Merge tag 'drm-intel-gt-next-2023-04-06' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- (Build-time only, should not have any impact)
  drm/i915/uapi: Replace fake flex-array with flexible-array member

  "Zero-length arrays as fake flexible arrays are deprecated and we are
  moving towards adopting C99 flexible-array members instead."

  This is on core kernel request moving towards GCC 13.

Driver Changes:

- Fix context runtime accounting on sysfs fdinfo for heavy workloads (Tvrtko)
- Add support for OA media units on MTL (Umesh)
- Add new workarounds for Meteorlake (Daniele, Radhakrishna, Haridhar)
- Fix sysfs to read actual frequency for MTL and Gen6 and earlier
  (Ashutosh)
- Synchronize i915/BIOS on C6 enabling on MTL (Vinay)
- Fix DMAR error noise due to GPU error capture (Andrej)
- Fix forcewake during BAR resize on discrete (Andrzej)
- Flush lmem contents after construction on discrete (Chris)
- Fix GuC loading timeout on systems where IFWI programs low boot
  frequency (John)
- Fix race condition UAF in i915_perf_add_config_ioctl (Min)

- Sanitycheck MMIO access early in driver load and during forcewake
  (Matt)
- Wakeref fixes for GuC RC error scenario and active VM tracking (Chris)
- Cancel HuC delayed load timer on reset (Daniele)
- Limit double GT reset to pre-MTL (Daniele)
- Use i915 instead of dev_priv insied the file_priv structure (Andi)
- Improve GuC load error reporting (John)
- Simplify VCS/BSD engine selection logic (Tvrtko)
- Perform uc late init after probe error injection (Andrzej)
- Fix format for perf_limit_reasons in debugfs (Vinay)
- Create per-gt debugfs files (Andi)

- Documentation and kerneldoc fixes (Nirmoy, Lee)
- Selftest improvements (Fei, Jonathan)

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZC6APj/feB+jBf2d@jlahtine-mobl.ger.corp.intel.com

60 files changed, 1214 insertions, 633 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 6d639ca24dfb..5402a7bbcb1d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -364,7 +364,7 @@ static int set_proto_ctx_vm(struct drm_i915_file_private *fpriv,
 			    struct i915_gem_proto_context *pc,
 			    const struct drm_i915_gem_context_param *args)
 {
-	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct drm_i915_private *i915 = fpriv->i915;
 	struct i915_address_space *vm;
 
 	if (args->size)
@@ -733,7 +733,7 @@ static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
 			         struct i915_gem_proto_context *pc,
 			         const struct drm_i915_gem_context_param *args)
 {
-	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct drm_i915_private *i915 = fpriv->i915;
 	struct set_proto_ctx_engines set = { .i915 = i915 };
 	struct i915_context_param_engines __user *user =
 		u64_to_user_ptr(args->value);
@@ -813,7 +813,7 @@ static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv,
 			      struct i915_gem_proto_context *pc,
 			      struct drm_i915_gem_context_param *args)
 {
-	struct drm_i915_private *i915 = fpriv->dev_priv;
+	struct drm_i915_private *i915 = fpriv->i915;
 	struct drm_i915_gem_context_param_sseu user_sseu;
 	struct intel_sseu *sseu;
 	int ret;
@@ -913,7 +913,7 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 		break;
 
 	case I915_CONTEXT_PARAM_PRIORITY:
-		ret = validate_priority(fpriv->dev_priv, args);
+		ret = validate_priority(fpriv->i915, args);
 		if (!ret)
 			pc->sched.priority = args->value;
 		break;
@@ -934,12 +934,12 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
 		if (args->size)
 			ret = -EINVAL;
 		else
-			ret = proto_context_set_persistence(fpriv->dev_priv, pc,
+			ret = proto_context_set_persistence(fpriv->i915, pc,
 							    args->value);
 		break;
 
 	case I915_CONTEXT_PARAM_PROTECTED_CONTENT:
-		ret = proto_context_set_protected(fpriv->dev_priv, pc,
+		ret = proto_context_set_protected(fpriv->i915, pc,
 						  args->value);
 		break;
 
@@ -1770,7 +1770,7 @@ void i915_gem_context_close(struct drm_file *file)
 	unsigned long idx;
 
 	xa_for_each(&file_priv->proto_context_xa, idx, pc)
-		proto_context_close(file_priv->dev_priv, pc);
+		proto_context_close(file_priv->i915, pc);
 	xa_destroy(&file_priv->proto_context_xa);
 	mutex_destroy(&file_priv->proto_context_lock);
 
@@ -2206,7 +2206,7 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv,
 
 	lockdep_assert_held(&file_priv->proto_context_lock);
 
-	ctx = i915_gem_create_context(file_priv->dev_priv, pc);
+	ctx = i915_gem_create_context(file_priv->i915, pc);
 	if (IS_ERR(ctx))
 		return ctx;
 
@@ -2223,7 +2223,7 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv,
 
 	old = xa_erase(&file_priv->proto_context_xa, id);
 	GEM_BUG_ON(old != pc);
-	proto_context_close(file_priv->dev_priv, pc);
+	proto_context_close(file_priv->i915, pc);
 
 	return ctx;
 }
@@ -2352,7 +2352,7 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
 	GEM_WARN_ON(ctx && pc);
 
 	if (pc)
-		proto_context_close(file_priv->dev_priv, pc);
+		proto_context_close(file_priv->i915, pc);
 
 	if (ctx)
 		context_close(ctx);
@@ -2505,7 +2505,7 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
 			 * GEM_CONTEXT_CREATE starting with graphics
 			 * version 13.
 			 */
-			WARN_ON(GRAPHICS_VER(file_priv->dev_priv) > 12);
+			WARN_ON(GRAPHICS_VER(file_priv->i915) > 12);
 			ret = set_proto_ctx_param(file_priv, pc, args);
 		} else {
 			ret = -ENOENT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_create.c b/drivers/gpu/drm/i915/gem/i915_gem_create.c
index e76c9703680e..bfe1dbda4cb7 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_create.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_create.c
@@ -144,7 +144,8 @@ object_free:
 }
 
 /**
- * Creates a new object using the same path as DRM_I915_GEM_CREATE_EXT
+ * __i915_gem_object_create_user - Creates a new object using the same path as
+ *                                 DRM_I915_GEM_CREATE_EXT
  * @i915: i915 private
  * @size: size of the buffer, in bytes
  * @placements: possible placement regions, in priority order
@@ -215,7 +216,7 @@ i915_gem_dumb_create(struct drm_file *file,
 }
 
 /**
- * Creates a new mm object and returns a handle to it.
+ * i915_gem_create_ioctl - Creates a new mm object and returns a handle to it.
  * @dev: drm device pointer
  * @data: ioctl data blob
  * @file: drm file pointer
@@ -399,7 +400,7 @@ static const i915_user_extension_fn create_extensions[] = {
 };
 
 /**
- * Creates a new mm object and returns a handle to it.
+ * i915_gem_create_ext_ioctl - Creates a new mm object and returns a handle to it.
  * @dev: drm device pointer
  * @data: ioctl data blob
  * @file: drm file pointer
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
index 497de40b8e68..d2d5a24301b2 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c
@@ -116,7 +116,8 @@ void i915_gem_object_flush_if_display_locked(struct drm_i915_gem_object *obj)
 }
 
 /**
- * Moves a single object to the WC read, and possibly write domain.
+ * i915_gem_object_set_to_wc_domain - Moves a single object to the WC read, and
+ *                                    possibly write domain.
  * @obj: object to act on
  * @write: ask for write access or read only
  *
@@ -177,7 +178,8 @@ i915_gem_object_set_to_wc_domain(struct drm_i915_gem_object *obj, bool write)
 }
 
 /**
- * Moves a single object to the GTT read, and possibly write domain.
+ * i915_gem_object_set_to_gtt_domain - Moves a single object to the GTT read,
+ *                                     and possibly write domain.
  * @obj: object to act on
  * @write: ask for write access or read only
  *
@@ -246,7 +248,7 @@ i915_gem_object_set_to_gtt_domain(struct drm_i915_gem_object *obj, bool write)
 }
 
 /**
- * Changes the cache-level of an object across all VMA.
+ * i915_gem_object_set_cache_level - Changes the cache-level of an object across all VMA.
  * @obj: object to act on
  * @cache_level: new cache level to set for the object
  *
@@ -467,7 +469,8 @@ i915_gem_object_pin_to_display_plane(struct drm_i915_gem_object *obj,
 }
 
 /**
- * Moves a single object to the CPU read, and possibly write domain.
+ * i915_gem_object_set_to_cpu_domain - Moves a single object to the CPU read,
+ *                                     and possibly write domain.
  * @obj: object to act on
  * @write: requesting write or read-only access
  *
@@ -511,7 +514,8 @@ i915_gem_object_set_to_cpu_domain(struct drm_i915_gem_object *obj, bool write)
 }
 
 /**
- * Called when user space prepares to use an object with the CPU, either
+ * i915_gem_set_domain_ioctl - Called when user space prepares to use an
+ *                             object with the CPU, either
  * through the mmap ioctl's mapping or a GTT mapping.
  * @dev: drm device
  * @data: ioctl data blob
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 9dce2957b4e5..3aeede6aee4d 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2449,11 +2449,6 @@ static int eb_submit(struct i915_execbuffer *eb)
 	return err;
 }
 
-static int num_vcs_engines(struct drm_i915_private *i915)
-{
-	return hweight_long(VDBOX_MASK(to_gt(i915)));
-}
-
 /*
  * Find one BSD ring to dispatch the corresponding BSD command.
  * The engine index is returned.
@@ -2467,7 +2462,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv,
 	/* Check whether the file_priv has already selected one ring. */
 	if ((int)file_priv->bsd_engine < 0)
 		file_priv->bsd_engine =
-			get_random_u32_below(num_vcs_engines(dev_priv));
+			get_random_u32_below(dev_priv->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO]);
 
 	return file_priv->bsd_engine;
 }
@@ -2655,7 +2650,8 @@ eb_select_legacy_ring(struct i915_execbuffer *eb)
 		return -1;
 	}
 
-	if (user_ring_id == I915_EXEC_BSD && num_vcs_engines(i915) > 1) {
+	if (user_ring_id == I915_EXEC_BSD &&
+	    i915->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO] > 1) {
 		unsigned int bsd_idx = args->flags & I915_EXEC_BSD_MASK;
 
 		if (bsd_idx == I915_EXEC_BSD_DEFAULT) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
index 8949fb0a944f..3198b64ad7db 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -127,7 +127,8 @@ i915_gem_object_create_lmem_from_data(struct drm_i915_private *i915,
 
 	memcpy(map, data, size);
 
-	i915_gem_object_unpin_map(obj);
+	i915_gem_object_flush_map(obj);
+	__i915_gem_object_release_map(obj);
 
 	return obj;
 }
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index e6d4efde4fc5..4666bb82f312 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -875,7 +875,7 @@ int i915_gem_object_wait_moving_fence(struct drm_i915_gem_object *obj,
 	return ret < 0 ? ret : 0;
 }
 
-/**
+/*
  * i915_gem_object_has_unknown_state - Return true if the object backing pages are
  * in an unknown_state. This means that userspace must NEVER be allowed to touch
  * the pages, with either the GPU or CPU.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 341b94672abc..9227f8146a58 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -1274,7 +1274,7 @@ void i915_ttm_bo_destroy(struct ttm_buffer_object *bo)
 	}
 }
 
-/**
+/*
  * __i915_gem_ttm_object_init - Initialize a ttm-backed i915 gem object
  * @mem: The initial memory region for the object.
  * @obj: The gem object.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index d030182ca176..dd188dfcc423 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -253,6 +253,7 @@ static struct dma_fence *i915_ttm_accel_move(struct ttm_buffer_object *bo,
  * @_src_iter: Storage space for the source kmap iterator.
  * @dst_iter: Pointer to the destination kmap iterator.
  * @src_iter: Pointer to the source kmap iterator.
+ * @num_pages: Number of pages
  * @clear: Whether to clear instead of copy.
  * @src_rsgt: Refcounted scatter-gather list of source memory.
  * @dst_rsgt: Refcounted scatter-gather list of destination memory.
@@ -557,6 +558,8 @@ out:
  * i915_ttm_move - The TTM move callback used by i915.
  * @bo: The buffer object.
  * @evict: Whether this is an eviction.
+ * @ctx: Pointer to a struct ttm_operation_ctx indicating how the waits should be
+ *       performed if waiting
  * @dst_mem: The destination ttm resource.
  * @hop: If we need multihop, what temporary memory type to move to.
  *
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
index dfe39c8e74d8..ad649523d5e0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_pm.c
@@ -144,8 +144,7 @@ void i915_ttm_recover_region(struct intel_memory_region *mr)
 /**
  * i915_ttm_backup_region - Back up all objects of a region to smem.
  * @mr: The memory region
- * @allow_gpu: Whether to allow the gpu blitter for this backup.
- * @backup_pinned: Backup also pinned objects.
+ * @flags: TTM backup flags
  *
  * Loops over all objects of a region and either evicts them if they are
  * evictable or backs them up using a backup object if they are pinned.
@@ -212,7 +211,7 @@ static int i915_ttm_restore(struct i915_gem_apply_to_region *apply,
 /**
  * i915_ttm_restore_region - Restore backed-up objects of a region from smem.
  * @mr: The memory region
- * @allow_gpu: Whether to allow the gpu blitter to recover.
+ * @flags: TTM backup flags
  *
  * Loops over all objects of a region and if they are backed-up, restores
  * them from smem.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_wait.c b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
index e6e01c2a74a6..4a33ad2d122b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_wait.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_wait.c
@@ -161,7 +161,7 @@ i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 }
 
 /**
- * Waits for rendering to the object to be completed
+ * i915_gem_object_wait - Waits for rendering to the object to be completed
  * @obj: i915 gem object
  * @flags: how to wait (under a lock, for all rendering or just for writes etc)
  * @timeout: how long to wait
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index 0a8d553da3f4..48f888c3da08 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -14,6 +14,7 @@
 #include "i915_drv.h"
 #include "intel_context_types.h"
 #include "intel_engine_types.h"
+#include "intel_gt_pm.h"
 #include "intel_ring_types.h"
 #include "intel_timeline_types.h"
 #include "i915_trace.h"
@@ -207,8 +208,11 @@ void intel_context_exit_engine(struct intel_context *ce);
 static inline void intel_context_enter(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->timeline->mutex);
-	if (!ce->active_count++)
-		ce->ops->enter(ce);
+	if (ce->active_count++)
+		return;
+
+	ce->ops->enter(ce);
+	intel_gt_pm_get(ce->vm->gt);
 }
 
 static inline void intel_context_mark_active(struct intel_context *ce)
@@ -222,8 +226,11 @@ static inline void intel_context_exit(struct intel_context *ce)
 {
 	lockdep_assert_held(&ce->timeline->mutex);
 	GEM_BUG_ON(!ce->active_count);
-	if (!--ce->active_count)
-		ce->ops->exit(ce);
+	if (--ce->active_count)
+		return;
+
+	intel_gt_pm_put_async(ce->vm->gt);
+	ce->ops->exit(ce);
 }
 
 static inline struct intel_context *intel_context_get(struct intel_context *ce)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index ad3413242100..5c6c9a6d469c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1428,8 +1428,8 @@ create_kernel_context(struct intel_engine_cs *engine)
 						  &kernel, "kernel_context");
 }
 
-/**
- * intel_engines_init_common - initialize cengine state which might require hw access
+/*
+ * engine_init_common - initialize engine state which might require hw access
  * @engine: Engine to initialize.
  *
  * Initializes @engine@ structure members shared between legacy and execlists
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index e971b153fda9..ee531a5c142c 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -115,6 +115,15 @@ __queue_and_release_pm(struct i915_request *rq,
 	ENGINE_TRACE(engine, "parking\n");
 
 	/*
+	 * Open coded one half of intel_context_enter, which we have to omit
+	 * here (see the large comment below) and because the other part must
+	 * not be called due constructing directly with __i915_request_create
+	 * which increments active count via intel_context_mark_active.
+	 */
+	GEM_BUG_ON(rq->context->active_count != 1);
+	__intel_gt_pm_get(engine->gt);
+
+	/*
 	 * We have to serialise all potential retirement paths with our
 	 * submission, as we don't want to underflow either the
 	 * engine->wakeref.counter or our timeline->active_count.
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 0a071e5da1a8..960291f88fd6 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -53,6 +53,8 @@ struct intel_gt;
 struct intel_ring;
 struct intel_uncore;
 struct intel_breadcrumbs;
+struct intel_engine_cs;
+struct i915_perf_group;
 
 typedef u32 intel_engine_mask_t;
 #define ALL_ENGINES ((intel_engine_mask_t)~0ul)
@@ -617,6 +619,14 @@ struct intel_engine_cs {
 	} props, defaults;
 
 	I915_SELFTEST_DECLARE(struct fault_attr reset_timeout);
+
+	/*
+	 * The perf group maps to one OA unit which controls one OA buffer. All
+	 * reports corresponding to this engine will be reported to this OA
+	 * buffer. An engine will map to a single OA unit, but a single OA unit
+	 * can generate reports for multiple engines.
+	 */
+	struct i915_perf_group *oa_group;
 };
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 1bbe6708d0a7..750326434677 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2018,6 +2018,8 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)
 	 * inspecting the queue to see if we need to resumbit.
 	 */