Commit 8ae275c2 authored by Maarten Lankhorst's avatar Maarten Lankhorst Committed by Joonas Lahtinen
Browse files

Revert "drm/i915/gem: Split eb_vma into its own allocation" 



This reverts commit 0f1dd022 ("drm/i915/gem: Split eb_vma into
its own allocation") and also moves all unreserving to a single
place at the end, which is a minor simplification.

With the WW locking, we will drop all references only at the
end when unlocking, so refcounting can now be removed.

Signed-off-by: default avatarMaarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: default avatarDaniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20200819140904.1708856-5-maarten.lankhorst@linux.intel.com


Signed-off-by: default avatarJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
parent fd1500fc

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

+51 −73
Original line number Diff line number Diff line
@@ -41,11 +41,6 @@ struct eb_vma { 
	u32 handle;

};



struct eb_vma_array {

	struct kref kref;

	struct eb_vma vma[];

};



enum {

	FORCE_CPU_RELOC = 1,

	FORCE_GTT_RELOC,
@@ -58,6 +53,7 @@ enum { 
#define __EXEC_OBJECT_NEEDS_MAP		BIT(29)

#define __EXEC_OBJECT_NEEDS_BIAS	BIT(28)

#define __EXEC_OBJECT_INTERNAL_FLAGS	(~0u << 28) /* all of the above */

#define __EXEC_OBJECT_RESERVED (__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_FENCE)



#define __EXEC_HAS_RELOC	BIT(31)

#define __EXEC_INTERNAL_FLAGS	(~0u << 31)
@@ -295,7 +291,6 @@ struct i915_execbuffer { 
	 */

	int lut_size;

	struct hlist_head *buckets; /** ht for relocation handles */

	struct eb_vma_array *array;



	struct eb_fence *fences;

	unsigned long num_fences;
@@ -308,62 +303,8 @@ static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb) 
		 eb->args->batch_len);

}



static struct eb_vma_array *eb_vma_array_create(unsigned int count)

{

	struct eb_vma_array *arr;



	arr = kvmalloc(struct_size(arr, vma, count), GFP_KERNEL | __GFP_NOWARN);

	if (!arr)

		return NULL;



	kref_init(&arr->kref);

	arr->vma[0].vma = NULL;



	return arr;

}



static inline void eb_unreserve_vma(struct eb_vma *ev)

{

	struct i915_vma *vma = ev->vma;



	if (unlikely(ev->flags & __EXEC_OBJECT_HAS_FENCE))

		__i915_vma_unpin_fence(vma);



	if (ev->flags & __EXEC_OBJECT_HAS_PIN)

		__i915_vma_unpin(vma);



	ev->flags &= ~(__EXEC_OBJECT_HAS_PIN |

		       __EXEC_OBJECT_HAS_FENCE);

}



static void eb_vma_array_destroy(struct kref *kref)

{

	struct eb_vma_array *arr = container_of(kref, typeof(*arr), kref);

	struct eb_vma *ev = arr->vma;



	while (ev->vma) {

		eb_unreserve_vma(ev);

		i915_vma_put(ev->vma);

		ev++;

	}



	kvfree(arr);

}



static void eb_vma_array_put(struct eb_vma_array *arr)

{

	kref_put(&arr->kref, eb_vma_array_destroy);

}



static int eb_create(struct i915_execbuffer *eb)

{

	/* Allocate an extra slot for use by the command parser + sentinel */

	eb->array = eb_vma_array_create(eb->buffer_count + 2);

	if (!eb->array)

		return -ENOMEM;



	eb->vma = eb->array->vma;



	if (!(eb->args->flags & I915_EXEC_HANDLE_LUT)) {

		unsigned int size = 1 + ilog2(eb->buffer_count);
@@ -397,10 +338,8 @@ static int eb_create(struct i915_execbuffer *eb) 
				break;

		} while (--size);



		if (unlikely(!size)) {

			eb_vma_array_put(eb->array);

		if (unlikely(!size))

			return -ENOMEM;

		}



		eb->lut_size = size;

	} else {
@@ -511,6 +450,26 @@ eb_pin_vma(struct i915_execbuffer *eb, 
	return !eb_vma_misplaced(entry, vma, ev->flags);

}



static inline void __eb_unreserve_vma(struct i915_vma *vma, unsigned int flags)

{

	GEM_BUG_ON(!(flags & __EXEC_OBJECT_HAS_PIN));



	if (unlikely(flags & __EXEC_OBJECT_HAS_FENCE))

		__i915_vma_unpin_fence(vma);



	__i915_vma_unpin(vma);

}



static inline void

eb_unreserve_vma(struct eb_vma *ev)

{

	if (!(ev->flags & __EXEC_OBJECT_HAS_PIN))

		return;



	__eb_unreserve_vma(ev->vma, ev->flags);

	ev->flags &= ~__EXEC_OBJECT_RESERVED;

}



static int

eb_validate_vma(struct i915_execbuffer *eb,

		struct drm_i915_gem_exec_object2 *entry,
@@ -933,13 +892,31 @@ eb_get_vma(const struct i915_execbuffer *eb, unsigned long handle) 
	}

}



static void eb_release_vmas(const struct i915_execbuffer *eb)

{

	const unsigned int count = eb->buffer_count;

	unsigned int i;



	for (i = 0; i < count; i++) {

		struct eb_vma *ev = &eb->vma[i];

		struct i915_vma *vma = ev->vma;



		if (!vma)

			break;



		eb->vma[i].vma = NULL;



		if (ev->flags & __EXEC_OBJECT_HAS_PIN)

			__eb_unreserve_vma(vma, ev->flags);



		i915_vma_put(vma);

	}

}



static void eb_destroy(const struct i915_execbuffer *eb)

{

	GEM_BUG_ON(eb->reloc_cache.rq);



	if (eb->array)

		eb_vma_array_put(eb->array);



	if (eb->lut_size > 0)

		kfree(eb->buckets);

}
@@ -2021,12 +1998,9 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb) 
			err = i915_vma_move_to_active(vma, eb->request, flags);



		i915_vma_unlock(vma);

		eb_unreserve_vma(ev);

	}

	ww_acquire_fini(&acquire);



	eb_vma_array_put(fetch_and_zero(&eb->array));



	if (unlikely(err))

		goto err_skip;
@@ -2323,7 +2297,6 @@ static int eb_parse(struct i915_execbuffer *eb) 
	eb->vma[eb->buffer_count].vma = i915_vma_get(shadow);

	eb->vma[eb->buffer_count].flags = __EXEC_OBJECT_HAS_PIN;

	eb->batch = &eb->vma[eb->buffer_count++];

	eb->vma[eb->buffer_count].vma = NULL;



	eb->trampoline = trampoline;

	eb->batch_start_offset = 0;
@@ -2989,6 +2962,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, 
		args->flags |= __EXEC_HAS_RELOC;



	eb.exec = exec;

	eb.vma = (struct eb_vma *)(exec + args->buffer_count + 1);

	eb.vma[0].vma = NULL;



	eb.invalid_flags = __EXEC_OBJECT_UNKNOWN_FLAGS;

	reloc_cache_init(&eb.reloc_cache, eb.i915);
@@ -3198,6 +3173,8 @@ i915_gem_do_execbuffer(struct drm_device *dev, 
	if (batch->private)

		intel_gt_buffer_pool_put(batch->private);

err_vma:

	if (eb.exec)

		eb_release_vmas(&eb);

	if (eb.trampoline)

		i915_vma_unpin(eb.trampoline);

	eb_unpin_engine(&eb);
@@ -3217,7 +3194,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, 


static size_t eb_element_size(void)

{

	return sizeof(struct drm_i915_gem_exec_object2);

	return sizeof(struct drm_i915_gem_exec_object2) + sizeof(struct eb_vma);

}



static bool check_buffer_count(size_t count)
@@ -3273,7 +3250,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data, 
	/* Copy in the exec list from userland */

	exec_list = kvmalloc_array(count, sizeof(*exec_list),

				   __GFP_NOWARN | GFP_KERNEL);

	exec2_list = kvmalloc_array(count, eb_element_size(),

	exec2_list = kvmalloc_array(count + 1, eb_element_size(),

				    __GFP_NOWARN | GFP_KERNEL);

	if (exec_list == NULL || exec2_list == NULL) {

		drm_dbg(&i915->drm,
@@ -3350,7 +3327,8 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data, 
	if (err)

		return err;



	exec2_list = kvmalloc_array(count, eb_element_size(),

	/* Allocate an extra slot for use by the command parser */

	exec2_list = kvmalloc_array(count + 1, eb_element_size(),

				    __GFP_NOWARN | GFP_KERNEL);

	if (exec2_list == NULL) {

		drm_dbg(&i915->drm, "Failed to allocate exec list for %zd buffers\n",