From: Magnus Karlsson <magnus.karlsson@gmail.com>
To: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: bpf <bpf@vger.kernel.org>, "Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
"Jakub Kicinski" <kuba@kernel.org>,
"Björn Töpel" <bjorn@kernel.org>,
"Magnus Karlsson" <magnus.karlsson@intel.com>,
"Jonathan Lemon" <jonathan.lemon@gmail.com>,
"Alexei Starovoitov" <ast@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
"John Fastabend" <john.fastabend@gmail.com>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Martin KaFai Lau" <kafai@fb.com>,
"Song Liu" <songliubraving@fb.com>, "Yonghong Song" <yhs@fb.com>,
"KP Singh" <kpsingh@kernel.org>,
virtualization@lists.linux-foundation.org,
"Network Development" <netdev@vger.kernel.org>
Subject: Re: [PATCH bpf-next v3 3/3] xsk: build skb by page
Date: Thu, 21 Jan 2021 16:17:24 +0100 [thread overview]
Message-ID: <CAJ8uoz3eOG+Fn8EUe9_f9SxcAj+0vetg3Y=oxtR9nXCc30wA0A@mail.gmail.com> (raw)
In-Reply-To: <340f1dfa40416dd966a56e08507daba82d633088.1611236588.git.xuanzhuo@linux.alibaba.com>
On Thu, Jan 21, 2021 at 2:51 PM Xuan Zhuo <xuanzhuo@linux.alibaba.com> wrote:
>
> This patch is used to construct skb based on page to save memory copy
> overhead.
>
> This function is implemented based on IFF_TX_SKB_NO_LINEAR. Only the
> network card priv_flags supports IFF_TX_SKB_NO_LINEAR will use page to
> directly construct skb. If this feature is not supported, it is still
> necessary to copy data to construct skb.
>
> ---------------- Performance Testing ------------
>
> The test environment is Aliyun ECS server.
> Test cmd:
> ```
> xdpsock -i eth0 -t -S -s <msg size>
> ```
>
> Test result data:
>
> size 64 512 1024 1500
> copy 1916747 1775988 1600203 1440054
> page 1974058 1953655 1945463 1904478
> percent 3.0% 10.0% 21.58% 32.3%
>
> Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
> Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
> ---
> net/xdp/xsk.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 86 insertions(+), 18 deletions(-)
Applied, compiled and tried it out on my NIC that does not support
IFF_TX_SKB_NO_LINEAR and it works fine. Thank you Xuan for all your
efforts. Appreciated.
Now it would be nice if we could get some physical NIC drivers to
support this too. Some probably already do and can just set the bit,
while others need some modifications to support this.
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 4a83117..38af7f1 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -430,6 +430,87 @@ static void xsk_destruct_skb(struct sk_buff *skb)
> sock_wfree(skb);
> }
>
> +static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
> + struct xdp_desc *desc)
> +{
> + u32 len, offset, copy, copied;
> + struct sk_buff *skb;
> + struct page *page;
> + void *buffer;
> + int err, i;
> + u64 addr;
> +
> + skb = sock_alloc_send_skb(&xs->sk, 0, 1, &err);
> + if (unlikely(!skb))
> + return ERR_PTR(err);
> +
> + addr = desc->addr;
> + len = desc->len;
> +
> + buffer = xsk_buff_raw_get_data(xs->pool, addr);
> + offset = offset_in_page(buffer);
> + addr = buffer - xs->pool->addrs;
> +
> + for (copied = 0, i = 0; copied < len; i++) {
> + page = xs->pool->umem->pgs[addr >> PAGE_SHIFT];
> +
> + get_page(page);
> +
> + copy = min_t(u32, PAGE_SIZE - offset, len - copied);
> +
> + skb_fill_page_desc(skb, i, page, offset, copy);
> +
> + copied += copy;
> + addr += copy;
> + offset = 0;
> + }
> +
> + skb->len += len;
> + skb->data_len += len;
> + skb->truesize += len;
> +
> + refcount_add(len, &xs->sk.sk_wmem_alloc);
> +
> + return skb;
> +}
> +
> +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
> + struct xdp_desc *desc)
> +{
> + struct sk_buff *skb;
> +
> + if (xs->dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
> + skb = xsk_build_skb_zerocopy(xs, desc);
> + if (IS_ERR(skb))
> + return skb;
> + } else {
> + void *buffer;
> + u32 len;
> + int err;
> +
> + len = desc->len;
> + skb = sock_alloc_send_skb(&xs->sk, len, 1, &err);
> + if (unlikely(!skb))
> + return ERR_PTR(err);
> +
> + skb_put(skb, len);
> + buffer = xsk_buff_raw_get_data(xs->pool, desc->addr);
> + err = skb_store_bits(skb, 0, buffer, len);
> + if (unlikely(err)) {
> + kfree_skb(skb);
> + return ERR_PTR(err);
> + }
> + }
> +
> + skb->dev = xs->dev;
> + skb->priority = xs->sk.sk_priority;
> + skb->mark = xs->sk.sk_mark;
> + skb_shinfo(skb)->destructor_arg = (void *)(long)desc->addr;
> + skb->destructor = xsk_destruct_skb;
> +
> + return skb;
> +}
> +
> static int xsk_generic_xmit(struct sock *sk)
> {
> struct xdp_sock *xs = xdp_sk(sk);
> @@ -446,43 +527,30 @@ static int xsk_generic_xmit(struct sock *sk)
> goto out;
>
> while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
> - char *buffer;
> - u64 addr;
> - u32 len;
> -
> if (max_batch-- == 0) {
> err = -EAGAIN;
> goto out;
> }
>
> - len = desc.len;
> - skb = sock_alloc_send_skb(sk, len, 1, &err);
> - if (unlikely(!skb))
> + skb = xsk_build_skb(xs, &desc);
> + if (IS_ERR(skb)) {
> + err = PTR_ERR(skb);
> goto out;
> + }
>
> - skb_put(skb, len);
> - addr = desc.addr;
> - buffer = xsk_buff_raw_get_data(xs->pool, addr);
> - err = skb_store_bits(skb, 0, buffer, len);
> /* This is the backpressure mechanism for the Tx path.
> * Reserve space in the completion queue and only proceed
> * if there is space in it. This avoids having to implement
> * any buffering in the Tx path.
> */
> spin_lock_irqsave(&xs->pool->cq_lock, flags);
> - if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
> + if (xskq_prod_reserve(xs->pool->cq)) {
> spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
> kfree_skb(skb);
> goto out;
> }
> spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
>
> - skb->dev = xs->dev;
> - skb->priority = sk->sk_priority;
> - skb->mark = sk->sk_mark;
> - skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
> - skb->destructor = xsk_destruct_skb;
> -
> err = __dev_direct_xmit(skb, xs->queue_id);
> if (err == NETDEV_TX_BUSY) {
> /* Tell user-space to retry the send */
> --
> 1.8.3.1
>
next prev parent reply other threads:[~2021-01-21 15:19 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-21 13:47 [PATCH bpf-next v3 0/3] xsk: build skb by page Xuan Zhuo
2021-01-21 13:47 ` [PATCH bpf-next v3 1/3] net: add priv_flags for allow tx skb without linear Xuan Zhuo
2021-01-21 15:13 ` Alexander Lobakin
2021-01-21 13:47 ` [PATCH bpf-next v3 2/3] virtio-net: support IFF_TX_SKB_NO_LINEAR Xuan Zhuo
2021-01-21 13:47 ` [PATCH bpf-next v3 3/3] xsk: build skb by page Xuan Zhuo
2021-01-21 15:17 ` Magnus Karlsson [this message]
2021-01-21 15:41 ` Eric Dumazet
2021-01-22 11:47 ` Alexander Lobakin
2021-01-22 11:55 ` Alexander Lobakin
2021-01-22 12:08 ` Alexander Lobakin
2021-01-22 12:18 ` Magnus Karlsson
2021-01-22 12:39 ` Alexander Lobakin
2021-01-22 12:55 ` Magnus Karlsson
[not found] <1611329789.3222687-1-xuanzhuo@linux.alibaba.com>
2021-01-22 16:24 ` Alexander Lobakin
[not found] <1611329955.4913929-2-xuanzhuo@linux.alibaba.com>
2021-01-22 17:26 ` Alexander Lobakin
2021-01-22 18:37 ` Magnus Karlsson
2021-01-22 18:45 ` Alexander Lobakin
[not found] ` <1611541335.3012564-1-xuanzhuo@linux.alibaba.com>
2021-01-25 7:44 ` Magnus Karlsson
[not found] ` <1611578136.5043845-1-xuanzhuo@linux.alibaba.com>
2021-01-25 13:16 ` Magnus Karlsson
[not found] ` <1611587242.9653594-2-xuanzhuo@linux.alibaba.com>
2021-01-26 7:34 ` Magnus Karlsson
[not found] <1611544243.8363645-1-xuanzhuo@linux.alibaba.com>
2021-01-25 13:25 ` Alexander Lobakin
[not found] <1611586627.1035807-1-xuanzhuo@linux.alibaba.com>
2021-01-25 15:07 ` Alexander Lobakin
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='CAJ8uoz3eOG+Fn8EUe9_f9SxcAj+0vetg3Y=oxtR9nXCc30wA0A@mail.gmail.com' \
--to=magnus.karlsson@gmail.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bjorn@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=hawk@kernel.org \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=jonathan.lemon@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=magnus.karlsson@intel.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=xuanzhuo@linux.alibaba.com \
--cc=yhs@fb.com \
/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).