Merge tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux

Merge drm updates from Dave Airlie:
 "This is the main drm pull request for 4.8.

  I'm down with a cold at the moment so hopefully this isn't in too bad
  a state, I finished pulling stuff last week mostly (nouveau fixes just
  went in today), so only this message should be influenced by illness.
  Apologies to anyone who's major feature I missed :-)

  Core:
        Lockless GEM BO freeing
        Non-blocking atomic work
        Documentation changes (rst/sphinx)
        Prep for new fencing changes
        Simple display helpers
        Master/auth changes
        Register/unregister rework
        Loads of trivial patches/fixes.

  New stuff:
        ARM Mali display driver (not the 3D chip)
        sii902x RGB->HDMI bridge

  Panel:
        Support for new panels
        Improved backlight support

  Bridge:
        Convert ADV7511 to bridge driver
        ADV7533 support
        TC358767 (DSI/DPI to eDP) encoder chip support

  i915:
        BXT support enabled by default
        GVT-g infrastructure
        GuC command submission and fixes
        BXT workarounds
        SKL/BKL workarounds
        Demidlayering device registration
        Thundering herd fixes
        Missing pci ids
        Atomic updates

  amdgpu/radeon:
        ATPX improvements for better dGPU power control on PX systems
        New power features for CZ/BR/ST
        Pipelined BO moves and evictions in TTM
        GPU scheduler improvements
        GPU reset improvements
        Overclocking on dGPUs with amdgpu
        Polaris powermanagement enabled

  nouveau:
        GK20A/GM20B volt and clock improvements.
        Initial support for GP100/GP104 GPUs, GP104 will not yet support
        acceleration due to NVIDIA having not released firmware for them as of yet.

  exynos:
        Exynos5433 SoC with IOMMU support.

  vc4:
        Shader validation for branching

  imx-drm:
        Atomic mode setting conversion
        Reworked DMFC FIFO allocation
        External bridge support

  analogix-dp:
        RK3399 eDP support
        Lots of fixes.

  rockchip:
        Lots of small fixes.

  msm:
        DT bindings cleanups
        Shrinker and madvise support
        ASoC HDMI codec support

  tegra:
        Host1x driver cleanups
        SOR reworking for DP support
        Runtime PM support

  omapdrm:
        PLL enhancements
        Header refactoring
        Gamma table support

  arcgpu:
        Simulator support

  virtio-gpu:
        Atomic modesetting fixes.

  rcar-du:
        Misc fixes.

  mediatek:
        MT8173 HDMI support

  sti:
        ASOC HDMI codec support
        Minor fixes

  fsl-dcu:
        Suspend/resume support
        Bridge support

  amdkfd:
        Minor fixes.

  etnaviv:
        Enable GPU clock gating

  hisilicon:
        Vblank and other fixes"

* tag 'drm-for-v4.8' of git://people.freedesktop.org/~airlied/linux: (1575 commits)
  drm/nouveau/gr/nv3x: fix instobj write offsets in gr setup
  drm/nouveau/acpi: fix lockup with PCIe runtime PM
  drm/nouveau/acpi: check for function 0x1B before using it
  drm/nouveau/acpi: return supported DSM functions
  drm/nouveau/acpi: ensure matching ACPI handle and supported functions
  drm/nouveau/fbcon: fix font width not divisible by 8
  drm/amd/powerplay: remove enable_clock_power_gatings_tasks from initialize and resume events
  drm/amd/powerplay: move clockgating to after ungating power in pp for uvd/vce
  drm/amdgpu: add query device id and revision id into system info entry at CGS
  drm/amdgpu: add new definition in bif header
  drm/amd/powerplay: rename smum header guards
  drm/amdgpu: enable UVD context buffer for older HW
  drm/amdgpu: fix default UVD context size
  drm/amdgpu: fix incorrect type of info_id
  drm/amdgpu: make amdgpu_cgs_call_acpi_method as static
  drm/amdgpu: comment out unused defaults_staturn_pro static const structure to fix the build
  drm/amdgpu: enable UVD VM only on polaris
  drm/amdgpu: increase timeout of IB test
  drm/amdgpu: add destroy session when generate VCE destroy msg.
  drm/amd: fix deadlock of job_list_lock V2
  ...

1 files changed, 22 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9bc8f1d99733..0307ff5887c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -216,11 +216,8 @@ int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 	if (ret)
 		goto free_all_kdata;
 
-	if (p->uf_entry.robj) {
-		p->job->uf_bo = amdgpu_bo_ref(p->uf_entry.robj);
-		p->job->uf_offset = uf_offset;
-	}
-
+	if (p->uf_entry.robj)
+		p->job->uf_addr = uf_offset;
 	kfree(chunk_array);
 	return 0;
 
@@ -459,7 +456,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		list_splice(&need_pages, &p->validated);
 	}
 
-	amdgpu_vm_get_pt_bos(&fpriv->vm, &duplicates);
+	amdgpu_vm_get_pt_bos(p->adev, &fpriv->vm, &duplicates);
 
 	p->bytes_moved_threshold = amdgpu_cs_get_threshold_for_moves(p->adev);
 	p->bytes_moved = 0;
@@ -472,6 +469,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	if (r)
 		goto error_validate;
 
+	fpriv->vm.last_eviction_counter =
+		atomic64_read(&p->adev->num_evictions);
+
 	if (p->bo_list) {
 		struct amdgpu_bo *gds = p->bo_list->gds_obj;
 		struct amdgpu_bo *gws = p->bo_list->gws_obj;
@@ -499,6 +499,9 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 		}
 	}
 
+	if (p->uf_entry.robj)
+		p->job->uf_addr += amdgpu_bo_gpu_offset(p->uf_entry.robj);
+
 error_validate:
 	if (r) {
 		amdgpu_vm_move_pt_bos_in_lru(p->adev, &fpriv->vm);
@@ -653,18 +656,21 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 
 	/* Only for UVD/VCE VM emulation */
 	if (ring->funcs->parse_cs) {
+		p->job->vm = NULL;
 		for (i = 0; i < p->job->num_ibs; i++) {
 			r = amdgpu_ring_parse_cs(ring, p, i);
 			if (r)
 				return r;
 		}
-	}
+	} else {
+		p->job->vm_pd_addr = amdgpu_bo_gpu_offset(vm->page_directory);
 
-	r = amdgpu_bo_vm_update_pte(p, vm);
-	if (!r)
-		amdgpu_cs_sync_rings(p);
+		r = amdgpu_bo_vm_update_pte(p, vm);
+		if (r)
+			return r;
+	}
 
-	return r;
+	return amdgpu_cs_sync_rings(p);
 }
 
 static int amdgpu_cs_handle_lockup(struct amdgpu_device *adev, int r)
@@ -761,7 +767,7 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 	}
 
 	/* UVD & VCE fw doesn't support user fences */
-	if (parser->job->uf_bo && (
+	if (parser->job->uf_addr && (
 	    parser->job->ring->type == AMDGPU_RING_TYPE_UVD ||
 	    parser->job->ring->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
@@ -830,17 +836,13 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 {
 	struct amdgpu_ring *ring = p->job->ring;
 	struct amd_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
-	struct fence *fence;
 	struct amdgpu_job *job;
 	int r;
 
 	job = p->job;
 	p->job = NULL;
 
-	r = amd_sched_job_init(&job->base, &ring->sched,
-			       entity, amdgpu_job_timeout_func,
-			       amdgpu_job_free_func,
-			       p->filp, &fence);
+	r = amd_sched_job_init(&job->base, &ring->sched, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		return r;
@@ -848,9 +850,10 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 
 	job->owner = p->filp;
 	job->ctx = entity->fence_context;
-	p->fence = fence_get(fence);
-	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, fence);
+	p->fence = fence_get(&job->base.s_fence->finished);
+	cs->out.handle = amdgpu_ctx_add_fence(p->ctx, ring, p->fence);
 	job->uf_sequence = cs->out.handle;
+	amdgpu_job_free_resources(job);
 
 	trace_amdgpu_cs_ioctl(job);
 	amd_sched_entity_push_job(&job->base);