From: Stefano Brivio <sbrivio@redhat.com>
To: Laurent Vivier <lvivier@redhat.com>
Cc: passt-dev@passt.top
Subject: Re: [PATCH v7 31/31] packet: use buf to store iovec array
Date: Fri, 18 Jul 2025 20:45:36 +0200 [thread overview]
Message-ID: <20250718204536.33ba94c0@elisabeth> (raw)
In-Reply-To: <20250623110635.1478625-32-lvivier@redhat.com>
On Mon, 23 Jun 2025 13:06:35 +0200
Laurent Vivier <lvivier@redhat.com> wrote:
> In vhost-user mode, where `pool->buf` doesn't store packet data directly,
> this patch repurposes it to hold the `struct iovec` array describing
> a scattered packet. This enables pools to manage true scatter-gather
> descriptors, with iovecs pointing to guest memory.
>
> `p->pkt[idx].iov_base` is now an index into this `pool->buf` iovec array,
> and `p->pkt[idx].iov_len` is the count of iovecs. `packet_add_do` uses
> `iov_tail_slice` to store these iovec descriptors from an input iov_tail
> into `pool->buf`. `packet_data_do` reconstructs the iov_tail for a
> packet by pointing to this stored array of iovecs.
>
> Signed-off-by: Laurent Vivier <lvivier@redhat.com>
> ---
> packet.c | 164 +++++++++++++++++++++++++++++++++++++++++++++++++------
> 1 file changed, 148 insertions(+), 16 deletions(-)
>
> diff --git a/packet.c b/packet.c
> index fd3b6db57c30..8dbe00af12c6 100644
> --- a/packet.c
> +++ b/packet.c
> @@ -84,6 +84,122 @@ bool pool_full(const struct pool *p)
> return p->count >= p->size;
> }
>
> +/**
> + * packet_iov_max_cnt() - Return the maximum number of iovec entries we can
> + * store
> + * @p: Pointer to packet pool
> + *
> + * Return: the maximum number of iovec entries we can store in the memory of
> + * the pool buffer
> + */
> +static size_t packet_iov_max_cnt(const struct pool *p)
> +{
> + return p->buf_size / sizeof(struct iovec);
> +}
> +
> +/**
> + * packet_iov_idx() - For a given packet index, return the iovec index and
> + * the number of iovec entry of the packet
> + * @p: Pointer to packet pool
> + * @idx: Index of packet descriptor in pool
> + * @iov_cnt: Pointer to store the number of the iovec entry of the packet
> + * @func: For tracing: name of calling function
> + * @line: For tracing: caller line of function call
> + *
> + * Return: the iovec index for the given packet index, @iov_cnt is set
> + * to the number of the iovec entry of the packet
> + */
> +static int packet_iov_idx(const struct pool *p, size_t idx, size_t *iov_cnt,
> + const char *func, int line)
> +{
> + size_t iov_idx, max = packet_iov_max_cnt(p);
> +
> + iov_idx = (size_t)p->pkt[idx].iov_base;
> + *iov_cnt = p->pkt[idx].iov_len;
> +
> + ASSERT_WITH_MSG(iov_idx + *iov_cnt <= max,
> + "Corrupt iov entry: (%zu, %zu), max: %zu, %s:%i",
> + iov_idx, *iov_cnt, max, func, line);
> +
> + return iov_idx;
> +}
> +
> +/**
> + * packet_iov_next_idx() - Give the the next available iovec index
I'm taking the liberty to fix this comment while applying ("Get the next
available iovec index").
--
Stefano
next prev parent reply other threads:[~2025-07-18 18:45 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-23 11:06 [PATCH v7 00/31] Introduce discontiguous frames management Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 01/31] style: Fix 'Return' comment style Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 02/31] arp: Don't mix incoming and outgoing buffers Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 03/31] iov: Introduce iov_tail_clone() and iov_tail_drop() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 04/31] iov: Update IOV_REMOVE_HEADER() and IOV_PEEK_HEADER() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 05/31] tap: Use iov_tail with tap_add_packet() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 06/31] packet: Use iov_tail with packet_add() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 07/31] packet: Add packet_data() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 08/31] arp: Convert to iov_tail Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 09/31] ndp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 10/31] icmp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 11/31] udp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 12/31] tcp: Convert tcp_tap_handler() to use iov_tail Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 13/31] tcp: Convert tcp_data_from_tap() " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 14/31] dhcpv6: move offset initialization out of dhcpv6_opt() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 15/31] dhcpv6: Extract sending of NotOnLink status Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 16/31] dhcpv6: Convert to iov_tail Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 17/31] dhcpv6: Use iov_tail in dhcpv6_opt() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 18/31] dhcp: Convert to iov_tail Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 19/31] ip: Use iov_tail in ipv6_l4hdr() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 20/31] tap: Convert tap4_handler() to iov_tail Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 21/31] tap: Convert tap6_handler() " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 22/31] packet: rename packet_data() to packet_get() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 23/31] arp: use iov_tail rather than pool Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 24/31] dhcp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 25/31] dhcpv6: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 26/31] icmp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 27/31] ndp: " Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 28/31] packet: remove PACKET_POOL() and PACKET_POOL_P() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 29/31] packet: remove unused parameter from PACKET_POOL_DECL() Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 30/31] packet: add memory regions information into pool Laurent Vivier
2025-06-23 11:06 ` [PATCH v7 31/31] packet: use buf to store iovec array Laurent Vivier
2025-07-18 18:45 ` Stefano Brivio [this message]
2025-07-18 18:45 ` [PATCH v7 00/31] Introduce discontiguous frames management Stefano Brivio
2025-07-24 13:01 ` Laurent Vivier
2025-07-25 11:45 ` Laurent Vivier
2025-07-25 14:18 ` Stefano Brivio
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=20250718204536.33ba94c0@elisabeth \
--to=sbrivio@redhat.com \
--cc=lvivier@redhat.com \
--cc=passt-dev@passt.top \
/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.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
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 IMAP folder(s).