[PATCH rdma-next 02/13] RDMA/core: Handle device name conflicts when changing net namespace

[Jiri Pirko <jiri@resnulli.us>]

From: Jiri Pirko <jiri@nvidia.com>

Prepare namespace moves for per-netns names. Check user-initiated moves for
destination-name conflicts before disabling the device, keep same-netns
moves as no-ops, and make teardown moves detach from the exiting namespace
even if fallback naming fails.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
---
 drivers/infiniband/core/device.c | 155 ++++++++++++++++++++++++++-----
 drivers/infiniband/core/nldev.c  |   3 +
 2 files changed, 137 insertions(+), 21 deletions(-)

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index de610f52c9b2..8d169658e312 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -268,7 +268,7 @@ static struct notifier_block ibdev_lsm_nb = {
 };
 
 static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
-				 struct net *net);
+				 struct net *net, const char *fallback_pattern);
 
 /* Pointer to the RCU head at the start of the ib_port_data array */
 struct ib_port_data_rcu {
@@ -437,7 +437,8 @@ int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
 }
 
 /* Pick a free index for the '%d' style @name pattern. */
-static int alloc_name_id(struct net *net, const char *name)
+static int __alloc_name_id(struct net *net, const char *name,
+			   const struct ib_device *skip)
 {
 	struct ib_device *device;
 	unsigned long index;
@@ -450,6 +451,8 @@ static int alloc_name_id(struct net *net, const char *name)
 	xa_for_each (&devices, index, device) {
 		char buf[IB_DEVICE_NAME_MAX];
 
+		if (device == skip)
+			continue;
 		if (sscanf(dev_name(&device->dev), name, &i) != 1)
 			continue;
 		if (i < 0 || i >= INT_MAX)
@@ -469,6 +472,11 @@ static int alloc_name_id(struct net *net, const char *name)
 	return rc;
 }
 
+static int alloc_name_id(struct net *net, const char *name)
+{
+	return __alloc_name_id(net, name, NULL);
+}
+
 static int alloc_name(struct ib_device *ibdev, const char *name)
 {
 	int id;
@@ -1160,8 +1168,17 @@ static void rdma_dev_exit_net(struct net *net)
 
 		/*
 		 * If the real device is in the NS then move it back to init.
+		 * Provide a fallback pattern so a name conflict in init_net
+		 * cannot make the teardown move fail.
 		 */
-		rdma_dev_change_netns(dev, net, &init_net);
+		if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
+			ret = rdma_dev_change_netns(dev, net, &init_net,
+						    "ibdev%d");
+			if (ret)
+				WARN(1,
+				     "Failed to move RDMA device %s to init_net on netns exit: %d\n",
+				     dev_name(&dev->dev), ret);
+		}
 
 		put_device(&dev->dev);
 		down_read(&devices_rwsem);
@@ -1680,14 +1697,71 @@ void ib_unregister_device_queued(struct ib_device *ib_dev)
 }
 EXPORT_SYMBOL(ib_unregister_device_queued);
 
+static bool rdma_dev_name_in_netns(struct ib_device *skip, struct net *net,
+				   const char *name)
+{
+	struct ib_device *device;
+	unsigned long index;
+
+	lockdep_assert_held_write(&devices_rwsem);
+
+	xa_for_each(&devices, index, device)
+		if (device != skip &&
+		    !strcmp(name, dev_name(&device->dev)))
+			return true;
+
+	return false;
+}
+
+/*
+ * Choose the name @device should use in net namespace @net: keep the current
+ * name when it is free, otherwise use a trusted '%d' @fallback_pattern
+ * (namespace teardown) to pick a free index. The caller must hold the write
+ * side of devices_rwsem.
+ */
+static int rdma_dev_pick_netns_name(struct ib_device *device, struct net *net,
+				    const char *fallback_pattern,
+				    char *buf, size_t buf_len,
+				    const char **new_name)
+{
+	int id;
+
+	lockdep_assert_held_write(&devices_rwsem);
+
+	if (!rdma_dev_name_in_netns(device, net, dev_name(&device->dev))) {
+		*new_name = dev_name(&device->dev);
+		return 0;
+	}
+
+	if (!fallback_pattern)
+		return -EEXIST;
+
+	snprintf(buf, buf_len, "ibdev%u", device->index);
+	if (!rdma_dev_name_in_netns(device, net, buf)) {
+		*new_name = buf;
+		return 0;
+	}
+
+	id = __alloc_name_id(net, fallback_pattern, device);
+	if (id < 0)
+		return id;
+	snprintf(buf, buf_len, fallback_pattern, id);
+	*new_name = buf;
+	return 0;
+}
+
 /*
  * The caller must pass in a device that has the kref held and the refcount
  * released. If the device is in cur_net and still registered then it is moved
  * into net.
+ *
+ * Naming rules are handled by rdma_dev_pick_netns_name().
  */
 static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
-				 struct net *net)
+				 struct net *net, const char *fallback_pattern)
 {
+	char buf[IB_DEVICE_NAME_MAX];
+	const char *new_name;
 	int ret2 = -EINVAL;
 	int ret;
 
@@ -1704,30 +1778,63 @@ static int rdma_dev_change_netns(struct ib_device *device, struct net *cur_net,
 		goto out;
 	}
 
+	if (!fallback_pattern) {
+		/*
+		 * Reject a predictable name conflict before tearing anything
+		 * down, so a doomed user move does not disable a live device.
+		 */
+		down_write(&devices_rwsem);
+		ret = rdma_dev_pick_netns_name(device, net, fallback_pattern,
+					       buf, sizeof(buf), &new_name);
+		up_write(&devices_rwsem);
+		if (ret)
+			goto out;
+	}
+
 	kobject_uevent(&device->dev.kobj, KOBJ_REMOVE);
 	disable_device(device);
 
 	/*
-	 * At this point no one can be using the device, so it is safe to
-	 * change the namespace.
+	 * Recompute the destination name under the write side of devices_rwsem
+	 * now that the device is disabled, closing races with a concurrent
+	 * registration or rename, then publish the new namespace at the sysfs
+	 * level.
 	 */
-	write_pnet(&device->coredev.rdma_net, net);
+	down_write(&devices_rwsem);
+	ret = rdma_dev_pick_netns_name(device, net, fallback_pattern, buf,
+				       sizeof(buf), &new_name);
+	if (ret) {
+		if (fallback_pattern) {
+			WARN(1,
+			     "%s: failed to pick device name during namespace teardown: %d\n",
+			     __func__, ret);
+			write_pnet(&device->coredev.rdma_net, net);
+			ret = 0;
+		}
+		goto rename_done;
+	}
 
-	down_read(&devices_rwsem);
-	/*
-	 * Currently rdma devices are system wide unique. So the device name
-	 * is guaranteed free in the new namespace. Publish the new namespace
-	 * at the sysfs level.
-	 */
-	ret = device_rename(&device->dev, dev_name(&device->dev));
-	up_read(&devices_rwsem);
+	write_pnet(&device->coredev.rdma_net, net);
+	ret = device_rename(&device->dev, new_name);
 	if (ret) {
-		dev_warn(&device->dev,
-			 "%s: Couldn't rename device after namespace change\n",
-			 __func__);
-		/* Try and put things back and re-enable the device */
-		write_pnet(&device->coredev.rdma_net, cur_net);
+		if (fallback_pattern) {
+			WARN(1,
+			     "%s: failed to rename device during namespace teardown: %d\n",
+			     __func__, ret);
+			ret = 0;
+		} else {
+			dev_warn(&device->dev,
+				 "%s: Couldn't rename device after namespace change\n",
+				 __func__);
+			/* Try and put things back and re-enable the device */
+			write_pnet(&device->coredev.rdma_net, cur_net);
+		}
+	} else {
+		strscpy(device->name, dev_name(&device->dev),
+			IB_DEVICE_NAME_MAX);
 	}
+rename_done:
+	up_write(&devices_rwsem);
 
 	ret2 = enable_device_and_get(device);
 	if (ret2) {
@@ -1766,6 +1873,12 @@ int ib_device_set_netns_put(struct sk_buff *skb,
 		goto ns_err;
 	}
 
+	/* Moving a device to the namespace it already lives in is a no-op. */
+	if (net_eq(net, read_pnet(&dev->coredev.rdma_net))) {
+		ret = 0;
+		goto ns_err;
+	}
+
 	/*
 	 * All the ib_clients, including uverbs, are reset when the namespace is
 	 * changed and this cannot be blocked waiting for userspace to do
@@ -1778,7 +1891,7 @@ int ib_device_set_netns_put(struct sk_buff *skb,
 
 	get_device(&dev->dev);
 	ib_device_put(dev);
-	ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net);
+	ret = rdma_dev_change_netns(dev, current->nsproxy->net_ns, net, NULL);
 	put_device(&dev->dev);
 
 	put_net(net);
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index f599c24b34e8..3a9ec43a16f1 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -1195,6 +1195,9 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 		ns_fd = nla_get_u32(tb[RDMA_NLDEV_NET_NS_FD]);
 		err = ib_device_set_netns_put(skb, device, ns_fd);
+		if (err == -EEXIST)
+			NL_SET_ERR_MSG(extack,
+				       "Device name already exists in the target net namespace");
 		goto put_done;
 	}
 
-- 
2.54.0