Merge branch 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux into drm-next

More features for 4.14.  Nothing too major here.  I have a few more additional
patches for large page support in vega10 among other things, but they require
some resevation object patches from drm-misc-next, so I'll send that request
once you've pulled the latest drm-misc-next.  Highlights:
- Fixes for ACP audio on stoney
- SR-IOV fixes for vega10
- various powerplay fixes
- lots of code clean up

* 'drm-next-4.14' of git://people.freedesktop.org/~agd5f/linux: (62 commits)
  drm/amdgpu/gfx7: fix function name
  drm/amd/amdgpu: Disabling Power Gating for Stoney platform
  drm/amd/amdgpu: Added a quirk for Stoney platform
  drm/amdgpu: jt_size was wrongly counted twice
  drm/amdgpu: fix missing endian-safe guard
  drm/amdgpu: ignore digest_size when loading sdma fw for raven
  drm/amdgpu: Uninitialized variable in amdgpu_ttm_backend_bind()
  drm/amd/powerplay: fix coding style in hwmgr.c
  drm/amd/powerplay: refine dmesg info under powerplay.
  drm/amdgpu: don't finish the ring if not initialized
  drm/radeon: Fix preferred typo
  drm/amdgpu: Fix preferred typo
  drm/radeon: Fix stolen typo
  drm/amdgpu: Fix stolen typo
  drm/amd/powerplay: fix coccinelle warnings in vega10_hwmgr.c
  drm/amdgpu: set gfx_v9_0_ip_funcs as static
  drm/radeon: switch to drm_*{get,put} helpers
  drm/amdgpu: switch to drm_*{get,put} helpers
  drm/amd/powerplay: add CZ profile support
  drm/amd/powerplay: fix PSI not enabled by kmd
  ...

1 files changed, 19 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 591f3e7fb508..fd7c72aaafa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -291,6 +291,8 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 	DRM_DEBUG("Setting write pointer\n");
 	if (ring->use_doorbell) {
+		u64 *wb = (u64 *)&adev->wb.wb[ring->wptr_offs];
+
 		DRM_DEBUG("Using doorbell -- "
 				"wptr_offs == 0x%08x "
 				"lower_32_bits(ring->wptr) << 2 == 0x%08x "
@@ -299,8 +301,7 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 				lower_32_bits(ring->wptr << 2),
 				upper_32_bits(ring->wptr << 2));
 		/* XXX check if swapping is necessary on BE */
-		adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr << 2);
-		adev->wb.wb[ring->wptr_offs + 1] = upper_32_bits(ring->wptr << 2);
+		WRITE_ONCE(*wb, (ring->wptr << 2));
 		DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
@@ -573,12 +574,13 @@ static void sdma_v4_0_enable(struct amdgpu_device *adev, bool enable)
 static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
 {
 	struct amdgpu_ring *ring;
-	u32 rb_cntl, ib_cntl;
+	u32 rb_cntl, ib_cntl, wptr_poll_cntl;
 	u32 rb_bufsz;
 	u32 wb_offset;
 	u32 doorbell;
 	u32 doorbell_offset;
 	u32 temp;
+	u64 wptr_gpu_addr;
 	int i, r;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
@@ -660,6 +662,19 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
 			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_F32_CNTL), temp);
 		}
 
+		/* setup the wptr shadow polling */
+		wptr_gpu_addr = adev->wb.gpu_addr + (ring->wptr_offs * 4);
+		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_LO),
+		       lower_32_bits(wptr_gpu_addr));
+		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_ADDR_HI),
+		       upper_32_bits(wptr_gpu_addr));
+		wptr_poll_cntl = RREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL));
+		if (amdgpu_sriov_vf(adev))
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 1);
+		else
+			wptr_poll_cntl = REG_SET_FIELD(wptr_poll_cntl, SDMA0_GFX_RB_WPTR_POLL_CNTL, F32_POLL_ENABLE, 0);
+		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_WPTR_POLL_CNTL), wptr_poll_cntl);
+
 		/* enable DMA RB */
 		rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 1);
 		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_GFX_RB_CNTL), rb_cntl);
@@ -687,6 +702,7 @@ static int sdma_v4_0_gfx_resume(struct amdgpu_device *adev)
 
 		if (adev->mman.buffer_funcs_ring == ring)
 			amdgpu_ttm_set_active_vram_size(adev, adev->mc.real_vram_size);
+
 	}
 
 	return 0;
@@ -783,15 +799,12 @@ static int sdma_v4_0_load_microcode(struct amdgpu_device *adev)
 	const struct sdma_firmware_header_v1_0 *hdr;
 	const __le32 *fw_data;
 	u32 fw_size;
-	u32 digest_size = 0;
 	int i, j;
 
 	/* halt the MEs */
 	sdma_v4_0_enable(adev, false);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		uint16_t version_major;
-		uint16_t version_minor;
 		if (!adev->sdma.instance[i].fw)
 			return -EINVAL;
 
@@ -799,23 +812,12 @@ static int sdma_v4_0_load_microcode(struct amdgpu_device *adev)
 		amdgpu_ucode_print_sdma_hdr(&hdr->header);
 		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
 
-		version_major = le16_to_cpu(hdr->header.header_version_major);
-		version_minor = le16_to_cpu(hdr->header.header_version_minor);
-
-		if (version_major == 1 && version_minor >= 1) {
-			const struct sdma_firmware_header_v1_1 *sdma_v1_1_hdr = (const struct sdma_firmware_header_v1_1 *) hdr;
-			digest_size = le32_to_cpu(sdma_v1_1_hdr->digest_size);
-		}
-
-		fw_size -= digest_size;
-
 		fw_data = (const __le32 *)
 			(adev->sdma.instance[i].fw->data +
 				le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
 		WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_UCODE_ADDR), 0);
 
-
 		for (j = 0; j < fw_size; j++)
 			WREG32(sdma_v4_0_get_reg_offset(i, mmSDMA0_UCODE_DATA), le32_to_cpup(fw_data++));