From:   Pavel Begunkov <asml.silence@gmail.com>
To:     io-uring@vger.kernel.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org
Cc:     Jakub Kicinski <kuba@kernel.org>,
        Jonathan Lemon <jonathan.lemon@gmail.com>,
        "David S . Miller" <davem@davemloft.net>,
        Willem de Bruijn <willemb@google.com>,
        Eric Dumazet <edumazet@google.com>,
        David Ahern <dsahern@kernel.org>, Jens Axboe <axboe@kernel.dk>,
        Pavel Begunkov <asml.silence@gmail.com>
Subject: [RFC v2 05/19] net: don't track pfmemalloc for zc registered mem
Date:   Tue, 21 Dec 2021 15:35:27 +0000
Message-Id: <598860fe8307c120f07b4383b98cc51bde9cd531.1640029579.git.asml.silence@gmail.com>
In-Reply-To: <cover.1640029579.git.asml.silence@gmail.com>
References: <cover.1640029579.git.asml.silence@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In case of zerocopy frags are filled with userspace allocated memory, we
shouldn't care about setting skb->pfmemalloc for them, and especially
when the buffers were somehow pre-registered (i.e. getting bvec from
io_uring). Remove the tracking from __zerocopy_sg_from_bvec().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 include/linux/skbuff.h | 28 +++++++++++++++++-----------
 net/core/datagram.c    |  7 +++++--
 2 files changed, 22 insertions(+), 13 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f6a6fd67e1ea..eef064fbf715 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2203,6 +2203,22 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb)
 	return skb_headlen(skb) + __skb_pagelen(skb);
 }
 
+static inline void __skb_fill_page_desc_noacc(struct skb_shared_info *shinfo,
+					      int i, struct page *page,
+					      int off, int size)
+{
+	skb_frag_t *frag = &shinfo->frags[i];
+
+	/*
+	 * Propagate page pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page but rely
+	 * on page_is_pfmemalloc doing the right thing(tm).
+	 */
+	frag->bv_page		  = page;
+	frag->bv_offset		  = off;
+	skb_frag_size_set(frag, size);
+}
+
 /**
  * __skb_fill_page_desc - initialise a paged fragment in an skb
  * @skb: buffer containing fragment to be initialised
@@ -2219,17 +2235,7 @@ static inline unsigned int skb_pagelen(const struct sk_buff *skb)
 static inline void __skb_fill_page_desc(struct sk_buff *skb, int i,
 					struct page *page, int off, int size)
 {
-	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
-
-	/*
-	 * Propagate page pfmemalloc to the skb if we can. The problem is
-	 * that not all callers have unique ownership of the page but rely
-	 * on page_is_pfmemalloc doing the right thing(tm).
-	 */
-	frag->bv_page		  = page;
-	frag->bv_offset		  = off;
-	skb_frag_size_set(frag, size);
-
+	__skb_fill_page_desc_noacc(skb_shinfo(skb), i, page, off, size);
 	page = compound_head(page);
 	if (page_is_pfmemalloc(page))
 		skb->pfmemalloc	= true;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 46526af40552..f8f147e14d1c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -619,7 +619,8 @@ EXPORT_SYMBOL(skb_copy_datagram_from_iter);
 static int __zerocopy_sg_from_bvec(struct sock *sk, struct sk_buff *skb,
 				   struct iov_iter *from, size_t length)
 {
-	int ret, frag = skb_shinfo(skb)->nr_frags;
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int ret, frag = shinfo->nr_frags;
 	struct bvec_iter bi;
 	struct bio_vec v;
 	ssize_t copied = 0;
@@ -638,11 +639,13 @@ static int __zerocopy_sg_from_bvec(struct sock *sk, struct sk_buff *skb,
 		v = mp_bvec_iter_bvec(from->bvec, bi);
 		copied += v.bv_len;
 		truesize += PAGE_ALIGN(v.bv_len + v.bv_offset);
-		skb_fill_page_desc(skb, frag++, v.bv_page, v.bv_offset, v.bv_len);
+		__skb_fill_page_desc_noacc(shinfo, frag++, v.bv_page,
+					   v.bv_offset, v.bv_len);
 		bvec_iter_advance_single(from->bvec, &bi, v.bv_len);
 	}
 	ret = 0;
 out:
+	shinfo->nr_frags = frag;
 	skb->data_len += copied;
 	skb->len += copied;
 	skb->truesize += truesize;
-- 
2.34.1