11 files changed, 94 insertions, 42 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index 85e6b2bbb34f..3a5ac13d5801 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -856,7 +856,7 @@ static unsigned long i915_audio_component_get_power(struct device *kdev)
 		}
 
 		/* Force CDCLK to 2*BCLK as long as we need audio powered. */
-		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		if (IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, true);
 
 		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
@@ -875,7 +875,7 @@ static void i915_audio_component_put_power(struct device *kdev,
 
 	/* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */
 	if (--dev_priv->audio_power_refcount == 0)
-		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		if (IS_GEMINILAKE(dev_priv))
 			glk_force_audio_cdclk(dev_priv, false);
 
 	intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO, cookie);
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index effc4250b230..301897791627 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -4515,8 +4515,6 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
 {
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	i915_reg_t reg;
-	u32 trans_ddi_func_ctl2_val;
 
 	if (old_crtc_state->master_transcoder == INVALID_TRANSCODER)
 		return;
@@ -4524,10 +4522,7 @@ static void icl_disable_transcoder_port_sync(const struct intel_crtc_state *old_
 	DRM_DEBUG_KMS("Disabling Transcoder Port Sync on Slave Transcoder %s\n",
 		      transcoder_name(old_crtc_state->cpu_transcoder));
 
-	reg = TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder);
-	trans_ddi_func_ctl2_val = ~(PORT_SYNC_MODE_ENABLE |
-				    PORT_SYNC_MODE_MASTER_SELECT_MASK);
-	I915_WRITE(reg, trans_ddi_func_ctl2_val);
+	I915_WRITE(TRANS_DDI_FUNC_CTL2(old_crtc_state->cpu_transcoder), 0);
 }
 
 static void intel_fdi_normal_train(struct intel_crtc *crtc)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index ef7bc41ffffa..5b7ff3ccfa8e 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -123,6 +123,10 @@ static int __context_pin_state(struct i915_vma *vma)
 	if (err)
 		return err;
 
+	err = i915_active_acquire(&vma->active);
+	if (err)
+		goto err_unpin;
+
 	/*
 	 * And mark it as a globally pinned object to let the shrinker know
 	 * it cannot reclaim the object until we release it.
@@ -131,14 +135,44 @@ static int __context_pin_state(struct i915_vma *vma)
 	vma->obj->mm.dirty = true;
 
 	return 0;
+
+err_unpin:
+	i915_vma_unpin(vma);
+	return err;
 }
 
 static void __context_unpin_state(struct i915_vma *vma)
 {
 	i915_vma_make_shrinkable(vma);
+	i915_active_release(&vma->active);
 	__i915_vma_unpin(vma);
 }
 
+static int __ring_active(struct intel_ring *ring)
+{
+	int err;
+
+	err = i915_active_acquire(&ring->vma->active);
+	if (err)
+		return err;
+
+	err = intel_ring_pin(ring);
+	if (err)
+		goto err_active;
+
+	return 0;
+
+err_active:
+	i915_active_release(&ring->vma->active);
+	return err;
+}
+
+static void __ring_retire(struct intel_ring *ring)
+{
+	intel_ring_unpin(ring);
+	i915_active_release(&ring->vma->active);
+}
+
 __i915_active_call
 static void __intel_context_retire(struct i915_active *active)
 {
@@ -151,7 +185,7 @@ static void __intel_context_retire(struct i915_active *active)
 		__context_unpin_state(ce->state);
 
 	intel_timeline_unpin(ce->timeline);
-	intel_ring_unpin(ce->ring);
+	__ring_retire(ce->ring);
 
 	intel_context_put(ce);
 }
@@ -163,7 +197,7 @@ static int __intel_context_active(struct i915_active *active)
 
 	intel_context_get(ce);
 
-	err = intel_ring_pin(ce->ring);
+	err = __ring_active(ce->ring);
 	if (err)
 		goto err_put;
 
@@ -183,7 +217,7 @@ static int __intel_context_active(struct i915_active *active)
 err_timeline:
 	intel_timeline_unpin(ce->timeline);
 err_ring:
-	intel_ring_unpin(ce->ring);
+	__ring_retire(ce->ring);
 err_put:
 	intel_context_put(ce);
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 75dd0e0367b7..d925a1035c9d 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -2664,6 +2664,14 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
 	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
+	/* WaClearSlmSpaceAtContextSwitch:skl,bxt,kbl,glk,cfl */
+	batch = gen8_emit_pipe_control(batch,
+				       PIPE_CONTROL_FLUSH_L3 |
+				       PIPE_CONTROL_STORE_DATA_INDEX |
+				       PIPE_CONTROL_CS_STALL |
+				       PIPE_CONTROL_QW_WRITE,
+				       LRC_PPHWSP_SCRATCH_ADDR);
+
 	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
 
 	/* WaMediaPoolStateCmdInWABB:bxt,glk */
@@ -4416,9 +4424,11 @@ intel_execlists_create_virtual(struct i915_gem_context *ctx,
 	ve->base.gt = siblings[0]->gt;
 	ve->base.uncore = siblings[0]->uncore;
 	ve->base.id = -1;
+
 	ve->base.class = OTHER_CLASS;
 	ve->base.uabi_class = I915_ENGINE_CLASS_INVALID;
 	ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
+	ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL;
 
 	/*
 	 * The decision on whether to submit a request using semaphores
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a47d5a7c32c9..93026217c121 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -1413,14 +1413,6 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	int len;
 	u32 *cs;
 
-	flags |= MI_MM_SPACE_GTT;
-	if (IS_HASWELL(i915))
-		/* These flags are for resource streamer on HSW+ */
-		flags |= HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN;
-	else
-		/* We need to save the extended state for powersaving modes */
-		flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN;
-
 	len = 4;
 	if (IS_GEN(i915, 7))
 		len += 2 + (num_engines ? 4 * num_engines + 6 : 0);
@@ -1589,22 +1581,21 @@ static int switch_context(struct i915_request *rq)
 	}
 
 	if (ce->state) {
-		u32 hw_flags;
+		u32 flags;
 
 		GEM_BUG_ON(rq->engine->id != RCS0);
 
-		/*
-		 * The kernel context(s) is treated as pure scratch and is not
-		 * expected to retain any state (as we sacrifice it during
-		 * suspend and on resume it may be corrupted). This is ok,
-		 * as nothing actually executes using the kernel context; it
-		 * is purely used for flushing user contexts.
-		 */
-		hw_flags = 0;
-		if (i915_gem_context_is_kernel(rq->gem_context))
-			hw_flags = MI_RESTORE_INHIBIT;
+		/* For resource streamer on HSW+ and power context elsewhere */
+		BUILD_BUG_ON(HSW_MI_RS_SAVE_STATE_EN != MI_SAVE_EXT_STATE_EN);
+		BUILD_BUG_ON(HSW_MI_RS_RESTORE_STATE_EN != MI_RESTORE_EXT_STATE_EN);
+
+		flags = MI_SAVE_EXT_STATE_EN | MI_MM_SPACE_GTT;
+		if (!i915_gem_context_is_kernel(rq->gem_context))
+			flags |= MI_RESTORE_EXT_STATE_EN;
+		else
+			flags |= MI_RESTORE_INHIBIT;
 
-		ret = mi_set_context(rq, hw_flags);
+		ret = mi_set_context(rq, flags);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e29bc137e7ba..21aa08f55811 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1660,8 +1660,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 	(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
 
 /* WaRsDisableCoarsePowerGating:skl,cnl */
-#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
+#define NEEDS_WaRsDisableCoarsePowerGating(dev_priv)			\
+	(IS_CANNONLAKE(dev_priv) ||					\
+	 IS_SKL_GT3(dev_priv) ||					\
+	 IS_SKL_GT4(dev_priv))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6239a9adbf14..c083f516fd35 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3304,7 +3304,7 @@ void i915_ggtt_disable_guc(struct i915_ggtt *ggtt)
 
 static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 {
-	struct i915_vma *vma, *vn;
+	struct i915_vma *vma;
 	bool flush = false;
 	int open;
 
@@ -3319,15 +3319,12 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 	open = atomic_xchg(&ggtt->vm.open, 0);
 
 	/* clflush objects bound into the GGTT and rebind them. */
-	list_for_each_entry_safe(vma, vn, &ggtt->vm.bound_list, vm_link) {
+	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
 		if (!i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND))
 			continue;
 
-		if (!__i915_vma_unbind(vma))
-			continue;
-
 		clear_bit(I915_VMA_GLOBAL_BIND_BIT, __i915_vma_flags(vma));
 		WARN_ON(i915_vma_bind(vma,
 				      obj ? obj->cache_level : 0,
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 6f09aa0be80a..d6d2e6fb8674 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -1074,12 +1074,17 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
 
-	if (!is_igp(i915))
+	if (!is_igp(i915)) {
 		pmu->name = kasprintf(GFP_KERNEL,
-				      "i915-%s",
+				      "i915_%s",
 				      dev_name(i915->drm.dev));
-	else
+		if (pmu->name) {
+			/* tools/perf reserves colons as special. */
+			strreplace((char *)pmu->name, ':', '_');
+		}
+	} else {
 		pmu->name = "i915";
+	}
 	if (!pmu->name)
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4fd3d76db346..094011b8f64d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4177,7 +4177,13 @@ enum {
 #define  CPSSUNIT_CLKGATE_DIS		REG_BIT(9)
 
 #define UNSLICE_UNIT_LEVEL_CLKGATE	_MMIO(0x9434)
-#define  VFUNIT_CLKGATE_DIS		(1 << 20)
+#define   VFUNIT_CLKGATE_DIS		REG_BIT(20)
+#define   HSUNIT_CLKGATE_DIS		REG_BIT(8)
+#define   VSUNIT_CLKGATE_DIS		REG_BIT(3)
+
+#define UNSLICE_UNIT_LEVEL_CLKGATE2	_MMIO(0x94e4)
+#define   VSUNIT_CLKGATE_DIS_TGL	REG_BIT(19)
+#define   PSDUNIT_CLKGATE_DIS		REG_BIT(5)
 
 #define INF_UNIT_LEVEL_CLKGATE		_MMIO(0x9560)
 #define   CGPSF_CLKGATE_DIS		(1 << 3)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 75ae6f495161..86379eddc908 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6565,6 +6565,17 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv)
 	/* WaEnable32PlaneMode:icl */
 	I915_WRITE(GEN9_CSFE_CHICKEN1_RCS,
 		   _MASKED_BIT_ENABLE(GEN11_ENABLE_32_PLANE_MODE));
+
+	/*
+	 * Wa_1408615072:icl,ehl  (vsunit)
+	 * Wa_1407596294:icl,ehl  (hsunit)
+	 */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE,
+			 0, VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
+
+	/* Wa_1407352427:icl,ehl */
+	intel_uncore_rmw(&dev_priv->uncore, UNSLICE_UNIT_LEVEL_CLKGATE2,
+			 0, PSDUNIT_CLKGATE_DIS);
 }
 
 static void tgl_init_clock_gating(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/selftests/i915_random.h b/drivers/gpu/drm/i915/selftests/i915_random.h
index 35cc69a3a1b9..05364eca20f7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_random.h
+++ b/drivers/gpu/drm/i915/selftests/i915_random.h
@@ -25,6 +25,7 @@
 #ifndef __I915_SELFTESTS_RANDOM_H__
 #define __I915_SELFTESTS_RANDOM_H__
 
+#include <linux/math64.h>
 #include <linux/random.h>
 
 #include "../i915_selftest.h"