Merge branch 'drm-next' of git://people.freedesktop.org/~airlied/linux

Pull drm updates from Dave Airlie:
 "I Was Almost Tempted To Capitalise Every Word, but then I decided I
  couldn't read it myself!

  I've also got one pull request for the sti driver outstanding.  It
  relied on a commit in Greg's tree and I didn't find out in time, that
  commit is in your tree now so I might send that along once this is
  merged.

  I also had the accidental misfortune to have access to a Skylake on my
  desk for a few days, and I've had to encourage Intel to try harder,
  which seems to be happening now.

  Here is the main drm-next pull request for 4.4.

  Highlights:

  New driver:
        vc4 driver for the Rasberry Pi VPU.
        (From Eric Anholt at Broadcom.)

  Core:
        Atomic fbdev support
        Atomic helpers for runtime pm
        dp/aux i2c STATUS_UPDATE handling
        struct_mutex usage cleanups.
        Generic of probing support.

  Documentation:
        Kerneldoc for VGA switcheroo code.
        Rename to gpu instead of drm to reflect scope.

  i915:
        Skylake GuC firmware fixes
        HPD A support
        VBT backlight fallbacks
        Fastboot by default for some systems
        FBC work
        BXT/SKL workarounds
        Skylake deeper sleep state fixes

  amdgpu:
        Enable GPU scheduler by default
        New atombios opcodes
        GPUVM debugging options
        Stoney support.
        Fencing cleanups.

  radeon:
        More efficient CS checking

  nouveau:
        gk20a instance memory handling improvements.
        Improved PGOB detection and GK107 support
        Kepler GDDR5 PLL statbility improvement
        G8x/GT2xx reclock improvements
        new userspace API compatiblity fixes.

  virtio-gpu:
        Add 3D support - qemu 2.5 has it merged for it's gtk backend.

  msm:
        Initial msm88896 (snapdragon 8200)

  exynos:
        HDMI cleanups
        Enable mixer driver byt default
        Add DECON-TV support

  vmwgfx:
        Move to using memremap + fixes.

  rcar-du:
        Add support for R8A7793/4 DU

  armada:
        Remove support for non-component mode
        Improved plane handling
        Power savings while in DPMS off.

  tda998x:
        Remove unused slave encoder support
        Use more HDMI helpers
        Fix EDID read handling

  dwhdmi:
        Interlace video mode support for ipu-v3/dw_hdmi
        Hotplug state fixes
        Audio driver integration

  imx:
        More color formats support.

  tegra:
        Minor fixes/improvements"

[ Merge fixup: remove unused variable 'dev' that had all uses removed in
  commit 4e270f088011: "drm/gem: Drop struct_mutex requirement from
  drm_gem_mmap_obj" ]

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (764 commits)
  drm/vmwgfx: Relax irq locking somewhat
  drm/vmwgfx: Properly flush cursor updates and page-flips
  drm/i915/skl: disable display side power well support for now
  drm/i915: Extend DSL readout fix to BDW and SKL.
  drm/i915: Do graphics device reset under forcewake
  drm/i915: Skip fence installation for objects with rotated views (v4)
  vga_switcheroo: Drop client power state VGA_SWITCHEROO_INIT
  drm/amdgpu: group together common fence implementation
  drm/amdgpu: remove AMDGPU_FENCE_OWNER_MOVE
  drm/amdgpu: remove now unused fence functions
  drm/amdgpu: fix fence fallback check
  drm/amdgpu: fix stoping the scheduler timeout
  drm/amdgpu: cleanup on error in amdgpu_cs_ioctl()
  drm/i915: Fix locking around GuC firmware load
  drm/amdgpu: update Fiji's Golden setting
  drm/amdgpu: update Fiji's rev id
  drm/amdgpu: extract common code in vi_common_early_init
  drm/amd/scheduler: don't oops on failure to load
  drm/amdgpu: don't oops on failure to load (v2)
  drm/amdgpu: don't VT switch on suspend
  ...

1 files changed, 31 insertions, 17 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index fd16652aa277..dfc4d02c7a38 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -104,10 +104,11 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
 		}
 		break;
 	case AMDGPU_HW_IP_DMA:
-		if (ring < 2) {
-			*out_ring = &adev->sdma[ring].ring;
+		if (ring < adev->sdma.num_instances) {
+			*out_ring = &adev->sdma.instance[ring].ring;
 		} else {
-			DRM_ERROR("only two SDMA rings are supported\n");
+			DRM_ERROR("only %d SDMA rings are supported\n",
+				  adev->sdma.num_instances);
 			return -EINVAL;
 		}
 		break;
@@ -567,9 +568,24 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p,
 			if (r)
 				return r;
 		}
+
+	}
+
+	r = amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync);
+
+	if (amdgpu_vm_debug && p->bo_list) {
+		/* Invalidate all BOs to test for userspace bugs */
+		for (i = 0; i < p->bo_list->num_entries; i++) {
+			/* ignore duplicates */
+			bo = p->bo_list->array[i].robj;
+			if (!bo)
+				continue;
+
+			amdgpu_vm_bo_invalidate(adev, bo);
+		}
 	}
 
-	return amdgpu_vm_clear_invalids(adev, vm, &p->ibs[0].sync);
+	return r;
 }
 
 static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
@@ -593,7 +609,6 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 		}
 	}
 
-	mutex_lock(&vm->mutex);
 	r = amdgpu_bo_vm_update_pte(parser, vm);
 	if (r) {
 		goto out;
@@ -604,7 +619,6 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 				       parser->filp);
 
 out:
-	mutex_unlock(&vm->mutex);
 	return r;
 }
 
@@ -812,15 +826,14 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
 	union drm_amdgpu_cs *cs = data;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_cs_parser *parser;
 	bool reserved_buffers = false;
 	int i, r;
 
-	down_read(&adev->exclusive_lock);
-	if (!adev->accel_working) {
-		up_read(&adev->exclusive_lock);
+	if (!adev->accel_working)
 		return -EBUSY;
-	}
 
 	parser = amdgpu_cs_parser_create(adev, filp, NULL, NULL, 0);
 	if (!parser)
@@ -828,12 +841,11 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	r = amdgpu_cs_parser_init(parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
-		kfree(parser);
-		up_read(&adev->exclusive_lock);
+		amdgpu_cs_parser_fini(parser, r, false);
 		r = amdgpu_cs_handle_lockup(adev, r);
 		return r;
 	}
-
+	mutex_lock(&vm->mutex);
 	r = amdgpu_cs_parser_relocs(parser);
 	if (r == -ENOMEM)
 		DRM_ERROR("Not enough memory for command submission!\n");
@@ -864,8 +876,10 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		struct amdgpu_job *job;
 		struct amdgpu_ring * ring =  parser->ibs->ring;
 		job = kzalloc(sizeof(struct amdgpu_job), GFP_KERNEL);
-		if (!job)
-			return -ENOMEM;
+		if (!job) {
+			r = -ENOMEM;
+			goto out;
+		}
 		job->base.sched = &ring->sched;
 		job->base.s_entity = &parser->ctx->rings[ring->idx].entity;
 		job->adev = parser->adev;
@@ -900,14 +914,14 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 		mutex_unlock(&job->job_lock);
 		amdgpu_cs_parser_fini_late(parser);
-		up_read(&adev->exclusive_lock);
+		mutex_unlock(&vm->mutex);
 		return 0;
 	}
 
 	cs->out.handle = parser->ibs[parser->num_ibs - 1].sequence;
 out:
 	amdgpu_cs_parser_fini(parser, r, reserved_buffers);
-	up_read(&adev->exclusive_lock);
+	mutex_unlock(&vm->mutex);
 	r = amdgpu_cs_handle_lockup(adev, r);
 	return r;
 }