[PATCH 2/3] drm/amdgpu: Query ras capablity from psp

[Zhang, Hawking]

[AMD Official Use Only - General]

The ret gives us a chance to fallback to legacy query approach (from vbios).


You might want to see patch #3 of the series for more details, go to the following lines in patch #3

+       /* query ras capability from psp */
+       if (amdgpu_psp_get_ras_capability(&adev->psp))
+               goto init_ras_enabled_flag;


Regards,
Hawking

-----Original Message-----
From: Wang, Yang(Kevin) <KevinYang.Wang at amd.com>
Sent: Tuesday, January 2, 2024 13:19
To: Zhang, Hawking <Hawking.Zhang at amd.com>; amd-gfx at lists.freedesktop.org; Zhou1, Tao <Tao.Zhou1 at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>; Chai, Thomas <YiPeng.Chai at amd.com>; Li, Candice <Candice.Li at amd.com>
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>; Lazar, Lijo <Lijo.Lazar at amd.com>; Ma, Le <Le.Ma at amd.com>
Subject: RE: [PATCH 2/3] drm/amdgpu: Query ras capablity from psp

[AMD Official Use Only - General]

-----Original Message-----
From: Hawking Zhang <Hawking.Zhang at amd.com>
Sent: Tuesday, January 2, 2024 11:45 AM
To: amd-gfx at lists.freedesktop.org; Zhou1, Tao <Tao.Zhou1 at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>; Wang, Yang(Kevin) <KevinYang.Wang at amd.com>; Chai, Thomas <YiPeng.Chai at amd.com>; Li, Candice <Candice.Li at amd.com>
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>; Lazar, Lijo <Lijo.Lazar at amd.com>; Ma, Le <Le.Ma at amd.com>
Subject: [PATCH 2/3] drm/amdgpu: Query ras capablity from psp

Instead of traditional atomfirmware interfaces for RAS capability, host driver can query ras capability from psp starting from psp v13_0_6.

Signed-off-by: Hawking Zhang <Hawking.Zhang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c | 13 +++++++++++++  drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h |  2 ++  drivers/gpu/drm/amd/amdgpu/psp_v13_0.c  | 26 +++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 94b536e3cada..8a3847d3041f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -2125,6 +2125,19 @@ int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev)
        return ret;
 }

+bool amdgpu_psp_get_ras_capability(struct psp_context *psp) {
+       bool ret;
+
+       if (psp->funcs &&
+           psp->funcs->get_ras_capability) {
+               ret = psp->funcs->get_ras_capability(psp);
+               return ret;
[kevin]:
This variable 'ret' seems to have no other purpose, can we remove it and return directly ?

Best Regards,
Kevin
+       } else {
+               return false;
+       }
+}
+
 static int psp_hw_start(struct psp_context *psp)  {
        struct amdgpu_device *adev = psp->adev; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index 09d1f8f72a9c..652b0a01854a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -134,6 +134,7 @@ struct psp_funcs {
        int (*update_spirom)(struct psp_context *psp, uint64_t fw_pri_mc_addr);
        int (*vbflash_stat)(struct psp_context *psp);
        int (*fatal_error_recovery_quirk)(struct psp_context *psp);
+       bool (*get_ras_capability)(struct psp_context *psp);
 };

 struct ta_funcs {
@@ -537,4 +538,5 @@ int psp_spatial_partition(struct psp_context *psp, int mode);  int is_psp_fw_valid(struct psp_bin_desc bin);

 int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev);
+bool amdgpu_psp_get_ras_capability(struct psp_context *psp);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 676bec2cc157..722b6066ce07 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -27,6 +27,7 @@
 #include "amdgpu_ucode.h"
 #include "soc15_common.h"
 #include "psp_v13_0.h"
+#include "amdgpu_ras.h"

 #include "mp/mp_13_0_2_offset.h"
 #include "mp/mp_13_0_2_sh_mask.h"
@@ -770,6 +771,30 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp)
        return 0;
 }

+static bool psp_v13_0_get_ras_capability(struct psp_context *psp) {
+       struct amdgpu_device *adev = psp->adev;
+       struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+       u32 reg_data;
+
+       /* query ras cap should be done from host side */
+       if (amdgpu_sriov_vf(adev))
+               return false;
+
+       if (!con)
+               return false;
+
+       if ((amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) &&
+           (!(adev->flags & AMD_IS_APU))) {
+               reg_data = RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_127);
+               adev->ras_hw_enabled = (reg_data & GENMASK_ULL(23, 0));
+               con->poison_supported = ((reg_data & GENMASK_ULL(24, 24)) >> 24) ? true : false;
+               return true;
+       } else {
+               return false;
+       }
+}
+
 static const struct psp_funcs psp_v13_0_funcs = {
        .init_microcode = psp_v13_0_init_microcode,
        .wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state,
@@ -792,6 +817,7 @@ static const struct psp_funcs psp_v13_0_funcs = {
        .update_spirom = psp_v13_0_update_spirom,
        .vbflash_stat = psp_v13_0_vbflash_status,
        .fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk,
+       .get_ras_capability = psp_v13_0_get_ras_capability,
 };

 void psp_v13_0_set_psp_funcs(struct psp_context *psp)
--
2.17.1