RDMA/nldev: Provide MR statistics

Add RDMA nldev netlink interface for dumping MR statistics information.

Output example:

$ ./ibv_rc_pingpong -o -P -s 500000000
local address: LID 0x0001, QPN 0x00008a, PSN 0xf81096, GID ::

$ rdma stat show mr
dev mlx5_0 mrn 2 page_faults 122071 page_invalidations 0

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Erez Alfasi <[e-mail]>
Signed-off-by: Leon Romanovsky <[e-mail]>
Reviewed-by: Jason Gunthorpe <[e-mail]>
Signed-off-by: Jason Gunthorpe <[e-mail]>

drivers/infiniband/core/device.c

···
 	SET_DEVICE_OP(dev_ops, drain_sq);
 	SET_DEVICE_OP(dev_ops, enable_driver);
 	SET_DEVICE_OP(dev_ops, fill_res_entry);
+	SET_DEVICE_OP(dev_ops, fill_stat_entry);
 	SET_DEVICE_OP(dev_ops, get_dev_fw_str);
 	SET_DEVICE_OP(dev_ops, get_dma_mr);
 	SET_DEVICE_OP(dev_ops, get_hw_stats);

drivers/infiniband/core/nldev.c

···
 	return dev->ops.fill_res_entry(msg, res);
 }
 
+static bool fill_stat_entry(struct ib_device *dev, struct sk_buff *msg,
+			    struct rdma_restrack_entry *res)
+{
+	if (!dev->ops.fill_stat_entry)
+		return false;
+	return dev->ops.fill_stat_entry(msg, res);
+}
+
 static int fill_res_qp_entry(struct sk_buff *msg, bool has_cap_net_admin,
 			     struct rdma_restrack_entry *res, uint32_t port)
 {
···
 	return ret;
 }
 
-static int fill_stat_hwcounter_entry(struct sk_buff *msg,
-				     const char *name, u64 value)
+int rdma_nl_stat_hwcounter_entry(struct sk_buff *msg, const char *name,
+				 u64 value)
 {
 	struct nlattr *entry_attr;
 
···
 	nla_nest_cancel(msg, entry_attr);
 	return -EMSGSIZE;
 }
+EXPORT_SYMBOL(rdma_nl_stat_hwcounter_entry);
+
+static int fill_stat_mr_entry(struct sk_buff *msg, bool has_cap_net_admin,
+			      struct rdma_restrack_entry *res, uint32_t port)
+{
+	struct ib_mr *mr = container_of(res, struct ib_mr, res);
+	struct ib_device *dev = mr->pd->device;
+
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_RES_MRN, res->id))
+		goto err;
+
+	if (fill_stat_entry(dev, msg, res))
+		goto err;
+
+	return 0;
+
+err:
+	return -EMSGSIZE;
+}
 
 static int fill_stat_counter_hwcounters(struct sk_buff *msg,
 					struct rdma_counter *counter)
···
 		return -EMSGSIZE;
 
 	for (i = 0; i < st->num_counters; i++)
-		if (fill_stat_hwcounter_entry(msg, st->names[i], st->value[i]))
+		if (rdma_nl_stat_hwcounter_entry(msg, st->names[i], st->value[i]))
 			goto err;
 
 	nla_nest_end(msg, table_attr);
···
 	for (i = 0; i < num_cnts; i++) {
 		v = stats->value[i] +
 			rdma_counter_get_hwstat_value(device, port, i);
-		if (fill_stat_hwcounter_entry(msg, stats->names[i], v)) {
+		if (rdma_nl_stat_hwcounter_entry(msg, stats->names[i], v)) {
 			ret = -EMSGSIZE;
 			goto err_table;
 		}
···
 	case RDMA_NLDEV_ATTR_RES_QP:
 		ret = stat_get_doit_qp(skb, nlh, extack, tb);
 		break;
-
+	case RDMA_NLDEV_ATTR_RES_MR:
+		ret = res_get_common_doit(skb, nlh, extack, RDMA_RESTRACK_MR,
+					  fill_stat_mr_entry);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
···
 	case RDMA_NLDEV_ATTR_RES_QP:
 		ret = nldev_res_get_counter_dumpit(skb, cb);
 		break;
-
+	case RDMA_NLDEV_ATTR_RES_MR:
+		ret = res_get_common_dumpit(skb, cb, RDMA_RESTRACK_MR,
+					    fill_stat_mr_entry);
+		break;
 	default:
 		ret = -EINVAL;
 		break;

drivers/infiniband/hw/mlx5/main.c

···
 #include <rdma/uverbs_std_types.h>
 #include <rdma/mlx5_user_ioctl_verbs.h>
 #include <rdma/mlx5_user_ioctl_cmds.h>
+#include <rdma/ib_umem_odp.h>
 
 #define UVERBS_MODULE_NAME mlx5_ib
 #include <rdma/uverbs_named_ioctl.h>
···
 	.drain_rq = mlx5_ib_drain_rq,
 	.drain_sq = mlx5_ib_drain_sq,
 	.fill_res_entry = mlx5_ib_fill_res_entry,
+	.fill_stat_entry = mlx5_ib_fill_stat_entry,
 	.get_dev_fw_str = get_dev_fw_str,
 	.get_dma_mr = mlx5_ib_get_dma_mr,
 	.get_link_layer = mlx5_ib_port_link_layer,

drivers/infiniband/hw/mlx5/mlx5_ib.h

···
 				  u8 port_num);
 int mlx5_ib_fill_res_entry(struct sk_buff *msg,
 			   struct rdma_restrack_entry *res);
+int mlx5_ib_fill_stat_entry(struct sk_buff *msg,
+			    struct rdma_restrack_entry *res);
 
 #if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
 int mlx5_ib_devx_create(struct mlx5_ib_dev *dev, bool is_user);

drivers/infiniband/hw/mlx5/restrack.c

···
 #include <rdma/restrack.h>
 #include "mlx5_ib.h"
 
+static int fill_stat_mr_entry(struct sk_buff *msg,
+			      struct rdma_restrack_entry *res)
+{
+	struct ib_mr *ibmr = container_of(res, struct ib_mr, res);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	struct nlattr *table_attr;
+
+	if (!(mr->access_flags & IB_ACCESS_ON_DEMAND))
+		return 0;
+
+	table_attr = nla_nest_start(msg,
+				    RDMA_NLDEV_ATTR_STAT_HWCOUNTERS);
+
+	if (!table_attr)
+		goto err;
+
+	if (rdma_nl_stat_hwcounter_entry(msg, "page_faults",
+					 atomic64_read(&mr->odp_stats.faults)))
+		goto err_table;
+	if (rdma_nl_stat_hwcounter_entry(
+		    msg, "page_invalidations",
+		    atomic64_read(&mr->odp_stats.invalidations)))
+		goto err_table;
+
+	nla_nest_end(msg, table_attr);
+	return 0;
+
+err_table:
+	nla_nest_cancel(msg, table_attr);
+err:
+	return -EMSGSIZE;
+}
+
 static int fill_res_mr_entry(struct sk_buff *msg,
 			     struct rdma_restrack_entry *res)
 {
···
 {
 	if (res->type == RDMA_RESTRACK_MR)
 		return fill_res_mr_entry(msg, res);
+
+	return 0;
+}
+
+int mlx5_ib_fill_stat_entry(struct sk_buff *msg,
+			    struct rdma_restrack_entry *res)
+{
+	if (res->type == RDMA_RESTRACK_MR)
+		return fill_stat_mr_entry(msg, res);
 
 	return 0;
 }

include/rdma/ib_verbs.h

···
 	 */
 	int (*counter_update_stats)(struct rdma_counter *counter);
 
+	/**
+	 * Allows rdma drivers to add their own restrack attributes
+	 * dumped via 'rdma stat' iproute2 command.
+	 */
+	int (*fill_stat_entry)(struct sk_buff *msg,
+			       struct rdma_restrack_entry *entry);
+
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);

include/rdma/restrack.h

···
 			       u64 value);
 int rdma_nl_put_driver_string(struct sk_buff *msg, const char *name,
 			      const char *str);
+int rdma_nl_stat_hwcounter_entry(struct sk_buff *msg, const char *name,
+				 u64 value);
 
 struct rdma_restrack_entry *rdma_restrack_get_byid(struct ib_device *dev,
 						   enum rdma_restrack_type type,