[][Add some eth performance patch cherry-pick from OpenWRT/Linux]
[Description]
Add some eth performance patch cherry-pick from OpenWRT/Linux
770-00-net-ethernet-mtk_eth_soc-use-napi_consume_skb.patch
770-01-net-ethernet-mtk_eth_soc-significantly-reduce-mdio-b.patch
770-08-net-ethernet-mtk_eth_soc-cache-hardware-pointer-of-l.patch
770-09-net-ethernet-mtk_eth_soc-only-read-the-full-rx-descr.patch
770-10-net-ethernet-mtk_eth_soc-unmap-rx-data-before-callin.patch
770-11-net-ethernet-mtk_eth_soc-avoid-rearming-interrupt-if.patch
[Release-log]
N/A
Change-Id: If7d5b278332fd9f54d43710ff178c8217d5dee09
Reviewed-on: https://gerrit.mediatek.inc/c/openwrt/feeds/mtk_openwrt_feeds/+/4588852
diff --git a/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 04128d6..99b24e9 100755
--- a/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -91,7 +91,7 @@
return 0;
if (time_after(jiffies, t_start + PHY_IAC_TIMEOUT))
break;
- usleep_range(10, 20);
+ cond_resched();
}
dev_err(eth->dev, "mdio: MDIO timeout\n");
@@ -806,17 +806,21 @@
return buf_size;
}
-static inline void mtk_rx_get_desc(struct mtk_rx_dma *rxd,
+static inline bool mtk_rx_get_desc(struct mtk_rx_dma *rxd,
struct mtk_rx_dma *dma_rxd)
{
- rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
rxd->rxd2 = READ_ONCE(dma_rxd->rxd2);
+ if (!(rxd->rxd2 & RX_DMA_DONE))
+ return false;
+
+ rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
rxd->rxd3 = READ_ONCE(dma_rxd->rxd3);
rxd->rxd4 = READ_ONCE(dma_rxd->rxd4);
#ifdef CONFIG_MEDIATEK_NETSYS_RX_V2
rxd->rxd5 = READ_ONCE(dma_rxd->rxd5);
rxd->rxd6 = READ_ONCE(dma_rxd->rxd6);
#endif
+ return true;
}
/* the qdma core needs scratch memory to be setup */
@@ -906,7 +910,8 @@
return ((void *)dma - (void *)ring->dma) / sizeof(*dma);
}
-static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf)
+static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf,
+ bool napi)
{
if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) {
if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) {
@@ -938,8 +943,12 @@
tx_buf->flags = 0;
if (tx_buf->skb &&
- (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC))
- dev_kfree_skb_any(tx_buf->skb);
+ (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC)) {
+ if (napi)
+ napi_consume_skb(tx_buf->skb, napi);
+ else
+ dev_kfree_skb_any(tx_buf->skb);
+ }
tx_buf->skb = NULL;
}
@@ -1181,7 +1190,7 @@
tx_buf = mtk_desc_to_tx_buf(ring, itxd);
/* unmap dma */
- mtk_tx_unmap(eth, tx_buf);
+ mtk_tx_unmap(eth, tx_buf, false);
itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU;
if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA))
@@ -1361,8 +1370,7 @@
rxd = &ring->dma[idx];
data = ring->data[idx];
- mtk_rx_get_desc(&trxd, rxd);
- if (!(trxd.rxd2 & RX_DMA_DONE))
+ if (!mtk_rx_get_desc(&trxd, rxd))
break;
/* find out which mac the packet come from. values start at 1 */
@@ -1404,17 +1412,18 @@
goto release_desc;
}
+ dma_unmap_single(eth->dev, trxd.rxd1,
+ ring->buf_size, DMA_FROM_DEVICE);
+
/* receive data */
skb = build_skb(data, ring->frag_size);
if (unlikely(!skb)) {
- skb_free_frag(new_data);
+ skb_free_frag(data);
netdev->stats.rx_dropped++;
- goto release_desc;
+ goto skip_rx;
}
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
- dma_unmap_single(eth->dev, trxd.rxd1,
- ring->buf_size, DMA_FROM_DEVICE);
pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
skb->dev = netdev;
skb_put(skb, pktlen);
@@ -1477,6 +1486,7 @@
skb_record_rx_queue(skb, 0);
napi_gro_receive(napi, skb);
+skip_rx:
ring->data[idx] = new_data;
rxd->rxd1 = (unsigned int)dma_addr;
@@ -1512,7 +1522,7 @@
struct mtk_tx_buf *tx_buf;
u32 cpu, dma;
- cpu = mtk_r32(eth, MTK_QTX_CRX_PTR);
+ cpu = ring->last_free_ptr;
dma = mtk_r32(eth, MTK_QTX_DRX_PTR);
desc = mtk_qdma_phys_to_virt(ring, cpu);
@@ -1539,7 +1549,7 @@
done[mac]++;
budget--;
}
- mtk_tx_unmap(eth, tx_buf);
+ mtk_tx_unmap(eth, tx_buf, true);
ring->last_free = desc;
atomic_inc(&ring->free_count);
@@ -1547,6 +1557,7 @@
cpu = next_cpu;
}
+ ring->last_free_ptr = cpu;
mtk_w32(eth, cpu, MTK_QTX_CRX_PTR);
return budget;
@@ -1576,7 +1587,7 @@
budget--;
}
- mtk_tx_unmap(eth, tx_buf);
+ mtk_tx_unmap(eth, tx_buf, true);
desc = &ring->dma[cpu];
ring->last_free = desc;
@@ -1656,8 +1667,8 @@
if (status & MTK_TX_DONE_INT)
return budget;
- napi_complete(napi);
- mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
+ if (napi_complete(napi))
+ mtk_tx_irq_enable(eth, MTK_TX_DONE_INT);
return tx_done;
}
@@ -1690,8 +1701,9 @@
remain_budget -= rx_done;
goto poll_again;
}
- napi_complete(napi);
- mtk_rx_irq_enable(eth, MTK_RX_DONE_INT);
+
+ if (napi_complete(napi))
+ mtk_rx_irq_enable(eth, MTK_RX_DONE_INT);
return rx_done + budget - remain_budget;
}
@@ -1755,6 +1767,7 @@
atomic_set(&ring->free_count, MTK_DMA_SIZE - 2);
ring->next_free = &ring->dma[0];
ring->last_free = &ring->dma[MTK_DMA_SIZE - 1];
+ ring->last_free_ptr = (u32)(ring->phys + ((MTK_DMA_SIZE - 1) * sz));
ring->thresh = MAX_SKB_FRAGS;
/* make sure that all changes to the dma ring are flushed before we
@@ -1768,9 +1781,7 @@
mtk_w32(eth,
ring->phys + ((MTK_DMA_SIZE - 1) * sz),
MTK_QTX_CRX_PTR);
- mtk_w32(eth,
- ring->phys + ((MTK_DMA_SIZE - 1) * sz),
- MTK_QTX_DRX_PTR);
+ mtk_w32(eth, ring->last_free_ptr, MTK_QTX_DRX_PTR);
mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES,
MTK_QTX_CFG(0));
} else {
@@ -1793,7 +1804,7 @@
if (ring->buf) {
for (i = 0; i < MTK_DMA_SIZE; i++)
- mtk_tx_unmap(eth, &ring->buf[i]);
+ mtk_tx_unmap(eth, &ring->buf[i], false);
kfree(ring->buf);
ring->buf = NULL;
}
diff --git a/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 25c2c21..41b46c4 100755
--- a/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/target/linux/mediatek/files-5.4/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -750,6 +750,7 @@
* @phys: The physical addr of tx_buf
* @next_free: Pointer to the next free descriptor
* @last_free: Pointer to the last free descriptor
+ * @last_free_ptr: Hardware pointer value of the last free descriptor
* @thresh: The threshold of minimum amount of free descriptors
* @free_count: QDMA uses a linked list. Track how many free descriptors
* are present
@@ -760,6 +761,7 @@
dma_addr_t phys;
struct mtk_tx_dma *next_free;
struct mtk_tx_dma *last_free;
+ u32 last_free_ptr;
u16 thresh;
atomic_t free_count;
int dma_size;