Merge tag 'drm-intel-gt-next-2022-03-03' of git://anongit.freedesktop…

….org/drm/drm-intel into drm-next

Cross-subsystem Changes:

- drm-next backmerge for buddy allocator changes

Driver Changes:

- Skip i915_perf init for DG2 as it is not yet enabled (Ram)
- Add missing workarounds for DG2 (Clint)
- Add 64K page/align support for platforms like DG2 that require it (Matt A, Ram, Bob)
- Add accelerated migration support for DG2 (Matt A)
- Add flat CCS support for XeHP SDV (Abdiel, Ram)
- Add Compute Command Streamer (CCS) engine support for XeHP SDV (Michel,
  Daniele, Aravind, Matt R)
- Don't support parallel submission on compute / render (Matt B, Matt R)

- Disable i915 build on PREEMPT_RT until RT behaviour fixed (Sebastian)
- Remove RPS interrupt support for TGL+ (Jose)
- Fix S/R with PM_EARLY for non-GTT mappable objects on DG2 (Matt, Lucas)
- Skip stolen memory init if it is fully reserved (Jose)
- Use iosys_map for GuC data structures that may be in LMEM BAR or SMEM (Lucas)
- Do not complain about stale GuC reset notifications for banned contexts (John)

- Move context descriptor fields to intel_lrc.h
- Start adding support for small BAR (Matt A)
- Clarify vma lifetime (Thomas)
- Simplify subplatform detection on TGL (Jose)
- Correct the param count for unset GuC SLPC param (Vinay, Umesh)
- Read RP_STATE_CAP correctly on Gen12 with GuC SLPC (Vinay)
- Initialize GuC submission locks and queues early (Daniele)
- Fix GuC flag query helper function to not modify state (John)

- Drop fake lmem support now we have real hardware available (Lucas)
- Move misplaced W/A to their correct locations (Srinivasan)
- Use get_reset_domain() helper (Tejas)
- Move context descriptor fields to intel_lrc.h (Matt R)
- Selftest improvements (Matt A)

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YiBzY1dM7bKwMQ3H@jlahtine-mobl.ger.corp.intel.com

drivers/gpu/drm/i915/Kconfig

@@ -3,6 +3,7 @@ config DRM_I915
 	tristate "Intel 8xx/9xx/G3x/G4x/HD Graphics"
 	depends on DRM
 	depends on X86 && PCI
+	depends on !PREEMPT_RT
 	select INTEL_GTT
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular

drivers/gpu/drm/i915/Kconfig.unstable

@@ -19,11 +19,3 @@ config DRM_I915_UNSTABLE
 	  Recommended for driver developers _only_.
 
 	  If in the slightest bit of doubt, say "N".
-
-config DRM_I915_UNSTABLE_FAKE_LMEM
-	bool "Enable the experimental fake lmem"
-	depends on DRM_I915_UNSTABLE
-	default n
-	help
-	  Convert some system memory into a fake local memory region for
-	  testing.

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

@@ -1321,7 +1321,7 @@ tgl_get_combo_buf_trans_dp(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
 	if (crtc_state->port_clock > 270000) {
-		if (IS_TGL_U(dev_priv) || IS_TGL_Y(dev_priv)) {
+		if (IS_TGL_UY(dev_priv)) {
 			return intel_get_buf_trans(&tgl_uy_combo_phy_trans_dp_hbr2,
 						   n_entries);
 		} else {

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

@@ -265,7 +265,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		struct intel_memory_region *mem = obj->mm.region;
 
 		info->apertures->ranges[0].base = mem->io_start;
-		info->apertures->ranges[0].size = mem->total;
+		info->apertures->ranges[0].size = mem->io_size;
 
 		/* Use fbdev's framebuffer from lmem for discrete */
 		info->fix.smem_start =

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

@@ -670,6 +670,16 @@ set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
 				goto out_err;
 			}
 
+			/*
+			 * We don't support breadcrumb handshake on these
+			 * classes
+			 */
+			if (siblings[n]->class == RENDER_CLASS ||
+			    siblings[n]->class == COMPUTE_CLASS) {
+				err = -EINVAL;
+				goto out_err;
+			}
+
 			if (n) {
 				if (prev_engine.engine_class !=
 				    ci.engine_class) {

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

@@ -272,26 +272,14 @@ void __i915_gem_object_pages_fini(struct drm_i915_gem_object *obj)
 	if (!list_empty(&obj->vma.list)) {
 		struct i915_vma *vma;
 
-		/*
-		 * Note that the vma keeps an object reference while
-		 * it is active, so it *should* not sleep while we
-		 * destroy it. Our debug code errs insits it *might*.
-		 * For the moment, play along.
-		 */
 		spin_lock(&obj->vma.lock);
 		while ((vma = list_first_entry_or_null(&obj->vma.list,
 						       struct i915_vma,
 						       obj_link))) {
 			GEM_BUG_ON(vma->obj != obj);
 			spin_unlock(&obj->vma.lock);
 
-			/* Verify that the vma is unbound under the vm mutex. */
-			mutex_lock(&vma->vm->mutex);
-			atomic_and(~I915_VMA_PIN_MASK, &vma->flags);
-			__i915_vma_unbind(vma);
-			mutex_unlock(&vma->vm->mutex);
-
-			__i915_vma_put(vma);
+			i915_vma_destroy(vma);
 
 			spin_lock(&obj->vma.lock);
 		}

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

@@ -319,16 +319,23 @@ struct drm_i915_gem_object {
 #define I915_BO_ALLOC_PM_VOLATILE BIT(4)
 /* Object needs to be restored early using memcpy during resume */
 #define I915_BO_ALLOC_PM_EARLY    BIT(5)
+/*
+ * Object is likely never accessed by the CPU. This will prioritise the BO to be
+ * allocated in the non-mappable portion of lmem. This is merely a hint, and if
+ * dealing with userspace objects the CPU fault handler is free to ignore this.
+ */
+#define I915_BO_ALLOC_GPU_ONLY	  BIT(6)
 #define I915_BO_ALLOC_FLAGS (I915_BO_ALLOC_CONTIGUOUS | \
 			     I915_BO_ALLOC_VOLATILE | \
 			     I915_BO_ALLOC_CPU_CLEAR | \
 			     I915_BO_ALLOC_USER | \
 			     I915_BO_ALLOC_PM_VOLATILE | \
-			     I915_BO_ALLOC_PM_EARLY)
-#define I915_BO_READONLY          BIT(6)
-#define I915_TILING_QUIRK_BIT     7 /* unknown swizzling; do not release! */
-#define I915_BO_PROTECTED         BIT(8)
-#define I915_BO_WAS_BOUND_BIT     9
+			     I915_BO_ALLOC_PM_EARLY | \
+			     I915_BO_ALLOC_GPU_ONLY)
+#define I915_BO_READONLY          BIT(7)
+#define I915_TILING_QUIRK_BIT     8 /* unknown swizzling; do not release! */
+#define I915_BO_PROTECTED         BIT(9)
+#define I915_BO_WAS_BOUND_BIT     10
 	/**
 	 * @mem_flags - Mutable placement-related flags
 	 *

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -358,6 +358,9 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 	    !i915_gem_object_has_iomem(obj))
 		return ERR_PTR(-ENXIO);
 
+	if (WARN_ON_ONCE(obj->flags & I915_BO_ALLOC_GPU_ONLY))
+		return ERR_PTR(-EINVAL);
+
 	assert_object_held(obj);
 
 	pinned = !(type & I915_MAP_OVERRIDE);

drivers/gpu/drm/i915/gem/i915_gem_region.c

@@ -45,6 +45,11 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 
 	GEM_BUG_ON(flags & ~I915_BO_ALLOC_FLAGS);
 
+	if (WARN_ON_ONCE(flags & I915_BO_ALLOC_GPU_ONLY &&
+			 (flags & I915_BO_ALLOC_CPU_CLEAR ||
+			  flags & I915_BO_ALLOC_PM_EARLY)))
+		return ERR_PTR(-EINVAL);
+
 	if (!mem)
 		return ERR_PTR(-ENODEV);
 
@@ -67,6 +72,17 @@ i915_gem_object_create_region(struct intel_memory_region *mem,
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Anything smaller than the min_page_size can't be freely inserted into
+	 * the GTT, due to alignemnt restrictions. For such special objects,
+	 * make sure we force memcpy based suspend-resume. In the future we can
+	 * revisit this, either by allowing special mis-aligned objects in the
+	 * migration path, or by mapping all of LMEM upfront using cheap 1G
+	 * GTT entries.
+	 */
+	if (default_page_size < mem->min_page_size)
+		flags |= I915_BO_ALLOC_PM_EARLY;
+
 	err = mem->ops->init_object(mem, obj, size, page_size, flags);
 	if (err)
 		goto err_object_free;

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -699,7 +699,7 @@ struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915,
 {
 	return intel_memory_region_create(i915, 0,
 					  totalram_pages() << PAGE_SHIFT,
-					  PAGE_SIZE, 0,
+					  PAGE_SIZE, 0, 0,
 					  type, instance,
 					  &shmem_region_ops);
 }

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

@@ -492,18 +492,22 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem)
 
 	/* Exclude the reserved region from driver use */
 	mem->region.end = reserved_base - 1;
+	mem->io_size = resource_size(&mem->region);
 
 	/* It is possible for the reserved area to end before the end of stolen
 	 * memory, so just consider the start. */
 	reserved_total = stolen_top - reserved_base;
 
+	i915->stolen_usable_size =
+		resource_size(&i915->dsm) - reserved_total;
+
 	drm_dbg(&i915->drm,
 		"Memory reserved for graphics device: %lluK, usable: %lluK\n",
 		(u64)resource_size(&i915->dsm) >> 10,
-		((u64)resource_size(&i915->dsm) - reserved_total) >> 10);
+		(u64)i915->stolen_usable_size >> 10);
 
-	i915->stolen_usable_size =
-		resource_size(&i915->dsm) - reserved_total;
+	if (i915->stolen_usable_size == 0)
+		return 0;
 
 	/* Basic memrange allocator for stolen space. */
 	drm_mm_init(&i915->mm.stolen, 0, i915->stolen_usable_size);
@@ -748,7 +752,7 @@ static int init_stolen_lmem(struct intel_memory_region *mem)
 
 	if (!io_mapping_init_wc(&mem->iomap,
 				mem->io_start,
-				resource_size(&mem->region)))
+				mem->io_size))
 		return -EIO;
 
 	/*
@@ -803,7 +807,8 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 						I915_GTT_PAGE_SIZE_4K;
 
 	mem = intel_memory_region_create(i915, lmem_base, lmem_size,
-					 min_page_size, io_start,
+					 min_page_size,
+					 io_start, lmem_size,
 					 type, instance,
 					 &i915_region_stolen_lmem_ops);
 	if (IS_ERR(mem))
@@ -834,7 +839,7 @@ i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type,
 	mem = intel_memory_region_create(i915,
 					 intel_graphics_stolen_res.start,
 					 resource_size(&intel_graphics_stolen_res),
-					 PAGE_SIZE, 0, type, instance,
+					 PAGE_SIZE, 0, 0, type, instance,
 					 &i915_region_stolen_smem_ops);
 	if (IS_ERR(mem))
 		return mem;