/hinic: fix the jumbo frame flag condition for mtu set net/nfp: fix the jumbo frame flag condition for mtu set net/liquidio: fix the jumbo frame flag condition for mtu set

For series,

Series applied to dpdk-next-net/main, thanks.

author
#92 lore raw

PATCH v3 2/22 app/testpmd: fix max rx packet length for VLAN packets

In reply to Steve Yang

When the max rx packet length is smaller than the sum of mtu size and ether overhead size, it should be enlarged, otherwise the VLAN packets will be dropped.

Removed the rx_offloads assignment for jumbo frame during command line parsing, and set the correct jumbo frame flag if MTU size is larger than the default value 'RTE_ETHER_MTU' within 'init_config()'.

Fixes 384161e00627 ("app/testpmd: adjust on the fly VLAN configuration")
Fixes 35b2d13fd6fd ("net: add rte prefix to ether defines")
Fixes ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
Fixes 150c9ac2df13 ("app/testpmd: update Rx offload after setting MTU")
---
 app/test-pmd/cmdline.c    |  6 ------
 app/test-pmd/config.c     |  2 +-
 app/test-pmd/parameters.c |  7 ++-----
 app/test-pmd/testpmd.c    | 18 ++++++++++++++++++
 4 files changed, 21 insertions(+), 12 deletions(-)
app/test-pmd/cmdline.c +0 -6
index 2ccbaa039e..65042fcff5 100644
@@ -1886,7 +1886,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 
 	RTE_ETH_FOREACH_DEV(pid) {
 		struct rte_port *port = &ports[pid];
-		uint64_t rx_offloads = port->dev_conf.rxmode.offloads;
 
 		if (!strcmp(res->name, "max-pkt-len")) {
 			if (res->value < RTE_ETHER_MIN_LEN) {
@@ -1898,11 +1897,6 @@ cmd_config_max_pkt_len_parsed(void *parsed_result,
 				return;
 
 			port->dev_conf.rxmode.max_rx_pkt_len = res->value;
-			if (res->value > RTE_ETHER_MAX_LEN)
-				rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
-			else
-				rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
-			port->dev_conf.rxmode.offloads = rx_offloads;
 		} else {
 			printf("Unknown parameter\n");
 			return;
app/test-pmd/config.c +1 -1
index 3f6c8642b1..1195f054f3 100644
@@ -1434,7 +1434,7 @@ port_mtu_set(portid_t port_id, uint16_t mtu)
 		 * device supports jumbo frame.
 		 */
 		eth_overhead = dev_info.max_rx_pktlen - dev_info.max_mtu;
-		if (mtu > RTE_ETHER_MAX_LEN - eth_overhead) {
+		if (mtu > RTE_ETHER_MTU) {
 			rte_port->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 			rte_port->dev_conf.rxmode.max_rx_pkt_len =
app/test-pmd/parameters.c +2 -5
index 414a0068fb..df5eb10d84 100644
@@ -834,12 +834,9 @@ launch_args_parse(int argc, char** argv)
 			}
 			if (!strcmp(lgopts[opt_idx].name, "max-pkt-len")) {
 				n = atoi(optarg);
-				if (n >= RTE_ETHER_MIN_LEN) {
+				if (n >= RTE_ETHER_MIN_LEN)
 					rx_mode.max_rx_pkt_len = (uint32_t) n;
-					if (n > RTE_ETHER_MAX_LEN)
-						rx_offloads |=
-							DEV_RX_OFFLOAD_JUMBO_FRAME;
-				} else
+				else
 					rte_exit(EXIT_FAILURE,
 						 "Invalid max-pkt-len=%d - should be > %d\n",
 						 n, RTE_ETHER_MIN_LEN);
app/test-pmd/testpmd.c +18 -0
index 2b60f6c5d3..c256e719ae 100644
@@ -1410,6 +1410,7 @@ init_config(void)
 	struct rte_gro_param gro_param;
 	uint32_t gso_types;
 	uint16_t data_size;
+	uint16_t eth_overhead;
 	bool warning = 0;
 	int k;
 	int ret;
@@ -1446,6 +1447,23 @@ init_config(void)
 			rte_exit(EXIT_FAILURE,
 				 "rte_eth_dev_info_get() failed\n");
 
+		/* Update the max_rx_pkt_len to have MTU as RTE_ETHER_MTU */
+		if (port->dev_info.max_mtu != UINT16_MAX &&
+		    port->dev_info.max_rx_pktlen > port->dev_info.max_mtu)
+			eth_overhead = port->dev_info.max_rx_pktlen -
+				port->dev_info.max_mtu;
+		else
+			eth_overhead =
+				RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN;
+
+		if (port->dev_conf.rxmode.max_rx_pkt_len <=
+			(uint32_t)(RTE_ETHER_MTU + eth_overhead))
+			port->dev_conf.rxmode.max_rx_pkt_len =
+					RTE_ETHER_MTU + eth_overhead;
+		else
+			port->dev_conf.rxmode.offloads |=
+					DEV_RX_OFFLOAD_JUMBO_FRAME;
+
 		if (!(port->dev_info.tx_offload_capa &
 		      DEV_TX_OFFLOAD_MBUF_FAST_FREE))
 			port->dev_conf.txmode.offloads &=
Signature · 1 line
2.17.1
author
#93 lore raw

PATCH v3 3/22 net/dpaa: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 25f854197abc ("net/dpaa: support jumbo frames")
---
 drivers/net/dpaa/dpaa_ethdev.c | 2 +-
 drivers/net/dpaa/dpaa_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa/dpaa_ethdev.c +1 -1
index f00279e004..0c87c136d7 100644
@@ -184,7 +184,7 @@ dpaa_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa/dpaa_ethdev.h +4 -0
index 659bceb467..a858b1372c 100644
@@ -51,6 +51,10 @@
 #define VLAN_TAG_SIZE   4 /** < Vlan Header Length */
 #endif
 
+#define DPAA_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			  RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			  VLAN_TAG_SIZE)
+
 /* PCD frame queues */
 #define DPAA_DEFAULT_NUM_PCD_QUEUES	1
 #define DPAA_VSP_PROFILE_MAX_NUM	8
Signature · 1 line
2.17.1
author
#95 lore raw

PATCH v3 4/22 net/dpaa2: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes e16408499412 ("net/dpaa2: configure jumbo frames")
---
 drivers/net/dpaa2/dpaa2_ethdev.c | 2 +-
 drivers/net/dpaa2/dpaa2_ethdev.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/dpaa2/dpaa2_ethdev.c +1 -1
index ab6863300e..6f38da3cce 100644
@@ -1420,7 +1420,7 @@ dpaa2_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > DPAA2_MAX_RX_PKT_LEN)
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > DPAA2_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/dpaa2/dpaa2_ethdev.h +4 -0
index 8d82f74684..cacb11bd3e 100644
@@ -26,6 +26,10 @@
 
 #define DPAA2_RX_DEFAULT_NBDESC 512
 
+#define DPAA2_ETH_MAX_LEN (RTE_ETHER_MTU + \
+			   RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
+			   VLAN_TAG_SIZE)
+
 /*default tc to be used for ,congestion, distribution etc configuration. */
 #define DPAA2_DEF_TC		0
 
Signature · 1 line
2.17.1
author
#97 lore raw

PATCH v3 5/22 net/e1000: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes ef990fb56e55 ("net/e1000: convert to new Rx offloads API")
---
 drivers/net/e1000/e1000_ethdev.h | 2 +-
 drivers/net/e1000/em_ethdev.c    | 5 ++---
 drivers/net/e1000/igb_ethdev.c   | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)
drivers/net/e1000/e1000_ethdev.h +1 -1
index 4755a5f333..3b4d9c3ee6 100644
@@ -97,7 +97,7 @@
  */
 #define E1000_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				VLAN_TAG_SIZE)
-
+#define E1000_ETH_MAX_LEN (RTE_ETHER_MTU + E1000_ETH_OVERHEAD)
 /*
  * Maximum number of Ring Descriptors.
  *
drivers/net/e1000/em_ethdev.c +2 -3
index 8ee9422bf4..2036c6e917 100644
@@ -1799,8 +1799,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	if (ret != 0)
 		return ret;
 
-	frame_size = mtu + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN +
-		VLAN_TAG_SIZE;
+	frame_size = mtu + E1000_ETH_OVERHEAD;
 
 	/* check that mtu is within the allowed range */
 	if (mtu < RTE_ETHER_MIN_MTU || frame_size > dev_info.max_rx_pktlen)
@@ -1816,7 +1815,7 @@ eth_em_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
drivers/net/e1000/igb_ethdev.c +1 -1
index 647aa8d995..dfe87508c2 100644
@@ -4369,7 +4369,7 @@ eth_igb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	rctl = E1000_READ_REG(hw, E1000_RCTL);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > E1000_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		rctl |= E1000_RCTL_LPE;
Signature · 1 line
2.17.1
author
#98 lore raw

PATCH v3 6/22 net/hns3: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'HSN3_DEFAULT_FRAME_LEN', that perhaps impacts the cases of the jumbo frame related.

Fixes 1f5ca0b460cd ("net/hns3: support some device operations")
Fixes a5475d61fa34 ("net/hns3: support VF")
---
 drivers/net/hns3/hns3_ethdev.c    | 2 +-
 drivers/net/hns3/hns3_ethdev_vf.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/hns3/hns3_ethdev.c +1 -1
index 7c34e382fb..10e0c0de46 100644
@@ -2467,7 +2467,7 @@ hns3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	rte_spinlock_lock(&hw->lock);
-	is_jumbo_frame = frame_size > RTE_ETHER_MAX_LEN ? true : false;
+	is_jumbo_frame = frame_size > HNS3_DEFAULT_FRAME_LEN ? true : false;
 	frame_size = RTE_MAX(frame_size, HNS3_DEFAULT_FRAME_LEN);
 
 	/*
drivers/net/hns3/hns3_ethdev_vf.c +1 -1
index f09cabcd82..ef03fb1c4e 100644
@@ -928,7 +928,7 @@ hns3vf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		rte_spinlock_unlock(&hw->lock);
 		return ret;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
Acked-by on v3 6/22
#99 lore raw

Re: [dpdk-dev] [PATCH v3 06/22] net/hns3: fix the jumbo frame flag condition for mtu set

Quoted 44 lines · Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'HSN3_DEFAULT_FRAME_LEN', that perhaps impacts the cases of the jumbo frame related.

Fixes 1f5ca0b460cd ("net/hns3: support some device operations")
Fixes a5475d61fa34 ("net/hns3: support VF")
---
  drivers/net/hns3/hns3_ethdev.c    | 2 +-
  drivers/net/hns3/hns3_ethdev_vf.c | 2 +-
  2 files changed, 2 insertions(+), 2 deletions(-)
drivers/net/hns3/hns3_ethdev.c +1 -1
index 7c34e382fb..10e0c0de46 100644
@@ -2467,7 +2467,7 @@ hns3_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
  	}
 
  	rte_spinlock_lock(&hw->lock);
-	is_jumbo_frame = frame_size > RTE_ETHER_MAX_LEN ? true : false;
+	is_jumbo_frame = frame_size > HNS3_DEFAULT_FRAME_LEN ? true : false;
  	frame_size = RTE_MAX(frame_size, HNS3_DEFAULT_FRAME_LEN);
 
  	/*
drivers/net/hns3/hns3_ethdev_vf.c +1 -1
index f09cabcd82..ef03fb1c4e 100644
@@ -928,7 +928,7 @@ hns3vf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
  		rte_spinlock_unlock(&hw->lock);
  		return ret;
  	}
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (mtu > RTE_ETHER_MTU)
  		dev->data->dev_conf.rxmode.offloads |=
  						DEV_RX_OFFLOAD_JUMBO_FRAME;
  	else
author
#100 lore raw

PATCH v3 7/22 net/i40e: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes c1715402df8f ("i40evf: fix jumbo frame support")
Fixes 43e5488c0ac6 ("net/i40e: support MTU configuration")
Fixes a778a1fa2e4e ("i40e: set up and initialize flow director")
Fixes c3ac7c5b0b8a ("net/i40e: convert to new Rx offloads API")
---
 drivers/net/i40e/i40e_ethdev.c    |  2 +-
 drivers/net/i40e/i40e_ethdev.h    |  1 +
 drivers/net/i40e/i40e_ethdev_vf.c | 10 +++++-----
 drivers/net/i40e/i40e_fdir.c      |  2 +-
 drivers/net/i40e/i40e_rxtx.c      |  8 ++++----
 5 files changed, 12 insertions(+), 11 deletions(-)
drivers/net/i40e/i40e_ethdev.c +1 -1
index 14622484a0..6074d3d928 100644
@@ -11745,7 +11745,7 @@ i40e_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_ethdev.h +1 -0
index 0617fe5e65..c1c429a075 100644
@@ -283,6 +283,7 @@ struct rte_flow {
  */
 #define I40E_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + I40E_VLAN_TAG_SIZE * 2)
+#define I40E_ETH_MAX_LEN (RTE_ETHER_MTU + I40E_ETH_OVERHEAD)
 
 #define I40E_RXTX_BYTES_H_16_BIT(bytes) ((bytes) & ~I40E_48_BIT_MASK)
 #define I40E_RXTX_BYTES_L_48_BIT(bytes) ((bytes) & I40E_48_BIT_MASK)
drivers/net/i40e/i40e_ethdev_vf.c +5 -5
index dc076ae552..bca8cb80e4 100644
@@ -1899,22 +1899,22 @@ i40evf_rxq_init(struct rte_eth_dev *dev, struct i40e_rx_queue *rxq)
 	 * Check if the jumbo frame and maximum packet length are set correctly
 	 */
 	if (dev_data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
-				"frame is enabled", (uint32_t)RTE_ETHER_MAX_LEN,
+				"frame is enabled", (uint32_t)I40E_ETH_MAX_LEN,
 					(uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				"larger than %u and smaller than %u, as jumbo "
 				"frame is disabled",
 				(uint32_t)RTE_ETHER_MIN_LEN,
-				(uint32_t)RTE_ETHER_MAX_LEN);
+				(uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
@@ -2836,7 +2836,7 @@ i40evf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > I40E_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/i40e/i40e_fdir.c +1 -1
index 0343e8b09a..f5defcf585 100644
@@ -116,7 +116,7 @@ i40e_fdir_rx_queue_init(struct i40e_rx_queue *rxq)
 #endif
 	rx_ctx.dtype = i40e_header_split_none;
 	rx_ctx.hsplit_0 = I40E_HEADER_SPLIT_NONE;
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = I40E_ETH_MAX_LEN;
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
 	rx_ctx.tphdata_ena = 1;
drivers/net/i40e/i40e_rxtx.c +4 -4
index 5df9a9df56..b8859bbff2 100644
@@ -2797,23 +2797,23 @@ i40e_rx_queue_config(struct i40e_rx_queue *rxq)
 		RTE_MIN((uint32_t)(hw->func_caps.rx_buf_chain_len *
 			rxq->rx_buf_len), data->dev_conf.rxmode.max_rx_pkt_len);
 	if (data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= I40E_ETH_MAX_LEN ||
 			rxq->max_pkt_len > I40E_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)I40E_ETH_MAX_LEN,
 				    (uint32_t)I40E_FRAME_SIZE_MAX);
 			return I40E_ERR_CONFIG;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-			rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+			rxq->max_pkt_len > I40E_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)I40E_ETH_MAX_LEN);
 			return I40E_ERR_CONFIG;
 		}
 	}
Signature · 1 line
2.17.1
author
#101 lore raw

PATCH v3 8/22 net/iavf: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 3fd7a3719c66 ("net/avf: enable ops for MTU setting")
Fixes 69dd4c3d0898 ("net/avf: enable queue and device")
---
 drivers/net/iavf/iavf.h        |  1 +
 drivers/net/iavf/iavf_ethdev.c | 10 +++++-----
 2 files changed, 6 insertions(+), 5 deletions(-)
drivers/net/iavf/iavf.h +1 -0
index af11268fe3..c934d2e614 100644
@@ -73,6 +73,7 @@
 #define IAVF_VLAN_TAG_SIZE               4
 #define IAVF_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IAVF_VLAN_TAG_SIZE * 2)
+#define IAVF_ETH_MAX_LEN (RTE_ETHER_MTU + IAVF_ETH_OVERHEAD)
 
 #define IAVF_32_BIT_WIDTH (CHAR_BIT * 4)
 #define IAVF_48_BIT_WIDTH (CHAR_BIT * 6)
drivers/net/iavf/iavf_ethdev.c +5 -5
index e22c62ed00..250ef6fc9a 100644
@@ -460,23 +460,23 @@ iavf_init_rxq(struct rte_eth_dev *dev, struct iavf_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= IAVF_ETH_MAX_LEN ||
 		    max_pkt_len > IAVF_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)IAVF_ETH_MAX_LEN,
 				    (uint32_t)IAVF_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > IAVF_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)IAVF_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -1303,7 +1303,7 @@ iavf_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IAVF_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#102 lore raw

PATCH v3 9/22 net/ice: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 84dc7a95a2d3 ("net/ice: enable flow director engine")
Fixes 1b009275e2c8 ("net/ice: add Rx queue init in DCF")
Fixes ae2bdd0219cb ("net/ice: support MTU setting")
Fixes 50370662b727 ("net/ice: support device and queue ops")
---
 drivers/net/ice/ice_dcf_ethdev.c |  8 ++++----
 drivers/net/ice/ice_ethdev.c     |  2 +-
 drivers/net/ice/ice_ethdev.h     |  1 +
 drivers/net/ice/ice_rxtx.c       | 10 +++++-----
 4 files changed, 11 insertions(+), 10 deletions(-)
drivers/net/ice/ice_dcf_ethdev.c +4 -4
index a9e78064d4..d46734a57b 100644
@@ -60,23 +60,23 @@ ice_dcf_init_rxq(struct rte_eth_dev *dev, struct ice_rx_queue *rxq)
 	 * correctly.
 	 */
 	if (dev->data->dev_conf.rxmode.offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
drivers/net/ice/ice_ethdev.c +1 -1
index e2799a8eb2..ba533a78ee 100644
@@ -3912,7 +3912,7 @@ ice_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ICE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/ice/ice_ethdev.h +1 -0
index 899f446cde..2b03c59671 100644
@@ -135,6 +135,7 @@
  */
 #define ICE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + ICE_VLAN_TAG_SIZE * 2)
+#define ICE_ETH_MAX_LEN (RTE_ETHER_MTU + ICE_ETH_OVERHEAD)
 
 #define ICE_RXTX_BYTES_HIGH(bytes) ((bytes) & ~ICE_40_BIT_MASK)
 #define ICE_RXTX_BYTES_LOW(bytes) ((bytes) & ICE_40_BIT_MASK)
drivers/net/ice/ice_rxtx.c +5 -5
index d052bd0f1b..c98328ce0b 100644
@@ -246,23 +246,23 @@ ice_program_hw_rx_queue(struct ice_rx_queue *rxq)
 				   dev->data->dev_conf.rxmode.max_rx_pkt_len);
 
 	if (rxmode->offloads & DEV_RX_OFFLOAD_JUMBO_FRAME) {
-		if (rxq->max_pkt_len <= RTE_ETHER_MAX_LEN ||
+		if (rxq->max_pkt_len <= ICE_ETH_MAX_LEN ||
 		    rxq->max_pkt_len > ICE_FRAME_SIZE_MAX) {
 			PMD_DRV_LOG(ERR, "maximum packet length must "
 				    "be larger than %u and smaller than %u,"
 				    "as jumbo frame is enabled",
-				    (uint32_t)RTE_ETHER_MAX_LEN,
+				    (uint32_t)ICE_ETH_MAX_LEN,
 				    (uint32_t)ICE_FRAME_SIZE_MAX);
 			return -EINVAL;
 		}
 	} else {
 		if (rxq->max_pkt_len < RTE_ETHER_MIN_LEN ||
-		    rxq->max_pkt_len > RTE_ETHER_MAX_LEN) {
+		    rxq->max_pkt_len > ICE_ETH_MAX_LEN) {
 			PMD_DRV_LOG(ERR, "maximum packet length must be "
 				    "larger than %u and smaller than %u, "
 				    "as jumbo frame is disabled",
 				    (uint32_t)RTE_ETHER_MIN_LEN,
-				    (uint32_t)RTE_ETHER_MAX_LEN);
+				    (uint32_t)ICE_ETH_MAX_LEN);
 			return -EINVAL;
 		}
 	}
@@ -701,7 +701,7 @@ ice_fdir_program_hw_rx_queue(struct ice_rx_queue *rxq)
 	rx_ctx.hbuf = rxq->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S;
 	rx_ctx.dtype = 0; /* No Header Split mode */
 	rx_ctx.dsize = 1; /* 32B descriptors */
-	rx_ctx.rxmax = RTE_ETHER_MAX_LEN;
+	rx_ctx.rxmax = ICE_ETH_MAX_LEN;
 	/* TPH: Transaction Layer Packet (TLP) processing hints */
 	rx_ctx.tphrdesc_ena = 1;
 	rx_ctx.tphwdesc_ena = 1;
Signature · 1 line
2.17.1
author
#103 lore raw

PATCH v3 10/22 net/ipn3ke: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 70d6b7f550f4 ("net/ipn3ke: add representor")
---
 drivers/net/ipn3ke/ipn3ke_ethdev.h      | 1 +
 drivers/net/ipn3ke/ipn3ke_representor.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/ipn3ke/ipn3ke_ethdev.h +1 -0
index 9b0cf309c8..a6815a9cca 100644
@@ -640,6 +640,7 @@ ipn3ke_tm_ops_get(struct rte_eth_dev *ethdev,
  */
 #define IPN3KE_ETH_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + IPN3KE_VLAN_TAG_SIZE * 2)
+#define IPN3KE_ETH_MAX_LEN (RTE_ETHER_MTU + IPN3KE_ETH_OVERHEAD)
 
 #define IPN3KE_MAC_FRAME_SIZE_MAX    9728
 #define IPN3KE_MAC_RX_FRAME_MAXLENGTH    0x00AE
drivers/net/ipn3ke/ipn3ke_representor.c +1 -1
index 8a53602576..9e15cce34f 100644
@@ -2801,7 +2801,7 @@ ipn3ke_rpst_mtu_set(struct rte_eth_dev *ethdev, uint16_t mtu)
 		return -EBUSY;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > IPN3KE_ETH_MAX_LEN)
 		dev_data->dev_conf.rxmode.offloads |=
 			(uint64_t)(DEV_RX_OFFLOAD_JUMBO_FRAME);
 	else
Signature · 1 line
2.17.1
author
#104 lore raw

PATCH v3 11/22 net/octeontx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 3151e6a687a3 ("net/octeontx: support MTU")
---
 drivers/net/octeontx/octeontx_ethdev.c | 2 +-
 drivers/net/octeontx/octeontx_ethdev.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/octeontx/octeontx_ethdev.c +1 -1
index 3ee7b043fd..81779885d5 100644
@@ -552,7 +552,7 @@ octeontx_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > OCCTX_L2_MAX_LEN)
 		nic->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		nic->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/octeontx/octeontx_ethdev.h +1 -0
index 7246fb6d1d..780a094ffa 100644
@@ -44,6 +44,7 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define OCCTX_L2_OVERHEAD	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + \
 				 OCCTX_MAX_VTAG_ACT_SIZE)
+#define OCCTX_L2_MAX_LEN	(RTE_ETHER_MTU + OCCTX_L2_OVERHEAD)
 
 /* Since HW FRS includes NPC VTAG insertion space, user has reduced FRS */
 #define OCCTX_MAX_FRS	\
Signature · 1 line
2.17.1
author
#105 lore raw

PATCH v3 12/22 net/octeontx2: fix the jumbo frame flag condition for mtu

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 0e2efd02db58 ("net/octeontx2: add MTU set operation")
---
 drivers/net/octeontx2/otx2_ethdev.h     | 2 ++
 drivers/net/octeontx2/otx2_ethdev_ops.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)
drivers/net/octeontx2/otx2_ethdev.h +2 -0
index 3b9871f4dc..99f0469d89 100644
@@ -51,6 +51,8 @@
 /* ETH_HLEN+ETH_FCS+2*VLAN_HLEN */
 #define NIX_L2_OVERHEAD \
 	(RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN + 8)
+#define NIX_L2_MAX_LEN \
+	(RTE_ETHER_MTU + NIX_L2_OVERHEAD)
 
 /* HW config of frame size doesn't include FCS */
 #define NIX_MAX_HW_FRS			9212
drivers/net/octeontx2/otx2_ethdev_ops.c +1 -1
index b36d37b9f7..963cc285ed 100644
@@ -58,7 +58,7 @@ otx2_nix_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 	if (rc)
 		return rc;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIX_L2_MAX_LEN)
 		dev->rx_offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->rx_offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#106 lore raw

PATCH v3 13/22 net/qede: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 200645ac7909 ("net/qede: set MTU")
---
 drivers/net/qede/qede_ethdev.c | 2 +-
 drivers/net/qede/qede_rxtx.h   | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/qede/qede_ethdev.c +1 -1
index 549013557c..6919378b8e 100644
@@ -2367,7 +2367,7 @@ static int qede_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 			fp->rxq->rx_buf_size = rc;
 		}
 	}
-	if (max_rx_pkt_len > RTE_ETHER_MAX_LEN)
+	if (frame_size > QEDE_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
drivers/net/qede/qede_rxtx.h +1 -0
index d7ff870b20..fcb564a1bb 100644
@@ -71,6 +71,7 @@
 				 + (QEDE_LLC_SNAP_HDR_LEN) + 2)
 
 #define QEDE_MAX_ETHER_HDR_LEN	(RTE_ETHER_HDR_LEN + QEDE_ETH_OVERHEAD)
+#define QEDE_ETH_MAX_LEN	(RTE_ETHER_MTU + QEDE_MAX_ETHER_HDR_LEN)
 
 #define QEDE_RSS_OFFLOAD_ALL    (ETH_RSS_IPV4			|\
 				 ETH_RSS_NONFRAG_IPV4_TCP	|\
Signature · 1 line
2.17.1
author
#107 lore raw

PATCH v3 14/22 net/sfc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports VLAN tag. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU', that perhaps impacts the cases of the jumbo frame related.

Fixes ff6a1197c3b1 ("net/sfc: convert to new Rx offload API")
---
 drivers/net/sfc/sfc_ethdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/sfc/sfc_ethdev.c +1 -1
index 93fc7baa0d..f2f5336435 100644
@@ -1017,7 +1017,7 @@ sfc_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 	 * The driver does not use it, but other PMDs update jumbo frame
 	 * flag and max_rx_pkt_len when MTU is set.
 	 */
-	if (mtu > RTE_ETHER_MAX_LEN) {
+	if (mtu > RTE_ETHER_MTU) {
 		struct rte_eth_rxmode *rxmode = &dev->data->dev_conf.rxmode;
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	}
Signature · 1 line
2.17.1
author
#108 lore raw

PATCH v3 15/22 net/thunderx: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition, but the Ether overhead is larger than 18 when it supports dual VLAN tags. That will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU' and overhead, that perhaps impacts the cases of the jumbo frame related.

Fixes 65d9804edc05 ("net/thunderx: support MTU configuration")
---
 drivers/net/thunderx/base/nicvf_hw_defs.h | 1 +
 drivers/net/thunderx/nicvf_ethdev.c       | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
drivers/net/thunderx/base/nicvf_hw_defs.h +1 -0
index b12c8ec50a..adc8ec943d 100644
@@ -176,6 +176,7 @@
 #define NIC_HW_MAX_MTU                  (9190)
 #define NIC_HW_MAX_FRS                  (NIC_HW_MAX_MTU + NIC_HW_L2_OVERHEAD)
 #define NIC_HW_MAX_SEGS                 (12)
+#define NIC_HW_L2_MAX_LEN		(RTE_ETHER_MTU + NIC_HW_L2_OVERHEAD)
 
 /* Descriptor alignments */
 #define NICVF_RBDR_BASE_ALIGN_BYTES     (128) /* 7 bits */
drivers/net/thunderx/nicvf_ethdev.c +1 -1
index b6bb05e500..c2e7c334d4 100644
@@ -176,7 +176,7 @@ nicvf_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 		(frame_size + 2 * VLAN_TAG_SIZE > buffsz * NIC_HW_MAX_SEGS))
 		return -EINVAL;
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > NIC_HW_L2_MAX_LEN)
 		rxmode->offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		rxmode->offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#109 lore raw

PATCH v3 16/22 net/ixgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 59d0ecdbf0e1 ("ethdev: MTU accessors")
Fixes 95a27b3ba5f5 ("net/ixgbe: enable jumbo frame for VF")
---
 drivers/net/ixgbe/ixgbe_ethdev.c | 2 +-
 drivers/net/ixgbe/ixgbe_ethdev.h | 3 +++
 drivers/net/ixgbe/ixgbe_pf.c     | 2 +-
 3 files changed, 5 insertions(+), 2 deletions(-)
drivers/net/ixgbe/ixgbe_ethdev.c +1 -1
index d7a1806ab8..fa0f5afd03 100644
@@ -5173,7 +5173,7 @@ ixgbe_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
 
 	/* switch to jumbo mode if needed */
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > IXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		hlreg0 |= IXGBE_HLREG0_JUMBOEN;
drivers/net/ixgbe/ixgbe_ethdev.h +3 -0
index 3d35ea791b..a0ce18ca24 100644
@@ -104,6 +104,9 @@
 /* The overhead from MTU to max frame size. */
 #define IXGBE_ETH_OVERHEAD (RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
 
+/* The max frame size with default MTU */
+#define IXGBE_ETH_MAX_LEN  (RTE_ETHER_MTU + IXGBE_ETH_OVERHEAD)
+
 /* bit of VXLAN tunnel type | 7 bits of zeros  | 8 bits of zeros*/
 #define IXGBE_FDIR_VXLAN_TUNNEL_TYPE    0x8000
 /* bit of NVGRE tunnel type | 7 bits of zeros  | 8 bits of zeros*/
drivers/net/ixgbe/ixgbe_pf.c +1 -1
index 833863af5a..89698e8470 100644
@@ -575,7 +575,7 @@ ixgbe_set_vf_lpe(struct rte_eth_dev *dev, __rte_unused uint32_t vf, uint32_t *ms
 		   IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT;
 	if (max_frs < new_mtu) {
 		hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0);
-		if (new_mtu > RTE_ETHER_MAX_LEN) {
+		if (new_mtu > IXGBE_ETH_MAX_LEN) {
 			dev->data->dev_conf.rxmode.offloads |=
 				DEV_RX_OFFLOAD_JUMBO_FRAME;
 			hlreg0 |= IXGBE_HLREG0_JUMBOEN;
Signature · 1 line
2.17.1
author
#110 lore raw

PATCH v3 17/22 net/cxgbe: fix the jumbo frame flag condition

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 4b2eff452d2e ("cxgbe: enable jumbo frames")
Fixes 0ec33be4c857 ("cxgbe: allow to change mtu")
---
 drivers/net/cxgbe/cxgbe.h        | 4 ++++
 drivers/net/cxgbe/cxgbe_ethdev.c | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)
drivers/net/cxgbe/cxgbe.h +4 -0
index ef62af1c3f..7c89a028bf 100644
@@ -19,6 +19,10 @@
 #define CXGBE_MAX_RX_PKTLEN (9000 + RTE_ETHER_HDR_LEN + \
 				RTE_ETHER_CRC_LEN) /* max pkt */
 
+/* The max frame size with default MTU */
+#define CXGBE_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /* Max poll time is 100 * 100msec = 10 sec */
 #define CXGBE_LINK_STATUS_POLL_MS 100 /* 100ms */
 #define CXGBE_LINK_STATUS_POLL_CNT 100 /* Max number of times to poll */
drivers/net/cxgbe/cxgbe_ethdev.c +2 -2
index 98d0362fa3..480d6f58a8 100644
@@ -300,7 +300,7 @@ int cxgbe_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -EINVAL;
 
 	/* set to jumbo mode if needed */
-	if (new_mtu > RTE_ETHER_MAX_LEN)
+	if (new_mtu > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
@@ -669,7 +669,7 @@ int cxgbe_dev_rx_queue_setup(struct rte_eth_dev *eth_dev,
 		rxq->fl.size = temp_nb_desc;
 
 	/* Set to jumbo mode if necessary */
-	if (pkt_len > RTE_ETHER_MAX_LEN)
+	if (pkt_len > CXGBE_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#111 lore raw

PATCH v3 18/22 net/axgbe: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes b58d8781fa1f ("net/axgbe: support setting MTU")
---
 drivers/net/axgbe/axgbe_ethdev.c | 2 +-
 drivers/net/axgbe/axgbe_ethdev.h | 6 ++++++
 2 files changed, 7 insertions(+), 1 deletion(-)
drivers/net/axgbe/axgbe_ethdev.c +1 -1
index ddd903680d..ebe9a2876d 100644
@@ -1490,7 +1490,7 @@ static int axgb_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 				dev->data->port_id);
 		return -EBUSY;
 	}
-	if (frame_size > RTE_ETHER_MAX_LEN) {
+	if (frame_size > AXGBE_ETH_MAX_LEN) {
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 		val = 1;
drivers/net/axgbe/axgbe_ethdev.h +6 -0
index 1481fd9ff3..a6226729fe 100644
@@ -125,6 +125,12 @@
 /* MDIO port types */
 #define AXGMAC_MAX_C22_PORT		3
 
+/* The max frame size with default MTU */
+#define AXGBE_ETH_MAX_LEN ( \
+	RTE_ETHER_MTU + \
+	RTE_ETHER_HDR_LEN + \
+	RTE_ETHER_CRC_LEN)
+
 /* Helper macro for descriptor handling
  *  Always use AXGBE_GET_DESC_DATA to access the descriptor data
  *  since the index is free-running and needs to be and-ed
Signature · 1 line
2.17.1
author
#112 lore raw

PATCH v3 19/22 net/enetc: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 5d5589b0c858 ("net/enetc: support MTU update and jumbo frames")
---
 drivers/net/enetc/enetc.h        | 4 ++++
 drivers/net/enetc/enetc_ethdev.c | 2 +-
 2 files changed, 5 insertions(+), 1 deletion(-)
drivers/net/enetc/enetc.h +4 -0
index 14ef3bc18b..7163633bce 100644
@@ -29,6 +29,10 @@
 /* maximum frame size supported */
 #define ENETC_MAC_MAXFRM_SIZE	9600
 
+/* The max frame size with default MTU */
+#define ENETC_ETH_MAX_LEN (RTE_ETHER_MTU + \
+		RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 /*
  * upper_32_bits - return bits 32-63 of a number
  * @n: the number we're accessing
drivers/net/enetc/enetc_ethdev.c +1 -1
index 6ff3022874..4d2c9c0474 100644
@@ -677,7 +677,7 @@ enetc_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 		return -EINVAL;
 	}
 
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > ENETC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads &=
 						DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#113 lore raw

PATCH v3 20/22 net/hinic: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 254bd849b132 ("net/hinic: set jumbo frame offload flag")
---
 drivers/net/hinic/hinic_pmd_ethdev.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/hinic/hinic_pmd_ethdev.c +4 -1
index 62642354cf..5a2c171099 100644
@@ -75,6 +75,9 @@
 #define HINIC_PKTLEN_TO_MTU(pktlen)	\
 	((pktlen) - (ETH_HLEN + ETH_CRC_LEN))
 
+/* The max frame size with default MTU */
+#define HINIC_ETH_MAX_LEN (RTE_ETHER_MTU + ETH_HLEN + ETH_CRC_LEN)
+
 /* lro numer limit for one packet */
 #define HINIC_LRO_WQE_NUM_DEFAULT	8
 
@@ -1556,7 +1559,7 @@ static int hinic_dev_set_mtu(struct rte_eth_dev *dev, uint16_t mtu)
 
 	/* update max frame size */
 	frame_size = HINIC_MTU_TO_PKTLEN(mtu);
-	if (frame_size > RTE_ETHER_MAX_LEN)
+	if (frame_size > HINIC_ETH_MAX_LEN)
 		dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
Signature · 1 line
2.17.1
author
#114 lore raw

PATCH v3 21/22 net/nfp: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will change the boundary condition with 'RTE_ETHER_MTU', that perhaps impacts the cases of the jumbo frame related.

Fixes d4a27a3b092a ("nfp: add basic features")
---
 drivers/net/nfp/nfp_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/nfp/nfp_net.c +1 -1
index 1608bf5ea1..9ea24e5bda 100644
@@ -1508,7 +1508,7 @@ nfp_net_dev_mtu_set(struct rte_eth_dev *dev, uint16_t mtu)
 	}
 
 	/* switch to jumbo mode if needed */
-	if ((uint32_t)mtu > RTE_ETHER_MAX_LEN)
+	if ((uint32_t)mtu > RTE_ETHER_MTU)
 		dev->data->dev_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
 		dev->data->dev_conf.rxmode.offloads &= ~DEV_RX_OFFLOAD_JUMBO_FRAME;
Signature · 1 line
2.17.1
author
#115 lore raw

PATCH v3 22/22 net/liquidio: fix the jumbo frame flag condition for mtu set

In reply to Steve Yang

The jumbo frame uses the 'RTE_ETHER_MAX_LEN' as boundary condition. If the Ether overhead is larger than 18 when it supports VLAN tag, that will cause the jumbo flag rx offload is wrong when MTU size is 'RTE_ETHER_MTU'.

This fix will normalize the boundary condition with 'RTE_ETHER_MTU' and overhead even though current overhead is 18.

Fixes 9f1c00266d82 ("net/liquidio: add API to set MTU")
---
 drivers/net/liquidio/lio_ethdev.c | 2 +-
 drivers/net/liquidio/lio_ethdev.h | 3 +++
 2 files changed, 4 insertions(+), 1 deletion(-)
drivers/net/liquidio/lio_ethdev.c +1 -1
index d4dd3768cd..eb0fdab45a 100644
@@ -481,7 +481,7 @@ lio_dev_mtu_set(struct rte_eth_dev *eth_dev, uint16_t mtu)
 		return -1;
 	}
 
-	if (frame_len > RTE_ETHER_MAX_LEN)
+	if (frame_len > LIO_ETH_MAX_LEN)
 		eth_dev->data->dev_conf.rxmode.offloads |=
 			DEV_RX_OFFLOAD_JUMBO_FRAME;
 	else
drivers/net/liquidio/lio_ethdev.h +3 -0
index 74cd2fb6c6..d33be1c44d 100644
@@ -13,6 +13,9 @@
 #define LIO_LSC_TIMEOUT		100000 /* 100000us (100ms) */
 #define LIO_MAX_CMD_TIMEOUT     10000 /* 10000ms (10s) */
 
+/* The max frame size with default MTU */
+#define LIO_ETH_MAX_LEN (RTE_ETHER_MTU + RTE_ETHER_HDR_LEN + RTE_ETHER_CRC_LEN)
+
 #define LIO_DEV(_eth_dev)		((_eth_dev)->data->dev_private)
 
 /* LIO Response condition variable */
Signature · 1 line
2.17.1