[PATCH 7/9] drm/amdgpu: more GPU page fault info for GC v9.4.3

Alex Deucher alexander.deucher at amd.com
Thu Mar 30 19:26:55 UTC 2023


From: Philip Yang <Philip.Yang at amd.com>

Output IH cookie node_id and translate it to the corresponding AID id
and XCC id, to help debug the GPU page fault.

Signed-off-by: Philip Yang <Philip.Yang at amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index d819b544b043..016adcfe8c49 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -555,7 +555,9 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	const char *mmhub_cid;
 	const char *hub_name;
 	u64 addr;
-	uint32_t node_id = 0;
+	uint32_t node_id;
+
+	node_id = (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3)) ? entry->node_id : 0;
 
 	addr = (u64)entry->src_data[0] << 12;
 	addr |= ((u64)entry->src_data[1] & 0xf) << 44;
@@ -568,8 +570,6 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 		hub = &adev->vmhub[AMDGPU_MMHUB1(0)];
 	} else {
 		hub_name = "gfxhub0";
-		node_id = (adev->ip_versions[GC_HWIP][0] ==
-			   IP_VERSION(9, 4, 3)) ? entry->node_id : 0;
 		hub = &adev->vmhub[node_id/2];
 	}
 
@@ -616,6 +616,11 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 		addr, entry->client_id,
 		soc15_ih_clientid_name[entry->client_id]);
 
+	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(9, 4, 3))
+		dev_err(adev->dev, "  cookie node_id %d fault from die %s%d%s\n",
+			node_id, node_id % 4 == 3 ? "RSV" : "AID", node_id / 4,
+			node_id % 4 == 1 ? ".XCD0" : node_id % 4 == 2 ? ".XCD1" : "");
+
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
-- 
2.39.2



More information about the amd-gfx mailing list