Merge tag 'drm-intel-gt-next-2023-02-01' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Driver Changes:

Fixes/improvements/new stuff:

- Fix bcs default context on Meteorlake (Lucas De Marchi)
- GAM registers don't need to be re-applied on engine resets (Matt Roper)
- Correct implementation of Wa_18018781329 (Matt Roper)
- Avoid potential vm use-after-free (Rob Clark)
- GuC error capture fixes (John Harrison)
- Fix potential bit_17 double-free (Rob Clark)
- Don't complain about missing regs on MTL (John Harrison)

Future platform enablement:

- Convert PSS_MODE2 to multicast register (Gustavo Sousa)
- Move/adjust register definitions related to Wa_22011450934 (Matt Roper)
- Move LSC_CHICKEN_BIT* workarounds to correct function (Gustavo Sousa)
- Document where to implement register workarounds (Gustavo Sousa)
- Use uabi engines for the default engine map (Tvrtko Ursulin)
- Flush all tiles on test exit (Tvrtko Ursulin)
- Annotate a couple more workaround registers as MCR (Matt Roper)

Driver refactors:

- Add and use GuC oriented print macros (Michal Wajdeczko)

Miscellaneous:

- Fix intel_selftest_modify_policy argument types (Arnd Bergmann)

Backmerges:

Merge drm/drm-next into drm-intel-gt-next (for conflict resolution) (Tvrtko Ursulin)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Y9pOsq7VKnq7rgnW@tursulin-desk

Author: airlied

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1096,24 +1096,23 @@ static struct i915_gem_engines *alloc_engines(unsigned int count)
 static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
 						struct intel_sseu rcs_sseu)
 {
-	const struct intel_gt *gt = to_gt(ctx->i915);
+	const unsigned int max = I915_NUM_ENGINES;
 	struct intel_engine_cs *engine;
 	struct i915_gem_engines *e, *err;
-	enum intel_engine_id id;
 
-	e = alloc_engines(I915_NUM_ENGINES);
+	e = alloc_engines(max);
 	if (!e)
 		return ERR_PTR(-ENOMEM);
 
-	for_each_engine(engine, gt, id) {
+	for_each_uabi_engine(engine, ctx->i915) {
 		struct intel_context *ce;
 		struct intel_sseu sseu = {};
 		int ret;
 
 		if (engine->legacy_idx == INVALID_ENGINE)
 			continue;
 
-		GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
+		GEM_BUG_ON(engine->legacy_idx >= max);
 		GEM_BUG_ON(e->engines[engine->legacy_idx]);
 
 		ce = intel_context_create(engine);
@@ -1861,11 +1860,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv,
 	vm = ctx->vm;
 	GEM_BUG_ON(!vm);
 
+	/*
+	 * Get a reference for the allocated handle.  Once the handle is
+	 * visible in the vm_xa table, userspace could try to close it
+	 * from under our feet, so we need to hold the extra reference
+	 * first.
+	 */
+	i915_vm_get(vm);
+
 	err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
-	if (err)
+	if (err) {
+		i915_vm_put(vm);
 		return err;
-
-	i915_vm_get(vm);
+	}
 
 	GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
 	args->value = id;

drivers/gpu/drm/i915/gem/i915_gem_tiling.c

@@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 	spin_unlock(&obj->vma.lock);
 
 	obj->tiling_and_stride = tiling | stride;
-	i915_gem_object_unlock(obj);
-
-	/* Force the fence to be reacquired for GTT access */
-	i915_gem_object_release_mmap_gtt(obj);
 
 	/* Try to preallocate memory required to save swizzling on put-pages */
 	if (i915_gem_object_needs_bit17_swizzle(obj)) {
@@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj,
 		obj->bit_17 = NULL;
 	}
 
+	i915_gem_object_unlock(obj);
+
+	/* Force the fence to be reacquired for GTT access */
+	i915_gem_object_release_mmap_gtt(obj);
+
 	return 0;
 }
 

drivers/gpu/drm/i915/gt/intel_context.c

@@ -528,7 +528,7 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
 	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;

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)
 {

drivers/gpu/drm/i915/gt/intel_engine.h

@@ -250,8 +250,8 @@ 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 *

drivers/gpu/drm/i915/gt/intel_engine_cs.c

@@ -1584,11 +1584,8 @@ static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine)
 	};
 	u32 val;
 
-	if (!_reg[engine->id].reg) {
-		drm_err(&engine->i915->drm,
-			"MSG IDLE undefined for engine id %u\n", engine->id);
+	if (!_reg[engine->id].reg)
 		return 0;
-	}
 
 	val = intel_uncore_read(engine->uncore, _reg[engine->id]);
 
@@ -2114,17 +2111,6 @@ 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);
@@ -2216,11 +2202,11 @@ 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.
@@ -2229,27 +2215,22 @@ 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,
@@ -2259,7 +2240,6 @@ 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) {
@@ -2296,13 +2276,8 @@ 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) {
@@ -2348,8 +2323,7 @@ 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;
 
@@ -2401,6 +2375,33 @@ 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)
 {
 	/*

drivers/gpu/drm/i915/gt/intel_engine_regs.h

@@ -81,6 +81,7 @@
 #define RING_EIR(base)				_MMIO((base) + 0xb0)
 #define RING_EMR(base)				_MMIO((base) + 0xb4)
 #define RING_ESR(base)				_MMIO((base) + 0xb8)
+#define GEN12_STATE_ACK_DEBUG(base)		_MMIO((base) + 0xbc)
 #define RING_INSTPM(base)			_MMIO((base) + 0xc0)
 #define RING_CMD_CCTL(base)			_MMIO((base) + 0xc4)
 #define ACTHD(base)				_MMIO((base) + 0xc8)

drivers/gpu/drm/i915/gt/intel_execlists_submission.c

@@ -4150,6 +4150,33 @@ 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

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);
 

drivers/gpu/drm/i915/gt/intel_gt_regs.h

@@ -407,6 +407,8 @@
 #define GEN9_WM_CHICKEN3			_MMIO(0x5588)
 #define   GEN9_FACTOR_IN_CLR_VAL_HIZ		(1 << 9)
 
+#define XEHP_CULLBIT1				MCR_REG(0x6100)
+
 #define CHICKEN_RASTER_1			MCR_REG(0x6204)
 #define   DIS_SF_ROUND_NEAREST_EVEN		REG_BIT(8)
 
@@ -457,10 +459,12 @@
 #define   HZ_DEPTH_TEST_LE_GE_OPT_DISABLE	REG_BIT(13)
 #define   BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	REG_BIT(3)
 
+#define XEHP_CULLBIT2				MCR_REG(0x7030)
+
 #define GEN8_L3CNTLREG				_MMIO(0x7034)
 #define   GEN8_ERRDETBCTRL			(1 << 9)
 
-#define PSS_MODE2				_MMIO(0x703c)
+#define XEHP_PSS_MODE2				MCR_REG(0x703c)
 #define   SCOREBOARD_STALL_FLUSH_CONTROL	REG_BIT(5)
 
 #define GEN7_SC_INSTDONE			_MMIO(0x7100)
@@ -1096,16 +1100,19 @@
 #define XEHP_MERT_MOD_CTRL			MCR_REG(0xcf28)
 #define RENDER_MOD_CTRL				MCR_REG(0xcf2c)
 #define COMP_MOD_CTRL				MCR_REG(0xcf30)
-#define VDBX_MOD_CTRL				MCR_REG(0xcf34)
-#define VEBX_MOD_CTRL				MCR_REG(0xcf38)
+#define XELPMP_GSC_MOD_CTRL			_MMIO(0xcf30)	/* media GT only */
+#define XEHP_VDBX_MOD_CTRL			MCR_REG(0xcf34)
+#define XELPMP_VDBX_MOD_CTRL			_MMIO(0xcf34)
+#define XEHP_VEBX_MOD_CTRL			MCR_REG(0xcf38)
+#define XELPMP_VEBX_MOD_CTRL			_MMIO(0xcf38)
 #define   FORCE_MISS_FTLB			REG_BIT(3)
 
-#define GEN12_GAMSTLB_CTRL			_MMIO(0xcf4c)
+#define XEHP_GAMSTLB_CTRL			MCR_REG(0xcf4c)
 #define   CONTROL_BLOCK_CLKGATE_DIS		REG_BIT(12)
 #define   EGRESS_BLOCK_CLKGATE_DIS		REG_BIT(11)
 #define   TAG_BLOCK_CLKGATE_DIS			REG_BIT(7)
 
-#define GEN12_GAMCNTRL_CTRL			_MMIO(0xcf54)
+#define XEHP_GAMCNTRL_CTRL			MCR_REG(0xcf54)
 #define   INVALIDATION_BROADCAST_MODE_DIS	REG_BIT(12)
 #define   GLOBAL_INVALIDATION_MODE		REG_BIT(2)