Merge branch 'net-stmmac-rx-performance-improvement'

Furong Xu says:

====================
net: stmmac: RX performance improvement

This series improves RX performance a lot, ~40% TCP RX throughput boost
has been observed with DWXGMAC CORE 3.20a running on Cortex-A65 CPUs:
from 2.18 Gbits/sec increased to 3.06 Gbits/sec.
====================

Link: https://patch.msgid.link/cover.1736910454.git.0x1207@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This commit is contained in:
Paolo Abeni 2025-01-16 12:14:24 +01:00
commit b44e27b4df
3 changed files with 21 additions and 15 deletions

View File

@ -126,6 +126,7 @@ struct stmmac_rx_queue {
unsigned int cur_rx;
unsigned int dirty_rx;
unsigned int buf_alloc_num;
unsigned int napi_skb_frag_size;
dma_addr_t dma_rx_phy;
u32 rx_tail_addr;
unsigned int state_saved;

View File

@ -1341,7 +1341,7 @@ static unsigned int stmmac_rx_offset(struct stmmac_priv *priv)
if (stmmac_xdp_is_enabled(priv))
return XDP_PACKET_HEADROOM;
return 0;
return NET_SKB_PAD;
}
static int stmmac_set_bfsize(int mtu, int bufsize)
@ -2040,22 +2040,26 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv,
struct stmmac_channel *ch = &priv->channel[queue];
bool xdp_prog = stmmac_xdp_is_enabled(priv);
struct page_pool_params pp_params = { 0 };
unsigned int num_pages;
unsigned int dma_buf_sz_pad, num_pages;
unsigned int napi_id;
int ret;
dma_buf_sz_pad = stmmac_rx_offset(priv) + dma_conf->dma_buf_sz +
SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
num_pages = DIV_ROUND_UP(dma_buf_sz_pad, PAGE_SIZE);
rx_q->queue_index = queue;
rx_q->priv_data = priv;
rx_q->napi_skb_frag_size = num_pages * PAGE_SIZE;
pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
pp_params.pool_size = dma_conf->dma_rx_size;
num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE);
pp_params.order = ilog2(num_pages);
pp_params.order = order_base_2(num_pages);
pp_params.nid = dev_to_node(priv->device);
pp_params.dev = priv->device;
pp_params.dma_dir = xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
pp_params.offset = stmmac_rx_offset(priv);
pp_params.max_len = STMMAC_MAX_RX_BUF_SIZE(num_pages);
pp_params.max_len = dma_conf->dma_buf_sz;
rx_q->page_pool = page_pool_create(&pp_params);
if (IS_ERR(rx_q->page_pool)) {
@ -5504,10 +5508,6 @@ read_again:
/* Buffer is good. Go on. */
prefetch(page_address(buf->page) + buf->page_offset);
if (buf->sec_page)
prefetch(page_address(buf->sec_page));
buf1_len = stmmac_rx_buf1_len(priv, p, status, len);
len += buf1_len;
buf2_len = stmmac_rx_buf2_len(priv, p, status, len);
@ -5529,6 +5529,8 @@ read_again:
dma_sync_single_for_cpu(priv->device, buf->addr,
buf1_len, dma_dir);
net_prefetch(page_address(buf->page) +
buf->page_offset);
xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq);
xdp_prepare_buff(&ctx.xdp, page_address(buf->page),
@ -5582,22 +5584,26 @@ read_again:
}
if (!skb) {
unsigned int head_pad_len;
/* XDP program may expand or reduce tail */
buf1_len = ctx.xdp.data_end - ctx.xdp.data;
skb = napi_alloc_skb(&ch->rx_napi, buf1_len);
skb = napi_build_skb(page_address(buf->page),
rx_q->napi_skb_frag_size);
if (!skb) {
page_pool_recycle_direct(rx_q->page_pool,
buf->page);
rx_dropped++;
count++;
goto drain_data;
}
/* XDP program may adjust header */
skb_copy_to_linear_data(skb, ctx.xdp.data, buf1_len);
head_pad_len = ctx.xdp.data - ctx.xdp.data_hard_start;
skb_reserve(skb, head_pad_len);
skb_put(skb, buf1_len);
/* Data payload copied into SKB, page ready for recycle */
page_pool_recycle_direct(rx_q->page_pool, buf->page);
skb_mark_for_recycle(skb);
buf->page = NULL;
} else if (buf1_len) {
dma_sync_single_for_cpu(priv->device, buf->addr,

View File

@ -4,7 +4,6 @@
#ifndef _STMMAC_XDP_H_
#define _STMMAC_XDP_H_
#define STMMAC_MAX_RX_BUF_SIZE(num) (((num) * PAGE_SIZE) - XDP_PACKET_HEADROOM)
#define STMMAC_RX_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
int stmmac_xdp_setup_pool(struct stmmac_priv *priv, struct xsk_buff_pool *pool,