From 0e2c057777fd1a60edfff99c0fed61fef76b4aae Mon Sep 17 00:00:00 2001
From: Jonathan Kim <jonathan.kim@amd.com>
Date: Thu, 12 May 2022 20:38:18 -0400
Subject: drm/amdkfd: simplify cpu hive assignment
Git-commit: a0af5dbdc914eae667fba8322cb02afc4ce3967b
Patch-mainline: v5.19-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

CPU hive assignment currently assumes when a GPU hive is connected_to_cpu,
there is only one hive in the system.

Only assign CPUs to the hive if they are explicitly directly connected to
the GPU hive to get rid of the need for this assumption.

It's more efficient to do this when querying IO links since other non-CRAT
info has to be filled in anyways.  Also, stop re-assigning the
same CPU to the same GPU hive if it has already been done before.

Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 2e20f54bb147..8d50d207cf66 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1271,6 +1271,12 @@ static void kfd_fill_iolink_non_crat_info(struct kfd_topology_device *dev)
 		if (!peer_dev)
 			continue;
 
+		/* Include the CPU peer in GPU hive if connected over xGMI. */
+		if (!peer_dev->gpu && !peer_dev->node_props.hive_id &&
+				dev->node_props.hive_id &&
+				dev->gpu->adev->gmc.xgmi.connected_to_cpu)
+			peer_dev->node_props.hive_id = dev->node_props.hive_id;
+
 		list_for_each_entry(inbound_link, &peer_dev->io_link_props,
 									list) {
 			if (inbound_link->node_to != link->node_from)
@@ -1302,22 +1308,6 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 
 	pr_debug("Adding new GPU (ID: 0x%x) to topology\n", gpu_id);
 
-	/* Include the CPU in xGMI hive if xGMI connected by assigning it the hive ID. */
-	if (gpu->hive_id && gpu->adev->gmc.xgmi.connected_to_cpu) {
-		struct kfd_topology_device *top_dev;
-
-		down_read(&topology_lock);
-
-		list_for_each_entry(top_dev, &topology_device_list, list) {
-			if (top_dev->gpu)
-				break;
-
-			top_dev->node_props.hive_id = gpu->hive_id;
-		}
-
-		up_read(&topology_lock);
-	}
-
 	/* Check to see if this gpu device exists in the topology_device_list.
 	 * If so, assign the gpu to that device,
 	 * else create a Virtual CRAT for this gpu device and then parse that
-- 
2.38.1