Merge branch 'drm-next-5.1' of git://people.freedesktop.org/~agd5f/linux into drm-next

New stuff for 5.1.
amdgpu:
- DC bandwidth formula updates
- Support for DCC on scanout surfaces
- Support for multiple IH rings on soc15 asics
- Fix xgmi locking
- Add sysfs interface to get pcie usage stats
- Simplify DC i2c/aux code
- Initial support for BACO on vega10/20
- New runtime SMU feature debug interface
- Expand existing sysfs power interfaces to new clock domains
- Handle kexec properly
- Simplify IH programming
- Rework doorbell handling across asics
- Drop old CI DPM implementation
- DC page flipping fixes
- Misc SR-IOV fixes

amdkfd:
- Simplify the interfaces between amdkfd and amdgpu

ttm:
- Add a callback to notify the driver when the lru changes

sched:
- Refactor mirror list handling
- Rework hw fence processing

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexdeucher@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190125231517.26268-1-alexander.deucher@amd.com

1 files changed, 32 insertions, 15 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 8a8bc60cb6b4..dac187454b33 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -40,26 +40,40 @@ void *amdgpu_xgmi_hive_try_lock(struct amdgpu_hive_info *hive)
 	return &hive->device_list;
 }
 
-struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
+struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev, int lock)
 {
 	int i;
 	struct amdgpu_hive_info *tmp;
 
 	if (!adev->gmc.xgmi.hive_id)
 		return NULL;
+
+	mutex_lock(&xgmi_mutex);
+
 	for (i = 0 ; i < hive_count; ++i) {
 		tmp = &xgmi_hives[i];
-		if (tmp->hive_id == adev->gmc.xgmi.hive_id)
+		if (tmp->hive_id == adev->gmc.xgmi.hive_id) {
+			if (lock)
+				mutex_lock(&tmp->hive_lock);
+			mutex_unlock(&xgmi_mutex);
 			return tmp;
+		}
 	}
-	if (i >= AMDGPU_MAX_XGMI_HIVE)
+	if (i >= AMDGPU_MAX_XGMI_HIVE) {
+		mutex_unlock(&xgmi_mutex);
 		return NULL;
+	}
 
 	/* initialize new hive if not exist */
 	tmp = &xgmi_hives[hive_count++];
 	tmp->hive_id = adev->gmc.xgmi.hive_id;
 	INIT_LIST_HEAD(&tmp->device_list);
 	mutex_init(&tmp->hive_lock);
+	mutex_init(&tmp->reset_lock);
+	if (lock)
+		mutex_lock(&tmp->hive_lock);
+
+	mutex_unlock(&xgmi_mutex);
 
 	return tmp;
 }
@@ -111,10 +125,14 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		return ret;
 	}
 
-	mutex_lock(&xgmi_mutex);
-	hive = amdgpu_get_xgmi_hive(adev);
-	if (!hive)
+	hive = amdgpu_get_xgmi_hive(adev, 1);
+	if (!hive) {
+		ret = -EINVAL;
+		dev_err(adev->dev,
+			"XGMI: node 0x%llx, can not matech hive 0x%llx in the hive list.\n",
+			adev->gmc.xgmi.node_id, adev->gmc.xgmi.hive_id);
 		goto exit;
+	}
 
 	hive_topology = &hive->topology_info;
 
@@ -142,8 +160,8 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 			break;
 	}
 
+	mutex_unlock(&hive->hive_lock);
 exit:
-	mutex_unlock(&xgmi_mutex);
 	return ret;
 }
 
@@ -154,15 +172,14 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 	if (!adev->gmc.xgmi.supported)
 		return;
 
-	mutex_lock(&xgmi_mutex);
-
-	hive = amdgpu_get_xgmi_hive(adev);
+	hive = amdgpu_get_xgmi_hive(adev, 1);
 	if (!hive)
-		goto exit;
+		return;
 
-	if (!(hive->number_devices--))
+	if (!(hive->number_devices--)) {
 		mutex_destroy(&hive->hive_lock);
-
-exit:
-	mutex_unlock(&xgmi_mutex);
+		mutex_destroy(&hive->reset_lock);
+	} else {
+		mutex_unlock(&hive->hive_lock);
+	}
 }