[PATCH net-next V2 0/5] Mellanox driver updates 2013-08-19

[PATCH net-next V2 0/5] Mellanox driver updates 2013-08-19

[Amir Vadai]

Hi Dave,

This small patchset contains 2 fixes to bad handling of error flows in TX
datapath, and a fix to a bug in mlx4_en_dcbnl_ieee_setpfc() where global pause
frames were enabled whenever PFC was configured.
Also added a patch to reduce the scope of some local variables in the moved
block of code and it's surrounding.

Thanks,
Amir

---
Changes from V1:
- Split coding style fix from logical fix

Changes from V0:
- Missing new lines + typo's
- Fixed frags dma leak
- Use local for ddev
- New patch (4/4), to reduce scope of some locals

Amir Vadai (4):
  net/mlx4_en: Coding style cleanup in mlx4_en_dcbnl_ieee_setpfc()
  net/mlx4_en: Notify user when TX ring in error state
  net/mlx4_en: Fix handling of dma_map failure
  net/mlx4_en: Reduce scope of local variables in mlx4_en_xmit

Eugenia Emantayev (1):
  net/mlx4_en: Disable global flow control when PFC enabled

 drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c |  15 ++--
 drivers/net/ethernet/mellanox/mlx4/en_tx.c     | 116 +++++++++++++++++--------
 2 files changed, 87 insertions(+), 44 deletions(-)

-- 
1.8.3.4

[PATCH net-next V2 1/5] net/mlx4_en: Coding style cleanup in mlx4_en_dcbnl_ieee_setpfc()

[Amir Vadai]

Fix some coding style issues in this function.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 9d4a1ea..f71fba9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -160,6 +160,7 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 		struct ieee_pfc *pfc)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_port_profile *prof = priv->prof;
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int err;
 
@@ -169,15 +170,17 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 			pfc->mbc,
 			pfc->delay);
 
-	priv->prof->rx_pause = priv->prof->tx_pause = !!pfc->pfc_en;
-	priv->prof->rx_ppp = priv->prof->tx_ppp = pfc->pfc_en;
+	prof->rx_pause = !!pfc->pfc_en;
+	prof->tx_pause = !!pfc->pfc_en;
+	prof->rx_ppp = pfc->pfc_en;
+	prof->tx_ppp = pfc->pfc_en;
 
 	err = mlx4_SET_PORT_general(mdev->dev, priv->port,
 				    priv->rx_skb_size + ETH_FCS_LEN,
-				    priv->prof->tx_pause,
-				    priv->prof->tx_ppp,
-				    priv->prof->rx_pause,
-				    priv->prof->rx_ppp);
+				    prof->tx_pause,
+				    prof->tx_ppp,
+				    prof->rx_pause,
+				    prof->rx_ppp);
 	if (err)
 		en_err(priv, "Failed setting pause params\n");
 
-- 
1.8.3.4

[PATCH net-next V2 2/5] net/mlx4_en: Disable global flow control when PFC enabled

[Amir Vadai]

From: Eugenia Emantayev <eugenia@mellanox.com>

Fix a bug when FC and PFC are enabled/disabled at the same time.
According to ConnectX-3 Programmer Manual these two features are mutial
exclusive.  So make sure when enabling PFC to turn off global FC and
vise versa.  Otherwise it hurts the performance.


Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index f71fba9..b4881b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -170,8 +170,8 @@ static int mlx4_en_dcbnl_ieee_setpfc(struct net_device *dev,
 			pfc->mbc,
 			pfc->delay);
 
-	prof->rx_pause = !!pfc->pfc_en;
-	prof->tx_pause = !!pfc->pfc_en;
+	prof->rx_pause = !pfc->pfc_en;
+	prof->tx_pause = !pfc->pfc_en;
 	prof->rx_ppp = pfc->pfc_en;
 	prof->tx_ppp = pfc->pfc_en;
 
-- 
1.8.3.4

[PATCH net-next V2 3/5] net/mlx4_en: Notify user when TX ring in error state

[Amir Vadai]

When hardware gets into error state, must notify user about it.
When QP in error state no traffic will be tx'ed from the attached
tx_ring.

Driver should know how to recover from this unexpected state. I will send later
on the recovery flow, but having the print shouldn't be delayed.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 6dcca98..0d691e3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -362,6 +362,15 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 		 */
 		rmb();
 
+		if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
+			     MLX4_CQE_OPCODE_ERROR)) {
+			struct mlx4_err_cqe *cqe_err = (struct mlx4_err_cqe *)cqe;
+
+			en_err(priv, "CQE error - vendor syndrome: 0x%x syndrome: 0x%x\n",
+			       cqe_err->vendor_err_syndrome,
+			       cqe_err->syndrome);
+		}
+
 		/* Skip over last polled CQE */
 		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
 
-- 
1.8.3.4

[PATCH net-next V2 4/5] net/mlx4_en: Fix handling of dma_map failure

[Amir Vadai]

Result of skb_frag_dma_map() and dma_map_single() wasn't checked.
Added a check and proper handling in case of failure.
Moved the mapping to the beginning of mlx4_en_xmit(), before updating
the ring data structure to make error handling easier.


Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 97 +++++++++++++++++++-----------
 1 file changed, 62 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0d691e3..c28868b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -588,6 +588,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct device *ddev = priv->ddev;
 	struct mlx4_en_tx_ring *ring;
 	struct mlx4_en_tx_desc *tx_desc;
 	struct mlx4_wqe_data_seg *data;
@@ -674,6 +675,56 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	tx_info->skb = skb;
 	tx_info->nr_txbb = nr_txbb;
 
+	if (lso_header_size)
+		data = ((void *)&tx_desc->lso + ALIGN(lso_header_size + 4,
+						      DS_SIZE));
+	else
+		data = &tx_desc->data;
+
+	/* valid only for none inline segments */
+	tx_info->data_offset = (void *)data - (void *)tx_desc;
+
+	tx_info->linear = (lso_header_size < skb_headlen(skb) &&
+			   !is_inline(skb, NULL)) ? 1 : 0;
+
+	data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1;
+
+	if (is_inline(skb, &fragptr)) {
+		tx_info->inl = 1;
+	} else {
+		/* Map fragments */
+		for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+			frag = &skb_shinfo(skb)->frags[i];
+			dma = skb_frag_dma_map(ddev, frag,
+					       0, skb_frag_size(frag),
+					       DMA_TO_DEVICE);
+			if (dma_mapping_error(ddev, dma))
+				goto tx_drop_unmap;
+
+			data->addr = cpu_to_be64(dma);
+			data->lkey = cpu_to_be32(mdev->mr.key);
+			wmb();
+			data->byte_count = cpu_to_be32(skb_frag_size(frag));
+			--data;
+		}
+
+		/* Map linear part */
+		if (tx_info->linear) {
+			u32 byte_count = skb_headlen(skb) - lso_header_size;
+			dma = dma_map_single(ddev, skb->data +
+					     lso_header_size, byte_count,
+					     PCI_DMA_TODEVICE);
+			if (dma_mapping_error(ddev, dma))
+				goto tx_drop_unmap;
+
+			data->addr = cpu_to_be64(dma);
+			data->lkey = cpu_to_be32(mdev->mr.key);
+			wmb();
+			data->byte_count = cpu_to_be32(byte_count);
+		}
+		tx_info->inl = 0;
+	}
+
 	/*
 	 * For timestamping add flag to skb_shinfo and
 	 * set flag for further reference
@@ -720,8 +771,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* Copy headers;
 		 * note that we already verified that it is linear */
 		memcpy(tx_desc->lso.header, skb->data, lso_header_size);
-		data = ((void *) &tx_desc->lso +
-			ALIGN(lso_header_size + 4, DS_SIZE));
 
 		priv->port_stats.tso_packets++;
 		i = ((skb->len - lso_header_size) / skb_shinfo(skb)->gso_size) +
@@ -733,7 +782,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		op_own = cpu_to_be32(MLX4_OPCODE_SEND) |
 			((ring->prod & ring->size) ?
 			 cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
-		data = &tx_desc->data;
 		tx_info->nr_bytes = max_t(unsigned int, skb->len, ETH_ZLEN);
 		ring->packets++;
 
@@ -742,38 +790,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes);
 	AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len);
 
-
-	/* valid only for none inline segments */
-	tx_info->data_offset = (void *) data - (void *) tx_desc;
-
-	tx_info->linear = (lso_header_size < skb_headlen(skb) && !is_inline(skb, NULL)) ? 1 : 0;
-	data += skb_shinfo(skb)->nr_frags + tx_info->linear - 1;
-
-	if (!is_inline(skb, &fragptr)) {
-		/* Map fragments */
-		for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
-			frag = &skb_shinfo(skb)->frags[i];
-			dma = skb_frag_dma_map(priv->ddev, frag,
-					       0, skb_frag_size(frag),
-					       DMA_TO_DEVICE);
-			data->addr = cpu_to_be64(dma);
-			data->lkey = cpu_to_be32(mdev->mr.key);
-			wmb();
-			data->byte_count = cpu_to_be32(skb_frag_size(frag));
-			--data;
-		}
-
-		/* Map linear part */
-		if (tx_info->linear) {
-			dma = dma_map_single(priv->ddev, skb->data + lso_header_size,
-					     skb_headlen(skb) - lso_header_size, PCI_DMA_TODEVICE);
-			data->addr = cpu_to_be64(dma);
-			data->lkey = cpu_to_be32(mdev->mr.key);
-			wmb();
-			data->byte_count = cpu_to_be32(skb_headlen(skb) - lso_header_size);
-		}
-		tx_info->inl = 0;
-	} else {
+	if (tx_info->inl) {
 		build_inline_wqe(tx_desc, skb, real_size, &vlan_tag, tx_ind, fragptr);
 		tx_info->inl = 1;
 	}
@@ -813,6 +830,16 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	return NETDEV_TX_OK;
 
+tx_drop_unmap:
+	en_err(priv, "DMA mapping error\n");
+
+	for (i++; i < skb_shinfo(skb)->nr_frags; i++) {
+		data++;
+		dma_unmap_page(ddev, (dma_addr_t) be64_to_cpu(data->addr),
+			       be32_to_cpu(data->byte_count),
+			       PCI_DMA_TODEVICE);
+	}
+
 tx_drop:
 	dev_kfree_skb_any(skb);
 	priv->stats.tx_dropped++;
-- 
1.8.3.4

[PATCH net-next V2 5/5] net/mlx4_en: Reduce scope of local variables in mlx4_en_xmit

[Amir Vadai]

Some variables could have their scope reduced.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index c28868b..0698c82 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -592,14 +592,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct mlx4_en_tx_ring *ring;
 	struct mlx4_en_tx_desc *tx_desc;
 	struct mlx4_wqe_data_seg *data;
-	struct skb_frag_struct *frag;
 	struct mlx4_en_tx_info *tx_info;
-	struct ethhdr *ethh;
 	int tx_ind = 0;
 	int nr_txbb;
 	int desc_size;
 	int real_size;
-	dma_addr_t dma;
 	u32 index, bf_index;
 	__be32 op_own;
 	u16 vlan_tag = 0;
@@ -694,6 +691,9 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		/* Map fragments */
 		for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+			struct skb_frag_struct *frag;
+			dma_addr_t dma;
+
 			frag = &skb_shinfo(skb)->frags[i];
 			dma = skb_frag_dma_map(ddev, frag,
 					       0, skb_frag_size(frag),
@@ -711,6 +711,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		/* Map linear part */
 		if (tx_info->linear) {
 			u32 byte_count = skb_headlen(skb) - lso_header_size;
+			dma_addr_t dma;
+
 			dma = dma_map_single(ddev, skb->data +
 					     lso_header_size, byte_count,
 					     PCI_DMA_TODEVICE);
@@ -749,6 +751,8 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (priv->flags & MLX4_EN_FLAG_ENABLE_HW_LOOPBACK) {
+		struct ethhdr *ethh;
+
 		/* Copy dst mac address to wqe. This allows loopback in eSwitch,
 		 * so that VFs and PF can communicate with each other
 		 */
-- 
1.8.3.4

Re: [PATCH net-next V2 0/5] Mellanox driver updates 2013-08-19

[David Miller]

From: Amir Vadai <amirv@mellanox.com>
Date: Wed, 21 Aug 2013 10:08:54 +0300

> This small patchset contains 2 fixes to bad handling of error flows in TX
> datapath, and a fix to a bug in mlx4_en_dcbnl_ieee_setpfc() where global pause
> frames were enabled whenever PFC was configured.
> Also added a patch to reduce the scope of some local variables in the moved
> block of code and it's surrounding.

Series applied, thanks.