Re: [PATCH net-next v3 3/7] iommu/dma: avoid expensive indirect calls for sync operations

[Robin Murphy <robin.murphy@arm.com>]

On 2024-02-14 4:21 pm, Alexander Lobakin wrote:
> When IOMMU is on, the actual synchronization happens in the same cases
> as with the direct DMA. Advertise %DMA_F_CAN_SKIP_SYNC in IOMMU DMA to
> skip sync ops calls (indirect) for non-SWIOTLB buffers.
> 
> perf profile before the patch:
> 
>      18.53%  [kernel]       [k] gq_rx_skb
>      14.77%  [kernel]       [k] napi_reuse_skb
>       8.95%  [kernel]       [k] skb_release_data
>       5.42%  [kernel]       [k] dev_gro_receive
>       5.37%  [kernel]       [k] memcpy
> <*>  5.26%  [kernel]       [k] iommu_dma_sync_sg_for_cpu
>       4.78%  [kernel]       [k] tcp_gro_receive
> <*>  4.42%  [kernel]       [k] iommu_dma_sync_sg_for_device
>       4.12%  [kernel]       [k] ipv6_gro_receive
>       3.65%  [kernel]       [k] gq_pool_get
>       3.25%  [kernel]       [k] skb_gro_receive
>       2.07%  [kernel]       [k] napi_gro_frags
>       1.98%  [kernel]       [k] tcp6_gro_receive
>       1.27%  [kernel]       [k] gq_rx_prep_buffers
>       1.18%  [kernel]       [k] gq_rx_napi_handler
>       0.99%  [kernel]       [k] csum_partial
>       0.74%  [kernel]       [k] csum_ipv6_magic
>       0.72%  [kernel]       [k] free_pcp_prepare
>       0.60%  [kernel]       [k] __napi_poll
>       0.58%  [kernel]       [k] net_rx_action
>       0.56%  [kernel]       [k] read_tsc
> <*>  0.50%  [kernel]       [k] __x86_indirect_thunk_r11
>       0.45%  [kernel]       [k] memset
> 
> After patch, lines with <*> no longer show up, and overall
> cpu usage looks much better (~60% instead of ~72%):
> 
>      25.56%  [kernel]       [k] gq_rx_skb
>       9.90%  [kernel]       [k] napi_reuse_skb
>       7.39%  [kernel]       [k] dev_gro_receive
>       6.78%  [kernel]       [k] memcpy
>       6.53%  [kernel]       [k] skb_release_data
>       6.39%  [kernel]       [k] tcp_gro_receive
>       5.71%  [kernel]       [k] ipv6_gro_receive
>       4.35%  [kernel]       [k] napi_gro_frags
>       4.34%  [kernel]       [k] skb_gro_receive
>       3.50%  [kernel]       [k] gq_pool_get
>       3.08%  [kernel]       [k] gq_rx_napi_handler
>       2.35%  [kernel]       [k] tcp6_gro_receive
>       2.06%  [kernel]       [k] gq_rx_prep_buffers
>       1.32%  [kernel]       [k] csum_partial
>       0.93%  [kernel]       [k] csum_ipv6_magic
>       0.65%  [kernel]       [k] net_rx_action
> 
> iavf yields +10% of Mpps on Rx. This also unblocks batched allocations
> of XSk buffers when IOMMU is active.

Acked-by: Robin Murphy <robin.murphy@arm.com>

> Co-developed-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
> ---
>   drivers/iommu/dma-iommu.c | 3 ++-
>   1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
> index 50ccc4f1ef81..4ab9ac13d362 100644
> --- a/drivers/iommu/dma-iommu.c
> +++ b/drivers/iommu/dma-iommu.c
> @@ -1707,7 +1707,8 @@ static size_t iommu_dma_opt_mapping_size(void)
>   }
>   
>   static const struct dma_map_ops iommu_dma_ops = {
> -	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
> +	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED |
> +				  DMA_F_CAN_SKIP_SYNC,
>   	.alloc			= iommu_dma_alloc,
>   	.free			= iommu_dma_free,
>   	.alloc_pages		= dma_common_alloc_pages,