20 files changed, 188 insertions, 95 deletions

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index b8c5f8934dbd..a1f2411aa21b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -294,7 +294,7 @@ extra-$(CONFIG_DRM_I915_WERROR) += \
 		$(shell cd $(srctree)/$(src) && find * -name '*.h')))
 
 quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@)
-      cmd_hdrtest = $(CC) $(c_flags) -S -o /dev/null -x c /dev/null -include $<; touch $@
+      cmd_hdrtest = $(CC) $(filter-out $(CFLAGS_GCOV), $(c_flags)) -S -o /dev/null -x c /dev/null -include $<; touch $@
 
 $(obj)/%.hdrtest: $(src)/%.h FORCE
 	$(call if_changed_dep,hdrtest)
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 21561acfa3ac..46c40db992dd 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -4466,13 +4466,19 @@ static void icl_dbuf_disable(struct drm_i915_private *dev_priv)
 
 static void icl_mbus_init(struct drm_i915_private *dev_priv)
 {
-	u32 val;
+	u32 mask, val;
 
-	val = MBUS_ABOX_BT_CREDIT_POOL1(16) |
-	      MBUS_ABOX_BT_CREDIT_POOL2(16) |
-	      MBUS_ABOX_B_CREDIT(1) |
-	      MBUS_ABOX_BW_CREDIT(1);
+	mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK |
+		MBUS_ABOX_BT_CREDIT_POOL2_MASK |
+		MBUS_ABOX_B_CREDIT_MASK |
+		MBUS_ABOX_BW_CREDIT_MASK;
 
+	val = I915_READ(MBUS_ABOX_CTL);
+	val &= ~mask;
+	val |= MBUS_ABOX_BT_CREDIT_POOL1(16) |
+		MBUS_ABOX_BT_CREDIT_POOL2(16) |
+		MBUS_ABOX_B_CREDIT(1) |
+		MBUS_ABOX_BW_CREDIT(1);
 	I915_WRITE(MBUS_ABOX_CTL, val);
 }
 
@@ -4968,8 +4974,21 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv)
 		I915_WRITE(BW_BUDDY1_CTL, BW_BUDDY_DISABLE);
 		I915_WRITE(BW_BUDDY2_CTL, BW_BUDDY_DISABLE);
 	} else {
+		u32 val;
+
 		I915_WRITE(BW_BUDDY1_PAGE_MASK, table[i].page_mask);
 		I915_WRITE(BW_BUDDY2_PAGE_MASK, table[i].page_mask);
+
+		/* Wa_22010178259:tgl */
+		val = I915_READ(BW_BUDDY1_CTL);
+		val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+		val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+		I915_WRITE(BW_BUDDY1_CTL, val);
+
+		val = I915_READ(BW_BUDDY2_CTL);
+		val &= ~BW_BUDDY_TLB_REQ_TIMER_MASK;
+		val |= REG_FIELD_PREP(BW_BUDDY_TLB_REQ_TIMER_MASK, 0x8);
+		I915_WRITE(BW_BUDDY2_CTL, val);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 89c9cf5f38d2..83025052c965 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -852,10 +852,12 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
-	if (!crtc_state->has_psr)
+	if (!CAN_PSR(dev_priv) || dev_priv->psr.dp != intel_dp)
 		return;
 
-	if (WARN_ON(!CAN_PSR(dev_priv)))
+	dev_priv->psr.force_mode_changed = false;
+
+	if (!crtc_state->has_psr)
 		return;
 
 	WARN_ON(dev_priv->drrs.dp);
@@ -1009,6 +1011,8 @@ void intel_psr_update(struct intel_dp *intel_dp,
 	if (!CAN_PSR(dev_priv) || READ_ONCE(psr->dp) != intel_dp)
 		return;
 
+	dev_priv->psr.force_mode_changed = false;
+
 	mutex_lock(&dev_priv->psr.lock);
 
 	enable = crtc_state->has_psr && psr_global_enabled(psr->debug);
@@ -1534,7 +1538,7 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 	struct drm_crtc_state *crtc_state;
 
 	if (!CAN_PSR(dev_priv) || !new_state->crtc ||
-	    dev_priv->psr.initially_probed)
+	    !dev_priv->psr.force_mode_changed)
 		return;
 
 	intel_connector = to_intel_connector(connector);
@@ -1545,5 +1549,18 @@ void intel_psr_atomic_check(struct drm_connector *connector,
 	crtc_state = drm_atomic_get_new_crtc_state(new_state->state,
 						   new_state->crtc);
 	crtc_state->mode_changed = true;
-	dev_priv->psr.initially_probed = true;
+}
+
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp)
+{
+	struct drm_i915_private *dev_priv;
+
+	if (!intel_dp)
+		return;
+
+	dev_priv = dp_to_i915(intel_dp);
+	if (!CAN_PSR(dev_priv) || intel_dp != dev_priv->psr.dp)
+		return;
+
+	dev_priv->psr.force_mode_changed = true;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_psr.h b/drivers/gpu/drm/i915/display/intel_psr.h
index c58a1d438808..274fc6bb6221 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.h
+++ b/drivers/gpu/drm/i915/display/intel_psr.h
@@ -40,5 +40,6 @@ bool intel_psr_enabled(struct intel_dp *intel_dp);
 void intel_psr_atomic_check(struct drm_connector *connector,
 			    struct drm_connector_state *old_state,
 			    struct drm_connector_state *new_state);
+void intel_psr_set_force_mode_changed(struct intel_dp *intel_dp);
 
 #endif /* __INTEL_PSR_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index 35985218bd85..5da9f9e534b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -225,6 +225,7 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 
 		/* But keep the pointer alive for RCU-protected lookups */
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
+		cond_resched();
 	}
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
index f7e4b39c734f..59b387ade49c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shrinker.c
@@ -256,8 +256,7 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *i915)
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		freed = i915_gem_shrink(i915, -1UL, NULL,
 					I915_SHRINK_BOUND |
-					I915_SHRINK_UNBOUND |
-					I915_SHRINK_ACTIVE);
+					I915_SHRINK_UNBOUND);
 	}
 
 	return freed;
@@ -336,7 +335,6 @@ i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
 	freed_pages = 0;
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
 		freed_pages += i915_gem_shrink(i915, -1UL, NULL,
-					       I915_SHRINK_ACTIVE |
 					       I915_SHRINK_BOUND |
 					       I915_SHRINK_UNBOUND |
 					       I915_SHRINK_WRITEBACK);
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index ef7c74cff28a..43912e9b683d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -570,7 +570,7 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 
 	obj = i915_gem_object_create_internal(i915, size);
 	if (IS_ERR(obj))
-		return PTR_ERR(obj);
+		return false;
 
 	mmo = mmap_offset_attach(obj, I915_MMAP_OFFSET_GTT, NULL);
 	i915_gem_object_put(obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index 8a5054f21bf8..24c99d0838af 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -147,24 +147,32 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 			fence = i915_active_fence_get(&tl->last_request);
 			if (fence) {
+				mutex_unlock(&tl->mutex);
+
 				timeout = dma_fence_wait_timeout(fence,
 								 interruptible,
 								 timeout);
 				dma_fence_put(fence);
+
+				/* Retirement is best effort */
+				if (!mutex_trylock(&tl->mutex)) {
+					active_count++;
+					goto out_active;
+				}
 			}
 		}
 
 		if (!retire_requests(tl) || flush_submission(gt))
 			active_count++;
+		mutex_unlock(&tl->mutex);
 
-		spin_lock(&timelines->lock);
+out_active:	spin_lock(&timelines->lock);
 
-		/* Resume iteration after dropping lock */
+		/* Resume list iteration after reacquiring spinlock */
 		list_safe_reset_next(tl, tn, link);
 		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
 
-		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 4e292d4bf7b9..173a7f2d109f 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -575,24 +575,19 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void tgl_ctx_workarounds_init(struct intel_engine_cs *engine,
 				     struct i915_wa_list *wal)
 {
-	u32 val;
-
 	/* Wa_1409142259:tgl */
 	WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 			  GEN12_DISABLE_CPS_AWARE_COLOR_PIPE);
 
-	/* Wa_1604555607:tgl */
-	val = intel_uncore_read(engine->uncore, FF_MODE2);
-	val &= ~FF_MODE2_TDS_TIMER_MASK;
-	val |= FF_MODE2_TDS_TIMER_128;
 	/*
-	 * FIXME: FF_MODE2 register is not readable till TGL B0. We can
-	 * enable verification of WA from the later steppings, which enables
-	 * the read of FF_MODE2.
+	 * Wa_1604555607:gen12 and Wa_1608008084:gen12
+	 * FF_MODE2 register will return the wrong value when read. The default
+	 * value for this register is zero for all fields and there are no bit
+	 * masks. So instead of doing a RMW we should just write the TDS timer
+	 * value for Wa_1604555607.
 	 */
-	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK, val,
-	       IS_TGL_REVID(engine->i915, TGL_REVID_A0, TGL_REVID_A0) ? 0 :
-			    FF_MODE2_TDS_TIMER_MASK);
+	wa_add(wal, FF_MODE2, FF_MODE2_TDS_TIMER_MASK,
+	       FF_MODE2_TDS_TIMER_128, 0);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 2477a1e5a166..ae139f0877ae 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -151,12 +151,12 @@ static void dmabuf_gem_object_free(struct kref *kref)
 			dmabuf_obj = container_of(pos,
 					struct intel_vgpu_dmabuf_obj, list);
 			if (dmabuf_obj == obj) {
+				list_del(pos);
 				intel_gvt_hypervisor_put_vfio_device(vgpu);
 				idr_remove(&vgpu->object_idr,
 					   dmabuf_obj->dmabuf_id);
 				kfree(dmabuf_obj->info);
 				kfree(dmabuf_obj);
-				list_del(pos);
 				break;
 			}
 		}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 85bd9bf4f6ee..487af6ea9972 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -560,9 +560,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 
 		intel_vgpu_reset_mmio(vgpu, dmlr);
 		populate_pvinfo_page(vgpu);
-		intel_vgpu_reset_display(vgpu);
 
 		if (dmlr) {
+			intel_vgpu_reset_display(vgpu);
 			intel_vgpu_reset_cfg_space(vgpu);
 			/* only reset the failsafe mode when dmlr reset */
 			vgpu->failsafe = false;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f7385abdd74b..8410330ce4f0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -56,6 +56,7 @@
 #include "display/intel_hotplug.h"
 #include "display/intel_overlay.h"
 #include "display/intel_pipe_crc.h"
+#include "display/intel_psr.h"
 #include "display/intel_sprite.h"
 #include "display/intel_vga.h"
 
@@ -330,6 +331,8 @@ static int i915_driver_modeset_probe(struct drm_i915_private *i915)
 
 	intel_init_ipc(i915);
 
+	intel_psr_set_force_mode_changed(i915->psr.dp);
+
 	return 0;
 
 cleanup_gem:
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 077af22b8340..810e3ccd56ec 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -505,7 +505,7 @@ struct i915_psr {
 	bool dc3co_enabled;
 	u32 dc3co_exit_delay;
 	struct delayed_work idle_work;
-	bool initially_probed;
+	bool force_mode_changed;
 };
 
 #define QUIRK_LVDS_SSC_DISABLE (1<<1)
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 83f01401b8b5..f631f6d21127 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -437,7 +437,7 @@ static const struct intel_device_info snb_m_gt2_info = {
 	.has_rc6 = 1, \
 	.has_rc6p = 1, \
 	.has_rps = true, \
-	.ppgtt_type = INTEL_PPGTT_FULL, \
+	.ppgtt_type = INTEL_PPGTT_ALIASING, \
 	.ppgtt_size = 31, \
 	IVB_PIPE_OFFSETS, \
 	IVB_CURSOR_OFFSETS, \
@@ -494,7 +494,7 @@ static const struct intel_device_info vlv_info = {
 	.has_rps = true,
 	.display.has_gmch = 1,
 	.display.has_hotplug = 1,
-	.ppgtt_type = INTEL_PPGTT_FULL,
+	.ppgtt_type = INTEL_PPGTT_ALIASING,
 	.ppgtt_size = 31,
 	.has_snoop = true,
 	.has_coherent_ggtt = false,
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 0f556d80ba36..3b6b913bd27a 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1954,9 +1954,10 @@ out:
 	return i915_vma_get(oa_bo->vma);
 }
 
-static int emit_oa_config(struct i915_perf_stream *stream,
-			  struct i915_oa_config *oa_config,
-			  struct intel_context *ce)
+static struct i915_request *
+emit_oa_config(struct i915_perf_stream *stream,
+	       struct i915_oa_config *oa_config,
+	       struct intel_context *ce)
 {
 	struct i915_request *rq;
 	struct i915_vma *vma;
@@ -1964,7 +1965,7 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 
 	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+		return ERR_CAST(vma);
 
 	err = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH);
 	if (err)
@@ -1989,13 +1990,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
+	if (err)
+		goto err_add_request;
+
+	i915_request_get(rq);
 err_add_request:
 	i915_request_add(rq);
 err_vma_unpin:
 	i915_vma_unpin(vma);
 err_vma_put:
 	i915_vma_put(vma);
-	return err;
+	return err ? ERR_PTR(err) : rq;
 }
 
 static struct intel_context *oa_context(struct i915_perf_stream *stream)
@@ -2003,7 +2008,8 @@ static struct intel_context *oa_context(struct i915_perf_stream *stream)
 	return stream->pinned_ctx ?: stream->engine->kernel_context;
 }
 
-static int hsw_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+hsw_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
@@ -2406,7 +2412,8 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
 }
 
-static int gen8_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2448,7 +2455,7 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
@@ -2460,7 +2467,8 @@ static u32 oag_report_ctx_switches(const struct i915_perf_stream *stream)
 			     0 : GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS);
 }
 
-static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+static struct i915_request *
+gen12_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 	struct i915_oa_config *oa_config = stream->oa_config;
@@ -2491,7 +2499,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 */
 	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
-		return ret;
+		return ERR_PTR(ret);
 
 	/*
 	 * For Gen12, performance counters are context
@@ -2501,7 +2509,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	if (stream->ctx) {
 		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
-			return ret;
+			return ERR_PTR(ret);
 	}
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
@@ -2696,6 +2704,20 @@ static const struct i915_perf_stream_ops i915_oa_stream_ops = {
 	.read = i915_oa_read,
 };
 
+static int i915_perf_stream_enable_sync(struct i915_perf_stream *stream)
+{
+	struct i915_request *rq;
+
+	rq = stream->perf->ops.enable_metric_set(stream);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return 0;
+}
+
 /**
  * i915_oa_stream_init - validate combined props for OA stream and init
  * @stream: An i915 perf stream
@@ -2829,7 +2851,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 	stream->ops = &i915_oa_stream_ops;
 	perf->exclusive_stream = stream;
 
-	ret = perf->ops.enable_metric_set(stream);
+	ret = i915_perf_stream_enable_sync(stream);
 	if (ret) {
 		DRM_DEBUG("Unable to enable metric set\n");
 		goto err_enable;
@@ -3147,7 +3169,7 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		return -EINVAL;
 
 	if (config != stream->oa_config) {
-		int err;
+		struct i915_request *rq;
 
 		/*
 		 * If OA is bound to a specific context, emit the
@@ -3158,11 +3180,13 @@ static long i915_perf_config_locked(struct i915_perf_stream *stream,
 		 * When set globally, we use a low priority kernel context,
 		 * so it will effectively take effect when idle.
 		 */
-		err = emit_oa_config(stream, config, oa_context(stream));
-		if (err == 0)
+		rq = emit_oa_config(stream, config, oa_context(stream));
+		if (!IS_ERR(rq)) {
 			config = xchg(&stream->oa_config, config);
-		else
-			ret = err;
+			i915_request_put(rq);
+		} else {
+			ret = PTR_ERR(rq);
+		}
 	}
 
 	i915_oa_config_put(config);
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index 45e581455f5d..a0e22f00f6cf 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -339,7 +339,8 @@ struct i915_oa_ops {
 	 * counter reports being sampled. May apply system constraints such as
 	 * disabling EU clock gating as required.
 	 */
-	int (*enable_metric_set)(struct i915_perf_stream *stream);
+	struct i915_request *
+		(*enable_metric_set)(struct i915_perf_stream *stream);
 
 	/**
 	 * @disable_metric_set: Remove system constraints associated with using
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index ec0299490dd4..aa729d04abe2 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -822,11 +822,6 @@ static ssize_t i915_pmu_event_show(struct device *dev,
 	return sprintf(buf, "config=0x%lx\n", eattr->val);
 }
 
-static struct attribute_group i915_pmu_events_attr_group = {
-	.name = "events",
-	/* Patch in attrs at runtime. */
-};
-
 static ssize_t
 i915_pmu_get_attr_cpumask(struct device *dev,
 			  struct device_attribute *attr,
@@ -846,13 +841,6 @@ static const struct attribute_group i915_pmu_cpumask_attr_group = {
 	.attrs = i915_cpumask_attrs,
 };
 
-static const struct attribute_group *i915_pmu_attr_groups[] = {
-	&i915_pmu_format_attr_group,
-	&i915_pmu_events_attr_group,
-	&i915_pmu_cpumask_attr_group,
-	NULL
-};
-
 #define __event(__config, __name, __unit) \
 { \
 	.config = (__config), \
@@ -1026,23 +1014,23 @@ err_alloc:
 
 static void free_event_attributes(struct i915_pmu *pmu)
 {
-	struct attribute **attr_iter = i915_pmu_events_attr_group.attrs;
+	struct attribute **attr_iter = pmu->events_attr_group.attrs;
 
 	for (; *attr_iter; attr_iter++)
 		kfree((*attr_iter)->name);
 
-	kfree(i915_pmu_events_attr_group.attrs);
+	kfree(pmu->events_attr_group.attrs);
 	kfree(pmu->i915_attr);
 	kfree(pmu->pmu_attr);
 
-	i915_pmu_events_attr_group.attrs = NULL;
+	pmu->events_attr_group.attrs = NULL;
 	pmu->i915_attr = NULL;
 	pmu->pmu_attr = NULL;
 }
 
 static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
 
 	GEM_BUG_ON(!pmu->base.event_init);
 
@@ -1055,7 +1043,7 @@ static int i915_pmu_cpu_online(unsigned int cpu, struct hlist_node *node)
 
 static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 {
-	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), node);
+	struct i915_pmu *pmu = hlist_entry_safe(node, typeof(*pmu), cpuhp.node);
 	unsigned int target;
 
 	GEM_BUG_ON(!pmu->base.event_init);
@@ -1072,8 +1060,6 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
-static enum cpuhp_state cpuhp_slot = CPUHP_INVALID;
-
 static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
 {
 	enum cpuhp_state slot;
@@ -1087,21 +1073,22 @@ static int i915_pmu_register_cpuhp_state(struct i915_pmu *pmu)
 		return ret;
 
 	slot = ret;
-	ret = cpuhp_state_add_instance(slot, &pmu->node);
+	ret = cpuhp_state_add_instance(slot, &pmu->cpuhp.node);
 	if (ret) {
 		cpuhp_remove_multi_state(slot);
 		return ret;
 	}
 
-	cpuhp_slot = slot;
+	pmu->cpuhp.slot = slot;
 	return 0;
 }
 
 static void i915_pmu_unregister_cpuhp_state(struct i915_pmu *pmu)
 {
-	WARN_ON(cpuhp_slot == CPUHP_INVALID);
-	WARN_ON(cpuhp_state_remove_instance(cpuhp_slot, &pmu->node));
-	cpuhp_remove_multi_state(cpuhp_slot);
+	WARN_ON(pmu->cpuhp.slot == CPUHP_INVALID);
+	WARN_ON(cpuhp_state_remove_instance(pmu->cpuhp.slot, &pmu->cpuhp.node));
+	cpuhp_remove_multi_state(pmu->cpuhp.slot);
+	pmu->cpuhp.slot = CPUHP_INVALID;
 }
 
 static bool is_igp(struct drm_i915_private *i915)
@@ -1118,6 +1105,13 @@ static bool is_igp(struct drm_i915_private *i915)
 void i915_pmu_register(struct drm_i915_private *i915)
 {
 	struct i915_pmu *pmu = &i915->pmu;
+	const struct attribute_group *attr_groups[] = {
+		&i915_pmu_format_attr_group,
+		&pmu->events_attr_group,
+		&i915_pmu_cpumask_attr_group,
+		NULL
+	};
+
 	int ret = -ENOMEM;
 
 	if (INTEL_GEN(i915) <= 2) {
@@ -1128,6 +1122,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	spin_lock_init(&pmu->lock);
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
+	pmu->cpuhp.slot = CPUHP_INVALID;
 
 	if (!is_igp(i915)) {
 		pmu->name = kasprintf(GFP_KERNEL,
@@ -1143,11 +1138,16 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	if (!pmu->name)
 		goto err;
 
-	i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
-	if (!i915_pmu_events_attr_group.attrs)
+	pmu->events_attr_group.name = "events";
+	pmu->events_attr_group.attrs = create_event_attributes(pmu);
+	if (!pmu->events_attr_group.attrs)
 		goto err_name;
 
-	pmu->base.attr_groups	= i915_pmu_attr_groups;
+	pmu->base.attr_groups = kmemdup(attr_groups, sizeof(attr_groups),
+					GFP_KERNEL);
+	if (!pmu->base.attr_groups)
+		goto err_attr;
+
 	pmu->base.task_ctx_nr	= perf_invalid_context;
 	pmu->base.event_init	= i915_pmu_event_init;
 	pmu->base.add		= i915_pmu_event_add;
@@ -1159,7 +1159,7 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 	ret = perf_pmu_register(&pmu->base, pmu->name, -1);
 	if (ret)
-		goto err_attr;
+		goto err_groups;
 
 	ret = i915_pmu_register_cpuhp_state(pmu);
 	if (ret)
@@ -1169,6 +1169,8 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 err_unreg:
 	perf_pmu_unregister(&pmu->base);
+err_groups:
+	kfree(pmu->base.attr_groups);
 err_attr:
 	pmu->base.event_init = NULL;
 	free_event_attributes(pmu);
@@ -1194,6 +1196,7 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	perf_pmu_unregister(&pmu->base);
 	pmu->base.event_init = NULL;
+	kfree(pmu->base.attr_groups);
 	if (!is_igp(i915))
 		kfree(pmu->name);
 	free_event_attributes(pmu);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 6c1647c5daf2..f1d6cad0d7d5 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -39,9 +39,12 @@ struct i915_pmu_sample {
 
 struct i915_pmu {
 	/**
-	 * @node: List node for CPU hotplug handling.
+	 * @cpuhp: Struct used for CPU hotplug handling.
 	 */
-	struct hlist_node node;
+	struct {
+		struct hlist_node node;
+		enum cpuhp_state slot;
+	} cpuhp;
 	/**
 	 * @base: PMU base.
 	 */
@@ -105,6 +108,10 @@ struct i915_pmu {
 	 */
 	ktime_t sleep_last;
 	/**
+	 * @events_attr_group: Device events attribute group.
+	 */
+	struct attribute_group events_attr_group;
+	/**
 	 * @i915_attr: Memory block holding device attributes.
 	 */
 	void *i915_attr;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6cc55c103f67..3575fd30756b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7757,6 +7757,7 @@ enum {
 #define BW_BUDDY1_CTL			_MMIO(0x45140)
 #define BW_BUDDY2_CTL			_MMIO(0x45150)
 #define   BW_BUDDY_DISABLE		REG_BIT(31)
+#define   BW_BUDDY_TLB_REQ_TIMER_MASK	REG_GENMASK(21, 16)
 
 #define BW_BUDDY1_PAGE_MASK		_MMIO(0x45144)
 #define BW_BUDDY2_PAGE_MASK		_MMIO(0x45154)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f56b046a32de..dcaa85a91090 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -275,7 +275,7 @@ bool i915_request_retire(struct i915_request *rq)
 	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
-	list_del(&rq->link);
+	list_del_rcu(&rq->link);
 
 	intel_context_exit(rq->context);
 	intel_context_unpin(rq->context);
@@ -721,6 +721,8 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
 	rq->infix = rq->ring->emit; /* end of header; start of user payload */
 
 	intel_context_mark_active(ce);
+	list_add_tail_rcu(&rq->link, &tl->requests);
+
 	return rq;
 
 err_unwind:
@@ -777,13 +779,23 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 	GEM_BUG_ON(i915_request_timeline(rq) ==
 		   rcu_access_pointer(signal->timeline));
 
+	if (i915_request_started(signal))
+		return 0;
+
 	fence = NULL;
 	rcu_read_lock();
 	spin_lock_irq(&signal->lock);
-	if (!i915_request_started(signal) &&
-	    !list_is_first(&signal->link,
-			   &rcu_dereference(signal->timeline)->requests)) {
-		struct i915_request *prev = list_prev_entry(signal, link);
+	do {
+		struct list_head *pos = READ_ONCE(signal->link.prev);
+		struct i915_request *prev;
+
+		/* Confirm signal has not been retired, the link is valid */
+		if (unlikely(i915_request_started(signal)))
+			break;
+
+		/* Is signal the earliest request on its timeline? */
+		if (pos == &rcu_dereference(signal->timeline)->requests)
+			break;
 
 		/*
 		 * Peek at the request before us in the timeline. That
@@ -791,13 +803,18 @@ i915_request_await_start(struct i915_request *rq, struct i915_request *signal)
 		 * after acquiring a reference to it, confirm that it is
 		 * still part of the signaler's timeline.
 		 */
-		if (i915_request_get_rcu(prev)) {
-			if (list_next_entry(prev, link) == signal)
-				fence = &prev->fence;
-			else
-				i915_request_put(prev);
+		prev = list_entry(pos, typeof(*prev), link);
+		if (!i915_request_get_rcu(prev))
+			break;
+
+		/* After the strong barrier, confirm prev is still attached */
+		if (unlikely(READ_ONCE(prev->link.next) != &signal->link)) {
+			i915_request_put(prev);
+			break;
 		}
-	}
+
+		fence = &prev->fence;
+	} while (0);
 	spin_unlock_irq(&signal->lock);
 	rcu_read_unlock();
 	if (!fence)
@@ -1242,8 +1259,6 @@ __i915_request_add_to_timeline(struct i915_request *rq)
 							 0);
 	}
 
-	list_add_tail(&rq->link, &timeline->requests);
-
 	/*
 	 * Make sure that no request gazumped us - if it was allocated after
 	 * our i915_request_alloc() and called __i915_request_add() before