Merge branch 'mlx4-misc-for-4.16'

Tariq Toukan says:

====================
mlx4 misc for 4.16

This patchset contains misc cleanups and improvements
to the mlx4 Core and Eth drivers.

In patches 1 and 2 I reduce and reorder the branches in the RX csum flow.
In patch 3 I align the FMR unmapping flow with the device spec, to allow
  a remapping afterwards.
Patch 4 by Moni changes the default QoS settings so that a pause
  frame stops all traffic regardless of its prio.

Series generated against net-next commit:
836df24a7062 net: hns3: hns3_get_channels() can be static
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 63 insertions, 46 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
index 5f41dc9..1a0c3bf8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_dcb_nl.c
@@ -310,6 +310,7 @@ static int mlx4_en_ets_validate(struct mlx4_en_priv *priv, struct ieee_ets *ets)
 		}
 
 		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
 		case IEEE_8021QAZ_TSA_STRICT:
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
@@ -347,6 +348,10 @@ static int mlx4_en_config_port_scheduler(struct mlx4_en_priv *priv,
 	/* higher TC means higher priority => lower pg */
 	for (i = IEEE_8021QAZ_MAX_TCS - 1; i >= 0; i--) {
 		switch (ets->tc_tsa[i]) {
+		case IEEE_8021QAZ_TSA_VENDOR:
+			pg[i] = MLX4_EN_TC_VENDOR;
+			tc_tx_bw[i] = MLX4_EN_BW_MAX;
+			break;
 		case IEEE_8021QAZ_TSA_STRICT:
 			pg[i] = num_strict++;
 			tc_tx_bw[i] = MLX4_EN_BW_MAX;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 99051a2..21bc17f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3336,6 +3336,13 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->msg_enable = MLX4_EN_MSG_LEVEL;
 #ifdef CONFIG_MLX4_EN_DCB
 	if (!mlx4_is_slave(priv->mdev->dev)) {
+		u8 prio;
+
+		for (prio = 0; prio < IEEE_8021QAZ_MAX_TCS; ++prio) {
+			priv->ets.prio_tc[prio] = prio;
+			priv->ets.tc_tsa[prio]  = IEEE_8021QAZ_TSA_VENDOR;
+		}
+
 		priv->dcbx_cap = DCB_CAP_DCBX_VER_CEE | DCB_CAP_DCBX_HOST |
 			DCB_CAP_DCBX_VER_IEEE;
 		priv->flags |= MLX4_EN_DCB_ENABLED;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 85e28ef..5f9dbc9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -617,6 +617,10 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 	return 0;
 }
 #endif
+
+/* We reach this function only after checking that any of
+ * the (IPv4 | IPv6) bits are set in cqe->status.
+ */
 static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
@@ -632,13 +636,11 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		hdr += sizeof(struct vlan_hdr);
 	}
 
-	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4))
-		return get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV6))
 		return get_fixed_ipv6_csum(hw_checksum, skb, hdr);
 #endif
-	return 0;
+	return get_fixed_ipv4_csum(hw_checksum, skb, hdr);
 }
 
 int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int budget)
@@ -814,33 +816,33 @@ xdp_drop_no_cnt:
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
 			if (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						      MLX4_CQE_STATUS_UDP)) {
-				if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
-				    cqe->checksum == cpu_to_be16(0xffff)) {
-					bool l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
-						(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
-
-					ip_summed = CHECKSUM_UNNECESSARY;
-					hash_type = PKT_HASH_TYPE_L4;
-					if (l2_tunnel)
-						skb->csum_level = 1;
-					ring->csum_ok++;
-				} else {
+				bool l2_tunnel;
+
+				if (!((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
+				      cqe->checksum == cpu_to_be16(0xffff)))
 					goto csum_none;
-				}
+
+				l2_tunnel = (dev->hw_enc_features & NETIF_F_RXCSUM) &&
+					(cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_L2_TUNNEL));
+				ip_summed = CHECKSUM_UNNECESSARY;
+				hash_type = PKT_HASH_TYPE_L4;
+				if (l2_tunnel)
+					skb->csum_level = 1;
+				ring->csum_ok++;
 			} else {
-				if (priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
-				    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
-							       MLX4_CQE_STATUS_IPV6))) {
-					if (check_csum(cqe, skb, va, dev->features)) {
-						goto csum_none;
-					} else {
-						ip_summed = CHECKSUM_COMPLETE;
-						hash_type = PKT_HASH_TYPE_L3;
-						ring->csum_complete++;
-					}
-				} else {
+				if (!(priv->flags & MLX4_EN_FLAG_RX_CSUM_NON_TCP_UDP &&
+				      (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 |
+#if IS_ENABLED(CONFIG_IPV6)
+								 MLX4_CQE_STATUS_IPV6))))
+#else
+								 0))))
+#endif
 					goto csum_none;
-				}
+				if (check_csum(cqe, skb, va, dev->features))
+					goto csum_none;
+				ip_summed = CHECKSUM_COMPLETE;
+				hash_type = PKT_HASH_TYPE_L3;
+				ring->csum_complete++;
 			}
 		} else {
 csum_none:
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 2b72677..7db3d0d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -479,6 +479,7 @@ struct mlx4_en_frag_info {
 #define MLX4_EN_BW_MIN 1
 #define MLX4_EN_BW_MAX 100 /* Utilize 100% of the line */
 
+#define MLX4_EN_TC_VENDOR 0
 #define MLX4_EN_TC_ETS 7
 
 enum dcb_pfc_type {
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index c7c0764..2e84f10 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -1103,30 +1103,16 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_enable);
 void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 		    u32 *lkey, u32 *rkey)
 {
-	struct mlx4_cmd_mailbox *mailbox;
-	int err;
-
 	if (!fmr->maps)
 		return;
 
-	fmr->maps = 0;
+	/* To unmap: it is sufficient to take back ownership from HW */
+	*(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW;
 
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox)) {
-		err = PTR_ERR(mailbox);
-		pr_warn("mlx4_ib: mlx4_alloc_cmd_mailbox failed (%d)\n", err);
-		return;
-	}
+	/* Make sure MPT status is visible */
+	wmb();
 
-	err = mlx4_HW2SW_MPT(dev, NULL,
-			     key_to_hw_index(fmr->mr.key) &
-			     (dev->caps.num_mpts - 1));
-	mlx4_free_cmd_mailbox(dev, mailbox);
-	if (err) {
-		pr_warn("mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n", err);
-		return;
-	}
-	fmr->mr.enabled = MLX4_MPT_EN_SW;
+	fmr->maps = 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
 
@@ -1136,6 +1122,22 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
 
 	if (fmr->maps)
 		return -EBUSY;
+	if (fmr->mr.enabled == MLX4_MPT_EN_HW) {
+		/* In case of FMR was enabled and unmapped
+		 * make sure to give ownership of MPT back to HW
+		 * so HW2SW_MPT command will success.
+		 */
+		*(u8 *)fmr->mpt = MLX4_MPT_STATUS_SW;
+		/* Make sure MPT status is visible before changing MPT fields */
+		wmb();
+		fmr->mpt->length = 0;
+		fmr->mpt->start  = 0;
+		/* Make sure MPT data is visible after changing MPT status */
+		wmb();
+		*(u8 *)fmr->mpt = MLX4_MPT_STATUS_HW;
+		/* make sure MPT status is visible */
+		wmb();
+	}
 
 	ret = mlx4_mr_free(dev, &fmr->mr);
 	if (ret)