Re: [Intel-gfx] [PATCH 4/6] drm/i915: use vmap in i915_gem_object_map

[Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>]

On 18/09/2020 17:37, Christoph Hellwig wrote:
> i915_gem_object_map implements fairly low-level vmap functionality in
> a driver.  Split it into two helpers, one for remapping kernel memory
> which can use vmap, and one for I/O memory that uses vmap_pfn.
> 
> The only practical difference is that alloc_vm_area prefeaults the
> vmalloc area PTEs, which doesn't seem to be required here for the
> kernel memory case (and could be added to vmap using a flag if actually
> required).

Patch looks good to me.

Series did not get a CI run from our side because of a different base so 
I don't know if you would like to have a run there? If so you would need 
to rebase against git://anongit.freedesktop.org/drm-tip drm-tip and you 
could even send a series to intel-gfx-trybot@lists.freedesktop.org, 
suppressing cc, to check it out without sending a copy to the real 
mailing list.

Regards,

Tvrtko

> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>   drivers/gpu/drm/i915/Kconfig              |   1 +
>   drivers/gpu/drm/i915/gem/i915_gem_pages.c | 101 ++++++++++------------
>   2 files changed, 47 insertions(+), 55 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
> index 9afa5c4a6bf006..1e1cb245fca778 100644
> --- a/drivers/gpu/drm/i915/Kconfig
> +++ b/drivers/gpu/drm/i915/Kconfig
> @@ -25,6 +25,7 @@ config DRM_I915
>   	select CRC32
>   	select SND_HDA_I915 if SND_HDA_CORE
>   	select CEC_CORE if CEC_NOTIFIER
> +	select VMAP_PFN
>   	help
>   	  Choose this option if you have a system that has "Intel Graphics
>   	  Media Accelerator" or "HD Graphics" integrated graphics,
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> index e8a083743e0927..90029ea83aede9 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
> @@ -234,50 +234,24 @@ int __i915_gem_object_put_pages(struct drm_i915_gem_object *obj)
>   	return err;
>   }
>   
> -static inline pte_t iomap_pte(resource_size_t base,
> -			      dma_addr_t offset,
> -			      pgprot_t prot)
> -{
> -	return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot));
> -}
> -
>   /* The 'mapping' part of i915_gem_object_pin_map() below */
> -static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
> +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj,
>   				 enum i915_map_type type)
>   {
> -	unsigned long n_pte = obj->base.size >> PAGE_SHIFT;
> -	struct sg_table *sgt = obj->mm.pages;
> -	pte_t *stack[32], **mem;
> -	struct vm_struct *area;
> +	unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i;
> +	struct page *stack[32], **pages = stack, *page;
> +	struct sgt_iter iter;
>   	pgprot_t pgprot;
> -
> -	if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC)
> -		return NULL;
> -
> -	/* A single page can always be kmapped */
> -	if (n_pte == 1 && type == I915_MAP_WB)
> -		return kmap(sg_page(sgt->sgl));
> -
> -	mem = stack;
> -	if (n_pte > ARRAY_SIZE(stack)) {
> -		/* Too big for stack -- allocate temporary array instead */
> -		mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL);
> -		if (!mem)
> -			return NULL;
> -	}
> -
> -	area = alloc_vm_area(obj->base.size, mem);
> -	if (!area) {
> -		if (mem != stack)
> -			kvfree(mem);
> -		return NULL;
> -	}
> +	void *vaddr;
>   
>   	switch (type) {
>   	default:
>   		MISSING_CASE(type);
>   		fallthrough;	/* to use PAGE_KERNEL anyway */
>   	case I915_MAP_WB:
> +		/* A single page can always be kmapped */
> +		if (n_pages == 1)
> +			return kmap(sg_page(obj->mm.pages->sgl));
>   		pgprot = PAGE_KERNEL;
>   		break;
>   	case I915_MAP_WC:
> @@ -285,30 +259,44 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
>   		break;
>   	}
>   
> -	if (i915_gem_object_has_struct_page(obj)) {
> -		struct sgt_iter iter;
> -		struct page *page;
> -		pte_t **ptes = mem;
> -
> -		for_each_sgt_page(page, iter, sgt)
> -			**ptes++ = mk_pte(page, pgprot);
> -	} else {
> -		resource_size_t iomap;
> -		struct sgt_iter iter;
> -		pte_t **ptes = mem;
> -		dma_addr_t addr;
> +	if (n_pages > ARRAY_SIZE(stack)) {
> +		/* Too big for stack -- allocate temporary array instead */
> +		pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL);
> +		if (!pages)
> +			return NULL;
> +	}
>   
> -		iomap = obj->mm.region->iomap.base;
> -		iomap -= obj->mm.region->region.start;
> +	for_each_sgt_page(page, iter, obj->mm.pages)
> +		pages[i++] = page;
> +	vaddr = vmap(pages, n_pages, 0, pgprot);
> +	if (pages != stack)
> +		kvfree(pages);
> +	return vaddr;
> +}
>   
> -		for_each_sgt_daddr(addr, iter, sgt)
> -			**ptes++ = iomap_pte(iomap, addr, pgprot);
> +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj)
> +{
> +	resource_size_t iomap = obj->mm.region->iomap.base -
> +		obj->mm.region->region.start;
> +	unsigned long n_pfn = obj->base.size >> PAGE_SHIFT;
> +	unsigned long stack[32], *pfns = stack, i;
> +	struct sgt_iter iter;
> +	dma_addr_t addr;
> +	void *vaddr;
> +
> +	if (n_pfn > ARRAY_SIZE(stack)) {
> +		/* Too big for stack -- allocate temporary array instead */
> +		pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL);
> +		if (!pfns)
> +			return NULL;
>   	}
>   
> -	if (mem != stack)
> -		kvfree(mem);
> -
> -	return area->addr;
> +	for_each_sgt_daddr(addr, iter, obj->mm.pages)
> +		pfns[i++] = (iomap + addr) >> PAGE_SHIFT;
> +	vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO));
> +	if (pfns != stack)
> +		kvfree(pfns);
> +	return vaddr;
>   }
>   
>   /* get, pin, and map the pages of the object into kernel space */
> @@ -360,7 +348,10 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
>   	}
>   
>   	if (!ptr) {
> -		ptr = i915_gem_object_map(obj, type);
> +		if (i915_gem_object_has_struct_page(obj))
> +			ptr = i915_gem_object_map_page(obj, type);
> +		else if (type == I915_MAP_WC)
> +			ptr = i915_gem_object_map_pfn(obj);
>   		if (!ptr) {
>   			err = -ENOMEM;
>   			goto err_unpin;
>