[PATCH v2 3/4] drm/amdgpu: VF Query RAS Caps from Host if supported

Victor Skvortsov victor.skvortsov at amd.com
Tue Nov 5 19:04:28 UTC 2024


If VF RAS Capability support is enabled, guest is able to
retrieve the real RAS support from the host.

Signed-off-by: Victor Skvortsov <victor.skvortsov at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c  |  5 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 53 ++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  7 ++++
 3 files changed, 65 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1d9eda883bb8..89d87dc17ac1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -3452,6 +3452,11 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev)
 	if (!amdgpu_ras_asic_supported(adev))
 		return;
 
+	if (amdgpu_sriov_vf(adev)) {
+		if (amdgpu_virt_get_ras_capability(adev))
+			goto init_ras_enabled_flag;
+	}
+
 	/* query ras capability from psp */
 	if (amdgpu_psp_get_ras_capability(&adev->psp))
 		goto init_ras_enabled_flag;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index b6397d3229e1..53297c40f09c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -523,6 +523,7 @@ static int amdgpu_virt_read_pf2vf_data(struct amdgpu_device *adev)
 
 		adev->unique_id =
 			((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->uuid;
+		adev->virt.ras_en_caps.all = ((struct amd_sriov_msg_pf2vf_info *)pf2vf_info)->ras_en_caps.all;
 		break;
 	default:
 		dev_err(adev->dev, "invalid pf2vf version: 0x%x\n", pf2vf_info->version);
@@ -1144,3 +1145,55 @@ bool amdgpu_sriov_xnack_support(struct amdgpu_device *adev)
 
 	return xnack_mode;
 }
+
+bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+
+	if (!amdgpu_sriov_ras_caps_en(adev))
+		return false;
+
+	if (adev->virt.ras_en_caps.bits.block_umc)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__UMC);
+	if (adev->virt.ras_en_caps.bits.block_sdma)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SDMA);
+	if (adev->virt.ras_en_caps.bits.block_gfx)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__GFX);
+	if (adev->virt.ras_en_caps.bits.block_mmhub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MMHUB);
+	if (adev->virt.ras_en_caps.bits.block_athub)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__ATHUB);
+	if (adev->virt.ras_en_caps.bits.block_pcie_bif)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__PCIE_BIF);
+	if (adev->virt.ras_en_caps.bits.block_hdp)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__HDP);
+	if (adev->virt.ras_en_caps.bits.block_xgmi_wafl)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__XGMI_WAFL);
+	if (adev->virt.ras_en_caps.bits.block_df)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__DF);
+	if (adev->virt.ras_en_caps.bits.block_smn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SMN);
+	if (adev->virt.ras_en_caps.bits.block_sem)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__SEM);
+	if (adev->virt.ras_en_caps.bits.block_mp0)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP0);
+	if (adev->virt.ras_en_caps.bits.block_mp1)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MP1);
+	if (adev->virt.ras_en_caps.bits.block_fuse)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__FUSE);
+	if (adev->virt.ras_en_caps.bits.block_mca)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MCA);
+	if (adev->virt.ras_en_caps.bits.block_vcn)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__VCN);
+	if (adev->virt.ras_en_caps.bits.block_jpeg)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__JPEG);
+	if (adev->virt.ras_en_caps.bits.block_ih)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__IH);
+	if (adev->virt.ras_en_caps.bits.block_mpio)
+		adev->ras_hw_enabled |= BIT(AMDGPU_RAS_BLOCK__MPIO);
+
+	if (adev->virt.ras_en_caps.bits.poison_propogation_mode)
+		con->poison_supported = true; /* Poison is handled by host */
+
+	return true;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index f6eee57338df..f0ff84add692 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -137,6 +137,7 @@ enum AMDGIM_FEATURE_FLAG {
 	AMDGIM_FEATURE_VCN_RB_DECOUPLE = (1 << 7),
 	/* MES info */
 	AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8),
+	AMDGIM_FEATURE_RAS_CAPS = (1 << 9),
 };
 
 enum AMDGIM_REG_ACCESS_FLAG {
@@ -277,6 +278,8 @@ struct amdgpu_virt {
 	uint32_t autoload_ucode_id;
 
 	struct mutex rlcg_reg_lock;
+
+	union amd_sriov_ras_caps ras_en_caps;
 };
 
 struct amdgpu_video_codec_info;
@@ -321,6 +324,9 @@ struct amdgpu_video_codec_info;
 #define amdgpu_sriov_vf_mmio_access_protection(adev) \
 ((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT)
 
+#define amdgpu_sriov_ras_caps_en(adev) \
+((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CAPS)
+
 static inline bool is_virtual_machine(void)
 {
 #if defined(CONFIG_X86)
@@ -384,4 +390,5 @@ bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
 					  u32 acc_flags, u32 hwip,
 					  bool write, u32 *rlcg_flag);
 u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id);
+bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev);
 #endif
-- 
2.34.1



More information about the amd-gfx mailing list