Merge tag 'drm-intel-fixes-2016-04-21' of git://anongit.freedesktop.org/drm-intel into drm-fixes

Hi Dave, fixes all around, all but one are cc: stable material, the most
important ones are likely the Skylake hang fixes from Mika.

* tag 'drm-intel-fixes-2016-04-21' of git://anongit.freedesktop.org/drm-intel:
  drm/i915: Use fw_domains_put_with_fifo() on HSW
  drm/i915: Force ringbuffers to not be at offset 0
  drm/i915: Adjust size of PIPE_CONTROL used for gen8 render seqno write
  drm/i915/skl: Fix spurious gpu hang with gt3/gt4 revs
  drm/i915/skl: Fix rc6 based gpu/system hang
  drm/i915/userptr: Hold mmref whilst calling get-user-pages
  drm/i915: Fixup the free space logic in ring_prepare
  drm/i915/skl+: Use plane size for relative data rate calculation

6 files changed, 75 insertions, 41 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 10480939159c..daba7ebb9699 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2634,8 +2634,9 @@ struct drm_i915_cmd_table {
 
 /* WaRsDisableCoarsePowerGating:skl,bxt */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev) (IS_BXT_REVID(dev, 0, BXT_REVID_A1) || \
-						 ((IS_SKL_GT3(dev) || IS_SKL_GT4(dev)) && \
-						  IS_SKL_REVID(dev, 0, SKL_REVID_F0)))
+						 IS_SKL_GT3(dev) || \
+						 IS_SKL_GT4(dev))
+
 /*
  * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
  * even when in MSI mode. This results in spurious interrupt warnings if the
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 18ba8139e922..4d30b60defda 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -501,19 +501,24 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	if (pvec != NULL) {
 		struct mm_struct *mm = obj->userptr.mm->mm;
 
-		down_read(&mm->mmap_sem);
-		while (pinned < npages) {
-			ret = get_user_pages_remote(work->task, mm,
-					obj->userptr.ptr + pinned * PAGE_SIZE,
-					npages - pinned,
-					!obj->userptr.read_only, 0,
-					pvec + pinned, NULL);
-			if (ret < 0)
-				break;
-
-			pinned += ret;
+		ret = -EFAULT;
+		if (atomic_inc_not_zero(&mm->mm_users)) {
+			down_read(&mm->mmap_sem);
+			while (pinned < npages) {
+				ret = get_user_pages_remote
+					(work->task, mm,
+					 obj->userptr.ptr + pinned * PAGE_SIZE,
+					 npages - pinned,
+					 !obj->userptr.read_only, 0,
+					 pvec + pinned, NULL);
+				if (ret < 0)
+					break;
+
+				pinned += ret;
+			}
+			up_read(&mm->mmap_sem);
+			mmput(mm);
 		}
-		up_read(&mm->mmap_sem);
 	}
 
 	mutex_lock(&dev->struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 6a978ce80244..5c6080fd0968 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -841,11 +841,11 @@ static int logical_ring_prepare(struct drm_i915_gem_request *req, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
@@ -1913,15 +1913,18 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	struct intel_ringbuffer *ringbuf = request->ringbuf;
 	int ret;
 
-	ret = intel_logical_ring_begin(request, 6 + WA_TAIL_DWORDS);
+	ret = intel_logical_ring_begin(request, 8 + WA_TAIL_DWORDS);
 	if (ret)
 		return ret;
 
+	/* We're using qword write, seqno should be aligned to 8 bytes. */
+	BUILD_BUG_ON(I915_GEM_HWS_INDEX & 1);
+
 	/* w/a for post sync ops following a GPGPU operation we
 	 * need a prior CS_STALL, which is emitted by the flush
 	 * following the batch.
 	 */
-	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(5));
+	intel_logical_ring_emit(ringbuf, GFX_OP_PIPE_CONTROL(6));
 	intel_logical_ring_emit(ringbuf,
 				(PIPE_CONTROL_GLOBAL_GTT_IVB |
 				 PIPE_CONTROL_CS_STALL |
@@ -1929,7 +1932,10 @@ static int gen8_emit_request_render(struct drm_i915_gem_request *request)
 	intel_logical_ring_emit(ringbuf, hws_seqno_address(request->ring));
 	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, i915_gem_request_get_seqno(request));
+	/* We're thrashing one dword of HWS. */
+	intel_logical_ring_emit(ringbuf, 0);
 	intel_logical_ring_emit(ringbuf, MI_USER_INTERRUPT);
+	intel_logical_ring_emit(ringbuf, MI_NOOP);
 	return intel_logical_ring_advance_and_submit(request);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 347d4df49a9b..8ed3cf34f82d 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2876,25 +2876,28 @@ skl_plane_relative_data_rate(const struct intel_crtc_state *cstate,
 			     const struct drm_plane_state *pstate,
 			     int y)
 {
-	struct intel_crtc *intel_crtc = to_intel_crtc(cstate->base.crtc);
+	struct intel_plane_state *intel_pstate = to_intel_plane_state(pstate);
 	struct drm_framebuffer *fb = pstate->fb;
+	uint32_t width = 0, height = 0;
+
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(pstate->rotation))
+		swap(width, height);
 
 	/* for planar format */
 	if (fb->pixel_format == DRM_FORMAT_NV12) {
 		if (y)  /* y-plane data rate */
-			return intel_crtc->config->pipe_src_w *
-				intel_crtc->config->pipe_src_h *
+			return width * height *
 				drm_format_plane_cpp(fb->pixel_format, 0);
 		else    /* uv-plane data rate */
-			return (intel_crtc->config->pipe_src_w/2) *
-				(intel_crtc->config->pipe_src_h/2) *
+			return (width / 2) * (height / 2) *
 				drm_format_plane_cpp(fb->pixel_format, 1);
 	}
 
 	/* for packed formats */
-	return intel_crtc->config->pipe_src_w *
-		intel_crtc->config->pipe_src_h *
-		drm_format_plane_cpp(fb->pixel_format, 0);
+	return width * height * drm_format_plane_cpp(fb->pixel_format, 0);
 }
 
 /*
@@ -2973,8 +2976,9 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		struct drm_framebuffer *fb = plane->state->fb;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (fb == NULL)
+		if (!to_intel_plane_state(plane->state)->visible)
 			continue;
+
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
 
@@ -3000,7 +3004,7 @@ skl_allocate_pipe_ddb(struct intel_crtc_state *cstate,
 		uint16_t plane_blocks, y_plane_blocks = 0;
 		int id = skl_wm_plane_id(intel_plane);
 
-		if (pstate->fb == NULL)
+		if (!to_intel_plane_state(pstate)->visible)
 			continue;
 		if (plane->type == DRM_PLANE_TYPE_CURSOR)
 			continue;
@@ -3123,26 +3127,36 @@ static bool skl_compute_plane_wm(const struct drm_i915_private *dev_priv,
 {
 	struct drm_plane *plane = &intel_plane->base;
 	struct drm_framebuffer *fb = plane->state->fb;
+	struct intel_plane_state *intel_pstate =
+					to_intel_plane_state(plane->state);
 	uint32_t latency = dev_priv->wm.skl_latency[level];
 	uint32_t method1, method2;
 	uint32_t plane_bytes_per_line, plane_blocks_per_line;
 	uint32_t res_blocks, res_lines;
 	uint32_t selected_result;
 	uint8_t cpp;
+	uint32_t width = 0, height = 0;
 
-	if (latency == 0 || !cstate->base.active || !fb)
+	if (latency == 0 || !cstate->base.active || !intel_pstate->visible)
 		return false;
 
+	width = drm_rect_width(&intel_pstate->src) >> 16;
+	height = drm_rect_height(&intel_pstate->src) >> 16;
+
+	if (intel_rotation_90_or_270(plane->state->rotation))
+		swap(width, height);
+
 	cpp = drm_format_plane_cpp(fb->pixel_format, 0);
 	method1 = skl_wm_method1(skl_pipe_pixel_rate(cstate),
 				 cpp, latency);
 	method2 = skl_wm_method2(skl_pipe_pixel_rate(cstate),
 				 cstate->base.adjusted_mode.crtc_htotal,
-				 cstate->pipe_src_w,
-				 cpp, fb->modifier[0],
+				 width,
+				 cpp,
+				 fb->modifier[0],
 				 latency);
 
-	plane_bytes_per_line = cstate->pipe_src_w * cpp;
+	plane_bytes_per_line = width * cpp;
 	plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512);
 
 	if (fb->modifier[0] == I915_FORMAT_MOD_Y_TILED ||
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 45ce45a5e122..9121646d7c4d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -968,7 +968,7 @@ static int gen9_init_workarounds(struct intel_engine_cs *ring)
 
 	/* WaForceContextSaveRestoreNonCoherent:skl,bxt */
 	tmp = HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT;
-	if (IS_SKL_REVID(dev, SKL_REVID_F0, SKL_REVID_F0) ||
+	if (IS_SKL_REVID(dev, SKL_REVID_F0, REVID_FOREVER) ||
 	    IS_BXT_REVID(dev, BXT_REVID_B0, REVID_FOREVER))
 		tmp |= HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE;
 	WA_SET_BIT_MASKED(HDC_CHICKEN0, tmp);
@@ -1085,7 +1085,8 @@ static int skl_init_workarounds(struct intel_engine_cs *ring)
 		WA_SET_BIT_MASKED(HIZ_CHICKEN,
 				  BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE);
 
-	if (IS_SKL_REVID(dev, 0, SKL_REVID_F0)) {
+	/* This is tied to WaForceContextSaveRestoreNonCoherent */
+	if (IS_SKL_REVID(dev, 0, REVID_FOREVER)) {
 		/*
 		 *Use Force Non-Coherent whenever executing a 3D context. This
 		 * is a workaround for a possible hang in the unlikely event
@@ -2090,10 +2091,12 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj = ringbuf->obj;
+	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+	unsigned flags = PIN_OFFSET_BIAS | 4096;
 	int ret;
 
 	if (HAS_LLC(dev_priv) && !obj->stolen) {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, 0);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, flags);
 		if (ret)
 			return ret;
 
@@ -2109,7 +2112,8 @@ int intel_pin_and_map_ringbuffer_obj(struct drm_device *dev,
 			return -ENOMEM;
 		}
 	} else {
-		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE, PIN_MAPPABLE);
+		ret = i915_gem_obj_ggtt_pin(obj, PAGE_SIZE,
+					    flags | PIN_MAPPABLE);
 		if (ret)
 			return ret;
 
@@ -2454,11 +2458,11 @@ static int __intel_ring_prepare(struct intel_engine_cs *ring, int bytes)
 		if (unlikely(total_bytes > remain_usable)) {
 			/*
 			 * The base request will fit but the reserved space
-			 * falls off the end. So only need to to wait for the
-			 * reserved size after flushing out the remainder.
+			 * falls off the end. So don't need an immediate wrap
+			 * and only need to effectively wait for the reserved
+			 * size space from the start of ringbuffer.
 			 */
 			wait_bytes = remain_actual + ringbuf->reserved_size;
-			need_wrap = true;
 		} else if (total_bytes > ringbuf->space) {
 			/* No wrapping required, just waiting. */
 			wait_bytes = total_bytes;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 436d8f2b8682..68b6f69aa682 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1189,7 +1189,11 @@ static void intel_uncore_fw_domains_init(struct drm_device *dev)
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		dev_priv->uncore.funcs.force_wake_get =
 			fw_domains_get_with_thread_status;
-		dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
+		if (IS_HASWELL(dev))
+			dev_priv->uncore.funcs.force_wake_put =
+				fw_domains_put_with_fifo;
+		else
+			dev_priv->uncore.funcs.force_wake_put = fw_domains_put;
 		fw_domain_init(dev_priv, FW_DOMAIN_ID_RENDER,
 			       FORCEWAKE_MT, FORCEWAKE_ACK_HSW);
 	} else if (IS_IVYBRIDGE(dev)) {