Re: [PATCH v5 2/2] rdma_rxe: use netlink messages to add/delete links

[Yanjun Zhu <yanjun.zhu@xxxxxxxxxx>]

On 2018/12/1 5:58, Steve Wise wrote:
> Add support for the RDMA_NLDEV_CMD_NEWLINK/DELLINK messages which allow
> dynamically adding new RXE links.  Deprecate the old module options
> for now.
>
> Cc: Moni Shoua <monis@xxxxxxxxxxxx>
> Signed-off-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx>
> ---
>   drivers/infiniband/sw/rxe/rxe.c       | 62 +++++++++++++++++++++++++++++++++--
>   drivers/infiniband/sw/rxe/rxe.h       |  2 +-
>   drivers/infiniband/sw/rxe/rxe_net.c   |  4 +--
>   drivers/infiniband/sw/rxe/rxe_net.h   |  2 +-
>   drivers/infiniband/sw/rxe/rxe_sysfs.c |  6 ++--
>   drivers/infiniband/sw/rxe/rxe_verbs.c |  4 +--
>   drivers/infiniband/sw/rxe/rxe_verbs.h |  2 +-
>   7 files changed, 70 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
> index 383e65c7bbc0..c09534b513ff 100644
> --- a/drivers/infiniband/sw/rxe/rxe.c
> +++ b/drivers/infiniband/sw/rxe/rxe.c
> @@ -31,6 +31,7 @@
>    * SOFTWARE.
>    */
>   
> +#include <rdma/rdma_netlink.h>
>   #include <net/addrconf.h>
>   #include "rxe.h"
>   #include "rxe_loc.h"
> @@ -308,7 +309,7 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
>   /* called by ifc layer to create new rxe device.
>    * The caller should allocate memory for rxe by calling ib_alloc_device.
>    */
> -int rxe_add(struct rxe_dev *rxe, unsigned int mtu)
> +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name)
>   {
>   	int err;
>   
> @@ -320,7 +321,7 @@ int rxe_add(struct rxe_dev *rxe, unsigned int mtu)
>   
>   	rxe_set_mtu(rxe, mtu);
>   
> -	err = rxe_register_device(rxe);
> +	err = rxe_register_device(rxe, ibdev_name);
>   	if (err)
>   		goto err1;
>   
> @@ -339,6 +340,59 @@ void rxe_remove(struct rxe_dev *rxe)
>   	rxe_dev_put(rxe);
>   }
>   
> +static struct ib_device *rxe_newlink(const char *ibdev_name,
> +				     const char *ndev_name)
> +{
> +	struct net_device *ndev = NULL;
> +	struct rxe_dev *rxe;
> +	int err = 0;
> +
> +	ndev = dev_get_by_name(&init_net, ndev_name);
> +	if (!ndev) {
> +		pr_err("interface %s not found\n", ndev_name);
> +		err = -ENODEV;
> +		goto err;
> +	}
> +
> +	if (net_to_rxe(ndev)) {
> +		pr_err("already configured on %s\n", ndev_name);
> +		err = -EEXIST;
> +		goto err;
> +	}
> +
> +	rxe = rxe_net_add(ibdev_name, ndev);
> +	if (!rxe) {
> +		pr_err("failed to add %s\n", ndev_name);
> +		err = -EINVAL;
> +		goto err;
> +	}
> +
> +	if (netif_running(ndev) && netif_carrier_ok(ndev))
> +		rxe_port_up(rxe);
> +	else
> +		rxe_port_down(rxe);
> +	pr_info("added %s to %s\n", rxe->ib_dev.name, ndev->name);
> +err:
> +	if (ndev)
> +		dev_put(ndev);
> +	return err ? ERR_PTR(err) : &rxe->ib_dev;
> +}
> +
> +static int rxe_dellink(struct ib_device *device)
> +{
> +	struct rxe_dev *rxe = to_rdev(device);
> +
diff --git a/drivers/infiniband/sw/rxe/rxe.c 
b/drivers/infiniband/sw/rxe/rxe.c
index c09534b513ff..e19d575d276f 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -382,7 +382,7 @@ static int rxe_dellink(struct ib_device *device)
 {
        struct rxe_dev *rxe = to_rdev(device);

-       list_del(&rxe->list);
+       rxe_net_remove(rxe);
        rxe_remove(rxe);
        return 0;
 }
diff --git a/drivers/infiniband/sw/rxe/rxe_net.c 
b/drivers/infiniband/sw/rxe/rxe_net.c
index 10a38b76f24b..1b57710008d3 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -573,6 +573,13 @@ struct rxe_dev *rxe_net_add(const char *ibdev_name, 
struct net_device *ndev)
        return rxe;
 }

+void rxe_net_remove(struct rxe_dev *rxe)
+{
+       spin_lock_bh(&dev_list_lock);
+       list_del(&rxe->list);
+       spin_unlock_bh(&dev_list_lock);
+}
+
 void rxe_remove_all(void)
 {
        spin_lock_bh(&dev_list_lock);
diff --git a/drivers/infiniband/sw/rxe/rxe_net.h 
b/drivers/infiniband/sw/rxe/rxe_net.h
index f8e00e6d5d38..45bf15fab87f 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.h
+++ b/drivers/infiniband/sw/rxe/rxe_net.h
@@ -44,6 +44,7 @@ struct rxe_recv_sockets {
 };

 struct rxe_dev *rxe_net_add(const char *ibdev_name, struct net_device 
*ndev);
+void rxe_net_remove(struct rxe_dev *rxe);

 int rxe_net_init(void);
 void rxe_net_exit(void);

> +	list_del(&rxe->list);

To avoid race, list_del(&rxe->list); should be replace the above.

If I am wrong, please correct me.

Zhu Yanjun

> +	rxe_remove(rxe);
> +	return 0;
> +}
> +
> +static struct rdma_link_ops rxe_link_ops = {
> +	.type = "rxe",
> +	.newlink = rxe_newlink,
> +	.dellink = rxe_dellink,
> +};
> +
>   static int __init rxe_module_init(void)
>   {
>   	int err;
> @@ -354,12 +408,14 @@ static int __init rxe_module_init(void)
>   	if (err)
>   		return err;
>   
> +	rdma_link_register(&rxe_link_ops);
>   	pr_info("loaded\n");
>   	return 0;
>   }
>   
>   static void __exit rxe_module_exit(void)
>   {
> +	rdma_link_unregister(&rxe_link_ops);
>   	rxe_remove_all();
>   	rxe_net_exit();
>   	rxe_cache_exit();
> @@ -369,3 +425,5 @@ static void __exit rxe_module_exit(void)
>   
>   late_initcall(rxe_module_init);
>   module_exit(rxe_module_exit);
> +
> +MODULE_ALIAS_RDMA_LINK("rxe");
> diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
> index 8f79bd86d033..e6e91fb14af8 100644
> --- a/drivers/infiniband/sw/rxe/rxe.h
> +++ b/drivers/infiniband/sw/rxe/rxe.h
> @@ -95,7 +95,7 @@ static inline u32 rxe_crc32(struct rxe_dev *rxe,
>   
>   void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu);
>   
> -int rxe_add(struct rxe_dev *rxe, unsigned int mtu);
> +int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name);
>   void rxe_remove(struct rxe_dev *rxe);
>   void rxe_remove_all(void);
>   
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
> index b26a8141f3ed..8bb908cae71b 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.c
> +++ b/drivers/infiniband/sw/rxe/rxe_net.c
> @@ -550,7 +550,7 @@ enum rdma_link_layer rxe_link_layer(struct rxe_dev *rxe, unsigned int port_num)
>   	return IB_LINK_LAYER_ETHERNET;
>   }
>   
> -struct rxe_dev *rxe_net_add(struct net_device *ndev)
> +struct rxe_dev *rxe_net_add(const char *ibdev_name, struct net_device *ndev)
>   {
>   	int err;
>   	struct rxe_dev *rxe = NULL;
> @@ -561,7 +561,7 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev)
>   
>   	rxe->ndev = ndev;
>   
> -	err = rxe_add(rxe, ndev->mtu);
> +	err = rxe_add(rxe, ndev->mtu, ibdev_name);
>   	if (err) {
>   		ib_dealloc_device(&rxe->ib_dev);
>   		return NULL;
> diff --git a/drivers/infiniband/sw/rxe/rxe_net.h b/drivers/infiniband/sw/rxe/rxe_net.h
> index 106c586dbb26..f8e00e6d5d38 100644
> --- a/drivers/infiniband/sw/rxe/rxe_net.h
> +++ b/drivers/infiniband/sw/rxe/rxe_net.h
> @@ -43,7 +43,7 @@ struct rxe_recv_sockets {
>   	struct socket *sk6;
>   };
>   
> -struct rxe_dev *rxe_net_add(struct net_device *ndev);
> +struct rxe_dev *rxe_net_add(const char *ibdev_name, struct net_device *ndev);
>   
>   int rxe_net_init(void);
>   void rxe_net_exit(void);
> diff --git a/drivers/infiniband/sw/rxe/rxe_sysfs.c b/drivers/infiniband/sw/rxe/rxe_sysfs.c
> index 73a19f808e1b..629f824d8d3e 100644
> --- a/drivers/infiniband/sw/rxe/rxe_sysfs.c
> +++ b/drivers/infiniband/sw/rxe/rxe_sysfs.c
> @@ -97,7 +97,7 @@ static int rxe_param_set_add(const char *val, const struct kernel_param *kp)
>   		goto err;
>   	}
>   
> -	rxe = rxe_net_add(ndev);
> +	rxe = rxe_net_add("rxe%d", ndev);
>   	if (!rxe) {
>   		pr_err("failed to add %s\n", intf);
>   		err = -EINVAL;
> @@ -152,6 +152,6 @@ static int rxe_param_set_remove(const char *val, const struct kernel_param *kp)
>   };
>   
>   module_param_cb(add, &rxe_add_ops, NULL, 0200);
> -MODULE_PARM_DESC(add, "Create RXE device over network interface");
> +MODULE_PARM_DESC(add, "DEPRECATED.  Create RXE device over network interface");
>   module_param_cb(remove, &rxe_remove_ops, NULL, 0200);
> -MODULE_PARM_DESC(remove, "Remove RXE device over network interface");
> +MODULE_PARM_DESC(remove, "DEPRECATED.  Remove RXE device over network interface");
> diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
> index 30817c79ba96..3536ca4627cd 100644
> --- a/drivers/infiniband/sw/rxe/rxe_verbs.c
> +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
> @@ -1165,7 +1165,7 @@ static ssize_t parent_show(struct device *device,
>   	.attrs = rxe_dev_attributes,
>   };
>   
> -int rxe_register_device(struct rxe_dev *rxe)
> +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name)
>   {
>   	int err;
>   	struct ib_device *dev = &rxe->ib_dev;
> @@ -1273,7 +1273,7 @@ int rxe_register_device(struct rxe_dev *rxe)
>   
>   	rdma_set_device_sysfs_group(dev, &rxe_attr_group);
>   	dev->driver_id = RDMA_DRIVER_RXE;
> -	err = ib_register_device(dev, "rxe%d", NULL);
> +	err = ib_register_device(dev, ibdev_name, NULL);
>   	if (err) {
>   		pr_warn("%s failed with error %d\n", __func__, err);
>   		goto err1;
> diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
> index 831381b7788d..c5f336d9aaf2 100644
> --- a/drivers/infiniband/sw/rxe/rxe_verbs.h
> +++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
> @@ -466,7 +466,7 @@ static inline struct rxe_mem *to_rmw(struct ib_mw *mw)
>   	return mw ? container_of(mw, struct rxe_mem, ibmw) : NULL;
>   }
>   
> -int rxe_register_device(struct rxe_dev *rxe);
> +int rxe_register_device(struct rxe_dev *rxe, const char *ibdev_name);
>   void rxe_unregister_device(struct rxe_dev *rxe);
>   
>   void rxe_mc_cleanup(struct rxe_pool_entry *arg);