From 1a91de28831a1bd913e14dacf25763f3672e24a9 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Wed, 7 May 2014 12:52:57 -0700
Subject: mellanox: Logging message cleanups

Use a more current logging style.

o Coalesce formats
o Add missing spaces for coalesced formats
o Align arguments for modified formats
o Add missing newlines for some logging messages
o Use DRV_NAME as part of format instead of %s, DRV_NAME to
  reduce overall text.
o Use ..., ##__VA_ARGS__ instead of args... in macros
o Correct a few format typos
o Use a single line message where appropriate

Signed-off-by: Joe Perches <joe@perches.com>
Acked-By: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/eq.c | 85 +++++++++++++--------------------
 1 file changed, 33 insertions(+), 52 deletions(-)

(limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')

diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d501a2b0fb79..6c088bc1845b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -152,14 +152,13 @@ void mlx4_gen_slave_eqe(struct work_struct *work)
 				if (i != dev->caps.function &&
 				    master->slave_state[i].active)
 					if (mlx4_GEN_EQE(dev, i, eqe))
-						mlx4_warn(dev, "Failed to "
-							  " generate event "
-							  "for slave %d\n", i);
+						mlx4_warn(dev, "Failed to generate event for slave %d\n",
+							  i);
 			}
 		} else {
 			if (mlx4_GEN_EQE(dev, slave, eqe))
-				mlx4_warn(dev, "Failed to generate event "
-					       "for slave %d\n", slave);
+				mlx4_warn(dev, "Failed to generate event for slave %d\n",
+					  slave);
 		}
 		++slave_eq->cons;
 	}
@@ -177,8 +176,8 @@ static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
 	s_eqe = &slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)];
 	if ((!!(s_eqe->owner & 0x80)) ^
 	    (!!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE))) {
-		mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. "
-			  "No free EQE on slave events queue\n", slave);
+		mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. No free EQE on slave events queue\n",
+			  slave);
 		spin_unlock_irqrestore(&slave_eq->event_lock, flags);
 		return;
 	}
@@ -375,9 +374,9 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave,
 		}
 		break;
 	default:
-		pr_err("%s: BUG!!! UNKNOWN state: "
-		       "slave:%d, port:%d\n", __func__, slave, port);
-			goto out;
+		pr_err("%s: BUG!!! UNKNOWN state: slave:%d, port:%d\n",
+		       __func__, slave, port);
+		goto out;
 	}
 	ret = mlx4_get_slave_port_state(dev, slave, port);
 
@@ -425,8 +424,8 @@ void mlx4_master_handle_slave_flr(struct work_struct *work)
 	for (i = 0 ; i < dev->num_slaves; i++) {
 
 		if (MLX4_COMM_CMD_FLR == slave_state[i].last_cmd) {
-			mlx4_dbg(dev, "mlx4_handle_slave_flr: "
-				 "clean slave: %d\n", i);
+			mlx4_dbg(dev, "mlx4_handle_slave_flr: clean slave: %d\n",
+				 i);
 
 			mlx4_delete_all_resources_for_slave(dev, i);
 			/*return the slave to running mode*/
@@ -438,8 +437,8 @@ void mlx4_master_handle_slave_flr(struct work_struct *work)
 			err = mlx4_cmd(dev, 0, i, 0, MLX4_CMD_INFORM_FLR_DONE,
 				       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 			if (err)
-				mlx4_warn(dev, "Failed to notify FW on "
-					  "FLR done (slave:%d)\n", i);
+				mlx4_warn(dev, "Failed to notify FW on FLR done (slave:%d)\n",
+					  i);
 		}
 	}
 }
@@ -490,9 +489,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						be32_to_cpu(eqe->event.qp.qpn)
 						& 0xffffff, &slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_dbg(dev, "QP event %02x(%02x) on "
-						 "EQ %d at index %u: could "
-						 "not get slave id (%d)\n",
+					mlx4_dbg(dev, "QP event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
 						 eqe->type, eqe->subtype,
 						 eq->eqn, eq->cons_index, ret);
 					break;
@@ -520,23 +517,19 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 						& 0xffffff,
 						&slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_warn(dev, "SRQ event %02x(%02x) "
-						  "on EQ %d at index %u: could"
-						  " not get slave id (%d)\n",
+					mlx4_warn(dev, "SRQ event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
 						  eqe->type, eqe->subtype,
 						  eq->eqn, eq->cons_index, ret);
 					break;
 				}
-				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x,"
-					  " event: %02x(%02x)\n", __func__,
-					  slave,
+				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x, event: %02x(%02x)\n",
+					  __func__, slave,
 					  be32_to_cpu(eqe->event.srq.srqn),
 					  eqe->type, eqe->subtype);
 
 				if (!ret && slave != dev->caps.function) {
-					mlx4_warn(dev, "%s: sending event "
-						  "%02x(%02x) to slave:%d\n",
-						   __func__, eqe->type,
+					mlx4_warn(dev, "%s: sending event %02x(%02x) to slave:%d\n",
+						  __func__, eqe->type,
 						  eqe->subtype, slave);
 					mlx4_slave_event(dev, slave, eqe);
 					break;
@@ -569,8 +562,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH) {
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN"
-							 " to slave: %d, port:%d\n",
+						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
 						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
@@ -634,11 +626,9 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 					be32_to_cpu(eqe->event.cq_err.cqn)
 					& 0xffffff, &slave);
 				if (ret && ret != -ENOENT) {
-					mlx4_dbg(dev, "CQ event %02x(%02x) on "
-						 "EQ %d at index %u: could "
-						  "not get slave id (%d)\n",
-						  eqe->type, eqe->subtype,
-						  eq->eqn, eq->cons_index, ret);
+					mlx4_dbg(dev, "CQ event %02x(%02x) on EQ %d at index %u: could not get slave id (%d)\n",
+						 eqe->type, eqe->subtype,
+						 eq->eqn, eq->cons_index, ret);
 					break;
 				}
 
@@ -667,8 +657,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 		case MLX4_EVENT_TYPE_COMM_CHANNEL:
 			if (!mlx4_is_master(dev)) {
-				mlx4_warn(dev, "Received comm channel event "
-					       "for non master device\n");
+				mlx4_warn(dev, "Received comm channel event for non master device\n");
 				break;
 			}
 			memcpy(&priv->mfunc.master.comm_arm_bit_vector,
@@ -681,8 +670,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_FLR_EVENT:
 			flr_slave = be32_to_cpu(eqe->event.flr_event.slave_id);
 			if (!mlx4_is_master(dev)) {
-				mlx4_warn(dev, "Non-master function received"
-					       "FLR event\n");
+				mlx4_warn(dev, "Non-master function received FLR event\n");
 				break;
 			}
 
@@ -711,22 +699,17 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			if (eqe->subtype == MLX4_FATAL_WARNING_SUBTYPE_WARMING) {
 				if (mlx4_is_master(dev))
 					for (i = 0; i < dev->num_slaves; i++) {
-						mlx4_dbg(dev, "%s: Sending "
-							"MLX4_FATAL_WARNING_SUBTYPE_WARMING"
-							" to slave: %d\n", __func__, i);
+						mlx4_dbg(dev, "%s: Sending MLX4_FATAL_WARNING_SUBTYPE_WARMING to slave: %d\n",
+							 __func__, i);
 						if (i == dev->caps.function)
 							continue;
 						mlx4_slave_event(dev, i, eqe);
 					}
-				mlx4_err(dev, "Temperature Threshold was reached! "
-					"Threshold: %d celsius degrees; "
-					"Current Temperature: %d\n",
-					be16_to_cpu(eqe->event.warming.warning_threshold),
-					be16_to_cpu(eqe->event.warming.current_temperature));
+				mlx4_err(dev, "Temperature Threshold was reached! Threshold: %d celsius degrees; Current Temperature: %d\n",
+					 be16_to_cpu(eqe->event.warming.warning_threshold),
+					 be16_to_cpu(eqe->event.warming.current_temperature));
 			} else
-				mlx4_warn(dev, "Unhandled event FATAL WARNING (%02x), "
-					  "subtype %02x on EQ %d at index %u. owner=%x, "
-					  "nent=0x%x, slave=%x, ownership=%s\n",
+				mlx4_warn(dev, "Unhandled event FATAL WARNING (%02x), subtype %02x on EQ %d at index %u. owner=%x, nent=0x%x, slave=%x, ownership=%s\n",
 					  eqe->type, eqe->subtype, eq->eqn,
 					  eq->cons_index, eqe->owner, eq->nent,
 					  eqe->slave_id,
@@ -743,9 +726,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
-			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at "
-				  "index %u. owner=%x, nent=0x%x, slave=%x, "
-				  "ownership=%s\n",
+			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at index %u. owner=%x, nent=0x%x, slave=%x, ownership=%s\n",
 				  eqe->type, eqe->subtype, eq->eqn,
 				  eq->cons_index, eqe->owner, eq->nent,
 				  eqe->slave_id,
@@ -1088,7 +1069,7 @@ static int mlx4_map_clr_int(struct mlx4_dev *dev)
 	priv->clr_base = ioremap(pci_resource_start(dev->pdev, priv->fw.clr_int_bar) +
 				 priv->fw.clr_int_base, MLX4_CLR_INT_SIZE);
 	if (!priv->clr_base) {
-		mlx4_err(dev, "Couldn't map interrupt clear register, aborting.\n");
+		mlx4_err(dev, "Couldn't map interrupt clear register, aborting\n");
 		return -ENOMEM;
 	}
 
-- 
cgit v1.2.3


From 2eacc23c422b4553030168f315cb49522fa1b1f6 Mon Sep 17 00:00:00 2001
From: Yuval Atias <yuvala@mellanox.com>
Date: Wed, 14 May 2014 12:15:10 +0300
Subject: net/mlx4_core: Enforce irq affinity changes immediatly

During heavy traffic, napi is constatntly polling the complition queue
and no interrupt is fired. Because of that, changes to irq affinity are
ignored until traffic is stopped and resumed.

By registering to the irq notifier mechanism, and forcing interrupt when
affinity is changed, irq affinity changes will be immediatly enforced.

Signed-off-by: Yuval Atias <yuvala@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cq.c    |  3 ++
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 11 +++++-
 drivers/net/ethernet/mellanox/mlx4/en_tx.c |  6 +++
 drivers/net/ethernet/mellanox/mlx4/eq.c    | 62 ++++++++++++++++++++++++++++++
 include/linux/mlx4/device.h                |  3 ++
 5 files changed, 83 insertions(+), 2 deletions(-)

(limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')

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_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/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;
-- 
cgit v1.2.3


From 70a640d0dae3a9b1b222ce673eb5d92c263ddd61 Mon Sep 17 00:00:00 2001
From: Yuval Atias <yuvala@mellanox.com>
Date: Sun, 25 May 2014 17:47:27 +0300
Subject: net/mlx4_en: Use affinity hint
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The “affinity hint” mechanism is used by the user space
daemon, irqbalancer, to indicate a preferred CPU mask for irqs.
Irqbalancer can use this hint to balance the irqs between the
cpus indicated by the mask.

We wish the HCA to preferentially map the IRQs it uses to numa cores
close to it.  To accomplish this, we use cpumask_set_cpu_local_first(), that
sets the affinity hint according the following policy:
First it maps IRQs to “close” numa cores.  If these are exhausted, the
remaining IRQs are mapped to “far” numa cores.

Signed-off-by: Yuval Atias <yuvala@mellanox.com>
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c              |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     |  6 +++++-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 30 ++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/eq.c        | 13 ++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 +
 include/linux/mlx4/device.h                    |  2 +-
 6 files changed, 50 insertions(+), 4 deletions(-)

(limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 199c7896f081..58b1f239ac2b 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1897,7 +1897,7 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 				 i, j, dev->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
 			if (mlx4_assign_eq(dev, name, NULL,
-					   &ibdev->eq_table[eq])) {
+					   &ibdev->eq_table[eq], NULL)) {
 				/* Use legacy (same as mlx4_en driver) */
 				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
 				ibdev->eq_table[eq] =
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 636963db598a..ea2cd72e5368 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -118,11 +118,15 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (cq->is_tx == RX) {
 		if (mdev->dev->caps.comp_pool) {
 			if (!cq->vector) {
+				struct mlx4_en_rx_ring *ring =
+					priv->rx_ring[cq->ring];
+
 				sprintf(name, "%s-%d", priv->dev->name,
 					cq->ring);
 				/* Set IRQ for specific name (per ring) */
 				if (mlx4_assign_eq(mdev->dev, name, rmap,
-						   &cq->vector)) {
+						   &cq->vector,
+						   ring->affinity_mask)) {
 					cq->vector = (cq->ring + 1 + priv->port)
 					    % mdev->dev->caps.num_comp_vectors;
 					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 58209bd0c94c..05d135572abc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1526,6 +1526,32 @@ static void mlx4_en_linkstate(struct work_struct *work)
 	mutex_unlock(&mdev->state_lock);
 }
 
+static void mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
+	int numa_node = priv->mdev->dev->numa_node;
+
+	if (numa_node == -1)
+		return;
+
+	if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) {
+		en_err(priv, "Failed to allocate core mask\n");
+		return;
+	}
+
+	if (cpumask_set_cpu_local_first(ring_idx, numa_node,
+					ring->affinity_mask)) {
+		en_err(priv, "Failed setting affinity hint\n");
+		free_cpumask_var(ring->affinity_mask);
+		ring->affinity_mask = NULL;
+	}
+}
+
+static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
+{
+	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
+	priv->rx_ring[ring_idx]->affinity_mask = NULL;
+}
 
 int mlx4_en_start_port(struct net_device *dev)
 {
@@ -1567,6 +1593,8 @@ int mlx4_en_start_port(struct net_device *dev)
 
 		mlx4_en_cq_init_lock(cq);
 
+		mlx4_en_init_affinity_hint(priv, i);
+
 		err = mlx4_en_activate_cq(priv, cq, i);
 		if (err) {
 			en_err(priv, "Failed activating Rx CQ\n");
@@ -1847,6 +1875,8 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 			msleep(1);
 		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 		mlx4_en_deactivate_cq(priv, cq);
+
+		mlx4_en_free_affinity_hint(priv, i);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index d954ec1eac17..f91659e5fa13 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1376,7 +1376,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 EXPORT_SYMBOL(mlx4_test_interrupts);
 
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector)
+		   int *vector, cpumask_var_t cpu_hint_mask)
 {
 
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1411,6 +1411,15 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 			}
 			mlx4_assign_irq_notifier(priv, dev,
 						 priv->eq_table.eq[vec].irq);
+			if (cpu_hint_mask) {
+				err = irq_set_affinity_hint(
+						priv->eq_table.eq[vec].irq,
+						cpu_hint_mask);
+				if (err) {
+					mlx4_warn(dev, "Failed setting affinity hint\n");
+					/*we dont want to break here*/
+				}
+			}
 
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
@@ -1441,6 +1450,8 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 			irq_set_affinity_notifier(
 				priv->eq_table.eq[vec].irq,
 				NULL);
+			irq_set_affinity_hint(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/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index b5db1bf361dc..0e15295bedd6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -313,6 +313,7 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	int hwtstamp_rx_filter;
+	cpumask_var_t affinity_mask;
 };
 
 struct mlx4_en_cq {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index ca38871a585c..b9b70e00e3c1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1161,7 +1161,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector);
+		   int *vector, cpumask_t *cpu_hint_mask);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
-- 
cgit v1.2.3


From 96b2e73c5471542cb9c622c4360716684f8797ed Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 2 Jun 2014 00:18:48 -0700
Subject: Revert "net/mlx4_en: Use affinity hint"

This reverts commit 70a640d0dae3a9b1b222ce673eb5d92c263ddd61.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c              |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_cq.c     |  6 +-----
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 30 --------------------------
 drivers/net/ethernet/mellanox/mlx4/eq.c        | 13 +----------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h   |  1 -
 include/linux/mlx4/device.h                    |  2 +-
 6 files changed, 4 insertions(+), 50 deletions(-)

(limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 58b1f239ac2b..199c7896f081 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1897,7 +1897,7 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 				 i, j, dev->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
 			if (mlx4_assign_eq(dev, name, NULL,
-					   &ibdev->eq_table[eq], NULL)) {
+					   &ibdev->eq_table[eq])) {
 				/* Use legacy (same as mlx4_en driver) */
 				pr_warn("Can't allocate EQ %d; reverting to legacy\n", eq);
 				ibdev->eq_table[eq] =
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index ea2cd72e5368..636963db598a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -118,15 +118,11 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	if (cq->is_tx == RX) {
 		if (mdev->dev->caps.comp_pool) {
 			if (!cq->vector) {
-				struct mlx4_en_rx_ring *ring =
-					priv->rx_ring[cq->ring];
-
 				sprintf(name, "%s-%d", priv->dev->name,
 					cq->ring);
 				/* Set IRQ for specific name (per ring) */
 				if (mlx4_assign_eq(mdev->dev, name, rmap,
-						   &cq->vector,
-						   ring->affinity_mask)) {
+						   &cq->vector)) {
 					cq->vector = (cq->ring + 1 + priv->port)
 					    % mdev->dev->caps.num_comp_vectors;
 					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 05d135572abc..58209bd0c94c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -1526,32 +1526,6 @@ static void mlx4_en_linkstate(struct work_struct *work)
 	mutex_unlock(&mdev->state_lock);
 }
 
-static void mlx4_en_init_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
-{
-	struct mlx4_en_rx_ring *ring = priv->rx_ring[ring_idx];
-	int numa_node = priv->mdev->dev->numa_node;
-
-	if (numa_node == -1)
-		return;
-
-	if (!zalloc_cpumask_var(&ring->affinity_mask, GFP_KERNEL)) {
-		en_err(priv, "Failed to allocate core mask\n");
-		return;
-	}
-
-	if (cpumask_set_cpu_local_first(ring_idx, numa_node,
-					ring->affinity_mask)) {
-		en_err(priv, "Failed setting affinity hint\n");
-		free_cpumask_var(ring->affinity_mask);
-		ring->affinity_mask = NULL;
-	}
-}
-
-static void mlx4_en_free_affinity_hint(struct mlx4_en_priv *priv, int ring_idx)
-{
-	free_cpumask_var(priv->rx_ring[ring_idx]->affinity_mask);
-	priv->rx_ring[ring_idx]->affinity_mask = NULL;
-}
 
 int mlx4_en_start_port(struct net_device *dev)
 {
@@ -1593,8 +1567,6 @@ int mlx4_en_start_port(struct net_device *dev)
 
 		mlx4_en_cq_init_lock(cq);
 
-		mlx4_en_init_affinity_hint(priv, i);
-
 		err = mlx4_en_activate_cq(priv, cq, i);
 		if (err) {
 			en_err(priv, "Failed activating Rx CQ\n");
@@ -1875,8 +1847,6 @@ void mlx4_en_stop_port(struct net_device *dev, int detach)
 			msleep(1);
 		mlx4_en_deactivate_rx_ring(priv, priv->rx_ring[i]);
 		mlx4_en_deactivate_cq(priv, cq);
-
-		mlx4_en_free_affinity_hint(priv, i);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index f91659e5fa13..d954ec1eac17 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -1376,7 +1376,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 EXPORT_SYMBOL(mlx4_test_interrupts);
 
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector, cpumask_var_t cpu_hint_mask)
+		   int *vector)
 {
 
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1411,15 +1411,6 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 			}
 			mlx4_assign_irq_notifier(priv, dev,
 						 priv->eq_table.eq[vec].irq);
-			if (cpu_hint_mask) {
-				err = irq_set_affinity_hint(
-						priv->eq_table.eq[vec].irq,
-						cpu_hint_mask);
-				if (err) {
-					mlx4_warn(dev, "Failed setting affinity hint\n");
-					/*we dont want to break here*/
-				}
-			}
 
 			eq_set_ci(&priv->eq_table.eq[vec], 1);
 		}
@@ -1450,8 +1441,6 @@ void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 			irq_set_affinity_notifier(
 				priv->eq_table.eq[vec].irq,
 				NULL);
-			irq_set_affinity_hint(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/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 0e15295bedd6..b5db1bf361dc 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -313,7 +313,6 @@ struct mlx4_en_rx_ring {
 	unsigned long csum_ok;
 	unsigned long csum_none;
 	int hwtstamp_rx_filter;
-	cpumask_var_t affinity_mask;
 };
 
 struct mlx4_en_cq {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b9b70e00e3c1..ca38871a585c 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1161,7 +1161,7 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
 int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
-		   int *vector, cpumask_t *cpu_hint_mask);
+		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
-- 
cgit v1.2.3


From 35f6f45368632f21bd27559c44dbb1cab51d8947 Mon Sep 17 00:00:00 2001
From: Amir Vadai <amirv@mellanox.com>
Date: Sun, 29 Jun 2014 11:54:55 +0300
Subject: net/mlx4_en: Don't use irq_affinity_notifier to track changes in IRQ
 affinity map

IRQ affinity notifier can only have a single notifier - cpu_rmap
notifier. Can't use it to track changes in IRQ affinity map.
Detect IRQ affinity changes by comparing CPU to current IRQ affinity map
during NAPI poll thread.

CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ben Hutchings <ben@decadent.org.uk>
Fixes: 2eacc23 ("net/mlx4_core: Enforce irq affinity changes immediatly")
Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/cq.c      |  2 -
 drivers/net/ethernet/mellanox/mlx4/en_cq.c   |  4 ++
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 16 +++++--
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   |  6 ---
 drivers/net/ethernet/mellanox/mlx4/eq.c      | 69 ++++------------------------
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 +
 include/linux/mlx4/device.h                  |  4 +-
 7 files changed, 28 insertions(+), 74 deletions(-)

(limited to 'drivers/net/ethernet/mellanox/mlx4/eq.c')

diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 80f725228f5b..56022d647837 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -294,8 +294,6 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	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_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 4b2130760eed..1213cc71348c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -128,6 +128,10 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 					mlx4_warn(mdev, "Failed assigning an EQ to %s, falling back to legacy EQ's\n",
 						  name);
 				}
+
+				cq->irq_desc =
+					irq_to_desc(mlx4_eq_get_irq(mdev->dev,
+								    cq->vector));
 			}
 		} else {
 			cq->vector = (cq->ring + 1 + priv->port) %
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index d2d415732d99..96724170308a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -40,6 +40,7 @@
 #include <linux/if_ether.h>
 #include <linux/if_vlan.h>
 #include <linux/vmalloc.h>
+#include <linux/irq.h>
 
 #include "mlx4_en.h"
 
@@ -896,16 +897,25 @@ int mlx4_en_poll_rx_cq(struct napi_struct *napi, int budget)
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget) {
+		int cpu_curr;
+		const struct cpumask *aff;
+
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
-		if (unlikely(cq->mcq.irq_affinity_change)) {
-			cq->mcq.irq_affinity_change = false;
+
+		cpu_curr = smp_processor_id();
+		aff = irq_desc_get_irq_data(cq->irq_desc)->affinity;
+
+		if (unlikely(!cpumask_test_cpu(cpu_curr, aff))) {
+			/* Current cpu is not according to smp_irq_affinity -
+			 * probably affinity changed. need to stop this NAPI
+			 * poll, and restart it on the right CPU
+			 */
 			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 8be7483f8236..ac3dead3792c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -474,15 +474,9 @@ 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 d954ec1eac17..2a004b347e1d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -53,11 +53,6 @@ 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)
@@ -1088,57 +1083,6 @@ 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);
@@ -1409,8 +1353,6 @@ 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);
 		}
@@ -1427,6 +1369,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 }
 EXPORT_SYMBOL(mlx4_assign_eq);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return priv->eq_table.eq[vec].irq;
+}
+EXPORT_SYMBOL(mlx4_eq_get_irq);
+
 void mlx4_release_eq(struct mlx4_dev *dev, int vec)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1438,9 +1388,6 @@ 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/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 0e15295bedd6..624e1939e9ee 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -343,6 +343,7 @@ struct mlx4_en_cq {
 #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD)
 	spinlock_t poll_lock; /* protects from LLS/napi conflicts */
 #endif  /* CONFIG_NET_RX_BUSY_POLL */
+	struct irq_desc *irq_desc;
 };
 
 struct mlx4_en_port_profile {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b12f4bbd064c..35b51e7af886 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -578,8 +578,6 @@ struct mlx4_cq {
 	u32			cons_index;
 
 	u16                     irq;
-	bool                    irq_affinity_change;
-
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
 	int			arm_sn;
@@ -1167,6 +1165,8 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
 		   int *vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
+int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec);
+
 int mlx4_get_phys_port_id(struct mlx4_dev *dev);
 int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
 int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
-- 
cgit v1.2.3