Merge tag 'drm-intel-fixes-2019-12-12' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

- Fix user reported issue #673: GPU hang on transition to idle
- Avoid corruption on the top of the screen on GLK+ by disabling FBC
- Fix non-privileged access to OA on Tigerlake
- Fix HDCP code not to touch global state when just computing commit
- Fix CI splat by saving irqstate around virtual_context_destroy
- Serialise context retirement possibly on another CPU

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191212100759.GA22260@jlahtine-desk.ger.corp.intel.com

9 files changed, 177 insertions, 148 deletions

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index c7c2b349858d..2a27fb5d7dc6 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3986,6 +3986,7 @@ static void intel_enable_ddi(struct intel_encoder *encoder,
 	if (conn_state->content_protection ==
 	    DRM_MODE_CONTENT_PROTECTION_DESIRED)
 		intel_hdcp_enable(to_intel_connector(conn_state->connector),
+				  crtc_state->cpu_transcoder,
 				  (u8)conn_state->hdcp_content_type);
 }
 
@@ -4089,7 +4090,9 @@ static void intel_ddi_update_pipe(struct intel_encoder *encoder,
 	if (conn_state->content_protection ==
 	    DRM_MODE_CONTENT_PROTECTION_DESIRED ||
 	    content_protection_type_changed)
-		intel_hdcp_enable(connector, (u8)conn_state->hdcp_content_type);
+		intel_hdcp_enable(connector,
+				  crtc_state->cpu_transcoder,
+				  (u8)conn_state->hdcp_content_type);
 }
 
 static void
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 050655a1a3d8..b05b2191b919 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -2414,9 +2414,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 
 	intel_psr_compute_config(intel_dp, pipe_config);
 
-	intel_hdcp_transcoder_config(intel_connector,
-				     pipe_config->cpu_transcoder);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
index 3111ecaeabd0..20616639b8ab 100644
--- a/drivers/gpu/drm/i915/display/intel_fbc.c
+++ b/drivers/gpu/drm/i915/display/intel_fbc.c
@@ -1284,7 +1284,7 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv)
 		return 0;
 
 	/* https://bugs.freedesktop.org/show_bug.cgi?id=108085 */
-	if (IS_GEMINILAKE(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
 		return 0;
 
 	if (IS_BROADWELL(dev_priv) || INTEL_GEN(dev_priv) >= 9)
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index f1f41ca8402b..a448815d8fc2 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -1821,23 +1821,6 @@ enum mei_fw_tc intel_get_mei_fw_tc(enum transcoder cpu_transcoder)
 	}
 }
 
-void intel_hdcp_transcoder_config(struct intel_connector *connector,
-				  enum transcoder cpu_transcoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	struct intel_hdcp *hdcp = &connector->hdcp;
-
-	if (!hdcp->shim)
-		return;
-
-	if (INTEL_GEN(dev_priv) >= 12) {
-		mutex_lock(&hdcp->mutex);
-		hdcp->cpu_transcoder = cpu_transcoder;
-		hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder);
-		mutex_unlock(&hdcp->mutex);
-	}
-}
-
 static inline int initialize_hdcp_port_data(struct intel_connector *connector,
 					    const struct intel_hdcp_shim *shim)
 {
@@ -1959,8 +1942,10 @@ int intel_hdcp_init(struct intel_connector *connector,
 	return 0;
 }
 
-int intel_hdcp_enable(struct intel_connector *connector, u8 content_type)
+int intel_hdcp_enable(struct intel_connector *connector,
+		      enum transcoder cpu_transcoder, u8 content_type)
 {
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	struct intel_hdcp *hdcp = &connector->hdcp;
 	unsigned long check_link_interval = DRM_HDCP_CHECK_PERIOD_MS;
 	int ret = -EINVAL;
@@ -1972,6 +1957,11 @@ int intel_hdcp_enable(struct intel_connector *connector, u8 content_type)
 	WARN_ON(hdcp->value == DRM_MODE_CONTENT_PROTECTION_ENABLED);
 	hdcp->content_type = content_type;
 
+	if (INTEL_GEN(dev_priv) >= 12) {
+		hdcp->cpu_transcoder = cpu_transcoder;
+		hdcp->port_data.fw_tc = intel_get_mei_fw_tc(cpu_transcoder);
+	}
+
 	/*
 	 * Considering that HDCP2.2 is more secure than HDCP1.4, If the setup
 	 * is capable of HDCP2.2, it is preferred to use HDCP2.2.
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.h b/drivers/gpu/drm/i915/display/intel_hdcp.h
index 41c1053d9e38..f3c3272e712a 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.h
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.h
@@ -21,11 +21,10 @@ enum transcoder;
 void intel_hdcp_atomic_check(struct drm_connector *connector,
 			     struct drm_connector_state *old_state,
 			     struct drm_connector_state *new_state);
-void intel_hdcp_transcoder_config(struct intel_connector *connector,
-				  enum transcoder cpu_transcoder);
 int intel_hdcp_init(struct intel_connector *connector,
 		    const struct intel_hdcp_shim *hdcp_shim);
-int intel_hdcp_enable(struct intel_connector *connector, u8 content_type);
+int intel_hdcp_enable(struct intel_connector *connector,
+		      enum transcoder cpu_transcoder, u8 content_type);
 int intel_hdcp_disable(struct intel_connector *connector);
 bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port);
 bool intel_hdcp_capable(struct intel_connector *connector);
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index f6f5312205c4..f56fffc474fa 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2489,9 +2489,6 @@ int intel_hdmi_compute_config(struct intel_encoder *encoder,
 		return -EINVAL;
 	}
 
-	intel_hdcp_transcoder_config(intel_hdmi->attached_connector,
-				     pipe_config->cpu_transcoder);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 9fdefbdc3546..75dd0e0367b7 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -845,12 +845,6 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 	}
 }
 
-static void unwind_wa_tail(struct i915_request *rq)
-{
-	rq->tail = intel_ring_wrap(rq->ring, rq->wa_tail - WA_TAIL_BYTES);
-	assert_ring_tail_valid(rq->ring, rq->tail);
-}
-
 static struct i915_request *
 __unwind_incomplete_requests(struct intel_engine_cs *engine)
 {
@@ -863,12 +857,10 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine)
 	list_for_each_entry_safe_reverse(rq, rn,
 					 &engine->active.requests,
 					 sched.link) {
-
 		if (i915_request_completed(rq))
 			continue; /* XXX */
 
 		__i915_request_unsubmit(rq);
-		unwind_wa_tail(rq);
 
 		/*
 		 * Push the request back into the queue for later resubmission.
@@ -1161,13 +1153,29 @@ execlists_schedule_out(struct i915_request *rq)
 	i915_request_put(rq);
 }
 
-static u64 execlists_update_context(const struct i915_request *rq)
+static u64 execlists_update_context(struct i915_request *rq)
 {
 	struct intel_context *ce = rq->hw_context;
-	u64 desc;
+	u64 desc = ce->lrc_desc;
+	u32 tail;
 
-	ce->lrc_reg_state[CTX_RING_TAIL] =
-		intel_ring_set_tail(rq->ring, rq->tail);
+	/*
+	 * WaIdleLiteRestore:bdw,skl
+	 *
+	 * We should never submit the context with the same RING_TAIL twice
+	 * just in case we submit an empty ring, which confuses the HW.
+	 *
+	 * We append a couple of NOOPs (gen8_emit_wa_tail) after the end of
+	 * the normal request to be able to always advance the RING_TAIL on
+	 * subsequent resubmissions (for lite restore). Should that fail us,
+	 * and we try and submit the same tail again, force the context
+	 * reload.
+	 */
+	tail = intel_ring_set_tail(rq->ring, rq->tail);
+	if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+		desc |= CTX_DESC_FORCE_RESTORE;
+	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
+	rq->tail = rq->wa_tail;
 
 	/*
 	 * Make sure the context image is complete before we submit it to HW.
@@ -1186,13 +1194,11 @@ static u64 execlists_update_context(const struct i915_request *rq)
 	 */
 	mb();
 
-	desc = ce->lrc_desc;
-	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
-
 	/* Wa_1607138340:tgl */
 	if (IS_TGL_REVID(rq->i915, TGL_REVID_A0, TGL_REVID_A0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 
+	ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE;
 	return desc;
 }
 
@@ -1703,16 +1709,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 
 				return;
 			}
-
-			/*
-			 * WaIdleLiteRestore:bdw,skl
-			 * Apply the wa NOOPs to prevent
-			 * ring:HEAD == rq:TAIL as we resubmit the
-			 * request. See gen8_emit_fini_breadcrumb() for
-			 * where we prepare the padding after the
-			 * end of the request.
-			 */
-			last->tail = last->wa_tail;
 		}
 	}
 
@@ -4120,17 +4116,18 @@ static void virtual_context_destroy(struct kref *kref)
 	for (n = 0; n < ve->num_siblings; n++) {
 		struct intel_engine_cs *sibling = ve->siblings[n];
 		struct rb_node *node = &ve->nodes[sibling->id].rb;
+		unsigned long flags;
 
 		if (RB_EMPTY_NODE(node))
 			continue;
 
-		spin_lock_irq(&sibling->active.lock);
+		spin_lock_irqsave(&sibling->active.lock, flags);
 
 		/* Detachment is lazily performed in the execlists tasklet */
 		if (!RB_EMPTY_NODE(node))
 			rb_erase_cached(node, &sibling->execlists.virtual);
 
-		spin_unlock_irq(&sibling->active.lock);
+		spin_unlock_irqrestore(&sibling->active.lock, flags);
 	}
 	GEM_BUG_ON(__tasklet_is_scheduled(&ve->base.execlists.tasklet));
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b9eb6b3149b7..d034fa413164 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -45,6 +45,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_context.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
@@ -1053,6 +1054,18 @@ out:
 	return err;
 }
 
+static int __intel_context_flush_retire(struct intel_context *ce)
+{
+	struct intel_timeline *tl;
+
+	tl = intel_context_timeline_lock(ce);
+	if (IS_ERR(tl))
+		return PTR_ERR(tl);
+
+	intel_context_timeline_unlock(tl);
+	return 0;
+}
+
 static int __intel_engines_record_defaults(struct intel_gt *gt)
 {
 	struct i915_request *requests[I915_NUM_ENGINES] = {};
@@ -1121,13 +1134,20 @@ err_rq:
 		if (!rq)
 			continue;
 
-		/* We want to be able to unbind the state from the GGTT */
-		GEM_BUG_ON(intel_context_is_pinned(rq->hw_context));
-
+		GEM_BUG_ON(!test_bit(CONTEXT_ALLOC_BIT,
+				     &rq->hw_context->flags));
 		state = rq->hw_context->state;
 		if (!state)
 			continue;
 
+		/* Serialise with retirement on another CPU */
+		err = __intel_context_flush_retire(rq->hw_context);
+		if (err)
+			goto out;
+
+		/* We want to be able to unbind the state from the GGTT */
+		GEM_BUG_ON(intel_context_is_pinned(rq->hw_context));
+
 		/*
 		 * As we will hold a reference to the logical state, it will
 		 * not be torn down with the context, and importantly the
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 65d7c2e599de..2ae14bc14931 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -2078,20 +2078,12 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,
 	u32 *reg_state = ce->lrc_reg_state;
 	int i;
 
-	if (IS_GEN(stream->perf->i915, 12)) {
-		u32 format = stream->oa_buffer.format;
+	reg_state[ctx_oactxctrl + 1] =
+		(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+		(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+		GEN8_OA_COUNTER_RESUME;
 
-		reg_state[ctx_oactxctrl + 1] =
-			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
-			(stream->oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
-	} else {
-		reg_state[ctx_oactxctrl + 1] =
-			(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
-			(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
-			GEN8_OA_COUNTER_RESUME;
-	}
-
-	for (i = 0; !!ctx_flexeu0 && i < ARRAY_SIZE(flex_regs); i++)
+	for (i = 0; i < ARRAY_SIZE(flex_regs); i++)
 		reg_state[ctx_flexeu0 + i * 2 + 1] =
 			oa_config_flex_reg(stream->oa_config, flex_regs[i]);
 
@@ -2224,34 +2216,51 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 	return err;
 }
 
-static int gen12_emit_oar_config(struct intel_context *ce, bool enable)
+static int gen12_configure_oar_context(struct i915_perf_stream *stream, bool enable)
 {
-	struct i915_request *rq;
-	u32 *cs;
-	int err = 0;
-
-	rq = i915_request_create(ce);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
-
-	cs = intel_ring_begin(rq, 4);
-	if (IS_ERR(cs)) {
-		err = PTR_ERR(cs);
-		goto out;
-	}
-
-	*cs++ = MI_LOAD_REGISTER_IMM(1);
-	*cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base));
-	*cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
-			      enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0);
-	*cs++ = MI_NOOP;
+	int err;
+	struct intel_context *ce = stream->pinned_ctx;
+	u32 format = stream->oa_buffer.format;
+	struct flex regs_context[] = {
+		{
+			GEN8_OACTXCONTROL,
+			stream->perf->ctx_oactxctrl_offset + 1,
+			enable ? GEN8_OA_COUNTER_RESUME : 0,
+		},
+	};
+	/* Offsets in regs_lri are not used since this configuration is only
+	 * applied using LRI. Initialize the correct offsets for posterity.
+	 */
+#define GEN12_OAR_OACONTROL_OFFSET 0x5B0
+	struct flex regs_lri[] = {
+		{
+			GEN12_OAR_OACONTROL,
+			GEN12_OAR_OACONTROL_OFFSET + 1,
+			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
+			(enable ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0)
+		},
+		{
+			RING_CONTEXT_CONTROL(ce->engine->mmio_base),
+			CTX_CONTEXT_CONTROL,
+			_MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
+				      enable ?
+				      GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE :
+				      0)
+		},
+	};
 
-	intel_ring_advance(rq, cs);
+	/* Modify the context image of pinned context with regs_context*/
+	err = intel_context_lock_pinned(ce);
+	if (err)
+		return err;
 
-out:
-	i915_request_add(rq);
+	err = gen8_modify_context(ce, regs_context, ARRAY_SIZE(regs_context));
+	intel_context_unlock_pinned(ce);
+	if (err)
+		return err;
 
-	return err;
+	/* Apply regs_lri using LRI with pinned context */
+	return gen8_modify_self(ce, regs_lri, ARRAY_SIZE(regs_lri));
 }
 
 /*
@@ -2277,53 +2286,16 @@ out:
  *   per-context OA state.
  *
  * Note: it's only the RCS/Render context that has any OA state.
+ * Note: the first flex register passed must always be R_PWR_CLK_STATE
  */
-static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
-				      const struct i915_oa_config *oa_config)
+static int oa_configure_all_contexts(struct i915_perf_stream *stream,
+				     struct flex *regs,
+				     size_t num_regs)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
-	/* The MMIO offsets for Flex EU registers aren't contiguous */
-	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
-#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
-	struct flex regs[] = {
-		{
-			GEN8_R_PWR_CLK_STATE,
-			CTX_R_PWR_CLK_STATE,
-		},
-		{
-			IS_GEN(i915, 12) ?
-			GEN12_OAR_OACONTROL : GEN8_OACTXCONTROL,
-			stream->perf->ctx_oactxctrl_offset + 1,
-		},
-		{ EU_PERF_CNTL0, ctx_flexeuN(0) },
-		{ EU_PERF_CNTL1, ctx_flexeuN(1) },
-		{ EU_PERF_CNTL2, ctx_flexeuN(2) },
-		{ EU_PERF_CNTL3, ctx_flexeuN(3) },
-		{ EU_PERF_CNTL4, ctx_flexeuN(4) },
-		{ EU_PERF_CNTL5, ctx_flexeuN(5) },
-		{ EU_PERF_CNTL6, ctx_flexeuN(6) },
-	};
-#undef ctx_flexeuN
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx, *cn;
-	size_t array_size = IS_GEN(i915, 12) ? 2 : ARRAY_SIZE(regs);
-	int i, err;
-
-	if (IS_GEN(i915, 12)) {
-		u32 format = stream->oa_buffer.format;
-
-		regs[1].value =
-			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
-			(oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
-	} else {
-		regs[1].value =
-			(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
-			(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
-			GEN8_OA_COUNTER_RESUME;
-	}
-
-	for (i = 2; !!ctx_flexeu0 && i < array_size; i++)
-		regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
+	int err;
 
 	lockdep_assert_held(&stream->perf->lock);
 
@@ -2353,7 +2325,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 
 		spin_unlock(&i915->gem.contexts.lock);
 
-		err = gen8_configure_context(ctx, regs, array_size);
+		err = gen8_configure_context(ctx, regs, num_regs);
 		if (err) {
 			i915_gem_context_put(ctx);
 			return err;
@@ -2378,7 +2350,7 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 
 		regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu);
 
-		err = gen8_modify_self(ce, regs, array_size);
+		err = gen8_modify_self(ce, regs, num_regs);
 		if (err)
 			return err;
 	}
@@ -2386,6 +2358,56 @@ static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
 	return 0;
 }
 
+static int gen12_configure_all_contexts(struct i915_perf_stream *stream,
+					const struct i915_oa_config *oa_config)
+{
+	struct flex regs[] = {
+		{
+			GEN8_R_PWR_CLK_STATE,
+			CTX_R_PWR_CLK_STATE,
+		},
+	};
+
+	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+}
+
+static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
+				      const struct i915_oa_config *oa_config)
+{
+	/* The MMIO offsets for Flex EU registers aren't contiguous */
+	const u32 ctx_flexeu0 = stream->perf->ctx_flexeu0_offset;
+#define ctx_flexeuN(N) (ctx_flexeu0 + 2 * (N) + 1)
+	struct flex regs[] = {
+		{
+			GEN8_R_PWR_CLK_STATE,
+			CTX_R_PWR_CLK_STATE,
+		},
+		{
+			GEN8_OACTXCONTROL,
+			stream->perf->ctx_oactxctrl_offset + 1,
+		},
+		{ EU_PERF_CNTL0, ctx_flexeuN(0) },
+		{ EU_PERF_CNTL1, ctx_flexeuN(1) },
+		{ EU_PERF_CNTL2, ctx_flexeuN(2) },
+		{ EU_PERF_CNTL3, ctx_flexeuN(3) },
+		{ EU_PERF_CNTL4, ctx_flexeuN(4) },
+		{ EU_PERF_CNTL5, ctx_flexeuN(5) },
+		{ EU_PERF_CNTL6, ctx_flexeuN(6) },
+	};
+#undef ctx_flexeuN
+	int i;
+
+	regs[1].value =
+		(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+		(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+		GEN8_OA_COUNTER_RESUME;
+
+	for (i = 2; i < ARRAY_SIZE(regs); i++)
+		regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
+
+	return oa_configure_all_contexts(stream, regs, ARRAY_SIZE(regs));
+}
+
 static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
@@ -2464,7 +2486,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 * to make sure all slices/subslices are ON before writing to NOA
 	 * registers.
 	 */
-	ret = lrc_configure_all_contexts(stream, oa_config);
+	ret = gen12_configure_all_contexts(stream, oa_config);
 	if (ret)
 		return ret;
 
@@ -2474,8 +2496,7 @@ static int gen12_enable_metric_set(struct i915_perf_stream *stream)
 	 * requested this.
 	 */
 	if (stream->ctx) {
-		ret = gen12_emit_oar_config(stream->pinned_ctx,
-					    oa_config != NULL);
+		ret = gen12_configure_oar_context(stream, true);
 		if (ret)
 			return ret;
 	}
@@ -2509,11 +2530,11 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	lrc_configure_all_contexts(stream, NULL);
+	gen12_configure_all_contexts(stream, NULL);
 
 	/* disable the context save/restore or OAR counters */
 	if (stream->ctx)
-		gen12_emit_oar_config(stream->pinned_ctx, false);
+		gen12_configure_oar_context(stream, false);
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
@@ -2713,7 +2734,8 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 		return -EINVAL;
 	}
 
-	if (!(props->sample_flags & SAMPLE_OA_REPORT)) {
+	if (!(props->sample_flags & SAMPLE_OA_REPORT) &&
+	    (INTEL_GEN(perf->i915) < 12 || !stream->ctx)) {
 		DRM_DEBUG("Only OA report sampling supported\n");
 		return -EINVAL;
 	}
@@ -2745,7 +2767,7 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream,
 
 	format_size = perf->oa_formats[props->oa_format].size;
 
-	stream->sample_flags |= SAMPLE_OA_REPORT;
+	stream->sample_flags = props->sample_flags;
 	stream->sample_size += format_size;
 
 	stream->oa_buffer.format_size = format_size;
@@ -2854,7 +2876,11 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 		return;
 
 	stream = engine->i915->perf.exclusive_stream;
-	if (stream)
+	/*
+	 * For gen12, only CTX_R_PWR_CLK_STATE needs update, but the caller
+	 * is already doing that, so nothing to be done for gen12 here.
+	 */
+	if (stream && INTEL_GEN(stream->perf->i915) < 12)
 		gen8_update_reg_state_unlocked(ce, stream);
 }