S2idle resume freeze can be observed on Intel ADL + AMD WX5500. This is
caused by commit 0064b0ce85bb ("drm/amd/pm: enable ASPM by default").
The root cause is still not clear for now.
So extend and apply the ASPM quirk from commit e02fe3bc7aba
("drm/amdgpu: vi: disable ASPM on Intel Alder Lake based systems"), to
workaround the issue on Navi cards too.
Fixes: 0064b0ce85bb ("drm/amd/pm: enable ASPM by default")
Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2458
Signed-off-by: Kai-Heng Feng <[email protected]>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 15 +++++++++++++++
drivers/gpu/drm/amd/amdgpu/nv.c | 2 +-
drivers/gpu/drm/amd/amdgpu/vi.c | 15 ---------------
4 files changed, 17 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 164141bc8b4a..c697580f1ee4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1272,6 +1272,7 @@ void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
int amdgpu_device_pci_reset(struct amdgpu_device *adev);
bool amdgpu_device_need_post(struct amdgpu_device *adev);
bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
+bool aspm_support_quirk_check(void);
void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
u64 num_vis_bytes);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c4a4e2fe6681..c09f19385628 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -80,6 +80,10 @@
#include <drm/drm_drv.h>
+#if IS_ENABLED(CONFIG_X86)
+#include <asm/intel-family.h>
+#endif
+
MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -1356,6 +1360,17 @@ bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev)
return pcie_aspm_enabled(adev->pdev);
}
+bool aspm_support_quirk_check(void)
+{
+#if IS_ENABLED(CONFIG_X86)
+ struct cpuinfo_x86 *c = &cpu_data(0);
+
+ return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
+#else
+ return true;
+#endif
+}
+
/* if we get transitioned to only one device, take VGA back */
/**
* amdgpu_device_vga_set_decode - enable/disable vga decode
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 855d390c41de..921adf66e3c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -578,7 +578,7 @@ static void nv_pcie_gen3_enable(struct amdgpu_device *adev)
static void nv_program_aspm(struct amdgpu_device *adev)
{
- if (!amdgpu_device_should_use_aspm(adev))
+ if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check())
return;
if (!(adev->flags & AMD_IS_APU) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 12ef782eb478..e61ae372d674 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -81,10 +81,6 @@
#include "mxgpu_vi.h"
#include "amdgpu_dm.h"
-#if IS_ENABLED(CONFIG_X86)
-#include <asm/intel-family.h>
-#endif
-
#define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6
#define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L
#define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L
@@ -1138,17 +1134,6 @@ static void vi_enable_aspm(struct amdgpu_device *adev)
WREG32_PCIE(ixPCIE_LC_CNTL, data);
}
-static bool aspm_support_quirk_check(void)
-{
-#if IS_ENABLED(CONFIG_X86)
- struct cpuinfo_x86 *c = &cpu_data(0);
-
- return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
-#else
- return true;
-#endif
-}
-
static void vi_program_aspm(struct amdgpu_device *adev)
{
u32 data, data1, orig;
--
2.34.1
On Tue, Mar 14, 2023 at 12:35 AM Kai-Heng Feng
<[email protected]> wrote:
>
> S2idle resume freeze can be observed on Intel ADL + AMD WX5500. This is
> caused by commit 0064b0ce85bb ("drm/amd/pm: enable ASPM by default").
>
> The root cause is still not clear for now.
>
> So extend and apply the ASPM quirk from commit e02fe3bc7aba
> ("drm/amdgpu: vi: disable ASPM on Intel Alder Lake based systems"), to
> workaround the issue on Navi cards too.
>
> Fixes: 0064b0ce85bb ("drm/amd/pm: enable ASPM by default")
> Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2458
> Signed-off-by: Kai-Heng Feng <[email protected]>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
> drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 15 +++++++++++++++
> drivers/gpu/drm/amd/amdgpu/nv.c | 2 +-
> drivers/gpu/drm/amd/amdgpu/vi.c | 15 ---------------
> 4 files changed, 17 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index 164141bc8b4a..c697580f1ee4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1272,6 +1272,7 @@ void amdgpu_device_pci_config_reset(struct amdgpu_device *adev);
> int amdgpu_device_pci_reset(struct amdgpu_device *adev);
> bool amdgpu_device_need_post(struct amdgpu_device *adev);
> bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev);
> +bool aspm_support_quirk_check(void);
>
> void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
> u64 num_vis_bytes);
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index c4a4e2fe6681..c09f19385628 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -80,6 +80,10 @@
>
> #include <drm/drm_drv.h>
>
> +#if IS_ENABLED(CONFIG_X86)
> +#include <asm/intel-family.h>
> +#endif
> +
> MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
> MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
> MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
> @@ -1356,6 +1360,17 @@ bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev)
> return pcie_aspm_enabled(adev->pdev);
> }
>
> +bool aspm_support_quirk_check(void)
For consistency with naming, rename this
amdgpu_device_aspm_support_quirk(). Other than that, looks good to
me. With that fixed:
Reviewed-by: Alex Deucher <[email protected]>
Alex
> +{
> +#if IS_ENABLED(CONFIG_X86)
> + struct cpuinfo_x86 *c = &cpu_data(0);
> +
> + return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
> +#else
> + return true;
> +#endif
> +}
> +
> /* if we get transitioned to only one device, take VGA back */
> /**
> * amdgpu_device_vga_set_decode - enable/disable vga decode
> diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
> index 855d390c41de..921adf66e3c4 100644
> --- a/drivers/gpu/drm/amd/amdgpu/nv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/nv.c
> @@ -578,7 +578,7 @@ static void nv_pcie_gen3_enable(struct amdgpu_device *adev)
>
> static void nv_program_aspm(struct amdgpu_device *adev)
> {
> - if (!amdgpu_device_should_use_aspm(adev))
> + if (!amdgpu_device_should_use_aspm(adev) || !aspm_support_quirk_check())
> return;
>
> if (!(adev->flags & AMD_IS_APU) &&
> diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
> index 12ef782eb478..e61ae372d674 100644
> --- a/drivers/gpu/drm/amd/amdgpu/vi.c
> +++ b/drivers/gpu/drm/amd/amdgpu/vi.c
> @@ -81,10 +81,6 @@
> #include "mxgpu_vi.h"
> #include "amdgpu_dm.h"
>
> -#if IS_ENABLED(CONFIG_X86)
> -#include <asm/intel-family.h>
> -#endif
> -
> #define ixPCIE_LC_L1_PM_SUBSTATE 0x100100C6
> #define PCIE_LC_L1_PM_SUBSTATE__LC_L1_SUBSTATES_OVERRIDE_EN_MASK 0x00000001L
> #define PCIE_LC_L1_PM_SUBSTATE__LC_PCI_PM_L1_2_OVERRIDE_MASK 0x00000002L
> @@ -1138,17 +1134,6 @@ static void vi_enable_aspm(struct amdgpu_device *adev)
> WREG32_PCIE(ixPCIE_LC_CNTL, data);
> }
>
> -static bool aspm_support_quirk_check(void)
> -{
> -#if IS_ENABLED(CONFIG_X86)
> - struct cpuinfo_x86 *c = &cpu_data(0);
> -
> - return !(c->x86 == 6 && c->x86_model == INTEL_FAM6_ALDERLAKE);
> -#else
> - return true;
> -#endif
> -}
> -
> static void vi_program_aspm(struct amdgpu_device *adev)
> {
> u32 data, data1, orig;
> --
> 2.34.1
>