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

Pull drm updates from Dave Airlie:
 "Here's the main drm pull request for 4.7, it's been a busy one, and
  I've been a bit more distracted in real life this merge window.  Lots
  more ARM drivers, not sure if it'll ever end.  I think I've at least
  one more coming the next merge window.

  But changes are all over the place, support for AMD Polaris GPUs is in
  here, some missing GM108 support for nouveau (found in some Lenovos),
  a bunch of MST and skylake fixes.

  I've also noticed a few fixes from Arnd in my inbox, that I'll try and
  get in asap, but I didn't think they should hold this up.

  New drivers:
   - Hisilicon kirin display driver
   - Mediatek MT8173 display driver
   - ARC PGU - bitstreamer on Synopsys ARC SDP boards
   - Allwinner A13 initial RGB output driver
   - Analogix driver for DisplayPort IP found in exynos and rockchip

  DRM Core:
   - UAPI headers fixes and C++ safety
   - DRM connector reference counting
   - DisplayID mode parsing for Dell 5K monitors
   - Removal of struct_mutex from drivers
   - Connector registration cleanups
   - MST robustness fixes
   - MAINTAINERS updates
   - Lockless GEM object freeing
   - Generic fbdev deferred IO support

  panel:
   - Support for a bunch of new panels

  i915:
   - VBT refactoring
   - PLL computation cleanups
   - DSI support for BXT
   - Color manager support
   - More atomic patches
   - GEM improvements
   - GuC fw loading fixes
   - DP detection fixes
   - SKL GPU hang fixes
   - Lots of BXT fixes

  radeon/amdgpu:
   - Initial Polaris support
   - GPUVM/Scheduler/Clock/Power improvements
   - ASYNC pageflip support
   - New mesa feature support

  nouveau:
   - GM108 support
   - Power sensor support improvements
   - GR init + ucode fixes.
   - Use GPU provided topology information

  vmwgfx:
   - Add host messaging support

  gma500:
   - Some cleanups and fixes

  atmel:
   - Bridge support
   - Async atomic commit support

  fsl-dcu:
   - Timing controller for LCD support
   - Pixel clock polarity support

  rcar-du:
   - Misc fixes

  exynos:
   - Pipeline clock support
   - Exynoss4533 SoC support
   - HW trigger mode support
   - export HDMI_PHY clock
   - DECON5433 fixes
   - Use generic prime functions
   - use DMA mapping APIs

  rockchip:
   - Lots of little fixes

  vc4:
   - Render node support
   - Gamma ramp support
   - DPI output support

  msm:
   - Mostly cleanups and fixes
   - Conversion to generic struct fence

  etnaviv:
   - Fix for prime buffer handling
   - Allow hangcheck to be coalesced with other wakeups

  tegra:
   - Gamme table size fix"

* 'drm-next' of git://people.freedesktop.org/~airlied/linux: (1050 commits)
  drm/edid: add displayid detailed 1 timings to the modelist. (v1.1)
  drm/edid: move displayid validation to it's own function.
  drm/displayid: Iterate over all DisplayID blocks
  drm/edid: move displayid tiled block parsing into separate function.
  drm: Nuke ->vblank_disable_allowed
  drm/vmwgfx: Report vmwgfx version to vmware.log
  drm/vmwgfx: Add VMWare host messaging capability
  drm/vmwgfx: Kill some lockdep warnings
  drm/nouveau/gr/gf100-: fix race condition in fecs/gpccs ucode
  drm/nouveau/core: recognise GM108 chipsets
  drm/nouveau/gr/gm107-: fix touching non-existent ppcs in attrib cb setup
  drm/nouveau/gr/gk104-: share implementation of ppc exception init
  drm/nouveau/gr/gk104-: move rop_active_fbps init to nonctx
  drm/nouveau/bios/pll: check BIT table version before trying to parse it
  drm/nouveau/bios/pll: prevent oops when limits table can't be parsed
  drm/nouveau/volt/gk104: round up in gk104_volt_set
  drm/nouveau/fb/gm200: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gk20a,gm20b: setup mmu debug buffer registers at init()
  drm/nouveau/fb/gf100-: allocate mmu debug buffers
  drm/nouveau/fb: allow chipset-specific actions for oneinit()
  ...

1 files changed, 56 insertions, 39 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 8443cea6821ad..34e35423b78e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -74,9 +74,6 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
 	}
 
-	ib->vm = vm;
-	ib->vm_id = 0;
-
 	return 0;
 }
 
@@ -89,7 +86,8 @@ int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  *
  * Free an IB (all asics).
  */
-void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, struct fence *f)
+void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib,
+		    struct fence *f)
 {
 	amdgpu_sa_bo_free(adev, &ib->sa_bo, f);
 }
@@ -117,28 +115,37 @@ void amdgpu_ib_free(struct amdgpu_device *adev, struct amdgpu_ib *ib, struct fen
  */
 int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		       struct amdgpu_ib *ibs, struct fence *last_vm_update,
-		       struct fence **f)
+		       struct amdgpu_job *job, struct fence **f)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib *ib = &ibs[0];
-	struct amdgpu_ctx *ctx, *old_ctx;
+	bool skip_preamble, need_ctx_switch;
+	unsigned patch_offset = ~0;
 	struct amdgpu_vm *vm;
 	struct fence *hwf;
+	uint64_t ctx;
+
 	unsigned i;
 	int r = 0;
 
 	if (num_ibs == 0)
 		return -EINVAL;
 
-	ctx = ibs->ctx;
-	vm = ibs->vm;
+	/* ring tests don't use a job */
+	if (job) {
+		vm = job->vm;
+		ctx = job->ctx;
+	} else {
+		vm = NULL;
+		ctx = 0;
+	}
 
 	if (!ring->ready) {
 		dev_err(adev->dev, "couldn't schedule ib\n");
 		return -EINVAL;
 	}
 
-	if (vm && !ibs->vm_id) {
+	if (vm && !job->vm_id) {
 		dev_err(adev->dev, "VM IB without ID\n");
 		return -EINVAL;
 	}
@@ -149,58 +156,68 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 		return r;
 	}
 
+	if (ring->type == AMDGPU_RING_TYPE_SDMA && ring->funcs->init_cond_exec)
+		patch_offset = amdgpu_ring_init_cond_exec(ring);
+
 	if (vm) {
-		/* do context switch */
-		amdgpu_vm_flush(ring, ib->vm_id, ib->vm_pd_addr,
-				ib->gds_base, ib->gds_size,
-				ib->gws_base, ib->gws_size,
-				ib->oa_base, ib->oa_size);
-
-		if (ring->funcs->emit_hdp_flush)
-			amdgpu_ring_emit_hdp_flush(ring);
+		r = amdgpu_vm_flush(ring, job->vm_id, job->vm_pd_addr,
+				    job->gds_base, job->gds_size,
+				    job->gws_base, job->gws_size,
+				    job->oa_base, job->oa_size);
+		if (r) {
+			amdgpu_ring_undo(ring);
+			return r;
+		}
 	}
 
-	old_ctx = ring->current_ctx;
+	if (ring->funcs->emit_hdp_flush)
+		amdgpu_ring_emit_hdp_flush(ring);
+
+	/* always set cond_exec_polling to CONTINUE */
+	*ring->cond_exe_cpu_addr = 1;
+
+	skip_preamble = ring->current_ctx == ctx;
+	need_ctx_switch = ring->current_ctx != ctx;
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
 
-		if (ib->ctx != ctx || ib->vm != vm) {
-			ring->current_ctx = old_ctx;
-			if (ib->vm_id)
-				amdgpu_vm_reset_id(adev, ib->vm_id);
-			amdgpu_ring_undo(ring);
-			return -EINVAL;
-		}
-		amdgpu_ring_emit_ib(ring, ib);
-		ring->current_ctx = ctx;
-	}
+		/* drop preamble IBs if we don't have a context switch */
+		if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && skip_preamble)
+			continue;
 
-	if (vm) {
-		if (ring->funcs->emit_hdp_invalidate)
-			amdgpu_ring_emit_hdp_invalidate(ring);
+		amdgpu_ring_emit_ib(ring, ib, job ? job->vm_id : 0,
+				    need_ctx_switch);
+		need_ctx_switch = false;
 	}
 
+	if (ring->funcs->emit_hdp_invalidate)
+		amdgpu_ring_emit_hdp_invalidate(ring);
+
 	r = amdgpu_fence_emit(ring, &hwf);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
-		ring->current_ctx = old_ctx;
-		if (ib->vm_id)
-			amdgpu_vm_reset_id(adev, ib->vm_id);
+		if (job && job->vm_id)
+			amdgpu_vm_reset_id(adev, job->vm_id);
 		amdgpu_ring_undo(ring);
 		return r;
 	}
 
 	/* wrap the last IB with fence */
-	if (ib->user) {
-		uint64_t addr = amdgpu_bo_gpu_offset(ib->user->bo);
-		addr += ib->user->offset;
-		amdgpu_ring_emit_fence(ring, addr, ib->sequence,
+	if (job && job->uf_bo) {
+		uint64_t addr = amdgpu_bo_gpu_offset(job->uf_bo);
+
+		addr += job->uf_offset;
+		amdgpu_ring_emit_fence(ring, addr, job->uf_sequence,
 				       AMDGPU_FENCE_FLAG_64BIT);
 	}
 
 	if (f)
 		*f = fence_get(hwf);
 
+	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
+		amdgpu_ring_patch_cond_exec(ring, patch_offset);
+
+	ring->current_ctx = ctx;
 	amdgpu_ring_commit(ring);
 	return 0;
 }
@@ -315,7 +332,7 @@ static int amdgpu_debugfs_sa_info(struct seq_file *m, void *data)
 
 }
 
-static struct drm_info_list amdgpu_debugfs_sa_list[] = {
+static const struct drm_info_list amdgpu_debugfs_sa_list[] = {
 	{"amdgpu_sa_info", &amdgpu_debugfs_sa_info, 0, NULL},
 };