| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Tue, 16 Feb 2021 14:15:32 +0000
From: Alexander Lobakin <alobakin@...me>
To: Magnus Karlsson <magnus.karlsson@...il.com>
Cc: Alexander Lobakin <alobakin@...me>,
Björn Töpel <bjorn@...nel.org>,
"Michael S. Tsirkin" <mst@...hat.com>,
Jason Wang <jasowang@...hat.com>,
"David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>,
Jonathan Lemon <jonathan.lemon@...il.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
KP Singh <kpsingh@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
Eric Dumazet <eric.dumazet@...il.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
Dust Li <dust.li@...ux.alibaba.com>,
virtualization@...ts.linux-foundation.org,
Network Development <netdev@...r.kernel.org>,
open list <linux-kernel@...r.kernel.org>,
bpf <bpf@...r.kernel.org>
Subject: Re: [PATCH v4 bpf-next 6/6] xsk: build skb by page (aka generic zerocopy xmit)
From: Magnus Karlsson <magnus.karlsson@...il.com>
Date: Tue, 16 Feb 2021 15:08:26 +0100
> On Tue, Feb 16, 2021 at 12:44 PM Alexander Lobakin <alobakin@...me> wrote:
> >
> > From: Xuan Zhuo <xuanzhuo@...ux.alibaba.com>
> >
> > 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@...ux.alibaba.com>
> > Reviewed-by: Dust Li <dust.li@...ux.alibaba.com>
> > [ alobakin:
> > - expand subject to make it clearer;
> > - improve skb->truesize calculation;
> > - reserve some headroom in skb for drivers;
> > - tailroom is not needed as skb is non-linear ]
> > Signed-off-by: Alexander Lobakin <alobakin@...me>
>
> Thank you Alexander!
>
> Acked-by: Magnus Karlsson <magnus.karlsson@...el.com>
Thanks!
I have one more generic zerocopy to offer (inspired by this series)
that wouldn't require IFF_TX_SKB_NO_LINEAR, only a capability to xmit
S/G packets that almost every NIC has. I'll publish an RFC once this
and your upcoming changes get merged.
> > ---
> > net/xdp/xsk.c | 119 ++++++++++++++++++++++++++++++++++++++++----------
> > 1 file changed, 95 insertions(+), 24 deletions(-)
> >
> > diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> > index 143979ea4165..ff7bd06e1241 100644
> > --- a/net/xdp/xsk.c
> > +++ b/net/xdp/xsk.c
> > @@ -445,6 +445,96 @@ 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)
> > +{
> > + struct xsk_buff_pool *pool = xs->pool;
> > + u32 hr, len, offset, copy, copied;
> > + struct sk_buff *skb;
> > + struct page *page;
> > + void *buffer;
> > + int err, i;
> > + u64 addr;
> > +
> > + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> > +
> > + skb = sock_alloc_send_skb(&xs->sk, hr, 1, &err);
> > + if (unlikely(!skb))
> > + return ERR_PTR(err);
> > +
> > + skb_reserve(skb, hr);
> > +
> > + addr = desc->addr;
> > + len = desc->len;
> > +
> > + buffer = xsk_buff_raw_get_data(pool, addr);
> > + offset = offset_in_page(buffer);
> > + addr = buffer - pool->addrs;
> > +
> > + for (copied = 0, i = 0; copied < len; i++) {
> > + page = 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 += pool->unaligned ? len : pool->chunk_size;
> > +
> > + refcount_add(skb->truesize, &xs->sk.sk_wmem_alloc);
> > +
> > + return skb;
> > +}
> > +
> > +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
> > + struct xdp_desc *desc)
> > +{
> > + struct net_device *dev = xs->dev;
> > + struct sk_buff *skb;
> > +
> > + if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) {
> > + skb = xsk_build_skb_zerocopy(xs, desc);
> > + if (IS_ERR(skb))
> > + return skb;
> > + } else {
> > + u32 hr, tr, len;
> > + void *buffer;
> > + int err;
> > +
> > + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom));
> > + tr = dev->needed_tailroom;
> > + len = desc->len;
> > +
> > + skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err);
> > + if (unlikely(!skb))
> > + return ERR_PTR(err);
> > +
> > + skb_reserve(skb, hr);
> > + 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 = 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);
> > @@ -454,56 +544,37 @@ static int xsk_generic_xmit(struct sock *sk)
> > struct sk_buff *skb;
> > unsigned long flags;
> > int err = 0;
> > - u32 hr, tr;
> >
> > mutex_lock(&xs->mutex);
> >
> > if (xs->queue_id >= xs->dev->real_num_tx_queues)
> > goto out;
> >
> > - hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(xs->dev->needed_headroom));
> > - tr = xs->dev->needed_tailroom;
> > -
> > 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, hr + len + tr, 1, &err);
> > - if (unlikely(!skb))
> > + skb = xsk_build_skb(xs, &desc);
> > + if (IS_ERR(skb)) {
> > + err = PTR_ERR(skb);
> > goto out;
> > + }
> >
> > - skb_reserve(skb, hr);
> > - 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 */
> > --
> > 2.30.1
Al
Powered by blists - more mailing lists