Re: [PATCH 1/2] drm/i915: Extend GET_APERTURE ioctl to report available map space

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On Wed, Jul 01, 2015 at 02:55:12PM +0530, ankitprasad.r.sharma@xxxxxxxxx wrote:
> From: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
> 
> When constructing a batchbuffer, it is sometimes crucial to know the
> largest hole into which we can fit a fenceable buffer (for example when
> handling very large objects on gen2 and gen3). This depends on the
> fragmentation of pinned buffers inside the aperture, a question only the
> kernel can easily answer.
> 
> This patch extends the current DRM_I915_GEM_GET_APERTURE ioctl to
> include a couple of new fields in its reply to userspace - the total
> amount of space available in the mappable region of the aperture and
> also the single largest block available.
> 
> This is not quite what userspace wants to answer the question of whether
> this batch will fit as fences are also required to meet severe alignment
> constraints within the batch. For this purpose, a third conservative
> estimate of largest fence available is also provided. For when userspace
> needs more than one batch, we also provide the culmulative space
> available for fences such that it has some additional guidance to how
> much space it could allocate to fences. Conservatism still wins.
> 
> The patch also adds a debugfs file for convenient testing and reporting.
> 
> v2: The first object cannot end at offset 0, so we can use last==0 to
> detect the empty list.
> 
> v3: Expand all values to 64bit, just in case.
>     Report total mappable aperture size for userspace that cannot easily
>     determine it by inspecting the PCI device.
> 
> v4: (Rodrigo) Fixed rebase conflicts.
> 
> v5: Rebased to the latest drm-intel-nightly (Ankit)
> 
> Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> Signed-off-by: Rodrigo Vivi <rodrigo.vivi at intel.com>
> ---
>  drivers/gpu/drm/i915/i915_debugfs.c |  27 +++++++++
>  drivers/gpu/drm/i915/i915_gem.c     | 116 ++++++++++++++++++++++++++++++++++--
>  2 files changed, 139 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
> index 31d8768..49ec438 100644
> --- a/drivers/gpu/drm/i915/i915_debugfs.c
> +++ b/drivers/gpu/drm/i915/i915_debugfs.c
> @@ -512,6 +512,32 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
>  	return 0;
>  }
>  
> +static int i915_gem_aperture_info(struct seq_file *m, void *data)
> +{
> +	struct drm_info_node *node = m->private;
> +	struct drm_i915_gem_get_aperture arg;
> +	int ret;
> +
> +	ret = i915_gem_get_aperture_ioctl(node->minor->dev, &arg, NULL);
> +	if (ret)
> +		return ret;
> +
> +	seq_printf(m, "Total size of the GTT: %llu bytes\n",
> +		   arg.aper_size);
> +	seq_printf(m, "Available space in the GTT: %llu bytes\n",
> +		   arg.aper_available_size);
> +	seq_printf(m, "Available space in the mappable aperture: %llu bytes\n",
> +		   arg.map_available_size);
> +	seq_printf(m, "Single largest space in the mappable aperture: %llu bytes\n",
> +		   arg.map_largest_size);
> +	seq_printf(m, "Available space for fences: %llu bytes\n",
> +		   arg.fence_available_size);
> +	seq_printf(m, "Single largest fence available: %llu bytes\n",
> +		   arg.fence_largest_size);
> +
> +	return 0;
> +}
> +
>  static int i915_gem_gtt_info(struct seq_file *m, void *data)
>  {
>  	struct drm_info_node *node = m->private;
> @@ -5030,6 +5056,7 @@ static int i915_debugfs_create(struct dentry *root,
>  static const struct drm_info_list i915_debugfs_list[] = {
>  	{"i915_capabilities", i915_capabilities, 0},
>  	{"i915_gem_objects", i915_gem_object_info, 0},
> +	{"i915_gem_aperture", i915_gem_aperture_info, 0},
>  	{"i915_gem_gtt", i915_gem_gtt_info, 0},
>  	{"i915_gem_pinned", i915_gem_gtt_info, 0, (void *) PINNED_LIST},
>  	{"i915_gem_active", i915_gem_object_list_info, 0, (void *) ACTIVE_LIST},
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index a2a4a27..ccfc8d3 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -32,6 +32,7 @@
>  #include "i915_vgpu.h"
>  #include "i915_trace.h"
>  #include "intel_drv.h"
> +#include <linux/list_sort.h>
>  #include <linux/shmem_fs.h>
>  #include <linux/slab.h>
>  #include <linux/swap.h>
> @@ -143,6 +144,55 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
>  	return 0;
>  }
>  
> +static inline bool
> +i915_gem_object_is_inactive(struct drm_i915_gem_object *obj)
> +{
> +	return i915_gem_obj_bound_any(obj) && !obj->active;
> +}
> +
> +static int obj_rank_by_ggtt(void *priv,
> +			    struct list_head *A,
> +			    struct list_head *B)
> +{
> +	struct drm_i915_gem_object *a = list_entry(A,typeof(*a), obj_exec_link);
> +	struct drm_i915_gem_object *b = list_entry(B,typeof(*b), obj_exec_link);
> +
> +	return i915_gem_obj_ggtt_offset(a) - i915_gem_obj_ggtt_offset(b);
> +}
> +
> +static u32 __fence_size(struct drm_i915_private *dev_priv, u32 start, u32 end)
> +{
> +	u32 size = end - start;
> +	u32 fence_size;
> +
> +	if (INTEL_INFO(dev_priv)->gen < 4) {
> +		u32 fence_max;
> +		u32 fence_next;
> +
> +		if (IS_GEN3(dev_priv)) {
> +			fence_max = I830_FENCE_MAX_SIZE_VAL << 20;
> +			fence_next = 1024*1024;
> +		} else {
> +			fence_max = I830_FENCE_MAX_SIZE_VAL << 19;
> +			fence_next = 512*1024;
> +		}
> +
> +		fence_max = min(fence_max, size);
> +		fence_size = 0;
> +		while (fence_next <= fence_max) {
> +			u32 base = ALIGN(start, fence_next);
> +			if (base + fence_next > end)
> +				break;
> +
> +			fence_size = fence_next;
> +			fence_next <<= 1;
> +		}
> +	} else
> +		fence_size = size;
> +
> +	return fence_size;
> +}
> +
>  int
>  i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
>  			    struct drm_file *file)
> @@ -150,17 +200,75 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
>  	struct drm_i915_private *dev_priv = dev->dev_private;
>  	struct drm_i915_gem_get_aperture *args = data;
>  	struct drm_i915_gem_object *obj;
> -	size_t pinned;
> +	struct list_head map_list;
> +	const u32 map_limit = dev_priv->gtt.mappable_end;
> +	size_t pinned, map_space, map_largest, fence_space, fence_largest;
> +	u32 last, size;
> +
> +	INIT_LIST_HEAD(&map_list);
>  
>  	pinned = 0;
> +	map_space = map_largest = 0;
> +	fence_space = fence_largest = 0;
> +
>  	mutex_lock(&dev->struct_mutex);
> -	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list)
> -		if (i915_gem_obj_is_pinned(obj))
> -			pinned += i915_gem_obj_ggtt_size(obj);
> +	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
> +		struct i915_vma *vma = i915_gem_obj_to_ggtt(obj);
> +
> +		if (vma == NULL || !vma->pin_count)
> +			continue;
> +
> +		pinned += vma->node.size;
> +
> +		if (vma->node.start < map_limit)
> +			list_add(&obj->obj_exec_link, &map_list);
> +	}
> +
> +	last = 0;
> +	list_sort(NULL, &map_list, obj_rank_by_ggtt);
> +	while (!list_empty(&map_list)) {
> +		struct i915_vma *vma;
> +
> +		obj = list_first_entry(&map_list, typeof(*obj), obj_exec_link);
> +		list_del_init(&obj->obj_exec_link);
> +
> +		vma = i915_gem_obj_to_ggtt(obj);
> +		if (last == 0)
> +			goto skip_first;
> +
> +		size = vma->node.start - last;
> +		if (size > map_largest)
> +			map_largest = size;
> +		map_space += size;
> +
> +		size = __fence_size(dev_priv, last, vma->node.start);
> +		if (size > fence_largest)
> +			fence_largest = size;
> +		fence_space += size;
> +
> +skip_first:
> +		last = vma->node.start + vma->node.size;
> +	}
> +	if (last < map_limit) {
> +		size = map_limit - last;
> +		if (size > map_largest)
> +			map_largest = size;
> +		map_space += size;
> +
> +		size = __fence_size(dev_priv, last, map_limit);
> +		if (size > fence_largest)
> +			fence_largest = size;
> +		fence_space += size;
> +	}
>  	mutex_unlock(&dev->struct_mutex);
>  
>  	args->aper_size = dev_priv->gtt.base.total;
>  	args->aper_available_size = args->aper_size - pinned;
> +	args->map_available_size = map_space;
> +	args->map_largest_size = map_largest;
> +	args->map_total_size = dev_priv->gtt.mappable_end;
> +	args->fence_available_size = fence_space;
> +	args->fence_largest_size = fence_largest;

Does this really compile? You only add all the new structure stuff in the
2nd patch.
-Daniel

>  
>  	return 0;
>  }
> -- 
> 1.9.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
http://lists.freedesktop.org/mailman/listinfo/intel-gfx




[Index of Archives]     [Linux USB Devel]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux