From: Willem de Bruijn <[email protected]>
To: Pavel Begunkov <[email protected]>,
[email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
[email protected],
"David S . Miller" <[email protected]>,
Jakub Kicinski <[email protected]>,
David Ahern <[email protected]>,
Eric Dumazet <[email protected]>,
Willem de Bruijn <[email protected]>
Subject: Re: [PATCH net-next 3/5] net: batch zerocopy_fill_skb_from_iter accounting
Date: Fri, 28 Jun 2024 13:06:11 -0400 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <a916f99aa91bc9066411015835cadd5677a454fb.1719190216.git.asml.silence@gmail.com>
Pavel Begunkov wrote:
> Instead of accounting every page range against the socket separately, do
> it in batch based on the change in skb->truesize. It's also moved into
> __zerocopy_sg_from_iter(), so that zerocopy_fill_skb_from_iter() is
> simpler and responsible for setting frags but not the accounting.
>
> Signed-off-by: Pavel Begunkov <[email protected]>
Reviewed-by: Willem de Bruijn <[email protected]>
> ---
> net/core/datagram.c | 31 ++++++++++++++++++-------------
> 1 file changed, 18 insertions(+), 13 deletions(-)
>
> diff --git a/net/core/datagram.c b/net/core/datagram.c
> index 7f7d5da2e406..2b24d69b1e94 100644
> --- a/net/core/datagram.c
> +++ b/net/core/datagram.c
> @@ -610,7 +610,7 @@ int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset,
> }
> EXPORT_SYMBOL(skb_copy_datagram_from_iter);
>
> -static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
> +static int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
> struct iov_iter *from, size_t length)
> {
> int frag = skb_shinfo(skb)->nr_frags;
> @@ -621,7 +621,6 @@ static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
> int refs, order, n = 0;
> size_t start;
> ssize_t copied;
> - unsigned long truesize;
>
> if (frag == MAX_SKB_FRAGS)
> return -EMSGSIZE;
Does the existing code then incorrectly not unwind sk_wmem_queued_add
and sk_mem_charge if returning with error from the second or later
loop..
> @@ -633,17 +632,9 @@ static int zerocopy_fill_skb_from_iter(struct sock *sk, struct sk_buff *skb,
>
> length -= copied;
>
> - truesize = PAGE_ALIGN(copied + start);
> skb->data_len += copied;
> skb->len += copied;
> - skb->truesize += truesize;
> - if (sk && sk->sk_type == SOCK_STREAM) {
> - sk_wmem_queued_add(sk, truesize);
> - if (!skb_zcopy_pure(skb))
> - sk_mem_charge(sk, truesize);
> - } else {
> - refcount_add(truesize, &skb->sk->sk_wmem_alloc);
> - }
> + skb->truesize += PAGE_ALIGN(copied + start);
>
> head = compound_head(pages[n]);
> order = compound_order(head);
> @@ -691,10 +682,24 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
> struct sk_buff *skb, struct iov_iter *from,
> size_t length)
> {
> + unsigned long orig_size = skb->truesize;
> + unsigned long truesize;
> + int ret;
> +
> if (msg && msg->msg_ubuf && msg->sg_from_iter)
> return msg->sg_from_iter(sk, skb, from, length);
> - else
> - return zerocopy_fill_skb_from_iter(sk, skb, from, length);
> +
> + ret = zerocopy_fill_skb_from_iter(skb, from, length);
> + truesize = skb->truesize - orig_size;
> +
> + if (sk && sk->sk_type == SOCK_STREAM) {
> + sk_wmem_queued_add(sk, truesize);
> + if (!skb_zcopy_pure(skb))
> + sk_mem_charge(sk, truesize);
> + } else {
> + refcount_add(truesize, &skb->sk->sk_wmem_alloc);
> + }
> + return ret;
> }
> EXPORT_SYMBOL(__zerocopy_sg_from_iter);
>
> --
> 2.44.0
>
next prev parent reply other threads:[~2024-06-28 17:06 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-27 12:59 [PATCH net-next 0/5] zerocopy tx cleanups Pavel Begunkov
2024-06-27 12:59 ` [PATCH net-next 1/5] net: always try to set ubuf in skb_zerocopy_iter_stream Pavel Begunkov
2024-06-28 17:03 ` Willem de Bruijn
2024-06-27 12:59 ` [PATCH net-next 2/5] net: split __zerocopy_sg_from_iter() Pavel Begunkov
2024-06-28 17:03 ` Willem de Bruijn
2024-06-27 12:59 ` [PATCH net-next 3/5] net: batch zerocopy_fill_skb_from_iter accounting Pavel Begunkov
2024-06-28 17:06 ` Willem de Bruijn [this message]
2024-07-01 11:11 ` Pavel Begunkov
2024-07-01 18:27 ` Willem de Bruijn
2024-06-27 12:59 ` [PATCH net-next 4/5] io_uring/net: move charging socket out of zc io_uring Pavel Begunkov
2024-06-28 17:06 ` Willem de Bruijn
2024-06-27 12:59 ` [PATCH net-next 5/5] net: limit scope of a skb_zerocopy_iter_stream var Pavel Begunkov
2024-06-28 17:07 ` Willem de Bruijn
2024-06-28 17:09 ` [PATCH net-next 0/5] zerocopy tx cleanups Jens Axboe
2024-07-02 10:30 ` patchwork-bot+netdevbpf
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=667eed8350f89_2185b294e2@willemb.c.googlers.com.notmuch \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
/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