kernel/patches/0490-net-hns3-optimize-the-rx-page-reuse-handling-process.patch

From eb403e52b15e84ee38bbce5b6145147a4df78b4f Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Sat, 24 Jul 2021 15:45:26 +0800
Subject: [PATCH 129/283] net: hns3: optimize the rx page reuse handling
 process

mainline inclusion
from mainline-v5.14-rc1
commit fa7711b888f24ee9291d90f8fbdaccfc80ed72c7
category: feature
bugzilla: https://gitee.com/src-openeuler/kernel/issues/I8EMYT
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fa7711b888f24ee9291d90f8fbdaccfc80ed72c7

----------------------------------------------------------------------

Current rx page offset only reset to zero when all the below
conditions are satisfied:
1. rx page is only owned by driver.
2. rx page is reusable.
3. the page offset that is above to be given to the stack has
reached the end of the page.

If the page offset is over the hns3_buf_size(), it means the
buffer below the offset of the page is usable when the above
condition 1 & 2 are satisfied, so page offset can be reset to
zero instead of increasing the offset. We may be able to always
reuse the first 4K buffer of a 64K page, which means we can
limit the hot buffer size as much as possible.

The above optimization is a side effect when refacting the
rx page reuse handling in order to support the rx copybreak.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Guangbin Huang <huangguangbin2@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Yongxin Li <liyongxin1@huawei.com>
Signed-off-by: Junxin Chen <chenjunxin1@huawei.com>
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: Xiaodong Li <lixiaodong67@huawei.com>

 Conflicts:
	drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
---
 .../net/ethernet/hisilicon/hns3/hns3_enet.c   | 60 +++++++++++--------
 include/linux/skbuff.h                        | 16 +++++
 2 files changed, 50 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 76bf5fc69e7d..c84a5e942b68 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3194,7 +3194,35 @@ static bool hns3_page_is_reusable(struct page *page)
 
 static bool hns3_can_reuse_page(struct hns3_desc_cb *cb)
 {
-	return (page_count(cb->priv) - cb->pagecnt_bias) == 1;
+	return page_count(cb->priv) == cb->pagecnt_bias;
+}
+
+static int hns3_handle_rx_copybreak(struct sk_buff *skb, int i,
+				    struct hns3_enet_ring *ring,
+				    int pull_len,
+				    struct hns3_desc_cb *desc_cb)
+{
+	struct hns3_desc *desc = &ring->desc[ring->next_to_clean];
+	u32 frag_offset = desc_cb->page_offset + pull_len;
+	int size = le16_to_cpu(desc->rx.size);
+	u32 frag_size = size - pull_len;
+	void *frag = napi_alloc_frag(frag_size);
+
+	if (unlikely(!frag)) {
+		hns3_ring_stats_update(ring, frag_alloc_err);
+
+		hns3_rl_err(ring_to_netdev(ring),
+			    "failed to allocate rx frag\n");
+		return -ENOMEM;
+	}
+
+	desc_cb->reuse_flag = 1;
+	memcpy(frag, desc_cb->buf + frag_offset, frag_size);
+	skb_add_rx_frag(skb, i, virt_to_page(frag),
+			offset_in_page(frag), frag_size, frag_size);
+
+	hns3_ring_stats_update(ring, frag_alloc);
+	return 0;
 }
 
 static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
@@ -3206,13 +3234,12 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	int size = le16_to_cpu(desc->rx.size);
 	u32 truesize = hns3_buf_size(ring);
 	u32 frag_size = size - pull_len;
+	int ret = 0;
 	bool reused;
 
-	if (unlikely(!hns3_page_is_reusable(desc_cb->priv)) ||
-	    (!desc_cb->page_offset && !hns3_can_reuse_page(desc_cb))) {
-		__page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias);
-		return;
-	}
+	/* Avoid re-using remote or pfmem page */
+	if (unlikely(!dev_page_is_reusable(desc_cb->priv)))
+		goto out;
 
 	reused = hns3_can_reuse_page(desc_cb);
 
@@ -3236,26 +3263,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 		desc_cb->page_offset = 0;
 		desc_cb->reuse_flag = 1;
 	} else if (frag_size <= ring->rx_copybreak) {
-		void *frag = napi_alloc_frag(frag_size);
-
-		if (unlikely(!frag)) {
-			u64_stats_update_begin(&ring->syncp);
-			ring->stats.frag_alloc_err++;
-			u64_stats_update_end(&ring->syncp);
-
-			hns3_rl_err(ring_to_netdev(ring),
-				    "failed to allocate rx frag\n");
-			goto out;
-		}
-
-		desc_cb->reuse_flag = 1;
-		memcpy(frag, desc_cb->buf + frag_offset, frag_size);
-		skb_add_rx_frag(skb, i, virt_to_page(frag),
-				offset_in_page(frag), frag_size, frag_size);
-
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.frag_alloc++;
-		u64_stats_update_end(&ring->syncp);
+		ret = hns3_handle_rx_copybreak(skb, i, ring, pull_len, desc_cb);
 		return;
 	}
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b67d42871ee9..bf080a114205 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2789,6 +2789,22 @@ static inline struct page *dev_alloc_page(void)
 	return dev_alloc_pages(0);
 }
 
+/**
+ * dev_page_is_reusable - check whether a page can be reused for network Rx
+ * @page: the page to test
+ *
+ * A page shouldn't be considered for reusing/recycling if it was allocated
+ * under memory pressure or at a distant memory node.
+ *
+ * Returns false if this page should be returned to page allocator, true
+ * otherwise.
+ */
+static inline bool dev_page_is_reusable(struct page *page)
+{
+	return likely(page_to_nid(page) == numa_mem_id() &&
+		      !page_is_pfmemalloc(page));
+}
+
 /**
  *	skb_propagate_pfmemalloc - Propagate pfmemalloc if skb is allocated after RX page
  *	@page: The page that was allocated from skb_alloc_page
-- 
2.34.1