* [Intel-wired-lan] [PATCH v4 bpf-next 0/8] xdp: introduce xdp-feature support
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Introduce the capability to export the XDP features supported by the NIC.
Introduce a XDP compliance test tool (xdp_features) to check the features
exported by the NIC match the real features supported by the driver.
Allow XDP_REDIRECT of non-linear XDP frames into a devmap.
Export XDP features for each XDP capable driver.
Extend libbpf netlink implementation in order to support netlink_generic
protocol.
Introduce a simple generic netlink family for netdev data.
Changes since v3:
- add IPv6 support to XDP compliance test tool
- rely on network_helpers in XDP compliance test tool
- cosmetics changes
Changes since v2:
- rebase on top of bpf-next
- fix compilation error
Changes since v1:
- add Documentation to netdev.yaml
- use flags instead of enum as type for netdev.yaml definitions
- squash XDP_PASS, XDP_DROP, XDP_TX and XDP_ABORTED into XDP_BASIC since they
are supported by all drivers.
- add notifier event to xdp_features_set_redirect_target() and
xdp_features_clear_redirect_target()
- add selftest for xdp-features support in bpf_xdp_detach()
- add IPv6 preliminary support to XDP compliance test tool
Changes since RFCv2:
- do not assume fixed layout for genl kernel messages
- fix warnings in netdev_nl_dev_fill
- fix capabilities for nfp driver
- add supported_sg parameter to xdp_features_set_redirect_target and drop
__xdp_features_set_redirect_target routine
Changes since RFCv1:
- Introduce netdev-genl implementation and get rid of rtnl one.
- Introduce netlink_generic support in libbpf netlink implementation
- Rename XDP_FEATURE_* in NETDEV_XDP_ACT_*
- Rename XDP_FEATURE_REDIRECT_TARGET in NETDEV_XDP_ACT_NDO_XMIT
- Rename XDP_FEATURE_FRAG_RX in NETDEV_XDP_ACT_RX_SG
- Rename XDP_FEATURE_FRAG_TARFET in NETDEV_XDP_ACT_NDO_XMIT
- Get rid of XDP_LOCK feature.
- Move xdp_feature field in a netdevice struct hole in the 4th cacheline.
Jakub Kicinski (1):
netdev-genl: create a simple family for netdev stuff
Lorenzo Bianconi (5):
libbpf: add the capability to specify netlink proto in
libbpf_netlink_send_recv
libbpf: add API to get XDP/XSK supported features
bpf: devmap: check XDP features in __xdp_enqueue routine
selftests/bpf: add test for bpf_xdp_query xdp-features support
selftests/bpf: introduce XDP compliance test tool
Marek Majtyka (2):
drivers: net: turn on XDP features
xsk: add usage of XDP features flags
Documentation/netlink/specs/netdev.yaml | 100 +++
drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 +
.../net/ethernet/aquantia/atlantic/aq_nic.c | 5 +
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +
.../net/ethernet/cavium/thunder/nicvf_main.c | 2 +
.../net/ethernet/freescale/dpaa/dpaa_eth.c | 4 +
.../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 +
.../net/ethernet/freescale/enetc/enetc_pf.c | 3 +
.../ethernet/fungible/funeth/funeth_main.c | 6 +
drivers/net/ethernet/intel/i40e/i40e_main.c | 10 +-
drivers/net/ethernet/intel/ice/ice_main.c | 5 +
drivers/net/ethernet/intel/igb/igb_main.c | 9 +-
drivers/net/ethernet/intel/igc/igc_main.c | 3 +
drivers/net/ethernet/intel/igc/igc_xdp.c | 5 +
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +
.../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 +
drivers/net/ethernet/marvell/mvneta.c | 3 +
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 +
.../ethernet/marvell/octeontx2/nic/otx2_pf.c | 8 +-
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 6 +
.../net/ethernet/mellanox/mlx4/en_netdev.c | 2 +
.../net/ethernet/mellanox/mlx5/core/en_main.c | 11 +
drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +
.../ethernet/netronome/nfp/nfp_net_common.c | 5 +
drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +
drivers/net/ethernet/sfc/efx.c | 4 +
drivers/net/ethernet/sfc/siena/efx.c | 4 +
drivers/net/ethernet/socionext/netsec.c | 3 +
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +
drivers/net/ethernet/ti/cpsw.c | 4 +
drivers/net/ethernet/ti/cpsw_new.c | 4 +
drivers/net/hyperv/netvsc_drv.c | 2 +
drivers/net/netdevsim/netdev.c | 1 +
drivers/net/tun.c | 5 +
drivers/net/veth.c | 4 +
drivers/net/virtio_net.c | 4 +
drivers/net/xen-netfront.c | 2 +
include/linux/netdevice.h | 3 +
include/net/xdp.h | 15 +
include/uapi/linux/netdev.h | 59 ++
kernel/bpf/devmap.c | 16 +-
net/core/Makefile | 3 +-
net/core/dev.c | 1 +
net/core/filter.c | 13 +-
net/core/netdev-genl-gen.c | 48 ++
net/core/netdev-genl-gen.h | 23 +
net/core/netdev-genl.c | 179 +++++
net/core/xdp.c | 18 +
net/xdp/xsk_buff_pool.c | 7 +-
tools/include/uapi/linux/netdev.h | 59 ++
tools/lib/bpf/libbpf.h | 3 +-
tools/lib/bpf/netlink.c | 118 ++-
tools/lib/bpf/nlattr.h | 12 +
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 11 +-
.../bpf/prog_tests/xdp_do_redirect.c | 27 +-
.../selftests/bpf/prog_tests/xdp_info.c | 8 +
.../selftests/bpf/progs/xdp_features.c | 275 +++++++
.../selftests/bpf/test_xdp_features.sh | 100 +++
tools/testing/selftests/bpf/xdp_features.c | 731 ++++++++++++++++++
tools/testing/selftests/bpf/xdp_features.h | 33 +
62 files changed, 1985 insertions(+), 33 deletions(-)
create mode 100644 Documentation/netlink/specs/netdev.yaml
create mode 100644 include/uapi/linux/netdev.h
create mode 100644 net/core/netdev-genl-gen.c
create mode 100644 net/core/netdev-genl-gen.h
create mode 100644 net/core/netdev-genl.c
create mode 100644 tools/include/uapi/linux/netdev.h
create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh
create mode 100644 tools/testing/selftests/bpf/xdp_features.c
create mode 100644 tools/testing/selftests/bpf/xdp_features.h
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* [PATCH v4 bpf-next 1/8] netdev-genl: create a simple family for netdev stuff
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
From: Jakub Kicinski <kuba@kernel.org>
Add a Netlink spec-compatible family for netdevs.
This is a very simple implementation without much
thought going into it.
It allows us to reap all the benefits of Netlink specs,
one can use the generic client to issue the commands:
$ ./cli.py --spec netdev.yaml --dump dev_get
[{'ifindex': 1, 'xdp-features': set()},
{'ifindex': 2, 'xdp-features': {'basic', 'ndo-xmit', 'redirect'}},
{'ifindex': 3, 'xdp-features': {'rx-sg'}}]
the generic python library does not have flags-by-name
support, yet, but we also don't have to carry strings
in the messages, as user space can get the names from
the spec.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
Documentation/netlink/specs/netdev.yaml | 100 +++++++++++++
include/linux/netdevice.h | 3 +
include/net/xdp.h | 3 +
include/uapi/linux/netdev.h | 59 ++++++++
net/core/Makefile | 3 +-
net/core/dev.c | 1 +
net/core/netdev-genl-gen.c | 48 +++++++
net/core/netdev-genl-gen.h | 23 +++
net/core/netdev-genl.c | 179 ++++++++++++++++++++++++
tools/include/uapi/linux/netdev.h | 59 ++++++++
10 files changed, 477 insertions(+), 1 deletion(-)
create mode 100644 Documentation/netlink/specs/netdev.yaml
create mode 100644 include/uapi/linux/netdev.h
create mode 100644 net/core/netdev-genl-gen.c
create mode 100644 net/core/netdev-genl-gen.h
create mode 100644 net/core/netdev-genl.c
create mode 100644 tools/include/uapi/linux/netdev.h
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
new file mode 100644
index 000000000000..b4dcdae54ffd
--- /dev/null
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -0,0 +1,100 @@
+name: netdev
+
+doc:
+ netdev configuration over generic netlink.
+
+definitions:
+ -
+ type: flags
+ name: xdp-act
+ entries:
+ -
+ name: basic
+ doc:
+ XDP feautues set supported by all drivers
+ (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ -
+ name: redirect
+ doc:
+ The netdev supports XDP_REDIRECT
+ -
+ name: ndo-xmit
+ doc:
+ This feature informs if netdev implements ndo_xdp_xmit callback.
+ -
+ name: xsk-zerocopy
+ doc:
+ This feature informs if netdev supports AF_XDP in zero copy mode.
+ -
+ name: hw-offload
+ doc:
+ This feature informs if netdev supports XDP hw oflloading.
+ -
+ name: rx-sg
+ doc:
+ This feature informs if netdev implements non-linear XDP buffer
+ support in the driver napi callback.
+ -
+ name: ndo-xmit-sg
+ doc:
+ This feature informs if netdev implements non-linear XDP buffer
+ support in ndo_xdp_xmit callback.
+
+attribute-sets:
+ -
+ name: dev
+ attributes:
+ -
+ name: ifindex
+ doc: netdev ifindex
+ type: u32
+ value: 1
+ checks:
+ min: 1
+ -
+ name: pad
+ type: pad
+ -
+ name: xdp-features
+ doc: Bitmask of enabled xdp-features.
+ type: u64
+ enum: xdp-act
+ enum-as-flags: true
+
+operations:
+ list:
+ -
+ name: dev-get
+ doc: Get / dump information about a netdev.
+ value: 1
+ attribute-set: dev
+ do:
+ request:
+ attributes:
+ - ifindex
+ reply: &dev-all
+ attributes:
+ - ifindex
+ - xdp-features
+ dump:
+ reply: *dev-all
+ -
+ name: dev-add-ntf
+ doc: Notification about device appearing.
+ notify: dev-get
+ mcgrp: mgmt
+ -
+ name: dev-del-ntf
+ doc: Notification about device disappearing.
+ notify: dev-get
+ mcgrp: mgmt
+ -
+ name: dev-change-ntf
+ doc: Notification about device configuration being changed.
+ notify: dev-get
+ mcgrp: mgmt
+
+mcast-groups:
+ list:
+ -
+ name: mgmt
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 90f2be194bc5..2cbe9a6ede76 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -47,6 +47,7 @@
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
#include <uapi/linux/pkt_cls.h>
+#include <uapi/linux/netdev.h>
#include <linux/hashtable.h>
#include <linux/rbtree.h>
#include <net/net_trackers.h>
@@ -2055,6 +2056,7 @@ struct net_device {
/* Read-mostly cache-line for fast-path access */
unsigned int flags;
+ xdp_features_t xdp_features;
unsigned long long priv_flags;
const struct net_device_ops *netdev_ops;
const struct xdp_metadata_ops *xdp_metadata_ops;
@@ -2839,6 +2841,7 @@ enum netdev_cmd {
NETDEV_OFFLOAD_XSTATS_DISABLE,
NETDEV_OFFLOAD_XSTATS_REPORT_USED,
NETDEV_OFFLOAD_XSTATS_REPORT_DELTA,
+ NETDEV_XDP_FEAT_CHANGE,
};
const char *netdev_cmd_to_name(enum netdev_cmd cmd);
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 91292aa13bc0..8d1c86914f4c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -7,6 +7,7 @@
#define __LINUX_NET_XDP_H__
#include <linux/skbuff.h> /* skb_shared_info */
+#include <uapi/linux/netdev.h>
/**
* DOC: XDP RX-queue information
@@ -43,6 +44,8 @@ enum xdp_mem_type {
MEM_TYPE_MAX,
};
+typedef u32 xdp_features_t;
+
/* XDP flags for ndo_xdp_xmit */
#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */
#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
new file mode 100644
index 000000000000..9ee459872600
--- /dev/null
+++ b/include/uapi/linux/netdev.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * oflloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+ NETDEV_CMD_DEV_GET = 1,
+ NETDEV_CMD_DEV_ADD_NTF,
+ NETDEV_CMD_DEV_DEL_NTF,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+
+ __NETDEV_CMD_MAX,
+ NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/net/core/Makefile b/net/core/Makefile
index 10edd66a8a37..8f367813bc68 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
- fib_notifier.o xdp.o flow_offload.o gro.o
+ fib_notifier.o xdp.o flow_offload.o gro.o \
+ netdev-genl.o netdev-genl-gen.o
obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
diff --git a/net/core/dev.c b/net/core/dev.c
index e66da626df84..2df1c940aa14 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE)
N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA)
+ N(XDP_FEAT_CHANGE)
}
#undef N
return "UNKNOWN_NETDEV_EVENT";
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
new file mode 100644
index 000000000000..48812ec843f5
--- /dev/null
+++ b/net/core/netdev-genl-gen.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netdev-genl-gen.h"
+
+#include <linux/netdev.h>
+
+/* NETDEV_CMD_DEV_GET - do */
+static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
+ [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+/* Ops table for netdev */
+static const struct genl_split_ops netdev_nl_ops[2] = {
+ {
+ .cmd = NETDEV_CMD_DEV_GET,
+ .doit = netdev_nl_dev_get_doit,
+ .policy = netdev_dev_get_nl_policy,
+ .maxattr = NETDEV_A_DEV_IFINDEX,
+ .flags = GENL_CMD_CAP_DO,
+ },
+ {
+ .cmd = NETDEV_CMD_DEV_GET,
+ .dumpit = netdev_nl_dev_get_dumpit,
+ .flags = GENL_CMD_CAP_DUMP,
+ },
+};
+
+static const struct genl_multicast_group netdev_nl_mcgrps[] = {
+ [NETDEV_NLGRP_MGMT] = { "mgmt", },
+};
+
+struct genl_family netdev_nl_family __ro_after_init = {
+ .name = NETDEV_FAMILY_NAME,
+ .version = NETDEV_FAMILY_VERSION,
+ .netnsok = true,
+ .parallel_ops = true,
+ .module = THIS_MODULE,
+ .split_ops = netdev_nl_ops,
+ .n_split_ops = ARRAY_SIZE(netdev_nl_ops),
+ .mcgrps = netdev_nl_mcgrps,
+ .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps),
+};
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
new file mode 100644
index 000000000000..b16dc7e026bb
--- /dev/null
+++ b/net/core/netdev-genl-gen.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_NETDEV_GEN_H
+#define _LINUX_NETDEV_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <linux/netdev.h>
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+
+enum {
+ NETDEV_NLGRP_MGMT,
+};
+
+extern struct genl_family netdev_nl_family;
+
+#endif /* _LINUX_NETDEV_GEN_H */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
new file mode 100644
index 000000000000..a4270fafdf11
--- /dev/null
+++ b/net/core/netdev-genl.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+
+#include "netdev-genl-gen.h"
+
+static int
+netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
+ u32 portid, u32 seq, int flags, u32 cmd)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
+ nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
+ netdev->xdp_features, NETDEV_A_DEV_PAD)) {
+ genlmsg_cancel(rsp, hdr);
+ return -EINVAL;
+ }
+
+ genlmsg_end(rsp, hdr);
+
+ return 0;
+}
+
+static void
+netdev_genl_dev_notify(struct net_device *netdev, int cmd)
+{
+ struct sk_buff *ntf;
+
+ if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev),
+ NETDEV_NLGRP_MGMT))
+ return;
+
+ ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!ntf)
+ return;
+
+ if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) {
+ nlmsg_free(ntf);
+ return;
+ }
+
+ genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf,
+ 0, NETDEV_NLGRP_MGMT, GFP_KERNEL);
+}
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *netdev;
+ struct sk_buff *rsp;
+ u32 ifindex;
+ int err;
+
+ if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX))
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+
+ rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!rsp)
+ return -ENOMEM;
+
+ rtnl_lock();
+
+ netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+ if (netdev)
+ err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid,
+ info->snd_seq, 0, info->genlhdr->cmd);
+ else
+ err = -ENODEV;
+
+ rtnl_unlock();
+
+ if (err)
+ goto err_free_msg;
+
+ return genlmsg_reply(rsp, info);
+
+err_free_msg:
+ nlmsg_free(rsp);
+ return err;
+}
+
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct net_device *netdev;
+ int idx = 0, s_idx;
+ int h, s_h;
+ int err;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ rtnl_lock();
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ struct hlist_head *head;
+
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry(netdev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ err = netdev_nl_dev_fill(netdev, skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NETDEV_CMD_DEV_GET);
+ if (err < 0)
+ break;
+cont:
+ idx++;
+ }
+ }
+
+ rtnl_unlock();
+
+ if (err != -EMSGSIZE)
+ return err;
+
+ cb->args[1] = idx;
+ cb->args[0] = h;
+ cb->seq = net->dev_base_seq;
+
+ return skb->len;
+}
+
+static int netdev_genl_netdevice_event(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF);
+ break;
+ case NETDEV_UNREGISTER:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF);
+ break;
+ case NETDEV_XDP_FEAT_CHANGE:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block netdev_genl_nb = {
+ .notifier_call = netdev_genl_netdevice_event,
+};
+
+static int __init netdev_genl_init(void)
+{
+ int err;
+
+ err = register_netdevice_notifier(&netdev_genl_nb);
+ if (err)
+ return err;
+
+ err = genl_register_family(&netdev_nl_family);
+ if (err)
+ goto err_unreg_ntf;
+
+ return 0;
+
+err_unreg_ntf:
+ unregister_netdevice_notifier(&netdev_genl_nb);
+ return err;
+}
+
+subsys_initcall(netdev_genl_init);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
new file mode 100644
index 000000000000..9ee459872600
--- /dev/null
+++ b/tools/include/uapi/linux/netdev.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * oflloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+ NETDEV_CMD_DEV_GET = 1,
+ NETDEV_CMD_DEV_ADD_NTF,
+ NETDEV_CMD_DEV_DEL_NTF,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+
+ __NETDEV_CMD_MAX,
+ NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 1/8] netdev-genl: create a simple family for netdev stuff
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
From: Jakub Kicinski <kuba@kernel.org>
Add a Netlink spec-compatible family for netdevs.
This is a very simple implementation without much
thought going into it.
It allows us to reap all the benefits of Netlink specs,
one can use the generic client to issue the commands:
$ ./cli.py --spec netdev.yaml --dump dev_get
[{'ifindex': 1, 'xdp-features': set()},
{'ifindex': 2, 'xdp-features': {'basic', 'ndo-xmit', 'redirect'}},
{'ifindex': 3, 'xdp-features': {'rx-sg'}}]
the generic python library does not have flags-by-name
support, yet, but we also don't have to carry strings
in the messages, as user space can get the names from
the spec.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
Documentation/netlink/specs/netdev.yaml | 100 +++++++++++++
include/linux/netdevice.h | 3 +
include/net/xdp.h | 3 +
include/uapi/linux/netdev.h | 59 ++++++++
net/core/Makefile | 3 +-
net/core/dev.c | 1 +
net/core/netdev-genl-gen.c | 48 +++++++
net/core/netdev-genl-gen.h | 23 +++
net/core/netdev-genl.c | 179 ++++++++++++++++++++++++
tools/include/uapi/linux/netdev.h | 59 ++++++++
10 files changed, 477 insertions(+), 1 deletion(-)
create mode 100644 Documentation/netlink/specs/netdev.yaml
create mode 100644 include/uapi/linux/netdev.h
create mode 100644 net/core/netdev-genl-gen.c
create mode 100644 net/core/netdev-genl-gen.h
create mode 100644 net/core/netdev-genl.c
create mode 100644 tools/include/uapi/linux/netdev.h
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
new file mode 100644
index 000000000000..b4dcdae54ffd
--- /dev/null
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -0,0 +1,100 @@
+name: netdev
+
+doc:
+ netdev configuration over generic netlink.
+
+definitions:
+ -
+ type: flags
+ name: xdp-act
+ entries:
+ -
+ name: basic
+ doc:
+ XDP feautues set supported by all drivers
+ (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ -
+ name: redirect
+ doc:
+ The netdev supports XDP_REDIRECT
+ -
+ name: ndo-xmit
+ doc:
+ This feature informs if netdev implements ndo_xdp_xmit callback.
+ -
+ name: xsk-zerocopy
+ doc:
+ This feature informs if netdev supports AF_XDP in zero copy mode.
+ -
+ name: hw-offload
+ doc:
+ This feature informs if netdev supports XDP hw oflloading.
+ -
+ name: rx-sg
+ doc:
+ This feature informs if netdev implements non-linear XDP buffer
+ support in the driver napi callback.
+ -
+ name: ndo-xmit-sg
+ doc:
+ This feature informs if netdev implements non-linear XDP buffer
+ support in ndo_xdp_xmit callback.
+
+attribute-sets:
+ -
+ name: dev
+ attributes:
+ -
+ name: ifindex
+ doc: netdev ifindex
+ type: u32
+ value: 1
+ checks:
+ min: 1
+ -
+ name: pad
+ type: pad
+ -
+ name: xdp-features
+ doc: Bitmask of enabled xdp-features.
+ type: u64
+ enum: xdp-act
+ enum-as-flags: true
+
+operations:
+ list:
+ -
+ name: dev-get
+ doc: Get / dump information about a netdev.
+ value: 1
+ attribute-set: dev
+ do:
+ request:
+ attributes:
+ - ifindex
+ reply: &dev-all
+ attributes:
+ - ifindex
+ - xdp-features
+ dump:
+ reply: *dev-all
+ -
+ name: dev-add-ntf
+ doc: Notification about device appearing.
+ notify: dev-get
+ mcgrp: mgmt
+ -
+ name: dev-del-ntf
+ doc: Notification about device disappearing.
+ notify: dev-get
+ mcgrp: mgmt
+ -
+ name: dev-change-ntf
+ doc: Notification about device configuration being changed.
+ notify: dev-get
+ mcgrp: mgmt
+
+mcast-groups:
+ list:
+ -
+ name: mgmt
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 90f2be194bc5..2cbe9a6ede76 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -47,6 +47,7 @@
#include <uapi/linux/netdevice.h>
#include <uapi/linux/if_bonding.h>
#include <uapi/linux/pkt_cls.h>
+#include <uapi/linux/netdev.h>
#include <linux/hashtable.h>
#include <linux/rbtree.h>
#include <net/net_trackers.h>
@@ -2055,6 +2056,7 @@ struct net_device {
/* Read-mostly cache-line for fast-path access */
unsigned int flags;
+ xdp_features_t xdp_features;
unsigned long long priv_flags;
const struct net_device_ops *netdev_ops;
const struct xdp_metadata_ops *xdp_metadata_ops;
@@ -2839,6 +2841,7 @@ enum netdev_cmd {
NETDEV_OFFLOAD_XSTATS_DISABLE,
NETDEV_OFFLOAD_XSTATS_REPORT_USED,
NETDEV_OFFLOAD_XSTATS_REPORT_DELTA,
+ NETDEV_XDP_FEAT_CHANGE,
};
const char *netdev_cmd_to_name(enum netdev_cmd cmd);
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 91292aa13bc0..8d1c86914f4c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -7,6 +7,7 @@
#define __LINUX_NET_XDP_H__
#include <linux/skbuff.h> /* skb_shared_info */
+#include <uapi/linux/netdev.h>
/**
* DOC: XDP RX-queue information
@@ -43,6 +44,8 @@ enum xdp_mem_type {
MEM_TYPE_MAX,
};
+typedef u32 xdp_features_t;
+
/* XDP flags for ndo_xdp_xmit */
#define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */
#define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
new file mode 100644
index 000000000000..9ee459872600
--- /dev/null
+++ b/include/uapi/linux/netdev.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * oflloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+ NETDEV_CMD_DEV_GET = 1,
+ NETDEV_CMD_DEV_ADD_NTF,
+ NETDEV_CMD_DEV_DEL_NTF,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+
+ __NETDEV_CMD_MAX,
+ NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
diff --git a/net/core/Makefile b/net/core/Makefile
index 10edd66a8a37..8f367813bc68 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
obj-y += dev.o dev_addr_lists.o dst.o netevent.o \
neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
- fib_notifier.o xdp.o flow_offload.o gro.o
+ fib_notifier.o xdp.o flow_offload.o gro.o \
+ netdev-genl.o netdev-genl-gen.o
obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
diff --git a/net/core/dev.c b/net/core/dev.c
index e66da626df84..2df1c940aa14 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE)
N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA)
+ N(XDP_FEAT_CHANGE)
}
#undef N
return "UNKNOWN_NETDEV_EVENT";
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
new file mode 100644
index 000000000000..48812ec843f5
--- /dev/null
+++ b/net/core/netdev-genl-gen.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netdev-genl-gen.h"
+
+#include <linux/netdev.h>
+
+/* NETDEV_CMD_DEV_GET - do */
+static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
+ [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+/* Ops table for netdev */
+static const struct genl_split_ops netdev_nl_ops[2] = {
+ {
+ .cmd = NETDEV_CMD_DEV_GET,
+ .doit = netdev_nl_dev_get_doit,
+ .policy = netdev_dev_get_nl_policy,
+ .maxattr = NETDEV_A_DEV_IFINDEX,
+ .flags = GENL_CMD_CAP_DO,
+ },
+ {
+ .cmd = NETDEV_CMD_DEV_GET,
+ .dumpit = netdev_nl_dev_get_dumpit,
+ .flags = GENL_CMD_CAP_DUMP,
+ },
+};
+
+static const struct genl_multicast_group netdev_nl_mcgrps[] = {
+ [NETDEV_NLGRP_MGMT] = { "mgmt", },
+};
+
+struct genl_family netdev_nl_family __ro_after_init = {
+ .name = NETDEV_FAMILY_NAME,
+ .version = NETDEV_FAMILY_VERSION,
+ .netnsok = true,
+ .parallel_ops = true,
+ .module = THIS_MODULE,
+ .split_ops = netdev_nl_ops,
+ .n_split_ops = ARRAY_SIZE(netdev_nl_ops),
+ .mcgrps = netdev_nl_mcgrps,
+ .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps),
+};
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
new file mode 100644
index 000000000000..b16dc7e026bb
--- /dev/null
+++ b/net/core/netdev-genl-gen.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_NETDEV_GEN_H
+#define _LINUX_NETDEV_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <linux/netdev.h>
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+
+enum {
+ NETDEV_NLGRP_MGMT,
+};
+
+extern struct genl_family netdev_nl_family;
+
+#endif /* _LINUX_NETDEV_GEN_H */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
new file mode 100644
index 000000000000..a4270fafdf11
--- /dev/null
+++ b/net/core/netdev-genl.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+
+#include "netdev-genl-gen.h"
+
+static int
+netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
+ u32 portid, u32 seq, int flags, u32 cmd)
+{
+ void *hdr;
+
+ hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd);
+ if (!hdr)
+ return -EMSGSIZE;
+
+ if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
+ nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
+ netdev->xdp_features, NETDEV_A_DEV_PAD)) {
+ genlmsg_cancel(rsp, hdr);
+ return -EINVAL;
+ }
+
+ genlmsg_end(rsp, hdr);
+
+ return 0;
+}
+
+static void
+netdev_genl_dev_notify(struct net_device *netdev, int cmd)
+{
+ struct sk_buff *ntf;
+
+ if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev),
+ NETDEV_NLGRP_MGMT))
+ return;
+
+ ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!ntf)
+ return;
+
+ if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) {
+ nlmsg_free(ntf);
+ return;
+ }
+
+ genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf,
+ 0, NETDEV_NLGRP_MGMT, GFP_KERNEL);
+}
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *netdev;
+ struct sk_buff *rsp;
+ u32 ifindex;
+ int err;
+
+ if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX))
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+
+ rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!rsp)
+ return -ENOMEM;
+
+ rtnl_lock();
+
+ netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+ if (netdev)
+ err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid,
+ info->snd_seq, 0, info->genlhdr->cmd);
+ else
+ err = -ENODEV;
+
+ rtnl_unlock();
+
+ if (err)
+ goto err_free_msg;
+
+ return genlmsg_reply(rsp, info);
+
+err_free_msg:
+ nlmsg_free(rsp);
+ return err;
+}
+
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net *net = sock_net(skb->sk);
+ struct net_device *netdev;
+ int idx = 0, s_idx;
+ int h, s_h;
+ int err;
+
+ s_h = cb->args[0];
+ s_idx = cb->args[1];
+
+ rtnl_lock();
+
+ for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+ struct hlist_head *head;
+
+ idx = 0;
+ head = &net->dev_index_head[h];
+ hlist_for_each_entry(netdev, head, index_hlist) {
+ if (idx < s_idx)
+ goto cont;
+ err = netdev_nl_dev_fill(netdev, skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, 0,
+ NETDEV_CMD_DEV_GET);
+ if (err < 0)
+ break;
+cont:
+ idx++;
+ }
+ }
+
+ rtnl_unlock();
+
+ if (err != -EMSGSIZE)
+ return err;
+
+ cb->args[1] = idx;
+ cb->args[0] = h;
+ cb->seq = net->dev_base_seq;
+
+ return skb->len;
+}
+
+static int netdev_genl_netdevice_event(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF);
+ break;
+ case NETDEV_UNREGISTER:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF);
+ break;
+ case NETDEV_XDP_FEAT_CHANGE:
+ netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF);
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block netdev_genl_nb = {
+ .notifier_call = netdev_genl_netdevice_event,
+};
+
+static int __init netdev_genl_init(void)
+{
+ int err;
+
+ err = register_netdevice_notifier(&netdev_genl_nb);
+ if (err)
+ return err;
+
+ err = genl_register_family(&netdev_nl_family);
+ if (err)
+ goto err_unreg_ntf;
+
+ return 0;
+
+err_unreg_ntf:
+ unregister_netdevice_notifier(&netdev_genl_nb);
+ return err;
+}
+
+subsys_initcall(netdev_genl_init);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
new file mode 100644
index 000000000000..9ee459872600
--- /dev/null
+++ b/tools/include/uapi/linux/netdev.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* Do not edit directly, auto-generated from: */
+/* Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_NETDEV_H
+#define _UAPI_LINUX_NETDEV_H
+
+#define NETDEV_FAMILY_NAME "netdev"
+#define NETDEV_FAMILY_VERSION 1
+
+/**
+ * enum netdev_xdp_act
+ * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers
+ * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX)
+ * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT
+ * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements
+ * ndo_xdp_xmit callback.
+ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP
+ * in zero copy mode.
+ * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw
+ * oflloading.
+ * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear
+ * XDP buffer support in the driver napi callback.
+ * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements
+ * non-linear XDP buffer support in ndo_xdp_xmit callback.
+ */
+enum netdev_xdp_act {
+ NETDEV_XDP_ACT_BASIC = 1,
+ NETDEV_XDP_ACT_REDIRECT = 2,
+ NETDEV_XDP_ACT_NDO_XMIT = 4,
+ NETDEV_XDP_ACT_XSK_ZEROCOPY = 8,
+ NETDEV_XDP_ACT_HW_OFFLOAD = 16,
+ NETDEV_XDP_ACT_RX_SG = 32,
+ NETDEV_XDP_ACT_NDO_XMIT_SG = 64,
+};
+
+enum {
+ NETDEV_A_DEV_IFINDEX = 1,
+ NETDEV_A_DEV_PAD,
+ NETDEV_A_DEV_XDP_FEATURES,
+
+ __NETDEV_A_DEV_MAX,
+ NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
+};
+
+enum {
+ NETDEV_CMD_DEV_GET = 1,
+ NETDEV_CMD_DEV_ADD_NTF,
+ NETDEV_CMD_DEV_DEL_NTF,
+ NETDEV_CMD_DEV_CHANGE_NTF,
+
+ __NETDEV_CMD_MAX,
+ NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1)
+};
+
+#define NETDEV_MCGRP_MGMT "mgmt"
+
+#endif /* _UAPI_LINUX_NETDEV_H */
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
From: Marek Majtyka <alardam@gmail.com>
A summary of the flags being set for various drivers is given below.
Note that XDP_F_REDIRECT_TARGET and XDP_F_FRAG_TARGET are features
that can be turned off and on at runtime. This means that these flags
may be set and unset under RTNL lock protection by the driver. Hence,
READ_ONCE must be used by code loading the flag value.
Also, these flags are not used for synchronization against the availability
of XDP resources on a device. It is merely a hint, and hence the read
may race with the actual teardown of XDP resources on the device. This
may change in the future, e.g. operations taking a reference on the XDP
resources of the driver, and in turn inhibiting turning off this flag.
However, for now, it can only be used as a hint to check whether device
supports becoming a redirection target.
Turn 'hw-offload' feature flag on for:
- netronome (nfp)
- netdevsim.
Turn 'native' and 'zerocopy' features flags on for:
- intel (i40e, ice, ixgbe, igc)
- mellanox (mlx5).
- stmmac
- netronome (nfp)
Turn 'native' features flags on for:
- amazon (ena)
- broadcom (bnxt)
- freescale (dpaa, dpaa2, enetc)
- funeth
- intel (igb)
- marvell (mvneta, mvpp2, octeontx2)
- mellanox (mlx4)
- qlogic (qede)
- sfc
- socionext (netsec)
- ti (cpsw)
- tap
- veth
- xen
- virtio_net.
Turn 'basic' (tx, pass, aborted and drop) features flags on for:
- netronome (nfp)
- cavium (thunder)
- hyperv.
Turn 'redirect_target' feature flag on for:
- amanzon (ena)
- broadcom (bnxt)
- freescale (dpaa, dpaa2)
- intel (i40e, ice, igb, ixgbe)
- ti (cpsw)
- marvell (mvneta, mvpp2)
- sfc
- socionext (netsec)
- qlogic (qede)
- mellanox (mlx5)
- tap
- veth
- virtio_net
- xen
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ++++
.../net/ethernet/aquantia/atlantic/aq_nic.c | 5 +++++
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 ++
.../net/ethernet/cavium/thunder/nicvf_main.c | 2 ++
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 ++++
.../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 ++++
.../net/ethernet/freescale/enetc/enetc_pf.c | 3 +++
.../net/ethernet/fungible/funeth/funeth_main.c | 6 ++++++
drivers/net/ethernet/intel/i40e/i40e_main.c | 10 ++++++++--
drivers/net/ethernet/intel/ice/ice_main.c | 5 +++++
drivers/net/ethernet/intel/igb/igb_main.c | 9 ++++++++-
drivers/net/ethernet/intel/igc/igc_main.c | 3 +++
drivers/net/ethernet/intel/igc/igc_xdp.c | 5 +++++
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++++++
.../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 +
drivers/net/ethernet/marvell/mvneta.c | 3 +++
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++++
.../ethernet/marvell/octeontx2/nic/otx2_pf.c | 8 ++++++--
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 6 ++++++
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 ++
.../net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++++++++
drivers/net/ethernet/microsoft/mana/mana_en.c | 2 ++
.../ethernet/netronome/nfp/nfp_net_common.c | 5 +++++
drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +++
drivers/net/ethernet/sfc/efx.c | 4 ++++
drivers/net/ethernet/sfc/siena/efx.c | 4 ++++
drivers/net/ethernet/socionext/netsec.c | 3 +++
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++
drivers/net/ethernet/ti/cpsw.c | 4 ++++
drivers/net/ethernet/ti/cpsw_new.c | 4 ++++
drivers/net/hyperv/netvsc_drv.c | 2 ++
drivers/net/netdevsim/netdev.c | 1 +
drivers/net/tun.c | 5 +++++
drivers/net/veth.c | 4 ++++
drivers/net/virtio_net.c | 4 ++++
drivers/net/xen-netfront.c | 2 ++
include/net/xdp.h | 12 ++++++++++++
net/core/xdp.c | 18 ++++++++++++++++++
39 files changed, 180 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index e8ad5ea31aff..d3999db7c6a2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
if (rc)
return rc;
}
+ xdp_features_set_redirect_target(netdev, false);
} else if (old_bpf_prog) {
+ xdp_features_clear_redirect_target(netdev);
rc = ena_destroy_and_free_all_xdp_queues(adapter);
if (rc)
return rc;
@@ -4103,6 +4105,8 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter,
/* Set offload features */
ena_set_dev_offloads(feat, netdev);
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
adapter->max_mtu = feat->dev_attr.max_mtu;
netdev->max_mtu = adapter->max_mtu;
netdev->min_mtu = ENA_MIN_MTU;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 06508eebb585..d6d6d5d37ff3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -384,6 +384,11 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN;
self->ndev->max_mtu = aq_hw_caps->mtu - ETH_FCS_LEN - ETH_HLEN;
+ self->ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
}
void aq_nic_set_tx_ring(struct aq_nic_s *self, unsigned int idx,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 16ce7a90610c..4fc2846950f8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13686,6 +13686,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_RX_SG;
+
#ifdef CONFIG_BNXT_SRIOV
init_waitqueue_head(&bp->sriov_cfg_wait);
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 36d5202c0aee..5843c93b1711 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -422,9 +422,11 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
if (prog) {
bnxt_set_rx_skb_mode(bp, true);
+ xdp_features_set_redirect_target(dev, true);
} else {
int rx, tx;
+ xdp_features_clear_redirect_target(dev);
bnxt_set_rx_skb_mode(bp, false);
bnxt_get_max_rings(bp, &rx, &tx, true);
if (rx > 1) {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index f2f95493ec89..8b25313c7f6b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2218,6 +2218,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->netdev_ops = &nicvf_netdev_ops;
netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+
/* MTU range: 64 - 9200 */
netdev->min_mtu = NIC_HW_MIN_FRS;
netdev->max_mtu = NIC_HW_MAX_FRS;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 3f8032947d86..63b30b64ba82 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -244,6 +244,10 @@ static int dpaa_netdev_init(struct net_device *net_dev,
net_dev->features |= net_dev->hw_features;
net_dev->vlan_features = net_dev->features;
+ net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (is_valid_ether_addr(mac_addr)) {
memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len);
eth_hw_addr_set(net_dev, mac_addr);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 0c35abb7d065..c4229868a6a8 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4593,6 +4593,10 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev)
NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO;
net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS;
net_dev->hw_features = net_dev->features;
+ net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY |
+ NETDEV_XDP_ACT_NDO_XMIT;
if (priv->dpni_attrs.vlan_filter_entries)
net_dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 9f6c4f5c0a6c..2036c5bbd3e9 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -825,6 +825,9 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
ndev->hw_features |= NETIF_F_RXHASH;
ndev->priv_flags |= IFF_UNICAST_FLT;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) {
priv->active_offloads |= ENETC_F_QCI;
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c
index b4cce30e526a..df86770731ad 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_main.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c
@@ -1160,6 +1160,11 @@ static int fun_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp)
WRITE_ONCE(rxqs[i]->xdp_prog, prog);
}
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+
dev->max_mtu = prog ? XDP_MAX_MTU : FUN_MAX_MTU;
old_prog = xchg(&fp->xdp_prog, prog);
if (old_prog)
@@ -1765,6 +1770,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid)
netdev->vlan_features = netdev->features & VLAN_FEAT;
netdev->mpls_features = netdev->vlan_features;
netdev->hw_enc_features = netdev->hw_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = FUN_MAX_MTU;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 53d0083e35da..8a79cc18c428 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -13339,9 +13339,11 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
old_prog = xchg(&vsi->xdp_prog, prog);
if (need_reset) {
- if (!prog)
+ if (!prog) {
+ xdp_features_clear_redirect_target(vsi->netdev);
/* Wait until ndo_xsk_wakeup completes. */
synchronize_rcu();
+ }
i40e_reset_and_rebuild(pf, true, true);
}
@@ -13362,11 +13364,13 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
/* Kick start the NAPI context if there is an AF_XDP socket open
* on that queue id. This so that receiving will start.
*/
- if (need_reset && prog)
+ if (need_reset && prog) {
for (i = 0; i < vsi->num_queue_pairs; i++)
if (vsi->xdp_rings[i]->xsk_pool)
(void)i40e_xsk_wakeup(vsi->netdev, i,
XDP_WAKEUP_RX);
+ xdp_features_set_redirect_target(vsi->netdev, true);
+ }
return 0;
}
@@ -13783,6 +13787,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
netdev->features &= ~NETIF_F_HW_TC;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
if (vsi->type == I40E_VSI_MAIN) {
SET_NETDEV_DEV(netdev, &pf->pdev->dev);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a9a7f8b52140..45cdb0f19a1e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -22,6 +22,7 @@
#include "ice_eswitch.h"
#include "ice_tc_lib.h"
#include "ice_vsi_vlan_ops.h"
+#include <net/xdp_sock_drv.h>
#define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver"
static const char ice_driver_string[] = DRV_SUMMARY;
@@ -2899,11 +2900,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
}
+ xdp_features_set_redirect_target(vsi->netdev, false);
/* reallocate Rx queues that are used for zero-copy */
xdp_ring_err = ice_realloc_zc_buf(vsi, true);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
+ xdp_features_clear_redirect_target(vsi->netdev);
xdp_ring_err = ice_destroy_xdp_rings(vsi);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
@@ -3446,6 +3449,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
np->vsi = vsi;
ice_set_netdev_features(netdev);
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
ice_set_ops(netdev);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 3c0c35ecea10..0e11a082f7a1 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2871,8 +2871,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
bpf_prog_put(old_prog);
/* bpf is just replaced, RXQ and MTU are already setup */
- if (!need_reset)
+ if (!need_reset) {
return 0;
+ } else {
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+ }
if (running)
igb_open(dev);
@@ -3317,6 +3323,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->priv_flags |= IFF_SUPP_NOFCS;
netdev->priv_flags |= IFF_UNICAST_FLT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
/* MTU range: 68 - 9216 */
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e86b15efaeb8..8b572cd2c350 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6533,6 +6533,9 @@ static int igc_probe(struct pci_dev *pdev,
netdev->mpls_features |= NETIF_F_HW_CSUM;
netdev->hw_enc_features |= netdev->vlan_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
/* MTU range: 68 - 9216 */
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index aeeb34e64610..e27af72aada8 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -29,6 +29,11 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
if (old_prog)
bpf_prog_put(old_prog);
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+
if (if_running)
igc_open(dev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ab8370c413f3..d0975c48aee5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10301,6 +10301,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
rcu_assign_pointer(adapter->xdp_prog, old_prog);
return -EINVAL;
}
+ if (!prog)
+ xdp_features_clear_redirect_target(dev);
} else {
for (i = 0; i < adapter->num_rx_queues; i++)
(void)xchg(&adapter->rx_ring[i]->xdp_prog,
@@ -10320,6 +10322,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
if (adapter->xdp_ring[i]->xsk_pool)
(void)ixgbe_xsk_wakeup(adapter->netdev, i,
XDP_WAKEUP_RX);
+ xdp_features_set_redirect_target(dev, true);
}
return 0;
@@ -11017,6 +11020,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->priv_flags |= IFF_SUPP_NOFCS;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
/* MTU range: 68 - 9710 */
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index ea0a230c1153..a44e4bd56142 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4634,6 +4634,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
NETIF_F_HW_VLAN_CTAG_TX;
netdev->priv_flags |= IFF_UNICAST_FLT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
/* MTU range: 68 - 1504 or 9710 */
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f8925cac61e4..dc2989103a77 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5612,6 +5612,9 @@ static int mvneta_probe(struct platform_device *pdev)
NETIF_F_TSO | NETIF_F_RXCSUM;
dev->hw_features |= dev->features;
dev->vlan_features |= dev->features;
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
netif_set_tso_max_segs(dev, MVNETA_MAX_TSO_SEGS);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 4da45c5abba5..9b4ecbe4f36d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -6866,6 +6866,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
dev->vlan_features |= features;
netif_set_tso_max_segs(dev, MVPP2_MAX_TSO_SEGS);
+
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
dev->priv_flags |= IFF_UNICAST_FLT;
/* MTU range: 68 - 9704 */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index c1ea60bc2630..179433d0a54a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2512,10 +2512,13 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
/* Network stack and XDP shared same rx queues.
* Use separate tx queues for XDP and network stack.
*/
- if (pf->xdp_prog)
+ if (pf->xdp_prog) {
pf->hw.xdp_queues = pf->hw.rx_queues;
- else
+ xdp_features_set_redirect_target(dev, false);
+ } else {
pf->hw.xdp_queues = 0;
+ xdp_features_clear_redirect_target(dev);
+ }
pf->hw.tot_tx_queues += pf->hw.xdp_queues;
@@ -2878,6 +2881,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
netdev->netdev_ops = &otx2_netdev_ops;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
netdev->min_mtu = OTX2_MIN_MTU;
netdev->max_mtu = otx2_get_max_mtu(pf);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index e3de9a53b2d9..7ed5ff18d05b 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4186,6 +4186,12 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
register_netdevice_notifier(&mac->device_notifier);
}
+ if (mtk_page_pool_enabled(eth))
+ eth->netdev[id]->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
+
return 0;
free_netdev:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index af4c4858f397..e11bc0ac880e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3416,6 +3416,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->rss_hash_fn = ETH_RSS_HASH_TOP;
}
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
/* MTU range: 68 - hw-specific max */
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = priv->max_mtu;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3370c8b9f983..c702d1fae764 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4776,6 +4776,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
if (old_prog)
bpf_prog_put(old_prog);
+ if (reset) {
+ if (prog)
+ xdp_features_set_redirect_target(netdev, true);
+ else
+ xdp_features_clear_redirect_target(netdev);
+ }
+
if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
goto unlock;
@@ -5171,6 +5178,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY |
+ NETDEV_XDP_ACT_RX_SG;
+
netdev->priv_flags |= IFF_UNICAST_FLT;
netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 2f6a048dee90..6120f2b6684f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2160,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
ndev->hw_features |= NETIF_F_RXHASH;
ndev->features = ndev->hw_features;
ndev->vlan_features = 0;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
err = register_netdev(ndev);
if (err) {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 18fc9971f1c8..e4825d885560 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2529,10 +2529,15 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
netdev->features &= ~NETIF_F_HW_VLAN_STAG_RX;
nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_RXQINQ;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+ if (nn->app && nn->app->type->id == NFP_APP_BPF_NIC)
+ netdev->xdp_features |= NETDEV_XDP_ACT_HW_OFFLOAD;
+
/* Finalise the netdev setup */
switch (nn->dp.ops->version) {
case NFP_NFD_VER_NFD3:
netdev->netdev_ops = &nfp_nfd3_netdev_ops;
+ netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
break;
case NFP_NFD_VER_NFDK:
netdev->netdev_ops = &nfp_nfdk_netdev_ops;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 953f304b8588..b6d999927e86 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -892,6 +892,9 @@ static void qede_init_ndev(struct qede_dev *edev)
ndev->hw_features = hw_features;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
/* MTU range: 46 - 9600 */
ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE;
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 0556542d7a6b..18ff8d8cff42 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1078,6 +1078,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
pci_info(pci_dev, "Solarflare NIC detected\n");
+ efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (!efx->type->is_vf)
efx_probe_vpd_strings(efx);
diff --git a/drivers/net/ethernet/sfc/siena/efx.c b/drivers/net/ethernet/sfc/siena/efx.c
index 60e5b7c8ccf9..a6ef21845224 100644
--- a/drivers/net/ethernet/sfc/siena/efx.c
+++ b/drivers/net/ethernet/sfc/siena/efx.c
@@ -1048,6 +1048,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
pci_info(pci_dev, "Solarflare NIC detected\n");
+ efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (!efx->type->is_vf)
efx_probe_vpd_strings(efx);
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 9b46579b5a10..2d7347b71c41 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -2104,6 +2104,9 @@ static int netsec_probe(struct platform_device *pdev)
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
ndev->hw_features = ndev->features;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
priv->rx_cksum_offload_flag = true;
ret = netsec_register_mdio(priv, phy_addr);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c6951c976f5d..9a88cc73259f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7145,6 +7145,8 @@ int stmmac_dvr_probe(struct device *device,
ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ret = stmmac_tc_init(priv, priv);
if (!ret) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 13c9c2d6b79b..37f0b62ec5d6 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1458,6 +1458,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
priv_sl2->emac_port = 1;
cpsw->slaves[1].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
@@ -1635,6 +1637,8 @@ static int cpsw_probe(struct platform_device *pdev)
cpsw->slaves[0].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 83596ec0c7cb..35128dd45ffc 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1405,6 +1405,10 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
SET_NETDEV_DEV(ndev, dev);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f9b219e6cd58..a9b139bbdb2c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2559,6 +2559,8 @@ static int netvsc_probe(struct hv_device *dev,
netdev_lockdep_set_classes(net);
+ net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
/* MTU range: 68 - 1500 or 65521 */
net->min_mtu = NETVSC_MTU_MIN;
if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 6db6a75ff9b9..35fa1ca98671 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -286,6 +286,7 @@ static void nsim_setup(struct net_device *dev)
NETIF_F_TSO;
dev->hw_features |= NETIF_F_HW_TC;
dev->max_mtu = ETH_MAX_MTU;
+ dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
}
static int nsim_init_netdevsim(struct netdevsim *ns)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a7d17c680f4a..36620afde373 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1401,6 +1401,11 @@ static void tun_net_initialize(struct net_device *dev)
eth_hw_addr_random(dev);
+ /* Currently tun does not support XDP, only tap does. */
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
break;
}
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ba3e05832843..1bb54de7124d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1686,6 +1686,10 @@ static void veth_setup(struct net_device *dev)
dev->hw_enc_features = VETH_FEATURES;
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
}
/*
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7723b2a49d8e..829b652f3309 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3155,7 +3155,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
if (i == 0 && !old_prog)
virtnet_clear_guest_offloads(vi);
}
+ if (!old_prog)
+ xdp_features_set_redirect_target(dev, false);
} else {
+ xdp_features_clear_redirect_target(dev);
vi->xdp_enabled = false;
}
@@ -3785,6 +3788,7 @@ static int virtnet_probe(struct virtio_device *vdev)
dev->hw_features |= NETIF_F_GRO_HW;
dev->vlan_features = dev->features;
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
/* MTU range: 68 - 65535 */
dev->min_mtu = MIN_MTU;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 14aec417fa06..416860c0f204 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1741,6 +1741,8 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
* negotiate with the backend regarding supported features.
*/
netdev->features |= netdev->hw_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
netdev->ethtool_ops = &xennet_ethtool_ops;
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8d1c86914f4c..d517bfac937b 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -428,9 +428,21 @@ MAX_XDP_METADATA_KFUNC,
#ifdef CONFIG_NET
u32 bpf_xdp_metadata_kfunc_id(int id);
bool bpf_dev_bound_kfunc_id(u32 btf_id);
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg);
+void xdp_features_clear_redirect_target(struct net_device *dev);
#else
static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; }
static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; }
+
+static inline void
+xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+}
+
+static inline void
+xdp_features_clear_redirect_target(struct net_device *dev)
+{
+}
#endif
#endif /* __LINUX_NET_XDP_H__ */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index a5a7ecf6391c..82727b47259d 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
}
late_initcall(xdp_metadata_init);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+ dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
+ if (support_sg)
+ dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
+
+ call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
+
+void xdp_features_clear_redirect_target(struct net_device *dev)
+{
+ dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_NDO_XMIT_SG);
+ call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
From: Marek Majtyka <alardam@gmail.com>
A summary of the flags being set for various drivers is given below.
Note that XDP_F_REDIRECT_TARGET and XDP_F_FRAG_TARGET are features
that can be turned off and on at runtime. This means that these flags
may be set and unset under RTNL lock protection by the driver. Hence,
READ_ONCE must be used by code loading the flag value.
Also, these flags are not used for synchronization against the availability
of XDP resources on a device. It is merely a hint, and hence the read
may race with the actual teardown of XDP resources on the device. This
may change in the future, e.g. operations taking a reference on the XDP
resources of the driver, and in turn inhibiting turning off this flag.
However, for now, it can only be used as a hint to check whether device
supports becoming a redirection target.
Turn 'hw-offload' feature flag on for:
- netronome (nfp)
- netdevsim.
Turn 'native' and 'zerocopy' features flags on for:
- intel (i40e, ice, ixgbe, igc)
- mellanox (mlx5).
- stmmac
- netronome (nfp)
Turn 'native' features flags on for:
- amazon (ena)
- broadcom (bnxt)
- freescale (dpaa, dpaa2, enetc)
- funeth
- intel (igb)
- marvell (mvneta, mvpp2, octeontx2)
- mellanox (mlx4)
- qlogic (qede)
- sfc
- socionext (netsec)
- ti (cpsw)
- tap
- veth
- xen
- virtio_net.
Turn 'basic' (tx, pass, aborted and drop) features flags on for:
- netronome (nfp)
- cavium (thunder)
- hyperv.
Turn 'redirect_target' feature flag on for:
- amanzon (ena)
- broadcom (bnxt)
- freescale (dpaa, dpaa2)
- intel (i40e, ice, igb, ixgbe)
- ti (cpsw)
- marvell (mvneta, mvpp2)
- sfc
- socionext (netsec)
- qlogic (qede)
- mellanox (mlx5)
- tap
- veth
- virtio_net
- xen
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Acked-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
---
drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ++++
.../net/ethernet/aquantia/atlantic/aq_nic.c | 5 +++++
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 ++
.../net/ethernet/cavium/thunder/nicvf_main.c | 2 ++
drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 ++++
.../net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 ++++
.../net/ethernet/freescale/enetc/enetc_pf.c | 3 +++
.../net/ethernet/fungible/funeth/funeth_main.c | 6 ++++++
drivers/net/ethernet/intel/i40e/i40e_main.c | 10 ++++++++--
drivers/net/ethernet/intel/ice/ice_main.c | 5 +++++
drivers/net/ethernet/intel/igb/igb_main.c | 9 ++++++++-
drivers/net/ethernet/intel/igc/igc_main.c | 3 +++
drivers/net/ethernet/intel/igc/igc_xdp.c | 5 +++++
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 ++++++
.../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 1 +
drivers/net/ethernet/marvell/mvneta.c | 3 +++
.../net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++++
.../ethernet/marvell/octeontx2/nic/otx2_pf.c | 8 ++++++--
drivers/net/ethernet/mediatek/mtk_eth_soc.c | 6 ++++++
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 2 ++
.../net/ethernet/mellanox/mlx5/core/en_main.c | 11 +++++++++++
drivers/net/ethernet/microsoft/mana/mana_en.c | 2 ++
.../ethernet/netronome/nfp/nfp_net_common.c | 5 +++++
drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +++
drivers/net/ethernet/sfc/efx.c | 4 ++++
drivers/net/ethernet/sfc/siena/efx.c | 4 ++++
drivers/net/ethernet/socionext/netsec.c | 3 +++
.../net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++
drivers/net/ethernet/ti/cpsw.c | 4 ++++
drivers/net/ethernet/ti/cpsw_new.c | 4 ++++
drivers/net/hyperv/netvsc_drv.c | 2 ++
drivers/net/netdevsim/netdev.c | 1 +
drivers/net/tun.c | 5 +++++
drivers/net/veth.c | 4 ++++
drivers/net/virtio_net.c | 4 ++++
drivers/net/xen-netfront.c | 2 ++
include/net/xdp.h | 12 ++++++++++++
net/core/xdp.c | 18 ++++++++++++++++++
39 files changed, 180 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index e8ad5ea31aff..d3999db7c6a2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf)
if (rc)
return rc;
}
+ xdp_features_set_redirect_target(netdev, false);
} else if (old_bpf_prog) {
+ xdp_features_clear_redirect_target(netdev);
rc = ena_destroy_and_free_all_xdp_queues(adapter);
if (rc)
return rc;
@@ -4103,6 +4105,8 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter,
/* Set offload features */
ena_set_dev_offloads(feat, netdev);
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
adapter->max_mtu = feat->dev_attr.max_mtu;
netdev->max_mtu = adapter->max_mtu;
netdev->min_mtu = ENA_MIN_MTU;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 06508eebb585..d6d6d5d37ff3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -384,6 +384,11 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN;
self->ndev->max_mtu = aq_hw_caps->mtu - ETH_FCS_LEN - ETH_HLEN;
+ self->ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
}
void aq_nic_set_tx_ring(struct aq_nic_s *self, unsigned int idx,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 16ce7a90610c..4fc2846950f8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -13686,6 +13686,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_RX_SG;
+
#ifdef CONFIG_BNXT_SRIOV
init_waitqueue_head(&bp->sriov_cfg_wait);
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 36d5202c0aee..5843c93b1711 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -422,9 +422,11 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
if (prog) {
bnxt_set_rx_skb_mode(bp, true);
+ xdp_features_set_redirect_target(dev, true);
} else {
int rx, tx;
+ xdp_features_clear_redirect_target(dev);
bnxt_set_rx_skb_mode(bp, false);
bnxt_get_max_rings(bp, &rx, &tx, true);
if (rx > 1) {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index f2f95493ec89..8b25313c7f6b 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -2218,6 +2218,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->netdev_ops = &nicvf_netdev_ops;
netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+
/* MTU range: 64 - 9200 */
netdev->min_mtu = NIC_HW_MIN_FRS;
netdev->max_mtu = NIC_HW_MAX_FRS;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 3f8032947d86..63b30b64ba82 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -244,6 +244,10 @@ static int dpaa_netdev_init(struct net_device *net_dev,
net_dev->features |= net_dev->hw_features;
net_dev->vlan_features = net_dev->features;
+ net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (is_valid_ether_addr(mac_addr)) {
memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len);
eth_hw_addr_set(net_dev, mac_addr);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 0c35abb7d065..c4229868a6a8 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -4593,6 +4593,10 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev)
NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO;
net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS;
net_dev->hw_features = net_dev->features;
+ net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY |
+ NETDEV_XDP_ACT_NDO_XMIT;
if (priv->dpni_attrs.vlan_filter_entries)
net_dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 9f6c4f5c0a6c..2036c5bbd3e9 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -825,6 +825,9 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
ndev->hw_features |= NETIF_F_RXHASH;
ndev->priv_flags |= IFF_UNICAST_FLT;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) {
priv->active_offloads |= ENETC_F_QCI;
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c
index b4cce30e526a..df86770731ad 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_main.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c
@@ -1160,6 +1160,11 @@ static int fun_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp)
WRITE_ONCE(rxqs[i]->xdp_prog, prog);
}
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+
dev->max_mtu = prog ? XDP_MAX_MTU : FUN_MAX_MTU;
old_prog = xchg(&fp->xdp_prog, prog);
if (old_prog)
@@ -1765,6 +1770,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid)
netdev->vlan_features = netdev->features & VLAN_FEAT;
netdev->mpls_features = netdev->vlan_features;
netdev->hw_enc_features = netdev->hw_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = FUN_MAX_MTU;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 53d0083e35da..8a79cc18c428 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -13339,9 +13339,11 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
old_prog = xchg(&vsi->xdp_prog, prog);
if (need_reset) {
- if (!prog)
+ if (!prog) {
+ xdp_features_clear_redirect_target(vsi->netdev);
/* Wait until ndo_xsk_wakeup completes. */
synchronize_rcu();
+ }
i40e_reset_and_rebuild(pf, true, true);
}
@@ -13362,11 +13364,13 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog,
/* Kick start the NAPI context if there is an AF_XDP socket open
* on that queue id. This so that receiving will start.
*/
- if (need_reset && prog)
+ if (need_reset && prog) {
for (i = 0; i < vsi->num_queue_pairs; i++)
if (vsi->xdp_rings[i]->xsk_pool)
(void)i40e_xsk_wakeup(vsi->netdev, i,
XDP_WAKEUP_RX);
+ xdp_features_set_redirect_target(vsi->netdev, true);
+ }
return 0;
}
@@ -13783,6 +13787,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID;
netdev->features &= ~NETIF_F_HW_TC;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
if (vsi->type == I40E_VSI_MAIN) {
SET_NETDEV_DEV(netdev, &pf->pdev->dev);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index a9a7f8b52140..45cdb0f19a1e 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -22,6 +22,7 @@
#include "ice_eswitch.h"
#include "ice_tc_lib.h"
#include "ice_vsi_vlan_ops.h"
+#include <net/xdp_sock_drv.h>
#define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver"
static const char ice_driver_string[] = DRV_SUMMARY;
@@ -2899,11 +2900,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
}
+ xdp_features_set_redirect_target(vsi->netdev, false);
/* reallocate Rx queues that are used for zero-copy */
xdp_ring_err = ice_realloc_zc_buf(vsi, true);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
+ xdp_features_clear_redirect_target(vsi->netdev);
xdp_ring_err = ice_destroy_xdp_rings(vsi);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
@@ -3446,6 +3449,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
np->vsi = vsi;
ice_set_netdev_features(netdev);
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
ice_set_ops(netdev);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 3c0c35ecea10..0e11a082f7a1 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2871,8 +2871,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf)
bpf_prog_put(old_prog);
/* bpf is just replaced, RXQ and MTU are already setup */
- if (!need_reset)
+ if (!need_reset) {
return 0;
+ } else {
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+ }
if (running)
igb_open(dev);
@@ -3317,6 +3323,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->priv_flags |= IFF_SUPP_NOFCS;
netdev->priv_flags |= IFF_UNICAST_FLT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
/* MTU range: 68 - 9216 */
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index e86b15efaeb8..8b572cd2c350 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -6533,6 +6533,9 @@ static int igc_probe(struct pci_dev *pdev,
netdev->mpls_features |= NETIF_F_HW_CSUM;
netdev->hw_enc_features |= netdev->vlan_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
/* MTU range: 68 - 9216 */
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index aeeb34e64610..e27af72aada8 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -29,6 +29,11 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
if (old_prog)
bpf_prog_put(old_prog);
+ if (prog)
+ xdp_features_set_redirect_target(dev, true);
+ else
+ xdp_features_clear_redirect_target(dev);
+
if (if_running)
igc_open(dev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ab8370c413f3..d0975c48aee5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10301,6 +10301,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
rcu_assign_pointer(adapter->xdp_prog, old_prog);
return -EINVAL;
}
+ if (!prog)
+ xdp_features_clear_redirect_target(dev);
} else {
for (i = 0; i < adapter->num_rx_queues; i++)
(void)xchg(&adapter->rx_ring[i]->xdp_prog,
@@ -10320,6 +10322,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
if (adapter->xdp_ring[i]->xsk_pool)
(void)ixgbe_xsk_wakeup(adapter->netdev, i,
XDP_WAKEUP_RX);
+ xdp_features_set_redirect_target(dev, true);
}
return 0;
@@ -11017,6 +11020,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
netdev->priv_flags |= IFF_UNICAST_FLT;
netdev->priv_flags |= IFF_SUPP_NOFCS;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY;
+
/* MTU range: 68 - 9710 */
netdev->min_mtu = ETH_MIN_MTU;
netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index ea0a230c1153..a44e4bd56142 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4634,6 +4634,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
NETIF_F_HW_VLAN_CTAG_TX;
netdev->priv_flags |= IFF_UNICAST_FLT;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
/* MTU range: 68 - 1504 or 9710 */
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index f8925cac61e4..dc2989103a77 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5612,6 +5612,9 @@ static int mvneta_probe(struct platform_device *pdev)
NETIF_F_TSO | NETIF_F_RXCSUM;
dev->hw_features |= dev->features;
dev->vlan_features |= dev->features;
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
netif_set_tso_max_segs(dev, MVNETA_MAX_TSO_SEGS);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 4da45c5abba5..9b4ecbe4f36d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -6866,6 +6866,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
dev->vlan_features |= features;
netif_set_tso_max_segs(dev, MVPP2_MAX_TSO_SEGS);
+
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
dev->priv_flags |= IFF_UNICAST_FLT;
/* MTU range: 68 - 9704 */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index c1ea60bc2630..179433d0a54a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2512,10 +2512,13 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
/* Network stack and XDP shared same rx queues.
* Use separate tx queues for XDP and network stack.
*/
- if (pf->xdp_prog)
+ if (pf->xdp_prog) {
pf->hw.xdp_queues = pf->hw.rx_queues;
- else
+ xdp_features_set_redirect_target(dev, false);
+ } else {
pf->hw.xdp_queues = 0;
+ xdp_features_clear_redirect_target(dev);
+ }
pf->hw.tot_tx_queues += pf->hw.xdp_queues;
@@ -2878,6 +2881,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
netdev->watchdog_timeo = OTX2_TX_TIMEOUT;
netdev->netdev_ops = &otx2_netdev_ops;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
netdev->min_mtu = OTX2_MIN_MTU;
netdev->max_mtu = otx2_get_max_mtu(pf);
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index e3de9a53b2d9..7ed5ff18d05b 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4186,6 +4186,12 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
register_netdevice_notifier(&mac->device_notifier);
}
+ if (mtk_page_pool_enabled(eth))
+ eth->netdev[id]->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
+
return 0;
free_netdev:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index af4c4858f397..e11bc0ac880e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3416,6 +3416,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
priv->rss_hash_fn = ETH_RSS_HASH_TOP;
}
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
/* MTU range: 68 - hw-specific max */
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = priv->max_mtu;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 3370c8b9f983..c702d1fae764 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4776,6 +4776,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
if (old_prog)
bpf_prog_put(old_prog);
+ if (reset) {
+ if (prog)
+ xdp_features_set_redirect_target(netdev, true);
+ else
+ xdp_features_clear_redirect_target(netdev);
+ }
+
if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset)
goto unlock;
@@ -5171,6 +5178,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_XSK_ZEROCOPY |
+ NETDEV_XDP_ACT_RX_SG;
+
netdev->priv_flags |= IFF_UNICAST_FLT;
netif_set_tso_max_size(netdev, GSO_MAX_SIZE);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 2f6a048dee90..6120f2b6684f 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -2160,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
ndev->hw_features |= NETIF_F_RXHASH;
ndev->features = ndev->hw_features;
ndev->vlan_features = 0;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
err = register_netdev(ndev);
if (err) {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 18fc9971f1c8..e4825d885560 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2529,10 +2529,15 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
netdev->features &= ~NETIF_F_HW_VLAN_STAG_RX;
nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_RXQINQ;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC;
+ if (nn->app && nn->app->type->id == NFP_APP_BPF_NIC)
+ netdev->xdp_features |= NETDEV_XDP_ACT_HW_OFFLOAD;
+
/* Finalise the netdev setup */
switch (nn->dp.ops->version) {
case NFP_NFD_VER_NFD3:
netdev->netdev_ops = &nfp_nfd3_netdev_ops;
+ netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY;
break;
case NFP_NFD_VER_NFDK:
netdev->netdev_ops = &nfp_nfdk_netdev_ops;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 953f304b8588..b6d999927e86 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -892,6 +892,9 @@ static void qede_init_ndev(struct qede_dev *edev)
ndev->hw_features = hw_features;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
/* MTU range: 46 - 9600 */
ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE;
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 0556542d7a6b..18ff8d8cff42 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1078,6 +1078,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
pci_info(pci_dev, "Solarflare NIC detected\n");
+ efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (!efx->type->is_vf)
efx_probe_vpd_strings(efx);
diff --git a/drivers/net/ethernet/sfc/siena/efx.c b/drivers/net/ethernet/sfc/siena/efx.c
index 60e5b7c8ccf9..a6ef21845224 100644
--- a/drivers/net/ethernet/sfc/siena/efx.c
+++ b/drivers/net/ethernet/sfc/siena/efx.c
@@ -1048,6 +1048,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
pci_info(pci_dev, "Solarflare NIC detected\n");
+ efx->net_dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
if (!efx->type->is_vf)
efx_probe_vpd_strings(efx);
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 9b46579b5a10..2d7347b71c41 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -2104,6 +2104,9 @@ static int netsec_probe(struct platform_device *pdev)
NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
ndev->hw_features = ndev->features;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
priv->rx_cksum_offload_flag = true;
ret = netsec_register_mdio(priv, phy_addr);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c6951c976f5d..9a88cc73259f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7145,6 +7145,8 @@ int stmmac_dvr_probe(struct device *device,
ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXCSUM;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ret = stmmac_tc_init(priv, priv);
if (!ret) {
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 13c9c2d6b79b..37f0b62ec5d6 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1458,6 +1458,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
priv_sl2->emac_port = 1;
cpsw->slaves[1].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
@@ -1635,6 +1637,8 @@ static int cpsw_probe(struct platform_device *pdev)
cpsw->slaves[0].ndev = ndev;
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 83596ec0c7cb..35128dd45ffc 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1405,6 +1405,10 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC;
+ ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
ndev->netdev_ops = &cpsw_netdev_ops;
ndev->ethtool_ops = &cpsw_ethtool_ops;
SET_NETDEV_DEV(ndev, dev);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index f9b219e6cd58..a9b139bbdb2c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2559,6 +2559,8 @@ static int netvsc_probe(struct hv_device *dev,
netdev_lockdep_set_classes(net);
+ net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
+
/* MTU range: 68 - 1500 or 65521 */
net->min_mtu = NETVSC_MTU_MIN;
if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 6db6a75ff9b9..35fa1ca98671 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -286,6 +286,7 @@ static void nsim_setup(struct net_device *dev)
NETIF_F_TSO;
dev->hw_features |= NETIF_F_HW_TC;
dev->max_mtu = ETH_MAX_MTU;
+ dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
}
static int nsim_init_netdevsim(struct netdevsim *ns)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a7d17c680f4a..36620afde373 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1401,6 +1401,11 @@ static void tun_net_initialize(struct net_device *dev)
eth_hw_addr_random(dev);
+ /* Currently tun does not support XDP, only tap does. */
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC |
+ NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
+
break;
}
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ba3e05832843..1bb54de7124d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1686,6 +1686,10 @@ static void veth_setup(struct net_device *dev)
dev->hw_enc_features = VETH_FEATURES;
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG;
}
/*
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7723b2a49d8e..829b652f3309 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3155,7 +3155,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
if (i == 0 && !old_prog)
virtnet_clear_guest_offloads(vi);
}
+ if (!old_prog)
+ xdp_features_set_redirect_target(dev, false);
} else {
+ xdp_features_clear_redirect_target(dev);
vi->xdp_enabled = false;
}
@@ -3785,6 +3788,7 @@ static int virtnet_probe(struct virtio_device *vdev)
dev->hw_features |= NETIF_F_GRO_HW;
dev->vlan_features = dev->features;
+ dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
/* MTU range: 68 - 65535 */
dev->min_mtu = MIN_MTU;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 14aec417fa06..416860c0f204 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1741,6 +1741,8 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev)
* negotiate with the backend regarding supported features.
*/
netdev->features |= netdev->hw_features;
+ netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT;
netdev->ethtool_ops = &xennet_ethtool_ops;
netdev->min_mtu = ETH_MIN_MTU;
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 8d1c86914f4c..d517bfac937b 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -428,9 +428,21 @@ MAX_XDP_METADATA_KFUNC,
#ifdef CONFIG_NET
u32 bpf_xdp_metadata_kfunc_id(int id);
bool bpf_dev_bound_kfunc_id(u32 btf_id);
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg);
+void xdp_features_clear_redirect_target(struct net_device *dev);
#else
static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; }
static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; }
+
+static inline void
+xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+}
+
+static inline void
+xdp_features_clear_redirect_target(struct net_device *dev)
+{
+}
#endif
#endif /* __LINUX_NET_XDP_H__ */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index a5a7ecf6391c..82727b47259d 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
}
late_initcall(xdp_metadata_init);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+ dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
+ if (support_sg)
+ dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
+
+ call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
+
+void xdp_features_clear_redirect_target(struct net_device *dev)
+{
+ dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
+ NETDEV_XDP_ACT_NDO_XMIT_SG);
+ call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-02-27 9:50 ` Shay Agroskin
-1 siblings, 0 replies; 32+ messages in thread
From: Shay Agroskin @ 2023-02-27 9:50 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: bpf, netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet,
hawk, toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Lorenzo Bianconi <lorenzo@kernel.org> writes:
> From: Marek Majtyka <alardam@gmail.com>
>
> ...
>
> diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> index e8ad5ea31aff..d3999db7c6a2 100644
> --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device
> *netdev, struct netdev_bpf *bpf)
> if (rc)
> return rc;
> }
> + xdp_features_set_redirect_target(netdev,
> false);
> } else if (old_bpf_prog) {
> +
> xdp_features_clear_redirect_target(netdev);
> rc =
> ena_destroy_and_free_all_xdp_queues(adapter);
> if (rc)
> return rc;
> @@ -4103,6 +4105,8 @@ static void
> ena_set_conf_feat_params(struct ena_adapter *adapter,
> /* Set offload features */
> ena_set_dev_offloads(feat, netdev);
>
> + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
> NETDEV_XDP_ACT_REDIRECT;
> +
> adapter->max_mtu = feat->dev_attr.max_mtu;
> netdev->max_mtu = adapter->max_mtu;
> netdev->min_mtu = ENA_MIN_MTU;
>
Hi, thanks for the time you put in adjusting the ENA driver as
well.
Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some
drivers (like ENA and mlx5) and statically for others (like
atlantic driver which also redirects packets only when XDP program
is loaded) ?
Is it only for the sake of notifying the user that an XDP program
has been loaded ?
Thanks,
Shay
> ...
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index a5a7ecf6391c..82727b47259d 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
> return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
> &xdp_metadata_kfunc_set);
> }
> late_initcall(xdp_metadata_init);
> +
> +void xdp_features_set_redirect_target(struct net_device *dev,
> bool support_sg)
> +{
> + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
> + if (support_sg)
> + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
> +
> + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> +}
> +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
> +
> +void xdp_features_clear_redirect_target(struct net_device *dev)
> +{
> + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
> + NETDEV_XDP_ACT_NDO_XMIT_SG);
> + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> +}
> +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
@ 2023-02-27 9:50 ` Shay Agroskin
0 siblings, 0 replies; 32+ messages in thread
From: Shay Agroskin @ 2023-02-27 9:50 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn, bpf,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Lorenzo Bianconi <lorenzo@kernel.org> writes:
> From: Marek Majtyka <alardam@gmail.com>
>
> ...
>
> diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> index e8ad5ea31aff..d3999db7c6a2 100644
> --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device
> *netdev, struct netdev_bpf *bpf)
> if (rc)
> return rc;
> }
> + xdp_features_set_redirect_target(netdev,
> false);
> } else if (old_bpf_prog) {
> +
> xdp_features_clear_redirect_target(netdev);
> rc =
> ena_destroy_and_free_all_xdp_queues(adapter);
> if (rc)
> return rc;
> @@ -4103,6 +4105,8 @@ static void
> ena_set_conf_feat_params(struct ena_adapter *adapter,
> /* Set offload features */
> ena_set_dev_offloads(feat, netdev);
>
> + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
> NETDEV_XDP_ACT_REDIRECT;
> +
> adapter->max_mtu = feat->dev_attr.max_mtu;
> netdev->max_mtu = adapter->max_mtu;
> netdev->min_mtu = ENA_MIN_MTU;
>
Hi, thanks for the time you put in adjusting the ENA driver as
well.
Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some
drivers (like ENA and mlx5) and statically for others (like
atlantic driver which also redirects packets only when XDP program
is loaded) ?
Is it only for the sake of notifying the user that an XDP program
has been loaded ?
Thanks,
Shay
> ...
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index a5a7ecf6391c..82727b47259d 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
> return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
> &xdp_metadata_kfunc_set);
> }
> late_initcall(xdp_metadata_init);
> +
> +void xdp_features_set_redirect_target(struct net_device *dev,
> bool support_sg)
> +{
> + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
> + if (support_sg)
> + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
> +
> + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> +}
> +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
> +
> +void xdp_features_clear_redirect_target(struct net_device *dev)
> +{
> + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
> + NETDEV_XDP_ACT_NDO_XMIT_SG);
> + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> +}
> +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
2023-02-27 9:50 ` [Intel-wired-lan] " Shay Agroskin
@ 2023-02-28 22:11 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-02-28 22:11 UTC (permalink / raw)
To: Shay Agroskin
Cc: bpf, netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet,
hawk, toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
[-- Attachment #1: Type: text/plain, Size: 2942 bytes --]
>
> Lorenzo Bianconi <lorenzo@kernel.org> writes:
>
> > From: Marek Majtyka <alardam@gmail.com>
> >
> > ...
> >
> > diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > index e8ad5ea31aff..d3999db7c6a2 100644
> > --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev,
> > struct netdev_bpf *bpf)
> > if (rc)
> > return rc;
> > }
> > + xdp_features_set_redirect_target(netdev, false);
> > } else if (old_bpf_prog) {
> > + xdp_features_clear_redirect_target(netdev);
> > rc = ena_destroy_and_free_all_xdp_queues(adapter);
> > if (rc)
> > return rc;
> > @@ -4103,6 +4105,8 @@ static void ena_set_conf_feat_params(struct
> > ena_adapter *adapter,
> > /* Set offload features */
> > ena_set_dev_offloads(feat, netdev);
> > + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
> > NETDEV_XDP_ACT_REDIRECT;
> > +
> > adapter->max_mtu = feat->dev_attr.max_mtu;
> > netdev->max_mtu = adapter->max_mtu;
> > netdev->min_mtu = ENA_MIN_MTU;
> >
>
> Hi, thanks for the time you put in adjusting the ENA driver as well.
Hi Shay,
>
> Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some drivers (like
> ENA and mlx5) and statically for others (like atlantic driver which also
> redirects packets only when XDP program is loaded) ?
> Is it only for the sake of notifying the user that an XDP program has been
> loaded ?
there are some drivers (e.g. mvneta) where NETDEV_XDP_ACT_NDO_XMIT is always
supported while there are other drivers (e.g. intel drivers) where it
depends on other configurations (e.g. if the driver needs to reserve
some queues for xdp).
Regards,
Lorenzo
>
> Thanks,
> Shay
>
> > ...
> > diff --git a/net/core/xdp.c b/net/core/xdp.c
> > index a5a7ecf6391c..82727b47259d 100644
> > --- a/net/core/xdp.c
> > +++ b/net/core/xdp.c
> > @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
> > return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
> > &xdp_metadata_kfunc_set);
> > }
> > late_initcall(xdp_metadata_init);
> > +
> > +void xdp_features_set_redirect_target(struct net_device *dev, bool
> > support_sg)
> > +{
> > + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
> > + if (support_sg)
> > + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
> > +
> > + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> > +}
> > +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
> > +
> > +void xdp_features_clear_redirect_target(struct net_device *dev)
> > +{
> > + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
> > + NETDEV_XDP_ACT_NDO_XMIT_SG);
> > + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> > +}
> > +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
@ 2023-02-28 22:11 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-02-28 22:11 UTC (permalink / raw)
To: Shay Agroskin
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn, bpf,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
[-- Attachment #1.1: Type: text/plain, Size: 2942 bytes --]
>
> Lorenzo Bianconi <lorenzo@kernel.org> writes:
>
> > From: Marek Majtyka <alardam@gmail.com>
> >
> > ...
> >
> > diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > index e8ad5ea31aff..d3999db7c6a2 100644
> > --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
> > @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev,
> > struct netdev_bpf *bpf)
> > if (rc)
> > return rc;
> > }
> > + xdp_features_set_redirect_target(netdev, false);
> > } else if (old_bpf_prog) {
> > + xdp_features_clear_redirect_target(netdev);
> > rc = ena_destroy_and_free_all_xdp_queues(adapter);
> > if (rc)
> > return rc;
> > @@ -4103,6 +4105,8 @@ static void ena_set_conf_feat_params(struct
> > ena_adapter *adapter,
> > /* Set offload features */
> > ena_set_dev_offloads(feat, netdev);
> > + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
> > NETDEV_XDP_ACT_REDIRECT;
> > +
> > adapter->max_mtu = feat->dev_attr.max_mtu;
> > netdev->max_mtu = adapter->max_mtu;
> > netdev->min_mtu = ENA_MIN_MTU;
> >
>
> Hi, thanks for the time you put in adjusting the ENA driver as well.
Hi Shay,
>
> Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some drivers (like
> ENA and mlx5) and statically for others (like atlantic driver which also
> redirects packets only when XDP program is loaded) ?
> Is it only for the sake of notifying the user that an XDP program has been
> loaded ?
there are some drivers (e.g. mvneta) where NETDEV_XDP_ACT_NDO_XMIT is always
supported while there are other drivers (e.g. intel drivers) where it
depends on other configurations (e.g. if the driver needs to reserve
some queues for xdp).
Regards,
Lorenzo
>
> Thanks,
> Shay
>
> > ...
> > diff --git a/net/core/xdp.c b/net/core/xdp.c
> > index a5a7ecf6391c..82727b47259d 100644
> > --- a/net/core/xdp.c
> > +++ b/net/core/xdp.c
> > @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void)
> > return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP,
> > &xdp_metadata_kfunc_set);
> > }
> > late_initcall(xdp_metadata_init);
> > +
> > +void xdp_features_set_redirect_target(struct net_device *dev, bool
> > support_sg)
> > +{
> > + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
> > + if (support_sg)
> > + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
> > +
> > + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> > +}
> > +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
> > +
> > +void xdp_features_clear_redirect_target(struct net_device *dev)
> > +{
> > + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
> > + NETDEV_XDP_ACT_NDO_XMIT_SG);
> > + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
> > +}
> > +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);
>
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
[-- Attachment #2: Type: text/plain, Size: 162 bytes --]
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
2023-02-28 22:11 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-03-02 13:44 ` Shay Agroskin
-1 siblings, 0 replies; 32+ messages in thread
From: Shay Agroskin @ 2023-03-02 13:44 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: bpf, netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet,
hawk, toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Lorenzo Bianconi <lorenzo@kernel.org> writes:
> [[PGP Signed Part:Undecided]]
>>
>> Lorenzo Bianconi <lorenzo@kernel.org> writes:
>>
>> > From: Marek Majtyka <alardam@gmail.com>
>> >
>> > ...
>> >
>> > diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > b/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > index e8ad5ea31aff..d3999db7c6a2 100644
>> > --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device
>> > *netdev,
>> > struct netdev_bpf *bpf)
>> > if (rc)
>> > return rc;
>> > }
>> > + xdp_features_set_redirect_target(netdev,
>> > false);
>> > } else if (old_bpf_prog) {
>> > + xdp_features_clear_redirect_target(netdev);
>> > rc =
>> > ena_destroy_and_free_all_xdp_queues(adapter);
>> > if (rc)
>> > return rc;
>> > @@ -4103,6 +4105,8 @@ static void
>> > ena_set_conf_feat_params(struct
>> > ena_adapter *adapter,
>> > /* Set offload features */
>> > ena_set_dev_offloads(feat, netdev);
>> > + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
>> > NETDEV_XDP_ACT_REDIRECT;
>> > +
>> > adapter->max_mtu = feat->dev_attr.max_mtu;
>> > netdev->max_mtu = adapter->max_mtu;
>> > netdev->min_mtu = ENA_MIN_MTU;
>> >
>>
>> Hi, thanks for the time you put in adjusting the ENA driver as
>> well.
>
> Hi Shay,
>
>>
>> Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some
>> drivers (like
>> ENA and mlx5) and statically for others (like atlantic driver
>> which also
>> redirects packets only when XDP program is loaded) ?
>> Is it only for the sake of notifying the user that an XDP
>> program has been
>> loaded ?
>
> there are some drivers (e.g. mvneta) where
> NETDEV_XDP_ACT_NDO_XMIT is always
> supported while there are other drivers (e.g. intel drivers)
> where it
> depends on other configurations (e.g. if the driver needs to
> reserve
> some queues for xdp).
>
> Regards,
> Lorenzo
>
Well given that ENA's ability to redirect packets goes hand in
hand with its ability to process any XDP traffic I'd say it always
supports ndo_xmit.
Doesn't seem like a big issue though.
Thanks for the explanation,
Shay
>
> [[End of PGP Signed Part]]
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 2/8] drivers: net: turn on XDP features
@ 2023-03-02 13:44 ` Shay Agroskin
0 siblings, 0 replies; 32+ messages in thread
From: Shay Agroskin @ 2023-03-02 13:44 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn, bpf,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Lorenzo Bianconi <lorenzo@kernel.org> writes:
> [[PGP Signed Part:Undecided]]
>>
>> Lorenzo Bianconi <lorenzo@kernel.org> writes:
>>
>> > From: Marek Majtyka <alardam@gmail.com>
>> >
>> > ...
>> >
>> > diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > b/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > index e8ad5ea31aff..d3999db7c6a2 100644
>> > --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
>> > @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device
>> > *netdev,
>> > struct netdev_bpf *bpf)
>> > if (rc)
>> > return rc;
>> > }
>> > + xdp_features_set_redirect_target(netdev,
>> > false);
>> > } else if (old_bpf_prog) {
>> > + xdp_features_clear_redirect_target(netdev);
>> > rc =
>> > ena_destroy_and_free_all_xdp_queues(adapter);
>> > if (rc)
>> > return rc;
>> > @@ -4103,6 +4105,8 @@ static void
>> > ena_set_conf_feat_params(struct
>> > ena_adapter *adapter,
>> > /* Set offload features */
>> > ena_set_dev_offloads(feat, netdev);
>> > + netdev->xdp_features = NETDEV_XDP_ACT_BASIC |
>> > NETDEV_XDP_ACT_REDIRECT;
>> > +
>> > adapter->max_mtu = feat->dev_attr.max_mtu;
>> > netdev->max_mtu = adapter->max_mtu;
>> > netdev->min_mtu = ENA_MIN_MTU;
>> >
>>
>> Hi, thanks for the time you put in adjusting the ENA driver as
>> well.
>
> Hi Shay,
>
>>
>> Why did you set NETDEV_XDP_ACT_NDO_XMIT dynamically for some
>> drivers (like
>> ENA and mlx5) and statically for others (like atlantic driver
>> which also
>> redirects packets only when XDP program is loaded) ?
>> Is it only for the sake of notifying the user that an XDP
>> program has been
>> loaded ?
>
> there are some drivers (e.g. mvneta) where
> NETDEV_XDP_ACT_NDO_XMIT is always
> supported while there are other drivers (e.g. intel drivers)
> where it
> depends on other configurations (e.g. if the driver needs to
> reserve
> some queues for xdp).
>
> Regards,
> Lorenzo
>
Well given that ENA's ability to redirect packets goes hand in
hand with its ability to process any XDP traffic I'd say it always
supports ndo_xmit.
Doesn't seem like a big issue though.
Thanks for the explanation,
Shay
>
> [[End of PGP Signed Part]]
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread
* [PATCH v4 bpf-next 3/8] xsk: add usage of XDP features flags
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
From: Marek Majtyka <alardam@gmail.com>
Change necessary condition check for XSK from ndo functions to
xdp features flags.
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
net/xdp/xsk_buff_pool.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index ed6c71826d31..b2df1e0f8153 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -140,6 +140,10 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
}
}
+#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \
+ NETDEV_XDP_ACT_REDIRECT | \
+ NETDEV_XDP_ACT_XSK_ZEROCOPY)
+
int xp_assign_dev(struct xsk_buff_pool *pool,
struct net_device *netdev, u16 queue_id, u16 flags)
{
@@ -178,8 +182,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
/* For copy-mode, we are done. */
return 0;
- if (!netdev->netdev_ops->ndo_bpf ||
- !netdev->netdev_ops->ndo_xsk_wakeup) {
+ if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) {
err = -EOPNOTSUPP;
goto err_unreg_pool;
}
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 3/8] xsk: add usage of XDP features flags
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
From: Marek Majtyka <alardam@gmail.com>
Change necessary condition check for XSK from ndo functions to
xdp features flags.
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
net/xdp/xsk_buff_pool.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index ed6c71826d31..b2df1e0f8153 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -140,6 +140,10 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
}
}
+#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \
+ NETDEV_XDP_ACT_REDIRECT | \
+ NETDEV_XDP_ACT_XSK_ZEROCOPY)
+
int xp_assign_dev(struct xsk_buff_pool *pool,
struct net_device *netdev, u16 queue_id, u16 flags)
{
@@ -178,8 +182,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
/* For copy-mode, we are done. */
return 0;
- if (!netdev->netdev_ops->ndo_bpf ||
- !netdev->netdev_ops->ndo_xsk_wakeup) {
+ if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) {
err = -EOPNOTSUPP;
goto err_unreg_pool;
}
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v4 bpf-next 4/8] libbpf: add the capability to specify netlink proto in libbpf_netlink_send_recv
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
This is a preliminary patch in order to introduce netlink_generic
protocol support to libbpf.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/lib/bpf/netlink.c | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 35104580870c..d2468a04a6c3 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -41,7 +41,7 @@ struct xdp_id_md {
struct xdp_link_info info;
};
-static int libbpf_netlink_open(__u32 *nl_pid)
+static int libbpf_netlink_open(__u32 *nl_pid, int proto)
{
struct sockaddr_nl sa;
socklen_t addrlen;
@@ -51,7 +51,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
- sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
+ sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto);
if (sock < 0)
return -errno;
@@ -212,14 +212,14 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
}
static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
- __dump_nlmsg_t parse_msg,
+ int proto, __dump_nlmsg_t parse_msg,
libbpf_dump_nlmsg_t parse_attr,
void *cookie)
{
__u32 nl_pid = 0;
int sock, ret;
- sock = libbpf_netlink_open(&nl_pid);
+ sock = libbpf_netlink_open(&nl_pid, proto);
if (sock < 0)
return sock;
@@ -271,7 +271,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
}
nlattr_end_nested(&req, nla);
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
@@ -382,7 +382,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
xdp_id.ifindex = ifindex;
xdp_id.flags = xdp_flags;
- err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+ err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg,
get_xdp_info, &xdp_id);
if (err)
return libbpf_err(err);
@@ -493,7 +493,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
if (ret < 0)
return ret;
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
@@ -673,7 +673,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
@@ -739,7 +740,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
return ret;
}
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_tc_detach(const struct bpf_tc_hook *hook,
@@ -804,7 +805,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 4/8] libbpf: add the capability to specify netlink proto in libbpf_netlink_send_recv
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
This is a preliminary patch in order to introduce netlink_generic
protocol support to libbpf.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/lib/bpf/netlink.c | 22 ++++++++++++----------
1 file changed, 12 insertions(+), 10 deletions(-)
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 35104580870c..d2468a04a6c3 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -41,7 +41,7 @@ struct xdp_id_md {
struct xdp_link_info info;
};
-static int libbpf_netlink_open(__u32 *nl_pid)
+static int libbpf_netlink_open(__u32 *nl_pid, int proto)
{
struct sockaddr_nl sa;
socklen_t addrlen;
@@ -51,7 +51,7 @@ static int libbpf_netlink_open(__u32 *nl_pid)
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
- sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
+ sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto);
if (sock < 0)
return -errno;
@@ -212,14 +212,14 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
}
static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
- __dump_nlmsg_t parse_msg,
+ int proto, __dump_nlmsg_t parse_msg,
libbpf_dump_nlmsg_t parse_attr,
void *cookie)
{
__u32 nl_pid = 0;
int sock, ret;
- sock = libbpf_netlink_open(&nl_pid);
+ sock = libbpf_netlink_open(&nl_pid, proto);
if (sock < 0)
return sock;
@@ -271,7 +271,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
}
nlattr_end_nested(&req, nla);
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts)
@@ -382,7 +382,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
xdp_id.ifindex = ifindex;
xdp_id.flags = xdp_flags;
- err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg,
+ err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg,
get_xdp_info, &xdp_id);
if (err)
return libbpf_err(err);
@@ -493,7 +493,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags)
if (ret < 0)
return ret;
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
static int tc_qdisc_create_excl(struct bpf_tc_hook *hook)
@@ -673,7 +673,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
@@ -739,7 +740,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook,
return ret;
}
- return libbpf_netlink_send_recv(&req, NULL, NULL, NULL);
+ return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL);
}
int bpf_tc_detach(const struct bpf_tc_hook *hook,
@@ -804,7 +805,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts)
info.opts = opts;
- ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info);
+ ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL,
+ &info);
if (ret < 0)
return libbpf_err(ret);
if (!info.processed)
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v4 bpf-next 5/8] libbpf: add API to get XDP/XSK supported features
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Extend bpf_xdp_query routine in order to get XDP/XSK supported features
of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic
protocol.
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/lib/bpf/libbpf.h | 3 +-
tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/nlattr.h | 12 ++++++
3 files changed, 110 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 8777ff21ea1d..b18581277eb2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1048,9 +1048,10 @@ struct bpf_xdp_query_opts {
__u32 hw_prog_id; /* output */
__u32 skb_prog_id; /* output */
__u8 attach_mode; /* output */
+ __u64 feature_flags; /* output */
size_t :0;
};
-#define bpf_xdp_query_opts__last_field attach_mode
+#define bpf_xdp_query_opts__last_field feature_flags
LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
const struct bpf_xdp_attach_opts *opts);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index d2468a04a6c3..32b13b7a11b0 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -9,6 +9,7 @@
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
#include <linux/rtnetlink.h>
+#include <linux/netdev.h>
#include <sys/socket.h>
#include <errno.h>
#include <time.h>
@@ -39,6 +40,12 @@ struct xdp_id_md {
int ifindex;
__u32 flags;
struct xdp_link_info info;
+ __u64 feature_flags;
+};
+
+struct xdp_features_md {
+ int ifindex;
+ __u64 flags;
};
static int libbpf_netlink_open(__u32 *nl_pid, int proto)
@@ -238,6 +245,43 @@ static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
return ret;
}
+static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1];
+ __u16 *id = cookie;
+
+ libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+ if (!tb[CTRL_ATTR_FAMILY_ID])
+ return NL_CONT;
+
+ *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+ return NL_DONE;
+}
+
+static int libbpf_netlink_resolve_genl_family_id(const char *name,
+ __u16 len, __u16 *id)
+{
+ struct libbpf_nla_req req = {
+ .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN),
+ .nh.nlmsg_type = GENL_ID_CTRL,
+ .nh.nlmsg_flags = NLM_F_REQUEST,
+ .gnl.cmd = CTRL_CMD_GETFAMILY,
+ .gnl.version = 2,
+ };
+ int err;
+
+ err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len);
+ if (err < 0)
+ return err;
+
+ return libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_genl_family_id, NULL, id);
+}
+
static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
__u32 flags)
{
@@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
return 0;
}
+static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[NETDEV_CMD_MAX + 1];
+ struct xdp_features_md *md = cookie;
+ __u32 ifindex;
+
+ libbpf_nla_parse(tb, NETDEV_CMD_MAX, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+
+ if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES])
+ return NL_CONT;
+
+ ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]);
+ if (ifindex != md->ifindex)
+ return NL_CONT;
+
+ md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
+ return NL_DONE;
+}
+
int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
{
struct libbpf_nla_req req = {
@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
.ifinfo.ifi_family = AF_PACKET,
};
struct xdp_id_md xdp_id = {};
+ struct xdp_features_md md = {
+ .ifindex = ifindex,
+ };
+ __u16 id;
int err;
if (!OPTS_VALID(opts, bpf_xdp_query_opts))
@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
+ if (!OPTS_HAS(opts, feature_flags))
+ return 0;
+
+ err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+ if (err < 0)
+ return libbpf_err(err);
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = id;
+ req.gnl.cmd = NETDEV_CMD_DEV_GET;
+ req.gnl.version = 2;
+
+ err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+ if (err < 0)
+ return err;
+
+ err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_xdp_features, NULL, &md);
+ if (err)
+ return libbpf_err(err);
+
+ opts->feature_flags = md.flags;
+
return 0;
}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 4d15ae2ff812..d92d1c1de700 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -14,6 +14,7 @@
#include <errno.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
+#include <linux/genetlink.h>
/* avoid multiple definition of netlink features */
#define __LINUX_NETLINK_H
@@ -58,6 +59,7 @@ struct libbpf_nla_req {
union {
struct ifinfomsg ifinfo;
struct tcmsg tc;
+ struct genlmsghdr gnl;
};
char buf[128];
};
@@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
return *(uint8_t *)libbpf_nla_data(nla);
}
+static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla)
+{
+ return *(uint16_t *)libbpf_nla_data(nla);
+}
+
static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
{
return *(uint32_t *)libbpf_nla_data(nla);
}
+static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla)
+{
+ return *(uint64_t *)libbpf_nla_data(nla);
+}
+
static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
{
return (const char *)libbpf_nla_data(nla);
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 5/8] libbpf: add API to get XDP/XSK supported features
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Extend bpf_xdp_query routine in order to get XDP/XSK supported features
of netdev over route netlink interface.
Extend libbpf netlink implementation in order to support netlink_generic
protocol.
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Co-developed-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Marek Majtyka <alardam@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/lib/bpf/libbpf.h | 3 +-
tools/lib/bpf/netlink.c | 96 +++++++++++++++++++++++++++++++++++++++++
tools/lib/bpf/nlattr.h | 12 ++++++
3 files changed, 110 insertions(+), 1 deletion(-)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 8777ff21ea1d..b18581277eb2 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -1048,9 +1048,10 @@ struct bpf_xdp_query_opts {
__u32 hw_prog_id; /* output */
__u32 skb_prog_id; /* output */
__u8 attach_mode; /* output */
+ __u64 feature_flags; /* output */
size_t :0;
};
-#define bpf_xdp_query_opts__last_field attach_mode
+#define bpf_xdp_query_opts__last_field feature_flags
LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags,
const struct bpf_xdp_attach_opts *opts);
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index d2468a04a6c3..32b13b7a11b0 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -9,6 +9,7 @@
#include <linux/if_ether.h>
#include <linux/pkt_cls.h>
#include <linux/rtnetlink.h>
+#include <linux/netdev.h>
#include <sys/socket.h>
#include <errno.h>
#include <time.h>
@@ -39,6 +40,12 @@ struct xdp_id_md {
int ifindex;
__u32 flags;
struct xdp_link_info info;
+ __u64 feature_flags;
+};
+
+struct xdp_features_md {
+ int ifindex;
+ __u64 flags;
};
static int libbpf_netlink_open(__u32 *nl_pid, int proto)
@@ -238,6 +245,43 @@ static int libbpf_netlink_send_recv(struct libbpf_nla_req *req,
return ret;
}
+static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1];
+ __u16 *id = cookie;
+
+ libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+ if (!tb[CTRL_ATTR_FAMILY_ID])
+ return NL_CONT;
+
+ *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]);
+ return NL_DONE;
+}
+
+static int libbpf_netlink_resolve_genl_family_id(const char *name,
+ __u16 len, __u16 *id)
+{
+ struct libbpf_nla_req req = {
+ .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN),
+ .nh.nlmsg_type = GENL_ID_CTRL,
+ .nh.nlmsg_flags = NLM_F_REQUEST,
+ .gnl.cmd = CTRL_CMD_GETFAMILY,
+ .gnl.version = 2,
+ };
+ int err;
+
+ err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len);
+ if (err < 0)
+ return err;
+
+ return libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_genl_family_id, NULL, id);
+}
+
static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd,
__u32 flags)
{
@@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb)
return 0;
}
+static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn,
+ void *cookie)
+{
+ struct genlmsghdr *gnl = NLMSG_DATA(nh);
+ struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN);
+ struct nlattr *tb[NETDEV_CMD_MAX + 1];
+ struct xdp_features_md *md = cookie;
+ __u32 ifindex;
+
+ libbpf_nla_parse(tb, NETDEV_CMD_MAX, na,
+ NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL);
+
+ if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES])
+ return NL_CONT;
+
+ ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]);
+ if (ifindex != md->ifindex)
+ return NL_CONT;
+
+ md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]);
+ return NL_DONE;
+}
+
int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
{
struct libbpf_nla_req req = {
@@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
.ifinfo.ifi_family = AF_PACKET,
};
struct xdp_id_md xdp_id = {};
+ struct xdp_features_md md = {
+ .ifindex = ifindex,
+ };
+ __u16 id;
int err;
if (!OPTS_VALID(opts, bpf_xdp_query_opts))
@@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts)
OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id);
OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode);
+ if (!OPTS_HAS(opts, feature_flags))
+ return 0;
+
+ err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id);
+ if (err < 0)
+ return libbpf_err(err);
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN);
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_type = id;
+ req.gnl.cmd = NETDEV_CMD_DEV_GET;
+ req.gnl.version = 2;
+
+ err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex));
+ if (err < 0)
+ return err;
+
+ err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC,
+ parse_xdp_features, NULL, &md);
+ if (err)
+ return libbpf_err(err);
+
+ opts->feature_flags = md.flags;
+
return 0;
}
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 4d15ae2ff812..d92d1c1de700 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -14,6 +14,7 @@
#include <errno.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
+#include <linux/genetlink.h>
/* avoid multiple definition of netlink features */
#define __LINUX_NETLINK_H
@@ -58,6 +59,7 @@ struct libbpf_nla_req {
union {
struct ifinfomsg ifinfo;
struct tcmsg tc;
+ struct genlmsghdr gnl;
};
char buf[128];
};
@@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla)
return *(uint8_t *)libbpf_nla_data(nla);
}
+static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla)
+{
+ return *(uint16_t *)libbpf_nla_data(nla);
+}
+
static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla)
{
return *(uint32_t *)libbpf_nla_data(nla);
}
+static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla)
+{
+ return *(uint64_t *)libbpf_nla_data(nla);
+}
+
static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla)
{
return (const char *)libbpf_nla_data(nla);
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [Intel-wired-lan] [PATCH v4 bpf-next 6/8] bpf: devmap: check XDP features in __xdp_enqueue routine
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Check if the destination device implements ndo_xdp_xmit callback relying
on NETDEV_XDP_ACT_NDO_XMIT flags. Moreover, check if the destination device
supports XDP non-linear frame in __xdp_enqueue and is_valid_dst routines.
This patch allows to perform XDP_REDIRECT on non-linear XDP buffers.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
kernel/bpf/devmap.c | 16 +++++++++++++---
net/core/filter.c | 13 +++++--------
2 files changed, 18 insertions(+), 11 deletions(-)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d01e4c55b376..2675fefc6cb6 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -474,7 +474,11 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
{
int err;
- if (!dev->netdev_ops->ndo_xdp_xmit)
+ if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+ return -EOPNOTSUPP;
+
+ if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+ xdp_frame_has_frags(xdpf)))
return -EOPNOTSUPP;
err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf));
@@ -532,8 +536,14 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf)
{
- if (!obj ||
- !obj->dev->netdev_ops->ndo_xdp_xmit)
+ if (!obj)
+ return false;
+
+ if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+ return false;
+
+ if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+ xdp_frame_has_frags(xdpf)))
return false;
if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf)))
diff --git a/net/core/filter.c b/net/core/filter.c
index 6da78b3d381e..d18f57ef7352 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4314,16 +4314,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
enum bpf_map_type map_type = ri->map_type;
- /* XDP_REDIRECT is not fully supported yet for xdp frags since
- * not all XDP capable drivers can map non-linear xdp_frame in
- * ndo_xdp_xmit.
- */
- if (unlikely(xdp_buff_has_frags(xdp) &&
- map_type != BPF_MAP_TYPE_CPUMAP))
- return -EOPNOTSUPP;
+ if (map_type == BPF_MAP_TYPE_XSKMAP) {
+ /* XDP_REDIRECT is not supported AF_XDP yet. */
+ if (unlikely(xdp_buff_has_frags(xdp)))
+ return -EOPNOTSUPP;
- if (map_type == BPF_MAP_TYPE_XSKMAP)
return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
+ }
return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
xdp_prog);
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v4 bpf-next 6/8] bpf: devmap: check XDP features in __xdp_enqueue routine
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Check if the destination device implements ndo_xdp_xmit callback relying
on NETDEV_XDP_ACT_NDO_XMIT flags. Moreover, check if the destination device
supports XDP non-linear frame in __xdp_enqueue and is_valid_dst routines.
This patch allows to perform XDP_REDIRECT on non-linear XDP buffers.
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
kernel/bpf/devmap.c | 16 +++++++++++++---
net/core/filter.c | 13 +++++--------
2 files changed, 18 insertions(+), 11 deletions(-)
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d01e4c55b376..2675fefc6cb6 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -474,7 +474,11 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
{
int err;
- if (!dev->netdev_ops->ndo_xdp_xmit)
+ if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+ return -EOPNOTSUPP;
+
+ if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+ xdp_frame_has_frags(xdpf)))
return -EOPNOTSUPP;
err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf));
@@ -532,8 +536,14 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf)
{
- if (!obj ||
- !obj->dev->netdev_ops->ndo_xdp_xmit)
+ if (!obj)
+ return false;
+
+ if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT))
+ return false;
+
+ if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) &&
+ xdp_frame_has_frags(xdpf)))
return false;
if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf)))
diff --git a/net/core/filter.c b/net/core/filter.c
index 6da78b3d381e..d18f57ef7352 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4314,16 +4314,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
enum bpf_map_type map_type = ri->map_type;
- /* XDP_REDIRECT is not fully supported yet for xdp frags since
- * not all XDP capable drivers can map non-linear xdp_frame in
- * ndo_xdp_xmit.
- */
- if (unlikely(xdp_buff_has_frags(xdp) &&
- map_type != BPF_MAP_TYPE_CPUMAP))
- return -EOPNOTSUPP;
+ if (map_type == BPF_MAP_TYPE_XSKMAP) {
+ /* XDP_REDIRECT is not supported AF_XDP yet. */
+ if (unlikely(xdp_buff_has_frags(xdp)))
+ return -EOPNOTSUPP;
- if (map_type == BPF_MAP_TYPE_XSKMAP)
return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
+ }
return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
xdp_prog);
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [Intel-wired-lan] [PATCH v4 bpf-next 7/8] selftests/bpf: add test for bpf_xdp_query xdp-features support
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Introduce a self-test to verify libbpf bpf_xdp_query capability to dump
the xdp-features supported by the device (lo and veth in this case).
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
.../bpf/prog_tests/xdp_do_redirect.c | 27 ++++++++++++++++++-
.../selftests/bpf/prog_tests/xdp_info.c | 8 ++++++
2 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index a50971c6cf4a..b7a3e476f619 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -4,10 +4,12 @@
#include <net/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
+#include <linux/if_link.h>
#include <linux/ipv6.h>
#include <linux/in6.h>
#include <linux/udp.h>
#include <bpf/bpf_endian.h>
+#include <uapi/linux/netdev.h>
#include "test_xdp_do_redirect.skel.h"
#define SYS(fmt, ...) \
@@ -92,7 +94,7 @@ void test_xdp_do_redirect(void)
struct test_xdp_do_redirect *skel = NULL;
struct nstoken *nstoken = NULL;
struct bpf_link *link;
-
+ LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
struct xdp_md ctx_in = { .data = sizeof(__u32),
.data_end = sizeof(data) };
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -153,6 +155,29 @@ void test_xdp_do_redirect(void)
!ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst"))
goto out;
+ /* Check xdp features supported by veth driver */
+ err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts);
+ if (!ASSERT_OK(err, "veth_src bpf_xdp_query"))
+ goto out;
+
+ if (!ASSERT_EQ(query_opts.feature_flags,
+ NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG,
+ "veth_src query_opts.feature_flags"))
+ goto out;
+
+ err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts);
+ if (!ASSERT_OK(err, "veth_dst bpf_xdp_query"))
+ goto out;
+
+ if (!ASSERT_EQ(query_opts.feature_flags,
+ NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG,
+ "veth_dst query_opts.feature_flags"))
+ goto out;
+
memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN);
skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */
skel->rodata->ifindex_in = ifindex_src;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
index cd3aa340e65e..286c21ecdc65 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -8,6 +8,7 @@ void serial_test_xdp_info(void)
{
__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
const char *file = "./xdp_dummy.bpf.o";
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
struct bpf_prog_info info = {};
struct bpf_object *obj;
int err, prog_fd;
@@ -61,6 +62,13 @@ void serial_test_xdp_info(void)
if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id))
goto out;
+ /* Check xdp features supported by lo device */
+ opts.feature_flags = ~0;
+ err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts);
+ if (!ASSERT_OK(err, "bpf_xdp_query"))
+ goto out;
+
+ ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags");
out:
bpf_xdp_detach(IFINDEX_LO, 0, NULL);
out_close:
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread* [PATCH v4 bpf-next 7/8] selftests/bpf: add test for bpf_xdp_query xdp-features support
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Introduce a self-test to verify libbpf bpf_xdp_query capability to dump
the xdp-features supported by the device (lo and veth in this case).
Acked-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
.../bpf/prog_tests/xdp_do_redirect.c | 27 ++++++++++++++++++-
.../selftests/bpf/prog_tests/xdp_info.c | 8 ++++++
2 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index a50971c6cf4a..b7a3e476f619 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -4,10 +4,12 @@
#include <net/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
+#include <linux/if_link.h>
#include <linux/ipv6.h>
#include <linux/in6.h>
#include <linux/udp.h>
#include <bpf/bpf_endian.h>
+#include <uapi/linux/netdev.h>
#include "test_xdp_do_redirect.skel.h"
#define SYS(fmt, ...) \
@@ -92,7 +94,7 @@ void test_xdp_do_redirect(void)
struct test_xdp_do_redirect *skel = NULL;
struct nstoken *nstoken = NULL;
struct bpf_link *link;
-
+ LIBBPF_OPTS(bpf_xdp_query_opts, query_opts);
struct xdp_md ctx_in = { .data = sizeof(__u32),
.data_end = sizeof(data) };
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
@@ -153,6 +155,29 @@ void test_xdp_do_redirect(void)
!ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst"))
goto out;
+ /* Check xdp features supported by veth driver */
+ err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts);
+ if (!ASSERT_OK(err, "veth_src bpf_xdp_query"))
+ goto out;
+
+ if (!ASSERT_EQ(query_opts.feature_flags,
+ NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG,
+ "veth_src query_opts.feature_flags"))
+ goto out;
+
+ err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts);
+ if (!ASSERT_OK(err, "veth_dst bpf_xdp_query"))
+ goto out;
+
+ if (!ASSERT_EQ(query_opts.feature_flags,
+ NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+ NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG |
+ NETDEV_XDP_ACT_NDO_XMIT_SG,
+ "veth_dst query_opts.feature_flags"))
+ goto out;
+
memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN);
skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */
skel->rodata->ifindex_in = ifindex_src;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
index cd3aa340e65e..286c21ecdc65 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -8,6 +8,7 @@ void serial_test_xdp_info(void)
{
__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
const char *file = "./xdp_dummy.bpf.o";
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
struct bpf_prog_info info = {};
struct bpf_object *obj;
int err, prog_fd;
@@ -61,6 +62,13 @@ void serial_test_xdp_info(void)
if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id))
goto out;
+ /* Check xdp features supported by lo device */
+ opts.feature_flags = ~0;
+ err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts);
+ if (!ASSERT_OK(err, "bpf_xdp_query"))
+ goto out;
+
+ ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags");
out:
bpf_xdp_detach(IFINDEX_LO, 0, NULL);
out_close:
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread
* [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 14:06 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet, hawk,
toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau, sdf
Introduce xdp_features tool in order to test XDP features supported by
the NIC and match them against advertised ones.
In order to test supported/advertised XDP features, xdp_features must
run on the Device Under Test (DUT) and on a Tester device.
xdp_features opens a control TCP channel between DUT and Tester devices
to send control commands from Tester to the DUT and a UDP data channel
where the Tester sends UDP 'echo' packets and the DUT is expected to
reply back with the same packet. DUT installs multiple XDP programs on the
NIC to test XDP capabilities and reports back to the Tester some XDP stats.
Currently xdp_features supports the following XDP features:
- XDP_DROP
- XDP_PASS
- XDP_TX
- XDP_REDIRECT
- XDP_REDIRECT_TARGET
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 11 +-
.../selftests/bpf/progs/xdp_features.c | 275 +++++++
.../selftests/bpf/test_xdp_features.sh | 100 +++
tools/testing/selftests/bpf/xdp_features.c | 731 ++++++++++++++++++
tools/testing/selftests/bpf/xdp_features.h | 33 +
6 files changed, 1149 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh
create mode 100644 tools/testing/selftests/bpf/xdp_features.c
create mode 100644 tools/testing/selftests/bpf/xdp_features.h
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 4aa5bba956ff..116fecf80ca1 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -48,3 +48,4 @@ xskxceiver
xdp_redirect_multi
xdp_synproxy
xdp_hw_metadata
+xdp_features
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 53eae7be8dff..6f06b03d93cd 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -73,7 +73,8 @@ TEST_PROGS := test_kmod.sh \
test_bpftool.sh \
test_bpftool_metadata.sh \
test_doc_build.sh \
- test_xsk.sh
+ test_xsk.sh \
+ test_xdp_features.sh
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
@@ -83,7 +84,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
+ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
+ xdp_features
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
TEST_GEN_FILES += liburandom_read.so
@@ -385,6 +387,7 @@ test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton
test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
+xdp_features.skel.h-deps := xdp_features.bpf.o
LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
@@ -586,6 +589,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPU
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c
new file mode 100644
index 000000000000..205a4526ea68
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_features.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/netdev.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/udp.h>
+#include <asm-generic/errno-base.h>
+
+#include "xdp_features.h"
+
+#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \
+ (a).s6_addr32[1] == (b).s6_addr32[1] && \
+ (a).s6_addr32[2] == (b).s6_addr32[2] && \
+ (a).s6_addr32[3] == (b).s6_addr32[3])
+
+struct net_device;
+struct bpf_prog;
+
+struct xdp_cpumap_stats {
+ unsigned int redirect;
+ unsigned int pass;
+ unsigned int drop;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} stats SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} dut_stats SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CPUMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_cpumap_val));
+ __uint(max_entries, 1);
+} cpu_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 1);
+} dev_map SEC(".maps");
+
+const volatile __u32 expected_feature = XDP_FEATURE_PASS;
+const volatile union {
+ struct in_addr ip;
+ struct in6_addr ip6;
+} tester_addr;
+const volatile union {
+ struct in_addr ip;
+ struct in6_addr ip6;
+} dut_addr;
+
+static __always_inline int xdp_process_echo_packet(struct xdp_md *xdp, bool dut)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ struct tlv_hdr *tlv;
+ struct udphdr *uh;
+ __be16 port;
+ __u8 *cmd;
+
+ if (eh + 1 > (struct ethhdr *)data_end)
+ return -EINVAL;
+
+ if (eh->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *ih = (struct iphdr *)(eh + 1);
+ __be32 saddr = dut ? tester_addr.ip.s_addr : dut_addr.ip.s_addr;
+ __be32 daddr = dut ? dut_addr.ip.s_addr : tester_addr.ip.s_addr;
+
+ ih = (struct iphdr *)(eh + 1);
+ if (ih + 1 > (struct iphdr *)data_end)
+ return -EINVAL;
+
+ if (saddr != ih->saddr)
+ return -EINVAL;
+
+ if (daddr != ih->daddr)
+ return -EINVAL;
+
+ if (ih->protocol != IPPROTO_UDP)
+ return -EINVAL;
+
+ uh = (struct udphdr *)(ih + 1);
+ } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct in6_addr saddr = dut ? tester_addr.ip6 : dut_addr.ip6;
+ struct in6_addr daddr = dut ? dut_addr.ip6 : tester_addr.ip6;
+ struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
+
+ if (ih6 + 1 > (struct ipv6hdr *)data_end)
+ return -EINVAL;
+
+ if (!ipv6_addr_equal(saddr, ih6->saddr))
+ return -EINVAL;
+
+ if (!ipv6_addr_equal(daddr, ih6->daddr))
+ return -EINVAL;
+
+ if (ih6->nexthdr != IPPROTO_UDP)
+ return -EINVAL;
+
+ uh = (struct udphdr *)(ih6 + 1);
+ } else {
+ return -EINVAL;
+ }
+
+ if (uh + 1 > (struct udphdr *)data_end)
+ return -EINVAL;
+
+ port = dut ? uh->dest : uh->source;
+ if (port != bpf_htons(DUT_ECHO_PORT))
+ return -EINVAL;
+
+ tlv = (struct tlv_hdr *)(uh + 1);
+ if (tlv + 1 > data_end)
+ return -EINVAL;
+
+ return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
+}
+
+SEC("xdp")
+int xdp_tester(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ switch (expected_feature) {
+ case XDP_FEATURE_NDO_XMIT:
+ case XDP_FEATURE_TX:
+ if (xdp_process_echo_packet(xdp, true))
+ goto out;
+ break;
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_REDIRECT:
+ if (xdp_process_echo_packet(xdp, false))
+ goto out;
+ break;
+ default:
+ goto out;
+ }
+
+ val = bpf_map_lookup_elem(&stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+out:
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_pass(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_drop(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_DROP;
+}
+
+SEC("xdp")
+int xdp_do_aborted(struct xdp_md *xdp)
+{
+ return xdp_process_echo_packet(xdp, true) ? XDP_PASS : XDP_ABORTED;
+}
+
+SEC("xdp")
+int xdp_do_tx(struct xdp_md *xdp)
+{
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ __u8 tmp_mac[ETH_ALEN];
+ __u32 *val, key = 0;
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+ __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+ __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_TX;
+}
+
+SEC("xdp")
+int xdp_do_redirect(struct xdp_md *xdp)
+{
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ return bpf_redirect_map(&cpu_map, 0, 0);
+}
+
+SEC("tp_btf/xdp_exception")
+int BPF_PROG(xdp_exception, const struct net_device *dev,
+ const struct bpf_prog *xdp, __u32 act)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return 0;
+}
+
+SEC("tp_btf/xdp_cpumap_kthread")
+int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
+ unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return 0;
+}
+
+SEC("xdp/cpumap")
+int xdp_do_redirect_cpumap(struct xdp_md *xdp)
+{
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ __u8 tmp_mac[ETH_ALEN];
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+ __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+ __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+ return bpf_redirect_map(&dev_map, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
new file mode 100755
index 000000000000..987845e18ea7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_features.sh
@@ -0,0 +1,100 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns1-$(mktemp -u XXXXXX)"
+readonly V0_IP=10.10.0.11
+readonly V1_IP=10.10.0.1
+readonly V0_IP6=2001:db8::11
+readonly V1_IP6=2001:db8::1
+
+ret=1
+
+setup() {
+ {
+ ip netns add ${NS}
+
+ ip link add v1 type veth peer name v0 netns ${NS}
+
+ ip link set v1 up
+ ip addr add $V1_IP/24 dev v1
+ ip addr add $V1_IP6/64 nodad dev v1
+ ip -n ${NS} link set dev v0 up
+ ip -n ${NS} addr add $V0_IP/24 dev v0
+ ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
+
+ sysctl -w net.ipv4.ip_forward=1
+
+ # Enable XDP mode and disable checksum offload
+ ethtool -K v1 gro on
+ ethtool -K v1 tx-checksumming off
+ ip netns exec ${NS} ethtool -K v0 gro on
+ ip netns exec ${NS} ethtool -K v0 tx-checksumming off
+ } > /dev/null 2>&1
+}
+
+cleanup() {
+ ip link del v1 2> /dev/null
+ ip netns del ${NS} 2> /dev/null
+ [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
+}
+
+wait_for_dut_server() {
+ while sleep 1; do
+ ss -tlp | grep -q xdp_features
+ [ $? -eq 0 ] && break
+ done
+}
+
+test_xdp_features() {
+ setup
+
+ ## XDP_PASS
+ ./xdp_features -6 -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_PASS -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_DROP
+ ./xdp_features -f XDP_DROP -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_DROP -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_ABORTED
+ ./xdp_features -6 -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_ABORTED -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_TX
+ ./xdp_features -f XDP_TX -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_TX -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_REDIRECT
+ ./xdp_features -6 -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_REDIRECT -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_NDO_XMIT
+ ./xdp_features -f XDP_NDO_XMIT -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ ret=$?
+ cleanup
+}
+
+set -e
+trap cleanup 2 3 6 9
+
+test_xdp_features
+
+exit $ret
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
new file mode 100644
index 000000000000..9b94d5cdf654
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -0,0 +1,731 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/netdev.h>
+#include <linux/if_link.h>
+#include <signal.h>
+#include <argp.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <pthread.h>
+
+#include <network_helpers.h>
+
+#include "xdp_features.skel.h"
+#include "xdp_features.h"
+
+#define RED(str) "\033[0;31m" str "\033[0m"
+#define GREEN(str) "\033[0;32m" str "\033[0m"
+#define YELLOW(str) "\033[0;33m" str "\033[0m"
+
+static struct env {
+ bool verbosity;
+ int ifindex;
+ unsigned int feature;
+ bool is_tester;
+ int family;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } dut_ctrl;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } dut;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } tester;
+} env;
+
+#define BUFSIZE 128
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !env.verbosity)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static volatile bool exiting;
+
+static void sig_handler(int sig)
+{
+ exiting = true;
+}
+
+const char *argp_program_version = "xdp-features 0.0";
+const char argp_program_doc[] =
+"XDP features detecion application.\n"
+"\n"
+"XDP features application checks the XDP advertised features match detected ones.\n"
+"\n"
+"USAGE: ./xdp-features [-6vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
+"\n"
+"XDP features\n:"
+"- XDP_PASS\n"
+"- XDP_DROP\n"
+"- XDP_ABORTED\n"
+"- XDP_REDIRECT\n"
+"- XDP_NDO_XMIT\n"
+"- XDP_TX\n";
+
+static const struct argp_option opts[] = {
+ { "ipv6", '6', NULL, 0, "Use IPv6 network stack" },
+ { "verbose", 'v', NULL, 0, "Verbose debug output" },
+ { "tester", 't', NULL, 0, "Tester mode" },
+ { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
+ { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
+ { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
+ { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" },
+ {},
+};
+
+static int get_xdp_feature(const char *arg)
+{
+ if (!strcmp(arg, "XDP_PASS"))
+ return XDP_FEATURE_PASS;
+ else if (!strcmp(arg, "XDP_DROP"))
+ return XDP_FEATURE_DROP;
+ else if (!strcmp(arg, "XDP_ABORTED"))
+ return XDP_FEATURE_ABORTED;
+ else if (!strcmp(arg, "XDP_REDIRECT"))
+ return XDP_FEATURE_REDIRECT;
+ else if (!strcmp(arg, "XDP_NDO_XMIT"))
+ return XDP_FEATURE_NDO_XMIT;
+ else if (!strcmp(arg, "XDP_TX"))
+ return XDP_FEATURE_TX;
+
+ return -EINVAL;
+}
+
+static char *get_xdp_feature_str(int feature)
+{
+ switch (feature) {
+ case XDP_FEATURE_PASS:
+ return YELLOW("XDP_PASS");
+ case XDP_FEATURE_DROP:
+ return YELLOW("XDP_DROP");
+ case XDP_FEATURE_ABORTED:
+ return YELLOW("XDP_ABORTED");
+ case XDP_FEATURE_TX:
+ return YELLOW("XDP_TX");
+ case XDP_FEATURE_REDIRECT:
+ return YELLOW("XDP_REDIRECT");
+ case XDP_FEATURE_NDO_XMIT:
+ return YELLOW("XDP_NDO_XMIT");
+ default:
+ return "";
+ }
+}
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case '6':
+ env.family = AF_INET6;
+ break;
+ case 'v':
+ env.verbosity = true;
+ break;
+ case 't':
+ env.is_tester = true;
+ break;
+ case 'f':
+ env.feature = get_xdp_feature(arg);
+ if (env.feature < 0) {
+ fprintf(stderr, "Invalid xdp feature: %s\n", arg);
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'D':
+ if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
+ &env.dut.addr, &env.dut.addrlen)) {
+ fprintf(stderr, "Invalid DUT address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'C':
+ if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
+ &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
+ fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'T':
+ if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
+ &env.tester.addrlen)) {
+ fprintf(stderr, "Invalid Tester address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case ARGP_KEY_ARG:
+ errno = 0;
+ if (strlen(arg) >= IF_NAMESIZE) {
+ fprintf(stderr, "Invalid device name: %s\n", arg);
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ env.ifindex = if_nametoindex(arg);
+ if (!env.ifindex)
+ env.ifindex = strtoul(arg, NULL, 0);
+ if (!env.ifindex) {
+ fprintf(stderr,
+ "Bad interface index or name (%d): %s\n",
+ errno, strerror(errno));
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ return 0;
+}
+
+static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+};
+
+static void set_env_defaul(void)
+{
+ env.feature = XDP_FEATURE_PASS;
+ env.ifindex = -ENODEV;
+ env.family = AF_INET;
+ make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
+ &env.dut_ctrl.addrlen);
+ make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
+ &env.dut.addrlen);
+ make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
+ &env.tester.addrlen);
+}
+
+static void *dut_echo_thread(void *arg)
+{
+ unsigned char buf[sizeof(struct tlv_hdr)];
+ int sockfd = *(int *)arg;
+
+ while (!exiting) {
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ size_t n;
+
+ n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
+ (struct sockaddr *)&addr, &addrlen);
+ if (n != ntohs(tlv->len))
+ continue;
+
+ if (ntohs(tlv->type) != CMD_ECHO)
+ continue;
+
+ sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+ (struct sockaddr *)&addr, addrlen);
+ }
+
+ pthread_exit((void *)0);
+ close(sockfd);
+
+ return NULL;
+}
+
+static int dut_run_echo_thread(pthread_t *t, int *sockfd)
+{
+ int err;
+
+ sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
+ DUT_ECHO_PORT, 0, 1);
+ if (!sockfd) {
+ fprintf(stderr, "Failed to create echo socket\n");
+ return -errno;
+ }
+
+ /* start echo channel */
+ err = pthread_create(t, NULL, dut_echo_thread, sockfd);
+ if (err) {
+ fprintf(stderr, "Failed creating dut_echo thread: %s\n",
+ strerror(-err));
+ free_fds(sockfd, 1);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
+ int flags)
+{
+ struct bpf_program *prog;
+ unsigned int key = 0;
+ int err, fd = 0;
+
+ switch (feature) {
+ case XDP_FEATURE_TX:
+ prog = skel->progs.xdp_do_tx;
+ break;
+ case XDP_FEATURE_DROP:
+ prog = skel->progs.xdp_do_drop;
+ break;
+ case XDP_FEATURE_ABORTED:
+ prog = skel->progs.xdp_do_aborted;
+ break;
+ case XDP_FEATURE_PASS:
+ prog = skel->progs.xdp_do_pass;
+ break;
+ case XDP_FEATURE_NDO_XMIT: {
+ struct bpf_devmap_val entry = {
+ .ifindex = env.ifindex,
+ };
+
+ err = bpf_map__update_elem(skel->maps.dev_map,
+ &key, sizeof(key),
+ &entry, sizeof(entry), 0);
+ if (err < 0)
+ return err;
+
+ fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
+ }
+ case XDP_FEATURE_REDIRECT: {
+ struct bpf_cpumap_val entry = {
+ .qsize = 2048,
+ .bpf_prog.fd = fd,
+ };
+
+ err = bpf_map__update_elem(skel->maps.cpu_map,
+ &key, sizeof(key),
+ &entry, sizeof(entry), 0);
+ if (err < 0)
+ return err;
+
+ prog = skel->progs.xdp_do_redirect;
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+
+ err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+ if (err)
+ fprintf(stderr,
+ "Failed to attach XDP program to ifindex %d\n",
+ env.ifindex);
+ return err;
+}
+
+static int __recv_msg(int sockfd, void *buf, size_t bufsize,
+ unsigned int *val, unsigned int val_size)
+{
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int len, n = sizeof(*tlv), i = 0;
+
+ len = recv(sockfd, buf, bufsize, 0);
+ if (len != ntohs(tlv->len))
+ return -EINVAL;
+
+ while (n < len && i < val_size) {
+ val[i] = ntohl(tlv->data[i]);
+ n += sizeof(tlv->data[0]);
+ i++;
+ }
+
+ return i;
+}
+
+static int recv_msg(int sockfd, void *buf, size_t bufsize)
+{
+ return __recv_msg(sockfd, buf, bufsize, NULL, 0);
+}
+
+static int dut_run(struct xdp_features *skel)
+{
+ int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+ int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
+ struct sockaddr_storage ctrl_addr;
+ pthread_t dut_thread;
+ socklen_t addrlen;
+
+ sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
+ DUT_CTRL_PORT, 0, 1);
+ if (!sockfd) {
+ fprintf(stderr, "Failed to create DUT socket\n");
+ return -errno;
+ }
+
+ ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
+ if (ctrl_sockfd < 0) {
+ fprintf(stderr, "Failed to accept connection on DUT socket\n");
+ free_fds(sockfd, 1);
+ return -errno;
+ }
+
+ /* CTRL loop */
+ while (!exiting) {
+ unsigned char buf[BUFSIZE] = {};
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+
+ err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
+ if (err)
+ continue;
+
+ switch (ntohs(tlv->type)) {
+ case CMD_START: {
+ if (state == CMD_START)
+ continue;
+
+ state = CMD_START;
+ /* Load the XDP program on the DUT */
+ err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
+ if (err)
+ goto out;
+
+ err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
+ if (err < 0)
+ goto out;
+
+ tlv->type = htons(CMD_ACK);
+ tlv->len = htons(sizeof(*tlv));
+ err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ case CMD_STOP:
+ if (state != CMD_START)
+ break;
+
+ state = CMD_STOP;
+
+ exiting = true;
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+
+ tlv->type = htons(CMD_ACK);
+ tlv->len = htons(sizeof(*tlv));
+ err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+ goto end_thread;
+ case CMD_GET_XDP_CAP: {
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+ size_t n;
+
+ err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
+ &opts);
+ if (err) {
+ fprintf(stderr,
+ "Failed to query XDP cap for ifindex %d\n",
+ env.ifindex);
+ goto end_thread;
+ }
+
+ tlv->type = htons(CMD_ACK);
+ n = sizeof(*tlv) + sizeof(opts.feature_flags);
+ tlv->len = htons(n);
+ tlv->data[0] = htonl(opts.feature_flags);
+
+ err = send(ctrl_sockfd, buf, n, 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ case CMD_GET_STATS: {
+ unsigned int key = 0, val;
+ size_t n;
+
+ err = bpf_map__lookup_elem(skel->maps.dut_stats,
+ &key, sizeof(key),
+ &val, sizeof(val), 0);
+ if (err) {
+ fprintf(stderr, "bpf_map_lookup_elem failed\n");
+ goto end_thread;
+ }
+
+ tlv->type = htons(CMD_ACK);
+ n = sizeof(*tlv) + sizeof(val);
+ tlv->len = htons(n);
+ tlv->data[0] = htonl(val);
+
+ err = send(ctrl_sockfd, buf, n, 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ default:
+ break;
+ }
+ }
+
+end_thread:
+ pthread_join(dut_thread, NULL);
+out:
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+ close(ctrl_sockfd);
+ free_fds(sockfd, 1);
+
+ return err;
+}
+
+static bool tester_collect_advertised_cap(unsigned int cap)
+{
+ switch (env.feature) {
+ case XDP_FEATURE_ABORTED:
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_TX:
+ return cap & NETDEV_XDP_ACT_BASIC;
+ case XDP_FEATURE_REDIRECT:
+ return cap & NETDEV_XDP_ACT_REDIRECT;
+ case XDP_FEATURE_NDO_XMIT:
+ return cap & NETDEV_XDP_ACT_NDO_XMIT;
+ default:
+ return false;
+ }
+}
+
+static bool tester_collect_detected_cap(struct xdp_features *skel,
+ unsigned int dut_stats)
+{
+ unsigned int err, key = 0, val;
+
+ if (!dut_stats)
+ return false;
+
+ err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
+ &val, sizeof(val), 0);
+ if (err) {
+ fprintf(stderr, "bpf_map_lookup_elem failed\n");
+ return false;
+ }
+
+ switch (env.feature) {
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_TX:
+ case XDP_FEATURE_REDIRECT:
+ case XDP_FEATURE_NDO_XMIT:
+ return val > 0;
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_ABORTED:
+ return val == 0;
+ default:
+ return false;
+ }
+}
+
+static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
+ unsigned int *val, unsigned int val_size)
+{
+ unsigned char buf[BUFSIZE] = {};
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int n = sizeof(*tlv), err;
+
+ tlv->type = htons(cmd);
+ switch (cmd) {
+ case CMD_START:
+ tlv->data[0] = htonl(env.feature);
+ n += sizeof(*val);
+ break;
+ default:
+ break;
+ }
+ tlv->len = htons(n);
+
+ err = send(sockfd, buf, n, 0);
+ if (err < 0)
+ return err;
+
+ err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
+ if (err < 0)
+ return err;
+
+ return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
+}
+
+static int send_and_recv_msg(int sockfd, enum test_commands cmd)
+{
+ return __send_and_recv_msg(sockfd, cmd, NULL, 0);
+}
+
+static int send_echo_msg(void)
+{
+ unsigned char buf[sizeof(struct tlv_hdr)];
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int sockfd, n;
+
+ sockfd = socket(env.family, SOCK_DGRAM, 0);
+ if (sockfd < 0) {
+ fprintf(stderr, "Failed to create echo socket\n");
+ return -errno;
+ }
+
+ tlv->type = htons(CMD_ECHO);
+ tlv->len = htons(sizeof(*tlv));
+
+ n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
+ (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
+ close(sockfd);
+
+ return n == ntohs(tlv->len) ? 0 : -EINVAL;
+}
+
+static int tester_run(struct xdp_features *skel)
+{
+ int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+ bool advertised_cap;
+ unsigned int val[1];
+ int i, err, sockfd;
+ bool detected_cap;
+
+ sockfd = socket(env.family, SOCK_STREAM, 0);
+ if (sockfd < 0) {
+ fprintf(stderr, "Failed to create tester socket\n");
+ return -errno;
+ }
+
+ if (settimeo(sockfd, 1000) < 0)
+ return -EINVAL;
+
+ err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
+ env.dut_ctrl.addrlen);
+ if (err) {
+ fprintf(stderr, "Failed to connect to the DUT\n");
+ return -errno;
+ }
+
+ err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
+ ARRAY_SIZE(val));
+ if (err < 0) {
+ close(sockfd);
+ return err;
+ }
+
+ advertised_cap = tester_collect_advertised_cap(val[0]);
+
+ err = bpf_xdp_attach(env.ifindex,
+ bpf_program__fd(skel->progs.xdp_tester),
+ flags, NULL);
+ if (err) {
+ fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
+ env.ifindex);
+ goto out;
+ }
+
+ err = send_and_recv_msg(sockfd, CMD_START);
+ if (err)
+ goto out;
+
+ for (i = 0; i < 10 && !exiting; i++) {
+ err = send_echo_msg();
+ if (err < 0)
+ goto out;
+
+ sleep(1);
+ }
+
+ err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
+ if (err)
+ goto out;
+
+ /* stop the test */
+ err = send_and_recv_msg(sockfd, CMD_STOP);
+ /* send a new echo message to wake echo thread of the dut */
+ send_echo_msg();
+
+ detected_cap = tester_collect_detected_cap(skel, val[0]);
+
+ fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(env.feature),
+ detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
+ advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
+out:
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+ close(sockfd);
+ return err < 0 ? err : 0;
+}
+
+static void set_skel_rodata(struct xdp_features *skel)
+{
+ skel->rodata->expected_feature = env.feature;
+ if (env.family == AF_INET6) {
+ struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
+ struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
+
+ skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
+ skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
+ } else {
+ struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
+ struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
+
+ skel->rodata->tester_addr.ip = tester_addr->sin_addr;
+ skel->rodata->dut_addr.ip = dut_addr->sin_addr;
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct xdp_features *skel;
+ int err;
+
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+ libbpf_set_print(libbpf_print_fn);
+
+ signal(SIGINT, sig_handler);
+ signal(SIGTERM, sig_handler);
+
+ set_env_defaul();
+
+ /* Parse command line arguments */
+ err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+ if (err)
+ return err;
+
+ if (env.ifindex < 0) {
+ fprintf(stderr, "Invalid ifindex\n");
+ return -ENODEV;
+ }
+
+ /* Load and verify BPF application */
+ skel = xdp_features__open();
+ if (!skel) {
+ fprintf(stderr, "Failed to open and load BPF skeleton\n");
+ return -EINVAL;
+ }
+
+ set_skel_rodata(skel);
+
+ /* Load & verify BPF programs */
+ err = xdp_features__load(skel);
+ if (err) {
+ fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+ goto cleanup;
+ }
+
+ err = xdp_features__attach(skel);
+ if (err) {
+ fprintf(stderr, "Failed to attach BPF skeleton\n");
+ goto cleanup;
+ }
+
+ if (env.is_tester) {
+ /* Tester */
+ fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
+ err = tester_run(skel);
+ } else {
+ /* DUT */
+ fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
+ err = dut_run(skel);
+ }
+
+cleanup:
+ xdp_features__destroy(skel);
+
+ return err < 0 ? -err : 0;
+}
diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
new file mode 100644
index 000000000000..28d7614c4f02
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* test commands */
+enum test_commands {
+ CMD_STOP, /* CMD */
+ CMD_START, /* CMD + xdp feature */
+ CMD_ECHO, /* CMD */
+ CMD_ACK, /* CMD + data */
+ CMD_GET_XDP_CAP, /* CMD */
+ CMD_GET_STATS, /* CMD */
+};
+
+#define DUT_CTRL_PORT 12345
+#define DUT_ECHO_PORT 12346
+
+struct tlv_hdr {
+ __be16 type;
+ __be16 len;
+ __be32 data[];
+};
+
+enum {
+ XDP_FEATURE_ABORTED,
+ XDP_FEATURE_DROP,
+ XDP_FEATURE_PASS,
+ XDP_FEATURE_TX,
+ XDP_FEATURE_REDIRECT,
+ XDP_FEATURE_NDO_XMIT,
+ XDP_FEATURE_XSK_ZEROCOPY,
+ XDP_FEATURE_HW_OFFLOAD,
+ XDP_FEATURE_RX_SG,
+ XDP_FEATURE_NDO_XMIT_SG,
+};
--
2.39.1
^ permalink raw reply related [flat|nested] 32+ messages in thread* [Intel-wired-lan] [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
@ 2023-01-28 14:06 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-28 14:06 UTC (permalink / raw)
To: bpf
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, sdf,
daniel, andrii, intel-wired-lan, simon.horman, kuba, pabeni,
aelior, hawk, christophe.jaillet, memxor, john, bjorn,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
Introduce xdp_features tool in order to test XDP features supported by
the NIC and match them against advertised ones.
In order to test supported/advertised XDP features, xdp_features must
run on the Device Under Test (DUT) and on a Tester device.
xdp_features opens a control TCP channel between DUT and Tester devices
to send control commands from Tester to the DUT and a UDP data channel
where the Tester sends UDP 'echo' packets and the DUT is expected to
reply back with the same packet. DUT installs multiple XDP programs on the
NIC to test XDP capabilities and reports back to the Tester some XDP stats.
Currently xdp_features supports the following XDP features:
- XDP_DROP
- XDP_PASS
- XDP_TX
- XDP_REDIRECT
- XDP_REDIRECT_TARGET
Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 11 +-
.../selftests/bpf/progs/xdp_features.c | 275 +++++++
.../selftests/bpf/test_xdp_features.sh | 100 +++
tools/testing/selftests/bpf/xdp_features.c | 731 ++++++++++++++++++
tools/testing/selftests/bpf/xdp_features.h | 33 +
6 files changed, 1149 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c
create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh
create mode 100644 tools/testing/selftests/bpf/xdp_features.c
create mode 100644 tools/testing/selftests/bpf/xdp_features.h
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 4aa5bba956ff..116fecf80ca1 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -48,3 +48,4 @@ xskxceiver
xdp_redirect_multi
xdp_synproxy
xdp_hw_metadata
+xdp_features
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 53eae7be8dff..6f06b03d93cd 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -73,7 +73,8 @@ TEST_PROGS := test_kmod.sh \
test_bpftool.sh \
test_bpftool_metadata.sh \
test_doc_build.sh \
- test_xsk.sh
+ test_xsk.sh \
+ test_xdp_features.sh
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
@@ -83,7 +84,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
- xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
+ xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
+ xdp_features
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
TEST_GEN_FILES += liburandom_read.so
@@ -385,6 +387,7 @@ test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton
test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
+xdp_features.skel.h-deps := xdp_features.bpf.o
LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
@@ -586,6 +589,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPU
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
+
# Make sure we are able to include and link libbpf against c++.
$(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
$(call msg,CXX,,$@)
diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c
new file mode 100644
index 000000000000..205a4526ea68
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_features.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/netdev.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_tracing.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/udp.h>
+#include <asm-generic/errno-base.h>
+
+#include "xdp_features.h"
+
+#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \
+ (a).s6_addr32[1] == (b).s6_addr32[1] && \
+ (a).s6_addr32[2] == (b).s6_addr32[2] && \
+ (a).s6_addr32[3] == (b).s6_addr32[3])
+
+struct net_device;
+struct bpf_prog;
+
+struct xdp_cpumap_stats {
+ unsigned int redirect;
+ unsigned int pass;
+ unsigned int drop;
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} stats SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} dut_stats SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_CPUMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_cpumap_val));
+ __uint(max_entries, 1);
+} cpu_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_DEVMAP);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_devmap_val));
+ __uint(max_entries, 1);
+} dev_map SEC(".maps");
+
+const volatile __u32 expected_feature = XDP_FEATURE_PASS;
+const volatile union {
+ struct in_addr ip;
+ struct in6_addr ip6;
+} tester_addr;
+const volatile union {
+ struct in_addr ip;
+ struct in6_addr ip6;
+} dut_addr;
+
+static __always_inline int xdp_process_echo_packet(struct xdp_md *xdp, bool dut)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ struct tlv_hdr *tlv;
+ struct udphdr *uh;
+ __be16 port;
+ __u8 *cmd;
+
+ if (eh + 1 > (struct ethhdr *)data_end)
+ return -EINVAL;
+
+ if (eh->h_proto == bpf_htons(ETH_P_IP)) {
+ struct iphdr *ih = (struct iphdr *)(eh + 1);
+ __be32 saddr = dut ? tester_addr.ip.s_addr : dut_addr.ip.s_addr;
+ __be32 daddr = dut ? dut_addr.ip.s_addr : tester_addr.ip.s_addr;
+
+ ih = (struct iphdr *)(eh + 1);
+ if (ih + 1 > (struct iphdr *)data_end)
+ return -EINVAL;
+
+ if (saddr != ih->saddr)
+ return -EINVAL;
+
+ if (daddr != ih->daddr)
+ return -EINVAL;
+
+ if (ih->protocol != IPPROTO_UDP)
+ return -EINVAL;
+
+ uh = (struct udphdr *)(ih + 1);
+ } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct in6_addr saddr = dut ? tester_addr.ip6 : dut_addr.ip6;
+ struct in6_addr daddr = dut ? dut_addr.ip6 : tester_addr.ip6;
+ struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
+
+ if (ih6 + 1 > (struct ipv6hdr *)data_end)
+ return -EINVAL;
+
+ if (!ipv6_addr_equal(saddr, ih6->saddr))
+ return -EINVAL;
+
+ if (!ipv6_addr_equal(daddr, ih6->daddr))
+ return -EINVAL;
+
+ if (ih6->nexthdr != IPPROTO_UDP)
+ return -EINVAL;
+
+ uh = (struct udphdr *)(ih6 + 1);
+ } else {
+ return -EINVAL;
+ }
+
+ if (uh + 1 > (struct udphdr *)data_end)
+ return -EINVAL;
+
+ port = dut ? uh->dest : uh->source;
+ if (port != bpf_htons(DUT_ECHO_PORT))
+ return -EINVAL;
+
+ tlv = (struct tlv_hdr *)(uh + 1);
+ if (tlv + 1 > data_end)
+ return -EINVAL;
+
+ return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
+}
+
+SEC("xdp")
+int xdp_tester(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ switch (expected_feature) {
+ case XDP_FEATURE_NDO_XMIT:
+ case XDP_FEATURE_TX:
+ if (xdp_process_echo_packet(xdp, true))
+ goto out;
+ break;
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_REDIRECT:
+ if (xdp_process_echo_packet(xdp, false))
+ goto out;
+ break;
+ default:
+ goto out;
+ }
+
+ val = bpf_map_lookup_elem(&stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+out:
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_pass(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_PASS;
+}
+
+SEC("xdp")
+int xdp_do_drop(struct xdp_md *xdp)
+{
+ __u32 *val, key = 0;
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_DROP;
+}
+
+SEC("xdp")
+int xdp_do_aborted(struct xdp_md *xdp)
+{
+ return xdp_process_echo_packet(xdp, true) ? XDP_PASS : XDP_ABORTED;
+}
+
+SEC("xdp")
+int xdp_do_tx(struct xdp_md *xdp)
+{
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ __u8 tmp_mac[ETH_ALEN];
+ __u32 *val, key = 0;
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+ __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+ __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return XDP_TX;
+}
+
+SEC("xdp")
+int xdp_do_redirect(struct xdp_md *xdp)
+{
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ return bpf_redirect_map(&cpu_map, 0, 0);
+}
+
+SEC("tp_btf/xdp_exception")
+int BPF_PROG(xdp_exception, const struct net_device *dev,
+ const struct bpf_prog *xdp, __u32 act)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return 0;
+}
+
+SEC("tp_btf/xdp_cpumap_kthread")
+int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
+ unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
+{
+ __u32 *val, key = 0;
+
+ val = bpf_map_lookup_elem(&dut_stats, &key);
+ if (val)
+ __sync_add_and_fetch(val, 1);
+
+ return 0;
+}
+
+SEC("xdp/cpumap")
+int xdp_do_redirect_cpumap(struct xdp_md *xdp)
+{
+ void *data = (void *)(long)xdp->data;
+ struct ethhdr *eh = data;
+ __u8 tmp_mac[ETH_ALEN];
+
+ if (xdp_process_echo_packet(xdp, true))
+ return XDP_PASS;
+
+ __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
+ __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
+ __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
+
+ return bpf_redirect_map(&dev_map, 0, 0);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh
new file mode 100755
index 000000000000..987845e18ea7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xdp_features.sh
@@ -0,0 +1,100 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+readonly NS="ns1-$(mktemp -u XXXXXX)"
+readonly V0_IP=10.10.0.11
+readonly V1_IP=10.10.0.1
+readonly V0_IP6=2001:db8::11
+readonly V1_IP6=2001:db8::1
+
+ret=1
+
+setup() {
+ {
+ ip netns add ${NS}
+
+ ip link add v1 type veth peer name v0 netns ${NS}
+
+ ip link set v1 up
+ ip addr add $V1_IP/24 dev v1
+ ip addr add $V1_IP6/64 nodad dev v1
+ ip -n ${NS} link set dev v0 up
+ ip -n ${NS} addr add $V0_IP/24 dev v0
+ ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
+
+ sysctl -w net.ipv4.ip_forward=1
+
+ # Enable XDP mode and disable checksum offload
+ ethtool -K v1 gro on
+ ethtool -K v1 tx-checksumming off
+ ip netns exec ${NS} ethtool -K v0 gro on
+ ip netns exec ${NS} ethtool -K v0 tx-checksumming off
+ } > /dev/null 2>&1
+}
+
+cleanup() {
+ ip link del v1 2> /dev/null
+ ip netns del ${NS} 2> /dev/null
+ [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null
+}
+
+wait_for_dut_server() {
+ while sleep 1; do
+ ss -tlp | grep -q xdp_features
+ [ $? -eq 0 ] && break
+ done
+}
+
+test_xdp_features() {
+ setup
+
+ ## XDP_PASS
+ ./xdp_features -6 -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_PASS -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_DROP
+ ./xdp_features -f XDP_DROP -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_DROP -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_ABORTED
+ ./xdp_features -6 -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_ABORTED -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_TX
+ ./xdp_features -f XDP_TX -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_TX -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_REDIRECT
+ ./xdp_features -6 -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -6 -t -f XDP_REDIRECT -D $V1_IP6 -C $V1_IP6 -T $V0_IP6 v0
+
+ [ $? -ne 0 ] && exit
+
+ ## XDP_NDO_XMIT
+ ./xdp_features -f XDP_NDO_XMIT -D $V1_IP -T $V0_IP v1 &
+ wait_for_dut_server
+ ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT -D $V1_IP -C $V1_IP -T $V0_IP v0
+
+ ret=$?
+ cleanup
+}
+
+set -e
+trap cleanup 2 3 6 9
+
+test_xdp_features
+
+exit $ret
diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c
new file mode 100644
index 000000000000..9b94d5cdf654
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.c
@@ -0,0 +1,731 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/netdev.h>
+#include <linux/if_link.h>
+#include <signal.h>
+#include <argp.h>
+#include <net/if.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include <pthread.h>
+
+#include <network_helpers.h>
+
+#include "xdp_features.skel.h"
+#include "xdp_features.h"
+
+#define RED(str) "\033[0;31m" str "\033[0m"
+#define GREEN(str) "\033[0;32m" str "\033[0m"
+#define YELLOW(str) "\033[0;33m" str "\033[0m"
+
+static struct env {
+ bool verbosity;
+ int ifindex;
+ unsigned int feature;
+ bool is_tester;
+ int family;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } dut_ctrl;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } dut;
+ struct {
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ } tester;
+} env;
+
+#define BUFSIZE 128
+
+void test__fail(void) { /* for network_helpers.c */ }
+
+static int libbpf_print_fn(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ if (level == LIBBPF_DEBUG && !env.verbosity)
+ return 0;
+ return vfprintf(stderr, format, args);
+}
+
+static volatile bool exiting;
+
+static void sig_handler(int sig)
+{
+ exiting = true;
+}
+
+const char *argp_program_version = "xdp-features 0.0";
+const char argp_program_doc[] =
+"XDP features detecion application.\n"
+"\n"
+"XDP features application checks the XDP advertised features match detected ones.\n"
+"\n"
+"USAGE: ./xdp-features [-6vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
+"\n"
+"XDP features\n:"
+"- XDP_PASS\n"
+"- XDP_DROP\n"
+"- XDP_ABORTED\n"
+"- XDP_REDIRECT\n"
+"- XDP_NDO_XMIT\n"
+"- XDP_TX\n";
+
+static const struct argp_option opts[] = {
+ { "ipv6", '6', NULL, 0, "Use IPv6 network stack" },
+ { "verbose", 'v', NULL, 0, "Verbose debug output" },
+ { "tester", 't', NULL, 0, "Tester mode" },
+ { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
+ { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
+ { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
+ { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" },
+ {},
+};
+
+static int get_xdp_feature(const char *arg)
+{
+ if (!strcmp(arg, "XDP_PASS"))
+ return XDP_FEATURE_PASS;
+ else if (!strcmp(arg, "XDP_DROP"))
+ return XDP_FEATURE_DROP;
+ else if (!strcmp(arg, "XDP_ABORTED"))
+ return XDP_FEATURE_ABORTED;
+ else if (!strcmp(arg, "XDP_REDIRECT"))
+ return XDP_FEATURE_REDIRECT;
+ else if (!strcmp(arg, "XDP_NDO_XMIT"))
+ return XDP_FEATURE_NDO_XMIT;
+ else if (!strcmp(arg, "XDP_TX"))
+ return XDP_FEATURE_TX;
+
+ return -EINVAL;
+}
+
+static char *get_xdp_feature_str(int feature)
+{
+ switch (feature) {
+ case XDP_FEATURE_PASS:
+ return YELLOW("XDP_PASS");
+ case XDP_FEATURE_DROP:
+ return YELLOW("XDP_DROP");
+ case XDP_FEATURE_ABORTED:
+ return YELLOW("XDP_ABORTED");
+ case XDP_FEATURE_TX:
+ return YELLOW("XDP_TX");
+ case XDP_FEATURE_REDIRECT:
+ return YELLOW("XDP_REDIRECT");
+ case XDP_FEATURE_NDO_XMIT:
+ return YELLOW("XDP_NDO_XMIT");
+ default:
+ return "";
+ }
+}
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+ switch (key) {
+ case '6':
+ env.family = AF_INET6;
+ break;
+ case 'v':
+ env.verbosity = true;
+ break;
+ case 't':
+ env.is_tester = true;
+ break;
+ case 'f':
+ env.feature = get_xdp_feature(arg);
+ if (env.feature < 0) {
+ fprintf(stderr, "Invalid xdp feature: %s\n", arg);
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'D':
+ if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
+ &env.dut.addr, &env.dut.addrlen)) {
+ fprintf(stderr, "Invalid DUT address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'C':
+ if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
+ &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
+ fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case 'T':
+ if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
+ &env.tester.addrlen)) {
+ fprintf(stderr, "Invalid Tester address: %s\n", arg);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ case ARGP_KEY_ARG:
+ errno = 0;
+ if (strlen(arg) >= IF_NAMESIZE) {
+ fprintf(stderr, "Invalid device name: %s\n", arg);
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ env.ifindex = if_nametoindex(arg);
+ if (!env.ifindex)
+ env.ifindex = strtoul(arg, NULL, 0);
+ if (!env.ifindex) {
+ fprintf(stderr,
+ "Bad interface index or name (%d): %s\n",
+ errno, strerror(errno));
+ argp_usage(state);
+ return ARGP_ERR_UNKNOWN;
+ }
+ break;
+ default:
+ return ARGP_ERR_UNKNOWN;
+ }
+
+ return 0;
+}
+
+static const struct argp argp = {
+ .options = opts,
+ .parser = parse_arg,
+ .doc = argp_program_doc,
+};
+
+static void set_env_defaul(void)
+{
+ env.feature = XDP_FEATURE_PASS;
+ env.ifindex = -ENODEV;
+ env.family = AF_INET;
+ make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
+ &env.dut_ctrl.addrlen);
+ make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
+ &env.dut.addrlen);
+ make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
+ &env.tester.addrlen);
+}
+
+static void *dut_echo_thread(void *arg)
+{
+ unsigned char buf[sizeof(struct tlv_hdr)];
+ int sockfd = *(int *)arg;
+
+ while (!exiting) {
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ struct sockaddr_storage addr;
+ socklen_t addrlen;
+ size_t n;
+
+ n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
+ (struct sockaddr *)&addr, &addrlen);
+ if (n != ntohs(tlv->len))
+ continue;
+
+ if (ntohs(tlv->type) != CMD_ECHO)
+ continue;
+
+ sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+ (struct sockaddr *)&addr, addrlen);
+ }
+
+ pthread_exit((void *)0);
+ close(sockfd);
+
+ return NULL;
+}
+
+static int dut_run_echo_thread(pthread_t *t, int *sockfd)
+{
+ int err;
+
+ sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
+ DUT_ECHO_PORT, 0, 1);
+ if (!sockfd) {
+ fprintf(stderr, "Failed to create echo socket\n");
+ return -errno;
+ }
+
+ /* start echo channel */
+ err = pthread_create(t, NULL, dut_echo_thread, sockfd);
+ if (err) {
+ fprintf(stderr, "Failed creating dut_echo thread: %s\n",
+ strerror(-err));
+ free_fds(sockfd, 1);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
+ int flags)
+{
+ struct bpf_program *prog;
+ unsigned int key = 0;
+ int err, fd = 0;
+
+ switch (feature) {
+ case XDP_FEATURE_TX:
+ prog = skel->progs.xdp_do_tx;
+ break;
+ case XDP_FEATURE_DROP:
+ prog = skel->progs.xdp_do_drop;
+ break;
+ case XDP_FEATURE_ABORTED:
+ prog = skel->progs.xdp_do_aborted;
+ break;
+ case XDP_FEATURE_PASS:
+ prog = skel->progs.xdp_do_pass;
+ break;
+ case XDP_FEATURE_NDO_XMIT: {
+ struct bpf_devmap_val entry = {
+ .ifindex = env.ifindex,
+ };
+
+ err = bpf_map__update_elem(skel->maps.dev_map,
+ &key, sizeof(key),
+ &entry, sizeof(entry), 0);
+ if (err < 0)
+ return err;
+
+ fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
+ }
+ case XDP_FEATURE_REDIRECT: {
+ struct bpf_cpumap_val entry = {
+ .qsize = 2048,
+ .bpf_prog.fd = fd,
+ };
+
+ err = bpf_map__update_elem(skel->maps.cpu_map,
+ &key, sizeof(key),
+ &entry, sizeof(entry), 0);
+ if (err < 0)
+ return err;
+
+ prog = skel->progs.xdp_do_redirect;
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
+
+ err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
+ if (err)
+ fprintf(stderr,
+ "Failed to attach XDP program to ifindex %d\n",
+ env.ifindex);
+ return err;
+}
+
+static int __recv_msg(int sockfd, void *buf, size_t bufsize,
+ unsigned int *val, unsigned int val_size)
+{
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int len, n = sizeof(*tlv), i = 0;
+
+ len = recv(sockfd, buf, bufsize, 0);
+ if (len != ntohs(tlv->len))
+ return -EINVAL;
+
+ while (n < len && i < val_size) {
+ val[i] = ntohl(tlv->data[i]);
+ n += sizeof(tlv->data[0]);
+ i++;
+ }
+
+ return i;
+}
+
+static int recv_msg(int sockfd, void *buf, size_t bufsize)
+{
+ return __recv_msg(sockfd, buf, bufsize, NULL, 0);
+}
+
+static int dut_run(struct xdp_features *skel)
+{
+ int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+ int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
+ struct sockaddr_storage ctrl_addr;
+ pthread_t dut_thread;
+ socklen_t addrlen;
+
+ sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
+ DUT_CTRL_PORT, 0, 1);
+ if (!sockfd) {
+ fprintf(stderr, "Failed to create DUT socket\n");
+ return -errno;
+ }
+
+ ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
+ if (ctrl_sockfd < 0) {
+ fprintf(stderr, "Failed to accept connection on DUT socket\n");
+ free_fds(sockfd, 1);
+ return -errno;
+ }
+
+ /* CTRL loop */
+ while (!exiting) {
+ unsigned char buf[BUFSIZE] = {};
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+
+ err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
+ if (err)
+ continue;
+
+ switch (ntohs(tlv->type)) {
+ case CMD_START: {
+ if (state == CMD_START)
+ continue;
+
+ state = CMD_START;
+ /* Load the XDP program on the DUT */
+ err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
+ if (err)
+ goto out;
+
+ err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
+ if (err < 0)
+ goto out;
+
+ tlv->type = htons(CMD_ACK);
+ tlv->len = htons(sizeof(*tlv));
+ err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ case CMD_STOP:
+ if (state != CMD_START)
+ break;
+
+ state = CMD_STOP;
+
+ exiting = true;
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+
+ tlv->type = htons(CMD_ACK);
+ tlv->len = htons(sizeof(*tlv));
+ err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
+ goto end_thread;
+ case CMD_GET_XDP_CAP: {
+ LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+ size_t n;
+
+ err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
+ &opts);
+ if (err) {
+ fprintf(stderr,
+ "Failed to query XDP cap for ifindex %d\n",
+ env.ifindex);
+ goto end_thread;
+ }
+
+ tlv->type = htons(CMD_ACK);
+ n = sizeof(*tlv) + sizeof(opts.feature_flags);
+ tlv->len = htons(n);
+ tlv->data[0] = htonl(opts.feature_flags);
+
+ err = send(ctrl_sockfd, buf, n, 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ case CMD_GET_STATS: {
+ unsigned int key = 0, val;
+ size_t n;
+
+ err = bpf_map__lookup_elem(skel->maps.dut_stats,
+ &key, sizeof(key),
+ &val, sizeof(val), 0);
+ if (err) {
+ fprintf(stderr, "bpf_map_lookup_elem failed\n");
+ goto end_thread;
+ }
+
+ tlv->type = htons(CMD_ACK);
+ n = sizeof(*tlv) + sizeof(val);
+ tlv->len = htons(n);
+ tlv->data[0] = htonl(val);
+
+ err = send(ctrl_sockfd, buf, n, 0);
+ if (err < 0)
+ goto end_thread;
+ break;
+ }
+ default:
+ break;
+ }
+ }
+
+end_thread:
+ pthread_join(dut_thread, NULL);
+out:
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+ close(ctrl_sockfd);
+ free_fds(sockfd, 1);
+
+ return err;
+}
+
+static bool tester_collect_advertised_cap(unsigned int cap)
+{
+ switch (env.feature) {
+ case XDP_FEATURE_ABORTED:
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_TX:
+ return cap & NETDEV_XDP_ACT_BASIC;
+ case XDP_FEATURE_REDIRECT:
+ return cap & NETDEV_XDP_ACT_REDIRECT;
+ case XDP_FEATURE_NDO_XMIT:
+ return cap & NETDEV_XDP_ACT_NDO_XMIT;
+ default:
+ return false;
+ }
+}
+
+static bool tester_collect_detected_cap(struct xdp_features *skel,
+ unsigned int dut_stats)
+{
+ unsigned int err, key = 0, val;
+
+ if (!dut_stats)
+ return false;
+
+ err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
+ &val, sizeof(val), 0);
+ if (err) {
+ fprintf(stderr, "bpf_map_lookup_elem failed\n");
+ return false;
+ }
+
+ switch (env.feature) {
+ case XDP_FEATURE_PASS:
+ case XDP_FEATURE_TX:
+ case XDP_FEATURE_REDIRECT:
+ case XDP_FEATURE_NDO_XMIT:
+ return val > 0;
+ case XDP_FEATURE_DROP:
+ case XDP_FEATURE_ABORTED:
+ return val == 0;
+ default:
+ return false;
+ }
+}
+
+static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
+ unsigned int *val, unsigned int val_size)
+{
+ unsigned char buf[BUFSIZE] = {};
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int n = sizeof(*tlv), err;
+
+ tlv->type = htons(cmd);
+ switch (cmd) {
+ case CMD_START:
+ tlv->data[0] = htonl(env.feature);
+ n += sizeof(*val);
+ break;
+ default:
+ break;
+ }
+ tlv->len = htons(n);
+
+ err = send(sockfd, buf, n, 0);
+ if (err < 0)
+ return err;
+
+ err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
+ if (err < 0)
+ return err;
+
+ return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
+}
+
+static int send_and_recv_msg(int sockfd, enum test_commands cmd)
+{
+ return __send_and_recv_msg(sockfd, cmd, NULL, 0);
+}
+
+static int send_echo_msg(void)
+{
+ unsigned char buf[sizeof(struct tlv_hdr)];
+ struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
+ int sockfd, n;
+
+ sockfd = socket(env.family, SOCK_DGRAM, 0);
+ if (sockfd < 0) {
+ fprintf(stderr, "Failed to create echo socket\n");
+ return -errno;
+ }
+
+ tlv->type = htons(CMD_ECHO);
+ tlv->len = htons(sizeof(*tlv));
+
+ n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
+ (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
+ close(sockfd);
+
+ return n == ntohs(tlv->len) ? 0 : -EINVAL;
+}
+
+static int tester_run(struct xdp_features *skel)
+{
+ int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
+ bool advertised_cap;
+ unsigned int val[1];
+ int i, err, sockfd;
+ bool detected_cap;
+
+ sockfd = socket(env.family, SOCK_STREAM, 0);
+ if (sockfd < 0) {
+ fprintf(stderr, "Failed to create tester socket\n");
+ return -errno;
+ }
+
+ if (settimeo(sockfd, 1000) < 0)
+ return -EINVAL;
+
+ err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
+ env.dut_ctrl.addrlen);
+ if (err) {
+ fprintf(stderr, "Failed to connect to the DUT\n");
+ return -errno;
+ }
+
+ err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
+ ARRAY_SIZE(val));
+ if (err < 0) {
+ close(sockfd);
+ return err;
+ }
+
+ advertised_cap = tester_collect_advertised_cap(val[0]);
+
+ err = bpf_xdp_attach(env.ifindex,
+ bpf_program__fd(skel->progs.xdp_tester),
+ flags, NULL);
+ if (err) {
+ fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
+ env.ifindex);
+ goto out;
+ }
+
+ err = send_and_recv_msg(sockfd, CMD_START);
+ if (err)
+ goto out;
+
+ for (i = 0; i < 10 && !exiting; i++) {
+ err = send_echo_msg();
+ if (err < 0)
+ goto out;
+
+ sleep(1);
+ }
+
+ err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
+ if (err)
+ goto out;
+
+ /* stop the test */
+ err = send_and_recv_msg(sockfd, CMD_STOP);
+ /* send a new echo message to wake echo thread of the dut */
+ send_echo_msg();
+
+ detected_cap = tester_collect_detected_cap(skel, val[0]);
+
+ fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(env.feature),
+ detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
+ advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
+out:
+ bpf_xdp_detach(env.ifindex, flags, NULL);
+ close(sockfd);
+ return err < 0 ? err : 0;
+}
+
+static void set_skel_rodata(struct xdp_features *skel)
+{
+ skel->rodata->expected_feature = env.feature;
+ if (env.family == AF_INET6) {
+ struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
+ struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
+
+ skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
+ skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
+ } else {
+ struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
+ struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
+
+ skel->rodata->tester_addr.ip = tester_addr->sin_addr;
+ skel->rodata->dut_addr.ip = dut_addr->sin_addr;
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct xdp_features *skel;
+ int err;
+
+ libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+ libbpf_set_print(libbpf_print_fn);
+
+ signal(SIGINT, sig_handler);
+ signal(SIGTERM, sig_handler);
+
+ set_env_defaul();
+
+ /* Parse command line arguments */
+ err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
+ if (err)
+ return err;
+
+ if (env.ifindex < 0) {
+ fprintf(stderr, "Invalid ifindex\n");
+ return -ENODEV;
+ }
+
+ /* Load and verify BPF application */
+ skel = xdp_features__open();
+ if (!skel) {
+ fprintf(stderr, "Failed to open and load BPF skeleton\n");
+ return -EINVAL;
+ }
+
+ set_skel_rodata(skel);
+
+ /* Load & verify BPF programs */
+ err = xdp_features__load(skel);
+ if (err) {
+ fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+ goto cleanup;
+ }
+
+ err = xdp_features__attach(skel);
+ if (err) {
+ fprintf(stderr, "Failed to attach BPF skeleton\n");
+ goto cleanup;
+ }
+
+ if (env.is_tester) {
+ /* Tester */
+ fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
+ err = tester_run(skel);
+ } else {
+ /* DUT */
+ fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
+ err = dut_run(skel);
+ }
+
+cleanup:
+ xdp_features__destroy(skel);
+
+ return err < 0 ? -err : 0;
+}
diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
new file mode 100644
index 000000000000..28d7614c4f02
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdp_features.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/* test commands */
+enum test_commands {
+ CMD_STOP, /* CMD */
+ CMD_START, /* CMD + xdp feature */
+ CMD_ECHO, /* CMD */
+ CMD_ACK, /* CMD + data */
+ CMD_GET_XDP_CAP, /* CMD */
+ CMD_GET_STATS, /* CMD */
+};
+
+#define DUT_CTRL_PORT 12345
+#define DUT_ECHO_PORT 12346
+
+struct tlv_hdr {
+ __be16 type;
+ __be16 len;
+ __be32 data[];
+};
+
+enum {
+ XDP_FEATURE_ABORTED,
+ XDP_FEATURE_DROP,
+ XDP_FEATURE_PASS,
+ XDP_FEATURE_TX,
+ XDP_FEATURE_REDIRECT,
+ XDP_FEATURE_NDO_XMIT,
+ XDP_FEATURE_XSK_ZEROCOPY,
+ XDP_FEATURE_HW_OFFLOAD,
+ XDP_FEATURE_RX_SG,
+ XDP_FEATURE_NDO_XMIT_SG,
+};
--
2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply related [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-28 21:34 ` Alexei Starovoitov
-1 siblings, 0 replies; 32+ messages in thread
From: Alexei Starovoitov @ 2023-01-28 21:34 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: bpf, Network Development, Alexei Starovoitov, Daniel Borkmann,
Andrii Nakryiko, David S. Miller, Jakub Kicinski, Paolo Abeni,
Eric Dumazet, Jesper Dangaard Brouer,
Toke Høiland-Jørgensen, Kumar Kartikeya Dwivedi,
Marek Majtyka, Saeed Mahameed, anthony.l.nguyen, Andy Gospodarek,
vladimir.oltean, Felix Fietkau, john, Leon Romanovsky,
Simon Horman, Ariel Elior, christophe.jaillet, ecree.xilinx,
Michael S. Tsirkin, Björn Töpel, Karlsson, Magnus,
Fijalkowski, Maciej, intel-wired-lan, Lorenzo Bianconi,
Martin KaFai Lau, Stanislav Fomichev
On Sat, Jan 28, 2023 at 6:07 AM Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
> new file mode 100644
> index 000000000000..28d7614c4f02
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.h
> @@ -0,0 +1,33 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +/* test commands */
> +enum test_commands {
> + CMD_STOP, /* CMD */
> + CMD_START, /* CMD + xdp feature */
> + CMD_ECHO, /* CMD */
> + CMD_ACK, /* CMD + data */
> + CMD_GET_XDP_CAP, /* CMD */
> + CMD_GET_STATS, /* CMD */
> +};
> +
> +#define DUT_CTRL_PORT 12345
> +#define DUT_ECHO_PORT 12346
> +
> +struct tlv_hdr {
> + __be16 type;
> + __be16 len;
> + __be32 data[];
> +};
> +
> +enum {
> + XDP_FEATURE_ABORTED,
> + XDP_FEATURE_DROP,
> + XDP_FEATURE_PASS,
> + XDP_FEATURE_TX,
> + XDP_FEATURE_REDIRECT,
> + XDP_FEATURE_NDO_XMIT,
> + XDP_FEATURE_XSK_ZEROCOPY,
> + XDP_FEATURE_HW_OFFLOAD,
> + XDP_FEATURE_RX_SG,
> + XDP_FEATURE_NDO_XMIT_SG,
> +};
This doesn't match the kernel.
How did you test this?
What should be the way to prevent such mistakes in the future?
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
@ 2023-01-28 21:34 ` Alexei Starovoitov
0 siblings, 0 replies; 32+ messages in thread
From: Alexei Starovoitov @ 2023-01-28 21:34 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: Michael S. Tsirkin, vladimir.oltean, Alexei Starovoitov,
Eric Dumazet, anthony.l.nguyen, Stanislav Fomichev,
Daniel Borkmann, Andrii Nakryiko, intel-wired-lan, Simon Horman,
Jakub Kicinski, Paolo Abeni, Ariel Elior, Jesper Dangaard Brouer,
christophe.jaillet, Kumar Kartikeya Dwivedi, john,
Björn Töpel, bpf, Karlsson, Magnus, Leon Romanovsky,
Network Development, Toke Høiland-Jørgensen,
Martin KaFai Lau, ecree.xilinx, Marek Majtyka, Andy Gospodarek,
Saeed Mahameed, David S. Miller, Felix Fietkau
On Sat, Jan 28, 2023 at 6:07 AM Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
> new file mode 100644
> index 000000000000..28d7614c4f02
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.h
> @@ -0,0 +1,33 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +/* test commands */
> +enum test_commands {
> + CMD_STOP, /* CMD */
> + CMD_START, /* CMD + xdp feature */
> + CMD_ECHO, /* CMD */
> + CMD_ACK, /* CMD + data */
> + CMD_GET_XDP_CAP, /* CMD */
> + CMD_GET_STATS, /* CMD */
> +};
> +
> +#define DUT_CTRL_PORT 12345
> +#define DUT_ECHO_PORT 12346
> +
> +struct tlv_hdr {
> + __be16 type;
> + __be16 len;
> + __be32 data[];
> +};
> +
> +enum {
> + XDP_FEATURE_ABORTED,
> + XDP_FEATURE_DROP,
> + XDP_FEATURE_PASS,
> + XDP_FEATURE_TX,
> + XDP_FEATURE_REDIRECT,
> + XDP_FEATURE_NDO_XMIT,
> + XDP_FEATURE_XSK_ZEROCOPY,
> + XDP_FEATURE_HW_OFFLOAD,
> + XDP_FEATURE_RX_SG,
> + XDP_FEATURE_NDO_XMIT_SG,
> +};
This doesn't match the kernel.
How did you test this?
What should be the way to prevent such mistakes in the future?
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
2023-01-28 21:34 ` [Intel-wired-lan] " Alexei Starovoitov
@ 2023-01-29 18:48 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-29 18:48 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: Michael S. Tsirkin, vladimir.oltean, Alexei Starovoitov,
Eric Dumazet, anthony.l.nguyen, Stanislav Fomichev,
Daniel Borkmann, Andrii Nakryiko, intel-wired-lan, Simon Horman,
Jakub Kicinski, Paolo Abeni, Ariel Elior, Jesper Dangaard Brouer,
christophe.jaillet, Kumar Kartikeya Dwivedi, john,
Björn Töpel, bpf, Karlsson, Magnus, Leon Romanovsky,
Network Development, Toke Høiland-Jørgensen,
Martin KaFai Lau, ecree.xilinx, Marek Majtyka, Andy Gospodarek,
Saeed Mahameed, David S. Miller, Felix Fietkau
[-- Attachment #1.1: Type: text/plain, Size: 2003 bytes --]
On Jan 28, Alexei Starovoitov wrote:
> On Sat, Jan 28, 2023 at 6:07 AM Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> > diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
> > new file mode 100644
> > index 000000000000..28d7614c4f02
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/xdp_features.h
> > @@ -0,0 +1,33 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +
> > +/* test commands */
> > +enum test_commands {
> > + CMD_STOP, /* CMD */
> > + CMD_START, /* CMD + xdp feature */
> > + CMD_ECHO, /* CMD */
> > + CMD_ACK, /* CMD + data */
> > + CMD_GET_XDP_CAP, /* CMD */
> > + CMD_GET_STATS, /* CMD */
> > +};
> > +
> > +#define DUT_CTRL_PORT 12345
> > +#define DUT_ECHO_PORT 12346
> > +
> > +struct tlv_hdr {
> > + __be16 type;
> > + __be16 len;
> > + __be32 data[];
> > +};
> > +
> > +enum {
> > + XDP_FEATURE_ABORTED,
> > + XDP_FEATURE_DROP,
> > + XDP_FEATURE_PASS,
> > + XDP_FEATURE_TX,
> > + XDP_FEATURE_REDIRECT,
> > + XDP_FEATURE_NDO_XMIT,
> > + XDP_FEATURE_XSK_ZEROCOPY,
> > + XDP_FEATURE_HW_OFFLOAD,
> > + XDP_FEATURE_RX_SG,
> > + XDP_FEATURE_NDO_XMIT_SG,
> > +};
>
> This doesn't match the kernel.
> How did you test this?
> What should be the way to prevent such mistakes in the future?
Hi Alexei,
I added the XDP_FEATURE_* enum above since the XDP compliance test tool needs
to differentiate between actions in NETDEV_XDP_ACT_BASIC (e.g XDP_TX and
XDP_PASS or XDP_REDIRECT are handled differently in the ebpf programs installed
on the tester and DUT devices). However, combining netdev_xdp_act and xdp_action
enum definitions, I think we can keep this logic in xdp_feature userspace part
and we can get rid of the XDP_FEATURE_* enum above.
I will fix it in v5.
Regards,
Lorenzo
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
[-- Attachment #2: Type: text/plain, Size: 162 bytes --]
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
@ 2023-01-29 18:48 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-29 18:48 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: bpf, Network Development, Alexei Starovoitov, Daniel Borkmann,
Andrii Nakryiko, David S. Miller, Jakub Kicinski, Paolo Abeni,
Eric Dumazet, Jesper Dangaard Brouer,
Toke Høiland-Jørgensen, Kumar Kartikeya Dwivedi,
Marek Majtyka, Saeed Mahameed, anthony.l.nguyen, Andy Gospodarek,
vladimir.oltean, Felix Fietkau, john, Leon Romanovsky,
Simon Horman, Ariel Elior, christophe.jaillet, ecree.xilinx,
Michael S. Tsirkin, Björn Töpel, Karlsson, Magnus,
Fijalkowski, Maciej, intel-wired-lan, Lorenzo Bianconi,
Martin KaFai Lau, Stanislav Fomichev
[-- Attachment #1: Type: text/plain, Size: 2003 bytes --]
On Jan 28, Alexei Starovoitov wrote:
> On Sat, Jan 28, 2023 at 6:07 AM Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> > diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h
> > new file mode 100644
> > index 000000000000..28d7614c4f02
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/xdp_features.h
> > @@ -0,0 +1,33 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +
> > +/* test commands */
> > +enum test_commands {
> > + CMD_STOP, /* CMD */
> > + CMD_START, /* CMD + xdp feature */
> > + CMD_ECHO, /* CMD */
> > + CMD_ACK, /* CMD + data */
> > + CMD_GET_XDP_CAP, /* CMD */
> > + CMD_GET_STATS, /* CMD */
> > +};
> > +
> > +#define DUT_CTRL_PORT 12345
> > +#define DUT_ECHO_PORT 12346
> > +
> > +struct tlv_hdr {
> > + __be16 type;
> > + __be16 len;
> > + __be32 data[];
> > +};
> > +
> > +enum {
> > + XDP_FEATURE_ABORTED,
> > + XDP_FEATURE_DROP,
> > + XDP_FEATURE_PASS,
> > + XDP_FEATURE_TX,
> > + XDP_FEATURE_REDIRECT,
> > + XDP_FEATURE_NDO_XMIT,
> > + XDP_FEATURE_XSK_ZEROCOPY,
> > + XDP_FEATURE_HW_OFFLOAD,
> > + XDP_FEATURE_RX_SG,
> > + XDP_FEATURE_NDO_XMIT_SG,
> > +};
>
> This doesn't match the kernel.
> How did you test this?
> What should be the way to prevent such mistakes in the future?
Hi Alexei,
I added the XDP_FEATURE_* enum above since the XDP compliance test tool needs
to differentiate between actions in NETDEV_XDP_ACT_BASIC (e.g XDP_TX and
XDP_PASS or XDP_REDIRECT are handled differently in the ebpf programs installed
on the tester and DUT devices). However, combining netdev_xdp_act and xdp_action
enum definitions, I think we can keep this logic in xdp_feature userspace part
and we can get rid of the XDP_FEATURE_* enum above.
I will fix it in v5.
Regards,
Lorenzo
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 32+ messages in thread
* Re: [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
2023-01-28 14:06 ` [Intel-wired-lan] " Lorenzo Bianconi
@ 2023-01-30 18:59 ` Stanislav Fomichev
-1 siblings, 0 replies; 32+ messages in thread
From: Stanislav Fomichev @ 2023-01-30 18:59 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: bpf, netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet,
hawk, toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau
On 01/28, Lorenzo Bianconi wrote:
> Introduce xdp_features tool in order to test XDP features supported by
> the NIC and match them against advertised ones.
> In order to test supported/advertised XDP features, xdp_features must
> run on the Device Under Test (DUT) and on a Tester device.
> xdp_features opens a control TCP channel between DUT and Tester devices
> to send control commands from Tester to the DUT and a UDP data channel
> where the Tester sends UDP 'echo' packets and the DUT is expected to
> reply back with the same packet. DUT installs multiple XDP programs on the
> NIC to test XDP capabilities and reports back to the Tester some XDP
> stats.
> Currently xdp_features supports the following XDP features:
> - XDP_DROP
> - XDP_PASS
> - XDP_TX
> - XDP_REDIRECT
> - XDP_REDIRECT_TARGET
> Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
> ---
> tools/testing/selftests/bpf/.gitignore | 1 +
> tools/testing/selftests/bpf/Makefile | 11 +-
> .../selftests/bpf/progs/xdp_features.c | 275 +++++++
> .../selftests/bpf/test_xdp_features.sh | 100 +++
> tools/testing/selftests/bpf/xdp_features.c | 731 ++++++++++++++++++
> tools/testing/selftests/bpf/xdp_features.h | 33 +
> 6 files changed, 1149 insertions(+), 2 deletions(-)
> create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c
> create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh
> create mode 100644 tools/testing/selftests/bpf/xdp_features.c
> create mode 100644 tools/testing/selftests/bpf/xdp_features.h
> diff --git a/tools/testing/selftests/bpf/.gitignore
> b/tools/testing/selftests/bpf/.gitignore
> index 4aa5bba956ff..116fecf80ca1 100644
> --- a/tools/testing/selftests/bpf/.gitignore
> +++ b/tools/testing/selftests/bpf/.gitignore
> @@ -48,3 +48,4 @@ xskxceiver
> xdp_redirect_multi
> xdp_synproxy
> xdp_hw_metadata
> +xdp_features
> diff --git a/tools/testing/selftests/bpf/Makefile
> b/tools/testing/selftests/bpf/Makefile
> index 53eae7be8dff..6f06b03d93cd 100644
> --- a/tools/testing/selftests/bpf/Makefile
> +++ b/tools/testing/selftests/bpf/Makefile
> @@ -73,7 +73,8 @@ TEST_PROGS := test_kmod.sh \
> test_bpftool.sh \
> test_bpftool_metadata.sh \
> test_doc_build.sh \
> - test_xsk.sh
> + test_xsk.sh \
> + test_xdp_features.sh
> TEST_PROGS_EXTENDED := with_addr.sh \
> with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
> @@ -83,7 +84,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \
> TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
> flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
> test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
> - xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
> + xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
> + xdp_features
> TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
> TEST_GEN_FILES += liburandom_read.so
> @@ -385,6 +387,7 @@ test_subskeleton_lib.skel.h-deps :=
> test_subskeleton_lib2.bpf.o test_subskeleton
> test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
> xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
> xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
> +xdp_features.skel.h-deps := xdp_features.bpf.o
> LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach
> skel,$(LINKED_SKELS),$($(skel)-deps)))
> @@ -586,6 +589,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c
> $(OUTPUT)/network_helpers.o $(OUTPU
> $(call msg,BINARY,,$@)
> $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
> +$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o
> $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)
> + $(call msg,BINARY,,$@)
> + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
> +
> # Make sure we are able to include and link libbpf against c++.
> $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h
> $(BPFOBJ)
> $(call msg,CXX,,$@)
> diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c
> b/tools/testing/selftests/bpf/progs/xdp_features.c
> new file mode 100644
> index 000000000000..205a4526ea68
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/xdp_features.c
> @@ -0,0 +1,275 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#include <stdbool.h>
> +#include <linux/bpf.h>
> +#include <linux/netdev.h>
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_endian.h>
> +#include <bpf/bpf_tracing.h>
> +#include <linux/if_ether.h>
> +#include <linux/ip.h>
> +#include <linux/ipv6.h>
> +#include <linux/in.h>
> +#include <linux/in6.h>
> +#include <linux/udp.h>
> +#include <asm-generic/errno-base.h>
> +
> +#include "xdp_features.h"
> +
> +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \
> + (a).s6_addr32[1] == (b).s6_addr32[1] && \
> + (a).s6_addr32[2] == (b).s6_addr32[2] && \
> + (a).s6_addr32[3] == (b).s6_addr32[3])
> +
> +struct net_device;
> +struct bpf_prog;
> +
> +struct xdp_cpumap_stats {
> + unsigned int redirect;
> + unsigned int pass;
> + unsigned int drop;
> +};
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_ARRAY);
> + __type(key, __u32);
> + __type(value, __u32);
> + __uint(max_entries, 1);
> +} stats SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_ARRAY);
> + __type(key, __u32);
> + __type(value, __u32);
> + __uint(max_entries, 1);
> +} dut_stats SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_CPUMAP);
> + __uint(key_size, sizeof(__u32));
> + __uint(value_size, sizeof(struct bpf_cpumap_val));
> + __uint(max_entries, 1);
> +} cpu_map SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_DEVMAP);
> + __uint(key_size, sizeof(__u32));
> + __uint(value_size, sizeof(struct bpf_devmap_val));
> + __uint(max_entries, 1);
> +} dev_map SEC(".maps");
> +
> +const volatile __u32 expected_feature = XDP_FEATURE_PASS;
> +const volatile union {
> + struct in_addr ip;
> + struct in6_addr ip6;
> +} tester_addr;
> +const volatile union {
> + struct in_addr ip;
> + struct in6_addr ip6;
> +} dut_addr;
> +
> +static __always_inline int xdp_process_echo_packet(struct xdp_md *xdp,
> bool dut)
> +{
> + void *data_end = (void *)(long)xdp->data_end;
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + struct tlv_hdr *tlv;
> + struct udphdr *uh;
> + __be16 port;
> + __u8 *cmd;
> +
> + if (eh + 1 > (struct ethhdr *)data_end)
> + return -EINVAL;
> +
> + if (eh->h_proto == bpf_htons(ETH_P_IP)) {
> + struct iphdr *ih = (struct iphdr *)(eh + 1);
> + __be32 saddr = dut ? tester_addr.ip.s_addr : dut_addr.ip.s_addr;
> + __be32 daddr = dut ? dut_addr.ip.s_addr : tester_addr.ip.s_addr;
> +
> + ih = (struct iphdr *)(eh + 1);
> + if (ih + 1 > (struct iphdr *)data_end)
> + return -EINVAL;
> +
> + if (saddr != ih->saddr)
> + return -EINVAL;
> +
> + if (daddr != ih->daddr)
> + return -EINVAL;
> +
> + if (ih->protocol != IPPROTO_UDP)
> + return -EINVAL;
> +
> + uh = (struct udphdr *)(ih + 1);
> + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
> + struct in6_addr saddr = dut ? tester_addr.ip6 : dut_addr.ip6;
> + struct in6_addr daddr = dut ? dut_addr.ip6 : tester_addr.ip6;
> + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
> +
> + if (ih6 + 1 > (struct ipv6hdr *)data_end)
> + return -EINVAL;
> +
> + if (!ipv6_addr_equal(saddr, ih6->saddr))
> + return -EINVAL;
> +
> + if (!ipv6_addr_equal(daddr, ih6->daddr))
> + return -EINVAL;
> +
> + if (ih6->nexthdr != IPPROTO_UDP)
> + return -EINVAL;
> +
> + uh = (struct udphdr *)(ih6 + 1);
> + } else {
> + return -EINVAL;
> + }
> +
> + if (uh + 1 > (struct udphdr *)data_end)
> + return -EINVAL;
> +
> + port = dut ? uh->dest : uh->source;
> + if (port != bpf_htons(DUT_ECHO_PORT))
> + return -EINVAL;
> +
> + tlv = (struct tlv_hdr *)(uh + 1);
> + if (tlv + 1 > data_end)
> + return -EINVAL;
> +
> + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
> +}
> +
> +SEC("xdp")
> +int xdp_tester(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + switch (expected_feature) {
> + case XDP_FEATURE_NDO_XMIT:
> + case XDP_FEATURE_TX:
> + if (xdp_process_echo_packet(xdp, true))
> + goto out;
> + break;
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_REDIRECT:
> + if (xdp_process_echo_packet(xdp, false))
> + goto out;
> + break;
> + default:
> + goto out;
> + }
> +
> + val = bpf_map_lookup_elem(&stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> +out:
> + return XDP_PASS;
> +}
> +
> +SEC("xdp")
> +int xdp_do_pass(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_PASS;
> +}
> +
> +SEC("xdp")
> +int xdp_do_drop(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_DROP;
> +}
> +
> +SEC("xdp")
> +int xdp_do_aborted(struct xdp_md *xdp)
> +{
> + return xdp_process_echo_packet(xdp, true) ? XDP_PASS : XDP_ABORTED;
> +}
> +
> +SEC("xdp")
> +int xdp_do_tx(struct xdp_md *xdp)
> +{
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + __u8 tmp_mac[ETH_ALEN];
> + __u32 *val, key = 0;
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
> + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
> + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_TX;
> +}
> +
> +SEC("xdp")
> +int xdp_do_redirect(struct xdp_md *xdp)
> +{
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + return bpf_redirect_map(&cpu_map, 0, 0);
> +}
> +
> +SEC("tp_btf/xdp_exception")
> +int BPF_PROG(xdp_exception, const struct net_device *dev,
> + const struct bpf_prog *xdp, __u32 act)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return 0;
> +}
> +
> +SEC("tp_btf/xdp_cpumap_kthread")
> +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
> + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return 0;
> +}
> +
> +SEC("xdp/cpumap")
> +int xdp_do_redirect_cpumap(struct xdp_md *xdp)
> +{
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + __u8 tmp_mac[ETH_ALEN];
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
> + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
> + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
> +
> + return bpf_redirect_map(&dev_map, 0, 0);
> +}
> +
> +char _license[] SEC("license") = "GPL";
> diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh
> b/tools/testing/selftests/bpf/test_xdp_features.sh
> new file mode 100755
> index 000000000000..987845e18ea7
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/test_xdp_features.sh
> @@ -0,0 +1,100 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +
> +readonly NS="ns1-$(mktemp -u XXXXXX)"
> +readonly V0_IP=10.10.0.11
> +readonly V1_IP=10.10.0.1
> +readonly V0_IP6=2001:db8::11
> +readonly V1_IP6=2001:db8::1
> +
> +ret=1
> +
> +setup() {
> + {
> + ip netns add ${NS}
> +
> + ip link add v1 type veth peer name v0 netns ${NS}
> +
> + ip link set v1 up
> + ip addr add $V1_IP/24 dev v1
> + ip addr add $V1_IP6/64 nodad dev v1
> + ip -n ${NS} link set dev v0 up
> + ip -n ${NS} addr add $V0_IP/24 dev v0
> + ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
> +
> + sysctl -w net.ipv4.ip_forward=1
> +
> + # Enable XDP mode and disable checksum offload
> + ethtool -K v1 gro on
> + ethtool -K v1 tx-checksumming off
> + ip netns exec ${NS} ethtool -K v0 gro on
> + ip netns exec ${NS} ethtool -K v0 tx-checksumming off
> + } > /dev/null 2>&1
> +}
> +
> +cleanup() {
> + ip link del v1 2> /dev/null
> + ip netns del ${NS} 2> /dev/null
> + [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2>
> /dev/null
> +}
> +
> +wait_for_dut_server() {
> + while sleep 1; do
> + ss -tlp | grep -q xdp_features
> + [ $? -eq 0 ] && break
> + done
> +}
> +
> +test_xdp_features() {
> + setup
> +
> + ## XDP_PASS
> + ./xdp_features -6 -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_PASS -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_DROP
> + ./xdp_features -f XDP_DROP -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_DROP -D $V1_IP -C $V1_IP
> -T $V0_IP v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_ABORTED
> + ./xdp_features -6 -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_ABORTED -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_TX
> + ./xdp_features -f XDP_TX -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_TX -D $V1_IP -C $V1_IP -T
> $V0_IP v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_REDIRECT
> + ./xdp_features -6 -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_REDIRECT -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_NDO_XMIT
> + ./xdp_features -f XDP_NDO_XMIT -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT -D $V1_IP -C
> $V1_IP -T $V0_IP v0
> +
> + ret=$?
> + cleanup
> +}
> +
> +set -e
> +trap cleanup 2 3 6 9
> +
> +test_xdp_features
> +
> +exit $ret
> diff --git a/tools/testing/selftests/bpf/xdp_features.c
> b/tools/testing/selftests/bpf/xdp_features.c
> new file mode 100644
> index 000000000000..9b94d5cdf654
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.c
> @@ -0,0 +1,731 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <uapi/linux/bpf.h>
> +#include <uapi/linux/netdev.h>
> +#include <linux/if_link.h>
> +#include <signal.h>
> +#include <argp.h>
> +#include <net/if.h>
> +#include <sys/socket.h>
> +#include <netinet/in.h>
> +#include <netinet/tcp.h>
> +#include <unistd.h>
> +#include <arpa/inet.h>
> +#include <bpf/bpf.h>
> +#include <bpf/libbpf.h>
> +#include <pthread.h>
> +
> +#include <network_helpers.h>
> +
> +#include "xdp_features.skel.h"
> +#include "xdp_features.h"
> +
> +#define RED(str) "\033[0;31m" str "\033[0m"
> +#define GREEN(str) "\033[0;32m" str "\033[0m"
> +#define YELLOW(str) "\033[0;33m" str "\033[0m"
> +
> +static struct env {
> + bool verbosity;
> + int ifindex;
> + unsigned int feature;
> + bool is_tester;
> + int family;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } dut_ctrl;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } dut;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } tester;
> +} env;
> +
> +#define BUFSIZE 128
> +
> +void test__fail(void) { /* for network_helpers.c */ }
> +
> +static int libbpf_print_fn(enum libbpf_print_level level,
> + const char *format, va_list args)
> +{
> + if (level == LIBBPF_DEBUG && !env.verbosity)
> + return 0;
> + return vfprintf(stderr, format, args);
> +}
> +
> +static volatile bool exiting;
> +
> +static void sig_handler(int sig)
> +{
> + exiting = true;
> +}
> +
> +const char *argp_program_version = "xdp-features 0.0";
> +const char argp_program_doc[] =
> +"XDP features detecion application.\n"
> +"\n"
> +"XDP features application checks the XDP advertised features match
> detected ones.\n"
> +"\n"
> +"USAGE: ./xdp-features [-6vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T
> <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
> +"\n"
> +"XDP features\n:"
> +"- XDP_PASS\n"
> +"- XDP_DROP\n"
> +"- XDP_ABORTED\n"
> +"- XDP_REDIRECT\n"
> +"- XDP_NDO_XMIT\n"
> +"- XDP_TX\n";
> +
> +static const struct argp_option opts[] = {
> + { "ipv6", '6', NULL, 0, "Use IPv6 network stack" },
> + { "verbose", 'v', NULL, 0, "Verbose debug output" },
> + { "tester", 't', NULL, 0, "Tester mode" },
> + { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
> + { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
> + { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
> + { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel"
> },
> + {},
> +};
> +
> +static int get_xdp_feature(const char *arg)
> +{
> + if (!strcmp(arg, "XDP_PASS"))
> + return XDP_FEATURE_PASS;
> + else if (!strcmp(arg, "XDP_DROP"))
> + return XDP_FEATURE_DROP;
> + else if (!strcmp(arg, "XDP_ABORTED"))
> + return XDP_FEATURE_ABORTED;
> + else if (!strcmp(arg, "XDP_REDIRECT"))
> + return XDP_FEATURE_REDIRECT;
> + else if (!strcmp(arg, "XDP_NDO_XMIT"))
> + return XDP_FEATURE_NDO_XMIT;
> + else if (!strcmp(arg, "XDP_TX"))
> + return XDP_FEATURE_TX;
> +
> + return -EINVAL;
> +}
> +
> +static char *get_xdp_feature_str(int feature)
> +{
> + switch (feature) {
> + case XDP_FEATURE_PASS:
> + return YELLOW("XDP_PASS");
> + case XDP_FEATURE_DROP:
> + return YELLOW("XDP_DROP");
> + case XDP_FEATURE_ABORTED:
> + return YELLOW("XDP_ABORTED");
> + case XDP_FEATURE_TX:
> + return YELLOW("XDP_TX");
> + case XDP_FEATURE_REDIRECT:
> + return YELLOW("XDP_REDIRECT");
> + case XDP_FEATURE_NDO_XMIT:
> + return YELLOW("XDP_NDO_XMIT");
> + default:
> + return "";
> + }
> +}
> +
> +static error_t parse_arg(int key, char *arg, struct argp_state *state)
> +{
> + switch (key) {
> + case '6':
> + env.family = AF_INET6;
> + break;
Thanks for making the changes! Since you're doing another respin to
address Alexei's feedback, maybe one thing we can also improve here
regarding v4-v6? Optionally, up to you, but IMO, it's much easier
to hard-code AF_INET6 everywhere:
socket(AF_INET6, ...)
inet_pton(AF_INET6, ...)
...
And then, if you want to use v4 by default, use '::ffff:127.0.0.1' as
the address. If the users need to use it with some other v4, they can also
pass the v4-mapped v6 address.
Up to you on whether to implement it or not, feel free to ignore me,
but IMO, that should avoid a lot of those env.family arguments and
making special cases for v4. Plus also removes the need for -6 argument.
The following would work:
./xdp_features ::ffff::<ipv4>
./xdp_features <ipv6>
(I'm assuming nothing runs exclusive non-dualstack v4 envs anymore)
> + case 'v':
> + env.verbosity = true;
> + break;
> + case 't':
> + env.is_tester = true;
> + break;
> + case 'f':
> + env.feature = get_xdp_feature(arg);
> + if (env.feature < 0) {
> + fprintf(stderr, "Invalid xdp feature: %s\n", arg);
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'D':
> + if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
> + &env.dut.addr, &env.dut.addrlen)) {
> + fprintf(stderr, "Invalid DUT address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'C':
> + if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
> + &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
> + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'T':
> + if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
> + &env.tester.addrlen)) {
> + fprintf(stderr, "Invalid Tester address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case ARGP_KEY_ARG:
> + errno = 0;
> + if (strlen(arg) >= IF_NAMESIZE) {
> + fprintf(stderr, "Invalid device name: %s\n", arg);
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> +
> + env.ifindex = if_nametoindex(arg);
> + if (!env.ifindex)
> + env.ifindex = strtoul(arg, NULL, 0);
> + if (!env.ifindex) {
> + fprintf(stderr,
> + "Bad interface index or name (%d): %s\n",
> + errno, strerror(errno));
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + default:
> + return ARGP_ERR_UNKNOWN;
> + }
> +
> + return 0;
> +}
> +
> +static const struct argp argp = {
> + .options = opts,
> + .parser = parse_arg,
> + .doc = argp_program_doc,
> +};
> +
> +static void set_env_defaul(void)
> +{
> + env.feature = XDP_FEATURE_PASS;
> + env.ifindex = -ENODEV;
> + env.family = AF_INET;
> + make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
> + &env.dut_ctrl.addrlen);
> + make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
> + &env.dut.addrlen);
> + make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
> + &env.tester.addrlen);
> +}
> +
> +static void *dut_echo_thread(void *arg)
> +{
> + unsigned char buf[sizeof(struct tlv_hdr)];
> + int sockfd = *(int *)arg;
> +
> + while (!exiting) {
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + size_t n;
> +
> + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
> + (struct sockaddr *)&addr, &addrlen);
> + if (n != ntohs(tlv->len))
> + continue;
> +
> + if (ntohs(tlv->type) != CMD_ECHO)
> + continue;
> +
> + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
> + (struct sockaddr *)&addr, addrlen);
> + }
> +
> + pthread_exit((void *)0);
> + close(sockfd);
> +
> + return NULL;
> +}
> +
> +static int dut_run_echo_thread(pthread_t *t, int *sockfd)
> +{
> + int err;
> +
> + sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
> + DUT_ECHO_PORT, 0, 1);
> + if (!sockfd) {
> + fprintf(stderr, "Failed to create echo socket\n");
> + return -errno;
> + }
> +
> + /* start echo channel */
> + err = pthread_create(t, NULL, dut_echo_thread, sockfd);
> + if (err) {
> + fprintf(stderr, "Failed creating dut_echo thread: %s\n",
> + strerror(-err));
> + free_fds(sockfd, 1);
> + return -EINVAL;
> + }
> +
> + return 0;
> +}
> +
> +static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
> + int flags)
> +{
> + struct bpf_program *prog;
> + unsigned int key = 0;
> + int err, fd = 0;
> +
> + switch (feature) {
> + case XDP_FEATURE_TX:
> + prog = skel->progs.xdp_do_tx;
> + break;
> + case XDP_FEATURE_DROP:
> + prog = skel->progs.xdp_do_drop;
> + break;
> + case XDP_FEATURE_ABORTED:
> + prog = skel->progs.xdp_do_aborted;
> + break;
> + case XDP_FEATURE_PASS:
> + prog = skel->progs.xdp_do_pass;
> + break;
> + case XDP_FEATURE_NDO_XMIT: {
> + struct bpf_devmap_val entry = {
> + .ifindex = env.ifindex,
> + };
> +
> + err = bpf_map__update_elem(skel->maps.dev_map,
> + &key, sizeof(key),
> + &entry, sizeof(entry), 0);
> + if (err < 0)
> + return err;
> +
> + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
> + }
> + case XDP_FEATURE_REDIRECT: {
> + struct bpf_cpumap_val entry = {
> + .qsize = 2048,
> + .bpf_prog.fd = fd,
> + };
> +
> + err = bpf_map__update_elem(skel->maps.cpu_map,
> + &key, sizeof(key),
> + &entry, sizeof(entry), 0);
> + if (err < 0)
> + return err;
> +
> + prog = skel->progs.xdp_do_redirect;
> + break;
> + }
> + default:
> + return -EINVAL;
> + }
> +
> + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
> + if (err)
> + fprintf(stderr,
> + "Failed to attach XDP program to ifindex %d\n",
> + env.ifindex);
> + return err;
> +}
> +
> +static int __recv_msg(int sockfd, void *buf, size_t bufsize,
> + unsigned int *val, unsigned int val_size)
> +{
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int len, n = sizeof(*tlv), i = 0;
> +
> + len = recv(sockfd, buf, bufsize, 0);
> + if (len != ntohs(tlv->len))
> + return -EINVAL;
> +
> + while (n < len && i < val_size) {
> + val[i] = ntohl(tlv->data[i]);
> + n += sizeof(tlv->data[0]);
> + i++;
> + }
> +
> + return i;
> +}
> +
> +static int recv_msg(int sockfd, void *buf, size_t bufsize)
> +{
> + return __recv_msg(sockfd, buf, bufsize, NULL, 0);
> +}
> +
> +static int dut_run(struct xdp_features *skel)
> +{
> + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> + int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
> + struct sockaddr_storage ctrl_addr;
> + pthread_t dut_thread;
> + socklen_t addrlen;
> +
> + sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
> + DUT_CTRL_PORT, 0, 1);
> + if (!sockfd) {
> + fprintf(stderr, "Failed to create DUT socket\n");
> + return -errno;
> + }
> +
> + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
> + if (ctrl_sockfd < 0) {
> + fprintf(stderr, "Failed to accept connection on DUT socket\n");
> + free_fds(sockfd, 1);
> + return -errno;
> + }
> +
> + /* CTRL loop */
> + while (!exiting) {
> + unsigned char buf[BUFSIZE] = {};
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> +
> + err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
> + if (err)
> + continue;
> +
> + switch (ntohs(tlv->type)) {
> + case CMD_START: {
> + if (state == CMD_START)
> + continue;
> +
> + state = CMD_START;
> + /* Load the XDP program on the DUT */
> + err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
> + if (err)
> + goto out;
> +
> + err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
> + if (err < 0)
> + goto out;
> +
> + tlv->type = htons(CMD_ACK);
> + tlv->len = htons(sizeof(*tlv));
> + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + case CMD_STOP:
> + if (state != CMD_START)
> + break;
> +
> + state = CMD_STOP;
> +
> + exiting = true;
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> +
> + tlv->type = htons(CMD_ACK);
> + tlv->len = htons(sizeof(*tlv));
> + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> + goto end_thread;
> + case CMD_GET_XDP_CAP: {
> + LIBBPF_OPTS(bpf_xdp_query_opts, opts);
> + size_t n;
> +
> + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
> + &opts);
> + if (err) {
> + fprintf(stderr,
> + "Failed to query XDP cap for ifindex %d\n",
> + env.ifindex);
> + goto end_thread;
> + }
> +
> + tlv->type = htons(CMD_ACK);
> + n = sizeof(*tlv) + sizeof(opts.feature_flags);
> + tlv->len = htons(n);
> + tlv->data[0] = htonl(opts.feature_flags);
> +
> + err = send(ctrl_sockfd, buf, n, 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + case CMD_GET_STATS: {
> + unsigned int key = 0, val;
> + size_t n;
> +
> + err = bpf_map__lookup_elem(skel->maps.dut_stats,
> + &key, sizeof(key),
> + &val, sizeof(val), 0);
> + if (err) {
> + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> + goto end_thread;
> + }
> +
> + tlv->type = htons(CMD_ACK);
> + n = sizeof(*tlv) + sizeof(val);
> + tlv->len = htons(n);
> + tlv->data[0] = htonl(val);
> +
> + err = send(ctrl_sockfd, buf, n, 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + default:
> + break;
> + }
> + }
> +
> +end_thread:
> + pthread_join(dut_thread, NULL);
> +out:
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> + close(ctrl_sockfd);
> + free_fds(sockfd, 1);
> +
> + return err;
> +}
> +
> +static bool tester_collect_advertised_cap(unsigned int cap)
> +{
> + switch (env.feature) {
> + case XDP_FEATURE_ABORTED:
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_TX:
> + return cap & NETDEV_XDP_ACT_BASIC;
> + case XDP_FEATURE_REDIRECT:
> + return cap & NETDEV_XDP_ACT_REDIRECT;
> + case XDP_FEATURE_NDO_XMIT:
> + return cap & NETDEV_XDP_ACT_NDO_XMIT;
> + default:
> + return false;
> + }
> +}
> +
> +static bool tester_collect_detected_cap(struct xdp_features *skel,
> + unsigned int dut_stats)
> +{
> + unsigned int err, key = 0, val;
> +
> + if (!dut_stats)
> + return false;
> +
> + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
> + &val, sizeof(val), 0);
> + if (err) {
> + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> + return false;
> + }
> +
> + switch (env.feature) {
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_TX:
> + case XDP_FEATURE_REDIRECT:
> + case XDP_FEATURE_NDO_XMIT:
> + return val > 0;
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_ABORTED:
> + return val == 0;
> + default:
> + return false;
> + }
> +}
> +
> +static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
> + unsigned int *val, unsigned int val_size)
> +{
> + unsigned char buf[BUFSIZE] = {};
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int n = sizeof(*tlv), err;
> +
> + tlv->type = htons(cmd);
> + switch (cmd) {
> + case CMD_START:
> + tlv->data[0] = htonl(env.feature);
> + n += sizeof(*val);
> + break;
> + default:
> + break;
> + }
> + tlv->len = htons(n);
> +
> + err = send(sockfd, buf, n, 0);
> + if (err < 0)
> + return err;
> +
> + err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
> + if (err < 0)
> + return err;
> +
> + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
> +}
> +
> +static int send_and_recv_msg(int sockfd, enum test_commands cmd)
> +{
> + return __send_and_recv_msg(sockfd, cmd, NULL, 0);
> +}
> +
> +static int send_echo_msg(void)
> +{
> + unsigned char buf[sizeof(struct tlv_hdr)];
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int sockfd, n;
> +
> + sockfd = socket(env.family, SOCK_DGRAM, 0);
> + if (sockfd < 0) {
> + fprintf(stderr, "Failed to create echo socket\n");
> + return -errno;
> + }
> +
> + tlv->type = htons(CMD_ECHO);
> + tlv->len = htons(sizeof(*tlv));
> +
> + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
> + (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
> + close(sockfd);
> +
> + return n == ntohs(tlv->len) ? 0 : -EINVAL;
> +}
> +
> +static int tester_run(struct xdp_features *skel)
> +{
> + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> + bool advertised_cap;
> + unsigned int val[1];
> + int i, err, sockfd;
> + bool detected_cap;
> +
> + sockfd = socket(env.family, SOCK_STREAM, 0);
> + if (sockfd < 0) {
> + fprintf(stderr, "Failed to create tester socket\n");
> + return -errno;
> + }
> +
> + if (settimeo(sockfd, 1000) < 0)
> + return -EINVAL;
> +
> + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
> + env.dut_ctrl.addrlen);
> + if (err) {
> + fprintf(stderr, "Failed to connect to the DUT\n");
> + return -errno;
> + }
> +
> + err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
> + ARRAY_SIZE(val));
> + if (err < 0) {
> + close(sockfd);
> + return err;
> + }
> +
> + advertised_cap = tester_collect_advertised_cap(val[0]);
> +
> + err = bpf_xdp_attach(env.ifindex,
> + bpf_program__fd(skel->progs.xdp_tester),
> + flags, NULL);
> + if (err) {
> + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
> + env.ifindex);
> + goto out;
> + }
> +
> + err = send_and_recv_msg(sockfd, CMD_START);
> + if (err)
> + goto out;
> +
> + for (i = 0; i < 10 && !exiting; i++) {
> + err = send_echo_msg();
> + if (err < 0)
> + goto out;
> +
> + sleep(1);
> + }
> +
> + err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
> + if (err)
> + goto out;
> +
> + /* stop the test */
> + err = send_and_recv_msg(sockfd, CMD_STOP);
> + /* send a new echo message to wake echo thread of the dut */
> + send_echo_msg();
> +
> + detected_cap = tester_collect_detected_cap(skel, val[0]);
> +
> + fprintf(stdout, "Feature %s: [%s][%s]\n",
> get_xdp_feature_str(env.feature),
> + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
> + advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
> +out:
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> + close(sockfd);
> + return err < 0 ? err : 0;
> +}
> +
> +static void set_skel_rodata(struct xdp_features *skel)
> +{
> + skel->rodata->expected_feature = env.feature;
> + if (env.family == AF_INET6) {
> + struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
> + struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
> +
> + skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
> + skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
> + } else {
> + struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
> + struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
> +
> + skel->rodata->tester_addr.ip = tester_addr->sin_addr;
> + skel->rodata->dut_addr.ip = dut_addr->sin_addr;
> + }
> +}
> +
> +int main(int argc, char **argv)
> +{
> + struct xdp_features *skel;
> + int err;
> +
> + libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
> + libbpf_set_print(libbpf_print_fn);
> +
> + signal(SIGINT, sig_handler);
> + signal(SIGTERM, sig_handler);
> +
> + set_env_defaul();
> +
> + /* Parse command line arguments */
> + err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
> + if (err)
> + return err;
> +
> + if (env.ifindex < 0) {
> + fprintf(stderr, "Invalid ifindex\n");
> + return -ENODEV;
> + }
> +
> + /* Load and verify BPF application */
> + skel = xdp_features__open();
> + if (!skel) {
> + fprintf(stderr, "Failed to open and load BPF skeleton\n");
> + return -EINVAL;
> + }
> +
> + set_skel_rodata(skel);
> +
> + /* Load & verify BPF programs */
> + err = xdp_features__load(skel);
> + if (err) {
> + fprintf(stderr, "Failed to load and verify BPF skeleton\n");
> + goto cleanup;
> + }
> +
> + err = xdp_features__attach(skel);
> + if (err) {
> + fprintf(stderr, "Failed to attach BPF skeleton\n");
> + goto cleanup;
> + }
> +
> + if (env.is_tester) {
> + /* Tester */
> + fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
> + err = tester_run(skel);
> + } else {
> + /* DUT */
> + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
> + err = dut_run(skel);
> + }
> +
> +cleanup:
> + xdp_features__destroy(skel);
> +
> + return err < 0 ? -err : 0;
> +}
> diff --git a/tools/testing/selftests/bpf/xdp_features.h
> b/tools/testing/selftests/bpf/xdp_features.h
> new file mode 100644
> index 000000000000..28d7614c4f02
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.h
> @@ -0,0 +1,33 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +/* test commands */
> +enum test_commands {
> + CMD_STOP, /* CMD */
> + CMD_START, /* CMD + xdp feature */
> + CMD_ECHO, /* CMD */
> + CMD_ACK, /* CMD + data */
> + CMD_GET_XDP_CAP, /* CMD */
> + CMD_GET_STATS, /* CMD */
> +};
> +
> +#define DUT_CTRL_PORT 12345
> +#define DUT_ECHO_PORT 12346
> +
> +struct tlv_hdr {
> + __be16 type;
> + __be16 len;
> + __be32 data[];
> +};
> +
> +enum {
> + XDP_FEATURE_ABORTED,
> + XDP_FEATURE_DROP,
> + XDP_FEATURE_PASS,
> + XDP_FEATURE_TX,
> + XDP_FEATURE_REDIRECT,
> + XDP_FEATURE_NDO_XMIT,
> + XDP_FEATURE_XSK_ZEROCOPY,
> + XDP_FEATURE_HW_OFFLOAD,
> + XDP_FEATURE_RX_SG,
> + XDP_FEATURE_NDO_XMIT_SG,
> +};
> --
> 2.39.1
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
@ 2023-01-30 18:59 ` Stanislav Fomichev
0 siblings, 0 replies; 32+ messages in thread
From: Stanislav Fomichev @ 2023-01-30 18:59 UTC (permalink / raw)
To: Lorenzo Bianconi
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, daniel,
andrii, intel-wired-lan, simon.horman, kuba, pabeni, aelior,
hawk, christophe.jaillet, memxor, john, bjorn, bpf,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
On 01/28, Lorenzo Bianconi wrote:
> Introduce xdp_features tool in order to test XDP features supported by
> the NIC and match them against advertised ones.
> In order to test supported/advertised XDP features, xdp_features must
> run on the Device Under Test (DUT) and on a Tester device.
> xdp_features opens a control TCP channel between DUT and Tester devices
> to send control commands from Tester to the DUT and a UDP data channel
> where the Tester sends UDP 'echo' packets and the DUT is expected to
> reply back with the same packet. DUT installs multiple XDP programs on the
> NIC to test XDP capabilities and reports back to the Tester some XDP
> stats.
> Currently xdp_features supports the following XDP features:
> - XDP_DROP
> - XDP_PASS
> - XDP_TX
> - XDP_REDIRECT
> - XDP_REDIRECT_TARGET
> Co-developed-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
> ---
> tools/testing/selftests/bpf/.gitignore | 1 +
> tools/testing/selftests/bpf/Makefile | 11 +-
> .../selftests/bpf/progs/xdp_features.c | 275 +++++++
> .../selftests/bpf/test_xdp_features.sh | 100 +++
> tools/testing/selftests/bpf/xdp_features.c | 731 ++++++++++++++++++
> tools/testing/selftests/bpf/xdp_features.h | 33 +
> 6 files changed, 1149 insertions(+), 2 deletions(-)
> create mode 100644 tools/testing/selftests/bpf/progs/xdp_features.c
> create mode 100755 tools/testing/selftests/bpf/test_xdp_features.sh
> create mode 100644 tools/testing/selftests/bpf/xdp_features.c
> create mode 100644 tools/testing/selftests/bpf/xdp_features.h
> diff --git a/tools/testing/selftests/bpf/.gitignore
> b/tools/testing/selftests/bpf/.gitignore
> index 4aa5bba956ff..116fecf80ca1 100644
> --- a/tools/testing/selftests/bpf/.gitignore
> +++ b/tools/testing/selftests/bpf/.gitignore
> @@ -48,3 +48,4 @@ xskxceiver
> xdp_redirect_multi
> xdp_synproxy
> xdp_hw_metadata
> +xdp_features
> diff --git a/tools/testing/selftests/bpf/Makefile
> b/tools/testing/selftests/bpf/Makefile
> index 53eae7be8dff..6f06b03d93cd 100644
> --- a/tools/testing/selftests/bpf/Makefile
> +++ b/tools/testing/selftests/bpf/Makefile
> @@ -73,7 +73,8 @@ TEST_PROGS := test_kmod.sh \
> test_bpftool.sh \
> test_bpftool_metadata.sh \
> test_doc_build.sh \
> - test_xsk.sh
> + test_xsk.sh \
> + test_xdp_features.sh
> TEST_PROGS_EXTENDED := with_addr.sh \
> with_tunnels.sh ima_setup.sh verify_sig_setup.sh \
> @@ -83,7 +84,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \
> TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
> flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
> test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
> - xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata
> + xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
> + xdp_features
> TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file
> TEST_GEN_FILES += liburandom_read.so
> @@ -385,6 +387,7 @@ test_subskeleton_lib.skel.h-deps :=
> test_subskeleton_lib2.bpf.o test_subskeleton
> test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o
> xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o
> xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o
> +xdp_features.skel.h-deps := xdp_features.bpf.o
> LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach
> skel,$(LINKED_SKELS),$($(skel)-deps)))
> @@ -586,6 +589,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c
> $(OUTPUT)/network_helpers.o $(OUTPU
> $(call msg,BINARY,,$@)
> $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
> +$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o
> $(OUTPUT)/xdp_features.skel.h | $(OUTPUT)
> + $(call msg,BINARY,,$@)
> + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@
> +
> # Make sure we are able to include and link libbpf against c++.
> $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h
> $(BPFOBJ)
> $(call msg,CXX,,$@)
> diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c
> b/tools/testing/selftests/bpf/progs/xdp_features.c
> new file mode 100644
> index 000000000000..205a4526ea68
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/xdp_features.c
> @@ -0,0 +1,275 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#include <stdbool.h>
> +#include <linux/bpf.h>
> +#include <linux/netdev.h>
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_endian.h>
> +#include <bpf/bpf_tracing.h>
> +#include <linux/if_ether.h>
> +#include <linux/ip.h>
> +#include <linux/ipv6.h>
> +#include <linux/in.h>
> +#include <linux/in6.h>
> +#include <linux/udp.h>
> +#include <asm-generic/errno-base.h>
> +
> +#include "xdp_features.h"
> +
> +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \
> + (a).s6_addr32[1] == (b).s6_addr32[1] && \
> + (a).s6_addr32[2] == (b).s6_addr32[2] && \
> + (a).s6_addr32[3] == (b).s6_addr32[3])
> +
> +struct net_device;
> +struct bpf_prog;
> +
> +struct xdp_cpumap_stats {
> + unsigned int redirect;
> + unsigned int pass;
> + unsigned int drop;
> +};
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_ARRAY);
> + __type(key, __u32);
> + __type(value, __u32);
> + __uint(max_entries, 1);
> +} stats SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_ARRAY);
> + __type(key, __u32);
> + __type(value, __u32);
> + __uint(max_entries, 1);
> +} dut_stats SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_CPUMAP);
> + __uint(key_size, sizeof(__u32));
> + __uint(value_size, sizeof(struct bpf_cpumap_val));
> + __uint(max_entries, 1);
> +} cpu_map SEC(".maps");
> +
> +struct {
> + __uint(type, BPF_MAP_TYPE_DEVMAP);
> + __uint(key_size, sizeof(__u32));
> + __uint(value_size, sizeof(struct bpf_devmap_val));
> + __uint(max_entries, 1);
> +} dev_map SEC(".maps");
> +
> +const volatile __u32 expected_feature = XDP_FEATURE_PASS;
> +const volatile union {
> + struct in_addr ip;
> + struct in6_addr ip6;
> +} tester_addr;
> +const volatile union {
> + struct in_addr ip;
> + struct in6_addr ip6;
> +} dut_addr;
> +
> +static __always_inline int xdp_process_echo_packet(struct xdp_md *xdp,
> bool dut)
> +{
> + void *data_end = (void *)(long)xdp->data_end;
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + struct tlv_hdr *tlv;
> + struct udphdr *uh;
> + __be16 port;
> + __u8 *cmd;
> +
> + if (eh + 1 > (struct ethhdr *)data_end)
> + return -EINVAL;
> +
> + if (eh->h_proto == bpf_htons(ETH_P_IP)) {
> + struct iphdr *ih = (struct iphdr *)(eh + 1);
> + __be32 saddr = dut ? tester_addr.ip.s_addr : dut_addr.ip.s_addr;
> + __be32 daddr = dut ? dut_addr.ip.s_addr : tester_addr.ip.s_addr;
> +
> + ih = (struct iphdr *)(eh + 1);
> + if (ih + 1 > (struct iphdr *)data_end)
> + return -EINVAL;
> +
> + if (saddr != ih->saddr)
> + return -EINVAL;
> +
> + if (daddr != ih->daddr)
> + return -EINVAL;
> +
> + if (ih->protocol != IPPROTO_UDP)
> + return -EINVAL;
> +
> + uh = (struct udphdr *)(ih + 1);
> + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) {
> + struct in6_addr saddr = dut ? tester_addr.ip6 : dut_addr.ip6;
> + struct in6_addr daddr = dut ? dut_addr.ip6 : tester_addr.ip6;
> + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1);
> +
> + if (ih6 + 1 > (struct ipv6hdr *)data_end)
> + return -EINVAL;
> +
> + if (!ipv6_addr_equal(saddr, ih6->saddr))
> + return -EINVAL;
> +
> + if (!ipv6_addr_equal(daddr, ih6->daddr))
> + return -EINVAL;
> +
> + if (ih6->nexthdr != IPPROTO_UDP)
> + return -EINVAL;
> +
> + uh = (struct udphdr *)(ih6 + 1);
> + } else {
> + return -EINVAL;
> + }
> +
> + if (uh + 1 > (struct udphdr *)data_end)
> + return -EINVAL;
> +
> + port = dut ? uh->dest : uh->source;
> + if (port != bpf_htons(DUT_ECHO_PORT))
> + return -EINVAL;
> +
> + tlv = (struct tlv_hdr *)(uh + 1);
> + if (tlv + 1 > data_end)
> + return -EINVAL;
> +
> + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL;
> +}
> +
> +SEC("xdp")
> +int xdp_tester(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + switch (expected_feature) {
> + case XDP_FEATURE_NDO_XMIT:
> + case XDP_FEATURE_TX:
> + if (xdp_process_echo_packet(xdp, true))
> + goto out;
> + break;
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_REDIRECT:
> + if (xdp_process_echo_packet(xdp, false))
> + goto out;
> + break;
> + default:
> + goto out;
> + }
> +
> + val = bpf_map_lookup_elem(&stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> +out:
> + return XDP_PASS;
> +}
> +
> +SEC("xdp")
> +int xdp_do_pass(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_PASS;
> +}
> +
> +SEC("xdp")
> +int xdp_do_drop(struct xdp_md *xdp)
> +{
> + __u32 *val, key = 0;
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_DROP;
> +}
> +
> +SEC("xdp")
> +int xdp_do_aborted(struct xdp_md *xdp)
> +{
> + return xdp_process_echo_packet(xdp, true) ? XDP_PASS : XDP_ABORTED;
> +}
> +
> +SEC("xdp")
> +int xdp_do_tx(struct xdp_md *xdp)
> +{
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + __u8 tmp_mac[ETH_ALEN];
> + __u32 *val, key = 0;
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
> + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
> + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return XDP_TX;
> +}
> +
> +SEC("xdp")
> +int xdp_do_redirect(struct xdp_md *xdp)
> +{
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + return bpf_redirect_map(&cpu_map, 0, 0);
> +}
> +
> +SEC("tp_btf/xdp_exception")
> +int BPF_PROG(xdp_exception, const struct net_device *dev,
> + const struct bpf_prog *xdp, __u32 act)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return 0;
> +}
> +
> +SEC("tp_btf/xdp_cpumap_kthread")
> +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
> + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
> +{
> + __u32 *val, key = 0;
> +
> + val = bpf_map_lookup_elem(&dut_stats, &key);
> + if (val)
> + __sync_add_and_fetch(val, 1);
> +
> + return 0;
> +}
> +
> +SEC("xdp/cpumap")
> +int xdp_do_redirect_cpumap(struct xdp_md *xdp)
> +{
> + void *data = (void *)(long)xdp->data;
> + struct ethhdr *eh = data;
> + __u8 tmp_mac[ETH_ALEN];
> +
> + if (xdp_process_echo_packet(xdp, true))
> + return XDP_PASS;
> +
> + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN);
> + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN);
> + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN);
> +
> + return bpf_redirect_map(&dev_map, 0, 0);
> +}
> +
> +char _license[] SEC("license") = "GPL";
> diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh
> b/tools/testing/selftests/bpf/test_xdp_features.sh
> new file mode 100755
> index 000000000000..987845e18ea7
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/test_xdp_features.sh
> @@ -0,0 +1,100 @@
> +#!/bin/bash
> +# SPDX-License-Identifier: GPL-2.0
> +
> +readonly NS="ns1-$(mktemp -u XXXXXX)"
> +readonly V0_IP=10.10.0.11
> +readonly V1_IP=10.10.0.1
> +readonly V0_IP6=2001:db8::11
> +readonly V1_IP6=2001:db8::1
> +
> +ret=1
> +
> +setup() {
> + {
> + ip netns add ${NS}
> +
> + ip link add v1 type veth peer name v0 netns ${NS}
> +
> + ip link set v1 up
> + ip addr add $V1_IP/24 dev v1
> + ip addr add $V1_IP6/64 nodad dev v1
> + ip -n ${NS} link set dev v0 up
> + ip -n ${NS} addr add $V0_IP/24 dev v0
> + ip -n ${NS} addr add $V0_IP6/64 nodad dev v0
> +
> + sysctl -w net.ipv4.ip_forward=1
> +
> + # Enable XDP mode and disable checksum offload
> + ethtool -K v1 gro on
> + ethtool -K v1 tx-checksumming off
> + ip netns exec ${NS} ethtool -K v0 gro on
> + ip netns exec ${NS} ethtool -K v0 tx-checksumming off
> + } > /dev/null 2>&1
> +}
> +
> +cleanup() {
> + ip link del v1 2> /dev/null
> + ip netns del ${NS} 2> /dev/null
> + [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2>
> /dev/null
> +}
> +
> +wait_for_dut_server() {
> + while sleep 1; do
> + ss -tlp | grep -q xdp_features
> + [ $? -eq 0 ] && break
> + done
> +}
> +
> +test_xdp_features() {
> + setup
> +
> + ## XDP_PASS
> + ./xdp_features -6 -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_PASS -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_DROP
> + ./xdp_features -f XDP_DROP -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_DROP -D $V1_IP -C $V1_IP
> -T $V0_IP v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_ABORTED
> + ./xdp_features -6 -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_ABORTED -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_TX
> + ./xdp_features -f XDP_TX -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_TX -D $V1_IP -C $V1_IP -T
> $V0_IP v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_REDIRECT
> + ./xdp_features -6 -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -6 -t -f XDP_REDIRECT -D $V1_IP6 -C
> $V1_IP6 -T $V0_IP6 v0
> +
> + [ $? -ne 0 ] && exit
> +
> + ## XDP_NDO_XMIT
> + ./xdp_features -f XDP_NDO_XMIT -D $V1_IP -T $V0_IP v1 &
> + wait_for_dut_server
> + ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT -D $V1_IP -C
> $V1_IP -T $V0_IP v0
> +
> + ret=$?
> + cleanup
> +}
> +
> +set -e
> +trap cleanup 2 3 6 9
> +
> +test_xdp_features
> +
> +exit $ret
> diff --git a/tools/testing/selftests/bpf/xdp_features.c
> b/tools/testing/selftests/bpf/xdp_features.c
> new file mode 100644
> index 000000000000..9b94d5cdf654
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.c
> @@ -0,0 +1,731 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#include <uapi/linux/bpf.h>
> +#include <uapi/linux/netdev.h>
> +#include <linux/if_link.h>
> +#include <signal.h>
> +#include <argp.h>
> +#include <net/if.h>
> +#include <sys/socket.h>
> +#include <netinet/in.h>
> +#include <netinet/tcp.h>
> +#include <unistd.h>
> +#include <arpa/inet.h>
> +#include <bpf/bpf.h>
> +#include <bpf/libbpf.h>
> +#include <pthread.h>
> +
> +#include <network_helpers.h>
> +
> +#include "xdp_features.skel.h"
> +#include "xdp_features.h"
> +
> +#define RED(str) "\033[0;31m" str "\033[0m"
> +#define GREEN(str) "\033[0;32m" str "\033[0m"
> +#define YELLOW(str) "\033[0;33m" str "\033[0m"
> +
> +static struct env {
> + bool verbosity;
> + int ifindex;
> + unsigned int feature;
> + bool is_tester;
> + int family;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } dut_ctrl;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } dut;
> + struct {
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + } tester;
> +} env;
> +
> +#define BUFSIZE 128
> +
> +void test__fail(void) { /* for network_helpers.c */ }
> +
> +static int libbpf_print_fn(enum libbpf_print_level level,
> + const char *format, va_list args)
> +{
> + if (level == LIBBPF_DEBUG && !env.verbosity)
> + return 0;
> + return vfprintf(stderr, format, args);
> +}
> +
> +static volatile bool exiting;
> +
> +static void sig_handler(int sig)
> +{
> + exiting = true;
> +}
> +
> +const char *argp_program_version = "xdp-features 0.0";
> +const char argp_program_doc[] =
> +"XDP features detecion application.\n"
> +"\n"
> +"XDP features application checks the XDP advertised features match
> detected ones.\n"
> +"\n"
> +"USAGE: ./xdp-features [-6vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T
> <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n"
> +"\n"
> +"XDP features\n:"
> +"- XDP_PASS\n"
> +"- XDP_DROP\n"
> +"- XDP_ABORTED\n"
> +"- XDP_REDIRECT\n"
> +"- XDP_NDO_XMIT\n"
> +"- XDP_TX\n";
> +
> +static const struct argp_option opts[] = {
> + { "ipv6", '6', NULL, 0, "Use IPv6 network stack" },
> + { "verbose", 'v', NULL, 0, "Verbose debug output" },
> + { "tester", 't', NULL, 0, "Tester mode" },
> + { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" },
> + { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" },
> + { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" },
> + { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel"
> },
> + {},
> +};
> +
> +static int get_xdp_feature(const char *arg)
> +{
> + if (!strcmp(arg, "XDP_PASS"))
> + return XDP_FEATURE_PASS;
> + else if (!strcmp(arg, "XDP_DROP"))
> + return XDP_FEATURE_DROP;
> + else if (!strcmp(arg, "XDP_ABORTED"))
> + return XDP_FEATURE_ABORTED;
> + else if (!strcmp(arg, "XDP_REDIRECT"))
> + return XDP_FEATURE_REDIRECT;
> + else if (!strcmp(arg, "XDP_NDO_XMIT"))
> + return XDP_FEATURE_NDO_XMIT;
> + else if (!strcmp(arg, "XDP_TX"))
> + return XDP_FEATURE_TX;
> +
> + return -EINVAL;
> +}
> +
> +static char *get_xdp_feature_str(int feature)
> +{
> + switch (feature) {
> + case XDP_FEATURE_PASS:
> + return YELLOW("XDP_PASS");
> + case XDP_FEATURE_DROP:
> + return YELLOW("XDP_DROP");
> + case XDP_FEATURE_ABORTED:
> + return YELLOW("XDP_ABORTED");
> + case XDP_FEATURE_TX:
> + return YELLOW("XDP_TX");
> + case XDP_FEATURE_REDIRECT:
> + return YELLOW("XDP_REDIRECT");
> + case XDP_FEATURE_NDO_XMIT:
> + return YELLOW("XDP_NDO_XMIT");
> + default:
> + return "";
> + }
> +}
> +
> +static error_t parse_arg(int key, char *arg, struct argp_state *state)
> +{
> + switch (key) {
> + case '6':
> + env.family = AF_INET6;
> + break;
Thanks for making the changes! Since you're doing another respin to
address Alexei's feedback, maybe one thing we can also improve here
regarding v4-v6? Optionally, up to you, but IMO, it's much easier
to hard-code AF_INET6 everywhere:
socket(AF_INET6, ...)
inet_pton(AF_INET6, ...)
...
And then, if you want to use v4 by default, use '::ffff:127.0.0.1' as
the address. If the users need to use it with some other v4, they can also
pass the v4-mapped v6 address.
Up to you on whether to implement it or not, feel free to ignore me,
but IMO, that should avoid a lot of those env.family arguments and
making special cases for v4. Plus also removes the need for -6 argument.
The following would work:
./xdp_features ::ffff::<ipv4>
./xdp_features <ipv6>
(I'm assuming nothing runs exclusive non-dualstack v4 envs anymore)
> + case 'v':
> + env.verbosity = true;
> + break;
> + case 't':
> + env.is_tester = true;
> + break;
> + case 'f':
> + env.feature = get_xdp_feature(arg);
> + if (env.feature < 0) {
> + fprintf(stderr, "Invalid xdp feature: %s\n", arg);
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'D':
> + if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
> + &env.dut.addr, &env.dut.addrlen)) {
> + fprintf(stderr, "Invalid DUT address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'C':
> + if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
> + &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
> + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case 'T':
> + if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
> + &env.tester.addrlen)) {
> + fprintf(stderr, "Invalid Tester address: %s\n", arg);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + case ARGP_KEY_ARG:
> + errno = 0;
> + if (strlen(arg) >= IF_NAMESIZE) {
> + fprintf(stderr, "Invalid device name: %s\n", arg);
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> +
> + env.ifindex = if_nametoindex(arg);
> + if (!env.ifindex)
> + env.ifindex = strtoul(arg, NULL, 0);
> + if (!env.ifindex) {
> + fprintf(stderr,
> + "Bad interface index or name (%d): %s\n",
> + errno, strerror(errno));
> + argp_usage(state);
> + return ARGP_ERR_UNKNOWN;
> + }
> + break;
> + default:
> + return ARGP_ERR_UNKNOWN;
> + }
> +
> + return 0;
> +}
> +
> +static const struct argp argp = {
> + .options = opts,
> + .parser = parse_arg,
> + .doc = argp_program_doc,
> +};
> +
> +static void set_env_defaul(void)
> +{
> + env.feature = XDP_FEATURE_PASS;
> + env.ifindex = -ENODEV;
> + env.family = AF_INET;
> + make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
> + &env.dut_ctrl.addrlen);
> + make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
> + &env.dut.addrlen);
> + make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
> + &env.tester.addrlen);
> +}
> +
> +static void *dut_echo_thread(void *arg)
> +{
> + unsigned char buf[sizeof(struct tlv_hdr)];
> + int sockfd = *(int *)arg;
> +
> + while (!exiting) {
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + struct sockaddr_storage addr;
> + socklen_t addrlen;
> + size_t n;
> +
> + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
> + (struct sockaddr *)&addr, &addrlen);
> + if (n != ntohs(tlv->len))
> + continue;
> +
> + if (ntohs(tlv->type) != CMD_ECHO)
> + continue;
> +
> + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
> + (struct sockaddr *)&addr, addrlen);
> + }
> +
> + pthread_exit((void *)0);
> + close(sockfd);
> +
> + return NULL;
> +}
> +
> +static int dut_run_echo_thread(pthread_t *t, int *sockfd)
> +{
> + int err;
> +
> + sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
> + DUT_ECHO_PORT, 0, 1);
> + if (!sockfd) {
> + fprintf(stderr, "Failed to create echo socket\n");
> + return -errno;
> + }
> +
> + /* start echo channel */
> + err = pthread_create(t, NULL, dut_echo_thread, sockfd);
> + if (err) {
> + fprintf(stderr, "Failed creating dut_echo thread: %s\n",
> + strerror(-err));
> + free_fds(sockfd, 1);
> + return -EINVAL;
> + }
> +
> + return 0;
> +}
> +
> +static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
> + int flags)
> +{
> + struct bpf_program *prog;
> + unsigned int key = 0;
> + int err, fd = 0;
> +
> + switch (feature) {
> + case XDP_FEATURE_TX:
> + prog = skel->progs.xdp_do_tx;
> + break;
> + case XDP_FEATURE_DROP:
> + prog = skel->progs.xdp_do_drop;
> + break;
> + case XDP_FEATURE_ABORTED:
> + prog = skel->progs.xdp_do_aborted;
> + break;
> + case XDP_FEATURE_PASS:
> + prog = skel->progs.xdp_do_pass;
> + break;
> + case XDP_FEATURE_NDO_XMIT: {
> + struct bpf_devmap_val entry = {
> + .ifindex = env.ifindex,
> + };
> +
> + err = bpf_map__update_elem(skel->maps.dev_map,
> + &key, sizeof(key),
> + &entry, sizeof(entry), 0);
> + if (err < 0)
> + return err;
> +
> + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
> + }
> + case XDP_FEATURE_REDIRECT: {
> + struct bpf_cpumap_val entry = {
> + .qsize = 2048,
> + .bpf_prog.fd = fd,
> + };
> +
> + err = bpf_map__update_elem(skel->maps.cpu_map,
> + &key, sizeof(key),
> + &entry, sizeof(entry), 0);
> + if (err < 0)
> + return err;
> +
> + prog = skel->progs.xdp_do_redirect;
> + break;
> + }
> + default:
> + return -EINVAL;
> + }
> +
> + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
> + if (err)
> + fprintf(stderr,
> + "Failed to attach XDP program to ifindex %d\n",
> + env.ifindex);
> + return err;
> +}
> +
> +static int __recv_msg(int sockfd, void *buf, size_t bufsize,
> + unsigned int *val, unsigned int val_size)
> +{
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int len, n = sizeof(*tlv), i = 0;
> +
> + len = recv(sockfd, buf, bufsize, 0);
> + if (len != ntohs(tlv->len))
> + return -EINVAL;
> +
> + while (n < len && i < val_size) {
> + val[i] = ntohl(tlv->data[i]);
> + n += sizeof(tlv->data[0]);
> + i++;
> + }
> +
> + return i;
> +}
> +
> +static int recv_msg(int sockfd, void *buf, size_t bufsize)
> +{
> + return __recv_msg(sockfd, buf, bufsize, NULL, 0);
> +}
> +
> +static int dut_run(struct xdp_features *skel)
> +{
> + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> + int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
> + struct sockaddr_storage ctrl_addr;
> + pthread_t dut_thread;
> + socklen_t addrlen;
> +
> + sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
> + DUT_CTRL_PORT, 0, 1);
> + if (!sockfd) {
> + fprintf(stderr, "Failed to create DUT socket\n");
> + return -errno;
> + }
> +
> + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
> + if (ctrl_sockfd < 0) {
> + fprintf(stderr, "Failed to accept connection on DUT socket\n");
> + free_fds(sockfd, 1);
> + return -errno;
> + }
> +
> + /* CTRL loop */
> + while (!exiting) {
> + unsigned char buf[BUFSIZE] = {};
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> +
> + err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
> + if (err)
> + continue;
> +
> + switch (ntohs(tlv->type)) {
> + case CMD_START: {
> + if (state == CMD_START)
> + continue;
> +
> + state = CMD_START;
> + /* Load the XDP program on the DUT */
> + err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
> + if (err)
> + goto out;
> +
> + err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
> + if (err < 0)
> + goto out;
> +
> + tlv->type = htons(CMD_ACK);
> + tlv->len = htons(sizeof(*tlv));
> + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + case CMD_STOP:
> + if (state != CMD_START)
> + break;
> +
> + state = CMD_STOP;
> +
> + exiting = true;
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> +
> + tlv->type = htons(CMD_ACK);
> + tlv->len = htons(sizeof(*tlv));
> + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> + goto end_thread;
> + case CMD_GET_XDP_CAP: {
> + LIBBPF_OPTS(bpf_xdp_query_opts, opts);
> + size_t n;
> +
> + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
> + &opts);
> + if (err) {
> + fprintf(stderr,
> + "Failed to query XDP cap for ifindex %d\n",
> + env.ifindex);
> + goto end_thread;
> + }
> +
> + tlv->type = htons(CMD_ACK);
> + n = sizeof(*tlv) + sizeof(opts.feature_flags);
> + tlv->len = htons(n);
> + tlv->data[0] = htonl(opts.feature_flags);
> +
> + err = send(ctrl_sockfd, buf, n, 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + case CMD_GET_STATS: {
> + unsigned int key = 0, val;
> + size_t n;
> +
> + err = bpf_map__lookup_elem(skel->maps.dut_stats,
> + &key, sizeof(key),
> + &val, sizeof(val), 0);
> + if (err) {
> + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> + goto end_thread;
> + }
> +
> + tlv->type = htons(CMD_ACK);
> + n = sizeof(*tlv) + sizeof(val);
> + tlv->len = htons(n);
> + tlv->data[0] = htonl(val);
> +
> + err = send(ctrl_sockfd, buf, n, 0);
> + if (err < 0)
> + goto end_thread;
> + break;
> + }
> + default:
> + break;
> + }
> + }
> +
> +end_thread:
> + pthread_join(dut_thread, NULL);
> +out:
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> + close(ctrl_sockfd);
> + free_fds(sockfd, 1);
> +
> + return err;
> +}
> +
> +static bool tester_collect_advertised_cap(unsigned int cap)
> +{
> + switch (env.feature) {
> + case XDP_FEATURE_ABORTED:
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_TX:
> + return cap & NETDEV_XDP_ACT_BASIC;
> + case XDP_FEATURE_REDIRECT:
> + return cap & NETDEV_XDP_ACT_REDIRECT;
> + case XDP_FEATURE_NDO_XMIT:
> + return cap & NETDEV_XDP_ACT_NDO_XMIT;
> + default:
> + return false;
> + }
> +}
> +
> +static bool tester_collect_detected_cap(struct xdp_features *skel,
> + unsigned int dut_stats)
> +{
> + unsigned int err, key = 0, val;
> +
> + if (!dut_stats)
> + return false;
> +
> + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
> + &val, sizeof(val), 0);
> + if (err) {
> + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> + return false;
> + }
> +
> + switch (env.feature) {
> + case XDP_FEATURE_PASS:
> + case XDP_FEATURE_TX:
> + case XDP_FEATURE_REDIRECT:
> + case XDP_FEATURE_NDO_XMIT:
> + return val > 0;
> + case XDP_FEATURE_DROP:
> + case XDP_FEATURE_ABORTED:
> + return val == 0;
> + default:
> + return false;
> + }
> +}
> +
> +static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
> + unsigned int *val, unsigned int val_size)
> +{
> + unsigned char buf[BUFSIZE] = {};
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int n = sizeof(*tlv), err;
> +
> + tlv->type = htons(cmd);
> + switch (cmd) {
> + case CMD_START:
> + tlv->data[0] = htonl(env.feature);
> + n += sizeof(*val);
> + break;
> + default:
> + break;
> + }
> + tlv->len = htons(n);
> +
> + err = send(sockfd, buf, n, 0);
> + if (err < 0)
> + return err;
> +
> + err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
> + if (err < 0)
> + return err;
> +
> + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
> +}
> +
> +static int send_and_recv_msg(int sockfd, enum test_commands cmd)
> +{
> + return __send_and_recv_msg(sockfd, cmd, NULL, 0);
> +}
> +
> +static int send_echo_msg(void)
> +{
> + unsigned char buf[sizeof(struct tlv_hdr)];
> + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> + int sockfd, n;
> +
> + sockfd = socket(env.family, SOCK_DGRAM, 0);
> + if (sockfd < 0) {
> + fprintf(stderr, "Failed to create echo socket\n");
> + return -errno;
> + }
> +
> + tlv->type = htons(CMD_ECHO);
> + tlv->len = htons(sizeof(*tlv));
> +
> + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
> + (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
> + close(sockfd);
> +
> + return n == ntohs(tlv->len) ? 0 : -EINVAL;
> +}
> +
> +static int tester_run(struct xdp_features *skel)
> +{
> + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> + bool advertised_cap;
> + unsigned int val[1];
> + int i, err, sockfd;
> + bool detected_cap;
> +
> + sockfd = socket(env.family, SOCK_STREAM, 0);
> + if (sockfd < 0) {
> + fprintf(stderr, "Failed to create tester socket\n");
> + return -errno;
> + }
> +
> + if (settimeo(sockfd, 1000) < 0)
> + return -EINVAL;
> +
> + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
> + env.dut_ctrl.addrlen);
> + if (err) {
> + fprintf(stderr, "Failed to connect to the DUT\n");
> + return -errno;
> + }
> +
> + err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
> + ARRAY_SIZE(val));
> + if (err < 0) {
> + close(sockfd);
> + return err;
> + }
> +
> + advertised_cap = tester_collect_advertised_cap(val[0]);
> +
> + err = bpf_xdp_attach(env.ifindex,
> + bpf_program__fd(skel->progs.xdp_tester),
> + flags, NULL);
> + if (err) {
> + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
> + env.ifindex);
> + goto out;
> + }
> +
> + err = send_and_recv_msg(sockfd, CMD_START);
> + if (err)
> + goto out;
> +
> + for (i = 0; i < 10 && !exiting; i++) {
> + err = send_echo_msg();
> + if (err < 0)
> + goto out;
> +
> + sleep(1);
> + }
> +
> + err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
> + if (err)
> + goto out;
> +
> + /* stop the test */
> + err = send_and_recv_msg(sockfd, CMD_STOP);
> + /* send a new echo message to wake echo thread of the dut */
> + send_echo_msg();
> +
> + detected_cap = tester_collect_detected_cap(skel, val[0]);
> +
> + fprintf(stdout, "Feature %s: [%s][%s]\n",
> get_xdp_feature_str(env.feature),
> + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
> + advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
> +out:
> + bpf_xdp_detach(env.ifindex, flags, NULL);
> + close(sockfd);
> + return err < 0 ? err : 0;
> +}
> +
> +static void set_skel_rodata(struct xdp_features *skel)
> +{
> + skel->rodata->expected_feature = env.feature;
> + if (env.family == AF_INET6) {
> + struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
> + struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
> +
> + skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
> + skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
> + } else {
> + struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
> + struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
> +
> + skel->rodata->tester_addr.ip = tester_addr->sin_addr;
> + skel->rodata->dut_addr.ip = dut_addr->sin_addr;
> + }
> +}
> +
> +int main(int argc, char **argv)
> +{
> + struct xdp_features *skel;
> + int err;
> +
> + libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
> + libbpf_set_print(libbpf_print_fn);
> +
> + signal(SIGINT, sig_handler);
> + signal(SIGTERM, sig_handler);
> +
> + set_env_defaul();
> +
> + /* Parse command line arguments */
> + err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
> + if (err)
> + return err;
> +
> + if (env.ifindex < 0) {
> + fprintf(stderr, "Invalid ifindex\n");
> + return -ENODEV;
> + }
> +
> + /* Load and verify BPF application */
> + skel = xdp_features__open();
> + if (!skel) {
> + fprintf(stderr, "Failed to open and load BPF skeleton\n");
> + return -EINVAL;
> + }
> +
> + set_skel_rodata(skel);
> +
> + /* Load & verify BPF programs */
> + err = xdp_features__load(skel);
> + if (err) {
> + fprintf(stderr, "Failed to load and verify BPF skeleton\n");
> + goto cleanup;
> + }
> +
> + err = xdp_features__attach(skel);
> + if (err) {
> + fprintf(stderr, "Failed to attach BPF skeleton\n");
> + goto cleanup;
> + }
> +
> + if (env.is_tester) {
> + /* Tester */
> + fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
> + err = tester_run(skel);
> + } else {
> + /* DUT */
> + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
> + err = dut_run(skel);
> + }
> +
> +cleanup:
> + xdp_features__destroy(skel);
> +
> + return err < 0 ? -err : 0;
> +}
> diff --git a/tools/testing/selftests/bpf/xdp_features.h
> b/tools/testing/selftests/bpf/xdp_features.h
> new file mode 100644
> index 000000000000..28d7614c4f02
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/xdp_features.h
> @@ -0,0 +1,33 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +/* test commands */
> +enum test_commands {
> + CMD_STOP, /* CMD */
> + CMD_START, /* CMD + xdp feature */
> + CMD_ECHO, /* CMD */
> + CMD_ACK, /* CMD + data */
> + CMD_GET_XDP_CAP, /* CMD */
> + CMD_GET_STATS, /* CMD */
> +};
> +
> +#define DUT_CTRL_PORT 12345
> +#define DUT_ECHO_PORT 12346
> +
> +struct tlv_hdr {
> + __be16 type;
> + __be16 len;
> + __be32 data[];
> +};
> +
> +enum {
> + XDP_FEATURE_ABORTED,
> + XDP_FEATURE_DROP,
> + XDP_FEATURE_PASS,
> + XDP_FEATURE_TX,
> + XDP_FEATURE_REDIRECT,
> + XDP_FEATURE_NDO_XMIT,
> + XDP_FEATURE_XSK_ZEROCOPY,
> + XDP_FEATURE_HW_OFFLOAD,
> + XDP_FEATURE_RX_SG,
> + XDP_FEATURE_NDO_XMIT_SG,
> +};
> --
> 2.39.1
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [Intel-wired-lan] [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
2023-01-30 18:59 ` [Intel-wired-lan] " Stanislav Fomichev
@ 2023-01-30 22:59 ` Lorenzo Bianconi
-1 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-30 22:59 UTC (permalink / raw)
To: Stanislav Fomichev
Cc: mst, vladimir.oltean, ast, edumazet, anthony.l.nguyen, daniel,
andrii, intel-wired-lan, simon.horman, kuba, pabeni, aelior,
hawk, christophe.jaillet, memxor, john, bjorn, bpf,
magnus.karlsson, leon, netdev, toke, martin.lau, ecree.xilinx,
alardam, gospo, saeedm, davem, nbd
[-- Attachment #1.1: Type: text/plain, Size: 19282 bytes --]
[...]
> > +static error_t parse_arg(int key, char *arg, struct argp_state *state)
> > +{
> > + switch (key) {
> > + case '6':
> > + env.family = AF_INET6;
> > + break;
>
> Thanks for making the changes! Since you're doing another respin to
> address Alexei's feedback, maybe one thing we can also improve here
> regarding v4-v6? Optionally, up to you, but IMO, it's much easier
> to hard-code AF_INET6 everywhere:
>
> socket(AF_INET6, ...)
> inet_pton(AF_INET6, ...)
> ...
>
> And then, if you want to use v4 by default, use '::ffff:127.0.0.1' as
> the address. If the users need to use it with some other v4, they can also
> pass the v4-mapped v6 address.
>
> Up to you on whether to implement it or not, feel free to ignore me,
> but IMO, that should avoid a lot of those env.family arguments and
> making special cases for v4. Plus also removes the need for -6 argument.
>
> The following would work:
> ./xdp_features ::ffff::<ipv4>
> ./xdp_features <ipv6>
>
> (I'm assuming nothing runs exclusive non-dualstack v4 envs anymore)
ack, I am fine with it. I think the code would be simpler and easier to read.
I will fix it in the next version.
Regards,
Lorenzo
>
> > + case 'v':
> > + env.verbosity = true;
> > + break;
> > + case 't':
> > + env.is_tester = true;
> > + break;
> > + case 'f':
> > + env.feature = get_xdp_feature(arg);
> > + if (env.feature < 0) {
> > + fprintf(stderr, "Invalid xdp feature: %s\n", arg);
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'D':
> > + if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
> > + &env.dut.addr, &env.dut.addrlen)) {
> > + fprintf(stderr, "Invalid DUT address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'C':
> > + if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
> > + &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
> > + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'T':
> > + if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
> > + &env.tester.addrlen)) {
> > + fprintf(stderr, "Invalid Tester address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case ARGP_KEY_ARG:
> > + errno = 0;
> > + if (strlen(arg) >= IF_NAMESIZE) {
> > + fprintf(stderr, "Invalid device name: %s\n", arg);
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > +
> > + env.ifindex = if_nametoindex(arg);
> > + if (!env.ifindex)
> > + env.ifindex = strtoul(arg, NULL, 0);
> > + if (!env.ifindex) {
> > + fprintf(stderr,
> > + "Bad interface index or name (%d): %s\n",
> > + errno, strerror(errno));
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + default:
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static const struct argp argp = {
> > + .options = opts,
> > + .parser = parse_arg,
> > + .doc = argp_program_doc,
> > +};
> > +
> > +static void set_env_defaul(void)
> > +{
> > + env.feature = XDP_FEATURE_PASS;
> > + env.ifindex = -ENODEV;
> > + env.family = AF_INET;
> > + make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
> > + &env.dut_ctrl.addrlen);
> > + make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
> > + &env.dut.addrlen);
> > + make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
> > + &env.tester.addrlen);
> > +}
> > +
> > +static void *dut_echo_thread(void *arg)
> > +{
> > + unsigned char buf[sizeof(struct tlv_hdr)];
> > + int sockfd = *(int *)arg;
> > +
> > + while (!exiting) {
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + struct sockaddr_storage addr;
> > + socklen_t addrlen;
> > + size_t n;
> > +
> > + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
> > + (struct sockaddr *)&addr, &addrlen);
> > + if (n != ntohs(tlv->len))
> > + continue;
> > +
> > + if (ntohs(tlv->type) != CMD_ECHO)
> > + continue;
> > +
> > + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
> > + (struct sockaddr *)&addr, addrlen);
> > + }
> > +
> > + pthread_exit((void *)0);
> > + close(sockfd);
> > +
> > + return NULL;
> > +}
> > +
> > +static int dut_run_echo_thread(pthread_t *t, int *sockfd)
> > +{
> > + int err;
> > +
> > + sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
> > + DUT_ECHO_PORT, 0, 1);
> > + if (!sockfd) {
> > + fprintf(stderr, "Failed to create echo socket\n");
> > + return -errno;
> > + }
> > +
> > + /* start echo channel */
> > + err = pthread_create(t, NULL, dut_echo_thread, sockfd);
> > + if (err) {
> > + fprintf(stderr, "Failed creating dut_echo thread: %s\n",
> > + strerror(-err));
> > + free_fds(sockfd, 1);
> > + return -EINVAL;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
> > + int flags)
> > +{
> > + struct bpf_program *prog;
> > + unsigned int key = 0;
> > + int err, fd = 0;
> > +
> > + switch (feature) {
> > + case XDP_FEATURE_TX:
> > + prog = skel->progs.xdp_do_tx;
> > + break;
> > + case XDP_FEATURE_DROP:
> > + prog = skel->progs.xdp_do_drop;
> > + break;
> > + case XDP_FEATURE_ABORTED:
> > + prog = skel->progs.xdp_do_aborted;
> > + break;
> > + case XDP_FEATURE_PASS:
> > + prog = skel->progs.xdp_do_pass;
> > + break;
> > + case XDP_FEATURE_NDO_XMIT: {
> > + struct bpf_devmap_val entry = {
> > + .ifindex = env.ifindex,
> > + };
> > +
> > + err = bpf_map__update_elem(skel->maps.dev_map,
> > + &key, sizeof(key),
> > + &entry, sizeof(entry), 0);
> > + if (err < 0)
> > + return err;
> > +
> > + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
> > + }
> > + case XDP_FEATURE_REDIRECT: {
> > + struct bpf_cpumap_val entry = {
> > + .qsize = 2048,
> > + .bpf_prog.fd = fd,
> > + };
> > +
> > + err = bpf_map__update_elem(skel->maps.cpu_map,
> > + &key, sizeof(key),
> > + &entry, sizeof(entry), 0);
> > + if (err < 0)
> > + return err;
> > +
> > + prog = skel->progs.xdp_do_redirect;
> > + break;
> > + }
> > + default:
> > + return -EINVAL;
> > + }
> > +
> > + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
> > + if (err)
> > + fprintf(stderr,
> > + "Failed to attach XDP program to ifindex %d\n",
> > + env.ifindex);
> > + return err;
> > +}
> > +
> > +static int __recv_msg(int sockfd, void *buf, size_t bufsize,
> > + unsigned int *val, unsigned int val_size)
> > +{
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int len, n = sizeof(*tlv), i = 0;
> > +
> > + len = recv(sockfd, buf, bufsize, 0);
> > + if (len != ntohs(tlv->len))
> > + return -EINVAL;
> > +
> > + while (n < len && i < val_size) {
> > + val[i] = ntohl(tlv->data[i]);
> > + n += sizeof(tlv->data[0]);
> > + i++;
> > + }
> > +
> > + return i;
> > +}
> > +
> > +static int recv_msg(int sockfd, void *buf, size_t bufsize)
> > +{
> > + return __recv_msg(sockfd, buf, bufsize, NULL, 0);
> > +}
> > +
> > +static int dut_run(struct xdp_features *skel)
> > +{
> > + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> > + int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
> > + struct sockaddr_storage ctrl_addr;
> > + pthread_t dut_thread;
> > + socklen_t addrlen;
> > +
> > + sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
> > + DUT_CTRL_PORT, 0, 1);
> > + if (!sockfd) {
> > + fprintf(stderr, "Failed to create DUT socket\n");
> > + return -errno;
> > + }
> > +
> > + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
> > + if (ctrl_sockfd < 0) {
> > + fprintf(stderr, "Failed to accept connection on DUT socket\n");
> > + free_fds(sockfd, 1);
> > + return -errno;
> > + }
> > +
> > + /* CTRL loop */
> > + while (!exiting) {
> > + unsigned char buf[BUFSIZE] = {};
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > +
> > + err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
> > + if (err)
> > + continue;
> > +
> > + switch (ntohs(tlv->type)) {
> > + case CMD_START: {
> > + if (state == CMD_START)
> > + continue;
> > +
> > + state = CMD_START;
> > + /* Load the XDP program on the DUT */
> > + err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
> > + if (err)
> > + goto out;
> > +
> > + err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
> > + if (err < 0)
> > + goto out;
> > +
> > + tlv->type = htons(CMD_ACK);
> > + tlv->len = htons(sizeof(*tlv));
> > + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + case CMD_STOP:
> > + if (state != CMD_START)
> > + break;
> > +
> > + state = CMD_STOP;
> > +
> > + exiting = true;
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > +
> > + tlv->type = htons(CMD_ACK);
> > + tlv->len = htons(sizeof(*tlv));
> > + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> > + goto end_thread;
> > + case CMD_GET_XDP_CAP: {
> > + LIBBPF_OPTS(bpf_xdp_query_opts, opts);
> > + size_t n;
> > +
> > + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
> > + &opts);
> > + if (err) {
> > + fprintf(stderr,
> > + "Failed to query XDP cap for ifindex %d\n",
> > + env.ifindex);
> > + goto end_thread;
> > + }
> > +
> > + tlv->type = htons(CMD_ACK);
> > + n = sizeof(*tlv) + sizeof(opts.feature_flags);
> > + tlv->len = htons(n);
> > + tlv->data[0] = htonl(opts.feature_flags);
> > +
> > + err = send(ctrl_sockfd, buf, n, 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + case CMD_GET_STATS: {
> > + unsigned int key = 0, val;
> > + size_t n;
> > +
> > + err = bpf_map__lookup_elem(skel->maps.dut_stats,
> > + &key, sizeof(key),
> > + &val, sizeof(val), 0);
> > + if (err) {
> > + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> > + goto end_thread;
> > + }
> > +
> > + tlv->type = htons(CMD_ACK);
> > + n = sizeof(*tlv) + sizeof(val);
> > + tlv->len = htons(n);
> > + tlv->data[0] = htonl(val);
> > +
> > + err = send(ctrl_sockfd, buf, n, 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + default:
> > + break;
> > + }
> > + }
> > +
> > +end_thread:
> > + pthread_join(dut_thread, NULL);
> > +out:
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > + close(ctrl_sockfd);
> > + free_fds(sockfd, 1);
> > +
> > + return err;
> > +}
> > +
> > +static bool tester_collect_advertised_cap(unsigned int cap)
> > +{
> > + switch (env.feature) {
> > + case XDP_FEATURE_ABORTED:
> > + case XDP_FEATURE_DROP:
> > + case XDP_FEATURE_PASS:
> > + case XDP_FEATURE_TX:
> > + return cap & NETDEV_XDP_ACT_BASIC;
> > + case XDP_FEATURE_REDIRECT:
> > + return cap & NETDEV_XDP_ACT_REDIRECT;
> > + case XDP_FEATURE_NDO_XMIT:
> > + return cap & NETDEV_XDP_ACT_NDO_XMIT;
> > + default:
> > + return false;
> > + }
> > +}
> > +
> > +static bool tester_collect_detected_cap(struct xdp_features *skel,
> > + unsigned int dut_stats)
> > +{
> > + unsigned int err, key = 0, val;
> > +
> > + if (!dut_stats)
> > + return false;
> > +
> > + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
> > + &val, sizeof(val), 0);
> > + if (err) {
> > + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> > + return false;
> > + }
> > +
> > + switch (env.feature) {
> > + case XDP_FEATURE_PASS:
> > + case XDP_FEATURE_TX:
> > + case XDP_FEATURE_REDIRECT:
> > + case XDP_FEATURE_NDO_XMIT:
> > + return val > 0;
> > + case XDP_FEATURE_DROP:
> > + case XDP_FEATURE_ABORTED:
> > + return val == 0;
> > + default:
> > + return false;
> > + }
> > +}
> > +
> > +static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
> > + unsigned int *val, unsigned int val_size)
> > +{
> > + unsigned char buf[BUFSIZE] = {};
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int n = sizeof(*tlv), err;
> > +
> > + tlv->type = htons(cmd);
> > + switch (cmd) {
> > + case CMD_START:
> > + tlv->data[0] = htonl(env.feature);
> > + n += sizeof(*val);
> > + break;
> > + default:
> > + break;
> > + }
> > + tlv->len = htons(n);
> > +
> > + err = send(sockfd, buf, n, 0);
> > + if (err < 0)
> > + return err;
> > +
> > + err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
> > + if (err < 0)
> > + return err;
> > +
> > + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
> > +}
> > +
> > +static int send_and_recv_msg(int sockfd, enum test_commands cmd)
> > +{
> > + return __send_and_recv_msg(sockfd, cmd, NULL, 0);
> > +}
> > +
> > +static int send_echo_msg(void)
> > +{
> > + unsigned char buf[sizeof(struct tlv_hdr)];
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int sockfd, n;
> > +
> > + sockfd = socket(env.family, SOCK_DGRAM, 0);
> > + if (sockfd < 0) {
> > + fprintf(stderr, "Failed to create echo socket\n");
> > + return -errno;
> > + }
> > +
> > + tlv->type = htons(CMD_ECHO);
> > + tlv->len = htons(sizeof(*tlv));
> > +
> > + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
> > + (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
> > + close(sockfd);
> > +
> > + return n == ntohs(tlv->len) ? 0 : -EINVAL;
> > +}
> > +
> > +static int tester_run(struct xdp_features *skel)
> > +{
> > + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> > + bool advertised_cap;
> > + unsigned int val[1];
> > + int i, err, sockfd;
> > + bool detected_cap;
> > +
> > + sockfd = socket(env.family, SOCK_STREAM, 0);
> > + if (sockfd < 0) {
> > + fprintf(stderr, "Failed to create tester socket\n");
> > + return -errno;
> > + }
> > +
> > + if (settimeo(sockfd, 1000) < 0)
> > + return -EINVAL;
> > +
> > + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
> > + env.dut_ctrl.addrlen);
> > + if (err) {
> > + fprintf(stderr, "Failed to connect to the DUT\n");
> > + return -errno;
> > + }
> > +
> > + err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
> > + ARRAY_SIZE(val));
> > + if (err < 0) {
> > + close(sockfd);
> > + return err;
> > + }
> > +
> > + advertised_cap = tester_collect_advertised_cap(val[0]);
> > +
> > + err = bpf_xdp_attach(env.ifindex,
> > + bpf_program__fd(skel->progs.xdp_tester),
> > + flags, NULL);
> > + if (err) {
> > + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
> > + env.ifindex);
> > + goto out;
> > + }
> > +
> > + err = send_and_recv_msg(sockfd, CMD_START);
> > + if (err)
> > + goto out;
> > +
> > + for (i = 0; i < 10 && !exiting; i++) {
> > + err = send_echo_msg();
> > + if (err < 0)
> > + goto out;
> > +
> > + sleep(1);
> > + }
> > +
> > + err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
> > + if (err)
> > + goto out;
> > +
> > + /* stop the test */
> > + err = send_and_recv_msg(sockfd, CMD_STOP);
> > + /* send a new echo message to wake echo thread of the dut */
> > + send_echo_msg();
> > +
> > + detected_cap = tester_collect_detected_cap(skel, val[0]);
> > +
> > + fprintf(stdout, "Feature %s: [%s][%s]\n",
> > get_xdp_feature_str(env.feature),
> > + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
> > + advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
> > +out:
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > + close(sockfd);
> > + return err < 0 ? err : 0;
> > +}
> > +
> > +static void set_skel_rodata(struct xdp_features *skel)
> > +{
> > + skel->rodata->expected_feature = env.feature;
> > + if (env.family == AF_INET6) {
> > + struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
> > + struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
> > +
> > + skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
> > + skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
> > + } else {
> > + struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
> > + struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
> > +
> > + skel->rodata->tester_addr.ip = tester_addr->sin_addr;
> > + skel->rodata->dut_addr.ip = dut_addr->sin_addr;
> > + }
> > +}
> > +
> > +int main(int argc, char **argv)
> > +{
> > + struct xdp_features *skel;
> > + int err;
> > +
> > + libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
> > + libbpf_set_print(libbpf_print_fn);
> > +
> > + signal(SIGINT, sig_handler);
> > + signal(SIGTERM, sig_handler);
> > +
> > + set_env_defaul();
> > +
> > + /* Parse command line arguments */
> > + err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
> > + if (err)
> > + return err;
> > +
> > + if (env.ifindex < 0) {
> > + fprintf(stderr, "Invalid ifindex\n");
> > + return -ENODEV;
> > + }
> > +
> > + /* Load and verify BPF application */
> > + skel = xdp_features__open();
> > + if (!skel) {
> > + fprintf(stderr, "Failed to open and load BPF skeleton\n");
> > + return -EINVAL;
> > + }
> > +
> > + set_skel_rodata(skel);
> > +
> > + /* Load & verify BPF programs */
> > + err = xdp_features__load(skel);
> > + if (err) {
> > + fprintf(stderr, "Failed to load and verify BPF skeleton\n");
> > + goto cleanup;
> > + }
> > +
> > + err = xdp_features__attach(skel);
> > + if (err) {
> > + fprintf(stderr, "Failed to attach BPF skeleton\n");
> > + goto cleanup;
> > + }
> > +
> > + if (env.is_tester) {
> > + /* Tester */
> > + fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
> > + err = tester_run(skel);
> > + } else {
> > + /* DUT */
> > + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
> > + err = dut_run(skel);
> > + }
> > +
> > +cleanup:
> > + xdp_features__destroy(skel);
> > +
> > + return err < 0 ? -err : 0;
> > +}
> > diff --git a/tools/testing/selftests/bpf/xdp_features.h
> > b/tools/testing/selftests/bpf/xdp_features.h
> > new file mode 100644
> > index 000000000000..28d7614c4f02
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/xdp_features.h
> > @@ -0,0 +1,33 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +
> > +/* test commands */
> > +enum test_commands {
> > + CMD_STOP, /* CMD */
> > + CMD_START, /* CMD + xdp feature */
> > + CMD_ECHO, /* CMD */
> > + CMD_ACK, /* CMD + data */
> > + CMD_GET_XDP_CAP, /* CMD */
> > + CMD_GET_STATS, /* CMD */
> > +};
> > +
> > +#define DUT_CTRL_PORT 12345
> > +#define DUT_ECHO_PORT 12346
> > +
> > +struct tlv_hdr {
> > + __be16 type;
> > + __be16 len;
> > + __be32 data[];
> > +};
> > +
> > +enum {
> > + XDP_FEATURE_ABORTED,
> > + XDP_FEATURE_DROP,
> > + XDP_FEATURE_PASS,
> > + XDP_FEATURE_TX,
> > + XDP_FEATURE_REDIRECT,
> > + XDP_FEATURE_NDO_XMIT,
> > + XDP_FEATURE_XSK_ZEROCOPY,
> > + XDP_FEATURE_HW_OFFLOAD,
> > + XDP_FEATURE_RX_SG,
> > + XDP_FEATURE_NDO_XMIT_SG,
> > +};
> > --
> > 2.39.1
>
[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
[-- Attachment #2: Type: text/plain, Size: 162 bytes --]
_______________________________________________
Intel-wired-lan mailing list
Intel-wired-lan@osuosl.org
https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
^ permalink raw reply [flat|nested] 32+ messages in thread* Re: [PATCH v4 bpf-next 8/8] selftests/bpf: introduce XDP compliance test tool
@ 2023-01-30 22:59 ` Lorenzo Bianconi
0 siblings, 0 replies; 32+ messages in thread
From: Lorenzo Bianconi @ 2023-01-30 22:59 UTC (permalink / raw)
To: Stanislav Fomichev
Cc: bpf, netdev, ast, daniel, andrii, davem, kuba, pabeni, edumazet,
hawk, toke, memxor, alardam, saeedm, anthony.l.nguyen, gospo,
vladimir.oltean, nbd, john, leon, simon.horman, aelior,
christophe.jaillet, ecree.xilinx, mst, bjorn, magnus.karlsson,
maciej.fijalkowski, intel-wired-lan, lorenzo.bianconi,
martin.lau
[-- Attachment #1: Type: text/plain, Size: 19282 bytes --]
[...]
> > +static error_t parse_arg(int key, char *arg, struct argp_state *state)
> > +{
> > + switch (key) {
> > + case '6':
> > + env.family = AF_INET6;
> > + break;
>
> Thanks for making the changes! Since you're doing another respin to
> address Alexei's feedback, maybe one thing we can also improve here
> regarding v4-v6? Optionally, up to you, but IMO, it's much easier
> to hard-code AF_INET6 everywhere:
>
> socket(AF_INET6, ...)
> inet_pton(AF_INET6, ...)
> ...
>
> And then, if you want to use v4 by default, use '::ffff:127.0.0.1' as
> the address. If the users need to use it with some other v4, they can also
> pass the v4-mapped v6 address.
>
> Up to you on whether to implement it or not, feel free to ignore me,
> but IMO, that should avoid a lot of those env.family arguments and
> making special cases for v4. Plus also removes the need for -6 argument.
>
> The following would work:
> ./xdp_features ::ffff::<ipv4>
> ./xdp_features <ipv6>
>
> (I'm assuming nothing runs exclusive non-dualstack v4 envs anymore)
ack, I am fine with it. I think the code would be simpler and easier to read.
I will fix it in the next version.
Regards,
Lorenzo
>
> > + case 'v':
> > + env.verbosity = true;
> > + break;
> > + case 't':
> > + env.is_tester = true;
> > + break;
> > + case 'f':
> > + env.feature = get_xdp_feature(arg);
> > + if (env.feature < 0) {
> > + fprintf(stderr, "Invalid xdp feature: %s\n", arg);
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'D':
> > + if (make_sockaddr(env.family, arg, DUT_ECHO_PORT,
> > + &env.dut.addr, &env.dut.addrlen)) {
> > + fprintf(stderr, "Invalid DUT address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'C':
> > + if (make_sockaddr(env.family, arg, DUT_CTRL_PORT,
> > + &env.dut_ctrl.addr, &env.dut_ctrl.addrlen)) {
> > + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case 'T':
> > + if (make_sockaddr(env.family, arg, 0, &env.tester.addr,
> > + &env.tester.addrlen)) {
> > + fprintf(stderr, "Invalid Tester address: %s\n", arg);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + case ARGP_KEY_ARG:
> > + errno = 0;
> > + if (strlen(arg) >= IF_NAMESIZE) {
> > + fprintf(stderr, "Invalid device name: %s\n", arg);
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > +
> > + env.ifindex = if_nametoindex(arg);
> > + if (!env.ifindex)
> > + env.ifindex = strtoul(arg, NULL, 0);
> > + if (!env.ifindex) {
> > + fprintf(stderr,
> > + "Bad interface index or name (%d): %s\n",
> > + errno, strerror(errno));
> > + argp_usage(state);
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > + break;
> > + default:
> > + return ARGP_ERR_UNKNOWN;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static const struct argp argp = {
> > + .options = opts,
> > + .parser = parse_arg,
> > + .doc = argp_program_doc,
> > +};
> > +
> > +static void set_env_defaul(void)
> > +{
> > + env.feature = XDP_FEATURE_PASS;
> > + env.ifindex = -ENODEV;
> > + env.family = AF_INET;
> > + make_sockaddr(AF_INET, "127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl.addr,
> > + &env.dut_ctrl.addrlen);
> > + make_sockaddr(AF_INET, "127.0.0.1", DUT_ECHO_PORT, &env.dut.addr,
> > + &env.dut.addrlen);
> > + make_sockaddr(AF_INET, "127.0.0.1", 0, &env.tester.addr,
> > + &env.tester.addrlen);
> > +}
> > +
> > +static void *dut_echo_thread(void *arg)
> > +{
> > + unsigned char buf[sizeof(struct tlv_hdr)];
> > + int sockfd = *(int *)arg;
> > +
> > + while (!exiting) {
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + struct sockaddr_storage addr;
> > + socklen_t addrlen;
> > + size_t n;
> > +
> > + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL,
> > + (struct sockaddr *)&addr, &addrlen);
> > + if (n != ntohs(tlv->len))
> > + continue;
> > +
> > + if (ntohs(tlv->type) != CMD_ECHO)
> > + continue;
> > +
> > + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
> > + (struct sockaddr *)&addr, addrlen);
> > + }
> > +
> > + pthread_exit((void *)0);
> > + close(sockfd);
> > +
> > + return NULL;
> > +}
> > +
> > +static int dut_run_echo_thread(pthread_t *t, int *sockfd)
> > +{
> > + int err;
> > +
> > + sockfd = start_reuseport_server(env.family, SOCK_DGRAM, NULL,
> > + DUT_ECHO_PORT, 0, 1);
> > + if (!sockfd) {
> > + fprintf(stderr, "Failed to create echo socket\n");
> > + return -errno;
> > + }
> > +
> > + /* start echo channel */
> > + err = pthread_create(t, NULL, dut_echo_thread, sockfd);
> > + if (err) {
> > + fprintf(stderr, "Failed creating dut_echo thread: %s\n",
> > + strerror(-err));
> > + free_fds(sockfd, 1);
> > + return -EINVAL;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static int dut_attach_xdp_prog(struct xdp_features *skel, int feature,
> > + int flags)
> > +{
> > + struct bpf_program *prog;
> > + unsigned int key = 0;
> > + int err, fd = 0;
> > +
> > + switch (feature) {
> > + case XDP_FEATURE_TX:
> > + prog = skel->progs.xdp_do_tx;
> > + break;
> > + case XDP_FEATURE_DROP:
> > + prog = skel->progs.xdp_do_drop;
> > + break;
> > + case XDP_FEATURE_ABORTED:
> > + prog = skel->progs.xdp_do_aborted;
> > + break;
> > + case XDP_FEATURE_PASS:
> > + prog = skel->progs.xdp_do_pass;
> > + break;
> > + case XDP_FEATURE_NDO_XMIT: {
> > + struct bpf_devmap_val entry = {
> > + .ifindex = env.ifindex,
> > + };
> > +
> > + err = bpf_map__update_elem(skel->maps.dev_map,
> > + &key, sizeof(key),
> > + &entry, sizeof(entry), 0);
> > + if (err < 0)
> > + return err;
> > +
> > + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap);
> > + }
> > + case XDP_FEATURE_REDIRECT: {
> > + struct bpf_cpumap_val entry = {
> > + .qsize = 2048,
> > + .bpf_prog.fd = fd,
> > + };
> > +
> > + err = bpf_map__update_elem(skel->maps.cpu_map,
> > + &key, sizeof(key),
> > + &entry, sizeof(entry), 0);
> > + if (err < 0)
> > + return err;
> > +
> > + prog = skel->progs.xdp_do_redirect;
> > + break;
> > + }
> > + default:
> > + return -EINVAL;
> > + }
> > +
> > + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL);
> > + if (err)
> > + fprintf(stderr,
> > + "Failed to attach XDP program to ifindex %d\n",
> > + env.ifindex);
> > + return err;
> > +}
> > +
> > +static int __recv_msg(int sockfd, void *buf, size_t bufsize,
> > + unsigned int *val, unsigned int val_size)
> > +{
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int len, n = sizeof(*tlv), i = 0;
> > +
> > + len = recv(sockfd, buf, bufsize, 0);
> > + if (len != ntohs(tlv->len))
> > + return -EINVAL;
> > +
> > + while (n < len && i < val_size) {
> > + val[i] = ntohl(tlv->data[i]);
> > + n += sizeof(tlv->data[0]);
> > + i++;
> > + }
> > +
> > + return i;
> > +}
> > +
> > +static int recv_msg(int sockfd, void *buf, size_t bufsize)
> > +{
> > + return __recv_msg(sockfd, buf, bufsize, NULL, 0);
> > +}
> > +
> > +static int dut_run(struct xdp_features *skel)
> > +{
> > + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> > + int state, err, *sockfd, ctrl_sockfd, echo_sockfd;
> > + struct sockaddr_storage ctrl_addr;
> > + pthread_t dut_thread;
> > + socklen_t addrlen;
> > +
> > + sockfd = start_reuseport_server(env.family, SOCK_STREAM, NULL,
> > + DUT_CTRL_PORT, 0, 1);
> > + if (!sockfd) {
> > + fprintf(stderr, "Failed to create DUT socket\n");
> > + return -errno;
> > + }
> > +
> > + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen);
> > + if (ctrl_sockfd < 0) {
> > + fprintf(stderr, "Failed to accept connection on DUT socket\n");
> > + free_fds(sockfd, 1);
> > + return -errno;
> > + }
> > +
> > + /* CTRL loop */
> > + while (!exiting) {
> > + unsigned char buf[BUFSIZE] = {};
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > +
> > + err = recv_msg(ctrl_sockfd, buf, BUFSIZE);
> > + if (err)
> > + continue;
> > +
> > + switch (ntohs(tlv->type)) {
> > + case CMD_START: {
> > + if (state == CMD_START)
> > + continue;
> > +
> > + state = CMD_START;
> > + /* Load the XDP program on the DUT */
> > + err = dut_attach_xdp_prog(skel, ntohl(tlv->data[0]), flags);
> > + if (err)
> > + goto out;
> > +
> > + err = dut_run_echo_thread(&dut_thread, &echo_sockfd);
> > + if (err < 0)
> > + goto out;
> > +
> > + tlv->type = htons(CMD_ACK);
> > + tlv->len = htons(sizeof(*tlv));
> > + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + case CMD_STOP:
> > + if (state != CMD_START)
> > + break;
> > +
> > + state = CMD_STOP;
> > +
> > + exiting = true;
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > +
> > + tlv->type = htons(CMD_ACK);
> > + tlv->len = htons(sizeof(*tlv));
> > + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0);
> > + goto end_thread;
> > + case CMD_GET_XDP_CAP: {
> > + LIBBPF_OPTS(bpf_xdp_query_opts, opts);
> > + size_t n;
> > +
> > + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE,
> > + &opts);
> > + if (err) {
> > + fprintf(stderr,
> > + "Failed to query XDP cap for ifindex %d\n",
> > + env.ifindex);
> > + goto end_thread;
> > + }
> > +
> > + tlv->type = htons(CMD_ACK);
> > + n = sizeof(*tlv) + sizeof(opts.feature_flags);
> > + tlv->len = htons(n);
> > + tlv->data[0] = htonl(opts.feature_flags);
> > +
> > + err = send(ctrl_sockfd, buf, n, 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + case CMD_GET_STATS: {
> > + unsigned int key = 0, val;
> > + size_t n;
> > +
> > + err = bpf_map__lookup_elem(skel->maps.dut_stats,
> > + &key, sizeof(key),
> > + &val, sizeof(val), 0);
> > + if (err) {
> > + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> > + goto end_thread;
> > + }
> > +
> > + tlv->type = htons(CMD_ACK);
> > + n = sizeof(*tlv) + sizeof(val);
> > + tlv->len = htons(n);
> > + tlv->data[0] = htonl(val);
> > +
> > + err = send(ctrl_sockfd, buf, n, 0);
> > + if (err < 0)
> > + goto end_thread;
> > + break;
> > + }
> > + default:
> > + break;
> > + }
> > + }
> > +
> > +end_thread:
> > + pthread_join(dut_thread, NULL);
> > +out:
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > + close(ctrl_sockfd);
> > + free_fds(sockfd, 1);
> > +
> > + return err;
> > +}
> > +
> > +static bool tester_collect_advertised_cap(unsigned int cap)
> > +{
> > + switch (env.feature) {
> > + case XDP_FEATURE_ABORTED:
> > + case XDP_FEATURE_DROP:
> > + case XDP_FEATURE_PASS:
> > + case XDP_FEATURE_TX:
> > + return cap & NETDEV_XDP_ACT_BASIC;
> > + case XDP_FEATURE_REDIRECT:
> > + return cap & NETDEV_XDP_ACT_REDIRECT;
> > + case XDP_FEATURE_NDO_XMIT:
> > + return cap & NETDEV_XDP_ACT_NDO_XMIT;
> > + default:
> > + return false;
> > + }
> > +}
> > +
> > +static bool tester_collect_detected_cap(struct xdp_features *skel,
> > + unsigned int dut_stats)
> > +{
> > + unsigned int err, key = 0, val;
> > +
> > + if (!dut_stats)
> > + return false;
> > +
> > + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key),
> > + &val, sizeof(val), 0);
> > + if (err) {
> > + fprintf(stderr, "bpf_map_lookup_elem failed\n");
> > + return false;
> > + }
> > +
> > + switch (env.feature) {
> > + case XDP_FEATURE_PASS:
> > + case XDP_FEATURE_TX:
> > + case XDP_FEATURE_REDIRECT:
> > + case XDP_FEATURE_NDO_XMIT:
> > + return val > 0;
> > + case XDP_FEATURE_DROP:
> > + case XDP_FEATURE_ABORTED:
> > + return val == 0;
> > + default:
> > + return false;
> > + }
> > +}
> > +
> > +static int __send_and_recv_msg(int sockfd, enum test_commands cmd,
> > + unsigned int *val, unsigned int val_size)
> > +{
> > + unsigned char buf[BUFSIZE] = {};
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int n = sizeof(*tlv), err;
> > +
> > + tlv->type = htons(cmd);
> > + switch (cmd) {
> > + case CMD_START:
> > + tlv->data[0] = htonl(env.feature);
> > + n += sizeof(*val);
> > + break;
> > + default:
> > + break;
> > + }
> > + tlv->len = htons(n);
> > +
> > + err = send(sockfd, buf, n, 0);
> > + if (err < 0)
> > + return err;
> > +
> > + err = __recv_msg(sockfd, buf, BUFSIZE, val, val_size);
> > + if (err < 0)
> > + return err;
> > +
> > + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL;
> > +}
> > +
> > +static int send_and_recv_msg(int sockfd, enum test_commands cmd)
> > +{
> > + return __send_and_recv_msg(sockfd, cmd, NULL, 0);
> > +}
> > +
> > +static int send_echo_msg(void)
> > +{
> > + unsigned char buf[sizeof(struct tlv_hdr)];
> > + struct tlv_hdr *tlv = (struct tlv_hdr *)buf;
> > + int sockfd, n;
> > +
> > + sockfd = socket(env.family, SOCK_DGRAM, 0);
> > + if (sockfd < 0) {
> > + fprintf(stderr, "Failed to create echo socket\n");
> > + return -errno;
> > + }
> > +
> > + tlv->type = htons(CMD_ECHO);
> > + tlv->len = htons(sizeof(*tlv));
> > +
> > + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM,
> > + (struct sockaddr *)&env.dut.addr, env.dut.addrlen);
> > + close(sockfd);
> > +
> > + return n == ntohs(tlv->len) ? 0 : -EINVAL;
> > +}
> > +
> > +static int tester_run(struct xdp_features *skel)
> > +{
> > + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE;
> > + bool advertised_cap;
> > + unsigned int val[1];
> > + int i, err, sockfd;
> > + bool detected_cap;
> > +
> > + sockfd = socket(env.family, SOCK_STREAM, 0);
> > + if (sockfd < 0) {
> > + fprintf(stderr, "Failed to create tester socket\n");
> > + return -errno;
> > + }
> > +
> > + if (settimeo(sockfd, 1000) < 0)
> > + return -EINVAL;
> > +
> > + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl.addr,
> > + env.dut_ctrl.addrlen);
> > + if (err) {
> > + fprintf(stderr, "Failed to connect to the DUT\n");
> > + return -errno;
> > + }
> > +
> > + err = __send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, val,
> > + ARRAY_SIZE(val));
> > + if (err < 0) {
> > + close(sockfd);
> > + return err;
> > + }
> > +
> > + advertised_cap = tester_collect_advertised_cap(val[0]);
> > +
> > + err = bpf_xdp_attach(env.ifindex,
> > + bpf_program__fd(skel->progs.xdp_tester),
> > + flags, NULL);
> > + if (err) {
> > + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n",
> > + env.ifindex);
> > + goto out;
> > + }
> > +
> > + err = send_and_recv_msg(sockfd, CMD_START);
> > + if (err)
> > + goto out;
> > +
> > + for (i = 0; i < 10 && !exiting; i++) {
> > + err = send_echo_msg();
> > + if (err < 0)
> > + goto out;
> > +
> > + sleep(1);
> > + }
> > +
> > + err = __send_and_recv_msg(sockfd, CMD_GET_STATS, val, ARRAY_SIZE(val));
> > + if (err)
> > + goto out;
> > +
> > + /* stop the test */
> > + err = send_and_recv_msg(sockfd, CMD_STOP);
> > + /* send a new echo message to wake echo thread of the dut */
> > + send_echo_msg();
> > +
> > + detected_cap = tester_collect_detected_cap(skel, val[0]);
> > +
> > + fprintf(stdout, "Feature %s: [%s][%s]\n",
> > get_xdp_feature_str(env.feature),
> > + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"),
> > + advertised_cap ? GREEN("ADVERTISED") : RED("NOT ADVERTISED"));
> > +out:
> > + bpf_xdp_detach(env.ifindex, flags, NULL);
> > + close(sockfd);
> > + return err < 0 ? err : 0;
> > +}
> > +
> > +static void set_skel_rodata(struct xdp_features *skel)
> > +{
> > + skel->rodata->expected_feature = env.feature;
> > + if (env.family == AF_INET6) {
> > + struct sockaddr_in6 *tester_addr = (void *)&env.tester.addr;
> > + struct sockaddr_in6 *dut_addr = (void *)&env.dut.addr;
> > +
> > + skel->rodata->tester_addr.ip6 = tester_addr->sin6_addr;
> > + skel->rodata->dut_addr.ip6 = dut_addr->sin6_addr;
> > + } else {
> > + struct sockaddr_in *tester_addr = (void *)&env.tester.addr;
> > + struct sockaddr_in *dut_addr = (void *)&env.dut.addr;
> > +
> > + skel->rodata->tester_addr.ip = tester_addr->sin_addr;
> > + skel->rodata->dut_addr.ip = dut_addr->sin_addr;
> > + }
> > +}
> > +
> > +int main(int argc, char **argv)
> > +{
> > + struct xdp_features *skel;
> > + int err;
> > +
> > + libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
> > + libbpf_set_print(libbpf_print_fn);
> > +
> > + signal(SIGINT, sig_handler);
> > + signal(SIGTERM, sig_handler);
> > +
> > + set_env_defaul();
> > +
> > + /* Parse command line arguments */
> > + err = argp_parse(&argp, argc, argv, 0, NULL, NULL);
> > + if (err)
> > + return err;
> > +
> > + if (env.ifindex < 0) {
> > + fprintf(stderr, "Invalid ifindex\n");
> > + return -ENODEV;
> > + }
> > +
> > + /* Load and verify BPF application */
> > + skel = xdp_features__open();
> > + if (!skel) {
> > + fprintf(stderr, "Failed to open and load BPF skeleton\n");
> > + return -EINVAL;
> > + }
> > +
> > + set_skel_rodata(skel);
> > +
> > + /* Load & verify BPF programs */
> > + err = xdp_features__load(skel);
> > + if (err) {
> > + fprintf(stderr, "Failed to load and verify BPF skeleton\n");
> > + goto cleanup;
> > + }
> > +
> > + err = xdp_features__attach(skel);
> > + if (err) {
> > + fprintf(stderr, "Failed to attach BPF skeleton\n");
> > + goto cleanup;
> > + }
> > +
> > + if (env.is_tester) {
> > + /* Tester */
> > + fprintf(stdout, "Starting tester on device %d\n", env.ifindex);
> > + err = tester_run(skel);
> > + } else {
> > + /* DUT */
> > + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex);
> > + err = dut_run(skel);
> > + }
> > +
> > +cleanup:
> > + xdp_features__destroy(skel);
> > +
> > + return err < 0 ? -err : 0;
> > +}
> > diff --git a/tools/testing/selftests/bpf/xdp_features.h
> > b/tools/testing/selftests/bpf/xdp_features.h
> > new file mode 100644
> > index 000000000000..28d7614c4f02
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/xdp_features.h
> > @@ -0,0 +1,33 @@
> > +/* SPDX-License-Identifier: GPL-2.0 */
> > +
> > +/* test commands */
> > +enum test_commands {
> > + CMD_STOP, /* CMD */
> > + CMD_START, /* CMD + xdp feature */
> > + CMD_ECHO, /* CMD */
> > + CMD_ACK, /* CMD + data */
> > + CMD_GET_XDP_CAP, /* CMD */
> > + CMD_GET_STATS, /* CMD */
> > +};
> > +
> > +#define DUT_CTRL_PORT 12345
> > +#define DUT_ECHO_PORT 12346
> > +
> > +struct tlv_hdr {
> > + __be16 type;
> > + __be16 len;
> > + __be32 data[];
> > +};
> > +
> > +enum {
> > + XDP_FEATURE_ABORTED,
> > + XDP_FEATURE_DROP,
> > + XDP_FEATURE_PASS,
> > + XDP_FEATURE_TX,
> > + XDP_FEATURE_REDIRECT,
> > + XDP_FEATURE_NDO_XMIT,
> > + XDP_FEATURE_XSK_ZEROCOPY,
> > + XDP_FEATURE_HW_OFFLOAD,
> > + XDP_FEATURE_RX_SG,
> > + XDP_FEATURE_NDO_XMIT_SG,
> > +};
> > --
> > 2.39.1
>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 228 bytes --]
^ permalink raw reply [flat|nested] 32+ messages in thread