Merge tag 'amd-drm-next-6.6-2023-07-28' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.6-2023-07-28:

amdgpu:
- Lots of checkpatch cleanups
- GFX 9.4.3 updates
- Add USB PD and IFWI flashing documentation
- GPUVM updates
- RAS fixes
- DRR fixes
- FAMS fixes
- Virtual display fixes
- Soft IH fixes
- SMU13 fixes
- Rework PSP firmware loading for other IPs
- Kernel doc fixes
- DCN 3.0.1 fixes
- LTTPR fixes
- DP MST fixes
- DCN 3.1.6 fixes
- SubVP fixes
- Display bandwidth calculation fixes
- VCN4 secure submission fixes
- Allow building DC on RISC-V
- Add visible FB info to bo_print_info
- HBR3 fixes
- Add PSP 14.0 support
- GFX9 MCBP fix
- GMC10 vmhub index fix
- GMC11 vmhub index fix
- Create a new doorbell manager
- SR-IOV fixes

amdkfd:
- Cleanup CRIU dma-buf handling
- Use KIQ to unmap HIQ
- GFX 9.4.3 debugger updates
- GFX 9.4.2 debugger fixes
- Enable cooperative groups fof gfx11
- SVM fixes

radeon:
- Lots of checkpatch cleanups

Merge conflicts:
- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
	The switch to drm eu helpers in 8a206685d36f ("drm/amdgpu: use
	drm_exec for GEM and CSA handling v2") clashed with the
	cosmetic cleanups from 30953c4d000b ("drm/amdgpu: Fix style
	issues in amdgpu_gem.c"). I
	kept the former since the cleanup up code is gone.
- drivers/gpu/drm/amd/amdgpu/atom.c.
	adf64e214280 ("drm/amd: Avoid reading the VBIOS part number
	twice") removed code that 992b8fe106ab ("drm/radeon: Replace
	all non-returning strlcpy with strscpy") polished.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230728214228.8102-1-alexander.deucher@amd.com
[sima: some merge conflict wrangling as noted]
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

1 files changed, 32 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 41aa853a07d2..ec044f711eb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -835,6 +835,16 @@ enum amdgpu_sriov_vf_mode amdgpu_virt_get_sriov_vf_mode(struct amdgpu_device *ad
 	return mode;
 }
 
+void amdgpu_virt_post_reset(struct amdgpu_device *adev)
+{
+	if (adev->ip_versions[GC_HWIP][0] == IP_VERSION(11, 0, 3)) {
+		/* force set to GFXOFF state after reset,
+		 * to avoid some invalid operation before GC enable
+		 */
+		adev->gfx.is_poweron = false;
+	}
+}
+
 bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev, uint32_t ucode_id)
 {
 	switch (adev->ip_versions[MP0_HWIP][0]) {
@@ -845,6 +855,17 @@ bool amdgpu_virt_fw_load_skip_check(struct amdgpu_device *adev, uint32_t ucode_i
 			return false;
 		else
 			return true;
+	case IP_VERSION(11, 0, 9):
+	case IP_VERSION(11, 0, 7):
+		/* black list for CHIP_NAVI12 and CHIP_SIENNA_CICHLID */
+		if (ucode_id == AMDGPU_UCODE_ID_RLC_G
+		    || ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL
+		    || ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM
+		    || ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM
+		    || ucode_id == AMDGPU_UCODE_ID_SMC)
+			return true;
+		else
+			return false;
 	case IP_VERSION(13, 0, 10):
 		/* white list */
 		if (ucode_id == AMDGPU_UCODE_ID_CAP
@@ -954,7 +975,7 @@ static bool amdgpu_virt_get_rlcg_reg_access_flag(struct amdgpu_device *adev,
 	return ret;
 }
 
-static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag)
+static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 flag, u32 xcc_id)
 {
 	struct amdgpu_rlcg_reg_access_ctrl *reg_access_ctrl;
 	uint32_t timeout = 50000;
@@ -972,7 +993,12 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v
 		return 0;
 	}
 
-	reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl;
+	if (adev->gfx.xcc_mask && (((1 << xcc_id) & adev->gfx.xcc_mask) == 0)) {
+		dev_err(adev->dev, "invalid xcc\n");
+		return 0;
+	}
+
+	reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl[xcc_id];
 	scratch_reg0 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg0;
 	scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1;
 	scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2;
@@ -1037,13 +1063,13 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v
 
 void amdgpu_sriov_wreg(struct amdgpu_device *adev,
 		       u32 offset, u32 value,
-		       u32 acc_flags, u32 hwip)
+		       u32 acc_flags, u32 hwip, u32 xcc_id)
 {
 	u32 rlcg_flag;
 
 	if (!amdgpu_sriov_runtime(adev) &&
 		amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, true, &rlcg_flag)) {
-		amdgpu_virt_rlcg_reg_rw(adev, offset, value, rlcg_flag);
+		amdgpu_virt_rlcg_reg_rw(adev, offset, value, rlcg_flag, xcc_id);
 		return;
 	}
 
@@ -1054,13 +1080,13 @@ void amdgpu_sriov_wreg(struct amdgpu_device *adev,
 }
 
 u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
-		      u32 offset, u32 acc_flags, u32 hwip)
+		      u32 offset, u32 acc_flags, u32 hwip, u32 xcc_id)
 {
 	u32 rlcg_flag;
 
 	if (!amdgpu_sriov_runtime(adev) &&
 		amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, false, &rlcg_flag))
-		return amdgpu_virt_rlcg_reg_rw(adev, offset, 0, rlcg_flag);
+		return amdgpu_virt_rlcg_reg_rw(adev, offset, 0, rlcg_flag, xcc_id);
 
 	if (acc_flags & AMDGPU_REGS_NO_KIQ)
 		return RREG32_NO_KIQ(offset);