From: David Howells <dhowells@redhat.com>
To: Matthew Wilcox <willy@infradead.org>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: David Howells <dhowells@redhat.com>,
Al Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>,
Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
Christian Brauner <brauner@kernel.org>,
Chuck Lever III <chuck.lever@oracle.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [RFC PATCH v2 10/48] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES
Date: Wed, 29 Mar 2023 15:13:16 +0100 [thread overview]
Message-ID: <20230329141354.516864-11-dhowells@redhat.com> (raw)
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>
Convert do_tcp_sendpages() to use sendmsg() with MSG_SPLICE_PAGES rather
than directly splicing in the pages itself. do_tcp_sendpages() can then be
inlined in subsequent patches into its callers.
This allows ->sendpage() to be replaced by something that can handle
multiple multipage folios in a single transaction.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Eric Dumazet <edumazet@google.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
---
net/ipv4/tcp.c | 161 +++----------------------------------------------
1 file changed, 10 insertions(+), 151 deletions(-)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6ef0518eb706..a1c5a6d9419c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -971,163 +971,22 @@ static int tcp_wmem_schedule(struct sock *sk, int copy)
return min(copy, sk->sk_forward_alloc);
}
-static 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 = tcp_write_queue_tail(sk);
- struct tcp_sock *tp = tcp_sk(sk);
- bool can_coalesce;
- int copy, i;
-
- if (!skb || (copy = size_goal - skb->len) <= 0 ||
- !tcp_skb_can_collapse_to(skb)) {
-new_segment:
- if (!sk_stream_memory_free(sk))
- return NULL;
-
- skb = tcp_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 = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
- tcp_skb_entail(sk, skb);
- copy = size_goal;
- }
-
- if (copy > *size)
- copy = *size;
-
- i = skb_shinfo(skb)->nr_frags;
- can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= READ_ONCE(sysctl_max_skb_frags)) {
- tcp_mark_push(tp, skb);
- goto new_segment;
- }
- if (tcp_downgrade_zcopy_pure(sk, skb))
- return NULL;
-
- copy = tcp_wmem_schedule(sk, copy);
- if (!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_noacc(skb, i, page, offset, copy);
- }
-
- if (!(flags & MSG_NO_SHARED_FRAGS))
- skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
-
- skb->len += copy;
- skb->data_len += copy;
- skb->truesize += copy;
- sk_wmem_queued_add(sk, copy);
- sk_mem_charge(sk, copy);
- WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
- TCP_SKB_CB(skb)->end_seq += copy;
- tcp_skb_pcount_set(skb, 0);
-
- *size = copy;
- return skb;
-}
-
ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
size_t size, int flags)
{
- struct tcp_sock *tp = tcp_sk(sk);
- int mss_now, size_goal;
- int err;
- ssize_t copied;
- long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
-
- if (IS_ENABLED(CONFIG_DEBUG_VM) &&
- WARN_ONCE(!sendpage_ok(page),
- "page must not be a Slab one and have page_count > 0"))
- return -EINVAL;
-
- /* Wait for a connection to finish. One exception is TCP Fast Open
- * (passive side) where data is allowed to be sent before a connection
- * is fully established.
- */
- if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) &&
- !tcp_passive_fastopen(sk)) {
- err = sk_stream_wait_connect(sk, &timeo);
- if (err != 0)
- goto out_err;
- }
-
- sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
-
- mss_now = tcp_send_mss(sk, &size_goal, flags);
- copied = 0;
-
- err = -EPIPE;
- if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
- goto out_err;
-
- while (size > 0) {
- struct sk_buff *skb;
- size_t copy = size;
-
- skb = tcp_build_frag(sk, size_goal, flags, page, offset, ©);
- if (!skb)
- goto wait_for_space;
-
- if (!copied)
- TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
-
- copied += copy;
- offset += copy;
- size -= copy;
- if (!size)
- goto out;
-
- if (skb->len < size_goal || (flags & MSG_OOB))
- continue;
-
- if (forced_push(tp)) {
- tcp_mark_push(tp, skb);
- __tcp_push_pending_frames(sk, mss_now, TCP_NAGLE_PUSH);
- } else if (skb == tcp_send_head(sk))
- tcp_push_one(sk, mss_now);
- continue;
-
-wait_for_space:
- set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
- tcp_push(sk, flags & ~MSG_MORE, mss_now,
- TCP_NAGLE_PUSH, size_goal);
-
- err = sk_stream_wait_memory(sk, &timeo);
- if (err != 0)
- goto do_error;
+ struct bio_vec bvec;
+ struct msghdr msg = {
+ .msg_flags = flags,
+ .msg_kflags = MSG_SPLICE_PAGES,
+ };
- mss_now = tcp_send_mss(sk, &size_goal, flags);
- }
+ bvec_set_page(&bvec, page, size, offset);
+ iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size);
-out:
- if (copied) {
- tcp_tx_timestamp(sk, sk->sk_tsflags);
- if (!(flags & MSG_SENDPAGE_NOTLAST))
- tcp_push(sk, flags, mss_now, tp->nonagle, size_goal);
- }
- return copied;
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ msg.msg_flags |= MSG_MORE;
-do_error:
- tcp_remove_empty_skb(sk);
- if (copied)
- goto out;
-out_err:
- /* make sure we wake any epoll edge trigger waiter */
- if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) {
- sk->sk_write_space(sk);
- tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
- }
- return sk_stream_error(sk, flags, err);
+ return tcp_sendmsg_locked(sk, &msg, size);
}
EXPORT_SYMBOL_GPL(do_tcp_sendpages);
next prev parent reply other threads:[~2023-03-29 14:17 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-29 14:13 [RFC PATCH v2 00/48] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 01/48] netfs: Fix netfs_extract_iter_to_sg() for ITER_UBUF/IOVEC David Howells
2023-03-29 14:13 ` [RFC PATCH v2 02/48] iov_iter: Remove last_offset member David Howells
2023-03-29 14:13 ` [RFC PATCH v2 03/48] iov_iter: Add an iterator-of-iterators David Howells
2023-03-29 14:13 ` [RFC PATCH v2 04/48] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-30 14:28 ` Willem de Bruijn
2023-03-30 15:07 ` David Howells
2023-03-30 17:51 ` Willem de Bruijn
2023-03-29 14:13 ` [RFC PATCH v2 05/48] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-03-29 14:13 ` [RFC PATCH v2 06/48] mm: Make the page_frag_cache allocator use multipage folios David Howells
2023-03-29 14:13 ` [RFC PATCH v2 07/48] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-03-29 14:13 ` [RFC PATCH v2 08/48] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 09/48] tcp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` David Howells [this message]
2023-03-29 14:13 ` [RFC PATCH v2 11/48] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 12/48] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 13/48] tls: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 14/48] siw: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 15/48] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 16/48] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-03-30 14:20 ` Willem de Bruijn
2023-03-30 14:39 ` David Howells
2023-03-30 17:46 ` Willem de Bruijn
2023-03-30 15:11 ` David Howells
2023-03-30 17:55 ` Willem de Bruijn
2023-03-30 19:49 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 17/48] ip, udp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 18/48] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 19/48] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 20/48] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 21/48] crypto: af_alg: Pin pages rather than ref'ing if appropriate David Howells
2023-03-29 14:13 ` [RFC PATCH v2 22/48] crypto: af_alg: Use netfs_extract_iter_to_sg() to create scatterlists David Howells
2023-03-29 14:13 ` [RFC PATCH v2 23/48] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 24/48] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 25/48] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 26/48] crypto: af_alg/hash: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 27/48] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 28/48] splice: Reimplement splice_to_socket() to pass multiple bufs to sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 29/48] Remove file->f_op->sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 30/48] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-03-29 15:18 ` Bernard Metzler
2023-03-29 15:32 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 31/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 32/48] iscsi: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 33/48] iscsi: Assume "sendpage" is okay in iscsi_tcp_segment_map() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 34/48] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 35/48] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 36/48] algif: Remove hash_sendpage*() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 37/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-30 1:45 ` Xiubo Li
2023-03-30 6:48 ` David Howells
2023-03-31 13:05 ` Xiubo Li
2023-04-03 3:27 ` Xiubo Li
2023-04-03 8:32 ` David Howells
2023-04-10 0:38 ` Xiubo Li
2023-03-29 14:13 ` [RFC PATCH v2 38/48] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 39/48] dlm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 40/48] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 15:28 ` Chuck Lever III
2023-03-29 19:58 ` David Howells
2023-03-30 9:29 ` David Howells
2023-03-30 9:41 ` David Howells
2023-03-30 13:16 ` Chuck Lever III
2023-03-30 13:01 ` David Howells
2023-03-30 13:16 ` David Howells
2023-03-30 13:27 ` Chuck Lever III
2023-03-30 14:26 ` David Howells
2023-03-30 16:36 ` Chuck Lever III
2023-04-14 14:41 ` Daire Byrne
2023-03-29 14:13 ` [RFC PATCH v2 41/48] sunrpc: Rely on TCP sendmsg + MSG_SPLICE_PAGES to copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 42/48] nvme: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 43/48] kcm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 44/48] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 45/48] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 46/48] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 47/48] drdb: Send an entire bio in a single sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 48/48] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:23 ` Hannes Reinecke
2023-03-29 14:39 ` David Howells
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=20230329141354.516864-11-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hch@infradead.org \
--cc=jlayton@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).