dim: pass dim_sample to net_dim() by reference

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@purestorage.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Arthur Kiyanovski <akiyano@amazon.com>
Reviewed-by: Louis Peens <louis.peens@corigine.com>
Link: https://patch.msgid.link/20241031002326.3426181-2-csander@purestorage.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 4 insertions, 4 deletions

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
@@ -1179,7 +1179,7 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget)
 		} 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) {
@@ -1194,7 +1194,7 @@ int nfp_nfd3_poll(struct napi_struct *napi, int budget)
 		} 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
@@ -1289,7 +1289,7 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget)
 		} 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) {
@@ -1304,7 +1304,7 @@ int nfp_nfdk_poll(struct napi_struct *napi, int budget)
 		} 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;