Merge tag 'kvm-riscv-6.3-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 6.3

- Fix wrong usage of PGDIR_SIZE to check page sizes
- Fix privilege mode setting in kvm_riscv_vcpu_trap_redirect()
- Redirect illegal instruction traps to guest
- SBI PMU support for guest

11 files changed, 138 insertions, 91 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e94365b08f1e..2aa63ec521b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -528,7 +528,7 @@ retry:
 	return rq;
 }
 
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
 {
 	struct intel_context *parent = intel_context_to_parent(ce);
 	struct i915_request *rq, *active = NULL;
@@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
 
 		active = rq;
 	}
+	if (active)
+		active = i915_request_get_rcu(active);
 	spin_unlock_irqrestore(&parent->guc_state.lock, flags);
 
 	return active;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index fb62b7b8cbcd..0a8d553da3f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 
 struct i915_request *intel_context_create_request(struct intel_context *ce);
 
-struct i915_request *
-intel_context_find_active_request(struct intel_context *ce);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
 
 static inline bool intel_context_is_barrier(const struct intel_context *ce)
 {
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index cbc8b857d5f7..7a4504ea35c3 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -248,8 +248,8 @@ void intel_engine_dump_active_requests(struct list_head *requests,
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine,
 				   ktime_t *now);
 
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine);
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+				  struct intel_context **ce, struct i915_request **rq);
 
 u32 intel_engine_context_size(struct intel_gt *gt, u8 class);
 struct intel_context *
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c33e0d72d670..d37931e16fd9 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
 	}
 }
 
-static unsigned long list_count(struct list_head *list)
-{
-	struct list_head *pos;
-	unsigned long count = 0;
-
-	list_for_each(pos, list)
-		count++;
-
-	return count;
-}
-
 static unsigned long read_ul(void *p, size_t x)
 {
 	return *(unsigned long *)(p + x);
@@ -2196,11 +2185,11 @@ void intel_engine_dump_active_requests(struct list_head *requests,
 	}
 }
 
-static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m)
+static void engine_dump_active_requests(struct intel_engine_cs *engine,
+					struct drm_printer *m)
 {
+	struct intel_context *hung_ce = NULL;
 	struct i915_request *hung_rq = NULL;
-	struct intel_context *ce;
-	bool guc;
 
 	/*
 	 * No need for an engine->irq_seqno_barrier() before the seqno reads.
@@ -2209,27 +2198,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
 	 * But the intention here is just to report an instantaneous snapshot
 	 * so that's fine.
 	 */
-	lockdep_assert_held(&engine->sched_engine->lock);
+	intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq);
 
 	drm_printf(m, "\tRequests:\n");
 
-	guc = intel_uc_uses_guc_submission(&engine->gt->uc);
-	if (guc) {
-		ce = intel_engine_get_hung_context(engine);
-		if (ce)
-			hung_rq = intel_context_find_active_request(ce);
-	} else {
-		hung_rq = intel_engine_execlist_find_hung_request(engine);
-	}
-
 	if (hung_rq)
 		engine_dump_request(hung_rq, m, "\t\thung");
+	else if (hung_ce)
+		drm_printf(m, "\t\tGot hung ce but no hung rq!\n");
 
-	if (guc)
+	if (intel_uc_uses_guc_submission(&engine->gt->uc))
 		intel_guc_dump_active_requests(engine, hung_rq, m);
 	else
-		intel_engine_dump_active_requests(&engine->sched_engine->requests,
-						  hung_rq, m);
+		intel_execlists_dump_active_requests(engine, hung_rq, m);
+
+	if (hung_rq)
+		i915_request_put(hung_rq);
 }
 
 void intel_engine_dump(struct intel_engine_cs *engine,
@@ -2239,7 +2223,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
 	struct i915_request *rq;
 	intel_wakeref_t wakeref;
-	unsigned long flags;
 	ktime_t dummy;
 
 	if (header) {
@@ -2276,13 +2259,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		   i915_reset_count(error));
 	print_properties(engine, m);
 
-	spin_lock_irqsave(&engine->sched_engine->lock, flags);
 	engine_dump_active_requests(engine, m);
 
-	drm_printf(m, "\tOn hold?: %lu\n",
-		   list_count(&engine->sched_engine->hold));
-	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
-
 	drm_printf(m, "\tMMIO base:  0x%08x\n", engine->mmio_base);
 	wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm);
 	if (wakeref) {
@@ -2328,8 +2306,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings,
 	return siblings[0]->cops->create_virtual(siblings, count, flags);
 }
 
-struct i915_request *
-intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
+static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 {
 	struct i915_request *request, *active = NULL;
 
@@ -2381,6 +2358,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine)
 	return active;
 }
 
+void intel_engine_get_hung_entity(struct intel_engine_cs *engine,
+				  struct intel_context **ce, struct i915_request **rq)
+{
+	unsigned long flags;
+
+	*ce = intel_engine_get_hung_context(engine);
+	if (*ce) {
+		intel_engine_clear_hung_context(engine);
+
+		*rq = intel_context_get_active_request(*ce);
+		return;
+	}
+
+	/*
+	 * Getting here with GuC enabled means it is a forced error capture
+	 * with no actual hang. So, no need to attempt the execlist search.
+	 */
+	if (intel_uc_uses_guc_submission(&engine->gt->uc))
+		return;
+
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
+	*rq = engine_execlist_find_hung_request(engine);
+	if (*rq)
+		*rq = i915_request_get_rcu(*rq);
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
 void xehp_enable_ccs_engines(struct intel_engine_cs *engine)
 {
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2daffa7c7dfd..21cb5b69d82e 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -4148,6 +4148,33 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 	spin_unlock_irqrestore(&sched_engine->lock, flags);
 }
 
+static unsigned long list_count(struct list_head *list)
+{
+	struct list_head *pos;
+	unsigned long count = 0;
+
+	list_for_each(pos, list)
+		count++;
+
+	return count;
+}
+
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+					  struct i915_request *hung_rq,
+					  struct drm_printer *m)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->sched_engine->lock, flags);
+
+	intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m);
+
+	drm_printf(m, "\tOn hold?: %lu\n",
+		   list_count(&engine->sched_engine->hold));
+
+	spin_unlock_irqrestore(&engine->sched_engine->lock, flags);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_execlists.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
index a1aa92c983a5..d2c7d45ea062 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h
@@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine,
 							int indent),
 				   unsigned int max);
 
+void intel_execlists_dump_active_requests(struct intel_engine_cs *engine,
+					  struct i915_request *hung_rq,
+					  struct drm_printer *m);
+
 bool
 intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index c3cd92691795..a5454af2a9cf 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -406,10 +406,10 @@
 #define GEN9_WM_CHICKEN3			_MMIO(0x5588)
 #define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
 
-#define CHICKEN_RASTER_1			_MMIO(0x6204)
+#define CHICKEN_RASTER_1			MCR_REG(0x6204)
 #define   DIS_SF_ROUND_NEAREST_EVEN		REG_BIT(8)
 
-#define CHICKEN_RASTER_2			_MMIO(0x6208)
+#define CHICKEN_RASTER_2			MCR_REG(0x6208)
 #define   TBIMR_FAST_CLIP			REG_BIT(5)
 
 #define VFLSKPD					MCR_REG(0x62a8)
@@ -429,9 +429,10 @@
 #define   RC_OP_FLUSH_ENABLE			(1 << 0)
 #define   HIZ_RAW_STALL_OPT_DISABLE		(1 << 2)
 #define CACHE_MODE_1				_MMIO(0x7004) /* IVB+ */
-#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1 << 6)
-#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
-#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
+#define   MSAA_OPTIMIZATION_REDUC_DISABLE	REG_BIT(11)
+#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	REG_BIT(6)
+#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	REG_BIT(6)
+#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	REG_BIT(1)
 
 #define GEN7_GT_MODE				_MMIO(0x7008)
 #define   GEN9_IZ_HASHING_MASK(slice)		(0x3 << ((slice) * 2))
@@ -457,6 +458,9 @@
 #define GEN8_L3CNTLREG				_MMIO(0x7034)
 #define   GEN8_ERRDETBCTRL			(1 << 9)
 
+#define PSS_MODE2				_MMIO(0x703c)
+#define   SCOREBOARD_STALL_FLUSH_CONTROL	REG_BIT(5)
+
 #define GEN7_SC_INSTDONE			_MMIO(0x7100)
 #define GEN12_SC_INSTDONE_EXTRA			_MMIO(0x7104)
 #define GEN12_SC_INSTDONE_EXTRA2		_MMIO(0x7108)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index 7771a19008c6..bbeeb6dde7ae 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = {
 	END
 };
 
-static const u8 mtl_xcs_offsets[] = {
-	NOP(1),
-	LRI(13, POSTED),
-	REG16(0x244),
-	REG(0x034),
-	REG(0x030),
-	REG(0x038),
-	REG(0x03c),
-	REG(0x168),
-	REG(0x140),
-	REG(0x110),
-	REG(0x1c0),
-	REG(0x1c4),
-	REG(0x1c8),
-	REG(0x180),
-	REG16(0x2b4),
-	NOP(4),
-
-	NOP(1),
-	LRI(9, POSTED),
-	REG16(0x3a8),
-	REG16(0x28c),
-	REG16(0x288),
-	REG16(0x284),
-	REG16(0x280),
-	REG16(0x27c),
-	REG16(0x278),
-	REG16(0x274),
-	REG16(0x270),
-
-	END
-};
-
 static const u8 gen8_rcs_offsets[] = {
 	NOP(1),
 	LRI(14, POSTED),
@@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine)
 		else
 			return gen8_rcs_offsets;
 	} else {
-		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70))
-			return mtl_xcs_offsets;
-		else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
+		if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55))
 			return dg2_xcs_offsets;
 		else if (GRAPHICS_VER(engine->i915) >= 12)
 			return gen12_xcs_offsets;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 24736ebee17c..78dc5e493c62 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -278,6 +278,7 @@ out:
 static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 {
 	struct intel_uncore *uncore = gt->uncore;
+	int loops = 2;
 	int err;
 
 	/*
@@ -285,18 +286,39 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask)
 	 * for fifo space for the write or forcewake the chip for
 	 * the read
 	 */
-	intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
+	do {
+		intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask);
 
-	/* Wait for the device to ack the reset requests */
-	err = __intel_wait_for_register_fw(uncore,
-					   GEN6_GDRST, hw_domain_mask, 0,
-					   500, 0,
-					   NULL);
+		/*
+		 * Wait for the device to ack the reset requests.
+		 *
+		 * On some platforms, e.g. Jasperlake, we see that the
+		 * engine register state is not cleared until shortly after
+		 * GDRST reports completion, causing a failure as we try
+		 * to immediately resume while the internal state is still
+		 * in flux. If we immediately repeat the reset, the second
+		 * reset appears to serialise with the first, and since
+		 * it is a no-op, the registers should retain their reset
+		 * value. However, there is still a concern that upon
+		 * leaving the second reset, the internal engine state
+		 * is still in flux and not ready for resuming.
+		 */
+		err = __intel_wait_for_register_fw(uncore, GEN6_GDRST,
+						   hw_domain_mask, 0,
+						   2000, 0,
+						   NULL);
+	} while (err == 0 && --loops);
 	if (err)
 		GT_TRACE(gt,
 			 "Wait for 0x%08x engines reset failed\n",
 			 hw_domain_mask);
 
+	/*
+	 * As we have observed that the engine state is still volatile
+	 * after GDRST is acked, impose a small delay to let everything settle.
+	 */
+	udelay(50);
+
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 2afb4f80a954..949c19339015 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -645,7 +645,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 				   struct i915_wa_list *wal)
 {
-	wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
+	wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
 	wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
 			     REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
 	wa_mcr_add(wal,
@@ -771,11 +771,19 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine,
 
 	/* Wa_14014947963:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) ||
-		IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+	    IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
 		wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000);
 
+	/* Wa_18018764978:dg2 */
+	if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) ||
+	    IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915))
+		wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL);
+
 	/* Wa_15010599737:dg2 */
-	wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+	wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN);
+
+	/* Wa_18019271663:dg2 */
+	wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE);
 }
 
 static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 0a42f1807f52..c10977cb06b9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 			goto next_context;
 
 		guilty = false;
-		rq = intel_context_find_active_request(ce);
+		rq = intel_context_get_active_request(ce);
 		if (!rq) {
 			head = ce->ring->tail;
 			goto out_replay;
@@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
 		head = intel_ring_wrap(ce->ring, rq->head);
 
 		__i915_request_reset(rq, guilty);
+		i915_request_put(rq);
 out_replay:
 		guc_reset_state(ce, head, guilty);
 next_context:
@@ -4817,6 +4818,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 
 	xa_lock_irqsave(&guc->context_lookup, flags);
 	xa_for_each(&guc->context_lookup, index, ce) {
+		bool found;
+
 		if (!kref_get_unless_zero(&ce->ref))
 			continue;
 
@@ -4833,10 +4836,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 				goto next;
 		}
 
+		found = false;
+		spin_lock(&ce->guc_state.lock);
 		list_for_each_entry(rq, &ce->guc_state.requests, sched.link) {
 			if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE)
 				continue;
 
+			found = true;
+			break;
+		}
+		spin_unlock(&ce->guc_state.lock);
+
+		if (found) {
 			intel_engine_set_hung_context(engine, ce);
 
 			/* Can only cope with one hang at a time... */
@@ -4844,6 +4855,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine)
 			xa_lock(&guc->context_lookup);
 			goto done;
 		}
+
 next:
 		intel_context_put(ce);
 		xa_lock(&guc->context_lookup);