[resend PATCH 2/2] dim: pass dim_sample to net_dim() by reference

[Louis Peens]

On Wed, Oct 30, 2024 at 06:23:26PM -0600, Caleb Sander Mateos wrote:
> net_dim() is currently passed a struct dim_sample argument by value.
> struct dim_sample is 24 bytes. Since this is greater 16 bytes, x86-64
> passes it on the stack. All callers have already initialized dim_sample
> on the stack, so passing it by value requires pushing a duplicated copy
> to the stack. Either witing to the stack and immediately reading it, or
> perhaps dereferencing addresses relative to the stack pointer in a chain
> of push instructions, seems to perform quite poorly.
> 
> In a heavy TCP workload, mlx5e_handle_rx_dim() consumes 3% of CPU time,
> 94% of which is attributed to the first push instruction to copy
> dim_sample on the stack for the call to net_dim():
> // Call ktime_get()
>   0.26 |4ead2:   call   4ead7 <mlx5e_handle_rx_dim+0x47>
> // Pass the address of struct dim in %rdi
>        |4ead7:   lea    0x3d0(%rbx),%rdi
> // Set dim_sample.pkt_ctr
>        |4eade:   mov    %r13d,0x8(%rsp)
> // Set dim_sample.byte_ctr
>        |4eae3:   mov    %r12d,0xc(%rsp)
> // Set dim_sample.event_ctr
>   0.15 |4eae8:   mov    %bp,0x10(%rsp)
> // Duplicate dim_sample on the stack
>  94.16 |4eaed:   push   0x10(%rsp)
>   2.79 |4eaf1:   push   0x10(%rsp)
>   0.07 |4eaf5:   push   %rax
> // Call net_dim()
>   0.21 |4eaf6:   call   4eafb <mlx5e_handle_rx_dim+0x6b>
> 
> To allow the caller to reuse the struct dim_sample already on the stack,
> pass the struct dim_sample by reference to net_dim().
> 
> Signed-off-by: Caleb Sander Mateos <csander at purestorage.com>
> ---
>  Documentation/networking/net_dim.rst                   |  2 +-
>  drivers/net/ethernet/amazon/ena/ena_netdev.c           |  2 +-
>  drivers/net/ethernet/broadcom/bcmsysport.c             |  2 +-
>  drivers/net/ethernet/broadcom/bnxt/bnxt.c              |  4 ++--
>  drivers/net/ethernet/broadcom/genet/bcmgenet.c         |  2 +-
>  drivers/net/ethernet/freescale/enetc/enetc.c           |  2 +-
>  drivers/net/ethernet/hisilicon/hns3/hns3_enet.c        |  4 ++--
>  drivers/net/ethernet/intel/ice/ice_txrx.c              |  4 ++--
>  drivers/net/ethernet/intel/idpf/idpf_txrx.c            |  4 ++--
>  drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c |  2 +-
>  drivers/net/ethernet/mediatek/mtk_eth_soc.c            |  4 ++--
>  drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c      |  4 ++--
>  drivers/net/ethernet/netronome/nfp/nfd3/dp.c           |  4 ++--
>  drivers/net/ethernet/netronome/nfp/nfdk/dp.c           |  4 ++--
>  drivers/net/ethernet/pensando/ionic/ionic_txrx.c       |  2 +-
>  drivers/net/virtio_net.c                               |  2 +-
>  drivers/soc/fsl/dpio/dpio-service.c                    |  2 +-
>  include/linux/dim.h                                    |  2 +-
>  lib/dim/net_dim.c                                      | 10 +++++-----
>  19 files changed, 31 insertions(+), 31 deletions(-)
> 
--- snip --

> diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
> index d215efc6cad0..f1c6c47564b1 100644
> --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
> +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c
> @@ -1177,11 +1177,11 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget)
>  			pkts = r_vec->rx_pkts;
>  			bytes = r_vec->rx_bytes;
>  		} while (u64_stats_fetch_retry(&r_vec->rx_sync, start));
>  
>  		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
> -		net_dim(&r_vec->rx_dim, dim_sample);
> +		net_dim(&r_vec->rx_dim, &dim_sample);
>  	}
>  
>  	if (r_vec->nfp_net->tx_coalesce_adapt_on && r_vec->tx_ring) {
>  		struct dim_sample dim_sample = {};
>  		unsigned int start;
> @@ -1192,11 +1192,11 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget)
>  			pkts = r_vec->tx_pkts;
>  			bytes = r_vec->tx_bytes;
>  		} while (u64_stats_fetch_retry(&r_vec->tx_sync, start));
>  
>  		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
> -		net_dim(&r_vec->tx_dim, dim_sample);
> +		net_dim(&r_vec->tx_dim, &dim_sample);
>  	}
>  
>  	return pkts_polled;
>  }
>  
> diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
> index dae5af7d1845..ebeb6ab4465c 100644
> --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
> +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c
> @@ -1287,11 +1287,11 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget)
>  			pkts = r_vec->rx_pkts;
>  			bytes = r_vec->rx_bytes;
>  		} while (u64_stats_fetch_retry(&r_vec->rx_sync, start));
>  
>  		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
> -		net_dim(&r_vec->rx_dim, dim_sample);
> +		net_dim(&r_vec->rx_dim, &dim_sample);
>  	}
>  
>  	if (r_vec->nfp_net->tx_coalesce_adapt_on && r_vec->tx_ring) {
>  		struct dim_sample dim_sample = {};
>  		unsigned int start;
> @@ -1302,11 +1302,11 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget)
>  			pkts = r_vec->tx_pkts;
>  			bytes = r_vec->tx_bytes;
>  		} while (u64_stats_fetch_retry(&r_vec->tx_sync, start));
>  
>  		dim_update_sample(r_vec->event_ctr, pkts, bytes, &dim_sample);
> -		net_dim(&r_vec->tx_dim, dim_sample);
> +		net_dim(&r_vec->tx_dim, &dim_sample);
>  	}
>  
>  	return pkts_polled;
>  }
--- snip ---

Hi Caleb. Looks like a fair enough update to me in general, but I am not an
expert on 'dim'. For the corresponding nfp driver changes feel free to add:

Signed-off-by: Louis Peens <louis.peens at corigine.com>