Merge branch 'drm-next-4.10' of git://people.freedesktop.org/~agd5f/linux into drm-next

- lots of code cleanup
- lots of bug fixes
- expose rpm based fan info via hwmon
- lots of clock and powergating fixes
- SI register header cleanup and conversion to common format used by newer asics

* 'drm-next-4.10' of git://people.freedesktop.org/~agd5f/linux: (54 commits)
  drm/amdgpu: drop is_display_hung from display funcs
  drm/amdgpu/uvd: reduce IB parsing overhead on UVD5+ (v2)
  drm/amdgpu/uvd: consolidate code for fetching addr from ctx
  drm/amdgpu: Disable DPM in virtualization
  drm/amdgpu: use AMDGPU_GEM_CREATE_VRAM_CLEARED for VM PD/PTs (v2)
  drm/amdgpu: improve AMDGPU_GEM_CREATE_VRAM_CLEARED handling (v2)
  drm/amdgpu: fix error handling in amdgpu_bo_create_restricted
  drm/amdgpu: fix amdgpu_fill_buffer (v2)
  drm/amdgpu: remove amdgpu_irq_get_delayed
  amdgpu: Wrap dev_err() calls on vm faults with printk_ratelimit()
  amdgpu: Use dev_err() over vanilla printk() in vm_decode_fault()
  drm/amd/amdgpu: port of DCE v6 to new headers (v3)
  drm/amdgpu: cleanup unused iterator members for sdma v2.4
  drm/amdgpu: cleanup unused iterator members for sdma v3
  drm/amdgpu:impl vgt_flush for VI(V5)
  drm/amdgpu: enable uvd mgcg for Fiji.
  drm/amdgpu: refine cz uvd clock gate logic.
  drm/amdgpu: change log level to KERN_INFO in ci_dpm.c
  drm/amdgpu: always un-gate UVD REGS path.
  drm/amdgpu/sdma: fix typo in packet setup
  ...

1 files changed, 19 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 5b631fd1a879..1a745cf93f47 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2105,6 +2105,18 @@ static void gfx_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, 0x20); /* poll interval */
 }
 
+static void gfx_v7_0_ring_emit_vgt_flush(struct amdgpu_ring *ring)
+{
+	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+	amdgpu_ring_write(ring, EVENT_TYPE(VS_PARTIAL_FLUSH) |
+		EVENT_INDEX(4));
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_EVENT_WRITE, 0));
+	amdgpu_ring_write(ring, EVENT_TYPE(VGT_FLUSH) |
+		EVENT_INDEX(0));
+}
+
+
 /**
  * gfx_v7_0_ring_emit_hdp_invalidate - emit an hdp invalidate on the cp
  *
@@ -2260,6 +2272,7 @@ static void gfx_v7_ring_emit_cntxcntl(struct amdgpu_ring *ring, uint32_t flags)
 
 	dw2 |= 0x80000000; /* set load_enable otherwise this package is just NOPs */
 	if (flags & AMDGPU_HAVE_CTX_SWITCH) {
+		gfx_v7_0_ring_emit_vgt_flush(ring);
 		/* set load_global_config & load_global_uconfig */
 		dw2 |= 0x8001;
 		/* set load_cs_sh_regs */
@@ -4359,7 +4372,11 @@ static void gfx_v7_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
 
 static uint32_t wave_read_ind(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t address)
 {
-	WREG32(mmSQ_IND_INDEX, (wave & 0xF) | ((simd & 0x3) << 4) | (address << 16) | (1 << 13));
+	WREG32(mmSQ_IND_INDEX,
+		(wave << SQ_IND_INDEX__WAVE_ID__SHIFT) |
+		(simd << SQ_IND_INDEX__SIMD_ID__SHIFT) |
+		(address << SQ_IND_INDEX__INDEX__SHIFT) |
+		(SQ_IND_INDEX__FORCE_READ_MASK));
 	return RREG32(mmSQ_IND_DATA);
 }
 
@@ -5149,7 +5166,7 @@ static const struct amdgpu_ring_funcs gfx_v7_0_ring_funcs_gfx = {
 		12 + 12 + 12 + /* gfx_v7_0_ring_emit_fence_gfx x3 for user fence, vm fence */
 		7 + 4 + /* gfx_v7_0_ring_emit_pipeline_sync */
 		17 + 6 + /* gfx_v7_0_ring_emit_vm_flush */
-		3, /* gfx_v7_ring_emit_cntxcntl */
+		3 + 4, /* gfx_v7_ring_emit_cntxcntl including vgt flush*/
 	.emit_ib_size = 4, /* gfx_v7_0_ring_emit_ib_gfx */
 	.emit_ib = gfx_v7_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v7_0_ring_emit_fence_gfx,