Merge tag 'drm-intel-gt-next-2024-06-12' of https://gitlab.freedeskto…

…p.org/drm/i915/kernel into drm-next

UAPI Changes:

- Support replaying GPU hangs with captured context image (Tvrtko Ursulin)

Driver Changes:

Fixes/improvements/new stuff:

- Automate CCS Mode setting during engine resets [gt] (Andi Shyti)
- Revert "drm/i915: Remove extra multi-gt pm-references" (Janusz Krzysztofik)
- Fix HAS_REGION() usage in intel_gt_probe_lmem() (Ville Syrjälä)
- Disarm breadcrumbs if engines are already idle [gt] (Chris Wilson)
- Shadow default engine context image in the context (Tvrtko Ursulin)
- Support replaying GPU hangs with captured context image (Tvrtko Ursulin)
- avoid FIELD_PREP warning [guc] (Arnd Bergmann)
- Fix CCS id's calculation for CCS mode setting [gt] (Andi Shyti)
- Increase FLR timeout from 3s to 9s (Andi Shyti)
- Update workaround 14018575942 [mtl] (Angus Chen)

Future platform enablement:

- Enable w/a 16021333562 for DG2, MTL and ARL [guc] (John Harrison)

Miscellaneous:

- Pass the region ID rather than a bitmask to HAS_REGION() (Ville Syrjälä)
- Remove counter productive REGION_* wrappers (Ville Syrjälä)
- Fix typo [gem/i915_gem_ttm_move] (Deming Wang)
- Delete the live_hearbeat_fast selftest [gt] (Krzysztof Niemiec)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Zmmazub+U9ewH9ts@linux

drivers/gpu/drm/i915/Kconfig.debug

@@ -16,6 +16,23 @@ config DRM_I915_WERROR
 
 	  If in doubt, say "N".
 
+config DRM_I915_REPLAY_GPU_HANGS_API
+	bool "Enable GPU hang replay userspace API"
+	depends on DRM_I915
+	depends on EXPERT
+	default n
+	help
+	  Choose this option if you want to enable special and unstable
+	  userspace API used for replaying GPU hangs on a running system.
+
+	  This API is intended to be used by userspace graphics stack developers
+	  and provides no stability guarantees.
+
+	  The API needs to be activated at boot time using the
+	  enable_debug_only_api module parameter.
+
+	  If in doubt, say "N".
+
 config DRM_I915_DEBUG
 	bool "Enable additional driver debugging"
 	depends on DRM_I915

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

@@ -78,6 +78,7 @@
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gpu_commands.h"
 #include "gt/intel_ring.h"
+#include "gt/shmem_utils.h"
 
 #include "pxp/intel_pxp.h"
 
@@ -957,6 +958,7 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	case I915_CONTEXT_PARAM_RINGSIZE:
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2104,6 +2106,95 @@ static int get_protected(struct i915_gem_context *ctx,
 	return 0;
 }
 
+static int set_context_image(struct i915_gem_context *ctx,
+			     struct drm_i915_gem_context_param *args)
+{
+	struct i915_gem_context_param_context_image user;
+	struct intel_context *ce;
+	struct file *shmem_state;
+	unsigned long lookup;
+	void *state;
+	int ret = 0;
+
+	if (!IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API))
+		return -EINVAL;
+
+	if (!ctx->i915->params.enable_debug_only_api)
+		return -EINVAL;
+
+	if (args->size < sizeof(user))
+		return -EINVAL;
+
+	if (copy_from_user(&user, u64_to_user_ptr(args->value), sizeof(user)))
+		return -EFAULT;
+
+	if (user.mbz)
+		return -EINVAL;
+
+	if (user.flags & ~(I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX))
+		return -EINVAL;
+
+	lookup = 0;
+	if (user.flags & I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX)
+		lookup |= LOOKUP_USER_INDEX;
+
+	ce = lookup_user_engine(ctx, lookup, &user.engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	if (user.size < ce->engine->context_size) {
+		ret = -EINVAL;
+		goto out_ce;
+	}
+
+	if (drm_WARN_ON_ONCE(&ctx->i915->drm,
+			     test_bit(CONTEXT_ALLOC_BIT, &ce->flags))) {
+		/*
+		 * This is racy but for a debug only API, if userspace is keen
+		 * to create and configure contexts, while simultaneously using
+		 * them from a second thread, let them suffer by potentially not
+		 * executing with the context image they just raced to apply.
+		 */
+		ret = -EBUSY;
+		goto out_ce;
+	}
+
+	state = kmalloc(ce->engine->context_size, GFP_KERNEL);
+	if (!state) {
+		ret = -ENOMEM;
+		goto out_ce;
+	}
+
+	if (copy_from_user(state, u64_to_user_ptr(user.image),
+			   ce->engine->context_size)) {
+		ret = -EFAULT;
+		goto out_state;
+	}
+
+	shmem_state = shmem_create_from_data(ce->engine->name,
+					     state, ce->engine->context_size);
+	if (IS_ERR(shmem_state)) {
+		ret = PTR_ERR(shmem_state);
+		goto out_state;
+	}
+
+	if (intel_context_set_own_state(ce)) {
+		ret = -EBUSY;
+		fput(shmem_state);
+		goto out_state;
+	}
+
+	ce->default_state = shmem_state;
+
+	args->size = sizeof(user);
+
+out_state:
+	kfree(state);
+out_ce:
+	intel_context_put(ce);
+	return ret;
+}
+
 static int ctx_setparam(struct drm_i915_file_private *fpriv,
 			struct i915_gem_context *ctx,
 			struct drm_i915_gem_context_param *args)
@@ -2156,6 +2247,10 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		ret = set_persistence(ctx, args);
 		break;
 
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
+		ret = set_context_image(ctx, args);
+		break;
+
 	case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
 	case I915_CONTEXT_PARAM_NO_ZEROMAP:
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
@@ -2500,6 +2595,7 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	case I915_CONTEXT_PARAM_ENGINES:
 	case I915_CONTEXT_PARAM_RINGSIZE:
+	case I915_CONTEXT_PARAM_CONTEXT_IMAGE:
 	default:
 		ret = -EINVAL;
 		break;
@@ -2612,5 +2708,22 @@ int __init i915_gem_context_module_init(void)
 	if (!slab_luts)
 		return -ENOMEM;
 
+	if (IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API)) {
+		pr_notice("**************************************************************\n");
+		pr_notice("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE     **\n");
+		pr_notice("**                                                          **\n");
+		if (i915_modparams.enable_debug_only_api)
+			pr_notice("** i915.enable_debug_only_api is intended to be set         **\n");
+		else
+			pr_notice("** CONFIG_DRM_I915_REPLAY_GPU_HANGS_API builds are intended **\n");
+		pr_notice("** for specific userspace graphics stack developers only!   **\n");
+		pr_notice("**                                                          **\n");
+		pr_notice("** If you are seeing this message please report this to the **\n");
+		pr_notice("** provider of your kernel build.                           **\n");
+		pr_notice("**                                                          **\n");
+		pr_notice("**     NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE     **\n");
+		pr_notice("**************************************************************\n");
+	}
+
 	return 0;
 }

drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c

@@ -155,7 +155,7 @@ void i915_ttm_adjust_gem_after_move(struct drm_i915_gem_object *obj)
  * @bo: The ttm buffer object.
  *
  * This function prepares an object for move by removing all GPU bindings,
- * removing all CPU mapings and finally releasing the pages sg-table.
+ * removing all CPU mappings and finally releasing the pages sg-table.
  *
  * Return: 0 if successful, negative error code on error.
  */

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

@@ -27,6 +27,8 @@ static void rcu_context_free(struct rcu_head *rcu)
 	struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);
 
 	trace_intel_context_free(ce);
+	if (intel_context_has_own_state(ce))
+		fput(ce->default_state);
 	kmem_cache_free(slab_ce, ce);
 }
 

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

@@ -375,6 +375,28 @@ intel_context_clear_nopreempt(struct intel_context *ce)
 	clear_bit(CONTEXT_NOPREEMPT, &ce->flags);
 }
 
+#if IS_ENABLED(CONFIG_DRM_I915_REPLAY_GPU_HANGS_API)
+static inline bool intel_context_has_own_state(const struct intel_context *ce)
+{
+	return test_bit(CONTEXT_OWN_STATE, &ce->flags);
+}
+
+static inline bool intel_context_set_own_state(struct intel_context *ce)
+{
+	return test_and_set_bit(CONTEXT_OWN_STATE, &ce->flags);
+}
+#else
+static inline bool intel_context_has_own_state(const struct intel_context *ce)
+{
+	return false;
+}
+
+static inline bool intel_context_set_own_state(struct intel_context *ce)
+{
+	return true;
+}
+#endif
+
 u64 intel_context_get_total_runtime_ns(struct intel_context *ce);
 u64 intel_context_get_avg_runtime_ns(struct intel_context *ce);
 

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

@@ -99,6 +99,8 @@ struct intel_context {
 	struct i915_address_space *vm;
 	struct i915_gem_context __rcu *gem_context;
 
+	struct file *default_state;
+
 	/*
 	 * @signal_lock protects the list of requests that need signaling,
 	 * @signals. While there are any requests that need signaling,
@@ -131,6 +133,7 @@ struct intel_context {
 #define CONTEXT_IS_PARKING		12
 #define CONTEXT_EXITING			13
 #define CONTEXT_LOW_LATENCY		14
+#define CONTEXT_OWN_STATE		15
 
 	struct {
 		u64 timeout_us;

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

@@ -1017,9 +1017,8 @@ void lrc_init_state(struct intel_context *ce,
 
 	set_redzone(state, engine);
 
-	if (engine->default_state) {
-		shmem_read(engine->default_state, 0,
-			   state, engine->context_size);
+	if (ce->default_state) {
+		shmem_read(ce->default_state, 0, state, engine->context_size);
 		__set_bit(CONTEXT_VALID_BIT, &ce->flags);
 		inhibit = false;
 	}
@@ -1131,6 +1130,9 @@ int lrc_alloc(struct intel_context *ce, struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(ce->state);
 
+	if (!intel_context_has_own_state(ce))
+		ce->default_state = engine->default_state;
+
 	vma = __lrc_alloc_state(ce, engine);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);

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

@@ -474,8 +474,7 @@ static int ring_context_init_default_state(struct intel_context *ce,
 	if (IS_ERR(vaddr))
 		return PTR_ERR(vaddr);
 
-	shmem_read(ce->engine->default_state, 0,
-		   vaddr, ce->engine->context_size);
+	shmem_read(ce->default_state, 0, vaddr, ce->engine->context_size);
 
 	i915_gem_object_flush_map(obj);
 	__i915_gem_object_release_map(obj);
@@ -491,7 +490,7 @@ static int ring_context_pre_pin(struct intel_context *ce,
 	struct i915_address_space *vm;
 	int err = 0;
 
-	if (ce->engine->default_state &&
+	if (ce->default_state &&
 	    !test_bit(CONTEXT_VALID_BIT, &ce->flags)) {
 		err = ring_context_init_default_state(ce, ww);
 		if (err)
@@ -570,6 +569,9 @@ static int ring_context_alloc(struct intel_context *ce)
 {
 	struct intel_engine_cs *engine = ce->engine;
 
+	if (!intel_context_has_own_state(ce))
+		ce->default_state = engine->default_state;
+
 	/* One ringbuffer to rule them all */
 	GEM_BUG_ON(!engine->legacy.ring);
 	ce->ring = engine->legacy.ring;

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

@@ -1590,6 +1590,14 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal)
 	 */
 	wa_write_or(wal, XELPMP_GSC_MOD_CTRL, FORCE_MISS_FTLB);
 
+	/*
+	 * Wa_14018575942
+	 *
+	 * Issue is seen on media KPI test running on VDBOX engine
+	 * especially VP9 encoding WLs
+	 */
+	wa_write_or(wal, XELPMP_VDBX_MOD_CTRL, FORCE_MISS_FTLB);
+
 	/* Wa_22016670082 */
 	wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE);