Merge tag 'amd-drm-next-5.13-2021-03-23' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.13-2021-03-23:

amdgpu:
- Debugfs cleanup
- Various cleanups and spelling fixes
- Flexible array cleanups
- Initial AMD Freesync HDMI
- Display fixes
- 10bpc dithering improvements
- Display ASSR support
- Clean up and unify powerplay and swsmu interfaces
- Vangogh fixes
- Add SMU gfx busy queues for RV/PCO
- PCIE DPM fixes
- S0ix fixes
- GPU metrics data fixes
- DCN secure display support
- Backlight type override
- Add initial support for Aldebaran
- RAS fixes
- Prime fixes for A+A systems
- Reset fixes
- Initial resource cursor support
- Drop legacy IO BAR requirements
- Various power fixes

amdkfd:
- MMU notifier fixes
- APU fixes

radeon:
- Debugfs cleanups
- Flexible array cleanups

UAPI:
- amdgpu: Add a new INFO ioctl interface to query video capabilities
  rather than hardcoding them in userspace.  This allows us to provide
  fine grained asic capabilities (e.g., if a particular part is
  bandwidth limited, we can limit the capabilities).  Proposed userspace:
  https://gitlab.freedesktop.org/leoliu/drm/-/commits/info_video_caps
  https://gitlab.freedesktop.org/leoliu/mesa/-/commits/info_video_caps
- amdkfd: bump the driver version.  There was a problem with reporting
  some RAS features on older versions of the driver. Proposed userspace:
  https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/commit/7cdd63475c36bb9f49bb960f90f9a8cdb7e80a21

Danvet: A bunch of conflicts all over, but it seems to compile ... I
did put the call to dc_allow_idle_optimizations() on a single line
since it looked a bit too jarring to be left alone.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210324040147.1990338-1-alexander.deucher@amd.com

1 files changed, 23 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index def583916294..b61d1ba1aa9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -238,7 +238,8 @@ static int vcn_v3_0_sw_init(void *handle)
 
 		fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
 		fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SW_RING_FLAG) |
-					     cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG);
+					     cpu_to_le32(AMDGPU_VCN_MULTI_QUEUE_FLAG) |
+					     cpu_to_le32(AMDGPU_VCN_FW_SHARED_FLAG_0_RB);
 		fw_shared->sw_ring.is_enabled = cpu_to_le32(DEC_SW_RING_ENABLED);
 	}
 
@@ -1074,7 +1075,13 @@ static int vcn_v3_0_start_dpg_mode(struct amdgpu_device *adev, int inst_idx, boo
 	WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR,
 		lower_32_bits(ring->wptr));
 
+	/* Reset FW shared memory RBC WPTR/RPTR */
+	fw_shared->rb.rptr = 0;
+	fw_shared->rb.wptr = lower_32_bits(ring->wptr);
+
+	/*resetting done, fw can check RB ring */
 	fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
 	/* Unstall DPG */
 	WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
 		0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
@@ -1239,9 +1246,11 @@ static int vcn_v3_0_start(struct amdgpu_device *adev)
 		/* Initialize the ring buffer's read and write pointers */
 		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR, 0);
 
+		WREG32_SOC15(VCN, i, mmUVD_SCRATCH2, 0);
 		ring->wptr = RREG32_SOC15(VCN, i, mmUVD_RBC_RB_RPTR);
 		WREG32_SOC15(VCN, i, mmUVD_RBC_RB_WPTR,
 			lower_32_bits(ring->wptr));
+		fw_shared->rb.wptr = lower_32_bits(ring->wptr);
 		fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
 
 		fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
@@ -1662,6 +1671,10 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
 				WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
 				fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
 
+				/* restore wptr/rptr with pointers saved in FW shared memory*/
+				WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_RPTR, fw_shared->rb.rptr);
+				WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, fw_shared->rb.wptr);
+
 				/* Unstall DPG */
 				WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
 					0, ~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
@@ -1721,6 +1734,15 @@ static uint64_t vcn_v3_0_dec_ring_get_wptr(struct amdgpu_ring *ring)
 static void vcn_v3_0_dec_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
+	volatile struct amdgpu_fw_shared *fw_shared;
+
+	if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+		/*whenever update RBC_RB_WPTR, we save the wptr in shared rb.wptr and scratch2 */
+		fw_shared = adev->vcn.inst[ring->me].fw_shared_cpu_addr;
+		fw_shared->rb.wptr = lower_32_bits(ring->wptr);
+		WREG32_SOC15(VCN, ring->me, mmUVD_SCRATCH2,
+			lower_32_bits(ring->wptr));
+	}
 
 	if (ring->use_doorbell) {
 		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);