- Linux-kselftest-mirror - lists.linaro.org

[PATCH AUTOSEL 4.19 43/81] selftests: netfilter: check icmp pkttoobig errors are set as related

by Sasha Levin

From: Florian Westphal <fw(a)strlen.de> [ Upstream commit becf2319f320cae43e20cf179cc51a355a0deb5f ] When an icmp error such as pkttoobig is received, conntrack checks if the "inner" header (header of packet that did not fit link mtu) is matches an existing connection, and, if so, sets that packet as being related to the conntrack entry it found. It was recently reported that this "related" setting also works if the inner header is from another, different connection (i.e., artificial/forged icmp error). Add a test, followup patch will add additional "inner dst matches outer dst in reverse direction" check before setting related state. Link: https://www.synacktiv.com/posts/systems/icmp-reachable.html Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/netfilter/Makefile | 2 +- .../netfilter/conntrack_icmp_related.sh | 283 ++++++++++++++++++ 2 files changed, 284 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_icmp_related.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain forward { + type filter hook forward priority 0; policy accept; + meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept + meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept + meta l4proto { icmp, icmpv6 } ct state new,established accept + counter name "unknown" drop + } +} +EOF +done + +ip netns exec nsclient1 nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept + counter name "unknown" drop + } +} +EOF + +ip netns exec nsclient2 nft -f - <<EOF +table inet filter { + counter unknown { } + counter new { } + counter established { } + + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept + counter name "unknown" drop + } + chain output { + type filter hook output priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" + counter name "unknown" drop + } +} +EOF + + +# make sure NAT core rewrites adress of icmp error if nat is used according to +# conntrack nat information (icmp error will be directed at nsrouter1 address, +# but it needs to be routed to nsclient1 address). +ip netns exec nsrouter1 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip protocol icmp oifname "veth0" counter masquerade + } +} +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip6 nexthdr icmpv6 oifname "veth0" counter masquerade + } +} +EOF + +ip netns exec nsrouter2 ip link set eth1 mtu 1280 +ip netns exec nsclient2 ip link set veth0 mtu 1280 +sleep 1 + +ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 4.19 23/81] selftests: fib_tests: Fix 'Command line is not complete' errors

by Sasha Levin

From: David Ahern <dsahern(a)gmail.com> [ Upstream commit a5f622984a623df9a84cf43f6b098d8dd76fbe05 ] A couple of tests are verifying a route has been removed. The helper expects the prefix as the first part of the expected output. When checking that a route has been deleted the prefix is empty leading to an invalid ip command: $ ip ro ls match Command line is not complete. Try option "help" Fix by moving the comparison of expected output and output to a new function that is used by both check_route and check_route6. Use the new helper for the 2 checks on route removal. Also, remove the reset of 'set -x' in route_setup which overrides the user managed setting. Fixes: d69faad76584c ("selftests: fib_tests: Add prefix route tests with metric") Signed-off-by: David Ahern <dsahern(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/fib_tests.sh | 94 ++++++++++-------------- 1 file changed, 40 insertions(+), 54 deletions(-) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a4ccde0e473b..2f190aa8fc5f 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -602,6 +602,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -646,31 +679,7 @@ check_route6() local rc=0 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -714,7 +723,7 @@ route_setup() $IP addr add 172.16.103.2/24 dev veth4 $IP addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -949,7 +958,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1009,34 +1019,9 @@ check_route() local pfx="172.16.104.0/24" local expected="$1" local out - local rc=0 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1301,7 +1286,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 5.0 73/99] selftests/net: correct the return value for run_afpackettests

by Sasha Levin

From: Po-Hsu Lin <po-hsu.lin(a)canonical.com> [ Upstream commit 8c03557c3f25271e62e39154af66ebdd1b59c9ca ] The run_afpackettests will be marked as passed regardless the return value of those sub-tests in the script: -------------------- running psock_tpacket test -------------------- [FAIL] selftests: run_afpackettests [PASS] Fix this by changing the return value for each tests. Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/run_afpackettests | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests index 2dc95fda7ef7..ea5938ec009a 100755 --- a/tools/testing/selftests/net/run_afpackettests +++ b/tools/testing/selftests/net/run_afpackettests @@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then exit 0 fi +ret=0 echo "--------------------" echo "running psock_fanout test" echo "--------------------" ./in_netns.sh ./psock_fanout if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -22,6 +24,7 @@ echo "--------------------" ./in_netns.sh ./psock_tpacket if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi @@ -32,6 +35,8 @@ echo "--------------------" ./in_netns.sh ./txring_overwrite if [ $? -ne 0 ]; then echo "[FAIL]" + ret=1 else echo "[PASS]" fi +exit $ret -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 5.0 72/99] selftests/net: correct the return value for run_netsocktests

by Sasha Levin

From: Po-Hsu Lin <po-hsu.lin(a)canonical.com> [ Upstream commit 30c04d796b693e22405c38e9b78e9a364e4c77e6 ] The run_netsocktests will be marked as passed regardless the actual test result from the ./socket: selftests: net: run_netsocktests ======================================== -------------------- running socket test -------------------- [FAIL] ok 1..6 selftests: net: run_netsocktests [PASS] This is because the test script itself has been successfully executed. Fix this by exit 1 when the test failed. Signed-off-by: Po-Hsu Lin <po-hsu.lin(a)canonical.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/run_netsocktests | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests index b093f39c298c..14e41faf2c57 100755 --- a/tools/testing/selftests/net/run_netsocktests +++ b/tools/testing/selftests/net/run_netsocktests @@ -7,7 +7,7 @@ echo "--------------------" ./socket if [ $? -ne 0 ]; then echo "[FAIL]" + exit 1 else echo "[PASS]" fi - -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 5.0 65/99] netfilter: nat: fix icmp id randomization

by Sasha Levin

From: Florian Westphal <fw(a)strlen.de> [ Upstream commit 5bdac418f33f60b07a34e01e722889140ee8fac9 ] Sven Auhagen reported that a 2nd ping request will fail if 'fully-random' mode is used. Reason is that if no proto information is given, min/max are both 0, so we set the icmp id to 0 instead of chosing a random value between 0 and 65535. Update test case as well to catch this, without fix this yields: [..] ERROR: cannot ping ns1 from ns2 with ip masquerade fully-random (attempt 2) ERROR: cannot ping ns1 from ns2 with ipv6 masquerade fully-random (attempt 2) ... becaus 2nd ping clashes with existing 'id 0' icmp conntrack and gets dropped. Fixes: 203f2e78200c27e ("netfilter: nat: remove l4proto->unique_tuple") Reported-by: Sven Auhagen <sven.auhagen(a)voleatech.de> Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- net/netfilter/nf_nat_core.c | 11 ++++-- tools/testing/selftests/netfilter/nft_nat.sh | 36 +++++++++++++++----- 2 files changed, 35 insertions(+), 12 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d159e9e7835b..ade527565127 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -358,9 +358,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple, case IPPROTO_ICMPV6: /* id is same for either direction... */ keyptr = &tuple->src.u.icmp.id; - min = range->min_proto.icmp.id; - range_size = ntohs(range->max_proto.icmp.id) - - ntohs(range->min_proto.icmp.id) + 1; + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + min = 0; + range_size = 65536; + } else { + min = ntohs(range->min_proto.icmp.id); + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; + } goto find_free_id; #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE) case IPPROTO_GRE: diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 8ec76681605c..3194007cf8d1 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -321,6 +321,7 @@ EOF test_masquerade6() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null @@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - <<EOF table ip6 nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags" lret=1 fi @@ -397,19 +398,26 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip6 nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2" return $lret } test_masquerade() { + local natflags=$1 local lret=0 ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null @@ -417,7 +425,7 @@ test_masquerade() ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: canot ping ns1 from ns2" + echo "ERROR: cannot ping ns1 from ns2 $natflags" lret=1 fi @@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - <<EOF table ip nat { chain postrouting { type nat hook postrouting priority 0; policy accept; - meta oif veth0 masquerade + meta oif veth0 masquerade $natflags } } EOF ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 if [ $? -ne 0 ] ; then - echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags" lret=1 fi @@ -485,13 +493,19 @@ EOF fi done + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)" + lret=1 + fi + ip netns exec ns0 nft flush chain ip nat postrouting if [ $? -ne 0 ]; then echo "ERROR: Could not flush nat postrouting" 1>&2 lret=1 fi - test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2" return $lret } @@ -750,8 +764,12 @@ test_local_dnat test_local_dnat6 reset_counters -test_masquerade -test_masquerade6 +test_masquerade "" +test_masquerade6 "" + +reset_counters +test_masquerade "fully-random" +test_masquerade6 "fully-random" reset_counters test_redirect -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 5.0 61/99] selftests: netfilter: check icmp pkttoobig errors are set as related

by Sasha Levin

From: Florian Westphal <fw(a)strlen.de> [ Upstream commit becf2319f320cae43e20cf179cc51a355a0deb5f ] When an icmp error such as pkttoobig is received, conntrack checks if the "inner" header (header of packet that did not fit link mtu) is matches an existing connection, and, if so, sets that packet as being related to the conntrack entry it found. It was recently reported that this "related" setting also works if the inner header is from another, different connection (i.e., artificial/forged icmp error). Add a test, followup patch will add additional "inner dst matches outer dst in reverse direction" check before setting related state. Link: https://www.synacktiv.com/posts/systems/icmp-reachable.html Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/netfilter/Makefile | 2 +- .../netfilter/conntrack_icmp_related.sh | 283 ++++++++++++++++++ 2 files changed, 284 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_icmp_related.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index c9ff2b47bd1c..a37cb1192c6a 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh nft_nat.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh new file mode 100755 index 000000000000..b48e1833bc89 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh @@ -0,0 +1,283 @@ +#!/bin/bash +# +# check that ICMP df-needed/pkttoobig icmp are set are set as related +# state +# +# Setup is: +# +# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2 +# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280). +# ping nsclient2 from nsclient1, checking that conntrack did set RELATED +# 'fragmentation needed' icmp packet. +# +# In addition, nsrouter1 will perform IP masquerading, i.e. also +# check the icmp errors are propagated to the correct host as per +# nat of "established" icmp-echo "connection". + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +cleanup() { + for i in 1 2;do ip netns del nsclient$i;done + for i in 1 2;do ip netns del nsrouter$i;done +} + +ipv4() { + echo -n 192.168.$1.2 +} + +ipv6 () { + echo -n dead:$1::2 +} + +check_counter() +{ + ns=$1 + name=$2 + expect=$3 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect") + if [ $? -ne 0 ]; then + echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter "$name" 1>&2 + lret=1 + fi + + return $lret +} + +check_unknown() +{ + expect="packets 0 bytes 0" + for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + check_counter $n "unknown" "$expect" + if [ $? -ne 0 ] ;then + return 1 + fi + done + + return 0 +} + +for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do + ip netns add $n + ip -net $n link set lo up +done + +DEV=veth0 +ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1 +DEV=veth0 +ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2 + +DEV=veth0 +ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2 + +DEV=veth0 +for i in 1 2; do + ip -net nsclient$i link set $DEV up + ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV + ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV +done + +ip -net nsrouter1 link set eth1 up +ip -net nsrouter1 link set veth0 up + +ip -net nsrouter2 link set eth1 up +ip -net nsrouter2 link set eth2 up + +ip -net nsclient1 route add default via 192.168.1.1 +ip -net nsclient1 -6 route add default via dead:1::1 + +ip -net nsclient2 route add default via 192.168.2.1 +ip -net nsclient2 route add default via dead:2::1 + +i=3 +ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1 +ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0 +ip -net nsrouter1 addr add dead:1::1/64 dev eth1 +ip -net nsrouter1 addr add dead:3::1/64 dev veth0 +ip -net nsrouter1 route add default via 192.168.3.10 +ip -net nsrouter1 -6 route add default via dead:3::10 + +ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1 +ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2 +ip -net nsrouter2 addr add dead:2::1/64 dev eth1 +ip -net nsrouter2 addr add dead:3::10/64 dev eth2 +ip -net nsrouter2 route add default via 192.168.3.1 +ip -net nsrouter2 route add default via dead:3::1 + +sleep 2 +for i in 4 6; do + ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1 + ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1 +done + +for netns in nsrouter1 nsrouter2; do +ip netns exec $netns nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain forward { + type filter hook forward priority 0; policy accept; + meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept + meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept + meta l4proto { icmp, icmpv6 } ct state new,established accept + counter name "unknown" drop + } +} +EOF +done + +ip netns exec nsclient1 nft -f - <<EOF +table inet filter { + counter unknown { } + counter related { } + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept + counter name "unknown" drop + } +} +EOF + +ip netns exec nsclient2 nft -f - <<EOF +table inet filter { + counter unknown { } + counter new { } + counter established { } + + chain input { + type filter hook input priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept + counter name "unknown" drop + } + chain output { + type filter hook output priority 0; policy accept; + meta l4proto { icmp, icmpv6 } ct state established,untracked accept + + meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" + meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" + counter name "unknown" drop + } +} +EOF + + +# make sure NAT core rewrites adress of icmp error if nat is used according to +# conntrack nat information (icmp error will be directed at nsrouter1 address, +# but it needs to be routed to nsclient1 address). +ip netns exec nsrouter1 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip protocol icmp oifname "veth0" counter masquerade + } +} +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + ip6 nexthdr icmpv6 oifname "veth0" counter masquerade + } +} +EOF + +ip netns exec nsrouter2 ip link set eth1 mtu 1280 +ip netns exec nsclient2 ip link set veth0 mtu 1280 +sleep 1 + +ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ip routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi +ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null +if [ $? -ne 0 ]; then + echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2 + cleanup + exit 1 +fi + +check_unknown +if [ $? -ne 0 ]; then + ret=1 +fi + +expect="packets 0 bytes 0" +for netns in nsrouter1 nsrouter2 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +expect="packets 2 bytes 2076" +check_counter nsclient2 "new" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +# nsrouter2 should have generated the icmp error, so +# related counter should be 0 (its in forward). +expect="packets 0 bytes 0" +check_counter "nsrouter2" "related" "$expect" +if [ $? -ne 0 ]; then + ret=1 +fi + +# but nsrouter1 should have seen it, same for nsclient1. +expect="packets 1 bytes 576" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null +if [ $? -eq 0 ]; then + echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2 + ret=1 +fi + +expect="packets 2 bytes 1856" +for netns in nsrouter1 nsclient1;do + check_counter "$netns" "related" "$expect" + if [ $? -ne 0 ]; then + ret=1 + fi +done + +if [ $ret -eq 0 ];then + echo "PASS: icmp mtu error had RELATED state" +else + echo "ERROR: icmp error RELATED state test has failed" +fi + +cleanup +exit $ret -- 2.20.1

6 years, 6 months

1
0
0 0

[PATCH AUTOSEL 5.0 26/99] selftests: fib_tests: Fix 'Command line is not complete' errors

by Sasha Levin

From: David Ahern <dsahern(a)gmail.com> [ Upstream commit a5f622984a623df9a84cf43f6b098d8dd76fbe05 ] A couple of tests are verifying a route has been removed. The helper expects the prefix as the first part of the expected output. When checking that a route has been deleted the prefix is empty leading to an invalid ip command: $ ip ro ls match Command line is not complete. Try option "help" Fix by moving the comparison of expected output and output to a new function that is used by both check_route and check_route6. Use the new helper for the 2 checks on route removal. Also, remove the reset of 'set -x' in route_setup which overrides the user managed setting. Fixes: d69faad76584c ("selftests: fib_tests: Add prefix route tests with metric") Signed-off-by: David Ahern <dsahern(a)gmail.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/testing/selftests/net/fib_tests.sh | 94 ++++++++++-------------- 1 file changed, 40 insertions(+), 54 deletions(-) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 1080ff55a788..0d2a5f4f1e63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -605,6 +605,39 @@ run_cmd() return $rc } +check_expected() +{ + local out="$1" + local expected="$2" + local rc=0 + + [ "${out}" = "${expected}" ] && return 0 + + if [ -z "${out}" ]; then + if [ "$VERBOSE" = "1" ]; then + printf "\nNo route entry found\n" + printf "Expected:\n" + printf " ${expected}\n" + fi + return 1 + fi + + # tricky way to convert output to 1-line without ip's + # messy '\'; this drops all extra white space + out=$(echo ${out}) + if [ "${out}" != "${expected}" ]; then + rc=1 + if [ "${VERBOSE}" = "1" ]; then + printf " Unexpected route entry. Have:\n" + printf " ${out}\n" + printf " Expected:\n" + printf " ${expected}\n\n" + fi + fi + + return $rc +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route6() @@ -652,31 +685,7 @@ check_route6() pfx=$1 out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//') - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } route_cleanup() @@ -725,7 +734,7 @@ route_setup() ip -netns ns2 addr add 172.16.103.2/24 dev veth4 ip -netns ns2 addr add 172.16.104.1/24 dev dummy1 - set +ex + set +e } # assumption is that basic add of a single path route works @@ -960,7 +969,8 @@ ipv6_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route6 "" + out=$($IP -6 ro ls match 2001:db8:104::/64) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" @@ -1091,38 +1101,13 @@ check_route() local pfx local expected="$1" local out - local rc=0 set -- $expected pfx=$1 [ "${pfx}" = "unreachable" ] && pfx=$2 out=$($IP ro ls match ${pfx}) - [ "${out}" = "${expected}" ] && return 0 - - if [ -z "${out}" ]; then - if [ "$VERBOSE" = "1" ]; then - printf "\nNo route entry found\n" - printf "Expected:\n" - printf " ${expected}\n" - fi - return 1 - fi - - # tricky way to convert output to 1-line without ip's - # messy '\'; this drops all extra white space - out=$(echo ${out}) - if [ "${out}" != "${expected}" ]; then - rc=1 - if [ "${VERBOSE}" = "1" ]; then - printf " Unexpected route entry. Have:\n" - printf " ${out}\n" - printf " Expected:\n" - printf " ${expected}\n\n" - fi - fi - - return $rc + check_expected "${out}" "${expected}" } # assumption is that basic add of a single path route works @@ -1387,7 +1372,8 @@ ipv4_addr_metric_test() run_cmd "$IP li set dev dummy2 down" rc=$? if [ $rc -eq 0 ]; then - check_route "" + out=$($IP ro ls match 172.16.104.0/24) + check_expected "${out}" "" rc=$? fi log_test $rc 0 "Prefix route removed on link down" -- 2.20.1

6 years, 6 months

1
0
0 0

[GIT PULL] Kselftest update for Linux 5.2-rc1

by Shuah Khan

Hi Linus, Please pull the following Kselftest update for Linux 5.2-rc1 This Kselftest update for Linux 5.2-rc1 consists of - fixes to seccomp test, and kselftest framework - cleanups to remove duplicate header defines - fixes to efivarfs "make clean" target - cgroup cleanup path - Moving the IMA kexec_load selftest to selftests/kexec work from Mimi Johar and Petr Vorel - A framework to kselftest for writing kernel test modules addition from Tobin C. Harding diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 15ade5d2e7775667cf191cf2f94327a4889f8b9d: Linux 5.1-rc4 (2019-04-07 14:09:59 -1000) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-5.2-rc1 for you to fetch changes up to d917fb876f6eaeeea8a2b620d2a266ce26372f4d: selftests: build and run gpio when output directory is the src dir (2019-04-22 17:02:26 -0600) ---------------------------------------------------------------- linux-kselftest-5.2-rc1 This Kselftest update for Linux 5.2-rc1 consists of - fixes to seccomp test, and kselftest framework - cleanups to remove duplicate header defines - fixes to efivarfs "make clean" target - cgroup cleanup path - Moving the IMA kexec_load selftest to selftests/kexec work from Mimi Johar and Petr Vorel - A framework to kselftest for writing kernel test modules addition from Tobin C. Harding ---------------------------------------------------------------- Kees Cook (3): selftests/seccomp: Handle namespace failures gracefully selftests/harness: Add 30 second timeout per test selftests/ipc: Fix msgque compiler warnings Mathieu Desnoyers (1): rseq/selftests: Adapt number of threads to the number of detected cpus Mimi Zohar (9): selftests/kexec: move the IMA kexec_load selftest to selftests/kexec selftests/kexec: cleanup the kexec selftest selftests/kexec: define a set of common functions selftests/kexec: define common logging functions selftests/kexec: define "require_root_privileges" selftests/kexec: kexec_file_load syscall test selftests/kexec: check kexec_load and kexec_file_load are enabled selftests/kexec: make kexec_load test independent of IMA being enabled selftests/kexec: update get_secureboot_mode Petr Vorel (1): selftests/kexec: Add missing '=y' to config options Po-Hsu Lin (1): selftests/efivarfs: clean up test files from test_create*() Roman Gushchin (1): selftests: cgroup: fix cleanup path in test_memcg_subtree_control() Sabyasachi Gupta (4): selftest/x86/mpx-dig.c: Remove duplicate header selftest/timers: Remove duplicate header selftest/rseq: Remove duplicate header selftest/gpio: Remove duplicate header Shuah Khan (2): selftests: fix headers_install circular dependency selftests: build and run gpio when output directory is the src dir Tobin C. Harding (6): lib/test_printf: Add empty module_exit function kselftest: Add test runner creation script kselftest: Add test module framework header lib: Use new kselftest header lib/string: Add strscpy_pad() function lib: Add test module for strscpy_pad ZhangXiaoxu (1): selftests: efivarfs: remove the test_create_read file if it was exist Documentation/dev-tools/kselftest.rst | 94 ++++++++- include/linux/string.h | 4 + lib/Kconfig.debug | 3 + lib/Makefile | 1 + lib/string.c | 47 ++++- lib/test_bitmap.c | 20 +- lib/test_printf.c | 17 +- lib/test_strscpy.c | 150 ++++++++++++++ tools/testing/selftests/Makefile | 63 +++++- tools/testing/selftests/cgroup/test_memcontrol.c | 38 ++-- tools/testing/selftests/efivarfs/efivarfs.sh | 28 ++- tools/testing/selftests/gpio/gpio-mockup-chardev.c | 1 - tools/testing/selftests/ima/config | 4 - tools/testing/selftests/ima/test_kexec_load.sh | 54 ----- tools/testing/selftests/ipc/msgque.c | 11 +- tools/testing/selftests/{ima => kexec}/Makefile | 5 +- tools/testing/selftests/kexec/config | 3 + tools/testing/selftests/kexec/kexec_common_lib.sh | 220 +++++++++++++++++++++ .../selftests/kexec/test_kexec_file_load.sh | 208 +++++++++++++++++++ tools/testing/selftests/kexec/test_kexec_load.sh | 47 +++++ tools/testing/selftests/kselftest_harness.h | 2 + tools/testing/selftests/kselftest_module.h | 48 +++++ tools/testing/selftests/kselftest_module.sh | 84 ++++++++ tools/testing/selftests/lib.mk | 38 +++- tools/testing/selftests/lib/Makefile | 2 +- tools/testing/selftests/lib/bitmap.sh | 18 +- tools/testing/selftests/lib/config | 1 + tools/testing/selftests/lib/prime_numbers.sh | 17 +- tools/testing/selftests/lib/printf.sh | 19 +- tools/testing/selftests/lib/strscpy.sh | 3 + tools/testing/selftests/rseq/rseq.h | 1 - tools/testing/selftests/rseq/run_param_test.sh | 7 +- tools/testing/selftests/seccomp/seccomp_bpf.c | 43 ++-- tools/testing/selftests/timers/skew_consistency.c | 1 - tools/testing/selftests/x86/mpx-dig.c | 2 - 35 files changed, 1081 insertions(+), 223 deletions(-) create mode 100644 lib/test_strscpy.c delete mode 100644 tools/testing/selftests/ima/config delete mode 100755 tools/testing/selftests/ima/test_kexec_load.sh rename tools/testing/selftests/{ima => kexec}/Makefile (59%) create mode 100644 tools/testing/selftests/kexec/config create mode 100755 tools/testing/selftests/kexec/kexec_common_lib.sh create mode 100755 tools/testing/selftests/kexec/test_kexec_file_load.sh create mode 100755 tools/testing/selftests/kexec/test_kexec_load.sh create mode 100644 tools/testing/selftests/kselftest_module.h create mode 100755 tools/testing/selftests/kselftest_module.sh create mode 100755 tools/testing/selftests/lib/strscpy.sh ----------------------------------------------------------------

6 years, 6 months

2
1
0 0

[PATCH v14 00/17] arm64: untag user pointers passed to the kernel

by Andrey Konovalov

=== Overview arm64 has a feature called Top Byte Ignore, which allows to embed pointer tags into the top byte of each pointer. Userspace programs (such as HWASan, a memory debugging tool [1]) might use this feature and pass tagged user pointers to the kernel through syscalls or other interfaces. Right now the kernel is already able to handle user faults with tagged pointers, due to these patches: 1. 81cddd65 ("arm64: traps: fix userspace cache maintenance emulation on a tagged pointer") 2. 7dcd9dd8 ("arm64: hw_breakpoint: fix watchpoint matching for tagged pointers") 3. 276e9327 ("arm64: entry: improve data abort handling of tagged pointers") This patchset extends tagged pointer support to syscall arguments. As per the proposed ABI change [3], tagged pointers are only allowed to be passed to syscalls when they point to memory ranges obtained by anonymous mmap() or sbrk() (see the patchset [3] for more details). For non-memory syscalls this is done by untaging user pointers when the kernel performs pointer checking to find out whether the pointer comes from userspace (most notably in access_ok). The untagging is done only when the pointer is being checked, the tag is preserved as the pointer makes its way through the kernel and stays tagged when the kernel dereferences the pointer when perfoming user memory accesses. Memory syscalls (mmap, mprotect, etc.) don't do user memory accesses but rather deal with memory ranges, and untagged pointers are better suited to describe memory ranges internally. Thus for memory syscalls we untag pointers completely when they enter the kernel. === Other approaches One of the alternative approaches to untagging that was considered is to completely strip the pointer tag as the pointer enters the kernel with some kind of a syscall wrapper, but that won't work with the countless number of different ioctl calls. With this approach we would need a custom wrapper for each ioctl variation, which doesn't seem practical. An alternative approach to untagging pointers in memory syscalls prologues is to inspead allow tagged pointers to be passed to find_vma() (and other vma related functions) and untag them there. Unfortunately, a lot of find_vma() callers then compare or subtract the returned vma start and end fields against the pointer that was being searched. Thus this approach would still require changing all find_vma() callers. === Testing The following testing approaches has been taken to find potential issues with user pointer untagging: 1. Static testing (with sparse [2] and separately with a custom static analyzer based on Clang) to track casts of __user pointers to integer types to find places where untagging needs to be done. 2. Static testing with grep to find parts of the kernel that call find_vma() (and other similar functions) or directly compare against vm_start/vm_end fields of vma. 3. Static testing with grep to find parts of the kernel that compare user pointers with TASK_SIZE or other similar consts and macros. 4. Dynamic testing: adding BUG_ON(has_tag(addr)) to find_vma() and running a modified syzkaller version that passes tagged pointers to the kernel. Based on the results of the testing the requried patches have been added to the patchset. === Notes This patchset is meant to be merged together with "arm64 relaxed ABI" [3]. This patchset is a prerequisite for ARM's memory tagging hardware feature support [4]. This patchset has been merged into the Pixel 2 & 3 kernel trees and is now being used to enable testing of Pixel phones with HWASan. Thanks! [1] http://clang.llvm.org/docs/HardwareAssistedAddressSanitizerDesign.html [2] https://github.com/lucvoo/sparse-dev/commit/5f960cb10f56ec2017c128ef9d16060… [3] https://lkml.org/lkml/2019/3/18/819 [4] https://community.arm.com/processors/b/blog/posts/arm-a-profile-architectur… Changes in v14: - Moved untagging for most memory syscalls to an arm64 specific implementation, instead of doing that in the common code. - Dropped "net, arm64: untag user pointers in tcp_zerocopy_receive", since the provided user pointers don't come from an anonymous map and thus are not covered by this ABI relaxation. - Dropped "kernel, arm64: untag user pointers in prctl_set_mm*". - Moved untagging from __check_mem_type() to tee_shm_register(). - Updated untagging for the amdgpu and radeon drivers to cover the MMU notifier, as suggested by Felix. - Since this ABI relaxation doesn't actually allow tagged instruction pointers, dropped the following patches: - Dropped "tracing, arm64: untag user pointers in seq_print_user_ip". - Dropped "uprobes, arm64: untag user pointers in find_active_uprobe". - Dropped "bpf, arm64: untag user pointers in stack_map_get_build_id_offset". - Rebased onto 5.1-rc7 (37624b58). Changes in v13: - Simplified untagging in tcp_zerocopy_receive(). - Looked at find_vma() callers in drivers/, which allowed to identify a few other places where untagging is needed. - Added patch "mm, arm64: untag user pointers in get_vaddr_frames". - Added patch "drm/amdgpu, arm64: untag user pointers in amdgpu_ttm_tt_get_user_pages". - Added patch "drm/radeon, arm64: untag user pointers in radeon_ttm_tt_pin_userptr". - Added patch "IB/mlx4, arm64: untag user pointers in mlx4_get_umem_mr". - Added patch "media/v4l2-core, arm64: untag user pointers in videobuf_dma_contig_user_get". - Added patch "tee/optee, arm64: untag user pointers in check_mem_type". - Added patch "vfio/type1, arm64: untag user pointers". Changes in v12: - Changed untagging in tcp_zerocopy_receive() to also untag zc->address. - Fixed untagging in prctl_set_mm* to only untag pointers for vma lookups and validity checks, but leave them as is for actual user space accesses. - Updated the link to the v2 of the "arm64 relaxed ABI" patchset [3]. - Dropped the documentation patch, as the "arm64 relaxed ABI" patchset [3] handles that. Changes in v11: - Added "uprobes, arm64: untag user pointers in find_active_uprobe" patch. - Added "bpf, arm64: untag user pointers in stack_map_get_build_id_offset" patch. - Fixed "tracing, arm64: untag user pointers in seq_print_user_ip" to correctly perform subtration with a tagged addr. - Moved untagged_addr() from SYSCALL_DEFINE3(mprotect) and SYSCALL_DEFINE4(pkey_mprotect) to do_mprotect_pkey(). - Moved untagged_addr() definition for other arches from include/linux/memory.h to include/linux/mm.h. - Changed untagging in strn*_user() to perform userspace accesses through tagged pointers. - Updated the documentation to mention that passing tagged pointers to memory syscalls is allowed. - Updated the test to use malloc'ed memory instead of stack memory. Changes in v10: - Added "mm, arm64: untag user pointers passed to memory syscalls" back. - New patch "fs, arm64: untag user pointers in fs/userfaultfd.c". - New patch "net, arm64: untag user pointers in tcp_zerocopy_receive". - New patch "kernel, arm64: untag user pointers in prctl_set_mm*". - New patch "tracing, arm64: untag user pointers in seq_print_user_ip". Changes in v9: - Rebased onto 4.20-rc6. - Used u64 instead of __u64 in type casts in the untagged_addr macro for arm64. - Added braces around (addr) in the untagged_addr macro for other arches. Changes in v8: - Rebased onto 65102238 (4.20-rc1). - Added a note to the cover letter on why syscall wrappers/shims that untag user pointers won't work. - Added a note to the cover letter that this patchset has been merged into the Pixel 2 kernel tree. - Documentation fixes, in particular added a list of syscalls that don't support tagged user pointers. Changes in v7: - Rebased onto 17b57b18 (4.19-rc6). - Dropped the "arm64: untag user address in __do_user_fault" patch, since the existing patches already handle user faults properly. - Dropped the "usb, arm64: untag user addresses in devio" patch, since the passed pointer must come from a vma and therefore be untagged. - Dropped the "arm64: annotate user pointers casts detected by sparse" patch (see the discussion to the replies of the v6 of this patchset). - Added more context to the cover letter. - Updated Documentation/arm64/tagged-pointers.txt. Changes in v6: - Added annotations for user pointer casts found by sparse. - Rebased onto 050cdc6c (4.19-rc1+). Changes in v5: - Added 3 new patches that add untagging to places found with static analysis. - Rebased onto 44c929e1 (4.18-rc8). Changes in v4: - Added a selftest for checking that passing tagged pointers to the kernel succeeds. - Rebased onto 81e97f013 (4.18-rc1+). Changes in v3: - Rebased onto e5c51f30 (4.17-rc6+). - Added linux-arch@ to the list of recipients. Changes in v2: - Rebased onto 2d618bdf (4.17-rc3+). - Removed excessive untagging in gup.c. - Removed untagging pointers returned from __uaccess_mask_ptr. Changes in v1: - Rebased onto 4.17-rc1. Changes in RFC v2: - Added "#ifndef untagged_addr..." fallback in linux/uaccess.h instead of defining it for each arch individually. - Updated Documentation/arm64/tagged-pointers.txt. - Dropped "mm, arm64: untag user addresses in memory syscalls". - Rebased onto 3eb2ce82 (4.16-rc7). Signed-off-by: Andrey Konovalov <andreyknvl(a)google.com> Andrey Konovalov (17): uaccess: add untagged_addr definition for other arches arm64: untag user pointers in access_ok and __uaccess_mask_ptr lib, arm64: untag user pointers in strn*_user mm: add ksys_ wrappers to memory syscalls arms64: untag user pointers passed to memory syscalls mm: untag user pointers in do_pages_move mm, arm64: untag user pointers in mm/gup.c mm, arm64: untag user pointers in get_vaddr_frames fs, arm64: untag user pointers in copy_mount_options fs, arm64: untag user pointers in fs/userfaultfd.c drm/amdgpu, arm64: untag user pointers drm/radeon, arm64: untag user pointers IB/mlx4, arm64: untag user pointers in mlx4_get_umem_mr media/v4l2-core, arm64: untag user pointers in videobuf_dma_contig_user_get tee, arm64: untag user pointers in tee_shm_register vfio/type1, arm64: untag user pointers in vaddr_get_pfn selftests, arm64: add a selftest for passing tagged pointers to kernel arch/arm64/include/asm/uaccess.h | 10 +- arch/arm64/kernel/sys.c | 128 ++++++++++++++++- .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 + drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- drivers/gpu/drm/radeon/radeon_gem.c | 2 + drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- drivers/infiniband/hw/mlx4/mr.c | 7 +- drivers/media/v4l2-core/videobuf-dma-contig.c | 9 +- drivers/tee/tee_shm.c | 1 + drivers/vfio/vfio_iommu_type1.c | 2 + fs/namespace.c | 2 +- fs/userfaultfd.c | 5 + include/linux/mm.h | 4 + include/linux/syscalls.h | 22 +++ ipc/shm.c | 7 +- lib/strncpy_from_user.c | 3 +- lib/strnlen_user.c | 3 +- mm/frame_vector.c | 2 + mm/gup.c | 4 + mm/madvise.c | 129 +++++++++--------- mm/mempolicy.c | 21 ++- mm/migrate.c | 1 + mm/mincore.c | 57 ++++---- mm/mlock.c | 20 ++- mm/mmap.c | 30 +++- mm/mprotect.c | 6 +- mm/mremap.c | 27 ++-- mm/msync.c | 35 +++-- tools/testing/selftests/arm64/.gitignore | 1 + tools/testing/selftests/arm64/Makefile | 11 ++ .../testing/selftests/arm64/run_tags_test.sh | 12 ++ tools/testing/selftests/arm64/tags_test.c | 21 +++ 33 files changed, 431 insertions(+), 159 deletions(-) create mode 100644 tools/testing/selftests/arm64/.gitignore create mode 100644 tools/testing/selftests/arm64/Makefile create mode 100755 tools/testing/selftests/arm64/run_tags_test.sh create mode 100644 tools/testing/selftests/arm64/tags_test.c -- 2.21.0.593.g511ec345e18-goog

6 years, 6 months

3
26
0 0

[PATCH] selftests: add sleep between detach and usbip list -l

by Shuah Khan

Add a sleep between detach and check for exportable devices to avoid the following segfault from libc-2.27.so [ 6268.136108] usbip[5565]: segfault at 0 ip 00007f2a947bddfd sp 00007ffd1a8705e8 error 4 in libc-2.27.so[7f2a94703000+1e7000] Signed-off-by: Shuah Khan <skhan(a)linuxfoundation.org> --- tools/testing/selftests/drivers/usb/usbip/usbip_test.sh | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh index 128f0ab24307..beacf24a8df7 100755 --- a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh +++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh @@ -171,10 +171,14 @@ echo "Detach invalid port tests - expect invalid port error message"; src/usbip detach -p 100; echo "==============================================================" +# let detach complete. Avoid segfaults from libc-2.27.so +sleep 3; + echo "Expect to see export-able devices"; src/usbip list -l; echo "==============================================================" + echo "Remove usbip_host module"; rmmod usbip_host; -- 2.17.1

6 years, 6 months

2
4
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror