[Intel-gfx] [PATCH 5/6] drm/i915: Support for pread/pwrite from/to non shmem backed objects

[Tvrtko Ursulin]

Hi,

On 08/10/15 07:24, ankitprasad.r.sharma at intel.com wrote:
> From: Ankitprasad Sharma <ankitprasad.r.sharma at intel.com>
>
> This patch adds support for extending the pread/pwrite functionality
> for objects not backed by shmem. The access will be made through
> gtt interface.
> This will cover prime objects as well as stolen memory backed objects
> but for userptr objects it is still forbidden.

Where is the part which forbids it for userptr objects?

> v2: Drop locks around slow_user_access, prefault the pages before
> access (Chris)
>
> v3: Rebased to the latest drm-intel-nightly (Ankit)
>
> v4: Moved page base & offset calculations outside the copy loop,
> corrected data types for size and offset variables, corrected if-else
> braces format (Tvrtko/kerneldocs)
>
> v5: Enabled pread/pwrite for all non-shmem backed objects including
> without tiling restrictions (Ankit)
>
> v6: Using pwrite_fast for non-shmem backed objects as well (Chris)
>
> Testcase: igt/gem_stolen
>
> Signed-off-by: Ankitprasad Sharma <ankitprasad.r.sharma at intel.com>
> ---
>   drivers/gpu/drm/i915/i915_gem.c | 125 +++++++++++++++++++++++++++++++++-------
>   1 file changed, 104 insertions(+), 21 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 91a2e97..2c94e22 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -614,6 +614,99 @@ shmem_pread_slow(struct page *page, int shmem_page_offset, int page_length,
>   	return ret ? - EFAULT : 0;
>   }
>
> +static inline uint64_t
> +slow_user_access(struct io_mapping *mapping,
> +		 uint64_t page_base, int page_offset,
> +		 char __user *user_data,
> +		 int length, bool pwrite)
> +{
> +	void __iomem *vaddr_inatomic;
> +	void *vaddr;
> +	uint64_t unwritten;
> +
> +	vaddr_inatomic = io_mapping_map_wc(mapping, page_base);
> +	/* We can use the cpu mem copy function because this is X86. */
> +	vaddr = (void __force *)vaddr_inatomic + page_offset;
> +	if (pwrite)
> +		unwritten = __copy_from_user(vaddr, user_data, length);
> +	else
> +		unwritten = __copy_to_user(user_data, vaddr, length);
> +
> +	io_mapping_unmap(vaddr_inatomic);
> +	return unwritten;
> +}
> +
> +static int
> +i915_gem_gtt_pread(struct drm_device *dev,
> +		   struct drm_i915_gem_object *obj, uint64_t size,
> +		   uint64_t data_offset, uint64_t data_ptr)
> +{
> +	struct drm_i915_private *dev_priv = dev->dev_private;
> +	char __user *user_data;
> +	uint64_t remain;
> +	uint64_t offset, page_base;
> +	int page_offset, page_length, ret = 0;
> +
> +	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE);
> +	if (ret)
> +		goto out;
> +
> +	ret = i915_gem_object_set_to_gtt_domain(obj, false);
> +	if (ret)
> +		goto out_unpin;
> +
> +	ret = i915_gem_object_put_fence(obj);
> +	if (ret)
> +		goto out_unpin;
> +
> +	user_data = to_user_ptr(data_ptr);
> +	remain = size;
> +	offset = i915_gem_obj_ggtt_offset(obj) + data_offset;
> +
> +	mutex_unlock(&dev->struct_mutex);
> +	if (likely(!i915.prefault_disable))
> +		ret = fault_in_multipages_writeable(user_data, remain);
> +
> +	/*
> +	 * page_offset = offset within page
> +	 * page_base = page offset within aperture
> +	 */
> +	page_offset = offset_in_page(offset);
> +	page_base = offset & PAGE_MASK;
> +
> +	while (remain > 0) {
> +		/* page_length = bytes to copy for this page */
> +		page_length = remain;
> +		if ((page_offset + remain) > PAGE_SIZE)
> +			page_length = PAGE_SIZE - page_offset;
> +
> +		/* This is a slow read/write as it tries to read from
> +		 * and write to user memory which may result into page
> +		 * faults
> +		 */
> +		ret = slow_user_access(dev_priv->gtt.mappable, page_base,
> +				       page_offset, user_data,
> +				       page_length, false);
> +
> +		if (ret) {
> +			ret = -EFAULT;
> +			break;
> +		}
> +
> +		remain -= page_length;
> +		user_data += page_length;
> +		page_base += page_length;
> +		page_offset = 0;
> +	}
> +
> +	mutex_lock(&dev->struct_mutex);
> +
> +out_unpin:
> +	i915_gem_object_ggtt_unpin(obj);
> +out:
> +	return ret;
> +}
> +
>   static int
>   i915_gem_shmem_pread(struct drm_device *dev,
>   		     struct drm_i915_gem_object *obj,
> @@ -737,17 +830,14 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
>   		goto out;
>   	}
>
> -	/* prime objects have no backing filp to GEM pread/pwrite
> -	 * pages from.
> -	 */
> -	if (!obj->base.filp) {
> -		ret = -EINVAL;
> -		goto out;
> -	}
> -
>   	trace_i915_gem_object_pread(obj, args->offset, args->size);
>
> -	ret = i915_gem_shmem_pread(dev, obj, args, file);
> +	/* pread for non shmem backed objects */
> +	if (!obj->base.filp && obj->tiling_mode == I915_TILING_NONE)
> +		ret = i915_gem_gtt_pread(dev, obj, args->size,
> +					 args->offset, args->data_ptr);
> +	else
> +		ret = i915_gem_shmem_pread(dev, obj, args, file);
>
>   out:
>   	drm_gem_object_unreference(&obj->base);
> @@ -795,7 +885,7 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
>   	char __user *user_data;
>   	int page_offset, page_length, ret;
>
> -	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE | PIN_NONBLOCK);
> +	ret = i915_gem_obj_ggtt_pin(obj, 0, PIN_MAPPABLE);

Why is this needed?

>   	if (ret)
>   		goto out;
>
> @@ -1090,14 +1180,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
>   		goto out;
>   	}
>
> -	/* prime objects have no backing filp to GEM pread/pwrite
> -	 * pages from.
> -	 */
> -	if (!obj->base.filp) {
> -		ret = -EINVAL;
> -		goto out;
> -	}
> -
>   	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
>
>   	ret = -EFAULT;
> @@ -1108,8 +1190,9 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
>   	 * perspective, requiring manual detiling by the client.
>   	 */
>   	if (obj->tiling_mode == I915_TILING_NONE &&
> -	    obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
> -	    cpu_write_needs_clflush(obj)) {
> +	    (!obj->base.filp ||
> +	    (obj->base.write_domain != I915_GEM_DOMAIN_CPU &&
> +	    cpu_write_needs_clflush(obj)))) {
>   		ret = i915_gem_gtt_pwrite_fast(dev, obj, args, file);

So the pwrite path will fail if a page fault happens, as opposed to the 
pread path which makes an effort to handle it. What is the reason for 
this asymmetry in the API? Or I am missing something?

Regards,

Tvrtko