Merge branch 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux into drm-next

First drm-next pull for radeon and amdgpu for 4.9.  Highlights:
- powerplay support for iceland asics
- improved GPU reset (both full asic and per block)
- UVD and VCE powergating for CZ and ST
- VCE clockgating for CZ and ST
- Support for pre-initialized (e.g., zeroed) vram buffers
- ttm cleanups
- virtual display support
- core and radeon/amdgpu support for page_flip_target
- lots of bug fixes and clean ups

* 'drm-next-4.9' of git://people.freedesktop.org/~agd5f/linux: (171 commits)
  drm/amdgpu: use memcpy_toio for VCE firmware upload
  drm/amdgpu: use memcpy_to/fromio for UVD fw upload
  drm/amd/powerplay: delete useless code in iceland_hwmgr.c.
  drm/radeon: switch UVD code to use UVD_NO_OP for padding
  drm/amdgpu: switch UVD code to use UVD_NO_OP for padding
  drm/radeon: add support for UVD_NO_OP register
  drm/amdgpu: add support for UVD_NO_OP register
  drm/amdgpu: fix VCE ib alignment value
  drm/amdgpu: fix IB alignment for UVD
  drm/amd/amdgpu: Print ring name in amdgpu_ib_schedule()
  drm/radeon: remove dead code, si_mc_load_microcode (v2)
  drm/radeon/cik: remove dead code (v2)
  drm/amd/powerplay: avoid NULL dereference, cz_hwmgr.c
  drm/amd/powerplay: avoid NULL pointer dereference
  drm/amdgpu/gmc8: remove dead code (v2)
  drm/amdgpu/gmc7: remove dead code (v2)
  drm/amdgpu: Fix indentation in dce_v8_0_audio_write_sad_regs()
  drm/amdgpu: Use correct mask in dce_v8_0_afmt_setmode() and fix comment typos.
  drm/amdgpu: cleanup amdgpu_vm_bo_update params
  drm/amdgpu: stop adding dummy entry in amdgpu_ttm_placement_init
  ...

1 files changed, 33 insertions, 68 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 76f96028313d..9af8d3c7ae8b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -41,7 +41,7 @@ static void amdgpu_flip_callback(struct fence *f, struct fence_cb *cb)
 		container_of(cb, struct amdgpu_flip_work, cb);
 
 	fence_put(f);
-	schedule_work(&work->flip_work);
+	schedule_work(&work->flip_work.work);
 }
 
 static bool amdgpu_flip_handle_fence(struct amdgpu_flip_work *work,
@@ -63,16 +63,17 @@ static bool amdgpu_flip_handle_fence(struct amdgpu_flip_work *work,
 
 static void amdgpu_flip_work_func(struct work_struct *__work)
 {
+	struct delayed_work *delayed_work =
+		container_of(__work, struct delayed_work, work);
 	struct amdgpu_flip_work *work =
-		container_of(__work, struct amdgpu_flip_work, flip_work);
+		container_of(delayed_work, struct amdgpu_flip_work, flip_work);
 	struct amdgpu_device *adev = work->adev;
 	struct amdgpu_crtc *amdgpuCrtc = adev->mode_info.crtcs[work->crtc_id];
 
 	struct drm_crtc *crtc = &amdgpuCrtc->base;
 	unsigned long flags;
-	unsigned i, repcnt = 4;
-	int vpos, hpos, stat, min_udelay = 0;
-	struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id];
+	unsigned i;
+	int vpos, hpos;
 
 	if (amdgpu_flip_handle_fence(work, &work->excl))
 		return;
@@ -81,55 +82,23 @@ static void amdgpu_flip_work_func(struct work_struct *__work)
 		if (amdgpu_flip_handle_fence(work, &work->shared[i]))
 			return;
 
-	/* We borrow the event spin lock for protecting flip_status */
-	spin_lock_irqsave(&crtc->dev->event_lock, flags);
-
-	/* If this happens to execute within the "virtually extended" vblank
-	 * interval before the start of the real vblank interval then it needs
-	 * to delay programming the mmio flip until the real vblank is entered.
-	 * This prevents completing a flip too early due to the way we fudge
-	 * our vblank counter and vblank timestamps in order to work around the
-	 * problem that the hw fires vblank interrupts before actual start of
-	 * vblank (when line buffer refilling is done for a frame). It
-	 * complements the fudging logic in amdgpu_get_crtc_scanoutpos() for
-	 * timestamping and amdgpu_get_vblank_counter_kms() for vblank counts.
-	 *
-	 * In practice this won't execute very often unless on very fast
-	 * machines because the time window for this to happen is very small.
+	/* Wait until we're out of the vertical blank period before the one
+	 * targeted by the flip
 	 */
-	while (amdgpuCrtc->enabled && --repcnt) {
-		/* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank
-		 * start in hpos, and to the "fudged earlier" vblank start in
-		 * vpos.
-		 */
-		stat = amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id,
-						  GET_DISTANCE_TO_VBLANKSTART,
-						  &vpos, &hpos, NULL, NULL,
-						  &crtc->hwmode);
-
-		if ((stat & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE)) !=
-		    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_ACCURATE) ||
-		    !(vpos >= 0 && hpos <= 0))
-			break;
-
-		/* Sleep at least until estimated real start of hw vblank */
-		min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5);
-		if (min_udelay > vblank->framedur_ns / 2000) {
-			/* Don't wait ridiculously long - something is wrong */
-			repcnt = 0;
-			break;
-		}
-		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
-		usleep_range(min_udelay, 2 * min_udelay);
-		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+	if (amdgpuCrtc->enabled &&
+	    (amdgpu_get_crtc_scanoutpos(adev->ddev, work->crtc_id, 0,
+					&vpos, &hpos, NULL, NULL,
+					&crtc->hwmode)
+	     & (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK)) ==
+	    (DRM_SCANOUTPOS_VALID | DRM_SCANOUTPOS_IN_VBLANK) &&
+	    (int)(work->target_vblank -
+		  amdgpu_get_vblank_counter_kms(adev->ddev, amdgpuCrtc->crtc_id)) > 0) {
+		schedule_delayed_work(&work->flip_work, usecs_to_jiffies(1000));
+		return;
 	}
 
-	if (!repcnt)
-		DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, "
-				 "framedur %d, linedur %d, stat %d, vpos %d, "
-				 "hpos %d\n", work->crtc_id, min_udelay,
-				 vblank->framedur_ns / 1000,
-				 vblank->linedur_ns / 1000, stat, vpos, hpos);
+	/* We borrow the event spin lock for protecting flip_status */
+	spin_lock_irqsave(&crtc->dev->event_lock, flags);
 
 	/* Do the flip (mmio) */
 	adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base, work->async);
@@ -169,10 +138,10 @@ static void amdgpu_unpin_work_func(struct work_struct *__work)
 	kfree(work);
 }
 
-int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
-			  struct drm_framebuffer *fb,
-			  struct drm_pending_vblank_event *event,
-			  uint32_t page_flip_flags)
+int amdgpu_crtc_page_flip_target(struct drm_crtc *crtc,
+				 struct drm_framebuffer *fb,
+				 struct drm_pending_vblank_event *event,
+				 uint32_t page_flip_flags, uint32_t target)
 {
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
@@ -191,7 +160,7 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	if (work == NULL)
 		return -ENOMEM;
 
-	INIT_WORK(&work->flip_work, amdgpu_flip_work_func);
+	INIT_DELAYED_WORK(&work->flip_work, amdgpu_flip_work_func);
 	INIT_WORK(&work->unpin_work, amdgpu_unpin_work_func);
 
 	work->event = event;
@@ -237,12 +206,8 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	amdgpu_bo_unreserve(new_rbo);
 
 	work->base = base;
-
-	r = drm_crtc_vblank_get(crtc);
-	if (r) {
-		DRM_ERROR("failed to get vblank before flip\n");
-		goto pflip_cleanup;
-	}
+	work->target_vblank = target - drm_crtc_vblank_count(crtc) +
+		amdgpu_get_vblank_counter_kms(dev, work->crtc_id);
 
 	/* we borrow the event spin lock for protecting flip_wrok */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
@@ -250,7 +215,7 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
 		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
 		r = -EBUSY;
-		goto vblank_cleanup;
+		goto pflip_cleanup;
 	}
 
 	amdgpu_crtc->pflip_status = AMDGPU_FLIP_PENDING;
@@ -262,12 +227,9 @@ int amdgpu_crtc_page_flip(struct drm_crtc *crtc,
 	/* update crtc fb */
 	crtc->primary->fb = fb;
 	spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
-	amdgpu_flip_work_func(&work->flip_work);
+	amdgpu_flip_work_func(&work->flip_work.work);
 	return 0;
 
-vblank_cleanup:
-	drm_crtc_vblank_put(crtc);
-
 pflip_cleanup:
 	if (unlikely(amdgpu_bo_reserve(new_rbo, false) != 0)) {
 		DRM_ERROR("failed to reserve new rbo in error path\n");
@@ -335,7 +297,7 @@ int amdgpu_crtc_set_config(struct drm_mode_set *set)
 	return ret;
 }
 
-static const char *encoder_names[38] = {
+static const char *encoder_names[41] = {
 	"NONE",
 	"INTERNAL_LVDS",
 	"INTERNAL_TMDS1",
@@ -374,6 +336,9 @@ static const char *encoder_names[38] = {
 	"TRAVIS",
 	"INTERNAL_VCE",
 	"INTERNAL_UNIPHY3",
+	"HDMI_ANX9805",
+	"INTERNAL_AMCLK",
+	"VIRTUAL",
 };
 
 static const char *hpd_names[6] = {