RDMA/nldev: Added configuration of RDMA dynamic interrupt moderation to netlink

Added parameter in ib_device for enabling dynamic interrupt moderation so
that it can be configured in userspace using rdma tool.

In order to set adaptive-moderation for an ib device the command is:
rdma dev set [DEV] adaptive-moderation [on|off]
Please set on/off.

rdma dev show
0: mlx5_0: node_type ca fw 16.26.0055 node_guid 248a:0703:00a5:29d0
sys_image_guid 248a:0703:00a5:29d0 adaptive-moderation on

rdma resource show cq
dev mlx5_0 cqn 0 cqe 1023 users 4 poll-ctx UNBOUND_WORKQUEUE
adaptive-moderation off comm [ib_core]
Signed-off-by: Yamin Friedman <yaminf@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/Kconfig

@@ -7,6 +7,7 @@ menuconfig INFINIBAND
 	depends on m || IPV6 != m
 	depends on !ALPHA
 	select IRQ_POLL
+	select DIMLIB
 	---help---
 	  Core support for InfiniBand (IB).  Make sure to also select
 	  any protocols you wish to use as well as drivers for your

drivers/infiniband/core/core_priv.h

@@ -60,6 +60,7 @@ extern bool ib_devices_shared_netns;
 int ib_device_register_sysfs(struct ib_device *device);
 void ib_device_unregister_sysfs(struct ib_device *device);
 int ib_device_rename(struct ib_device *ibdev, const char *name);
+int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim);
 
 typedef void (*roce_netdev_callback)(struct ib_device *device, u8 port,
 	      struct net_device *idev, void *cookie);

drivers/infiniband/core/device.c

@@ -448,6 +448,15 @@ int ib_device_rename(struct ib_device *ibdev, const char *name)
 	return 0;
 }
 
+int ib_device_set_dim(struct ib_device *ibdev, u8 use_dim)
+{
+	if (use_dim > 1)
+		return -EINVAL;
+	ibdev->use_cq_dim = use_dim;
+
+	return 0;
+}
+
 static int alloc_name(struct ib_device *ibdev, const char *name)
 {
 	struct ib_device *device;

drivers/infiniband/core/nldev.c

@@ -52,6 +52,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 					.len = RDMA_NLDEV_ATTR_EMPTY_STRING },
 	[RDMA_NLDEV_ATTR_CHARDEV_TYPE]		= { .type = NLA_NUL_STRING,
 					.len = RDMA_NLDEV_ATTR_CHARDEV_TYPE_SIZE },
+	[RDMA_NLDEV_ATTR_DEV_DIM]               = { .type = NLA_U8 },
 	[RDMA_NLDEV_ATTR_DEV_INDEX]		= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_DEV_NAME]		= { .type = NLA_NUL_STRING,
 					.len = IB_DEVICE_NAME_MAX },
@@ -252,6 +253,8 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 		return -EMSGSIZE;
 	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_NODE_TYPE, device->node_type))
 		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, device->use_cq_dim))
+		return -EMSGSIZE;
 
 	/*
 	 * Link type is determined on first port and mlx4 device
@@ -552,6 +555,9 @@ static int fill_res_cq_entry(struct sk_buff *msg, bool has_cap_net_admin,
 	    nla_put_u8(msg, RDMA_NLDEV_ATTR_RES_POLL_CTX, cq->poll_ctx))
 		goto err;
 
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_DEV_DIM, (cq->dim != NULL)))
+		goto err;
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_CQN, res->id))
 		goto err;
 	if (!rdma_is_kernel_res(res) &&
@@ -870,6 +876,14 @@ static int nldev_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto put_done;
 	}
 
+	if (tb[RDMA_NLDEV_ATTR_DEV_DIM]) {
+		u8 use_dim;
+
+		use_dim = nla_get_u8(tb[RDMA_NLDEV_ATTR_DEV_DIM]);
+		err = ib_device_set_dim(device,  use_dim);
+		goto done;
+	}
+
 done:
 	ib_device_put(device);
 put_done:

include/uapi/rdma/rdma_netlink.h

@@ -520,6 +520,11 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_NAME,	/* string */
 	RDMA_NLDEV_ATTR_STAT_HWCOUNTER_ENTRY_VALUE,	/* u64 */
 
+	/*
+	 * CQ adaptive moderatio (DIM)
+	 */
+	RDMA_NLDEV_ATTR_DEV_DIM,                /* u8 */
+
 	/*
 	 * Always the end
 	 */