IB/core: Let IB core distribute cache update events

Currently when the low level driver notifies Pkey, GID, and port change
events they are notified to the registered handlers in the order they are
registered.

IB core and other ULPs such as IPoIB are interested in GID, LID, Pkey
change events.

Since all GID queries done by ULPs are serviced by IB core, and the IB
core deferes cache updates to a work queue, it is possible for other
clients to see stale cache data when they handle their own events.

For example, the below call tree shows how ipoib will call
rdma_query_gid() concurrently with the update to the cache sitting in the
WQ.

mlx5_ib_handle_event()
  ib_dispatch_event()
    ib_cache_event()
       queue_work() -> slow cache update

    [..]
    ipoib_event()
     queue_work()
       [..]
       work handler
         ipoib_ib_dev_flush_light()
           __ipoib_ib_dev_flush()
              ipoib_dev_addr_changed_valid()
                rdma_query_gid() <- Returns old GID, cache not updated.

Move all the event dispatch to a work queue so that the cache update is
always done before any clients are notified.

Fixes: f35faa4ba956 ("IB/core: Simplify ib_query_gid to always refer to cache")
Link: https://lore.kernel.org/r/20191212113024.336702-3-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 75 insertions, 46 deletions

diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
index d535995711c3..e55f345799e4 100644
--- a/drivers/infiniband/core/cache.c
+++ b/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[] = {
@@ -1381,9 +1380,8 @@ err:
 	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;
@@ -1391,11 +1389,11 @@ static void ib_cache_update(struct ib_device *device,
 	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;
 
@@ -1446,50 +1446,84 @@ 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)
 {
@@ -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);