Merge tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "Cannonlake and Vega12 support are probably the two major things. This
  pull lacks nouveau, Ben had some unforseen leave and a few other
  blockers so we'll see how things look or maybe leave it for this merge
  window.

  core:
   - Device links to handle sound/gpu pm dependency
   - Color encoding/range properties
   - Plane clipping into plane check helper
   - Backlight helpers
   - DP TP4 + HBR3 helper support

  amdgpu:
   - Vega12 support
   - Enable DC by default on all supported GPUs
   - Powerplay restructuring and cleanup
   - DC bandwidth calc updates
   - DC backlight on pre-DCE11
   - TTM backing store dropping support
   - SR-IOV fixes
   - Adding "wattman" like functionality
   - DC crc support
   - Improved DC dual-link handling

  amdkfd:
   - GPUVM support for dGPU
   - KFD events for dGPU
   - Enable PCIe atomics for dGPUs
   - HSA process eviction support
   - Live-lock fixes for process eviction
   - VM page table allocation fix for large-bar systems

  panel:
   - Raydium RM68200
   - AUO G104SN02 V2
   - KEO TX31D200VM0BAA
   - ARM Versatile panels

  i915:
   - Cannonlake support enabled
   - AUX-F port support added
   - Icelake base enabling until internal milestone of forcewake support
   - Query uAPI interface (used for GPU topology information currently)
   - Compressed framebuffer support for sprites
   - kmem cache shrinking when GPU is idle
   - Avoid boosting GPU when waited item is being processed already
   - Avoid retraining LSPCON link unnecessarily
   - Decrease request signaling latency
   - Deprecation of I915_SET_COLORKEY_NONE
   - Kerneldoc and compiler warning cleanup for upcoming CI enforcements
   - Full range ycbcr toggling
   - HDCP support

  i915/gvt:
   - Big refactor for shadow ppgtt
   - KBL context save/restore via LRI cmd (Weinan)
   - Properly unmap dma for guest page (Changbin)

  vmwgfx:
   - Lots of various improvements

  etnaviv:
   - Use the drm gpu scheduler
   - prep work for GC7000L support

  vc4:
   - fix alpha blending
   - Expose perf counters to userspace

  pl111:
   - Bandwidth checking/limiting
   - Versatile panel support

  sun4i:
   - A83T HDMI support
   - A80 support
   - YUV plane support
   - H3/H5 HDMI support

  omapdrm:
   - HPD support for DVI connector
   - remove lots of static variables

  msm:
   - DSI updates from 10nm / SDM845
   - fix for race condition with a3xx/a4xx fence completion irq
   - some refactoring/prep work for eventual a6xx support (ie. when we
     have a userspace)
   - a5xx debugfs enhancements
   - some mdp5 fixes/cleanups to prepare for eventually merging
     writeback
   - support (ie. when we have a userspace)

  tegra:
   - mmap() fixes for fbdev devices
   - Overlay plane for hw cursor fix
   - dma-buf cache maintenance support

  mali-dp:
   - YUV->RGB conversion support

  rockchip:
   - rk3399/chromebook fixes and improvements

  rcar-du:
   - LVDS support move to drm bridge
   - DT bindings for R8A77995
   - Driver/DT support for R8A77970

  tilcdc:
   - DRM panel support"

* tag 'drm-for-v4.17' of git://people.freedesktop.org/~airlied/linux: (1646 commits)
  drm/i915: Fix hibernation with ACPI S0 target state
  drm/i915/execlists: Use a locked clear_bit() for synchronisation with interrupt
  drm/i915: Specify which engines to reset following semaphore/event lockups
  drm/i915/dp: Write to SET_POWER dpcd to enable MST hub.
  drm/amdkfd: Use ordered workqueue to restore processes
  drm/amdgpu: Fix acquiring VM on large-BAR systems
  drm/amd/pp: clean header file hwmgr.h
  drm/amd/pp: use mlck_table.count for array loop index limit
  drm: Fix uabi regression by allowing garbage mode->type from userspace
  drm/amdgpu: Add an ATPX quirk for hybrid laptop
  drm/amdgpu: fix spelling mistake: "asssert" -> "assert"
  drm/amd/pp: Add new asic support in pp_psm.c
  drm/amd/pp: Clean up powerplay code on Vega12
  drm/amd/pp: Add smu irq handlers for legacy asics
  drm/amd/pp: Fix set wrong temperature range on smu7
  drm/amdgpu: Don't change preferred domian when fallback GTT v5
  drm/vmwgfx: Bump version patchlevel and date
  drm/vmwgfx: use monotonic event timestamps
  drm/vmwgfx: Unpin the screen object backup buffer when not used
  drm/vmwgfx: Stricter count of legacy surface device resources
  ...

1 files changed, 135 insertions, 29 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index ae9c106979d7..4b584cb75bf4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -26,9 +26,12 @@
 #include <drm/drmP.h>
 
 #include "amdgpu.h"
+#include "amdgpu_display.h"
 #include <drm/amdgpu_drm.h>
 #include <linux/dma-buf.h>
 
+static const struct dma_buf_ops amdgpu_dmabuf_ops;
+
 struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -102,59 +105,95 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	int ret;
 
 	ww_mutex_lock(&resv->lock, NULL);
-	ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE, false,
-			       AMDGPU_GEM_DOMAIN_GTT, 0, sg, resv, 0, &bo);
-	ww_mutex_unlock(&resv->lock);
+	ret = amdgpu_bo_create(adev, attach->dmabuf->size, PAGE_SIZE,
+			       AMDGPU_GEM_DOMAIN_CPU, 0, ttm_bo_type_sg,
+			       resv, &bo);
 	if (ret)
-		return ERR_PTR(ret);
+		goto error;
 
-	bo->prime_shared_count = 1;
+	bo->tbo.sg = sg;
+	bo->tbo.ttm->sg = sg;
+	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
+	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
+	if (attach->dmabuf->ops != &amdgpu_dmabuf_ops)
+		bo->prime_shared_count = 1;
+
+	ww_mutex_unlock(&resv->lock);
 	return &bo->gem_base;
+
+error:
+	ww_mutex_unlock(&resv->lock);
+	return ERR_PTR(ret);
 }
 
-int amdgpu_gem_prime_pin(struct drm_gem_object *obj)
+static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
+				 struct device *target_dev,
+				 struct dma_buf_attachment *attach)
 {
+	struct drm_gem_object *obj = dma_buf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	long ret = 0;
-
-	ret = amdgpu_bo_reserve(bo, false);
-	if (unlikely(ret != 0))
-		return ret;
-
-	/*
-	 * Wait for all shared fences to complete before we switch to future
-	 * use of exclusive fence on this prime shared bo.
-	 */
-	ret = reservation_object_wait_timeout_rcu(bo->tbo.resv, true, false,
-						  MAX_SCHEDULE_TIMEOUT);
-	if (unlikely(ret < 0)) {
-		DRM_DEBUG_PRIME("Fence wait failed: %li\n", ret);
-		amdgpu_bo_unreserve(bo);
-		return ret;
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	long r;
+
+	r = drm_gem_map_attach(dma_buf, target_dev, attach);
+	if (r)
+		return r;
+
+	r = amdgpu_bo_reserve(bo, false);
+	if (unlikely(r != 0))
+		goto error_detach;
+
+
+	if (attach->dev->driver != adev->dev->driver) {
+		/*
+		 * Wait for all shared fences to complete before we switch to future
+		 * use of exclusive fence on this prime shared bo.
+		 */
+		r = reservation_object_wait_timeout_rcu(bo->tbo.resv,
+							true, false,
+							MAX_SCHEDULE_TIMEOUT);
+		if (unlikely(r < 0)) {
+			DRM_DEBUG_PRIME("Fence wait failed: %li\n", r);
+			goto error_unreserve;
+		}
 	}
 
 	/* pin buffer into GTT */
-	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
-	if (likely(ret == 0))
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	if (r)
+		goto error_unreserve;
+
+	if (attach->dev->driver != adev->dev->driver)
 		bo->prime_shared_count++;
 
+error_unreserve:
 	amdgpu_bo_unreserve(bo);
-	return ret;
+
+error_detach:
+	if (r)
+		drm_gem_map_detach(dma_buf, attach);
+	return r;
 }
 
-void amdgpu_gem_prime_unpin(struct drm_gem_object *obj)
+static void amdgpu_gem_map_detach(struct dma_buf *dma_buf,
+				  struct dma_buf_attachment *attach)
 {
+	struct drm_gem_object *obj = dma_buf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	int ret = 0;
 
 	ret = amdgpu_bo_reserve(bo, true);
 	if (unlikely(ret != 0))
-		return;
+		goto error;
 
 	amdgpu_bo_unpin(bo);
-	if (bo->prime_shared_count)
+	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
 		bo->prime_shared_count--;
 	amdgpu_bo_unreserve(bo);
+
+error:
+	drm_gem_map_detach(dma_buf, attach);
 }
 
 struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
@@ -164,6 +203,50 @@ struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
 	return bo->tbo.resv;
 }
 
+static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
+				       enum dma_data_direction direction)
+{
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(dma_buf->priv);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct ttm_operation_ctx ctx = { true, false };
+	u32 domain = amdgpu_display_framebuffer_domains(adev);
+	int ret;
+	bool reads = (direction == DMA_BIDIRECTIONAL ||
+		      direction == DMA_FROM_DEVICE);
+
+	if (!reads || !(domain & AMDGPU_GEM_DOMAIN_GTT))
+		return 0;
+
+	/* move to gtt */
+	ret = amdgpu_bo_reserve(bo, false);
+	if (unlikely(ret != 0))
+		return ret;
+
+	if (!bo->pin_count && (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
+		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+	}
+
+	amdgpu_bo_unreserve(bo);
+	return ret;
+}
+
+static const struct dma_buf_ops amdgpu_dmabuf_ops = {
+	.attach = amdgpu_gem_map_attach,
+	.detach = amdgpu_gem_map_detach,
+	.map_dma_buf = drm_gem_map_dma_buf,
+	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.release = drm_gem_dmabuf_release,
+	.begin_cpu_access = amdgpu_gem_begin_cpu_access,
+	.map = drm_gem_dmabuf_kmap,
+	.map_atomic = drm_gem_dmabuf_kmap_atomic,
+	.unmap = drm_gem_dmabuf_kunmap,
+	.unmap_atomic = drm_gem_dmabuf_kunmap_atomic,
+	.mmap = drm_gem_dmabuf_mmap,
+	.vmap = drm_gem_dmabuf_vmap,
+	.vunmap = drm_gem_dmabuf_vunmap,
+};
+
 struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 					struct drm_gem_object *gobj,
 					int flags)
@@ -176,7 +259,30 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 		return ERR_PTR(-EPERM);
 
 	buf = drm_gem_prime_export(dev, gobj, flags);
-	if (!IS_ERR(buf))
+	if (!IS_ERR(buf)) {
 		buf->file->f_mapping = dev->anon_inode->i_mapping;
+		buf->ops = &amdgpu_dmabuf_ops;
+	}
+
 	return buf;
 }
+
+struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
+					    struct dma_buf *dma_buf)
+{
+	struct drm_gem_object *obj;
+
+	if (dma_buf->ops == &amdgpu_dmabuf_ops) {
+		obj = dma_buf->priv;
+		if (obj->dev == dev) {
+			/*
+			 * Importing dmabuf exported from out own gem increases
+			 * refcount on gem itself instead of f_count of dmabuf.
+			 */
+			drm_gem_object_get(obj);
+			return obj;
+		}
+	}
+
+	return drm_gem_prime_import(dev, dma_buf);
+}