Merge tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "This is the main pull request for 5.4-rc1 merge window. I don't think
  there is anything outstanding so next week should just be fixes, but
  we'll see if I missed anything. I landed some fixes earlier in the
  week but got delayed writing summary and sending it out, due to a mix
  of sick kid and jetlag!

  There are some fixes pending, but I'd rather get the main merge out of
  the way instead of delaying it longer.

  It's also pretty large in commit count and new amd header file size.
  The largest thing is four new amdgpu products (navi12/14, arcturus and
  renoir APU support).

  Otherwise it's pretty much lots of work across the board, i915 has
  started landing tigerlake support, lots of icelake fixes and lots of
  locking reworking for future gpu support, lots of header file rework
  (drmP.h is nearly gone), some old legacy hacks (DRM_WAIT_ON) have been
  put into the places they are needed.

  uapi:
   - content protection type property for HDCP

  core:
   - rework include dependencies
   - lots of drmP.h removals
   - link rate calculation robustness fix
   - make fb helper map only when required
   - add connector->DDC adapter link
   - DRM_WAIT_ON removed
   - drop DRM_AUTH usage from drivers

  dma-buf:
   - reservation object fence helper

  dma-fence:
   - shrink dma_fence struct
   - merge signal functions
   - store timestamps in dma_fence
   - selftests

  ttm:
   - embed drm_get_object struct into ttm_buffer_object
   - release_notify callback

  bridges:
   - sii902x - audio graph card support
   - tc358767 - aux data handling rework
   - ti-snd64dsi86 - debugfs support, DSI mode flags support

  panels:
   - Support for GiantPlus GPM940B0, Sharp LQ070Y3DG3B, Ortustech
     COM37H3M, Novatek NT39016, Sharp LS020B1DD01D, Raydium RM67191, Boe
     Himax8279d, Sharp LD-D5116Z01B
   - TI nspire, NEC NL8048HL11, LG Philips LB035Q02, Sharp LS037V7DW01,
     Sony ACX565AKM, Toppoly TD028TTEC1 Toppoly TD043MTEA1

  i915:
   - Initial tigerlake platform support
   - Locking simplification work, general all over refactoring.
   - Selftests
   - HDCP debug info improvements
   - DSI properties
   - Icelake display PLL fixes, colorspace fixes, bandwidth fixes, DSI
     suspend/resume
   - GuC fixes
   - Perf fixes
   - ElkhartLake enablement
   - DP MST fixes
   - GVT - command parser enhancements

  amdgpu:
   - add wipe memory on release flag for buffer creation
   - Navi12/14 support (may be marked experimental)
   - Arcturus support
   - Renoir APU support
   - mclk DPM for Navi
   - DC display fixes
   - Raven scatter/gather support
   - RAS support for GFX
   - Navi12 + Arcturus power features
   - GPU reset for Picasso
   - smu11 i2c controller support

  amdkfd:
   - navi12/14 support
   - Arcturus support

  radeon:
   - kexec fix

  nouveau:
   - improved display color management
   - detect lack of GPU power cables

  vmwgfx:
   - evicition priority support
   - remove unused security feature

  msm:
   - msm8998 display support
   - better async commit support for cursor updates

  etnaviv:
   - per-process address space support
   - performance counter fixes
   - softpin support

  mcde:
   - DCS transfers fix

  exynos:
   - drmP.h cleanup

  lima:
   - reduce logging

  kirin:
   - misc clenaups

  komeda:
   - dual-link support
   - DT memory regions

  hisilicon:
   - misc fixes

  imx:
   - IPUv3 image converter fixes
   - 32-bit RGB V4L2 pixel format support

  ingenic:
   - more support for panel related cases

  mgag200:
   - cursor support fix

  panfrost:
   - export GPU features register to userspace
   - gpu heap allocations
   - per-fd address space support

  pl111:
   - CLD pads wiring support removed from DT

  rockchip:
   - rework to use DRM PSR helpers
   - fix bug in VOP_WIN_GET macro
   - DSI DT binding rework

  sun4i:
   - improve support for color encoding and range
   - DDC enabled GPIO

  tinydrm:
   - rework SPI support
   - improve MIPI-DBI support
   - moved to drm/tiny

  vkms:
   - rework CRC tracking

  dw-hdmi:
   - get_eld and i2s improvements

  gm12u320:
   - misc fixes

  meson:
   - global code cleanup
   - vpu feature detect

  omap:
   - alpha/pixel blend mode properties

  rcar-du:
   - misc fixes"

* tag 'drm-next-2019-09-18' of git://anongit.freedesktop.org/drm/drm: (2112 commits)
  drm/nouveau/bar/gm20b: Avoid BAR1 teardown during init
  drm/nouveau: Fix ordering between TTM and GEM release
  drm/nouveau/prime: Extend DMA reservation object lock
  drm/nouveau: Fix fallout from reservation object rework
  drm/nouveau/kms/nv50-: Don't create MSTMs for eDP connectors
  drm/i915: Use NOEVICT for first pass on attemping to pin a GGTT mmap
  drm/i915: to make vgpu ppgtt notificaiton as atomic operation
  drm/i915: Flush the existing fence before GGTT read/write
  drm/i915: Hold irq-off for the entire fake lock period
  drm/i915/gvt: update RING_START reg of vGPU when the context is submitted to i915
  drm/i915/gvt: update vgpu workload head pointer correctly
  drm/mcde: Fix DSI transfers
  drm/msm: Use the correct dma_sync calls harder
  drm/msm: remove unlikely() from WARN_ON() conditions
  drm/msm/dsi: Fix return value check for clk_get_parent
  drm/msm: add atomic traces
  drm/msm/dpu: async commit support
  drm/msm: async commit support
  drm/msm: split power control from prepare/complete_commit
  drm/msm: add kms->flush_commit()
  ...

1 files changed, 136 insertions, 44 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 23120901c55f..f55691d151ae 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -53,12 +53,24 @@ int __intel_context_do_pin(struct intel_context *ce)
 	if (likely(!atomic_read(&ce->pin_count))) {
 		intel_wakeref_t wakeref;
 
+		if (unlikely(!test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
+			err = ce->ops->alloc(ce);
+			if (unlikely(err))
+				goto err;
+
+			__set_bit(CONTEXT_ALLOC_BIT, &ce->flags);
+		}
+
 		err = 0;
 		with_intel_runtime_pm(&ce->engine->i915->runtime_pm, wakeref)
 			err = ce->ops->pin(ce);
 		if (err)
 			goto err;
 
+		GEM_TRACE("%s context:%llx pin ring:{head:%04x, tail:%04x}\n",
+			  ce->engine->name, ce->timeline->fence_context,
+			  ce->ring->head, ce->ring->tail);
+
 		i915_gem_context_get(ce->gem_context); /* for ctx->ppgtt */
 
 		smp_mb__before_atomic(); /* flush pin before it is visible */
@@ -85,6 +97,9 @@ void intel_context_unpin(struct intel_context *ce)
 	mutex_lock_nested(&ce->pin_mutex, SINGLE_DEPTH_NESTING);
 
 	if (likely(atomic_dec_and_test(&ce->pin_count))) {
+		GEM_TRACE("%s context:%llx retire\n",
+			  ce->engine->name, ce->timeline->fence_context);
+
 		ce->ops->unpin(ce);
 
 		i915_gem_context_put(ce->gem_context);
@@ -95,11 +110,15 @@ void intel_context_unpin(struct intel_context *ce)
 	intel_context_put(ce);
 }
 
-static int __context_pin_state(struct i915_vma *vma, unsigned long flags)
+static int __context_pin_state(struct i915_vma *vma)
 {
+	u64 flags;
 	int err;
 
-	err = i915_vma_pin(vma, 0, 0, flags | PIN_GLOBAL);
+	flags = i915_ggtt_pin_bias(vma) | PIN_OFFSET_BIAS;
+	flags |= PIN_HIGH | PIN_GLOBAL;
+
+	err = i915_vma_pin(vma, 0, 0, flags);
 	if (err)
 		return err;
 
@@ -107,7 +126,7 @@ static int __context_pin_state(struct i915_vma *vma, unsigned long flags)
 	 * And mark it as a globally pinned object to let the shrinker know
 	 * it cannot reclaim the object until we release it.
 	 */
-	vma->obj->pin_global++;
+	i915_vma_make_unshrinkable(vma);
 	vma->obj->mm.dirty = true;
 
 	return 0;
@@ -115,83 +134,79 @@ static int __context_pin_state(struct i915_vma *vma, unsigned long flags)
 
 static void __context_unpin_state(struct i915_vma *vma)
 {
-	vma->obj->pin_global--;
 	__i915_vma_unpin(vma);
+	i915_vma_make_shrinkable(vma);
 }
 
-static void intel_context_retire(struct i915_active *active)
+static void __intel_context_retire(struct i915_active *active)
 {
 	struct intel_context *ce = container_of(active, typeof(*ce), active);
 
+	GEM_TRACE("%s context:%llx retire\n",
+		  ce->engine->name, ce->timeline->fence_context);
+
 	if (ce->state)
 		__context_unpin_state(ce->state);
 
+	intel_timeline_unpin(ce->timeline);
 	intel_ring_unpin(ce->ring);
 	intel_context_put(ce);
 }
 
-void
-intel_context_init(struct intel_context *ce,
-		   struct i915_gem_context *ctx,
-		   struct intel_engine_cs *engine)
-{
-	GEM_BUG_ON(!engine->cops);
-
-	kref_init(&ce->ref);
-
-	ce->gem_context = ctx;
-	ce->engine = engine;
-	ce->ops = engine->cops;
-	ce->sseu = engine->sseu;
-
-	INIT_LIST_HEAD(&ce->signal_link);
-	INIT_LIST_HEAD(&ce->signals);
-
-	mutex_init(&ce->pin_mutex);
-
-	i915_active_init(ctx->i915, &ce->active, intel_context_retire);
-}
-
-int intel_context_active_acquire(struct intel_context *ce, unsigned long flags)
+static int __intel_context_active(struct i915_active *active)
 {
+	struct intel_context *ce = container_of(active, typeof(*ce), active);
 	int err;
 
-	if (!i915_active_acquire(&ce->active))
-		return 0;
-
 	intel_context_get(ce);
 
 	err = intel_ring_pin(ce->ring);
 	if (err)
 		goto err_put;
 
+	err = intel_timeline_pin(ce->timeline);
+	if (err)
+		goto err_ring;
+
 	if (!ce->state)
 		return 0;
 
-	err = __context_pin_state(ce->state, flags);
+	err = __context_pin_state(ce->state);
 	if (err)
-		goto err_ring;
-
-	/* Preallocate tracking nodes */
-	if (!i915_gem_context_is_kernel(ce->gem_context)) {
-		err = i915_active_acquire_preallocate_barrier(&ce->active,
-							      ce->engine);
-		if (err)
-			goto err_state;
-	}
+		goto err_timeline;
 
 	return 0;
 
-err_state:
-	__context_unpin_state(ce->state);
+err_timeline:
+	intel_timeline_unpin(ce->timeline);
 err_ring:
 	intel_ring_unpin(ce->ring);
 err_put:
 	intel_context_put(ce);
-	i915_active_cancel(&ce->active);
 	return err;
 }
 
+int intel_context_active_acquire(struct intel_context *ce)
+{
+	int err;
+
+	err = i915_active_acquire(&ce->active);
+	if (err)
+		return err;
+
+	/* Preallocate tracking nodes */
+	if (!i915_gem_context_is_kernel(ce->gem_context)) {
+		err = i915_active_acquire_preallocate_barrier(&ce->active,
+							      ce->engine);
+		if (err) {
+			i915_active_release(&ce->active);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 void intel_context_active_release(struct intel_context *ce)
 {
 	/* Nodes preallocated in intel_context_active() */
@@ -199,6 +214,44 @@ void intel_context_active_release(struct intel_context *ce)
 	i915_active_release(&ce->active);
 }
 
+void
+intel_context_init(struct intel_context *ce,
+		   struct i915_gem_context *ctx,
+		   struct intel_engine_cs *engine)
+{
+	GEM_BUG_ON(!engine->cops);
+
+	kref_init(&ce->ref);
+
+	ce->gem_context = ctx;
+	ce->vm = i915_vm_get(ctx->vm ?: &engine->gt->ggtt->vm);
+	if (ctx->timeline)
+		ce->timeline = intel_timeline_get(ctx->timeline);
+
+	ce->engine = engine;
+	ce->ops = engine->cops;
+	ce->sseu = engine->sseu;
+	ce->ring = __intel_context_ring_size(SZ_16K);
+
+	INIT_LIST_HEAD(&ce->signal_link);
+	INIT_LIST_HEAD(&ce->signals);
+
+	mutex_init(&ce->pin_mutex);
+
+	i915_active_init(ctx->i915, &ce->active,
+			 __intel_context_active, __intel_context_retire);
+}
+
+void intel_context_fini(struct intel_context *ce)
+{
+	if (ce->timeline)
+		intel_timeline_put(ce->timeline);
+	i915_vm_put(ce->vm);
+
+	mutex_destroy(&ce->pin_mutex);
+	i915_active_fini(&ce->active);
+}
+
 static void i915_global_context_shrink(void)
 {
 	kmem_cache_shrink(global.slab_ce);
@@ -227,13 +280,48 @@ int __init i915_global_context_init(void)
 void intel_context_enter_engine(struct intel_context *ce)
 {
 	intel_engine_pm_get(ce->engine);
+	intel_timeline_enter(ce->timeline);
 }
 
 void intel_context_exit_engine(struct intel_context *ce)
 {
+	intel_timeline_exit(ce->timeline);
 	intel_engine_pm_put(ce->engine);
 }
 
+int intel_context_prepare_remote_request(struct intel_context *ce,
+					 struct i915_request *rq)
+{
+	struct intel_timeline *tl = ce->timeline;
+	int err;
+
+	/* Only suitable for use in remotely modifying this context */
+	GEM_BUG_ON(rq->hw_context == ce);
+
+	if (rq->timeline != tl) { /* beware timeline sharing */
+		err = mutex_lock_interruptible_nested(&tl->mutex,
+						      SINGLE_DEPTH_NESTING);
+		if (err)
+			return err;
+
+		/* Queue this switch after current activity by this context. */
+		err = i915_active_request_set(&tl->last_request, rq);
+		mutex_unlock(&tl->mutex);
+		if (err)
+			return err;
+	}
+
+	/*
+	 * Guarantee context image and the timeline remains pinned until the
+	 * modifying request is retired by setting the ce activity tracker.
+	 *
+	 * But we only need to take one pin on the account of it. Or in other
+	 * words transfer the pinned ce object to tracked active request.
+	 */
+	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	return i915_active_ref(&ce->active, rq->timeline, rq);
+}
+
 struct i915_request *intel_context_create_request(struct intel_context *ce)
 {
 	struct i915_request *rq;
@@ -248,3 +336,7 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 
 	return rq;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_context.c"
+#endif