Merge tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Intel have enabled DG2 on certain SKUs for laptops, AMD has started
  some new GPU support, msm has user allocated VA controls

  dma-buf:
   - add dma_resv_replace_fences
   - add dma_resv_get_singleton
   - make dma_excl_fence private

  core:
   - EDID parser refactorings
   - switch drivers to drm_mode_copy/duplicate
   - DRM managed mutex initialization

  display-helper:
   - put HDMI, SCDC, HDCP, DSC and DP into new module

  gem:
   - rework fence handling

  ttm:
   - rework bulk move handling
   - add common debugfs for resource managers
   - convert to kvcalloc

  format helpers:
   - support monochrome formats
   - RGB888, RGB565 to XRGB8888 conversions

  fbdev:
   - cfb/sys_imageblit fixes
   - pagelist corruption fix
   - create offb platform device
   - deferred io improvements

  sysfb:
   - Kconfig rework
   - support for VESA mode selection

  bridge:
   - conversions to devm_drm_of_get_bridge
   - conversions to panel_bridge
   - analogix_dp - autosuspend support
   - it66121 - audio support
   - tc358767 - DSI to DPI support
   - icn6211 - PLL/I2C fixes, DT property
   - adv7611 - enable DRM_BRIDGE_OP_HPD
   - anx7625 - fill ELD if no monitor
   - dw_hdmi - add audio support
   - lontium LT9211 support, i.MXMP LDB
   - it6505: Kconfig fix, DPCD set power fix
   - adv7511 - CEC support for ADV7535

  panel:
   - ltk035c5444t, B133UAN01, NV3052C panel support
   - DataImage FG040346DSSWBG04 support
   - st7735r - DT bindings fix
   - ssd130x - fixes

  i915:
   - DG2 laptop PCI-IDs ("motherboard down")
   - Initial RPL-P PCI IDs
   - compute engine ABI
   - DG2 Tile4 support
   - DG2 CCS clear color compression support
   - DG2 render/media compression formats support
   - ATS-M platform info
   - RPL-S PCI IDs added
   - Bump ADL-P DMC version to v2.16
   - Support static DRRS
   - Support multiple eDP/LVDS native mode refresh rates
   - DP HDR support for HSW+
   - Lots of display refactoring + fixes
   - GuC hwconfig support and query
   - sysfs support for multi-tile
   - fdinfo per-client gpu utilisation
   - add geometry subslices query
   - fix prime mmap with LMEM
   - fix vm open count and remove vma refcounts
   - contiguous allocation fixes
   - steered register write support
   - small PCI BAR enablement
   - GuC error capture support
   - sunset igpu legacy mmap support for newer devices
   - GuC version 70.1.1 support

  amdgpu:
   - Initial SoC21 support
   - SMU 13.x enablement
   - SMU 13.0.4 support
   - ttm_eu cleanups
   - USB-C, GPUVM updates
   - TMZ fixes for RV
   - RAS support for VCN
   - PM sysfs code cleanup
   - DC FP rework
   - extend CG/PG flags to 64-bit
   - SI dpm lockdep fix
   - runtime PM fixes

  amdkfd:
   - RAS/SVM fixes
   - TLB flush fixes
   - CRIU GWS support
   - ignore bogus MEC signals more efficiently

  msm:
   - Fourcc modifier for tiled but not compressed layouts
   - Support for userspace allocated IOVA (GPU virtual address)
   - DPU: DSC (Display Stream Compression) support
   - DP: eDP support
   - DP: conversion to use drm_bridge and drm_bridge_connector
   - Merge DPU1 and MDP5 MDSS driver
   - DPU: writeback support

  nouveau:
   - make some structures static
   - make some variables static
   - switch to drm_gem_plane_helper_prepare_fb

  radeon:
   - misc fixes/cleanups

  mxsfb:
   - rework crtc mode setting
   - LCDIF CRC support

  etnaviv:
   - fencing improvements
   - fix address space collisions
   - cleanup MMU reference handling

  gma500:
   - GEM/GTT improvements
   - connector handling fixes

  komeda:
   - switch to plane reset helper

  mediatek:
   - MIPI DSI improvements

  omapdrm:
   - GEM improvements

  qxl:
   - aarch64 support

  vc4:
   - add a CL submission tracepoint
   - HDMI YUV support
   - HDMI/clock improvements
   - drop is_hdmi caching

  virtio:
   - remove restriction of non-zero blob types

  vmwgfx:
   - support for cursormob and cursorbypass 4
   - fence improvements

  tidss:
   - reset DISPC on startup

  solomon:
   - SPI support
   - DT improvements

  sun4i:
   - allwinner D1 support
   - drop is_hdmi caching

  imx:
   - use swap() instead of open-coding
   - use devm_platform_ioremap_resource
   - remove redunant initializations

  ast:
   - Displayport support

  rockchip:
   - Refactor IOMMU initialisation
   - make some structures static
   - replace drm_detect_hdmi_monitor with drm_display_info.is_hdmi
   - support swapped YUV formats,
   - clock improvements
   - rk3568 support
   - VOP2 support

  mediatek:
   - MT8186 support

  tegra:
   - debugabillity improvements"

* tag 'drm-next-2022-05-25' of git://anongit.freedesktop.org/drm/drm: (1740 commits)
  drm/i915/dsi: fix VBT send packet port selection for ICL+
  drm/i915/uc: Fix undefined behavior due to shift overflowing the constant
  drm/i915/reg: fix undefined behavior due to shift overflowing the constant
  drm/i915/gt: Fix use of static in macro mismatch
  drm/i915/audio: fix audio code enable/disable pipe logging
  drm/i915: Fix CFI violation with show_dynamic_id()
  drm/i915: Fix 'mixing different enum types' warnings in intel_display_power.c
  drm/i915/gt: Fix build error without CONFIG_PM
  drm/msm/dpu: handle pm_runtime_get_sync() errors in bind path
  drm/msm/dpu: add DRM_MODE_ROTATE_180 back to supported rotations
  drm/msm: don't free the IRQ if it was not requested
  drm/msm/dpu: limit writeback modes according to max_linewidth
  drm/amd: Don't reset dGPUs if the system is going to s2idle
  drm/amdgpu: Unmap legacy queue when MES is enabled
  drm: msm: fix possible memory leak in mdp5_crtc_cursor_set()
  drm/msm: Fix fb plane offset calculation
  drm/msm/a6xx: Fix refcount leak in a6xx_gpu_init
  drm/msm/dsi: don't powerup at modeset time for parade-ps8640
  drm/rockchip: Change register space names in vop2
  dt-bindings: display: rockchip: make reg-names mandatory for VOP2
  ...

1 files changed, 152 insertions, 41 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 7f33ae87cb41e..13db99d653bd3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -149,6 +149,16 @@ void amdgpu_ring_undo(struct amdgpu_ring *ring)
 		ring->funcs->end_use(ring);
 }
 
+#define amdgpu_ring_get_gpu_addr(ring, offset)				\
+	(ring->is_mes_queue ?						\
+	 (ring->mes_ctx->meta_data_gpu_addr + offset) :			\
+	 (ring->adev->wb.gpu_addr + offset * 4))
+
+#define amdgpu_ring_get_cpu_addr(ring, offset)				\
+	(ring->is_mes_queue ?						\
+	 (void *)((uint8_t *)(ring->mes_ctx->meta_data_ptr) + offset) : \
+	 (&ring->adev->wb.wb[offset]))
+
 /**
  * amdgpu_ring_init - init driver ring struct.
  *
@@ -189,51 +199,88 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 			return -EINVAL;
 
 		ring->adev = adev;
-		ring->idx = adev->num_rings++;
-		adev->rings[ring->idx] = ring;
 		ring->num_hw_submission = sched_hw_submission;
 		ring->sched_score = sched_score;
 		ring->vmid_wait = dma_fence_get_stub();
+
+		if (!ring->is_mes_queue) {
+			ring->idx = adev->num_rings++;
+			adev->rings[ring->idx] = ring;
+		}
+
 		r = amdgpu_fence_driver_init_ring(ring);
 		if (r)
 			return r;
 	}
 
-	r = amdgpu_device_wb_get(adev, &ring->rptr_offs);
-	if (r) {
-		dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
-		return r;
-	}
+	if (ring->is_mes_queue) {
+		ring->rptr_offs = amdgpu_mes_ctx_get_offs(ring,
+				AMDGPU_MES_CTX_RPTR_OFFS);
+		ring->wptr_offs = amdgpu_mes_ctx_get_offs(ring,
+				AMDGPU_MES_CTX_WPTR_OFFS);
+		ring->fence_offs = amdgpu_mes_ctx_get_offs(ring,
+				AMDGPU_MES_CTX_FENCE_OFFS);
+		ring->trail_fence_offs = amdgpu_mes_ctx_get_offs(ring,
+				AMDGPU_MES_CTX_TRAIL_FENCE_OFFS);
+		ring->cond_exe_offs = amdgpu_mes_ctx_get_offs(ring,
+				AMDGPU_MES_CTX_COND_EXE_OFFS);
+	} else {
+		r = amdgpu_device_wb_get(adev, &ring->rptr_offs);
+		if (r) {
+			dev_err(adev->dev, "(%d) ring rptr_offs wb alloc failed\n", r);
+			return r;
+		}
 
-	r = amdgpu_device_wb_get(adev, &ring->wptr_offs);
-	if (r) {
-		dev_err(adev->dev, "(%d) ring wptr_offs wb alloc failed\n", r);
-		return r;
-	}
+		r = amdgpu_device_wb_get(adev, &ring->wptr_offs);
+		if (r) {
+			dev_err(adev->dev, "(%d) ring wptr_offs wb alloc failed\n", r);
+			return r;
+		}
 
-	r = amdgpu_device_wb_get(adev, &ring->fence_offs);
-	if (r) {
-		dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
-		return r;
-	}
+		r = amdgpu_device_wb_get(adev, &ring->fence_offs);
+		if (r) {
+			dev_err(adev->dev, "(%d) ring fence_offs wb alloc failed\n", r);
+			return r;
+		}
 
-	r = amdgpu_device_wb_get(adev, &ring->trail_fence_offs);
-	if (r) {
-		dev_err(adev->dev,
-			"(%d) ring trail_fence_offs wb alloc failed\n", r);
-		return r;
+		r = amdgpu_device_wb_get(adev, &ring->trail_fence_offs);
+		if (r) {
+			dev_err(adev->dev, "(%d) ring trail_fence_offs wb alloc failed\n", r);
+			return r;
+		}
+
+		r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
+		if (r) {
+			dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
+			return r;
+		}
 	}
+
+	ring->fence_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->fence_offs);
+	ring->fence_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->fence_offs);
+
+	ring->rptr_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->rptr_offs);
+	ring->rptr_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->rptr_offs);
+
+	ring->wptr_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->wptr_offs);
+	ring->wptr_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->wptr_offs);
+
 	ring->trail_fence_gpu_addr =
-		adev->wb.gpu_addr + (ring->trail_fence_offs * 4);
-	ring->trail_fence_cpu_addr = &adev->wb.wb[ring->trail_fence_offs];
+		amdgpu_ring_get_gpu_addr(ring, ring->trail_fence_offs);
+	ring->trail_fence_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->trail_fence_offs);
+
+	ring->cond_exe_gpu_addr =
+		amdgpu_ring_get_gpu_addr(ring, ring->cond_exe_offs);
+	ring->cond_exe_cpu_addr =
+		amdgpu_ring_get_cpu_addr(ring, ring->cond_exe_offs);
 
-	r = amdgpu_device_wb_get(adev, &ring->cond_exe_offs);
-	if (r) {
-		dev_err(adev->dev, "(%d) ring cond_exec_polling wb alloc failed\n", r);
-		return r;
-	}
-	ring->cond_exe_gpu_addr = adev->wb.gpu_addr + (ring->cond_exe_offs * 4);
-	ring->cond_exe_cpu_addr = &adev->wb.wb[ring->cond_exe_offs];
 	/* always set cond_exec_polling to CONTINUE */
 	*ring->cond_exe_cpu_addr = 1;
 
@@ -248,8 +295,20 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 	ring->buf_mask = (ring->ring_size / 4) - 1;
 	ring->ptr_mask = ring->funcs->support_64bit_ptrs ?
 		0xffffffffffffffff : ring->buf_mask;
+
 	/* Allocate ring buffer */
-	if (ring->ring_obj == NULL) {
+	if (ring->is_mes_queue) {
+		int offset = 0;
+
+		BUG_ON(ring->ring_size > PAGE_SIZE*4);
+
+		offset = amdgpu_mes_ctx_get_offs(ring,
+					 AMDGPU_MES_CTX_RING_OFFS);
+		ring->gpu_addr = amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset);
+		ring->ring = amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset);
+		amdgpu_ring_clear_ring(ring);
+
+	} else if (ring->ring_obj == NULL) {
 		r = amdgpu_bo_create_kernel(adev, ring->ring_size + ring->funcs->extra_dw, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_GTT,
 					    &ring->ring_obj,
@@ -286,26 +345,30 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring)
 {
 
 	/* Not to finish a ring which is not initialized */
-	if (!(ring->adev) || !(ring->adev->rings[ring->idx]))
+	if (!(ring->adev) ||
+	    (!ring->is_mes_queue && !(ring->adev->rings[ring->idx])))
 		return;
 
 	ring->sched.ready = false;
 
-	amdgpu_device_wb_free(ring->adev, ring->rptr_offs);
-	amdgpu_device_wb_free(ring->adev, ring->wptr_offs);
+	if (!ring->is_mes_queue) {
+		amdgpu_device_wb_free(ring->adev, ring->rptr_offs);
+		amdgpu_device_wb_free(ring->adev, ring->wptr_offs);
 
-	amdgpu_device_wb_free(ring->adev, ring->cond_exe_offs);
-	amdgpu_device_wb_free(ring->adev, ring->fence_offs);
+		amdgpu_device_wb_free(ring->adev, ring->cond_exe_offs);
+		amdgpu_device_wb_free(ring->adev, ring->fence_offs);
 
-	amdgpu_bo_free_kernel(&ring->ring_obj,
-			      &ring->gpu_addr,
-			      (void **)&ring->ring);
+		amdgpu_bo_free_kernel(&ring->ring_obj,
+				      &ring->gpu_addr,
+				      (void **)&ring->ring);
+	}
 
 	dma_fence_put(ring->vmid_wait);
 	ring->vmid_wait = NULL;
 	ring->me = 0;
 
-	ring->adev->rings[ring->idx] = NULL;
+	if (!ring->is_mes_queue)
+		ring->adev->rings[ring->idx] = NULL;
 }
 
 /**
@@ -458,3 +521,51 @@ int amdgpu_ring_test_helper(struct amdgpu_ring *ring)
 	ring->sched.ready = !r;
 	return r;
 }
+
+static void amdgpu_ring_to_mqd_prop(struct amdgpu_ring *ring,
+				    struct amdgpu_mqd_prop *prop)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	memset(prop, 0, sizeof(*prop));
+
+	prop->mqd_gpu_addr = ring->mqd_gpu_addr;
+	prop->hqd_base_gpu_addr = ring->gpu_addr;
+	prop->rptr_gpu_addr = ring->rptr_gpu_addr;
+	prop->wptr_gpu_addr = ring->wptr_gpu_addr;
+	prop->queue_size = ring->ring_size;
+	prop->eop_gpu_addr = ring->eop_gpu_addr;
+	prop->use_doorbell = ring->use_doorbell;
+	prop->doorbell_index = ring->doorbell_index;
+
+	/* map_queues packet doesn't need activate the queue,
+	 * so only kiq need set this field.
+	 */
+	prop->hqd_active = ring->funcs->type == AMDGPU_RING_TYPE_KIQ;
+
+	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
+		if (amdgpu_gfx_is_high_priority_compute_queue(adev, ring)) {
+			prop->hqd_pipe_priority = AMDGPU_GFX_PIPE_PRIO_HIGH;
+			prop->hqd_queue_priority =
+				AMDGPU_GFX_QUEUE_PRIORITY_MAXIMUM;
+		}
+	}
+}
+
+int amdgpu_ring_init_mqd(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_mqd *mqd_mgr;
+	struct amdgpu_mqd_prop prop;
+
+	amdgpu_ring_to_mqd_prop(ring, &prop);
+
+	ring->wptr = 0;
+
+	if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+		mqd_mgr = &adev->mqds[AMDGPU_HW_IP_COMPUTE];
+	else
+		mqd_mgr = &adev->mqds[ring->funcs->type];
+
+	return mqd_mgr->init_mqd(adev, ring->mqd_ptr, &prop);
+}