[PATCH v2 13/15] net/ice: limit the number of queues to sched capabilities

[Bruce Richardson <bruce.richardson@intel.com>]

Rather than assuming that each VSI can hold up to 256 queue pairs,
or the reported device limit, query the available nodes in the scheduler
tree to check that we are not overflowing the limit for number of
child scheduling nodes at each level. Do this by multiplying
max_children for each level beyond the VSI and using that as an
additional cap on the number of queues.

Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
---
 drivers/net/ice/ice_ethdev.c | 25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c
index 0d2445a317..ab3f88fd7d 100644
--- a/drivers/net/ice/ice_ethdev.c
+++ b/drivers/net/ice/ice_ethdev.c
@@ -913,7 +913,7 @@ ice_vsi_config_default_rss(struct ice_aqc_vsi_props *info)
 }
 
 static int
-ice_vsi_config_tc_queue_mapping(struct ice_vsi *vsi,
+ice_vsi_config_tc_queue_mapping(struct ice_hw *hw, struct ice_vsi *vsi,
 				struct ice_aqc_vsi_props *info,
 				uint8_t enabled_tcmap)
 {
@@ -929,13 +929,28 @@ ice_vsi_config_tc_queue_mapping(struct ice_vsi *vsi,
 	}
 
 	/* vector 0 is reserved and 1 vector for ctrl vsi */
-	if (vsi->adapter->hw.func_caps.common_cap.num_msix_vectors < 2)
+	if (vsi->adapter->hw.func_caps.common_cap.num_msix_vectors < 2) {
 		vsi->nb_qps = 0;
-	else
+	} else {
 		vsi->nb_qps = RTE_MIN
 			((uint16_t)vsi->adapter->hw.func_caps.common_cap.num_msix_vectors - 2,
 			RTE_MIN(vsi->nb_qps, ICE_MAX_Q_PER_TC));
 
+		/* cap max QPs to what the HW reports as num-children for each layer.
+		 * Multiply num_children for each layer from the entry_point layer to
+		 * the qgroup, or second-last layer.
+		 * Avoid any potential overflow by using uint32_t type and breaking loop
+		 * once we have a number greater than the already configured max.
+		 */
+		uint32_t max_sched_vsi_nodes = 1;
+		for (uint8_t i = hw->sw_entry_point_layer; i < hw->num_tx_sched_layers - 1; i++) {
+			max_sched_vsi_nodes *= hw->max_children[i];
+			if (max_sched_vsi_nodes >= vsi->nb_qps)
+				break;
+		}
+		vsi->nb_qps = RTE_MIN(vsi->nb_qps, max_sched_vsi_nodes);
+	}
+
 	/* nb_qps(hex)  -> fls */
 	/* 0000		-> 0 */
 	/* 0001		-> 0 */
@@ -1707,7 +1722,7 @@ ice_setup_vsi(struct ice_pf *pf, enum ice_vsi_type type)
 			rte_cpu_to_le_16(hw->func_caps.fd_fltr_best_effort);
 
 		/* Enable VLAN/UP trip */
-		ret = ice_vsi_config_tc_queue_mapping(vsi,
+		ret = ice_vsi_config_tc_queue_mapping(hw, vsi,
 						      &vsi_ctx.info,
 						      ICE_DEFAULT_TCMAP);
 		if (ret) {
@@ -1731,7 +1746,7 @@ ice_setup_vsi(struct ice_pf *pf, enum ice_vsi_type type)
 		vsi_ctx.info.fd_options = rte_cpu_to_le_16(cfg);
 		vsi_ctx.info.sw_id = hw->port_info->sw_id;
 		vsi_ctx.info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA;
-		ret = ice_vsi_config_tc_queue_mapping(vsi,
+		ret = ice_vsi_config_tc_queue_mapping(hw, vsi,
 						      &vsi_ctx.info,
 						      ICE_DEFAULT_TCMAP);
 		if (ret) {
-- 
2.43.0