Re: [PATCH v3] swiotlb: Adjust SWIOTBL bounce buffer size for SEV guests.

[Konrad Rzeszutek Wilk]

On Wed, Nov 04, 2020 at 10:08:04PM +0000, Ashish Kalra wrote:
> From: Ashish Kalra <ashish.kalra@xxxxxxx>
> 
> For SEV, all DMA to and from guest has to use shared
> (un-encrypted) pages. SEV uses SWIOTLB to make this
> happen without requiring changes to device drivers.
> However, depending on workload being run, the default
> 64MB of SWIOTLB might not be enough and SWIOTLB
> may run out of buffers to use for DMA, resulting
> in I/O errors and/or performance degradation for
> high I/O workloads.
> 
> Increase the default size of SWIOTLB for SEV guests
> using a minimum value of 128MB and a maximum value

<blinks>

64MB for a 1GB VM is not enough?

> of 512MB, determining on amount of provisioned guest

I like the implementation on how this is done.. but
the choices of memory and how much seems very much
random. Could there be some math behind this?

> memory.
> 
> Using late_initcall() interface to invoke
> swiotlb_adjust() does not work as the size
> adjustment needs to be done before mem_encrypt_init()
> and reserve_crashkernel() which use the allocated
> SWIOTLB buffer size, hence calling it explicitly
> from setup_arch().
> 
> The SWIOTLB default size adjustment is added as an
> architecture specific interface/callback to allow
> architectures such as those supporting memory
> encryption to adjust/expand SWIOTLB size for their
> use.
> 
> Signed-off-by: Ashish Kalra <ashish.kalra@xxxxxxx>
> ---
>  arch/x86/kernel/setup.c   |  2 ++
>  arch/x86/mm/mem_encrypt.c | 42 +++++++++++++++++++++++++++++++++++++++
>  include/linux/swiotlb.h   |  1 +
>  kernel/dma/swiotlb.c      | 27 +++++++++++++++++++++++++
>  4 files changed, 72 insertions(+)
> 
> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
> index 3511736fbc74..b073d58dd4a3 100644
> --- a/arch/x86/kernel/setup.c
> +++ b/arch/x86/kernel/setup.c
> @@ -1166,6 +1166,8 @@ void __init setup_arch(char **cmdline_p)
>  	if (boot_cpu_has(X86_FEATURE_GBPAGES))
>  		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
>  
> +	swiotlb_adjust();
> +
>  	/*
>  	 * Reserve memory for crash kernel after SRAT is parsed so that it
>  	 * won't consume hotpluggable memory.
> diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
> index 3f248f0d0e07..e0deb157cddd 100644
> --- a/arch/x86/mm/mem_encrypt.c
> +++ b/arch/x86/mm/mem_encrypt.c
> @@ -489,7 +489,49 @@ static void print_mem_encrypt_feature_info(void)
>  	pr_cont("\n");
>  }
>  
> +#define TOTAL_MEM_1G	0x40000000UL
> +#define TOTAL_MEM_4G	0x100000000UL
> +
> +#define SIZE_128M (128UL<<20)
> +#define SIZE_256M (256UL<<20)
> +#define SIZE_512M (512UL<<20)
> +
>  /* Architecture __weak replacement functions */
> +unsigned long __init arch_swiotlb_adjust(unsigned long iotlb_default_size)
> +{
> +	unsigned long size = 0;
> +
> +	/*
> +	 * For SEV, all DMA has to occur via shared/unencrypted pages.
> +	 * SEV uses SWOTLB to make this happen without changing device
> +	 * drivers. However, depending on the workload being run, the
> +	 * default 64MB of SWIOTLB may not be enough & SWIOTLB may
> +	 * run out of buffers for DMA, resulting in I/O errors and/or
> +	 * performance degradation especially with high I/O workloads.
> +	 * Increase the default size of SWIOTLB for SEV guests using
> +	 * a minimum value of 128MB and a maximum value of 512MB,
> +	 * depending on amount of provisioned guest memory.
> +	 */
> +	if (sev_active()) {
> +		phys_addr_t total_mem = memblock_phys_mem_size();
> +
> +		if (total_mem <= TOTAL_MEM_1G)
> +			size = clamp(iotlb_default_size * 2, SIZE_128M,
> +				     SIZE_128M);
> +		else if (total_mem <= TOTAL_MEM_4G)
> +			size = clamp(iotlb_default_size * 4, SIZE_256M,
> +				     SIZE_256M);
> +		else
> +			size = clamp(iotlb_default_size * 8, SIZE_512M,
> +				     SIZE_512M);
> +
> +		pr_info("SEV adjusted max SWIOTLB size = %luMB",
> +			size >> 20);
> +	}
> +
> +	return size;
> +}
> +
>  void __init mem_encrypt_init(void)
>  {
>  	if (!sme_me_mask)
> diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
> index 046bb94bd4d6..01ae6d891327 100644
> --- a/include/linux/swiotlb.h
> +++ b/include/linux/swiotlb.h
> @@ -33,6 +33,7 @@ extern void swiotlb_init(int verbose);
>  int swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose);
>  extern unsigned long swiotlb_nr_tbl(void);
>  unsigned long swiotlb_size_or_default(void);
> +extern void __init swiotlb_adjust(void);
>  extern int swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs);
>  extern void __init swiotlb_update_mem_attributes(void);
>  
> diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
> index c19379fabd20..66a9e627bb51 100644
> --- a/kernel/dma/swiotlb.c
> +++ b/kernel/dma/swiotlb.c
> @@ -163,6 +163,33 @@ unsigned long swiotlb_size_or_default(void)
>  	return size ? size : (IO_TLB_DEFAULT_SIZE);
>  }
>  
> +unsigned long __init __weak arch_swiotlb_adjust(unsigned long size)
> +{
> +	return 0;
> +}
> +
> +void __init swiotlb_adjust(void)
> +{
> +	unsigned long size;
> +
> +	/*
> +	 * If swiotlb parameter has not been specified, give a chance to
> +	 * architectures such as those supporting memory encryption to
> +	 * adjust/expand SWIOTLB size for their use.
> +	 */
> +	if (!io_tlb_nslabs) {
> +		size = arch_swiotlb_adjust(IO_TLB_DEFAULT_SIZE);
> +		if (size) {
> +			size = ALIGN(size, 1 << IO_TLB_SHIFT);
> +			io_tlb_nslabs = size >> IO_TLB_SHIFT;
> +			io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
> +
> +			pr_info("architecture adjusted SWIOTLB slabs = %lu\n",
> +				io_tlb_nslabs);
> +		}
> +	}
> +}
> +
>  void swiotlb_print_info(void)
>  {
>  	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
> -- 
> 2.17.1
>