Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit a9979d60 authored by Dave Airlie's avatar Dave Airlie
Browse files

Merge branch 'drm-ttm-next' into drm-core-next 

* drm-ttm-next:
  drm/radeon: Use the ttm execbuf utilities
  drm/ttm: Fix up io_mem_reserve / io_mem_free calling
  drm/ttm/vmwgfx: Have TTM manage the validation sequence.
  drm/ttm: Improved fencing of buffer object lists
  drm/ttm/radeon/nouveau: Kill the bo lock in favour of a bo device fence_lock
  drm/ttm: Don't deadlock on recursive multi-bo reservations
  drm/ttm: Optimize ttm_eu_backoff_reservation
  drm/ttm: Use kref_sub instead of repeatedly calling kref_put
  kref: Add a kref_sub function
  drm/ttm: Add a bo list reserve fastpath (v2)
parents 27641c3f 147666fb

drivers/gpu/drm/nouveau/nouveau_gem.c

+6 −6
Original line number Diff line number Diff line
@@ -234,10 +234,10 @@ validate_fini_list(struct list_head *list, struct nouveau_fence *fence) 
		if (likely(fence)) {

			struct nouveau_fence *prev_fence;



			spin_lock(&nvbo->bo.lock);

			spin_lock(&nvbo->bo.bdev->fence_lock);

			prev_fence = nvbo->bo.sync_obj;

			nvbo->bo.sync_obj = nouveau_fence_ref(fence);

			spin_unlock(&nvbo->bo.lock);

			spin_unlock(&nvbo->bo.bdev->fence_lock);

			nouveau_fence_unref((void *)&prev_fence);

		}
@@ -557,9 +557,9 @@ nouveau_gem_pushbuf_reloc_apply(struct drm_device *dev, 
				data |= r->vor;

		}



		spin_lock(&nvbo->bo.lock);

		spin_lock(&nvbo->bo.bdev->fence_lock);

		ret = ttm_bo_wait(&nvbo->bo, false, false, false);

		spin_unlock(&nvbo->bo.lock);

		spin_unlock(&nvbo->bo.bdev->fence_lock);

		if (ret) {

			NV_ERROR(dev, "reloc wait_idle failed: %d\n", ret);

			break;
@@ -791,9 +791,9 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data, 
	}



	if (req->flags & NOUVEAU_GEM_CPU_PREP_NOBLOCK) {

		spin_lock(&nvbo->bo.lock);

		spin_lock(&nvbo->bo.bdev->fence_lock);

		ret = ttm_bo_wait(&nvbo->bo, false, false, no_wait);

		spin_unlock(&nvbo->bo.lock);

		spin_unlock(&nvbo->bo.bdev->fence_lock);

	} else {

		ret = ttm_bo_synccpu_write_grab(&nvbo->bo, no_wait);

		if (ret == 0)

drivers/gpu/drm/radeon/radeon.h

+2 −2
Original line number Diff line number Diff line
@@ -69,6 +69,7 @@ 
#include <ttm/ttm_bo_driver.h>

#include <ttm/ttm_placement.h>

#include <ttm/ttm_module.h>

#include <ttm/ttm_execbuf_util.h>



#include "radeon_family.h"

#include "radeon_mode.h"
@@ -259,13 +260,12 @@ struct radeon_bo { 
};



struct radeon_bo_list {

	struct list_head	list;

	struct ttm_validate_buffer tv;

	struct radeon_bo	*bo;

	uint64_t		gpu_offset;

	unsigned		rdomain;

	unsigned		wdomain;

	u32			tiling_flags;

	bool			reserved;

};



/*

drivers/gpu/drm/radeon/radeon_cs.c

+10 −7
Original line number Diff line number Diff line
@@ -77,11 +77,11 @@ int radeon_cs_parser_relocs(struct radeon_cs_parser *p) 
			p->relocs_ptr[i] = &p->relocs[i];

			p->relocs[i].robj = p->relocs[i].gobj->driver_private;

			p->relocs[i].lobj.bo = p->relocs[i].robj;

			p->relocs[i].lobj.rdomain = r->read_domains;

			p->relocs[i].lobj.wdomain = r->write_domain;

			p->relocs[i].lobj.rdomain = r->read_domains;

			p->relocs[i].lobj.tv.bo = &p->relocs[i].robj->tbo;

			p->relocs[i].handle = r->handle;

			p->relocs[i].flags = r->flags;

			INIT_LIST_HEAD(&p->relocs[i].lobj.list);

			radeon_bo_list_add_object(&p->relocs[i].lobj,

						  &p->validated);

		}
@@ -189,10 +189,13 @@ static void radeon_cs_parser_fini(struct radeon_cs_parser *parser, int error) 
{

	unsigned i;



	if (!error && parser->ib) {

		radeon_bo_list_fence(&parser->validated, parser->ib->fence);

	}

	radeon_bo_list_unreserve(&parser->validated);



	if (!error && parser->ib)

		ttm_eu_fence_buffer_objects(&parser->validated,

					    parser->ib->fence);

	else

		ttm_eu_backoff_reservation(&parser->validated);



	if (parser->relocs != NULL) {

		for (i = 0; i < parser->nrelocs; i++) {

			if (parser->relocs[i].gobj)

drivers/gpu/drm/radeon/radeon_object.c

+4 −51
Original line number Diff line number Diff line
@@ -293,34 +293,9 @@ void radeon_bo_list_add_object(struct radeon_bo_list *lobj, 
				struct list_head *head)

{

	if (lobj->wdomain) {

		list_add(&lobj->list, head);

		list_add(&lobj->tv.head, head);

	} else {

		list_add_tail(&lobj->list, head);

	}

}



int radeon_bo_list_reserve(struct list_head *head)

{

	struct radeon_bo_list *lobj;

	int r;



	list_for_each_entry(lobj, head, list){

		r = radeon_bo_reserve(lobj->bo, false);

		if (unlikely(r != 0))

			return r;

		lobj->reserved = true;

	}

	return 0;

}



void radeon_bo_list_unreserve(struct list_head *head)

{

	struct radeon_bo_list *lobj;



	list_for_each_entry(lobj, head, list) {

		/* only unreserve object we successfully reserved */

		if (lobj->reserved && radeon_bo_is_reserved(lobj->bo))

			radeon_bo_unreserve(lobj->bo);

		list_add_tail(&lobj->tv.head, head);

	}

}
@@ -331,14 +306,11 @@ int radeon_bo_list_validate(struct list_head *head) 
	u32 domain;

	int r;



	list_for_each_entry(lobj, head, list) {

		lobj->reserved = false;

	}

	r = radeon_bo_list_reserve(head);

	r = ttm_eu_reserve_buffers(head);

	if (unlikely(r != 0)) {

		return r;

	}

	list_for_each_entry(lobj, head, list) {

	list_for_each_entry(lobj, head, tv.head) {

		bo = lobj->bo;

		if (!bo->pin_count) {

			domain = lobj->wdomain ? lobj->wdomain : lobj->rdomain;
@@ -361,25 +333,6 @@ int radeon_bo_list_validate(struct list_head *head) 
	return 0;

}



void radeon_bo_list_fence(struct list_head *head, void *fence)

{

	struct radeon_bo_list *lobj;

	struct radeon_bo *bo;

	struct radeon_fence *old_fence = NULL;



	list_for_each_entry(lobj, head, list) {

		bo = lobj->bo;

		spin_lock(&bo->tbo.lock);

		old_fence = (struct radeon_fence *)bo->tbo.sync_obj;

		bo->tbo.sync_obj = radeon_fence_ref(fence);

		bo->tbo.sync_obj_arg = NULL;

		spin_unlock(&bo->tbo.lock);

		if (old_fence) {

			radeon_fence_unref(&old_fence);

		}

	}

}



int radeon_bo_fbdev_mmap(struct radeon_bo *bo,

			     struct vm_area_struct *vma)

{

drivers/gpu/drm/radeon/radeon_object.h

+2 −5
Original line number Diff line number Diff line
@@ -126,12 +126,12 @@ static inline int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type, 
	r = ttm_bo_reserve(&bo->tbo, true, no_wait, false, 0);

	if (unlikely(r != 0))

		return r;

	spin_lock(&bo->tbo.lock);

	spin_lock(&bo->tbo.bdev->fence_lock);

	if (mem_type)

		*mem_type = bo->tbo.mem.mem_type;

	if (bo->tbo.sync_obj)

		r = ttm_bo_wait(&bo->tbo, true, true, no_wait);

	spin_unlock(&bo->tbo.lock);

	spin_unlock(&bo->tbo.bdev->fence_lock);

	ttm_bo_unreserve(&bo->tbo);

	return r;

}
@@ -152,10 +152,7 @@ extern int radeon_bo_init(struct radeon_device *rdev); 
extern void radeon_bo_fini(struct radeon_device *rdev);

extern void radeon_bo_list_add_object(struct radeon_bo_list *lobj,

				struct list_head *head);

extern int radeon_bo_list_reserve(struct list_head *head);

extern void radeon_bo_list_unreserve(struct list_head *head);

extern int radeon_bo_list_validate(struct list_head *head);

extern void radeon_bo_list_fence(struct list_head *head, void *fence);

extern int radeon_bo_fbdev_mmap(struct radeon_bo *bo,

				struct vm_area_struct *vma);

extern int radeon_bo_set_tiling_flags(struct radeon_bo *bo,