Merge branch 'mlx4-next'

Or Gerlitz says:

====================
Mellanox driver update 2014-05-12

This patchset introduce some small bug fixes:

Eyal fixed some compilation and syntactic checkers warnings. Ido fixed a
coruption in user priority mapping when changing number of channels. Shani
fixed some other problems when modifying MAC address. Yuval fixed a problem
when changing IRQ affinity during high traffic - IRQ changes got effective
only after the first pause in traffic.

This patchset was tested and applied over commit 93dccc5: "mdio_bus: fix
devm_mdiobus_alloc_size export"

Changes from V1:
- applied feedback from Dave to use true/false and not 0/1 in patch 1/9
- removed the patch from Noa which adddressed a bug in flow steering table
  when using a bond device, as the fix might need to be in the bonding driver,
  this is now dicussed in the netdev thread "bonding directly changes
  underlying device address"

Changes from V0:
- Patch 1/9 - net/mlx4_core: Enforce irq affinity changes immediatly
  - Moved the new members to a hot cache line as Eric suggested
====================

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

10 files changed, 110 insertions, 15 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 24201033661b..357dcb0f04fb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -473,6 +473,13 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 		goto out;
 	}
 
+	if (out_is_imm && !out_param) {
+		mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+			 op);
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
 			    in_modifier, op_modifier, op, CMD_POLL_TOKEN, 0);
 	if (err)
@@ -551,6 +558,13 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	cmd->free_head = context->next;
 	spin_unlock(&cmd->context_lock);
 
+	if (out_is_imm && !out_param) {
+		mlx4_err(dev, "response expected while output mailbox is NULL for command 0x%x\n",
+			 op);
+		err = -EINVAL;
+		goto out;
+	}
+
 	init_completion(&context->done);
 
 	mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 0487121e4a0f..8542030b89cf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -293,6 +293,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	atomic_set(&cq->refcount, 1);
 	init_completion(&cq->free);
 
+	cq->irq = priv->eq_table.eq[cq->vector].irq;
+	cq->irq_affinity_change = false;
+
 	return 0;
 
 err_radix:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index c3736045e7af..a72d99fd7a2d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -1151,7 +1151,8 @@ static int mlx4_en_set_channels(struct net_device *dev,
 	netif_set_real_num_tx_queues(dev, priv->tx_ring_num);
 	netif_set_real_num_rx_queues(dev, priv->rx_ring_num);
 
-	mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
+	if (dev->num_tc)
+		mlx4_en_setup_tc(dev, MLX4_EN_NUM_UP);
 
 	en_warn(priv, "Using %d TX rings\n", priv->tx_ring_num);
 	en_warn(priv, "Using %d RX rings\n", priv->rx_ring_num);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 79c6f467d17e..58209bd0c94c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -130,7 +130,7 @@ static enum mlx4_net_trans_rule_id mlx4_ip_proto_to_trans_rule_id(u8 ip_proto)
 	case IPPROTO_TCP:
 		return MLX4_NET_TRANS_RULE_ID_TCP;
 	default:
-		return -EPROTONOSUPPORT;
+		return MLX4_NET_TRANS_RULE_NUM;
 	}
 };
 
@@ -177,7 +177,7 @@ static void mlx4_en_filter_work(struct work_struct *work)
 	int rc;
 	__be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
 
-	if (spec_tcp_udp.id < 0) {
+	if (spec_tcp_udp.id >= MLX4_NET_TRANS_RULE_NUM) {
 		en_warn(priv, "RFS: ignoring unsupported ip protocol (%d)\n",
 			filter->ip_proto);
 		goto ignore;
@@ -770,11 +770,12 @@ static int mlx4_en_do_set_mac(struct mlx4_en_priv *priv)
 					  priv->dev->dev_addr, priv->prev_mac);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
-		memcpy(priv->prev_mac, priv->dev->dev_addr,
-		       sizeof(priv->prev_mac));
 	} else
 		en_dbg(HW, priv, "Port is down while registering mac, exiting...\n");
 
+	memcpy(priv->prev_mac, priv->dev->dev_addr,
+	       sizeof(priv->prev_mac));
+
 	return err;
 }
 
@@ -788,9 +789,8 @@ static int mlx4_en_set_mac(struct net_device *dev, void *addr)
 	if (!is_valid_ether_addr(saddr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
-
 	mutex_lock(&mdev->state_lock);
+	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
 	err = mlx4_en_do_set_mac(priv);
 	mutex_unlock(&mdev->state_lock);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a1512450816d..e8c0d2b832b7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -895,10 +895,17 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 	mlx4_en_cq_unlock_napi(cq);
 
 	/* If we used up all the quota - we're probably not done yet... */
-	if (done == budget)
+	if (done == budget) {
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
-	else {
+		if (unlikely(cq->mcq.irq_affinity_change)) {
+			cq->mcq.irq_affinity_change = false;
+			napi_complete(napi);
+			mlx4_en_arm_cq(priv, cq);
+			return 0;
+		}
+	} else {
 		/* Done for now */
+		cq->mcq.irq_affinity_change = false;
 		napi_complete(napi);
 		mlx4_en_arm_cq(priv, cq);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 89585c6311c3..cb964056d710 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -474,9 +474,15 @@ int mlx4_en_poll_tx_cq(struct napi_struct *napi, int budget)
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done < budget) {
 		/* Done for now */
+		cq->mcq.irq_affinity_change = false;
 		napi_complete(napi);
 		mlx4_en_arm_cq(priv, cq);
 		return done;
+	} else if (unlikely(cq->mcq.irq_affinity_change)) {
+		cq->mcq.irq_affinity_change = false;
+		napi_complete(napi);
+		mlx4_en_arm_cq(priv, cq);
+		return 0;
 	}
 	return budget;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 6c088bc1845b..d954ec1eac17 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -53,6 +53,11 @@ enum {
 	MLX4_EQ_ENTRY_SIZE	= 0x20
 };
 
+struct mlx4_irq_notify {
+	void *arg;
+	struct irq_affinity_notify notify;
+};
+
 #define MLX4_EQ_STATUS_OK	   ( 0 << 28)
 #define MLX4_EQ_STATUS_WRITE_FAIL  (10 << 28)
 #define MLX4_EQ_OWNER_SW	   ( 0 << 24)
@@ -1083,6 +1088,57 @@ static void mlx4_unmap_clr_int(struct mlx4_dev *dev)
 	iounmap(priv->clr_base);
 }
 
+static void mlx4_irq_notifier_notify(struct irq_affinity_notify *notify,
+				     const cpumask_t *mask)
+{
+	struct mlx4_irq_notify *n = container_of(notify,
+						 struct mlx4_irq_notify,
+						 notify);
+	struct mlx4_priv *priv = (struct mlx4_priv *)n->arg;
+	struct radix_tree_iter iter;
+	void **slot;
+
+	radix_tree_for_each_slot(slot, &priv->cq_table.tree, &iter, 0) {
+		struct mlx4_cq *cq = (struct mlx4_cq *)(*slot);
+
+		if (cq->irq == notify->irq)
+			cq->irq_affinity_change = true;
+	}
+}
+
+static void mlx4_release_irq_notifier(struct kref *ref)
+{
+	struct mlx4_irq_notify *n = container_of(ref, struct mlx4_irq_notify,
+						 notify.kref);
+	kfree(n);
+}
+
+static void mlx4_assign_irq_notifier(struct mlx4_priv *priv,
+				     struct mlx4_dev *dev, int irq)
+{
+	struct mlx4_irq_notify *irq_notifier = NULL;
+	int err = 0;
+
+	irq_notifier = kzalloc(sizeof(*irq_notifier), GFP_KERNEL);
+	if (!irq_notifier) {
+		mlx4_warn(dev, "Failed to allocate irq notifier. irq %d\n",
+			  irq);
+		return;
+	}
+
+	irq_notifier->notify.irq = irq;
+	irq_notifier->notify.notify = mlx4_irq_notifier_notify;
+	irq_notifier->notify.release = mlx4_release_irq_notifier;
+	irq_notifier->arg = priv;
+	err = irq_set_affinity_notifier(irq, &irq_notifier->notify);
+	if (err) {
+		kfree(irq_notifier);
+		irq_notifier = NULL;
+		mlx4_warn(dev, "Failed to set irq notifier. irq %d\n", irq);
+	}
+}
+
+
 int mlx4_alloc_eq_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1353,6 +1409,9 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 				continue;
 				/*we dont want to break here*/
 			}
+			mlx4_assign_irq_notifier(priv, dev,
+						 priv->eq_table.eq[vec].irq);
+
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
 	}
@@ -1379,6 +1438,9 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 		  Belonging to a legacy EQ*/
 		mutex_lock(&priv->msix_ctl.pool_lock);
 		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			irq_set_affinity_notifier(
+				priv->eq_table.eq[vec].irq,
+				NULL);
 			free_irq(priv->eq_table.eq[vec].irq,
 				 &priv->eq_table.eq[vec]);
 			priv->msix_ctl.pool_bm &= ~(1ULL << i);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 5db97a4fdc01..a56f6012258d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -104,8 +104,6 @@ module_param(enable_64b_cqe_eqe, bool, 0444);
 MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
-#define HCA_GLOBAL_CAP_MASK            0
-
 #define PF_CONTEXT_BEHAVIOUR_MASK	MLX4_FUNC_CAP_64B_EQE_CQE
 
 static char mlx4_version[] =
@@ -582,9 +580,10 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return err;
 	}
 
-	/*fail if the hca has an unknown capability */
-	if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) !=
-	    HCA_GLOBAL_CAP_MASK) {
+	/* fail if the hca has an unknown global capability
+	 * at this time global_caps should be always zeroed
+	 */
+	if (hca_param.global_caps) {
 		mlx4_err(dev, "Unknown hca global capabilities\n");
 		return -ENOSYS;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 7c6eba622186..4c36def8e10f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -897,7 +897,7 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
 		ret = parse_trans_rule(dev, cur, mailbox->buf + size);
 		if (ret < 0) {
 			mlx4_free_cmd_mailbox(dev, mailbox);
-			return -EINVAL;
+			return ret;
 		}
 		size += ret;
 	}
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index ba87bd21295a..c0468e6f0442 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -577,6 +577,9 @@ struct mlx4_cq {
 
 	u32			cons_index;
 
+	u16                     irq;
+	bool                    irq_affinity_change;
+
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
 	int			arm_sn;