Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

1 files changed, 295 insertions, 32 deletions

diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 0ab9423d009f..a369d616b390 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -6,6 +6,26 @@
 #
 # Tests currently implemented:
 #
+# - pmtu_ipv4
+#	Set up two namespaces, A and B, with two paths between them over routers
+#	R1 and R2 (also implemented with namespaces), with different MTUs:
+#
+#	  segment a_r1    segment b_r1		a_r1: 2000
+#	.--------------R1--------------.	a_r2: 1500
+#	A                               B	a_r3: 2000
+#	'--------------R2--------------'	a_r4: 1400
+#	  segment a_r2    segment b_r2
+#
+#	Check that PMTU exceptions with the correct PMTU are created. Then
+#	decrease and increase the MTU of the local link for one of the paths,
+#	A to R1, checking that route exception PMTU changes accordingly over
+#	this path. Also check that locked exceptions are created when an ICMP
+#	message advertising a PMTU smaller than net.ipv4.route.min_pmtu is
+#	received
+#
+# - pmtu_ipv6
+#	Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
+#
 # - pmtu_vti4_exception
 #	Set up vti tunnel on top of veth, with xfrm states and policies, in two
 #	namespaces with matching endpoints. Check that route exception is not
@@ -50,6 +70,8 @@ ksft_skip=4
 which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
 
 tests="
+	pmtu_ipv4_exception		ipv4: PMTU exceptions
+	pmtu_ipv6_exception		ipv6: PMTU exceptions
 	pmtu_vti6_exception		vti6: PMTU exceptions
 	pmtu_vti4_exception		vti4: PMTU exceptions
 	pmtu_vti4_default_mtu		vti4: default MTU assignment
@@ -60,8 +82,45 @@ tests="
 
 NS_A="ns-$(mktemp -u XXXXXX)"
 NS_B="ns-$(mktemp -u XXXXXX)"
+NS_R1="ns-$(mktemp -u XXXXXX)"
+NS_R2="ns-$(mktemp -u XXXXXX)"
 ns_a="ip netns exec ${NS_A}"
 ns_b="ip netns exec ${NS_B}"
+ns_r1="ip netns exec ${NS_R1}"
+ns_r2="ip netns exec ${NS_R2}"
+
+# Addressing and routing for tests with routers: four network segments, with
+# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
+# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
+# Addresses are:
+# - IPv4: PREFIX4.SEGMENT.ID (/24)
+# - IPv6: PREFIX6:SEGMENT::ID (/64)
+prefix4="192.168"
+prefix6="fd00"
+a_r1=1
+a_r2=2
+b_r1=3
+b_r2=4
+#	ns	peer	segment
+routing_addrs="
+	A	R1	${a_r1}
+	A	R2	${a_r2}
+	B	R1	${b_r1}
+	B	R2	${b_r2}
+"
+# Traffic from A to B goes through R1 by default, and through R2, if destined to
+# B's address on the b_r2 segment.
+# Traffic from B to A goes through R1.
+#	ns	destination		gateway
+routes="
+	A	default			${prefix4}.${a_r1}.2
+	A	${prefix4}.${b_r2}.1	${prefix4}.${a_r2}.2
+	B	default			${prefix4}.${b_r1}.2
+
+	A	default			${prefix6}:${a_r1}::2
+	A	${prefix6}:${b_r2}::1	${prefix6}:${a_r2}::2
+	B	default			${prefix6}:${b_r1}::2
+"
 
 veth4_a_addr="192.168.1.1"
 veth4_b_addr="192.168.1.2"
@@ -83,6 +142,7 @@ dummy6_mask="64"
 
 cleanup_done=1
 err_buf=
+tcpdump_pids=
 
 err() {
 	err_buf="${err_buf}${1}
@@ -94,9 +154,15 @@ err_flush() {
 	err_buf=
 }
 
+# Find the auto-generated name for this namespace
+nsname() {
+	eval echo \$NS_$1
+}
+
 setup_namespaces() {
-	ip netns add ${NS_A} || return 1
-	ip netns add ${NS_B}
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns add ${n} || return 1
+	done
 }
 
 setup_veth() {
@@ -167,6 +233,49 @@ setup_xfrm6() {
 	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
 }
 
+setup_routing() {
+	for i in ${NS_R1} ${NS_R2}; do
+		ip netns exec ${i} sysctl -q net/ipv4/ip_forward=1
+		ip netns exec ${i} sysctl -q net/ipv6/conf/all/forwarding=1
+	done
+
+	for i in ${routing_addrs}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${peer}" = "" ]	&& peer="${i}"		&& continue
+		[ "${segment}" = "" ]	&& segment="${i}"
+
+		ns_name="$(nsname ${ns})"
+		peer_name="$(nsname ${peer})"
+		if="veth_${ns}-${peer}"
+		ifpeer="veth_${peer}-${ns}"
+
+		# Create veth links
+		ip link add ${if} up netns ${ns_name} type veth peer name ${ifpeer} netns ${peer_name} || return 1
+		ip -n ${peer_name} link set dev ${ifpeer} up
+
+		# Add addresses
+		ip -n ${ns_name}   addr add ${prefix4}.${segment}.1/24  dev ${if}
+		ip -n ${ns_name}   addr add ${prefix6}:${segment}::1/64 dev ${if}
+
+		ip -n ${peer_name} addr add ${prefix4}.${segment}.2/24  dev ${ifpeer}
+		ip -n ${peer_name} addr add ${prefix6}:${segment}::2/64 dev ${ifpeer}
+
+		ns=""; peer=""; segment=""
+	done
+
+	for i in ${routes}; do
+		[ "${ns}" = "" ]	&& ns="${i}"		&& continue
+		[ "${addr}" = "" ]	&& addr="${i}"		&& continue
+		[ "${gw}" = "" ]	&& gw="${i}"
+
+		ns_name="$(nsname ${ns})"
+
+		ip -n ${ns_name} route add ${addr} via ${gw}
+
+		ns=""; addr=""; gw=""
+	done
+}
+
 setup() {
 	[ "$(id -u)" -ne 0 ] && echo "  need to run as root" && return $ksft_skip
 
@@ -176,10 +285,28 @@ setup() {
 	done
 }
 
+trace() {
+	[ $tracing -eq 0 ] && return
+
+	for arg do
+		[ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue
+		${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null &
+		tcpdump_pids="${tcpdump_pids} $!"
+		ns_cmd=
+	done
+	sleep 1
+}
+
 cleanup() {
+	for pid in ${tcpdump_pids}; do
+		kill ${pid}
+	done
+	tcpdump_pids=
+
 	[ ${cleanup_done} -eq 1 ] && return
-	ip netns del ${NS_A} 2> /dev/null
-	ip netns del ${NS_B} 2> /dev/null
+	for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
+		ip netns del ${n} 2> /dev/null
+	done
 	cleanup_done=1
 }
 
@@ -196,7 +323,9 @@ mtu_parse() {
 
 	next=0
 	for i in ${input}; do
+		[ ${next} -eq 1 -a "${i}" = "lock" ] && next=2 && continue
 		[ ${next} -eq 1 ] && echo "${i}" && return
+		[ ${next} -eq 2 ] && echo "lock ${i}" && return
 		[ "${i}" = "mtu" ] && next=1
 	done
 }
@@ -229,8 +358,117 @@ route_get_dst_pmtu_from_exception() {
 	mtu_parse "$(route_get_dst_exception "${ns_cmd}" ${dst})"
 }
 
+check_pmtu_value() {
+	expected="${1}"
+	value="${2}"
+	event="${3}"
+
+	[ "${expected}" = "any" ] && [ -n "${value}" ] && return 0
+	[ "${value}" = "${expected}" ] && return 0
+	[ -z "${value}" ] &&    err "  PMTU exception wasn't created after ${event}" && return 1
+	[ -z "${expected}" ] && err "  PMTU exception shouldn't exist after ${event}" && return 1
+	err "  found PMTU exception with incorrect MTU ${value}, expected ${expected}, after ${event}"
+	return 1
+}
+
+test_pmtu_ipvX() {
+	family=${1}
+
+	setup namespaces routing || return 2
+	trace "${ns_a}"  veth_A-R1    "${ns_r1}" veth_R1-A \
+	      "${ns_r1}" veth_R1-B    "${ns_b}"  veth_B-R1 \
+	      "${ns_a}"  veth_A-R2    "${ns_r2}" veth_R2-A \
+	      "${ns_r2}" veth_R2-B    "${ns_b}"  veth_B-R2
+
+	if [ ${family} -eq 4 ]; then
+		ping=ping
+		dst1="${prefix4}.${b_r1}.1"
+		dst2="${prefix4}.${b_r2}.1"
+	else
+		ping=${ping6}
+		dst1="${prefix6}:${b_r1}::1"
+		dst2="${prefix6}:${b_r2}::1"
+	fi
+
+	# Set up initial MTU values
+	mtu "${ns_a}"  veth_A-R1 2000
+	mtu "${ns_r1}" veth_R1-A 2000
+	mtu "${ns_r1}" veth_R1-B 1400
+	mtu "${ns_b}"  veth_B-R1 1400
+
+	mtu "${ns_a}"  veth_A-R2 2000
+	mtu "${ns_r2}" veth_R2-A 2000
+	mtu "${ns_r2}" veth_R2-B 1500
+	mtu "${ns_b}"  veth_B-R2 1500
+
+	# Create route exceptions
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null
+
+	# Check that exceptions have been created with the correct PMTU
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1400" "${pmtu_1}" "exceeding MTU" || return 1
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "exceeding MTU" || return 1
+
+	# Decrease local MTU below PMTU, check for PMTU decrease in route exception
+	mtu "${ns_a}"  veth_A-R1 1300
+	mtu "${ns_r1}" veth_R1-A 1300
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1300" "${pmtu_1}" "decreasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Increase MTU, check for PMTU increase in route exception
+	mtu "${ns_a}"  veth_A-R1 1700
+	mtu "${ns_r1}" veth_R1-A 1700
+	pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})"
+	check_pmtu_value "1700" "${pmtu_1}" "increasing local MTU" || return 1
+	# Second exception shouldn't be modified
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "changing local MTU on a link not on this path" || return 1
+
+	# Skip PMTU locking tests for IPv6
+	[ $family -eq 6 ] && return 0
+
+	# Decrease remote MTU on path via R2, get new exception
+	mtu "${ns_r2}" veth_R2-B 400
+	mtu "${ns_b}"  veth_B-R2 400
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+
+	# Decrease local MTU below PMTU
+	mtu "${ns_a}"  veth_A-R2 500
+	mtu "${ns_r2}" veth_R2-A 500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "500" "${pmtu_2}" "decreasing local MTU" || return 1
+
+	# Increase local MTU
+	mtu "${ns_a}"  veth_A-R2 1500
+	mtu "${ns_r2}" veth_R2-A 1500
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1
+
+	# Get new exception
+	${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null
+	pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})"
+	check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1
+}
+
+test_pmtu_ipv4_exception() {
+	test_pmtu_ipvX 4
+}
+
+test_pmtu_ipv6_exception() {
+	test_pmtu_ipvX 6
+}
+
 test_pmtu_vti4_exception() {
 	setup namespaces veth vti4 xfrm4 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti4_a    "${ns_b}" vti4_b
 
 	veth_mtu=1500
 	vti_mtu=$((veth_mtu - 20))
@@ -248,28 +486,19 @@ test_pmtu_vti4_exception() {
 	# exception is created
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" != "" ]; then
-		err "  unexpected exception created with PMTU ${pmtu} for IP payload length ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
 
 	# Now exceed link layer MTU by one byte, check that exception is created
+	# with the right PMTU value
 	${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
 	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
-	if [ "${pmtu}" = "" ]; then
-		err "  exception not created for IP payload length $((esp_payload_rfc4106 + 1))"
-		return 1
-	fi
-
-	# ...with the right PMTU value
-	if [ ${pmtu} -ne ${esp_payload_rfc4106} ]; then
-		err "  wrong PMTU ${pmtu} in exception, expected: ${esp_payload_rfc4106}"
-		return 1
-	fi
+	check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
 }
 
 test_pmtu_vti6_exception() {
 	setup namespaces veth vti6 xfrm6 || return 2
+	trace "${ns_a}" veth_a    "${ns_b}" veth_b \
+	      "${ns_a}" vti6_a    "${ns_b}" vti6_b
 	fail=0
 
 	# Create route exception by exceeding link layer MTU
@@ -280,25 +509,18 @@ test_pmtu_vti6_exception() {
 	${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
 
 	# Check that exception was created
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then
-		err "  tunnel exceeding link layer MTU didn't create route exception"
-		return 1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
 
 	# Decrease tunnel MTU, check for PMTU decrease in route exception
 	mtu "${ns_a}" vti6_a 3000
-
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 3000 ]; then
-		err "  decreasing tunnel MTU didn't decrease route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
 
 	# Increase tunnel MTU, check for PMTU increase in route exception
 	mtu "${ns_a}" vti6_a 9000
-	if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" -ne 9000 ]; then
-		err "  increasing tunnel MTU didn't increase route exception PMTU"
-		fail=1
-	fi
+	pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+	check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
 
 	return ${fail}
 }
@@ -445,15 +667,56 @@ test_pmtu_vti6_link_change_mtu() {
 	return ${fail}
 }
 
-trap cleanup EXIT
+usage() {
+	echo
+	echo "$0 [OPTIONS] [TEST]..."
+	echo "If no TEST argument is given, all tests will be run."
+	echo
+	echo "Options"
+	echo "  --trace: capture traffic to TEST_INTERFACE.pcap"
+	echo
+	echo "Available tests${tests}"
+	exit 1
+}
 
 exitcode=0
 desc=0
 IFS="	
 "
+
+tracing=0
+for arg do
+	if [ "${arg}" != "${arg#--*}" ]; then
+		opt="${arg#--}"
+		if [ "${opt}" = "trace" ]; then
+			if which tcpdump > /dev/null 2>&1; then
+				tracing=1
+			else
+				echo "=== tcpdump not available, tracing disabled"
+			fi
+		else
+			usage
+		fi
+	else
+		# Check first that all requested tests are available before
+		# running any
+		command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+	fi
+done
+
+trap cleanup EXIT
+
 for t in ${tests}; do
 	[ $desc -eq 0 ] && name="${t}" && desc=1 && continue || desc=0
 
+	run_this=1
+	for arg do
+		[ "${arg}" != "${arg#--*}" ] && continue
+		[ "${arg}" = "${name}" ] && run_this=1 && break
+		run_this=0
+	done
+	[ $run_this -eq 0 ] && continue
+
 	(
 		unset IFS
 		eval test_${name}