From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8A6CFC7EE25 for ; Wed, 7 Jun 2023 16:03:17 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id D1E108E0001; Wed, 7 Jun 2023 12:03:16 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id CCDED6B0075; Wed, 7 Jun 2023 12:03:16 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id B98198E0001; Wed, 7 Jun 2023 12:03:16 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0011.hostedemail.com [216.40.44.11]) by kanga.kvack.org (Postfix) with ESMTP id A9D436B0074 for ; Wed, 7 Jun 2023 12:03:16 -0400 (EDT) Received: from smtpin27.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay08.hostedemail.com (Postfix) with ESMTP id 7A3A714035F for ; Wed, 7 Jun 2023 16:03:16 +0000 (UTC) X-FDA: 80876421192.27.C9B00CC Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by imf12.hostedemail.com (Postfix) with ESMTP id A638440068 for ; Wed, 7 Jun 2023 16:01:59 +0000 (UTC) Authentication-Results: imf12.hostedemail.com; dkim=pass header.d=redhat.com header.s=mimecast20190719 header.b=YXk1uUbF; spf=pass (imf12.hostedemail.com: domain of dhowells@redhat.com designates 170.10.133.124 as permitted sender) smtp.mailfrom=dhowells@redhat.com; dmarc=pass (policy=none) header.from=redhat.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1686153720; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=8D0wC9fv92syi9P0txy4u3x9OYG9qdDRSwlIhKUuZis=; b=56rfin/ILw0MpdiOOFMpoOiPJn5xBQKjXv2e/gg5I72xvuCNlk6P9+ZbsFte/Kx8zOVyYz PligoEVufx0ke+PRXs6CwGHvG4cTKagD//NMqKcOE6qm2h0ykmfuSXRnCiwxt0nrO8//PG Wp79eQx3OsaA85dcjvFO9yLS9inob8M= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1686153720; a=rsa-sha256; cv=none; b=g1AGyh2ygDTUgoDZOEc3YP0citFHRoTUkhD7z6bWQ7c1fII0zC2C/EL+QqKhChl9ll4dqY WQ/WRRLEsdv3gsxRgNV6swB3Ab2H/Lc2thE1u91Ngu7Zj9B73KlKm0ZXWUpLKyx947GCxc StoYmsI73uI772OGICqNbOgSXDgStRo= ARC-Authentication-Results: i=1; imf12.hostedemail.com; dkim=pass header.d=redhat.com header.s=mimecast20190719 header.b=YXk1uUbF; spf=pass (imf12.hostedemail.com: domain of dhowells@redhat.com designates 170.10.133.124 as permitted sender) smtp.mailfrom=dhowells@redhat.com; dmarc=pass (policy=none) header.from=redhat.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1686153719; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=8D0wC9fv92syi9P0txy4u3x9OYG9qdDRSwlIhKUuZis=; b=YXk1uUbFNNTipIFy4A9RxSbETCZhstlXr/mVSKySKoGvXEAeq/ZQfg+KdG6C7lZrlr8F0r C+9Fv7PjeBbxYfDg5Qmj3I/96YiEiDX5LVIvR0u6LVRob5QIdQZGE8n4DPK1tABOjFeN41 QQGpOj8N+a5WkwrhT/aNUhFchHZza8o= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-382-5P-u-6H6Mdur6K0hMBQNtg-1; Wed, 07 Jun 2023 12:01:55 -0400 X-MC-Unique: 5P-u-6H6Mdur6K0hMBQNtg-1 Received: from smtp.corp.redhat.com (int-mx02.intmail.prod.int.rdu2.redhat.com [10.11.54.2]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 93E991C01E9B; Wed, 7 Jun 2023 16:01:51 +0000 (UTC) Received: from warthog.procyon.org.uk (unknown [10.42.28.182]) by smtp.corp.redhat.com (Postfix) with ESMTP id 775CD400E400; Wed, 7 Jun 2023 16:01:49 +0000 (UTC) Organization: Red Hat UK Ltd. Registered Address: Red Hat UK Ltd, Amberley Place, 107-111 Peascod Street, Windsor, Berkshire, SI4 1TE, United Kingdom. Registered in England and Wales under Company Registration No. 3798903 From: David Howells In-Reply-To: <20230607155420.11462-1-kuniyu@amazon.com> References: <20230607155420.11462-1-kuniyu@amazon.com> <2269950.1686152632@warthog.procyon.org.uk> To: Kuniyuki Iwashima Cc: dhowells@redhat.com, axboe@kernel.dk, borisp@nvidia.com, chuck.lever@oracle.com, davem@davemloft.net, dsahern@kernel.org, edumazet@google.com, john.fastabend@gmail.com, kuba@kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, netdev@vger.kernel.org, pabeni@redhat.com, torvalds@linux-foundation.org, willemdebruijn.kernel@gmail.com, willy@infradead.org Subject: Re: [PATCH net-next v5 07/14] ipv4, ipv6: Use splice_eof() to flush MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-ID: <2284050.1686153708.1@warthog.procyon.org.uk> Content-Transfer-Encoding: quoted-printable Date: Wed, 07 Jun 2023 17:01:48 +0100 Message-ID: <2284051.1686153708@warthog.procyon.org.uk> X-Scanned-By: MIMEDefang 3.1 on 10.11.54.2 X-Stat-Signature: f74y7m6c5ki8oejjtizxh3iecefy5wp6 X-Rspamd-Server: rspam10 X-Rspamd-Queue-Id: A638440068 X-Rspam-User: X-HE-Tag: 1686153719-906100 X-HE-Meta: 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 25/S2JEd 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 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: Kuniyuki Iwashima wrote: > > - In udpv6_splice_eof(), use udp_v6_push_pending_frames(). > = > You missed this change ;) No I didn't - I just forgot to save the buffer :-/ David --- commit a630e96e3b1073dc39fd370d60ccb3d5367ce9e6 Author: David Howells Date: Wed Jun 7 14:44:34 2023 +0100 ipv4, ipv6: Use splice_eof() to flush = Allow splice to undo the effects of MSG_MORE after prematurely ending = a splice/sendfile due to getting an EOF condition (->splice_read() retur= ned 0) after splice had called sendmsg() with MSG_MORE set when the user d= idn't set MSG_MORE. = For UDP, a pending packet will not be emitted if the socket is closed before it is flushed; with this change, it be flushed by ->splice_eof(= ). = For TCP, it's not clear that MSG_MORE is actually effective. = Suggested-by: Linus Torvalds Link: https://lore.kernel.org/r/CAHk-=3Dwh=3DV579PDYvkpnTobCLGczbgxpMg= GmmhqiTyE34Cpi5Gg@mail.gmail.com/ Signed-off-by: David Howells cc: Kuniyuki Iwashima cc: Eric Dumazet cc: Willem de Bruijn cc: David Ahern cc: "David S. Miller" cc: Jakub Kicinski cc: Paolo Abeni cc: Jens Axboe cc: Matthew Wilcox cc: netdev@vger.kernel.org Notes: ver #6) - In inet_splice_eof(), use prot after deref of sk->sk_prot. - In udpv6_splice_eof(), use udp_v6_push_pending_frames(). - In udpv6_splice_eof(), don't check for AF_INET. diff --git a/include/net/inet_common.h b/include/net/inet_common.h index 77f4b0ef5b92..a75333342c4e 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -35,6 +35,7 @@ void __inet_accept(struct socket *sock, struct socket *n= ewsock, struct sock *newsk); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); +void inet_splice_eof(struct socket *sock); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, diff --git a/include/net/tcp.h b/include/net/tcp.h index 68990a8f556a..49611af31bb7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -327,6 +327,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, s= ize_t size); int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied= , size_t size, struct ubuf_info *uarg); +void tcp_splice_eof(struct socket *sock); int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t s= ize, int flags); int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, diff --git a/include/net/udp.h b/include/net/udp.h index 5cad44318d71..4ed0b47c5582 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -278,6 +278,7 @@ int udp_get_port(struct sock *sk, unsigned short snum, int udp_err(struct sk_buff *, u32); int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); +void udp_splice_eof(struct socket *sock); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b5735b3551cf..fd233c4195ac 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -831,6 +831,21 @@ int inet_sendmsg(struct socket *sock, struct msghdr *= msg, size_t size) } EXPORT_SYMBOL(inet_sendmsg); = +void inet_splice_eof(struct socket *sock) +{ + const struct proto *prot; + struct sock *sk =3D sock->sk; + + if (unlikely(inet_send_prepare(sk))) + return; + + /* IPV6_ADDRFORM can change sk->sk_prot under us. */ + prot =3D READ_ONCE(sk->sk_prot); + if (prot->splice_eof) + prot->splice_eof(sock); +} +EXPORT_SYMBOL_GPL(inet_splice_eof); + ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1050,6 +1065,7 @@ const struct proto_ops inet_stream_ops =3D { #ifdef CONFIG_MMU .mmap =3D tcp_mmap, #endif + .splice_eof =3D inet_splice_eof, .sendpage =3D inet_sendpage, .splice_read =3D tcp_splice_read, .read_sock =3D tcp_read_sock, @@ -1084,6 +1100,7 @@ const struct proto_ops inet_dgram_ops =3D { .read_skb =3D udp_read_skb, .recvmsg =3D inet_recvmsg, .mmap =3D sock_no_mmap, + .splice_eof =3D inet_splice_eof, .sendpage =3D inet_sendpage, .set_peek_off =3D sk_set_peek_off, #ifdef CONFIG_COMPAT @@ -1115,6 +1132,7 @@ static const struct proto_ops inet_sockraw_ops =3D { .sendmsg =3D inet_sendmsg, .recvmsg =3D inet_recvmsg, .mmap =3D sock_no_mmap, + .splice_eof =3D inet_splice_eof, .sendpage =3D inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl =3D inet_compat_ioctl, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 53b7751b68e1..09f03221a6f1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1371,6 +1371,22 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg= , size_t size) } EXPORT_SYMBOL(tcp_sendmsg); = +void tcp_splice_eof(struct socket *sock) +{ + struct sock *sk =3D sock->sk; + struct tcp_sock *tp =3D tcp_sk(sk); + int mss_now, size_goal; + + if (!tcp_write_queue_tail(sk)) + return; + + lock_sock(sk); + mss_now =3D tcp_send_mss(sk, &size_goal, 0); + tcp_push(sk, 0, mss_now, tp->nonagle, size_goal); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(tcp_splice_eof); + /* * Handle reading urgent data. BSD has very simple semantics for * this, no blocking and very strange errors 8) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 53e9ce2f05bb..84a5d557dc1a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3116,6 +3116,7 @@ struct proto tcp_prot =3D { .keepalive =3D tcp_set_keepalive, .recvmsg =3D tcp_recvmsg, .sendmsg =3D tcp_sendmsg, + .splice_eof =3D tcp_splice_eof, .sendpage =3D tcp_sendpage, .backlog_rcv =3D tcp_v4_do_rcv, .release_cb =3D tcp_release_cb, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index fd3dae081f3a..df5e407286d7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1324,6 +1324,21 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg= , size_t len) } EXPORT_SYMBOL(udp_sendmsg); = +void udp_splice_eof(struct socket *sock) +{ + struct sock *sk =3D sock->sk; + struct udp_sock *up =3D udp_sk(sk); + + if (!up->pending || READ_ONCE(up->corkflag)) + return; + + lock_sock(sk); + if (up->pending && !READ_ONCE(up->corkflag)) + udp_push_pending_frames(sk); + release_sock(sk); +} +EXPORT_SYMBOL_GPL(udp_splice_eof); + int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -2918,6 +2933,7 @@ struct proto udp_prot =3D { .getsockopt =3D udp_getsockopt, .sendmsg =3D udp_sendmsg, .recvmsg =3D udp_recvmsg, + .splice_eof =3D udp_splice_eof, .sendpage =3D udp_sendpage, .release_cb =3D ip4_datagram_release_cb, .hash =3D udp_lib_hash, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2bbf13216a3d..564942bee067 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -695,6 +695,7 @@ const struct proto_ops inet6_stream_ops =3D { #ifdef CONFIG_MMU .mmap =3D tcp_mmap, #endif + .splice_eof =3D inet_splice_eof, .sendpage =3D inet_sendpage, .sendmsg_locked =3D tcp_sendmsg_locked, .sendpage_locked =3D tcp_sendpage_locked, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d657713d1c71..c17c8ff94b79 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2150,6 +2150,7 @@ struct proto tcpv6_prot =3D { .keepalive =3D tcp_set_keepalive, .recvmsg =3D tcp_recvmsg, .sendmsg =3D tcp_sendmsg, + .splice_eof =3D tcp_splice_eof, .sendpage =3D tcp_sendpage, .backlog_rcv =3D tcp_v6_do_rcv, .release_cb =3D tcp_release_cb, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e5a337e6b970..317b01c9bc39 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1653,6 +1653,20 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *m= sg, size_t len) } EXPORT_SYMBOL(udpv6_sendmsg); = +static void udpv6_splice_eof(struct socket *sock) +{ + struct sock *sk =3D sock->sk; + struct udp_sock *up =3D udp_sk(sk); + + if (!up->pending || READ_ONCE(up->corkflag)) + return; + + lock_sock(sk); + if (up->pending && !READ_ONCE(up->corkflag)) + udp_v6_push_pending_frames(sk); + release_sock(sk); +} + void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up =3D udp_sk(sk); @@ -1764,6 +1778,7 @@ struct proto udpv6_prot =3D { .getsockopt =3D udpv6_getsockopt, .sendmsg =3D udpv6_sendmsg, .recvmsg =3D udpv6_recvmsg, + .splice_eof =3D udpv6_splice_eof, .release_cb =3D ip6_datagram_release_cb, .hash =3D udp_lib_hash, .unhash =3D udp_lib_unhash,