Merge tag 'amd-drm-next-6.5-2023-06-16' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-16:

amdgpu:
- Misc display fixes
- W=1 fixes
- Improve scheduler naming
- DCN 3.1.4 fixes
- kdoc fixes
- Enable W=1
- VCN 4.0 fix
- xgmi fixes
- TOPDOWN fix for large BAR systems
- eDP fix
- PSR fixes
- SubVP fixes
- Freesync fix
- DPIA fix
- SMU 13.0.5 fixes
- vblflash fix
- RAS fixes
- SDMA 4 fix
- BO locking fix
- BO backing store fix
- NBIO 7.9 fixes
- GC 9.4.3 fixes
- GPU reset recovery fixes
- HMM fix

amdkfd:
- Fix NULL check
- Trap fixes
- Queue count fix
- Add event age tracking

radeon:
- fbdev client fix

scheduler:
- Avoid an infinite loop

UAPI:
- Add KFD event age tracking:
  Proposed ROCT-Thunk-Interface:
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/efdbf6cfbc026bd68ac3c35d00dacf84370eb81e
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/1820ae0a2db85b6f584611dc0cde1a00e7c22915
  Proposed ROCR-Runtime:
  https://github.com/RadeonOpenCompute/ROCR-Runtime/compare/master...zhums:ROCR-Runtime:new_event_wait_review
  https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/e1f5bdb88eb882ac798aeca2c00ea3fbb2dba459
  https://github.com/RadeonOpenCompute/ROCR-Runtime/commit/7d26afd14107b5c2a754c1a3f415d89f3aabb503

drm:
- DP MST fix

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230616163548.7706-1-alexander.deucher@amd.com

1 files changed, 46 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 85ee1af963dd..03dc59cbe8aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -325,6 +325,36 @@ static ssize_t amdgpu_xgmi_show_device_id(struct device *dev,
 
 }
 
+static ssize_t amdgpu_xgmi_show_num_hops(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	int i;
+
+	for (i = 0; i < top->num_nodes; i++)
+		sprintf(buf + 3 * i, "%02x ", top->nodes[i].num_hops);
+
+	return sysfs_emit(buf, "%s\n", buf);
+}
+
+static ssize_t amdgpu_xgmi_show_num_links(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(ddev);
+	struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+	int i;
+
+	for (i = 0; i < top->num_nodes; i++)
+		sprintf(buf + 3 * i, "%02x ", top->nodes[i].num_links);
+
+	return sysfs_emit(buf, "%s\n", buf);
+}
+
 #define AMDGPU_XGMI_SET_FICAA(o)	((o) | 0x456801)
 static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 				      struct device_attribute *attr,
@@ -361,6 +391,8 @@ static ssize_t amdgpu_xgmi_show_error(struct device *dev,
 
 static DEVICE_ATTR(xgmi_device_id, S_IRUGO, amdgpu_xgmi_show_device_id, NULL);
 static DEVICE_ATTR(xgmi_error, S_IRUGO, amdgpu_xgmi_show_error, NULL);
+static DEVICE_ATTR(xgmi_num_hops, S_IRUGO, amdgpu_xgmi_show_num_hops, NULL);
+static DEVICE_ATTR(xgmi_num_links, S_IRUGO, amdgpu_xgmi_show_num_links, NULL);
 
 static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 					 struct amdgpu_hive_info *hive)
@@ -380,6 +412,15 @@ static int amdgpu_xgmi_sysfs_add_dev_info(struct amdgpu_device *adev,
 	if (ret)
 		pr_err("failed to create xgmi_error\n");
 
+	/* Create xgmi num hops file */
+	ret = device_create_file(adev->dev, &dev_attr_xgmi_num_hops);
+	if (ret)
+		pr_err("failed to create xgmi_num_hops\n");
+
+	/* Create xgmi num links file */
+	ret = device_create_file(adev->dev, &dev_attr_xgmi_num_links);
+	if (ret)
+		pr_err("failed to create xgmi_num_links\n");
 
 	/* Create sysfs link to hive info folder on the first device */
 	if (hive->kobj.parent != (&adev->dev->kobj)) {
@@ -407,6 +448,9 @@ remove_link:
 
 remove_file:
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
+	device_remove_file(adev->dev, &dev_attr_xgmi_error);
+	device_remove_file(adev->dev, &dev_attr_xgmi_num_hops);
+	device_remove_file(adev->dev, &dev_attr_xgmi_num_links);
 
 success:
 	return ret;
@@ -420,6 +464,8 @@ static void amdgpu_xgmi_sysfs_rem_dev_info(struct amdgpu_device *adev,
 
 	device_remove_file(adev->dev, &dev_attr_xgmi_device_id);
 	device_remove_file(adev->dev, &dev_attr_xgmi_error);
+	device_remove_file(adev->dev, &dev_attr_xgmi_num_hops);
+	device_remove_file(adev->dev, &dev_attr_xgmi_num_links);
 
 	if (hive->kobj.parent != (&adev->dev->kobj))
 		sysfs_remove_link(&adev->dev->kobj,"xgmi_hive_info");