iommu/dma: avoid expensive indirect calls for sync operations

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.

Co-developed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index c745196bc1504280b3c4a2eea9a503f57ed94084..2a1dbe5867c454b4c3987a2ac1718c5b996993c8 100644 (file)
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1723,7 +1723,8 @@ static size_t iommu_dma_max_mapping_size(struct device *dev)
 }
 
 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,