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

[Alexander Lobakin]

From: Eric Dumazet <edumazet@xxxxxxxxxx>

Use the new dma_map_ops::can_skip_sync() callback in IOMMU DMA. It is
enough to check only for the DMA coherence, as SWIOTLB is checked
dynamically later.

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 batch allocations
of XSk buffers when IOMMU is active.

Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Co-developed-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@xxxxxxxxx>
---
 drivers/iommu/dma-iommu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 50ccc4f1ef81..86290562eda5 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1720,6 +1720,7 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.unmap_page		= iommu_dma_unmap_page,
 	.map_sg			= iommu_dma_map_sg,
 	.unmap_sg		= iommu_dma_unmap_sg,
+	.can_skip_sync		= dev_is_dma_coherent,
 	.sync_single_for_cpu	= iommu_dma_sync_single_for_cpu,
 	.sync_single_for_device	= iommu_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= iommu_dma_sync_sg_for_cpu,
-- 
2.43.0