[PATCH] drm/amdgpu: add safeguards for accessing mmhub CG registers

[Deucher, Alexander]

[Public]

Should we set *flags = 0 before we return?

Alex

________________________________
From: Yu, Lang <Lang.Yu at amd.com>
Sent: Wednesday, January 26, 2022 2:53 AM
To: amd-gfx at lists.freedesktop.org <amd-gfx at lists.freedesktop.org>
Cc: Deucher, Alexander <Alexander.Deucher at amd.com>; Lazar, Lijo <Lijo.Lazar at amd.com>; Huang, Ray <Ray.Huang at amd.com>; Yu, Lang <Lang.Yu at amd.com>
Subject: [PATCH] drm/amdgpu: add safeguards for accessing mmhub CG registers

We observed a gpu hang when querying mmhub CG status(i.e.,
cat amdgpu_pm_info) on cyan skillfish. Acctually, cyan
skillfish doesn't support any CG features.

Only allow asics which support CG features accessing related
registers. Will add similar safeguards for other IPs in the
furture.

Signed-off-by: Lang Yu <Lang.Yu at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c | 3 +++
 5 files changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 4c9f0c0f3116..1869e2019461 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -550,6 +550,9 @@ static void mmhub_v1_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
         int data, data1;

+       if (!(adev->cg_flags & (AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS)))
+               return;
+
         if (amdgpu_sriov_vf(adev))
                 *flags = 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
index 3b901f941627..f7b9843b36e6 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
@@ -546,6 +546,9 @@ static void mmhub_v1_7_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
         int data, data1;

+       if (!(adev->cg_flags & (AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS)))
+               return;
+
         if (amdgpu_sriov_vf(adev))
                 *flags = 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 3718ff610ab2..3f5f326379b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -686,6 +686,9 @@ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
         int data, data1;

+       if (!(adev->cg_flags & (AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS)))
+               return;
+
         if (amdgpu_sriov_vf(adev))
                 *flags = 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
index 9e16da28505a..b23dd9ddfb5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_3.c
@@ -580,6 +580,9 @@ static void mmhub_v2_3_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
         int data, data1, data2, data3;

+       if (!(adev->cg_flags & (AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS)))
+               return;
+
         if (amdgpu_sriov_vf(adev))
                 *flags = 0;

diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 619106f7d23d..a2d5c8424e2b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -651,6 +651,9 @@ static void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u32 *flags)
 {
         int data, data1;

+       if (!(adev->cg_flags & (AMD_CG_SUPPORT_MC_MGCG | AMD_CG_SUPPORT_MC_LS)))
+               return;
+
         if (amdgpu_sriov_vf(adev))
                 *flags = 0;

--
2.25.1

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20220126/098693f1/attachment.htm>