From: David Ahern <dsahern@kernel.org>
To: netdev@vger.kernel.org
Cc: davem@davemloft.net, kuba@kernel.org,
prashantbhole.linux@gmail.com, jasowang@redhat.com,
brouer@redhat.com, toke@redhat.com, toshiaki.makita1@gmail.com,
daniel@iogearbox.net, john.fastabend@gmail.com, ast@kernel.org,
kafai@fb.com, songliubraving@fb.com, yhs@fb.com, andriin@fb.com,
dsahern@gmail.com, David Ahern <dahern@digitalocean.com>
Subject: [PATCH bpf-next 10/16] net: Support xdp in the Tx path for packets as an skb
Date: Mon, 20 Apr 2020 14:00:49 -0600 [thread overview]
Message-ID: <20200420200055.49033-11-dsahern@kernel.org> (raw)
In-Reply-To: <20200420200055.49033-1-dsahern@kernel.org>
From: David Ahern <dahern@digitalocean.com>
Add support to run Tx path program on packets about to hit the
ndo_start_xmit function for a device. Only XDP_DROP and XDP_PASS
are supported now. Conceptually, XDP_REDIRECT for this path can
work the same as it does for the Rx path, but that support is left
for a follow on series.
Signed-off-by: David Ahern <dahern@digitalocean.com>
---
include/linux/netdevice.h | 11 +++++++++
net/core/dev.c | 52 ++++++++++++++++++++++++++++++++++++++-
2 files changed, 62 insertions(+), 1 deletion(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0c89996a6bec..39e1b42c042f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3714,6 +3714,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)
void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
int do_xdp_generic_rx(struct bpf_prog *xdp_prog, struct sk_buff *skb);
+u32 do_xdp_egress_skb(struct net_device *dev, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
@@ -4534,6 +4535,16 @@ static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
struct sk_buff *skb, struct net_device *dev,
bool more)
{
+ if (static_branch_unlikely(&xdp_egress_needed_key)) {
+ u32 act;
+
+ rcu_read_lock();
+ act = do_xdp_egress_skb(dev, skb);
+ rcu_read_unlock();
+ if (act == XDP_DROP)
+ return NET_XMIT_DROP;
+ }
+
__this_cpu_write(softnet_data.xmit.more, more);
return ops->ndo_start_xmit(skb, dev);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 6718048c3448..d47e88beeeca 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4620,7 +4620,6 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
}
static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
-DEFINE_STATIC_KEY_FALSE(xdp_egress_needed_key);
int do_xdp_generic_rx(struct bpf_prog *xdp_prog, struct sk_buff *skb)
{
@@ -4671,6 +4670,57 @@ int do_xdp_generic_rx(struct bpf_prog *xdp_prog, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(do_xdp_generic_rx);
+DEFINE_STATIC_KEY_FALSE(xdp_egress_needed_key);
+EXPORT_SYMBOL_GPL(xdp_egress_needed_key);
+
+static u32 handle_xdp_egress_act(u32 act, struct net_device *dev,
+ struct bpf_prog *xdp_prog)
+{
+ switch (act) {
+ case XDP_DROP:
+ /* fall through */
+ case XDP_PASS:
+ break;
+ case XDP_TX:
+ /* fall through */
+ case XDP_REDIRECT:
+ /* fall through */
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(dev, xdp_prog, act);
+ act = XDP_DROP;
+ break;
+ }
+
+ return act;
+}
+
+u32 do_xdp_egress_skb(struct net_device *dev, struct sk_buff *skb)
+{
+ struct bpf_prog *xdp_prog;
+ u32 act = XDP_PASS;
+
+ xdp_prog = rcu_dereference(dev->xdp_egress_prog);
+ if (xdp_prog) {
+ struct xdp_txq_info txq = { .dev = dev };
+ struct xdp_buff xdp;
+
+ xdp.txq = &txq;
+ act = do_xdp_generic_core(skb, &xdp, xdp_prog);
+ act = handle_xdp_egress_act(act, dev, xdp_prog);
+ if (act == XDP_DROP) {
+ atomic_long_inc(&dev->tx_dropped);
+ skb_tx_error(skb);
+ kfree_skb(skb);
+ }
+ }
+
+ return act;
+}
+EXPORT_SYMBOL_GPL(do_xdp_egress_skb);
+
static int netif_rx_internal(struct sk_buff *skb)
{
int ret;
--
2.21.1 (Apple Git-122.3)
next prev parent reply other threads:[~2020-04-20 20:01 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-04-20 20:00 [PATCH bpf-next 00/16] net: Add support for XDP in egress path David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 01/16] net: Refactor convert_to_xdp_frame David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 02/16] net: Move handling of IFLA_XDP attribute out of do_setlink David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 03/16] net: Add XDP setup and query commands for Tx programs David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 04/16] net: Add BPF_XDP_EGRESS as a bpf_attach_type David Ahern
2020-04-21 10:14 ` Toke Høiland-Jørgensen
2020-04-21 12:50 ` David Ahern
2020-04-21 13:25 ` Toke Høiland-Jørgensen
2020-04-21 13:49 ` David Ahern
2020-04-22 11:21 ` Toke Høiland-Jørgensen
2020-04-22 14:51 ` David Ahern
2020-04-22 15:27 ` Toke Høiland-Jørgensen
2020-04-22 15:33 ` David Ahern
2020-04-22 15:51 ` Toke Høiland-Jørgensen
2020-04-22 15:56 ` David Ahern
2020-04-23 15:23 ` Toke Høiland-Jørgensen
2020-04-23 0:39 ` Alexei Starovoitov
2020-04-23 16:40 ` Toke Høiland-Jørgensen
2020-04-23 16:52 ` Alexei Starovoitov
2020-04-23 17:05 ` Toke Høiland-Jørgensen
2020-04-23 22:44 ` Alexei Starovoitov
2020-04-23 23:49 ` Toke Høiland-Jørgensen
2020-04-24 0:53 ` Alexei Starovoitov
2020-04-24 0:58 ` David Ahern
2020-04-24 8:55 ` Toke Høiland-Jørgensen
2020-04-20 20:00 ` [PATCH bpf-next 05/16] xdp: Add xdp_txq_info to xdp_buff David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 06/16] net: Add IFLA_XDP_EGRESS for XDP programs in the egress path David Ahern
2020-04-21 10:17 ` Toke Høiland-Jørgensen
2020-04-21 12:59 ` David Ahern
2020-04-21 13:27 ` Toke Høiland-Jørgensen
2020-04-20 20:00 ` [PATCH bpf-next 07/16] net: Rename do_xdp_generic to do_xdp_generic_rx David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 08/16] net: rename netif_receive_generic_xdp to do_generic_xdp_core David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 09/16] net: set XDP egress program on netdevice David Ahern
2020-04-20 20:00 ` David Ahern [this message]
2020-04-20 20:00 ` [PATCH bpf-next 11/16] net: Support xdp in the Tx path for xdp_frames David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 12/16] libbpf: Add egress XDP support David Ahern
2020-04-21 10:20 ` Toke Høiland-Jørgensen
2020-04-21 13:03 ` David Ahern
2020-04-21 13:28 ` Toke Høiland-Jørgensen
2020-04-23 1:19 ` Andrii Nakryiko
2020-04-23 1:33 ` David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 13/16] bpftool: Add support for XDP egress David Ahern
2020-04-23 10:43 ` Quentin Monnet
2020-04-23 18:50 ` David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 14/16] selftest: Add test for xdp_egress David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 15/16] selftest: Add xdp_egress attach tests David Ahern
2020-04-20 20:00 ` [PATCH bpf-next 16/16] samples/bpf: add XDP egress support to xdp1 David Ahern
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=20200420200055.49033-11-dsahern@kernel.org \
--to=dsahern@kernel.org \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=brouer@redhat.com \
--cc=dahern@digitalocean.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=prashantbhole.linux@gmail.com \
--cc=songliubraving@fb.com \
--cc=toke@redhat.com \
--cc=toshiaki.makita1@gmail.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).