Merge tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Core:
   - Fence destaging work
   - DRIVER_LEGACY to split off legacy drm drivers
   - drm_mm refactoring
   - Splitting drm_crtc.c into chunks and documenting better
   - Display info fixes
   - rbtree support for prime buffer lookup
   - Simple VGA DAC driver

  Panel:
   - Add Nexus 7 panel
   - More simple panels

  i915:
   - Refactoring GEM naming
   - Refactored vma/active tracking
   - Lockless request lookups
   - Better stolen memory support
   - FBC fixes
   - SKL watermark fixes
   - VGPU improvements
   - dma-buf fencing support
   - Better DP dongle support

  amdgpu:
   - Powerplay for Iceland asics
   - Improved GPU reset support
   - UVD/VEC powergating support for CZ/ST
   - Preinitialised VRAM buffer support
   - Virtual display support
   - Initial SI support
   - GTT rework
   - PCI shutdown callback support
   - HPD IRQ storm fixes

  amdkfd:
   - bugfixes

  tilcdc:
   - Atomic modesetting support

  mediatek:
   - AAL + GAMMA engine support
   - Hook up gamma LUT
   - Temporal dithering support

  imx:
   - Pixel clock from devicetree
   - drm bridge support for LVDS bridges
   - active plane reconfiguration
   - VDIC deinterlacer support
   - Frame synchronisation unit support
   - Color space conversion support

  analogix:
   - PSR support
   - Better panel on/off support

  rockchip:
   - rk3399 vop/crtc support
   - PSR support

  vc4:
   - Interlaced vblank timing
   - 3D rendering CPU overhead reduction
   - HDMI output fixes

  tda998x:
   - HDMI audio ASoC support

  sunxi:
   - Allwinner A33 support
   - better TCON support

  msm:
   - DT binding cleanups
   - Explicit fence-fd support

  sti:
   - remove sti415/416 support

  etnaviv:
   - MMUv2 refactoring
   - GC3000 support

  exynos:
   - Refactoring HDMI DCC/PHY
   - G2D pm regression fix
   - Page fault issues with wait for vblank

  There is no nouveau work in this tree, as Ben didn't get a pull
  request in, and he was fighting moving to atomic and adding mst
  support, so maybe best it waits for a cycle"

* tag 'drm-for-v4.9' of git://people.freedesktop.org/~airlied/linux: (1412 commits)
  drm/crtc: constify drm_crtc_index parameter
  drm/i915: Fix conflict resolution from backmerge of v4.8-rc8 to drm-next
  drm/i915/guc: Unwind GuC workqueue reservation if request construction fails
  drm/i915: Reset the breadcrumbs IRQ more carefully
  drm/i915: Force relocations via cpu if we run out of idle aperture
  drm/i915: Distinguish last emitted request from last submitted request
  drm/i915: Allow DP to work w/o EDID
  drm/i915: Move long hpd handling into the hotplug work
  drm/i915/execlists: Reinitialise context image after GPU hang
  drm/i915: Use correct index for backtracking HUNG semaphores
  drm/i915: Unalias obj->phys_handle and obj->userptr
  drm/i915: Just clear the mmiodebug before a register access
  drm/i915/gen9: only add the planes actually affected by ddb changes
  drm/i915: Allow PCH DPLL sharing regardless of DPLL_SDVO_HIGH_SPEED
  drm/i915/bxt: Fix HDMI DPLL configuration
  drm/i915/gen9: fix the watermark res_blocks value
  drm/i915/gen9: fix plane_blocks_per_line on watermarks calculations
  drm/i915/gen9: minimum scanlines for Y tile is not always 4
  drm/i915/gen9: fix the WaWmMemoryReadLatency implementation
  drm/i915/kbl: KBL also needs to run the SAGV code
  ...

1 files changed, 55 insertions, 76 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index 77fdd9911c3cb..cb952acc71339 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -695,24 +695,16 @@ static void cik_sdma_vm_copy_pte(struct amdgpu_ib *ib,
 				 uint64_t pe, uint64_t src,
 				 unsigned count)
 {
-	while (count) {
-		unsigned bytes = count * 8;
-		if (bytes > 0x1FFFF8)
-			bytes = 0x1FFFF8;
-
-		ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_COPY,
-			SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
-		ib->ptr[ib->length_dw++] = bytes;
-		ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
-		ib->ptr[ib->length_dw++] = lower_32_bits(src);
-		ib->ptr[ib->length_dw++] = upper_32_bits(src);
-		ib->ptr[ib->length_dw++] = lower_32_bits(pe);
-		ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-
-		pe += bytes;
-		src += bytes;
-		count -= bytes / 8;
-	}
+	unsigned bytes = count * 8;
+
+	ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_COPY,
+		SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+	ib->ptr[ib->length_dw++] = bytes;
+	ib->ptr[ib->length_dw++] = 0; /* src/dst endian swap */
+	ib->ptr[ib->length_dw++] = lower_32_bits(src);
+	ib->ptr[ib->length_dw++] = upper_32_bits(src);
+	ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+	ib->ptr[ib->length_dw++] = upper_32_bits(pe);
 }
 
 /**
@@ -720,39 +712,27 @@ static void cik_sdma_vm_copy_pte(struct amdgpu_ib *ib,
  *
  * @ib: indirect buffer to fill with commands
  * @pe: addr of the page entry
- * @addr: dst addr to write into pe
+ * @value: dst addr to write into pe
  * @count: number of page entries to update
  * @incr: increase next addr by incr bytes
- * @flags: access flags
  *
  * Update PTEs by writing them manually using sDMA (CIK).
  */
-static void cik_sdma_vm_write_pte(struct amdgpu_ib *ib,
-				  const dma_addr_t *pages_addr, uint64_t pe,
-				  uint64_t addr, unsigned count,
-				  uint32_t incr, uint32_t flags)
+static void cik_sdma_vm_write_pte(struct amdgpu_ib *ib, uint64_t pe,
+				  uint64_t value, unsigned count,
+				  uint32_t incr)
 {
-	uint64_t value;
-	unsigned ndw;
-
-	while (count) {
-		ndw = count * 2;
-		if (ndw > 0xFFFFE)
-			ndw = 0xFFFFE;
-
-		/* for non-physically contiguous pages (system) */
-		ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_WRITE,
-			SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
-		ib->ptr[ib->length_dw++] = pe;
-		ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-		ib->ptr[ib->length_dw++] = ndw;
-		for (; ndw > 0; ndw -= 2, --count, pe += 8) {
-			value = amdgpu_vm_map_gart(pages_addr, addr);
-			addr += incr;
-			value |= flags;
-			ib->ptr[ib->length_dw++] = value;
-			ib->ptr[ib->length_dw++] = upper_32_bits(value);
-		}
+	unsigned ndw = count * 2;
+
+	ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_WRITE,
+		SDMA_WRITE_SUB_OPCODE_LINEAR, 0);
+	ib->ptr[ib->length_dw++] = lower_32_bits(pe);
+	ib->ptr[ib->length_dw++] = upper_32_bits(pe);
+	ib->ptr[ib->length_dw++] = ndw;
+	for (; ndw > 0; ndw -= 2) {
+		ib->ptr[ib->length_dw++] = lower_32_bits(value);
+		ib->ptr[ib->length_dw++] = upper_32_bits(value);
+		value += incr;
 	}
 }
 
@@ -768,40 +748,21 @@ static void cik_sdma_vm_write_pte(struct amdgpu_ib *ib,
  *
  * Update the page tables using sDMA (CIK).
  */
-static void cik_sdma_vm_set_pte_pde(struct amdgpu_ib *ib,
-				    uint64_t pe,
+static void cik_sdma_vm_set_pte_pde(struct amdgpu_ib *ib, uint64_t pe,
 				    uint64_t addr, unsigned count,
 				    uint32_t incr, uint32_t flags)
 {
-	uint64_t value;
-	unsigned ndw;
-
-	while (count) {
-		ndw = count;
-		if (ndw > 0x7FFFF)
-			ndw = 0x7FFFF;
-
-		if (flags & AMDGPU_PTE_VALID)
-			value = addr;
-		else
-			value = 0;
-
-		/* for physically contiguous pages (vram) */
-		ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
-		ib->ptr[ib->length_dw++] = pe; /* dst addr */
-		ib->ptr[ib->length_dw++] = upper_32_bits(pe);
-		ib->ptr[ib->length_dw++] = flags; /* mask */
-		ib->ptr[ib->length_dw++] = 0;
-		ib->ptr[ib->length_dw++] = value; /* value */
-		ib->ptr[ib->length_dw++] = upper_32_bits(value);
-		ib->ptr[ib->length_dw++] = incr; /* increment size */
-		ib->ptr[ib->length_dw++] = 0;
-		ib->ptr[ib->length_dw++] = ndw; /* number of entries */
-
-		pe += ndw * 8;
-		addr += ndw * incr;
-		count -= ndw;
-	}
+	/* for physically contiguous pages (vram) */
+	ib->ptr[ib->length_dw++] = SDMA_PACKET(SDMA_OPCODE_GENERATE_PTE_PDE, 0, 0);
+	ib->ptr[ib->length_dw++] = lower_32_bits(pe); /* dst addr */
+	ib->ptr[ib->length_dw++] = upper_32_bits(pe);
+	ib->ptr[ib->length_dw++] = flags; /* mask */
+	ib->ptr[ib->length_dw++] = 0;
+	ib->ptr[ib->length_dw++] = lower_32_bits(addr); /* value */
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = incr; /* increment size */
+	ib->ptr[ib->length_dw++] = 0;
+	ib->ptr[ib->length_dw++] = count; /* number of entries */
 }
 
 /**
@@ -887,6 +848,22 @@ static void cik_sdma_ring_emit_vm_flush(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, (0xfff << 16) | 10); /* retry count, poll interval */
 }
 
+static unsigned cik_sdma_ring_get_emit_ib_size(struct amdgpu_ring *ring)
+{
+	return
+		7 + 4; /* cik_sdma_ring_emit_ib */
+}
+
+static unsigned cik_sdma_ring_get_dma_frame_size(struct amdgpu_ring *ring)
+{
+	return
+		6 + /* cik_sdma_ring_emit_hdp_flush */
+		3 + /* cik_sdma_ring_emit_hdp_invalidate */
+		6 + /* cik_sdma_ring_emit_pipeline_sync */
+		12 + /* cik_sdma_ring_emit_vm_flush */
+		9 + 9 + 9; /* cik_sdma_ring_emit_fence x3 for user fence, vm fence */
+}
+
 static void cik_enable_sdma_mgcg(struct amdgpu_device *adev,
 				 bool enable)
 {
@@ -1262,6 +1239,8 @@ static const struct amdgpu_ring_funcs cik_sdma_ring_funcs = {
 	.test_ib = cik_sdma_ring_test_ib,
 	.insert_nop = cik_sdma_ring_insert_nop,
 	.pad_ib = cik_sdma_ring_pad_ib,
+	.get_emit_ib_size = cik_sdma_ring_get_emit_ib_size,
+	.get_dma_frame_size = cik_sdma_ring_get_dma_frame_size,
 };
 
 static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)