LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Yunsheng Lin <linyunsheng@huawei.com>
To: <davem@davemloft.net>, <kuba@kernel.org>
Cc: <alexander.duyck@gmail.com>, <linux@armlinux.org.uk>,
	<mw@semihalf.com>, <linuxarm@openeuler.org>,
	<yisen.zhuang@huawei.com>, <salil.mehta@huawei.com>,
	<thomas.petazzoni@bootlin.com>, <hawk@kernel.org>,
	<ilias.apalodimas@linaro.org>, <ast@kernel.org>,
	<daniel@iogearbox.net>, <john.fastabend@gmail.com>,
	<akpm@linux-foundation.org>, <peterz@infradead.org>,
	<will@kernel.org>, <willy@infradead.org>, <vbabka@suse.cz>,
	<fenghua.yu@intel.com>, <guro@fb.com>, <peterx@redhat.com>,
	<feng.tang@intel.com>, <jgg@ziepe.ca>, <mcroce@microsoft.com>,
	<hughd@google.com>, <jonathan.lemon@gmail.com>, <alobakin@pm.me>,
	<willemb@google.com>, <wenxu@ucloud.cn>,
	<cong.wang@bytedance.com>, <haokexin@gmail.com>,
	<nogikh@google.com>, <elver@google.com>, <yhs@fb.com>,
	<kpsingh@kernel.org>, <andrii@kernel.org>, <kafai@fb.com>,
	<songliubraving@fb.com>, <netdev@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>, <bpf@vger.kernel.org>,
	<chenhao288@hisilicon.com>, <edumazet@google.com>,
	<yoshfuji@linux-ipv6.org>, <dsahern@kernel.org>,
	<memxor@gmail.com>, <linux@rempel-privat.de>,
	<atenart@kernel.org>, <weiwan@google.com>, <ap420073@gmail.com>,
	<arnd@arndb.de>, <mathew.j.martineau@linux.intel.com>,
	<aahringo@redhat.com>, <ceggers@arri.de>, <yangbo.lu@nxp.com>,
	<fw@strlen.de>, <xiangxia.m.yue@gmail.com>,
	<linmiaohe@huawei.com>
Subject: [PATCH RFC 2/7] skbuff: add interface to manipulate frag count for tx recycling
Date: Wed, 18 Aug 2021 11:32:18 +0800	[thread overview]
Message-ID: <1629257542-36145-3-git-send-email-linyunsheng@huawei.com> (raw)
In-Reply-To: <1629257542-36145-1-git-send-email-linyunsheng@huawei.com>

As the skb->pp_recycle and page->pp_magic may not be enough
to track if a frag page is from page pool after the calling
of __skb_frag_ref(), mostly because of a data race, see:
commit 2cc3aeb5eccc ("skbuff: Fix a potential race while
recycling page_pool packets").

As the case of tcp, there may be fragmenting, coalescing or
retransmiting case that might lose the track if a frag page
is from page pool or not.

So increment the frag count when __skb_frag_ref() is called,
and use the bit 0 in frag->bv_page to indicate if a page is
from a page pool, which automically pass down to another
frag->bv_page when doing a '*new_frag = *frag' or memcpying
the shinfo.

It seems we could do the trick for rx too if it makes sense.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/skbuff.h  | 43 ++++++++++++++++++++++++++++++++++++++++---
 include/net/page_pool.h |  5 +++++
 2 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6bdb0db..2878d26 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -331,6 +331,11 @@ static inline unsigned int skb_frag_size(const skb_frag_t *frag)
 	return frag->bv_len;
 }
 
+static inline bool skb_frag_is_pp(const skb_frag_t *frag)
+{
+	return (unsigned long)frag->bv_page & 1UL;
+}
+
 /**
  * skb_frag_size_set() - Sets the size of a skb fragment
  * @frag: skb fragment
@@ -2190,6 +2195,21 @@ static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 		skb->pfmemalloc	= true;
 }
 
+static inline void __skb_fill_pp_page_desc(struct sk_buff *skb, int i,
+					   struct page *page, int off,
+					   int size)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+	frag->bv_page = (struct page *)((unsigned long)page | 0x1UL);
+	frag->bv_offset = off;
+	skb_frag_size_set(frag, size);
+
+	page = compound_head(page);
+	if (page_is_pfmemalloc(page))
+		skb->pfmemalloc = true;
+}
+
 /**
  * skb_fill_page_desc - initialise a paged fragment in an skb
  * @skb: buffer containing fragment to be initialised
@@ -2211,6 +2231,14 @@ static inline void skb_fill_page_desc(struct sk_buff *skb, int i,
 	skb_shinfo(skb)->nr_frags = i + 1;
 }
 
+static inline void skb_fill_pp_page_desc(struct sk_buff *skb, int i,
+					 struct page *page, int off,
+					 int size)
+{
+	__skb_fill_pp_page_desc(skb, i, page, off, size);
+	skb_shinfo(skb)->nr_frags = i + 1;
+}
+
 void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
 		     int size, unsigned int truesize);
 
@@ -3062,7 +3090,10 @@ static inline void skb_frag_off_copy(skb_frag_t *fragto,
  */
 static inline struct page *skb_frag_page(const skb_frag_t *frag)
 {
-	return frag->bv_page;
+	unsigned long page = (unsigned long)frag->bv_page;
+
+	page &= ~1UL;
+	return (struct page *)page;
 }
 
 /**
@@ -3073,7 +3104,12 @@ static inline struct page *skb_frag_page(const skb_frag_t *frag)
  */
 static inline void __skb_frag_ref(skb_frag_t *frag)
 {
-	get_page(skb_frag_page(frag));
+	struct page *page = skb_frag_page(frag);
+
+	if (skb_frag_is_pp(frag))
+		page_pool_atomic_inc_frag_count(page);
+	else
+		get_page(page);
 }
 
 /**
@@ -3101,7 +3137,8 @@ static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle)
 	struct page *page = skb_frag_page(frag);
 
 #ifdef CONFIG_PAGE_POOL
-	if (recycle && page_pool_return_skb_page(page))
+	if ((recycle || skb_frag_is_pp(frag)) &&
+	    page_pool_return_skb_page(page))
 		return;
 #endif
 	put_page(page);
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index 8d4ae4b..86babb2 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -270,6 +270,11 @@ static inline long page_pool_atomic_sub_frag_count_return(struct page *page,
 	return ret;
 }
 
+static void page_pool_atomic_inc_frag_count(struct page *page)
+{
+	atomic_long_inc(&page->pp_frag_count);
+}
+
 static inline bool is_page_pool_compiled_in(void)
 {
 #ifdef CONFIG_PAGE_POOL
-- 
2.7.4


  parent reply	other threads:[~2021-08-18  3:34 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-18  3:32 [PATCH RFC 0/7] add socket to netdev page frag recycling support Yunsheng Lin
2021-08-18  3:32 ` [PATCH RFC 1/7] page_pool: refactor the page pool to support multi alloc context Yunsheng Lin
2021-08-18  3:32 ` Yunsheng Lin [this message]
2021-08-18  3:32 ` [PATCH RFC 3/7] net: add NAPI api to register and retrieve the page pool ptr Yunsheng Lin
2021-08-18  3:32 ` [PATCH RFC 4/7] net: pfrag_pool: add pfrag pool support based on page pool Yunsheng Lin
2021-08-18  3:32 ` [PATCH RFC 5/7] sock: support refilling pfrag from pfrag_pool Yunsheng Lin
2021-08-18  3:32 ` [PATCH RFC 6/7] net: hns3: support tx recycling in the hns3 driver Yunsheng Lin
2021-08-18  8:57 ` [PATCH RFC 0/7] add socket to netdev page frag recycling support Eric Dumazet
2021-08-18  9:36   ` Yunsheng Lin
2021-08-23  9:25     ` [Linuxarm] " Yunsheng Lin
2021-08-23 15:04       ` Eric Dumazet
2021-08-24  8:03         ` Yunsheng Lin
2021-08-25 16:29         ` David Ahern
2021-08-25 16:32           ` Eric Dumazet
2021-08-25 16:38             ` David Ahern
2021-08-25 17:24               ` Eric Dumazet
2021-08-26  4:05                 ` David Ahern
2021-08-18 22:05 ` David Ahern
2021-08-19  8:18   ` Yunsheng Lin
2021-08-20 14:35     ` David Ahern
2021-08-23  3:32       ` Yunsheng Lin
2021-08-24  3:34         ` David Ahern
2021-08-24  8:41           ` Yunsheng Lin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1629257542-36145-3-git-send-email-linyunsheng@huawei.com \
    --to=linyunsheng@huawei.com \
    --cc=aahringo@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=alobakin@pm.me \
    --cc=andrii@kernel.org \
    --cc=ap420073@gmail.com \
    --cc=arnd@arndb.de \
    --cc=ast@kernel.org \
    --cc=atenart@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=ceggers@arri.de \
    --cc=chenhao288@hisilicon.com \
    --cc=cong.wang@bytedance.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=elver@google.com \
    --cc=feng.tang@intel.com \
    --cc=fenghua.yu@intel.com \
    --cc=fw@strlen.de \
    --cc=guro@fb.com \
    --cc=haokexin@gmail.com \
    --cc=hawk@kernel.org \
    --cc=hughd@google.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jgg@ziepe.ca \
    --cc=john.fastabend@gmail.com \
    --cc=jonathan.lemon@gmail.com \
    --cc=kafai@fb.com \
    --cc=kpsingh@kernel.org \
    --cc=kuba@kernel.org \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=linux@rempel-privat.de \
    --cc=linuxarm@openeuler.org \
    --cc=mathew.j.martineau@linux.intel.com \
    --cc=mcroce@microsoft.com \
    --cc=memxor@gmail.com \
    --cc=mw@semihalf.com \
    --cc=netdev@vger.kernel.org \
    --cc=nogikh@google.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=salil.mehta@huawei.com \
    --cc=songliubraving@fb.com \
    --cc=thomas.petazzoni@bootlin.com \
    --cc=vbabka@suse.cz \
    --cc=weiwan@google.com \
    --cc=wenxu@ucloud.cn \
    --cc=will@kernel.org \
    --cc=willemb@google.com \
    --cc=willy@infradead.org \
    --cc=xiangxia.m.yue@gmail.com \
    --cc=yangbo.lu@nxp.com \
    --cc=yhs@fb.com \
    --cc=yisen.zhuang@huawei.com \
    --cc=yoshfuji@linux-ipv6.org \
    --subject='Re: [PATCH RFC 2/7] skbuff: add interface to manipulate frag count for tx recycling' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).