From 45933b2db91b9ee7c812b03f455316a1a61f7985 Mon Sep 17 00:00:00 2001 From: Vishvambar Panth S Date: Thu, 16 Nov 2023 11:13:50 +0530 Subject: net: microchip: lan743x : bidirectional throughput improvement The LAN743x/PCI11xxx DMA descriptors are always 4 dwords long, but the device supports placing the descriptors in memory back to back or reserving space in between them using its DMA_DESCRIPTOR_SPACE (DSPACE) configurable hardware setting. Currently DSPACE is unnecessarily set to match the host's L1 cache line size, resulting in space reserved in between descriptors in most platforms and causing a suboptimal behavior (single PCIe Mem transaction per descriptor). By changing the setting to DSPACE=16 many descriptors can be packed in a single PCIe Mem transaction resulting in a massive performance improvement in bidirectional tests without any negative effects. Tested and verified improvements on x64 PC and several ARM platforms (typical data below) Test setup 1: x64 PC with LAN7430 ---> x64 PC iperf3 UDP bidirectional with DSPACE set to L1 CACHE Size: - - - - - - - - - - - - - - - - - - - - - - - - - [ ID][Role] Interval Transfer Bitrate [ 5][TX-C] 0.00-10.00 sec 170 MBytes 143 Mbits/sec sender [ 5][TX-C] 0.00-10.04 sec 169 MBytes 141 Mbits/sec receiver [ 7][RX-C] 0.00-10.00 sec 1.02 GBytes 876 Mbits/sec sender [ 7][RX-C] 0.00-10.04 sec 1.02 GBytes 870 Mbits/sec receiver iperf3 UDP bidirectional with DSPACE set to 16 Bytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID][Role] Interval Transfer Bitrate [ 5][TX-C] 0.00-10.00 sec 1.11 GBytes 956 Mbits/sec sender [ 5][TX-C] 0.00-10.04 sec 1.11 GBytes 951 Mbits/sec receiver [ 7][RX-C] 0.00-10.00 sec 1.10 GBytes 948 Mbits/sec sender [ 7][RX-C] 0.00-10.04 sec 1.10 GBytes 942 Mbits/sec receiver Test setup 2 : RK3399 with LAN7430 ---> x64 PC RK3399 Spec: The SOM-RK3399 is ARM module designed and developed by FriendlyElec. Cores: 64-bit Dual Core Cortex-A72 + Quad Core Cortex-A53 Frequency: Cortex-A72(up to 2.0GHz), Cortex-A53(up to 1.5GHz) PCIe: PCIe x4, compatible with PCIe 2.1, Dual operation mode iperf3 UDP bidirectional with DSPACE set to L1 CACHE Size: - - - - - - - - - - - - - - - - - - - - - - - - - [ ID][Role] Interval Transfer Bitrate [ 5][TX-C] 0.00-10.00 sec 534 MBytes 448 Mbits/sec sender [ 5][TX-C] 0.00-10.05 sec 534 MBytes 446 Mbits/sec receiver [ 7][RX-C] 0.00-10.00 sec 1.12 GBytes 961 Mbits/sec sender [ 7][RX-C] 0.00-10.05 sec 1.11 GBytes 946 Mbits/sec receiver iperf3 UDP bidirectional with DSPACE set to 16 Bytes - - - - - - - - - - - - - - - - - - - - - - - - - [ ID][Role] Interval Transfer Bitrate [ 5][TX-C] 0.00-10.00 sec 966 MBytes 810 Mbits/sec sender [ 5][TX-C] 0.00-10.04 sec 965 MBytes 806 Mbits/sec receiver [ 7][RX-C] 0.00-10.00 sec 1.11 GBytes 956 Mbits/sec sender [ 7][RX-C] 0.00-10.04 sec 1.07 GBytes 919 Mbits/sec receiver Signed-off-by: Vishvambar Panth S Reviewed-by: Simon Horman Reviewed-by: Florian Fainelli Reviewed-by: Jacob Keller Link: https://lore.kernel.org/r/20231116054350.620420-1-vishvambarpanth.s@microchip.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index b648461787d2..be79cb0ae5af 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -1075,7 +1075,7 @@ struct lan743x_adapter { #define DMA_DESCRIPTOR_SPACING_32 (32) #define DMA_DESCRIPTOR_SPACING_64 (64) #define DMA_DESCRIPTOR_SPACING_128 (128) -#define DEFAULT_DMA_DESCRIPTOR_SPACING (L1_CACHE_BYTES) +#define DEFAULT_DMA_DESCRIPTOR_SPACING (DMA_DESCRIPTOR_SPACING_16) #define DMAC_CHANNEL_STATE_SET(start_bit, stop_bit) \ (((start_bit) ? 2 : 0) | ((stop_bit) ? 1 : 0)) -- cgit v1.2.3