[PATCH v2] drm/amdgpu: Fix potential double free and null pointer dereference

[Liang He]

In amdgpu_get_xgmi_hive(), we should not call kfree() after
kobject_put() as the PUT will call kfree().

In amdgpu_device_ip_init(), we need to check the returned *hive*
which can be NULL before we dereference it.

Signed-off-by: Liang He <windhl at 126.com>
---
 v1->v2: we need the extra GET to keep *hive* alive, it is
 my fault to remove the GET in v1.


 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c   | 2 --
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f1e9663b4051..00976e15b698 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2462,6 +2462,11 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			if (!amdgpu_sriov_vf(adev)) {
 				struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev);
 
+				if (WARN_ON(!hive)) {
+					r = -ENOENT;
+					goto init_failed;
+				}
+
 				if (!hive->reset_domain ||
 				    !amdgpu_reset_get_reset_domain(hive->reset_domain)) {
 					r = -ENOENT;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 47159e9a0884..4b9e7b050ccd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -386,7 +386,6 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 	if (ret) {
 		dev_err(adev->dev, "XGMI: failed initializing kobject for xgmi hive\n");
 		kobject_put(&hive->kobj);
-		kfree(hive);
 		hive = NULL;
 		goto pro_end;
 	}
@@ -410,7 +409,6 @@ struct amdgpu_hive_info *amdgpu_get_xgmi_hive(struct amdgpu_device *adev)
 				dev_err(adev->dev, "XGMI: failed initializing reset domain for xgmi hive\n");
 				ret = -ENOMEM;
 				kobject_put(&hive->kobj);
-				kfree(hive);
 				hive = NULL;
 				goto pro_end;
 			}
-- 
2.25.1