From 0ff1fb654bec0cff62ddf81a8a8edec4263604a0 Mon Sep 17 00:00:00 2001
From: Hadar Hen Zion
Date: Thu, 5 Jul 2012 04:03:46 +0000
Subject: {NET, IB}/mlx4: Add device managed flow steering firmware API

The driver is modified to support three operation modes.

If supported by firmware use the device managed flow steering
API, that which we call device managed steering mode. Else, if
the firmware supports the B0 steering mode use it, and finally,
if none of the above, use the A0 steering mode.

When the steering mode is device managed, the code is modified
such that L2 based rules set by the mlx4_en driver for Ethernet
unicast and multicast, and the IB stack multicast attach calls
done through the mlx4_ib driver are all routed to use the device
managed API.

When attaching rule using device managed flow steering API,
the firmware returns a 64 bit registration id, which is to be
provided during detach.

Currently the firmware is always programmed during HCA initialization
to use standard L2 hashing. Future work should be done to allow
configuring the flow-steering hash function with common, non
proprietary means.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c    | 62 ++++++++++++++++++++++++++++++++----
 drivers/infiniband/hw/mlx4/mlx4_ib.h |  1 +
 drivers/infiniband/hw/mlx4/qp.c      |  1 +
 3 files changed, 57 insertions(+), 7 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3530c41fcd1f..8a3a2037b005 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -718,26 +718,53 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 	return ret;
 }
 
+struct mlx4_ib_steering {
+	struct list_head list;
+	u64 reg_id;
+	union ib_gid gid;
+};
+
 static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
 	int err;
 	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+	u64 reg_id;
+	struct mlx4_ib_steering *ib_steering = NULL;
+
+	if (mdev->dev->caps.steering_mode ==
+	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL);
+		if (!ib_steering)
+			return -ENOMEM;
+	}
 
-	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
-				    !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROT_IB_IPV6);
+	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
+				    !!(mqp->flags &
+				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
+				    MLX4_PROT_IB_IPV6, &reg_id);
 	if (err)
-		return err;
+		goto err_malloc;
 
 	err = add_gid_entry(ibqp, gid);
 	if (err)
 		goto err_add;
 
+	if (ib_steering) {
+		memcpy(ib_steering->gid.raw, gid->raw, 16);
+		ib_steering->reg_id = reg_id;
+		mutex_lock(&mqp->mutex);
+		list_add(&ib_steering->list, &mqp->steering_rules);
+		mutex_unlock(&mqp->mutex);
+	}
 	return 0;
 
 err_add:
-	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+			      MLX4_PROT_IB_IPV6, reg_id);
+err_malloc:
+	kfree(ib_steering);
+
 	return err;
 }
 
@@ -765,9 +792,30 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	u8 mac[6];
 	struct net_device *ndev;
 	struct mlx4_ib_gid_entry *ge;
+	u64 reg_id = 0;
+
+	if (mdev->dev->caps.steering_mode ==
+	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		struct mlx4_ib_steering *ib_steering;
+
+		mutex_lock(&mqp->mutex);
+		list_for_each_entry(ib_steering, &mqp->steering_rules, list) {
+			if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) {
+				list_del(&ib_steering->list);
+				break;
+			}
+		}
+		mutex_unlock(&mqp->mutex);
+		if (&ib_steering->list == &mqp->steering_rules) {
+			pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n");
+			return -EINVAL;
+		}
+		reg_id = ib_steering->reg_id;
+		kfree(ib_steering);
+	}
 
-	err = mlx4_multicast_detach(mdev->dev,
-				    &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+	err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+				    MLX4_PROT_IB_IPV6, reg_id);
 	if (err)
 		return err;
 
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index ff36655d23d3..42df4f7a6a5b 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -163,6 +163,7 @@ struct mlx4_ib_qp {
 	u8			state;
 	int			mlx_type;
 	struct list_head	gid_list;
+	struct list_head	steering_rules;
 };
 
 struct mlx4_ib_srq {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8d4ed24aef93..6af19f6c2b11 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -495,6 +495,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
 	INIT_LIST_HEAD(&qp->gid_list);
+	INIT_LIST_HEAD(&qp->steering_rules);
 
 	qp->state	 = IB_QPS_RESET;
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
-- 
cgit v1.2.3-55-g7522


From b1d8eb5a213640f1be98a90e73a241d15b70045c Mon Sep 17 00:00:00 2001
From: Jack Morgenstein
Date: Tue, 19 Jun 2012 11:21:35 +0300
Subject: IB/mlx4: Add debug prints

Define pr_fmt and add some pr_debug prints.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/mad.c     | 19 +++++++++++++++++++
 drivers/infiniband/hw/mlx4/main.c    |  2 +-
 drivers/infiniband/hw/mlx4/mlx4_ib.h | 10 ++++++++++
 drivers/infiniband/hw/mlx4/qp.c      | 27 +++++++++++++++++++++++++--
 4 files changed, 55 insertions(+), 3 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 259b0670b51c..84786a9fb64f 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -242,6 +242,25 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	int err;
 	struct ib_port_attr pattr;
 
+	if (in_wc && in_wc->qp->qp_num) {
+		pr_debug("received MAD: slid:%d sqpn:%d "
+			"dlid_bits:%d dqpn:%d wc_flags:0x%x, cls %x, mtd %x, atr %x\n",
+			in_wc->slid, in_wc->src_qp,
+			in_wc->dlid_path_bits,
+			in_wc->qp->qp_num,
+			in_wc->wc_flags,
+			in_mad->mad_hdr.mgmt_class, in_mad->mad_hdr.method,
+			be16_to_cpu(in_mad->mad_hdr.attr_id));
+		if (in_wc->wc_flags & IB_WC_GRH) {
+			pr_debug("sgid_hi:0x%016llx sgid_lo:0x%016llx\n",
+				 be64_to_cpu(in_grh->sgid.global.subnet_prefix),
+				 be64_to_cpu(in_grh->sgid.global.interface_id));
+			pr_debug("dgid_hi:0x%016llx dgid_lo:0x%016llx\n",
+				 be64_to_cpu(in_grh->dgid.global.subnet_prefix),
+				 be64_to_cpu(in_grh->dgid.global.interface_id));
+		}
+	}
+
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3530c41fcd1f..5266b49c46ee 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -50,7 +50,7 @@
 #include "mlx4_ib.h"
 #include "user.h"
 
-#define DRV_NAME	"mlx4_ib"
+#define DRV_NAME	MLX4_IB_DRV_NAME
 #define DRV_VERSION	"1.0"
 #define DRV_RELDATE	"April 4, 2008"
 
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index ff36655d23d3..5f298afaa81f 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -44,6 +44,16 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 
+#define MLX4_IB_DRV_NAME	"mlx4_ib"
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+#define pr_fmt(fmt)	"<" MLX4_IB_DRV_NAME "> %s: " fmt, __func__
+
+#define mlx4_ib_warn(ibdev, format, arg...) \
+	dev_warn((ibdev)->dma_device, MLX4_IB_DRV_NAME ": " format, ## arg)
+
 enum {
 	MLX4_IB_SQ_MIN_WQE_SHIFT = 6,
 	MLX4_IB_MAX_HEADROOM	 = 2048
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8d4ed24aef93..84b26963c8d4 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1335,11 +1335,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+		pr_debug("qpn 0x%x: invalid attribute mask specified "
+			 "for transition %d to %d. qp_type %d,"
+			 " attr_mask 0x%x\n",
+			 ibqp->qp_num, cur_state, new_state,
+			 ibqp->qp_type, attr_mask);
 		goto out;
+	}
 
 	if ((attr_mask & IB_QP_PORT) &&
 	    (attr->port_num == 0 || attr->port_num > dev->dev->caps.num_ports)) {
+		pr_debug("qpn 0x%x: invalid port number (%d) specified "
+			 "for transition %d to %d. qp_type %d\n",
+			 ibqp->qp_num, attr->port_num, cur_state,
+			 new_state, ibqp->qp_type);
 		goto out;
 	}
 
@@ -1350,17 +1360,30 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 	if (attr_mask & IB_QP_PKEY_INDEX) {
 		int p = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
-		if (attr->pkey_index >= dev->dev->caps.pkey_table_len[p])
+		if (attr->pkey_index >= dev->dev->caps.pkey_table_len[p]) {
+			pr_debug("qpn 0x%x: invalid pkey index (%d) specified "
+				 "for transition %d to %d. qp_type %d\n",
+				 ibqp->qp_num, attr->pkey_index, cur_state,
+				 new_state, ibqp->qp_type);
 			goto out;
+		}
 	}
 
 	if (attr_mask & IB_QP_MAX_QP_RD_ATOMIC &&
 	    attr->max_rd_atomic > dev->dev->caps.max_qp_init_rdma) {
+		pr_debug("qpn 0x%x: max_rd_atomic (%d) too large. "
+			 "Transition %d to %d. qp_type %d\n",
+			 ibqp->qp_num, attr->max_rd_atomic, cur_state,
+			 new_state, ibqp->qp_type);
 		goto out;
 	}
 
 	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC &&
 	    attr->max_dest_rd_atomic > dev->dev->caps.max_qp_dest_rdma) {
+		pr_debug("qpn 0x%x: max_dest_rd_atomic (%d) too large. "
+			 "Transition %d to %d. qp_type %d\n",
+			 ibqp->qp_num, attr->max_dest_rd_atomic, cur_state,
+			 new_state, ibqp->qp_type);
 		goto out;
 	}
 
-- 
cgit v1.2.3-55-g7522


From 00f5ce99dc6ee46c3113393cc8fa12173f9bbcd7 Mon Sep 17 00:00:00 2001
From: Jack Morgenstein
Date: Tue, 19 Jun 2012 11:21:40 +0300
Subject: mlx4: Use port management change event instead of smp_snoop

The port management change event can replace smp_snoop.  If the
capability bit for this event is set in dev-caps, the event is used
(by the driver setting the PORT_MNG_CHG_EVENT bit in the async event
mask in the MAP_EQ fw command).  In this case, when the driver passes
incoming SMP PORT_INFO SET mads to the FW, the FW generates port
management change events to signal any changes to the driver.

If the FW generates these events, smp_snoop shouldn't be invoked in
ib_process_mad(), or duplicate events will occur (once from the
FW-generated event, and once from smp_snoop).

In the case where the FW does not generate port management change
events smp_snoop needs to be invoked to create these events.  The flow
in smp_snoop has been modified to make use of the same procedures as
in the fw-generated-event event case to generate the port management
events (LID change, Client-rereg, Pkey change, and/or GID change).

Port management change event handling required changing the
mlx4_ib_event and mlx4_dispatch_event prototypes; the "param" argument
(last argument) had to be changed to unsigned long in order to
accomodate passing the EQE pointer.

We also needed to move the definition of struct mlx4_eqe from
net/mlx4.h to file device.h -- to make it available to the IB driver,
to handle port management change events.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/mad.c             | 118 ++++++++++++++++++++-------
 drivers/infiniband/hw/mlx4/main.c            |  29 +++++--
 drivers/infiniband/hw/mlx4/mlx4_ib.h         |   9 ++
 drivers/net/ethernet/mellanox/mlx4/en_main.c |   5 +-
 drivers/net/ethernet/mellanox/mlx4/eq.c      |  22 ++++-
 drivers/net/ethernet/mellanox/mlx4/fw.c      |   1 +
 drivers/net/ethernet/mellanox/mlx4/intf.c    |   5 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h    |  63 +-------------
 include/linux/mlx4/device.h                  |  99 +++++++++++++++++++++-
 include/linux/mlx4/driver.h                  |   3 +-
 10 files changed, 249 insertions(+), 105 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 84786a9fb64f..58c45fb5bd31 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -147,47 +147,49 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 }
 
 /*
- * Snoop SM MADs for port info and P_Key table sets, so we can
- * synthesize LID change and P_Key change events.
+ * Snoop SM MADs for port info, GUID info, and  P_Key table sets, so we can
+ * synthesize LID change, Client-Rereg, GID change, and P_Key change events.
  */
 static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
-				u16 prev_lid)
+		      u16 prev_lid)
 {
-	struct ib_event event;
+	struct ib_port_info *pinfo;
+	u16 lid;
 
+	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
 	     mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
-	    mad->mad_hdr.method == IB_MGMT_METHOD_SET) {
-		if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO) {
-			struct ib_port_info *pinfo =
-				(struct ib_port_info *) ((struct ib_smp *) mad)->data;
-			u16 lid = be16_to_cpu(pinfo->lid);
+	    mad->mad_hdr.method == IB_MGMT_METHOD_SET)
+		switch (mad->mad_hdr.attr_id) {
+		case IB_SMP_ATTR_PORT_INFO:
+			pinfo = (struct ib_port_info *) ((struct ib_smp *) mad)->data;
+			lid = be16_to_cpu(pinfo->lid);
 
-			update_sm_ah(to_mdev(ibdev), port_num,
+			update_sm_ah(dev, port_num,
 				     be16_to_cpu(pinfo->sm_lid),
 				     pinfo->neighbormtu_mastersmsl & 0xf);
 
-			event.device	       = ibdev;
-			event.element.port_num = port_num;
+			if (pinfo->clientrereg_resv_subnetto & 0x80)
+				mlx4_ib_dispatch_event(dev, port_num,
+						       IB_EVENT_CLIENT_REREGISTER);
 
-			if (pinfo->clientrereg_resv_subnetto & 0x80) {
-				event.event    = IB_EVENT_CLIENT_REREGISTER;
-				ib_dispatch_event(&event);
-			}
+			if (prev_lid != lid)
+				mlx4_ib_dispatch_event(dev, port_num,
+						       IB_EVENT_LID_CHANGE);
+			break;
 
-			if (prev_lid != lid) {
-				event.event    = IB_EVENT_LID_CHANGE;
-				ib_dispatch_event(&event);
-			}
-		}
+		case IB_SMP_ATTR_PKEY_TABLE:
+			mlx4_ib_dispatch_event(dev, port_num,
+					       IB_EVENT_PKEY_CHANGE);
+			break;
 
-		if (mad->mad_hdr.attr_id == IB_SMP_ATTR_PKEY_TABLE) {
-			event.device	       = ibdev;
-			event.event	       = IB_EVENT_PKEY_CHANGE;
-			event.element.port_num = port_num;
-			ib_dispatch_event(&event);
+		case IB_SMP_ATTR_GUID_INFO:
+			mlx4_ib_dispatch_event(dev, port_num,
+					       IB_EVENT_GID_CHANGE);
+			break;
+		default:
+			break;
 		}
-	}
 }
 
 static void node_desc_override(struct ib_device *dev,
@@ -305,7 +307,8 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		return IB_MAD_RESULT_FAILURE;
 
 	if (!out_mad->mad_hdr.status) {
-		smp_snoop(ibdev, port_num, in_mad, prev_lid);
+		if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV))
+			smp_snoop(ibdev, port_num, in_mad, prev_lid);
 		node_desc_override(ibdev, out_mad);
 	}
 
@@ -446,3 +449,62 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
 			ib_destroy_ah(dev->sm_ah[p]);
 	}
 }
+
+void handle_port_mgmt_change_event(struct work_struct *work)
+{
+	struct ib_event_work *ew = container_of(work, struct ib_event_work, work);
+	struct mlx4_ib_dev *dev = ew->ib_dev;
+	struct mlx4_eqe *eqe = &(ew->ib_eqe);
+	u8 port = eqe->event.port_mgmt_change.port;
+	u32 changed_attr;
+
+	switch (eqe->subtype) {
+	case MLX4_DEV_PMC_SUBTYPE_PORT_INFO:
+		changed_attr = be32_to_cpu(eqe->event.port_mgmt_change.params.port_info.changed_attr);
+
+		/* Update the SM ah - This should be done before handling
+		   the other changed attributes so that MADs can be sent to the SM */
+		if (changed_attr & MSTR_SM_CHANGE_MASK) {
+			u16 lid = be16_to_cpu(eqe->event.port_mgmt_change.params.port_info.mstr_sm_lid);
+			u8 sl = eqe->event.port_mgmt_change.params.port_info.mstr_sm_sl & 0xf;
+			update_sm_ah(dev, port, lid, sl);
+		}
+
+		/* Check if it is a lid change event */
+		if (changed_attr & MLX4_EQ_PORT_INFO_LID_CHANGE_MASK)
+			mlx4_ib_dispatch_event(dev, port, IB_EVENT_LID_CHANGE);
+
+		/* Generate GUID changed event */
+		if (changed_attr & MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK)
+			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+
+		if (changed_attr & MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK)
+			mlx4_ib_dispatch_event(dev, port,
+					       IB_EVENT_CLIENT_REREGISTER);
+		break;
+
+	case MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE:
+		mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE);
+		break;
+	case MLX4_DEV_PMC_SUBTYPE_GUID_INFO:
+		mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+		break;
+	default:
+		pr_warn("Unsupported subtype 0x%x for "
+			"Port Management Change event\n", eqe->subtype);
+	}
+
+	kfree(ew);
+}
+
+void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num,
+			    enum ib_event_type type)
+{
+	struct ib_event event;
+
+	event.device		= &dev->ib_dev;
+	event.element.port_num	= port_num;
+	event.event		= type;
+
+	ib_dispatch_event(&event);
+}
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 5266b49c46ee..4f230c26622d 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -898,7 +898,6 @@ static void update_gids_task(struct work_struct *work)
 	union ib_gid *gids;
 	int err;
 	struct mlx4_dev	*dev = gw->dev->dev;
-	struct ib_event event;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox)) {
@@ -916,10 +915,7 @@ static void update_gids_task(struct work_struct *work)
 		pr_warn("set port command failed\n");
 	else {
 		memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
-		event.device = &gw->dev->ib_dev;
-		event.element.port_num = gw->port;
-		event.event    = IB_EVENT_GID_CHANGE;
-		ib_dispatch_event(&event);
+		mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
 	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
@@ -1383,10 +1379,18 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 }
 
 static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
-			  enum mlx4_dev_event event, int port)
+			  enum mlx4_dev_event event, unsigned long param)
 {
 	struct ib_event ibev;
 	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
+	struct mlx4_eqe *eqe = NULL;
+	struct ib_event_work *ew;
+	int port = 0;
+
+	if (event == MLX4_DEV_EVENT_PORT_MGMT_CHANGE)
+		eqe = (struct mlx4_eqe *)param;
+	else
+		port = (u8)param;
 
 	if (port > ibdev->num_ports)
 		return;
@@ -1405,6 +1409,19 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 		ibev.event = IB_EVENT_DEVICE_FATAL;
 		break;
 
+	case MLX4_DEV_EVENT_PORT_MGMT_CHANGE:
+		ew = kmalloc(sizeof *ew, GFP_ATOMIC);
+		if (!ew) {
+			pr_err("failed to allocate memory for events work\n");
+			break;
+		}
+
+		INIT_WORK(&ew->work, handle_port_mgmt_change_event);
+		memcpy(&ew->ib_eqe, eqe, sizeof *eqe);
+		ew->ib_dev = ibdev;
+		handle_port_mgmt_change_event(&ew->work);
+		return;
+
 	default:
 		return;
 	}
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 5f298afaa81f..23bfbf9ee0e0 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -224,6 +224,12 @@ struct mlx4_ib_dev {
 	int			eq_added;
 };
 
+struct ib_event_work {
+	struct work_struct	work;
+	struct mlx4_ib_dev	*ib_dev;
+	struct mlx4_eqe		ib_eqe;
+};
+
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
 {
 	return container_of(ibdev, struct mlx4_ib_dev, ib_dev);
@@ -381,4 +387,7 @@ static inline int mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 		   union ib_gid *gid);
 
+void mlx4_ib_dispatch_event(struct mlx4_ib_dev *dev, u8 port_num,
+			    enum ib_event_type type);
+
 #endif /* MLX4_IB_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_main.c b/drivers/net/ethernet/mellanox/mlx4/en_main.c
index 69ba57270481..a52922ed85c1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_main.c
@@ -131,7 +131,7 @@ static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port)
 }
 
 static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
-			  enum mlx4_dev_event event, int port)
+			  enum mlx4_dev_event event, unsigned long port)
 {
 	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
 	struct mlx4_en_priv *priv;
@@ -156,7 +156,8 @@ static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 		if (port < 1 || port > dev->caps.num_ports ||
 		    !mdev->pndev[port])
 			return;
-		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event, port);
+		mlx4_warn(mdev, "Unhandled event %d for port %d\n", event,
+			  (int) port);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index bce98d9c0039..9b15d0219950 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -82,6 +82,15 @@ enum {
 			       (1ull << MLX4_EVENT_TYPE_FLR_EVENT)	    | \
 			       (1ull << MLX4_EVENT_TYPE_FATAL_WARNING))
 
+static u64 get_async_ev_mask(struct mlx4_dev *dev)
+{
+	u64 async_ev_mask = MLX4_ASYNC_EVENT_MASK;
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV)
+		async_ev_mask |= (1ull << MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT);
+
+	return async_ev_mask;
+}
+
 static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 {
 	__raw_writel((__force u32) cpu_to_be32((eq->cons_index & 0xffffff) |
@@ -473,6 +482,11 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 			break;
 
+		case MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT:
+			mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_MGMT_CHANGE,
+					    (unsigned long) eqe);
+			break;
+
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
@@ -956,7 +970,7 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		priv->eq_table.have_irq = 1;
 	}
 
-	err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+	err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
 			  priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
 	if (err)
 		mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n",
@@ -996,7 +1010,7 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
-	mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1,
+	mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 1,
 		    priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
 
 	mlx4_free_irqs(dev);
@@ -1040,7 +1054,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 		mlx4_cmd_use_polling(dev);
 
 		/* Map the new eq to handle all asyncronous events */
-		err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+		err = mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
 				  priv->eq_table.eq[i].eqn);
 		if (err) {
 			mlx4_warn(dev, "Failed mapping eq for interrupt test\n");
@@ -1054,7 +1068,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 	}
 
 	/* Return to default */
-	mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0,
+	mlx4_MAP_EQ(dev, get_async_ev_mask(dev), 0,
 		    priv->eq_table.eq[dev->caps.num_comp_vectors].eqn);
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 4281ce09add8..ee9d6b0b4d20 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -109,6 +109,7 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u64 flags)
 		[41] = "Unicast VEP steering support",
 		[42] = "Multicast VEP steering support",
 		[48] = "Counters support",
+		[59] = "Port management change event support",
 	};
 	int i;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index b4e9f6f5cc04..116895ac8b35 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -115,7 +115,8 @@ void mlx4_unregister_interface(struct mlx4_interface *intf)
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_interface);
 
-void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, int port)
+void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
+			 unsigned long param)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_device_context *dev_ctx;
@@ -125,7 +126,7 @@ void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, int por
 
 	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
 		if (dev_ctx->intf->event)
-			dev_ctx->intf->event(dev, dev_ctx->context, type, port);
+			dev_ctx->intf->event(dev, dev_ctx->context, type, param);
 
 	spin_unlock_irqrestore(&priv->ctx_lock, flags);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index e5d20220762c..4d11d12b9db4 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -338,66 +338,6 @@ struct mlx4_srq_context {
 	__be64			db_rec_addr;
 };
 
-struct mlx4_eqe {
-	u8			reserved1;
-	u8			type;
-	u8			reserved2;
-	u8			subtype;
-	union {
-		u32		raw[6];
-		struct {
-			__be32	cqn;
-		} __packed comp;
-		struct {
-			u16	reserved1;
-			__be16	token;
-			u32	reserved2;
-			u8	reserved3[3];
-			u8	status;
-			__be64	out_param;
-		} __packed cmd;
-		struct {
-			__be32	qpn;
-		} __packed qp;
-		struct {
-			__be32	srqn;
-		} __packed srq;
-		struct {
-			__be32	cqn;
-			u32	reserved1;
-			u8	reserved2[3];
-			u8	syndrome;
-		} __packed cq_err;
-		struct {
-			u32	reserved1[2];
-			__be32	port;
-		} __packed port_change;
-		struct {
-			#define COMM_CHANNEL_BIT_ARRAY_SIZE	4
-			u32 reserved;
-			u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
-		} __packed comm_channel_arm;
-		struct {
-			u8	port;
-			u8	reserved[3];
-			__be64	mac;
-		} __packed mac_update;
-		struct {
-			u8	port;
-		} __packed sw_event;
-		struct {
-			__be32	slave_id;
-		} __packed flr_event;
-		struct {
-			__be16  current_temperature;
-			__be16  warning_threshold;
-		} __packed warming;
-	}			event;
-	u8			slave_id;
-	u8			reserved3[2];
-	u8			owner;
-} __packed;
-
 struct mlx4_eq {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *doorbell;
@@ -887,7 +827,8 @@ void mlx4_catas_init(void);
 int mlx4_restart_one(struct pci_dev *pdev);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
-void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, int port);
+void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
+			 unsigned long param);
 
 struct mlx4_dev_cap;
 struct mlx4_init_hca_param;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 8eadf0f14cc5..560b2201519f 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -96,7 +96,8 @@ enum {
 	MLX4_DEV_CAP_FLAG_VEP_UC_STEER	= 1LL << 41,
 	MLX4_DEV_CAP_FLAG_VEP_MC_STEER	= 1LL << 42,
 	MLX4_DEV_CAP_FLAG_COUNTERS	= 1LL << 48,
-	MLX4_DEV_CAP_FLAG_SENSE_SUPPORT	= 1LL << 55
+	MLX4_DEV_CAP_FLAG_SENSE_SUPPORT	= 1LL << 55,
+	MLX4_DEV_CAP_FLAG_PORT_MNG_CHG_EV = 1LL << 59,
 };
 
 enum {
@@ -138,6 +139,7 @@ enum mlx4_event {
 	MLX4_EVENT_TYPE_COMM_CHANNEL	   = 0x18,
 	MLX4_EVENT_TYPE_FATAL_WARNING	   = 0x1b,
 	MLX4_EVENT_TYPE_FLR_EVENT	   = 0x1c,
+	MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d,
 	MLX4_EVENT_TYPE_NONE		   = 0xff,
 };
 
@@ -235,6 +237,24 @@ enum {
 	MLX4_MAX_FAST_REG_PAGES = 511,
 };
 
+enum {
+	MLX4_DEV_PMC_SUBTYPE_GUID_INFO	 = 0x14,
+	MLX4_DEV_PMC_SUBTYPE_PORT_INFO	 = 0x15,
+	MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE	 = 0x16,
+};
+
+/* Port mgmt change event handling */
+enum {
+	MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK	= 1 << 0,
+	MLX4_EQ_PORT_INFO_GID_PFX_CHANGE_MASK		= 1 << 1,
+	MLX4_EQ_PORT_INFO_LID_CHANGE_MASK		= 1 << 2,
+	MLX4_EQ_PORT_INFO_CLIENT_REREG_MASK		= 1 << 3,
+	MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK	= 1 << 4,
+};
+
+#define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \
+			     MLX4_EQ_PORT_INFO_MSTR_SM_LID_CHANGE_MASK)
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
@@ -511,6 +531,81 @@ struct mlx4_dev {
 	int			num_vfs;
 };
 
+struct mlx4_eqe {
+	u8			reserved1;
+	u8			type;
+	u8			reserved2;
+	u8			subtype;
+	union {
+		u32		raw[6];
+		struct {
+			__be32	cqn;
+		} __packed comp;
+		struct {
+			u16	reserved1;
+			__be16	token;
+			u32	reserved2;
+			u8	reserved3[3];
+			u8	status;
+			__be64	out_param;
+		} __packed cmd;
+		struct {
+			__be32	qpn;
+		} __packed qp;
+		struct {
+			__be32	srqn;
+		} __packed srq;
+		struct {
+			__be32	cqn;
+			u32	reserved1;
+			u8	reserved2[3];
+			u8	syndrome;
+		} __packed cq_err;
+		struct {
+			u32	reserved1[2];
+			__be32	port;
+		} __packed port_change;
+		struct {
+			#define COMM_CHANNEL_BIT_ARRAY_SIZE	4
+			u32 reserved;
+			u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
+		} __packed comm_channel_arm;
+		struct {
+			u8	port;
+			u8	reserved[3];
+			__be64	mac;
+		} __packed mac_update;
+		struct {
+			__be32	slave_id;
+		} __packed flr_event;
+		struct {
+			__be16  current_temperature;
+			__be16  warning_threshold;
+		} __packed warming;
+		struct {
+			u8 reserved[3];
+			u8 port;
+			union {
+				struct {
+					__be16 mstr_sm_lid;
+					__be16 port_lid;
+					__be32 changed_attr;
+					u8 reserved[3];
+					u8 mstr_sm_sl;
+					__be64 gid_prefix;
+				} __packed port_info;
+				struct {
+					__be32 block_ptr;
+					__be32 tbl_entries_mask;
+				} __packed tbl_change_info;
+			} params;
+		} __packed port_mgmt_change;
+	}			event;
+	u8			slave_id;
+	u8			reserved3[2];
+	u8			owner;
+} __packed;
+
 struct mlx4_init_port_param {
 	int			set_guid0;
 	int			set_node_guid;
@@ -536,6 +631,8 @@ struct mlx4_init_port_param {
 
 #define MLX4_INVALID_SLAVE_ID	0xFF
 
+void handle_port_mgmt_change_event(struct work_struct *work);
+
 static inline int mlx4_is_master(struct mlx4_dev *dev)
 {
 	return dev->flags & MLX4_FLAG_MASTER;
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 5f1298b1b5ef..0f509229fb3d 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -42,13 +42,14 @@ enum mlx4_dev_event {
 	MLX4_DEV_EVENT_PORT_UP,
 	MLX4_DEV_EVENT_PORT_DOWN,
 	MLX4_DEV_EVENT_PORT_REINIT,
+	MLX4_DEV_EVENT_PORT_MGMT_CHANGE,
 };
 
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
 	void			(*event) (struct mlx4_dev *dev, void *context,
-					  enum mlx4_dev_event event, int port);
+					  enum mlx4_dev_event event, unsigned long param);
 	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
 	struct list_head	list;
 	enum mlx4_protocol	protocol;
-- 
cgit v1.2.3-55-g7522


From 47e956b2a6a4539f948ff2b85dfd259704dc5021 Mon Sep 17 00:00:00 2001
From: Dotan Barak
Date: Wed, 11 Jul 2012 15:39:29 +0000
Subject: IB/mlx4: Fill the masked_atomic_cap attribute in query device

When the user queries for device capabilities, fill in the
masked_atomic_cap attribute with the real support level of atomic
capabilities instead of using a hard coded value.

Signed-off-by: Dotan Barak <dotanb@dev.mellanox.co.il>
Reviewed-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3530c41fcd1f..07efe4b84a74 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -157,7 +157,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->local_ca_ack_delay  = dev->dev->caps.local_ca_ack_delay;
 	props->atomic_cap	   = dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_ATOMIC ?
 		IB_ATOMIC_HCA : IB_ATOMIC_NONE;
-	props->masked_atomic_cap   = IB_ATOMIC_HCA;
+	props->masked_atomic_cap   = props->atomic_cap;
 	props->max_pkeys	   = dev->dev->caps.pkey_table_len[1];
 	props->max_mcast_grp	   = dev->dev->caps.num_mgms + dev->dev->caps.num_amgms;
 	props->max_mcast_qp_attach = dev->dev->caps.num_qp_per_mgm;
-- 
cgit v1.2.3-55-g7522


From 6634961c14d38ef64ec284c07aecb03d3dd03b4a Mon Sep 17 00:00:00 2001
From: Jack Morgenstein
Date: Tue, 19 Jun 2012 11:21:44 +0300
Subject: mlx4: Put physical GID and P_Key table sizes in mlx4_phys_caps struct
 and paravirtualize them

To allow easy paravirtualization of P_Key and GID table sizes, keep
paravirtualized sizes in mlx4_dev->caps, but save the actual physical
sizes from FW in struct: mlx4_dev->phys_cap.

In addition, in SR-IOV mode, do the following:

1. Reduce reported P_Key table size by 1.
   This is done to reserve the highest P_Key index for internal use,
   for declaring an invalid P_Key in P_Key paravirtualization.
   We require a P_Key index which always contain an invalid P_Key
   value for this purpose (i.e., one which cannot be modified by
   the subnet manager).  The way to do this is to reduce the
   P_Key table size reported to the subnet manager by 1, so that
   it will not attempt to access the P_Key at index #127.

2. Paravirtualize the GID table size to 1. Thus, each guest sees
   only a single GID (at its paravirtualized index 0).

In addition, since we are paravirtualizing the GID table size to 1, we
add paravirtualization of the master GID event here (i.e., we do not
do ib_dispatch_event() for the GUID change event on the master, since
its (only) GUID never changes).

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/mad.c          | 10 ++++---
 drivers/net/ethernet/mellanox/mlx4/fw.c   | 43 +++++++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/main.c | 32 ++++++++++++++++++++---
 drivers/net/ethernet/mellanox/mlx4/mlx4.h |  4 ++-
 drivers/net/ethernet/mellanox/mlx4/port.c | 11 ++++++--
 include/linux/mlx4/device.h               |  2 ++
 6 files changed, 92 insertions(+), 10 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 58c45fb5bd31..c27141fef1ab 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -184,8 +184,10 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
 			break;
 
 		case IB_SMP_ATTR_GUID_INFO:
-			mlx4_ib_dispatch_event(dev, port_num,
-					       IB_EVENT_GID_CHANGE);
+			/* paravirtualized master's guid is guid 0 -- does not change */
+			if (!mlx4_is_master(dev->dev))
+				mlx4_ib_dispatch_event(dev, port_num,
+						       IB_EVENT_GID_CHANGE);
 			break;
 		default:
 			break;
@@ -487,7 +489,9 @@ void handle_port_mgmt_change_event(struct work_struct *work)
 		mlx4_ib_dispatch_event(dev, port, IB_EVENT_PKEY_CHANGE);
 		break;
 	case MLX4_DEV_PMC_SUBTYPE_GUID_INFO:
-		mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
+		/* paravirtualized master's guid is guid 0 -- does not change */
+		if (!mlx4_is_master(dev->dev))
+			mlx4_ib_dispatch_event(dev, port, IB_EVENT_GID_CHANGE);
 		break;
 	default:
 		pr_warn("Unsupported subtype 0x%x for "
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 5549f6b3bb67..473d63b63b4e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -730,9 +730,12 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 {
 	u64 def_mac;
 	u8 port_type;
+	u16 short_field;
 	int err;
 
 #define MLX4_VF_PORT_NO_LINK_SENSE_MASK	0xE0
+#define QUERY_PORT_CUR_MAX_PKEY_OFFSET	0x0c
+#define QUERY_PORT_CUR_MAX_GID_OFFSET	0x0e
 
 	err = mlx4_cmd_box(dev, 0, outbox->dma, vhcr->in_modifier, 0,
 			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
@@ -755,11 +758,51 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 
 		MLX4_PUT(outbox->buf, port_type,
 			 QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+
+		short_field = 1; /* slave max gids */
+		MLX4_PUT(outbox->buf, short_field,
+			 QUERY_PORT_CUR_MAX_GID_OFFSET);
+
+		short_field = dev->caps.pkey_table_len[vhcr->in_modifier];
+		MLX4_PUT(outbox->buf, short_field,
+			 QUERY_PORT_CUR_MAX_PKEY_OFFSET);
 	}
 
 	return err;
 }
 
+int mlx4_get_slave_pkey_gid_tbl_len(struct mlx4_dev *dev, u8 port,
+				    int *gid_tbl_len, int *pkey_tbl_len)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32			*outbox;
+	u16			field;
+	int			err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	err =  mlx4_cmd_box(dev, 0, mailbox->dma, port, 0,
+			    MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+			    MLX4_CMD_WRAPPED);
+	if (err)
+		goto out;
+
+	outbox = mailbox->buf;
+
+	MLX4_GET(field, outbox, QUERY_PORT_CUR_MAX_GID_OFFSET);
+	*gid_tbl_len = field;
+
+	MLX4_GET(field, outbox, QUERY_PORT_CUR_MAX_PKEY_OFFSET);
+	*pkey_tbl_len = field;
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL(mlx4_get_slave_pkey_gid_tbl_len);
+
 int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 {
 	struct mlx4_cmd_mailbox *mailbox;
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 58544b72bacb..5df3ac40a490 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -215,6 +215,10 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
 		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
+		dev->phys_caps.gid_phys_table_len[i]  = dev_cap->max_gids[i];
+		dev->phys_caps.pkey_phys_table_len[i] = dev_cap->max_pkeys[i];
+		/* set gid and pkey table operating lengths by default
+		 * to non-sriov values */
 		dev->caps.gid_table_len[i]  = dev_cap->max_gids[i];
 		dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
 		dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
@@ -498,8 +502,13 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 		return -ENODEV;
 	}
 
-	for (i = 1; i <= dev->caps.num_ports; ++i)
+	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.port_mask[i] = dev->caps.port_type[i];
+		if (mlx4_get_slave_pkey_gid_tbl_len(dev, i,
+						    &dev->caps.gid_table_len[i],
+						    &dev->caps.pkey_table_len[i]))
+			return -ENODEV;
+	}
 
 	if (dev->caps.uar_page_size * (dev->caps.num_uars -
 				       dev->caps.reserved_uars) >
@@ -536,7 +545,7 @@ int mlx4_change_port_types(struct mlx4_dev *dev,
 		for (port = 1; port <= dev->caps.num_ports; port++) {
 			mlx4_CLOSE_PORT(dev, port);
 			dev->caps.port_type[port] = port_types[port - 1];
-			err = mlx4_SET_PORT(dev, port);
+			err = mlx4_SET_PORT(dev, port, -1);
 			if (err) {
 				mlx4_err(dev, "Failed to set port %d, "
 					      "aborting\n", port);
@@ -722,7 +731,7 @@ static ssize_t set_port_ib_mtu(struct device *dev,
 	mlx4_unregister_device(mdev);
 	for (port = 1; port <= mdev->caps.num_ports; port++) {
 		mlx4_CLOSE_PORT(mdev, port);
-		err = mlx4_SET_PORT(mdev, port);
+		err = mlx4_SET_PORT(mdev, port, -1);
 		if (err) {
 			mlx4_err(mdev, "Failed to set port %d, "
 				      "aborting\n", port);
@@ -1173,6 +1182,17 @@ err:
 	return -EIO;
 }
 
+static void mlx4_parav_master_pf_caps(struct mlx4_dev *dev)
+{
+	int i;
+
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		dev->caps.gid_table_len[i] = 1;
+		dev->caps.pkey_table_len[i] =
+			dev->phys_caps.pkey_phys_table_len[i] - 1;
+	}
+}
+
 static int mlx4_init_hca(struct mlx4_dev *dev)
 {
 	struct mlx4_priv	  *priv = mlx4_priv(dev);
@@ -1212,6 +1232,9 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 			goto err_stop_fw;
 		}
 
+		if (mlx4_is_master(dev))
+			mlx4_parav_master_pf_caps(dev);
+
 		profile = default_profile;
 
 		icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
@@ -1500,7 +1523,8 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 			else
 				dev->caps.port_ib_mtu[port] = IB_MTU_4096;
 
-			err = mlx4_SET_PORT(dev, port);
+			err = mlx4_SET_PORT(dev, port, mlx4_is_master(dev) ?
+					    dev->caps.pkey_table_len[port] : -1);
 			if (err) {
 				mlx4_err(dev, "Failed to set port %d, aborting\n",
 					port);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 4d11d12b9db4..cde6e511899f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -969,7 +969,7 @@ int mlx4_change_port_types(struct mlx4_dev *dev,
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
 void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 
-int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
+int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz);
 /* resource tracker functions*/
 int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
 				    enum mlx4_resource resource_type,
@@ -1012,6 +1012,8 @@ int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
 			    struct mlx4_cmd_info *cmd);
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
 
+int mlx4_get_slave_pkey_gid_tbl_len(struct mlx4_dev *dev, u8 port,
+				    int *gid_tbl_len, int *pkey_tbl_len);
 
 int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 			   struct mlx4_vhcr *vhcr,
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index a8fb52992c64..90dc47542b8b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -726,14 +726,15 @@ int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
 enum {
 	MLX4_SET_PORT_VL_CAP	 = 4, /* bits 7:4 */
 	MLX4_SET_PORT_MTU_CAP	 = 12, /* bits 15:12 */
+	MLX4_CHANGE_PORT_PKEY_TBL_SZ = 20,
 	MLX4_CHANGE_PORT_VL_CAP	 = 21,
 	MLX4_CHANGE_PORT_MTU_CAP = 22,
 };
 
-int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
+int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port, int pkey_tbl_sz)
 {
 	struct mlx4_cmd_mailbox *mailbox;
-	int err, vl_cap;
+	int err, vl_cap, pkey_tbl_flag = 0;
 
 	if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
 		return 0;
@@ -746,11 +747,17 @@ int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 
 	((__be32 *) mailbox->buf)[1] = dev->caps.ib_port_def_cap[port];
 
+	if (pkey_tbl_sz >= 0 && mlx4_is_master(dev)) {
+		pkey_tbl_flag = 1;
+		((__be16 *) mailbox->buf)[20] = cpu_to_be16(pkey_tbl_sz);
+	}
+
 	/* IB VL CAP enum isn't used by the firmware, just numerical values */
 	for (vl_cap = 8; vl_cap >= 1; vl_cap >>= 1) {
 		((__be32 *) mailbox->buf)[0] = cpu_to_be32(
 			(1 << MLX4_CHANGE_PORT_MTU_CAP) |
 			(1 << MLX4_CHANGE_PORT_VL_CAP)  |
+			(pkey_tbl_flag << MLX4_CHANGE_PORT_PKEY_TBL_SZ) |
 			(dev->caps.port_ib_mtu[port] << MLX4_SET_PORT_MTU_CAP) |
 			(vl_cap << MLX4_SET_PORT_VL_CAP));
 		err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index c30a314e095c..441caf1a497d 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -268,6 +268,8 @@ static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 }
 
 struct mlx4_phys_caps {
+	u32			gid_phys_table_len[MLX4_MAX_PORTS + 1];
+	u32			pkey_phys_table_len[MLX4_MAX_PORTS + 1];
 	u32			num_phys_eqs;
 };
 
-- 
cgit v1.2.3-55-g7522


From d9236c3f10490cd0b3fd4516af12ba62dcbae0b0 Mon Sep 17 00:00:00 2001
From: Amir Vadai
Date: Wed, 18 Jul 2012 22:33:51 +0000
Subject: {NET,IB}/mlx4: Add rmap support to mlx4_assign_eq

Enable callers of mlx4_assign_eq to supply a pointer to cpu_rmap.
If supplied, the assigned IRQ is tracked using rmap infrastructure.

Signed-off-by: Amir Vadai <amirv@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c          |  3 ++-
 drivers/net/ethernet/mellanox/mlx4/en_cq.c |  3 ++-
 drivers/net/ethernet/mellanox/mlx4/eq.c    | 12 +++++++++++-
 include/linux/mlx4/device.h                |  4 +++-
 4 files changed, 18 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 8a3a2037b005..a07b774e7864 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1159,7 +1159,8 @@ static void mlx4_ib_alloc_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 			sprintf(name, "mlx4-ib-%d-%d@%s",
 				i, j, dev->pdev->bus->name);
 			/* Set IRQ for specific name (per ring) */
-			if (mlx4_assign_eq(dev, name, &ibdev->eq_table[eq])) {
+			if (mlx4_assign_eq(dev, name, 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 908a460d8db6..0ef615684021 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -91,7 +91,8 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 				sprintf(name, "%s-%d", priv->dev->name,
 					cq->ring);
 				/* Set IRQ for specific name (per ring) */
-				if (mlx4_assign_eq(mdev->dev, name, &cq->vector)) {
+				if (mlx4_assign_eq(mdev->dev, name, NULL,
+						   &cq->vector)) {
 					cq->vector = (cq->ring + 1 + priv->port)
 					    % mdev->dev->caps.num_comp_vectors;
 					mlx4_warn(mdev, "Failed Assigning an EQ to "
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index bce98d9c0039..cd48337cbfc0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -39,6 +39,7 @@
 #include <linux/dma-mapping.h>
 
 #include <linux/mlx4/cmd.h>
+#include <linux/cpu_rmap.h>
 
 #include "mlx4.h"
 #include "fw.h"
@@ -1060,7 +1061,8 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 }
 EXPORT_SYMBOL(mlx4_test_interrupts);
 
-int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector)
+int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap,
+		   int *vector)
 {
 
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -1074,6 +1076,14 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector)
 			snprintf(priv->eq_table.irq_names +
 					vec * MLX4_IRQNAME_SIZE,
 					MLX4_IRQNAME_SIZE, "%s", name);
+#ifdef CONFIG_RFS_ACCEL
+			if (rmap) {
+				err = irq_cpu_rmap_add(rmap,
+						       priv->eq_table.eq[vec].irq);
+				if (err)
+					mlx4_warn(dev, "Failed adding irq rmap\n");
+			}
+#endif
 			err = request_irq(priv->eq_table.eq[vec].irq,
 					  mlx4_msi_x_interrupt, 0,
 					  &priv->eq_table.irq_names[vec<<5],
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6f0d133cc7ad..4d7761f8c3f6 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -36,6 +36,7 @@
 #include <linux/pci.h>
 #include <linux/completion.h>
 #include <linux/radix-tree.h>
+#include <linux/cpu_rmap.h>
 
 #include <linux/atomic.h>
 
@@ -784,7 +785,8 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 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 , int* vector);
+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_wol_read(struct mlx4_dev *dev, u64 *config, int port);
-- 
cgit v1.2.3-55-g7522


From df7fba66471c6bbbaebb55e1bb3658eb7ce00a9b Mon Sep 17 00:00:00 2001
From: Jack Morgenstein
Date: Fri, 3 Aug 2012 08:26:45 +0000
Subject: IB/mlx4: Fix possible deadlock on sm_lock spinlock

The sm_lock spinlock is taken in the process context by
mlx4_ib_modify_device, and in the interrupt context by update_sm_ah,
so we need to take that spinlock with irqsave, and release it with
irqrestore.

Lockdeps reports this as follows:

    [ INFO: inconsistent lock state ]
    3.5.0+ #20 Not tainted
    inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
    swapper/0/0 [HC1[1]:SC0[0]:HE0:SE1] takes:
    (&(&ibdev->sm_lock)->rlock){?.+...}, at: [<ffffffffa028af1d>] update_sm_ah+0xad/0x100 [mlx4_ib]
    {HARDIRQ-ON-W} state was registered at:
      [<ffffffff810b84a0>] mark_irqflags+0x120/0x190
      [<ffffffff810b9ce7>] __lock_acquire+0x307/0x4c0
      [<ffffffff810b9f51>] lock_acquire+0xb1/0x150
      [<ffffffff815523b1>] _raw_spin_lock+0x41/0x50
      [<ffffffffa028d563>] mlx4_ib_modify_device+0x63/0x240 [mlx4_ib]
      [<ffffffffa026d1fc>] ib_modify_device+0x1c/0x20 [ib_core]
      [<ffffffffa026c353>] set_node_desc+0x83/0xc0 [ib_core]
      [<ffffffff8136a150>] dev_attr_store+0x20/0x30
      [<ffffffff81201fd6>] sysfs_write_file+0xe6/0x170
      [<ffffffff8118da38>] vfs_write+0xc8/0x190
      [<ffffffff8118dc01>] sys_write+0x51/0x90
      [<ffffffff8155b869>] system_call_fastpath+0x16/0x1b

    ...
    *** DEADLOCK ***

    1 lock held by swapper/0/0:

    stack backtrace:
    Pid: 0, comm: swapper/0 Not tainted 3.5.0+ #20
    Call Trace:
    <IRQ>  [<ffffffff810b7bea>] print_usage_bug+0x18a/0x190
    [<ffffffff810b7370>] ? print_irq_inversion_bug+0x210/0x210
    [<ffffffff810b7fb2>] mark_lock_irq+0xf2/0x280
    [<ffffffff810b8290>] mark_lock+0x150/0x240
    [<ffffffff810b84ef>] mark_irqflags+0x16f/0x190
    [<ffffffff810b9ce7>] __lock_acquire+0x307/0x4c0
    [<ffffffffa028af1d>] ? update_sm_ah+0xad/0x100 [mlx4_ib]
    [<ffffffff810b9f51>] lock_acquire+0xb1/0x150
    [<ffffffffa028af1d>] ? update_sm_ah+0xad/0x100 [mlx4_ib]
    [<ffffffff815523b1>] _raw_spin_lock+0x41/0x50
    [<ffffffffa028af1d>] ? update_sm_ah+0xad/0x100 [mlx4_ib]
    [<ffffffffa026b2fa>] ? ib_create_ah+0x1a/0x40 [ib_core]
    [<ffffffffa028af1d>] update_sm_ah+0xad/0x100 [mlx4_ib]
    [<ffffffff810c27c3>] ? is_module_address+0x23/0x30
    [<ffffffffa028b05b>] handle_port_mgmt_change_event+0xeb/0x150 [mlx4_ib]
    [<ffffffffa028c177>] mlx4_ib_event+0x117/0x160 [mlx4_ib]
    [<ffffffff81552501>] ? _raw_spin_lock_irqsave+0x61/0x70
    [<ffffffffa022718c>] mlx4_dispatch_event+0x6c/0x90 [mlx4_core]
    [<ffffffffa0221b40>] mlx4_eq_int+0x500/0x950 [mlx4_core]

Reported by: Or Gerlitz <ogerlitz@mellanox.com>
Tested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/mad.c  | 16 ++++++++++------
 drivers/infiniband/hw/mlx4/main.c |  5 +++--
 2 files changed, 13 insertions(+), 8 deletions(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index c27141fef1ab..9c2ae7efd00f 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -125,6 +125,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 {
 	struct ib_ah *new_ah;
 	struct ib_ah_attr ah_attr;
+	unsigned long flags;
 
 	if (!dev->send_agent[port_num - 1][0])
 		return;
@@ -139,11 +140,11 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
 	if (IS_ERR(new_ah))
 		return;
 
-	spin_lock(&dev->sm_lock);
+	spin_lock_irqsave(&dev->sm_lock, flags);
 	if (dev->sm_ah[port_num - 1])
 		ib_destroy_ah(dev->sm_ah[port_num - 1]);
 	dev->sm_ah[port_num - 1] = new_ah;
-	spin_unlock(&dev->sm_lock);
+	spin_unlock_irqrestore(&dev->sm_lock, flags);
 }
 
 /*
@@ -197,13 +198,15 @@ static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
 static void node_desc_override(struct ib_device *dev,
 			       struct ib_mad *mad)
 {
+	unsigned long flags;
+
 	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED ||
 	     mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) &&
 	    mad->mad_hdr.method == IB_MGMT_METHOD_GET_RESP &&
 	    mad->mad_hdr.attr_id == IB_SMP_ATTR_NODE_DESC) {
-		spin_lock(&to_mdev(dev)->sm_lock);
+		spin_lock_irqsave(&to_mdev(dev)->sm_lock, flags);
 		memcpy(((struct ib_smp *) mad)->data, dev->node_desc, 64);
-		spin_unlock(&to_mdev(dev)->sm_lock);
+		spin_unlock_irqrestore(&to_mdev(dev)->sm_lock, flags);
 	}
 }
 
@@ -213,6 +216,7 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 	struct ib_mad_send_buf *send_buf;
 	struct ib_mad_agent *agent = dev->send_agent[port_num - 1][qpn];
 	int ret;
+	unsigned long flags;
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
@@ -225,13 +229,13 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 		 * wrong following the IB spec strictly, but we know
 		 * it's OK for our devices).
 		 */
-		spin_lock(&dev->sm_lock);
+		spin_lock_irqsave(&dev->sm_lock, flags);
 		memcpy(send_buf->mad, mad, sizeof *mad);
 		if ((send_buf->ah = dev->sm_ah[port_num - 1]))
 			ret = ib_post_send_mad(send_buf, NULL);
 		else
 			ret = -EINVAL;
-		spin_unlock(&dev->sm_lock);
+		spin_unlock_irqrestore(&dev->sm_lock, flags);
 
 		if (ret)
 			ib_free_send_mad(send_buf);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index fe2088cfa6ee..cc05579ebce7 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -423,6 +423,7 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 				 struct ib_device_modify *props)
 {
 	struct mlx4_cmd_mailbox *mailbox;
+	unsigned long flags;
 
 	if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
 		return -EOPNOTSUPP;
@@ -430,9 +431,9 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 	if (!(mask & IB_DEVICE_MODIFY_NODE_DESC))
 		return 0;
 
-	spin_lock(&to_mdev(ibdev)->sm_lock);
+	spin_lock_irqsave(&to_mdev(ibdev)->sm_lock, flags);
 	memcpy(ibdev->node_desc, props->node_desc, 64);
-	spin_unlock(&to_mdev(ibdev)->sm_lock);
+	spin_unlock_irqrestore(&to_mdev(ibdev)->sm_lock, flags);
 
 	/*
 	 * If possible, pass node desc to FW, so it can generate
-- 
cgit v1.2.3-55-g7522


From a0675a386a3a68f71e831bd064082e6717b45fdc Mon Sep 17 00:00:00 2001
From: Kleber Sacilotto de Souza
Date: Fri, 10 Aug 2012 18:25:34 +0000
Subject: IB/mlx4: Check iboe netdev pointer before dereferencing it

Unlike other parts of the mlx4_ib code, the function build_mlx_header()
doesn't check if the iboe netdev of the given port is valid before
dereferencing it, which can cause a crash if the ethernet interface
has already been taken down.

Fix this by checking for a valid netdev pointer before using it to get
the port MAC address.

Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/infiniband/hw/mlx4/qp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/hw/mlx4')

diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index a6d8ea060ea8..f585eddef4b7 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1407,6 +1407,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	struct mlx4_wqe_mlx_seg *mlx = wqe;
 	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
 	struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
+	struct net_device *ndev;
 	union ib_gid sgid;
 	u16 pkey;
 	int send_size;
@@ -1483,7 +1484,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 
 		memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
 		/* FIXME: cache smac value? */
-		smac = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+		ndev = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1];
+		if (!ndev)
+			return -ENODEV;
+		smac = ndev->dev_addr;
 		memcpy(sqp->ud_header.eth.smac_h, smac, 6);
 		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
 			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
-- 
cgit v1.2.3-55-g7522