Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull RDMA subsystem updates from Jason Gunthorpe:
 "This cycle mainly saw lots of bug fixes and clean up code across the
  core code and several drivers, few new functional changes were made.

   - Many cleanup and bug fixes for hns

   - Various small bug fixes and cleanups in hfi1, mlx5, usnic, qed,
     bnxt_re, efa

   - Share the query_port code between all the iWarp drivers

   - General rework and cleanup of the ODP MR umem code to fit better
     with the mmu notifier get/put scheme

   - Support rdma netlink in non init_net name spaces

   - mlx5 support for XRC devx and DC ODP"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (99 commits)
  RDMA: Fix double-free in srq creation error flow
  RDMA/efa: Fix incorrect error print
  IB/mlx5: Free mpi in mp_slave mode
  IB/mlx5: Use the original address for the page during free_pages
  RDMA/bnxt_re: Fix spelling mistake "missin_resp" -> "missing_resp"
  RDMA/hns: Package operations of rq inline buffer into separate functions
  RDMA/hns: Optimize cmd init and mode selection for hip08
  IB/hfi1: Define variables as unsigned long to fix KASAN warning
  IB/{rdmavt, hfi1, qib}: Add a counter for credit waits
  IB/hfi1: Add traces for TID RDMA READ
  RDMA/siw: Relax from kmap_atomic() use in TX path
  IB/iser: Support up to 16MB data transfer in a single command
  RDMA/siw: Fix page address mapping in TX path
  RDMA: Fix goto target to release the allocated memory
  RDMA/usnic: Avoid overly large buffers on stack
  RDMA/odp: Add missing cast for 32 bit
  RDMA/hns: Use devm_platform_ioremap_resource() to simplify code
  Documentation/infiniband: update name of some functions
  RDMA/cma: Fix false error message
  RDMA/hns: Fix wrong assignment of qp_access_flags
  ...

79 files changed, 2548 insertions, 1849 deletions

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 9b76a8fcdd24..1dd467bed8fc 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -183,7 +183,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(&init_net, 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/cache.c b/drivers/infiniband/core/cache.c
index 18e476b3ced0..00fb3eacda19 100644
--- a/drivers/infiniband/core/cache.c
+++ b/drivers/infiniband/core/cache.c
@@ -810,6 +810,7 @@ static void release_gid_table(struct ib_device *device,
 	if (leak)
 		return;
 
+	mutex_destroy(&table->lock);
 	kfree(table->data_vec);
 	kfree(table);
 }
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index a68d0ccf67a4..0e3cf3461999 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -3046,7 +3046,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 		if (status)
 			pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n",
 					     status);
-	} else {
+	} else if (status) {
 		pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status);
 	}
 
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 3ec2c415bb70..8b0b5ae22e4c 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -342,12 +342,18 @@ static struct configfs_subsystem cma_subsys = {
 
 int __init cma_configfs_init(void)
 {
+	int ret;
+
 	config_group_init(&cma_subsys.su_group);
 	mutex_init(&cma_subsys.su_mutex);
-	return configfs_register_subsystem(&cma_subsys);
+	ret = configfs_register_subsystem(&cma_subsys);
+	if (ret)
+		mutex_destroy(&cma_subsys.su_mutex);
+	return ret;
 }
 
 void __exit cma_configfs_exit(void)
 {
 	configfs_unregister_subsystem(&cma_subsys);
+	mutex_destroy(&cma_subsys.su_mutex);
 }
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index beee7b7e0d9a..3a8b0911c3bc 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -36,6 +36,8 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/cgroup_rdma.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/opa_addr.h>
@@ -54,8 +56,26 @@ struct pkey_index_qp_list {
 	struct list_head    qp_list;
 };
 
+/**
+ * struct rdma_dev_net - rdma net namespace metadata for a net
+ * @nl_sock:	Pointer to netlink socket
+ * @net:	Pointer to owner net namespace
+ * @id:		xarray id to identify the net namespace.
+ */
+struct rdma_dev_net {
+	struct sock *nl_sock;
+	possible_net_t net;
+	u32 id;
+};
+
 extern const struct attribute_group ib_dev_attr_group;
 extern bool ib_devices_shared_netns;
+extern unsigned int rdma_dev_net_id;
+
+static inline struct rdma_dev_net *rdma_net_to_dev_net(struct net *net)
+{
+	return net_generic(net, rdma_dev_net_id);
+}
 
 int ib_device_register_sysfs(struct ib_device *device);
 void ib_device_unregister_sysfs(struct ib_device *device);
@@ -179,7 +199,6 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int rdma_nl_init(void);
 void rdma_nl_exit(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
@@ -365,4 +384,7 @@ void ib_port_unregister_module_stat(struct kobject *kobj);
 
 int ib_device_set_netns_put(struct sk_buff *skb,
 			    struct ib_device *dev, u32 ns_fd);
+
+int rdma_nl_net_init(struct rdma_dev_net *rnet);
+void rdma_nl_net_exit(struct rdma_dev_net *rnet);
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index af8c85d18e62..680ad27f497d 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -599,7 +599,7 @@ int rdma_counter_get_mode(struct ib_device *dev, u8 port,
 void rdma_counter_init(struct ib_device *dev)
 {
 	struct rdma_port_counter *port_counter;
-	u32 port;
+	u32 port, i;
 
 	if (!dev->port_data)
 		return;
@@ -620,13 +620,12 @@ void rdma_counter_init(struct ib_device *dev)
 	return;
 
 fail:
-	rdma_for_each_port(dev, port) {
+	for (i = port; i >= rdma_start_port(dev); i--) {
 		port_counter = &dev->port_data[port].port_counter;
 		kfree(port_counter->hstats);
 		port_counter->hstats = NULL;
+		mutex_destroy(&port_counter->lock);
 	}
-
-	return;
 }
 
 void rdma_counter_release(struct ib_device *dev)
@@ -637,5 +636,6 @@ void rdma_counter_release(struct ib_device *dev)
 	rdma_for_each_port(dev, port) {
 		port_counter = &dev->port_data[port].port_counter;
 		kfree(port_counter->hstats);
+		mutex_destroy(&port_counter->lock);
 	}
 }
diff --git a/drivers/infiniband/core/cq.c b/drivers/infiniband/core/cq.c
index 7c599878ccf7..bbfded6d5d3d 100644
--- a/drivers/infiniband/core/cq.c
+++ b/drivers/infiniband/core/cq.c
@@ -253,6 +253,34 @@ out_free_cq:
 EXPORT_SYMBOL(__ib_alloc_cq_user);
 
 /**
+ * __ib_alloc_cq_any - allocate a completion queue
+ * @dev:		device to allocate the CQ for
+ * @private:		driver private data, accessible from cq->cq_context
+ * @nr_cqe:		number of CQEs to allocate
+ * @poll_ctx:		context to poll the CQ from
+ * @caller:		module owner name
+ *
+ * Attempt to spread ULP Completion Queues over each device's interrupt
+ * vectors. A simple best-effort mechanism is used.
+ */
+struct ib_cq *__ib_alloc_cq_any(struct ib_device *dev, void *private,
+				int nr_cqe, enum ib_poll_context poll_ctx,
+				const char *caller)
+{
+	static atomic_t counter;
+	int comp_vector = 0;
+
+	if (dev->num_comp_vectors > 1)
+		comp_vector =
+			atomic_inc_return(&counter) %
+			min_t(int, dev->num_comp_vectors, num_online_cpus());
+
+	return __ib_alloc_cq_user(dev, private, nr_cqe, comp_vector, poll_ctx,
+				  caller, NULL);
+}
+EXPORT_SYMBOL(__ib_alloc_cq_any);
+
+/**
  * ib_free_cq_user - free a completion queue
  * @cq:		completion queue to free.
  * @udata:	User data or NULL for kernel object
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index b5631b8a0397..99c4a55545cf 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -39,7 +39,6 @@
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <net/net_namespace.h>
-#include <net/netns/generic.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/hashtable.h>
@@ -111,17 +110,7 @@ static void ib_client_put(struct ib_client *client)
  */
 #define CLIENT_DATA_REGISTERED XA_MARK_1
 
-/**
- * struct rdma_dev_net - rdma net namespace metadata for a net
- * @net:	Pointer to owner net namespace
- * @id:		xarray id to identify the net namespace.
- */
-struct rdma_dev_net {
-	possible_net_t net;
-	u32 id;
-};
-
-static unsigned int rdma_dev_net_id;
+unsigned int rdma_dev_net_id;
 
 /*
  * A list of net namespaces is maintained in an xarray. This is necessary
@@ -514,6 +503,9 @@ static void ib_device_release(struct device *device)
 			  rcu_head);
 	}
 
+	mutex_destroy(&dev->unregistration_lock);
+	mutex_destroy(&dev->compat_devs_mutex);
+
 	xa_destroy(&dev->compat_devs);
 	xa_destroy(&dev->client_data);
 	kfree_rcu(dev, rcu_head);
@@ -1060,7 +1052,7 @@ int rdma_compatdev_set(u8 enable)
 
 static void rdma_dev_exit_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	struct ib_device *dev;
 	unsigned long index;
 	int ret;
@@ -1094,25 +1086,32 @@ static void rdma_dev_exit_net(struct net *net)
 	}
 	up_read(&devices_rwsem);
 
+	rdma_nl_net_exit(rnet);
 	xa_erase(&rdma_nets, rnet->id);
 }
 
 static __net_init int rdma_dev_init_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	unsigned long index;
 	struct ib_device *dev;
 	int ret;
 
+	write_pnet(&rnet->net, net);
+
+	ret = rdma_nl_net_init(rnet);
+	if (ret)
+		return ret;
+
 	/* No need to create any compat devices in default init_net. */
 	if (net_eq(net, &init_net))
 		return 0;
 
-	write_pnet(&rnet->net, net);
-
 	ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL);
-	if (ret)
+	if (ret) {
+		rdma_nl_net_exit(rnet);
 		return ret;
+	}
 
 	down_read(&devices_rwsem);
 	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {
@@ -1974,31 +1973,64 @@ void ib_dispatch_event(struct ib_event *event)
 }
 EXPORT_SYMBOL(ib_dispatch_event);
 
-/**
- * ib_query_port - Query IB port attributes
- * @device:Device to query
- * @port_num:Port number to query
- * @port_attr:Port attributes
- *
- * ib_query_port() returns the attributes of a port through the
- * @port_attr pointer.
- */
-int ib_query_port(struct ib_device *device,
-		  u8 port_num,
-		  struct ib_port_attr *port_attr)
+static int iw_query_port(struct ib_device *device,
+			   u8 port_num,
+			   struct ib_port_attr *port_attr)
 {
-	union ib_gid gid;
+	struct in_device *inetdev;
+	struct net_device *netdev;
 	int err;
 
-	if (!rdma_is_port_valid(device, port_num))
-		return -EINVAL;
+	memset(port_attr, 0, sizeof(*port_attr));
+
+	netdev = ib_device_get_netdev(device, port_num);
+	if (!netdev)
+		return -ENODEV;
+
+	dev_put(netdev);
+
+	port_attr->max_mtu = IB_MTU_4096;
+	port_attr->active_mtu = ib_mtu_int_to_enum(netdev->mtu);
+
+	if (!netif_carrier_ok(netdev)) {
+		port_attr->state = IB_PORT_DOWN;
+		port_attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
+	} else {
+		inetdev = in_dev_get(netdev);
+
+		if (inetdev && inetdev->ifa_list) {
+			port_attr->state = IB_PORT_ACTIVE;
+			port_attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
+			in_dev_put(inetdev);
+		} else {
+			port_attr->state = IB_PORT_INIT;
+			port_attr->phys_state =
+				IB_PORT_PHYS_STATE_PORT_CONFIGURATION_TRAINING;
+		}
+	}
+
+	err = device->ops.query_port(device, port_num, port_attr);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int __ib_query_port(struct ib_device *device,
+			   u8 port_num,
+			   struct ib_port_attr *port_attr)
+{
+	union ib_gid gid = {};
+	int err;
 
 	memset(port_attr, 0, sizeof(*port_attr));
+
 	err = device->ops.query_port(device, port_num, port_attr);
 	if (err || port_attr->subnet_prefix)
 		return err;
 
-	if (rdma_port_get_link_layer(device, port_num) != IB_LINK_LAYER_INFINIBAND)
+	if (rdma_port_get_link_layer(device, port_num) !=
+	    IB_LINK_LAYER_INFINIBAND)
 		return 0;
 
 	err = device->ops.query_gid(device, port_num, 0, &gid);
@@ -2008,6 +2040,28 @@ int ib_query_port(struct ib_device *device,
 	port_attr->subnet_prefix = be64_to_cpu(gid.global.subnet_prefix);
 	return 0;
 }
+
+/**
+ * ib_query_port - Query IB port attributes
+ * @device:Device to query
+ * @port_num:Port number to query
+ * @port_attr:Port attributes
+ *
+ * ib_query_port() returns the attributes of a port through the