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

Pull rdma updates from Jason Gunthorpe:
 "A very quiet cycle with few notable changes. Mostly the usual list of
  one or two patches to drivers changing something that isn't quite rc
  worthy. The subsystem seems to be seeing a larger number of rework and
  cleanup style patches right now, I feel that several vendors are
  prepping their drivers for new silicon.

  Summary:

   - Driver updates and cleanup for qedr, bnxt_re, hns, siw, mlx5, mlx4,
     rxe, i40iw

   - Larger series doing cleanup and rework for hns and hfi1.

   - Some general reworking of the CM code to make it a little more
     understandable

   - Unify the different code paths connected to the uverbs FD scheme

   - New UAPI ioctls conversions for get context and get async fd

   - Trace points for CQ and CM portions of the RDMA stack

   - mlx5 driver support for virtio-net formatted rings as RDMA raw
     ethernet QPs

   - verbs support for setting the PCI-E relaxed ordering bit on DMA
     traffic connected to a MR

   - A couple of bug fixes that came too late to make rc7"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (108 commits)
  RDMA/core: Make the entire API tree static
  RDMA/efa: Mask access flags with the correct optional range
  RDMA/cma: Fix unbalanced cm_id reference count during address resolve
  RDMA/umem: Fix ib_umem_find_best_pgsz()
  IB/mlx4: Fix leak in id_map_find_del
  IB/opa_vnic: Spelling correction of 'erorr' to 'error'
  IB/hfi1: Fix logical condition in msix_request_irq
  RDMA/cm: Remove CM message structs
  RDMA/cm: Use IBA functions for complex structure members
  RDMA/cm: Use IBA functions for simple structure members
  RDMA/cm: Use IBA functions for swapping get/set acessors
  RDMA/cm: Use IBA functions for simple get/set acessors
  RDMA/cm: Add SET/GET implementations to hide IBA wire format
  RDMA/cm: Add accessors for CM_REQ transport_type
  IB/mlx5: Return the administrative GUID if exists
  RDMA/core: Ensure that rdma_user_mmap_entry_remove() is a fence
  IB/mlx4: Fix memory leak in add_gid error flow
  IB/mlx5: Expose RoCE accelerator counters
  RDMA/mlx5: Set relaxed ordering when requested
  RDMA/core: Add the core support field to METHOD_GET_CONTEXT
  ...

Author: torvalds

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 \
-				nldev.o restrack.o counters.o ib_core_uverbs.o
+				nldev.o restrack.o counters.o ib_core_uverbs.o \
+				trace.o
 
 ib_core-$(CONFIG_SECURITY_INFINIBAND) += security.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
@@ -20,7 +21,8 @@ ib_cm-y :=			cm.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
 
-rdma_cm-y :=			cma.o
+CFLAGS_cma_trace.o +=		-I$(src)
+rdma_cm-y :=			cma.o cma_trace.o
 
 rdma_cm-$(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS) += cma_configfs.o
 
@@ -33,6 +35,7 @@ ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				uverbs_std_types_cq.o \
 				uverbs_std_types_flow_action.o uverbs_std_types_dm.o \
 				uverbs_std_types_mr.o uverbs_std_types_counters.o \
-				uverbs_uapi.o uverbs_std_types_device.o
+				uverbs_uapi.o uverbs_std_types_device.o \
+				uverbs_std_types_async_fd.o
 ib_uverbs-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_uverbs-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o

drivers/infiniband/core/addr.c

@@ -139,7 +139,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	if (ib_nl_is_good_ip_resp(nlh))
 		ib_nl_process_good_ip_rsep(nlh);
 
-	return skb->len;
+	return 0;
 }
 
 static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,

drivers/infiniband/core/cache.c

@@ -51,9 +51,8 @@ struct ib_pkey_cache {
 
 struct ib_update_work {
 	struct work_struct work;
-	struct ib_device  *device;
-	u8                 port_num;
-	bool		   enforce_security;
+	struct ib_event event;
+	bool enforce_security;
 };
 
 union ib_gid zgid;
@@ -130,7 +129,7 @@ static void dispatch_gid_change_event(struct ib_device *ib_dev, u8 port)
 	event.element.port_num	= port;
 	event.event		= IB_EVENT_GID_CHANGE;
 
-	ib_dispatch_event(&event);
+	ib_dispatch_event_clients(&event);
 }
 
 static const char * const gid_type_str[] = {
@@ -1034,7 +1033,7 @@ int ib_get_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1043,7 +1042,7 @@ int ib_get_cached_pkey(struct ib_device *device,
 	else
 		*pkey = cache->table[index];
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1058,9 +1057,9 @@ int ib_get_cached_subnet_prefix(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*sn_pfx = device->port_data[port_num].cache.subnet_prefix;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return 0;
 }
@@ -1080,7 +1079,7 @@ int ib_find_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1101,7 +1100,7 @@ int ib_find_cached_pkey(struct ib_device *device,
 		ret = 0;
 	}
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1120,7 +1119,7 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 
 	cache = device->port_data[port_num].cache.pkey;
 
@@ -1133,7 +1132,7 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 			break;
 		}
 
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1149,9 +1148,9 @@ int ib_get_cached_lmc(struct ib_device *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*lmc = device->port_data[port_num].cache.lmc;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1167,9 +1166,9 @@ int ib_get_cached_port_state(struct ib_device   *device,
 	if (!rdma_is_port_valid(device, port_num))
 		return -EINVAL;
 
-	read_lock_irqsave(&device->cache.lock, flags);
+	read_lock_irqsave(&device->cache_lock, flags);
 	*port_state = device->port_data[port_num].cache.port_state;
-	read_unlock_irqrestore(&device->cache.lock, flags);
+	read_unlock_irqrestore(&device->cache_lock, flags);
 
 	return ret;
 }
@@ -1381,21 +1380,20 @@ static int config_non_roce_gid_cache(struct ib_device *device,
 	return ret;
 }
 
-static void ib_cache_update(struct ib_device *device,
-			    u8                port,
-			    bool	      enforce_security)
+static int
+ib_cache_update(struct ib_device *device, u8 port, bool enforce_security)
 {
 	struct ib_port_attr       *tprops = NULL;
 	struct ib_pkey_cache      *pkey_cache = NULL, *old_pkey_cache;
 	int                        i;
 	int                        ret;
 
 	if (!rdma_is_port_valid(device, port))
-		return;
+		return -EINVAL;
 
 	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
 	if (!tprops)
-		return;
+		return -ENOMEM;
 
 	ret = ib_query_port(device, port, tprops);
 	if (ret) {
@@ -1413,8 +1411,10 @@ static void ib_cache_update(struct ib_device *device,
 	pkey_cache = kmalloc(struct_size(pkey_cache, table,
 					 tprops->pkey_tbl_len),
 			     GFP_KERNEL);
-	if (!pkey_cache)
+	if (!pkey_cache) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	pkey_cache->table_len = tprops->pkey_tbl_len;
 
@@ -1428,7 +1428,7 @@ static void ib_cache_update(struct ib_device *device,
 		}
 	}
 
-	write_lock_irq(&device->cache.lock);
+	write_lock_irq(&device->cache_lock);
 
 	old_pkey_cache = device->port_data[port].cache.pkey;
 
@@ -1437,7 +1437,7 @@ static void ib_cache_update(struct ib_device *device,
 	device->port_data[port].cache.port_state = tprops->state;
 
 	device->port_data[port].cache.subnet_prefix = tprops->subnet_prefix;
-	write_unlock_irq(&device->cache.lock);
+	write_unlock_irq(&device->cache_lock);
 
 	if (enforce_security)
 		ib_security_cache_change(device,
@@ -1446,57 +1446,91 @@ static void ib_cache_update(struct ib_device *device,
 
 	kfree(old_pkey_cache);
 	kfree(tprops);
-	return;
+	return 0;
 
 err:
 	kfree(pkey_cache);
 	kfree(tprops);
+	return ret;
+}
+
+static void ib_cache_event_task(struct work_struct *_work)
+{
+	struct ib_update_work *work =
+		container_of(_work, struct ib_update_work, work);
+	int ret;
+
+	/* Before distributing the cache update event, first sync
+	 * the cache.
+	 */
+	ret = ib_cache_update(work->event.device, work->event.element.port_num,
+			      work->enforce_security);
+
+	/* GID event is notified already for individual GID entries by
+	 * dispatch_gid_change_event(). Hence, notifiy for rest of the
+	 * events.
+	 */
+	if (!ret && work->event.event != IB_EVENT_GID_CHANGE)
+		ib_dispatch_event_clients(&work->event);
+
+	kfree(work);
 }
 
-static void ib_cache_task(struct work_struct *_work)
+static void ib_generic_event_task(struct work_struct *_work)
 {
 	struct ib_update_work *work =
 		container_of(_work, struct ib_update_work, work);
 
-	ib_cache_update(work->device,
-			work->port_num,
-			work->enforce_security);
+	ib_dispatch_event_clients(&work->event);
 	kfree(work);
 }
 
-static void ib_cache_event(struct ib_event_handler *handler,
-			   struct ib_event *event)
+static bool is_cache_update_event(const struct ib_event *event)
+{
+	return (event->event == IB_EVENT_PORT_ERR    ||
+		event->event == IB_EVENT_PORT_ACTIVE ||
+		event->event == IB_EVENT_LID_CHANGE  ||
+		event->event == IB_EVENT_PKEY_CHANGE ||
+		event->event == IB_EVENT_CLIENT_REREGISTER ||
+		event->event == IB_EVENT_GID_CHANGE);
+}
+
+/**
+ * ib_dispatch_event - Dispatch an asynchronous event
+ * @event:Event to dispatch
+ *
+ * Low-level drivers must call ib_dispatch_event() to dispatch the
+ * event to all registered event handlers when an asynchronous event
+ * occurs.
+ */
+void ib_dispatch_event(const struct ib_event *event)
 {
 	struct ib_update_work *work;
 
-	if (event->event == IB_EVENT_PORT_ERR    ||
-	    event->event == IB_EVENT_PORT_ACTIVE ||
-	    event->event == IB_EVENT_LID_CHANGE  ||
-	    event->event == IB_EVENT_PKEY_CHANGE ||
-	    event->event == IB_EVENT_CLIENT_REREGISTER ||
-	    event->event == IB_EVENT_GID_CHANGE) {
-		work = kmalloc(sizeof *work, GFP_ATOMIC);
-		if (work) {
-			INIT_WORK(&work->work, ib_cache_task);
-			work->device   = event->device;
-			work->port_num = event->element.port_num;
-			if (event->event == IB_EVENT_PKEY_CHANGE ||
-			    event->event == IB_EVENT_GID_CHANGE)
-				work->enforce_security = true;
-			else
-				work->enforce_security = false;
-
-			queue_work(ib_wq, &work->work);
-		}
-	}
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return;
+
+	if (is_cache_update_event(event))
+		INIT_WORK(&work->work, ib_cache_event_task);
+	else
+		INIT_WORK(&work->work, ib_generic_event_task);
+
+	work->event = *event;
+	if (event->event == IB_EVENT_PKEY_CHANGE ||
+	    event->event == IB_EVENT_GID_CHANGE)
+		work->enforce_security = true;
+
+	queue_work(ib_wq, &work->work);
 }
+EXPORT_SYMBOL(ib_dispatch_event);
 
 int ib_cache_setup_one(struct ib_device *device)
 {
 	unsigned int p;
 	int err;
 
-	rwlock_init(&device->cache.lock);
+	rwlock_init(&device->cache_lock);
 
 	err = gid_table_setup_one(device);
 	if (err)
@@ -1505,9 +1539,6 @@ int ib_cache_setup_one(struct ib_device *device)
 	rdma_for_each_port (device, p)
 		ib_cache_update(device, p, true);
 
-	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
-			      device, ib_cache_event);
-	ib_register_event_handler(&device->cache.event_handler);
 	return 0;
 }
 
@@ -1529,14 +1560,12 @@ void ib_cache_release_one(struct ib_device *device)
 
 void ib_cache_cleanup_one(struct ib_device *device)
 {
-	/* The cleanup function unregisters the event handler,
-	 * waits for all in-progress workqueue elements and cleans
-	 * up the GID cache. This function should be called after
-	 * the device was removed from the devices list and all
-	 * clients were removed, so the cache exists but is
+	/* The cleanup function waits for all in-progress workqueue
+	 * elements and cleans up the GID cache. This function should be
+	 * called after the device was removed from the devices list and
+	 * all clients were removed, so the cache exists but is
 	 * non-functional and shouldn't be updated anymore.
 	 */
-	ib_unregister_event_handler(&device->cache.event_handler);
 	flush_workqueue(ib_wq);
 	gid_table_cleanup_one(device);