| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1449543751-131670-1-git-send-email-yankejian@huawei.com>
Date: Tue, 8 Dec 2015 11:02:31 +0800
From: Kejian Yan <yankejian@...wei.com>
To: <davem@...emloft.net>, <lisheng011@...wei.com>,
<lipeng321@...wei.com>, <yankejian@...wei.com>,
<salil.mehta@...wei.com>, <huangdaode@...ilicon.com>,
<xuwei5@...ilicon.com>, <liguozhu@...wei.com>
CC: <haifeng.wei@...wei.com>, <yisen.zhuang@...wei.com>,
<linuxarm@...wei.com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>
Subject: [PATCH v2 net-next] net: hns: optimize XGE capability by reducing cpu usage
here is the patch raising the performance of XGE by:
1)changes the way page management method for enet momery, and
2)reduces the count of rmb, and
3)adds Memory prefetching
Signed-off-by: Kejian Yan <yankejian@...wei.com>
---
change log:
v2:
fixes the review comments by Devid and joe:
- makes indented properly
- removes useless variable initialization
v1:
Intial driver Version
v1 patch reference: https://lkml.org/lkml/2015/12/5/20
---
drivers/net/ethernet/hisilicon/hns/hnae.h | 5 +-
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 1 -
drivers/net/ethernet/hisilicon/hns/hns_enet.c | 79 +++++++++++++++--------
3 files changed, 55 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index d1f3316..6ca94dc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -341,7 +341,8 @@ struct hnae_queue {
void __iomem *io_base;
phys_addr_t phy_base;
struct hnae_ae_dev *dev; /* the device who use this queue */
- struct hnae_ring rx_ring, tx_ring;
+ struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp;
+ struct hnae_ring tx_ring ____cacheline_internodealigned_in_smp;
struct hnae_handle *handle;
};
@@ -597,11 +598,9 @@ static inline void hnae_replace_buffer(struct hnae_ring *ring, int i,
struct hnae_desc_cb *res_cb)
{
struct hnae_buf_ops *bops = ring->q->handle->bops;
- struct hnae_desc_cb tmp_cb = ring->desc_cb[i];
bops->unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc_cb[i] = *res_cb;
- *res_cb = tmp_cb;
ring->desc[i].addr = (__le64)ring->desc_cb[i].dma;
ring->desc[i].rx.ipoff_bnum_pid_flag = 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index 77c6edb..522b264 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -341,7 +341,6 @@ void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
else
flag = RCB_INT_FLAG_RX;
- hns_rcb_int_clr_hw(ring->q, flag);
hns_rcb_int_ctrl_hw(ring->q, flag, mask);
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index cad2663..5a81daf 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -33,6 +33,7 @@
#define RCB_IRQ_NOT_INITED 0
#define RCB_IRQ_INITED 1
+#define HNS_BUFFER_SIZE_2048 2048
#define BD_MAX_SEND_SIZE 8191
#define SKB_TMP_LEN(SKB) \
@@ -491,13 +492,51 @@ static unsigned int hns_nic_get_headlen(unsigned char *data, u32 flag,
return max_size;
}
-static void
-hns_nic_reuse_page(struct hnae_desc_cb *desc_cb, int tsize, int last_offset)
+static void hns_nic_reuse_page(struct sk_buff *skb, int i,
+ struct hnae_ring *ring, int pull_len,
+ struct hnae_desc_cb *desc_cb)
{
+ struct hnae_desc *desc;
+ int truesize, size;
+ int last_offset;
+
+ desc = &ring->desc[ring->next_to_clean];
+ size = le16_to_cpu(desc->rx.size);
+
+#if (PAGE_SIZE < 8192)
+ if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) {
+ truesize = hnae_buf_size(ring);
+ } else {
+ truesize = ALIGN(size, L1_CACHE_BYTES);
+ last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
+ }
+
+#else
+ truesize = ALIGN(size, L1_CACHE_BYTES);
+ last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
+#endif
+
+ skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
+ size - pull_len, truesize - pull_len);
+
/* avoid re-using remote pages,flag default unreuse */
if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) {
+#if (PAGE_SIZE < 8192)
+ if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) {
+ /* if we are only owner of page we can reuse it */
+ if (likely(page_count(desc_cb->priv) == 1)) {
+ /* flip page offset to other buffer */
+ desc_cb->page_offset ^= truesize;
+
+ desc_cb->reuse_flag = 1;
+ /* bump ref count on page before it is given*/
+ get_page(desc_cb->priv);
+ }
+ return;
+ }
+#endif
/* move offset up to the next cache line */
- desc_cb->page_offset += tsize;
+ desc_cb->page_offset += truesize;
if (desc_cb->page_offset <= last_offset) {
desc_cb->reuse_flag = 1;
@@ -529,11 +568,10 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
struct hnae_desc *desc;
struct hnae_desc_cb *desc_cb;
unsigned char *va;
- int bnum, length, size, i, truesize, last_offset;
+ int bnum, length, i;
int pull_len;
u32 bnum_flag;
- last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
desc = &ring->desc[ring->next_to_clean];
desc_cb = &ring->desc_cb[ring->next_to_clean];
@@ -555,17 +593,12 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
return -ENOMEM;
}
+ prefetchw(skb->data);
length = le16_to_cpu(desc->rx.pkt_len);
bnum_flag = le32_to_cpu(desc->rx.ipoff_bnum_pid_flag);
priv->ops.get_rxd_bnum(bnum_flag, &bnum);
*out_bnum = bnum;
- /* we will be copying header into skb->data in
- * pskb_may_pull so it is in our interest to prefetch
- * it now to avoid a possible cache miss
- */
- prefetchw(skb->data);
-
if (length <= HNS_RX_HEAD_SIZE) {
memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
@@ -588,13 +621,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
memcpy(__skb_put(skb, pull_len), va,
ALIGN(pull_len, sizeof(long)));
- size = le16_to_cpu(desc->rx.size);
- truesize = ALIGN(size, L1_CACHE_BYTES);
- skb_add_rx_frag(skb, 0, desc_cb->priv,
- desc_cb->page_offset + pull_len,
- size - pull_len, truesize - pull_len);
-
- hns_nic_reuse_page(desc_cb, truesize, last_offset);
+ hns_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
ring_ptr_move_fw(ring, next_to_clean);
if (unlikely(bnum >= (int)MAX_SKB_FRAGS)) { /* check err*/
@@ -604,13 +631,8 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data,
for (i = 1; i < bnum; i++) {
desc = &ring->desc[ring->next_to_clean];
desc_cb = &ring->desc_cb[ring->next_to_clean];
- size = le16_to_cpu(desc->rx.size);
- truesize = ALIGN(size, L1_CACHE_BYTES);
- skb_add_rx_frag(skb, i, desc_cb->priv,
- desc_cb->page_offset,
- size, truesize);
- hns_nic_reuse_page(desc_cb, truesize, last_offset);
+ hns_nic_reuse_page(skb, i, ring, 0, desc_cb);
ring_ptr_move_fw(ring, next_to_clean);
}
}
@@ -750,9 +772,10 @@ recv:
/* make all data has been write before submit */
if (recv_pkts < budget) {
ex_num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM);
- rmb(); /*complete read rx ring bd number*/
+
if (ex_num > clean_count) {
num += ex_num - clean_count;
+ rmb(); /*complete read rx ring bd number*/
goto recv;
}
}
@@ -849,8 +872,11 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
bytes = 0;
pkts = 0;
- while (head != ring->next_to_clean)
+ while (head != ring->next_to_clean) {
hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
+ /* issue prefetch for next Tx descriptor */
+ prefetch(&ring->desc_cb[ring->next_to_clean]);
+ }
NETIF_TX_UNLOCK(ndev);
@@ -926,6 +952,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget)
ring_data->ring, 0);
ring_data->fini_process(ring_data);
+ return 0;
}
return clean_complete;
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists