[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5efdb532-2589-4327-9eb7-cfa0a40ed000@grimberg.me>
Date: Mon, 10 Jun 2024 13:05:13 +0300
From: Sagi Grimberg <sagi@...mberg.me>
To: Ofir Gal <ofir.gal@...umez.com>, davem@...emloft.net,
linux-block@...r.kernel.org, linux-nvme@...ts.infradead.org,
netdev@...r.kernel.org, ceph-devel@...r.kernel.org
Cc: dhowells@...hat.com, edumazet@...gle.com, kuba@...nel.org,
pabeni@...hat.com, kbusch@...nel.org, axboe@...nel.dk, hch@....de,
philipp.reisner@...bit.com, lars.ellenberg@...bit.com,
christoph.boehmwalder@...bit.com, idryomov@...il.com, xiubli@...hat.com
Subject: Re: [PATCH v3 1/4] net: introduce helper sendpages_ok()
On 06/06/2024 19:12, Ofir Gal wrote:
> Network drivers are using sendpage_ok() to check the first page of an
> iterator in order to disable MSG_SPLICE_PAGES. The iterator can
> represent list of contiguous pages.
>
> When MSG_SPLICE_PAGES is enabled skb_splice_from_iter() is being used,
> it requires all pages in the iterator to be sendable. Therefore it needs
> to check that each page is sendable.
>
> The patch introduces a helper sendpages_ok(), it returns true if all the
> contiguous pages are sendable.
>
> Drivers who want to send contiguous pages with MSG_SPLICE_PAGES may use
> this helper to check whether the page list is OK. If the helper does not
> return true, the driver should remove MSG_SPLICE_PAGES flag.
>
> Reviewed-by: Christoph Hellwig <hch@....de>
> Signed-off-by: Ofir Gal <ofir.gal@...umez.com>
> ---
> include/linux/net.h | 22 ++++++++++++++++++++++
> 1 file changed, 22 insertions(+)
>
> diff --git a/include/linux/net.h b/include/linux/net.h
> index 688320b79fcc..421a6b5b9ad1 100644
> --- a/include/linux/net.h
> +++ b/include/linux/net.h
> @@ -322,6 +322,28 @@ static inline bool sendpage_ok(struct page *page)
> return !PageSlab(page) && page_count(page) >= 1;
> }
>
> +/*
> + * Check sendpage_ok on contiguous pages.
> + */
> +static inline bool sendpages_ok(struct page *page, size_t len, size_t offset)
> +{
> + struct page *p;
> + size_t count;
> +
> + p = page + (offset >> PAGE_SHIFT);
> +
> + count = 0;
Assignment can move to the declaration.
> + while (count < len) {
> + if (!sendpage_ok(p))
> + return false;
> +
> + p++;
> + count += PAGE_SIZE;
> + }
> +
> + return true;
> +}
> +
> int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
> size_t num, size_t len);
> int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
Other than that,
Reviewed-by: Sagi Grimberg <sagi@...mberg.me>
Powered by blists - more mailing lists