Commit 213d5092 authored by Thomas Hellström's avatar Thomas Hellström Committed by Maarten Lankhorst
Browse files

drm/i915/ttm: Introduce a TTM i915 gem object backend 



Most logical place to introduce TTM buffer objects is as an i915
gem object backend. We need to add some ops to account for added
functionality like delayed delete and LRU list manipulation.

Initially we support only LMEM and SYSTEM memory, but SYSTEM
(which in this case means evicted LMEM objects) is not
visible to i915 GEM yet. The plan is to move the i915 gem system region
over to the TTM system memory type in upcoming patches.

We set up GPU bindings directly both from LMEM and from the system region,
as there is no need to use the legacy TTM_TT memory type. We reserve
that for future porting of GGTT bindings to TTM.

Remove the old lmem backend.

Signed-off-by: default avatarThomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: default avatarMatthew Auld <matthew.auld@intel.com>
Signed-off-by: default avatarMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210610070152.572423-2-thomas.hellstrom@linux.intel.com
parent 1bd8a7dc

drivers/gpu/drm/i915/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -155,6 +155,7 @@ gem-y += \ 
	gem/i915_gem_stolen.o \

	gem/i915_gem_throttle.o \

	gem/i915_gem_tiling.o \

	gem/i915_gem_ttm.o \

	gem/i915_gem_userptr.o \

	gem/i915_gem_wait.o \

	gem/i915_gemfs.o

drivers/gpu/drm/i915/gem/i915_gem_create.c

+3 −6
Original line number Diff line number Diff line
@@ -85,13 +85,10 @@ i915_gem_setup(struct drm_i915_gem_object *obj, u64 size) 
		return -E2BIG;



	/*

	 * For now resort to CPU based clearing for device local-memory, in the

	 * near future this will use the blitter engine for accelerated, GPU

	 * based clearing.

	 * I915_BO_ALLOC_USER will make sure the object is cleared before

	 * any user access.

	 */

	flags = 0;

	if (mr->type == INTEL_MEMORY_LOCAL)

		flags = I915_BO_ALLOC_CPU_CLEAR;

	flags = I915_BO_ALLOC_USER;



	ret = mr->ops->init_object(mr, obj, size, flags);

	if (ret)

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

+0 −84
Original line number Diff line number Diff line
@@ -4,74 +4,10 @@ 
 */



#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 = lmem_get_pages,

	.put_pages = lmem_put_pages,

	.release = i915_gem_object_release_memory_region,

};



void __iomem *

i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,

			    unsigned long n,
@@ -103,23 +39,3 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915, 
	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],

					     size, flags);

}
 


int __i915_gem_lmem_object_init(struct intel_memory_region *mem,

				struct drm_i915_gem_object *obj,

				resource_size_t size,

				unsigned int flags)

{

	static struct lock_class_key lock_class;

	struct drm_i915_private *i915 = mem->i915;



	drm_gem_private_object_init(&i915->drm, &obj->base, size);

	i915_gem_object_init(obj, &i915_gem_lmem_obj_ops, &lock_class, flags);



	obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;



	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);



	i915_gem_object_init_memory_region(obj, mem);



	return 0;

}

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

+0 −5
Original line number Diff line number Diff line
@@ -26,9 +26,4 @@ i915_gem_object_create_lmem(struct drm_i915_private *i915, 
			    resource_size_t size,

			    unsigned int flags);



int __i915_gem_lmem_object_init(struct intel_memory_region *mem,

				struct drm_i915_gem_object *obj,

				resource_size_t size,

				unsigned int flags);



#endif /* !__I915_GEM_LMEM_H */

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

+86 −39
Original line number Diff line number Diff line
@@ -172,7 +172,7 @@ static void i915_gem_close_object(struct drm_gem_object *gem, struct drm_file *f 
	}

}



static void __i915_gem_free_object_rcu(struct rcu_head *head)

void __i915_gem_free_object_rcu(struct rcu_head *head)

{

	struct drm_i915_gem_object *obj =

		container_of(head, typeof(*obj), rcu);
@@ -208,12 +208,8 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) 
	}

}



static void __i915_gem_free_objects(struct drm_i915_private *i915,

				    struct llist_node *freed)

void __i915_gem_free_object(struct drm_i915_gem_object *obj)

{

	struct drm_i915_gem_object *obj, *on;



	llist_for_each_entry_safe(obj, on, freed, freed) {

	trace_i915_gem_object_destroy(obj);



	if (!list_empty(&obj->vma.list)) {
@@ -261,6 +257,20 @@ static void __i915_gem_free_objects(struct drm_i915_private *i915, 


	if (obj->shares_resv_from)

		i915_vm_resv_put(obj->shares_resv_from);

}



static void __i915_gem_free_objects(struct drm_i915_private *i915,

				    struct llist_node *freed)

{

	struct drm_i915_gem_object *obj, *on;



	llist_for_each_entry_safe(obj, on, freed, freed) {

		might_sleep();

		if (obj->ops->delayed_free) {

			obj->ops->delayed_free(obj);

			continue;

		}

		__i915_gem_free_object(obj);



		/* But keep the pointer alive for RCU-protected lookups */

		call_rcu(&obj->rcu, __i915_gem_free_object_rcu);
@@ -318,6 +328,7 @@ static void i915_gem_free_object(struct drm_gem_object *gem_obj) 
	 * worker and performing frees directly from subsequent allocations for

	 * crude but effective memory throttling.

	 */



	if (llist_add(&obj->freed, &i915->mm.free_list))

		queue_work(i915->wq, &i915->mm.free_work);

}
@@ -410,6 +421,42 @@ int i915_gem_object_read_from_page(struct drm_i915_gem_object *obj, u64 offset, 
	return 0;

}



/**

 * i915_gem_object_evictable - Whether object is likely evictable after unbind.

 * @obj: The object to check

 *

 * This function checks whether the object is likely unvictable after unbind.

 * If the object is not locked when checking, the result is only advisory.

 * If the object is locked when checking, and the function returns true,

 * then an eviction should indeed be possible. But since unlocked vma

 * unpinning and unbinding is currently possible, the object can actually

 * become evictable even if this function returns false.

 *

 * Return: true if the object may be evictable. False otherwise.

 */

bool i915_gem_object_evictable(struct drm_i915_gem_object *obj)

{

	struct i915_vma *vma;

	int pin_count = atomic_read(&obj->mm.pages_pin_count);



	if (!pin_count)

		return true;



	spin_lock(&obj->vma.lock);

	list_for_each_entry(vma, &obj->vma.list, obj_link) {

		if (i915_vma_is_pinned(vma)) {

			spin_unlock(&obj->vma.lock);

			return false;

		}

		if (atomic_read(&vma->pages_count))

			pin_count--;

	}

	spin_unlock(&obj->vma.lock);

	GEM_WARN_ON(pin_count < 0);



	return pin_count == 0;

}



void i915_gem_init__objects(struct drm_i915_private *i915)

{

	INIT_WORK(&i915->mm.free_work, __i915_gem_free_work);