Merge tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Not a huge amount of big things here, AMD has support for a few new HW
  variants (vangogh, green sardine, dimgrey cavefish), Intel has some
  more DG1 enablement. We have a few big reworks of the TTM layers and
  interfaces, GEM and atomic internal API reworks cross tree. fbdev is
  marked orphaned in here as well to reflect the current reality.

  core:
   - documentation updates
   - deprecate DRM_FORMAT_MOD_NONE
   - atomic crtc enable/disable rework
   - GEM convert drivers to gem object functions
   - remove SCATTER_LIST_MAX_SEGMENT

  sched:
   - avoid infinite waits

  ttm:
   - remove AGP support
   - don't modify caching for swapout
   - ttm pinning rework
   - major TTM reworks
   - new backend allocator
   - multihop support

  vram-helper:
   - top down BO placement fix
   - TTM changes
   - GEM object support

  displayport:
   - DP 2.0 DPCD prep work
   - DP MST extended DPCD caps

  fbdev:
   - mark as orphaned

  amdgpu:
   - Initial Vangogh support
   - Green Sardine support
   - Dimgrey Cavefish support
   - SG display support for renoir
   - SMU7 improvements
   - gfx9+ modiifier support
   - CI BACO fixes

  radeon:
   - expose voltage via hwmon on SUMO

  amdkfd:
   - fix unique id handling

  i915:
   - more DG1 enablement
   - bigjoiner support
   - integer scaling filter support
   - async flip support
   - ICL+ DSI command mode
   - Improve display shutdown
   - Display refactoring
   - eLLC machine fbdev loading fix
   - dma scatterlist fixes
   - TGL hang fixes
   - eLLC display buffer caching on SKL+
   - MOCS PTE seeting for gen9+

  msm:
   - Shutdown hook
   - GPU cooling device support
   - DSI 7nm and 10nm phy/pll updates
   - sm8150/sm2850 DPU support
   - GEM locking re-work
   - LLCC system cache support

  aspeed:
   - sysfs output config support

  ast:
   - LUT fix
   - new display mode

  gma500:
   - remove 2d framebuffer accel

  panfrost:
   - move gpu reset to a worker

  exynos:
   - new HDMI mode support

  mediatek:
   - MT8167 support
   - yaml bindings
   - MIPI DSI phy code moved

  etnaviv:
   - new perf counter
   - more lockdep annotation

  hibmc:
   - i2c DDC support

  ingenic:
   - pixel clock reset fix
   - reserved memory support
   - allow both DMA channels at once
   - different pixel format support
   - 30/24/8-bit palette modes

  tilcdc:
   - don't keep vblank irq enabled

  vc4:
   - new maintainer added
   - DSI registration fix

  virtio:
   - blob resource support
   - host visible and cross-device support
   - uuid api support"

* tag 'drm-next-2020-12-11' of git://anongit.freedesktop.org/drm/drm: (1754 commits)
  drm/amdgpu: Initialise drm_gem_object_funcs for imported BOs
  drm/amdgpu: fix size calculation with stolen vga memory
  drm/amdgpu: remove amdgpu_ttm_late_init  and amdgpu_bo_late_init
  drm/amdgpu: free the pre-OS console framebuffer after the first modeset
  drm/amdgpu: enable runtime pm using BACO on CI dGPUs
  drm/amdgpu/cik: enable BACO reset on Bonaire
  drm/amd/pm: update smu10.h WORKLOAD_PPLIB setting for raven
  drm/amd/pm: remove one unsupported smu function for vangogh
  drm/amd/display: setup system context for APUs
  drm/amd/display: add S/G support for Vangogh
  drm/amdkfd: Fix leak in dmabuf import
  drm/amdgpu: use AMDGPU_NUM_VMID when possible
  drm/amdgpu: fix sdma instance fw version and feature version init
  drm/amd/pm: update driver if version for dimgrey_cavefish
  drm/amd/display: 3.2.115
  drm/amd/display: [FW Promotion] Release 0.0.45
  drm/amd/display: Revert DCN2.1 dram_clock_change_latency update
  drm/amd/display: Enable gpu_vm_support for dcn3.01
  drm/amd/display: Fixed the audio noise during mode switching with HDCP mode on
  drm/amd/display: Add wm table for Renoir
  ...

1 files changed, 176 insertions, 20 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index a563328e3dae..1c97244e0d74 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -37,14 +37,16 @@
 #define FIRMWARE_RAVEN		"amdgpu/raven_vcn.bin"
 #define FIRMWARE_PICASSO	"amdgpu/picasso_vcn.bin"
 #define FIRMWARE_RAVEN2		"amdgpu/raven2_vcn.bin"
-#define FIRMWARE_ARCTURUS 	"amdgpu/arcturus_vcn.bin"
-#define FIRMWARE_RENOIR 	"amdgpu/renoir_vcn.bin"
-#define FIRMWARE_GREEN_SARDINE 	"amdgpu/green_sardine_vcn.bin"
-#define FIRMWARE_NAVI10 	"amdgpu/navi10_vcn.bin"
-#define FIRMWARE_NAVI14 	"amdgpu/navi14_vcn.bin"
-#define FIRMWARE_NAVI12 	"amdgpu/navi12_vcn.bin"
-#define FIRMWARE_SIENNA_CICHLID 	"amdgpu/sienna_cichlid_vcn.bin"
-#define FIRMWARE_NAVY_FLOUNDER 	"amdgpu/navy_flounder_vcn.bin"
+#define FIRMWARE_ARCTURUS	"amdgpu/arcturus_vcn.bin"
+#define FIRMWARE_RENOIR		"amdgpu/renoir_vcn.bin"
+#define FIRMWARE_GREEN_SARDINE	"amdgpu/green_sardine_vcn.bin"
+#define FIRMWARE_NAVI10		"amdgpu/navi10_vcn.bin"
+#define FIRMWARE_NAVI14		"amdgpu/navi14_vcn.bin"
+#define FIRMWARE_NAVI12		"amdgpu/navi12_vcn.bin"
+#define FIRMWARE_SIENNA_CICHLID	"amdgpu/sienna_cichlid_vcn.bin"
+#define FIRMWARE_NAVY_FLOUNDER	"amdgpu/navy_flounder_vcn.bin"
+#define FIRMWARE_VANGOGH	"amdgpu/vangogh_vcn.bin"
+#define FIRMWARE_DIMGREY_CAVEFISH	"amdgpu/dimgrey_cavefish_vcn.bin"
 
 MODULE_FIRMWARE(FIRMWARE_RAVEN);
 MODULE_FIRMWARE(FIRMWARE_PICASSO);
@@ -57,6 +59,8 @@ MODULE_FIRMWARE(FIRMWARE_NAVI14);
 MODULE_FIRMWARE(FIRMWARE_NAVI12);
 MODULE_FIRMWARE(FIRMWARE_SIENNA_CICHLID);
 MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER);
+MODULE_FIRMWARE(FIRMWARE_VANGOGH);
+MODULE_FIRMWARE(FIRMWARE_DIMGREY_CAVEFISH);
 
 static void amdgpu_vcn_idle_work_handler(struct work_struct *work);
 
@@ -130,6 +134,15 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
 		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
 			adev->vcn.indirect_sram = true;
 		break;
+	case CHIP_VANGOGH:
+		fw_name = FIRMWARE_VANGOGH;
+		break;
+	case CHIP_DIMGREY_CAVEFISH:
+		fw_name = FIRMWARE_DIMGREY_CAVEFISH;
+		if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) &&
+		    (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG))
+			adev->vcn.indirect_sram = true;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -319,6 +332,7 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		container_of(work, struct amdgpu_device, vcn.idle_work.work);
 	unsigned int fences = 0, fence[AMDGPU_MAX_VCN_INSTANCES] = {0};
 	unsigned int i, j;
+	int r = 0;
 
 	for (j = 0; j < adev->vcn.num_vcn_inst; ++j) {
 		if (adev->vcn.harvest_config & (1 << j))
@@ -345,8 +359,13 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 	}
 
 	if (!fences && !atomic_read(&adev->vcn.total_submission_cnt)) {
+		amdgpu_gfx_off_ctrl(adev, true);
 		amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
 		       AMD_PG_STATE_GATE);
+		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+				false);
+		if (r)
+			dev_warn(adev->dev, "(%d) failed to disable video power profile mode\n", r);
 	} else {
 		schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
 	}
@@ -355,9 +374,17 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
+	int r = 0;
 
 	atomic_inc(&adev->vcn.total_submission_cnt);
-	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
+	if (!cancel_delayed_work_sync(&adev->vcn.idle_work)) {
+		amdgpu_gfx_off_ctrl(adev, false);
+		r = amdgpu_dpm_switch_power_profile(adev, PP_SMC_POWER_PROFILE_VIDEO,
+				true);
+		if (r)
+			dev_warn(adev->dev, "(%d) failed to switch to video power profile mode\n", r);
+	}
 
 	mutex_lock(&adev->vcn.vcn_pg_lock);
 	amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
@@ -429,6 +456,37 @@ int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring)
 	return r;
 }
 
+int amdgpu_vcn_dec_sw_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t rptr;
+	unsigned int i;
+	int r;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	r = amdgpu_ring_alloc(ring, 16);
+	if (r)
+		return r;
+
+	rptr = amdgpu_ring_get_rptr(ring);
+
+	amdgpu_ring_write(ring, VCN_DEC_SW_CMD_END);
+	amdgpu_ring_commit(ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (amdgpu_ring_get_rptr(ring) != rptr)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		r = -ETIMEDOUT;
+
+	return r;
+}
+
 static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 				   struct amdgpu_bo *bo,
 				   struct dma_fence **fence)
@@ -483,16 +541,16 @@ err:
 }
 
 static int amdgpu_vcn_dec_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence)
+					 struct amdgpu_bo **bo)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_bo *bo = NULL;
 	uint32_t *msg;
 	int r, i;
 
+	*bo = NULL;
 	r = amdgpu_bo_create_reserved(adev, 1024, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &bo, NULL, (void **)&msg);
+				      bo, NULL, (void **)&msg);
 	if (r)
 		return r;
 
@@ -513,20 +571,20 @@ static int amdgpu_vcn_dec_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = 14; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	return amdgpu_vcn_dec_send_msg(ring, bo, fence);
+	return 0;
 }
 
 static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-			       struct dma_fence **fence)
+					  struct amdgpu_bo **bo)
 {
 	struct amdgpu_device *adev = ring->adev;
-	struct amdgpu_bo *bo = NULL;
 	uint32_t *msg;
 	int r, i;
 
+	*bo = NULL;
 	r = amdgpu_bo_create_reserved(adev, 1024, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
-				      &bo, NULL, (void **)&msg);
+				      bo, NULL, (void **)&msg);
 	if (r)
 		return r;
 
@@ -539,19 +597,117 @@ static int amdgpu_vcn_dec_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = 6; i < 1024; ++i)
 		msg[i] = cpu_to_le32(0x0);
 
-	return amdgpu_vcn_dec_send_msg(ring, bo, fence);
+	return 0;
 }
 
 int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
-	struct dma_fence *fence;
+	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo;
 	long r;
 
-	r = amdgpu_vcn_dec_get_create_msg(ring, 1, NULL);
+	r = amdgpu_vcn_dec_get_create_msg(ring, 1, &bo);
+	if (r)
+		goto error;
+
+	r = amdgpu_vcn_dec_send_msg(ring, bo, NULL);
+	if (r)
+		goto error;
+	r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, &bo);
+	if (r)
+		goto error;
+
+	r = amdgpu_vcn_dec_send_msg(ring, bo, &fence);
+	if (r)
+		goto error;
+
+	r = dma_fence_wait_timeout(fence, false, timeout);
+	if (r == 0)
+		r = -ETIMEDOUT;
+	else if (r > 0)
+		r = 0;
+
+	dma_fence_put(fence);
+error:
+	return r;
+}
+
+static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
+				   struct amdgpu_bo *bo,
+				   struct dma_fence **fence)
+{
+	struct amdgpu_vcn_decode_buffer *decode_buffer = NULL;
+	const unsigned int ib_size_dw = 64;
+	struct amdgpu_device *adev = ring->adev;
+	struct dma_fence *f = NULL;
+	struct amdgpu_job *job;
+	struct amdgpu_ib *ib;
+	uint64_t addr;
+	int i, r;
+
+	r = amdgpu_job_alloc_with_ib(adev, ib_size_dw * 4,
+				AMDGPU_IB_POOL_DIRECT, &job);
+	if (r)
+		goto err;
+
+	ib = &job->ibs[0];
+	addr = amdgpu_bo_gpu_offset(bo);
+	ib->length_dw = 0;
+
+	ib->ptr[ib->length_dw++] = sizeof(struct amdgpu_vcn_decode_buffer) + 8;
+	ib->ptr[ib->length_dw++] = cpu_to_le32(AMDGPU_VCN_IB_FLAG_DECODE_BUFFER);
+	decode_buffer = (struct amdgpu_vcn_decode_buffer *)&(ib->ptr[ib->length_dw]);
+	ib->length_dw += sizeof(struct amdgpu_vcn_decode_buffer) / 4;
+	memset(decode_buffer, 0, sizeof(struct amdgpu_vcn_decode_buffer));
+
+	decode_buffer->valid_buf_flag |= cpu_to_le32(AMDGPU_VCN_CMD_FLAG_MSG_BUFFER);
+	decode_buffer->msg_buffer_address_hi = cpu_to_le32(addr >> 32);
+	decode_buffer->msg_buffer_address_lo = cpu_to_le32(addr);
+
+	for (i = ib->length_dw; i < ib_size_dw; ++i)
+		ib->ptr[i] = 0x0;
+
+	r = amdgpu_job_submit_direct(job, ring, &f);
+	if (r)
+		goto err_free;
+
+	amdgpu_bo_fence(bo, f, false);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
+
+	if (fence)
+		*fence = dma_fence_get(f);
+	dma_fence_put(f);
+
+	return 0;
+
+err_free:
+	amdgpu_job_free(job);
+
+err:
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
+	return r;
+}
+
+int amdgpu_vcn_dec_sw_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo;
+	long r;
+
+	r = amdgpu_vcn_dec_get_create_msg(ring, 1, &bo);
+	if (r)
+		goto error;
+
+	r = amdgpu_vcn_dec_sw_send_msg(ring, bo, NULL);
+	if (r)
+		goto error;
+	r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, &bo);
 	if (r)
 		goto error;
 
-	r = amdgpu_vcn_dec_get_destroy_msg(ring, 1, &fence);
+	r = amdgpu_vcn_dec_sw_send_msg(ring, bo, &fence);
 	if (r)
 		goto error;