Commit 08c6a2f6 authored by Daniel Borkmann's avatar Daniel Borkmann
Browse files

Merge branch 'bpf-xsk-selftests' 



Weqaar Janjua says:

====================
This patch set adds AF_XDP selftests based on veth to selftests/bpf.

 # Topology:
 # ---------
 #                 -----------
 #               _ | Process | _
 #              /  -----------  \
 #             /        |        \
 #            /         |         \
 #      -----------     |     -----------
 #      | Thread1 |     |     | Thread2 |
 #      -----------     |     -----------
 #           |          |          |
 #      -----------     |     -----------
 #      |  xskX   |     |     |  xskY   |
 #      -----------     |     -----------
 #           |          |          |
 #      -----------     |     ----------
 #      |  vethX  | --------- |  vethY |
 #      -----------   peer    ----------
 #           |          |          |
 #      namespaceX      |     namespaceY

These selftests test AF_XDP SKB and Native/DRV modes using veth Virtual
Ethernet interfaces.

The test program contains two threads, each thread is single socket with
a unique UMEM. It validates in-order packet delivery and packet content
by sending packets to each other.

Prerequisites setup by script test_xsk.sh:

   Set up veth interfaces as per the topology shown ^^:
   * setup two veth interfaces and one namespace
   ** veth<xxxx> in root namespace
   ** veth<yyyy> in af_xdp<xxxx> namespace
   ** namespace af_xdp<xxxx>
   * create a spec file veth.spec that includes this run-time configuration
   *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid
       conflict with any existing interface

   Adds xsk framework test to validate veth xdp DRV and SKB modes.

The following tests are provided:

1. AF_XDP SKB mode
   Generic mode XDP is driver independent, used when the driver does
   not have support for XDP. Works on any netdevice using sockets and
   generic XDP path. XDP hook from netif_receive_skb().
   a. nopoll - soft-irq processing
   b. poll - using poll() syscall
   c. Socket Teardown
      Create a Tx and a Rx socket, Tx from one socket, Rx on another.
      Destroy both sockets, then repeat multiple times. Only nopoll mode
	  is used
   d. Bi-directional Sockets
      Configure sockets as bi-directional tx/rx sockets, sets up fill
	  and completion rings on each socket, tx/rx in both directions.
	  Only nopoll mode is used

2. AF_XDP DRV/Native mode
   Works on any netdevice with XDP_REDIRECT support, driver dependent.
   Processes packets before SKB allocation. Provides better performance
   than SKB. Driver hook available just after DMA of buffer descriptor.
   a. nopoll
   b. poll
   c. Socket Teardown
   d. Bi-directional Sockets
   * Only copy mode is supported because veth does not currently support
     zero-copy mode

Total tests: 8

Flow:
* Single process spawns two threads: Tx and Rx
* Each of these two threads attach to a veth interface within their
  assigned namespaces
* Each thread creates one AF_XDP socket connected to a unique umem
  for each veth interface
* Tx thread transmits 10k packets from veth<xxxx> to veth<yyyy>
* Rx thread verifies if all 10k packets were received and delivered
  in-order, and have the right content

v2 changes:
* Move selftests/xsk to selftests/bpf
* Remove Makefiles under selftests/xsk, and utilize selftests/bpf/Makefile
v3 changes:
* merge all test scripts test_xsk_*.sh into test_xsk.sh
v4 changes:
* merge xsk_env.sh into xsk_prereqs.sh
* test_xsk.sh add cliarg -c for color-coded output
* test_xsk.sh PREREQUISITES disables IPv6 on veth interfaces
* test_xsk.sh PREREQUISITES adds xsk framework test
* test_xsk.sh is independently executable
* xdpxceiver.c Tx/Rx validates only IPv4 packets with TOS 0x9, ignores
  others
====================

Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parents b60da495 7d20441e

tools/testing/selftests/bpf/Makefile

+5 −2
Original line number Diff line number Diff line
@@ -46,7 +46,8 @@ endif 


TEST_GEN_FILES =

TEST_FILES = test_lwt_ip_encap.o \

	test_tc_edt.o

	test_tc_edt.o \

	xsk_prereqs.sh



# Order correspond to 'make run_tests' order

TEST_PROGS := test_kmod.sh \
@@ -70,6 +71,7 @@ TEST_PROGS := test_kmod.sh \ 
	test_bpftool_build.sh \

	test_bpftool.sh \

	test_bpftool_metadata.sh \

	test_xsk.sh



TEST_PROGS_EXTENDED := with_addr.sh \

	with_tunnels.sh \
@@ -80,7 +82,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \ 
# Compile but not part of 'make run_tests'

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

	test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \

	xdpxceiver



TEST_CUSTOM_PROGS = urandom_read

tools/testing/selftests/bpf/test_xsk.sh

0 → 100755
+259 −0
Original line number Diff line number Diff line 
#!/bin/bash

# SPDX-License-Identifier: GPL-2.0

# Copyright(c) 2020 Intel Corporation, Weqaar Janjua <weqaar.a.janjua@intel.com>



# AF_XDP selftests based on veth

#

# End-to-end AF_XDP over Veth test

#

# Topology:

# ---------

#                 -----------

#               _ | Process | _

#              /  -----------  \

#             /        |        \

#            /         |         \

#      -----------     |     -----------

#      | Thread1 |     |     | Thread2 |

#      -----------     |     -----------

#           |          |          |

#      -----------     |     -----------

#      |  xskX   |     |     |  xskY   |

#      -----------     |     -----------

#           |          |          |

#      -----------     |     ----------

#      |  vethX  | --------- |  vethY |

#      -----------   peer    ----------

#           |          |          |

#      namespaceX      |     namespaceY

#

# AF_XDP is an address family optimized for high performance packet processing,

# it is XDP’s user-space interface.

#

# An AF_XDP socket is linked to a single UMEM which is a region of virtual

# contiguous memory, divided into equal-sized frames.

#

# Refer to AF_XDP Kernel Documentation for detailed information:

# https://www.kernel.org/doc/html/latest/networking/af_xdp.html

#

# Prerequisites setup by script:

#

#   Set up veth interfaces as per the topology shown ^^:

#   * setup two veth interfaces and one namespace

#   ** veth<xxxx> in root namespace

#   ** veth<yyyy> in af_xdp<xxxx> namespace

#   ** namespace af_xdp<xxxx>

#   * create a spec file veth.spec that includes this run-time configuration

#   *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid

#       conflict with any existing interface

#   * tests the veth and xsk layers of the topology

#

# See the source xdpxceiver.c for information on each test

#

# Kernel configuration:

# ---------------------

# See "config" file for recommended kernel config options.

#

# Turn on XDP sockets and veth support when compiling i.e.

# 	Networking support -->

# 		Networking options -->

# 			[ * ] XDP sockets

#

# Executing Tests:

# ----------------

# Must run with CAP_NET_ADMIN capability.

#

# Run (full color-coded output):

#   sudo ./test_xsk.sh -c

#

# If running from kselftests:

#   sudo make colorconsole=1 run_tests

#

# Run (full output without color-coding):

#   sudo ./test_xsk.sh



. xsk_prereqs.sh



while getopts c flag

do

	case "${flag}" in

		c) colorconsole=1;;

	esac

done



TEST_NAME="PREREQUISITES"



URANDOM=/dev/urandom

[ ! -e "${URANDOM}" ] && { echo "${URANDOM} not found. Skipping tests."; test_exit 1 1; }



VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)

VETH0=ve${VETH0_POSTFIX}

VETH1_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)

VETH1=ve${VETH1_POSTFIX}

NS0=root

NS1=af_xdp${VETH1_POSTFIX}

MTU=1500



setup_vethPairs() {

	echo "setting up ${VETH0}: namespace: ${NS0}"

	ip netns add ${NS1}

	ip link add ${VETH0} type veth peer name ${VETH1}

	if [ -f /proc/net/if_inet6 ]; then

		echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6

	fi

	echo "setting up ${VETH1}: namespace: ${NS1}"

	ip link set ${VETH1} netns ${NS1}

	ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}

	ip link set ${VETH0} mtu ${MTU}

	ip netns exec ${NS1} ip link set ${VETH1} up

	ip link set ${VETH0} up

}



validate_root_exec

validate_veth_support ${VETH0}

validate_ip_utility

setup_vethPairs



retval=$?

if [ $retval -ne 0 ]; then

	test_status $retval "${TEST_NAME}"

	cleanup_exit ${VETH0} ${VETH1} ${NS1}

	exit $retval

fi



echo "${VETH0}:${VETH1},${NS1}" > ${SPECFILE}



validate_veth_spec_file



echo "Spec file created: ${SPECFILE}"



test_status $retval "${TEST_NAME}"



## START TESTS



statusList=()



### TEST 1

TEST_NAME="XSK KSELFTEST FRAMEWORK"



echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"

vethXDPgeneric ${VETH0} ${VETH1} ${NS1}



retval=$?

if [ $retval -eq 0 ]; then

	echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"

	vethXDPnative ${VETH0} ${VETH1} ${NS1}

fi



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 2

TEST_NAME="SKB NOPOLL"



vethXDPgeneric ${VETH0} ${VETH1} ${NS1}



params=("-S")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 3

TEST_NAME="SKB POLL"



vethXDPgeneric ${VETH0} ${VETH1} ${NS1}



params=("-S" "-p")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 4

TEST_NAME="DRV NOPOLL"



vethXDPnative ${VETH0} ${VETH1} ${NS1}



params=("-N")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 5

TEST_NAME="DRV POLL"



vethXDPnative ${VETH0} ${VETH1} ${NS1}



params=("-N" "-p")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 6

TEST_NAME="SKB SOCKET TEARDOWN"



vethXDPgeneric ${VETH0} ${VETH1} ${NS1}



params=("-S" "-T")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 7

TEST_NAME="DRV SOCKET TEARDOWN"



vethXDPnative ${VETH0} ${VETH1} ${NS1}



params=("-N" "-T")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 8

TEST_NAME="SKB BIDIRECTIONAL SOCKETS"



vethXDPgeneric ${VETH0} ${VETH1} ${NS1}



params=("-S" "-B")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



### TEST 9

TEST_NAME="DRV BIDIRECTIONAL SOCKETS"



vethXDPnative ${VETH0} ${VETH1} ${NS1}



params=("-N" "-B")

execxdpxceiver params



retval=$?

test_status $retval "${TEST_NAME}"

statusList+=($retval)



## END TESTS



cleanup_exit ${VETH0} ${VETH1} ${NS1}



for _status in "${statusList[@]}"

do

	if [ $_status -ne 0 ]; then

		test_exit $ksft_fail 0

	fi

done



test_exit $ksft_pass 0

tools/testing/selftests/bpf/xdpxceiver.c

0 → 100644
+1074 −0

File added.

Preview size limit exceeded, changes collapsed.

tools/testing/selftests/bpf/xdpxceiver.h

0 → 100644
+160 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0

 * Copyright(c) 2020 Intel Corporation.

 */



#ifndef XDPXCEIVER_H_

#define XDPXCEIVER_H_



#ifndef SOL_XDP

#define SOL_XDP 283

#endif



#ifndef AF_XDP

#define AF_XDP 44

#endif



#ifndef PF_XDP

#define PF_XDP AF_XDP

#endif



#define MAX_INTERFACES 2

#define MAX_INTERFACE_NAME_CHARS 7

#define MAX_INTERFACES_NAMESPACE_CHARS 10

#define MAX_SOCKS 1

#define MAX_TEARDOWN_ITER 10

#define MAX_BIDI_ITER 2

#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \

			sizeof(struct udphdr))

#define MIN_PKT_SIZE 64

#define ETH_FCS_SIZE 4

#define PKT_SIZE (MIN_PKT_SIZE - ETH_FCS_SIZE)

#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr))

#define IP_PKT_VER 0x4

#define IP_PKT_TOS 0x9

#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))

#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))

#define TMOUT_SEC (3)

#define EOT (-1)

#define USLEEP_MAX 200000

#define THREAD_STACK 60000000

#define SOCK_RECONF_CTR 10

#define BATCH_SIZE 64

#define POLL_TMOUT 1000

#define NEED_WAKEUP true



typedef __u32 u32;

typedef __u16 u16;

typedef __u8 u8;



enum TESTS {

	ORDER_CONTENT_VALIDATE_XDP_SKB = 0,

	ORDER_CONTENT_VALIDATE_XDP_DRV = 1,

};



u8 uut;

u8 debug_pkt_dump;

u32 num_frames;

u8 switching_notify;

u8 bidi_pass;



static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;

static int opt_queue;

static int opt_pkt_count;

static int opt_poll;

static int opt_teardown;

static int opt_bidi;

static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;

static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];

static u32 pkt_counter;

static u32 prev_pkt = -1;

static int sigvar;



struct xsk_umem_info {

	struct xsk_ring_prod fq;

	struct xsk_ring_cons cq;

	struct xsk_umem *umem;

	void *buffer;

};



struct xsk_socket_info {

	struct xsk_ring_cons rx;

	struct xsk_ring_prod tx;

	struct xsk_umem_info *umem;

	struct xsk_socket *xsk;

	unsigned long rx_npkts;

	unsigned long tx_npkts;

	unsigned long prev_rx_npkts;

	unsigned long prev_tx_npkts;

	u32 outstanding_tx;

};



struct flow_vector {

	enum fvector {

		tx,

		rx,

		bidi,

		undef,

	} vector;

};



struct generic_data {

	u32 seqnum;

};



struct ifaceconfigobj {

	u8 dst_mac[ETH_ALEN];

	u8 src_mac[ETH_ALEN];

	struct in_addr dst_ip;

	struct in_addr src_ip;

	u16 src_port;

	u16 dst_port;

} *ifaceconfig;



struct ifobject {

	int ifindex;

	int ifdict_index;

	char ifname[MAX_INTERFACE_NAME_CHARS];

	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];

	struct flow_vector fv;

	struct xsk_socket_info *xsk;

	struct xsk_umem_info *umem;

	u8 dst_mac[ETH_ALEN];

	u8 src_mac[ETH_ALEN];

	u32 dst_ip;

	u32 src_ip;

	u16 src_port;

	u16 dst_port;

};



static struct ifobject *ifdict[MAX_INTERFACES];



/*threads*/

atomic_int spinning_tx;

atomic_int spinning_rx;

pthread_mutex_t sync_mutex;

pthread_mutex_t sync_mutex_tx;

pthread_cond_t signal_rx_condition;

pthread_cond_t signal_tx_condition;

pthread_t t0, t1, ns_thread;

pthread_attr_t attr;



struct targs {

	bool retptr;

	int idx;

};



TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);

struct head_s *head_p;

struct pkt {

	char *pkt_frame;



	TAILQ_ENTRY(pkt) pkt_nodes;

} *pkt_node_rx, *pkt_node_rx_q;



struct pkt_frame {

	char *payload;

} *pkt_obj;



struct pkt_frame **pkt_buf;



#endif				/* XDPXCEIVER_H */

tools/testing/selftests/bpf/xsk_prereqs.sh

0 → 100755
+135 −0
Original line number Diff line number Diff line 
#!/bin/bash

# SPDX-License-Identifier: GPL-2.0

# Copyright(c) 2020 Intel Corporation.



ksft_pass=0

ksft_fail=1

ksft_xfail=2

ksft_xpass=3

ksft_skip=4



GREEN='\033[0;92m'

YELLOW='\033[0;93m'

RED='\033[0;31m'

NC='\033[0m'

STACK_LIM=131072

SPECFILE=veth.spec

XSKOBJ=xdpxceiver

NUMPKTS=10000



validate_root_exec()

{

	msg="skip all tests:"

	if [ $UID != 0 ]; then

		echo $msg must be run as root >&2

		test_exit $ksft_fail 2

	else

		return $ksft_pass

	fi

}



validate_veth_support()

{

	msg="skip all tests:"

	if [ $(ip link add $1 type veth 2>/dev/null; echo $?;) != 0 ]; then

		echo $msg veth kernel support not available >&2

		test_exit $ksft_skip 1

	else

		ip link del $1

		return $ksft_pass

	fi

}



validate_veth_spec_file()

{

	if [ ! -f ${SPECFILE} ]; then

		test_exit $ksft_skip 1

	fi

}



test_status()

{

	statusval=$1

	if [ -n "${colorconsole+set}" ]; then

		if [ $statusval -eq 2 ]; then

			echo -e "${YELLOW}$2${NC}: [ ${RED}FAIL${NC} ]"

		elif [ $statusval -eq 1 ]; then

			echo -e "${YELLOW}$2${NC}: [ ${RED}SKIPPED${NC} ]"

		elif [ $statusval -eq 0 ]; then

			echo -e "${YELLOW}$2${NC}: [ ${GREEN}PASS${NC} ]"

		fi

	else

		if [ $statusval -eq 2 ]; then

			echo -e "$2: [ FAIL ]"

		elif [ $statusval -eq 1 ]; then

			echo -e "$2: [ SKIPPED ]"

		elif [ $statusval -eq 0 ]; then

			echo -e "$2: [ PASS ]"

		fi

	fi

}



test_exit()

{

	retval=$1

	if [ $2 -ne 0 ]; then

		test_status $2 $(basename $0)

	fi

	exit $retval

}



clear_configs()

{

	if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then

		[ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] &&

			{ echo "removing link $1:$2"; ip netns exec $3 ip link del $2; }

		echo "removing ns $3"

		ip netns del $3

	fi

	#Once we delete a veth pair node, the entire veth pair is removed,

	#this is just to be cautious just incase the NS does not exist then

	#veth node inside NS won't get removed so we explicitly remove it

	[ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&

		{ echo "removing link $1"; ip link del $1; }

	if [ -f ${SPECFILE} ]; then

		echo "removing spec file:" ${SPECFILE}

		rm -f ${SPECFILE}

	fi

}



cleanup_exit()

{

	echo "cleaning up..."

	clear_configs $1 $2 $3

}



validate_ip_utility()

{

	[ ! $(type -P ip) ] && { echo "'ip' not found. Skipping tests."; test_exit $ksft_skip 1; }

}



vethXDPgeneric()

{

	ip link set dev $1 xdpdrv off

	ip netns exec $3 ip link set dev $2 xdpdrv off

}



vethXDPnative()

{

	ip link set dev $1 xdpgeneric off

	ip netns exec $3 ip link set dev $2 xdpgeneric off

}



execxdpxceiver()

{

	local -a 'paramkeys=("${!'"$1"'[@]}")' copy

	paramkeysstr=${paramkeys[*]}



	for index in $paramkeysstr;

		do

			current=$1"[$index]"

			copy[$index]=${!current}

		done



	./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS}

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE