Content-Type: multipart/mixed; boundary="===============4570967661311319979==" MIME-Version: 1.0 From: Mat Martineau To: mptcp at lists.01.org Subject: [MPTCP] Re: [PATCH net-next 1/2] tcp: factor out tcp_build_frag() Date: Thu, 15 Oct 2020 17:24:43 -0700 Message-ID: In-Reply-To: 3f6f46cb7133df6f4ef2ffcdc05d9805d46ca939.1602693911.git.pabeni@redhat.com X-Status: X-Keywords: X-UID: 6324 --===============4570967661311319979== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On Wed, 14 Oct 2020, Paolo Abeni wrote: > Will be needed by the next patch, as MPTCP needs to handle > directly the error/memory-allocation-needed path. > > No functional changes intented. Minor: "intended" Worth mentioning the change to tcp_remove_empty_skb() visibility too? > > Signed-off-by: Paolo Abeni > --- > RFC -> v1: > - rename do_tcp_sendfrag() -> tcp_buildfrag() > - changed return type and argument list to > simplify the caller > --- > include/net/tcp.h | 3 ++ > net/ipv4/tcp.c | 119 ++++++++++++++++++++++++++-------------------- > 2 files changed, 70 insertions(+), 52 deletions(-) > > diff --git a/include/net/tcp.h b/include/net/tcp.h > index 3601dea931a6..dbde4ec3cfa3 100644 > --- a/include/net/tcp.h > +++ b/include/net/tcp.h > @@ -322,6 +322,7 @@ void tcp_shutdown(struct sock *sk, int how); > int tcp_v4_early_demux(struct sk_buff *skb); > int tcp_v4_rcv(struct sk_buff *skb); > > +void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb); > int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); > int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); > int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); > @@ -329,6 +330,8 @@ int tcp_sendpage(struct sock *sk, struct page *page, = int offset, size_t size, > int flags); > int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, > size_t size, int flags); > +struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, > + struct page *page, int offset, size_t *size); > ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, > size_t size, int flags); > int tcp_send_mss(struct sock *sk, int *size_goal, int flags); > diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c > index bae4284bf542..259dca2bd3dd 100644 > --- a/net/ipv4/tcp.c > +++ b/net/ipv4/tcp.c > @@ -952,7 +952,7 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int= flags) > * importantly be able to generate EPOLLOUT for Edge Trigger epoll() > * users. > */ > -static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) > +void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) > { > if (skb && !skb->len) { > tcp_unlink_write_queue(skb, sk); > @@ -962,6 +962,68 @@ static void tcp_remove_empty_skb(struct sock *sk, st= ruct sk_buff *skb) > } > } > > +struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags, > + struct page *page, int offset, size_t *size) > +{ > + struct sk_buff *skb =3D tcp_write_queue_tail(sk); > + struct tcp_sock *tp =3D tcp_sk(sk); > + bool can_coalesce; > + int copy, i; > + > + if (!skb || (copy =3D size_goal - skb->len) <=3D 0 || > + !tcp_skb_can_collapse_to(skb)) { > +new_segment: > + if (!sk_stream_memory_free(sk)) > + return NULL; > + > + skb =3D sk_stream_alloc_skb(sk, 0, sk->sk_allocation, > + tcp_rtx_and_write_queues_empty(sk)); > + if (!skb) > + return NULL; > + > +#ifdef CONFIG_TLS_DEVICE > + skb->decrypted =3D !!(flags & MSG_SENDPAGE_DECRYPTED); > +#endif > + skb_entail(sk, skb); > + copy =3D size_goal; > + } > + > + if (copy > *size) > + copy =3D *size; > + > + i =3D skb_shinfo(skb)->nr_frags; > + can_coalesce =3D skb_can_coalesce(skb, i, page, offset); > + if (!can_coalesce && i >=3D sysctl_max_skb_frags) { > + tcp_mark_push(tp, skb); > + goto new_segment; > + } > + if (!sk_wmem_schedule(sk, copy)) > + return NULL; > + > + if (can_coalesce) { > + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); > + } else { > + get_page(page); > + skb_fill_page_desc(skb, i, page, offset, copy); > + } > + > + if (!(flags & MSG_NO_SHARED_FRAGS)) > + skb_shinfo(skb)->tx_flags |=3D SKBTX_SHARED_FRAG; > + > + skb->len +=3D copy; > + skb->data_len +=3D copy; > + skb->truesize +=3D copy; > + sk_wmem_queued_add(sk, copy); > + sk_mem_charge(sk, copy); > + skb->ip_summed =3D CHECKSUM_PARTIAL; > + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); > + TCP_SKB_CB(skb)->end_seq +=3D copy; > + tcp_skb_pcount_set(skb, 0); > + > + *size =3D copy; > + return skb; > +} > + > ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, > size_t size, int flags) > { > @@ -997,60 +1059,13 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct p= age *page, int offset, > goto out_err; > > while (size > 0) { > - struct sk_buff *skb =3D tcp_write_queue_tail(sk); > - int copy, i; > - bool can_coalesce; > - > - if (!skb || (copy =3D size_goal - skb->len) <=3D 0 || > - !tcp_skb_can_collapse_to(skb)) { > -new_segment: > - if (!sk_stream_memory_free(sk)) > - goto wait_for_space; > - > - skb =3D sk_stream_alloc_skb(sk, 0, sk->sk_allocation, > - tcp_rtx_and_write_queues_empty(sk)); > - if (!skb) > - goto wait_for_space; > - > -#ifdef CONFIG_TLS_DEVICE > - skb->decrypted =3D !!(flags & MSG_SENDPAGE_DECRYPTED); > -#endif > - skb_entail(sk, skb); > - copy =3D size_goal; > - } > + struct sk_buff *skb; > + size_t copy =3D size; This initialization is the only thing that needed a deeper look, but = following how it's used in tcp_build_frag() the behavior does look the = same. This patch (with commit message comments above) and #2 look good to post = to netdev for feedback. Thanks, Mat > > - if (copy > size) > - copy =3D size; > - > - i =3D skb_shinfo(skb)->nr_frags; > - can_coalesce =3D skb_can_coalesce(skb, i, page, offset); > - if (!can_coalesce && i >=3D sysctl_max_skb_frags) { > - tcp_mark_push(tp, skb); > - goto new_segment; > - } > - if (!sk_wmem_schedule(sk, copy)) > + skb =3D tcp_build_frag(sk, size_goal, flags, page, offset, ©); > + if (!skb) > goto wait_for_space; > > - if (can_coalesce) { > - skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); > - } else { > - get_page(page); > - skb_fill_page_desc(skb, i, page, offset, copy); > - } > - > - if (!(flags & MSG_NO_SHARED_FRAGS)) > - skb_shinfo(skb)->tx_flags |=3D SKBTX_SHARED_FRAG; > - > - skb->len +=3D copy; > - skb->data_len +=3D copy; > - skb->truesize +=3D copy; > - sk_wmem_queued_add(sk, copy); > - sk_mem_charge(sk, copy); > - skb->ip_summed =3D CHECKSUM_PARTIAL; > - WRITE_ONCE(tp->write_seq, tp->write_seq + copy); > - TCP_SKB_CB(skb)->end_seq +=3D copy; > - tcp_skb_pcount_set(skb, 0); > - > if (!copied) > TCP_SKB_CB(skb)->tcp_flags &=3D ~TCPHDR_PSH; > > -- = > 2.26.2 > _______________________________________________ > mptcp mailing list -- mptcp(a)lists.01.org > To unsubscribe send an email to mptcp-leave(a)lists.01.org > -- Mat Martineau Intel --===============4570967661311319979==--