From: "D. Wythe" <alibuda@linux.alibaba.com>
To: David Howells <dhowells@redhat.com>,
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: 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,
Karsten Graul <kgraul@linux.ibm.com>,
Wenjia Zhang <wenjia@linux.ibm.com>,
Jan Karcher <jaka@linux.ibm.com>,
linux-s390@vger.kernel.org
Subject: Re: [PATCH v3 51/55] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES
Date: Fri, 28 Apr 2023 11:12:03 +0800 [thread overview]
Message-ID: <b9a15afe-c65d-5cf3-e6c7-eaec46cc99c1@linux.alibaba.com> (raw)
In-Reply-To: <4253f27c-2c5e-3033-14b3-6e31ee344e8b@linux.alibaba.com>
On 4/26/23 9:07 PM, D. Wythe wrote:
>
> Hi David,
>
> Fallback is one of the most important features of SMC, which
> automatically downgrades to TCP
> when SMC discovers that the peer does not support SMC. After fallback,
> SMC hopes the the ability can be
> consistent with that of TCP sock. If you delete the smc_sendpage, when
> fallback occurs, it means that the sock after the fallback
> loses the ability of sendpage( tcp_sendpage).
>
> Thanks
> D. Wythe
Sorry, I missed the key email context. The problem mentioned here does
not exist ...
>
> On 4/1/23 12:09 AM, David Howells wrote:
>> Drop the smc_sendpage() code as smc_sendmsg() just passes the call
>> down to
>> the underlying TCP socket and smc_tx_sendpage() is just a wrapper around
>> its sendmsg implementation.
>> Signed-off-by: David Howells <dhowells@redhat.com>
>> cc: Karsten Graul <kgraul@linux.ibm.com>
>> cc: Wenjia Zhang <wenjia@linux.ibm.com>
>> cc: Jan Karcher <jaka@linux.ibm.com>
>> cc: "David S. Miller" <davem@davemloft.net>
>> cc: Eric Dumazet <edumazet@google.com>
>> 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: linux-s390@vger.kernel.org
>> cc: netdev@vger.kernel.org
>> ---
>> net/smc/af_smc.c | 29 -----------------------------
>> net/smc/smc_stats.c | 2 +-
>> net/smc/smc_stats.h | 1 -
>> net/smc/smc_tx.c | 16 ----------------
>> net/smc/smc_tx.h | 2 --
>> 5 files changed, 1 insertion(+), 49 deletions(-)
>>
>> diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
>> index a4cccdfdc00a..d4113c8a7cda 100644
>> --- a/net/smc/af_smc.c
>> +++ b/net/smc/af_smc.c
>> @@ -3125,34 +3125,6 @@ static int smc_ioctl(struct socket *sock,
>> unsigned int cmd,
>> return put_user(answ, (int __user *)arg);
>> }
>> -static ssize_t smc_sendpage(struct socket *sock, struct page *page,
>> - int offset, size_t size, int flags)
>> -{
>> - struct sock *sk = sock->sk;
>> - struct smc_sock *smc;
>> - int rc = -EPIPE;
>> -
>> - smc = smc_sk(sk);
>> - lock_sock(sk);
>> - if (sk->sk_state != SMC_ACTIVE) {
>> - release_sock(sk);
>> - goto out;
>> - }
>> - release_sock(sk);
>> - if (smc->use_fallback) {
>> - rc = kernel_sendpage(smc->clcsock, page, offset,
>> - size, flags);
>> - } else {
>> - lock_sock(sk);
>> - rc = smc_tx_sendpage(smc, page, offset, size, flags);
>> - release_sock(sk);
>> - SMC_STAT_INC(smc, sendpage_cnt);
>> - }
>> -
>> -out:
>> - return rc;
>> -}
>> -
>> /* Map the affected portions of the rmbe into an spd, note the
>> number of bytes
>> * to splice in conn->splice_pending, and press 'go'. Delays
>> consumer cursor
>> * updates till whenever a respective page has been fully processed.
>> @@ -3224,7 +3196,6 @@ static const struct proto_ops smc_sock_ops = {
>> .sendmsg = smc_sendmsg,
>> .recvmsg = smc_recvmsg,
>> .mmap = sock_no_mmap,
>> - .sendpage = smc_sendpage,
>> .splice_read = smc_splice_read,
>> };
>> diff --git a/net/smc/smc_stats.c b/net/smc/smc_stats.c
>> index e80e34f7ac15..ca14c0f3a07d 100644
>> --- a/net/smc/smc_stats.c
>> +++ b/net/smc/smc_stats.c
>> @@ -227,7 +227,7 @@ static int smc_nl_fill_stats_tech_data(struct
>> sk_buff *skb,
>> SMC_NLA_STATS_PAD))
>> goto errattr;
>> if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_SENDPAGE_CNT,
>> - smc_tech->sendpage_cnt,
>> + 0,
>> SMC_NLA_STATS_PAD))
>> goto errattr;
>> if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_CORK_CNT,
>> diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
>> index 84b7ecd8c05c..b60fe1eb37ab 100644
>> --- a/net/smc/smc_stats.h
>> +++ b/net/smc/smc_stats.h
>> @@ -71,7 +71,6 @@ struct smc_stats_tech {
>> u64 clnt_v2_succ_cnt;
>> u64 srv_v1_succ_cnt;
>> u64 srv_v2_succ_cnt;
>> - u64 sendpage_cnt;
>> u64 urg_data_cnt;
>> u64 splice_cnt;
>> u64 cork_cnt;
>> diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
>> index f4b6a71ac488..d31ce8209fa2 100644
>> --- a/net/smc/smc_tx.c
>> +++ b/net/smc/smc_tx.c
>> @@ -298,22 +298,6 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct
>> msghdr *msg, size_t len)
>> return rc;
>> }
>> -int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int
>> offset,
>> - size_t size, int flags)
>> -{
>> - struct msghdr msg = {.msg_flags = flags};
>> - char *kaddr = kmap(page);
>> - struct kvec iov;
>> - int rc;
>> -
>> - iov.iov_base = kaddr + offset;
>> - iov.iov_len = size;
>> - iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iov, 1, size);
>> - rc = smc_tx_sendmsg(smc, &msg, size);
>> - kunmap(page);
>> - return rc;
>> -}
>> -
>> /***************************** sndbuf consumer
>> *******************************/
>> /* sndbuf consumer: actual data transfer of one target chunk with
>> ISM write */
>> diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
>> index 34b578498b1f..a59f370b8b43 100644
>> --- a/net/smc/smc_tx.h
>> +++ b/net/smc/smc_tx.h
>> @@ -31,8 +31,6 @@ void smc_tx_pending(struct smc_connection *conn);
>> void smc_tx_work(struct work_struct *work);
>> void smc_tx_init(struct smc_sock *smc);
>> int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t
>> len);
>> -int smc_tx_sendpage(struct smc_sock *smc, struct page *page, int
>> offset,
>> - size_t size, int flags);
>> int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
>> void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
>> void smc_tx_consumer_update(struct smc_connection *conn, bool force);
>
next prev parent reply other threads:[~2023-04-28 3:12 UTC|newest]
Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-31 16:08 [PATCH v3 00/55] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-31 16:08 ` [PATCH v3 01/55] netfs: Fix netfs_extract_iter_to_sg() for ITER_UBUF/IOVEC David Howells
2023-03-31 19:05 ` Jeff Layton
2023-03-31 16:08 ` [PATCH v3 02/55] iov_iter: Remove last_offset member David Howells
2023-03-31 19:16 ` Jeff Layton
2023-03-31 16:08 ` [PATCH v3 03/55] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-04-02 14:56 ` Willem de Bruijn
2023-03-31 16:08 ` [PATCH v3 04/55] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-03-31 16:08 ` [PATCH v3 05/55] mm: Make the page_frag_cache allocator use multipage folios David Howells
2023-03-31 16:08 ` [PATCH v3 06/55] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-04-05 15:04 ` Christoph Hellwig
2023-03-31 16:08 ` [PATCH v3 07/55] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 08/55] tcp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-31 16:08 ` [PATCH v3 09/55] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 10/55] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-31 16:08 ` [PATCH v3 11/55] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-31 16:08 ` [PATCH v3 12/55] tls: " David Howells
2023-03-31 16:08 ` [PATCH v3 13/55] siw: " David Howells
2023-03-31 16:08 ` [PATCH v3 14/55] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-31 16:08 ` [PATCH v3 15/55] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-04-02 15:10 ` Willem de Bruijn
2023-04-03 9:50 ` David Howells
2023-04-03 13:46 ` Willem de Bruijn
2023-04-03 22:04 ` David Howells
2023-04-04 16:58 ` Willem de Bruijn
2023-04-04 17:16 ` David Howells
2023-04-04 17:36 ` Willem de Bruijn
2023-04-03 11:18 ` David Howells
2023-03-31 16:08 ` [PATCH v3 16/55] ip, udp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-31 16:08 ` [PATCH v3 17/55] ip6, udp6: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 18/55] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 19/55] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 20/55] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-31 16:08 ` [PATCH v3 21/55] crypto: af_alg: Pin pages rather than ref'ing if appropriate David Howells
2023-03-31 16:08 ` [PATCH v3 22/55] crypto: af_alg: Use netfs_extract_iter_to_sg() to create scatterlists David Howells
2023-03-31 16:08 ` [PATCH v3 23/55] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-31 16:08 ` [PATCH v3 24/55] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 25/55] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 26/55] crypto: af_alg/hash: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 27/55] tls/device: " David Howells
2023-03-31 16:08 ` [PATCH v3 28/55] tls/device: Convert tls_device_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 29/55] tls/sw: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 30/55] tls/sw: Convert tls_sw_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 31/55] chelsio: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 32/55] chelsio: Convert chtls_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 33/55] kcm: Support MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 34/55] kcm: Convert kcm_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-31 16:08 ` [PATCH v3 35/55] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-31 16:08 ` [PATCH v3 36/55] splice, net: Reimplement splice_to_socket() to pass multiple bufs to sendmsg() David Howells
2023-03-31 16:08 ` [PATCH v3 37/55] Remove file->f_op->sendpage David Howells
2023-03-31 16:08 ` [PATCH v3 38/55] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-04-04 10:52 ` Bernard Metzler
2023-04-05 8:18 ` David Howells
2023-03-31 16:08 ` [PATCH v3 39/55] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-31 16:08 ` [PATCH v3 40/55] iscsi: " David Howells
2023-03-31 16:09 ` [PATCH v3 41/55] iscsi: Assume "sendpage" is okay in iscsi_tcp_segment_map() David Howells
2023-04-24 17:19 ` Fabio M. De Francesco
2023-04-25 8:30 ` David Howells
2023-04-25 13:13 ` Fabio M. De Francesco
2023-03-31 16:09 ` [PATCH v3 42/55] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-31 16:09 ` [PATCH v3 43/55] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-31 16:09 ` [PATCH v3 44/55] algif: Remove hash_sendpage*() David Howells
2023-03-31 16:09 ` [PATCH v3 45/55] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-04-10 12:20 ` Xiubo Li
2023-03-31 16:09 ` [PATCH v3 46/55] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-31 16:09 ` [PATCH v3 47/55] dlm: " David Howells
2023-03-31 16:09 ` [PATCH v3 48/55] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-31 16:09 ` [PATCH v3 49/55] nvme: " David Howells
2023-03-31 16:09 ` [PATCH v3 50/55] kcm: " David Howells
2023-03-31 16:09 ` [PATCH v3 51/55] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES David Howells
2023-04-26 13:07 ` D. Wythe
2023-04-28 3:12 ` D. Wythe [this message]
2023-03-31 16:09 ` [PATCH v3 52/55] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-31 16:09 ` [PATCH v3 53/55] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendmsg() David Howells
2023-03-31 16:09 ` [PATCH v3 54/55] drdb: Send an entire bio in a single sendmsg David Howells
2023-03-31 16:27 ` Trivial TLS server David Howells
2023-03-31 16:28 ` Trivial TLS client David Howells
2023-03-31 17:37 ` Test program for AF_KCM David Howells
2023-04-03 9:30 ` [PATCH v3 00/55] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) Christoph Hellwig
2023-04-03 9:34 ` Is AF_KCM functional? 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=b9a15afe-c65d-5cf3-e6c7-eaec46cc99c1@linux.alibaba.com \
--to=alibuda@linux.alibaba.com \
--cc=axboe@kernel.dk \
--cc=brauner@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=davem@davemloft.net \
--cc=dhowells@redhat.com \
--cc=edumazet@google.com \
--cc=hch@infradead.org \
--cc=jaka@linux.ibm.com \
--cc=jlayton@kernel.org \
--cc=kgraul@linux.ibm.com \
--cc=kuba@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--cc=wenjia@linux.ibm.com \
--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