Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux

Pull drm u pdates from Dave Airlie:
 "This is the main drm pull request for v4.12. Apart from two fixes
  pulls, everything should have been in drm-next for at least 2 weeks.

  The biggest thing in here is AMD released the public headers for their
  upcoming VEGA GPUs. These as always are quite a sizeable chunk of
  header files. They've also added initial non-display support for those
  GPUs, though they aren't available in production yet.

  Otherwise it's pretty much normal.

  New bridge drivers:
   - megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
   - generic LVDS bridge support.

  Core:
   - Displayport link train failure reporting to userspace
   - debugfs interface cleaned up
   - subsystem TODO in kerneldoc now
   - Extended fbdev support (flipping and vblank wait)
   - drm_platform removed
   - EDP CRC support in helper
   - HF-VSDB SCDC support in EDID parser
   - Lots of code cleanups and header extraction
   - Thunderbolt external GPU awareness
   - Atomic helper improvements
   - Documentation improvements

  panel:
   - Sitronix and Samsung new panel support

  amdgpu:
   - Preliminary vega10 support
   - Multi-level page table support
   - GPU sensor support for userspace
   - PRT support for sparse buffers
   - SR-IOV improvements
   - Non-contig VRAM CPU mapping

  i915:
   - Atomic modesetting enabled by default on Gen5+
   - LSPCON improvements
   - Atomic state handling for cdclk
   - GPU reset improvements
   - In-kernel unit tests
   - Geminilake improvements and color manager support
   - Designware i2c fixes
   - vblank evasion improvements
   - Hotplug safe connector iterators
   - GVT scheduler QoS support
   - GVT Kabylake support

  nouveau:
   - Acceleration support for Pascal (GP10x).
   - Rearchitecture of code handling proprietary signed firmware
   - Fix GTX 970 with odd MMU configuration
   - GP10B support
   - GP107 acceleration support

  vmwgfx:
   - Atomic modesetting support for vmwgfx

  omapdrm:
   - Support for render nodes
   - Refactor omapdss code
   - Fix some probe ordering issues
   - Fix too dark RGB565 rendering

  sunxi:
   - prelim rework for multiple pipes.

  mali-dp:
   - Color management support
   - Plane scaling
   - Power management improvements

  imx-drm:
   - Prefetch Resolve Engine/Gasket on i.MX6QP
   - Deferred plane disabling
   - Separate alpha support

  mediatek:
   - Mediatek SoC MT2701 support

  rcar-du:
   - Gen3 HDMI support

  msm:
   - 4k support for newer chips
   - OPP bindings for gpu
   - prep work for per-process pagetables

  vc4:
   - HDMI audio support
   - fixes

  qxl:
   - minor fixes.

  dw-hdmi:
   - PHY improvements
   - CSC fixes
   - Amlogic GX SoC support"

* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
  drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
  drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
  drm/nouveau/kms: Increase max retries in scanout position queries.
  drm/nouveau/bios/bitP: check that table is long enough for optional pointers
  drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
  drm: mali-dp: use div_u64 for expensive 64-bit divisions
  drm/i915: Confirm the request is still active before adding it to the await
  drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
  drm/i915/selftests: Allocate inode/file dynamically
  drm/i915: Fix system hang with EI UP masked on Haswell
  drm/i915: checking for NULL instead of IS_ERR() in mock selftests
  drm/i915: Perform link quality check unconditionally during long pulse
  drm/i915: Fix use after free in lpe_audio_platdev_destroy()
  drm/i915: Use the right mapping_gfp_mask for final shmem allocation
  drm/i915: Make legacy cursor updates more unsynced
  drm/i915: Apply a cond_resched() to the saturated signaler
  drm/i915: Park the signaler before sleeping
  drm: mali-dp: Check the mclk rate and allow up/down scaling
  drm: mali-dp: Enable image enhancement when scaling
  drm: mali-dp: Add plane upscaling support
  ...

1 files changed, 32 insertions, 55 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 9ea99348e493..47f70827195b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -52,7 +52,7 @@ static void vce_v2_0_set_irq_funcs(struct amdgpu_device *adev);
  *
  * Returns the current hardware read pointer
  */
-static uint32_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
+static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
@@ -69,7 +69,7 @@ static uint32_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
  *
  * Returns the current hardware write pointer
  */
-static uint32_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
+static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
@@ -91,9 +91,9 @@ static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 
 	if (ring == &adev->vce.ring[0])
-		WREG32(mmVCE_RB_WPTR, ring->wptr);
+		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	else
-		WREG32(mmVCE_RB_WPTR2, ring->wptr);
+		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 }
 
 static int vce_v2_0_lmi_clean(struct amdgpu_device *adev)
@@ -167,8 +167,7 @@ static void vce_v2_0_init_cg(struct amdgpu_device *adev)
 
 static void vce_v2_0_mc_resume(struct amdgpu_device *adev)
 {
-	uint64_t addr = adev->vce.gpu_addr;
-	uint32_t size;
+	uint32_t size, offset;
 
 	WREG32_P(mmVCE_CLOCK_GATING_A, 0, ~(1 << 16));
 	WREG32_P(mmVCE_UENC_CLOCK_GATING, 0x1FF000, ~0xFF9FF000);
@@ -181,19 +180,21 @@ static void vce_v2_0_mc_resume(struct amdgpu_device *adev)
 	WREG32(mmVCE_LMI_SWAP_CNTL1, 0);
 	WREG32(mmVCE_LMI_VM_CTRL, 0);
 
-	addr += AMDGPU_VCE_FIRMWARE_OFFSET;
+	WREG32(mmVCE_LMI_VCPU_CACHE_40BIT_BAR, (adev->vce.gpu_addr >> 8));
+
+	offset = AMDGPU_VCE_FIRMWARE_OFFSET;
 	size = VCE_V2_0_FW_SIZE;
-	WREG32(mmVCE_VCPU_CACHE_OFFSET0, addr & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_OFFSET0, offset & 0x7fffffff);
 	WREG32(mmVCE_VCPU_CACHE_SIZE0, size);
 
-	addr += size;
+	offset += size;
 	size = VCE_V2_0_STACK_SIZE;
-	WREG32(mmVCE_VCPU_CACHE_OFFSET1, addr & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_OFFSET1, offset & 0x7fffffff);
 	WREG32(mmVCE_VCPU_CACHE_SIZE1, size);
 
-	addr += size;
+	offset += size;
 	size = VCE_V2_0_DATA_SIZE;
-	WREG32(mmVCE_VCPU_CACHE_OFFSET2, addr & 0x7fffffff);
+	WREG32(mmVCE_VCPU_CACHE_OFFSET2, offset & 0x7fffffff);
 	WREG32(mmVCE_VCPU_CACHE_SIZE2, size);
 
 	WREG32_P(mmVCE_LMI_CTRL2, 0x0, ~0x100);
@@ -240,15 +241,15 @@ static int vce_v2_0_start(struct amdgpu_device *adev)
 	vce_v2_0_mc_resume(adev);
 
 	ring = &adev->vce.ring[0];
-	WREG32(mmVCE_RB_RPTR, ring->wptr);
-	WREG32(mmVCE_RB_WPTR, ring->wptr);
+	WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr);
 	WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
 	WREG32(mmVCE_RB_SIZE, ring->ring_size / 4);
 
 	ring = &adev->vce.ring[1];
-	WREG32(mmVCE_RB_RPTR2, ring->wptr);
-	WREG32(mmVCE_RB_WPTR2, ring->wptr);
+	WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr));
+	WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 	WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr);
 	WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4);
@@ -273,24 +274,14 @@ static int vce_v2_0_start(struct amdgpu_device *adev)
 
 static int vce_v2_0_stop(struct amdgpu_device *adev)
 {
-	int i, j;
+	int i;
 	int status;
 
 	if (vce_v2_0_lmi_clean(adev)) {
 		DRM_INFO("vce is not idle \n");
 		return 0;
 	}
-/*
-	for (i = 0; i < 10; ++i) {
-		for (j = 0; j < 100; ++j) {
-			status = RREG32(mmVCE_FW_REG_STATUS);
-			if (!(status & 1))
-				break;
-			mdelay(1);
-		}
-		break;
-	}
-*/
+
 	if (vce_v2_0_wait_for_idle(adev)) {
 		DRM_INFO("VCE is busy, Can't set clock gateing");
 		return 0;
@@ -299,14 +290,11 @@ static int vce_v2_0_stop(struct amdgpu_device *adev)
 	/* Stall UMC and register bus before resetting VCPU */
 	WREG32_P(mmVCE_LMI_CTRL2, 1 << 8, ~(1 << 8));
 
-	for (i = 0; i < 10; ++i) {
-		for (j = 0; j < 100; ++j) {
-			status = RREG32(mmVCE_LMI_STATUS);
-			if (status & 0x240)
-				break;
-			mdelay(1);
-		}
-		break;
+	for (i = 0; i < 100; ++i) {
+		status = RREG32(mmVCE_LMI_STATUS);
+		if (status & 0x240)
+			break;
+		mdelay(1);
 	}
 
 	WREG32_P(mmVCE_VCPU_CNTL, 0, ~0x80001);
@@ -429,7 +417,7 @@ static int vce_v2_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* VCE */
-	r = amdgpu_irq_add_id(adev, 167, &adev->vce.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 167, &adev->vce.irq);
 	if (r)
 		return r;
 
@@ -463,11 +451,7 @@ static int vce_v2_0_sw_fini(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_vce_sw_fini(adev);
-	if (r)
-		return r;
-
-	return r;
+	return amdgpu_vce_sw_fini(adev);
 }
 
 static int vce_v2_0_hw_init(void *handle)
@@ -507,11 +491,7 @@ static int vce_v2_0_suspend(void *handle)
 	if (r)
 		return r;
 
-	r = amdgpu_vce_suspend(adev);
-	if (r)
-		return r;
-
-	return r;
+	return amdgpu_vce_suspend(adev);
 }
 
 static int vce_v2_0_resume(void *handle)
@@ -523,11 +503,7 @@ static int vce_v2_0_resume(void *handle)
 	if (r)
 		return r;
 
-	r = vce_v2_0_hw_init(adev);
-	if (r)
-		return r;
-
-	return r;
+	return vce_v2_0_hw_init(adev);
 }
 
 static int vce_v2_0_soft_reset(void *handle)
@@ -559,14 +535,14 @@ static int vce_v2_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_iv_entry *entry)
 {
 	DRM_DEBUG("IH: VCE\n");
-	switch (entry->src_data) {
+	switch (entry->src_data[0]) {
 	case 0:
 	case 1:
-		amdgpu_fence_process(&adev->vce.ring[entry->src_data]);
+		amdgpu_fence_process(&adev->vce.ring[entry->src_data[0]]);
 		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
-			  entry->src_id, entry->src_data);
+			  entry->src_id, entry->src_data[0]);
 		break;
 	}
 
@@ -630,6 +606,7 @@ static const struct amdgpu_ring_funcs vce_v2_0_ring_funcs = {
 	.type = AMDGPU_RING_TYPE_VCE,
 	.align_mask = 0xf,
 	.nop = VCE_CMD_NO_OP,
+	.support_64bit_ptrs = false,
 	.get_rptr = vce_v2_0_ring_get_rptr,
 	.get_wptr = vce_v2_0_ring_get_wptr,
 	.set_wptr = vce_v2_0_ring_set_wptr,