Re: [PATCH v5 05/16] swiotlb: Add restricted DMA pool initialization

[Steven Price]

On 22/04/2021 09:14, Claire Chang wrote:
> Add the initialization function to create restricted DMA pools from
> matching reserved-memory nodes.
>
> Signed-off-by: Claire Chang <tientzu@xxxxxxxxxxxx>
> ---
>   include/linux/device.h  |  4 +++
>   include/linux/swiotlb.h |  3 +-
>   kernel/dma/swiotlb.c    | 80 +++++++++++++++++++++++++++++++++++++++++
>   3 files changed, 86 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/device.h b/include/linux/device.h
> index 38a2071cf776..4987608ea4ff 100644
> --- a/include/linux/device.h
> +++ b/include/linux/device.h
> @@ -416,6 +416,7 @@ struct dev_links_info {
>    * @dma_pools:	Dma pools (if dma'ble device).
>    * @dma_mem:	Internal for coherent mem override.
>    * @cma_area:	Contiguous memory area for dma allocations
> + * @dma_io_tlb_mem: Internal for swiotlb io_tlb_mem override.
>    * @archdata:	For arch-specific additions.
>    * @of_node:	Associated device tree node.
>    * @fwnode:	Associated device node supplied by platform firmware.
> @@ -521,6 +522,9 @@ struct device {
>   #ifdef CONFIG_DMA_CMA
>   	struct cma *cma_area;		/* contiguous memory area for dma
>   					   allocations */
> +#endif
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +	struct io_tlb_mem *dma_io_tlb_mem;
>   #endif
>   	/* arch specific additions */
>   	struct dev_archdata	archdata;
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 216854a5e513..03ad6e3b4056 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -72,7 +72,8 @@ extern enum swiotlb_force swiotlb_force;
>    *		range check to see if the memory was in fact allocated by this
>    *		API.
>    * @nslabs:	The number of IO TLB blocks (in groups of 64) between @start and
> - *		@end. This is command line adjustable via setup_io_tlb_npages.
> + *		@end. For default swiotlb, this is command line adjustable via
> + *		setup_io_tlb_npages.
>    * @used:	The number of used IO TLB block.
>    * @list:	The free list describing the number of free entries available
>    *		from each index.
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index 57a9adb920bf..ffbb8724e06c 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -39,6 +39,13 @@
>   #ifdef CONFIG_DEBUG_FS
>   #include <linux/debugfs.h>
>   #endif
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +#include <linux/io.h>
> +#include <linux/of.h>
> +#include <linux/of_fdt.h>
> +#include <linux/of_reserved_mem.h>
> +#include <linux/slab.h>
> +#endif
>   
>   #include <asm/io.h>
>   #include <asm/dma.h>
> @@ -681,3 +688,76 @@ static int __init swiotlb_create_default_debugfs(void)
>   late_initcall(swiotlb_create_default_debugfs);
>   
>   #endif
> +
> +#ifdef CONFIG_DMA_RESTRICTED_POOL
> +static int rmem_swiotlb_device_init(struct reserved_mem *rmem,
> +				    struct device *dev)
> +{
> +	struct io_tlb_mem *mem = rmem->priv;
> +	unsigned long nslabs = rmem->size >> IO_TLB_SHIFT;
> +
> +	if (dev->dma_io_tlb_mem)
> +		return 0;
> +
> +	/* Since multiple devices can share the same pool, the private data,
> +	 * io_tlb_mem struct, will be initialized by the first device attached
> +	 * to it.
> +	 */
> +	if (!mem) {
> +		mem = kzalloc(struct_size(mem, slots, nslabs), GFP_KERNEL);
> +		if (!mem)
> +			return -ENOMEM;
> +#ifdef CONFIG_ARM
> +		if (!PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) {
> +			kfree(mem);
> +			return -EINVAL;
> +		}
> +#endif /* CONFIG_ARM */
> +		swiotlb_init_io_tlb_mem(mem, rmem->base, nslabs, false);
> +
> +		rmem->priv = mem;
> +	}
> +
> +#ifdef CONFIG_DEBUG_FS
> +	if (!io_tlb_default_mem->debugfs)
> +		io_tlb_default_mem->debugfs =
> +			debugfs_create_dir("swiotlb", NULL);

At this point it's possible for io_tlb_default_mem to be NULL, leading 
to a splat.

But even then if it's not and we have the situation where debugfs==NULL 
then the debugfs_create_dir() here will cause a subsequent attempt in 
swiotlb_create_debugfs() to fail (directory already exists) leading to 
mem->debugfs being assigned an error value. I suspect the creation of 
the debugfs directory needs to be separated from io_tlb_default_mem 
being set.

Other than that I gave this series a go with our prototype of Arm's 
Confidential Computer Architecture[1] - since the majority of the 
guest's memory is protected from the host the restricted DMA pool allows 
(only) a small area to be shared with the host.

After fixing (well hacking round) the above it all seems to be working 
fine with virtio drivers.

Thanks,

Steve

[1] 
https://www.arm.com/why-arm/architecture/security-features/arm-confidential-compute-architecture