RDMA/nldev: provide detailed MR information

Implement the RDMA nldev netlink interface for dumping detailed
MR information.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/core/nldev.c

@@ -85,6 +85,12 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_RES_CQE]		= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_RES_USECNT]		= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_RES_POLL_CTX]		= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_RES_MR]		= { .type = NLA_NESTED },
+	[RDMA_NLDEV_ATTR_RES_MR_ENTRY]		= { .type = NLA_NESTED },
+	[RDMA_NLDEV_ATTR_RES_RKEY]		= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_RES_LKEY]		= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_RES_IOVA]		= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_RES_MRLEN]		= { .type = NLA_U64 },
 };
 
 static int fill_nldev_handle(struct sk_buff *msg, struct ib_device *device)
@@ -197,6 +203,7 @@ static int fill_res_info(struct sk_buff *msg, struct ib_device *device)
 		[RDMA_RESTRACK_CQ] = "cq",
 		[RDMA_RESTRACK_QP] = "qp",
 		[RDMA_RESTRACK_CM_ID] = "cm_id",
+		[RDMA_RESTRACK_MR] = "mr",
 	};
 
 	struct rdma_restrack_root *res = &device->res;
@@ -397,6 +404,41 @@ static int fill_res_cq_entry(struct sk_buff *msg, struct netlink_callback *cb,
 	return -EMSGSIZE;
 }
 
+static int fill_res_mr_entry(struct sk_buff *msg, struct netlink_callback *cb,
+			     struct rdma_restrack_entry *res, uint32_t port)
+{
+	struct ib_mr *mr = container_of(res, struct ib_mr, res);
+	struct nlattr *entry_attr;
+
+	entry_attr = nla_nest_start(msg, RDMA_NLDEV_ATTR_RES_MR_ENTRY);
+	if (!entry_attr)
+		goto out;
+
+	if (netlink_capable(cb->skb, CAP_NET_ADMIN)) {
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_RKEY, mr->rkey))
+			goto err;
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_LKEY, mr->lkey))
+			goto err;
+		if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_IOVA,
+				      mr->iova, 0))
+			goto err;
+	}
+
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_RES_MRLEN, mr->length, 0))
+		goto err;
+
+	if (fill_res_name_pid(msg, res))
+		goto err;
+
+	nla_nest_end(msg, entry_attr);
+	return 0;
+
+err:
+	nla_nest_cancel(msg, entry_attr);
+out:
+	return -EMSGSIZE;
+}
+
 static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
@@ -694,6 +736,11 @@ static const struct nldev_fill_res_entry fill_entries[RDMA_RESTRACK_MAX] = {
 		.nldev_cmd = RDMA_NLDEV_CMD_RES_CQ_GET,
 		.nldev_attr = RDMA_NLDEV_ATTR_RES_CQ,
 	},
+	[RDMA_RESTRACK_MR] = {
+		.fill_res_func = fill_res_mr_entry,
+		.nldev_cmd = RDMA_NLDEV_CMD_RES_MR_GET,
+		.nldev_attr = RDMA_NLDEV_ATTR_RES_MR,
+	},
 };
 
 static int res_get_common_dumpit(struct sk_buff *skb,
@@ -848,6 +895,12 @@ static int nldev_res_get_cq_dumpit(struct sk_buff *skb,
 	return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_CQ);
 }
 
+static int nldev_res_get_mr_dumpit(struct sk_buff *skb,
+				   struct netlink_callback *cb)
+{
+	return res_get_common_dumpit(skb, cb, RDMA_RESTRACK_MR);
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
@@ -880,6 +933,9 @@ static const struct rdma_nl_cbs nldev_cb_table[RDMA_NLDEV_NUM_OPS] = {
 	[RDMA_NLDEV_CMD_RES_CQ_GET] = {
 		.dump = nldev_res_get_cq_dumpit,
 	},
+	[RDMA_NLDEV_CMD_RES_MR_GET] = {
+		.dump = nldev_res_get_mr_dumpit,
+	},
 };
 
 void __init nldev_init(void)

drivers/infiniband/core/restrack.c

@@ -43,22 +43,28 @@ EXPORT_SYMBOL(rdma_restrack_count);
 
 static void set_kern_name(struct rdma_restrack_entry *res)
 {
-	enum rdma_restrack_type type = res->type;
-	struct ib_qp *qp;
+	struct ib_pd *pd;
 
-	if (type != RDMA_RESTRACK_QP)
-		/* Other types already have this name embedded in */
-		return;
-
-	qp = container_of(res, struct ib_qp, res);
-	if (!qp->pd) {
+	switch (res->type) {
+	case RDMA_RESTRACK_QP:
+		pd = container_of(res, struct ib_qp, res)->pd;
+		if (!pd) {
 			WARN_ONCE(true, "XRC QPs are not supported\n");
 			/* Survive, despite the programmer's error */
 			res->kern_name = " ";
-		return;
+		}
+		break;
+	case RDMA_RESTRACK_MR:
+		pd = container_of(res, struct ib_mr, res)->pd;
+		break;
+	default:
+		/* Other types set kern_name directly */
+		pd = NULL;
+		break;
 	}
 
-	res->kern_name = qp->pd->res.kern_name;
+	if (pd)
+		res->kern_name = pd->res.kern_name;
 }
 
 static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
@@ -73,6 +79,8 @@ static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
 	case RDMA_RESTRACK_CM_ID:
 		return container_of(res, struct rdma_id_private,
 				    res)->id.device;
+	case RDMA_RESTRACK_MR:
+		return container_of(res, struct ib_mr, res)->device;
 	default:
 		WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
 		return NULL;
@@ -90,6 +98,8 @@ static bool res_is_user(struct rdma_restrack_entry *res)
 		return container_of(res, struct ib_qp, res)->uobject;
 	case RDMA_RESTRACK_CM_ID:
 		return !res->kern_name;
+	case RDMA_RESTRACK_MR:
+		return container_of(res, struct ib_mr, res)->pd->uobject;
 	default:
 		WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
 		return false;

drivers/infiniband/core/uverbs_cmd.c

@@ -693,6 +693,8 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 	mr->pd      = pd;
 	mr->uobject = uobj;
 	atomic_inc(&pd->usecnt);
+	mr->res.type = RDMA_RESTRACK_MR;
+	rdma_restrack_add(&mr->res);
 
 	uobj->object = mr;
 

drivers/infiniband/core/verbs.c

@@ -1622,6 +1622,7 @@ int ib_dereg_mr(struct ib_mr *mr)
 	struct ib_pd *pd = mr->pd;
 	int ret;
 
+	rdma_restrack_del(&mr->res);
 	ret = mr->device->dereg_mr(mr);
 	if (!ret)
 		atomic_dec(&pd->usecnt);
@@ -1658,6 +1659,8 @@ struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
 		mr->uobject = NULL;
 		atomic_inc(&pd->usecnt);
 		mr->need_inval = false;
+		mr->res.type = RDMA_RESTRACK_MR;
+		rdma_restrack_add(&mr->res);
 	}
 
 	return mr;

include/rdma/ib_verbs.h

@@ -1772,6 +1772,11 @@ struct ib_mr {
 		struct ib_uobject	*uobject;	/* user */
 		struct list_head	qp_entry;	/* FR */
 	};
+
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct rdma_restrack_entry res;
 };
 
 struct ib_mw {

include/rdma/restrack.h

@@ -33,6 +33,10 @@ enum rdma_restrack_type {
 	 * @RDMA_RESTRACK_CM_ID: Connection Manager ID (CM_ID)
 	 */
 	RDMA_RESTRACK_CM_ID,
+	/**
+	 * @RDMA_RESTRACK_MR: Memory Region (MR)
+	 */
+	RDMA_RESTRACK_MR,
 	/**
 	 * @RDMA_RESTRACK_MAX: Last entry, used for array dclarations
 	 */

include/uapi/rdma/rdma_netlink.h

@@ -242,6 +242,8 @@ enum rdma_nldev_command {
 
 	RDMA_NLDEV_CMD_RES_CQ_GET, /* can dump */
 
+	RDMA_NLDEV_CMD_RES_MR_GET, /* can dump */
+
 	RDMA_NLDEV_NUM_OPS
 };
 
@@ -372,6 +374,13 @@ enum rdma_nldev_attr {
 	RDMA_NLDEV_ATTR_RES_USECNT,		/* u64 */
 	RDMA_NLDEV_ATTR_RES_POLL_CTX,		/* u8 */
 
+	RDMA_NLDEV_ATTR_RES_MR,			/* nested table */
+	RDMA_NLDEV_ATTR_RES_MR_ENTRY,		/* nested table */
+	RDMA_NLDEV_ATTR_RES_RKEY,		/* u32 */
+	RDMA_NLDEV_ATTR_RES_LKEY,		/* u32 */
+	RDMA_NLDEV_ATTR_RES_IOVA,		/* u64 */
+	RDMA_NLDEV_ATTR_RES_MRLEN,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */