Merge tag 'drm-intel-gt-next-2023-12-08' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

-   drm/i915: Implement fdinfo memory stats printing

    Use the newly added drm_print_memory_stats helper to show memory
    utilisation of our objects in drm/driver specific fdinfo output.

    To collect the stats we walk the per memory regions object lists
    and accumulate object size into the respective drm_memory_stats
    categories.

Cross-subsystem Changes:

- Backmerge of drm-next (to bring drm-intel-next for PXP changes)

Driver Changes:

- Wa_18028616096 now applies to all DG2 (Matt R)
- Drop Wa_22014600077 on all DG2 (Matt R)
- Add new ATS-M device ID (Haridhar)
- More Meteorlake (MTL) workarounds (Matt R, Dnyaneshwar, Jonathan,
  Gustavo, Radhakrishna)
- PMU WARN_ON cleanup on driver unbind (Umesh)
- Limit GGTT WC flushing workaround to pre BXT/ICL platforms
- Complement implementation for Wa_16018031267 / Wa_16018063123
  (Andrzej, Jonathan, Nirmoy, Chris)

- Properly print internal GSC engine in trace logs (Tvrtko)
- Track gt pm wakerefs (Andrzej)
- Fix null deref bugs on perf code when perf is disabled (Harshit,
  Tvrtko)
- Fix __i915_request_create memory leak on driver unbind (Andrzej)
- Remove spurious unsupported HuC message on MTL (Daniele)
- Read a shadowed mmio register for ggtt flush (Vinay)
- Add missing new-line to GT_TRACE (Andrzej)
- Add drm_dbgs for critical PXP events (Alan)
- Skip pxp init if gt is wedged (Zhanjun)

- Replace custom intel runtime_pm tracker with ref_tracker library
  (Andrzej)
- Compiler warning/static checker/coding style cleanups (Arnd, Nirmoy,
  Soumya, Gilbert, Dorcas, Kunwu, Sam, Tvrtko)
- Code structure and helper cleanups (Jani, Tvrtko, Andi)
- Selftest improvements (John, Tvrtko, Andrzej)

Signed-off-by: Dave Airlie <[email protected]>

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_gt_mcr.c
From: Joonas Lahtinen <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

drivers/gpu/drm/i915/Kconfig.debug

@@ -24,7 +24,9 @@ config DRM_I915_DEBUG
 	select DEBUG_FS
 	select PREEMPT_COUNT
 	select I2C_CHARDEV
+	select REF_TRACKER
 	select STACKDEPOT
+	select STACKTRACE
 	select DRM_DP_AUX_CHARDEV
 	select X86_MSR # used by igt/pm_rpm
 	select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
@@ -38,6 +40,7 @@ config DRM_I915_DEBUG
 	select DRM_I915_DEBUG_GEM_ONCE
 	select DRM_I915_DEBUG_MMIO
 	select DRM_I915_DEBUG_RUNTIME_PM
+	select DRM_I915_DEBUG_WAKEREF
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
 	select DRM_I915_SELFTEST
 	default n
@@ -231,7 +234,9 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	bool "Enable extra state checking for runtime PM"
 	depends on DRM_I915
 	default n
+	select REF_TRACKER
 	select STACKDEPOT
+	select STACKTRACE
 	help
 	  Choose this option to turn on extra state checking for the
 	  runtime PM functionality. This may introduce overhead during
@@ -240,3 +245,16 @@ config DRM_I915_DEBUG_RUNTIME_PM
 	  Recommended for driver developers only.
 
 	  If in doubt, say "N"
+
+config DRM_I915_DEBUG_WAKEREF
+	bool "Enable extra tracking for wakerefs"
+	depends on DRM_I915
+	select REF_TRACKER
+	select STACKDEPOT
+	select STACKTRACE
+	help
+	  Choose this option to turn on extra state checking and usage
+	  tracking for the wakerefPM functionality. This may introduce
+	  overhead during driver runtime.
+
+	  If in doubt, say "N"

drivers/gpu/drm/i915/display/intel_display_power.c

@@ -405,7 +405,7 @@ print_async_put_domains_state(struct i915_power_domains *power_domains)
 						     struct drm_i915_private,
 						     display.power.domains);
 
-	drm_dbg(&i915->drm, "async_put_wakeref %u\n",
+	drm_dbg(&i915->drm, "async_put_wakeref %lu\n",
 		power_domains->async_put_wakeref);
 
 	print_power_domains(power_domains, "async_put_domains[0]",

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

@@ -279,14 +279,16 @@ static int proto_context_set_protected(struct drm_i915_private *i915,
 }
 
 static struct i915_gem_proto_context *
-proto_context_create(struct drm_i915_private *i915, unsigned int flags)
+proto_context_create(struct drm_i915_file_private *fpriv,
+		     struct drm_i915_private *i915, unsigned int flags)
 {
 	struct i915_gem_proto_context *pc, *err;
 
 	pc = kzalloc(sizeof(*pc), GFP_KERNEL);
 	if (!pc)
 		return ERR_PTR(-ENOMEM);
 
+	pc->fpriv = fpriv;
 	pc->num_user_engines = -1;
 	pc->user_engines = NULL;
 	pc->user_flags = BIT(UCONTEXT_BANNABLE) |
@@ -1622,6 +1624,7 @@ i915_gem_create_context(struct drm_i915_private *i915,
 			err = PTR_ERR(ppgtt);
 			goto err_ctx;
 		}
+		ppgtt->vm.fpriv = pc->fpriv;
 		vm = &ppgtt->vm;
 	}
 	if (vm)
@@ -1741,7 +1744,7 @@ int i915_gem_context_open(struct drm_i915_private *i915,
 	/* 0 reserved for invalid/unassigned ppgtt */
 	xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
 
-	pc = proto_context_create(i915, 0);
+	pc = proto_context_create(file_priv, i915, 0);
 	if (IS_ERR(pc)) {
 		err = PTR_ERR(pc);
 		goto err;
@@ -1823,6 +1826,7 @@ int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
 
 	GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
 	args->vm_id = id;
+	ppgtt->vm.fpriv = file_priv;
 	return 0;
 
 err_put:
@@ -2285,7 +2289,8 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 		return -EIO;
 	}
 
-	ext_data.pc = proto_context_create(i915, args->flags);
+	ext_data.pc = proto_context_create(file->driver_priv, i915,
+					   args->flags);
 	if (IS_ERR(ext_data.pc))
 		return PTR_ERR(ext_data.pc);
 

drivers/gpu/drm/i915/gem/i915_gem_context_types.h

@@ -188,6 +188,9 @@ struct i915_gem_proto_engine {
  * CONTEXT_CREATE_SET_PARAM during GEM_CONTEXT_CREATE.
  */
 struct i915_gem_proto_context {
+	/** @fpriv: Client which creates the context */
+	struct drm_i915_file_private *fpriv;
+
 	/** @vm: See &i915_gem_context.vm */
 	struct i915_address_space *vm;
 

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -254,6 +254,8 @@ struct i915_execbuffer {
 	struct intel_gt *gt; /* gt for the execbuf */
 	struct intel_context *context; /* logical state for the request */
 	struct i915_gem_context *gem_context; /** caller's context */
+	intel_wakeref_t wakeref;
+	intel_wakeref_t wakeref_gt0;
 
 	/** our requests to build */
 	struct i915_request *requests[MAX_ENGINE_INSTANCE + 1];
@@ -1679,7 +1681,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 		urelocs = u64_to_user_ptr(eb->exec[i].relocs_ptr);
 		size = nreloc * sizeof(*relocs);
 
-		relocs = kvmalloc_array(size, 1, GFP_KERNEL);
+		relocs = kvmalloc_array(1, size, GFP_KERNEL);
 		if (!relocs) {
 			err = -ENOMEM;
 			goto err;
@@ -2720,13 +2722,13 @@ eb_select_engine(struct i915_execbuffer *eb)
 
 	for_each_child(ce, child)
 		intel_context_get(child);
-	intel_gt_pm_get(gt);
+	eb->wakeref = intel_gt_pm_get(ce->engine->gt);
 	/*
 	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
 	 * free VMAs while execbuf ioctl is validating VMAs.
 	 */
 	if (gt->info.id)
-		intel_gt_pm_get(to_gt(gt->i915));
+		eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2766,9 +2768,9 @@ eb_select_engine(struct i915_execbuffer *eb)
 
 err:
 	if (gt->info.id)
-		intel_gt_pm_put(to_gt(gt->i915));
+		intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0);
 
-	intel_gt_pm_put(gt);
+	intel_gt_pm_put(ce->engine->gt, eb->wakeref);
 	for_each_child(ce, child)
 		intel_context_put(child);
 	intel_context_put(ce);
@@ -2786,8 +2788,8 @@ eb_put_engine(struct i915_execbuffer *eb)
 	 * i915_vma_parked() from interfering while execbuf validates vmas.
 	 */
 	if (eb->gt->info.id)
-		intel_gt_pm_put(to_gt(eb->gt->i915));
-	intel_gt_pm_put(eb->gt);
+		intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0);
+	intel_gt_pm_put(eb->context->engine->gt, eb->wakeref);
 	for_each_child(eb->context, child)
 		intel_context_put(child);
 	intel_context_put(eb->context);

drivers/gpu/drm/i915/gem/i915_gem_object.c

@@ -106,6 +106,10 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 
 	INIT_LIST_HEAD(&obj->mm.link);
 
+#ifdef CONFIG_PROC_FS
+	INIT_LIST_HEAD(&obj->client_link);
+#endif
+
 	INIT_LIST_HEAD(&obj->lut_list);
 	spin_lock_init(&obj->lut_lock);
 
@@ -293,6 +297,10 @@ void __i915_gem_free_object_rcu(struct rcu_head *head)
 		container_of(head, typeof(*obj), rcu);
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 
+	/* We need to keep this alive for RCU read access from fdinfo. */
+	if (obj->mm.n_placements > 1)
+		kfree(obj->mm.placements);
+
 	i915_gem_object_free(obj);
 
 	GEM_BUG_ON(!atomic_read(&i915->mm.free_count));
@@ -389,9 +397,6 @@ void __i915_gem_free_object(struct drm_i915_gem_object *obj)
 	if (obj->ops->release)
 		obj->ops->release(obj);
 
-	if (obj->mm.n_placements > 1)
-		kfree(obj->mm.placements);
-
 	if (obj->shares_resv_from)
 		i915_vm_resv_put(obj->shares_resv_from);
 
@@ -442,6 +447,8 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj)
 
 	GEM_BUG_ON(i915_gem_object_is_framebuffer(obj));
 
+	i915_drm_client_remove_object(obj);
+
 	/*
 	 * Before we free the object, make sure any pure RCU-only
 	 * read-side critical sections are complete, e.g.

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -302,6 +302,18 @@ struct drm_i915_gem_object {
 	 */
 	struct i915_address_space *shares_resv_from;
 
+#ifdef CONFIG_PROC_FS
+	/**
+	 * @client: @i915_drm_client which created the object
+	 */
+	struct i915_drm_client *client;
+
+	/**
+	 * @client_link: Link into @i915_drm_client.objects_list
+	 */
+	struct list_head client_link;
+#endif
+
 	union {
 		struct rcu_head rcu;
 		struct llist_node freed;

drivers/gpu/drm/i915/gem/i915_gem_stolen.c

@@ -386,6 +386,27 @@ static void icl_get_stolen_reserved(struct drm_i915_private *i915,
 
 	drm_dbg(&i915->drm, "GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
 
+	/* Wa_14019821291 */
+	if (MEDIA_VER_FULL(i915) == IP_VER(13, 0)) {
+		/*
+		 * This workaround is primarily implemented by the BIOS.  We
+		 * just need to figure out whether the BIOS has applied the
+		 * workaround (meaning the programmed address falls within
+		 * the DSM) and, if so, reserve that part of the DSM to
+		 * prevent accidental reuse.  The DSM location should be just
+		 * below the WOPCM.
+		 */
+		u64 gscpsmi_base = intel_uncore_read64_2x32(uncore,
+							    MTL_GSCPSMI_BASEADDR_LSB,
+							    MTL_GSCPSMI_BASEADDR_MSB);
+		if (gscpsmi_base >= i915->dsm.stolen.start &&
+		    gscpsmi_base < i915->dsm.stolen.end) {
+			*base = gscpsmi_base;
+			*size = i915->dsm.stolen.end - gscpsmi_base;
+			return;
+		}
+	}
+
 	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
 	case GEN8_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;

drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c

@@ -85,6 +85,7 @@ static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 
 static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
@@ -99,7 +100,7 @@ static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
@@ -112,12 +113,13 @@ static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 	i915_vma_unpin_iomap(vma);
 
 out_rpm:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
 static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
@@ -132,7 +134,7 @@ static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
@@ -145,7 +147,7 @@ static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 	i915_vma_unpin_iomap(vma);
 
 out_rpm:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 

drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c

@@ -630,14 +630,14 @@ static bool assert_mmap_offset(struct drm_i915_private *i915,
 static void disable_retire_worker(struct drm_i915_private *i915)
 {
 	i915_gem_driver_unregister__shrinker(i915);
-	intel_gt_pm_get(to_gt(i915));
+	intel_gt_pm_get_untracked(to_gt(i915));
 	cancel_delayed_work_sync(&to_gt(i915)->requests.retire_work);
 }
 
 static void restore_retire_worker(struct drm_i915_private *i915)
 {
 	igt_flush_test(i915);
-	intel_gt_pm_put(to_gt(i915));
+	intel_gt_pm_put_untracked(to_gt(i915));
 	i915_gem_driver_register__shrinker(i915);
 }
 
@@ -778,6 +778,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 static int gtt_set(struct drm_i915_gem_object *obj)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	void __iomem *map;
 	int err = 0;
@@ -786,7 +787,7 @@ static int gtt_set(struct drm_i915_gem_object *obj)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
 	if (IS_ERR(map)) {
@@ -798,12 +799,13 @@ static int gtt_set(struct drm_i915_gem_object *obj)
 	i915_vma_unpin_iomap(vma);
 
 out:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }
 
 static int gtt_check(struct drm_i915_gem_object *obj)
 {
+	intel_wakeref_t wakeref;
 	struct i915_vma *vma;
 	void __iomem *map;
 	int err = 0;
@@ -812,7 +814,7 @@ static int gtt_check(struct drm_i915_gem_object *obj)
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	intel_gt_pm_get(vma->vm->gt);
+	wakeref = intel_gt_pm_get(vma->vm->gt);
 	map = i915_vma_pin_iomap(vma);
 	i915_vma_unpin(vma);
 	if (IS_ERR(map)) {
@@ -828,7 +830,7 @@ static int gtt_check(struct drm_i915_gem_object *obj)
 	i915_vma_unpin_iomap(vma);
 
 out:
-	intel_gt_pm_put(vma->vm->gt);
+	intel_gt_pm_put(vma->vm->gt, wakeref);
 	return err;
 }