From 63a5f483af0ead9e936e8580c6a029b13819b4dc Mon Sep 17 00:00:00 2001
From: Moni Shoua <monis@mellanox.com>
Date: Tue, 30 May 2017 09:47:34 +0300
Subject: IB/cma: Set default gid type to RoCEv2

RoCEv2 is the preferred RDMA protocol for Ethernet link layer because
of its advantages over RoCEv1. For better user experience make it the
default choice for RDMA_CM connections if device/port support it.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cma.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0eb393237ba2..476de9a18948 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,6 +72,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
+#define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
 
 static const char * const cma_events[] = {
 	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
@@ -4280,8 +4281,12 @@ static void cma_add_one(struct ib_device *device)
 	for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) {
 		supported_gids = roce_gid_type_mask_support(device, i);
 		WARN_ON(!supported_gids);
-		cma_dev->default_gid_type[i - rdma_start_port(device)] =
-			find_first_bit(&supported_gids, BITS_PER_LONG);
+		if (supported_gids & CMA_PREFERRED_ROCE_GID_TYPE)
+			cma_dev->default_gid_type[i - rdma_start_port(device)] =
+				CMA_PREFERRED_ROCE_GID_TYPE;
+		else
+			cma_dev->default_gid_type[i - rdma_start_port(device)] =
+				find_first_bit(&supported_gids, BITS_PER_LONG);
 		cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0;
 	}
 
-- 
cgit v1.2.3-59-g8ed1b


From d41861942fc55c14b6280d9568a0d0112037f065 Mon Sep 17 00:00:00 2001
From: Yuval Shaia <yuval.shaia@oracle.com>
Date: Wed, 14 Jun 2017 23:13:34 +0300
Subject: IB/core: Add generic function to extract IB speed from netdev

Logic of retrieving netdev speed from net_device and translating it to
IB speed is implemented in rxe, in usnic and in bnxt drivers.

Define new function which merges all.

Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: Christian Benvenuti <benve@cisco.com>
Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/roce_gid_mgmt.c      |  2 +
 drivers/infiniband/core/verbs.c              | 55 ++++++++++++++++++++++++++++
 drivers/infiniband/hw/bnxt_re/ib_verbs.c     | 49 ++-----------------------
 drivers/infiniband/hw/usnic/usnic_ib_verbs.c | 31 +++-------------
 drivers/infiniband/sw/rxe/rxe_verbs.c        | 53 +++------------------------
 include/rdma/ib_verbs.h                      |  1 +
 6 files changed, 73 insertions(+), 118 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 94a9eefb3cfc..90e3889b7fbe 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -44,6 +44,8 @@
 
 static struct workqueue_struct *gid_cache_wq;
 
+static struct workqueue_struct *gid_cache_wq;
+
 enum gid_op_type {
 	GID_DEL = 0,
 	GID_ADD
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index fb98ed67d5bc..40de69bf07cd 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1302,6 +1302,61 @@ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr,
 }
 EXPORT_SYMBOL(ib_modify_qp_with_udata);
 
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width)
+{
+	int rc;
+	u32 netdev_speed;
+	struct net_device *netdev;
+	struct ethtool_link_ksettings lksettings;
+
+	if (rdma_port_get_link_layer(dev, port_num) != IB_LINK_LAYER_ETHERNET)
+		return -EINVAL;
+
+	if (!dev->get_netdev)
+		return -EOPNOTSUPP;
+
+	netdev = dev->get_netdev(dev, port_num);
+	if (!netdev)
+		return -ENODEV;
+
+	rtnl_lock();
+	rc = __ethtool_get_link_ksettings(netdev, &lksettings);
+	rtnl_unlock();
+
+	dev_put(netdev);
+
+	if (!rc) {
+		netdev_speed = lksettings.base.speed;
+	} else {
+		netdev_speed = SPEED_1000;
+		pr_warn("%s speed is unknown, defaulting to %d\n", netdev->name,
+			netdev_speed);
+	}
+
+	if (netdev_speed <= SPEED_1000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_SDR;
+	} else if (netdev_speed <= SPEED_10000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_FDR10;
+	} else if (netdev_speed <= SPEED_20000) {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_DDR;
+	} else if (netdev_speed <= SPEED_25000) {
+		*width = IB_WIDTH_1X;
+		*speed = IB_SPEED_EDR;
+	} else if (netdev_speed <= SPEED_40000) {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_FDR10;
+	} else {
+		*width = IB_WIDTH_4X;
+		*speed = IB_SPEED_EDR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_get_eth_speed);
+
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 5dc6e7ce3ab9..b10e1a6dce84 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -223,50 +223,6 @@ int bnxt_re_modify_device(struct ib_device *ibdev,
 	return 0;
 }
 
-static void __to_ib_speed_width(struct net_device *netdev, u8 *speed, u8 *width)
-{
-	struct ethtool_link_ksettings lksettings;
-	u32 espeed;
-
-	if (netdev->ethtool_ops && netdev->ethtool_ops->get_link_ksettings) {
-		memset(&lksettings, 0, sizeof(lksettings));
-		rtnl_lock();
-		netdev->ethtool_ops->get_link_ksettings(netdev, &lksettings);
-		rtnl_unlock();
-		espeed = lksettings.base.speed;
-	} else {
-		espeed = SPEED_UNKNOWN;
-	}
-	switch (espeed) {
-	case SPEED_1000:
-		*speed = IB_SPEED_SDR;
-		*width = IB_WIDTH_1X;
-		break;
-	case SPEED_10000:
-		*speed = IB_SPEED_QDR;
-		*width = IB_WIDTH_1X;
-		break;
-	case SPEED_20000:
-		*speed = IB_SPEED_DDR;
-		*width = IB_WIDTH_4X;
-		break;
-	case SPEED_25000:
-		*speed = IB_SPEED_EDR;
-		*width = IB_WIDTH_1X;
-		break;
-	case SPEED_40000:
-		*speed = IB_SPEED_QDR;
-		*width = IB_WIDTH_4X;
-		break;
-	case SPEED_50000:
-		break;
-	default:
-		*speed = IB_SPEED_SDR;
-		*width = IB_WIDTH_1X;
-		break;
-	}
-}
-
 /* Port */
 int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
 		       struct ib_port_attr *port_attr)
@@ -308,8 +264,9 @@ int bnxt_re_query_port(struct ib_device *ibdev, u8 port_num,
 	 * IB stack to avoid race in the NETDEV_UNREG path
 	 */
 	if (test_bit(BNXT_RE_FLAG_IBDEV_REGISTERED, &rdev->flags))
-		__to_ib_speed_width(rdev->netdev, &port_attr->active_speed,
-				    &port_attr->active_width);
+		if (!ib_get_eth_speed(ibdev, port_num, &port_attr->active_speed,
+				      &port_attr->active_width))
+			return -EINVAL;
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index f9dc1e80c3b7..e5f57dd49980 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -226,27 +226,6 @@ static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp)
 	spin_unlock(&vf->lock);
 }
 
-static void eth_speed_to_ib_speed(int speed, u8 *active_speed,
-					u8 *active_width)
-{
-	if (speed <= 10000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_FDR10;
-	} else if (speed <= 20000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_DDR;
-	} else if (speed <= 30000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_QDR;
-	} else if (speed <= 40000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_FDR10;
-	} else {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_EDR;
-	}
-}
-
 static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd)
 {
 	if (cmd.spec.trans_type <= USNIC_TRANSPORT_UNKNOWN ||
@@ -326,12 +305,16 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 				struct ib_port_attr *props)
 {
 	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
-	struct ethtool_link_ksettings cmd;
 
 	usnic_dbg("\n");
 
 	mutex_lock(&us_ibdev->usdev_lock);
-	__ethtool_get_link_ksettings(us_ibdev->netdev, &cmd);
+	if (!ib_get_eth_speed(ibdev, port, &props->active_speed,
+			      &props->active_width)) {
+		mutex_unlock(&us_ibdev->usdev_lock);
+		return -EINVAL;
+	}
+
 	/* props being zeroed by the caller, avoid zeroing it here */
 
 	props->lid = 0;
@@ -355,8 +338,6 @@ int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 	props->pkey_tbl_len = 1;
 	props->bad_pkey_cntr = 0;
 	props->qkey_viol_cntr = 0;
-	eth_speed_to_ib_speed(cmd.base.speed, &props->active_speed,
-			      &props->active_width);
 	props->max_mtu = IB_MTU_4096;
 	props->active_mtu = iboe_get_mtu(us_ibdev->ufdev->mtu);
 	/* Userspace will adjust for hdrs */
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index af90a7d42b96..e6c10e43a6d7 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -51,40 +51,16 @@ static int rxe_query_device(struct ib_device *dev,
 	return 0;
 }
 
-static void rxe_eth_speed_to_ib_speed(int speed, u8 *active_speed,
-				      u8 *active_width)
-{
-	if (speed <= 1000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_SDR;
-	} else if (speed <= 10000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_FDR10;
-	} else if (speed <= 20000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_DDR;
-	} else if (speed <= 30000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_QDR;
-	} else if (speed <= 40000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_FDR10;
-	} else {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_EDR;
-	}
-}
-
 static int rxe_query_port(struct ib_device *dev,
 			  u8 port_num, struct ib_port_attr *attr)
 {
 	struct rxe_dev *rxe = to_rdev(dev);
 	struct rxe_port *port;
-	u32 speed;
+	int rc = -EINVAL;
 
 	if (unlikely(port_num != 1)) {
 		pr_warn("invalid port_number %d\n", port_num);
-		goto err1;
+		goto out;
 	}
 
 	port = &rxe->port;
@@ -93,29 +69,12 @@ static int rxe_query_port(struct ib_device *dev,
 	*attr = port->attr;
 
 	mutex_lock(&rxe->usdev_lock);
-	if (rxe->ndev->ethtool_ops->get_link_ksettings) {
-		struct ethtool_link_ksettings ks;
-
-		rxe->ndev->ethtool_ops->get_link_ksettings(rxe->ndev, &ks);
-		speed = ks.base.speed;
-	} else if (rxe->ndev->ethtool_ops->get_settings) {
-		struct ethtool_cmd cmd;
-
-		rxe->ndev->ethtool_ops->get_settings(rxe->ndev, &cmd);
-		speed = cmd.speed;
-	} else {
-		pr_warn("%s speed is unknown, defaulting to 1000\n",
-			rxe->ndev->name);
-		speed = 1000;
-	}
-	rxe_eth_speed_to_ib_speed(speed, &attr->active_speed,
-				  &attr->active_width);
+	rc = ib_get_eth_speed(dev, port_num, &attr->active_speed,
+			      &attr->active_width);
 	mutex_unlock(&rxe->usdev_lock);
 
-	return 0;
-
-err1:
-	return -EINVAL;
+out:
+	return rc;
 }
 
 static int rxe_query_gid(struct ib_device *device,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b5732432bb29..68d947dac9a2 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3555,6 +3555,7 @@ void ib_drain_qp(struct ib_qp *qp);
 
 int ib_resolve_eth_dmac(struct ib_device *device,
 			struct rdma_ah_attr *ah_attr);
+int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width);
 
 static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr)
 {
-- 
cgit v1.2.3-59-g8ed1b


From 5236333592244557a19694a51337df6ac018f0a7 Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Mon, 12 Jun 2017 11:14:02 +0300
Subject: IB/core: Fix the validations of a multicast LID in attach or detach
 operations

RoCE Annex (A16.9.10/11) declares that during attach (detach) QP to a
multicast group, if the QP is associated with a RoCE port, the
multicast group MLID is unused and is ignored.

During attach or detach multicast, when the QP is associated with a
port, it is enough to check the port's link layer and validate the
LID only if it is Infiniband. Otherwise, avoid validating the
multicast LID.

Fixes: 8561eae60ff9 ("IB/core: For multicast functions, verify that LIDs are multicast LIDs")
Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 44 +++++++++++++++++++++++++++++++++++++----
 1 file changed, 40 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index fb98ed67d5bc..802bdc397a57 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1569,6 +1569,44 @@ EXPORT_SYMBOL(ib_dealloc_fmr);
 
 /* Multicast groups */
 
+static bool is_valid_mcast_lid(struct ib_qp *qp, u16 lid)
+{
+	struct ib_qp_init_attr init_attr = {};
+	struct ib_qp_attr attr = {};
+	int num_eth_ports = 0;
+	int port;
+
+	/* If QP state >= init, it is assigned to a port and we can check this
+	 * port only.
+	 */
+	if (!ib_query_qp(qp, &attr, IB_QP_STATE | IB_QP_PORT, &init_attr)) {
+		if (attr.qp_state >= IB_QPS_INIT) {
+			if (qp->device->get_link_layer(qp->device, attr.port_num) !=
+			    IB_LINK_LAYER_INFINIBAND)
+				return true;
+			goto lid_check;
+		}
+	}
+
+	/* Can't get a quick answer, iterate over all ports */
+	for (port = 0; port < qp->device->phys_port_cnt; port++)
+		if (qp->device->get_link_layer(qp->device, port) !=
+		    IB_LINK_LAYER_INFINIBAND)
+			num_eth_ports++;
+
+	/* If we have at lease one Ethernet port, RoCE annex declares that
+	 * multicast LID should be ignored. We can't tell at this step if the
+	 * QP belongs to an IB or Ethernet port.
+	 */
+	if (num_eth_ports)
+		return true;
+
+	/* If all the ports are IB, we can check according to IB spec. */
+lid_check:
+	return !(lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
+		 lid == be16_to_cpu(IB_LID_PERMISSIVE));
+}
+
 int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 {
 	int ret;
@@ -1576,8 +1614,7 @@ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 	if (!qp->device->attach_mcast)
 		return -ENOSYS;
 	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
-	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
+	    !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->attach_mcast(qp, gid, lid);
@@ -1594,8 +1631,7 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 	if (!qp->device->detach_mcast)
 		return -ENOSYS;
 	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    lid < be16_to_cpu(IB_MULTICAST_LID_BASE) ||
-	    lid == be16_to_cpu(IB_LID_PERMISSIVE))
+	    !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->detach_mcast(qp, gid, lid);
-- 
cgit v1.2.3-59-g8ed1b


From be1d325a335840a86c133a56c6a911c368bac0fd Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Mon, 12 Jun 2017 11:14:03 +0300
Subject: IB/core: Set RoCEv2 MGID according to spec

RoCEv2 Annex states that for RoCEv2 over IPv4, the corresponding
IPv4 address is encoded into the GID according to the following rule:
GID= :ffff:<IPv4 address>

Remove the 0xff0e prefix for RoCEv2 packets with IPv4 and leave it
zeroed and change rdma_is_multicast_addr() to consider the new logic.

Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cma.c   | 13 +++++++------
 drivers/infiniband/core/verbs.c | 10 ++++++----
 include/rdma/ib_addr.h          |  8 +++++++-
 3 files changed, 20 insertions(+), 11 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0eb393237ba2..a8c2f0ccd225 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -3998,7 +3998,8 @@ static void iboe_mcast_work_handler(struct work_struct *work)
 	kfree(mw);
 }
 
-static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid)
+static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid,
+			      enum ib_gid_type gid_type)
 {
 	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
@@ -4008,8 +4009,8 @@ static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid)
 	} else if (addr->sa_family == AF_INET6) {
 		memcpy(mgid, &sin6->sin6_addr, sizeof *mgid);
 	} else {
-		mgid->raw[0] = 0xff;
-		mgid->raw[1] = 0x0e;
+		mgid->raw[0] = (gid_type == IB_GID_TYPE_IB) ? 0xff : 0;
+		mgid->raw[1] = (gid_type == IB_GID_TYPE_IB) ? 0x0e : 0;
 		mgid->raw[2] = 0;
 		mgid->raw[3] = 0;
 		mgid->raw[4] = 0;
@@ -4050,7 +4051,9 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 		goto out1;
 	}
 
-	cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid);
+	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
+		   rdma_start_port(id_priv->cma_dev->device)];
+	cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid, gid_type);
 
 	mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff);
 	if (id_priv->id.ps == RDMA_PS_UDP)
@@ -4066,8 +4069,6 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 	mc->multicast.ib->rec.hop_limit = 1;
 	mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu);
 
-	gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num -
-		   rdma_start_port(id_priv->cma_dev->device)];
 	if (addr->sa_family == AF_INET) {
 		if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
 			mc->multicast.ib->rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 802bdc397a57..30fdc3ae1bbd 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1613,8 +1613,9 @@ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 
 	if (!qp->device->attach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    !is_valid_mcast_lid(qp, lid))
+
+	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
+	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->attach_mcast(qp, gid, lid);
@@ -1630,8 +1631,9 @@ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid)
 
 	if (!qp->device->detach_mcast)
 		return -ENOSYS;
-	if (gid->raw[0] != 0xff || qp->qp_type != IB_QPT_UD ||
-	    !is_valid_mcast_lid(qp, lid))
+
+	if (!rdma_is_multicast_addr((struct in6_addr *)gid->raw) ||
+	    qp->qp_type != IB_QPT_UD || !is_valid_mcast_lid(qp, lid))
 		return -EINVAL;
 
 	ret = qp->device->detach_mcast(qp, gid, lid);
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index b73a14edc85e..7aca12188ef3 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -304,7 +304,13 @@ static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
 
 static inline int rdma_is_multicast_addr(struct in6_addr *addr)
 {
-	return addr->s6_addr[0] == 0xff;
+	u32 ipv4_addr;
+
+	if (addr->s6_addr[0] == 0xff)
+		return 1;
+
+	memcpy(&ipv4_addr, addr->s6_addr + 12, 4);
+	return (ipv6_addr_v4mapped(addr) && ipv4_is_multicast(ipv4_addr));
 }
 
 static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
-- 
cgit v1.2.3-59-g8ed1b


From 9636a56fa864464896bf7d1272c701f2b9a57737 Mon Sep 17 00:00:00 2001
From: Noa Osherovich <noaos@mellanox.com>
Date: Mon, 12 Jun 2017 11:14:04 +0300
Subject: IB/core: Add support for RoCEv2 multicast

When creating address handle from multicast GID, set MAC according to
the appropriate formula instead of searching for it in the GID table:
- For IPv4 multicast GID use ip_eth_mc_map().
- For IPv6 multicast GID use ipv6_eth_mc_map().

Signed-off-by: Noa Osherovich <noaos@mellanox.com>
Reviewed-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 30fdc3ae1bbd..e8006677b01c 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1244,6 +1244,18 @@ int ib_resolve_eth_dmac(struct ib_device *device,
 	if (rdma_link_local_addr((struct in6_addr *)grh->dgid.raw)) {
 		rdma_get_ll_mac((struct in6_addr *)grh->dgid.raw,
 				ah_attr->roce.dmac);
+		return 0;
+	}
+	if (rdma_is_multicast_addr((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw)) {
+			__be32 addr = 0;
+
+			memcpy(&addr, ah_attr->grh.dgid.raw + 12, 4);
+			ip_eth_mc_map(addr, (char *)ah_attr->roce.dmac);
+		} else {
+			ipv6_eth_mc_map((struct in6_addr *)ah_attr->grh.dgid.raw,
+					(char *)ah_attr->roce.dmac);
+		}
 	} else {
 		union ib_gid		sgid;
 		struct ib_gid_attr	sgid_attr;
-- 
cgit v1.2.3-59-g8ed1b


From 2dee0e545894c23b1a2cc2019ac87dffb42e5984 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@mellanox.com>
Date: Thu, 8 Jun 2017 16:15:07 +0300
Subject: IB/uverbs: Enable QP creation with a given source QP number

Enable QP creation with a given source QP number, the created QP will
use the source QPN as its wire QP number.

To create such a QP, root privileges (i.e. CAP_NET_RAW) are required
from the user application.

This comes as a pre-patch for downstream patches in this series to
allow user space applications to accelerate traffic which is typically
handled by IPoIB ULP.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 17 ++++++++++++++---
 include/uapi/rdma/ib_user_verbs.h    |  2 +-
 2 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2c98533a0203..60535c754db3 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1383,8 +1383,9 @@ static int create_qp(struct ib_uverbs_file *file,
 		attr.rwq_ind_tbl = ind_tbl;
 	}
 
-	if ((cmd_sz >= offsetof(typeof(*cmd), reserved1) +
-		       sizeof(cmd->reserved1)) && cmd->reserved1) {
+	if (cmd_sz > sizeof(*cmd) &&
+	    !ib_is_udata_cleared(ucore, sizeof(*cmd),
+				 cmd_sz - sizeof(*cmd))) {
 		ret = -EOPNOTSUPP;
 		goto err_put;
 	}
@@ -1482,11 +1483,21 @@ static int create_qp(struct ib_uverbs_file *file,
 				IB_QP_CREATE_MANAGED_SEND |
 				IB_QP_CREATE_MANAGED_RECV |
 				IB_QP_CREATE_SCATTER_FCS |
-				IB_QP_CREATE_CVLAN_STRIPPING)) {
+				IB_QP_CREATE_CVLAN_STRIPPING |
+				IB_QP_CREATE_SOURCE_QPN)) {
 		ret = -EINVAL;
 		goto err_put;
 	}
 
+	if (attr.create_flags & IB_QP_CREATE_SOURCE_QPN) {
+		if (!capable(CAP_NET_RAW)) {
+			ret = -EPERM;
+			goto err_put;
+		}
+
+		attr.source_qpn = cmd->source_qpn;
+	}
+
 	buf = (void *)cmd + sizeof(*cmd);
 	if (cmd_sz > sizeof(*cmd))
 		if (!(buf[0] == 0 && !memcmp(buf, buf + 1,
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 270c350bedc6..63656d2e8705 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -578,7 +578,7 @@ struct ib_uverbs_ex_create_qp {
 	__u32 comp_mask;
 	__u32 create_flags;
 	__u32 rwq_ind_tbl_handle;
-	__u32  reserved1;
+	__u32  source_qpn;
 };
 
 struct ib_uverbs_open_qp {
-- 
cgit v1.2.3-59-g8ed1b


From 3c7f67d1880db4bda8eed12ca603c92b5434390e Mon Sep 17 00:00:00 2001
From: Doug Ledford <dledford@redhat.com>
Date: Fri, 28 Jul 2017 13:47:24 -0400
Subject: IB/cma: Fix default RoCE type setting

The initial patch for changing the stack to use RoCEv2 GIDs by default
set the CMA_PREFERRED_ROCE_GID_TYPE to an incorrect value.  Instead of
an absolute value, we needed to set the right bit in a bitmask.  Correct
the default setting so we use RoCEv2 by default.

Fixes: 63a5f483af0e (IB/cma: Set default gid type to RoCEv2)
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 2d1fb8205ff0..ca4135c596ba 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,7 +72,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
-#define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
+#define CMA_PREFERRED_ROCE_GID_TYPE (1 << IB_GID_TYPE_ROCE_UDP_ENCAP)
 
 static const char * const cma_events[] = {
 	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
-- 
cgit v1.2.3-59-g8ed1b


From d541e45500bd269060c26387902e1bec9783c07c Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:37:43 -0400
Subject: IB/core: Convert ah_attr from OPA to IB when copying to user

OPA address handle atttibutes that have 32 bit LIDs would have to
be converted to IB address handle attribute with the LID field
programmed in the GID before copying to user space.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Don Hiatt <don.hiatt@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/ucm.c             |  2 +-
 drivers/infiniband/core/ucma.c            | 10 ++++---
 drivers/infiniband/core/uverbs_marshall.c | 48 +++++++++++++++++++++++++++----
 include/rdma/ib_marshall.h                |  6 ++--
 4 files changed, 54 insertions(+), 12 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 112099c86a19..f2a7f62c2834 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -618,7 +618,7 @@ static ssize_t ib_ucm_init_qp_attr(struct ib_ucm_file *file,
 	if (result)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 276f0ef835bd..eb85b546e223 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -248,14 +248,15 @@ static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst,
 	dst->qp_num = src->qp_num;
 }
 
-static void ucma_copy_ud_event(struct rdma_ucm_ud_param *dst,
+static void ucma_copy_ud_event(struct ib_device *device,
+			       struct rdma_ucm_ud_param *dst,
 			       struct rdma_ud_param *src)
 {
 	if (src->private_data_len)
 		memcpy(dst->private_data, src->private_data,
 		       src->private_data_len);
 	dst->private_data_len = src->private_data_len;
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
 	dst->qp_num = src->qp_num;
 	dst->qkey = src->qkey;
 }
@@ -335,7 +336,8 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 	uevent->resp.event = event->event;
 	uevent->resp.status = event->status;
 	if (cm_id->qp_type == IB_QPT_UD)
-		ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud);
+		ucma_copy_ud_event(cm_id->device, &uevent->resp.param.ud,
+				   &event->param.ud);
 	else
 		ucma_copy_conn_event(&uevent->resp.param.conn,
 				     &event->param.conn);
@@ -1157,7 +1159,7 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
 	if (ret)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))
 		ret = -EFAULT;
diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c
index 94fd989c9060..bd0acf376af0 100644
--- a/drivers/infiniband/core/uverbs_marshall.c
+++ b/drivers/infiniband/core/uverbs_marshall.c
@@ -33,10 +33,47 @@
 #include <linux/export.h>
 #include <rdma/ib_marshall.h>
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
-			     struct rdma_ah_attr *src)
+#define OPA_DEFAULT_GID_PREFIX cpu_to_be64(0xfe80000000000000ULL)
+static int rdma_ah_conv_opa_to_ib(struct ib_device *dev,
+				  struct rdma_ah_attr *ib,
+				  struct rdma_ah_attr *opa)
 {
+	struct ib_port_attr port_attr;
+	int ret = 0;
+
+	/* Do structure copy and the over-write fields */
+	*ib = *opa;
+
+	ib->type = RDMA_AH_ATTR_TYPE_IB;
+	rdma_ah_set_grh(ib, NULL, 0, 0, 1, 0);
+
+	if (ib_query_port(dev, opa->port_num, &port_attr)) {
+		/* Set to default subnet to indicate error */
+		rdma_ah_set_subnet_prefix(ib, OPA_DEFAULT_GID_PREFIX);
+		ret = -EINVAL;
+	} else {
+		rdma_ah_set_subnet_prefix(ib,
+					  cpu_to_be64(port_attr.subnet_prefix));
+	}
+	rdma_ah_set_interface_id(ib, OPA_MAKE_ID(rdma_ah_get_dlid(opa)));
+	return ret;
+}
+
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
+			     struct rdma_ah_attr *ah_attr)
+{
+	struct rdma_ah_attr *src = ah_attr;
+	struct rdma_ah_attr conv_ah;
+
 	memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved));
+
+	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
+	    (rdma_ah_get_dlid(ah_attr) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+	    (!rdma_ah_conv_opa_to_ib(device, &conv_ah, ah_attr)))
+		src = &conv_ah;
+
 	dst->dlid		   = rdma_ah_get_dlid(src);
 	dst->sl			   = rdma_ah_get_sl(src);
 	dst->src_path_bits	   = rdma_ah_get_path_bits(src);
@@ -57,7 +94,8 @@ void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
 }
 EXPORT_SYMBOL(ib_copy_ah_attr_to_user);
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src)
 {
 	dst->qp_state	        = src->qp_state;
@@ -76,8 +114,8 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
 	dst->max_recv_sge	= src->cap.max_recv_sge;
 	dst->max_inline_data	= src->cap.max_inline_data;
 
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
-	ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->alt_ah_attr, &src->alt_ah_attr);
 
 	dst->pkey_index		= src->pkey_index;
 	dst->alt_pkey_index	= src->alt_pkey_index;
diff --git a/include/rdma/ib_marshall.h b/include/rdma/ib_marshall.h
index 68cef3bd50fb..8ebf84ae9ed1 100644
--- a/include/rdma/ib_marshall.h
+++ b/include/rdma/ib_marshall.h
@@ -38,10 +38,12 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_user_sa.h>
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src);
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
 			     struct rdma_ah_attr *src);
 
 void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,
-- 
cgit v1.2.3-59-g8ed1b


From 1cb2fc0db764dae2c484dac5c93824003fe571fb Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:37:46 -0400
Subject: IB/mad: Change slid in RMPP recv from 16 to 32 bits

MAD RMPP contains slid field which is 16 bits in
length, increase it to 32 bits.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/mad_rmpp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/mad_rmpp.c b/drivers/infiniband/core/mad_rmpp.c
index 0d3cca0a8890..e5cf09c66fe6 100644
--- a/drivers/infiniband/core/mad_rmpp.c
+++ b/drivers/infiniband/core/mad_rmpp.c
@@ -64,7 +64,7 @@ struct mad_rmpp_recv {
 
 	__be64 tid;
 	u32 src_qp;
-	u16 slid;
+	u32 slid;
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;
-- 
cgit v1.2.3-59-g8ed1b


From 582faf3150f57b8364ac9d2aa731d7368ada7a4b Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:37:47 -0400
Subject: IB/core: Change port_attr.lid size from 16 to 32 bits

lid field in struct ib_port_attr is increased to 32 bits. This enables core
components to use larger LIDs if needed.
The user ABI is unchanged and return 16 bit values when queried.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/core_priv.h     | 1 +
 drivers/infiniband/core/uverbs_cmd.c    | 5 ++++-
 drivers/infiniband/hw/mlx4/alias_GUID.c | 2 +-
 drivers/infiniband/hw/mlx4/mad.c        | 2 +-
 drivers/infiniband/hw/mthca/mthca_mad.c | 2 +-
 include/rdma/ib_verbs.h                 | 2 +-
 include/rdma/opa_addr.h                 | 3 ++-
 7 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 11ae67514e13..6b54280530c9 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -38,6 +38,7 @@
 #include <linux/cgroup_rdma.h>
 
 #include <rdma/ib_verbs.h>
+#include <rdma/opa_addr.h>
 #include <rdma/ib_mad.h>
 #include "mad_priv.h"
 
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2c98533a0203..eef2623406cc 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -275,8 +275,11 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.bad_pkey_cntr   = attr.bad_pkey_cntr;
 	resp.qkey_viol_cntr  = attr.qkey_viol_cntr;
 	resp.pkey_tbl_len    = attr.pkey_tbl_len;
-	resp.lid 	     = attr.lid;
 	resp.sm_lid 	     = attr.sm_lid;
+	if (rdma_cap_opa_ah(ib_dev, cmd.port_num))
+		resp.lid  = OPA_TO_IB_UCAST_LID(attr.lid);
+	else
+		resp.lid     = (u16)attr.lid;
 	resp.lmc 	     = attr.lmc;
 	resp.max_vl_num      = attr.max_vl_num;
 	resp.sm_sl 	     = attr.sm_sl;
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index ea24230ea0d4..5a897b0106a9 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -528,7 +528,7 @@ static int set_guid_rec(struct ib_device *ibdev,
 
 	memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec));
 
-	guid_info_rec.lid = cpu_to_be16(attr.lid);
+	guid_info_rec.lid = cpu_to_be16((u16)attr.lid);
 	guid_info_rec.block_num = index;
 
 	memcpy(guid_info_rec.guid_info_list, rec_det->all_recs,
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 21d31cb1325f..00f057033cb9 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -860,7 +860,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = (u16)pattr.lid;
 
 	err = mlx4_MAD_IFC(to_mdev(ibdev),
 			   (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) |
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 7df3db71777a..617531f1bfc6 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -256,7 +256,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = (u16)pattr.lid;
 
 	err = mthca_MAD_IFC(to_mdev(ibdev),
 			    mad_flags & IB_MAD_IGNORE_MKEY,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b5732432bb29..4fa94e69b1fc 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -549,8 +549,8 @@ struct ib_port_attr {
 	u32			bad_pkey_cntr;
 	u32			qkey_viol_cntr;
 	u16			pkey_tbl_len;
-	u16			lid;
 	u16			sm_lid;
+	u32			lid;
 	u8			lmc;
 	u8			max_vl_num;
 	u8			sm_sl;
diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h
index eace28f1555d..46d0567fffea 100644
--- a/include/rdma/opa_addr.h
+++ b/include/rdma/opa_addr.h
@@ -50,7 +50,8 @@
 
 #define	OPA_SPECIAL_OUI		(0x00066AULL)
 #define OPA_MAKE_ID(x)          (cpu_to_be64(OPA_SPECIAL_OUI << 40 | (x)))
-
+#define OPA_TO_IB_UCAST_LID(x) (((x) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) \
+				? 0 : x)
 /**
  * ib_is_opa_gid: Returns true if the top 24 bits of the gid
  * contains the OPA_STL_OUI identifier. This identifies that
-- 
cgit v1.2.3-59-g8ed1b


From db58540b021a17e0ede64f761b740556d77f1679 Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:37:48 -0400
Subject: IB/core: Change port_attr.sm_lid from 16 to 32 bits

sm_lid field in struct ib_port_attr is increased to 32 bits. This
enables core components to use larger LIDs if needed.
The user ABI is unchanged and return 16 bit values when queried.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 8 +++++---
 include/rdma/ib_verbs.h              | 2 +-
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index eef2623406cc..01e2ff023980 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -275,11 +275,13 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.bad_pkey_cntr   = attr.bad_pkey_cntr;
 	resp.qkey_viol_cntr  = attr.qkey_viol_cntr;
 	resp.pkey_tbl_len    = attr.pkey_tbl_len;
-	resp.sm_lid 	     = attr.sm_lid;
-	if (rdma_cap_opa_ah(ib_dev, cmd.port_num))
+	if (rdma_cap_opa_ah(ib_dev, cmd.port_num)) {
 		resp.lid  = OPA_TO_IB_UCAST_LID(attr.lid);
-	else
+		resp.sm_lid  = OPA_TO_IB_UCAST_LID(attr.sm_lid);
+	} else {
 		resp.lid     = (u16)attr.lid;
+		resp.sm_lid  = (u16)attr.sm_lid;
+	}
 	resp.lmc 	     = attr.lmc;
 	resp.max_vl_num      = attr.max_vl_num;
 	resp.sm_sl 	     = attr.sm_sl;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 4fa94e69b1fc..620535908118 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -549,7 +549,7 @@ struct ib_port_attr {
 	u32			bad_pkey_cntr;
 	u32			qkey_viol_cntr;
 	u16			pkey_tbl_len;
-	u16			sm_lid;
+	u32			sm_lid;
 	u32			lid;
 	u8			lmc;
 	u8			max_vl_num;
-- 
cgit v1.2.3-59-g8ed1b


From 7db20ecd1d9700e2c240dee505162eb56ab55b5b Mon Sep 17 00:00:00 2001
From: "Hiatt, Don" <don.hiatt@intel.com>
Date: Thu, 8 Jun 2017 13:37:49 -0400
Subject: IB/core: Change wc.slid from 16 to 32 bits

slid field in struct ib_wc is increased to 32 bits.
This enables core components to use larger LIDs if needed.
The user ABI is unchanged and return 16 bit values when queried.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c            |  4 ++--
 drivers/infiniband/core/user_mad.c      |  2 +-
 drivers/infiniband/core/uverbs_cmd.c    | 10 +++++++---
 drivers/infiniband/hw/hfi1/mad.c        |  2 +-
 drivers/infiniband/hw/mlx4/mad.c        |  6 +++---
 drivers/infiniband/hw/mlx5/mad.c        |  2 +-
 drivers/infiniband/hw/mthca/mthca_cmd.c |  4 ++--
 drivers/infiniband/hw/mthca/mthca_mad.c |  2 +-
 drivers/infiniband/sw/rdmavt/cq.c       |  2 +-
 include/rdma/ib_verbs.h                 | 14 +++++++++++++-
 10 files changed, 32 insertions(+), 16 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 2b4d613a3474..b39ee16aa479 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1703,7 +1703,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 {
 	if (!cm_req_get_primary_subnet_local(req_msg)) {
 		if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->primary_local_lid = cpu_to_be16(wc->slid);
+			req_msg->primary_local_lid = ib_slid_be16(wc->slid);
 			cm_req_set_primary_sl(req_msg, wc->sl);
 		}
 
@@ -1713,7 +1713,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 
 	if (!cm_req_get_alt_subnet_local(req_msg)) {
 		if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->alt_local_lid = cpu_to_be16(wc->slid);
+			req_msg->alt_local_lid = ib_slid_be16(wc->slid);
 			cm_req_set_alt_sl(req_msg, wc->sl);
 		}
 
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 36a6f5c8914c..ff3c67a7aaad 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -229,7 +229,7 @@ static void recv_handler(struct ib_mad_agent *agent,
 	packet->mad.hdr.status	   = 0;
 	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
 	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
-	packet->mad.hdr.lid	   = cpu_to_be16(mad_recv_wc->wc->slid);
+	packet->mad.hdr.lid	   = ib_slid_be16(mad_recv_wc->wc->slid);
 	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
 	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
 	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 01e2ff023980..eb0da3784bf4 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1190,7 +1190,8 @@ out:
 	return ret ? ret : in_len;
 }
 
-static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
+static int copy_wc_to_user(struct ib_device *ib_dev, void __user *dest,
+			   struct ib_wc *wc)
 {
 	struct ib_uverbs_wc tmp;
 
@@ -1204,7 +1205,10 @@ static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
 	tmp.src_qp		= wc->src_qp;
 	tmp.wc_flags		= wc->wc_flags;
 	tmp.pkey_index		= wc->pkey_index;
-	tmp.slid		= wc->slid;
+	if (rdma_cap_opa_ah(ib_dev, wc->port_num))
+		tmp.slid  = OPA_TO_IB_UCAST_LID(wc->slid);
+	else
+		tmp.slid  = ib_slid_cpu16(wc->slid);
 	tmp.sl			= wc->sl;
 	tmp.dlid_path_bits	= wc->dlid_path_bits;
 	tmp.port_num		= wc->port_num;
@@ -1248,7 +1252,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file,
 		if (!ret)
 			break;
 
-		ret = copy_wc_to_user(data_ptr, &wc);
+		ret = copy_wc_to_user(ib_dev, data_ptr, &wc);
 		if (ret)
 			goto out_put;
 
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 5977673a52d4..00ebc26cd187 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -3958,7 +3958,7 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 			       const struct ib_wc *in_wc)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u16 slid = in_wc->slid;
+	u16 slid = ib_slid_cpu16(in_wc->slid);
 	u16 pkey;
 
 	if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys))
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 00f057033cb9..04fb44e7699e 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -169,7 +169,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier,
@@ -625,7 +625,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
 	} else {
 		tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
-		tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+		tun_mad->hdr.slid_mac_47_32 = ib_slid_be16(wc->slid);
 	}
 
 	ib_dma_sync_single_for_device(&dev->ib_dev,
@@ -826,7 +826,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		}
 	}
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
 		forward_trap(to_mdev(ibdev), port_num, in_mad);
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 95db929bdc34..cd2264ac88ae 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -78,7 +78,7 @@ static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	u16 slid;
 	int err;
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0)
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 9d83a53c0c67..e19ae0b9b439 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1921,7 +1921,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
 		MTHCA_PUT(inbox, val,               MAD_IFC_G_PATH_OFFSET);
 
-		MTHCA_PUT(inbox, in_wc->slid,       MAD_IFC_RLID_OFFSET);
+		MTHCA_PUT(inbox, ib_slid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET);
 		MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
 
 		if (in_grh)
@@ -1929,7 +1929,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mthca_cmd_box(dev, inmailbox->dma, outmailbox->dma,
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 617531f1bfc6..a9caadab22cf 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -205,7 +205,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 		      u16 *out_mad_pkey_index)
 {
 	int err;
-	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	u16 slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 0ae2ff8cf81e..0335a3df74d5 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
 		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = entry->slid;
+		wc->uqueue[head].slid = ib_slid_cpu16(entry->slid);
 		wc->uqueue[head].sl = entry->sl;
 		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
 		wc->uqueue[head].port_num = entry->port_num;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 620535908118..7eaf7d2ab424 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -948,7 +948,7 @@ struct ib_wc {
 	u32			src_qp;
 	int			wc_flags;
 	u16			pkey_index;
-	u16			slid;
+	u32			slid;
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
@@ -3706,4 +3706,16 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 	else
 		return RDMA_AH_ATTR_TYPE_IB;
 }
+
+/* Return slid in 16bit CPU encoding */
+static inline u16 ib_slid_cpu16(u32 slid)
+{
+	return (u16)slid;
+}
+
+/* Return slid in 16bit BE encoding */
+static inline u16 ib_slid_be16(u32 slid)
+{
+	return cpu_to_be16((u16)slid);
+}
 #endif /* IB_VERBS_H */
-- 
cgit v1.2.3-59-g8ed1b


From e92aa00a518971fca6b79aa87a1a9c5e5aa51f3b Mon Sep 17 00:00:00 2001
From: "Hiatt, Don" <don.hiatt@intel.com>
Date: Thu, 8 Jun 2017 13:38:02 -0400
Subject: IB/CM: Add OPA Path record support to CM

Add OPA path record support to the Connection Manager.

Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c | 50 +++++++++++++++++++++++++++++++++++++-------
 include/rdma/opa_addr.h      | 18 ++++++++++++++++
 2 files changed, 60 insertions(+), 8 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index b39ee16aa479..885c429b4942 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1175,6 +1175,11 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 {
 	struct sa_path_rec *pri_path = param->primary_path;
 	struct sa_path_rec *alt_path = param->alternate_path;
+	bool pri_ext = false;
+
+	if (pri_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		pri_ext = opa_is_extended_lid(pri_path->opa.dlid,
+					      pri_path->opa.slid);
 
 	cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_REQ));
@@ -1202,18 +1207,24 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 		cm_req_set_srq(req_msg, param->srq);
 	}
 
+	req_msg->primary_local_gid = pri_path->sgid;
+	req_msg->primary_remote_gid = pri_path->dgid;
+	if (pri_ext) {
+		req_msg->primary_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid));
+		req_msg->primary_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid));
+	}
 	if (pri_path->hop_limit <= 1) {
-		req_msg->primary_local_lid =
+		req_msg->primary_local_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_slid(pri_path)));
-		req_msg->primary_remote_lid =
+		req_msg->primary_remote_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_dlid(pri_path)));
 	} else {
 		/* Work-around until there's a way to obtain remote LID info */
 		req_msg->primary_local_lid = IB_LID_PERMISSIVE;
 		req_msg->primary_remote_lid = IB_LID_PERMISSIVE;
 	}
-	req_msg->primary_local_gid = pri_path->sgid;
-	req_msg->primary_remote_gid = pri_path->dgid;
 	cm_req_set_primary_flow_label(req_msg, pri_path->flow_label);
 	cm_req_set_primary_packet_rate(req_msg, pri_path->rate);
 	req_msg->primary_traffic_class = pri_path->traffic_class;
@@ -1225,17 +1236,29 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 			       pri_path->packet_life_time));
 
 	if (alt_path) {
+		bool alt_ext = false;
+
+		if (alt_path->rec_type == SA_PATH_REC_TYPE_OPA)
+			alt_ext = opa_is_extended_lid(alt_path->opa.dlid,
+						      alt_path->opa.slid);
+
+		req_msg->alt_local_gid = alt_path->sgid;
+		req_msg->alt_remote_gid = alt_path->dgid;
+		if (alt_ext) {
+			req_msg->alt_local_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid));
+			req_msg->alt_remote_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid));
+		}
 		if (alt_path->hop_limit <= 1) {
-			req_msg->alt_local_lid =
+			req_msg->alt_local_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_slid(alt_path)));
-			req_msg->alt_remote_lid =
+			req_msg->alt_remote_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_dlid(alt_path)));
 		} else {
 			req_msg->alt_local_lid = IB_LID_PERMISSIVE;
 			req_msg->alt_remote_lid = IB_LID_PERMISSIVE;
 		}
-		req_msg->alt_local_gid = alt_path->sgid;
-		req_msg->alt_remote_gid = alt_path->dgid;
 		cm_req_set_alt_flow_label(req_msg,
 					  alt_path->flow_label);
 		cm_req_set_alt_packet_rate(req_msg, alt_path->rate);
@@ -2843,6 +2866,11 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 			  const void *private_data,
 			  u8 private_data_len)
 {
+	bool alt_ext = false;
+
+	if (alternate_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		alt_ext = opa_is_extended_lid(alternate_path->opa.dlid,
+					      alternate_path->opa.slid);
 	cm_format_mad_hdr(&lap_msg->hdr, CM_LAP_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_LAP));
 	lap_msg->local_comm_id = cm_id_priv->id.local_id;
@@ -2856,6 +2884,12 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 		htons(ntohl(sa_path_get_dlid(alternate_path)));
 	lap_msg->alt_local_gid = alternate_path->sgid;
 	lap_msg->alt_remote_gid = alternate_path->dgid;
+	if (alt_ext) {
+		lap_msg->alt_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.slid));
+		lap_msg->alt_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.dlid));
+	}
 	cm_lap_set_flow_label(lap_msg, alternate_path->flow_label);
 	cm_lap_set_traffic_class(lap_msg, alternate_path->traffic_class);
 	lap_msg->alt_hop_limit = alternate_path->hop_limit;
diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h
index 46d0567fffea..9b5e642cf550 100644
--- a/include/rdma/opa_addr.h
+++ b/include/rdma/opa_addr.h
@@ -77,4 +77,22 @@ static inline u32 opa_get_lid_from_gid(union ib_gid *gid)
 {
 	return be64_to_cpu(gid->global.interface_id) & 0xFFFFFFFF;
 }
+
+/**
+ * opa_is_extended_lid: Returns true if dlid or slid are
+ * extended.
+ *
+ * @dlid: The DLID
+ * @slid: The SLID
+ */
+static inline bool opa_is_extended_lid(u32 dlid, u32 slid)
+{
+	if ((be32_to_cpu(dlid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
+	    (be32_to_cpu(slid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)))
+		return true;
+	else
+		return false;
+}
 #endif /* OPA_ADDR_H */
-- 
cgit v1.2.3-59-g8ed1b


From 6b3c0e6e6d5abfefb0112cd450e0aee97fcab7a8 Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:38:03 -0400
Subject: IB/CM: Create appropriate path records when handling CM request

When handling an incoming conection request, ib_cm creates
either an IB or an OPA path record based on the gid field
in the request.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Don Hiatt <don.hiatt@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c | 38 +++++++++++++++++++++++++++++++-------
 1 file changed, 31 insertions(+), 7 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 885c429b4942..4d870a0c2955 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1428,6 +1428,21 @@ static inline int cm_is_active_peer(__be64 local_ca_guid, __be64 remote_ca_guid,
 		 (be32_to_cpu(local_qpn) > be32_to_cpu(remote_qpn))));
 }
 
+static bool cm_req_has_alt_path(struct cm_req_msg *req_msg)
+{
+	return ((req_msg->alt_local_lid) ||
+		(ib_is_opa_gid(&req_msg->alt_local_gid)));
+}
+
+static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
+				 struct sa_path_rec *path, union ib_gid *gid)
+{
+	if (ib_is_opa_gid(gid) && rdma_cap_opa_ah(ib_device, port_num))
+		path->rec_type = SA_PATH_REC_TYPE_OPA;
+	else
+		path->rec_type = SA_PATH_REC_TYPE_IB;
+}
+
 static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 				     struct sa_path_rec *primary_path,
 				     struct sa_path_rec *alt_path)
@@ -1807,9 +1822,12 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		cm_format_paths_from_req(req_msg, &work->path[0],
 					 &work->path[1]);
@@ -1834,16 +1852,19 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
 			       &work->path[0].sgid, sizeof work->path[0].sgid,
 			       NULL, 0);
 		goto rejected;
 	}
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
 					 cm_id_priv);
 		if (ret) {
@@ -2962,8 +2983,6 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 				    struct sa_path_rec *path,
 				    struct cm_lap_msg *lap_msg)
 {
-	memset(path, 0, sizeof *path);
-	path->rec_type = SA_PATH_REC_TYPE_IB;
 	path->dgid = lap_msg->alt_local_gid;
 	path->sgid = lap_msg->alt_remote_gid;
 	sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
@@ -2999,6 +3018,11 @@ static int cm_lap_handler(struct cm_work *work)
 		return -EINVAL;
 
 	param = &work->cm_event.param.lap_rcvd;
+	memset(&work->path[0], 0, sizeof(work->path[1]));
+	cm_path_set_rec_type(work->port->cm_dev->ib_device,
+			     work->port->port_num,
+			     &work->path[0],
+			     &lap_msg->alt_local_gid);
 	param->alternate_path = &work->path[0];
 	cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg);
 	work->cm_event.private_data = &lap_msg->private_data;
-- 
cgit v1.2.3-59-g8ed1b


From ac3a949fb2fff36bebdc4fab90567ed349ea7245 Mon Sep 17 00:00:00 2001
From: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Date: Thu, 8 Jun 2017 13:38:04 -0400
Subject: IB/CM: Set appropriate slid and dlid when handling CM request

If extended LIDs are being used, a connection request contains
OPA GIDs in them. Extract the lids from the OPA gids and populate
slid/dlid fields in the path records that are created when handling
a connection request.

Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Reviewed-by: Don Hiatt <don.hiatt@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c | 67 ++++++++++++++++++++++++++++++++++++--------
 1 file changed, 56 insertions(+), 11 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 4d870a0c2955..d5ca101057b7 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1443,16 +1443,48 @@ static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
 		path->rec_type = SA_PATH_REC_TYPE_IB;
 }
 
+static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
+					struct sa_path_rec *primary_path,
+					struct sa_path_rec *alt_path)
+{
+	u32 lid;
+
+	if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(primary_path,
+				 htonl(ntohs(req_msg->primary_local_lid)));
+		sa_path_set_slid(primary_path,
+				 htonl(ntohs(req_msg->primary_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->primary_local_gid);
+		sa_path_set_dlid(primary_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid);
+		sa_path_set_slid(primary_path, cpu_to_be32(lid));
+	}
+
+	if (!cm_req_has_alt_path(req_msg))
+		return;
+
+	if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(alt_path,
+				 htonl(ntohs(req_msg->alt_local_lid)));
+		sa_path_set_slid(alt_path,
+				 htonl(ntohs(req_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->alt_local_gid);
+		sa_path_set_dlid(alt_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid);
+		sa_path_set_slid(alt_path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 				     struct sa_path_rec *primary_path,
 				     struct sa_path_rec *alt_path)
 {
 	primary_path->dgid = req_msg->primary_local_gid;
 	primary_path->sgid = req_msg->primary_remote_gid;
-	sa_path_set_dlid(primary_path,
-			 htonl(ntohs(req_msg->primary_local_lid)));
-	sa_path_set_slid(primary_path,
-			 htonl(ntohs(req_msg->primary_remote_lid)));
 	primary_path->flow_label = cm_req_get_primary_flow_label(req_msg);
 	primary_path->hop_limit = req_msg->primary_hop_limit;
 	primary_path->traffic_class = req_msg->primary_traffic_class;
@@ -1469,13 +1501,9 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 	primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
 	primary_path->service_id = req_msg->service_id;
 
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		alt_path->dgid = req_msg->alt_local_gid;
 		alt_path->sgid = req_msg->alt_remote_gid;
-		sa_path_set_dlid(alt_path,
-				 htonl(ntohs(req_msg->alt_local_lid)));
-		sa_path_set_slid(alt_path,
-				 htonl(ntohs(req_msg->alt_remote_lid)));
 		alt_path->flow_label = cm_req_get_alt_flow_label(req_msg);
 		alt_path->hop_limit = req_msg->alt_hop_limit;
 		alt_path->traffic_class = req_msg->alt_traffic_class;
@@ -1492,6 +1520,7 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 		alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
 		alt_path->service_id = req_msg->service_id;
 	}
+	cm_format_path_lid_from_req(req_msg, primary_path, alt_path);
 }
 
 static u16 cm_get_bth_pkey(struct cm_work *work)
@@ -2979,14 +3008,29 @@ out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 }
 EXPORT_SYMBOL(ib_send_cm_lap);
 
+static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg,
+					struct sa_path_rec *path)
+{
+	u32 lid;
+
+	if (path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
+		sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid);
+		sa_path_set_dlid(path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid);
+		sa_path_set_slid(path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 				    struct sa_path_rec *path,
 				    struct cm_lap_msg *lap_msg)
 {
 	path->dgid = lap_msg->alt_local_gid;
 	path->sgid = lap_msg->alt_remote_gid;
-	sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
-	sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
 	path->flow_label = cm_lap_get_flow_label(lap_msg);
 	path->hop_limit = lap_msg->alt_hop_limit;
 	path->traffic_class = cm_lap_get_traffic_class(lap_msg);
@@ -3000,6 +3044,7 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 	path->packet_life_time_selector = IB_SA_EQ;
 	path->packet_life_time = cm_lap_get_local_ack_timeout(lap_msg);
 	path->packet_life_time -= (path->packet_life_time > 0);
+	cm_format_path_lid_from_lap(lap_msg, path);
 }
 
 static int cm_lap_handler(struct cm_work *work)
-- 
cgit v1.2.3-59-g8ed1b


From 9047811b776ce09ba06623dd2a846cc501f0065b Mon Sep 17 00:00:00 2001
From: "Ismail, Mustafa" <mustafa.ismail@intel.com>
Date: Wed, 28 Jun 2017 09:02:45 -0500
Subject: RDMA/core: Add wait/retry version of ibnl_unicast

Add a wait/retry version of ibnl_unicast, ibnl_unicast_wait,
and modify ibnl_unicast to not wait/retry.  This eliminates
the undesirable wait for future users of ibnl_unicast.

Change Portmapper calls originating from kernel to user-space
to use ibnl_unicast_wait and take advantage of the wait/retry
logic in netlink_unicast.

Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Chien Tin Tung <chien.tin.tung@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/core/iwpm_msg.c |  6 +++---
 drivers/infiniband/core/netlink.c  | 12 +++++++++++-
 include/rdma/rdma_netlink.h        | 10 ++++++++++
 3 files changed, 24 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index a0e7c16d8bd8..add99b92afdf 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -174,7 +174,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -251,7 +251,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";
@@ -312,7 +312,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 94931c474d41..0fc50e15ae22 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -232,11 +232,21 @@ int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	int err;
 
-	err = netlink_unicast(nls, skb, pid, 0);
+	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
 	return (err < 0) ? err : 0;
 }
 EXPORT_SYMBOL(ibnl_unicast);
 
+int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      __u32 pid)
+{
+	int err;
+
+	err = netlink_unicast(nls, skb, pid, 0);
+	return (err < 0) ? err : 0;
+}
+EXPORT_SYMBOL(ibnl_unicast_wait);
+
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)
 {
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 348c102cb5f6..5b1466770917 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -63,6 +63,16 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			__u32 pid);
 
+/**
+ * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @nlh: Header of the netlink message to send
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      __u32 pid);
+
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
-- 
cgit v1.2.3-59-g8ed1b


From c9901724a2f14128ef6a57986babcbfbcf61a257 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 5 Jun 2017 10:20:11 +0300
Subject: RDMA/netlink: Remove netlink clients infrastructure

RDMA netlink has a complicated infrastructure for dynamically
registering and de-registering netlink clients to the NETLINK_RDMA
group. The complicated portion of this code is not widely used because
2 of the 3 current clients are statically compiled together with
netlink.c. The infrastructure, therefore, is deemed overkill.

Refactor the code to eliminate the dynamically added clients. Now all
clients are pre-registered in a client array at compile time, and at run
time they merely check-in with the infrastructure to pass their callback
table for inclusion in the pre-sized client array.

This also allows for future cleanups and removal of unneeded code in the
iwcm* netlink handler.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Chien Tin Tung <chien.tin.tung@intel.com>
---
 drivers/infiniband/core/cma.c       |   6 +-
 drivers/infiniband/core/core_priv.h |   4 +-
 drivers/infiniband/core/device.c    |  45 +++------
 drivers/infiniband/core/iwcm.c      |  10 +-
 drivers/infiniband/core/netlink.c   | 185 +++++++++++++++++-------------------
 include/rdma/rdma_netlink.h         |  13 +--
 6 files changed, 112 insertions(+), 151 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index ca4135c596ba..2a16a559bdda 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4512,9 +4512,7 @@ static int __init cma_init(void)
 	if (ret)
 		goto err;
 
-	if (ibnl_add_client(RDMA_NL_RDMA_CM, ARRAY_SIZE(cma_cb_table),
-			    cma_cb_table))
-		pr_warn("RDMA CMA: failed to add netlink callback\n");
+	rdma_nl_register(RDMA_NL_RDMA_CM, cma_cb_table);
 	cma_configfs_init();
 
 	return 0;
@@ -4531,7 +4529,7 @@ err_wq:
 static void __exit cma_cleanup(void)
 {
 	cma_configfs_exit();
-	ibnl_remove_client(RDMA_NL_RDMA_CM);
+	rdma_nl_unregister(RDMA_NL_RDMA_CM);
 	ib_unregister_client(&cma_client);
 	unregister_netdevice_notifier(&cma_nb);
 	rdma_addr_unregister_client(&addr_client);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 11ae67514e13..e759c27113cd 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -179,8 +179,8 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int ibnl_init(void);
-void ibnl_cleanup(void);
+int rdma_nl_init(void);
+void rdma_nl_exit(void);
 
 /**
  * Check if there are any listeners to the netlink group
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index a5dfab6adf49..d0994cd30eae 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1086,29 +1086,15 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
-		.module = THIS_MODULE },
+		.dump = ib_nl_handle_resolve_resp},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
-		.module = THIS_MODULE },
+		.dump = ib_nl_handle_set_timeout},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp,
-		.module = THIS_MODULE },
+		.dump = ib_nl_handle_ip_res_resp},
 };
 
-static int ib_add_ibnl_clients(void)
-{
-	return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table),
-			       ibnl_ls_cb_table);
-}
-
-static void ib_remove_ibnl_clients(void)
-{
-	ibnl_remove_client(RDMA_NL_LS);
-}
-
 static int __init ib_core_init(void)
 {
 	int ret;
@@ -1130,9 +1116,9 @@ static int __init ib_core_init(void)
 		goto err_comp;
 	}
 
-	ret = ibnl_init();
+	ret = rdma_nl_init();
 	if (ret) {
-		pr_warn("Couldn't init IB netlink interface\n");
+		pr_warn("Couldn't init IB netlink interface: err %d\n", ret);
 		goto err_sysfs;
 	}
 
@@ -1154,24 +1140,17 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
-	ret = ib_add_ibnl_clients();
-	if (ret) {
-		pr_warn("Couldn't register ibnl clients\n");
-		goto err_sa;
-	}
-
 	ret = register_lsm_notifier(&ibdev_lsm_nb);
 	if (ret) {
 		pr_warn("Couldn't register LSM notifier. ret %d\n", ret);
-		goto err_ibnl_clients;
+		goto err_sa;
 	}
 
+	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 
 	return 0;
 
-err_ibnl_clients:
-	ib_remove_ibnl_clients();
 err_sa:
 	ib_sa_cleanup();
 err_mad:
@@ -1179,7 +1158,7 @@ err_mad:
 err_addr:
 	addr_cleanup();
 err_ibnl:
-	ibnl_cleanup();
+	rdma_nl_exit();
 err_sysfs:
 	class_unregister(&ib_class);
 err_comp:
@@ -1191,13 +1170,13 @@ err:
 
 static void __exit ib_core_cleanup(void)
 {
-	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_cache_cleanup();
-	ib_remove_ibnl_clients();
+	rdma_nl_unregister(RDMA_NL_LS);
+	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_sa_cleanup();
 	ib_mad_cleanup();
 	addr_cleanup();
-	ibnl_cleanup();
+	rdma_nl_exit();
 	class_unregister(&ib_class);
 	destroy_workqueue(ib_comp_wq);
 	/* Make sure that any pending umem accounting work is done. */
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 31661b5c1743..8599271d8be6 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -1175,12 +1175,8 @@ static int __init iw_cm_init(void)
 	ret = iwpm_init(RDMA_NL_IWCM);
 	if (ret)
 		pr_err("iw_cm: couldn't init iwpm\n");
-
-	ret = ibnl_add_client(RDMA_NL_IWCM, ARRAY_SIZE(iwcm_nl_cb_table),
-			      iwcm_nl_cb_table);
-	if (ret)
-		pr_err("iw_cm: couldn't register netlink callbacks\n");
-
+	else
+		rdma_nl_register(RDMA_NL_IWCM, iwcm_nl_cb_table);
 	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM);
 	if (!iwcm_wq)
 		return -ENOMEM;
@@ -1200,7 +1196,7 @@ static void __exit iw_cm_cleanup(void)
 {
 	unregister_net_sysctl_table(iwcm_ctl_table_hdr);
 	destroy_workqueue(iwcm_wq);
-	ibnl_remove_client(RDMA_NL_IWCM);
+	rdma_nl_unregister(RDMA_NL_IWCM);
 	iwpm_exit(RDMA_NL_IWCM);
 }
 
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 0fc50e15ae22..06f7ba31fbdd 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -39,16 +39,13 @@
 #include <rdma/rdma_netlink.h>
 #include "core_priv.h"
 
-struct ibnl_client {
-	struct list_head		list;
-	int				index;
-	int				nops;
-	const struct ibnl_client_cbs   *cb_table;
-};
+#include "core_priv.h"
 
-static DEFINE_MUTEX(ibnl_mutex);
+static DEFINE_MUTEX(rdma_nl_mutex);
 static struct sock *nls;
-static LIST_HEAD(client_list);
+static struct {
+	const struct ibnl_client_cbs   *cb_table;
+} rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 int ibnl_chk_listeners(unsigned int group)
 {
@@ -57,58 +54,74 @@ int ibnl_chk_listeners(unsigned int group)
 	return 0;
 }
 
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[])
+static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {
-	struct ibnl_client *cur;
-	struct ibnl_client *nl_client;
+	static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS - 1] = {
+				  RDMA_NL_RDMA_CM_NUM_OPS,
+				  RDMA_NL_IWPM_NUM_OPS,
+				  0,
+				  RDMA_NL_LS_NUM_OPS,
+				  0 };
 
-	nl_client = kmalloc(sizeof *nl_client, GFP_KERNEL);
-	if (!nl_client)
-		return -ENOMEM;
+	/*
+	 * This BUILD_BUG_ON is intended to catch addition of new
+	 * RDMA netlink protocol without updating the array above.
+	 */
+	BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6);
 
-	nl_client->index	= index;
-	nl_client->nops		= nops;
-	nl_client->cb_table	= cb_table;
+	if (type > RDMA_NL_NUM_CLIENTS - 1)
+		return false;
 
-	mutex_lock(&ibnl_mutex);
+	return (op < max_num_ops[type - 1]) ? true : false;
+}
 
-	list_for_each_entry(cur, &client_list, list) {
-		if (cur->index == index) {
-			pr_warn("Client for %d already exists\n", index);
-			mutex_unlock(&ibnl_mutex);
-			kfree(nl_client);
-			return -EINVAL;
-		}
-	}
+static bool is_nl_valid(unsigned int type, unsigned int op)
+{
+	if (!is_nl_msg_valid(type, op) ||
+	    !rdma_nl_types[type].cb_table ||
+	    !rdma_nl_types[type].cb_table[op].dump)
+		return false;
+	return true;
+}
 
-	list_add_tail(&nl_client->list, &client_list);
+void rdma_nl_register(unsigned int index,
+		      const struct ibnl_client_cbs cb_table[])
+{
+	mutex_lock(&rdma_nl_mutex);
+	if (!is_nl_msg_valid(index, 0)) {
+		/*
+		 * All clients are not interesting in success/failure of
+		 * this call. They want to see the print to error log and
+		 * continue their initialization. Print warning for them,
+		 * because it is programmer's error to be here.
+		 */
+		mutex_unlock(&rdma_nl_mutex);
+		WARN(true,
+		     "The not-valid %u index was supplied to RDMA netlink\n",
+		     index);
+		return;
+	}
 
-	mutex_unlock(&ibnl_mutex);
+	if (rdma_nl_types[index].cb_table) {
+		mutex_unlock(&rdma_nl_mutex);
+		WARN(true,
+		     "The %u index is already registered in RDMA netlink\n",
+		     index);
+		return;
+	}
 
-	return 0;
+	rdma_nl_types[index].cb_table = cb_table;
+	mutex_unlock(&rdma_nl_mutex);
 }
-EXPORT_SYMBOL(ibnl_add_client);
+EXPORT_SYMBOL(rdma_nl_register);
 
-int ibnl_remove_client(int index)
+void rdma_nl_unregister(unsigned int index)
 {
-	struct ibnl_client *cur, *next;
-
-	mutex_lock(&ibnl_mutex);
-	list_for_each_entry_safe(cur, next, &client_list, list) {
-		if (cur->index == index) {
-			list_del(&(cur->list));
-			mutex_unlock(&ibnl_mutex);
-			kfree(cur);
-			return 0;
-		}
-	}
-	pr_warn("Can't remove callback for client idx %d. Not found\n", index);
-	mutex_unlock(&ibnl_mutex);
-
-	return -EINVAL;
+	mutex_lock(&rdma_nl_mutex);
+	rdma_nl_types[index].cb_table = NULL;
+	mutex_unlock(&rdma_nl_mutex);
 }
-EXPORT_SYMBOL(ibnl_remove_client);
+EXPORT_SYMBOL(rdma_nl_unregister);
 
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 		   int len, int client, int op, int flags)
@@ -149,45 +162,31 @@ EXPORT_SYMBOL(ibnl_put_attr);
 static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
-	struct ibnl_client *client;
 	int type = nlh->nlmsg_type;
-	int index = RDMA_NL_GET_CLIENT(type);
+	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
+	struct netlink_callback cb = {};
+	struct netlink_dump_control c = {};
 
-	list_for_each_entry(client, &client_list, list) {
-		if (client->index == index) {
-			if (op >= client->nops || !client->cb_table[op].dump)
-				return -EINVAL;
-
-			/*
-			 * For response or local service set_timeout request,
-			 * there is no need to use netlink_dump_start.
-			 */
-			if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-			    (index == RDMA_NL_LS &&
-			     op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
-				struct netlink_callback cb = {
-					.skb = skb,
-					.nlh = nlh,
-					.dump = client->cb_table[op].dump,
-					.module = client->cb_table[op].module,
-				};
-
-				return cb.dump(skb, &cb);
-			}
-
-			{
-				struct netlink_dump_control c = {
-					.dump = client->cb_table[op].dump,
-					.module = client->cb_table[op].module,
-				};
-				return netlink_dump_start(nls, skb, nlh, &c);
-			}
-		}
+	if (!is_nl_valid(index, op))
+		return -EINVAL;
+
+	/*
+	 * For response or local service set_timeout request,
+	 * there is no need to use netlink_dump_start.
+	 */
+	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
+	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
+		cb.skb = skb;
+		cb.nlh = nlh;
+		cb.dump = rdma_nl_types[index].cb_table[op].dump;
+		cb.module = rdma_nl_types[index].cb_table[op].module;
+		return cb.dump(skb, &cb);
 	}
 
-	pr_info("Index %d wasn't found in client list\n", index);
-	return -EINVAL;
+	c.dump = rdma_nl_types[index].cb_table[op].dump;
+	c.module = rdma_nl_types[index].cb_table[op].module;
+	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
 static void ibnl_rcv_reply_skb(struct sk_buff *skb)
@@ -221,10 +220,10 @@ static void ibnl_rcv_reply_skb(struct sk_buff *skb)
 
 static void ibnl_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&ibnl_mutex);
+	mutex_lock(&rdma_nl_mutex);
 	ibnl_rcv_reply_skb(skb);
 	netlink_rcv_skb(skb, &ibnl_rcv_msg);
-	mutex_unlock(&ibnl_mutex);
+	mutex_unlock(&rdma_nl_mutex);
 }
 
 int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -254,32 +253,26 @@ int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 EXPORT_SYMBOL(ibnl_multicast);
 
-int __init ibnl_init(void)
+int __init rdma_nl_init(void)
 {
 	struct netlink_kernel_cfg cfg = {
 		.input	= ibnl_rcv,
 	};
 
 	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
-	if (!nls) {
-		pr_warn("Failed to create netlink socket\n");
+	if (!nls)
 		return -ENOMEM;
-	}
 
 	nls->sk_sndtimeo = 10 * HZ;
 	return 0;
 }
 
-void ibnl_cleanup(void)
+void rdma_nl_exit(void)
 {
-	struct ibnl_client *cur, *next;
+	int idx;
 
-	mutex_lock(&ibnl_mutex);
-	list_for_each_entry_safe(cur, next, &client_list, list) {
-		list_del(&(cur->list));
-		kfree(cur);
-	}
-	mutex_unlock(&ibnl_mutex);
+	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
+		rdma_nl_unregister(idx);
 
 	netlink_kernel_release(nls);
 }
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 5b1466770917..aadf0ab963b2 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -11,23 +11,18 @@ struct ibnl_client_cbs {
 };
 
 /**
- * Add a a client to the list of IB netlink exporters.
+ * Register client in RDMA netlink.
  * @index: Index of the added client
- * @nops: Number of supported ops by the added client.
  * @cb_table: A table for op->callback
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[]);
+void rdma_nl_register(unsigned int index,
+		      const struct ibnl_client_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
  * @index: Index of the removed IB client.
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_remove_client(int index);
+void rdma_nl_unregister(unsigned int index);
 
 /**
  * Put a new message in a supplied skb.
-- 
cgit v1.2.3-59-g8ed1b


From 64401b69b29164c5731018cc44fc9b144ac9c5ae Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 30 May 2017 11:29:56 +0300
Subject: RDMA/netlink: Remove redundant owner option for netlink callbacks

Owner field is not needed to be set because netlink is part of ib_core
which will be unloaded last after all other modules are unloaded.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/cma.c     | 3 +--
 drivers/infiniband/core/netlink.c | 2 --
 include/rdma/rdma_netlink.h       | 1 -
 3 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 2a16a559bdda..0c85f140e616 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4459,8 +4459,7 @@ out:
 }
 
 static const struct ibnl_client_cbs cma_cb_table[] = {
-	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats,
-				       .module = THIS_MODULE },
+	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
 static int cma_init_net(struct net *net)
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 06f7ba31fbdd..cd9b7e7b7d2c 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -180,12 +180,10 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cb.skb = skb;
 		cb.nlh = nlh;
 		cb.dump = rdma_nl_types[index].cb_table[op].dump;
-		cb.module = rdma_nl_types[index].cb_table[op].module;
 		return cb.dump(skb, &cb);
 	}
 
 	c.dump = rdma_nl_types[index].cb_table[op].dump;
-	c.module = rdma_nl_types[index].cb_table[op].module;
 	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index aadf0ab963b2..c124d8e43fc8 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -7,7 +7,6 @@
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
-	struct module *module;
 };
 
 /**
-- 
cgit v1.2.3-59-g8ed1b


From 3c3e75d5ff75f9a076cac254fd32476ca80fdffc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 8 Jun 2017 09:05:12 +0300
Subject: RDMA/netlink: Avoid double pass for RDMA netlink messages

The standard netlink_rcv_skb function skips messages without
NLM_F_REQUEST flag in it, while SA netlink client issues them.

In commit bc10ed7d3d19 ("IB/core: Add rdma netlink helper functions")
the local function was introduced to allow such messages.

This led to double pass for every incoming message.

In this patch, we unify that local implementation and netlink_rcv_skb
functions, so there will be no need for double pass anymore.

As a outcome, this combined function gained more strict check
for NLM_F_REQUEST flag and it is now allowed for SA pathquery
client only.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/netlink.c | 62 +++++++++++++++++++++++++++------------
 1 file changed, 44 insertions(+), 18 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index cd9b7e7b7d2c..826fbd612c7d 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -159,8 +159,8 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct netlink_ext_ack *extack)
+static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct netlink_ext_ack *extack)
 {
 	int type = nlh->nlmsg_type;
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
@@ -187,40 +187,66 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
-static void ibnl_rcv_reply_skb(struct sk_buff *skb)
+/*
+ * This function is similar to netlink_rcv_skb with one exception:
+ * It calls to the callback for the netlink messages without NLM_F_REQUEST
+ * flag. These messages are intended for RDMA_NL_LS consumer, so it is allowed
+ * for that consumer only.
+ */
+static int rdma_nl_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
+						   struct nlmsghdr *,
+						   struct netlink_ext_ack *))
 {
+	struct netlink_ext_ack extack = {};
 	struct nlmsghdr *nlh;
-	int msglen;
+	int err;
 
-	/*
-	 * Process responses until there is no more message or the first
-	 * request. Generally speaking, it is not recommended to mix responses
-	 * with requests.
-	 */
 	while (skb->len >= nlmsg_total_size(0)) {
+		int msglen;
+
 		nlh = nlmsg_hdr(skb);
+		err = 0;
 
 		if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
-			return;
+			return 0;
 
-		/* Handle response only */
-		if (nlh->nlmsg_flags & NLM_F_REQUEST)
-			return;
+		/*
+		 * Generally speaking, the only requests are handled
+		 * by the kernel, but RDMA_NL_LS is different, because it
+		 * runs backward netlink scheme. Kernel initiates messages
+		 * and waits for reply with data to keep pathrecord cache
+		 * in sync.
+		 */
+		if (!(nlh->nlmsg_flags & NLM_F_REQUEST) &&
+		    (RDMA_NL_GET_CLIENT(nlh->nlmsg_type) != RDMA_NL_LS))
+			goto ack;
+
+		/* Skip control messages */
+		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
+			goto ack;
 
-		ibnl_rcv_msg(skb, nlh, NULL);
+		err = cb(skb, nlh, &extack);
+		if (err == -EINTR)
+			goto skip;
 
+ack:
+		if (nlh->nlmsg_flags & NLM_F_ACK || err)
+			netlink_ack(skb, nlh, err, &extack);
+
+skip:
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
 		skb_pull(skb, msglen);
 	}
+
+	return 0;
 }
 
-static void ibnl_rcv(struct sk_buff *skb)
+static void rdma_nl_rcv(struct sk_buff *skb)
 {
 	mutex_lock(&rdma_nl_mutex);
-	ibnl_rcv_reply_skb(skb);
-	netlink_rcv_skb(skb, &ibnl_rcv_msg);
+	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
 	mutex_unlock(&rdma_nl_mutex);
 }
 
@@ -254,7 +280,7 @@ EXPORT_SYMBOL(ibnl_multicast);
 int __init rdma_nl_init(void)
 {
 	struct netlink_kernel_cfg cfg = {
-		.input	= ibnl_rcv,
+		.input	= rdma_nl_rcv,
 	};
 
 	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
-- 
cgit v1.2.3-59-g8ed1b


From 93fa50760b99aa12950421d0f3d2631694ca3e74 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 1 Jun 2017 12:42:36 +0300
Subject: RDMA/iwcm: Remove useless check of netlink client validity

RDMA netlink implementation guarantees that supplied
client number is in allowed range.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Chien Tin Tung <chien.tin.tung@intel.com>
---
 drivers/infiniband/core/iwpm_util.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index f13870e69ccd..32ca2aaa4e3b 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -54,8 +54,6 @@ static struct iwpm_admin_data iwpm_admin;
 int iwpm_init(u8 nl_client)
 {
 	int ret = 0;
-	if (iwpm_valid_client(nl_client))
-		return -EINVAL;
 	mutex_lock(&iwpm_admin_lock);
 	if (atomic_read(&iwpm_admin.refcount) == 0) {
 		iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE *
@@ -383,15 +381,11 @@ int iwpm_get_nlmsg_seq(void)
 
 int iwpm_valid_client(u8 nl_client)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return 0;
 	return iwpm_admin.client_list[nl_client];
 }
 
 void iwpm_set_valid(u8 nl_client, int valid)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return;
 	iwpm_admin.client_list[nl_client] = valid;
 }
 
-- 
cgit v1.2.3-59-g8ed1b


From 5d7ee40907507e8439044f415f3e1de216a26dea Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 1 Jun 2017 11:59:44 +0300
Subject: RDMA/iwcm: Remove extra EXPORT_SYMBOLS

The iwcm exports functions which are not used outside of ib_core.
This patch simply removes these EXPORT_SYMBOLS.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Chien Tin Tung <chien.tin.tung@intel.com>
---
 drivers/infiniband/core/iwpm_msg.c  | 12 ------------
 drivers/infiniband/core/iwpm_util.c |  5 -----
 2 files changed, 17 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index add99b92afdf..45de263305f5 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -42,7 +42,6 @@ int iwpm_valid_pid(void)
 {
 	return iwpm_user_pid > 0;
 }
-EXPORT_SYMBOL(iwpm_valid_pid);
 
 /*
  * iwpm_register_pid - Send a netlink query to user space
@@ -122,7 +121,6 @@ pid_query_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_register_pid);
 
 /*
  * iwpm_add_mapping - Send a netlink add mapping message
@@ -191,7 +189,6 @@ add_mapping_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_mapping);
 
 /*
  * iwpm_add_and_query_mapping - Send a netlink add and query
@@ -267,7 +264,6 @@ query_mapping_error:
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping);
 
 /*
  * iwpm_remove_mapping - Send a netlink remove mapping message
@@ -328,7 +324,6 @@ remove_mapping_error:
 		dev_kfree_skb_any(skb);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapping);
 
 /* netlink attribute policy for the received response to register pid request */
 static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = {
@@ -397,7 +392,6 @@ register_pid_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_register_pid_cb);
 
 /* netlink attribute policy for the received response to add mapping request */
 static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = {
@@ -466,7 +460,6 @@ add_mapping_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_mapping_cb);
 
 /* netlink attribute policy for the response to add and query mapping request
  * and response with remote address info */
@@ -558,7 +551,6 @@ query_mapping_response_exit:
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
 
 /*
  * iwpm_remote_info_cb - Process a port mapper message, containing
@@ -627,7 +619,6 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 			"remote_info: Mapped remote sockaddr:");
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remote_info_cb);
 
 /* netlink attribute policy for the received request for mapping info */
 static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {
@@ -677,7 +668,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_mapping_info_cb);
 
 /* netlink attribute policy for the received mapping info ack */
 static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = {
@@ -707,7 +697,6 @@ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_ack_mapping_info_cb);
 
 /* netlink attribute policy for the received port mapper error message */
 static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = {
@@ -751,4 +740,3 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_mapping_error_cb);
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index 32ca2aaa4e3b..c46442ac71a2 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -81,7 +81,6 @@ init_exit:
 	}
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_init);
 
 static void free_hash_bucket(void);
 static void free_reminfo_bucket(void);
@@ -107,7 +106,6 @@ int iwpm_exit(u8 nl_client)
 	iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_exit);
 
 static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *,
 					       struct sockaddr_storage *);
@@ -146,7 +144,6 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_create_mapinfo);
 
 int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 			struct sockaddr_storage *mapped_local_addr)
@@ -182,7 +179,6 @@ remove_mapinfo_exit:
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapinfo);
 
 static void free_hash_bucket(void)
 {
@@ -295,7 +291,6 @@ get_remote_info_exit:
 	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_get_remote_info);
 
 struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 					u8 nl_client, gfp_t gfp)
-- 
cgit v1.2.3-59-g8ed1b


From e3a2b93dddad315f01a4b67faee738954c084072 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 12 Jun 2017 16:00:19 +0300
Subject: RDMA/netlink: Add flag to consolidate common handling

Add ability to provide flags to control RDMA netlink callbacks
and convert addr.c and sa_query.c to be first users of such
infrastructure. It allows to move their CAP_NET_ADMIN checks
into netlink core.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c     |  3 +--
 drivers/infiniband/core/device.c   | 12 +++++++++---
 drivers/infiniband/core/netlink.c  |  4 ++++
 drivers/infiniband/core/sa_query.c |  6 ++----
 include/rdma/rdma_netlink.h        |  6 ++++++
 5 files changed, 22 insertions(+), 9 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 01236cef7bfb..9f3339861ec5 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -134,8 +134,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	if (ib_nl_is_good_ip_resp(nlh))
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index d0994cd30eae..7ae29cc49a5e 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1088,11 +1088,17 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp},
+		.dump = ib_nl_handle_resolve_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout},
+		.dump = ib_nl_handle_set_timeout,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp},
+		.dump = ib_nl_handle_ip_res_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
 static int __init ib_core_init(void)
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 826fbd612c7d..c5ee62a24960 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -171,6 +171,10 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
+	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
 	/*
 	 * For response or local service set_timeout request,
 	 * there is no need to use netlink_dump_start.
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 70fa4cabe48e..b499f4422f41 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1033,8 +1033,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	int ret;
 
 	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
@@ -1109,8 +1108,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	int ret;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	spin_lock_irqsave(&ib_nl_request_lock, flags);
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index c124d8e43fc8..6ea36ec45401 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -7,6 +7,12 @@
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
+	u8 flags;
+};
+
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
 /**
-- 
cgit v1.2.3-59-g8ed1b


From 1a1c116f3dcf1658ee1e395bd13a556187d547f2 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 16:38:04 +0300
Subject: RDMA/netlink: Simplify the put_msg and put_attr

Reuse standard macros to cancel the netlink message
in case of error.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 27 ++++++---------------------
 1 file changed, 6 insertions(+), 21 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index c5ee62a24960..e2395a1d9f45 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -126,36 +126,21 @@ EXPORT_SYMBOL(rdma_nl_unregister);
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 		   int len, int client, int op, int flags)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			 len, flags);
+	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags);
 	if (!*nlh)
-		goto out_nlmsg_trim;
-	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
+		return NULL;
 	return nlmsg_data(*nlh);
-
-out_nlmsg_trim:
-	nlmsg_trim(skb, prev_tail);
-	return NULL;
 }
 EXPORT_SYMBOL(ibnl_put_msg);
 
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	if (nla_put(skb, type, len, data))
-		goto nla_put_failure;
-	nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail;
+	if (nla_put(skb, type, len, data)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
 	return 0;
-
-nla_put_failure:
-	nlmsg_trim(skb, prev_tail - nlh->nlmsg_len);
-	return -EMSGSIZE;
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-- 
cgit v1.2.3-59-g8ed1b


From f00e64637061876ec7b6383b0bd80197c51e7312 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 15:35:20 +0300
Subject: RDMA/netlink: Rename and remove redundant parameter from
 ibnl_unicast*

Netlink message header is not needed for unicast reply, hence remove it.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/iwpm_msg.c  |  6 +++---
 drivers/infiniband/core/iwpm_util.c |  4 ++--
 drivers/infiniband/core/netlink.c   | 10 ++++------
 include/rdma/rdma_netlink.h         |  8 ++------
 4 files changed, 11 insertions(+), 17 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 45de263305f5..ca3c160bb9da 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -172,7 +172,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
@@ -248,7 +248,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";
@@ -308,7 +308,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index c46442ac71a2..c81c55942626 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -597,7 +597,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
-	ret = ibnl_unicast(skb, nlh, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";
@@ -626,7 +626,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index e2395a1d9f45..b95a70013f19 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -239,25 +239,23 @@ static void rdma_nl_rcv(struct sk_buff *skb)
 	mutex_unlock(&rdma_nl_mutex);
 }
 
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid)
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
 {
 	int err;
 
 	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
 	return (err < 0) ? err : 0;
 }
-EXPORT_SYMBOL(ibnl_unicast);
+EXPORT_SYMBOL(rdma_nl_unicast);
 
-int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
-		      __u32 pid)
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
 {
 	int err;
 
 	err = netlink_unicast(nls, skb, pid, 0);
 	return (err < 0) ? err : 0;
 }
-EXPORT_SYMBOL(ibnl_unicast_wait);
+EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 6ea36ec45401..e7b0779385e9 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -56,22 +56,18 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
 
 /**
  * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
-		      __u32 pid);
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
-- 
cgit v1.2.3-59-g8ed1b


From 4d7f693af0c9d0d6940ff36f5adca1adfa0e7e6e Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 15:44:32 +0300
Subject: RDMA/netlink: Rename and remove redundant parameter from
 ibnl_multicast

The pointer to netlink header was not used in the ibnl_multicast
function, so let's remove it and simplify the function
signature.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c     | 2 +-
 drivers/infiniband/core/iwpm_msg.c | 2 +-
 drivers/infiniband/core/netlink.c  | 5 ++---
 drivers/infiniband/core/sa_query.c | 2 +-
 include/rdma/rdma_netlink.h        | 4 +---
 5 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 9f3339861ec5..30cf764824ec 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -184,7 +184,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
 
 	/* Make the request retry, so when we get the response from userspace
 	 * we will have something.
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index ca3c160bb9da..30825bb9b8e9 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -103,7 +103,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index b95a70013f19..5c627d1fbaa9 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -257,12 +257,11 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
 }
 EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags)
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
 {
 	return nlmsg_multicast(nls, skb, 0, group, flags);
 }
-EXPORT_SYMBOL(ibnl_multicast);
+EXPORT_SYMBOL(rdma_nl_multicast);
 
 int __init rdma_nl_init(void)
 {
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index b499f4422f41..977f64d0e983 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -861,7 +861,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
 	if (!ret)
 		ret = len;
 	else
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index e7b0779385e9..16a94c425938 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -72,12 +72,10 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
 #endif /* _RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From ff61c425c1c563f1d688d59caf3b18a395cbf9c4 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 15:51:16 +0300
Subject: RDMA/netlink: Simplify and rename ibnl_chk_listeners

Make ibnl_chk_listeners function to be one line by removing
unneeded comparison.

Rename that function to be complaint to other functions in RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c     | 2 +-
 drivers/infiniband/core/netlink.c  | 7 +++----
 drivers/infiniband/core/sa_query.c | 2 +-
 include/rdma/rdma_netlink.h        | 6 ++++++
 4 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 30cf764824ec..7310ece99cd9 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -325,7 +325,7 @@ static void queue_req(struct addr_req *req)
 static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 			  const void *daddr, u32 seq, u16 family)
 {
-	if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+	if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
 		return -EADDRNOTAVAIL;
 
 	/* We fill in what we can, the response will fill the rest */
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 5c627d1fbaa9..514959ccaf2d 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -47,12 +47,11 @@ static struct {
 	const struct ibnl_client_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
-int ibnl_chk_listeners(unsigned int group)
+int rdma_nl_chk_listeners(unsigned int group)
 {
-	if (netlink_has_listeners(nls, group) == 0)
-		return -1;
-	return 0;
+	return (netlink_has_listeners(nls, group)) ? 0 : -1;
 }
+EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
 static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 977f64d0e983..2cc85c2b74b7 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1418,7 +1418,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
 	if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
 	    (!(query->flags & IB_SA_QUERY_OPA))) {
-		if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
+		if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
 			if (!ib_nl_make_request(query, gfp_mask))
 				return id;
 		}
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 16a94c425938..348e0bbe0fc9 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -78,4 +78,10 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
  */
 int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int rdma_nl_chk_listeners(unsigned int group);
 #endif /* _RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 3250b4dbd87aa08c21891cabfc6f6b48b36fd7e5 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 19 Jun 2017 18:23:45 +0300
Subject: RDMA/netlink: Rename netlink callback struct

The RDMA netlink client infrastructure was removed and made obsolete.
The old infrastructure defined struct ibnl_client_cbs. Now that all
uses of this have been updated to the new infrastructure, rename the
struct to be compliant with the current stack naming standards:
struct rdma_nl_cbs.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/cma.c     | 2 +-
 drivers/infiniband/core/device.c  | 2 +-
 drivers/infiniband/core/iwcm.c    | 2 +-
 drivers/infiniband/core/netlink.c | 4 ++--
 include/rdma/rdma_netlink.h       | 4 ++--
 5 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0c85f140e616..d8edd8b11561 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4458,7 +4458,7 @@ out:
 	return skb->len;
 }
 
-static const struct ibnl_client_cbs cma_cb_table[] = {
+static const struct rdma_nl_cbs cma_cb_table[] = {
 	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 7ae29cc49a5e..33a39518848c 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1086,7 +1086,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
 		.dump = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 8599271d8be6..452a3115e3e6 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason)
 }
 EXPORT_SYMBOL(iwcm_reject_msg);
 
-static struct ibnl_client_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 514959ccaf2d..a7082adae16b 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -44,7 +44,7 @@
 static DEFINE_MUTEX(rdma_nl_mutex);
 static struct sock *nls;
 static struct {
-	const struct ibnl_client_cbs   *cb_table;
+	const struct rdma_nl_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 int rdma_nl_chk_listeners(unsigned int group)
@@ -84,7 +84,7 @@ static bool is_nl_valid(unsigned int type, unsigned int op)
 }
 
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[])
+		      const struct rdma_nl_cbs cb_table[])
 {
 	mutex_lock(&rdma_nl_mutex);
 	if (!is_nl_msg_valid(index, 0)) {
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 348e0bbe0fc9..92f8832297ab 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -5,7 +5,7 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };
@@ -21,7 +21,7 @@ enum rdma_nl_flags {
  * @cb_table: A table for op->callback
  */
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[]);
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
-- 
cgit v1.2.3-59-g8ed1b


From 8030c8357a94ce6397dd8df6296925f0f4b1f9b7 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Mon, 19 Jun 2017 14:04:56 +0300
Subject: RDMA/core: Add iterator over ib_devices

The coming nldev needs to iterate over all IB devices in the system
and in order to not expose the ib_devices list outside the devices.c,
it is necessary to provide function iterator.

Current version is written explicitly for nldev callback to avoid
over-engineering at this stage, but it can be easily extended for
other types.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/core_priv.h |  8 ++++++++
 drivers/infiniband/core/device.c    | 25 +++++++++++++++++++++++++
 2 files changed, 33 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index e759c27113cd..0c175590cf92 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -102,6 +102,14 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+typedef int (*nldev_callback)(struct ib_device *device,
+			      struct sk_buff *skb,
+			      struct netlink_callback *cb,
+			      unsigned int idx);
+
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb);
+
 enum ib_cache_gid_default_mode {
 	IB_CACHE_GID_DEFAULT_MODE_SET,
 	IB_CACHE_GID_DEFAULT_MODE_DELETE
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 33a39518848c..8828f26250a8 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -892,6 +892,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 	up_read(&lists_rwsem);
 }
 
+/**
+ * ib_enum_all_devs - enumerate all ib_devices
+ * @cb: Callback to call for each found ib_device
+ *
+ * Enumerates all ib_devices and calls callback() on each device.
+ */
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb)
+{
+	struct ib_device *dev;
+	unsigned int idx = 0;
+	int ret = 0;
+
+	down_read(&lists_rwsem);
+	list_for_each_entry(dev, &device_list, core_list) {
+		ret = nldev_cb(dev, skb, cb, idx);
+		if (ret)
+			break;
+		idx++;
+	}
+
+	up_read(&lists_rwsem);
+	return ret;
+}
+
 /**
  * ib_query_pkey - Get P_Key table entry
  * @device:Device to query
-- 
cgit v1.2.3-59-g8ed1b


From ecc82c53f9a4ce08ba7df626a4262c86841ced8f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 14:39:59 +0300
Subject: RDMA/core: Add and expose static device index

This patch adds static device index in similar fashion to
already available in netdev world (struct net->ifindex).

In downstream patches, the RDMA nelink will use this idx-to-ib_device
conversion, so as part of this commit, we are exposing the translation
function to be visible for IB/core users.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/core_priv.h |  5 +++++
 drivers/infiniband/core/device.c    | 37 ++++++++++++++++++++++++++++++++++++-
 include/rdma/ib_verbs.h             |  2 ++
 3 files changed, 43 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 0c175590cf92..cbdcc81e1df8 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -309,4 +309,9 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map,
 	return 0;
 }
 #endif
+
+struct ib_device *__ib_device_get_by_index(u32 ifindex);
+/* RDMA device netlink */
+void nldev_init(void);
+void nldev_exit(void);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 8828f26250a8..deae8b940994 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -134,6 +134,17 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
+struct ib_device *__ib_device_get_by_index(u32 index)
+{
+	struct ib_device *device;
+
+	list_for_each_entry(device, &device_list, core_list)
+		if (device->index == index)
+			return device;
+
+	return NULL;
+}
+
 static struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;
@@ -145,7 +156,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 	return NULL;
 }
 
-
 static int alloc_name(char *name)
 {
 	unsigned long *inuse;
@@ -394,6 +404,30 @@ static int ib_security_change(struct notifier_block *nb, unsigned long event,
 	return NOTIFY_OK;
 }
 
+/**
+ *	__dev_new_index	-	allocate an device index
+ *
+ *	Returns a suitable unique value for a new device interface
+ *	number.  It assumes that there are less than 2^32-1 ib devices
+ *	will be present in the system.
+ */
+static u32 __dev_new_index(void)
+{
+	/*
+	 * The device index to allow stable naming.
+	 * Similar to struct net -> ifindex.
+	 */
+	static u32 index;
+
+	for (;;) {
+		if (!(++index))
+			index = 1;
+
+		if (!__ib_device_get_by_index(index))
+			return index;
+	}
+}
+
 /**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register
@@ -492,6 +526,7 @@ int ib_register_device(struct ib_device *device,
 		if (client->add && !add_client_context(device, client))
 			client->add(device);
 
+	device->index = __dev_new_index();
 	down_write(&lists_rwsem);
 	list_add_tail(&device->core_list, &device_list);
 	up_write(&lists_rwsem);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 1082b4c81b2c..3391df5fdc9c 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2298,6 +2298,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this
-- 
cgit v1.2.3-59-g8ed1b


From 1830ba21b9a475cfc6159e6cfe532c75fe7682a4 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 15 Jun 2017 12:46:33 +0300
Subject: RDMA/netlink: Add and implement doit netlink callback

The .doit callback is used by netlink core to differentiate
between get and set operations. Common convention is to use
that call for command operations like (SET, ADD, e.t.c.) and/or
access without NLF_M_DUMP flag.

This commit adds proper declaration and implementation
to RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 19 ++++++++++++++-----
 include/rdma/rdma_netlink.h       |  2 ++
 2 files changed, 16 insertions(+), 5 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index a7082adae16b..484d6a8a2811 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -76,9 +76,13 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 
 static bool is_nl_valid(unsigned int type, unsigned int op)
 {
-	if (!is_nl_msg_valid(type, op) ||
-	    !rdma_nl_types[type].cb_table ||
-	    !rdma_nl_types[type].cb_table[op].dump)
+	const struct rdma_nl_cbs *cb_table;
+
+	if (!is_nl_msg_valid(type, op))
+		return false;
+
+	cb_table = rdma_nl_types[type].cb_table;
+	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
 		return false;
 	return true;
 }
@@ -151,6 +155,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
@@ -169,10 +174,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cb.nlh = nlh;
 		cb.dump = rdma_nl_types[index].cb_table[op].dump;
 		return cb.dump(skb, &cb);
+	} else {
+		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+	if (rdma_nl_types[index].cb_table[op].doit)
+		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	return ret;
 
-	c.dump = rdma_nl_types[index].cb_table[op].dump;
-	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
 /*
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 92f8832297ab..e25bf1988846 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -6,6 +6,8 @@
 #include <uapi/rdma/rdma_netlink.h>
 
 struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };
-- 
cgit v1.2.3-59-g8ed1b


From c729943a77c108253c46b2d50c8a15a888facf4c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 15 Jun 2017 13:14:13 +0300
Subject: RDMA/netlink: Reduce indirection access to cb_table

Introduce intermediate variable to store access to fields
of cb_table.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 484d6a8a2811..e36c39e3cc2b 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -155,12 +155,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	const struct rdma_nl_cbs *cb_table;
 	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	cb_table = rdma_nl_types[type].cb_table;
+
+	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
@@ -172,14 +175,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
 		cb.skb = skb;
 		cb.nlh = nlh;
-		cb.dump = rdma_nl_types[index].cb_table[op].dump;
+		cb.dump = cb_table[op].dump;
 		return cb.dump(skb, &cb);
 	} else {
-		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		c.dump = cb_table[op].dump;
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
-	if (rdma_nl_types[index].cb_table[op].doit)
-		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	if (cb_table[op].doit)
+		ret = cb_table[op].doit(skb, nlh, extack);
 	return ret;
 
 }
-- 
cgit v1.2.3-59-g8ed1b


From 647c75ac59a48a54dafd4475d14a645a0025a4f4 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 15 Jun 2017 14:20:39 +0300
Subject: RDMA/netlink: Convert LS to doit callback

RDMA_NL_LS protocol is actually does not dump anything,
but sets data and it should be handled by doit callback.

This patch actually converts RDMA_NL_LS to doit callback, while
preserving IWCM and RDMA_CM flows through netlink_dump_start().

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/addr.c      |  5 ++---
 drivers/infiniband/core/core_priv.h |  9 ++++++---
 drivers/infiniband/core/device.c    |  6 +++---
 drivers/infiniband/core/netlink.c   | 28 ++++++++++------------------
 drivers/infiniband/core/sa_query.c  |  8 ++++----
 5 files changed, 25 insertions(+), 31 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 7310ece99cd9..16b3bdffeb96 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -129,10 +129,9 @@ static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
-
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
 	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index cbdcc81e1df8..57beb1cceda3 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -198,11 +198,14 @@ void rdma_nl_exit(void);
 int ibnl_chk_listeners(unsigned int group);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb);
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack);
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 
 int ib_get_cached_subnet_prefix(struct ib_device *device,
 				u8                port_num,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index deae8b940994..5272c3806c39 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1148,15 +1148,15 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
+		.doit = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
+		.doit = ib_nl_handle_set_timeout,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp,
+		.doit = ib_nl_handle_ip_res_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 };
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index e36c39e3cc2b..145ad5343780 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -153,38 +153,30 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int type = nlh->nlmsg_type;
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
-	struct netlink_callback cb = {};
-	struct netlink_dump_control c = {};
 	const struct rdma_nl_cbs *cb_table;
-	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	cb_table = rdma_nl_types[type].cb_table;
+	cb_table = rdma_nl_types[index].cb_table;
 
 	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	/*
-	 * For response or local service set_timeout request,
-	 * there is no need to use netlink_dump_start.
-	 */
-	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
-		cb.skb = skb;
-		cb.nlh = nlh;
-		cb.dump = cb_table[op].dump;
-		return cb.dump(skb, &cb);
-	} else {
-		c.dump = cb_table[op].dump;
+	/* FIXME: Convert IWCM to properly handle doit callbacks */
+	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM ||
+	    index == RDMA_NL_IWCM) {
+		struct netlink_dump_control c = {
+			.dump = cb_table[op].dump,
+		};
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+
 	if (cb_table[op].doit)
-		ret = cb_table[op].doit(skb, nlh, extack);
-	return ret;
+		return cb_table[op].doit(skb, nlh, extack);
 
+	return 0;
 }
 
 /*
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 2cc85c2b74b7..da29e2863c84 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1021,9 +1021,9 @@ static void ib_nl_request_timeout(struct work_struct *work)
 }
 
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
 	const struct nlattr *attr;
 	unsigned long flags;
@@ -1097,9 +1097,9 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb)
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
 	struct ib_sa_query *query;
 	struct ib_mad_send_buf *send_buf;
-- 
cgit v1.2.3-59-g8ed1b


From 8bc67414f28c995ccfa29a12984b5dae188b3df8 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Sun, 18 Jun 2017 16:37:27 +0300
Subject: RDMA/netlink: Update copyright

Add Mellanox to the copyright header.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 145ad5343780..cd692bd73793 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2017 Mellanox Technologies Inc.  All rights reserved.
  * Copyright (c) 2010 Voltaire Inc.  All rights reserved.
  *
  * This software is available to you under a choice of one of two
-- 
cgit v1.2.3-59-g8ed1b


From 1a6e7c31d71db34d1b9bc3acc87eaea6c2ecc997 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 20 Jun 2017 07:55:53 +0300
Subject: RDMA/netlink: Add netlink device definitions to UAPI

Introduce new defines to rdma_netlink.h, so the RDMA configuration tool
will be able to communicate with RDMA subsystem by using the shared defines.

The addition of new client (NLDEV) revealed the fact that we exposed by
mistake the RDMA_NL_I40IW define which is not backed by any RDMA netlink
by now and it won't be exposed in the future too. So this patch reuses
the value and deletes the old defines.

The NLDEV operates with objects. The struct ib_device has two straightforward
objects: device itself and ports of that device.

This brings us to propose the following commands to work on those objects:
 * RDMA_NLDEV_CMD_{GET,SET,NEW,DEL} - works on ib_device itself
 * RDMA_NLDEV_CMD_PORT_{GET,SET,NEW,DEL} - works on ports of specific ib_device

Those commands receive/return the device index (RDMA_NLDEV_ATTR_DEV_INDEX)
and port index (RDMA_NLDEV_ATTR_PORT_INDEX). For device object accesses,
the RDMA_NLDEV_ATTR_PORT_INDEX will return the maximum number of ports
for specific ib_device and for port access the actual port index.

The port index starts from 1 to follow RDMA/core internal semantics and
the sysfs exposed knobs.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/netlink.c |  2 +-
 include/uapi/rdma/rdma_netlink.h  | 39 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 39 insertions(+), 2 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index cd692bd73793..27352a352770 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -61,7 +61,7 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 				  RDMA_NL_IWPM_NUM_OPS,
 				  0,
 				  RDMA_NL_LS_NUM_OPS,
-				  0 };
+				  RDMA_NLDEV_NUM_OPS };
 
 	/*
 	 * This BUILD_BUG_ON is intended to catch addition of new
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 02fe8390c18f..a44229fa5eca 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 
@@ -222,4 +222,41 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET commamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 6c80b41abe22ae3c0d98f39a88f4b8fb501910d3 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 20 Jun 2017 09:14:15 +0300
Subject: RDMA/netlink: Add nldev initialization flows

Add nldev init and exit flows to the RDMA/core.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/Makefile |  3 ++-
 drivers/infiniband/core/device.c |  2 ++
 drivers/infiniband/core/nldev.c  | 45 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+), 1 deletion(-)
 create mode 100644 drivers/infiniband/core/nldev.c

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index e3cdafff8ece..920609a0872e 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -11,7 +11,8 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o \
-				security.o
+				security.o nldev.o
+
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 5272c3806c39..66b109bc6753 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1212,6 +1212,7 @@ static int __init ib_core_init(void)
 		goto err_sa;
 	}
 
+	nldev_init();
 	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 
@@ -1237,6 +1238,7 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	nldev_exit();
 	rdma_nl_unregister(RDMA_NL_LS);
 	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_sa_cleanup();
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
new file mode 100644
index 000000000000..1d1e4f214874
--- /dev/null
+++ b/drivers/infiniband/core/nldev.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <rdma/rdma_netlink.h>
+
+#include "core_priv.h"
+
+void __init nldev_init(void)
+{
+	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+}
+
+void __exit nldev_exit(void)
+{
+	rdma_nl_unregister(RDMA_NL_NLDEV);
+}
-- 
cgit v1.2.3-59-g8ed1b


From b4c598a67ea19c5784e542c03dd912a0ce36109a Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 20 Jun 2017 09:59:14 +0300
Subject: RDMA/netlink: Implement nldev device dumpit calback

This patch adds the ability to return all available devices
together with their properties.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 64 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 1d1e4f214874..4b8b0f5d5344 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -30,13 +30,75 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/netlink.h>
 #include <rdma/rdma_netlink.h>
 
 #include "core_priv.h"
 
+static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
+	[RDMA_NLDEV_ATTR_DEV_INDEX]     = { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = IB_DEVICE_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+};
+
+static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int _nldev_get_dumpit(struct ib_device *device,
+			     struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     unsigned int idx)
+{
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+
+	if (idx < start)
+		return 0;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, NLM_F_MULTI);
+
+	if (fill_dev_info(skb, device)) {
+		nlmsg_cancel(skb, nlh);
+		goto out;
+	}
+
+	nlmsg_end(skb, nlh);
+
+	idx++;
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	/*
+	 * There is no need to take lock, because
+	 * we are relying on ib_core's lists_rwsem
+	 */
+	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
+}
+
+static const struct rdma_nl_cbs nldev_cb_table[] = {
+	[RDMA_NLDEV_CMD_GET] = {
+		.dump = nldev_get_dumpit,
+	},
+};
+
 void __init nldev_init(void)
 {
-	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+	rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
 }
 
 void __exit nldev_exit(void)
-- 
cgit v1.2.3-59-g8ed1b


From e5c9469efcb18a6b7aed5e6f32e478b0298ad968 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 15 Jun 2017 20:33:08 +0300
Subject: RDMA/netlink: Add nldev device doit implementation

Provide ability to query specific device.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 4b8b0f5d5344..666940f2b49a 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -53,6 +53,45 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_dev_info(msg, device);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int _nldev_get_dumpit(struct ib_device *device,
 			     struct sk_buff *skb,
 			     struct netlink_callback *cb,
@@ -92,6 +131,7 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
+		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
 };
-- 
cgit v1.2.3-59-g8ed1b


From 7d02f605f0dce0ef1b76aeffe2d36794738f24a0 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 20 Jun 2017 11:30:33 +0300
Subject: RDMA/netlink: Add nldev port dumpit implementation

This patch implements the query interface to get all
ports data for the specific device.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 71 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 666940f2b49a..1318e246196a 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -53,6 +53,18 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int fill_port_info(struct sk_buff *msg,
+			  struct ib_device *device, u32 port)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
+		return -EMSGSIZE;
+	return 0;
+}
+
 static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
@@ -129,11 +141,70 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+	u32 idx = 0;
+	u32 ifindex;
+	int err;
+	u32 p;
+
+	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, NULL);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(ifindex);
+	if (!device)
+		return -EINVAL;
+
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+		/*
+		 * The dumpit function returns all information from specific
+		 * index. This specific index is taken from the netlink
+		 * messages request sent by user and it is available
+		 * in cb->args[0].
+		 *
+		 * Usually, the user doesn't fill this field and it causes
+		 * to return everything.
+		 *
+		 */
+		if (idx < start) {
+			idx++;
+			continue;
+		}
+
+		nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+				cb->nlh->nlmsg_seq,
+				RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+						 RDMA_NLDEV_CMD_PORT_GET),
+				0, NLM_F_MULTI);
+
+		if (fill_port_info(skb, device, p)) {
+			nlmsg_cancel(skb, nlh);
+			goto out;
+		}
+		idx++;
+		nlmsg_end(skb, nlh);
+	}
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
+	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.dump = nldev_port_get_dumpit,
+	},
 };
 
 void __init nldev_init(void)
-- 
cgit v1.2.3-59-g8ed1b


From c3f66f7b0052ea854744372fdaae7817f5358e4f Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 22 Jun 2017 16:10:38 +0300
Subject: RDMA/netlink: Implement nldev port doit callback

Provide ability to get specific to device and port information.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c | 44 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 1318e246196a..db9d9ffc1415 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -141,6 +141,49 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	u32 port;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (!rdma_is_port_valid(device, port))
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_port_info(msg, device, port);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int nldev_port_get_dumpit(struct sk_buff *skb,
 				 struct netlink_callback *cb)
 {
@@ -203,6 +246,7 @@ static const struct rdma_nl_cbs nldev_cb_table[] = {
 		.dump = nldev_get_dumpit,
 	},
 	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.doit = nldev_port_get_doit,
 		.dump = nldev_port_get_dumpit,
 	},
 };
-- 
cgit v1.2.3-59-g8ed1b


From ac50525374315b9b609747f83b07f8dccb06b722 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 20 Jun 2017 14:47:08 +0300
Subject: RDMA/netlink: Expose device and port capability masks

The port capability mask is exposed to user space via sysfs interface,
while device capabilities are available for verbs only.

This patch provides those capabilities through netlink interface.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
---
 drivers/infiniband/core/nldev.c  | 19 +++++++++++++++++++
 include/uapi/rdma/rdma_netlink.h |  5 +++++
 2 files changed, 24 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index db9d9ffc1415..94c1e49074f5 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -50,18 +50,37 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
 		return -EMSGSIZE;
+
+	BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      device->attrs.device_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
 static int fill_port_info(struct sk_buff *msg,
 			  struct ib_device *device, u32 port)
 {
+	struct ib_port_attr attr;
+	int ret;
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
 		return -EMSGSIZE;
 	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
 		return -EMSGSIZE;
+
+	ret = ib_query_port(device, port, &attr);
+	if (ret)
+		return ret;
+
+	BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      (u64)attr.port_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index a44229fa5eca..90de11db6580 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -257,6 +257,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
 
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 9abb0d1bbd9529c574eacd8586e2bf68d17966cd Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 27 Jun 2017 16:49:53 +0300
Subject: RDMA: Simplify get firmware interface

There is a need to forward FW version to user space
application through RDMA netlink. In order to make it safe, there
is need to declare nla_policy and limit the size of FW string.

The new define IB_FW_VERSION_NAME_MAX will limit the size of
FW version string. That define was chosen to be equal to
ETHTOOL_FWVERS_LEN, because many drivers anyway are limited
by that value indirectly.

The introduction of this define allows us to remove the string size
from get_fw_str function signature.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/device.c               | 4 ++--
 drivers/infiniband/core/sysfs.c                | 4 ++--
 drivers/infiniband/hw/cxgb3/iwch_provider.c    | 5 ++---
 drivers/infiniband/hw/cxgb4/provider.c         | 5 ++---
 drivers/infiniband/hw/hfi1/verbs.c             | 5 ++---
 drivers/infiniband/hw/i40iw/i40iw_verbs.c      | 7 +++----
 drivers/infiniband/hw/mlx4/main.c              | 5 ++---
 drivers/infiniband/hw/mlx5/main.c              | 8 ++++----
 drivers/infiniband/hw/mthca/mthca_provider.c   | 5 ++---
 drivers/infiniband/hw/nes/nes_verbs.c          | 5 ++---
 drivers/infiniband/hw/ocrdma/ocrdma_main.c     | 5 ++---
 drivers/infiniband/hw/qedr/main.c              | 5 ++---
 drivers/infiniband/hw/usnic/usnic_ib_main.c    | 6 ++----
 drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c | 5 ++---
 drivers/infiniband/ulp/ipoib/ipoib_ethtool.c   | 3 +--
 include/rdma/ib_verbs.h                        | 6 ++++--
 16 files changed, 36 insertions(+), 47 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 66b109bc6753..fbc92c649be8 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -336,10 +336,10 @@ static int read_port_immutable(struct ib_device *device)
 	return 0;
 }
 
-void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
+void ib_get_device_fw_str(struct ib_device *dev, char *str)
 {
 	if (dev->get_dev_fw_str)
-		dev->get_dev_fw_str(dev, str, str_len);
+		dev->get_dev_fw_str(dev, str);
 	else
 		str[0] = '\0';
 }
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 7ebe1ef23652..abc5ab581f82 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -1210,8 +1210,8 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
 {
 	struct ib_device *dev = container_of(device, struct ib_device, dev);
 
-	ib_get_device_fw_str(dev, buf, PAGE_SIZE);
-	strlcat(buf, "\n", PAGE_SIZE);
+	ib_get_device_fw_str(dev, buf);
+	strlcat(buf, "\n", IB_FW_VERSION_NAME_MAX);
 	return strlen(buf);
 }
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index 0cd0c1fa27d4..099e76f3758a 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -1336,8 +1336,7 @@ static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
-			       size_t str_len)
+static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str)
 {
 	struct iwch_dev *iwch_dev = to_iwch_dev(ibdev);
 	struct ethtool_drvinfo info;
@@ -1345,7 +1344,7 @@ static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
 
 	pr_debug("%s dev 0x%p\n", __func__, iwch_dev);
 	lldev->ethtool_ops->get_drvinfo(lldev, &info);
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 int iwch_register_device(struct iwch_dev *dev)
diff --git a/drivers/infiniband/hw/cxgb4/provider.c b/drivers/infiniband/hw/cxgb4/provider.c
index 0771e9a4d061..346e8334279a 100644
--- a/drivers/infiniband/hw/cxgb4/provider.c
+++ b/drivers/infiniband/hw/cxgb4/provider.c
@@ -517,14 +517,13 @@ static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev,
 						 ibdev);
 	pr_debug("%s dev 0x%p\n", __func__, dev);
 
-	snprintf(str, str_len, "%u.%u.%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u.%u",
 		 FW_HDR_FW_VER_MAJOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MINOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MICRO_G(c4iw_dev->rdev.lldi.fw_vers),
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index dc51bf247006..c88c03c11555 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1561,14 +1561,13 @@ static void init_ibport(struct hfi1_pportdata *ppd)
 	RCU_INIT_POINTER(ibp->rvp.qp[1], NULL);
 }
 
-static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
 	struct hfi1_ibdev *dev = dev_from_rdi(rdi);
 	u32 ver = dd_from_dev(dev)->dc8051_ver;
 
-	snprintf(str, str_len, "%u.%u.%u", dc8051_ver_maj(ver),
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u", dc8051_ver_maj(ver),
 		 dc8051_ver_min(ver), dc8051_ver_patch(ver));
 }
 
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 02d871db7ca5..1aa411034a27 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -2584,13 +2584,12 @@ static const char * const i40iw_hw_stat_names[] = {
 		"iwRdmaInv"
 };
 
-static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str,
-				 size_t str_len)
+static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	u32 firmware_version = I40IW_FW_VERSION;
 
-	snprintf(str, str_len, "%u.%u", firmware_version,
-		       (firmware_version & 0x000000ff));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u", firmware_version,
+		 (firmware_version & 0x000000ff));
 }
 
 /**
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 1f25a37eb056..c636842c5be0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -2587,12 +2587,11 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_fw_ver_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct mlx4_ib_dev *dev =
 		container_of(device, struct mlx4_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->dev->caps.fw_ver >> 32),
 		 (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dev->caps.fw_ver & 0xffff);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 9279631d8da0..0a5a4e3fa66d 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3285,13 +3285,13 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *ibdev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct mlx5_ib_dev *dev =
 		container_of(ibdev, struct mlx5_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%04d", fw_rev_maj(dev->mdev),
-		       fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%04d",
+		 fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev),
+		 fw_rev_sub(dev->mdev));
 }
 
 static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index c197cd9b193f..eae9bffd45d4 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -1178,12 +1178,11 @@ static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct mthca_dev *dev =
 		container_of(device, struct mthca_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->fw_ver >> 32),
 		 (int) (dev->fw_ver >> 16) & 0xffff,
 		 (int) dev->fw_ver & 0xffff);
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index 25dcd7573df9..c2943e39d2f9 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -3672,15 +3672,14 @@ static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct nes_ib_device *nesibdev =
 			container_of(dev, struct nes_ib_device, ibdev);
 	struct nes_vnic *nesvnic = nesibdev->nesvnic;
 
 	nes_debug(NES_DBG_INIT, "\n");
-	snprintf(str, str_len, "%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u",
 		 (nesvnic->nesdev->nesadapter->firmware_version >> 16),
 		 (nesvnic->nesdev->nesadapter->firmware_version & 0x000000ff));
 }
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 757c65816295..fbfbd9e96147 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -107,12 +107,11 @@ static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct ocrdma_dev *dev = get_ocrdma_dev(device);
 
-	snprintf(str, str_len, "%s", &dev->attr.fw_ver[0]);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]);
 }
 
 static int ocrdma_register_device(struct ocrdma_dev *dev)
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 199b6edbef92..97d033f51dc9 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -68,13 +68,12 @@ static enum rdma_link_layer qedr_link_layer(struct ib_device *device,
 	return IB_LINK_LAYER_ETHERNET;
 }
 
-static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct qedr_dev *qedr = get_qedr_dev(ibdev);
 	u32 fw_ver = (u32)qedr->attr.fw_ver;
 
-	snprintf(str, str_len, "%d. %d. %d. %d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d",
 		 (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
 		 (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
 }
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c
index e69c8e476a2b..e86700f994cb 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_main.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c
@@ -333,9 +333,7 @@ static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void usnic_get_dev_fw_str(struct ib_device *device,
-				 char *str,
-				 size_t str_len)
+static void usnic_get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct usnic_ib_dev *us_ibdev =
 		container_of(device, struct usnic_ib_dev, ib_dev);
@@ -345,7 +343,7 @@ static void usnic_get_dev_fw_str(struct ib_device *device,
 	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
 	mutex_unlock(&us_ibdev->usdev_lock);
 
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 /* Start of PF discovery section */
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index e76565280afa..7f29e4db28a1 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -102,12 +102,11 @@ static struct device_attribute *pvrdma_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str,
-				  size_t str_len)
+static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct pvrdma_dev *dev =
 		container_of(device, struct pvrdma_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d\n",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d\n",
 		 (int) (dev->dsr->caps.fw_ver >> 32),
 		 (int) (dev->dsr->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dsr->caps.fw_ver & 0xffff);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
index 7871379342f4..98e30b41e436 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ethtool.c
@@ -62,8 +62,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev,
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(netdev);
 
-	ib_get_device_fw_str(priv->ca, drvinfo->fw_version,
-			     sizeof(drvinfo->fw_version));
+	ib_get_device_fw_str(priv->ca, drvinfo->fw_version);
 
 	strlcpy(drvinfo->bus_info, dev_name(priv->ca->dev.parent),
 		sizeof(drvinfo->bus_info));
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 3391df5fdc9c..e0e87a1f66fb 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 
+#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
+
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 
@@ -2307,7 +2309,7 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
-	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	void (*get_dev_fw_str)(struct ib_device *, char *str);
 };
 
 struct ib_client {
@@ -2343,7 +2345,7 @@ struct ib_client {
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
-void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+void ib_get_device_fw_str(struct ib_device *device, char *str);
 
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
-- 
cgit v1.2.3-59-g8ed1b


From 8621a7e3c1c22e18385c9ced1647363884ea2aa1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Tue, 27 Jun 2017 16:58:59 +0300
Subject: RDMA/netlink: Export FW version

Add FW version to the device properties exported
by RDMA netlink, to be used by RDMAtool.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 9 +++++++++
 include/uapi/rdma/rdma_netlink.h | 4 ++++
 2 files changed, 13 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 94c1e49074f5..cdc970ca5a1b 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -40,10 +40,14 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
 					    .len = IB_DEVICE_NAME_MAX - 1},
 	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_FW_VERSION]	= { .type = NLA_NUL_STRING,
+					    .len = IB_FW_VERSION_NAME_MAX - 1},
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 {
+	char fw[IB_FW_VERSION_NAME_MAX];
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
 		return -EMSGSIZE;
 	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
@@ -56,6 +60,11 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 			      device->attrs.device_cap_flags, 0))
 		return -EMSGSIZE;
 
+	ib_get_device_fw_str(device, fw);
+	/* Device without FW has strlen(fw) */
+	if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 90de11db6580..5159858730b0 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -262,6 +262,10 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
 
+	/*
+	 * FW version
+	 */
+	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 1aaff896ca6b968a639e3e1e72ba6146ba332501 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Jun 2017 14:01:37 +0300
Subject: RDMA/netlink: Export node_guid and sys_image_guid

Add Node GUID and system image GUID to the device properties
exported by RDMA netlink, to be used by RDMAtool.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  |  8 ++++++++
 include/uapi/rdma/rdma_netlink.h | 13 +++++++++++++
 2 files changed, 21 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index cdc970ca5a1b..f932c2c3fad0 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -42,6 +42,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_FW_VERSION]	= { .type = NLA_NUL_STRING,
 					    .len = IB_FW_VERSION_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -65,6 +67,12 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw))
 		return -EMSGSIZE;
 
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_NODE_GUID,
+			      be64_to_cpu(device->node_guid), 0))
+		return -EMSGSIZE;
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,
+			      be64_to_cpu(device->attrs.sys_image_guid), 0))
+		return -EMSGSIZE;
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 5159858730b0..fe3a7429e7a1 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -266,6 +266,19 @@ enum rdma_nldev_attr {
 	 * FW version
 	 */
 	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
+
+	/*
+	 * Node GUID (in host byte order) associated with the RDMA device.
+	 */
+	RDMA_NLDEV_ATTR_NODE_GUID,			/* u64 */
+
+	/*
+	 * System image GUID (in host byte order) associated with
+	 * this RDMA device and other devices which are part of a
+	 * single system.
+	 */
+	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 12026fbba6af2fc53c3c6cf88bdfc6561986ba82 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Jun 2017 15:05:14 +0300
Subject: RDMA/netlink: Advertise IB subnet prefix

Add IB subnet prefix to the port properties exported
by RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 5 +++++
 include/uapi/rdma/rdma_netlink.h | 5 +++++
 2 files changed, 10 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index f932c2c3fad0..7af71d5e52c8 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -44,6 +44,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 					    .len = IB_FW_VERSION_NAME_MAX - 1},
 	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -97,6 +98,10 @@ static int fill_port_info(struct sk_buff *msg,
 	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
 			      (u64)attr.port_cap_flags, 0))
 		return -EMSGSIZE;
+	if (rdma_protocol_ib(device, port) &&
+	    nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
+			      attr.subnet_prefix, 0))
+		return -EMSGSIZE;
 
 	return 0;
 }
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index fe3a7429e7a1..481003182a35 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -279,6 +279,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
 
+	/*
+	 * Subnet prefix (in host byte order)
+	 */
+	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 80a06dd36f79de7007f21f5cbe42181a4e5c7d6d Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Jun 2017 15:38:36 +0300
Subject: RDMA/netink: Export lids and sm_lids

According to the IB specification, the LID and SM_LID
are 16-bit wide, but to support OmniPath users, export
it as 32-bit value from the beginning.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 9 ++++++++-
 include/uapi/rdma/rdma_netlink.h | 8 ++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 7af71d5e52c8..16f1d28bea69 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -45,6 +45,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -102,7 +104,12 @@ static int fill_port_info(struct sk_buff *msg,
 	    nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
 			      attr.subnet_prefix, 0))
 		return -EMSGSIZE;
-
+	if (rdma_protocol_ib(device, port)) {
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_LID, attr.lid))
+			return -EMSGSIZE;
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid))
+			return -EMSGSIZE;
+	}
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 481003182a35..7d5caaf54126 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -284,6 +284,14 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
 
+	/*
+	 * Local Identifier (LID),
+	 * According to IB specification, It is 16-bit address assigned
+	 * by the Subnet Manager. Extended to be 32-bit for OmniPath users.
+	 */
+	RDMA_NLDEV_ATTR_LID,			/* u32 */
+	RDMA_NLDEV_ATTR_SM_LID,			/* u32 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 34840fea112d36507c19dc6052b8c6d88bdd9c16 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Wed, 28 Jun 2017 15:49:30 +0300
Subject: RDMA/netlink: Export LID mask control (LMC)

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 3 +++
 include/uapi/rdma/rdma_netlink.h | 5 +++++
 2 files changed, 8 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 16f1d28bea69..11546f87c5dc 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -47,6 +47,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_LMC]		= { .type = NLA_U8 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -109,6 +110,8 @@ static int fill_port_info(struct sk_buff *msg,
 			return -EMSGSIZE;
 		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid))
 			return -EMSGSIZE;
+		if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc))
+			return -EMSGSIZE;
 	}
 	return 0;
 }
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 7d5caaf54126..035706e6b016 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -292,6 +292,11 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_LID,			/* u32 */
 	RDMA_NLDEV_ATTR_SM_LID,			/* u32 */
 
+	/*
+	 * LID mask control (LMC)
+	 */
+	RDMA_NLDEV_ATTR_LMC,			/* u8 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 5654e49db0b2d87c12b6e120b6a830abe3d3921b Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 29 Jun 2017 13:12:45 +0300
Subject: RDMA/netlink: Provide port state and physical link state

Add port state and physical link state to the users of RDMA netlink.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 6 ++++++
 include/uapi/rdma/rdma_netlink.h | 3 +++
 2 files changed, 9 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 11546f87c5dc..32ccb2b88933 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -48,6 +48,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_LMC]		= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_STATE]	= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -113,6 +115,10 @@ static int fill_port_info(struct sk_buff *msg,
 		if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc))
 			return -EMSGSIZE;
 	}
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_STATE, attr.state))
+		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state))
+		return -EMSGSIZE;
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index 035706e6b016..c488c3cf361b 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -297,6 +297,9 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_LMC,			/* u8 */
 
+	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
+	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From 1bb77b8c1d57149ed0aa6825255ead80ae584034 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 29 Jun 2017 16:01:29 +0300
Subject: RDMA/netlink: Export node_type

Add ability to get node_type for RDAM netlink users.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
 drivers/infiniband/core/nldev.c  | 3 +++
 include/uapi/rdma/rdma_netlink.h | 2 ++
 2 files changed, 5 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 32ccb2b88933..474022274e09 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -50,6 +50,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_LMC]		= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_PORT_STATE]	= { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_DEV_NODE_TYPE] = { .type = NLA_U8 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
@@ -79,6 +80,8 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,
 			      be64_to_cpu(device->attrs.sys_image_guid), 0))
 		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type))
+		return -EMSGSIZE;
 	return 0;
 }
 
diff --git a/include/uapi/rdma/rdma_netlink.h b/include/uapi/rdma/rdma_netlink.h
index c488c3cf361b..861440a87e7c 100644
--- a/include/uapi/rdma/rdma_netlink.h
+++ b/include/uapi/rdma/rdma_netlink.h
@@ -300,6 +300,8 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
 	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
 
+	RDMA_NLDEV_ATTR_DEV_NODE_TYPE,		/* u8 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */
-- 
cgit v1.2.3-59-g8ed1b


From b059e2108d7ac2d63001735f11d79ee670d9e3fe Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Sun, 2 Jul 2017 11:20:50 +0300
Subject: RDMA/core: make ib_device.add method optional

ib_clients can indeed fill .add to NULL, but then they will not see
any device removal notifications. The reason is that that
ib_register_client and ib_register_device checked existence of .add
before adding the creating a corresponding client_data and adding
it to the list. Simple condition reverse fixes the issue.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/device.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index a5dfab6adf49..9b7e110e7d8e 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -489,7 +489,7 @@ int ib_register_device(struct ib_device *device,
 	device->reg_state = IB_DEV_REGISTERED;
 
 	list_for_each_entry(client, &client_list, list)
-		if (client->add && !add_client_context(device, client))
+		if (!add_client_context(device, client) && client->add)
 			client->add(device);
 
 	down_write(&lists_rwsem);
@@ -577,7 +577,7 @@ int ib_register_client(struct ib_client *client)
 	mutex_lock(&device_mutex);
 
 	list_for_each_entry(device, &device_list, core_list)
-		if (client->add && !add_client_context(device, client))
+		if (!add_client_context(device, client) && client->add)
 			client->add(device);
 
 	down_write(&lists_rwsem);
-- 
cgit v1.2.3-59-g8ed1b


From cb93e597779e565dfeda34aede83c2565ddadc97 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Tue, 15 Aug 2017 22:20:37 +0300
Subject: cm: Don't allocate ib_cm workqueue with WQ_MEM_RECLAIM

create_workqueue always creates the workqueue with WQ_MEM_RECLAIM
and silences a flush dependency warn for WQ_LEGACY. Instead, we
want to keep the warn in case the allocator tries to flush the
cm workqueue because its very likely that cm work execution will
yield memory allocations (for example cm connection requests).

Reported-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 2b4d613a3474..838e3507eadc 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -4201,7 +4201,7 @@ static int __init ib_cm_init(void)
 		goto error1;
 	}
 
-	cm.wq = create_workqueue("ib_cm");
+	cm.wq = alloc_workqueue("ib_cm", 0, 1);
 	if (!cm.wq) {
 		ret = -ENOMEM;
 		goto error2;
-- 
cgit v1.2.3-59-g8ed1b


From 75215e5bb22c9c502e47398bdc35c247b1469809 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Tue, 15 Aug 2017 22:20:38 +0300
Subject: iwcm: Don't allocate iwcm workqueue with WQ_MEM_RECLAIM

Its very likely that iwcm work execution will yield memory
allocations (for example cm connection request).

Reported-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/iwcm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 31661b5c1743..ff6d7bc44c1f 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -1181,7 +1181,7 @@ static int __init iw_cm_init(void)
 	if (ret)
 		pr_err("iw_cm: couldn't register netlink callbacks\n");
 
-	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM);
+	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", 0);
 	if (!iwcm_wq)
 		return -ENOMEM;
 
-- 
cgit v1.2.3-59-g8ed1b


From 699a2d5b1b880b4e4e1c7d55fa25659322cf5b51 Mon Sep 17 00:00:00 2001
From: Bharat Potnuri <bharat@chelsio.com>
Date: Tue, 1 Aug 2017 10:58:35 +0530
Subject: RDMA/uverbs: Initialize cq_context appropriately

Initializing cq_context with ev_queue in create_cq(), leads to NULL pointer
dereference in ib_uverbs_comp_handler(), if application doesnot use completion
channel. This patch fixes the cq_context initialization.

Fixes: 1e7710f3f65 ("IB/core: Change completion channel to use the reworked")
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Reviewed-by: Matan Barak <matanb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 2c98533a0203..50a6c64f0388 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1015,7 +1015,7 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
 	cq->uobject       = &obj->uobject;
 	cq->comp_handler  = ib_uverbs_comp_handler;
 	cq->event_handler = ib_uverbs_cq_event_handler;
-	cq->cq_context    = &ev_file->ev_queue;
+	cq->cq_context    = ev_file ? &ev_file->ev_queue : NULL;
 	atomic_set(&cq->usecnt, 0);
 
 	obj->uobject.object = cq;
-- 
cgit v1.2.3-59-g8ed1b


From 62ede7779904bc75bdd84f1ff0016113956ce3b4 Mon Sep 17 00:00:00 2001
From: "Hiatt, Don" <don.hiatt@intel.com>
Date: Mon, 14 Aug 2017 14:17:43 -0400
Subject: Add OPA extended LID support

This patch series primarily increases sizes of variables that hold
lid values from 16 to 32 bits. Additionally, it adds a check in
the IB mad stack to verify a properly formatted MAD when OPA
extended LIDs are used.

Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c            |  4 ++--
 drivers/infiniband/core/user_mad.c      |  2 +-
 drivers/infiniband/core/uverbs_cmd.c    | 11 ++++++-----
 drivers/infiniband/hw/hfi1/mad.c        |  2 +-
 drivers/infiniband/hw/mlx4/alias_GUID.c |  2 +-
 drivers/infiniband/hw/mlx4/mad.c        |  8 ++++----
 drivers/infiniband/hw/mlx5/mad.c        |  2 +-
 drivers/infiniband/hw/mthca/mthca_cmd.c |  4 ++--
 drivers/infiniband/hw/mthca/mthca_mad.c |  4 ++--
 drivers/infiniband/sw/rdmavt/cq.c       |  2 +-
 include/rdma/ib_verbs.h                 | 26 ++++++++++++++++++++------
 11 files changed, 41 insertions(+), 26 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index 7a389697e2ec..fa3b0a428195 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -1770,7 +1770,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 {
 	if (!cm_req_get_primary_subnet_local(req_msg)) {
 		if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->primary_local_lid = ib_slid_be16(wc->slid);
+			req_msg->primary_local_lid = ib_lid_be16(wc->slid);
 			cm_req_set_primary_sl(req_msg, wc->sl);
 		}
 
@@ -1780,7 +1780,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 
 	if (!cm_req_get_alt_subnet_local(req_msg)) {
 		if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->alt_local_lid = ib_slid_be16(wc->slid);
+			req_msg->alt_local_lid = ib_lid_be16(wc->slid);
 			cm_req_set_alt_sl(req_msg, wc->sl);
 		}
 
diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index ff3c67a7aaad..c1696e6084b2 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/drivers/infiniband/core/user_mad.c
@@ -229,7 +229,7 @@ static void recv_handler(struct ib_mad_agent *agent,
 	packet->mad.hdr.status	   = 0;
 	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
 	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
-	packet->mad.hdr.lid	   = ib_slid_be16(mad_recv_wc->wc->slid);
+	packet->mad.hdr.lid	   = ib_lid_be16(mad_recv_wc->wc->slid);
 	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
 	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
 	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 39a0f1dc84e4..a21881e22bad 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -275,12 +275,13 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.bad_pkey_cntr   = attr.bad_pkey_cntr;
 	resp.qkey_viol_cntr  = attr.qkey_viol_cntr;
 	resp.pkey_tbl_len    = attr.pkey_tbl_len;
+
 	if (rdma_cap_opa_ah(ib_dev, cmd.port_num)) {
-		resp.lid  = OPA_TO_IB_UCAST_LID(attr.lid);
+		resp.lid     = OPA_TO_IB_UCAST_LID(attr.lid);
 		resp.sm_lid  = OPA_TO_IB_UCAST_LID(attr.sm_lid);
 	} else {
-		resp.lid     = (u16)attr.lid;
-		resp.sm_lid  = (u16)attr.sm_lid;
+		resp.lid     = ib_lid_cpu16(attr.lid);
+		resp.sm_lid  = ib_lid_cpu16(attr.sm_lid);
 	}
 	resp.lmc 	     = attr.lmc;
 	resp.max_vl_num      = attr.max_vl_num;
@@ -1206,9 +1207,9 @@ static int copy_wc_to_user(struct ib_device *ib_dev, void __user *dest,
 	tmp.wc_flags		= wc->wc_flags;
 	tmp.pkey_index		= wc->pkey_index;
 	if (rdma_cap_opa_ah(ib_dev, wc->port_num))
-		tmp.slid  = OPA_TO_IB_UCAST_LID(wc->slid);
+		tmp.slid	= OPA_TO_IB_UCAST_LID(wc->slid);
 	else
-		tmp.slid  = ib_slid_cpu16(wc->slid);
+		tmp.slid	= ib_lid_cpu16(wc->slid);
 	tmp.sl			= wc->sl;
 	tmp.dlid_path_bits	= wc->dlid_path_bits;
 	tmp.port_num		= wc->port_num;
diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c
index 8daa3a5f7e95..11be4d19e607 100644
--- a/drivers/infiniband/hw/hfi1/mad.c
+++ b/drivers/infiniband/hw/hfi1/mad.c
@@ -4216,7 +4216,7 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 			       const struct ib_wc *in_wc)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u16 slid = ib_slid_cpu16(in_wc->slid);
+	u16 slid = ib_lid_cpu16(in_wc->slid);
 	u16 pkey;
 
 	if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys))
diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
index 5a897b0106a9..0e4f60cfc59d 100644
--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
+++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
@@ -528,7 +528,7 @@ static int set_guid_rec(struct ib_device *ibdev,
 
 	memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec));
 
-	guid_info_rec.lid = cpu_to_be16((u16)attr.lid);
+	guid_info_rec.lid = ib_lid_be16(attr.lid);
 	guid_info_rec.block_num = index;
 
 	memcpy(guid_info_rec.guid_info_list, rec_det->all_recs,
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 04fb44e7699e..0793a21d76f4 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -169,7 +169,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
+		in_modifier |= ib_lid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier,
@@ -625,7 +625,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
 	} else {
 		tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
-		tun_mad->hdr.slid_mac_47_32 = ib_slid_be16(wc->slid);
+		tun_mad->hdr.slid_mac_47_32 = ib_lid_be16(wc->slid);
 	}
 
 	ib_dma_sync_single_for_device(&dev->ib_dev,
@@ -826,7 +826,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		}
 	}
 
-	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
 		forward_trap(to_mdev(ibdev), port_num, in_mad);
@@ -860,7 +860,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = (u16)pattr.lid;
+		prev_lid = ib_lid_cpu16(pattr.lid);
 
 	err = mlx4_MAD_IFC(to_mdev(ibdev),
 			   (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) |
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index cd2264ac88ae..18cfe5bf0fa3 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -78,7 +78,7 @@ static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	u16 slid;
 	int err;
 
-	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0)
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index e19ae0b9b439..d0f062fc2a4b 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -1921,7 +1921,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
 		MTHCA_PUT(inbox, val,               MAD_IFC_G_PATH_OFFSET);
 
-		MTHCA_PUT(inbox, ib_slid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET);
+		MTHCA_PUT(inbox, ib_lid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET);
 		MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
 
 		if (in_grh)
@@ -1929,7 +1929,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
+		in_modifier |= ib_lid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mthca_cmd_box(dev, inmailbox->dma, outmailbox->dma,
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index a9caadab22cf..093f7755c843 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -205,7 +205,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 		      u16 *out_mad_pkey_index)
 {
 	int err;
-	u16 slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
+	u16 slid = in_wc ? ib_lid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
@@ -256,7 +256,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = (u16)pattr.lid;
+		prev_lid = ib_lid_cpu16(pattr.lid);
 
 	err = mthca_MAD_IFC(to_mdev(ibdev),
 			    mad_flags & IB_MAD_IGNORE_MKEY,
diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index 0335a3df74d5..97d71e49c092 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
 		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = ib_slid_cpu16(entry->slid);
+		wc->uqueue[head].slid = ib_lid_cpu16(entry->slid);
 		wc->uqueue[head].sl = entry->sl;
 		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
 		wc->uqueue[head].port_num = entry->port_num;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 4db4ad56ace6..70a183179224 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -3724,16 +3724,30 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 		return RDMA_AH_ATTR_TYPE_IB;
 }
 
-/* Return slid in 16bit CPU encoding */
-static inline u16 ib_slid_cpu16(u32 slid)
+/**
+ * ib_lid_cpu16 - Return lid in 16bit CPU encoding.
+ *     In the current implementation the only way to get
+ *     get the 32bit lid is from other sources for OPA.
+ *     For IB, lids will always be 16bits so cast the
+ *     value accordingly.
+ *
+ * @lid: A 32bit LID
+ */
+static inline u16 ib_lid_cpu16(u32 lid)
 {
-	return (u16)slid;
+	WARN_ON_ONCE(lid & 0xFFFF0000);
+	return (u16)lid;
 }
 
-/* Return slid in 16bit BE encoding */
-static inline u16 ib_slid_be16(u32 slid)
+/**
+ * ib_lid_be16 - Return lid in 16bit BE encoding.
+ *
+ * @lid: A 32bit LID
+ */
+static inline __be16 ib_lid_be16(u32 lid)
 {
-	return cpu_to_be16((u16)slid);
+	WARN_ON_ONCE(lid & 0xFFFF0000);
+	return cpu_to_be16((u16)lid);
 }
 
 /**
-- 
cgit v1.2.3-59-g8ed1b


From e093111ddb6c786e32b882108c1c08ef83d781f4 Mon Sep 17 00:00:00 2001
From: "Amrani, Ram" <Ram.Amrani@cavium.com>
Date: Tue, 27 Jun 2017 17:04:42 +0300
Subject: IB/core: Fix input len in multiple user verbs

Most user verbs pass user data to the kernel with the inclusion of the
ib_uverbs_cmd_hdr structure. This is problematic because the vendor has
no ideas if the verb was called by a legacy verb or an extended verb.
Also, the incosistency between the verbs is confusing.

Fixes: 565197dd8fb1 ("IB/core: Extend ib_uverbs_create_cq")
Signed-off-by: Ram Amrani <Ram.Amrani@cavium.com>
Signed-off-by: Ariel Elior <Ariel.Elior@cavium.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c         | 70 ++++++++++++++++------------
 drivers/infiniband/hw/mlx5/cq.c              |  6 +--
 drivers/infiniband/hw/mlx5/main.c            | 11 ++---
 drivers/infiniband/hw/mthca/mthca_provider.c |  2 +-
 4 files changed, 46 insertions(+), 43 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index a21881e22bad..7ea5a3bb5a04 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -91,9 +91,10 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 		goto err;
 	}
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = ib_rdmacg_try_charge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
 	if (ret)
@@ -319,9 +320,10 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	uobj  = uobj_alloc(uobj_get_type(pd), file->ucontext);
 	if (IS_ERR(uobj))
@@ -488,9 +490,10 @@ ssize_t ib_uverbs_open_xrcd(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof  resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	mutex_lock(&file->device->xrcd_tree_mutex);
 
@@ -652,9 +655,10 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	if ((cmd.start & ~PAGE_MASK) != (cmd.hca_va & ~PAGE_MASK))
 		return -EINVAL;
@@ -746,7 +750,8 @@ ssize_t ib_uverbs_rereg_mr(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof(cmd),
 		   (unsigned long) cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+                   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+                   out_len - sizeof(resp));
 
 	if (cmd.flags & ~IB_MR_REREG_SUPPORTED || !cmd.flags)
 		return -EINVAL;
@@ -1086,7 +1091,8 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&uhw, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	memset(&cmd_ex, 0, sizeof(cmd_ex));
 	cmd_ex.user_handle = cmd.user_handle;
@@ -1167,9 +1173,10 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	cq = uobj_get_obj_read(cq, cmd.cq_handle, file->ucontext);
 	if (!cq)
@@ -1742,9 +1749,10 @@ ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	obj  = (struct ib_uqp_object *)uobj_alloc(uobj_get_type(qp),
 						  file->ucontext);
@@ -2055,7 +2063,8 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 		return -EOPNOTSUPP;
 
 	INIT_UDATA(&udata, buf + sizeof(cmd.base), NULL,
-		   in_len - sizeof(cmd.base), out_len);
+		   in_len - sizeof(cmd.base) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len);
 
 	ret = modify_qp(file, &cmd, &udata);
 	if (ret)
@@ -2561,7 +2570,8 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 
 	INIT_UDATA(&udata, buf + sizeof(cmd),
 		   (unsigned long)cmd.response + sizeof(resp),
-		   in_len - sizeof(cmd), out_len - sizeof(resp));
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	uobj  = uobj_alloc(uobj_get_type(ah), file->ucontext);
 	if (IS_ERR(uobj))
@@ -3625,10 +3635,10 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file,
 	xcmd.max_sge	 = cmd.max_sge;
 	xcmd.srq_limit	 = cmd.srq_limit;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
-		   out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &xcmd, &udata);
 	if (ret)
@@ -3652,10 +3662,10 @@ ssize_t ib_uverbs_create_xsrq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd - sizeof(struct ib_uverbs_cmd_hdr),
-		   out_len - sizeof resp);
+	INIT_UDATA(&udata, buf + sizeof(cmd),
+		   (unsigned long) cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
+		   out_len - sizeof(resp));
 
 	ret = __uverbs_create_xsrq(file, ib_dev, &cmd, &udata);
 	if (ret)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index a384d72ea3cd..c155df465c44 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -751,10 +751,8 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	void *cqc;
 	int err;
 
-	ucmdlen =
-		(udata->inlen - sizeof(struct ib_uverbs_cmd_hdr) <
-		 sizeof(ucmd)) ? (sizeof(ucmd) -
-				  sizeof(ucmd.reserved)) : sizeof(ucmd);
+	ucmdlen = udata->inlen < sizeof(ucmd) ?
+		  (sizeof(ucmd) - sizeof(ucmd.reserved)) : sizeof(ucmd);
 
 	if (ib_copy_from_udata(&ucmd, udata, ucmdlen))
 		return -EFAULT;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index cde7d1ce4a3c..e2fffdc43c86 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1273,7 +1273,6 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_bfreg_info *bfregi;
 	int ver;
 	int err;
-	size_t reqlen;
 	size_t min_req_v2 = offsetof(struct mlx5_ib_alloc_ucontext_req_v2,
 				     max_cqe_version);
 	bool lib_uar_4k;
@@ -1281,18 +1280,14 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (!dev->ib_active)
 		return ERR_PTR(-EAGAIN);
 
-	if (udata->inlen < sizeof(struct ib_uverbs_cmd_hdr))
-		return ERR_PTR(-EINVAL);
-
-	reqlen = udata->inlen - sizeof(struct ib_uverbs_cmd_hdr);
-	if (reqlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
+	if (udata->inlen == sizeof(struct mlx5_ib_alloc_ucontext_req))
 		ver = 0;
-	else if (reqlen >= min_req_v2)
+	else if (udata->inlen >= min_req_v2)
 		ver = 2;
 	else
 		return ERR_PTR(-EINVAL);
 
-	err = ib_copy_from_udata(&req, udata, min(reqlen, sizeof(req)));
+	err = ib_copy_from_udata(&req, udata, min(udata->inlen, sizeof(req)));
 	if (err)
 		return ERR_PTR(err);
 
diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c
index eae9bffd45d4..6fee7795d1c8 100644
--- a/drivers/infiniband/hw/mthca/mthca_provider.c
+++ b/drivers/infiniband/hw/mthca/mthca_provider.c
@@ -914,7 +914,7 @@ static struct ib_mr *mthca_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int err = 0;
 	int write_mtt_size;
 
-	if (udata->inlen - sizeof (struct ib_uverbs_cmd_hdr) < sizeof ucmd) {
+	if (udata->inlen < sizeof ucmd) {
 		if (!to_mucontext(pd->uobject->context)->reg_mr_warned) {
 			mthca_warn(dev, "Process '%s' did not pass in MR attrs.\n",
 				   current->comm);
-- 
cgit v1.2.3-59-g8ed1b


From d98bb7f7e6fa29d45008370084d5cabac7ac69ed Mon Sep 17 00:00:00 2001
From: Don Hiatt <don.hiatt@intel.com>
Date: Fri, 4 Aug 2017 13:54:16 -0700
Subject: IB/hfi1: Determine 9B/16B L2 header type based on Address handle

When address handle attributes are initialized, the LIDs are
transformed to be in the 32 bit LID space.
When constructing the header, hfi1 driver will look at the LID
to determine the packet header to be created.

Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Dasaratharaman Chandramouli <dasaratharaman.chandramouli@intel.com>
Signed-off-by: Don Hiatt <don.hiatt@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/sa_query.c   | 21 +++++---
 drivers/infiniband/core/uverbs_cmd.c |  3 ++
 drivers/infiniband/hw/hfi1/hfi.h     | 92 ++++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/hfi1/qp.c      | 28 +++++++++++
 drivers/infiniband/hw/hfi1/verbs.c   | 12 +++++
 drivers/infiniband/hw/hfi1/verbs.h   |  1 +
 include/rdma/ib_verbs.h              | 15 ++++++
 include/rdma/opa_addr.h              |  4 +-
 8 files changed, 168 insertions(+), 8 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index da29e2863c84..0179b21bad34 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -50,6 +50,7 @@
 #include <uapi/rdma/ib_user_sa.h>
 #include <rdma/ib_marshall.h>
 #include <rdma/ib_addr.h>
+#include <rdma/opa_addr.h>
 #include "sa.h"
 #include "core_priv.h"
 
@@ -1239,6 +1240,11 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 	ah_attr->type = rdma_ah_find_type(device, port_num);
 
 	rdma_ah_set_dlid(ah_attr, be32_to_cpu(sa_path_get_dlid(rec)));
+
+	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
+	    (rdma_ah_get_dlid(ah_attr) == be16_to_cpu(IB_LID_PERMISSIVE)))
+		rdma_ah_set_make_grd(ah_attr, true);
+
 	rdma_ah_set_sl(ah_attr, rec->sl);
 	rdma_ah_set_path_bits(ah_attr, be32_to_cpu(sa_path_get_slid(rec)) &
 			      get_src_path_mask(device, port_num));
@@ -2288,12 +2294,15 @@ static void update_sm_ah(struct work_struct *work)
 	rdma_ah_set_sl(&ah_attr, port_attr.sm_sl);
 	rdma_ah_set_port_num(&ah_attr, port->port_num);
 	if (port_attr.grh_required) {
-		rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
-
-		rdma_ah_set_subnet_prefix(&ah_attr,
-					  cpu_to_be64(port_attr.subnet_prefix));
-		rdma_ah_set_interface_id(&ah_attr,
-					 cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
+		if (ah_attr.type == RDMA_AH_ATTR_TYPE_OPA) {
+			rdma_ah_set_make_grd(&ah_attr, true);
+		} else {
+			rdma_ah_set_ah_flags(&ah_attr, IB_AH_GRH);
+			rdma_ah_set_subnet_prefix(&ah_attr,
+						  cpu_to_be64(port_attr.subnet_prefix));
+			rdma_ah_set_interface_id(&ah_attr,
+						 cpu_to_be64(IB_SA_WELL_KNOWN_GUID));
+		}
 	}
 
 	new_ah->ah = rdma_create_ah(port->agent->qp->pd, &ah_attr);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 7ea5a3bb5a04..dc7d773a96ec 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2009,6 +2009,7 @@ static int modify_qp(struct ib_uverbs_file *file,
 	rdma_ah_set_static_rate(&attr->ah_attr, cmd->base.dest.static_rate);
 	rdma_ah_set_port_num(&attr->ah_attr,
 			     cmd->base.dest.port_num);
+	rdma_ah_set_make_grd(&attr->ah_attr, false);
 
 	attr->alt_ah_attr.type = rdma_ah_find_type(qp->device,
 						   cmd->base.dest.port_num);
@@ -2032,6 +2033,7 @@ static int modify_qp(struct ib_uverbs_file *file,
 				cmd->base.alt_dest.static_rate);
 	rdma_ah_set_port_num(&attr->alt_ah_attr,
 			     cmd->base.alt_dest.port_num);
+	rdma_ah_set_make_grd(&attr->alt_ah_attr, false);
 
 	ret = ib_modify_qp_with_udata(qp, attr,
 				      modify_qp_mask(qp->qp_type,
@@ -2584,6 +2586,7 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	}
 
 	attr.type = rdma_ah_find_type(ib_dev, cmd.attr.port_num);
+	rdma_ah_set_make_grd(&attr, false);
 	rdma_ah_set_dlid(&attr, cmd.attr.dlid);
 	rdma_ah_set_sl(&attr, cmd.attr.sl);
 	rdma_ah_set_path_bits(&attr, cmd.attr.src_path_bits);
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index ee19660ca2fa..cec9590870ba 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -70,6 +70,7 @@
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
 #include <rdma/rdma_vt.h>
+#include <rdma/opa_addr.h>
 
 #include "chip_registers.h"
 #include "common.h"
@@ -353,6 +354,10 @@ struct hfi1_packet {
 	bool fecn;
 };
 
+/* Packet types */
+#define HFI1_PKT_TYPE_9B  0
+#define HFI1_PKT_TYPE_16B 1
+
 /*
  * OPA 16B Header
  */
@@ -2170,6 +2175,31 @@ int hfi1_tempsense_rd(struct hfi1_devdata *dd, struct hfi1_temp *temp);
 #define DD_DEV_ENTRY(dd)       __string(dev, dev_name(&(dd)->pcidev->dev))
 #define DD_DEV_ASSIGN(dd)      __assign_str(dev, dev_name(&(dd)->pcidev->dev))
 
+static inline void hfi1_update_ah_attr(struct ib_device *ibdev,
+				       struct rdma_ah_attr *attr)
+{
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	u32 dlid = rdma_ah_get_dlid(attr);
+
+	/*
+	 * Kernel clients may not have setup GRH information
+	 * Set that here.
+	 */
+	ibp = to_iport(ibdev, rdma_ah_get_port_num(attr));
+	ppd = ppd_from_ibp(ibp);
+	if ((((dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
+	      (ppd->lid >= be16_to_cpu(IB_MULTICAST_LID_BASE))) &&
+	    (dlid != be32_to_cpu(OPA_LID_PERMISSIVE)) &&
+	    (dlid != be16_to_cpu(IB_LID_PERMISSIVE)) &&
+	    (!(rdma_ah_get_ah_flags(attr) & IB_AH_GRH))) ||
+	    (rdma_ah_get_make_grd(attr))) {
+		rdma_ah_set_ah_flags(attr, IB_AH_GRH);
+		rdma_ah_set_interface_id(attr, OPA_MAKE_ID(dlid));
+		rdma_ah_set_subnet_prefix(attr, ibp->rvp.gid_prefix);
+	}
+}
+
 /*
  * hfi1_check_mcast- Check if the given lid is
  * in the OPA multicast range.
@@ -2223,4 +2253,66 @@ static inline bool hfi1_is_16B_mcast(u32 lid)
 		opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR), 16B)) &&
 		(lid != opa_get_lid(be32_to_cpu(OPA_LID_PERMISSIVE), 16B)));
 }
+
+static inline void hfi1_make_opa_lid(struct rdma_ah_attr *attr)
+{
+	const struct ib_global_route *grh = rdma_ah_read_grh(attr);
+	u32 dlid = rdma_ah_get_dlid(attr);
+
+	/* Modify ah_attr.dlid to be in the 32 bit LID space.
+	 * This is how the address will be laid out:
+	 * Assuming MCAST_NR to be 4,
+	 * 32 bit permissive LID = 0xFFFFFFFF
+	 * Multicast LID range = 0xFFFFFFFE to 0xF0000000
+	 * Unicast LID range = 0xEFFFFFFF to 1
+	 * Invalid LID = 0
+	 */
+	if (ib_is_opa_gid(&grh->dgid))
+		dlid = opa_get_lid_from_gid(&grh->dgid);
+	else if ((dlid >= be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+		 (dlid != be16_to_cpu(IB_LID_PERMISSIVE)) &&
+		 (dlid != be32_to_cpu(OPA_LID_PERMISSIVE)))
+		dlid = dlid - be16_to_cpu(IB_MULTICAST_LID_BASE) +
+			opa_get_mcast_base(OPA_MCAST_NR);
+	else if (dlid == be16_to_cpu(IB_LID_PERMISSIVE))
+		dlid = be32_to_cpu(OPA_LID_PERMISSIVE);
+
+	rdma_ah_set_dlid(attr, dlid);
+}
+
+static inline u8 hfi1_get_packet_type(u32 lid)
+{
+	/* 9B if lid > 0xF0000000 */
+	if (lid >= opa_get_mcast_base(OPA_MCAST_NR))
+		return HFI1_PKT_TYPE_9B;
+
+	/* 16B if lid > 0xC000 */
+	if (lid >= opa_get_lid(opa_get_mcast_base(OPA_MCAST_NR), 9B))
+		return HFI1_PKT_TYPE_16B;
+
+	return HFI1_PKT_TYPE_9B;
+}
+
+static inline bool hfi1_get_hdr_type(u32 lid, struct rdma_ah_attr *attr)
+{
+	/*
+	 * If there was an incoming 16B packet with permissive
+	 * LIDs, OPA GIDs would have been programmed when those
+	 * packets were received. A 16B packet will have to
+	 * be sent in response to that packet. Return a 16B
+	 * header type if that's the case.
+	 */
+	if (rdma_ah_get_dlid(attr) == be32_to_cpu(OPA_LID_PERMISSIVE))
+		return (ib_is_opa_gid(&rdma_ah_read_grh(attr)->dgid)) ?
+			HFI1_PKT_TYPE_16B : HFI1_PKT_TYPE_9B;
+
+	/*
+	 * Return a 16B header type if either the the destination
+	 * or source lid is extended.
+	 */
+	if (hfi1_get_packet_type(rdma_ah_get_dlid(attr)) == HFI1_PKT_TYPE_16B)
+		return HFI1_PKT_TYPE_16B;
+
+	return hfi1_get_packet_type(lid);
+}
 #endif                          /* _HFI1_KERNEL_H */
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index b801d8469956..0fca6dfe8d9f 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -232,6 +232,31 @@ int hfi1_check_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 	return 0;
 }
 
+/*
+ * qp_set_16b - Set the hdr_type based on whether the slid or the
+ * dlid in the connection is extended. Only applicable for RC and UC
+ * QPs. UD QPs determine this on the fly from the ah in the wqe
+ */
+static inline void qp_set_16b(struct rvt_qp *qp)
+{
+	struct hfi1_pportdata *ppd;
+	struct hfi1_ibport *ibp;
+	struct hfi1_qp_priv *priv = qp->priv;
+
+	/* Update ah_attr to account for extended LIDs */
+	hfi1_update_ah_attr(qp->ibqp.device, &qp->remote_ah_attr);
+
+	/* Create 32 bit LIDs */
+	hfi1_make_opa_lid(&qp->remote_ah_attr);
+
+	if (!(rdma_ah_get_ah_flags(&qp->remote_ah_attr) & IB_AH_GRH))
+		return;
+
+	ibp = to_iport(qp->ibqp.device, qp->port_num);
+	ppd = ppd_from_ibp(ibp);
+	priv->hdr_type = hfi1_get_hdr_type(ppd->lid, &qp->remote_ah_attr);
+}
+
 void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		    int attr_mask, struct ib_udata *udata)
 {
@@ -242,6 +267,7 @@ void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		priv->s_sc = ah_to_sc(ibqp->device, &qp->remote_ah_attr);
 		priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
 		priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
+		qp_set_16b(qp);
 	}
 
 	if (attr_mask & IB_QP_PATH_MIG_STATE &&
@@ -251,6 +277,7 @@ void hfi1_modify_qp(struct rvt_qp *qp, struct ib_qp_attr *attr,
 		priv->s_sc = ah_to_sc(ibqp->device, &qp->remote_ah_attr);
 		priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
 		priv->s_sendcontext = qp_to_send_context(qp, priv->s_sc);
+		qp_set_16b(qp);
 	}
 }
 
@@ -751,6 +778,7 @@ void hfi1_migrate_qp(struct rvt_qp *qp)
 	qp->s_flags |= RVT_S_AHG_CLEAR;
 	priv->s_sc = ah_to_sc(qp->ibqp.device, &qp->remote_ah_attr);
 	priv->s_sde = qp_to_sdma_engine(qp, priv->s_sc);
+	qp_set_16b(qp);
 
 	ev.device = qp->ibqp.device;
 	ev.element.qp = &qp->ibqp;
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 0b1556fed47e..18b27276f202 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1421,6 +1421,15 @@ static int query_port(struct rvt_dev_info *rdi, u8 port_num,
 	props->active_mtu = !valid_ib_mtu(ppd->ibmtu) ? props->max_mtu :
 		mtu_to_enum(ppd->ibmtu, IB_MTU_2048);
 
+	/*
+	 * sm_lid of 0xFFFF needs special handling so that it can
+	 * be differentiated from a permissve LID of 0xFFFF.
+	 * We set the grh_required flag here so the SA can program
+	 * the DGID in the address handle appropriately
+	 */
+	if (props->sm_lid == be16_to_cpu(IB_LID_PERMISSIVE))
+		props->grh_required = true;
+
 	return 0;
 }
 
@@ -1528,6 +1537,7 @@ static void hfi1_notify_new_ah(struct ib_device *ibdev,
 	struct hfi1_pportdata *ppd;
 	struct hfi1_devdata *dd;
 	u8 sc5;
+	struct rdma_ah_attr *attr = &ah->attr;
 
 	/*
 	 * Do not trust reading anything from rvt_ah at this point as it is not
@@ -1537,6 +1547,8 @@ static void hfi1_notify_new_ah(struct ib_device *ibdev,
 	ibp = to_iport(ibdev, rdma_ah_get_port_num(ah_attr));
 	ppd = ppd_from_ibp(ibp);
 	sc5 = ibp->sl_to_sc[rdma_ah_get_sl(&ah->attr)];
+	hfi1_update_ah_attr(ibdev, attr);
+	hfi1_make_opa_lid(attr);
 	dd = dd_from_ppd(ppd);
 	ah->vl = sc_to_vlt(dd, sc5);
 	if (ah->vl < num_vls || ah->vl == 15)
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 68577a0c922b..d3dd0c01b8f6 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -147,6 +147,7 @@ struct hfi1_qp_priv {
 	u8 s_sc;		                  /* SC[0..4] for next packet */
 	struct iowait s_iowait;
 	struct rvt_qp *owner;
+	u8 hdr_type; /* 9B or 16B */
 };
 
 /*
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 70a183179224..8f263930c56f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -864,6 +864,7 @@ struct roce_ah_attr {
 struct opa_ah_attr {
 	u32			dlid;
 	u8			src_path_bits;
+	bool			make_grd;
 };
 
 struct rdma_ah_attr {
@@ -3625,6 +3626,20 @@ static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr)
 	return 0;
 }
 
+static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr,
+					bool make_grd)
+{
+	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
+		attr->opa.make_grd = make_grd;
+}
+
+static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr)
+{
+	if (attr->type == RDMA_AH_ATTR_TYPE_OPA)
+		return attr->opa.make_grd;
+	return false;
+}
+
 static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u8 port_num)
 {
 	attr->port_num = port_num;
diff --git a/include/rdma/opa_addr.h b/include/rdma/opa_addr.h
index 8d3ad4ecbea1..9ae126fb8648 100644
--- a/include/rdma/opa_addr.h
+++ b/include/rdma/opa_addr.h
@@ -71,7 +71,7 @@
  *
  * @gid: The Global identifier
  */
-static inline bool ib_is_opa_gid(union ib_gid *gid)
+static inline bool ib_is_opa_gid(const union ib_gid *gid)
 {
 	return ((be64_to_cpu(gid->global.interface_id) >> 40) ==
 		OPA_SPECIAL_OUI);
@@ -84,7 +84,7 @@ static inline bool ib_is_opa_gid(union ib_gid *gid)
  *
  * @gid: The Global identifier
  */
-static inline u32 opa_get_lid_from_gid(union ib_gid *gid)
+static inline u32 opa_get_lid_from_gid(const union ib_gid *gid)
 {
 	return be64_to_cpu(gid->global.interface_id) & 0xFFFFFFFF;
 }
-- 
cgit v1.2.3-59-g8ed1b


From 1eb5be0ec79a7b21cd6b5b73d9de294dc1809e0f Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Date: Mon, 14 Aug 2017 14:57:38 -0600
Subject: rdma: Allow demand loading of NETLINK_RDMA

Provide a module alias so that if userspace opens a netlink
socket for RDMA the kernel support is loaded automatically.

Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/netlink.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 27352a352770..f782697cf4d8 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -38,6 +38,7 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <rdma/rdma_netlink.h>
+#include <linux/module.h>
 #include "core_priv.h"
 
 #include "core_priv.h"
@@ -290,3 +291,5 @@ void rdma_nl_exit(void)
 
 	netlink_kernel_release(nls);
 }
+
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_RDMA);
-- 
cgit v1.2.3-59-g8ed1b


From e3bf14bdc17a8e917f337760cc7cacf3232d7dbc Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Date: Mon, 14 Aug 2017 14:57:39 -0600
Subject: rdma: Autoload netlink client modules

If a message comes in and we do not have the client in the table, then
try to load the module supplying that client using MODULE_ALIAS to find
it.

This duplicates the scheme seen in other netlink muxes (eg nfnetlink).

Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cma.c     |  2 ++
 drivers/infiniband/core/device.c  |  2 ++
 drivers/infiniband/core/iwcm.c    |  2 ++
 drivers/infiniband/core/netlink.c |  9 +++++++++
 drivers/infiniband/core/nldev.c   |  3 +++
 include/rdma/rdma_netlink.h       | 12 ++++++++++++
 6 files changed, 30 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index d8edd8b11561..b76de2e2b209 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -4537,5 +4537,7 @@ static void __exit cma_cleanup(void)
 	destroy_workqueue(cma_wq);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_RDMA_CM, 1);
+
 module_init(cma_init);
 module_exit(cma_cleanup);
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 91d7cea1a0b9..fc6be1175183 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1252,5 +1252,7 @@ static void __exit ib_core_cleanup(void)
 	destroy_workqueue(ib_wq);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_LS, 4);
+
 module_init(ib_core_init);
 module_exit(ib_core_cleanup);
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index e33528e102f8..fcf42f6bb82a 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -1200,5 +1200,7 @@ static void __exit iw_cm_cleanup(void)
 	iwpm_exit(RDMA_NL_IWCM);
 }
 
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_IWCM, 2);
+
 module_init(iw_cm_init);
 module_exit(iw_cm_cleanup);
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index f782697cf4d8..e685148dd3e6 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -84,6 +84,15 @@ static bool is_nl_valid(unsigned int type, unsigned int op)
 		return false;
 
 	cb_table = rdma_nl_types[type].cb_table;
+#ifdef CONFIG_MODULES
+	if (!cb_table) {
+		mutex_unlock(&rdma_nl_mutex);
+		request_module("rdma-netlink-subsys-%d", type);
+		mutex_lock(&rdma_nl_mutex);
+		cb_table = rdma_nl_types[type].cb_table;
+	}
+#endif
+
 	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
 		return false;
 	return true;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 474022274e09..3ba24c428c3b 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -30,6 +30,7 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/module.h>
 #include <net/netlink.h>
 #include <rdma/rdma_netlink.h>
 
@@ -320,3 +321,5 @@ void __exit nldev_exit(void)
 {
 	rdma_nl_unregister(RDMA_NL_NLDEV);
 }
+
+MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_NLDEV, 5);
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index e25bf1988846..2d878596b1e0 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -17,6 +17,18 @@ enum rdma_nl_flags {
 	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
+/* Define this module as providing netlink services for NETLINK_RDMA, with
+ * index _index.  Since the client indexes were setup in a uapi header as an
+ * enum and we do no want to change that, the user must supply the expanded
+ * constant as well and the compiler checks they are the same.
+ */
+#define MODULE_ALIAS_RDMA_NETLINK(_index, _val)                                \
+	static inline void __chk_##_index(void)                                \
+	{                                                                      \
+		BUILD_BUG_ON(_index != _val);                                  \
+	}                                                                      \
+	MODULE_ALIAS("rdma-netlink-subsys-" __stringify(_val))
+
 /**
  * Register client in RDMA netlink.
  * @index: Index of the added client
-- 
cgit v1.2.3-59-g8ed1b


From 5ab2d89b85a6c5c2d7604c9674f77a68f3d24f91 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Aug 2017 15:50:32 +0300
Subject: IB/cma: Fix erroneous validation of supported default GID type

When rdma_cm is initializing a cma_device it checks if this device
supports the preferred default GID type. This check was done in a wrong way
and therefore sometimes rdma_cm is coming up with default GID type that is
not supported by the device.

Fix that by checking for supported GID type properly.

Fixes: 3c7f67d1880d ("IB/cma: Fix default RoCE type setting")
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cma.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b76de2e2b209..852c8fec8088 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -72,7 +72,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
-#define CMA_PREFERRED_ROCE_GID_TYPE (1 << IB_GID_TYPE_ROCE_UDP_ENCAP)
+#define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP
 
 static const char * const cma_events[] = {
 	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
@@ -4282,7 +4282,7 @@ static void cma_add_one(struct ib_device *device)
 	for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) {
 		supported_gids = roce_gid_type_mask_support(device, i);
 		WARN_ON(!supported_gids);
-		if (supported_gids & CMA_PREFERRED_ROCE_GID_TYPE)
+		if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE))
 			cma_dev->default_gid_type[i - rdma_start_port(device)] =
 				CMA_PREFERRED_ROCE_GID_TYPE;
 		else
-- 
cgit v1.2.3-59-g8ed1b


From 89caa0538ecf2114e1badbb1e75120d25bec985e Mon Sep 17 00:00:00 2001
From: Parav Pandit <parav@mellanox.com>
Date: Thu, 17 Aug 2017 15:50:33 +0300
Subject: IB/uverbs: Introduce and use helper functions to copy ah attributes

This patch introduces two helper functions to copy ah attributes
from uverbs to internal ib_ah_attr structure and the other way
during modify qp and query qp respectively.

Signed-off-by: Parav Pandit <parav@mellanox.com>
Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 127 ++++++++++++++---------------------
 1 file changed, 51 insertions(+), 76 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 59696f568f53..8e9fea03dec4 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1820,6 +1820,28 @@ err_put:
 	return ret;
 }
 
+static void copy_ah_attr_to_uverbs(struct ib_uverbs_qp_dest *uverb_attr,
+				   struct rdma_ah_attr *rdma_attr)
+{
+	const struct ib_global_route   *grh;
+
+	uverb_attr->dlid              = rdma_ah_get_dlid(rdma_attr);
+	uverb_attr->sl                = rdma_ah_get_sl(rdma_attr);
+	uverb_attr->src_path_bits     = rdma_ah_get_path_bits(rdma_attr);
+	uverb_attr->static_rate       = rdma_ah_get_static_rate(rdma_attr);
+	uverb_attr->is_global         = !!(rdma_ah_get_ah_flags(rdma_attr) &
+					 IB_AH_GRH);
+	if (uverb_attr->is_global) {
+		grh = rdma_ah_read_grh(rdma_attr);
+		memcpy(uverb_attr->dgid, grh->dgid.raw, 16);
+		uverb_attr->flow_label        = grh->flow_label;
+		uverb_attr->sgid_index        = grh->sgid_index;
+		uverb_attr->hop_limit         = grh->hop_limit;
+		uverb_attr->traffic_class     = grh->traffic_class;
+	}
+	uverb_attr->port_num          = rdma_ah_get_port_num(rdma_attr);
+}
+
 ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 			   struct ib_device *ib_dev,
 			   const char __user *buf, int in_len,
@@ -1830,7 +1852,6 @@ ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 	struct ib_qp                   *qp;
 	struct ib_qp_attr              *attr;
 	struct ib_qp_init_attr         *init_attr;
-	const struct ib_global_route   *grh;
 	int                            ret;
 
 	if (copy_from_user(&cmd, buf, sizeof cmd))
@@ -1880,39 +1901,8 @@ ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 	resp.alt_port_num           = attr->alt_port_num;
 	resp.alt_timeout            = attr->alt_timeout;
 
-	resp.dest.dlid              = rdma_ah_get_dlid(&attr->ah_attr);
-	resp.dest.sl                = rdma_ah_get_sl(&attr->ah_attr);
-	resp.dest.src_path_bits     = rdma_ah_get_path_bits(&attr->ah_attr);
-	resp.dest.static_rate       = rdma_ah_get_static_rate(&attr->ah_attr);
-	resp.dest.is_global         = !!(rdma_ah_get_ah_flags(&attr->ah_attr) &
-					 IB_AH_GRH);
-	if (resp.dest.is_global) {
-		grh = rdma_ah_read_grh(&attr->ah_attr);
-		memcpy(resp.dest.dgid, grh->dgid.raw, 16);
-		resp.dest.flow_label        = grh->flow_label;
-		resp.dest.sgid_index        = grh->sgid_index;
-		resp.dest.hop_limit         = grh->hop_limit;
-		resp.dest.traffic_class     = grh->traffic_class;
-	}
-	resp.dest.port_num          = rdma_ah_get_port_num(&attr->ah_attr);
-
-	resp.alt_dest.dlid          = rdma_ah_get_dlid(&attr->alt_ah_attr);
-	resp.alt_dest.sl            = rdma_ah_get_sl(&attr->alt_ah_attr);
-	resp.alt_dest.src_path_bits = rdma_ah_get_path_bits(&attr->alt_ah_attr);
-	resp.alt_dest.static_rate
-			= rdma_ah_get_static_rate(&attr->alt_ah_attr);
-	resp.alt_dest.is_global
-			= !!(rdma_ah_get_ah_flags(&attr->alt_ah_attr) &
-						  IB_AH_GRH);
-	if (resp.alt_dest.is_global) {
-		grh = rdma_ah_read_grh(&attr->alt_ah_attr);
-		memcpy(resp.alt_dest.dgid, grh->dgid.raw, 16);
-		resp.alt_dest.flow_label    = grh->flow_label;
-		resp.alt_dest.sgid_index    = grh->sgid_index;
-		resp.alt_dest.hop_limit     = grh->hop_limit;
-		resp.alt_dest.traffic_class = grh->traffic_class;
-	}
-	resp.alt_dest.port_num      = rdma_ah_get_port_num(&attr->alt_ah_attr);
+	copy_ah_attr_to_uverbs(&resp.dest, &attr->ah_attr);
+	copy_ah_attr_to_uverbs(&resp.alt_dest, &attr->alt_ah_attr);
 
 	resp.max_send_wr            = init_attr->cap.max_send_wr;
 	resp.max_recv_wr            = init_attr->cap.max_recv_wr;
@@ -1946,6 +1936,29 @@ static int modify_qp_mask(enum ib_qp_type qp_type, int mask)
 	}
 }
 
+static void copy_ah_attr_from_uverbs(struct ib_device *dev,
+				     struct rdma_ah_attr *rdma_attr,
+				     struct ib_uverbs_qp_dest *uverb_attr)
+{
+	rdma_attr->type = rdma_ah_find_type(dev, uverb_attr->port_num);
+	if (uverb_attr->is_global) {
+		rdma_ah_set_grh(rdma_attr, NULL,
+				uverb_attr->flow_label,
+				uverb_attr->sgid_index,
+				uverb_attr->hop_limit,
+				uverb_attr->traffic_class);
+		rdma_ah_set_dgid_raw(rdma_attr, uverb_attr->dgid);
+	} else {
+		rdma_ah_set_ah_flags(rdma_attr, 0);
+	}
+	rdma_ah_set_dlid(rdma_attr, uverb_attr->dlid);
+	rdma_ah_set_sl(rdma_attr, uverb_attr->sl);
+	rdma_ah_set_path_bits(rdma_attr, uverb_attr->src_path_bits);
+	rdma_ah_set_static_rate(rdma_attr, uverb_attr->static_rate);
+	rdma_ah_set_port_num(rdma_attr, uverb_attr->port_num);
+	rdma_ah_set_make_grd(rdma_attr, false);
+}
+
 static int modify_qp(struct ib_uverbs_file *file,
 		     struct ib_uverbs_ex_modify_qp *cmd, struct ib_udata *udata)
 {
@@ -1993,50 +2006,12 @@ static int modify_qp(struct ib_uverbs_file *file,
 	attr->rate_limit	  = cmd->rate_limit;
 
 	if (cmd->base.attr_mask & IB_QP_AV)
-		attr->ah_attr.type = rdma_ah_find_type(qp->device,
-						       cmd->base.dest.port_num);
-	if (cmd->base.dest.is_global) {
-		rdma_ah_set_grh(&attr->ah_attr, NULL,
-				cmd->base.dest.flow_label,
-				cmd->base.dest.sgid_index,
-				cmd->base.dest.hop_limit,
-				cmd->base.dest.traffic_class);
-		rdma_ah_set_dgid_raw(&attr->ah_attr, cmd->base.dest.dgid);
-	} else {
-		rdma_ah_set_ah_flags(&attr->ah_attr, 0);
-	}
-	rdma_ah_set_dlid(&attr->ah_attr, cmd->base.dest.dlid);
-	rdma_ah_set_sl(&attr->ah_attr, cmd->base.dest.sl);
-	rdma_ah_set_path_bits(&attr->ah_attr, cmd->base.dest.src_path_bits);
-	rdma_ah_set_static_rate(&attr->ah_attr, cmd->base.dest.static_rate);
-	rdma_ah_set_port_num(&attr->ah_attr,
-			     cmd->base.dest.port_num);
-	rdma_ah_set_make_grd(&attr->ah_attr, false);
+		copy_ah_attr_from_uverbs(qp->device, &attr->ah_attr,
+					 &cmd->base.dest);
 
 	if (cmd->base.attr_mask & IB_QP_ALT_PATH)
-		attr->alt_ah_attr.type =
-			rdma_ah_find_type(qp->device, cmd->base.dest.port_num);
-	if (cmd->base.alt_dest.is_global) {
-		rdma_ah_set_grh(&attr->alt_ah_attr, NULL,
-				cmd->base.alt_dest.flow_label,
-				cmd->base.alt_dest.sgid_index,
-				cmd->base.alt_dest.hop_limit,
-				cmd->base.alt_dest.traffic_class);
-		rdma_ah_set_dgid_raw(&attr->alt_ah_attr,
-				     cmd->base.alt_dest.dgid);
-	} else {
-		rdma_ah_set_ah_flags(&attr->alt_ah_attr, 0);
-	}
-
-	rdma_ah_set_dlid(&attr->alt_ah_attr, cmd->base.alt_dest.dlid);
-	rdma_ah_set_sl(&attr->alt_ah_attr, cmd->base.alt_dest.sl);
-	rdma_ah_set_path_bits(&attr->alt_ah_attr,
-			      cmd->base.alt_dest.src_path_bits);
-	rdma_ah_set_static_rate(&attr->alt_ah_attr,
-				cmd->base.alt_dest.static_rate);
-	rdma_ah_set_port_num(&attr->alt_ah_attr,
-			     cmd->base.alt_dest.port_num);
-	rdma_ah_set_make_grd(&attr->alt_ah_attr, false);
+		copy_ah_attr_from_uverbs(qp->device, &attr->alt_ah_attr,
+					 &cmd->base.alt_dest);
 
 	ret = ib_modify_qp_with_udata(qp, attr,
 				      modify_qp_mask(qp->qp_type,
-- 
cgit v1.2.3-59-g8ed1b


From dcc9881e6767559c04faf15804ac145a2ea026cb Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Aug 2017 15:50:36 +0300
Subject: RDMA/(core, ulp): Convert register/unregister event handler to be
 void

The functions ib_register_event_handler() and
ib_unregister_event_handler() always returned success and they can't fail.

Let's convert those functions to be void, remove redundant checks and
cleanup tons of goto statements.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cache.c                 | 23 ++++++++---------------
 drivers/infiniband/core/device.c                |  8 ++------
 drivers/infiniband/core/sa_query.c              |  3 +--
 drivers/infiniband/core/uverbs_main.c           | 13 +------------
 drivers/infiniband/ulp/ipoib/ipoib_main.c       | 10 +---------
 drivers/infiniband/ulp/iser/iser_verbs.c        |  6 ++----
 drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c |  7 +------
 drivers/infiniband/ulp/srpt/ib_srpt.c           |  5 ++---
 include/rdma/ib_verbs.h                         |  4 ++--
 9 files changed, 20 insertions(+), 59 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index efc94304dee3..77515638c55c 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -1199,30 +1199,23 @@ int ib_cache_setup_one(struct ib_device *device)
 	device->cache.ports =
 		kzalloc(sizeof(*device->cache.ports) *
 			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
-	if (!device->cache.ports) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!device->cache.ports)
+		return -ENOMEM;
 
 	err = gid_table_setup_one(device);
-	if (err)
-		goto out;
+	if (err) {
+		kfree(device->cache.ports);
+		device->cache.ports = NULL;
+		return err;
+	}
 
 	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p)
 		ib_cache_update(device, p + rdma_start_port(device), true);
 
 	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
 			      device, ib_cache_event);
-	err = ib_register_event_handler(&device->cache.event_handler);
-	if (err)
-		goto err;
-
+	ib_register_event_handler(&device->cache.event_handler);
 	return 0;
-
-err:
-	gid_table_cleanup_one(device);
-out:
-	return err;
 }
 
 void ib_cache_release_one(struct ib_device *device)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index fc6be1175183..ec4786777447 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -747,7 +747,7 @@ EXPORT_SYMBOL(ib_set_client_data);
  * chapter 11 of the InfiniBand Architecture Specification).  This
  * callback may occur in interrupt context.
  */
-int ib_register_event_handler  (struct ib_event_handler *event_handler)
+void ib_register_event_handler(struct ib_event_handler *event_handler)
 {
 	unsigned long flags;
 
@@ -755,8 +755,6 @@ int ib_register_event_handler  (struct ib_event_handler *event_handler)
 	list_add_tail(&event_handler->list,
 		      &event_handler->device->event_handler_list);
 	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
-
-	return 0;
 }
 EXPORT_SYMBOL(ib_register_event_handler);
 
@@ -767,15 +765,13 @@ EXPORT_SYMBOL(ib_register_event_handler);
  * Unregister an event handler registered with
  * ib_register_event_handler().
  */
-int ib_unregister_event_handler(struct ib_event_handler *event_handler)
+void ib_unregister_event_handler(struct ib_event_handler *event_handler)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&event_handler->device->event_handler_lock, flags);
 	list_del(&event_handler->list);
 	spin_unlock_irqrestore(&event_handler->device->event_handler_lock, flags);
-
-	return 0;
 }
 EXPORT_SYMBOL(ib_unregister_event_handler);
 
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 0179b21bad34..ab5e1024fea9 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -2417,8 +2417,7 @@ static void ib_sa_add_one(struct ib_device *device)
 	 */
 
 	INIT_IB_EVENT_HANDLER(&sa_dev->event_handler, device, ib_sa_event);
-	if (ib_register_event_handler(&sa_dev->event_handler))
-		goto err;
+	ib_register_event_handler(&sa_dev->event_handler);
 
 	for (i = 0; i <= e - s; ++i) {
 		if (rdma_cap_ib_sa(device, i + 1))
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 5e530d2bee44..defeda33e27f 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -595,7 +595,6 @@ struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file
 {
 	struct ib_uverbs_async_event_file *ev_file;
 	struct file *filp;
-	int ret;
 
 	ev_file = kzalloc(sizeof(*ev_file), GFP_KERNEL);
 	if (!ev_file)
@@ -621,21 +620,11 @@ struct file *ib_uverbs_alloc_async_event_file(struct ib_uverbs_file *uverbs_file
 	INIT_IB_EVENT_HANDLER(&uverbs_file->event_handler,
 			      ib_dev,
 			      ib_uverbs_event_handler);
-	ret = ib_register_event_handler(&uverbs_file->event_handler);
-	if (ret)
-		goto err_put_file;
-
+	ib_register_event_handler(&uverbs_file->event_handler);
 	/* At that point async file stuff was fully set */
 
 	return filp;
 
-err_put_file:
-	fput(filp);
-	kref_put(&uverbs_file->async_file->ref,
-		 ib_uverbs_release_async_event_file);
-	uverbs_file->async_file = NULL;
-	return ERR_PTR(ret);
-
 err_put_refs:
 	kref_put(&ev_file->uverbs_file->ref, ib_uverbs_release_file);
 	kref_put(&ev_file->ref, ib_uverbs_release_async_event_file);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index ee9f5d281b37..344e8d3d47bd 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -2227,13 +2227,7 @@ static struct net_device *ipoib_add_port(const char *format,
 
 	INIT_IB_EVENT_HANDLER(&priv->event_handler,
 			      priv->ca, ipoib_event);
-	result = ib_register_event_handler(&priv->event_handler);
-	if (result < 0) {
-		printk(KERN_WARNING "%s: ib_register_event_handler failed for "
-		       "port %d (ret = %d)\n",
-		       hca->name, port, result);
-		goto event_failed;
-	}
+	ib_register_event_handler(&priv->event_handler);
 
 	result = register_netdev(priv->dev);
 	if (result) {
@@ -2266,8 +2260,6 @@ register_failed:
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	cancel_delayed_work(&priv->neigh_reap_task);
 	flush_workqueue(priv->wq);
-
-event_failed:
 	ipoib_dev_cleanup(priv->dev);
 
 device_init_failed:
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index 26a004e97ae0..55a73b0ed4c6 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -106,9 +106,7 @@ static int iser_create_device_ib_res(struct iser_device *device)
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, ib_dev,
 			      iser_event_handler);
-	if (ib_register_event_handler(&device->event_handler))
-		goto cq_err;
-
+	ib_register_event_handler(&device->event_handler);
 	return 0;
 
 cq_err:
@@ -141,7 +139,7 @@ static void iser_free_device_ib_res(struct iser_device *device)
 		comp->cq = NULL;
 	}
 
-	(void)ib_unregister_event_handler(&device->event_handler);
+	ib_unregister_event_handler(&device->event_handler);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
index 57b862b94dca..21f0b481edcc 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_vema.c
@@ -954,12 +954,7 @@ static int vema_register(struct opa_vnic_ctrl_port *cport)
 
 		INIT_IB_EVENT_HANDLER(&port->event_handler,
 				      cport->ibdev, opa_vnic_event);
-		ret = ib_register_event_handler(&port->event_handler);
-		if (ret) {
-			c_err("port %d: event handler register failed\n", i);
-			vema_unregister(cport);
-			return ret;
-		}
+		ib_register_event_handler(&port->event_handler);
 
 		idr_init(&port->vport_idr);
 		mutex_init(&port->lock);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 402275be0931..9e8e9220f816 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2238,7 +2238,7 @@ static int srpt_write_pending(struct se_cmd *se_cmd)
 				cqe, first_wr);
 		cqe = NULL;
 	}
-	
+
 	ret = ib_post_send(ch->qp, first_wr, &bad_wr);
 	if (ret) {
 		pr_err("%s: ib_post_send() returned %d for %d (avail: %d)\n",
@@ -2530,8 +2530,7 @@ static void srpt_add_one(struct ib_device *device)
 
 	INIT_IB_EVENT_HANDLER(&sdev->event_handler, sdev->device,
 			      srpt_event_handler);
-	if (ib_register_event_handler(&sdev->event_handler))
-		goto err_cm;
+	ib_register_event_handler(&sdev->event_handler);
 
 	sdev->ioctx_ring = (struct srpt_recv_ioctx **)
 		srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c155c105589d..e536a052e5dd 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2413,8 +2413,8 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
 		       enum rdma_link_layer ll);
 
-int ib_register_event_handler  (struct ib_event_handler *event_handler);
-int ib_unregister_event_handler(struct ib_event_handler *event_handler);
+void ib_register_event_handler(struct ib_event_handler *event_handler);
+void ib_unregister_event_handler(struct ib_event_handler *event_handler);
 void ib_dispatch_event(struct ib_event *event);
 
 int ib_query_port(struct ib_device *device,
-- 
cgit v1.2.3-59-g8ed1b


From cdc596d89e39521cf412209a19b8baeb8d788cdc Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Aug 2017 15:50:38 +0300
Subject: RDMA/core: Delete BUG() from unreachable flow

Remove call to BUG() in case wrong node_type was provided.
This flow is unreachable, because node_types are supplied
from specific enum.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 6a7cbc1540aa..4c1485e01c83 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -180,21 +180,15 @@ EXPORT_SYMBOL(ib_rate_to_mbps);
 __attribute_const__ enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type)
 {
-	switch (node_type) {
-	case RDMA_NODE_IB_CA:
-	case RDMA_NODE_IB_SWITCH:
-	case RDMA_NODE_IB_ROUTER:
-		return RDMA_TRANSPORT_IB;
-	case RDMA_NODE_RNIC:
-		return RDMA_TRANSPORT_IWARP;
-	case RDMA_NODE_USNIC:
+
+	if (node_type == RDMA_NODE_USNIC)
 		return RDMA_TRANSPORT_USNIC;
-	case RDMA_NODE_USNIC_UDP:
+	if (node_type == RDMA_NODE_USNIC_UDP)
 		return RDMA_TRANSPORT_USNIC_UDP;
-	default:
-		BUG();
-		return 0;
-	}
+	if (node_type == RDMA_NODE_RNIC)
+		return RDMA_TRANSPORT_IWARP;
+
+	return RDMA_TRANSPORT_IB;
 }
 EXPORT_SYMBOL(rdma_node_get_transport);
 
-- 
cgit v1.2.3-59-g8ed1b


From 82901e3eb8f72326b06ac8c7285462d90cd3a56c Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 17 Aug 2017 15:50:39 +0300
Subject: RDMA/core: Refactor get link layer wrapper

The return values from rdma_node_get_transport() are strict
and IB_LINK_LAYER_UNSPECIFIED is unreachable in this flow.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 4c1485e01c83..b29d0ff94463 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -194,19 +194,15 @@ EXPORT_SYMBOL(rdma_node_get_transport);
 
 enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num)
 {
+	enum rdma_transport_type lt;
 	if (device->get_link_layer)
 		return device->get_link_layer(device, port_num);
 
-	switch (rdma_node_get_transport(device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	lt = rdma_node_get_transport(device->node_type);
+	if (lt == RDMA_TRANSPORT_IB)
 		return IB_LINK_LAYER_INFINIBAND;
-	case RDMA_TRANSPORT_IWARP:
-	case RDMA_TRANSPORT_USNIC:
-	case RDMA_TRANSPORT_USNIC_UDP:
-		return IB_LINK_LAYER_ETHERNET;
-	default:
-		return IB_LINK_LAYER_UNSPECIFIED;
-	}
+
+	return IB_LINK_LAYER_ETHERNET;
 }
 EXPORT_SYMBOL(rdma_port_get_link_layer);
 
-- 
cgit v1.2.3-59-g8ed1b


From 61e0962d52216f2e5bab59bb055f1210e41f484f Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Wed, 23 Aug 2017 01:08:07 -0700
Subject: IB: Avoid ib_modify_port() failure for RoCE devices

IB CM calls ib_modify_port() irrespective of link layer. If the
failure is returned, the mad agent gets unregistered for those
devices. Recently, modify_port() hook was removed from some of the
low level drivers as it was always returning success. This breaks
rdma connection establishment over those devices.
For ethernet devices, Qkey violation and port capabilities are not
applicable. So returning success for RoCE when modify_port hook is
is not implemented.

Cc: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/device.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index fc6be1175183..2466ffc6362d 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -1005,14 +1005,17 @@ int ib_modify_port(struct ib_device *device,
 		   u8 port_num, int port_modify_mask,
 		   struct ib_port_modify *port_modify)
 {
-	if (!device->modify_port)
-		return -ENOSYS;
+	int rc;
 
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	return device->modify_port(device, port_num, port_modify_mask,
-				   port_modify);
+	if (device->modify_port)
+		rc = device->modify_port(device, port_num, port_modify_mask,
+					   port_modify);
+	else
+		rc = rdma_protocol_roce(device, port_num) ? 0 : -ENOSYS;
+	return rc;
 }
 EXPORT_SYMBOL(ib_modify_port);
 
-- 
cgit v1.2.3-59-g8ed1b


From 1a56ff6daab1e062aadec582eb10e7090f0b370a Mon Sep 17 00:00:00 2001
From: Artemy Kovalyov <artemyko@mellanox.com>
Date: Thu, 17 Aug 2017 15:52:04 +0300
Subject: IB/core: Separate CQ handle in SRQ context

Before this change CQ attached to SRQ was part of XRC specific extension.
Moving CQ handle out makes it available to other types extending SRQ
functionality.

Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 27 +++++++++++++++++----------
 drivers/infiniband/core/verbs.c      | 16 +++++++++-------
 drivers/infiniband/hw/mlx4/srq.c     |  4 ++--
 drivers/infiniband/hw/mlx5/main.c    | 10 +++++-----
 drivers/infiniband/hw/mlx5/srq.c     | 11 +++++++----
 include/rdma/ib_verbs.h              | 31 ++++++++++++++++++++-----------
 6 files changed, 60 insertions(+), 39 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 8e9fea03dec4..9f690af46a7e 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3497,10 +3497,12 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 
 		obj->uxrcd = container_of(xrcd_uobj, struct ib_uxrcd_object, uobject);
 		atomic_inc(&obj->uxrcd->refcnt);
+	}
 
-		attr.ext.xrc.cq  = uobj_get_obj_read(cq, cmd->cq_handle,
-						     file->ucontext);
-		if (!attr.ext.xrc.cq) {
+	if (ib_srq_has_cq(cmd->srq_type)) {
+		attr.ext.cq  = uobj_get_obj_read(cq, cmd->cq_handle,
+						 file->ucontext);
+		if (!attr.ext.cq) {
 			ret = -EINVAL;
 			goto err_put_xrcd;
 		}
@@ -3535,10 +3537,13 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	srq->event_handler = attr.event_handler;
 	srq->srq_context   = attr.srq_context;
 
+	if (ib_srq_has_cq(cmd->srq_type)) {
+		srq->ext.cq       = attr.ext.cq;
+		atomic_inc(&attr.ext.cq->usecnt);
+	}
+
 	if (cmd->srq_type == IB_SRQT_XRC) {
-		srq->ext.xrc.cq   = attr.ext.xrc.cq;
 		srq->ext.xrc.xrcd = attr.ext.xrc.xrcd;
-		atomic_inc(&attr.ext.xrc.cq->usecnt);
 		atomic_inc(&attr.ext.xrc.xrcd->usecnt);
 	}
 
@@ -3561,10 +3566,12 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 		goto err_copy;
 	}
 
-	if (cmd->srq_type == IB_SRQT_XRC) {
+	if (cmd->srq_type == IB_SRQT_XRC)
 		uobj_put_read(xrcd_uobj);
-		uobj_put_obj_read(attr.ext.xrc.cq);
-	}
+
+	if (ib_srq_has_cq(cmd->srq_type))
+		uobj_put_obj_read(attr.ext.cq);
+
 	uobj_put_obj_read(pd);
 	uobj_alloc_commit(&obj->uevent.uobject);
 
@@ -3577,8 +3584,8 @@ err_put:
 	uobj_put_obj_read(pd);
 
 err_put_cq:
-	if (cmd->srq_type == IB_SRQT_XRC)
-		uobj_put_obj_read(attr.ext.xrc.cq);
+	if (ib_srq_has_cq(cmd->srq_type))
+		uobj_put_obj_read(attr.ext.cq);
 
 err_put_xrcd:
 	if (cmd->srq_type == IB_SRQT_XRC) {
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index b29d0ff94463..ecb6c395f19b 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -622,11 +622,13 @@ struct ib_srq *ib_create_srq(struct ib_pd *pd,
 		srq->event_handler = srq_init_attr->event_handler;
 		srq->srq_context   = srq_init_attr->srq_context;
 		srq->srq_type      = srq_init_attr->srq_type;
+		if (ib_srq_has_cq(srq->srq_type)) {
+			srq->ext.cq   = srq_init_attr->ext.cq;
+			atomic_inc(&srq->ext.cq->usecnt);
+		}
 		if (srq->srq_type == IB_SRQT_XRC) {
 			srq->ext.xrc.xrcd = srq_init_attr->ext.xrc.xrcd;
-			srq->ext.xrc.cq   = srq_init_attr->ext.xrc.cq;
 			atomic_inc(&srq->ext.xrc.xrcd->usecnt);
-			atomic_inc(&srq->ext.xrc.cq->usecnt);
 		}
 		atomic_inc(&pd->usecnt);
 		atomic_set(&srq->usecnt, 0);
@@ -667,18 +669,18 @@ int ib_destroy_srq(struct ib_srq *srq)
 
 	pd = srq->pd;
 	srq_type = srq->srq_type;
-	if (srq_type == IB_SRQT_XRC) {
+	if (ib_srq_has_cq(srq_type))
+		cq = srq->ext.cq;
+	if (srq_type == IB_SRQT_XRC)
 		xrcd = srq->ext.xrc.xrcd;
-		cq = srq->ext.xrc.cq;
-	}
 
 	ret = srq->device->destroy_srq(srq);
 	if (!ret) {
 		atomic_dec(&pd->usecnt);
-		if (srq_type == IB_SRQT_XRC) {
+		if (srq_type == IB_SRQT_XRC)
 			atomic_dec(&xrcd->usecnt);
+		if (ib_srq_has_cq(srq_type))
 			atomic_dec(&cq->usecnt);
-		}
 	}
 
 	return ret;
diff --git a/drivers/infiniband/hw/mlx4/srq.c b/drivers/infiniband/hw/mlx4/srq.c
index dd7a2fce9df4..ebee56cbc0e2 100644
--- a/drivers/infiniband/hw/mlx4/srq.c
+++ b/drivers/infiniband/hw/mlx4/srq.c
@@ -178,8 +178,8 @@ struct ib_srq *mlx4_ib_create_srq(struct ib_pd *pd,
 		}
 	}
 
-	cqn = (init_attr->srq_type == IB_SRQT_XRC) ?
-		to_mcq(init_attr->ext.xrc.cq)->mcq.cqn : 0;
+	cqn = ib_srq_has_cq(init_attr->srq_type) ?
+		to_mcq(init_attr->ext.cq)->mcq.cqn : 0;
 	xrcdn = (init_attr->srq_type == IB_SRQT_XRC) ?
 		to_mxrcd(init_attr->ext.xrc.xrcd)->xrcdn :
 		(u16) dev->dev->caps.reserved_xrcds;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 62e6298810e7..7ad585257fd3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3217,7 +3217,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	attr.attr.max_sge = 1;
 	attr.attr.max_wr = 1;
 	attr.srq_type = IB_SRQT_XRC;
-	attr.ext.xrc.cq = devr->c0;
+	attr.ext.cq = devr->c0;
 	attr.ext.xrc.xrcd = devr->x0;
 
 	devr->s0 = mlx5_ib_create_srq(devr->p0, &attr, NULL);
@@ -3232,9 +3232,9 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->s0->srq_context   = NULL;
 	devr->s0->srq_type      = IB_SRQT_XRC;
 	devr->s0->ext.xrc.xrcd	= devr->x0;
-	devr->s0->ext.xrc.cq	= devr->c0;
+	devr->s0->ext.cq	= devr->c0;
 	atomic_inc(&devr->s0->ext.xrc.xrcd->usecnt);
-	atomic_inc(&devr->s0->ext.xrc.cq->usecnt);
+	atomic_inc(&devr->s0->ext.cq->usecnt);
 	atomic_inc(&devr->p0->usecnt);
 	atomic_set(&devr->s0->usecnt, 0);
 
@@ -3253,9 +3253,9 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->s1->event_handler = NULL;
 	devr->s1->srq_context   = NULL;
 	devr->s1->srq_type      = IB_SRQT_BASIC;
-	devr->s1->ext.xrc.cq	= devr->c0;
+	devr->s1->ext.cq	= devr->c0;
 	atomic_inc(&devr->p0->usecnt);
-	atomic_set(&devr->s0->usecnt, 0);
+	atomic_set(&devr->s1->usecnt, 0);
 
 	for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) {
 		INIT_WORK(&devr->ports[port].pkey_change_work,
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 30b3ddd8e1ab..e6be4f2927a7 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -292,13 +292,16 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 	in.wqe_shift = srq->msrq.wqe_shift - 4;
 	if (srq->wq_sig)
 		in.flags |= MLX5_SRQ_FLAG_WQ_SIG;
-	if (init_attr->srq_type == IB_SRQT_XRC) {
+
+	if (init_attr->srq_type == IB_SRQT_XRC)
 		in.xrcd = to_mxrcd(init_attr->ext.xrc.xrcd)->xrcdn;
-		in.cqn = to_mcq(init_attr->ext.xrc.cq)->mcq.cqn;
-	} else if (init_attr->srq_type == IB_SRQT_BASIC) {
+	else
 		in.xrcd = to_mxrcd(dev->devr.x0)->xrcdn;
+
+	if (ib_srq_has_cq(init_attr->srq_type))
+		in.cqn = to_mcq(init_attr->ext.cq)->mcq.cqn;
+	else
 		in.cqn = to_mcq(dev->devr.c0)->mcq.cqn;
-	}
 
 	in.pd = to_mpd(pd)->pdn;
 	in.db_record = srq->db.dma;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index cab0bdcfad51..f0e46757185b 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -994,6 +994,11 @@ enum ib_srq_type {
 	IB_SRQT_XRC
 };
 
+static inline bool ib_srq_has_cq(enum ib_srq_type srq_type)
+{
+	return srq_type == IB_SRQT_XRC;
+}
+
 enum ib_srq_attr_mask {
 	IB_SRQ_MAX_WR	= 1 << 0,
 	IB_SRQ_LIMIT	= 1 << 1,
@@ -1011,11 +1016,13 @@ struct ib_srq_init_attr {
 	struct ib_srq_attr	attr;
 	enum ib_srq_type	srq_type;
 
-	union {
-		struct {
-			struct ib_xrcd *xrcd;
-			struct ib_cq   *cq;
-		} xrc;
+	struct {
+		struct ib_cq   *cq;
+		union {
+			struct {
+				struct ib_xrcd *xrcd;
+			} xrc;
+		};
 	} ext;
 };
 
@@ -1554,12 +1561,14 @@ struct ib_srq {
 	enum ib_srq_type	srq_type;
 	atomic_t		usecnt;
 
-	union {
-		struct {
-			struct ib_xrcd *xrcd;
-			struct ib_cq   *cq;
-			u32		srq_num;
-		} xrc;
+	struct {
+		struct ib_cq   *cq;
+		union {
+			struct {
+				struct ib_xrcd *xrcd;
+				u32		srq_num;
+			} xrc;
+		};
 	} ext;
 };
 
-- 
cgit v1.2.3-59-g8ed1b


From 38eb44fac71729fabdef71166e72bee5964c10d6 Mon Sep 17 00:00:00 2001
From: Artemy Kovalyov <artemyko@mellanox.com>
Date: Thu, 17 Aug 2017 15:52:07 +0300
Subject: IB/uverbs: Add new SRQ type IB_SRQT_TM

Add new SRQ type capable of new tag matching feature.

When SRQ receives a message it will search through the matching list
for the corresponding posted receive buffer. The process of searching
the matching list is called tag matching.

In case the tag matching results in a match, the received message will
be placed in the address specified by the receive buffer. In case no
match was found the message will be placed in a generic buffer until the
corresponding receive buffer will be posted. These messages are called
unexpected and their set is called an unexpected list.

Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 9f690af46a7e..e69038a07fa0 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1438,7 +1438,7 @@ static int create_qp(struct ib_uverbs_file *file,
 			if (cmd->is_srq) {
 				srq = uobj_get_obj_read(srq, cmd->srq_handle,
 							file->ucontext);
-				if (!srq || srq->srq_type != IB_SRQT_BASIC) {
+				if (!srq || srq->srq_type == IB_SRQT_XRC) {
 					ret = -EINVAL;
 					goto err_put;
 				}
@@ -3481,6 +3481,9 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
+	if (cmd->srq_type == IB_SRQT_TM)
+		attr.ext.tag_matching.max_num_tags = cmd->max_num_tags;
+
 	if (cmd->srq_type == IB_SRQT_XRC) {
 		xrcd_uobj = uobj_get_read(uobj_get_type(xrcd), cmd->xrcd_handle,
 					  file->ucontext);
@@ -3615,6 +3618,7 @@ ssize_t ib_uverbs_create_srq(struct ib_uverbs_file *file,
 	if (copy_from_user(&cmd, buf, sizeof cmd))
 		return -EFAULT;
 
+	memset(&xcmd, 0, sizeof(xcmd));
 	xcmd.response	 = cmd.response;
 	xcmd.user_handle = cmd.user_handle;
 	xcmd.srq_type	 = IB_SRQT_BASIC;
-- 
cgit v1.2.3-59-g8ed1b


From 8d50505ada728258fcdce99120b937ce68298c4e Mon Sep 17 00:00:00 2001
From: Artemy Kovalyov <artemyko@mellanox.com>
Date: Thu, 17 Aug 2017 15:52:08 +0300
Subject: IB/uverbs: Expose XRQ capabilities

Make XRQ capabilities available via ibv_query_device() verb.

Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Yossi Itigin <yosefe@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 10 ++++++++++
 include/uapi/rdma/ib_user_verbs.h    | 15 +++++++++++++++
 2 files changed, 25 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index e69038a07fa0..e0cb99860934 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3868,6 +3868,16 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 
 	resp.raw_packet_caps = attr.raw_packet_caps;
 	resp.response_length += sizeof(resp.raw_packet_caps);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.xrq_caps))
+		goto end;
+
+	resp.xrq_caps.max_rndv_hdr_size = attr.xrq_caps.max_rndv_hdr_size;
+	resp.xrq_caps.max_num_tags      = attr.xrq_caps.max_num_tags;
+	resp.xrq_caps.max_ops		= attr.xrq_caps.max_ops;
+	resp.xrq_caps.max_sge		= attr.xrq_caps.max_sge;
+	resp.xrq_caps.flags		= attr.xrq_caps.flags;
+	resp.response_length += sizeof(resp.xrq_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index d5434bbf40c8..9a0b6479fe0c 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -236,6 +236,20 @@ struct ib_uverbs_rss_caps {
 	__u32 reserved;
 };
 
+struct ib_uverbs_tm_caps {
+	/* Max size of rendezvous request message */
+	__u32 max_rndv_hdr_size;
+	/* Max number of entries in tag matching list */
+	__u32 max_num_tags;
+	/* TM flags */
+	__u32 flags;
+	/* Max number of outstanding list operations */
+	__u32 max_ops;
+	/* Max number of SGE in tag matching entry */
+	__u32 max_sge;
+	__u32 reserved;
+};
+
 struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_query_device_resp base;
 	__u32 comp_mask;
@@ -247,6 +261,7 @@ struct ib_uverbs_ex_query_device_resp {
 	struct ib_uverbs_rss_caps rss_caps;
 	__u32  max_wq_type_rq;
 	__u32 raw_packet_caps;
+	struct ib_uverbs_tm_caps xrq_caps;
 };
 
 struct ib_uverbs_query_port {
-- 
cgit v1.2.3-59-g8ed1b


From a0aa309c39de58b86b704654434431aeb5a8bdf1 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:06:55 +0300
Subject: IB/core: Add a generic way to execute an operation on a uobject

The ioctl infrastructure treats all user-objects in the same manner.
It gets objects ids from the user-space and by using the object type
and type attributes mentioned in the object specification, it executes
this required method. Passing an object id from the user-space as
an attribute is carried out in three stages. The first is carried out
before the actual handler and the last is carried out afterwards.

The different supported operations are read, write, destroy and create.
In the first stage, the former three actions just fetches the object
from the repository (by using its id) and locks it. The last action
allocates a new uobject. Afterwards, the second stage is carried out
when the handler itself carries out the required modification of the
object. The last stage is carried out after the handler finishes and
commits the result. The former two operations just unlock the object.
Destroy calls the "free object" operation, taking into account the
object's type and releases the uobject as well. Creation just adds the
new uobject to the repository, making the object visible to the
application.

In order to abstract these details from the ioctl infrastructure
layer, we add uverbs_get_uobject_from_context and
uverbs_finalize_object functions which corresponds to the first
and last stages respectively.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/rdma_core.c | 58 +++++++++++++++++++++++++++++++++++++
 drivers/infiniband/core/rdma_core.h | 17 +++++++++++
 include/rdma/uverbs_ioctl.h         | 52 +++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+)
 create mode 100644 include/rdma/uverbs_ioctl.h

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 41c31a2bf093..2bd58ff17bb8 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -35,6 +35,7 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/uverbs_types.h>
 #include <linux/rcupdate.h>
+#include <rdma/uverbs_ioctl.h>
 #include "uverbs.h"
 #include "core_priv.h"
 #include "rdma_core.h"
@@ -625,3 +626,60 @@ const struct uverbs_obj_type_class uverbs_fd_class = {
 	.needs_kfree_rcu = false,
 };
 
+struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type *type_attrs,
+						   struct ib_ucontext *ucontext,
+						   enum uverbs_obj_access access,
+						   int id)
+{
+	switch (access) {
+	case UVERBS_ACCESS_READ:
+		return rdma_lookup_get_uobject(type_attrs, ucontext, id, false);
+	case UVERBS_ACCESS_DESTROY:
+	case UVERBS_ACCESS_WRITE:
+		return rdma_lookup_get_uobject(type_attrs, ucontext, id, true);
+	case UVERBS_ACCESS_NEW:
+		return rdma_alloc_begin_uobject(type_attrs, ucontext);
+	default:
+		WARN_ON(true);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+}
+
+int uverbs_finalize_object(struct ib_uobject *uobj,
+			   enum uverbs_obj_access access,
+			   bool commit)
+{
+	int ret = 0;
+
+	/*
+	 * refcounts should be handled at the object level and not at the
+	 * uobject level. Refcounts of the objects themselves are done in
+	 * handlers.
+	 */
+
+	switch (access) {
+	case UVERBS_ACCESS_READ:
+		rdma_lookup_put_uobject(uobj, false);
+		break;
+	case UVERBS_ACCESS_WRITE:
+		rdma_lookup_put_uobject(uobj, true);
+		break;
+	case UVERBS_ACCESS_DESTROY:
+		if (commit)
+			ret = rdma_remove_commit_uobject(uobj);
+		else
+			rdma_lookup_put_uobject(uobj, true);
+		break;
+	case UVERBS_ACCESS_NEW:
+		if (commit)
+			ret = rdma_alloc_commit_uobject(uobj);
+		else
+			rdma_alloc_abort_uobject(uobj);
+		break;
+	default:
+		WARN_ON(true);
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
diff --git a/drivers/infiniband/core/rdma_core.h b/drivers/infiniband/core/rdma_core.h
index 1b82e7ff7fe8..97483d1a7336 100644
--- a/drivers/infiniband/core/rdma_core.h
+++ b/drivers/infiniband/core/rdma_core.h
@@ -39,6 +39,7 @@
 
 #include <linux/idr.h>
 #include <rdma/uverbs_types.h>
+#include <rdma/uverbs_ioctl.h>
 #include <rdma/ib_verbs.h>
 #include <linux/mutex.h>
 
@@ -75,4 +76,20 @@ void uverbs_uobject_put(struct ib_uobject *uobject);
  */
 void uverbs_close_fd(struct file *f);
 
+/*
+ * Get an ib_uobject that corresponds to the given id from ucontext, assuming
+ * the object is from the given type. Lock it to the required access when
+ * applicable.
+ * This function could create (access == NEW), destroy (access == DESTROY)
+ * or unlock (access == READ || access == WRITE) objects if required.
+ * The action will be finalized only when uverbs_finalize_object is called.
+ */
+struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type *type_attrs,
+						   struct ib_ucontext *ucontext,
+						   enum uverbs_obj_access access,
+						   int id);
+int uverbs_finalize_object(struct ib_uobject *uobj,
+			   enum uverbs_obj_access access,
+			   bool commit);
+
 #endif /* RDMA_CORE_H */
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
new file mode 100644
index 000000000000..6885b92db4a8
--- /dev/null
+++ b/include/rdma/uverbs_ioctl.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _UVERBS_IOCTL_
+#define _UVERBS_IOCTL_
+
+#include <rdma/uverbs_types.h>
+
+/*
+ * =======================================
+ *	Verbs action specifications
+ * =======================================
+ */
+
+enum uverbs_obj_access {
+	UVERBS_ACCESS_READ,
+	UVERBS_ACCESS_WRITE,
+	UVERBS_ACCESS_NEW,
+	UVERBS_ACCESS_DESTROY
+};
+
+#endif
+
-- 
cgit v1.2.3-59-g8ed1b


From f43dbebfa32041826299bdccae0352887fa007ea Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:06:56 +0300
Subject: IB/core: Add support to finalize objects in one transaction

The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.

This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.

For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.

When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/rdma_core.c | 40 ++++++++++++++++++++++++++++
 drivers/infiniband/core/rdma_core.h | 22 ++++++++++++++-
 include/rdma/uverbs_ioctl.h         | 53 +++++++++++++++++++++++++++++++++++++
 3 files changed, 114 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 2bd58ff17bb8..0fe8ef913387 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -683,3 +683,43 @@ int uverbs_finalize_object(struct ib_uobject *uobj,
 
 	return ret;
 }
+
+int uverbs_finalize_objects(struct uverbs_attr_bundle *attrs_bundle,
+			    struct uverbs_attr_spec_hash * const *spec_hash,
+			    size_t num,
+			    bool commit)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < num; i++) {
+		struct uverbs_attr_bundle_hash *curr_bundle =
+			&attrs_bundle->hash[i];
+		const struct uverbs_attr_spec_hash *curr_spec_bucket =
+			spec_hash[i];
+		unsigned int j;
+
+		for (j = 0; j < curr_bundle->num_attrs; j++) {
+			struct uverbs_attr *attr;
+			const struct uverbs_attr_spec *spec;
+
+			if (!uverbs_attr_is_valid_in_hash(curr_bundle, j))
+				continue;
+
+			attr = &curr_bundle->attrs[j];
+			spec = &curr_spec_bucket->attrs[j];
+
+			if (spec->type == UVERBS_ATTR_TYPE_IDR ||
+			    spec->type == UVERBS_ATTR_TYPE_FD) {
+				int current_ret;
+
+				current_ret = uverbs_finalize_object(attr->obj_attr.uobject,
+								     spec->obj.access,
+								     commit);
+				if (!ret)
+					ret = current_ret;
+			}
+		}
+	}
+	return ret;
+}
diff --git a/drivers/infiniband/core/rdma_core.h b/drivers/infiniband/core/rdma_core.h
index 97483d1a7336..9ed6ad0324c7 100644
--- a/drivers/infiniband/core/rdma_core.h
+++ b/drivers/infiniband/core/rdma_core.h
@@ -82,7 +82,8 @@ void uverbs_close_fd(struct file *f);
  * applicable.
  * This function could create (access == NEW), destroy (access == DESTROY)
  * or unlock (access == READ || access == WRITE) objects if required.
- * The action will be finalized only when uverbs_finalize_object is called.
+ * The action will be finalized only when uverbs_finalize_object or
+ * uverbs_finalize_objects are called.
  */
 struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type *type_attrs,
 						   struct ib_ucontext *ucontext,
@@ -91,5 +92,24 @@ struct ib_uobject *uverbs_get_uobject_from_context(const struct uverbs_obj_type
 int uverbs_finalize_object(struct ib_uobject *uobj,
 			   enum uverbs_obj_access access,
 			   bool commit);
+/*
+ * Note that certain finalize stages could return a status:
+ *   (a) alloc_commit could return a failure if the object is committed at the
+ *       same time when the context is destroyed.
+ *   (b) remove_commit could fail if the object wasn't destroyed successfully.
+ * Since multiple objects could be finalized in one transaction, it is very NOT
+ * recommended to have several finalize actions which have side effects.
+ * For example, it's NOT recommended to have a certain action which has both
+ * a commit action and a destroy action or two destroy objects in the same
+ * action. The rule of thumb is to have one destroy or commit action with
+ * multiple lookups.
+ * The first non zero return value of finalize_object is returned from this
+ * function. For example, this could happen when we couldn't destroy an
+ * object.
+ */
+int uverbs_finalize_objects(struct uverbs_attr_bundle *attrs_bundle,
+			    struct uverbs_attr_spec_hash * const *spec_hash,
+			    size_t num,
+			    bool commit);
 
 #endif /* RDMA_CORE_H */
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 6885b92db4a8..d3ec02b7d937 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -41,6 +41,12 @@
  * =======================================
  */
 
+enum uverbs_attr_type {
+	UVERBS_ATTR_TYPE_NA,
+	UVERBS_ATTR_TYPE_IDR,
+	UVERBS_ATTR_TYPE_FD,
+};
+
 enum uverbs_obj_access {
 	UVERBS_ACCESS_READ,
 	UVERBS_ACCESS_WRITE,
@@ -48,5 +54,52 @@ enum uverbs_obj_access {
 	UVERBS_ACCESS_DESTROY
 };
 
+struct uverbs_attr_spec {
+	enum uverbs_attr_type		type;
+	struct {
+		/*
+		 * higher bits mean the namespace and lower bits mean
+		 * the type id within the namespace.
+		 */
+		u16			obj_type;
+		u8			access;
+	} obj;
+};
+
+struct uverbs_attr_spec_hash {
+	size_t				num_attrs;
+	struct uverbs_attr_spec		attrs[0];
+};
+
+struct uverbs_obj_attr {
+	struct ib_uobject		*uobject;
+};
+
+struct uverbs_attr {
+	struct uverbs_obj_attr	obj_attr;
+};
+
+struct uverbs_attr_bundle_hash {
+	/* if bit i is set, it means attrs[i] contains valid information */
+	unsigned long *valid_bitmap;
+	size_t num_attrs;
+	/*
+	 * arrays of attributes, each element corresponds to the specification
+	 * of the attribute in the same index.
+	 */
+	struct uverbs_attr *attrs;
+};
+
+struct uverbs_attr_bundle {
+	size_t				num_buckets;
+	struct uverbs_attr_bundle_hash  hash[];
+};
+
+static inline bool uverbs_attr_is_valid_in_hash(const struct uverbs_attr_bundle_hash *attrs_hash,
+						unsigned int idx)
+{
+	return test_bit(idx, attrs_hash->valid_bitmap);
+}
+
 #endif
 
-- 
cgit v1.2.3-59-g8ed1b


From c76161181193985087cd716fdf69b5cb6cf9ee85 Mon Sep 17 00:00:00 2001
From: Roland Dreier <roland@purestorage.com>
Date: Tue, 29 Aug 2017 10:34:43 -0700
Subject: IB/cm: Fix sleeping in atomic when RoCE is used

A couple of places in the CM do

    spin_lock_irq(&cm_id_priv->lock);
    ...
    if (cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg))

However when the underlying transport is RoCE, this leads to a sleeping function
being called with the lock held - the callchain is

    cm_alloc_response_msg() ->
      ib_create_ah_from_wc() ->
        ib_init_ah_from_wc() ->
          rdma_addr_find_l2_eth_by_grh() ->
            rdma_resolve_ip()

and rdma_resolve_ip() starts out by doing

    req = kzalloc(sizeof *req, GFP_KERNEL);

not to mention rdma_addr_find_l2_eth_by_grh() doing

    wait_for_completion(&ctx.comp);

to wait for the task that rdma_resolve_ip() queues up.

Fix this by moving the AH creation out of the lock.

Signed-off-by: Roland Dreier <roland@purestorage.com>
Reviewed-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/cm.c | 63 +++++++++++++++++++++++++++++++-------------
 1 file changed, 44 insertions(+), 19 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index fa3b0a428195..4c4b46586af2 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -373,11 +373,19 @@ out:
 	return ret;
 }
 
-static int cm_alloc_response_msg(struct cm_port *port,
-				 struct ib_mad_recv_wc *mad_recv_wc,
-				 struct ib_mad_send_buf **msg)
+static struct ib_mad_send_buf *cm_alloc_response_msg_no_ah(struct cm_port *port,
+							   struct ib_mad_recv_wc *mad_recv_wc)
+{
+	return ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
+				  0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
+				  GFP_ATOMIC,
+				  IB_MGMT_BASE_VERSION);
+}
+
+static int cm_create_response_msg_ah(struct cm_port *port,
+				     struct ib_mad_recv_wc *mad_recv_wc,
+				     struct ib_mad_send_buf *msg)
 {
-	struct ib_mad_send_buf *m;
 	struct ib_ah *ah;
 
 	ah = ib_create_ah_from_wc(port->mad_agent->qp->pd, mad_recv_wc->wc,
@@ -385,27 +393,40 @@ static int cm_alloc_response_msg(struct cm_port *port,
 	if (IS_ERR(ah))
 		return PTR_ERR(ah);
 
-	m = ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
-			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC,
-			       IB_MGMT_BASE_VERSION);
-	if (IS_ERR(m)) {
-		rdma_destroy_ah(ah);
-		return PTR_ERR(m);
-	}
-	m->ah = ah;
-	*msg = m;
+	msg->ah = ah;
 	return 0;
 }
 
 static void cm_free_msg(struct ib_mad_send_buf *msg)
 {
-	rdma_destroy_ah(msg->ah);
+	if (msg->ah)
+		rdma_destroy_ah(msg->ah);
 	if (msg->context[0])
 		cm_deref_id(msg->context[0]);
 	ib_free_send_mad(msg);
 }
 
+static int cm_alloc_response_msg(struct cm_port *port,
+				 struct ib_mad_recv_wc *mad_recv_wc,
+				 struct ib_mad_send_buf **msg)
+{
+	struct ib_mad_send_buf *m;
+	int ret;
+
+	m = cm_alloc_response_msg_no_ah(port, mad_recv_wc);
+	if (IS_ERR(m))
+		return PTR_ERR(m);
+
+	ret = cm_create_response_msg_ah(port, mad_recv_wc, m);
+	if (ret) {
+		cm_free_msg(m);
+		return ret;
+	}
+
+	*msg = m;
+	return 0;
+}
+
 static void * cm_copy_private_data(const void *private_data,
 				   u8 private_data_len)
 {
@@ -2497,7 +2518,8 @@ static int cm_dreq_handler(struct cm_work *work)
 	case IB_CM_TIMEWAIT:
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_DREQ_COUNTER]);
-		if (cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg))
+		msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
+		if (IS_ERR(msg))
 			goto unlock;
 
 		cm_format_drep((struct cm_drep_msg *) msg->mad, cm_id_priv,
@@ -2505,7 +2527,8 @@ static int cm_dreq_handler(struct cm_work *work)
 			       cm_id_priv->private_data_len);
 		spin_unlock_irq(&cm_id_priv->lock);
 
-		if (ib_post_send_mad(msg, NULL))
+		if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
+		    ib_post_send_mad(msg, NULL))
 			cm_free_msg(msg);
 		goto deref;
 	case IB_CM_DREQ_RCVD:
@@ -3083,7 +3106,8 @@ static int cm_lap_handler(struct cm_work *work)
 	case IB_CM_MRA_LAP_SENT:
 		atomic_long_inc(&work->port->counter_group[CM_RECV_DUPLICATES].
 				counter[CM_LAP_COUNTER]);
-		if (cm_alloc_response_msg(work->port, work->mad_recv_wc, &msg))
+		msg = cm_alloc_response_msg_no_ah(work->port, work->mad_recv_wc);
+		if (IS_ERR(msg))
 			goto unlock;
 
 		cm_format_mra((struct cm_mra_msg *) msg->mad, cm_id_priv,
@@ -3093,7 +3117,8 @@ static int cm_lap_handler(struct cm_work *work)
 			      cm_id_priv->private_data_len);
 		spin_unlock_irq(&cm_id_priv->lock);
 
-		if (ib_post_send_mad(msg, NULL))
+		if (cm_create_response_msg_ah(work->port, work->mad_recv_wc, msg) ||
+		    ib_post_send_mad(msg, NULL))
 			cm_free_msg(msg);
 		goto deref;
 	case IB_CM_LAP_RCVD:
-- 
cgit v1.2.3-59-g8ed1b


From 79364227e6b4923478e99d8480d62482b588ef84 Mon Sep 17 00:00:00 2001
From: Roland Dreier <roland@purestorage.com>
Date: Tue, 29 Aug 2017 10:34:44 -0700
Subject: IB/core: Add might_sleep() annotation to ib_init_ah_from_wc()

For RoCE, ib_init_ah_from_wc() can follow the path

    ib_init_ah_from_wc() ->
      rdma_addr_find_l2_eth_by_grh() ->
        rdma_resolve_ip()

and rdma_resolve_ip() will sleep in kzalloc() and wait_for_completion().

However, developers will not see any warnings if they use ib_init_ah_from_wc()
in an atomic context and test only on IB, because the function doesn't
sleep in that case.

Add a might_sleep() so that lockdep will catch bugs no matter what hardware is
used to test.

Signed-off-by: Roland Dreier <roland@purestorage.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/verbs.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index ecb6c395f19b..ee9e27dc799b 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -468,6 +468,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
 	union ib_gid dgid;
 	union ib_gid sgid;
 
+	might_sleep();
+
 	memset(ah_attr, 0, sizeof *ah_attr);
 	ah_attr->type = rdma_ah_find_type(device, port_num);
 	if (rdma_cap_eth_ah(device, port_num)) {
-- 
cgit v1.2.3-59-g8ed1b


From fac9658cabb98afb68ef1630c558864e6f559c07 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:06:57 +0300
Subject: IB/core: Add new ioctl interface

In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.

Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.

For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.

Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.

When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.

Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR

If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.

 objects
+--------+
|        |
|        |   methods                                                                +--------+
|        |   ns         method      method_spec                           +-----+   |len     |
+--------+  +------+[d]+-------+   +----------------+[d]+------------+    |attr1+-> |type    |
| object +> |method+-> | spec  +-> +  attr_buckets  +-> |default_chain+--> +-----+   |idr_type|
+--------+  +------+   |handler|   |                |   +------------+    |attr2|   |access  |
|        |  |      |   +-------+   +----------------+   |driver chain|    +-----+   +--------+
|        |  |      |                                    +------------+
|        |  +------+
|        |
|        |
|        |
|        |
|        |
|        |
|        |
|        |
|        |
|        |
+--------+

[d] = Hash ids to groups using the high order bits

The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.

Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
               struct uverbs_attr_bundle *ctx);

ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:

 ctx                               core
+----------------------------+     +------------+
| core:                      +---> | valid      |
+----------------------------+     | cmd_attr   |
| driver:                    |     +------------+
|----------------------------+--+  | valid      |
                                |  | cmd_attr   |
                                |  +------------+
                                |  | valid      |
                                |  | obj_attr   |
                                |  +------------+
                                |
                                |  drivers
                                |  +------------+
                                +> | valid      |
                                   | cmd_attr   |
                                   +------------+
                                   | valid      |
                                   | cmd_attr   |
                                   +------------+
                                   | valid      |
                                   | obj_attr   |
                                   +------------+

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/Makefile       |   2 +-
 drivers/infiniband/core/rdma_core.c    |  46 +++++
 drivers/infiniband/core/rdma_core.h    |   5 +
 drivers/infiniband/core/uverbs_ioctl.c | 364 +++++++++++++++++++++++++++++++++
 include/rdma/ib_verbs.h                |   2 +
 include/rdma/uverbs_ioctl.h            | 101 ++++++++-
 include/uapi/rdma/rdma_user_ioctl.h    |  33 +++
 7 files changed, 543 insertions(+), 10 deletions(-)
 create mode 100644 drivers/infiniband/core/uverbs_ioctl.c

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 920609a0872e..746756dc9877 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -32,4 +32,4 @@ ib_umad-y :=			user_mad.o
 ib_ucm-y :=			ucm.o
 
 ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
-				rdma_core.o uverbs_std_types.o
+				rdma_core.o uverbs_std_types.o uverbs_ioctl.o
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 0fe8ef913387..2a2f002ac7cb 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -36,10 +36,56 @@
 #include <rdma/uverbs_types.h>
 #include <linux/rcupdate.h>
 #include <rdma/uverbs_ioctl.h>
+#include <rdma/rdma_user_ioctl.h>
 #include "uverbs.h"
 #include "core_priv.h"
 #include "rdma_core.h"
 
+int uverbs_ns_idx(u16 *id, unsigned int ns_count)
+{
+	int ret = (*id & UVERBS_ID_NS_MASK) >> UVERBS_ID_NS_SHIFT;
+
+	if (ret >= ns_count)
+		return -EINVAL;
+
+	*id &= ~UVERBS_ID_NS_MASK;
+	return ret;
+}
+
+const struct uverbs_object_spec *uverbs_get_object(const struct ib_device *ibdev,
+						   uint16_t object)
+{
+	const struct uverbs_root_spec *object_hash = ibdev->specs_root;
+	const struct uverbs_object_spec_hash *objects;
+	int ret = uverbs_ns_idx(&object, object_hash->num_buckets);
+
+	if (ret < 0)
+		return NULL;
+
+	objects = object_hash->object_buckets[ret];
+
+	if (object >= objects->num_objects)
+		return NULL;
+
+	return objects->objects[object];
+}
+
+const struct uverbs_method_spec *uverbs_get_method(const struct uverbs_object_spec *object,
+						   uint16_t method)
+{
+	const struct uverbs_method_spec_hash *methods;
+	int ret = uverbs_ns_idx(&method, object->num_buckets);
+
+	if (ret < 0)
+		return NULL;
+
+	methods = object->method_buckets[ret];
+	if (method >= methods->num_methods)
+		return NULL;
+
+	return methods->methods[method];
+}
+
 void uverbs_uobject_get(struct ib_uobject *uobject)
 {
 	kref_get(&uobject->ref);
diff --git a/drivers/infiniband/core/rdma_core.h b/drivers/infiniband/core/rdma_core.h
index 9ed6ad0324c7..1efcf93238dd 100644
--- a/drivers/infiniband/core/rdma_core.h
+++ b/drivers/infiniband/core/rdma_core.h
@@ -43,6 +43,11 @@
 #include <rdma/ib_verbs.h>
 #include <linux/mutex.h>
 
+int uverbs_ns_idx(u16 *id, unsigned int ns_count);
+const struct uverbs_object_spec *uverbs_get_object(const struct ib_device *ibdev,
+						   uint16_t object);
+const struct uverbs_method_spec *uverbs_get_method(const struct uverbs_object_spec *object,
+						   uint16_t method);
 /*
  * These functions initialize the context and cleanups its uobjects.
  * The context has a list of objects which is protected by a mutex
diff --git a/drivers/infiniband/core/uverbs_ioctl.c b/drivers/infiniband/core/uverbs_ioctl.c
new file mode 100644
index 000000000000..5286ad57d903
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_ioctl.c
@@ -0,0 +1,364 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <rdma/rdma_user_ioctl.h>
+#include <rdma/uverbs_ioctl.h>
+#include "rdma_core.h"
+#include "uverbs.h"
+
+static int uverbs_process_attr(struct ib_device *ibdev,
+			       struct ib_ucontext *ucontext,
+			       const struct ib_uverbs_attr *uattr,
+			       u16 attr_id,
+			       const struct uverbs_attr_spec_hash *attr_spec_bucket,
+			       struct uverbs_attr_bundle_hash *attr_bundle_h,
+			       struct ib_uverbs_attr __user *uattr_ptr)
+{
+	const struct uverbs_attr_spec *spec;
+	struct uverbs_attr *e;
+	const struct uverbs_object_spec *object;
+	struct uverbs_obj_attr *o_attr;
+	struct uverbs_attr *elements = attr_bundle_h->attrs;
+
+	if (uattr->reserved)
+		return -EINVAL;
+
+	if (attr_id >= attr_spec_bucket->num_attrs) {
+		if (uattr->flags & UVERBS_ATTR_F_MANDATORY)
+			return -EINVAL;
+		else
+			return 0;
+	}
+
+	spec = &attr_spec_bucket->attrs[attr_id];
+	e = &elements[attr_id];
+	e->uattr = uattr_ptr;
+
+	switch (spec->type) {
+	case UVERBS_ATTR_TYPE_PTR_IN:
+	case UVERBS_ATTR_TYPE_PTR_OUT:
+		if (uattr->len < spec->len ||
+		    (!(spec->flags & UVERBS_ATTR_SPEC_F_MIN_SZ) &&
+		     uattr->len > spec->len))
+			return -EINVAL;
+
+		e->ptr_attr.data = uattr->data;
+		e->ptr_attr.len = uattr->len;
+		e->ptr_attr.flags = uattr->flags;
+		break;
+
+	case UVERBS_ATTR_TYPE_IDR:
+		if (uattr->data >> 32)
+			return -EINVAL;
+	/* fall through */
+	case UVERBS_ATTR_TYPE_FD:
+		if (uattr->len != 0 || !ucontext || uattr->data > INT_MAX)
+			return -EINVAL;
+
+		o_attr = &e->obj_attr;
+		object = uverbs_get_object(ibdev, spec->obj.obj_type);
+		if (!object)
+			return -EINVAL;
+		o_attr->type = object->type_attrs;
+
+		o_attr->id = (int)uattr->data;
+		o_attr->uobject = uverbs_get_uobject_from_context(
+					o_attr->type,
+					ucontext,
+					spec->obj.access,
+					o_attr->id);
+
+		if (IS_ERR(o_attr->uobject))
+			return PTR_ERR(o_attr->uobject);
+
+		if (spec->obj.access == UVERBS_ACCESS_NEW) {
+			u64 id = o_attr->uobject->id;
+
+			/* Copy the allocated id to the user-space */
+			if (put_user(id, &e->uattr->data)) {
+				uverbs_finalize_object(o_attr->uobject,
+						       UVERBS_ACCESS_NEW,
+						       false);
+				return -EFAULT;
+			}
+		}
+
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	set_bit(attr_id, attr_bundle_h->valid_bitmap);
+	return 0;
+}
+
+static int uverbs_uattrs_process(struct ib_device *ibdev,
+				 struct ib_ucontext *ucontext,
+				 const struct ib_uverbs_attr *uattrs,
+				 size_t num_uattrs,
+				 const struct uverbs_method_spec *method,
+				 struct uverbs_attr_bundle *attr_bundle,
+				 struct ib_uverbs_attr __user *uattr_ptr)
+{
+	size_t i;
+	int ret = 0;
+	int num_given_buckets = 0;
+
+	for (i = 0; i < num_uattrs; i++) {
+		const struct ib_uverbs_attr *uattr = &uattrs[i];
+		u16 attr_id = uattr->attr_id;
+		struct uverbs_attr_spec_hash *attr_spec_bucket;
+
+		ret = uverbs_ns_idx(&attr_id, method->num_buckets);
+		if (ret < 0) {
+			if (uattr->flags & UVERBS_ATTR_F_MANDATORY) {
+				uverbs_finalize_objects(attr_bundle,
+							method->attr_buckets,
+							num_given_buckets,
+							false);
+				return ret;
+			}
+			continue;
+		}
+
+		/*
+		 * ret is the found ns, so increase num_given_buckets if
+		 * necessary.
+		 */
+		if (ret >= num_given_buckets)
+			num_given_buckets = ret + 1;
+
+		attr_spec_bucket = method->attr_buckets[ret];
+		ret = uverbs_process_attr(ibdev, ucontext, uattr, attr_id,
+					  attr_spec_bucket, &attr_bundle->hash[ret],
+					  uattr_ptr++);
+		if (ret) {
+			uverbs_finalize_objects(attr_bundle,
+						method->attr_buckets,
+						num_given_buckets,
+						false);
+			return ret;
+		}
+	}
+
+	return num_given_buckets;
+}
+
+static int uverbs_validate_kernel_mandatory(const struct uverbs_method_spec *method_spec,
+					    struct uverbs_attr_bundle *attr_bundle)
+{
+	unsigned int i;
+
+	for (i = 0; i < attr_bundle->num_buckets; i++) {
+		struct uverbs_attr_spec_hash *attr_spec_bucket =
+			method_spec->attr_buckets[i];
+
+		if (!bitmap_subset(attr_spec_bucket->mandatory_attrs_bitmask,
+				   attr_bundle->hash[i].valid_bitmap,
+				   attr_spec_bucket->num_attrs))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int uverbs_handle_method(struct ib_uverbs_attr __user *uattr_ptr,
+				const struct ib_uverbs_attr *uattrs,
+				size_t num_uattrs,
+				struct ib_device *ibdev,
+				struct ib_uverbs_file *ufile,
+				const struct uverbs_method_spec *method_spec,
+				struct uverbs_attr_bundle *attr_bundle)
+{
+	int ret;
+	int finalize_ret;
+	int num_given_buckets;
+
+	num_given_buckets = uverbs_uattrs_process(ibdev, ufile->ucontext, uattrs,
+						  num_uattrs, method_spec,
+						  attr_bundle, uattr_ptr);
+	if (num_given_buckets <= 0)
+		return -EINVAL;
+
+	attr_bundle->num_buckets = num_given_buckets;
+	ret = uverbs_validate_kernel_mandatory(method_spec, attr_bundle);
+	if (ret)
+		goto cleanup;
+
+	ret = method_spec->handler(ibdev, ufile, attr_bundle);
+cleanup:
+	finalize_ret = uverbs_finalize_objects(attr_bundle,
+					       method_spec->attr_buckets,
+					       attr_bundle->num_buckets,
+					       !ret);
+
+	return ret ? ret : finalize_ret;
+}
+
+#define UVERBS_OPTIMIZE_USING_STACK_SZ  256
+static long ib_uverbs_cmd_verbs(struct ib_device *ib_dev,
+				struct ib_uverbs_file *file,
+				struct ib_uverbs_ioctl_hdr *hdr,
+				void __user *buf)
+{
+	const struct uverbs_object_spec *object_spec;
+	const struct uverbs_method_spec *method_spec;
+	long err = 0;
+	unsigned int i;
+	struct {
+		struct ib_uverbs_attr		*uattrs;
+		struct uverbs_attr_bundle	*uverbs_attr_bundle;
+	} *ctx = NULL;
+	struct uverbs_attr *curr_attr;
+	unsigned long *curr_bitmap;
+	size_t ctx_size;
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	uintptr_t data[UVERBS_OPTIMIZE_USING_STACK_SZ / sizeof(uintptr_t)];
+#endif
+
+	if (hdr->reserved)
+		return -EINVAL;
+
+	object_spec = uverbs_get_object(ib_dev, hdr->object_id);
+	if (!object_spec)
+		return -EOPNOTSUPP;
+
+	method_spec = uverbs_get_method(object_spec, hdr->method_id);
+	if (!method_spec)
+		return -EOPNOTSUPP;
+
+	if ((method_spec->flags & UVERBS_ACTION_FLAG_CREATE_ROOT) ^ !file->ucontext)
+		return -EINVAL;
+
+	ctx_size = sizeof(*ctx) +
+		   sizeof(struct uverbs_attr_bundle) +
+		   sizeof(struct uverbs_attr_bundle_hash) * method_spec->num_buckets +
+		   sizeof(*ctx->uattrs) * hdr->num_attrs +
+		   sizeof(*ctx->uverbs_attr_bundle->hash[0].attrs) *
+		   method_spec->num_child_attrs +
+		   sizeof(*ctx->uverbs_attr_bundle->hash[0].valid_bitmap) *
+			(method_spec->num_child_attrs / BITS_PER_LONG +
+			 method_spec->num_buckets);
+
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	if (ctx_size <= UVERBS_OPTIMIZE_USING_STACK_SZ)
+		ctx = (void *)data;
+
+	if (!ctx)
+#endif
+	ctx = kmalloc(ctx_size, GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->uverbs_attr_bundle = (void *)ctx + sizeof(*ctx);
+	ctx->uattrs = (void *)(ctx->uverbs_attr_bundle + 1) +
+			      (sizeof(ctx->uverbs_attr_bundle->hash[0]) *
+			       method_spec->num_buckets);
+	curr_attr = (void *)(ctx->uattrs + hdr->num_attrs);
+	curr_bitmap = (void *)(curr_attr + method_spec->num_child_attrs);
+
+	/*
+	 * We just fill the pointers and num_attrs here. The data itself will be
+	 * filled at a later stage (uverbs_process_attr)
+	 */
+	for (i = 0; i < method_spec->num_buckets; i++) {
+		unsigned int curr_num_attrs = method_spec->attr_buckets[i]->num_attrs;
+
+		ctx->uverbs_attr_bundle->hash[i].attrs = curr_attr;
+		curr_attr += curr_num_attrs;
+		ctx->uverbs_attr_bundle->hash[i].num_attrs = curr_num_attrs;
+		ctx->uverbs_attr_bundle->hash[i].valid_bitmap = curr_bitmap;
+		bitmap_zero(curr_bitmap, curr_num_attrs);
+		curr_bitmap += BITS_TO_LONGS(curr_num_attrs);
+	}
+
+	err = copy_from_user(ctx->uattrs, buf,
+			     sizeof(*ctx->uattrs) * hdr->num_attrs);
+	if (err) {
+		err = -EFAULT;
+		goto out;
+	}
+
+	err = uverbs_handle_method(buf, ctx->uattrs, hdr->num_attrs, ib_dev,
+				   file, method_spec, ctx->uverbs_attr_bundle);
+out:
+#ifdef UVERBS_OPTIMIZE_USING_STACK_SZ
+	if (ctx_size > UVERBS_OPTIMIZE_USING_STACK_SZ)
+#endif
+	kfree(ctx);
+	return err;
+}
+
+#define IB_UVERBS_MAX_CMD_SZ 4096
+
+long ib_uverbs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	struct ib_uverbs_file *file = filp->private_data;
+	struct ib_uverbs_ioctl_hdr __user *user_hdr =
+		(struct ib_uverbs_ioctl_hdr __user *)arg;
+	struct ib_uverbs_ioctl_hdr hdr;
+	struct ib_device *ib_dev;
+	int srcu_key;
+	long err;
+
+	srcu_key = srcu_read_lock(&file->device->disassociate_srcu);
+	ib_dev = srcu_dereference(file->device->ib_dev,
+				  &file->device->disassociate_srcu);
+	if (!ib_dev) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (cmd == RDMA_VERBS_IOCTL) {
+		err = copy_from_user(&hdr, user_hdr, sizeof(hdr));
+
+		if (err || hdr.length > IB_UVERBS_MAX_CMD_SZ ||
+		    hdr.length != sizeof(hdr) + hdr.num_attrs * sizeof(struct ib_uverbs_attr)) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		if (hdr.reserved) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
+
+		err = ib_uverbs_cmd_verbs(ib_dev, file, &hdr,
+					  (__user void *)arg + sizeof(hdr));
+	} else {
+		err = -ENOIOCTLCMD;
+	}
+out:
+	srcu_read_unlock(&file->device->disassociate_srcu, srcu_key);
+
+	return err;
+}
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 1b4bb8743969..e6df68048517 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2348,6 +2348,8 @@ struct ib_device {
 	void (*get_dev_fw_str)(struct ib_device *, char *str);
 	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
 						     int comp_vector);
+
+	struct uverbs_root_spec		*specs_root;
 };
 
 struct ib_client {
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index d3ec02b7d937..f83f56329761 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -43,6 +43,8 @@
 
 enum uverbs_attr_type {
 	UVERBS_ATTR_TYPE_NA,
+	UVERBS_ATTR_TYPE_PTR_IN,
+	UVERBS_ATTR_TYPE_PTR_OUT,
 	UVERBS_ATTR_TYPE_IDR,
 	UVERBS_ATTR_TYPE_FD,
 };
@@ -54,29 +56,110 @@ enum uverbs_obj_access {
 	UVERBS_ACCESS_DESTROY
 };
 
+enum {
+	UVERBS_ATTR_SPEC_F_MANDATORY	= 1U << 0,
+	/* Support extending attributes by length */
+	UVERBS_ATTR_SPEC_F_MIN_SZ	= 1U << 1,
+};
+
 struct uverbs_attr_spec {
 	enum uverbs_attr_type		type;
-	struct {
-		/*
-		 * higher bits mean the namespace and lower bits mean
-		 * the type id within the namespace.
-		 */
-		u16			obj_type;
-		u8			access;
-	} obj;
+	union {
+		u16				len;
+		struct {
+			/*
+			 * higher bits mean the namespace and lower bits mean
+			 * the type id within the namespace.
+			 */
+			u16			obj_type;
+			u8			access;
+		} obj;
+	};
+	/* Combination of bits from enum UVERBS_ATTR_SPEC_F_XXXX */
+	u8				flags;
 };
 
 struct uverbs_attr_spec_hash {
 	size_t				num_attrs;
+	unsigned long			*mandatory_attrs_bitmask;
 	struct uverbs_attr_spec		attrs[0];
 };
 
+struct uverbs_attr_bundle;
+struct ib_uverbs_file;
+
+enum {
+	/*
+	 * Action marked with this flag creates a context (or root for all
+	 * objects).
+	 */
+	UVERBS_ACTION_FLAG_CREATE_ROOT = 1U << 0,
+};
+
+struct uverbs_method_spec {
+	/* Combination of bits from enum UVERBS_ACTION_FLAG_XXXX */
+	u32						flags;
+	size_t						num_buckets;
+	size_t						num_child_attrs;
+	int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
+		       struct uverbs_attr_bundle *ctx);
+	struct uverbs_attr_spec_hash		*attr_buckets[0];
+};
+
+struct uverbs_method_spec_hash {
+	size_t					num_methods;
+	struct uverbs_method_spec		*methods[0];
+};
+
+struct uverbs_object_spec {
+	const struct uverbs_obj_type		*type_attrs;
+	size_t					num_buckets;
+	struct uverbs_method_spec_hash		*method_buckets[0];
+};
+
+struct uverbs_object_spec_hash {
+	size_t					num_objects;
+	struct uverbs_object_spec		*objects[0];
+};
+
+struct uverbs_root_spec {
+	size_t					num_buckets;
+	struct uverbs_object_spec_hash		*object_buckets[0];
+};
+
+/* =================================================
+ *              Parsing infrastructure
+ * =================================================
+ */
+
+struct uverbs_ptr_attr {
+	union {
+		u64		data;
+		void	__user *ptr;
+	};
+	u16		len;
+	/* Combination of bits from enum UVERBS_ATTR_F_XXXX */
+	u16		flags;
+};
+
 struct uverbs_obj_attr {
+	/* pointer to the kernel descriptor -> type, access, etc */
+	const struct uverbs_obj_type	*type;
 	struct ib_uobject		*uobject;
+	/* fd or id in idr of this object */
+	int				id;
 };
 
 struct uverbs_attr {
-	struct uverbs_obj_attr	obj_attr;
+	/*
+	 * pointer to the user-space given attribute, in order to write the
+	 * new uobject's id or update flags.
+	 */
+	struct ib_uverbs_attr __user	*uattr;
+	union {
+		struct uverbs_ptr_attr	ptr_attr;
+		struct uverbs_obj_attr	obj_attr;
+	};
 };
 
 struct uverbs_attr_bundle_hash {
diff --git a/include/uapi/rdma/rdma_user_ioctl.h b/include/uapi/rdma/rdma_user_ioctl.h
index 9388125ad51b..165a27e969d5 100644
--- a/include/uapi/rdma/rdma_user_ioctl.h
+++ b/include/uapi/rdma/rdma_user_ioctl.h
@@ -43,6 +43,39 @@
 /* Legacy name, for user space application which already use it */
 #define IB_IOCTL_MAGIC		RDMA_IOCTL_MAGIC
 
+#define RDMA_VERBS_IOCTL \
+	_IOWR(RDMA_IOCTL_MAGIC, 1, struct ib_uverbs_ioctl_hdr)
+
+#define UVERBS_ID_NS_MASK 0xF000
+#define UVERBS_ID_NS_SHIFT 12
+
+enum {
+	/* User input */
+	UVERBS_ATTR_F_MANDATORY = 1U << 0,
+	/*
+	 * Valid output bit should be ignored and considered set in
+	 * mandatory fields. This bit is kernel output.
+	 */
+	UVERBS_ATTR_F_VALID_OUTPUT = 1U << 1,
+};
+
+struct ib_uverbs_attr {
+	__u16 attr_id;		/* command specific type attribute */
+	__u16 len;		/* only for pointers */
+	__u16 flags;		/* combination of UVERBS_ATTR_F_XXXX */
+	__u16 reserved;
+	__u64 data;		/* ptr to command, inline data or idr/fd */
+};
+
+struct ib_uverbs_ioctl_hdr {
+	__u16 length;
+	__u16 object_id;
+	__u16 method_id;
+	__u16 num_attrs;
+	__u64 reserved;
+	struct ib_uverbs_attr  attrs[0];
+};
+
 /*
  * General blocks assignments
  * It is closed on purpose do not expose it it user space
-- 
cgit v1.2.3-59-g8ed1b


From 5009010fbf54bdc27e57baca490e1f9d6a4609e0 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:06:58 +0300
Subject: IB/core: Declare an object instead of declaring only type attributes

Switch all uverbs_type_attrs_xxxx with DECLARE_UVERBS_OBJECT
macros. This will be later used in order to embed the object
specific methods in the objects as well.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_std_types.c | 112 +++++++++++++----------------
 include/rdma/uverbs_ioctl.h                |  16 +++++
 include/rdma/uverbs_std_types.h            |  40 +++++------
 include/rdma/uverbs_types.h                |  38 ++++++----
 4 files changed, 107 insertions(+), 99 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index ef293379f37a..b75c7da0d0a4 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -209,67 +209,51 @@ static int uverbs_hot_unplug_completion_event_file(struct ib_uobject_file *uobj_
 	return 0;
 };
 
-const struct uverbs_obj_fd_type uverbs_type_attrs_comp_channel = {
-	.type = UVERBS_TYPE_ALLOC_FD(sizeof(struct ib_uverbs_completion_event_file), 0),
-	.context_closed = uverbs_hot_unplug_completion_event_file,
-	.fops = &uverbs_event_fops,
-	.name = "[infinibandevent]",
-	.flags = O_RDONLY,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_cq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_ucq_object), 0),
-	.destroy_object = uverbs_free_cq,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_qp = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uqp_object), 0),
-	.destroy_object = uverbs_free_qp,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_mw = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_mw,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_mr = {
-	/* 1 is used in order to free the MR after all the MWs */
-	.type = UVERBS_TYPE_ALLOC_IDR(1),
-	.destroy_object = uverbs_free_mr,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_srq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_usrq_object), 0),
-	.destroy_object = uverbs_free_srq,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_ah = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_ah,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_flow = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_flow,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_wq = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uwq_object), 0),
-	.destroy_object = uverbs_free_wq,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_rwq_ind_table = {
-	.type = UVERBS_TYPE_ALLOC_IDR(0),
-	.destroy_object = uverbs_free_rwq_ind_tbl,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_xrcd = {
-	.type = UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uxrcd_object), 0),
-	.destroy_object = uverbs_free_xrcd,
-};
-
-const struct uverbs_obj_idr_type uverbs_type_attrs_pd = {
-	/* 2 is used in order to free the PD after MRs */
-	.type = UVERBS_TYPE_ALLOC_IDR(2),
-	.destroy_object = uverbs_free_pd,
-};
+DECLARE_UVERBS_OBJECT(uverbs_object_comp_channel,
+		      UVERBS_OBJECT_COMP_CHANNEL,
+		      &UVERBS_TYPE_ALLOC_FD(0,
+					      sizeof(struct ib_uverbs_completion_event_file),
+					      uverbs_hot_unplug_completion_event_file,
+					      &uverbs_event_fops,
+					      "[infinibandevent]", O_RDONLY));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_cq, UVERBS_OBJECT_CQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_ucq_object), 0,
+						  uverbs_free_cq));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_qp, UVERBS_OBJECT_QP,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uqp_object), 0,
+						  uverbs_free_qp));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_mw, UVERBS_OBJECT_MW,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_mw));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_mr, UVERBS_OBJECT_MR,
+		      /* 1 is used in order to free the MR after all the MWs */
+		      &UVERBS_TYPE_ALLOC_IDR(1, uverbs_free_mr));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_srq, UVERBS_OBJECT_SRQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_usrq_object), 0,
+						  uverbs_free_srq));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_ah, UVERBS_OBJECT_AH,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_ah));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_flow, UVERBS_OBJECT_FLOW,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_flow));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_wq, UVERBS_OBJECT_WQ,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uwq_object), 0,
+						  uverbs_free_wq));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_rwq_ind_table,
+		      UVERBS_OBJECT_RWQ_IND_TBL,
+		      &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_rwq_ind_tbl));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_xrcd, UVERBS_OBJECT_XRCD,
+		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uxrcd_object), 0,
+						  uverbs_free_xrcd));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_pd, UVERBS_OBJECT_PD,
+		      /* 2 is used in order to free the PD after MRs */
+		      &UVERBS_TYPE_ALLOC_IDR(2, uverbs_free_pd));
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index f83f56329761..99130083615e 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -127,6 +127,22 @@ struct uverbs_root_spec {
 	struct uverbs_object_spec_hash		*object_buckets[0];
 };
 
+/*
+ * =======================================
+ *	Verbs definitions
+ * =======================================
+ */
+
+struct uverbs_object_def {
+	const struct uverbs_obj_type	        *type_attrs;
+};
+
+#define _UVERBS_OBJECT(_id, _type_attrs, ...)				\
+	((const struct uverbs_object_def) {				\
+	 .type_attrs = _type_attrs})
+#define DECLARE_UVERBS_OBJECT(_name, _id, _type_attrs, ...)		\
+	const struct uverbs_object_def _name =				\
+		_UVERBS_OBJECT(_id, _type_attrs, ##__VA_ARGS__)
 /* =================================================
  *              Parsing infrastructure
  * =================================================
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 7771ce966952..eda271b4aa6c 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -35,18 +35,18 @@
 
 #include <rdma/uverbs_types.h>
 
-extern const struct uverbs_obj_fd_type uverbs_type_attrs_comp_channel;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_cq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_qp;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_rwq_ind_table;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_wq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_srq;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_ah;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_flow;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_mr;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_mw;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_pd;
-extern const struct uverbs_obj_idr_type uverbs_type_attrs_xrcd;
+extern const struct uverbs_object_def uverbs_object_comp_channel;
+extern const struct uverbs_object_def uverbs_object_cq;
+extern const struct uverbs_object_def uverbs_object_qp;
+extern const struct uverbs_object_def uverbs_object_rwq_ind_table;
+extern const struct uverbs_object_def uverbs_object_wq;
+extern const struct uverbs_object_def uverbs_object_srq;
+extern const struct uverbs_object_def uverbs_object_ah;
+extern const struct uverbs_object_def uverbs_object_flow;
+extern const struct uverbs_object_def uverbs_object_mr;
+extern const struct uverbs_object_def uverbs_object_mw;
+extern const struct uverbs_object_def uverbs_object_pd;
+extern const struct uverbs_object_def uverbs_object_xrcd;
 
 static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 					    bool write,
@@ -56,22 +56,22 @@ static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 	return rdma_lookup_get_uobject(type, ucontext, id, write);
 }
 
-#define uobj_get_type(_type) uverbs_type_attrs_##_type.type
+#define uobj_get_type(_object) uverbs_object_##_object.type_attrs
 
 #define uobj_get_read(_type, _id, _ucontext)				\
-	 __uobj_get(&(_type), false, _ucontext, _id)
+	 __uobj_get(_type, false, _ucontext, _id)
 
-#define uobj_get_obj_read(_type, _id, _ucontext)			\
+#define uobj_get_obj_read(_object, _id, _ucontext)			\
 ({									\
-	struct ib_uobject *uobj =					\
-		__uobj_get(&uobj_get_type(_type),			\
+	struct ib_uobject *__uobj =					\
+		__uobj_get(uverbs_object_##_object.type_attrs,		\
 			   false, _ucontext, _id);			\
 									\
-	(struct ib_##_type *)(IS_ERR(uobj) ? NULL : uobj->object);	\
+	(struct ib_##_object *)(IS_ERR(__uobj) ? NULL : __uobj->object);\
 })
 
 #define uobj_get_write(_type, _id, _ucontext)				\
-	 __uobj_get(&(_type), true, _ucontext, _id)
+	 __uobj_get(_type, true, _ucontext, _id)
 
 static inline void uobj_put_read(struct ib_uobject *uobj)
 {
@@ -108,7 +108,7 @@ static inline struct ib_uobject *__uobj_alloc(const struct uverbs_obj_type *type
 }
 
 #define uobj_alloc(_type, ucontext)	\
-	__uobj_alloc(&(_type), ucontext)
+	__uobj_alloc(_type, ucontext)
 
 #endif
 
diff --git a/include/rdma/uverbs_types.h b/include/rdma/uverbs_types.h
index 351ea185df44..9760b6d70744 100644
--- a/include/rdma/uverbs_types.h
+++ b/include/rdma/uverbs_types.h
@@ -151,22 +151,30 @@ extern const struct uverbs_obj_type_class uverbs_fd_class;
 
 #define UVERBS_BUILD_BUG_ON(cond) (sizeof(char[1 - 2 * !!(cond)]) -	\
 				   sizeof(char))
-#define UVERBS_TYPE_ALLOC_FD(_size, _order)				 \
-	{								 \
-		.destroy_order = _order,				 \
-		.type_class = &uverbs_fd_class,				 \
-		.obj_size = (_size) +					 \
-			  UVERBS_BUILD_BUG_ON((_size) <			 \
-					      sizeof(struct ib_uobject_file)),\
-	}
-#define UVERBS_TYPE_ALLOC_IDR_SZ(_size, _order)				\
-	{								\
+#define UVERBS_TYPE_ALLOC_FD(_order, _obj_size, _context_closed, _fops, _name, _flags)\
+	((&((const struct uverbs_obj_fd_type)				\
+	 {.type = {							\
+		.destroy_order = _order,				\
+		.type_class = &uverbs_fd_class,				\
+		.obj_size = (_obj_size) +				\
+			UVERBS_BUILD_BUG_ON((_obj_size) < sizeof(struct ib_uobject_file)), \
+	 },								\
+	 .context_closed = _context_closed,				\
+	 .fops = _fops,							\
+	 .name = _name,							\
+	 .flags = _flags}))->type)
+#define UVERBS_TYPE_ALLOC_IDR_SZ(_size, _order, _destroy_object)	\
+	((&((const struct uverbs_obj_idr_type)				\
+	 {.type = {							\
 		.destroy_order = _order,				\
 		.type_class = &uverbs_idr_class,			\
 		.obj_size = (_size) +					\
-			  UVERBS_BUILD_BUG_ON((_size) <			\
-					      sizeof(struct ib_uobject)), \
-	}
-#define UVERBS_TYPE_ALLOC_IDR(_order)					\
-	 UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uobject), _order)
+			UVERBS_BUILD_BUG_ON((_size) <			\
+					    sizeof(struct ib_uobject))	\
+	 },								\
+	 .destroy_object = _destroy_object,}))->type)
+#define UVERBS_TYPE_ALLOC_IDR(_order, _destroy_object)			\
+	 UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uobject), _order,	\
+				  _destroy_object)
+
 #endif
-- 
cgit v1.2.3-59-g8ed1b


From 09e3ebf8c193d3f154c4ffb7cb18995df0243bc6 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:06:59 +0300
Subject: IB/core: Add DEVICE object and root tree structure

This adds the DEVICE object. This object supports creating the context
that all objects are created from. Moreover, it supports executing
methods which are related to the device itself, such as QUERY_DEVICE.
This is a singleton object (per file instance).

All standard objects are put in the root structure. This root will later
on be used in drivers as the source for their whole parsing tree.
Later on, when new features are added, these drivers could mix this root
with other customized objects.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_std_types.c | 17 +++++++++++++++
 include/rdma/uverbs_ioctl.h                | 35 ++++++++++++++++++++++++++++++
 include/rdma/uverbs_std_types.h            | 18 +++++++++++++++
 3 files changed, 70 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index b75c7da0d0a4..5f90978bda8d 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -257,3 +257,20 @@ DECLARE_UVERBS_OBJECT(uverbs_object_xrcd, UVERBS_OBJECT_XRCD,
 DECLARE_UVERBS_OBJECT(uverbs_object_pd, UVERBS_OBJECT_PD,
 		      /* 2 is used in order to free the PD after MRs */
 		      &UVERBS_TYPE_ALLOC_IDR(2, uverbs_free_pd));
+
+DECLARE_UVERBS_OBJECT(uverbs_object_device, UVERBS_OBJECT_DEVICE, NULL);
+
+DECLARE_UVERBS_OBJECT_TREE(uverbs_default_objects,
+			   &uverbs_object_device,
+			   &uverbs_object_pd,
+			   &uverbs_object_mr,
+			   &uverbs_object_comp_channel,
+			   &uverbs_object_cq,
+			   &uverbs_object_qp,
+			   &uverbs_object_ah,
+			   &uverbs_object_mw,
+			   &uverbs_object_srq,
+			   &uverbs_object_flow,
+			   &uverbs_object_wq,
+			   &uverbs_object_rwq_ind_table,
+			   &uverbs_object_xrcd);
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 99130083615e..2e8925434d74 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -133,16 +133,51 @@ struct uverbs_root_spec {
  * =======================================
  */
 
+struct uverbs_attr_def {
+	u16                           id;
+	struct uverbs_attr_spec       attr;
+};
+
+struct uverbs_method_def {
+	u16                                  id;
+	/* Combination of bits from enum UVERBS_ACTION_FLAG_XXXX */
+	u32				     flags;
+	size_t				     num_attrs;
+	const struct uverbs_attr_def * const (*attrs)[];
+	int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
+		       struct uverbs_attr_bundle *ctx);
+};
+
 struct uverbs_object_def {
+	u16					 id;
 	const struct uverbs_obj_type	        *type_attrs;
+	size_t				         num_methods;
+	const struct uverbs_method_def * const (*methods)[];
+};
+
+struct uverbs_object_tree_def {
+	size_t					 num_objects;
+	const struct uverbs_object_def * const (*objects)[];
 };
 
 #define _UVERBS_OBJECT(_id, _type_attrs, ...)				\
 	((const struct uverbs_object_def) {				\
+	 .id = _id,							\
 	 .type_attrs = _type_attrs})
 #define DECLARE_UVERBS_OBJECT(_name, _id, _type_attrs, ...)		\
 	const struct uverbs_object_def _name =				\
 		_UVERBS_OBJECT(_id, _type_attrs, ##__VA_ARGS__)
+#define _UVERBS_TREE_OBJECTS_SZ(...)					\
+	(sizeof((const struct uverbs_object_def * const []){__VA_ARGS__}) / \
+	 sizeof(const struct uverbs_object_def *))
+#define _UVERBS_OBJECT_TREE(...)					\
+	((const struct uverbs_object_tree_def) {			\
+	 .num_objects = _UVERBS_TREE_OBJECTS_SZ(__VA_ARGS__),		\
+	 .objects = &(const struct uverbs_object_def * const []){__VA_ARGS__} })
+#define DECLARE_UVERBS_OBJECT_TREE(_name, ...)				\
+	const struct uverbs_object_tree_def _name =			\
+		_UVERBS_OBJECT_TREE(__VA_ARGS__)
+
 /* =================================================
  *              Parsing infrastructure
  * =================================================
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index eda271b4aa6c..bef74099b7c5 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -35,6 +35,23 @@
 
 #include <rdma/uverbs_types.h>
 
+enum uverbs_default_objects {
+	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
+	UVERBS_OBJECT_PD,
+	UVERBS_OBJECT_COMP_CHANNEL,
+	UVERBS_OBJECT_CQ,
+	UVERBS_OBJECT_QP,
+	UVERBS_OBJECT_SRQ,
+	UVERBS_OBJECT_AH,
+	UVERBS_OBJECT_MR,
+	UVERBS_OBJECT_MW,
+	UVERBS_OBJECT_FLOW,
+	UVERBS_OBJECT_XRCD,
+	UVERBS_OBJECT_RWQ_IND_TBL,
+	UVERBS_OBJECT_WQ,
+	UVERBS_OBJECT_LAST,
+};
+
 extern const struct uverbs_object_def uverbs_object_comp_channel;
 extern const struct uverbs_object_def uverbs_object_cq;
 extern const struct uverbs_object_def uverbs_object_qp;
@@ -47,6 +64,7 @@ extern const struct uverbs_object_def uverbs_object_mr;
 extern const struct uverbs_object_def uverbs_object_mw;
 extern const struct uverbs_object_def uverbs_object_pd;
 extern const struct uverbs_object_def uverbs_object_xrcd;
+extern const struct uverbs_object_def uverbs_object_device;
 
 static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 					    bool write,
-- 
cgit v1.2.3-59-g8ed1b


From 118620d3686b2d624f9a5019f2f14c64cf50d21a Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:00 +0300
Subject: IB/core: Add uverbs merge trees functionality

Different drivers support different features and even subset of the
common uverbs implementation. Currently, this is handled as bitmask
in every driver that represents which kind of methods it supports, but
doesn't go down to attributes granularity. Moreover, drivers might
want to add their specific types, methods and attributes to let
their user-space counter-parts be exposed to some more efficient
abstractions. It means that existence of different features is
validated syntactically via the parsing infrastructure rather than
using a complex in-handler logic.

In order to do that, we allow defining features and abstractions
as parsing trees. These per-feature parsing tree could be merged
to an efficient (perfect-hash based) parsing tree, which is later
used by the parsing infrastructure.

To sum it up, this makes a parse tree unique for a device and
represents only the features this particular device supports.
This is done by having a root specification tree per feature.
Before a device registers itself as an IB device, it merges
all these trees into one parsing tree. This parsing tree
is used to parse all user-space commands.

A future user-space application could read this parse tree. This
tree represents which objects, methods and attributes are
supported by this device.

This is based on the idea of
Jason Gunthorpe <jgunthorpe@obsidianresearch.com>

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/Makefile             |   3 +-
 drivers/infiniband/core/uverbs_ioctl_merge.c | 665 +++++++++++++++++++++++++++
 include/rdma/uverbs_ioctl.h                  |  40 +-
 3 files changed, 706 insertions(+), 2 deletions(-)
 create mode 100644 drivers/infiniband/core/uverbs_ioctl_merge.c

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 746756dc9877..b4df164f71a6 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -32,4 +32,5 @@ ib_umad-y :=			user_mad.o
 ib_ucm-y :=			ucm.o
 
 ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
-				rdma_core.o uverbs_std_types.o uverbs_ioctl.o
+				rdma_core.o uverbs_std_types.o uverbs_ioctl.o \
+				uverbs_ioctl_merge.o
diff --git a/drivers/infiniband/core/uverbs_ioctl_merge.c b/drivers/infiniband/core/uverbs_ioctl_merge.c
new file mode 100644
index 000000000000..76ddb6564578
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_ioctl_merge.c
@@ -0,0 +1,665 @@
+/*
+ * Copyright (c) 2017, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <rdma/uverbs_ioctl.h>
+#include <rdma/rdma_user_ioctl.h>
+#include <linux/bitops.h>
+#include "uverbs.h"
+
+#define UVERBS_NUM_NS (UVERBS_ID_NS_MASK >> UVERBS_ID_NS_SHIFT)
+#define GET_NS_ID(idx) (((idx) & UVERBS_ID_NS_MASK) >> UVERBS_ID_NS_SHIFT)
+#define GET_ID(idx) ((idx) & ~UVERBS_ID_NS_MASK)
+
+#define _for_each_element(elem, tmpi, tmpj, hashes, num_buckets_offset,	       \
+			  buckets_offset)				       \
+	for (tmpj = 0,							       \
+	     elem = (*(const void ***)((hashes)[tmpi] +			       \
+				       (buckets_offset)))[0];	               \
+	     tmpj < *(size_t *)((hashes)[tmpi] + (num_buckets_offset));        \
+	     tmpj++)						               \
+		if ((elem = ((*(const void ***)(hashes[tmpi] +		       \
+						(buckets_offset)))[tmpj])))
+
+/*
+ * Iterate all elements of a few @hashes. The number of given hashes is
+ * indicated by @num_hashes. The offset of the number of buckets in the hash is
+ * represented by @num_buckets_offset, while the offset of the buckets array in
+ * the hash structure is represented by @buckets_offset. tmpi and tmpj are two
+ * short (or int) based indices that are given by the user. tmpi iterates over
+ * the different hashes. @elem points the current element in the hashes[tmpi]
+ * bucket we are looping on. To be honest, @hashes representation isn't exactly
+ * a hash, but more a collection of elements. These elements' ids are treated
+ * in a hash like manner, where the first upper bits are the bucket number.
+ * These elements are later mapped into a perfect-hash.
+ */
+#define for_each_element(elem, tmpi, tmpj, hashes, num_hashes,                 \
+			 num_buckets_offset, buckets_offset)		       \
+	for (tmpi = 0; tmpi < (num_hashes); tmpi++)		               \
+		_for_each_element(elem, tmpi, tmpj, hashes, num_buckets_offset,\
+				  buckets_offset)
+
+#define get_elements_iterators_entry_above(iters, num_elements, elements,     \
+					  num_objects_fld, objects_fld, bucket,\
+					  min_id)			       \
+	get_elements_above_id((const void **)iters, num_elements,       \
+				     (const void **)(elements),		       \
+				     offsetof(typeof(**elements),	       \
+					      num_objects_fld),		       \
+				     offsetof(typeof(**elements), objects_fld),\
+				     offsetof(typeof(***(*elements)->objects_fld), id),\
+				     bucket, min_id)
+
+#define get_objects_above_id(iters, num_trees, trees, bucket, min_id)	       \
+	get_elements_iterators_entry_above(iters, num_trees, trees,	       \
+					   num_objects, objects, bucket, min_id)
+
+#define get_methods_above_id(method_iters, num_iters, iters, bucket, min_id)\
+	get_elements_iterators_entry_above(method_iters, num_iters, iters,     \
+					   num_methods, methods, bucket, min_id)
+
+#define get_attrs_above_id(attrs_iters, num_iters, iters, bucket, min_id)\
+	get_elements_iterators_entry_above(attrs_iters, num_iters, iters,      \
+					   num_attrs, attrs, bucket, min_id)
+
+/*
+ * get_elements_above_id get a few hashes represented by @elements and
+ * @num_elements. The hashes fields are described by @num_offset, @data_offset
+ * and @id_offset in the same way as required by for_each_element. The function
+ * returns an array of @iters, represents an array of elements in the hashes
+ * buckets, which their ids are the smallest ids in all hashes but are all
+ * larger than the id given by min_id. Elements are only added to the iters
+ * array if their id belongs to the bucket @bucket. The number of elements in
+ * the returned array is returned by the function. @min_id is also updated to
+ * reflect the new min_id of all elements in iters.
+ */
+static size_t get_elements_above_id(const void **iters,
+				    unsigned int num_elements,
+				    const void **elements,
+				    size_t num_offset,
+				    size_t data_offset,
+				    size_t id_offset,
+				    u16 bucket,
+				    short *min_id)
+{
+	size_t num_iters = 0;
+	short min = SHRT_MAX;
+	const void *elem;
+	int i, j, last_stored = -1;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) != bucket)
+			continue;
+
+		if (GET_ID(id) < *min_id ||
+		    (min != SHRT_MAX && GET_ID(id) > min))
+			continue;
+
+		/*
+		 * We first iterate all hashes represented by @elements. When
+		 * we do, we try to find an element @elem in the bucket @bucket
+		 * which its id is min. Since we can't ensure the user sorted
+		 * the elements in increasing order, we override this hash's
+		 * minimal id element we found, if a new element with a smaller
+		 * id was just found.
+		 */
+		iters[last_stored == i ? num_iters - 1 : num_iters++] = elem;
+		last_stored = i;
+		min = GET_ID(id);
+	}
+
+	/*
+	 * We only insert to our iters array an element, if its id is smaller
+	 * than all previous ids. Therefore, the final iters array is sorted so
+	 * that smaller ids are in the end of the array.
+	 * Therefore, we need to clean the beginning of the array to make sure
+	 * all ids of final elements are equal to min.
+	 */
+	for (i = num_iters - 1; i >= 0 &&
+	     GET_ID(*(u16 *)(iters[i] + id_offset)) == min; i--)
+		;
+
+	num_iters -= i + 1;
+	memmove(iters, iters + i + 1, sizeof(*iters) * num_iters);
+
+	*min_id = min;
+	return num_iters;
+}
+
+#define find_max_element_entry_id(num_elements, elements, num_objects_fld, \
+				  objects_fld, bucket)			   \
+	find_max_element_id(num_elements, (const void **)(elements),	   \
+			    offsetof(typeof(**elements), num_objects_fld),    \
+			    offsetof(typeof(**elements), objects_fld),	      \
+			    offsetof(typeof(***(*elements)->objects_fld), id),\
+			    bucket)
+
+static short find_max_element_ns_id(unsigned int num_elements,
+				    const void **elements,
+				    size_t num_offset,
+				    size_t data_offset,
+				    size_t id_offset)
+{
+	short max_ns = SHRT_MIN;
+	const void *elem;
+	int i, j;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) > max_ns)
+			max_ns = GET_NS_ID(id);
+	}
+
+	return max_ns;
+}
+
+static short find_max_element_id(unsigned int num_elements,
+				 const void **elements,
+				 size_t num_offset,
+				 size_t data_offset,
+				 size_t id_offset,
+				 u16 bucket)
+{
+	short max_id = SHRT_MIN;
+	const void *elem;
+	int i, j;
+
+	for_each_element(elem, i, j, elements, num_elements, num_offset,
+			 data_offset) {
+		u16 id = *(u16 *)(elem + id_offset);
+
+		if (GET_NS_ID(id) == bucket &&
+		    GET_ID(id) > max_id)
+			max_id = GET_ID(id);
+	}
+	return max_id;
+}
+
+#define find_max_element_entry_id(num_elements, elements, num_objects_fld,   \
+				  objects_fld, bucket)			      \
+	find_max_element_id(num_elements, (const void **)(elements),	      \
+			    offsetof(typeof(**elements), num_objects_fld),    \
+			    offsetof(typeof(**elements), objects_fld),	      \
+			    offsetof(typeof(***(*elements)->objects_fld), id),\
+			    bucket)
+
+#define find_max_element_ns_entry_id(num_elements, elements,		    \
+				     num_objects_fld, objects_fld)	    \
+	find_max_element_ns_id(num_elements, (const void **)(elements),	    \
+			      offsetof(typeof(**elements), num_objects_fld),\
+			      offsetof(typeof(**elements), objects_fld),    \
+			      offsetof(typeof(***(*elements)->objects_fld), id))
+
+/*
+ * find_max_xxxx_ns_id gets a few elements. Each element is described by an id
+ * which its upper bits represents a namespace. It finds the max namespace. This
+ * could be used in order to know how many buckets do we need to allocate. If no
+ * elements exist, SHRT_MIN is returned. Namespace represents here different
+ * buckets. The common example is "common bucket" and "driver bucket".
+ *
+ * find_max_xxxx_id gets a few elements and a bucket. Each element is described
+ * by an id which its upper bits represent a namespace. It returns the max id
+ * which is contained in the same namespace defined in @bucket. This could be
+ * used in order to know how many elements do we need to allocate in the bucket.
+ * If no elements exist, SHRT_MIN is returned.
+ */
+
+#define find_max_object_id(num_trees, trees, bucket)			\
+		find_max_element_entry_id(num_trees, trees, num_objects,\
+					  objects, bucket)
+#define find_max_object_ns_id(num_trees, trees)			\
+		find_max_element_ns_entry_id(num_trees, trees,		\
+					     num_objects, objects)
+
+#define find_max_method_id(num_iters, iters, bucket)			\
+		find_max_element_entry_id(num_iters, iters, num_methods,\
+					  methods, bucket)
+#define find_max_method_ns_id(num_iters, iters)			\
+		find_max_element_ns_entry_id(num_iters, iters,		\
+					     num_methods, methods)
+
+#define find_max_attr_id(num_iters, iters, bucket)			\
+		find_max_element_entry_id(num_iters, iters, num_attrs,  \
+					  attrs, bucket)
+#define find_max_attr_ns_id(num_iters, iters)				\
+		find_max_element_ns_entry_id(num_iters, iters,		\
+					     num_attrs, attrs)
+
+static void free_method(struct uverbs_method_spec *method)
+{
+	unsigned int i;
+
+	if (!method)
+		return;
+
+	for (i = 0; i < method->num_buckets; i++)
+		kfree(method->attr_buckets[i]);
+
+	kfree(method);
+}
+
+#define IS_ATTR_OBJECT(attr) ((attr)->type == UVERBS_ATTR_TYPE_IDR || \
+			      (attr)->type == UVERBS_ATTR_TYPE_FD)
+
+/*
+ * This function gets array of size @num_method_defs which contains pointers to
+ * method definitions @method_defs. The function allocates an
+ * uverbs_method_spec structure and initializes its number of buckets and the
+ * elements in buckets to the correct attributes. While doing that, it
+ * validates that there aren't conflicts between attributes of different
+ * method_defs.
+ */
+static struct uverbs_method_spec *build_method_with_attrs(const struct uverbs_method_def **method_defs,
+							  size_t num_method_defs)
+{
+	int bucket_idx;
+	int max_attr_buckets = 0;
+	size_t num_attr_buckets = 0;
+	int res = 0;
+	struct uverbs_method_spec *method = NULL;
+	const struct uverbs_attr_def **attr_defs;
+	unsigned int num_of_singularities = 0;
+
+	max_attr_buckets = find_max_attr_ns_id(num_method_defs, method_defs);
+	if (max_attr_buckets >= 0)
+		num_attr_buckets = max_attr_buckets + 1;
+
+	method = kzalloc(sizeof(*method) +
+			 num_attr_buckets * sizeof(*method->attr_buckets),
+			 GFP_KERNEL);
+	if (!method)
+		return ERR_PTR(-ENOMEM);
+
+	method->num_buckets = num_attr_buckets;
+	attr_defs = kcalloc(num_method_defs, sizeof(*attr_defs), GFP_KERNEL);
+	if (!attr_defs) {
+		res = -ENOMEM;
+		goto free_method;
+	}
+	for (bucket_idx = 0; bucket_idx < method->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		int attr_max_bucket = 0;
+		struct uverbs_attr_spec_hash *hash = NULL;
+
+		attr_max_bucket = find_max_attr_id(num_method_defs, method_defs,
+						   bucket_idx);
+		if (attr_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       ALIGN(sizeof(*hash->attrs) * (attr_max_bucket + 1),
+				     sizeof(long)) +
+			       BITS_TO_LONGS(attr_max_bucket) * sizeof(long),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+		hash->num_attrs = attr_max_bucket + 1;
+		method->num_child_attrs += hash->num_attrs;
+		hash->mandatory_attrs_bitmask = (void *)(hash + 1) +
+						 ALIGN(sizeof(*hash->attrs) *
+						       (attr_max_bucket + 1),
+						       sizeof(long));
+
+		method->attr_buckets[bucket_idx] = hash;
+
+		do {
+			size_t			 num_attr_defs;
+			struct uverbs_attr_spec	*attr;
+			bool attr_obj_with_special_access;
+
+			num_attr_defs =
+				get_attrs_above_id(attr_defs,
+						   num_method_defs,
+						   method_defs,
+						   bucket_idx,
+						   &min_id);
+			/* Last attr in bucket */
+			if (!num_attr_defs)
+				break;
+
+			if (num_attr_defs > 1) {
+				/*
+				 * We don't allow two attribute definitions for
+				 * the same attribute. This is usually a
+				 * programmer error. If required, it's better to
+				 * just add a new attribute to capture the new
+				 * semantics.
+				 */
+				res = -EEXIST;
+				goto free;
+			}
+
+			attr = &hash->attrs[min_id];
+			memcpy(attr, &attr_defs[0]->attr, sizeof(*attr));
+
+			attr_obj_with_special_access = IS_ATTR_OBJECT(attr) &&
+				   (attr->obj.access == UVERBS_ACCESS_NEW ||
+				    attr->obj.access == UVERBS_ACCESS_DESTROY);
+			num_of_singularities +=  !!attr_obj_with_special_access;
+			if (WARN(num_of_singularities > 1,
+				 "ib_uverbs: Method contains more than one object attr (%d) with new/destroy access\n",
+				 min_id) ||
+			    WARN(attr_obj_with_special_access &&
+				 !(attr->flags & UVERBS_ATTR_SPEC_F_MANDATORY),
+				 "ib_uverbs: Tried to merge attr (%d) but it's an object with new/destroy aceess but isn't mandatory\n",
+				 min_id) ||
+			    WARN(IS_ATTR_OBJECT(attr) &&
+				 attr->flags & UVERBS_ATTR_SPEC_F_MIN_SZ,
+				 "ib_uverbs: Tried to merge attr (%d) but it's an object with min_sz flag\n",
+				 min_id)) {
+				res = -EINVAL;
+				goto free;
+			}
+
+			if (attr->flags & UVERBS_ATTR_SPEC_F_MANDATORY)
+				set_bit(min_id, hash->mandatory_attrs_bitmask);
+			min_id++;
+
+		} while (1);
+	}
+	kfree(attr_defs);
+	return method;
+
+free:
+	kfree(attr_defs);
+free_method:
+	free_method(method);
+	return ERR_PTR(res);
+}
+
+static void free_object(struct uverbs_object_spec *object)
+{
+	unsigned int i, j;
+
+	if (!object)
+		return;
+
+	for (i = 0; i < object->num_buckets; i++) {
+		struct uverbs_method_spec_hash	*method_buckets =
+			object->method_buckets[i];
+
+		if (!method_buckets)
+			continue;
+
+		for (j = 0; j < method_buckets->num_methods; j++)
+			free_method(method_buckets->methods[j]);
+
+		kfree(method_buckets);
+	}
+
+	kfree(object);
+}
+
+/*
+ * This function gets array of size @num_object_defs which contains pointers to
+ * object definitions @object_defs. The function allocated an
+ * uverbs_object_spec structure and initialize its number of buckets and the
+ * elements in buckets to the correct methods. While doing that, it
+ * sorts out the correct relationship between conflicts in the same method.
+ */
+static struct uverbs_object_spec *build_object_with_methods(const struct uverbs_object_def **object_defs,
+							    size_t num_object_defs)
+{
+	u16 bucket_idx;
+	int max_method_buckets = 0;
+	u16 num_method_buckets = 0;
+	int res = 0;
+	struct uverbs_object_spec *object = NULL;
+	const struct uverbs_method_def **method_defs;
+
+	max_method_buckets = find_max_method_ns_id(num_object_defs, object_defs);
+	if (max_method_buckets >= 0)
+		num_method_buckets = max_method_buckets + 1;
+
+	object = kzalloc(sizeof(*object) +
+			 num_method_buckets *
+			 sizeof(*object->method_buckets), GFP_KERNEL);
+	if (!object)
+		return ERR_PTR(-ENOMEM);
+
+	object->num_buckets = num_method_buckets;
+	method_defs = kcalloc(num_object_defs, sizeof(*method_defs), GFP_KERNEL);
+	if (!method_defs) {
+		res = -ENOMEM;
+		goto free_object;
+	}
+
+	for (bucket_idx = 0; bucket_idx < object->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		int methods_max_bucket = 0;
+		struct uverbs_method_spec_hash *hash = NULL;
+
+		methods_max_bucket = find_max_method_id(num_object_defs, object_defs,
+							bucket_idx);
+		if (methods_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       sizeof(*hash->methods) * (methods_max_bucket + 1),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+
+		hash->num_methods = methods_max_bucket + 1;
+		object->method_buckets[bucket_idx] = hash;
+
+		do {
+			size_t				num_method_defs;
+			struct uverbs_method_spec	*method;
+			int i;
+
+			num_method_defs =
+				get_methods_above_id(method_defs,
+						     num_object_defs,
+						     object_defs,
+						     bucket_idx,
+						     &min_id);
+			/* Last method in bucket */
+			if (!num_method_defs)
+				break;
+
+			method = build_method_with_attrs(method_defs,
+							 num_method_defs);
+			if (IS_ERR(method)) {
+				res = PTR_ERR(method);
+				goto free;
+			}
+
+			/*
+			 * The last tree which is given as an argument to the
+			 * merge overrides previous method handler.
+			 * Therefore, we iterate backwards and search for the
+			 * first handler which != NULL. This also defines the
+			 * set of flags used for this handler.
+			 */
+			for (i = num_object_defs - 1;
+			     i >= 0 && !method_defs[i]->handler; i--)
+				;
+			hash->methods[min_id++] = method;
+			/* NULL handler isn't allowed */
+			if (WARN(i < 0,
+				 "ib_uverbs: tried to merge function id %d, but all handlers are NULL\n",
+				 min_id)) {
+				res = -EINVAL;
+				goto free;
+			}
+			method->handler = method_defs[i]->handler;
+			method->flags = method_defs[i]->flags;
+
+		} while (1);
+	}
+	kfree(method_defs);
+	return object;
+
+free:
+	kfree(method_defs);
+free_object:
+	free_object(object);
+	return ERR_PTR(res);
+}
+
+void uverbs_free_spec_tree(struct uverbs_root_spec *root)
+{
+	unsigned int i, j;
+
+	if (!root)
+		return;
+
+	for (i = 0; i < root->num_buckets; i++) {
+		struct uverbs_object_spec_hash *object_hash =
+			root->object_buckets[i];
+
+		if (!object_hash)
+			continue;
+
+		for (j = 0; j < object_hash->num_objects; j++)
+			free_object(object_hash->objects[j]);
+
+		kfree(object_hash);
+	}
+
+	kfree(root);
+}
+EXPORT_SYMBOL(uverbs_free_spec_tree);
+
+struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+						const struct uverbs_object_tree_def **trees)
+{
+	u16 bucket_idx;
+	short max_object_buckets = 0;
+	size_t num_objects_buckets = 0;
+	struct uverbs_root_spec *root_spec = NULL;
+	const struct uverbs_object_def **object_defs;
+	int i;
+	int res = 0;
+
+	max_object_buckets = find_max_object_ns_id(num_trees, trees);
+	/*
+	 * Devices which don't want to support ib_uverbs, should just allocate
+	 * an empty parsing tree. Every user-space command won't hit any valid
+	 * entry in the parsing tree and thus will fail.
+	 */
+	if (max_object_buckets >= 0)
+		num_objects_buckets = max_object_buckets + 1;
+
+	root_spec = kzalloc(sizeof(*root_spec) +
+			    num_objects_buckets * sizeof(*root_spec->object_buckets),
+			    GFP_KERNEL);
+	if (!root_spec)
+		return ERR_PTR(-ENOMEM);
+	root_spec->num_buckets = num_objects_buckets;
+
+	object_defs = kcalloc(num_trees, sizeof(*object_defs),
+			      GFP_KERNEL);
+	if (!object_defs) {
+		res = -ENOMEM;
+		goto free_root;
+	}
+
+	for (bucket_idx = 0; bucket_idx < root_spec->num_buckets; bucket_idx++) {
+		short min_id = SHRT_MIN;
+		short objects_max_bucket;
+		struct uverbs_object_spec_hash *hash = NULL;
+
+		objects_max_bucket = find_max_object_id(num_trees, trees,
+							bucket_idx);
+		if (objects_max_bucket < 0)
+			continue;
+
+		hash = kzalloc(sizeof(*hash) +
+			       sizeof(*hash->objects) * (objects_max_bucket + 1),
+			       GFP_KERNEL);
+		if (!hash) {
+			res = -ENOMEM;
+			goto free;
+		}
+		hash->num_objects = objects_max_bucket + 1;
+		root_spec->object_buckets[bucket_idx] = hash;
+
+		do {
+			size_t				num_object_defs;
+			struct uverbs_object_spec	*object;
+
+			num_object_defs = get_objects_above_id(object_defs,
+							       num_trees,
+							       trees,
+							       bucket_idx,
+							       &min_id);
+			/* Last object in bucket */
+			if (!num_object_defs)
+				break;
+
+			object = build_object_with_methods(object_defs,
+							   num_object_defs);
+			if (IS_ERR(object)) {
+				res = PTR_ERR(object);
+				goto free;
+			}
+
+			/*
+			 * The last tree which is given as an argument to the
+			 * merge overrides previous object's type_attrs.
+			 * Therefore, we iterate backwards and search for the
+			 * first type_attrs which != NULL.
+			 */
+			for (i = num_object_defs - 1;
+			     i >= 0 && !object_defs[i]->type_attrs; i--)
+				;
+			/*
+			 * NULL is a valid type_attrs. It means an object we
+			 * can't instantiate (like DEVICE).
+			 */
+			object->type_attrs = i < 0 ? NULL :
+				object_defs[i]->type_attrs;
+
+			hash->objects[min_id++] = object;
+		} while (1);
+	}
+
+	kfree(object_defs);
+	return root_spec;
+
+free:
+	kfree(object_defs);
+free_root:
+	uverbs_free_spec_tree(root_spec);
+	return ERR_PTR(res);
+}
+EXPORT_SYMBOL(uverbs_alloc_spec_tree);
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 2e8925434d74..cf5b238d2d81 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -235,5 +235,43 @@ static inline bool uverbs_attr_is_valid_in_hash(const struct uverbs_attr_bundle_
 	return test_bit(idx, attrs_hash->valid_bitmap);
 }
 
-#endif
+/* =================================================
+ *	 Definitions -> Specs infrastructure
+ * =================================================
+ */
+
+/*
+ * uverbs_alloc_spec_tree - Merges different common and driver specific feature
+ *	into one parsing tree that every uverbs command will be parsed upon.
+ *
+ * @num_trees: Number of trees in the array @trees.
+ * @trees: Array of pointers to tree root definitions to merge. Each such tree
+ *	   possibly contains objects, methods and attributes definitions.
+ *
+ * Returns:
+ *	uverbs_root_spec *: The root of the merged parsing tree.
+ *	On error, we return an error code. Error is checked via IS_ERR.
+ *
+ * The following merges could take place:
+ * a. Two trees representing the same method with different handler
+ *	-> We take the handler of the tree that its handler != NULL
+ *	   and its index in the trees array is greater. The incentive for that
+ *	   is that developers are expected to first merge common trees and then
+ *	   merge trees that gives specialized the behaviour.
+ * b. Two trees representing the same object with different
+ *    type_attrs (struct uverbs_obj_type):
+ *	-> We take the type_attrs of the tree that its type_attr != NULL
+ *	   and its index in the trees array is greater. This could be used
+ *	   in order to override the free function, allocation size, etc.
+ * c. Two trees representing the same method attribute (same id but possibly
+ *    different attributes):
+ *	-> ERROR (-ENOENT), we believe that's not the programmer's intent.
+ *
+ * An object without any methods is considered invalid and will abort the
+ * function with -ENOENT error.
+ */
+struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+						const struct uverbs_object_tree_def **trees);
+void uverbs_free_spec_tree(struct uverbs_root_spec *root);
 
+#endif
-- 
cgit v1.2.3-59-g8ed1b


From 4da70da23e9ba03f7f9e067fbe0eec6ebbfee401 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:02 +0300
Subject: IB/core: Explicitly destroy an object while keeping uobject

When some objects are destroyed, we need to extract their status at
destruction. After object's destruction, this status
(e.g. events_reported) relies in the uobject. In order to have the
latest and correct status, the underlying object should be destroyed,
but we should keep the uobject alive and read this information off the
uobject. We introduce a rdma_explicit_destroy function. This function
destroys the class type object (for example, the IDR class type which
destroys the underlying object as well) and then convert the uobject
to be of a null class type. This uobject will then be destroyed as any
other uobject once uverbs_finalize_object[s] is called.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/rdma_core.c | 35 +++++++++++++++++++++++++++++++++++
 include/rdma/uverbs_types.h         |  1 +
 2 files changed, 36 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index 2a2f002ac7cb..85b5ee4defa4 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -451,6 +451,41 @@ int __must_check rdma_remove_commit_uobject(struct ib_uobject *uobj)
 	return ret;
 }
 
+static int null_obj_type_class_remove_commit(struct ib_uobject *uobj,
+					     enum rdma_remove_reason why)
+{
+	return 0;
+}
+
+static const struct uverbs_obj_type null_obj_type = {
+	.type_class = &((const struct uverbs_obj_type_class){
+			.remove_commit = null_obj_type_class_remove_commit,
+			/* be cautious */
+			.needs_kfree_rcu = true}),
+};
+
+int rdma_explicit_destroy(struct ib_uobject *uobject)
+{
+	int ret;
+	struct ib_ucontext *ucontext = uobject->context;
+
+	/* Cleanup is running. Calling this should have been impossible */
+	if (!down_read_trylock(&ucontext->cleanup_rwsem)) {
+		WARN(true, "ib_uverbs: Cleanup is running while removing an uobject\n");
+		return 0;
+	}
+	lockdep_check(uobject, true);
+	ret = uobject->type->type_class->remove_commit(uobject,
+						       RDMA_REMOVE_DESTROY);
+	if (ret)
+		return ret;
+
+	uobject->type = &null_obj_type;
+
+	up_read(&ucontext->cleanup_rwsem);
+	return 0;
+}
+
 static void alloc_commit_idr_uobject(struct ib_uobject *uobj)
 {
 	uverbs_uobject_add(uobj);
diff --git a/include/rdma/uverbs_types.h b/include/rdma/uverbs_types.h
index 9760b6d70744..cc04ec65588d 100644
--- a/include/rdma/uverbs_types.h
+++ b/include/rdma/uverbs_types.h
@@ -129,6 +129,7 @@ struct ib_uobject *rdma_alloc_begin_uobject(const struct uverbs_obj_type *type,
 void rdma_alloc_abort_uobject(struct ib_uobject *uobj);
 int __must_check rdma_remove_commit_uobject(struct ib_uobject *uobj);
 int rdma_alloc_commit_uobject(struct ib_uobject *uobj);
+int rdma_explicit_destroy(struct ib_uobject *uobject);
 
 struct uverbs_obj_fd_type {
 	/*
-- 
cgit v1.2.3-59-g8ed1b


From d70724f149b107f8e4062320270d3d8b6713a1bb Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:04 +0300
Subject: IB/core: Add legacy driver's user-data

In this phase, we don't want to change all the drivers to use
flexible driver's specific attributes. Therefore, we add two default
attributes: UHW_IN and UHW_OUT. These attributes are optional in some
methods and they encode the driver specific command data. We add
a function that extract this data and creates the legacy udata over
it.

Driver's data should start from UVERBS_UDATA_DRIVER_DATA_FLAG. This
turns on the first bit of the namespace, indicating this attribute
belongs to the driver's namespace.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_std_types.c | 40 ++++++++++++++++++++++++++
 include/rdma/uverbs_ioctl.h                | 46 ++++++++++++++++++++++++++++++
 include/uapi/rdma/ib_user_ioctl_verbs.h    | 10 +++++++
 3 files changed, 96 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 5f90978bda8d..db66c18857e4 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -209,6 +209,46 @@ static int uverbs_hot_unplug_completion_event_file(struct ib_uobject_file *uobj_
 	return 0;
 };
 
+/*
+ * This spec is used in order to pass information to the hardware driver in a
+ * legacy way. Every verb that could get driver specific data should get this
+ * spec.
+ */
+static const struct uverbs_attr_def uverbs_uhw_compat_in =
+	UVERBS_ATTR_PTR_IN_SZ(UVERBS_UHW_IN, 0, UA_FLAGS(UVERBS_ATTR_SPEC_F_MIN_SZ));
+static const struct uverbs_attr_def uverbs_uhw_compat_out =
+	UVERBS_ATTR_PTR_OUT_SZ(UVERBS_UHW_OUT, 0, UA_FLAGS(UVERBS_ATTR_SPEC_F_MIN_SZ));
+
+static void create_udata(struct uverbs_attr_bundle *ctx,
+			 struct ib_udata *udata)
+{
+	/*
+	 * This is for ease of conversion. The purpose is to convert all drivers
+	 * to use uverbs_attr_bundle instead of ib_udata.
+	 * Assume attr == 0 is input and attr == 1 is output.
+	 */
+	void __user *inbuf;
+	size_t inbuf_len = 0;
+	void __user *outbuf;
+	size_t outbuf_len = 0;
+	const struct uverbs_attr *uhw_in =
+		uverbs_attr_get(ctx, UVERBS_UHW_IN);
+	const struct uverbs_attr *uhw_out =
+		uverbs_attr_get(ctx, UVERBS_UHW_OUT);
+
+	if (!IS_ERR(uhw_in)) {
+		inbuf = uhw_in->ptr_attr.ptr;
+		inbuf_len = uhw_in->ptr_attr.len;
+	}
+
+	if (!IS_ERR(uhw_out)) {
+		outbuf = uhw_out->ptr_attr.ptr;
+		outbuf_len = uhw_out->ptr_attr.len;
+	}
+
+	INIT_UDATA_BUF_OR_NULL(udata, inbuf, outbuf, inbuf_len, outbuf_len);
+}
+
 DECLARE_UVERBS_OBJECT(uverbs_object_comp_channel,
 		      UVERBS_OBJECT_COMP_CHANNEL,
 		      &UVERBS_TYPE_ALLOC_FD(0,
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 9a8d217cdc1d..759afa0621ea 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -36,6 +36,7 @@
 #include <rdma/uverbs_types.h>
 #include <linux/uaccess.h>
 #include <rdma/rdma_user_ioctl.h>
+#include <rdma/ib_user_ioctl_verbs.h>
 
 /*
  * =======================================
@@ -338,6 +339,51 @@ static inline bool uverbs_attr_is_valid(const struct uverbs_attr_bundle *attrs_b
 					    idx & ~UVERBS_ID_NS_MASK);
 }
 
+static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr_bundle *attrs_bundle,
+							u16 idx)
+{
+	u16 idx_bucket = idx >>	UVERBS_ID_NS_SHIFT;
+
+	if (!uverbs_attr_is_valid(attrs_bundle, idx))
+		return ERR_PTR(-ENOENT);
+
+	return &attrs_bundle->hash[idx_bucket].attrs[idx & ~UVERBS_ID_NS_MASK];
+}
+
+static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle,
+				 size_t idx, const void *from)
+{
+	const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
+	u16 flags;
+
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	flags = attr->ptr_attr.flags | UVERBS_ATTR_F_VALID_OUTPUT;
+	return (!copy_to_user(attr->ptr_attr.ptr, from, attr->ptr_attr.len) &&
+		!put_user(flags, &attr->uattr->flags)) ? 0 : -EFAULT;
+}
+
+static inline int _uverbs_copy_from(void *to, size_t to_size,
+				    const struct uverbs_attr_bundle *attrs_bundle,
+				    size_t idx)
+{
+	const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
+
+	if (IS_ERR(attr))
+		return PTR_ERR(attr);
+
+	if (to_size <= sizeof(((struct ib_uverbs_attr *)0)->data))
+		memcpy(to, &attr->ptr_attr.data, attr->ptr_attr.len);
+	else if (copy_from_user(to, attr->ptr_attr.ptr, attr->ptr_attr.len))
+		return -EFAULT;
+
+	return 0;
+}
+
+#define uverbs_copy_from(to, attrs_bundle, idx)				      \
+	_uverbs_copy_from(to, sizeof(*(to)), attrs_bundle, idx)
+
 /* =================================================
  *	 Definitions -> Specs infrastructure
  * =================================================
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 78a2e5be4d6e..90f81eeca35b 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -33,6 +33,11 @@
 #ifndef IB_USER_IOCTL_VERBS_H
 #define IB_USER_IOCTL_VERBS_H
 
+#include <rdma/rdma_user_ioctl.h>
+
+#define UVERBS_UDATA_DRIVER_DATA_NS	1
+#define UVERBS_UDATA_DRIVER_DATA_FLAG	(1UL << UVERBS_ID_NS_SHIFT)
+
 enum uverbs_default_objects {
 	UVERBS_OBJECT_DEVICE, /* No instances of DEVICE are allowed */
 	UVERBS_OBJECT_PD,
@@ -50,5 +55,10 @@ enum uverbs_default_objects {
 	UVERBS_OBJECT_LAST,
 };
 
+enum {
+	UVERBS_UHW_IN = UVERBS_UDATA_DRIVER_DATA_FLAG,
+	UVERBS_UHW_OUT,
+};
+
 #endif
 
-- 
cgit v1.2.3-59-g8ed1b


From 9ee79fce364216df35ec46e26d20780c3c1644cc Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:05 +0300
Subject: IB/core: Add completion queue (cq) object actions

Adding CQ ioctl actions:
1. create_cq
2. destroy_cq

This requires adding the following:
1. A specification describing the method
	a. Handler
	b. Attributes specification
		Each attribute is one of the following:
		a. PTR_IN - input data
			    Note: This could be encoded inlined for
				  data < 64bit
		b. PTR_OUT - response data
		c. IDR - idr based object
		d. FD - fd based object
                Blobs attributes (clauses a and b) contain their type,
	        while objects specifications (clauses c and d)
                contains the expected object type (for example, the
                given id should be UVERBS_TYPE_PD) and the required
                access (READ, WRITE, NEW or DESTROY). If a NEW is
                required, the new object's id will be assigned to this
                attribute. All attributes could get UA_FLAGS
                attribute. Currently we support stating that an
		attribute is mandatory or that the specification size
                corresponds to a lower bound (and that this attribute
		could be extended).
		We currently add both default attributes and the two
		generic UHW_IN and UHW_OUT driver specific attributes.
2. Handler
   A handler gets a uverbs_attr_bundle. The handler developer uses
   uverbs_attr_get to fetch an attribute of a given id.
   Each of these attribute groups correspond to the specification
   group defined in the action (clauses 1.b and 1.c respectively).
   The indices of these arrays corresponds to the attribute ids
   declared in the specifications (clause 2).

   The handler is quite simple. It assumes the infrastructure fetched
   all objects and locked, created or destroyed them as required by
   the specification. Pointer (or blob) attributes were validated to
   match their required sizes. After the handler finished, the
   infrastructure commits or rollbacks the objects.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs_std_types.c | 138 ++++++++++++++++++++++++++++-
 include/uapi/rdma/ib_user_ioctl_verbs.h    |  20 +++++
 2 files changed, 157 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index db66c18857e4..0a98579700ec 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -249,6 +249,140 @@ static void create_udata(struct uverbs_attr_bundle *ctx,
 	INIT_UDATA_BUF_OR_NULL(udata, inbuf, outbuf, inbuf_len, outbuf_len);
 }
 
+static int uverbs_create_cq_handler(struct ib_device *ib_dev,
+				    struct ib_uverbs_file *file,
+				    struct uverbs_attr_bundle *attrs)
+{
+	struct ib_ucontext *ucontext = file->ucontext;
+	struct ib_ucq_object           *obj;
+	struct ib_udata uhw;
+	int ret;
+	u64 user_handle;
+	struct ib_cq_init_attr attr = {};
+	struct ib_cq                   *cq;
+	struct ib_uverbs_completion_event_file    *ev_file = NULL;
+	const struct uverbs_attr *ev_file_attr;
+	struct ib_uobject *ev_file_uobj;
+
+	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_CREATE_CQ))
+		return -EOPNOTSUPP;
+
+	ret = uverbs_copy_from(&attr.comp_vector, attrs, CREATE_CQ_COMP_VECTOR);
+	if (!ret)
+		ret = uverbs_copy_from(&attr.cqe, attrs, CREATE_CQ_CQE);
+	if (!ret)
+		ret = uverbs_copy_from(&user_handle, attrs, CREATE_CQ_USER_HANDLE);
+	if (ret)
+		return ret;
+
+	/* Optional param, if it doesn't exist, we get -ENOENT and skip it */
+	if (uverbs_copy_from(&attr.flags, attrs, CREATE_CQ_FLAGS) == -EFAULT)
+		return -EFAULT;
+
+	ev_file_attr = uverbs_attr_get(attrs, CREATE_CQ_COMP_CHANNEL);
+	if (!IS_ERR(ev_file_attr)) {
+		ev_file_uobj = ev_file_attr->obj_attr.uobject;
+
+		ev_file = container_of(ev_file_uobj,
+				       struct ib_uverbs_completion_event_file,
+				       uobj_file.uobj);
+		uverbs_uobject_get(ev_file_uobj);
+	}
+
+	if (attr.comp_vector >= ucontext->ufile->device->num_comp_vectors) {
+		ret = -EINVAL;
+		goto err_event_file;
+	}
+
+	obj = container_of(uverbs_attr_get(attrs, CREATE_CQ_HANDLE)->obj_attr.uobject,
+			   typeof(*obj), uobject);
+	obj->uverbs_file	   = ucontext->ufile;
+	obj->comp_events_reported  = 0;
+	obj->async_events_reported = 0;
+	INIT_LIST_HEAD(&obj->comp_list);
+	INIT_LIST_HEAD(&obj->async_list);
+
+	/* Temporary, only until drivers get the new uverbs_attr_bundle */
+	create_udata(attrs, &uhw);
+
+	cq = ib_dev->create_cq(ib_dev, &attr, ucontext, &uhw);
+	if (IS_ERR(cq)) {
+		ret = PTR_ERR(cq);
+		goto err_event_file;
+	}
+
+	cq->device        = ib_dev;
+	cq->uobject       = &obj->uobject;
+	cq->comp_handler  = ib_uverbs_comp_handler;
+	cq->event_handler = ib_uverbs_cq_event_handler;
+	cq->cq_context    = &ev_file->ev_queue;
+	obj->uobject.object = cq;
+	obj->uobject.user_handle = user_handle;
+	atomic_set(&cq->usecnt, 0);
+
+	ret = uverbs_copy_to(attrs, CREATE_CQ_RESP_CQE, &cq->cqe);
+	if (ret)
+		goto err_cq;
+
+	return 0;
+err_cq:
+	ib_destroy_cq(cq);
+
+err_event_file:
+	if (ev_file)
+		uverbs_uobject_put(ev_file_uobj);
+	return ret;
+};
+
+static DECLARE_UVERBS_METHOD(
+	uverbs_method_cq_create, UVERBS_CQ_CREATE, uverbs_create_cq_handler,
+	&UVERBS_ATTR_IDR(CREATE_CQ_HANDLE, UVERBS_OBJECT_CQ, UVERBS_ACCESS_NEW,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_CQE, u32,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_USER_HANDLE, u64,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_FD(CREATE_CQ_COMP_CHANNEL, UVERBS_OBJECT_COMP_CHANNEL,
+			UVERBS_ACCESS_READ),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_COMP_VECTOR, u32,
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(CREATE_CQ_FLAGS, u32),
+	&UVERBS_ATTR_PTR_OUT(CREATE_CQ_RESP_CQE, u32,
+			     UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&uverbs_uhw_compat_in, &uverbs_uhw_compat_out);
+
+static int uverbs_destroy_cq_handler(struct ib_device *ib_dev,
+				     struct ib_uverbs_file *file,
+				     struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uverbs_destroy_cq_resp resp;
+	struct ib_uobject *uobj =
+		uverbs_attr_get(attrs, DESTROY_CQ_HANDLE)->obj_attr.uobject;
+	struct ib_ucq_object *obj = container_of(uobj, struct ib_ucq_object,
+						 uobject);
+	int ret;
+
+	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_DESTROY_CQ))
+		return -EOPNOTSUPP;
+
+	ret = rdma_explicit_destroy(uobj);
+	if (ret)
+		return ret;
+
+	resp.comp_events_reported  = obj->comp_events_reported;
+	resp.async_events_reported = obj->async_events_reported;
+
+	return uverbs_copy_to(attrs, DESTROY_CQ_RESP, &resp);
+}
+
+static DECLARE_UVERBS_METHOD(
+	uverbs_method_cq_destroy, UVERBS_CQ_DESTROY, uverbs_destroy_cq_handler,
+	&UVERBS_ATTR_IDR(DESTROY_CQ_HANDLE, UVERBS_OBJECT_CQ,
+			 UVERBS_ACCESS_DESTROY,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_OUT(DESTROY_CQ_RESP, struct ib_uverbs_destroy_cq_resp,
+			     UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)));
+
 DECLARE_UVERBS_OBJECT(uverbs_object_comp_channel,
 		      UVERBS_OBJECT_COMP_CHANNEL,
 		      &UVERBS_TYPE_ALLOC_FD(0,
@@ -259,7 +393,9 @@ DECLARE_UVERBS_OBJECT(uverbs_object_comp_channel,
 
 DECLARE_UVERBS_OBJECT(uverbs_object_cq, UVERBS_OBJECT_CQ,
 		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_ucq_object), 0,
-						  uverbs_free_cq));
+						  uverbs_free_cq),
+		      &uverbs_method_cq_create,
+		      &uverbs_method_cq_destroy);
 
 DECLARE_UVERBS_OBJECT(uverbs_object_qp, UVERBS_OBJECT_QP,
 		      &UVERBS_TYPE_ALLOC_IDR_SZ(sizeof(struct ib_uqp_object), 0,
diff --git a/include/uapi/rdma/ib_user_ioctl_verbs.h b/include/uapi/rdma/ib_user_ioctl_verbs.h
index 90f81eeca35b..842792eae383 100644
--- a/include/uapi/rdma/ib_user_ioctl_verbs.h
+++ b/include/uapi/rdma/ib_user_ioctl_verbs.h
@@ -60,5 +60,25 @@ enum {
 	UVERBS_UHW_OUT,
 };
 
+enum uverbs_create_cq_cmd_attr_ids {
+	CREATE_CQ_HANDLE,
+	CREATE_CQ_CQE,
+	CREATE_CQ_USER_HANDLE,
+	CREATE_CQ_COMP_CHANNEL,
+	CREATE_CQ_COMP_VECTOR,
+	CREATE_CQ_FLAGS,
+	CREATE_CQ_RESP_CQE,
+};
+
+enum uverbs_destroy_cq_cmd_attr_ids {
+	DESTROY_CQ_HANDLE,
+	DESTROY_CQ_RESP,
+};
+
+enum uverbs_actions_cq_ops {
+	UVERBS_CQ_CREATE,
+	UVERBS_CQ_DESTROY,
+};
+
 #endif
 
-- 
cgit v1.2.3-59-g8ed1b


From 524271129401ed896dc76e49acdbafc506cb41ac Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:06 +0300
Subject: IB/core: Assign root to all drivers

In order to use the parsing tree, we need to assign the root
to all drivers. Currently, we just assign the default parsing
tree via ib_uverbs_add_one. The driver could override this by
assigning a parsing tree prior to registering the device.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/uverbs.h      |  1 +
 drivers/infiniband/core/uverbs_main.c | 18 ++++++++++++++++++
 include/rdma/uverbs_ioctl.h           | 12 ++++++++++++
 include/rdma/uverbs_std_types.h       | 14 ++++++++++++++
 4 files changed, 45 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 64d494a64daf..0f6f768f687e 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -100,6 +100,7 @@ struct ib_uverbs_device {
 	struct mutex				lists_mutex; /* protect lists */
 	struct list_head			uverbs_file_list;
 	struct list_head			uverbs_events_file_list;
+	struct uverbs_root_spec			*specs_root;
 };
 
 struct ib_uverbs_event_queue {
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index defeda33e27f..872fec910c16 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -49,6 +49,7 @@
 #include <linux/uaccess.h>
 
 #include <rdma/ib.h>
+#include <rdma/uverbs_std_types.h>
 
 #include "uverbs.h"
 #include "core_priv.h"
@@ -1097,6 +1098,18 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	if (device_create_file(uverbs_dev->dev, &dev_attr_abi_version))
 		goto err_class;
 
+	if (!device->specs_root) {
+		const struct uverbs_object_tree_def *default_root[] = {
+			uverbs_default_get_objects()};
+
+		uverbs_dev->specs_root = uverbs_alloc_spec_tree(1,
+								default_root);
+		if (IS_ERR(uverbs_dev->specs_root))
+			goto err_class;
+
+		device->specs_root = uverbs_dev->specs_root;
+	}
+
 	ib_set_client_data(device, &uverbs_client, uverbs_dev);
 
 	return;
@@ -1228,6 +1241,11 @@ static void ib_uverbs_remove_one(struct ib_device *device, void *client_data)
 		ib_uverbs_comp_dev(uverbs_dev);
 	if (wait_clients)
 		wait_for_completion(&uverbs_dev->comp);
+	if (uverbs_dev->specs_root) {
+		uverbs_free_spec_tree(uverbs_dev->specs_root);
+		device->specs_root = NULL;
+	}
+
 	kobject_put(&uverbs_dev->kobj);
 }
 
diff --git a/include/rdma/uverbs_ioctl.h b/include/rdma/uverbs_ioctl.h
index 759afa0621ea..6da44079aa58 100644
--- a/include/rdma/uverbs_ioctl.h
+++ b/include/rdma/uverbs_ioctl.h
@@ -419,8 +419,20 @@ static inline int _uverbs_copy_from(void *to, size_t to_size,
  * An object without any methods is considered invalid and will abort the
  * function with -ENOENT error.
  */
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
 						const struct uverbs_object_tree_def **trees);
 void uverbs_free_spec_tree(struct uverbs_root_spec *root);
+#else
+static inline struct uverbs_root_spec *uverbs_alloc_spec_tree(unsigned int num_trees,
+							      const struct uverbs_object_tree_def **trees)
+{
+	return NULL;
+}
+
+static inline void uverbs_free_spec_tree(struct uverbs_root_spec *root)
+{
+}
+#endif
 
 #endif
diff --git a/include/rdma/uverbs_std_types.h b/include/rdma/uverbs_std_types.h
index 400efe2a4d3c..5f8e20bbd67c 100644
--- a/include/rdma/uverbs_std_types.h
+++ b/include/rdma/uverbs_std_types.h
@@ -34,8 +34,10 @@
 #define _UVERBS_STD_TYPES__
 
 #include <rdma/uverbs_types.h>
+#include <rdma/uverbs_ioctl.h>
 #include <rdma/ib_user_ioctl_verbs.h>
 
+#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 extern const struct uverbs_object_def uverbs_object_comp_channel;
 extern const struct uverbs_object_def uverbs_object_cq;
 extern const struct uverbs_object_def uverbs_object_qp;
@@ -50,6 +52,18 @@ extern const struct uverbs_object_def uverbs_object_pd;
 extern const struct uverbs_object_def uverbs_object_xrcd;
 extern const struct uverbs_object_def uverbs_object_device;
 
+extern const struct uverbs_object_tree_def uverbs_default_objects;
+static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void)
+{
+	return &uverbs_default_objects;
+}
+#else
+static inline const struct uverbs_object_tree_def *uverbs_default_get_objects(void)
+{
+	return NULL;
+}
+#endif
+
 static inline struct ib_uobject *__uobj_get(const struct uverbs_obj_type *type,
 					    bool write,
 					    struct ib_ucontext *ucontext,
-- 
cgit v1.2.3-59-g8ed1b


From 8eb19e8e7c8658226d8b7e75728e6dfa2ef32717 Mon Sep 17 00:00:00 2001
From: Matan Barak <matanb@mellanox.com>
Date: Thu, 3 Aug 2017 16:07:07 +0300
Subject: IB/core: Expose ioctl interface through experimental Kconfig

Add CONFIG_INFINIBAND_EXP_USER_ACCESS that enables the ioctl
interface. This interface is experimental and is subject to change.

Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/Kconfig            | 9 +++++++++
 drivers/infiniband/core/uverbs.h      | 2 ++
 drivers/infiniband/core/uverbs_main.c | 6 ++++++
 3 files changed, 17 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index 234fe01904e7..3726205c8704 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -34,6 +34,15 @@ config INFINIBAND_USER_ACCESS
 	  libibverbs, libibcm and a hardware driver library from
 	  <http://www.openfabrics.org/git/>.
 
+config INFINIBAND_EXP_USER_ACCESS
+	bool "Allow experimental support for Infiniband ABI"
+	depends on INFINIBAND_USER_ACCESS
+	---help---
+	  IOCTL based ABI support for Infiniband. This allows userspace
+	  to invoke the experimental IOCTL based ABI.
+	  These commands are parsed via per-device parsing tree and
+	  enables per-device features.
+
 config INFINIBAND_USER_MEM
 	bool
 	depends on INFINIBAND_USER_ACCESS != n
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 0f6f768f687e..37c8903e7fd0 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -219,6 +219,8 @@ int uverbs_dealloc_mw(struct ib_mw *mw);
 void ib_uverbs_detach_umcast(struct ib_qp *qp,
 			     struct ib_uqp_object *uobj);
 
+long ib_uverbs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+
 struct ib_uverbs_flow_spec {
 	union {
 		union {
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 872fec910c16..dc2aed6fb21b 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -939,6 +939,9 @@ static const struct file_operations uverbs_fops = {
 	.open	 = ib_uverbs_open,
 	.release = ib_uverbs_close,
 	.llseek	 = no_llseek,
+#if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS)
+	.unlocked_ioctl = ib_uverbs_ioctl,
+#endif
 };
 
 static const struct file_operations uverbs_mmap_fops = {
@@ -948,6 +951,9 @@ static const struct file_operations uverbs_mmap_fops = {
 	.open	 = ib_uverbs_open,
 	.release = ib_uverbs_close,
 	.llseek	 = no_llseek,
+#if IS_ENABLED(CONFIG_INFINIBAND_EXP_USER_ACCESS)
+	.unlocked_ioctl = ib_uverbs_ioctl,
+#endif
 };
 
 static struct ib_client uverbs_client = {
-- 
cgit v1.2.3-59-g8ed1b