| 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: <1628161526-29076-5-git-send-email-linyunsheng@huawei.com>
Date: Thu, 5 Aug 2021 19:05:26 +0800
From: Yunsheng Lin <linyunsheng@...wei.com>
To: <davem@...emloft.net>, <kuba@...nel.org>
CC: <alexander.duyck@...il.com>, <linux@...linux.org.uk>,
<mw@...ihalf.com>, <linuxarm@...neuler.org>,
<yisen.zhuang@...wei.com>, <salil.mehta@...wei.com>,
<thomas.petazzoni@...tlin.com>, <hawk@...nel.org>,
<ilias.apalodimas@...aro.org>, <ast@...nel.org>,
<daniel@...earbox.net>, <john.fastabend@...il.com>,
<akpm@...ux-foundation.org>, <peterz@...radead.org>,
<will@...nel.org>, <willy@...radead.org>, <vbabka@...e.cz>,
<fenghua.yu@...el.com>, <guro@...com>, <peterx@...hat.com>,
<feng.tang@...el.com>, <jgg@...pe.ca>, <mcroce@...rosoft.com>,
<hughd@...gle.com>, <jonathan.lemon@...il.com>, <alobakin@...me>,
<willemb@...gle.com>, <wenxu@...oud.cn>, <cong.wang@...edance.com>,
<haokexin@...il.com>, <nogikh@...gle.com>, <elver@...gle.com>,
<yhs@...com>, <kpsingh@...nel.org>, <andrii@...nel.org>,
<kafai@...com>, <songliubraving@...com>, <netdev@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <bpf@...r.kernel.org>,
<chenhao288@...ilicon.com>
Subject: [PATCH net-next 4/4] net: hns3: support skb's frag page recycling based on page pool
This patch adds skb's frag page recycling support based on
the frag page support in page pool.
The performance improves above 10~20% for single thread iperf
TCP flow with IOMMU disabled when iperf server and irq/NAPI
have a different CPU.
The performance improves about 135%(14Gbit to 33Gbit) for single
thread iperf TCP flow IOMMU is in strict mode and iperf server
shares the same cpu with irq/NAPI.
Signed-off-by: Yunsheng Lin <linyunsheng@...wei.com>
---
drivers/net/ethernet/hisilicon/Kconfig | 1 +
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 79 +++++++++++++++++++++++--
drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 3 +
3 files changed, 78 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index bb062b0..4e114f4 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -90,6 +90,7 @@ config HNS_ENET
config HNS3
tristate "Hisilicon Network Subsystem Support HNS3 (Framework)"
depends on PCI
+ select PAGE_POOL
help
This selects the framework support for Hisilicon Network Subsystem 3.
This layer facilitates clients like ENET, RoCE and user-space ethernet
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index cdb5f14..90597fe 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3205,6 +3205,21 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
unsigned int order = hns3_page_order(ring);
struct page *p;
+ if (ring->page_pool) {
+ p = page_pool_dev_alloc_frag(ring->page_pool,
+ &cb->page_offset,
+ hns3_buf_size(ring));
+ if (unlikely(!p))
+ return -ENOMEM;
+
+ cb->priv = p;
+ cb->buf = page_address(p);
+ cb->dma = page_pool_get_dma_addr(p);
+ cb->type = DESC_TYPE_PP_FRAG;
+ cb->reuse_flag = 0;
+ return 0;
+ }
+
p = dev_alloc_pages(order);
if (!p)
return -ENOMEM;
@@ -3227,8 +3242,13 @@ static void hns3_free_buffer(struct hns3_enet_ring *ring,
if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD |
DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB))
napi_consume_skb(cb->priv, budget);
- else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias)
- __page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+ else if (!HNAE3_IS_TX_RING(ring)) {
+ if (cb->type & DESC_TYPE_PAGE && cb->pagecnt_bias)
+ __page_frag_cache_drain(cb->priv, cb->pagecnt_bias);
+ else if (cb->type & DESC_TYPE_PP_FRAG)
+ page_pool_put_full_page(ring->page_pool, cb->priv,
+ false);
+ }
memset(cb, 0, sizeof(*cb));
}
@@ -3315,7 +3335,7 @@ static int hns3_alloc_and_map_buffer(struct hns3_enet_ring *ring,
int ret;
ret = hns3_alloc_buffer(ring, cb);
- if (ret)
+ if (ret || ring->page_pool)
goto out;
ret = hns3_map_buffer(ring, cb);
@@ -3337,7 +3357,8 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i)
if (ret)
return ret;
- ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+ ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+ ring->desc_cb[i].page_offset);
return 0;
}
@@ -3367,7 +3388,8 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
{
hns3_unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc_cb[i] = *res_cb;
- ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma);
+ ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
+ ring->desc_cb[i].page_offset);
ring->desc[i].rx.bd_base_info = 0;
}
@@ -3539,6 +3561,12 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
u32 frag_size = size - pull_len;
bool reused;
+ if (ring->page_pool) {
+ skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset,
+ frag_size, truesize);
+ return;
+ }
+
/* Avoid re-using remote or pfmem page */
if (unlikely(!dev_page_is_reusable(desc_cb->priv)))
goto out;
@@ -3856,6 +3884,9 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
/* We can reuse buffer as-is, just make sure it is reusable */
if (dev_page_is_reusable(desc_cb->priv))
desc_cb->reuse_flag = 1;
+ else if (desc_cb->type & DESC_TYPE_PP_FRAG)
+ page_pool_put_full_page(ring->page_pool, desc_cb->priv,
+ false);
else /* This page cannot be reused so discard it */
__page_frag_cache_drain(desc_cb->priv,
desc_cb->pagecnt_bias);
@@ -3863,6 +3894,10 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length,
hns3_rx_ring_move_fw(ring);
return 0;
}
+
+ if (ring->page_pool)
+ skb_mark_for_recycle(skb);
+
u64_stats_update_begin(&ring->syncp);
ring->stats.seg_pkt_cnt++;
u64_stats_update_end(&ring->syncp);
@@ -3901,6 +3936,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring)
"alloc rx fraglist skb fail\n");
return -ENXIO;
}
+
+ if (ring->page_pool)
+ skb_mark_for_recycle(new_skb);
+
ring->frag_num = 0;
if (ring->tail_skb) {
@@ -4705,6 +4744,29 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv)
priv->ring = NULL;
}
+static void hns3_alloc_page_pool(struct hns3_enet_ring *ring)
+{
+ struct page_pool_params pp_params = {
+ .flags = PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG |
+ PP_FLAG_DMA_SYNC_DEV,
+ .order = hns3_page_order(ring),
+ .pool_size = ring->desc_num * hns3_buf_size(ring) /
+ (PAGE_SIZE << hns3_page_order(ring)),
+ .nid = dev_to_node(ring_to_dev(ring)),
+ .dev = ring_to_dev(ring),
+ .dma_dir = DMA_FROM_DEVICE,
+ .offset = 0,
+ .max_len = PAGE_SIZE << hns3_page_order(ring),
+ };
+
+ ring->page_pool = page_pool_create(&pp_params);
+ if (IS_ERR(ring->page_pool)) {
+ dev_warn(ring_to_dev(ring), "page pool creation failed: %ld\n",
+ PTR_ERR(ring->page_pool));
+ ring->page_pool = NULL;
+ }
+}
+
static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
{
int ret;
@@ -4724,6 +4786,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring)
goto out_with_desc_cb;
if (!HNAE3_IS_TX_RING(ring)) {
+ hns3_alloc_page_pool(ring);
+
ret = hns3_alloc_ring_buffers(ring);
if (ret)
goto out_with_desc;
@@ -4764,6 +4828,11 @@ void hns3_fini_ring(struct hns3_enet_ring *ring)
devm_kfree(ring_to_dev(ring), tx_spare);
ring->tx_spare = NULL;
}
+
+ if (!HNAE3_IS_TX_RING(ring) && ring->page_pool) {
+ page_pool_destroy(ring->page_pool);
+ ring->page_pool = NULL;
+ }
}
static int hns3_buf_size2type(u32 buf_size)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 15af3d9..27809d6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -6,6 +6,7 @@
#include <linux/dim.h>
#include <linux/if_vlan.h>
+#include <net/page_pool.h>
#include "hnae3.h"
@@ -307,6 +308,7 @@ enum hns3_desc_type {
DESC_TYPE_BOUNCE_ALL = 1 << 3,
DESC_TYPE_BOUNCE_HEAD = 1 << 4,
DESC_TYPE_SGL_SKB = 1 << 5,
+ DESC_TYPE_PP_FRAG = 1 << 6,
};
struct hns3_desc_cb {
@@ -451,6 +453,7 @@ struct hns3_enet_ring {
struct hnae3_queue *tqp;
int queue_index;
struct device *dev; /* will be used for DMA mapping of descriptors */
+ struct page_pool *page_pool;
/* statistic */
struct ring_stats stats;
--
2.7.4
Powered by blists - more mailing lists