drm/amdgpu: add check for RAS instance mask

The mask is only needed to be set when RAS block instance number is
more than 1 and invalid bits should be also masked out.
We only check valid bits for GFX and SDMA block for now, and will
add check for other RAS blocks in the future.

v2: move the check under injection operation since the mask is only
    used by RAS error inject.
v3: add valid bits handling for SDMA.
v4: print message if the mask is adjusted.

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Hawking Zhang <Hawking.Zhang@amd.com>
Reviewed-by: Stanley.Yang <Stanley.Yang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 38 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index b7d8250a9281..6bb438642cc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -333,6 +333,42 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 	return 0;
 }
 
+static void amdgpu_ras_instance_mask_check(struct amdgpu_device *adev,
+				struct ras_debug_if *data)
+{
+	int num_xcc = adev->gfx.xcc_mask ? NUM_XCC(adev->gfx.xcc_mask) : 1;
+	uint32_t mask, inst_mask = data->inject.instance_mask;
+
+	/* no need to set instance mask if there is only one instance */
+	if (num_xcc <= 1 && inst_mask) {
+		data->inject.instance_mask = 0;
+		dev_dbg(adev->dev,
+			"RAS inject mask(0x%x) isn't supported and force it to 0.\n",
+			inst_mask);
+
+		return;
+	}
+
+	switch (data->head.block) {
+	case AMDGPU_RAS_BLOCK__GFX:
+		mask = GENMASK(num_xcc - 1, 0);
+		break;
+	case AMDGPU_RAS_BLOCK__SDMA:
+		mask = GENMASK(adev->sdma.num_instances - 1, 0);
+		break;
+	default:
+		mask = 0;
+		break;
+	}
+
+	/* remove invalid bits in instance mask */
+	data->inject.instance_mask &= mask;
+	if (inst_mask != data->inject.instance_mask)
+		dev_dbg(adev->dev,
+			"Adjust RAS inject mask 0x%x to 0x%x\n",
+			inst_mask, data->inject.instance_mask);
+}
+
 /**
  * DOC: AMDGPU RAS debugfs control interface
  *
@@ -468,6 +504,8 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f,
 			break;
 		}
 
+		amdgpu_ras_instance_mask_check(adev, &data);
+
 		/* data.inject.address is offset instead of absolute gpu address */
 		ret = amdgpu_ras_error_inject(adev, &data.inject);
 		break;