[PATCH V2 7/7] mlx5: add backward compatibility for RDMA monitor

["Minggang Li(Gavin)" <gavinl@nvidia.com>]

Fallback to the old way to update port information if the kernel driver
does not support RDMA monitor.

Signed-off-by: Minggang Li(Gavin) <gavinl@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
 doc/guides/rel_notes/release_24_11.rst  | 14 +++++
 drivers/common/mlx5/linux/mlx5_nl.c     | 73 +++++++++++++++++++++++++
 drivers/common/mlx5/version.map         |  1 +
 drivers/net/mlx5/linux/mlx5_ethdev_os.c |  2 +-
 drivers/net/mlx5/linux/mlx5_os.c        | 27 +++++++--
 drivers/net/mlx5/mlx5.h                 |  1 +
 6 files changed, 111 insertions(+), 7 deletions(-)

diff --git a/doc/guides/rel_notes/release_24_11.rst b/doc/guides/rel_notes/release_24_11.rst
index fa4822d928..02827ff392 100644
--- a/doc/guides/rel_notes/release_24_11.rst
+++ b/doc/guides/rel_notes/release_24_11.rst
@@ -247,6 +247,20 @@ New Features
   Added ability for node to advertise and update multiple xstat counters,
   that can be retrieved using ``rte_graph_cluster_stats_get``.
 
+* **Updated NVIDIA mlx5 driver.**
+
+  Optimized port probe in large scale.
+  In previous release, it would take long time to probe one VF/SF if
+  hundreds of VF/SF were created in the system. With this newly introduced
+  feature optimization, the time to probe a VF/SF will be reduced greatly in
+  large scale, eg hundreds of VF/SFs. This feature is controlled through the
+  ``probe_opt_en`` device argument. Setting it to a non-zero value indicates
+  the application will enable this functionality when probing a device. This
+  feature relies on a feature of RDMA driver to be release in incoming
+  upstream kernel 6.13 or the equivalent in OFED 24.10, ie. RDMA monitor.
+  For further information on the devargs limitation, see
+  "doc/guides/nics/mlx5.rst".
+
 
 Removed Items
 -------------
diff --git a/drivers/common/mlx5/linux/mlx5_nl.c b/drivers/common/mlx5/linux/mlx5_nl.c
index ce1c2a8e75..12f1a620f3 100644
--- a/drivers/common/mlx5/linux/mlx5_nl.c
+++ b/drivers/common/mlx5/linux/mlx5_nl.c
@@ -2152,3 +2152,76 @@ mlx5_nl_rdma_monitor_info_get(struct nlmsghdr *hdr, struct mlx5_nl_port_info *da
 error:
 	rte_errno = EINVAL;
 }
+
+static int
+mlx5_nl_rdma_monitor_cap_get_cb(struct nlmsghdr *hdr, void *arg)
+{
+	size_t off = NLMSG_HDRLEN;
+	uint8_t *cap = arg;
+
+	if (hdr->nlmsg_type != RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_SYS_GET))
+		goto error;
+
+	*cap = 0;
+	while (off < hdr->nlmsg_len) {
+		struct nlattr *na = (void *)((uintptr_t)hdr + off);
+		void *payload = (void *)((uintptr_t)na + NLA_HDRLEN);
+
+		if (na->nla_len > hdr->nlmsg_len - off)
+			goto error;
+		switch (na->nla_type) {
+		case RDMA_NLDEV_SYS_ATTR_MONITOR_MODE:
+			*cap = *(uint8_t *)payload;
+			return 0;
+		default:
+			break;
+		}
+		off += NLA_ALIGN(na->nla_len);
+	}
+
+	return 0;
+
+error:
+	return -EINVAL;
+}
+
+/**
+ * Get RDMA monitor support in driver.
+ *
+ *
+ * @param nl
+ *   Netlink socket of the RDMA kind (NETLINK_RDMA).
+ * @param[out] cap
+ *   Pointer to port info.
+ * @return
+ *   0 on success, negative on error and rte_errno is set.
+ */
+int
+mlx5_nl_rdma_monitor_cap_get(int nl, uint8_t *cap)
+{
+	union {
+		struct nlmsghdr nh;
+		uint8_t buf[NLMSG_HDRLEN];
+	} req = {
+		.nh = {
+			.nlmsg_len = NLMSG_LENGTH(0),
+			.nlmsg_type = RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+						       RDMA_NLDEV_CMD_SYS_GET),
+			.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+		},
+	};
+	uint32_t sn = MLX5_NL_SN_GENERATE;
+	int ret;
+
+	ret = mlx5_nl_send(nl, &req.nh, sn);
+	if (ret < 0) {
+		rte_errno = -ret;
+		return ret;
+	}
+	ret = mlx5_nl_recv(nl, sn, mlx5_nl_rdma_monitor_cap_get_cb, cap);
+	if (ret < 0) {
+		rte_errno = -ret;
+		return ret;
+	}
+	return 0;
+}
diff --git a/drivers/common/mlx5/version.map b/drivers/common/mlx5/version.map
index 5230576006..8301485839 100644
--- a/drivers/common/mlx5/version.map
+++ b/drivers/common/mlx5/version.map
@@ -148,6 +148,7 @@ INTERNAL {
 	mlx5_nl_vlan_vmwa_delete; # WINDOWS_NO_EXPORT
 	mlx5_nl_rdma_monitor_init; # WINDOWS_NO_EXPORT
 	mlx5_nl_rdma_monitor_info_get; # WINDOWS_NO_EXPORT
+	mlx5_nl_rdma_monitor_cap_get; # WINDOWS_NO_EXPORT
 
 	mlx5_os_umem_dereg;
 	mlx5_os_umem_reg;
diff --git a/drivers/net/mlx5/linux/mlx5_ethdev_os.c b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
index 5156d96b3a..6b2c25a7c2 100644
--- a/drivers/net/mlx5/linux/mlx5_ethdev_os.c
+++ b/drivers/net/mlx5/linux/mlx5_ethdev_os.c
@@ -736,7 +736,7 @@ mlx5_dev_interrupt_nl_cb(struct nlmsghdr *hdr, void *cb_arg)
 
 	if (mlx5_nl_parse_link_status_update(hdr, &if_index) < 0)
 		return;
-	if (sh->cdev->config.probe_opt && sh->cdev->dev_info.port_num > 1)
+	if (sh->cdev->config.probe_opt && sh->cdev->dev_info.port_num > 1 && !sh->rdma_monitor_supp)
 		mlx5_handle_port_info_update(&sh->cdev->dev_info, if_index, hdr->nlmsg_type);
 
 	for (i = 0; i < sh->max_port; i++) {
diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c
index 47da00937b..93556dc580 100644
--- a/drivers/net/mlx5/linux/mlx5_os.c
+++ b/drivers/net/mlx5/linux/mlx5_os.c
@@ -3022,6 +3022,7 @@ mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh)
 {
 	struct ibv_context *ctx = sh->cdev->ctx;
 	int nlsk_fd;
+	uint8_t rdma_monitor_supp = 0;
 
 	sh->intr_handle = mlx5_os_interrupt_handler_create
 		(RTE_INTR_INSTANCE_F_SHARED, true,
@@ -3030,20 +3031,34 @@ mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh)
 		DRV_LOG(ERR, "Failed to allocate intr_handle.");
 		return;
 	}
-	if (sh->cdev->config.probe_opt && sh->cdev->dev_info.port_num > 1) {
+	if (sh->cdev->config.probe_opt &&
+	    sh->cdev->dev_info.port_num > 1 &&
+	    !sh->rdma_monitor_supp) {
 		nlsk_fd = mlx5_nl_rdma_monitor_init();
 		if (nlsk_fd < 0) {
 			DRV_LOG(ERR, "Failed to create a socket for RDMA Netlink events: %s",
 				rte_strerror(rte_errno));
 			return;
 		}
-		sh->intr_handle_ib = mlx5_os_interrupt_handler_create
-			(RTE_INTR_INSTANCE_F_SHARED, true,
-			 nlsk_fd, mlx5_dev_interrupt_handler_ib, sh);
-		if (sh->intr_handle_ib == NULL) {
-			DRV_LOG(ERR, "Fail to allocate intr_handle");
+		if (mlx5_nl_rdma_monitor_cap_get(nlsk_fd, &rdma_monitor_supp)) {
+			DRV_LOG(ERR, "Failed to query RDMA monitor support: %s",
+				rte_strerror(rte_errno));
+			close(nlsk_fd);
 			return;
 		}
+		sh->rdma_monitor_supp = rdma_monitor_supp;
+		if (sh->rdma_monitor_supp) {
+			sh->intr_handle_ib = mlx5_os_interrupt_handler_create
+				(RTE_INTR_INSTANCE_F_SHARED, true,
+				 nlsk_fd, mlx5_dev_interrupt_handler_ib, sh);
+			if (sh->intr_handle_ib == NULL) {
+				DRV_LOG(ERR, "Fail to allocate intr_handle");
+				close(nlsk_fd);
+				return;
+			}
+		} else {
+			close(nlsk_fd);
+		}
 	}
 	nlsk_fd = mlx5_nl_init(NETLINK_ROUTE, RTMGRP_LINK);
 	if (nlsk_fd < 0) {
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index fe56bc897a..126b48ac61 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -1517,6 +1517,7 @@ struct mlx5_dev_ctx_shared {
 	uint32_t lag_rx_port_affinity_en:1;
 	/* lag_rx_port_affinity is supported. */
 	uint32_t hws_max_log_bulk_sz:5;
+	uint32_t rdma_monitor_supp:1;
 	/* Log of minimal HWS counters created hard coded. */
 	uint32_t hws_max_nb_counters; /* Maximal number for HWS counters. */
 	uint32_t max_port; /* Maximal IB device port index. */
-- 
2.34.1