From: Prashant Bhole <prashantbhole.linux@gmail.com>
To: "David S . Miller" <davem@davemloft.net>,
"Michael S . Tsirkin" <mst@redhat.com>,
Alexei Starovoitov <ast@kernel.org>,
Daniel Borkmann <daniel@iogearbox.net>,
Jesper Dangaard Brouer <hawk@kernel.org>
Cc: David Ahern <dahern@digitalocean.com>,
Jason Wang <jasowang@redhat.com>, David Ahern <dsahern@gmail.com>,
Jakub Kicinski <jakub.kicinski@netronome.com>,
John Fastabend <john.fastabend@gmail.com>,
Toshiaki Makita <toshiaki.makita1@gmail.com>,
Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
Yonghong Song <yhs@fb.com>, Andrii Nakryiko <andriin@fb.com>,
netdev@vger.kernel.org,
Prashant Bhole <prashantbhole.linux@gmail.com>
Subject: [RFC net-next 01/14] net: add tx path XDP support
Date: Wed, 18 Dec 2019 17:10:37 +0900 [thread overview]
Message-ID: <20191218081050.10170-2-prashantbhole.linux@gmail.com> (raw)
In-Reply-To: <20191218081050.10170-1-prashantbhole.linux@gmail.com>
From: David Ahern <dahern@digitalocean.com>
Add a way to run XDP program in tx path. Drivers those want to support
tx path XDP needs to handle XDP_SETUP_PROG_TX and XDP_QUERY_PROG_TX
cases in their ndo_bpf handler.
Signed-off-by: David Ahern <dahern@digitalocean.com>
Co-developed-by: Prashant Bhole <prashantbhole.linux@gmail.com>
Signed-off-by: Prashant Bhole <prashantbhole.linux@gmail.com>
---
include/linux/netdevice.h | 4 +-
include/uapi/linux/if_link.h | 1 +
net/core/dev.c | 31 +++++++---
net/core/rtnetlink.c | 112 ++++++++++++++++++++++++++++++++++-
4 files changed, 137 insertions(+), 11 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 30745068fb39..7b5256d374d2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -864,8 +864,10 @@ enum bpf_netdev_command {
*/
XDP_SETUP_PROG,
XDP_SETUP_PROG_HW,
+ XDP_SETUP_PROG_TX,
XDP_QUERY_PROG,
XDP_QUERY_PROG_HW,
+ XDP_QUERY_PROG_TX,
/* BPF program for offload callbacks, invoked at program load time. */
BPF_OFFLOAD_MAP_ALLOC,
BPF_OFFLOAD_MAP_FREE,
@@ -3724,7 +3726,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, u32 flags);
+ int fd, u32 flags, bool tx);
u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
enum bpf_netdev_command cmd);
int xdp_umem_query(struct net_device *dev, u16 queue_id);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 1d69f637c5d6..be97c9787140 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -170,6 +170,7 @@ enum {
IFLA_PROP_LIST,
IFLA_ALT_IFNAME, /* Alternative ifname */
IFLA_PERM_ADDRESS,
+ IFLA_XDP_TX,
__IFLA_MAX
};
diff --git a/net/core/dev.c b/net/core/dev.c
index 2c277b8aba38..a46db72759cf 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8540,7 +8540,7 @@ u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
struct netlink_ext_ack *extack, u32 flags,
- struct bpf_prog *prog)
+ struct bpf_prog *prog, bool tx)
{
struct netdev_bpf xdp;
@@ -8548,7 +8548,8 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
if (flags & XDP_FLAGS_HW_MODE)
xdp.command = XDP_SETUP_PROG_HW;
else
- xdp.command = XDP_SETUP_PROG;
+ xdp.command = tx ? XDP_SETUP_PROG_TX : XDP_SETUP_PROG;
+
xdp.extack = extack;
xdp.flags = flags;
xdp.prog = prog;
@@ -8562,7 +8563,8 @@ static void dev_xdp_uninstall(struct net_device *dev)
bpf_op_t ndo_bpf;
/* Remove generic XDP */
- WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL));
+ WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL,
+ false));
/* Remove from the driver */
ndo_bpf = dev->netdev_ops->ndo_bpf;
@@ -8574,14 +8576,21 @@ static void dev_xdp_uninstall(struct net_device *dev)
WARN_ON(ndo_bpf(dev, &xdp));
if (xdp.prog_id)
WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
- NULL));
+ NULL, false));
/* Remove HW offload */
memset(&xdp, 0, sizeof(xdp));
xdp.command = XDP_QUERY_PROG_HW;
if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
- NULL));
+ NULL, false));
+
+ /* Remove HW offload */
+ memset(&xdp, 0, sizeof(xdp));
+ xdp.command = XDP_QUERY_PROG_TX;
+ if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
+ WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+ NULL, true));
}
/**
@@ -8594,7 +8603,7 @@ static void dev_xdp_uninstall(struct net_device *dev)
* Set or clear a bpf program for a device
*/
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
- int fd, u32 flags)
+ int fd, u32 flags, bool tx)
{
const struct net_device_ops *ops = dev->netdev_ops;
enum bpf_netdev_command query;
@@ -8606,7 +8615,10 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
ASSERT_RTNL();
offload = flags & XDP_FLAGS_HW_MODE;
- query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
+ if (tx)
+ query = XDP_QUERY_PROG_TX;
+ else
+ query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
bpf_op = bpf_chk = ops->ndo_bpf;
if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) {
@@ -8621,7 +8633,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
if (fd >= 0) {
u32 prog_id;
- if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
+ if (!offload && !tx &&
+ __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) {
NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time");
return -EEXIST;
}
@@ -8653,7 +8666,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
return 0;
}
- err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
+ err = dev_xdp_install(dev, bpf_op, extack, flags, prog, tx);
if (err < 0 && prog)
bpf_prog_put(prog);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 20bc406f3871..9dc4b2547f62 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1395,6 +1395,36 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
return 0;
}
+static u32 rtnl_xdp_tx_prog_drv(struct net_device *dev)
+{
+ return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
+ XDP_QUERY_PROG_TX);
+}
+
+static int rtnl_xdp_tx_report_one(struct sk_buff *skb, struct net_device *dev,
+ u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr,
+ u32 (*get_prog_id)(struct net_device *dev))
+{
+ u32 curr_id;
+ int err;
+
+ curr_id = get_prog_id(dev);
+ if (!curr_id)
+ return 0;
+
+ *prog_id = curr_id;
+ err = nla_put_u32(skb, attr, curr_id);
+ if (err)
+ return err;
+
+ if (*mode != XDP_ATTACHED_NONE)
+ *mode = XDP_ATTACHED_MULTI;
+ else
+ *mode = tgt_mode;
+
+ return 0;
+}
+
static u32 rtnl_xdp_prog_skb(struct net_device *dev)
{
const struct bpf_prog *generic_xdp_prog;
@@ -1486,6 +1516,41 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
return err;
}
+static int rtnl_xdp_tx_fill(struct sk_buff *skb, struct net_device *dev)
+{
+ u8 mode = XDP_ATTACHED_NONE;
+ struct nlattr *xdp;
+ u32 prog_id = 0;
+ int err;
+
+ xdp = nla_nest_start_noflag(skb, IFLA_XDP_TX);
+ if (!xdp)
+ return -EMSGSIZE;
+
+ err = rtnl_xdp_tx_report_one(skb, dev, &prog_id, &mode,
+ XDP_ATTACHED_DRV, IFLA_XDP_DRV_PROG_ID,
+ rtnl_xdp_tx_prog_drv);
+ if (err)
+ goto err_cancel;
+
+ err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
+ if (err)
+ goto err_cancel;
+
+ if (prog_id && mode != XDP_ATTACHED_MULTI) {
+ err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
+ if (err)
+ goto err_cancel;
+ }
+
+ nla_nest_end(skb, xdp);
+ return 0;
+
+err_cancel:
+ nla_nest_cancel(skb, xdp);
+ return err;
+}
+
static u32 rtnl_get_event(unsigned long event)
{
u32 rtnl_event_type = IFLA_EVENT_NONE;
@@ -1743,6 +1808,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
if (rtnl_xdp_fill(skb, dev))
goto nla_put_failure;
+ if (rtnl_xdp_tx_fill(skb, dev))
+ goto nla_put_failure;
+
if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) {
if (rtnl_link_fill(skb, dev) < 0)
goto nla_put_failure;
@@ -1827,6 +1895,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_ALT_IFNAME] = { .type = NLA_STRING,
.len = ALTIFNAMSIZ - 1 },
[IFLA_PERM_ADDRESS] = { .type = NLA_REJECT },
+ [IFLA_XDP_TX] = { .type = NLA_NESTED },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2801,7 +2870,48 @@ static int do_setlink(const struct sk_buff *skb,
if (xdp[IFLA_XDP_FD]) {
err = dev_change_xdp_fd(dev, extack,
nla_get_s32(xdp[IFLA_XDP_FD]),
- xdp_flags);
+ xdp_flags, false);
+ if (err)
+ goto errout;
+ status |= DO_SETLINK_NOTIFY;
+ }
+ }
+
+ if (tb[IFLA_XDP_TX]) {
+ struct nlattr *xdp[IFLA_XDP_MAX + 1];
+ u32 xdp_flags = 0;
+
+ err = nla_parse_nested_deprecated(xdp, IFLA_XDP_MAX,
+ tb[IFLA_XDP_TX],
+ ifla_xdp_policy, NULL);
+ if (err < 0)
+ goto errout;
+
+ if (xdp[IFLA_XDP_ATTACHED] || xdp[IFLA_XDP_PROG_ID]) {
+ err = -EINVAL;
+ goto errout;
+ }
+
+ if (xdp[IFLA_XDP_FLAGS]) {
+ xdp_flags = nla_get_u32(xdp[IFLA_XDP_FLAGS]);
+ if (xdp_flags & XDP_FLAGS_HW_MODE) {
+ err = -EINVAL;
+ goto errout;
+ }
+ if (xdp_flags & ~XDP_FLAGS_MASK) {
+ err = -EINVAL;
+ goto errout;
+ }
+ if (hweight32(xdp_flags & XDP_FLAGS_MODES) > 1) {
+ err = -EINVAL;
+ goto errout;
+ }
+ }
+
+ if (xdp[IFLA_XDP_FD]) {
+ err = dev_change_xdp_fd(dev, extack,
+ nla_get_s32(xdp[IFLA_XDP_FD]),
+ xdp_flags, true);
if (err)
goto errout;
status |= DO_SETLINK_NOTIFY;
--
2.21.0
next prev parent reply other threads:[~2019-12-18 8:12 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-18 8:10 [RFC net-next 00/14] XDP in tx path Prashant Bhole
2019-12-18 8:10 ` Prashant Bhole [this message]
2019-12-18 8:10 ` [RFC net-next 02/14] tools: sync kernel uapi/linux/if_link.h header Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 03/14] libbpf: API for tx path XDP support Prashant Bhole
2019-12-18 18:20 ` Alexei Starovoitov
2019-12-18 8:10 ` [RFC net-next 04/14] samples/bpf: xdp1, add XDP tx support Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 05/14] net: core: rename netif_receive_generic_xdp() to do_generic_xdp_core() Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 06/14] net: core: export do_xdp_generic_core() Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 07/14] tuntap: check tun_msg_ctl type at necessary places Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 08/14] vhost_net: user tap recvmsg api to access ptr ring Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 09/14] tuntap: remove usage of ptr ring in vhost_net Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 10/14] tun: set tx path XDP program Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 11/14] tun: run XDP program in tx path Prashant Bhole
2019-12-18 10:07 ` Jesper Dangaard Brouer
2019-12-18 11:48 ` Toke Høiland-Jørgensen
2019-12-18 16:33 ` David Ahern
2019-12-19 2:44 ` Jason Wang
2019-12-18 18:19 ` Alexei Starovoitov
2019-12-19 2:34 ` Prashant Bhole
2019-12-19 10:15 ` Toke Høiland-Jørgensen
2019-12-20 0:07 ` Prashant Bhole
2019-12-20 3:24 ` Jason Wang
2019-12-20 4:46 ` Prashant Bhole
2019-12-20 7:36 ` Jason Wang
2019-12-20 10:11 ` Toke Høiland-Jørgensen
2019-12-20 16:11 ` David Ahern
2019-12-20 22:17 ` Prashant Bhole
2019-12-23 6:05 ` Jason Wang
2019-12-23 8:09 ` Prashant Bhole
2019-12-23 8:34 ` Jason Wang
2019-12-23 11:06 ` Prashant Bhole
2019-12-18 16:29 ` David Ahern
2019-12-19 1:47 ` Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 12/14] tun: add a way to inject tx path packet into Rx path Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 13/14] tun: handle XDP_TX action of tx path XDP program Prashant Bhole
2019-12-18 8:10 ` [RFC net-next 14/14] tun: run xdp prog when tun is read from file interface Prashant Bhole
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=20191218081050.10170-2-prashantbhole.linux@gmail.com \
--to=prashantbhole.linux@gmail.com \
--cc=andriin@fb.com \
--cc=ast@kernel.org \
--cc=dahern@digitalocean.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@gmail.com \
--cc=hawk@kernel.org \
--cc=jakub.kicinski@netronome.com \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=kafai@fb.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.