Merge tag 'drm-intel-gt-next-2021-06-10' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

UAPI Changes:

- Disable mmap ioctl for gen12+ (excl. TGL-LP)
- Start enabling HuC loading by default for upcoming Gen12+
  platforms (excludes TGL and RKL)

Core Changes:

- Backmerge of drm-next

Driver Changes:

- Revert "i915: use io_mapping_map_user" (Eero, Matt A)
- Initialize the TTM device and memory managers (Thomas)
- Major rework to the GuC submission backend to prepare
  for enabling on new platforms (Michal Wa., Daniele,
  Matt B, Rodrigo)
- Fix i915_sg_page_sizes to record dma segments rather
  than physical pages (Thomas)

- Locking rework to prep for TTM conversion (Thomas)
- Replace IS_GEN and friends with GRAPHICS_VER (Lucas)
- Use DEVICE_ATTR_RO macro (Yue)
- Static code checker fixes (Zhihao)

Signed-off-by: Dave Airlie <[email protected]>
From: Joonas Lahtinen <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

drivers/gpu/drm/i915/Kconfig

@@ -20,13 +20,13 @@ config DRM_I915
 	select INPUT if ACPI
 	select ACPI_VIDEO if ACPI
 	select ACPI_BUTTON if ACPI
-	select IO_MAPPING
 	select SYNC_FILE
 	select IOSF_MBI
 	select CRC32
 	select SND_HDA_I915 if SND_HDA_CORE
 	select CEC_CORE if CEC_NOTIFIER
 	select VMAP_PFN
+	select DRM_TTM
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,

drivers/gpu/drm/i915/Makefile

@@ -50,6 +50,7 @@ i915-y += i915_drv.o \
 	  intel_memory_region.o \
 	  intel_pch.o \
 	  intel_pm.o \
+	  intel_region_ttm.o \
 	  intel_runtime_pm.o \
 	  intel_sideband.o \
 	  intel_step.o \
@@ -160,7 +161,6 @@ gem-y += \
 i915-y += \
 	  $(gem-y) \
 	  i915_active.o \
-	  i915_buddy.o \
 	  i915_cmd_parser.o \
 	  i915_gem_evict.o \
 	  i915_gem_gtt.o \

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

@@ -1190,7 +1190,7 @@ static void set_ppgtt_barrier(void *data)
 {
 	struct i915_address_space *old = data;
 
-	if (INTEL_GEN(old->i915) < 8)
+	if (GRAPHICS_VER(old->i915) < 8)
 		gen6_ppgtt_unpin_all(i915_vm_to_ppgtt(old));
 
 	i915_vm_close(old);
@@ -1436,7 +1436,7 @@ i915_gem_user_to_context_sseu(struct intel_gt *gt,
 	context->max_eus_per_subslice = user->max_eus_per_subslice;
 
 	/* Part specific restrictions. */
-	if (IS_GEN(i915, 11)) {
+	if (GRAPHICS_VER(i915) == 11) {
 		unsigned int hw_s = hweight8(device->slice_mask);
 		unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
 		unsigned int req_s = hweight8(context->slice_mask);
@@ -1503,7 +1503,7 @@ static int set_sseu(struct i915_gem_context *ctx,
 	if (args->size < sizeof(user_sseu))
 		return -EINVAL;
 
-	if (!IS_GEN(i915, 11))
+	if (GRAPHICS_VER(i915) != 11)
 		return -ENODEV;
 
 	if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),

drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c

@@ -209,7 +209,7 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
-	sg_page_sizes = i915_sg_page_sizes(pages->sgl);
+	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);
 
 	__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
 

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

@@ -500,7 +500,7 @@ eb_validate_vma(struct i915_execbuffer *eb,
 	 * also covers all platforms with local memory.
 	 */
 	if (entry->relocation_count &&
-	    INTEL_GEN(eb->i915) >= 12 && !IS_TIGERLAKE(eb->i915))
+	    GRAPHICS_VER(eb->i915) >= 12 && !IS_TIGERLAKE(eb->i915))
 		return -EINVAL;
 
 	if (unlikely(entry->flags & eb->invalid_flags))
@@ -1439,7 +1439,7 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 
 static bool reloc_can_use_engine(const struct intel_engine_cs *engine)
 {
-	return engine->class != VIDEO_DECODE_CLASS || !IS_GEN(engine->i915, 6);
+	return engine->class != VIDEO_DECODE_CLASS || GRAPHICS_VER(engine->i915) != 6;
 }
 
 static u32 *reloc_gpu(struct i915_execbuffer *eb,
@@ -1671,7 +1671,7 @@ eb_relocate_entry(struct i915_execbuffer *eb,
 		 * batchbuffers.
 		 */
 		if (reloc->write_domain == I915_GEM_DOMAIN_INSTRUCTION &&
-		    IS_GEN(eb->i915, 6)) {
+		    GRAPHICS_VER(eb->i915) == 6) {
 			err = i915_vma_bind(target->vma,
 					    target->vma->obj->cache_level,
 					    PIN_GLOBAL, NULL);
@@ -2332,7 +2332,7 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	u32 *cs;
 	int i;
 
-	if (!IS_GEN(rq->engine->i915, 7) || rq->engine->id != RCS0) {
+	if (GRAPHICS_VER(rq->engine->i915) != 7 || rq->engine->id != RCS0) {
 		drm_dbg(&rq->engine->i915->drm, "sol reset is gen7/rcs only\n");
 		return -EINVAL;
 	}
@@ -3375,7 +3375,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
-		if (INTEL_GEN(i915) >= 11)
+		if (GRAPHICS_VER(i915) >= 11)
 			return -ENODEV;
 
 		/* Return -EPERM to trigger fallback code on old binaries. */

drivers/gpu/drm/i915/gem/i915_gem_lmem.c

@@ -4,16 +4,71 @@
  */
 
 #include "intel_memory_region.h"
+#include "intel_region_ttm.h"
 #include "gem/i915_gem_region.h"
 #include "gem/i915_gem_lmem.h"
 #include "i915_drv.h"
 
+static void lmem_put_pages(struct drm_i915_gem_object *obj,
+			   struct sg_table *pages)
+{
+	intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+	obj->mm.dirty = false;
+	sg_free_table(pages);
+	kfree(pages);
+}
+
+static int lmem_get_pages(struct drm_i915_gem_object *obj)
+{
+	unsigned int flags;
+	struct sg_table *pages;
+
+	flags = I915_ALLOC_MIN_PAGE_SIZE;
+	if (obj->flags & I915_BO_ALLOC_CONTIGUOUS)
+		flags |= I915_ALLOC_CONTIGUOUS;
+
+	obj->mm.st_mm_node = intel_region_ttm_node_alloc(obj->mm.region,
+							 obj->base.size,
+							 flags);
+	if (IS_ERR(obj->mm.st_mm_node))
+		return PTR_ERR(obj->mm.st_mm_node);
+
+	/* Range manager is always contigous */
+	if (obj->mm.region->is_range_manager)
+		obj->flags |= I915_BO_ALLOC_CONTIGUOUS;
+	pages = intel_region_ttm_node_to_st(obj->mm.region, obj->mm.st_mm_node);
+	if (IS_ERR(pages)) {
+		intel_region_ttm_node_free(obj->mm.region, obj->mm.st_mm_node);
+		return PTR_ERR(pages);
+	}
+
+	__i915_gem_object_set_pages(obj, pages, i915_sg_dma_sizes(pages->sgl));
+
+	if (obj->flags & I915_BO_ALLOC_CPU_CLEAR) {
+		void __iomem *vaddr =
+			i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
+
+		if (!vaddr) {
+			struct sg_table *pages =
+				__i915_gem_object_unset_pages(obj);
+
+			if (!IS_ERR_OR_NULL(pages))
+				lmem_put_pages(obj, pages);
+		}
+
+		memset_io(vaddr, 0, obj->base.size);
+		io_mapping_unmap(vaddr);
+	}
+
+	return 0;
+}
+
 const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
 	.name = "i915_gem_object_lmem",
 	.flags = I915_GEM_OBJECT_HAS_IOMEM,
 
-	.get_pages = i915_gem_object_get_pages_buddy,
-	.put_pages = i915_gem_object_put_pages_buddy,
+	.get_pages = lmem_get_pages,
+	.put_pages = lmem_put_pages,
 	.release = i915_gem_object_release_memory_region,
 };
 

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

@@ -56,10 +56,17 @@ int
 i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
 		    struct drm_file *file)
 {
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_mmap *args = data;
 	struct drm_i915_gem_object *obj;
 	unsigned long addr;
 
+	/* mmap ioctl is disallowed for all platforms after TGL-LP.  This also
+	 * covers all platforms with local memory.
+	 */
+	if (GRAPHICS_VER(i915) >= 12 && !IS_TIGERLAKE(i915))
+		return -EOPNOTSUPP;
+
 	if (args->flags & ~(I915_MMAP_WC))
 		return -EINVAL;
 
@@ -367,10 +374,11 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 		goto err_unpin;
 
 	/* Finally, remap it using the new GTT offset */
-	ret = io_mapping_map_user(&ggtt->iomap, area, area->vm_start +
-			(vma->ggtt_view.partial.offset << PAGE_SHIFT),
-			(ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT,
-			min_t(u64, vma->size, area->vm_end - area->vm_start));
+	ret = remap_io_mapping(area,
+			       area->vm_start + (vma->ggtt_view.partial.offset << PAGE_SHIFT),
+			       (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT,
+			       min_t(u64, vma->size, area->vm_end - area->vm_start),
+			       &ggtt->iomap);
 	if (ret)
 		goto err_fence;
 

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

@@ -62,6 +62,13 @@ void i915_gem_object_init(struct drm_i915_gem_object *obj,
 			  const struct drm_i915_gem_object_ops *ops,
 			  struct lock_class_key *key, unsigned flags)
 {
+	/*
+	 * A gem object is embedded both in a struct ttm_buffer_object :/ and
+	 * in a drm_i915_gem_object. Make sure they are aliased.
+	 */
+	BUILD_BUG_ON(offsetof(typeof(*obj), base) !=
+		     offsetof(typeof(*obj), __do_not_access.base));
+
 	spin_lock_init(&obj->vma.lock);
 	INIT_LIST_HEAD(&obj->vma.list);
 
@@ -252,6 +259,9 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915,
 		if (obj->mm.n_placements > 1)
 			kfree(obj->mm.placements);
 
+		if (obj->shares_resv_from)
+			i915_vm_resv_put(obj->shares_resv_from);
+
 		/* But keep the pointer alive for RCU-protected lookups */
 		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
 		cond_resched();

drivers/gpu/drm/i915/gem/i915_gem_object_blt.c

@@ -72,7 +72,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 
 		GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
 
-		if (INTEL_GEN(i915) >= 8) {
+		if (GRAPHICS_VER(i915) >= 8) {
 			*cmd++ = XY_COLOR_BLT_CMD | BLT_WRITE_RGBA | (7 - 2);
 			*cmd++ = BLT_DEPTH_32 | BLT_ROP_COLOR_COPY | PAGE_SIZE;
 			*cmd++ = 0;
@@ -232,7 +232,7 @@ static bool wa_1209644611_applies(struct drm_i915_private *i915, u32 size)
 {
 	u32 height = size >> PAGE_SHIFT;
 
-	if (!IS_GEN(i915, 11))
+	if (GRAPHICS_VER(i915) != 11)
 		return false;
 
 	return height % 4 == 3 && height <= 8;
@@ -297,7 +297,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 		size = min_t(u64, rem, block_size);
 		GEM_BUG_ON(size >> PAGE_SHIFT > S16_MAX);
 
-		if (INTEL_GEN(i915) >= 9 &&
+		if (GRAPHICS_VER(i915) >= 9 &&
 		    !wa_1209644611_applies(i915, size)) {
 			*cmd++ = GEN9_XY_FAST_COPY_BLT_CMD | (10 - 2);
 			*cmd++ = BLT_DEPTH_32 | PAGE_SIZE;
@@ -309,7 +309,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 			*cmd++ = PAGE_SIZE;
 			*cmd++ = lower_32_bits(src_offset);
 			*cmd++ = upper_32_bits(src_offset);
-		} else if (INTEL_GEN(i915) >= 8) {
+		} else if (GRAPHICS_VER(i915) >= 8) {
 			*cmd++ = XY_SRC_COPY_BLT_CMD | BLT_WRITE_RGBA | (10 - 2);
 			*cmd++ = BLT_DEPTH_32 | BLT_ROP_SRC_COPY | PAGE_SIZE;
 			*cmd++ = 0;

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

@@ -10,6 +10,7 @@
 #include <linux/mmu_notifier.h>
 
 #include <drm/drm_gem.h>
+#include <drm/ttm/ttm_bo_api.h>
 #include <uapi/drm/i915_drm.h>
 
 #include "i915_active.h"
@@ -99,7 +100,16 @@ struct i915_gem_object_page_iter {
 };
 
 struct drm_i915_gem_object {
-	struct drm_gem_object base;
+	/*
+	 * We might have reason to revisit the below since it wastes
+	 * a lot of space for non-ttm gem objects.
+	 * In any case, always use the accessors for the ttm_buffer_object
+	 * when accessing it.
+	 */
+	union {
+		struct drm_gem_object base;
+		struct ttm_buffer_object __do_not_access;
+	};
 
 	const struct drm_i915_gem_object_ops *ops;
 
@@ -149,6 +159,10 @@ struct drm_i915_gem_object {
 	 * when i915_gem_ww_ctx_backoff() or i915_gem_ww_ctx_fini() are called.
 	 */
 	struct list_head obj_link;
+	/**
+	 * @shared_resv_from: The object shares the resv from this vm.
+	 */
+	struct i915_address_space *shares_resv_from;
 
 	union {
 		struct rcu_head rcu;
@@ -231,10 +245,12 @@ struct drm_i915_gem_object {
 		 * Memory region for this object.
 		 */
 		struct intel_memory_region *region;
+
 		/**
-		 * List of memory region blocks allocated for this object.
+		 * Memory manager node allocated for this object.
 		 */
-		struct list_head blocks;
+		void *st_mm_node;
+
 		/**
 		 * Element within memory_region->objects or region->purgeable
 		 * if the object is marked as DONTNEED. Access is protected by