diff mbox

[for-next,V6,04/10] IB/core: Add rwsem to allow reading device list or client list

Message ID 1435150766-6803-5-git-send-email-matanb@mellanox.com (mailing list archive)
State Changes Requested
Headers show

Commit Message

Matan Barak June 24, 2015, 12:59 p.m. UTC 
From: Haggai Eran <haggaie@mellanox.com>

Currently the RDMA subsystem's device list and client list are
protected by a single mutex. This prevents adding user-facing APIs
that iterate these lists, since using them may cause a deadlock.
The patch attempts to solve this problem by adding a read-write
semaphore to protect the lists. Readers now don't need the mutex,
and are safe just by read-locking the semaphore.

The ib_register_device, ib_register_client, ib_unregister_device, and
ib_unregister_client functions are modified to lock the semaphore for
write during their respective list modification. Also, in order to
make sure client callbacks are called only between add() and remove()
calls, the code is changed to only add items to the lists after the
add() calls and remove from the lists before the remove() calls.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Matan Barak <matanb@mellanox.com>
---
 drivers/infiniband/core/device.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)

Comments

Jason Gunthorpe July 13, 2015, 5:29 p.m. UTC | #1 
On Wed, Jun 24, 2015 at 03:59:20PM +0300, Matan Barak wrote:
> From: Haggai Eran <haggaie@mellanox.com>
> 
> Currently the RDMA subsystem's device list and client list are
> protected by a single mutex. This prevents adding user-facing APIs
> that iterate these lists, since using them may cause a deadlock.
> The patch attempts to solve this problem by adding a read-write
> semaphore to protect the lists. Readers now don't need the mutex,
> and are safe just by read-locking the semaphore.
> 
> The ib_register_device, ib_register_client, ib_unregister_device, and
> ib_unregister_client functions are modified to lock the semaphore for
> write during their respective list modification. Also, in order to
> make sure client callbacks are called only between add() and remove()
> calls, the code is changed to only add items to the lists after the
> add() calls and remove from the lists before the remove() calls.
> 
> Signed-off-by: Haggai Eran <haggaie@mellanox.com>
> Signed-off-by: Matan Barak <matanb@mellanox.com>

Looks OK

Reviewed-By: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>

Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 9567756..f08d438 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -55,17 +55,24 @@  struct ib_client_data {
 struct workqueue_struct *ib_wq;
 EXPORT_SYMBOL_GPL(ib_wq);
 
+/* The device_list and client_list contain devices and clients after their
+ * registration has completed, and the devices and clients are removed
+ * during unregistration. */
 static LIST_HEAD(device_list);
 static LIST_HEAD(client_list);
 
 /*
- * device_mutex protects access to both device_list and client_list.
- * There's no real point to using multiple locks or something fancier
- * like an rwsem: we always access both lists, and we're always
- * modifying one list or the other list.  In any case this is not a
- * hot path so there's no point in trying to optimize.
+ * device_mutex and lists_rwsem protect access to both device_list and
+ * client_list.  device_mutex protects writer access by device and client
+ * registration / de-registration.  lists_rwsem protects reader access to
+ * these lists.  Iterators of these lists must lock it for read, while updates
+ * to the lists must be done with a write lock. A special case is when the
+ * device_mutex is locked. In this case locking the lists for read access is
+ * not necessary as the device_mutex implies it.
  */
 static DEFINE_MUTEX(device_mutex);
+static DECLARE_RWSEM(lists_rwsem);
+
 
 static int ib_device_check_mandatory(struct ib_device *device)
 {
@@ -305,8 +312,6 @@  int ib_register_device(struct ib_device *device,
 		goto out;
 	}
 
-	list_add_tail(&device->core_list, &device_list);
-
 	device->reg_state = IB_DEV_REGISTERED;
 
 	{
@@ -317,6 +322,10 @@  int ib_register_device(struct ib_device *device,
 				client->add(device);
 	}
 
+	down_write(&lists_rwsem);
+	list_add_tail(&device->core_list, &device_list);
+	up_write(&lists_rwsem);
+
  out:
 	mutex_unlock(&device_mutex);
 	return ret;
@@ -337,12 +346,14 @@  void ib_unregister_device(struct ib_device *device)
 
 	mutex_lock(&device_mutex);
 
+	down_write(&lists_rwsem);
+	list_del(&device->core_list);
+	up_write(&lists_rwsem);
+
 	list_for_each_entry_reverse(client, &client_list, list)
 		if (client->remove)
 			client->remove(device);
 
-	list_del(&device->core_list);
-
 	mutex_unlock(&device_mutex);
 
 	ib_device_unregister_sysfs(device);
@@ -375,11 +386,14 @@  int ib_register_client(struct ib_client *client)
 
 	mutex_lock(&device_mutex);
 
-	list_add_tail(&client->list, &client_list);
 	list_for_each_entry(device, &device_list, core_list)
 		if (client->add && !add_client_context(device, client))
 			client->add(device);
 
+	down_write(&lists_rwsem);
+	list_add_tail(&client->list, &client_list);
+	up_write(&lists_rwsem);
+
 	mutex_unlock(&device_mutex);
 
 	return 0;
@@ -402,6 +416,10 @@  void ib_unregister_client(struct ib_client *client)
 
 	mutex_lock(&device_mutex);
 
+	down_write(&lists_rwsem);
+	list_del(&client->list);
+	up_write(&lists_rwsem);
+
 	list_for_each_entry(device, &device_list, core_list) {
 		if (client->remove)
 			client->remove(device);
@@ -414,7 +432,6 @@  void ib_unregister_client(struct ib_client *client)
 			}
 		spin_unlock_irqrestore(&device->client_data_lock, flags);
 	}
-	list_del(&client->list);
 
 	mutex_unlock(&device_mutex);
 }