From 33b8aad21ac175eba9577a73eb62b0aa141c241c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 18 Oct 2021 14:38:13 +0200 Subject: [PATCH 01/94] selftests: netfilter: add a vrf+conntrack testcase Rework the reproducer for the vrf+conntrack regression reported by Eugene into a selftest and also add a test for ip masquerading that Lahav fixed recently. With net or net-next tree, the first test fails and the latter two pass. With 09e856d54bda5f28 ("vrf: Reset skb conntrack connection on VRF rcv") reverted first test passes but the last two fail. A proper fix needs more work, for time being a revert seems to be the best choice, snat/masquerade did not work before the fix. Link: https://lore.kernel.org/netdev/378ca299-4474-7e9a-3d36-2350c8c98995@gmail.com/T/#m95358a31810df7392f541f99d187227bc75c9963 Reported-by: Eugene Crosser Cc: Lahav Schlesinger Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/Makefile | 3 +- .../selftests/netfilter/conntrack_vrf.sh | 219 ++++++++++++++++++ 2 files changed, 221 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/netfilter/conntrack_vrf.sh diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 8748199ac109..ffca314897c4 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -5,7 +5,8 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \ nft_concat_range.sh nft_conntrack_helper.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ - ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh + ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ + conntrack_vrf.sh LDLIBS = -lmnl TEST_GEN_FILES = nf-queue diff --git a/tools/testing/selftests/netfilter/conntrack_vrf.sh b/tools/testing/selftests/netfilter/conntrack_vrf.sh new file mode 100755 index 000000000000..91f3ef0f1192 --- /dev/null +++ b/tools/testing/selftests/netfilter/conntrack_vrf.sh @@ -0,0 +1,219 @@ +#!/bin/sh + +# This script demonstrates interaction of conntrack and vrf. +# The vrf driver calls the netfilter hooks again, with oif/iif +# pointing at the VRF device. +# +# For ingress, this means first iteration has iifname of lower/real +# device. In this script, thats veth0. +# Second iteration is iifname set to vrf device, tvrf in this script. +# +# For egress, this is reversed: first iteration has the vrf device, +# second iteration is done with the lower/real/veth0 device. +# +# test_ct_zone_in demonstrates unexpected change of nftables +# behavior # caused by commit 09e856d54bda5f28 "vrf: Reset skb conntrack +# connection on VRF rcv" +# +# It was possible to assign conntrack zone to a packet (or mark it for +# `notracking`) in the prerouting chain before conntrack, based on real iif. +# +# After the change, the zone assignment is lost and the zone is assigned based +# on the VRF master interface (in case such a rule exists). +# assignment is lost. Instead, assignment based on the `iif` matching +# Thus it is impossible to distinguish packets based on the original +# interface. +# +# test_masquerade_vrf and test_masquerade_veth0 demonstrate the problem +# that was supposed to be fixed by the commit mentioned above to make sure +# that any fix to test case 1 won't break masquerade again. + +ksft_skip=4 + +IP0=172.30.30.1 +IP1=172.30.30.2 +PFXL=30 +ret=0 + +sfx=$(mktemp -u "XXXXXXXX") +ns0="ns0-$sfx" +ns1="ns1-$sfx" + +cleanup() +{ + ip netns pids $ns0 | xargs kill 2>/dev/null + ip netns pids $ns1 | xargs kill 2>/dev/null + + ip netns del $ns0 $ns1 +} + +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 $ksft_skip +fi + +ip netns add "$ns0" +if [ $? -ne 0 ];then + echo "SKIP: Could not create net namespace $ns0" + exit $ksft_skip +fi +ip netns add "$ns1" + +trap cleanup EXIT + +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.default.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 +ip netns exec $ns0 sysctl -q -w net.ipv4.conf.all.rp_filter=0 + +ip link add veth0 netns "$ns0" type veth peer name veth0 netns "$ns1" > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not add veth device" + exit $ksft_skip +fi + +ip -net $ns0 li add tvrf type vrf table 9876 +if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + exit $ksft_skip +fi + +ip -net $ns0 li set lo up + +ip -net $ns0 li set veth0 master tvrf +ip -net $ns0 li set tvrf up +ip -net $ns0 li set veth0 up +ip -net $ns1 li set veth0 up + +ip -net $ns0 addr add $IP0/$PFXL dev veth0 +ip -net $ns1 addr add $IP1/$PFXL dev veth0 + +ip netns exec $ns1 iperf3 -s > /dev/null 2>&1& +if [ $? -ne 0 ];then + echo "SKIP: Could not start iperf3" + exit $ksft_skip +fi + +# test vrf ingress handling. +# The incoming connection should be placed in conntrack zone 1, +# as decided by the first iteration of the ruleset. +test_ct_zone_in() +{ +ip netns exec $ns0 nft -f - < /dev/null + + # should be in zone 1, not zone 2 + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 1 2>/dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "PASS: entry found in conntrack zone 1" + else + echo "FAIL: entry not found in conntrack zone 1" + count=$(ip netns exec $ns0 conntrack -L -s $IP1 -d $IP0 -p icmp --zone 2 2> /dev/null | wc -l) + if [ $count -eq 1 ]; then + echo "FAIL: entry found in zone 2 instead" + else + echo "FAIL: entry not in zone 1 or 2, dumping table" + ip netns exec $ns0 conntrack -L + ip netns exec $ns0 nft list ruleset + fi + fi +} + +# add masq rule that gets evaluated w. outif set to vrf device. +# This tests the first iteration of the packet through conntrack, +# oifname is the vrf device. +test_masquerade_vrf() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null + +ip netns exec $ns0 nft -f - </dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on vrf device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +# add masq rule that gets evaluated w. outif set to veth device. +# This tests the 2nd iteration of the packet through conntrack, +# oifname is the lower device (veth0 in this case). +test_masquerade_veth() +{ + ip netns exec $ns0 conntrack -F 2>/dev/null +ip netns exec $ns0 nft -f - < /dev/null + if [ $? -ne 0 ]; then + echo "FAIL: iperf3 connect failure with masquerade + sport rewrite on veth device" + ret=1 + return + fi + + # must also check that nat table was evaluated on second (lower device) iteration. + ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' + if [ $? -eq 0 ]; then + echo "PASS: iperf3 connect with masquerade + sport rewrite on veth device" + else + echo "FAIL: vrf masq rule has unexpected counter value" + ret=1 + fi +} + +test_ct_zone_in +test_masquerade_vrf +test_masquerade_veth + +exit $ret From 228c3fa054ad118f78fc60f1a3f05ba29b043608 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Oct 2021 18:25:37 +0200 Subject: [PATCH 02/94] selftests: netfilter: extend nfqueue tests to cover vrf device VRF device calls the output/postrouting hooks so packet should be seeon with oifname tvrf and once with eth0. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- .../testing/selftests/netfilter/nft_queue.sh | 54 +++++++++++++++++++ 1 file changed, 54 insertions(+) diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 3d202b90b33d..7d27f1f3bc01 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -16,6 +16,10 @@ timeout=4 cleanup() { + ip netns pids ${ns1} | xargs kill 2>/dev/null + ip netns pids ${ns2} | xargs kill 2>/dev/null + ip netns pids ${nsrouter} | xargs kill 2>/dev/null + ip netns del ${ns1} ip netns del ${ns2} ip netns del ${nsrouter} @@ -332,6 +336,55 @@ EOF echo "PASS: tcp via loopback and re-queueing" } +test_icmp_vrf() { + ip -net $ns1 link add tvrf type vrf table 9876 + if [ $? -ne 0 ];then + echo "SKIP: Could not add vrf device" + return + fi + + ip -net $ns1 li set eth0 master tvrf + ip -net $ns1 li set tvrf up + + ip -net $ns1 route add 10.0.2.0/24 via 10.0.1.1 dev eth0 table 9876 +ip netns exec ${ns1} nft -f /dev/stdin < /dev/null + + for n in output post; do + for d in tvrf eth0; do + ip netns exec ${ns1} nft list chain inet filter $n | grep -q "oifname \"$d\" icmp type echo-request counter packets 1" + if [ $? -ne 0 ] ; then + echo "FAIL: chain $n: icmp packet counter mismatch for device $d" 1>&2 + ip netns exec ${ns1} nft list ruleset + ret=1 + return + fi + done + done + + wait $nfqpid + [ $? -eq 0 ] && echo "PASS: icmp+nfqueue via vrf" + wait 2>/dev/null +} + ip netns exec ${nsrouter} sysctl net.ipv6.conf.all.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec ${nsrouter} sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null @@ -372,5 +425,6 @@ test_queue 20 test_tcp_forward test_tcp_localhost test_tcp_localhost_requeue +test_icmp_vrf exit $ret From 00d8b83725e9b9bf5eac1f23712aa94ce30dad46 Mon Sep 17 00:00:00 2001 From: Wan Jiabing Date: Tue, 2 Nov 2021 05:13:55 -0400 Subject: [PATCH 03/94] netfilter: nft_payload: Remove duplicated include in nft_payload.c Fix following checkincludes.pl warning: ./net/netfilter/nft_payload.c: linux/ip.h is included more than once. Signed-off-by: Wan Jiabing Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_payload.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index cbfe4e4a4ad7..bd689938a2e0 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,7 +22,6 @@ #include #include #include -#include #include static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, From e1f8bc06e49794ebecc0f276429a7ab9f105ac06 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 3 Nov 2021 19:53:42 +0100 Subject: [PATCH 04/94] selftests: nft_nat: Improve port shadow test stability Setup phase in test_port_shadow() relied upon a race-condition: Listening nc on port 1405 was started in background before attempting to create the fake conntrack entry using the same source port. If listening nc won, fake conntrack entry could not be created causing wrong behaviour. Reorder nc calls to fix this and introduce a short delay before testing the setup to wait for listening nc process startup. Fixes: 465f15a6d1a8f ("selftests: nft_nat: add udp hole punch test case") Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index da1c1e4b6c86..905c033db74d 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -759,14 +759,16 @@ test_port_shadow() local result="" local logmsg="" + # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. + echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & nc_r=$! echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & nc_c=$! - # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. From 85c0c8b342e89761554eed3f572ee55c0e5c6536 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 3 Nov 2021 19:53:43 +0100 Subject: [PATCH 05/94] selftests: nft_nat: Simplify port shadow notrack test The second rule in prerouting chain was probably a leftover: The router listens on veth0, so not tracking connections via that interface is sufficient. Likewise, the rule in output chain can be limited to that interface as well. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index 905c033db74d..c62e4e26252c 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -818,11 +818,10 @@ table $family raw { chain prerouting { type filter hook prerouting priority -300; policy accept; meta iif veth0 udp dport 1405 notrack - udp dport 1405 notrack } chain output { type filter hook output priority -300; policy accept; - udp sport 1405 notrack + meta oif veth0 udp sport 1405 notrack } } EOF From ad81d4daf6a3f4769a346e635d5e1e967ca455d9 Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Wed, 3 Nov 2021 23:21:54 +0100 Subject: [PATCH 06/94] netfilter: ctnetlink: fix filtering with CTA_TUPLE_REPLY filter->orig_flags was used for a reply context. Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Signed-off-by: Florent Fourcot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f1e5443fe7c7..2663764d0b6e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1011,7 +1011,7 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) CTA_TUPLE_REPLY, filter->family, &filter->zone, - filter->orig_flags); + filter->reply_flags); if (err < 0) { err = -EINVAL; goto err_filter; From 77522ff02f333434612bd72df9b376f8d3836e4d Mon Sep 17 00:00:00 2001 From: Florent Fourcot Date: Wed, 3 Nov 2021 23:21:55 +0100 Subject: [PATCH 07/94] netfilter: ctnetlink: do not erase error code with EINVAL And be consistent in error management for both orig/reply filtering Fixes: cb8aa9a3affb ("netfilter: ctnetlink: add kernel side filtering for dump") Signed-off-by: Florent Fourcot Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_netlink.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 2663764d0b6e..c7708bde057c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1012,10 +1012,8 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) filter->family, &filter->zone, filter->reply_flags); - if (err < 0) { - err = -EINVAL; + if (err < 0) goto err_filter; - } } return filter; From c95c07836fa4c1767ed11d8eca0769c652760e32 Mon Sep 17 00:00:00 2001 From: yangxingwu Date: Thu, 4 Nov 2021 03:10:29 +0100 Subject: [PATCH 08/94] netfilter: ipvs: Fix reuse connection if RS weight is 0 We are changing expire_nodest_conn to work even for reused connections when conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead"). For controlled and persistent connections, the new connection will get the needed real server depending on the rules in ip_vs_check_template(). Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected") Co-developed-by: Chuanqi Liu Signed-off-by: Chuanqi Liu Signed-off-by: yangxingwu Acked-by: Simon Horman Acked-by: Julian Anastasov Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/ipvs-sysctl.rst | 3 +-- net/netfilter/ipvs/ip_vs_core.c | 8 ++++---- 2 files changed, 5 insertions(+), 6 deletions(-) diff --git a/Documentation/networking/ipvs-sysctl.rst b/Documentation/networking/ipvs-sysctl.rst index 95ef56d62077..387fda80f05f 100644 --- a/Documentation/networking/ipvs-sysctl.rst +++ b/Documentation/networking/ipvs-sysctl.rst @@ -37,8 +37,7 @@ conn_reuse_mode - INTEGER 0: disable any special handling on port reuse. The new connection will be delivered to the same real server that was - servicing the previous connection. This will effectively - disable expire_nodest_conn. + servicing the previous connection. bit 1: enable rescheduling of new connections when it is safe. That is, whenever expire_nodest_conn and for TCP sockets, when diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e93c937a8bf0..51ad557a525b 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1919,7 +1919,6 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - int conn_reuse_mode; struct sock *sk; int af = state->pf; @@ -1997,15 +1996,16 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, ipvs, af, skb, &iph); - conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); - if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { + if (!iph.fragoffs && is_new_conn(skb, &iph) && cp) { + int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); - } else if (is_new_conn_expected(cp, conn_reuse_mode)) { + } else if (conn_reuse_mode && + is_new_conn_expected(cp, conn_reuse_mode)) { old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; From c08d3286caf1ec774b80ebb26e3ec31a0b434973 Mon Sep 17 00:00:00 2001 From: Jing Yao Date: Thu, 4 Nov 2021 11:49:11 +0000 Subject: [PATCH 09/94] netfilter: xt_IDLETIMER: replace snprintf in show functions with sysfs_emit coccicheck complains about the use of snprintf() in sysfs show functions: WARNING use scnprintf or sprintf Use sysfs_emit instead of scnprintf, snprintf or sprintf makes more sense. Reported-by: Zeal Robot Signed-off-by: Jing Yao Signed-off-by: Pablo Neira Ayuso --- net/netfilter/xt_IDLETIMER.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index 2f7cf5ecebf4..0f8bb0bf558f 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -85,9 +85,9 @@ static ssize_t idletimer_tg_show(struct device *dev, mutex_unlock(&list_mutex); if (time_after(expires, jiffies) || ktimespec.tv_sec > 0) - return snprintf(buf, PAGE_SIZE, "%ld\n", time_diff); + return sysfs_emit(buf, "%ld\n", time_diff); - return snprintf(buf, PAGE_SIZE, "0\n"); + return sysfs_emit(buf, "0\n"); } static void idletimer_tg_work(struct work_struct *work) From 39f6eed4cb209643f3f8633291854ed7375d7264 Mon Sep 17 00:00:00 2001 From: Will Mortensen Date: Sat, 6 Nov 2021 18:28:21 -0700 Subject: [PATCH 10/94] netfilter: flowtable: fix IPv6 tunnel addr match Previously the IPv6 addresses in the key were clobbered and the mask was left unset. I haven't tested this; I noticed it while skimming the code to understand an unrelated issue. Fixes: cfab6dbd0ecf ("netfilter: flowtable: add tunnel match offload support") Cc: wenxu Signed-off-by: Will Mortensen Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_flow_table_offload.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index d6bf1b2cd541..b561e0a44a45 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -65,11 +65,11 @@ static void nf_flow_rule_lwt_match(struct nf_flow_match *match, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.src, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.src, 0xff, + memset(&mask->enc_ipv6.src, 0xff, sizeof(struct in6_addr)); if (memcmp(&key->enc_ipv6.dst, &in6addr_any, sizeof(struct in6_addr))) - memset(&key->enc_ipv6.dst, 0xff, + memset(&mask->enc_ipv6.dst, 0xff, sizeof(struct in6_addr)); enc_keys |= BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS); key->enc_control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; From a2acf0c0e2da29950d0361a3b5ea05e8d0351dfe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 Nov 2021 18:23:30 +0100 Subject: [PATCH 11/94] selftests: nft_nat: switch port shadow test cases to socat There are now at least three distinct flavours of netcat/nc tool: 'original' version, one version ported from openbsd and nmap-ncat. The script only works with original because it sets SOREUSEPORT option. Other nc versions return 'port already in use' error and port shadow test fails: PASS: inet IPv6 redirection for ns2-hMHcaRvx nc: bind failed: Address already in use ERROR: portshadow test default: got reply from "ROUTER", not CLIENT as intended Switch to socat instead. Reported-by: kernel test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- tools/testing/selftests/netfilter/nft_nat.sh | 26 ++++++++++++++------ 1 file changed, 19 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh index c62e4e26252c..d88867d2fed7 100755 --- a/tools/testing/selftests/netfilter/nft_nat.sh +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -760,20 +760,20 @@ test_port_shadow() local logmsg="" # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405. - echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null + echo "fake-entry" | ip netns exec "$ns2" timeout 1 socat -u STDIN UDP:"$daddrc":41404,sourceport=1405 - echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_r=$! + echo ROUTER | ip netns exec "$ns0" timeout 5 socat -u STDIN UDP4-LISTEN:1405 & + sc_r=$! - echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 & - nc_c=$! + echo CLIENT | ip netns exec "$ns2" timeout 5 socat -u STDIN UDP4-LISTEN:1405,reuseport & + sc_c=$! sleep 0.3 # ns1 tries to connect to ns0:1405. With default settings this should connect # to client, it matches the conntrack entry created above. - result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405) + result=$(echo "data" | ip netns exec "$ns1" timeout 1 socat - UDP:"$daddrs":1405,sourceport=41404) if [ "$result" = "$expect" ] ;then echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}" @@ -782,7 +782,7 @@ test_port_shadow() ret=1 fi - kill $nc_r $nc_c 2>/dev/null + kill $sc_r $sc_c 2>/dev/null # flush udp entries for next test round, if any ip netns exec "$ns0" conntrack -F >/dev/null 2>&1 @@ -852,6 +852,18 @@ test_port_shadowing() { local family="ip" + conntrack -h >/dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without conntrack tool" + return + fi + + socat -h > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not run nat port shadowing test without socat tool" + return + fi + ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null From 451dc48c806a7ce9fbec5e7a24ccf4b2c936e834 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 11 Nov 2021 22:09:16 -0500 Subject: [PATCH 12/94] net: ieee802154: handle iftypes as u32 This patch fixes an issue that an u32 netlink value is handled as a signed enum value which doesn't fit into the range of u32 netlink type. If it's handled as -1 value some BIT() evaluation ends in a shift-out-of-bounds issue. To solve the issue we set the to u32 max which is s32 "-1" value to keep backwards compatibility and let the followed enum values start counting at 0. This brings the compiler to never handle the enum as signed and a check if the value is above NL802154_IFTYPE_MAX should filter -1 out. Fixes: f3ea5e44231a ("ieee802154: add new interface command") Signed-off-by: Alexander Aring Link: https://lore.kernel.org/r/20211112030916.685793-1-aahringo@redhat.com Signed-off-by: Stefan Schmidt --- include/net/nl802154.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/include/net/nl802154.h b/include/net/nl802154.h index ddcee128f5d9..145acb8f2509 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -150,10 +152,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, From 253e9b4d11e577bb8cbc77ef68a9ff46438065ca Mon Sep 17 00:00:00 2001 From: Volodymyr Mytnyk Date: Thu, 18 Nov 2021 21:48:03 +0200 Subject: [PATCH 13/94] net: marvell: prestera: fix brige port operation Return NOTIFY_DONE (dont't care) for switchdev notifications that prestera driver don't know how to handle them. With introduction of SWITCHDEV_BRPORT_[UN]OFFLOADED switchdev events, the driver rejects adding swport to bridge operation which is handled by prestera_bridge_port_join() func. The root cause of this is that prestera driver returns error (EOPNOTSUPP) in prestera_switchdev_blk_event() handler for unknown swdev events. This causes switchdev_bridge_port_offload() to fail when adding port to bridge in prestera_bridge_port_join(). Fixes: 957e2235e526 ("net: make switchdev_bridge_port_{,unoffload} loosely coupled with the bridge") Signed-off-by: Volodymyr Mytnyk Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 3ce6ccd0f539..79f2fca0d412 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -1124,7 +1124,7 @@ static int prestera_switchdev_blk_event(struct notifier_block *unused, prestera_port_obj_attr_set); break; default: - err = -EOPNOTSUPP; + return NOTIFY_DONE; } return notifier_from_errno(err); From e8d032507cb7912baf1d3e0af54516f823befefd Mon Sep 17 00:00:00 2001 From: Volodymyr Mytnyk Date: Thu, 18 Nov 2021 21:51:40 +0200 Subject: [PATCH 14/94] net: marvell: prestera: fix double free issue on err path fix error path handling in prestera_bridge_port_join() that cases prestera driver to crash (see below). Trace: Internal error: Oops: 96000044 [#1] SMP Modules linked in: prestera_pci prestera uio_pdrv_genirq CPU: 1 PID: 881 Comm: ip Not tainted 5.15.0 #1 pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : prestera_bridge_destroy+0x2c/0xb0 [prestera] lr : prestera_bridge_port_join+0x2cc/0x350 [prestera] sp : ffff800011a1b0f0 ... x2 : ffff000109ca6c80 x1 : dead000000000100 x0 : dead000000000122 Call trace: prestera_bridge_destroy+0x2c/0xb0 [prestera] prestera_bridge_port_join+0x2cc/0x350 [prestera] prestera_netdev_port_event.constprop.0+0x3c4/0x450 [prestera] prestera_netdev_event_handler+0xf4/0x110 [prestera] raw_notifier_call_chain+0x54/0x80 call_netdevice_notifiers_info+0x54/0xa0 __netdev_upper_dev_link+0x19c/0x380 Fixes: e1189d9a5fbe ("net: marvell: prestera: Add Switchdev driver implementation") Signed-off-by: Volodymyr Mytnyk Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/prestera/prestera_switchdev.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c index 79f2fca0d412..b4599fe4ca8d 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_switchdev.c @@ -497,8 +497,8 @@ int prestera_bridge_port_join(struct net_device *br_dev, br_port = prestera_bridge_port_add(bridge, port->dev); if (IS_ERR(br_port)) { - err = PTR_ERR(br_port); - goto err_brport_create; + prestera_bridge_put(bridge); + return PTR_ERR(br_port); } err = switchdev_bridge_port_offload(br_port->dev, port->dev, NULL, @@ -519,8 +519,6 @@ int prestera_bridge_port_join(struct net_device *br_dev, switchdev_bridge_port_unoffload(br_port->dev, NULL, NULL, NULL); err_switchdev_offload: prestera_bridge_port_put(br_port); -err_brport_create: - prestera_bridge_put(bridge); return err; } From 6a405f6c372d14707b87d3097b361b69899a26c8 Mon Sep 17 00:00:00 2001 From: Zekun Shen Date: Thu, 18 Nov 2021 16:08:02 -0500 Subject: [PATCH 15/94] atlantic: fix double-free in aq_ring_tx_clean We found this bug while fuzzing the device driver. Using and freeing the dangling pointer buff->skb would cause use-after-free and double-free. This bug is triggerable with compromised/malfunctioning devices. We found the bug with QEMU emulation and tested the patch by emulation. We did NOT test on a real device. Attached is the bug report. BUG: KASAN: double-free or invalid-free in consume_skb+0x6c/0x1c0 Call Trace: dump_stack+0x76/0xa0 print_address_description.constprop.0+0x16/0x200 ? consume_skb+0x6c/0x1c0 kasan_report_invalid_free+0x61/0xa0 ? consume_skb+0x6c/0x1c0 __kasan_slab_free+0x15e/0x170 ? consume_skb+0x6c/0x1c0 kfree+0x8c/0x230 consume_skb+0x6c/0x1c0 aq_ring_tx_clean+0x5c2/0xa80 [atlantic] aq_vec_poll+0x309/0x5d0 [atlantic] ? _sub_I_65535_1+0x20/0x20 [atlantic] ? __next_timer_interrupt+0xba/0xf0 net_rx_action+0x363/0xbd0 ? call_timer_fn+0x240/0x240 ? __switch_to_asm+0x34/0x70 ? napi_busy_loop+0x520/0x520 ? net_tx_action+0x379/0x720 __do_softirq+0x18c/0x634 ? takeover_tasklets+0x5f0/0x5f0 run_ksoftirqd+0x15/0x20 smpboot_thread_fn+0x2f1/0x6b0 ? smpboot_unregister_percpu_thread+0x160/0x160 ? __kthread_parkme+0x80/0x100 ? smpboot_unregister_percpu_thread+0x160/0x160 kthread+0x2b5/0x3b0 ? kthread_create_on_node+0xd0/0xd0 ret_from_fork+0x22/0x40 Reported-by: Brendan Dolan-Gavitt Signed-off-by: Zekun Shen Reviewed-by: Igor Russkikh Signed-off-by: David S. Miller --- drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 24122ccda614..81b3756417ec 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -298,13 +298,14 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) { + if (unlikely(buff->is_eop && buff->skb)) { u64_stats_update_begin(&self->stats.tx.syncp); ++self->stats.tx.packets; self->stats.tx.bytes += buff->skb->len; u64_stats_update_end(&self->stats.tx.syncp); dev_kfree_skb_any(buff->skb); + buff->skb = NULL; } buff->pa = 0U; buff->eop_index = 0xffffU; From 0f296e782f21dc1c55475a3c107ac68ab09cc1cf Mon Sep 17 00:00:00 2001 From: Zekun Shen Date: Thu, 18 Nov 2021 16:42:47 -0500 Subject: [PATCH 16/94] stmmac_pci: Fix underflow size in stmmac_rx This bug report came up when we were testing the device driver by fuzzing. It shows that buf1_len can get underflowed and be 0xfffffffc (4294967292). This bug is triggerable with a compromised/malfunctioning device. We found the bug through QEMU emulation tested the patch with emulation. We did NOT test it on real hardware. Attached is the bug report by fuzzing. BUG: KASAN: use-after-free in stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] Read of size 4294967292 at addr ffff888016358000 by task ksoftirqd/0/9 CPU: 0 PID: 9 Comm: ksoftirqd/0 Tainted: G W 5.6.0 #1 Call Trace: dump_stack+0x76/0xa0 print_address_description.constprop.0+0x16/0x200 ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] __kasan_report.cold+0x37/0x7c ? stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] kasan_report+0xe/0x20 check_memory_region+0x15a/0x1d0 memcpy+0x20/0x50 stmmac_napi_poll_rx+0x1c08/0x36e0 [stmmac] ? stmmac_suspend+0x850/0x850 [stmmac] ? __next_timer_interrupt+0xba/0xf0 net_rx_action+0x363/0xbd0 ? call_timer_fn+0x240/0x240 ? __switch_to_asm+0x40/0x70 ? napi_busy_loop+0x520/0x520 ? __schedule+0x839/0x15a0 __do_softirq+0x18c/0x634 ? takeover_tasklets+0x5f0/0x5f0 run_ksoftirqd+0x15/0x20 smpboot_thread_fn+0x2f1/0x6b0 ? smpboot_unregister_percpu_thread+0x160/0x160 ? __kthread_parkme+0x80/0x100 ? smpboot_unregister_percpu_thread+0x160/0x160 kthread+0x2b5/0x3b0 ? kthread_create_on_node+0xd0/0xd0 ret_from_fork+0x22/0x40 Reported-by: Brendan Dolan-Gavitt Signed-off-by: Zekun Shen Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 2eb284576336..19bc86f2092f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5161,12 +5161,13 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) if (likely(!(status & rx_not_ls)) && (likely(priv->synopsys_id >= DWMAC_CORE_4_00) || unlikely(status != llc_snap))) { - if (buf2_len) + if (buf2_len) { buf2_len -= ETH_FCS_LEN; - else + len -= ETH_FCS_LEN; + } else if (buf1_len) { buf1_len -= ETH_FCS_LEN; - - len -= ETH_FCS_LEN; + len -= ETH_FCS_LEN; + } } if (!skb) { From e792779e6b639c182df91b46ac1e5803460b0b15 Mon Sep 17 00:00:00 2001 From: Nitesh B Venkatesh Date: Fri, 4 Jun 2021 09:53:31 -0700 Subject: [PATCH 17/94] iavf: Prevent changing static ITR values if adaptive moderation is on Resolve being able to change static values on VF when adaptive interrupt moderation is enabled. This problem is fixed by checking the interrupt settings is not a combination of change of static value while adaptive interrupt moderation is turned on. Without this fix, the user would be able to change static values on VF with adaptive moderation enabled. Fixes: 65e87c0398f5 ("i40evf: support queue-specific settings for interrupt moderation") Signed-off-by: Nitesh B Venkatesh Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen --- .../net/ethernet/intel/iavf/iavf_ethtool.c | 30 ++++++++++++++++--- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 144a77679359..71b23922089f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -723,12 +723,31 @@ static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, * * Change the ITR settings for a specific queue. **/ -static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, - struct ethtool_coalesce *ec, int queue) +static int iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) { struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; struct iavf_q_vector *q_vector; + u16 itr_setting; + + itr_setting = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->rx_coalesce_usecs != itr_setting && + ec->use_adaptive_rx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); + return -EINVAL; + } + + itr_setting = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + if (ec->tx_coalesce_usecs != itr_setting && + ec->use_adaptive_tx_coalesce) { + netif_info(adapter, drv, adapter->netdev, + "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); + return -EINVAL; + } rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); @@ -751,6 +770,7 @@ static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, * the Tx and Rx ITR values based on the values we have entered * into the q_vector, no need to write the values now. */ + return 0; } /** @@ -792,9 +812,11 @@ static int __iavf_set_coalesce(struct net_device *netdev, */ if (queue < 0) { for (i = 0; i < adapter->num_active_queues; i++) - iavf_set_itr_per_queue(adapter, ec, i); + if (iavf_set_itr_per_queue(adapter, ec, i)) + return -EINVAL; } else if (queue < adapter->num_active_queues) { - iavf_set_itr_per_queue(adapter, ec, queue); + if (iavf_set_itr_per_queue(adapter, ec, queue)) + return -EINVAL; } else { netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", adapter->num_active_queues - 1); From 0cc318d2e8408bc0ffb4662a0c3e5e57005ac6ff Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Tue, 7 Sep 2021 09:25:40 +0000 Subject: [PATCH 18/94] iavf: Fix deadlock occurrence during resetting VF interface System hangs if close the interface is called from the kernel during the interface is in resetting state. During resetting operation the link is closing but kernel didn't know it and it tried to close this interface again what sometimes led to deadlock. Inform kernel about current state of interface and turn off the flag IFF_UP when interface is closing until reset is finished. Previously it was most likely to hang the system when kernel (network manager) tried to close the interface in the same time when interface was in resetting state because of deadlock. Fixes: 3c8e0b989aa1 ("i40vf: don't stop me now") Signed-off-by: Jaroslaw Gawin Signed-off-by: Jedrzej Jagielski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 336e6bf95e48..84680777ac12 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2254,6 +2254,7 @@ static void iavf_reset_task(struct work_struct *work) (adapter->state == __IAVF_RESETTING)); if (running) { + netdev->flags &= ~IFF_UP; netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; @@ -2365,7 +2366,7 @@ static void iavf_reset_task(struct work_struct *work) * to __IAVF_RUNNING */ iavf_up_complete(adapter); - + netdev->flags |= IFF_UP; iavf_irq_enable(adapter, true); } else { iavf_change_state(adapter, __IAVF_DOWN); @@ -2378,8 +2379,10 @@ static void iavf_reset_task(struct work_struct *work) reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (running) + if (running) { iavf_change_state(adapter, __IAVF_RUNNING); + netdev->flags |= IFF_UP; + } dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); iavf_close(netdev); } From 3b5bdd18eb76e7570d9bacbcab6828a9b26ae121 Mon Sep 17 00:00:00 2001 From: Jedrzej Jagielski Date: Wed, 15 Sep 2021 09:01:00 +0000 Subject: [PATCH 19/94] iavf: Fix refreshing iavf adapter stats on ethtool request Currently iavf adapter statistics are refreshed only in a watchdog task, triggered approximately every two seconds, which causes some ethtool requests to return outdated values. Add explicit statistics refresh when requested by ethtool -S. Fixes: b476b0030e61 ("iavf: Move commands processing to the separate function") Signed-off-by: Jan Sokolowski Signed-off-by: Jedrzej Jagielski Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 2 ++ drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 3 +++ drivers/net/ethernet/intel/iavf/iavf_main.c | 18 ++++++++++++++++++ .../net/ethernet/intel/iavf/iavf_virtchnl.c | 2 ++ 4 files changed, 25 insertions(+) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 75635bd57cf6..bb9cc227d1e1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -305,6 +305,7 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DEL_FDIR_FILTER BIT(26) #define IAVF_FLAG_AQ_ADD_ADV_RSS_CFG BIT(27) #define IAVF_FLAG_AQ_DEL_ADV_RSS_CFG BIT(28) +#define IAVF_FLAG_AQ_REQUEST_STATS BIT(29) /* OS defined structs */ struct net_device *netdev; @@ -444,6 +445,7 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_request_stats(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 71b23922089f..0cecaff38d04 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -354,6 +354,9 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, struct iavf_adapter *adapter = netdev_priv(netdev); unsigned int i; + /* Explicitly request stats refresh */ + iavf_schedule_request_stats(adapter); + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); rcu_read_lock(); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 84680777ac12..8e96ae746c3d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -174,6 +174,19 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) } } +/** + * iavf_schedule_request_stats - Set the flags and schedule statistics request + * @adapter: board private structure + * + * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly + * request and refresh ethtool stats + **/ +void iavf_schedule_request_stats(struct iavf_adapter *adapter) +{ + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; + mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); +} + /** * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure @@ -1709,6 +1722,11 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_del_adv_rss_cfg(adapter); return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { + iavf_request_stats(adapter); + return 0; + } + return -EAGAIN; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8c3f0f77cb57..8421cbe6a197 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -784,6 +784,8 @@ void iavf_request_stats(struct iavf_adapter *adapter) /* no error message, this isn't crucial */ return; } + + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_STATS; adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ From 5951a2b9812d8227d33f20d1899fae60e4f72c04 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 5 Nov 2021 09:20:25 -0700 Subject: [PATCH 20/94] iavf: Fix VLAN feature flags after VFR When a VF goes through a reset, it's possible for the VF's feature set to change. For example it may lose the VIRTCHNL_VF_OFFLOAD_VLAN capability after VF reset. Unfortunately, the driver doesn't correctly deal with this situation and errors are seen from downing/upping the interface and/or moving the interface in/out of a network namespace. When setting the interface down/up we see the following errors after the VIRTCHNL_VF_OFFLOAD_VLAN capability was taken away from the VF: ice 0000:51:00.1: VF 1 failed opcode 12, retval: -64 iavf 0000:51:09.1: Failed to add VLAN filter, error IAVF_NOT_SUPPORTED ice 0000:51:00.1: VF 1 failed opcode 13, retval: -64 iavf 0000:51:09.1: Failed to delete VLAN filter, error IAVF_NOT_SUPPORTED These add/delete errors are happening because the VLAN filters are tracked internally to the driver and regardless of the VLAN_ALLOWED() setting the driver tries to delete/re-add them over virtchnl. Fix the delete failure by making sure to delete any VLAN filter tracking in the driver when a removal request is made, while preventing the virtchnl request. This makes it so the driver's VLAN list is up to date and the errors are Fix the add failure by making sure the check for VLAN_ALLOWED() during reset is done after the VF receives its capability list from the PF via VIRTCHNL_OP_GET_VF_RESOURCES. If VLAN functionality is not allowed, then prevent requesting re-adding the filters over virtchnl. When moving the interface into a network namespace we see the following errors after the VIRTCHNL_VF_OFFLOAD_VLAN capability was taken away from the VF: iavf 0000:51:09.1 enp81s0f1v1: NIC Link is Up Speed is 25 Gbps Full Duplex iavf 0000:51:09.1 temp_27: renamed from enp81s0f1v1 iavf 0000:51:09.1 mgmt: renamed from temp_27 iavf 0000:51:09.1 dev27: set_features() failed (-22); wanted 0x020190001fd54833, left 0x020190001fd54bb3 These errors are happening because we aren't correctly updating the netdev capabilities and dealing with ndo_fix_features() and ndo_set_features() correctly. Fix this by only reporting errors in the driver's ndo_set_features() callback when VIRTCHNL_VF_OFFLOAD_VLAN is not allowed and any attempt to enable the VLAN features is made. Also, make sure to disable VLAN insertion, filtering, and stripping since the VIRTCHNL_VF_OFFLOAD_VLAN flag applies to all of them and not just VLAN stripping. Also, after we process the capabilities in the VF reset path, make sure to call netdev_update_features() in case the capabilities have changed in order to update the netdev's feature set to match the VF's actual capabilities. Lastly, make sure to always report success on VLAN filter delete when VIRTCHNL_VF_OFFLOAD_VLAN is not supported. The changed flow in iavf_del_vlans() allows the stack to delete previosly existing VLAN filters even if VLAN filtering is not allowed. This makes it so the VLAN filter list is up to date. Fixes: 8774370d268f ("i40e/i40evf: support for VF VLAN tag stripping control") Signed-off-by: Brett Creeley Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/iavf/iavf.h | 1 + drivers/net/ethernet/intel/iavf/iavf_main.c | 33 ++++++-------- .../net/ethernet/intel/iavf/iavf_virtchnl.c | 45 +++++++++++++++++-- 3 files changed, 56 insertions(+), 23 deletions(-) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index bb9cc227d1e1..3789269ce741 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -503,4 +503,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 8e96ae746c3d..14934a7a13ef 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -147,7 +147,7 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, * * Returns 0 on success, negative on failure **/ -static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) +int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) { unsigned int wait, delay = 10; @@ -717,13 +717,11 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - /* re-add all VLAN filters */ - if (VLAN_ALLOWED(adapter)) { - u16 vid; + u16 vid; - for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) - iavf_add_vlan(adapter, vid); - } + /* re-add all VLAN filters */ + for_each_set_bit(vid, adapter->vsi.active_vlans, VLAN_N_VID) + iavf_add_vlan(adapter, vid); } /** @@ -758,9 +756,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!VLAN_ALLOWED(adapter)) - return -EIO; - iavf_del_vlan(adapter, vid); clear_bit(vid, adapter->vsi.active_vlans); @@ -2191,7 +2186,6 @@ static void iavf_reset_task(struct work_struct *work) struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; struct iavf_mac_filter *f, *ftmp; - struct iavf_vlan_filter *vlf; struct iavf_cloud_filter *cf; u32 reg_val; int i = 0, err; @@ -2332,11 +2326,6 @@ static void iavf_reset_task(struct work_struct *work) list_for_each_entry(f, &adapter->mac_filter_list, list) { f->add = true; } - /* re-add all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->add = true; - } - spin_unlock_bh(&adapter->mac_vlan_list_lock); /* check if TCs are running and re-add all cloud filters */ @@ -2350,7 +2339,6 @@ static void iavf_reset_task(struct work_struct *work) spin_unlock_bh(&adapter->cloud_filter_list_lock); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); @@ -3462,11 +3450,16 @@ static int iavf_set_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when adapter is not capable - * of VLAN offload + /* Don't allow enabling VLAN features when adapter is not capable + * of VLAN offload/filtering */ if (!VLAN_ALLOWED(adapter)) { - if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + netdev->hw_features &= ~(NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER); + if (features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER)) return -EINVAL; } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8421cbe6a197..d60bf7c21200 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -607,7 +607,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) if (f->add) count++; } - if (!count) { + if (!count || !VLAN_ALLOWED(adapter)) { adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; @@ -673,9 +673,19 @@ void iavf_del_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); - list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->remove) + list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { + /* since VLAN capabilities are not allowed, we dont want to send + * a VLAN delete request because it will most likely fail and + * create unnecessary errors/noise, so just free the VLAN + * filters marked for removal to enable bailing out before + * sending a virtchnl message + */ + if (f->remove && !VLAN_ALLOWED(adapter)) { + list_del(&f->list); + kfree(f); + } else if (f->remove) { count++; + } } if (!count) { adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; @@ -1724,8 +1734,37 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } spin_lock_bh(&adapter->mac_vlan_list_lock); iavf_add_filter(adapter, adapter->hw.mac.addr); + + if (VLAN_ALLOWED(adapter)) { + if (!list_empty(&adapter->vlan_filter_list)) { + struct iavf_vlan_filter *vlf; + + /* re-add all VLAN filters over virtchnl */ + list_for_each_entry(vlf, + &adapter->vlan_filter_list, + list) + vlf->add = true; + + adapter->aq_required |= + IAVF_FLAG_AQ_ADD_VLAN_FILTER; + } + } + spin_unlock_bh(&adapter->mac_vlan_list_lock); iavf_process_config(adapter); + + /* unlock crit_lock before acquiring rtnl_lock as other + * processes holding rtnl_lock could be waiting for the same + * crit_lock + */ + mutex_unlock(&adapter->crit_lock); + rtnl_lock(); + netdev_update_features(adapter->netdev); + rtnl_unlock(); + if (iavf_lock_timeout(&adapter->crit_lock, 10000)) + dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", + __FUNCTION__); + } break; case VIRTCHNL_OP_ENABLE_QUEUES: From ee50e67ba0e17b1a1a8d76691d02eadf9e0f392c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2021 15:27:54 +0100 Subject: [PATCH 21/94] mptcp: fix delack timer To compute the rtx timeout schedule_3rdack_retransmission() does multiple things in the wrong way: srtt_us is measured in usec/8 and the timeout itself is an absolute value. Fixes: ec3edaa7ca6ce02f ("mptcp: Add handling of outgoing MP_JOIN requests") Acked-by: Paolo Abeni Reviewed-by: Mat Martineau @linux.intel.com> Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/mptcp/options.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7c3420afb1a0..2e9b73eeeeb5 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -434,9 +434,10 @@ static void schedule_3rdack_retransmission(struct sock *sk) /* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) - timeout = tp->srtt_us << 1; + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); else timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; From bcd97734318d1d87bb237dbc0a60c81237b0ac50 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 19 Nov 2021 15:27:55 +0100 Subject: [PATCH 22/94] mptcp: use delegate action to schedule 3rd ack retrans Scheduling a delack in mptcp_established_options_mp() is not a good idea: such function is called by tcp_send_ack() and the pending delayed ack will be cleared shortly after by the tcp_event_ack_sent() call in __tcp_transmit_skb(). Instead use the mptcp delegated action infrastructure to schedule the delayed ack after the current bh processing completes. Additionally moves the schedule_3rdack_retransmission() helper into protocol.c to avoid making it visible in a different compilation unit. Fixes: ec3edaa7ca6ce02f ("mptcp: Add handling of outgoing MP_JOIN requests") Reviewed-by: Mat Martineau @linux.intel.com> Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/mptcp/options.c | 33 ++++++++-------------------- net/mptcp/protocol.c | 51 ++++++++++++++++++++++++++++++++++++-------- net/mptcp/protocol.h | 17 ++++++++------- 3 files changed, 60 insertions(+), 41 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2e9b73eeeeb5..fe98e4f475ba 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -422,29 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -/* MP_JOIN client subflow must wait for 4th ack before sending any data: - * TCP can't schedule delack timer before the subflow is fully established. - * MPTCP uses the delack timer to do 3rd ack retransmissions - */ -static void schedule_3rdack_retransmission(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - unsigned long timeout; - - /* reschedule with a timeout above RTT, as we must look only for drop */ - if (tp->srtt_us) - timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); - else - timeout = TCP_TIMEOUT_INIT; - timeout += jiffies; - - WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); - icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; - icsk->icsk_ack.timeout = timeout; - sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); -} - static void clear_3rdack_retransmission(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -527,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size = TCPOLEN_MPTCP_MPJ_ACK; pr_debug("subflow=%p", subflow); - schedule_3rdack_retransmission(sk); + /* we can use the full delegate action helper only from BH context + * If we are in process context - sk is flushing the backlog at + * socket lock release time - just set the appropriate flag, will + * be handled by the release callback + */ + if (sock_owned_by_user(sk)) + set_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status); + else + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_ACK); return true; } return false; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7e32e316738..c82a76d2d0bf 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1596,7 +1596,8 @@ static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk) if (!xmit_ssk) goto out; if (xmit_ssk != ssk) { - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), + MPTCP_DELEGATE_SEND); goto out; } @@ -2943,7 +2944,7 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk) if (xmit_ssk == ssk) __mptcp_subflow_push_pending(sk, ssk); else if (xmit_ssk) - mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk)); + mptcp_subflow_delegate(mptcp_subflow_ctx(xmit_ssk), MPTCP_DELEGATE_SEND); } else { set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); } @@ -2993,18 +2994,50 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_update_rmem(sk); } +/* MP_JOIN client subflow must wait for 4th ack before sending any data: + * TCP can't schedule delack timer before the subflow is fully established. + * MPTCP uses the delack timer to do 3rd ack retransmissions + */ +static void schedule_3rdack_retransmission(struct sock *ssk) +{ + struct inet_connection_sock *icsk = inet_csk(ssk); + struct tcp_sock *tp = tcp_sk(ssk); + unsigned long timeout; + + if (mptcp_subflow_ctx(ssk)->fully_established) + return; + + /* reschedule with a timeout above RTT, as we must look only for drop */ + if (tp->srtt_us) + timeout = usecs_to_jiffies(tp->srtt_us >> (3 - 1)); + else + timeout = TCP_TIMEOUT_INIT; + timeout += jiffies; + + WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER); + icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; + icsk->icsk_ack.timeout = timeout; + sk_reset_timer(ssk, &icsk->icsk_delack_timer, timeout); +} + void mptcp_subflow_process_delegated(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) - __mptcp_subflow_push_pending(sk, ssk); - else - set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); - mptcp_data_unlock(sk); - mptcp_subflow_delegated_done(subflow); + if (test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_subflow_push_pending(sk, ssk); + else + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); + mptcp_data_unlock(sk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_SEND); + } + if (test_bit(MPTCP_DELEGATE_ACK, &subflow->delegated_status)) { + schedule_3rdack_retransmission(ssk); + mptcp_subflow_delegated_done(subflow, MPTCP_DELEGATE_ACK); + } } static int mptcp_hash(struct sock *sk) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 67a61ac48b20..d87cc040352e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,6 +387,7 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SEND 0 +#define MPTCP_DELEGATE_ACK 1 /* MPTCP subflow context */ struct mptcp_subflow_context { @@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk, void mptcp_subflow_process_delegated(struct sock *ssk); -static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow, int action) { struct mptcp_delegated_action *delegated; bool schedule; + /* the caller held the subflow bh socket lock */ + lockdep_assert_in_softirq(); + /* The implied barrier pairs with mptcp_subflow_delegated_done(), and * ensures the below list check sees list updates done prior to status * bit changes */ - if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) { + if (!test_and_set_bit(action, &subflow->delegated_status)) { /* still on delegated list from previous scheduling */ if (!list_empty(&subflow->delegated_node)) return; - /* the caller held the subflow bh socket lock */ - lockdep_assert_in_softirq(); - delegated = this_cpu_ptr(&mptcp_delegated_actions); schedule = list_empty(&delegated->head); list_add_tail(&subflow->delegated_node, &delegated->head); @@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated) static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow) { - return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + return !!READ_ONCE(subflow->delegated_status); } -static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow, int action) { /* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before * touching the status bit */ smp_wmb(); - clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status); + clear_bit(action, &subflow->delegated_status); } int mptcp_is_enabled(const struct net *net); From f9390b249c90a15a4d9e69fbfb7a53c860b1fcaf Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 19 Nov 2021 13:05:21 +0100 Subject: [PATCH 23/94] af_unix: fix regression in read after shutdown On kernels before v5.15, calling read() on a unix socket after shutdown(SHUT_RD) or shutdown(SHUT_RDWR) would return the data previously written or EOF. But now, while read() after shutdown(SHUT_RD) still behaves the same way, read() after shutdown(SHUT_RDWR) always fails with -EINVAL. This behaviour change was apparently inadvertently introduced as part of a bug fix for a different regression caused by the commit adding sockmap support to af_unix, commit 94531cfcbe79c359 ("af_unix: Add unix_stream_proto for sockmap"). Those commits, for unclear reasons, started setting the socket state to TCP_CLOSE on shutdown(SHUT_RDWR), while this state change had previously only been done in unix_release_sock(). Restore the original behaviour. The sockmap tests in tests/selftests/bpf continue to pass after this patch. Fixes: d0c6416bd7091647f60 ("unix: Fix an issue in unix_shutdown causing the other end read/write failures") Link: https://lore.kernel.org/lkml/20211111140000.GA10779@axis.com/ Signed-off-by: Vincent Whitchurch Tested-by: Casey Schaufler Signed-off-by: David S. Miller --- net/unix/af_unix.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 78e08e82c08c..b0bfc78e421c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2882,9 +2882,6 @@ static int unix_shutdown(struct socket *sock, int mode) unix_state_lock(sk); sk->sk_shutdown |= mode; - if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) && - mode == SHUTDOWN_MASK) - sk->sk_state = TCP_CLOSE; other = unix_peer(sk); if (other) sock_hold(other); From 3b00a07c2443745d62babfe08dbb2ad8e649526e Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Fri, 19 Nov 2021 03:03:49 +0100 Subject: [PATCH 24/94] net: dsa: qca8k: fix internal delay applied to the wrong PAD config With SGMII phy the internal delay is always applied to the PAD0 config. This is caused by the falling edge configuration that hardcode the reg to PAD0 (as the falling edge bits are present only in PAD0 reg) Move the delay configuration before the reg overwrite to correctly apply the delay. Fixes: cef08115846e ("net: dsa: qca8k: set internal delay also for sgmii") Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index a429c9750add..d7bcecbc1c53 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1433,6 +1433,12 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, qca8k_write(priv, QCA8K_REG_SGMII_CTRL, val); + /* From original code is reported port instability as SGMII also + * require delay set. Apply advised values here or take them from DT. + */ + if (state->interface == PHY_INTERFACE_MODE_SGMII) + qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); + /* For qca8327/qca8328/qca8334/qca8338 sgmii is unique and * falling edge is set writing in the PORT0 PAD reg */ @@ -1455,12 +1461,6 @@ qca8k_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, QCA8K_PORT0_PAD_SGMII_TXCLK_FALLING_EDGE, val); - /* From original code is reported port instability as SGMII also - * require delay set. Apply advised values here or take them from DT. - */ - if (state->interface == PHY_INTERFACE_MODE_SGMII) - qca8k_mac_config_setup_internal_delay(priv, cpu_port_index, reg); - break; default: dev_err(ds->dev, "xMII mode %s not supported for port %d\n", From 65258b9d8cde45689bdc86ca39b50f01f983733b Mon Sep 17 00:00:00 2001 From: Robert Marko Date: Fri, 19 Nov 2021 03:03:50 +0100 Subject: [PATCH 25/94] net: dsa: qca8k: fix MTU calculation qca8k has a global MTU, so its tracking the MTU per port to make sure that the largest MTU gets applied. Since it uses the frame size instead of MTU the driver MTU change function will then add the size of Ethernet header and checksum on top of MTU. The driver currently populates the per port MTU size as Ethernet frame length + checksum which equals 1518. The issue is that then MTU change function will go through all of the ports, find the largest MTU and apply the Ethernet header + checksum on top of it again, so for a desired MTU of 1500 you will end up with 1536. This is obviously incorrect, so to correct it populate the per port struct MTU with just the MTU and not include the Ethernet header + checksum size as those will be added by the MTU change function. Fixes: f58d2598cf70 ("net: dsa: qca8k: implement the port MTU callbacks") Signed-off-by: Robert Marko Signed-off-by: Ansuel Smith Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/qca8k.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index d7bcecbc1c53..147ca39531a3 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1256,8 +1256,12 @@ qca8k_setup(struct dsa_switch *ds) /* Set initial MTU for every port. * We have only have a general MTU setting. So track * every port and set the max across all port. + * Set per port MTU to 1500 as the MTU change function + * will add the overhead and if its set to 1518 then it + * will apply the overhead again and we will end up with + * MTU of 1536 instead of 1518 */ - priv->port_mtu[i] = ETH_FRAME_LEN + ETH_FCS_LEN; + priv->port_mtu[i] = ETH_DATA_LEN; } /* Special GLOBAL_FC_THRESH value are needed for ar8327 switch */ From bdf1565fe03d29777d24e239163d0d53e4af9ce0 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Fri, 19 Nov 2021 14:24:56 +0800 Subject: [PATCH 26/94] selftests/tc-testing: match any qdisc type We should not always presume all kernels use pfifo_fast as the default qdisc. For example, a fq_codel qdisk could have below output: qdisc fq_codel 0: parent 1:4 limit 10240p flows 1024 quantum 1514 target 5ms interval 100ms memory_limit 32Mb ecn drop_batch 64 Reported-by: kernel test robot Suggested-by: Peilin Ye Signed-off-by: Li Zhijian Signed-off-by: David S. Miller --- .../selftests/tc-testing/tc-tests/qdiscs/mq.json | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json index 88a20c781e49..c6046096d9db 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/mq.json @@ -15,7 +15,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -37,7 +37,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-9,a-f][0-9,a-f]{0,2} bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-9,a-f][0-9,a-f]{0,2}", "matchCount": "256", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -60,7 +60,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "4", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -82,7 +82,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -106,7 +106,7 @@ "cmdUnderTest": "$TC qdisc del dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" @@ -128,7 +128,7 @@ "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: mq", "expExitCode": "2", "verifyCmd": "$TC qdisc show dev $ETH", - "matchPattern": "qdisc pfifo_fast 0: parent 1:[1-4] bands 3 priomap 1 2 2 2 1 2 0 0 1 1 1 1 1 1 1 1", + "matchPattern": "qdisc [a-zA-Z0-9_]+ 0: parent 1:[1-4]", "matchCount": "0", "teardown": [ "echo \"1\" > /sys/bus/netdevsim/del_device" From ac2944abe4d7732f29a79f063c9cae7df2a3e3cc Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Fri, 19 Nov 2021 14:24:57 +0800 Subject: [PATCH 27/94] selftests/tc-testings: Be compatible with newer tc output old tc(iproute2-5.9.0) output: action order 1: bpf action.o:[action-ok] id 60 tag bcf7977d3b93787c jited default-action pipe newer tc(iproute2-5.14.0) output: action order 1: bpf action.o:[action-ok] id 64 name tag bcf7977d3b93787c jited default-action pipe It can fix below errors: # ok 260 f84a - Add cBPF action with invalid bytecode # not ok 261 e939 - Add eBPF action with valid object-file # Could not match regex pattern. Verify command output: # total acts 0 # # action order 1: bpf action.o:[action-ok] id 42 name tag bcf7977d3b93787c jited default-action pipe # index 667 ref 1 bind 0 Signed-off-by: Li Zhijian Signed-off-by: David S. Miller --- tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 503982b8f295..91832400ddbd 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -68,7 +68,7 @@ "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9].* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf" From 19d36c5f294879949c9d6f57cb61d39cc4c48553 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Nov 2021 17:37:58 -0800 Subject: [PATCH 28/94] ipv6: fix typos in __ip6_finish_output() We deal with IPv6 packets, so we need to use IP6CB(skb)->flags and IP6SKB_REROUTED, instead of IPCB(skb)->flags and IPSKB_REROUTED Found by code inspection, please double check that fixing this bug does not surface other bugs. Fixes: 09ee9dba9611 ("ipv6: Reinject IPv6 packets if IPsec policy matches after SNAT") Signed-off-by: Eric Dumazet Cc: Tobias Brunner Cc: Steffen Klassert Cc: David Ahern Reviewed-by: David Ahern Tested-by: Tobias Brunner Acked-by: Tobias Brunner Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2f044a49afa8..ff4e83e2a506 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -174,7 +174,7 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; + IP6CB(skb)->flags |= IP6SKB_REROUTED; return dst_output(net, sk, skb); } #endif From 3bd6b2a838ba6a3b86d41b077f570b1b61174def Mon Sep 17 00:00:00 2001 From: Diana Wang Date: Fri, 19 Nov 2021 14:38:03 +0100 Subject: [PATCH 29/94] nfp: checking parameter process for rx-usecs/tx-usecs is invalid Use nn->tlv_caps.me_freq_mhz instead of nn->me_freq_mhz to check whether rx-usecs/tx-usecs is valid. This is because nn->tlv_caps.me_freq_mhz represents the clock_freq (MHz) of the flow processing cores (FPC) on the NIC. While nn->me_freq_mhz is not be set. Fixes: ce991ab6662a ("nfp: read ME frequency from vNIC ctrl memory") Signed-off-by: Diana Wang Signed-off-by: Simon Horman Reviewed-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net.h | 3 --- drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 2 +- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index df203738511b..0b1865e9f0b5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -565,7 +565,6 @@ struct nfp_net_dp { * @exn_name: Name for Exception interrupt * @shared_handler: Handler for shared interrupts * @shared_name: Name for shared interrupt - * @me_freq_mhz: ME clock_freq (MHz) * @reconfig_lock: Protects @reconfig_posted, @reconfig_timer_active, * @reconfig_sync_present and HW reconfiguration request * regs/machinery from async requests (sync must take @@ -650,8 +649,6 @@ struct nfp_net { irq_handler_t shared_handler; char shared_name[IFNAMSIZ + 8]; - u32 me_freq_mhz; - bool link_up; spinlock_t link_status_lock; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1de076f55740..cf7882933993 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1344,7 +1344,7 @@ static int nfp_net_set_coalesce(struct net_device *netdev, * ME timestamp ticks. There are 16 ME clock cycles for each timestamp * count. */ - factor = nn->me_freq_mhz / 16; + factor = nn->tlv_caps.me_freq_mhz / 16; /* Each pair of (usecs, max_frames) fields specifies that interrupts * should be coalesced until From a6da2bbb0005e6b4909472962c9d0af29e75dd06 Mon Sep 17 00:00:00 2001 From: Holger Assmann Date: Sun, 21 Nov 2021 19:57:04 +0200 Subject: [PATCH 30/94] net: stmmac: retain PTP clock time during SIOCSHWTSTAMP ioctls Currently, when user space emits SIOCSHWTSTAMP ioctl calls such as enabling/disabling timestamping or changing filter settings, the driver reads the current CLOCK_REALTIME value and programming this into the NIC's hardware clock. This might be necessary during system initialization, but at runtime, when the PTP clock has already been synchronized to a grandmaster, a reset of the timestamp settings might result in a clock jump. Furthermore, if the clock is also controlled by phc2sys in automatic mode (where the UTC offset is queried from ptp4l), that UTC-to-TAI offset (currently 37 seconds in 2021) would be temporarily reset to 0, and it would take a long time for phc2sys to readjust so that CLOCK_REALTIME and the PHC are apart by 37 seconds again. To address the issue, we introduce a new function called stmmac_init_tstamp_counter(), which gets called during ndo_open(). It contains the code snippet moved from stmmac_hwtstamp_set() that manages the time synchronization. Besides, the sub second increment configuration is also moved here since the related values are hardware dependent and runtime invariant. Furthermore, the hardware clock must be kept running even when no time stamping mode is selected in order to retain the synchronized time base. That way, timestamping can be enabled again at any time only with the need to compensate the clock's natural drifting. As a side effect, this patch fixes the issue that ptp_clock_info::enable can be called before SIOCSHWTSTAMP and the driver (which looks at priv->systime_flags) was not prepared to handle that ordering. Fixes: 92ba6888510c ("stmmac: add the support for PTP hw clock driver") Reported-by: Michael Olbrich Signed-off-by: Ahmad Fatoum Signed-off-by: Holger Assmann Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/stmmac.h | 1 + .../net/ethernet/stmicro/stmmac/stmmac_main.c | 125 +++++++++++------- .../ethernet/stmicro/stmmac/stmmac_platform.c | 2 +- 3 files changed, 81 insertions(+), 47 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 43eead726886..5f129733aabd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -314,6 +314,7 @@ int stmmac_mdio_reset(struct mii_bus *mii); int stmmac_xpcs_setup(struct mii_bus *mii); void stmmac_set_ethtool_ops(struct net_device *netdev); +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags); void stmmac_ptp_register(struct stmmac_priv *priv); void stmmac_ptp_unregister(struct stmmac_priv *priv); int stmmac_open(struct net_device *dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 19bc86f2092f..f12097c8a485 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -50,6 +50,13 @@ #include "dwxgmac2.h" #include "hwif.h" +/* As long as the interface is active, we keep the timestamping counter enabled + * with fine resolution and binary rollover. This avoid non-monotonic behavior + * (clock jumps) when changing timestamping settings at runtime. + */ +#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \ + PTP_TCR_TSCTRLSSR) + #define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) @@ -613,8 +620,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) { struct stmmac_priv *priv = netdev_priv(dev); struct hwtstamp_config config; - struct timespec64 now; - u64 temp = 0; u32 ptp_v2 = 0; u32 tstamp_all = 0; u32 ptp_over_ipv4_udp = 0; @@ -623,11 +628,6 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) u32 snap_type_sel = 0; u32 ts_master_en = 0; u32 ts_event_en = 0; - u32 sec_inc = 0; - u32 value = 0; - bool xmac; - - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; if (!(priv->dma_cap.time_stamp || priv->adv_ts)) { netdev_alert(priv->dev, "No support for HW time stamping\n"); @@ -789,42 +789,17 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) priv->hwts_rx_en = ((config.rx_filter == HWTSTAMP_FILTER_NONE) ? 0 : 1); priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; - if (!priv->hwts_tx_en && !priv->hwts_rx_en) - stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0); - else { - value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | - tstamp_all | ptp_v2 | ptp_over_ethernet | - ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | - ts_master_en | snap_type_sel); - stmmac_config_hw_tstamping(priv, priv->ptpaddr, value); + priv->systime_flags = STMMAC_HWTS_ACTIVE; - /* program Sub Second Increment reg */ - stmmac_config_sub_second_increment(priv, - priv->ptpaddr, priv->plat->clk_ptp_rate, - xmac, &sec_inc); - temp = div_u64(1000000000ULL, sec_inc); - - /* Store sub second increment and flags for later use */ - priv->sub_second_inc = sec_inc; - priv->systime_flags = value; - - /* calculate default added value: - * formula is : - * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = 1e9ns/sec_inc - */ - temp = (u64)(temp << 32); - priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); - stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); - - /* initialize system time */ - ktime_get_real_ts64(&now); - - /* lower 32 bits of tv_sec are safe until y2106 */ - stmmac_init_systime(priv, priv->ptpaddr, - (u32)now.tv_sec, now.tv_nsec); + if (priv->hwts_tx_en || priv->hwts_rx_en) { + priv->systime_flags |= tstamp_all | ptp_v2 | + ptp_over_ethernet | ptp_over_ipv6_udp | + ptp_over_ipv4_udp | ts_event_en | + ts_master_en | snap_type_sel; } + stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags); + memcpy(&priv->tstamp_config, &config, sizeof(config)); return copy_to_user(ifr->ifr_data, &config, @@ -852,6 +827,66 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) sizeof(*config)) ? -EFAULT : 0; } +/** + * stmmac_init_tstamp_counter - init hardware timestamping counter + * @priv: driver private structure + * @systime_flags: timestamping flags + * Description: + * Initialize hardware counter for packet timestamping. + * This is valid as long as the interface is open and not suspended. + * Will be rerun after resuming from suspend, case in which the timestamping + * flags updated by stmmac_hwtstamp_set() also need to be restored. + */ +int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) +{ + bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + struct timespec64 now; + u32 sec_inc = 0; + u64 temp = 0; + int ret; + + if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) + return -EOPNOTSUPP; + + ret = clk_prepare_enable(priv->plat->clk_ptp_ref); + if (ret < 0) { + netdev_warn(priv->dev, + "failed to enable PTP reference clock: %pe\n", + ERR_PTR(ret)); + return ret; + } + + stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); + priv->systime_flags = systime_flags; + + /* program Sub Second Increment reg */ + stmmac_config_sub_second_increment(priv, priv->ptpaddr, + priv->plat->clk_ptp_rate, + xmac, &sec_inc); + temp = div_u64(1000000000ULL, sec_inc); + + /* Store sub second increment for later use */ + priv->sub_second_inc = sec_inc; + + /* calculate default added value: + * formula is : + * addend = (2^32)/freq_div_ratio; + * where, freq_div_ratio = 1e9ns/sec_inc + */ + temp = (u64)(temp << 32); + priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); + stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); + + /* initialize system time */ + ktime_get_real_ts64(&now); + + /* lower 32 bits of tv_sec are safe until y2106 */ + stmmac_init_systime(priv, priv->ptpaddr, (u32)now.tv_sec, now.tv_nsec); + + return 0; +} +EXPORT_SYMBOL_GPL(stmmac_init_tstamp_counter); + /** * stmmac_init_ptp - init PTP * @priv: driver private structure @@ -862,9 +897,11 @@ static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) static int stmmac_init_ptp(struct stmmac_priv *priv) { bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + int ret; - if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp)) - return -EOPNOTSUPP; + ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); + if (ret) + return ret; priv->adv_ts = 0; /* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */ @@ -3272,10 +3309,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_mmc_setup(priv); if (init_ptp) { - ret = clk_prepare_enable(priv->plat->clk_ptp_ref); - if (ret < 0) - netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret); - ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) netdev_warn(priv->dev, "PTP not supported by HW\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 232ac98943cd..5d29f336315b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -816,7 +816,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (ret) return ret; - clk_prepare_enable(priv->plat->clk_ptp_ref); + stmmac_init_tstamp_counter(priv, priv->systime_flags); } return 0; From f93fd0ca5e7de743ce687951266950fb37877e34 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Sun, 21 Nov 2021 21:06:42 +0100 Subject: [PATCH 31/94] net: ax88796c: do not receive data in pointer MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function axspi_read_status calls: ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); status is a pointer to a struct spi_status, which is 3-byte wide: struct spi_status { u16 isr; u8 status; }; But &status is the pointer to this pointer, and spi_write_then_read does not dereference this parameter: int spi_write_then_read(struct spi_device *spi, const void *txbuf, unsigned n_tx, void *rxbuf, unsigned n_rx) Therefore axspi_read_status currently receive a SPI response in the pointer status, which overwrites 24 bits of the pointer. Thankfully, on Little-Endian systems, the pointer is only used in le16_to_cpus(&status->isr); ... which is a no-operation. So there, the overwritten pointer is not dereferenced. Nevertheless on Big-Endian systems, this can lead to dereferencing pointers after their 24 most significant bits were overwritten. And in all systems this leads to possible use of uninitialized value in functions calling spi_write_then_read which expect status to be initialized when the function returns. Moreover function axspi_read_status (and macro AX_READ_STATUS) do not seem to be used anywhere. So currently this seems to be dead code. Fix the issue anyway so that future code works properly when using function axspi_read_status. Fixes: a97c69ba4f30 ("net: ax88796c: ASIX AX88796C SPI Ethernet Adapter Driver") Signed-off-by: Nicolas Iooss Acked-by: Łukasz Stelmach Signed-off-by: David S. Miller --- drivers/net/ethernet/asix/ax88796c_spi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/asix/ax88796c_spi.c b/drivers/net/ethernet/asix/ax88796c_spi.c index 94df4f96d2be..0710e716d682 100644 --- a/drivers/net/ethernet/asix/ax88796c_spi.c +++ b/drivers/net/ethernet/asix/ax88796c_spi.c @@ -34,7 +34,7 @@ int axspi_read_status(struct axspi_data *ax_spi, struct spi_status *status) /* OP */ ax_spi->cmd_buf[0] = AX_SPICMD_READ_STATUS; - ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)&status, 3); + ret = spi_write_then_read(ax_spi->spi, ax_spi->cmd_buf, 1, (u8 *)status, 3); if (ret) dev_err(&ax_spi->spi->dev, "%s() failed: ret = %d\n", __func__, ret); else From f7a36b03a7320d1a3ba52f9305571eddad325a05 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 22 Nov 2021 04:32:01 -0500 Subject: [PATCH 32/94] vsock/virtio: suppress used length validation It turns out that vhost vsock violates the virtio spec by supplying the out buffer length in the used length (should just be the in length). As a result, attempts to validate the used length fail with: vmw_vsock_virtio_transport virtio1: tx: used len 44 is larger than in buflen 0 Since vsock driver does not use the length fox tx and validates the length before use for rx, it is safe to suppress the validation in virtio core for this driver. Reported-by: Halil Pasic Fixes: 939779f5152d ("virtio_ring: validate used buffer length") Cc: "Jason Wang" Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- net/vmw_vsock/virtio_transport.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 4f7c99dfd16c..3f82b2f1e6dd 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -731,6 +731,7 @@ static unsigned int features[] = { static struct virtio_driver virtio_vsock_driver = { .feature_table = features, .feature_table_size = ARRAY_SIZE(features), + .suppress_used_validation = true, .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, From 7a61432dc81375be06b02f0061247d3efbdfce3a Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Mon, 22 Nov 2021 20:32:53 +0800 Subject: [PATCH 33/94] net/smc: Avoid warning of possible recursive locking Possible recursive locking is detected by lockdep when SMC falls back to TCP. The corresponding warnings are as follows: ============================================ WARNING: possible recursive locking detected 5.16.0-rc1+ #18 Tainted: G E -------------------------------------------- wrk/1391 is trying to acquire lock: ffff975246c8e7d8 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0x109/0x250 [smc] but task is already holding lock: ffff975246c8f918 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0xfe/0x250 [smc] other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&ei->socket.wq.wait); lock(&ei->socket.wq.wait); *** DEADLOCK *** May be due to missing lock nesting notation 2 locks held by wrk/1391: #0: ffff975246040130 (sk_lock-AF_SMC){+.+.}-{0:0}, at: smc_connect+0x43/0x150 [smc] #1: ffff975246c8f918 (&ei->socket.wq.wait){..-.}-{3:3}, at: smc_switch_to_fallback+0xfe/0x250 [smc] stack backtrace: Call Trace: dump_stack_lvl+0x56/0x7b __lock_acquire+0x951/0x11f0 lock_acquire+0x27a/0x320 ? smc_switch_to_fallback+0x109/0x250 [smc] ? smc_switch_to_fallback+0xfe/0x250 [smc] _raw_spin_lock_irq+0x3b/0x80 ? smc_switch_to_fallback+0x109/0x250 [smc] smc_switch_to_fallback+0x109/0x250 [smc] smc_connect_fallback+0xe/0x30 [smc] __smc_connect+0xcf/0x1090 [smc] ? mark_held_locks+0x61/0x80 ? __local_bh_enable_ip+0x77/0xe0 ? lockdep_hardirqs_on+0xbf/0x130 ? smc_connect+0x12a/0x150 [smc] smc_connect+0x12a/0x150 [smc] __sys_connect+0x8a/0xc0 ? syscall_enter_from_user_mode+0x20/0x70 __x64_sys_connect+0x16/0x20 do_syscall_64+0x34/0x90 entry_SYSCALL_64_after_hwframe+0x44/0xae The nested locking in smc_switch_to_fallback() is considered to possibly cause a deadlock because smc_wait->lock and clc_wait->lock are the same type of lock. But actually it is safe so far since there is no other place trying to obtain smc_wait->lock when clc_wait->lock is held. So the patch replaces spin_lock() with spin_lock_nested() to avoid false report by lockdep. Link: https://lkml.org/lkml/2021/11/19/962 Fixes: 2153bd1e3d3d ("Transfer remaining wait queue entries during fallback") Reported-by: syzbot+e979d3597f48262cb4ee@syzkaller.appspotmail.com Signed-off-by: Wen Gu Acked-by: Tony Lu Signed-off-by: David S. Miller --- net/smc/af_smc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b61c802e3bf3..2692cba5a7b6 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -585,7 +585,7 @@ static void smc_switch_to_fallback(struct smc_sock *smc, int reason_code) * to clcsocket->wq during the fallback. */ spin_lock_irqsave(&smc_wait->lock, flags); - spin_lock(&clc_wait->lock); + spin_lock_nested(&clc_wait->lock, SINGLE_DEPTH_NESTING); list_splice_init(&smc_wait->head, &clc_wait->head); spin_unlock(&clc_wait->lock); spin_unlock_irqrestore(&smc_wait->lock, flags); From a68229ca634066975fff6d4780155bd2eb14a82a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Nov 2021 16:02:49 +0100 Subject: [PATCH 34/94] nixge: fix mac address error handling again The change to eth_hw_addr_set() caused gcc to correctly spot a bug that was introduced in an earlier incorrect fix: In file included from include/linux/etherdevice.h:21, from drivers/net/ethernet/ni/nixge.c:7: In function '__dev_addr_set', inlined from 'eth_hw_addr_set' at include/linux/etherdevice.h:319:2, inlined from 'nixge_probe' at drivers/net/ethernet/ni/nixge.c:1286:3: include/linux/netdevice.h:4648:9: error: 'memcpy' reading 6 bytes from a region of size 0 [-Werror=stringop-overread] 4648 | memcpy(dev->dev_addr, addr, len); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ As nixge_get_nvmem_address() can return either NULL or an error pointer, the NULL check is wrong, and we can end up reading from ERR_PTR(-EOPNOTSUPP), which gcc knows to contain zero readable bytes. Make the function always return an error pointer again but fix the check to match that. Fixes: f3956ebb3bf0 ("ethernet: use eth_hw_addr_set() instead of ether_addr_copy()") Fixes: abcd3d6fc640 ("net: nixge: Fix error path for obtaining mac address") Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ni/nixge.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index cfeb7620ae20..07a00dd9cfe0 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1209,7 +1209,7 @@ static void *nixge_get_nvmem_address(struct device *dev) cell = nvmem_cell_get(dev, "address"); if (IS_ERR(cell)) - return NULL; + return cell; mac = nvmem_cell_read(cell, &cell_size); nvmem_cell_put(cell); @@ -1282,7 +1282,7 @@ static int nixge_probe(struct platform_device *pdev) ndev->max_mtu = NIXGE_JUMBO_MTU; mac_addr = nixge_get_nvmem_address(&pdev->dev); - if (mac_addr && is_valid_ether_addr(mac_addr)) { + if (!IS_ERR(mac_addr) && is_valid_ether_addr(mac_addr)) { eth_hw_addr_set(ndev, mac_addr); kfree(mac_addr); } else { From 4177d5b017a71433d4760889b88f7a29e11fad10 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 22 Nov 2021 16:01:51 +0100 Subject: [PATCH 35/94] net, neigh: Fix crash in v6 module initialization error path When IPv6 module gets initialized, but it's hitting an error in inet6_init() where it then needs to undo all the prior initialization work, it also might do a call to ndisc_cleanup() which then calls neigh_table_clear(). In there is a missing timer cancellation of the table's managed_work item. The kernel test robot explicitly triggered this error path and caused a UAF crash similar to the below: [...] [ 28.833183][ C0] BUG: unable to handle page fault for address: f7a43288 [ 28.833973][ C0] #PF: supervisor write access in kernel mode [ 28.834660][ C0] #PF: error_code(0x0002) - not-present page [ 28.835319][ C0] *pde = 06b2c067 *pte = 00000000 [ 28.835853][ C0] Oops: 0002 [#1] PREEMPT [ 28.836367][ C0] CPU: 0 PID: 303 Comm: sed Not tainted 5.16.0-rc1-00233-g83ff5faa0d3b #7 [ 28.837293][ C0] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1 04/01/2014 [ 28.838338][ C0] EIP: __run_timers.constprop.0+0x82/0x440 [...] [ 28.845607][ C0] Call Trace: [ 28.845942][ C0] [ 28.846333][ C0] ? check_preemption_disabled.isra.0+0x2a/0x80 [ 28.846975][ C0] ? __this_cpu_preempt_check+0x8/0xa [ 28.847570][ C0] run_timer_softirq+0xd/0x40 [ 28.848050][ C0] __do_softirq+0xf5/0x576 [ 28.848547][ C0] ? __softirqentry_text_start+0x10/0x10 [ 28.849127][ C0] do_softirq_own_stack+0x2b/0x40 [ 28.849749][ C0] [ 28.850087][ C0] irq_exit_rcu+0x7d/0xc0 [ 28.850587][ C0] common_interrupt+0x2a/0x40 [ 28.851068][ C0] asm_common_interrupt+0x119/0x120 [...] Note that IPv6 module cannot be unloaded as per 8ce440610357 ("ipv6: do not allow ipv6 module to be removed") hence this can only be seen during module initialization error. Tested with kernel test robot's reproducer. Fixes: 7482e3841d52 ("net, neigh: Add NTF_MANAGED flag for managed neighbor entries") Reported-by: kernel test robot Signed-off-by: Daniel Borkmann Cc: Li Zhijian Signed-off-by: David S. Miller --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 47931c8be04b..72ba027c34cf 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1779,6 +1779,7 @@ int neigh_table_clear(int index, struct neigh_table *tbl) { neigh_tables[index] = NULL; /* It is not clean... Fix it to unload IPv6 module safely */ + cancel_delayed_work_sync(&tbl->managed_work); cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); From 8837cbbf854246f5f4d565f21e6baa945d37aded Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:12 +0200 Subject: [PATCH 36/94] net: ipv6: add fib6_nh_release_dsts stub We need a way to release a fib6_nh's per-cpu dsts when replacing nexthops otherwise we can end up with stale per-cpu dsts which hold net device references, so add a new IPv6 stub called fib6_nh_release_dsts. It must be used after an RCU grace period, so no new dsts can be created through a group's nexthop entry. Similar to fib6_nh_release it shouldn't be used if fib6_nh_init has failed so it doesn't need a dummy stub when IPv6 is not enabled. Fixes: 7bf4796dd099 ("nexthops: add support for replace") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 1 + include/net/ipv6_stubs.h | 1 + net/ipv6/af_inet6.c | 1 + net/ipv6/route.c | 19 +++++++++++++++++++ 4 files changed, 22 insertions(+) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index c412dde4d67d..83b8070d1cc9 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -485,6 +485,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index afbce90c4480..45e0339be6fa 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -47,6 +47,7 @@ struct ipv6_stub { struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void (*fib6_nh_release)(struct fib6_nh *fib6_nh); + void (*fib6_nh_release_dsts)(struct fib6_nh *fib6_nh); void (*fib6_update_sernum)(struct net *net, struct fib6_info *rt); int (*ip6_del_rt)(struct net *net, struct fib6_info *rt, bool skip_notify); void (*fib6_rt_update)(struct net *net, struct fib6_info *rt, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 0c4da163535a..dab4a047590b 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1026,6 +1026,7 @@ static const struct ipv6_stub ipv6_stub_impl = { .ip6_mtu_from_fib6 = ip6_mtu_from_fib6, .fib6_nh_init = fib6_nh_init, .fib6_nh_release = fib6_nh_release, + .fib6_nh_release_dsts = fib6_nh_release_dsts, .fib6_update_sernum = fib6_update_sernum_stub, .fib6_rt_update = fib6_rt_update, .ip6_del_rt = ip6_del_rt, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3ae25b8ffbd6..42d60c76d30a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3680,6 +3680,25 @@ void fib6_nh_release(struct fib6_nh *fib6_nh) fib_nh_common_release(&fib6_nh->nh_common); } +void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) +{ + int cpu; + + if (!fib6_nh->rt6i_pcpu) + return; + + for_each_possible_cpu(cpu) { + struct rt6_info *pcpu_rt, **ppcpu_rt; + + ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); + pcpu_rt = xchg(ppcpu_rt, NULL); + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + } + } +} + static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) From 1005f19b9357b81aa64e1decd08d6e332caaa284 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:13 +0200 Subject: [PATCH 37/94] net: nexthop: release IPv6 per-cpu dsts when replacing a nexthop group When replacing a nexthop group, we must release the IPv6 per-cpu dsts of the removed nexthop entries after an RCU grace period because they contain references to the nexthop's net device and to the fib6 info. With specific series of events[1] we can reach net device refcount imbalance which is unrecoverable. IPv4 is not affected because dsts don't take a refcount on the route. [1] $ ip nexthop list id 200 via 2002:db8::2 dev bridge.10 scope link onlink id 201 via 2002:db8::3 dev bridge scope link onlink id 203 group 201/200 $ ip -6 route 2001:db8::10 nhid 203 metric 1024 pref medium nexthop via 2002:db8::3 dev bridge weight 1 onlink nexthop via 2002:db8::2 dev bridge.10 weight 1 onlink Create rt6_info through one of the multipath legs, e.g.: $ taskset -a -c 1 ./pkt_inj 24 bridge.10 2001:db8::10 (pkt_inj is just a custom packet generator, nothing special) Then remove that leg from the group by replace (let's assume it is id 200 in this case): $ ip nexthop replace id 203 group 201 Now remove the IPv6 route: $ ip -6 route del 2001:db8::10/128 The route won't be really deleted due to the stale rt6_info holding 1 refcnt in nexthop id 200. At this point we have the following reference count dependency: (deleted) IPv6 route holds 1 reference over nhid 203 nh 203 holds 1 ref over id 201 nh 200 holds 1 ref over the net device and the route due to the stale rt6_info Now to create circular dependency between nh 200 and the IPv6 route, and also to get a reference over nh 200, restore nhid 200 in the group: $ ip nexthop replace id 203 group 201/200 And now we have a permanent circular dependncy because nhid 203 holds a reference over nh 200 and 201, but the route holds a ref over nh 203 and is deleted. To trigger the bug just delete the group (nhid 203): $ ip nexthop del id 203 It won't really be deleted due to the IPv6 route dependency, and now we have 2 unlinked and deleted objects that reference each other: the group and the IPv6 route. Since the group drops the reference it holds over its entries at free time (i.e. its own refcount needs to drop to 0) that will never happen and we get a permanent ref on them, since one of the entries holds a reference over the IPv6 route it will also never be released. At this point the dependencies are: (deleted, only unlinked) IPv6 route holds reference over group nh 203 (deleted, only unlinked) group nh 203 holds reference over nh 201 and 200 nh 200 holds 1 ref over the net device and the route due to the stale rt6_info This is the last point where it can be fixed by running traffic through nh 200, and specifically through the same CPU so the rt6_info (dst) will get released due to the IPv6 genid, that in turn will free the IPv6 route, which in turn will free the ref count over the group nh 203. If nh 200 is deleted at this point, it will never be released due to the ref from the unlinked group 203, it will only be unlinked: $ ip nexthop del id 200 $ ip nexthop $ Now we can never release that stale rt6_info, we have IPv6 route with ref over group nh 203, group nh 203 with ref over nh 200 and 201, nh 200 with rt6_info (dst) with ref over the net device and the IPv6 route. All of these objects are only unlinked, and cannot be released, thus they can't release their ref counts. Message from syslogd@dev at Nov 19 14:04:10 ... kernel:[73501.828730] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 Message from syslogd@dev at Nov 19 14:04:20 ... kernel:[73512.068811] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3 Fixes: 7bf4796dd099 ("nexthops: add support for replace") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 25 +++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 9e8100728d46..a69a9e76f99f 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1899,15 +1899,36 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, /* if any FIB entries reference this nexthop, any dst entries * need to be regenerated */ -static void nh_rt_cache_flush(struct net *net, struct nexthop *nh) +static void nh_rt_cache_flush(struct net *net, struct nexthop *nh, + struct nexthop *replaced_nh) { struct fib6_info *f6i; + struct nh_group *nhg; + int i; if (!list_empty(&nh->fi_list)) rt_cache_flush(net); list_for_each_entry(f6i, &nh->f6i_list, nh_list) ipv6_stub->fib6_update_sernum(net, f6i); + + /* if an IPv6 group was replaced, we have to release all old + * dsts to make sure all refcounts are released + */ + if (!replaced_nh->is_group) + return; + + /* new dsts must use only the new nexthop group */ + synchronize_net(); + + nhg = rtnl_dereference(replaced_nh->nh_grp); + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + struct nh_info *nhi = rtnl_dereference(nhge->nh->nh_info); + + if (nhi->family == AF_INET6) + ipv6_stub->fib6_nh_release_dsts(&nhi->fib6_nh); + } } static int replace_nexthop_grp(struct net *net, struct nexthop *old, @@ -2247,7 +2268,7 @@ static int replace_nexthop(struct net *net, struct nexthop *old, err = replace_nexthop_single(net, old, new, extack); if (!err) { - nh_rt_cache_flush(net, old); + nh_rt_cache_flush(net, old, new); __remove_nexthop(net, new, NULL); nexthop_put(new); From 02ebe49ab06111a887202959e4d58a3cf252b5ee Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Mon, 22 Nov 2021 17:15:14 +0200 Subject: [PATCH 38/94] selftests: net: fib_nexthops: add test for group refcount imbalance bug The new selftest runs a sequence which causes circular refcount dependency between deleted objects which cannot be released and results in a netdevice refcount imbalance. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- tools/testing/selftests/net/fib_nexthops.sh | 63 +++++++++++++++++++++ 1 file changed, 63 insertions(+) diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index b5a69ad191b0..d444ee6aa3cb 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -629,6 +629,66 @@ ipv6_fcnal() log_test $? 0 "Nexthops removed on admin down" } +ipv6_grp_refs() +{ + if [ ! -x "$(command -v mausezahn)" ]; then + echo "SKIP: Could not run test; need mausezahn tool" + return + fi + + run_cmd "$IP link set dev veth1 up" + run_cmd "$IP link add veth1.10 link veth1 up type vlan id 10" + run_cmd "$IP link add veth1.20 link veth1 up type vlan id 20" + run_cmd "$IP -6 addr add 2001:db8:91::1/64 dev veth1.10" + run_cmd "$IP -6 addr add 2001:db8:92::1/64 dev veth1.20" + run_cmd "$IP -6 neigh add 2001:db8:91::2 lladdr 00:11:22:33:44:55 dev veth1.10" + run_cmd "$IP -6 neigh add 2001:db8:92::2 lladdr 00:11:22:33:44:55 dev veth1.20" + run_cmd "$IP nexthop add id 100 via 2001:db8:91::2 dev veth1.10" + run_cmd "$IP nexthop add id 101 via 2001:db8:92::2 dev veth1.20" + run_cmd "$IP nexthop add id 102 group 100" + run_cmd "$IP route add 2001:db8:101::1/128 nhid 102" + + # create per-cpu dsts through nh 100 + run_cmd "ip netns exec me mausezahn -6 veth1.10 -B 2001:db8:101::1 -A 2001:db8:91::1 -c 5 -t tcp "dp=1-1023, flags=syn" >/dev/null 2>&1" + + # remove nh 100 from the group to delete the route potentially leaving + # a stale per-cpu dst which holds a reference to the nexthop's net + # device and to the IPv6 route + run_cmd "$IP nexthop replace id 102 group 101" + run_cmd "$IP route del 2001:db8:101::1/128" + + # add both nexthops to the group so a reference is taken on them + run_cmd "$IP nexthop replace id 102 group 100/101" + + # if the bug described in commit "net: nexthop: release IPv6 per-cpu + # dsts when replacing a nexthop group" exists at this point we have + # an unlinked IPv6 route (but not freed due to stale dst) with a + # reference over the group so we delete the group which will again + # only unlink it due to the route reference + run_cmd "$IP nexthop del id 102" + + # delete the nexthop with stale dst, since we have an unlinked + # group with a ref to it and an unlinked IPv6 route with ref to the + # group, the nh will only be unlinked and not freed so the stale dst + # remains forever and we get a net device refcount imbalance + run_cmd "$IP nexthop del id 100" + + # if a reference was lost this command will hang because the net device + # cannot be removed + timeout -s KILL 5 ip netns exec me ip link del veth1.10 >/dev/null 2>&1 + + # we can't cleanup if the command is hung trying to delete the netdev + if [ $? -eq 137 ]; then + return 1 + fi + + # cleanup + run_cmd "$IP link del veth1.20" + run_cmd "$IP nexthop flush" + + return 0 +} + ipv6_grp_fcnal() { local rc @@ -734,6 +794,9 @@ ipv6_grp_fcnal() run_cmd "$IP nexthop add id 108 group 31/24" log_test $? 2 "Nexthop group can not have a blackhole and another nexthop" + + ipv6_grp_refs + log_test $? 0 "Nexthop group replace refcounts" } ipv6_res_grp_fcnal() From 792b2086584f25d84081a526beee80d103c2a913 Mon Sep 17 00:00:00 2001 From: Maciej Fijalkowski Date: Tue, 26 Oct 2021 18:47:18 +0200 Subject: [PATCH 39/94] ice: fix vsi->txq_map sizing The approach of having XDP queue per CPU regardless of user's setting exposed a hidden bug that could occur in case when Rx queue count differ from Tx queue count. Currently vsi->txq_map's size is equal to the doubled vsi->alloc_txq, which is not correct due to the fact that XDP rings were previously based on the Rx queue count. Below splat can be seen when ethtool -L is used and XDP rings are configured: [ 682.875339] BUG: kernel NULL pointer dereference, address: 000000000000000f [ 682.883403] #PF: supervisor read access in kernel mode [ 682.889345] #PF: error_code(0x0000) - not-present page [ 682.895289] PGD 0 P4D 0 [ 682.898218] Oops: 0000 [#1] PREEMPT SMP PTI [ 682.903055] CPU: 42 PID: 2878 Comm: ethtool Tainted: G OE 5.15.0-rc5+ #1 [ 682.912214] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 [ 682.923380] RIP: 0010:devres_remove+0x44/0x130 [ 682.928527] Code: 49 89 f4 55 48 89 fd 4c 89 ff 53 48 83 ec 10 e8 92 b9 49 00 48 8b 9d a8 02 00 00 48 8d 8d a0 02 00 00 49 89 c2 48 39 cb 74 0f <4c> 3b 63 10 74 25 48 8b 5b 08 48 39 cb 75 f1 4c 89 ff 4c 89 d6 e8 [ 682.950237] RSP: 0018:ffffc90006a679f0 EFLAGS: 00010002 [ 682.956285] RAX: 0000000000000286 RBX: ffffffffffffffff RCX: ffff88908343a370 [ 682.964538] RDX: 0000000000000001 RSI: ffffffff81690d60 RDI: 0000000000000000 [ 682.972789] RBP: ffff88908343a0d0 R08: 0000000000000000 R09: 0000000000000000 [ 682.981040] R10: 0000000000000286 R11: 3fffffffffffffff R12: ffffffff81690d60 [ 682.989282] R13: ffffffff81690a00 R14: ffff8890819807a8 R15: ffff88908343a36c [ 682.997535] FS: 00007f08c7bfa740(0000) GS:ffff88a03fd00000(0000) knlGS:0000000000000000 [ 683.006910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 683.013557] CR2: 000000000000000f CR3: 0000001080a66003 CR4: 00000000003706e0 [ 683.021819] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 683.030075] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 683.038336] Call Trace: [ 683.041167] devm_kfree+0x33/0x50 [ 683.045004] ice_vsi_free_arrays+0x5e/0xc0 [ice] [ 683.050380] ice_vsi_rebuild+0x4c8/0x750 [ice] [ 683.055543] ice_vsi_recfg_qs+0x9a/0x110 [ice] [ 683.060697] ice_set_channels+0x14f/0x290 [ice] [ 683.065962] ethnl_set_channels+0x333/0x3f0 [ 683.070807] genl_family_rcv_msg_doit+0xea/0x150 [ 683.076152] genl_rcv_msg+0xde/0x1d0 [ 683.080289] ? channels_prepare_data+0x60/0x60 [ 683.085432] ? genl_get_cmd+0xd0/0xd0 [ 683.089667] netlink_rcv_skb+0x50/0xf0 [ 683.094006] genl_rcv+0x24/0x40 [ 683.097638] netlink_unicast+0x239/0x340 [ 683.102177] netlink_sendmsg+0x22e/0x470 [ 683.106717] sock_sendmsg+0x5e/0x60 [ 683.110756] __sys_sendto+0xee/0x150 [ 683.114894] ? handle_mm_fault+0xd0/0x2a0 [ 683.119535] ? do_user_addr_fault+0x1f3/0x690 [ 683.134173] __x64_sys_sendto+0x25/0x30 [ 683.148231] do_syscall_64+0x3b/0xc0 [ 683.161992] entry_SYSCALL_64_after_hwframe+0x44/0xae Fix this by taking into account the value that num_possible_cpus() yields in addition to vsi->alloc_txq instead of doubling the latter. Fixes: efc2214b6047 ("ice: Add support for XDP") Fixes: 22bf877e528f ("ice: introduce XDP_TX fallback path") Reviewed-by: Alexander Lobakin Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_lib.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 40562600a8cf..09a3297cd63c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -89,8 +89,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rx_rings) goto err_rings; - /* XDP will have vsi->alloc_txq Tx queues as well, so double the size */ - vsi->txq_map = devm_kcalloc(dev, (2 * vsi->alloc_txq), + /* txq_map needs to have enough space to track both Tx (stack) rings + * and XDP rings; at this point vsi->num_xdp_txq might not be set, + * so use num_possible_cpus() as we want to always provide XDP ring + * per CPU, regardless of queue count settings from user that might + * have come from ethtool's set_channels() callback; + */ + vsi->txq_map = devm_kcalloc(dev, (vsi->alloc_txq + num_possible_cpus()), sizeof(*vsi->txq_map), GFP_KERNEL); if (!vsi->txq_map) From f65ee535df775a13a1046c0a0b2d72db342f8a5b Mon Sep 17 00:00:00 2001 From: Marta Plantykow Date: Tue, 26 Oct 2021 18:47:19 +0200 Subject: [PATCH 40/94] ice: avoid bpf_prog refcount underflow Ice driver has the routines for managing XDP resources that are shared between ndo_bpf op and VSI rebuild flow. The latter takes place for example when user changes queue count on an interface via ethtool's set_channels(). There is an issue around the bpf_prog refcounting when VSI is being rebuilt - since ice_prepare_xdp_rings() is called with vsi->xdp_prog as an argument that is used later on by ice_vsi_assign_bpf_prog(), same bpf_prog pointers are swapped with each other. Then it is also interpreted as an 'old_prog' which in turn causes us to call bpf_prog_put on it that will decrement its refcount. Below splat can be interpreted in a way that due to zero refcount of a bpf_prog it is wiped out from the system while kernel still tries to refer to it: [ 481.069429] BUG: unable to handle page fault for address: ffffc9000640f038 [ 481.077390] #PF: supervisor read access in kernel mode [ 481.083335] #PF: error_code(0x0000) - not-present page [ 481.089276] PGD 100000067 P4D 100000067 PUD 1001cb067 PMD 106d2b067 PTE 0 [ 481.097141] Oops: 0000 [#1] PREEMPT SMP PTI [ 481.101980] CPU: 12 PID: 3339 Comm: sudo Tainted: G OE 5.15.0-rc5+ #1 [ 481.110840] Hardware name: Intel Corp. GRANTLEY/GRANTLEY, BIOS GRRFCRB1.86B.0276.D07.1605190235 05/19/2016 [ 481.122021] RIP: 0010:dev_xdp_prog_id+0x25/0x40 [ 481.127265] Code: 80 00 00 00 00 0f 1f 44 00 00 89 f6 48 c1 e6 04 48 01 fe 48 8b 86 98 08 00 00 48 85 c0 74 13 48 8b 50 18 31 c0 48 85 d2 74 07 <48> 8b 42 38 8b 40 20 c3 48 8b 96 90 08 00 00 eb e8 66 2e 0f 1f 84 [ 481.148991] RSP: 0018:ffffc90007b63868 EFLAGS: 00010286 [ 481.155034] RAX: 0000000000000000 RBX: ffff889080824000 RCX: 0000000000000000 [ 481.163278] RDX: ffffc9000640f000 RSI: ffff889080824010 RDI: ffff889080824000 [ 481.171527] RBP: ffff888107af7d00 R08: 0000000000000000 R09: ffff88810db5f6e0 [ 481.179776] R10: 0000000000000000 R11: ffff8890885b9988 R12: ffff88810db5f4bc [ 481.188026] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 481.196276] FS: 00007f5466d5bec0(0000) GS:ffff88903fb00000(0000) knlGS:0000000000000000 [ 481.205633] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 481.212279] CR2: ffffc9000640f038 CR3: 000000014429c006 CR4: 00000000003706e0 [ 481.220530] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 481.228771] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 481.237029] Call Trace: [ 481.239856] rtnl_fill_ifinfo+0x768/0x12e0 [ 481.244602] rtnl_dump_ifinfo+0x525/0x650 [ 481.249246] ? __alloc_skb+0xa5/0x280 [ 481.253484] netlink_dump+0x168/0x3c0 [ 481.257725] netlink_recvmsg+0x21e/0x3e0 [ 481.262263] ____sys_recvmsg+0x87/0x170 [ 481.266707] ? __might_fault+0x20/0x30 [ 481.271046] ? _copy_from_user+0x66/0xa0 [ 481.275591] ? iovec_from_user+0xf6/0x1c0 [ 481.280226] ___sys_recvmsg+0x82/0x100 [ 481.284566] ? sock_sendmsg+0x5e/0x60 [ 481.288791] ? __sys_sendto+0xee/0x150 [ 481.293129] __sys_recvmsg+0x56/0xa0 [ 481.297267] do_syscall_64+0x3b/0xc0 [ 481.301395] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 481.307238] RIP: 0033:0x7f5466f39617 [ 481.311373] Code: 0c 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb bd 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2f 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10 [ 481.342944] RSP: 002b:00007ffedc7f4308 EFLAGS: 00000246 ORIG_RAX: 000000000000002f [ 481.361783] RAX: ffffffffffffffda RBX: 00007ffedc7f5460 RCX: 00007f5466f39617 [ 481.380278] RDX: 0000000000000000 RSI: 00007ffedc7f5360 RDI: 0000000000000003 [ 481.398500] RBP: 00007ffedc7f53f0 R08: 0000000000000000 R09: 000055d556f04d50 [ 481.416463] R10: 0000000000000077 R11: 0000000000000246 R12: 00007ffedc7f5360 [ 481.434131] R13: 00007ffedc7f5350 R14: 00007ffedc7f5344 R15: 0000000000000e98 [ 481.451520] Modules linked in: ice(OE) af_packet binfmt_misc nls_iso8859_1 ipmi_ssif intel_rapl_msr intel_rapl_common x86_pkg_temp_thermal intel_powerclamp mxm_wmi mei_me coretemp mei ipmi_si ipmi_msghandler wmi acpi_pad acpi_power_meter ip_tables x_tables autofs4 crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel ahci crypto_simd cryptd libahci lpc_ich [last unloaded: ice] [ 481.528558] CR2: ffffc9000640f038 [ 481.542041] ---[ end trace d1f24c9ecf5b61c1 ]--- Fix this by only calling ice_vsi_assign_bpf_prog() inside ice_prepare_xdp_rings() when current vsi->xdp_prog pointer is NULL. This way set_channels() flow will not attempt to swap the vsi->xdp_prog pointers with itself. Also, sprinkle around some comments that provide a reasoning about correlation between driver and kernel in terms of bpf_prog refcount. Fixes: efc2214b6047 ("ice: Add support for XDP") Reviewed-by: Alexander Lobakin Signed-off-by: Marta Plantykow Co-developed-by: Maciej Fijalkowski Signed-off-by: Maciej Fijalkowski Tested-by: Kiran Bhandare Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice_main.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f099797f35e3..4d1fc48c9744 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2609,7 +2609,18 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog) ice_stat_str(status)); goto clear_xdp_rings; } - ice_vsi_assign_bpf_prog(vsi, prog); + + /* assign the prog only when it's not already present on VSI; + * this flow is a subject of both ethtool -L and ndo_bpf flows; + * VSI rebuild that happens under ethtool -L can expose us to + * the bpf_prog refcount issues as we would be swapping same + * bpf_prog pointers from vsi->xdp_prog and calling bpf_prog_put + * on it as it would be treated as an 'old_prog'; for ndo_bpf + * this is not harmful as dev_xdp_install bumps the refcount + * before calling the op exposed by the driver; + */ + if (!ice_is_xdp_ena_vsi(vsi)) + ice_vsi_assign_bpf_prog(vsi, prog); return 0; clear_xdp_rings: @@ -2785,6 +2796,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); } else { + /* safe to call even when prog == vsi->xdp_prog as + * dev_xdp_install in net/core/dev.c incremented prog's + * refcount so corresponding bpf_prog_put won't cause + * underflow + */ ice_vsi_assign_bpf_prog(vsi, prog); } From 16517829f2e02f096fb5ea9083d160381127faf3 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Tue, 23 Nov 2021 19:07:48 +0800 Subject: [PATCH 41/94] hamradio: fix macro redefine warning MIPS/IA64 define END as assembly function ending, which conflict with END definition in mkiss.c, just undef it at first Reported-by: lkp@intel.com Signed-off-by: Huang Pei Signed-off-by: David S. Miller --- drivers/net/hamradio/mkiss.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index e2b332b54f06..7da2bb8a443c 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -31,6 +31,8 @@ #define AX_MTU 236 +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP/KISS protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ From e5b40668e930979bd1e82c7ed7c9029db635f0e4 Mon Sep 17 00:00:00 2001 From: Huang Pei Date: Tue, 23 Nov 2021 19:07:49 +0800 Subject: [PATCH 42/94] slip: fix macro redefine warning MIPS/IA64 define END as assembly function ending, which conflict with END definition in slip.h, just undef it at first Reported-by: lkp@intel.com Signed-off-by: Huang Pei Signed-off-by: David S. Miller --- drivers/net/slip/slip.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/slip/slip.h b/drivers/net/slip/slip.h index c420e5948522..3d7f88b330c1 100644 --- a/drivers/net/slip/slip.h +++ b/drivers/net/slip/slip.h @@ -40,6 +40,8 @@ insmod -oslip_maxdev=nnn */ #define SL_MTU 296 /* 296; I am used to 600- FvK */ +/* some arch define END as assembly function ending, just undef it */ +#undef END /* SLIP protocol characters. */ #define END 0300 /* indicates end of frame */ #define ESC 0333 /* indicates byte stuffing */ From 1c743127cc54b112b155f434756bd4b5fa565a99 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 23 Nov 2021 12:27:19 +0200 Subject: [PATCH 43/94] net: nexthop: fix null pointer dereference when IPv6 is not enabled When we try to add an IPv6 nexthop and IPv6 is not enabled (!CONFIG_IPV6) we'll hit a NULL pointer dereference[1] in the error path of nh_create_ipv6() due to calling ipv6_stub->fib6_nh_release. The bug has been present since the beginning of IPv6 nexthop gateway support. Commit 1aefd3de7bc6 ("ipv6: Add fib6_nh_init and release to stubs") tells us that only fib6_nh_init has a dummy stub because fib6_nh_release should not be called if fib6_nh_init returns an error, but the commit below added a call to ipv6_stub->fib6_nh_release in its error path. To fix it return the dummy stub's -EAFNOSUPPORT error directly without calling ipv6_stub->fib6_nh_release in nh_create_ipv6()'s error path. [1] Output is a bit truncated, but it clearly shows the error. BUG: kernel NULL pointer dereference, address: 000000000000000000 #PF: supervisor instruction fetch in kernel modede #PF: error_code(0x0010) - not-present pagege PGD 0 P4D 0 Oops: 0010 [#1] PREEMPT SMP NOPTI CPU: 4 PID: 638 Comm: ip Kdump: loaded Not tainted 5.16.0-rc1+ #446 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-4.fc34 04/01/2014 RIP: 0010:0x0 Code: Unable to access opcode bytes at RIP 0xffffffffffffffd6. RSP: 0018:ffff888109f5b8f0 EFLAGS: 00010286^Ac RAX: 0000000000000000 RBX: ffff888109f5ba28 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8881008a2860 RBP: ffff888109f5b9d8 R08: 0000000000000000 R09: 0000000000000000 R10: ffff888109f5b978 R11: ffff888109f5b948 R12: 00000000ffffff9f R13: ffff8881008a2a80 R14: ffff8881008a2860 R15: ffff8881008a2840 FS: 00007f98de70f100(0000) GS:ffff88822bf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 0000000100efc000 CR4: 00000000000006e0 Call Trace: nh_create_ipv6+0xed/0x10c rtm_new_nexthop+0x6d7/0x13f3 ? check_preemption_disabled+0x3d/0xf2 ? lock_is_held_type+0xbe/0xfd rtnetlink_rcv_msg+0x23f/0x26a ? check_preemption_disabled+0x3d/0xf2 ? rtnl_calcit.isra.0+0x147/0x147 netlink_rcv_skb+0x61/0xb2 netlink_unicast+0x100/0x187 netlink_sendmsg+0x37f/0x3a0 ? netlink_unicast+0x187/0x187 sock_sendmsg_nosec+0x67/0x9b ____sys_sendmsg+0x19d/0x1f9 ? copy_msghdr_from_user+0x4c/0x5e ? rcu_read_lock_any_held+0x2a/0x78 ___sys_sendmsg+0x6c/0x8c ? asm_sysvec_apic_timer_interrupt+0x12/0x20 ? lockdep_hardirqs_on+0xd9/0x102 ? sockfd_lookup_light+0x69/0x99 __sys_sendmsg+0x50/0x6e do_syscall_64+0xcb/0xf2 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f98dea28914 Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b5 0f 1f 80 00 00 00 00 48 8d 05 e9 5d 0c 00 8b 00 85 c0 75 13 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 41 54 41 89 d4 55 48 89 f5 53 RSP: 002b:00007fff859f5e68 EFLAGS: 00000246 ORIG_RAX: 000000000000002e2e RAX: ffffffffffffffda RBX: 00000000619cb810 RCX: 00007f98dea28914 RDX: 0000000000000000 RSI: 00007fff859f5ed0 RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000001 R09: 0000000000000008 R10: fffffffffffffce6 R11: 0000000000000246 R12: 0000000000000001 R13: 000055c0097ae520 R14: 000055c0097957fd R15: 00007fff859f63a0 Modules linked in: bridge stp llc bonding virtio_net Cc: stable@vger.kernel.org Fixes: 53010f991a9f ("nexthop: Add support for IPv6 gateways") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index a69a9e76f99f..5dbd4b5505eb 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -2565,11 +2565,15 @@ static int nh_create_ipv6(struct net *net, struct nexthop *nh, /* sets nh_dev if successful */ err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL, extack); - if (err) + if (err) { + /* IPv6 is not enabled, don't call fib6_nh_release */ + if (err == -EAFNOSUPPORT) + goto out; ipv6_stub->fib6_nh_release(fib6_nh); - else + } else { nh->nh_flags = fib6_nh->fib_nh_flags; - + } +out: return err; } From 45c3ff7a9ac195135536057021c1d3ac664f3f62 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 23 Nov 2021 16:25:16 +0800 Subject: [PATCH 44/94] net/smc: Clean up local struct sock variables There remains some variables to replace with local struct sock. So clean them up all. Fixes: 3163c5071f25 ("net/smc: use local struct sock variables consistently") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Signed-off-by: David S. Miller --- net/smc/smc_close.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 0f9ffba07d26..9b235fbb089a 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -354,9 +354,9 @@ static void smc_close_passive_work(struct work_struct *work) if (rxflags->peer_conn_abort) { /* peer has not received all data */ smc_close_passive_abort_received(smc); - release_sock(&smc->sk); + release_sock(sk); cancel_delayed_work_sync(&conn->tx_work); - lock_sock(&smc->sk); + lock_sock(sk); goto wakeup; } From 606a63c9783a32a45bd2ef0eee393711d75b3284 Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Tue, 23 Nov 2021 16:25:18 +0800 Subject: [PATCH 45/94] net/smc: Ensure the active closing peer first closes clcsock The side that actively closed socket, it's clcsock doesn't enter TIME_WAIT state, but the passive side does it. It should show the same behavior as TCP sockets. Consider this, when client actively closes the socket, the clcsock in server enters TIME_WAIT state, which means the address is occupied and won't be reused before TIME_WAIT dismissing. If we restarted server, the service would be unavailable for a long time. To solve this issue, shutdown the clcsock in [A], perform the TCP active close progress first, before the passive closed side closing it. So that the actively closed side enters TIME_WAIT, not the passive one. Client | Server close() // client actively close | smc_release() | smc_close_active() // PEERCLOSEWAIT1 | smc_close_final() // abort or closed = 1| smc_cdc_get_slot_and_msg_send() | [A] | |smc_cdc_msg_recv_action() // ACTIVE | queue_work(smc_close_wq, &conn->close_work) | smc_close_passive_work() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_passive_abort_received() // only in abort | |close() // server recv zero, close | smc_release() // PROCESSABORT or APPCLOSEWAIT1 | smc_close_active() | smc_close_abort() or smc_close_final() // CLOSED | smc_cdc_get_slot_and_msg_send() // abort or closed = 1 smc_cdc_msg_recv_action() | smc_clcsock_release() queue_work(smc_close_wq, &conn->close_work) | sock_release(tcp) // actively close clc, enter TIME_WAIT smc_close_passive_work() // PEERCLOSEWAIT1 | smc_conn_free() smc_close_passive_abort_received() // CLOSED| smc_conn_free() | smc_clcsock_release() | sock_release(tcp) // passive close clc | Link: https://www.spinics.net/lists/netdev/msg780407.html Fixes: b38d732477e4 ("smc: socket closing and linkgroup cleanup") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Signed-off-by: David S. Miller --- net/smc/smc_close.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index 9b235fbb089a..3715d2f5ad55 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -228,6 +228,12 @@ int smc_close_active(struct smc_sock *smc) /* send close request */ rc = smc_close_final(conn); sk->sk_state = SMC_PEERCLOSEWAIT1; + + /* actively shutdown clcsock before peer close it, + * prevent peer from entering TIME_WAIT state. + */ + if (smc->clcsock && smc->clcsock->sk) + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } else { /* peer event has changed the state */ goto again; From ce4995bc6c8eec9685707e36c3f38aea3c8694fa Mon Sep 17 00:00:00 2001 From: Danielle Ratson Date: Tue, 23 Nov 2021 09:52:55 +0200 Subject: [PATCH 46/94] mlxsw: spectrum: Allow driver to load with old firmware versions The driver fails to load with old firmware versions that cannot report the maximum number of RIF MAC profiles [1]. Fix this by defaulting to a maximum of a single profile in such situations, as multiple profiles are not supported by old firmware versions. [1] mlxsw_spectrum 0000:03:00.0: cannot register bus device mlxsw_spectrum: probe of 0000:03:00.0 failed with error -5 Fixes: 1c375ffb2efab ("mlxsw: spectrum_router: Expose RIF MAC profiles to devlink resource") Signed-off-by: Danielle Ratson Reported-by: Vadim Pasternak Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 5925db386b1b..738ee3b0d3c3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3290,10 +3290,10 @@ mlxsw_sp_resources_rif_mac_profile_register(struct mlxsw_core *mlxsw_core) u8 max_rif_mac_profiles; if (!MLXSW_CORE_RES_VALID(mlxsw_core, MAX_RIF_MAC_PROFILES)) - return -EIO; - - max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, - MAX_RIF_MAC_PROFILES); + max_rif_mac_profiles = 1; + else + max_rif_mac_profiles = MLXSW_CORE_RES_GET(mlxsw_core, + MAX_RIF_MAC_PROFILES); devlink_resource_size_params_init(&size_params, max_rif_mac_profiles, max_rif_mac_profiles, 1, DEVLINK_RESOURCE_UNIT_ENTRY); From 63b08b1f6834bbb0b4f7783bf63b80c8c8e9a047 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Tue, 23 Nov 2021 09:52:56 +0200 Subject: [PATCH 47/94] mlxsw: spectrum: Protect driver from buggy firmware When processing port up/down events generated by the device's firmware, the driver protects itself from events reported for non-existent local ports, but not the CPU port (local port 0), which exists, but lacks a netdev. This can result in a NULL pointer dereference when calling netif_carrier_{on,off}(). Fix this by bailing early when processing an event reported for the CPU port. Problem was only observed when running on top of a buggy emulator. Fixes: 28b1987ef506 ("mlxsw: spectrum: Register CPU port with devlink") Signed-off-by: Amit Cohen Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 738ee3b0d3c3..03e5bad4e405 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2153,7 +2153,7 @@ static void mlxsw_sp_pude_event_func(const struct mlxsw_reg_info *reg, max_ports = mlxsw_core_max_ports(mlxsw_sp->core); local_port = mlxsw_reg_pude_local_port_get(pude_pl); - if (WARN_ON_ONCE(local_port >= max_ports)) + if (WARN_ON_ONCE(!local_port || local_port >= max_ports)) return; mlxsw_sp_port = mlxsw_sp->ports[local_port]; if (!mlxsw_sp_port) From 33a153100bb3459479bd95d3259c2915b53fefa8 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 18:15:54 -0600 Subject: [PATCH 48/94] net: ipa: directly disable ipa-setup-ready interrupt We currently maintain a "disabled" Boolean flag to determine whether the "ipa-setup-ready" SMP2P IRQ handler does anything. That flag must be accessed under protection of a mutex. Instead, disable the SMP2P interrupt when requested, which prevents the interrupt handler from ever being called. More importantly, it synchronizes a thread disabling the interrupt with the completion of the interrupt handler in case they run concurrently. Use the IPA setup_complete flag rather than the disabled flag in the handler to determine whether to ignore any interrupts arriving after the first. Rename the "disabled" flag to be "setup_disabled", to be specific about its purpose. Fixes: 530f9216a953 ("soc: qcom: ipa: AP/modem communications") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_smp2p.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index df7639c39d71..24bc112a072c 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @setup_ready_irq: IPA interrupt triggered by modem to signal GSI ready * @power_on: Whether IPA power is on * @notified: Whether modem has been notified of power state - * @disabled: Whether setup ready interrupt handling is disabled + * @setup_disabled: Whether setup ready interrupt handler is disabled * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ @@ -67,7 +67,7 @@ struct ipa_smp2p { u32 setup_ready_irq; bool power_on; bool notified; - bool disabled; + bool setup_disabled; struct mutex mutex; struct notifier_block panic_notifier; }; @@ -155,11 +155,9 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) struct device *dev; int ret; - mutex_lock(&smp2p->mutex); - - if (smp2p->disabled) - goto out_mutex_unlock; - smp2p->disabled = true; /* If any others arrive, ignore them */ + /* Ignore any (spurious) interrupts received after the first */ + if (smp2p->ipa->setup_complete) + return IRQ_HANDLED; /* Power needs to be active for setup */ dev = &smp2p->ipa->pdev->dev; @@ -176,8 +174,6 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) out_power_put: pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); -out_mutex_unlock: - mutex_unlock(&smp2p->mutex); return IRQ_HANDLED; } @@ -322,7 +318,10 @@ void ipa_smp2p_disable(struct ipa *ipa) mutex_lock(&smp2p->mutex); - smp2p->disabled = true; + if (!smp2p->setup_disabled) { + disable_irq(smp2p->setup_ready_irq); + smp2p->setup_disabled = true; + } mutex_unlock(&smp2p->mutex); } From 8afc7e471ad3c92a9c96adc62d1b67de77378bb6 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 18:15:55 -0600 Subject: [PATCH 49/94] net: ipa: separate disabling setup from modem stop The IPA setup_complete flag is set at the end of ipa_setup(), when the setup phase of initialization has completed successfully. This occurs as part of driver probe processing, or (if "modem-init" is specified in the DTS file) it is triggered by the "ipa-setup-ready" SMP2P interrupt generated by the modem. In the latter case, it's possible for driver shutdown (or remove) to begin while setup processing is underway, and this can't be allowed. The problem is that the setup_complete flag is not adequate to signal that setup is underway. If setup_complete is set, it will never be un-set, so that case is not a problem. But if setup_complete is false, there's a chance setup is underway. Because setup is triggered by an interrupt on a "modem-init" system, there is a simple way to ensure the value of setup_complete is safe to read. The threaded handler--if it is executing--will complete as part of a request to disable the "ipa-modem-ready" interrupt. This means that ipa_setup() (which is called from the handler) will run to completion if it was underway, or will never be called otherwise. The request to disable the "ipa-setup-ready" interrupt is currently made within ipa_modem_stop(). Instead, disable the interrupt outside that function in the two places it's called. In the case of ipa_remove(), this ensures the setup_complete flag is safe to read before we read it. Rename ipa_smp2p_disable() to be ipa_smp2p_irq_disable_setup(), to be more specific about its effect. Fixes: 530f9216a953 ("soc: qcom: ipa: AP/modem communications") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_main.c | 6 ++++++ drivers/net/ipa/ipa_modem.c | 6 +++--- drivers/net/ipa/ipa_smp2p.c | 2 +- drivers/net/ipa/ipa_smp2p.h | 7 +++---- 4 files changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index cdfa98a76e1f..a448ec198bee 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -28,6 +28,7 @@ #include "ipa_reg.h" #include "ipa_mem.h" #include "ipa_table.h" +#include "ipa_smp2p.h" #include "ipa_modem.h" #include "ipa_uc.h" #include "ipa_interrupt.h" @@ -801,6 +802,11 @@ static int ipa_remove(struct platform_device *pdev) struct device *dev = &pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup(). This + * also ensures a modem-initiated setup that's underway completes. + */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (WARN_ON(ret < 0)) goto out_power_put; diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index ad116bcc0580..d0ab4d70c303 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -339,9 +339,6 @@ int ipa_modem_stop(struct ipa *ipa) if (state != IPA_MODEM_STATE_RUNNING) return -EBUSY; - /* Prevent the modem from triggering a call to ipa_setup() */ - ipa_smp2p_disable(ipa); - /* Clean up the netdev and endpoints if it was started */ if (netdev) { struct ipa_priv *priv = netdev_priv(netdev); @@ -369,6 +366,9 @@ static void ipa_modem_crashed(struct ipa *ipa) struct device *dev = &ipa->pdev->dev; int ret; + /* Prevent the modem from triggering a call to ipa_setup() */ + ipa_smp2p_irq_disable_setup(ipa); + ret = pm_runtime_get_sync(dev); if (ret < 0) { dev_err(dev, "error %d getting power to handle crash\n", ret); diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 24bc112a072c..211233612039 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -309,7 +309,7 @@ void ipa_smp2p_exit(struct ipa *ipa) kfree(smp2p); } -void ipa_smp2p_disable(struct ipa *ipa) +void ipa_smp2p_irq_disable_setup(struct ipa *ipa) { struct ipa_smp2p *smp2p = ipa->smp2p; diff --git a/drivers/net/ipa/ipa_smp2p.h b/drivers/net/ipa/ipa_smp2p.h index 99a956789638..59cee31a7383 100644 --- a/drivers/net/ipa/ipa_smp2p.h +++ b/drivers/net/ipa/ipa_smp2p.h @@ -27,13 +27,12 @@ int ipa_smp2p_init(struct ipa *ipa, bool modem_init); void ipa_smp2p_exit(struct ipa *ipa); /** - * ipa_smp2p_disable() - Prevent "ipa-setup-ready" interrupt handling + * ipa_smp2p_irq_disable_setup() - Disable the "setup ready" interrupt * @ipa: IPA pointer * - * Prevent handling of the "setup ready" interrupt from the modem. - * This is used before initiating shutdown of the driver. + * Disable the "ipa-setup-ready" interrupt from the modem. */ -void ipa_smp2p_disable(struct ipa *ipa); +void ipa_smp2p_irq_disable_setup(struct ipa *ipa); /** * ipa_smp2p_notify_reset() - Reset modem notification state From c75a9ad43691de040bead75f1924928111571f9c Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Mon, 22 Nov 2021 22:35:33 +0100 Subject: [PATCH 50/94] r8169: fix incorrect mac address assignment The original changes brakes MAC address assignment on older chip versions (see bug report [0]), and it brakes random MAC assignment. is_valid_ether_addr() requires that its argument is word-aligned. Add the missing alignment to array mac_addr. [0] https://bugzilla.kernel.org/show_bug.cgi?id=215087 Fixes: 1c5d09d58748 ("ethernet: r8169: use eth_hw_addr_set()") Reported-by: Richard Herbert Tested-by: Richard Herbert Signed-off-by: Heiner Kallweit Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169_main.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bbe21db20417..86c44bc5f73f 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5217,8 +5217,8 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp) static void rtl_init_mac_address(struct rtl8169_private *tp) { + u8 mac_addr[ETH_ALEN] __aligned(2) = {}; struct net_device *dev = tp->dev; - u8 mac_addr[ETH_ALEN]; int rc; rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr); @@ -5233,7 +5233,8 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) if (is_valid_ether_addr(mac_addr)) goto done; - eth_hw_addr_random(dev); + eth_random_addr(mac_addr); + dev->addr_assign_type = NET_ADDR_RANDOM; dev_warn(tp_to_dev(tp), "can't read MAC address, setting random one\n"); done: eth_hw_addr_set(dev, mac_addr); From b82d71c0f84a2e5ccaaa7571dfd5c69e0e2cfb4a Mon Sep 17 00:00:00 2001 From: Zheyu Ma Date: Tue, 23 Nov 2021 02:21:50 +0000 Subject: [PATCH 51/94] net: chelsio: cxgb4vf: Fix an error code in cxgb4vf_pci_probe() During the process of driver probing, probe function should return < 0 for failure, otherwise kernel will treat value == 0 as success. Therefore, we should set err to -EINVAL when adapter->registered_device_map is NULL. Otherwise kernel will assume that driver has been successfully probed and will cause unexpected errors. Signed-off-by: Zheyu Ma Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 64479c464b4e..ae9cca768d74 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -3196,6 +3196,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, } if (adapter->registered_device_map == 0) { dev_err(&pdev->dev, "could not register any net devices\n"); + err = -EINVAL; goto err_disable_interrupts; } From a049a30fc27c1cb2e12889bbdbd463dbf750103a Mon Sep 17 00:00:00 2001 From: Martyn Welch Date: Mon, 22 Nov 2021 18:44:45 +0000 Subject: [PATCH 52/94] net: usb: Correct PHY handling of smsc95xx MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The smsc95xx driver is dropping phy speed settings and causing a stack trace at device unbind: [  536.379147] smsc95xx 2-1:1.0 eth1: unregister 'smsc95xx' usb-ci_hdrc.2-1, smsc95xx USB 2.0 Ethernet [  536.425029] ------------[ cut here ]------------ [  536.429650] WARNING: CPU: 0 PID: 439 at fs/kernfs/dir.c:1535 kernfs_remove_by_name_ns+0xb8/0xc0 [  536.438416] kernfs: can not remove 'attached_dev', no directory [  536.444363] Modules linked in: xts dm_crypt dm_mod atmel_mxt_ts smsc95xx usbnet [  536.451748] CPU: 0 PID: 439 Comm: sh Tainted: G        W         5.15.0 #1 [  536.458636] Hardware name: Freescale i.MX53 (Device Tree Support) [  536.464735] Backtrace:  [  536.467190] [<80b1c904>] (dump_backtrace) from [<80b1cb48>] (show_stack+0x20/0x24) [  536.474787]  r7:000005ff r6:8035b294 r5:600f0013 r4:80d8af78 [  536.480449] [<80b1cb28>] (show_stack) from [<80b1f764>] (dump_stack_lvl+0x48/0x54) [  536.488035] [<80b1f71c>] (dump_stack_lvl) from [<80b1f788>] (dump_stack+0x18/0x1c) [  536.495620]  r5:00000009 r4:80d9b820 [  536.499198] [<80b1f770>] (dump_stack) from [<80124fac>] (__warn+0xfc/0x114) [  536.506187] [<80124eb0>] (__warn) from [<80b1d21c>] (warn_slowpath_fmt+0xa8/0xdc) [  536.513688]  r7:000005ff r6:80d9b820 r5:80d9b8e0 r4:83744000 [  536.519349] [<80b1d178>] (warn_slowpath_fmt) from [<8035b294>] (kernfs_remove_by_name_ns+0xb8/0xc0) [  536.528416]  r9:00000001 r8:00000000 r7:824926dc r6:00000000 r5:80df6c2c r4:00000000 [  536.536162] [<8035b1dc>] (kernfs_remove_by_name_ns) from [<80b1f56c>] (sysfs_remove_link+0x4c/0x50) [  536.545225]  r6:7f00f02c r5:80df6c2c r4:83306400 [  536.549845] [<80b1f520>] (sysfs_remove_link) from [<806f9c8c>] (phy_detach+0xfc/0x11c) [  536.557780]  r5:82492000 r4:83306400 [  536.561359] [<806f9b90>] (phy_detach) from [<806f9cf8>] (phy_disconnect+0x4c/0x58) [  536.568943]  r7:824926dc r6:7f00f02c r5:82492580 r4:83306400 [  536.574604] [<806f9cac>] (phy_disconnect) from [<7f00a310>] (smsc95xx_disconnect_phy+0x30/0x38 [smsc95xx]) [  536.584290]  r5:82492580 r4:82492580 [  536.587868] [<7f00a2e0>] (smsc95xx_disconnect_phy [smsc95xx]) from [<7f001570>] (usbnet_stop+0x70/0x1a0 [usbnet]) [  536.598161]  r5:82492580 r4:82492000 [  536.601740] [<7f001500>] (usbnet_stop [usbnet]) from [<808baa70>] (__dev_close_many+0xb4/0x12c) [  536.610466]  r8:83744000 r7:00000000 r6:83744000 r5:83745b74 r4:82492000 [  536.617170] [<808ba9bc>] (__dev_close_many) from [<808bab78>] (dev_close_many+0x90/0x120) [  536.625365]  r7:00000001 r6:83745b74 r5:83745b8c r4:82492000 [  536.631026] [<808baae8>] (dev_close_many) from [<808bf408>] (unregister_netdevice_many+0x15c/0x704) [  536.640094]  r9:00000001 r8:81130b98 r7:83745b74 r6:83745bc4 r5:83745b8c r4:82492000 [  536.647840] [<808bf2ac>] (unregister_netdevice_many) from [<808bfa50>] (unregister_netdevice_queue+0xa0/0xe8) [  536.657775]  r10:8112bcc0 r9:83306c00 r8:83306c80 r7:8291e420 r6:83744000 r5:00000000 [  536.665608]  r4:82492000 [  536.668143] [<808bf9b0>] (unregister_netdevice_queue) from [<808bfac0>] (unregister_netdev+0x28/0x30) [  536.677381]  r6:7f01003c r5:82492000 r4:82492000 [  536.682000] [<808bfa98>] (unregister_netdev) from [<7f000b40>] (usbnet_disconnect+0x64/0xdc [usbnet]) [  536.691241]  r5:82492000 r4:82492580 [  536.694819] [<7f000adc>] (usbnet_disconnect [usbnet]) from [<8076b958>] (usb_unbind_interface+0x80/0x248) [  536.704406]  r5:7f01003c r4:83306c80 [  536.707984] [<8076b8d8>] (usb_unbind_interface) from [<8061765c>] (device_release_driver_internal+0x1c4/0x1cc) [  536.718005]  r10:8112bcc0 r9:80dff1dc r8:83306c80 r7:83744000 r6:7f01003c r5:00000000 [  536.725838]  r4:8291e420 [  536.728373] [<80617498>] (device_release_driver_internal) from [<80617684>] (device_release_driver+0x20/0x24) [  536.738302]  r7:83744000 r6:810d4f4c r5:8291e420 r4:8176ae30 [  536.743963] [<80617664>] (device_release_driver) from [<806156cc>] (bus_remove_device+0xf0/0x148) [  536.752858] [<806155dc>] (bus_remove_device) from [<80610018>] (device_del+0x198/0x41c) [  536.760880]  r7:83744000 r6:8116e2e4 r5:8291e464 r4:8291e420 [  536.766542] [<8060fe80>] (device_del) from [<80768fe8>] (usb_disable_device+0xcc/0x1e0) [  536.774576]  r10:8112bcc0 r9:80dff1dc r8:00000001 r7:8112bc48 r6:8291e400 r5:00000001 [  536.782410]  r4:83306c00 [  536.784945] [<80768f1c>] (usb_disable_device) from [<80769c30>] (usb_set_configuration+0x514/0x8dc) [  536.794011]  r10:00000000 r9:00000000 r8:832c3600 r7:00000004 r6:810d5688 r5:00000000 [  536.801844]  r4:83306c00 [  536.804379] [<8076971c>] (usb_set_configuration) from [<80775fac>] (usb_generic_driver_disconnect+0x34/0x38) [  536.814236]  r10:832c3610 r9:83745ef8 r8:832c3600 r7:00000004 r6:810d5688 r5:83306c00 [  536.822069]  r4:83306c00 [  536.824605] [<80775f78>] (usb_generic_driver_disconnect) from [<8076b850>] (usb_unbind_device+0x30/0x70) [  536.834100]  r5:83306c00 r4:810d5688 [  536.837678] [<8076b820>] (usb_unbind_device) from [<8061765c>] (device_release_driver_internal+0x1c4/0x1cc) [  536.847432]  r5:822fb480 r4:83306c80 [  536.851009] [<80617498>] (device_release_driver_internal) from [<806176a8>] (device_driver_detach+0x20/0x24) [  536.860853]  r7:00000004 r6:810d4f4c r5:810d5688 r4:83306c80 [  536.866515] [<80617688>] (device_driver_detach) from [<80614d98>] (unbind_store+0x70/0xe4) [  536.874793] [<80614d28>] (unbind_store) from [<80614118>] (drv_attr_store+0x30/0x3c) [  536.882554]  r7:00000000 r6:00000000 r5:83739200 r4:80614d28 [  536.888217] [<806140e8>] (drv_attr_store) from [<8035cb68>] (sysfs_kf_write+0x48/0x54) [  536.896154]  r5:83739200 r4:806140e8 [  536.899732] [<8035cb20>] (sysfs_kf_write) from [<8035be84>] (kernfs_fop_write_iter+0x11c/0x1d4) [  536.908446]  r5:83739200 r4:00000004 [  536.912024] [<8035bd68>] (kernfs_fop_write_iter) from [<802b87fc>] (vfs_write+0x258/0x3e4) [  536.920317]  r10:00000000 r9:83745f58 r8:83744000 r7:00000000 r6:00000004 r5:00000000 [  536.928151]  r4:82adacc0 [  536.930687] [<802b85a4>] (vfs_write) from [<802b8b0c>] (ksys_write+0x74/0xf4) [  536.937842]  r10:00000004 r9:007767a0 r8:83744000 r7:00000000 r6:00000000 r5:82adacc0 [  536.945676]  r4:82adacc0 [  536.948213] [<802b8a98>] (ksys_write) from [<802b8ba4>] (sys_write+0x18/0x1c) [  536.955367]  r10:00000004 r9:83744000 r8:80100244 r7:00000004 r6:76f47b58 r5:76fc0350 [  536.963200]  r4:00000004 [  536.965735] [<802b8b8c>] (sys_write) from [<80100060>] (ret_fast_syscall+0x0/0x48) [  536.973320] Exception stack(0x83745fa8 to 0x83745ff0) [  536.978383] 5fa0:                   00000004 76fc0350 00000001 007767a0 00000004 00000000 [  536.986569] 5fc0: 00000004 76fc0350 76f47b58 00000004 76f47c7c 76f48114 00000000 7e87991c [  536.994753] 5fe0: 00000498 7e879908 76e6dce8 76eca2e8 [  536.999922] ---[ end trace 9b835d809816b435 ]--- The driver should not be connecting and disconnecting the PHY when the device is opened and closed, it should be stopping and starting the PHY. The phy should be connected as part of binding and disconnected during unbinding. As this results in the PHY not being reset during open, link speed, etc. settings set prior to the link coming up are now not being lost. It is necessary for phy_stop() to only be called when the phydev still exists (resolving the above stack trace). When unbinding, ".unbind" will be called prior to ".stop", with phy_disconnect() already having called phy_stop() before the phydev becomes inaccessible. Signed-off-by: Martyn Welch Cc: Steve Glendinning Cc: UNGLinuxDriver@microchip.com Cc: "David S. Miller" Cc: Jakub Kicinski Cc: stable@kernel.org # v5.15 Signed-off-by: David S. Miller --- drivers/net/usb/smsc95xx.c | 55 ++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 29 deletions(-) diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 20fe4cd8f784..abe0149ed917 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1050,6 +1050,14 @@ static const struct net_device_ops smsc95xx_netdev_ops = { .ndo_set_features = smsc95xx_set_features, }; +static void smsc95xx_handle_link_change(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + + phy_print_status(net->phydev); + usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); +} + static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata; @@ -1154,6 +1162,17 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->min_mtu = ETH_MIN_MTU; dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + + ret = phy_connect_direct(dev->net, pdata->phydev, + &smsc95xx_handle_link_change, + PHY_INTERFACE_MODE_MII); + if (ret) { + netdev_err(dev->net, "can't attach PHY to %s\n", pdata->mdiobus->id); + goto unregister_mdio; + } + + phy_attached_info(dev->net->phydev); + return 0; unregister_mdio: @@ -1171,47 +1190,25 @@ static void smsc95xx_unbind(struct usbnet *dev, struct usb_interface *intf) { struct smsc95xx_priv *pdata = dev->driver_priv; + phy_disconnect(dev->net->phydev); mdiobus_unregister(pdata->mdiobus); mdiobus_free(pdata->mdiobus); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); } -static void smsc95xx_handle_link_change(struct net_device *net) -{ - struct usbnet *dev = netdev_priv(net); - - phy_print_status(net->phydev); - usbnet_defer_kevent(dev, EVENT_LINK_CHANGE); -} - static int smsc95xx_start_phy(struct usbnet *dev) { - struct smsc95xx_priv *pdata = dev->driver_priv; - struct net_device *net = dev->net; - int ret; + phy_start(dev->net->phydev); - ret = smsc95xx_reset(dev); - if (ret < 0) - return ret; - - ret = phy_connect_direct(net, pdata->phydev, - &smsc95xx_handle_link_change, - PHY_INTERFACE_MODE_MII); - if (ret) { - netdev_err(net, "can't attach PHY to %s\n", pdata->mdiobus->id); - return ret; - } - - phy_attached_info(net->phydev); - phy_start(net->phydev); return 0; } -static int smsc95xx_disconnect_phy(struct usbnet *dev) +static int smsc95xx_stop(struct usbnet *dev) { - phy_stop(dev->net->phydev); - phy_disconnect(dev->net->phydev); + if (dev->net->phydev) + phy_stop(dev->net->phydev); + return 0; } @@ -1966,7 +1963,7 @@ static const struct driver_info smsc95xx_info = { .unbind = smsc95xx_unbind, .link_reset = smsc95xx_link_reset, .reset = smsc95xx_start_phy, - .stop = smsc95xx_disconnect_phy, + .stop = smsc95xx_stop, .rx_fixup = smsc95xx_rx_fixup, .tx_fixup = smsc95xx_tx_fixup, .status = smsc95xx_status, From e4e9bfb7c93d7e78aa4ad7e1c411a8df15386062 Mon Sep 17 00:00:00 2001 From: Alex Elder Date: Mon, 22 Nov 2021 19:16:40 -0600 Subject: [PATCH 53/94] net: ipa: kill ipa_cmd_pipeline_clear() Calling ipa_cmd_pipeline_clear() after stopping the channel underlying the AP<-modem RX endpoint can lead to a deadlock. This occurs in the ->runtime_suspend device power operation for the IPA driver. While this callback is in progress, any other requests for power will block until the callback returns. Stopping the AP<-modem RX channel does not prevent the modem from sending another packet to this endpoint. If a packet arrives for an RX channel when the channel is stopped, an SUSPEND IPA interrupt condition will be pending. Handling an IPA interrupt requires power, so ipa_isr_thread() calls pm_runtime_get_sync() first thing. The problem occurs because a "pipeline clear" command will not complete while such a SUSPEND interrupt condition exists. So the SUSPEND IPA interrupt handler won't proceed until it gets power; that won't happen until the ->runtime_suspend callback (and its "pipeline clear" command) completes; and that can't happen while the SUSPEND interrupt condition exists. It turns out that in this case there is no need to use the "pipeline clear" command. There are scenarios in which clearing the pipeline is required while suspending, but those are not (yet) supported upstream. So a simple fix, avoiding the potential deadlock, is to stop calling ipa_cmd_pipeline_clear() in ipa_endpoint_suspend(). This removes the only user of ipa_cmd_pipeline_clear(), so get rid of that function. It can be restored again whenever it's needed. This is basically a manual revert along with an explanation for commit 6cb63ea6a39ea ("net: ipa: introduce ipa_cmd_tag_process()"). Fixes: 6cb63ea6a39ea ("net: ipa: introduce ipa_cmd_tag_process()") Signed-off-by: Alex Elder Signed-off-by: David S. Miller --- drivers/net/ipa/ipa_cmd.c | 16 ---------------- drivers/net/ipa/ipa_cmd.h | 6 ------ drivers/net/ipa/ipa_endpoint.c | 2 -- 3 files changed, 24 deletions(-) diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index cff51731195a..d57472ea077f 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -661,22 +661,6 @@ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa) wait_for_completion(&ipa->completion); } -void ipa_cmd_pipeline_clear(struct ipa *ipa) -{ - u32 count = ipa_cmd_pipeline_clear_count(); - struct gsi_trans *trans; - - trans = ipa_cmd_trans_alloc(ipa, count); - if (trans) { - ipa_cmd_pipeline_clear_add(trans); - gsi_trans_commit_wait(trans); - ipa_cmd_pipeline_clear_wait(ipa); - } else { - dev_err(&ipa->pdev->dev, - "error allocating %u entry tag transaction\n", count); - } -} - static struct ipa_cmd_info * ipa_cmd_info_alloc(struct ipa_endpoint *endpoint, u32 tre_count) { diff --git a/drivers/net/ipa/ipa_cmd.h b/drivers/net/ipa/ipa_cmd.h index 69cd085d427d..05ed7e42e184 100644 --- a/drivers/net/ipa/ipa_cmd.h +++ b/drivers/net/ipa/ipa_cmd.h @@ -163,12 +163,6 @@ u32 ipa_cmd_pipeline_clear_count(void); */ void ipa_cmd_pipeline_clear_wait(struct ipa *ipa); -/** - * ipa_cmd_pipeline_clear() - Clear the hardware pipeline - * @ipa: - IPA pointer - */ -void ipa_cmd_pipeline_clear(struct ipa *ipa); - /** * ipa_cmd_trans_alloc() - Allocate a transaction for the command TX endpoint * @ipa: IPA pointer diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index ef790fd0ab56..03a170993420 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1636,8 +1636,6 @@ void ipa_endpoint_suspend(struct ipa *ipa) if (ipa->modem_netdev) ipa_modem_suspend(ipa->modem_netdev); - ipa_cmd_pipeline_clear(ipa); - ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]); ipa_endpoint_suspend_one(ipa->name_map[IPA_ENDPOINT_AP_COMMAND_TX]); } From 7b1b62bc1e6a7b2fd5ee7a4296268eb291d23aeb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Beh=C3=BAn?= Date: Mon, 22 Nov 2021 21:08:34 +0100 Subject: [PATCH 54/94] net: marvell: mvpp2: increase MTU limit when XDP enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently mvpp2_xdp_setup won't allow attaching XDP program if mtu > ETH_DATA_LEN (1500). The mvpp2_change_mtu on the other hand checks whether MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE. These two checks are semantically different. Moreover this limit can be increased to MVPP2_MAX_RX_BUF_SIZE, since in mvpp2_rx we have xdp.data = data + MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM; xdp.frame_sz = PAGE_SIZE; Change the checks to check whether mtu > MVPP2_MAX_RX_BUF_SIZE Fixes: 07dd0a7aae7f ("mvpp2: add basic XDP support") Signed-off-by: Marek Behún Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 2b18d89d9756..ce486e16489c 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5017,11 +5017,13 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } + if (port->xdp_prog && mtu > MVPP2_MAX_RX_BUF_SIZE) { + netdev_err(dev, "Illegal MTU value %d (> %d) for XDP mode\n", + mtu, (int)MVPP2_MAX_RX_BUF_SIZE); + return -EINVAL; + } + if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) { - if (port->xdp_prog) { - netdev_err(dev, "Jumbo frames are not supported with XDP\n"); - return -EINVAL; - } if (priv->percpu_pools) { netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu); mvpp2_bm_switch_buffers(priv, false); @@ -5307,8 +5309,8 @@ static int mvpp2_xdp_setup(struct mvpp2_port *port, struct netdev_bpf *bpf) bool running = netif_running(port->dev); bool reset = !prog != !port->xdp_prog; - if (port->dev->mtu > ETH_DATA_LEN) { - NL_SET_ERR_MSG_MOD(bpf->extack, "XDP is not supported with jumbo frames enabled"); + if (port->dev->mtu > MVPP2_MAX_RX_BUF_SIZE) { + NL_SET_ERR_MSG_MOD(bpf->extack, "MTU too large for XDP"); return -EOPNOTSUPP; } From 710d5835b7ae17c517f5aeaff853c300959c87ec Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Nov 2021 10:48:10 -0800 Subject: [PATCH 55/94] tools: sync uapi/linux/if_link.h header This file has not been updated for a while. Sync it before BIG TCP patch series. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20211122184810.769159-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- tools/include/uapi/linux/if_link.h | 293 +++++++++++++++++++++++++---- 1 file changed, 259 insertions(+), 34 deletions(-) diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index b3610fdd1fee..eebd3894fe89 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -7,24 +7,23 @@ /* This struct should be in sync with struct rtnl_link_stats64 */ struct rtnl_link_stats { - __u32 rx_packets; /* total packets received */ - __u32 tx_packets; /* total packets transmitted */ - __u32 rx_bytes; /* total bytes received */ - __u32 tx_bytes; /* total bytes transmitted */ - __u32 rx_errors; /* bad packets received */ - __u32 tx_errors; /* packet transmit problems */ - __u32 rx_dropped; /* no space in linux buffers */ - __u32 tx_dropped; /* no space available in linux */ - __u32 multicast; /* multicast packets received */ + __u32 rx_packets; + __u32 tx_packets; + __u32 rx_bytes; + __u32 tx_bytes; + __u32 rx_errors; + __u32 tx_errors; + __u32 rx_dropped; + __u32 tx_dropped; + __u32 multicast; __u32 collisions; - /* detailed rx_errors: */ __u32 rx_length_errors; - __u32 rx_over_errors; /* receiver ring buff overflow */ - __u32 rx_crc_errors; /* recved pkt with crc error */ - __u32 rx_frame_errors; /* recv'd frame alignment error */ - __u32 rx_fifo_errors; /* recv'r fifo overrun */ - __u32 rx_missed_errors; /* receiver missed packet */ + __u32 rx_over_errors; + __u32 rx_crc_errors; + __u32 rx_frame_errors; + __u32 rx_fifo_errors; + __u32 rx_missed_errors; /* detailed tx_errors */ __u32 tx_aborted_errors; @@ -37,29 +36,201 @@ struct rtnl_link_stats { __u32 rx_compressed; __u32 tx_compressed; - __u32 rx_nohandler; /* dropped, no handler found */ + __u32 rx_nohandler; }; -/* The main device statistics structure */ +/** + * struct rtnl_link_stats64 - The main device statistics structure. + * + * @rx_packets: Number of good packets received by the interface. + * For hardware interfaces counts all good packets received from the device + * by the host, including packets which host had to drop at various stages + * of processing (even in the driver). + * + * @tx_packets: Number of packets successfully transmitted. + * For hardware interfaces counts packets which host was able to successfully + * hand over to the device, which does not necessarily mean that packets + * had been successfully transmitted out of the device, only that device + * acknowledged it copied them out of host memory. + * + * @rx_bytes: Number of good received bytes, corresponding to @rx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @tx_bytes: Number of good transmitted bytes, corresponding to @tx_packets. + * + * For IEEE 802.3 devices should count the length of Ethernet Frames + * excluding the FCS. + * + * @rx_errors: Total number of bad packets received on this network device. + * This counter must include events counted by @rx_length_errors, + * @rx_crc_errors, @rx_frame_errors and other errors not otherwise + * counted. + * + * @tx_errors: Total number of transmit problems. + * This counter must include events counter by @tx_aborted_errors, + * @tx_carrier_errors, @tx_fifo_errors, @tx_heartbeat_errors, + * @tx_window_errors and other errors not otherwise counted. + * + * @rx_dropped: Number of packets received but not processed, + * e.g. due to lack of resources or unsupported protocol. + * For hardware interfaces this counter may include packets discarded + * due to L2 address filtering but should not include packets dropped + * by the device due to buffer exhaustion which are counted separately in + * @rx_missed_errors (since procfs folds those two counters together). + * + * @tx_dropped: Number of packets dropped on their way to transmission, + * e.g. due to lack of resources. + * + * @multicast: Multicast packets received. + * For hardware interfaces this statistic is commonly calculated + * at the device level (unlike @rx_packets) and therefore may include + * packets which did not reach the host. + * + * For IEEE 802.3 devices this counter may be equivalent to: + * + * - 30.3.1.1.21 aMulticastFramesReceivedOK + * + * @collisions: Number of collisions during packet transmissions. + * + * @rx_length_errors: Number of packets dropped due to invalid length. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to a sum + * of the following attributes: + * + * - 30.3.1.1.23 aInRangeLengthErrors + * - 30.3.1.1.24 aOutOfRangeLengthField + * - 30.3.1.1.25 aFrameTooLongErrors + * + * @rx_over_errors: Receiver FIFO overflow event counter. + * + * Historically the count of overflow events. Such events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * The recommended interpretation for high speed interfaces is - + * number of packets dropped because they did not fit into buffers + * provided by the host, e.g. packets larger than MTU or next buffer + * in the ring was not available for a scatter transfer. + * + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * This statistics was historically used interchangeably with + * @rx_fifo_errors. + * + * This statistic corresponds to hardware events and is not commonly used + * on software devices. + * + * @rx_crc_errors: Number of packets received with a CRC error. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.6 aFrameCheckSequenceErrors + * + * @rx_frame_errors: Receiver frame alignment errors. + * Part of aggregate "frame" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter should be equivalent to: + * + * - 30.3.1.1.7 aAlignmentErrors + * + * @rx_fifo_errors: Receiver FIFO error counter. + * + * Historically the count of overflow events. Those events may be + * reported in the receive descriptors or via interrupts, and may + * not correspond one-to-one with dropped packets. + * + * This statistics was used interchangeably with @rx_over_errors. + * Not recommended for use in drivers for high speed interfaces. + * + * This statistic is used on software devices, e.g. to count software + * packet queue overflow (can) or sequencing errors (GRE). + * + * @rx_missed_errors: Count of packets missed by the host. + * Folded into the "drop" counter in `/proc/net/dev`. + * + * Counts number of packets dropped by the device due to lack + * of buffer space. This usually indicates that the host interface + * is slower than the network interface, or host is not keeping up + * with the receive packet rate. + * + * This statistic corresponds to hardware events and is not used + * on software devices. + * + * @tx_aborted_errors: + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * For IEEE 802.3 devices capable of half-duplex operation this counter + * must be equivalent to: + * + * - 30.3.1.1.11 aFramesAbortedDueToXSColls + * + * High speed interfaces may use this counter as a general device + * discard counter. + * + * @tx_carrier_errors: Number of frame transmission errors due to loss + * of carrier during transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.13 aCarrierSenseErrors + * + * @tx_fifo_errors: Number of frame transmission errors due to device + * FIFO underrun / underflow. This condition occurs when the device + * begins transmission of a frame but is unable to deliver the + * entire frame to the transmitter in time for transmission. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * @tx_heartbeat_errors: Number of Heartbeat / SQE Test errors for + * old half-duplex Ethernet. + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices possibly equivalent to: + * + * - 30.3.2.1.4 aSQETestErrors + * + * @tx_window_errors: Number of frame transmission errors due + * to late collisions (for Ethernet - after the first 64B of transmission). + * Part of aggregate "carrier" errors in `/proc/net/dev`. + * + * For IEEE 802.3 devices this counter must be equivalent to: + * + * - 30.3.1.1.10 aLateCollisions + * + * @rx_compressed: Number of correctly received compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @tx_compressed: Number of transmitted compressed packets. + * This counters is only meaningful for interfaces which support + * packet compression (e.g. CSLIP, PPP). + * + * @rx_nohandler: Number of packets received on the interface + * but dropped by the networking stack because the device is + * not designated to receive packets (e.g. backup link in a bond). + */ struct rtnl_link_stats64 { - __u64 rx_packets; /* total packets received */ - __u64 tx_packets; /* total packets transmitted */ - __u64 rx_bytes; /* total bytes received */ - __u64 tx_bytes; /* total bytes transmitted */ - __u64 rx_errors; /* bad packets received */ - __u64 tx_errors; /* packet transmit problems */ - __u64 rx_dropped; /* no space in linux buffers */ - __u64 tx_dropped; /* no space available in linux */ - __u64 multicast; /* multicast packets received */ + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; __u64 collisions; /* detailed rx_errors: */ __u64 rx_length_errors; - __u64 rx_over_errors; /* receiver ring buff overflow */ - __u64 rx_crc_errors; /* recved pkt with crc error */ - __u64 rx_frame_errors; /* recv'd frame alignment error */ - __u64 rx_fifo_errors; /* recv'r fifo overrun */ - __u64 rx_missed_errors; /* receiver missed packet */ + __u64 rx_over_errors; + __u64 rx_crc_errors; + __u64 rx_frame_errors; + __u64 rx_fifo_errors; + __u64 rx_missed_errors; /* detailed tx_errors */ __u64 tx_aborted_errors; @@ -71,8 +242,7 @@ struct rtnl_link_stats64 { /* for cslip etc */ __u64 rx_compressed; __u64 tx_compressed; - - __u64 rx_nohandler; /* dropped, no handler found */ + __u64 rx_nohandler; }; /* The struct should be in sync with struct ifmap */ @@ -170,12 +340,29 @@ enum { IFLA_PROP_LIST, IFLA_ALT_IFNAME, /* Alternative ifname */ IFLA_PERM_ADDRESS, + IFLA_PROTO_DOWN_REASON, + + /* device (sysfs) name as parent, used instead + * of IFLA_LINK where there's no parent netdev + */ + IFLA_PARENT_DEV_NAME, + IFLA_PARENT_DEV_BUS_NAME, + __IFLA_MAX }; #define IFLA_MAX (__IFLA_MAX - 1) +enum { + IFLA_PROTO_DOWN_REASON_UNSPEC, + IFLA_PROTO_DOWN_REASON_MASK, /* u32, mask for reason bits */ + IFLA_PROTO_DOWN_REASON_VALUE, /* u32, reason bit value */ + + __IFLA_PROTO_DOWN_REASON_CNT, + IFLA_PROTO_DOWN_REASON_MAX = __IFLA_PROTO_DOWN_REASON_CNT - 1 +}; + /* backwards compatibility for userspace */ #ifndef __KERNEL__ #define IFLA_RTA(r) ((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct ifinfomsg)))) @@ -293,6 +480,7 @@ enum { IFLA_BR_MCAST_MLD_VERSION, IFLA_BR_VLAN_STATS_PER_PORT, IFLA_BR_MULTI_BOOLOPT, + IFLA_BR_MCAST_QUERIER_STATE, __IFLA_BR_MAX, }; @@ -346,6 +534,8 @@ enum { IFLA_BRPORT_BACKUP_PORT, IFLA_BRPORT_MRP_RING_OPEN, IFLA_BRPORT_MRP_IN_OPEN, + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, + IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -433,6 +623,7 @@ enum macvlan_macaddr_mode { }; #define MACVLAN_FLAG_NOPROMISC 1 +#define MACVLAN_FLAG_NODST 2 /* skip dst macvlan if matching src macvlan */ /* VRF section */ enum { @@ -597,6 +788,18 @@ enum ifla_geneve_df { GENEVE_DF_MAX = __GENEVE_DF_END - 1, }; +/* Bareudp section */ +enum { + IFLA_BAREUDP_UNSPEC, + IFLA_BAREUDP_PORT, + IFLA_BAREUDP_ETHERTYPE, + IFLA_BAREUDP_SRCPORT_MIN, + IFLA_BAREUDP_MULTIPROTO_MODE, + __IFLA_BAREUDP_MAX +}; + +#define IFLA_BAREUDP_MAX (__IFLA_BAREUDP_MAX - 1) + /* PPP section */ enum { IFLA_PPP_UNSPEC, @@ -899,7 +1102,14 @@ enum { #define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1) -/* HSR section */ +/* HSR/PRP section, both uses same interface */ + +/* Different redundancy protocols for hsr device */ +enum { + HSR_PROTOCOL_HSR, + HSR_PROTOCOL_PRP, + HSR_PROTOCOL_MAX, +}; enum { IFLA_HSR_UNSPEC, @@ -909,6 +1119,9 @@ enum { IFLA_HSR_SUPERVISION_ADDR, /* Supervision frame multicast addr */ IFLA_HSR_SEQ_NR, IFLA_HSR_VERSION, /* HSR version */ + IFLA_HSR_PROTOCOL, /* Indicate different protocol than + * HSR. For example PRP. + */ __IFLA_HSR_MAX, }; @@ -1033,6 +1246,8 @@ enum { #define RMNET_FLAGS_INGRESS_MAP_COMMANDS (1U << 1) #define RMNET_FLAGS_INGRESS_MAP_CKSUMV4 (1U << 2) #define RMNET_FLAGS_EGRESS_MAP_CKSUMV4 (1U << 3) +#define RMNET_FLAGS_INGRESS_MAP_CKSUMV5 (1U << 4) +#define RMNET_FLAGS_EGRESS_MAP_CKSUMV5 (1U << 5) enum { IFLA_RMNET_UNSPEC, @@ -1048,4 +1263,14 @@ struct ifla_rmnet_flags { __u32 mask; }; +/* MCTP section */ + +enum { + IFLA_MCTP_UNSPEC, + IFLA_MCTP_NET, + __IFLA_MCTP_MAX, +}; + +#define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ From 0afefdced47d039bd418f5d67f594a60aea20871 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Mon, 22 Nov 2021 09:42:52 -0500 Subject: [PATCH 56/94] tc-testing: Add link for reviews with TC MAINTAINERS Signed-off-by: Jamal Hadi Salim Acked-by: Cong Wang Link: https://lore.kernel.org/r/20211122144252.25156-1-jhs@emojatatu.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 10c8ae3a8c73..2f1e78333883 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -18483,6 +18483,7 @@ F: include/uapi/linux/pkt_sched.h F: include/uapi/linux/tc_act/ F: include/uapi/linux/tc_ematch/ F: net/sched/ +F: tools/testing/selftests/tc-testing TC90522 MEDIA DRIVER M: Akihiro Tsukada From 619ca0d0108a5866cca7793bd7e19c5d7a30e750 Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 22 Nov 2021 09:18:06 -0800 Subject: [PATCH 57/94] selftests: add arp_ndisc_evict_nocarrier to Makefile This was previously added in selftests but never added to the Makefile Signed-off-by: James Prestwood Link: https://lore.kernel.org/r/20211122171806.3529401-1-prestwoj@gmail.com Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 7615f29831eb..9897fa9ab953 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += srv6_end_dt46_l3vpn_test.sh TEST_PROGS += srv6_end_dt4_l3vpn_test.sh TEST_PROGS += srv6_end_dt6_l3vpn_test.sh TEST_PROGS += vrf_strict_mode_test.sh +TEST_PROGS += arp_ndisc_evict_nocarrier.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest From ac132852147ad303a938dda318970dd1bbdfda4e Mon Sep 17 00:00:00 2001 From: Kumar Thangavel Date: Mon, 22 Nov 2021 22:08:18 +0530 Subject: [PATCH 58/94] net/ncsi : Add payload to be 32-bit aligned to fix dropped packets Update NC-SI command handler (both standard and OEM) to take into account of payload paddings in allocating skb (in case of payload size is not 32-bit aligned). The checksum field follows payload field, without taking payload padding into account can cause checksum being truncated, leading to dropped packets. Fixes: fb4ee67529ff ("net/ncsi: Add NCSI OEM command support") Signed-off-by: Kumar Thangavel Acked-by: Samuel Mendoza-Jonas Reviewed-by: Paul Menzel Signed-off-by: David S. Miller --- net/ncsi/ncsi-cmd.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index ba9ae482141b..dda8b76b7798 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -18,6 +18,8 @@ #include "internal.h" #include "ncsi-pkt.h" +static const int padding_bytes = 26; + u32 ncsi_calculate_checksum(unsigned char *data, int len) { u32 checksum = 0; @@ -213,12 +215,17 @@ static int ncsi_cmd_handler_oem(struct sk_buff *skb, { struct ncsi_cmd_oem_pkt *cmd; unsigned int len; + int payload; + /* NC-SI spec DSP_0222_1.2.0, section 8.2.2.2 + * requires payload to be padded with 0 to + * 32-bit boundary before the checksum field. + * Ensure the padding bytes are accounted for in + * skb allocation + */ + payload = ALIGN(nca->payload, 4); len = sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + len += max(payload, padding_bytes); cmd = skb_put_zero(skb, len); memcpy(&cmd->mfr_id, nca->data, nca->payload); @@ -272,6 +279,7 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) struct net_device *dev = nd->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; + int payload; int len = hlen + tlen; struct sk_buff *skb; struct ncsi_request *nr; @@ -281,14 +289,14 @@ static struct ncsi_request *ncsi_alloc_command(struct ncsi_cmd_arg *nca) return NULL; /* NCSI command packet has 16-bytes header, payload, 4 bytes checksum. + * Payload needs padding so that the checksum field following payload is + * aligned to 32-bit boundary. * The packet needs padding if its payload is less than 26 bytes to * meet 64 bytes minimal ethernet frame length. */ len += sizeof(struct ncsi_cmd_pkt_hdr) + 4; - if (nca->payload < 26) - len += 26; - else - len += nca->payload; + payload = ALIGN(nca->payload, 4); + len += max(payload, padding_bytes); /* Allocate skb */ skb = alloc_skb(len, GFP_ATOMIC); From 550b8e1d182cdc59bf99852503b9ce8a5ab2c34e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 23 Nov 2021 14:24:22 -0800 Subject: [PATCH 59/94] MAINTAINERS: Update B53 section to cover SF2 switch driver Update the B53 Ethernet switch section to contain drivers/net/dsa/bcm_sf2*. Reported-by: Russell King (Oracle) Signed-off-by: Florian Fainelli Acked-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20211123222422.3745485-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 2f1e78333883..384566f61192 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3570,13 +3570,14 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/broadcom/b44.* -BROADCOM B53 ETHERNET SWITCH DRIVER +BROADCOM B53/SF2 ETHERNET SWITCH DRIVER M: Florian Fainelli L: netdev@vger.kernel.org L: openwrt-devel@lists.openwrt.org (subscribers-only) S: Supported F: Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml F: drivers/net/dsa/b53/* +F: drivers/net/dsa/bcm_sf2* F: include/linux/dsa/brcm.h F: include/linux/platform_data/b53.h From 4e1fddc98d2585ddd4792b5e44433dcee7ece001 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 23 Nov 2021 12:25:35 -0800 Subject: [PATCH 60/94] tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows While testing BIG TCP patch series, I was expecting that TCP_RR workloads with 80KB requests/answers would send one 80KB TSO packet, then being received as a single GRO packet. It turns out this was not happening, and the root cause was that cubic Hystart ACK train was triggering after a few (2 or 3) rounds of RPC. Hystart was wrongly setting CWND/SSTHRESH to 30, while my RPC needed a budget of ~20 segments. Ideally these TCP_RR flows should not exit slow start. Cubic Hystart should reset itself at each round, instead of assuming every TCP flow is a bulk one. Note that even after this patch, Hystart can still trigger, depending on scheduling artifacts, but at a higher CWND/SSTHRESH threshold, keeping optimal TSO packet sizes. Tested: ip link set dev eth0 gro_ipv6_max_size 131072 gso_ipv6_max_size 131072 nstat -n; netperf -H ... -t TCP_RR -l 5 -- -r 80000,80000 -K cubic; nstat|egrep "Ip6InReceives|Hystart|Ip6OutRequests" Before: 8605 Ip6InReceives 87541 0.0 Ip6OutRequests 129496 0.0 TcpExtTCPHystartTrainDetect 1 0.0 TcpExtTCPHystartTrainCwnd 30 0.0 After: 8760 Ip6InReceives 88514 0.0 Ip6OutRequests 87975 0.0 Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3") Co-developed-by: Neal Cardwell Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Yuchung Cheng Cc: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20211123202535.1843771-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_cubic.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5e9d9c51164c..e07837e23b3f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -330,8 +330,6 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; if (tcp_in_slow_start(tp)) { - if (hystart && after(ack, ca->end_seq)) - bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); if (!acked) return; @@ -391,6 +389,9 @@ static void hystart_update(struct sock *sk, u32 delay) struct bictcp *ca = inet_csk_ca(sk); u32 threshold; + if (after(tp->snd_una, ca->end_seq)) + bictcp_hystart_reset(sk); + if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); From ddb826c2c92d461f290a7bab89e7c28696191875 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Wed, 24 Nov 2021 08:16:25 +0100 Subject: [PATCH 61/94] lan743x: fix deadlock in lan743x_phy_link_status_change() Usage of phy_ethtool_get_link_ksettings() in the link status change handler isn't needed, and in combination with the referenced change it results in a deadlock. Simply remove the call and replace it with direct access to phydev->speed. The duplex argument of lan743x_phy_update_flowcontrol() isn't used and can be removed. Fixes: c10a485c3de5 ("phy: phy_ethtool_ksettings_get: Lock the phy for consistency") Reported-by: Alessandro B Maurici Tested-by: Alessandro B Maurici Signed-off-by: Heiner Kallweit Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/40e27f76-0ba3-dcef-ee32-a78b9df38b0f@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/microchip/lan743x_main.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 4fc97823bc84..7d7647481f70 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -914,8 +914,7 @@ static int lan743x_phy_reset(struct lan743x_adapter *adapter) } static void lan743x_phy_update_flowcontrol(struct lan743x_adapter *adapter, - u8 duplex, u16 local_adv, - u16 remote_adv) + u16 local_adv, u16 remote_adv) { struct lan743x_phy *phy = &adapter->phy; u8 cap; @@ -943,7 +942,6 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) phy_print_status(phydev); if (phydev->state == PHY_RUNNING) { - struct ethtool_link_ksettings ksettings; int remote_advertisement = 0; int local_advertisement = 0; @@ -980,18 +978,14 @@ static void lan743x_phy_link_status_change(struct net_device *netdev) } lan743x_csr_write(adapter, MAC_CR, data); - memset(&ksettings, 0, sizeof(ksettings)); - phy_ethtool_get_link_ksettings(netdev, &ksettings); local_advertisement = linkmode_adv_to_mii_adv_t(phydev->advertising); remote_advertisement = linkmode_adv_to_mii_adv_t(phydev->lp_advertising); - lan743x_phy_update_flowcontrol(adapter, - ksettings.base.duplex, - local_advertisement, + lan743x_phy_update_flowcontrol(adapter, local_advertisement, remote_advertisement); - lan743x_ptp_update_latency(adapter, ksettings.base.speed); + lan743x_ptp_update_latency(adapter, phydev->speed); } } From 80662f4fd4771bc9c7cc4abdfbe866ebd1179621 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 23 Nov 2021 16:44:02 +0100 Subject: [PATCH 62/94] net: phylink: Force link down and retrigger resolve on interface change MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On PHY state change the phylink_resolve() function can read stale information from the MAC and report incorrect link speed and duplex to the kernel message log. Example with a Marvell 88X3310 PHY connected to a SerDes port on Marvell 88E6393X switch: - PHY driver triggers state change due to PHY interface mode being changed from 10gbase-r to 2500base-x due to copper change in speed from 10Gbps to 2.5Gbps, but the PHY itself either hasn't yet changed its interface to the host, or the interrupt about loss of SerDes link hadn't arrived yet (there can be a delay of several milliseconds for this), so we still think that the 10gbase-r mode is up - phylink_resolve() - phylink_mac_pcs_get_state() - this fills in speed=10g link=up - interface mode is updated to 2500base-x but speed is left at 10Gbps - phylink_major_config() - interface is changed to 2500base-x - phylink_link_up() - mv88e6xxx_mac_link_up() - .port_set_speed_duplex() - speed is set to 10Gbps - reports "Link is Up - 10Gbps/Full" to dmesg Afterwards when the interrupt finally arrives for mv88e6xxx, another resolve is forced in which we get the correct speed from phylink_mac_pcs_get_state(), but since the interface is not being changed anymore, we don't call phylink_major_config() but only phylink_mac_config(), which does not set speed/duplex anymore. To fix this, we need to force the link down and trigger another resolve on PHY interface change event. Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: Russell King (Oracle) Signed-off-by: Marek Behún Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ad7397b8119..708d2a984621 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -710,6 +710,7 @@ static void phylink_resolve(struct work_struct *w) struct phylink_link_state link_state; struct net_device *ndev = pl->netdev; bool mac_config = false; + bool retrigger = false; bool cur_link_state; mutex_lock(&pl->state_mutex); @@ -723,6 +724,7 @@ static void phylink_resolve(struct work_struct *w) link_state.link = false; } else if (pl->mac_link_dropped) { link_state.link = false; + retrigger = true; } else { switch (pl->cur_link_an_mode) { case MLO_AN_PHY: @@ -747,6 +749,15 @@ static void phylink_resolve(struct work_struct *w) /* Only update if the PHY link is up */ if (pl->phydev && pl->phy_state.link) { + /* If the interface has changed, force a + * link down event if the link isn't already + * down, and re-resolve. + */ + if (link_state.interface != + pl->phy_state.interface) { + retrigger = true; + link_state.link = false; + } link_state.interface = pl->phy_state.interface; /* If we have a PHY, we need to update with @@ -789,7 +800,7 @@ static void phylink_resolve(struct work_struct *w) else phylink_link_up(pl, link_state); } - if (!link_state.link && pl->mac_link_dropped) { + if (!link_state.link && retrigger) { pl->mac_link_dropped = false; queue_work(system_power_efficient_wq, &pl->resolve); } From dbae3388ea9ca33bd1d5eabc3b0ef17e69c74677 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 23 Nov 2021 16:44:03 +0100 Subject: [PATCH 63/94] net: phylink: Force retrigger in case of latched link-fail indicator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On mv88e6xxx 1G/2.5G PCS, the SerDes register 4.2001.2 has the following description: This register bit indicates when link was lost since the last read. For the current link status, read this register back-to-back. Thus to get current link state, we need to read the register twice. But doing that in the link change interrupt handler would lead to potentially ignoring link down events, which we really want to avoid. Thus this needs to be solved in phylink's resolve, by retriggering another resolve in the event when PCS reports link down and previous link was up, and by re-reading PCS state if the previous link was down. The wrong value is read when phylink requests change from sgmii to 2500base-x mode, and link won't come up. This fixes the bug. Fixes: 9525ae83959b ("phylink: add phylink infrastructure") Signed-off-by: Russell King (Oracle) Signed-off-by: Marek Behún Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 708d2a984621..5904546acae6 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -741,6 +741,19 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_INBAND: phylink_mac_pcs_get_state(pl, &link_state); + /* The PCS may have a latching link-fail indicator. + * If the link was up, bring the link down and + * re-trigger the resolve. Otherwise, re-read the + * PCS state to get the current status of the link. + */ + if (!link_state.link) { + if (cur_link_state) + retrigger = true; + else + phylink_mac_pcs_get_state(pl, + &link_state); + } + /* If we have a phy, the "up" state is the union of * both the PHY and the MAC */ From 587acad41f1bc48e16f42bb2aca63bf323380be8 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Wed, 24 Nov 2021 13:32:37 +0100 Subject: [PATCH 64/94] net/smc: Fix NULL pointer dereferencing in smc_vlan_by_tcpsk() Coverity reports a possible NULL dereferencing problem: in smc_vlan_by_tcpsk(): 6. returned_null: netdev_lower_get_next returns NULL (checked 29 out of 30 times). 7. var_assigned: Assigning: ndev = NULL return value from netdev_lower_get_next. 1623 ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); CID 1468509 (#1 of 1): Dereference null return value (NULL_RETURNS) 8. dereference: Dereferencing a pointer that might be NULL ndev when calling is_vlan_dev. 1624 if (is_vlan_dev(ndev)) { Remove the manual implementation and use netdev_walk_all_lower_dev() to iterate over the lower devices. While on it remove an obsolete function parameter comment. Fixes: cb9d43f67754 ("net/smc: determine vlan_id of stacked net_device") Suggested-by: Julian Wiedmann Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/smc_core.c | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 25ebd30feecd..bb52c8b5f148 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1672,14 +1672,26 @@ static void smc_link_down_work(struct work_struct *work) mutex_unlock(&lgr->llc_conf_mutex); } -/* Determine vlan of internal TCP socket. - * @vlan_id: address to store the determined vlan id into - */ +static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) +{ + unsigned short *vlan_id = (unsigned short *)priv->data; + + if (is_vlan_dev(lower_dev)) { + *vlan_id = vlan_dev_vlan_id(lower_dev); + return 1; + } + + return 0; +} + +/* Determine vlan of internal TCP socket. */ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(clcsock->sk); + struct netdev_nested_priv priv; struct net_device *ndev; - int i, nest_lvl, rc = 0; + int rc = 0; ini->vlan_id = 0; if (!dst) { @@ -1697,20 +1709,9 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini) goto out_rel; } + priv.data = (void *)&ini->vlan_id; rtnl_lock(); - nest_lvl = ndev->lower_level; - for (i = 0; i < nest_lvl; i++) { - struct list_head *lower = &ndev->adj_list.lower; - - if (list_empty(lower)) - break; - lower = lower->next; - ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); - if (is_vlan_dev(ndev)) { - ini->vlan_id = vlan_dev_vlan_id(ndev); - break; - } - } + netdev_walk_all_lower_dev(ndev, smc_vlan_by_tcpsk_walk, &priv); rtnl_unlock(); out_rel: From 9ebb0c4b27a6158303b791b5b91e66d7665ee30e Mon Sep 17 00:00:00 2001 From: Guo DaXing Date: Wed, 24 Nov 2021 13:32:38 +0100 Subject: [PATCH 65/94] net/smc: Fix loop in smc_listen The kernel_listen function in smc_listen will fail when all the available ports are occupied. At this point smc->clcsock->sk->sk_data_ready has been changed to smc_clcsock_data_ready. When we call smc_listen again, now both smc->clcsock->sk->sk_data_ready and smc->clcsk_data_ready point to the smc_clcsock_data_ready function. The smc_clcsock_data_ready() function calls lsmc->clcsk_data_ready which now points to itself resulting in an infinite loop. This patch restores smc->clcsock->sk->sk_data_ready with the old value. Fixes: a60a2b1e0af1 ("net/smc: reduce active tcp_listen workers") Signed-off-by: Guo DaXing Acked-by: Tony Lu Signed-off-by: Karsten Graul Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 2692cba5a7b6..4b62c925a13e 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2134,8 +2134,10 @@ static int smc_listen(struct socket *sock, int backlog) smc->clcsock->sk->sk_user_data = (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY); rc = kernel_listen(smc->clcsock, backlog); - if (rc) + if (rc) { + smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready; goto out; + } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = SMC_LISTEN; From eaeace60778e524a2820d0c0ad60bf80289e292c Mon Sep 17 00:00:00 2001 From: Jesse Brandeburg Date: Tue, 23 Nov 2021 12:40:00 -0800 Subject: [PATCH 66/94] igb: fix netpoll exit with traffic Oleksandr brought a bug report where netpoll causes trace messages in the log on igb. Danielle brought this back up as still occurring, so we'll try again. [22038.710800] ------------[ cut here ]------------ [22038.710801] igb_poll+0x0/0x1440 [igb] exceeded budget in poll [22038.710802] WARNING: CPU: 12 PID: 40362 at net/core/netpoll.c:155 netpoll_poll_dev+0x18a/0x1a0 As Alex suggested, change the driver to return work_done at the exit of napi_poll, which should be safe to do in this driver because it is not polling multiple queues in this single napi context (multiple queues attached to one MSI-X vector). Several other drivers contain the same simple sequence, so I hope this will not create new problems. Fixes: 16eb8815c235 ("igb: Refactor clean_rx_irq to reduce overhead and improve performance") Reported-by: Oleksandr Natalenko Reported-by: Danielle Ratson Suggested-by: Alexander Duyck Signed-off-by: Jesse Brandeburg Tested-by: Oleksandr Natalenko Tested-by: Danielle Ratson Link: https://lore.kernel.org/r/20211123204000.1597971-1-jesse.brandeburg@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 836be0d3b291..fd54d3ef890b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8026,7 +8026,7 @@ static int igb_poll(struct napi_struct *napi, int budget) if (likely(napi_complete_done(napi, work_done))) igb_ring_irq_enable(q_vector); - return min(work_done, budget - 1); + return work_done; } /** From 9dbe33cf371bd70330858370bdbc35c7668f00c3 Mon Sep 17 00:00:00 2001 From: Dylan Hung Date: Thu, 25 Nov 2021 10:44:32 +0800 Subject: [PATCH 67/94] mdio: aspeed: Fix "Link is Down" issue The issue happened randomly in runtime. The message "Link is Down" is popped but soon it recovered to "Link is Up". The "Link is Down" results from the incorrect read data for reading the PHY register via MDIO bus. The correct sequence for reading the data shall be: 1. fire the command 2. wait for command done (this step was missing) 3. wait for data idle 4. read data from data register Cc: stable@vger.kernel.org Fixes: f160e99462c6 ("net: phy: Add mdio-aspeed") Reviewed-by: Joel Stanley Signed-off-by: Dylan Hung Reviewed-by: Andrew Lunn Reviewed-by: Russell King (Oracle) Link: https://lore.kernel.org/r/20211125024432.15809-1-dylan_hung@aspeedtech.com Signed-off-by: Jakub Kicinski --- drivers/net/mdio/mdio-aspeed.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/net/mdio/mdio-aspeed.c b/drivers/net/mdio/mdio-aspeed.c index cad820568f75..966c3b4ad59d 100644 --- a/drivers/net/mdio/mdio-aspeed.c +++ b/drivers/net/mdio/mdio-aspeed.c @@ -61,6 +61,13 @@ static int aspeed_mdio_read(struct mii_bus *bus, int addr, int regnum) iowrite32(ctrl, ctx->base + ASPEED_MDIO_CTRL); + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_CTRL, ctrl, + !(ctrl & ASPEED_MDIO_CTRL_FIRE), + ASPEED_MDIO_INTERVAL_US, + ASPEED_MDIO_TIMEOUT_US); + if (rc < 0) + return rc; + rc = readl_poll_timeout(ctx->base + ASPEED_MDIO_DATA, data, data & ASPEED_MDIO_DATA_IDLE, ASPEED_MDIO_INTERVAL_US, From a125f91fe783a79c9d990fe6e28a3da8d9a0857f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:49 -0800 Subject: [PATCH 68/94] selftests: tls: add helper for creating sock pairs We have the same code 3 times, about to add a fourth copy. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 128 +++++++----------------------- 1 file changed, 29 insertions(+), 99 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index e61fc4c32ba2..8fb7cf8c4bfb 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -78,26 +78,21 @@ static void memrnd(void *s, size_t n) *byte++ = rand(); } -FIXTURE(tls_basic) -{ - int fd, cfd; - bool notls; -}; - -FIXTURE_SETUP(tls_basic) +static void ulp_sock_pair(struct __test_metadata *_metadata, + int *fd, int *cfd, bool *notls) { struct sockaddr_in addr; socklen_t len; int sfd, ret; - self->notls = false; + *notls = false; len = sizeof(addr); addr.sin_family = AF_INET; addr.sin_addr.s_addr = htonl(INADDR_ANY); addr.sin_port = 0; - self->fd = socket(AF_INET, SOCK_STREAM, 0); + *fd = socket(AF_INET, SOCK_STREAM, 0); sfd = socket(AF_INET, SOCK_STREAM, 0); ret = bind(sfd, &addr, sizeof(addr)); @@ -108,26 +103,37 @@ FIXTURE_SETUP(tls_basic) ret = getsockname(sfd, &addr, &len); ASSERT_EQ(ret, 0); - ret = connect(self->fd, &addr, sizeof(addr)); + ret = connect(*fd, &addr, sizeof(addr)); ASSERT_EQ(ret, 0); - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); + *cfd = accept(sfd, &addr, &len); + ASSERT_GE(*cfd, 0); close(sfd); - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); if (ret != 0) { ASSERT_EQ(errno, ENOENT); - self->notls = true; + *notls = true; printf("Failure setting TCP_ULP, testing without tls\n"); return; } - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + ret = setsockopt(*cfd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); ASSERT_EQ(ret, 0); } +FIXTURE(tls_basic) +{ + int fd, cfd; + bool notls; +}; + +FIXTURE_SETUP(tls_basic) +{ + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); +} + FIXTURE_TEARDOWN(tls_basic) { close(self->fd); @@ -199,60 +205,21 @@ FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm) FIXTURE_SETUP(tls) { struct tls_crypto_info_keys tls12; - struct sockaddr_in addr; - socklen_t len; - int sfd, ret; - - self->notls = false; - len = sizeof(addr); + int ret; tls_crypto_info_init(variant->tls_version, variant->cipher_type, &tls12); - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); - self->fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); + if (self->notls) + return; - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - ret = getsockname(sfd, &addr, &len); + ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, tls12.len); ASSERT_EQ(ret, 0); - - ret = connect(self->fd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - self->notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } - - if (!self->notls) { - ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - self->cfd = accept(sfd, &addr, &len); - ASSERT_GE(self->cfd, 0); - - if (!self->notls) { - ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - ASSERT_EQ(ret, 0); - - ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12, - tls12.len); - ASSERT_EQ(ret, 0); - } - - close(sfd); } FIXTURE_TEARDOWN(tls) @@ -1355,62 +1322,25 @@ TEST(non_established) { TEST(keysizes) { struct tls12_crypto_info_aes_gcm_256 tls12; - struct sockaddr_in addr; - int sfd, ret, fd, cfd; - socklen_t len; + int ret, fd, cfd; bool notls; - notls = false; - len = sizeof(addr); - memset(&tls12, 0, sizeof(tls12)); tls12.info.version = TLS_1_2_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; - addr.sin_family = AF_INET; - addr.sin_addr.s_addr = htonl(INADDR_ANY); - addr.sin_port = 0; - - fd = socket(AF_INET, SOCK_STREAM, 0); - sfd = socket(AF_INET, SOCK_STREAM, 0); - - ret = bind(sfd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - ret = listen(sfd, 10); - ASSERT_EQ(ret, 0); - - ret = getsockname(sfd, &addr, &len); - ASSERT_EQ(ret, 0); - - ret = connect(fd, &addr, sizeof(addr)); - ASSERT_EQ(ret, 0); - - ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); - if (ret != 0) { - notls = true; - printf("Failure setting TCP_ULP, testing without tls\n"); - } + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); if (!notls) { ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, sizeof(tls12)); EXPECT_EQ(ret, 0); - } - - cfd = accept(sfd, &addr, &len); - ASSERT_GE(cfd, 0); - - if (!notls) { - ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", - sizeof("tls")); - EXPECT_EQ(ret, 0); ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, sizeof(tls12)); EXPECT_EQ(ret, 0); } - close(sfd); close(fd); close(cfd); } From 31180adb0bed7d3e67ae97121dc83f320bbd45be Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:50 -0800 Subject: [PATCH 69/94] selftests: tls: factor out cmsg send/receive Add helpers for sending and receiving special record types. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 111 +++++++++++++++++++----------- 1 file changed, 70 insertions(+), 41 deletions(-) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 8fb7cf8c4bfb..642d1d629b28 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -123,6 +123,65 @@ static void ulp_sock_pair(struct __test_metadata *_metadata, ASSERT_EQ(ret, 0); } +/* Produce a basic cmsg */ +static int tls_send_cmsg(int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + int cmsg_len = sizeof(char); + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec vec; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_TLS; + /* test sending non-record types. */ + cmsg->cmsg_type = TLS_SET_RECORD_TYPE; + cmsg->cmsg_len = CMSG_LEN(cmsg_len); + *CMSG_DATA(cmsg) = record_type; + msg.msg_controllen = cmsg->cmsg_len; + + return sendmsg(fd, &msg, flags); +} + +static int tls_recv_cmsg(struct __test_metadata *_metadata, + int fd, unsigned char record_type, + void *data, size_t len, int flags) +{ + char cbuf[CMSG_SPACE(sizeof(char))]; + struct cmsghdr *cmsg; + unsigned char ctype; + struct msghdr msg; + struct iovec vec; + int n; + + vec.iov_base = data; + vec.iov_len = len; + memset(&msg, 0, sizeof(struct msghdr)); + msg.msg_iov = &vec; + msg.msg_iovlen = 1; + msg.msg_control = cbuf; + msg.msg_controllen = sizeof(cbuf); + + n = recvmsg(fd, &msg, flags); + + cmsg = CMSG_FIRSTHDR(&msg); + EXPECT_NE(cmsg, NULL); + EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); + EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); + ctype = *((unsigned char *)CMSG_DATA(cmsg)); + EXPECT_EQ(ctype, record_type); + + return n; +} + FIXTURE(tls_basic) { int fd, cfd; @@ -1160,60 +1219,30 @@ TEST_F(tls, mutliproc_sendpage_writers) TEST_F(tls, control_msg) { - if (self->notls) - return; - - char cbuf[CMSG_SPACE(sizeof(char))]; - char const *test_str = "test_read"; - int cmsg_len = sizeof(char); + char *test_str = "test_read"; char record_type = 100; - struct cmsghdr *cmsg; - struct msghdr msg; int send_len = 10; - struct iovec vec; char buf[10]; - vec.iov_base = (char *)test_str; - vec.iov_len = 10; - memset(&msg, 0, sizeof(struct msghdr)); - msg.msg_iov = &vec; - msg.msg_iovlen = 1; - msg.msg_control = cbuf; - msg.msg_controllen = sizeof(cbuf); - cmsg = CMSG_FIRSTHDR(&msg); - cmsg->cmsg_level = SOL_TLS; - /* test sending non-record types. */ - cmsg->cmsg_type = TLS_SET_RECORD_TYPE; - cmsg->cmsg_len = CMSG_LEN(cmsg_len); - *CMSG_DATA(cmsg) = record_type; - msg.msg_controllen = cmsg->cmsg_len; + if (self->notls) + SKIP(return, "no TLS support"); - EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, record_type, test_str, send_len, 0), + send_len); /* Should fail because we didn't provide a control message */ EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); - vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL | MSG_PEEK), send_len); - - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL | MSG_PEEK), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); /* Recv the message again without MSG_PEEK */ - record_type = 0; memset(buf, 0, sizeof(buf)); - EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); - cmsg = CMSG_FIRSTHDR(&msg); - EXPECT_NE(cmsg, NULL); - EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); - EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE); - record_type = *((unsigned char *)CMSG_DATA(cmsg)); - EXPECT_EQ(record_type, 100); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } From ef0fc0b3cc2b8df7f29656a190a13ceb644b0c00 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:51 -0800 Subject: [PATCH 70/94] selftests: tls: add tests for handling of bad records Test broken records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 154 ++++++++++++++++++++++++++++++ 1 file changed, 154 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 642d1d629b28..2108b197d3f6 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1297,6 +1297,160 @@ TEST_F(tls, shutdown_reuse) EXPECT_EQ(errno, EISCONN); } +FIXTURE(tls_err) +{ + int fd, cfd; + int fd2, cfd2; + bool notls; +}; + +FIXTURE_VARIANT(tls_err) +{ + uint16_t tls_version; +}; + +FIXTURE_VARIANT_ADD(tls_err, 12_aes_gcm) +{ + .tls_version = TLS_1_2_VERSION, +}; + +FIXTURE_VARIANT_ADD(tls_err, 13_aes_gcm) +{ + .tls_version = TLS_1_3_VERSION, +}; + +FIXTURE_SETUP(tls_err) +{ + struct tls_crypto_info_keys tls12; + int ret; + + tls_crypto_info_init(variant->tls_version, TLS_CIPHER_AES_GCM_128, + &tls12); + + ulp_sock_pair(_metadata, &self->fd, &self->cfd, &self->notls); + ulp_sock_pair(_metadata, &self->fd2, &self->cfd2, &self->notls); + if (self->notls) + return; + + ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(self->cfd2, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); +} + +FIXTURE_TEARDOWN(tls_err) +{ + close(self->fd); + close(self->cfd); + close(self->fd2); + close(self->cfd2); +} + +TEST_F(tls_err, bad_rec) +{ + char buf[64]; + + if (self->notls) + SKIP(return, "no TLS support"); + + memset(buf, 0x55, sizeof(buf)); + EXPECT_EQ(send(self->fd2, buf, sizeof(buf), 0), sizeof(buf)); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EMSGSIZE); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), MSG_DONTWAIT), -1); + EXPECT_EQ(errno, EAGAIN); +} + +TEST_F(tls_err, bad_auth) +{ + char buf[128]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + memrnd(buf, sizeof(buf) / 2); + EXPECT_EQ(send(self->fd, buf, sizeof(buf) / 2, 0), sizeof(buf) / 2); + n = recv(self->cfd, buf, sizeof(buf), 0); + EXPECT_GT(n, sizeof(buf) / 2); + + buf[n - 1]++; + + EXPECT_EQ(send(self->fd2, buf, n, 0), n); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_in_large_read) +{ + char txt[3][64]; + char cip[3][128]; + char buf[3 * 128]; + int i, n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Put 3 records in the sockets */ + for (i = 0; i < 3; i++) { + memrnd(txt[i], sizeof(txt[i])); + EXPECT_EQ(send(self->fd, txt[i], sizeof(txt[i]), 0), + sizeof(txt[i])); + n = recv(self->cfd, cip[i], sizeof(cip[i]), 0); + EXPECT_GT(n, sizeof(txt[i])); + /* Break the third message */ + if (i == 2) + cip[2][n - 1]++; + EXPECT_EQ(send(self->fd2, cip[i], n, 0), n); + } + + /* We should be able to receive the first two messages */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt[0]) * 2); + EXPECT_EQ(memcmp(buf, txt[0], sizeof(txt[0])), 0); + EXPECT_EQ(memcmp(buf + sizeof(txt[0]), txt[1], sizeof(txt[1])), 0); + /* Third mesasge is bad */ + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + +TEST_F(tls_err, bad_cmsg) +{ + char *test_str = "test_read"; + int send_len = 10; + char cip[128]; + char buf[128]; + char txt[64]; + int n; + + if (self->notls) + SKIP(return, "no TLS support"); + + /* Queue up one data record */ + memrnd(txt, sizeof(txt)); + EXPECT_EQ(send(self->fd, txt, sizeof(txt), 0), sizeof(txt)); + n = recv(self->cfd, cip, sizeof(cip), 0); + EXPECT_GT(n, sizeof(txt)); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + n = recv(self->cfd, cip, sizeof(cip), 0); + cip[n - 1]++; /* Break it */ + EXPECT_GT(n, send_len); + EXPECT_EQ(send(self->fd2, cip, n, 0), n); + + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), sizeof(txt)); + EXPECT_EQ(memcmp(buf, txt, sizeof(txt)), 0); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); + EXPECT_EQ(recv(self->cfd2, buf, sizeof(buf), 0), -1); + EXPECT_EQ(errno, EBADMSG); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; From 520493f66f6822551aef2879cd40207074fe6980 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:52 -0800 Subject: [PATCH 71/94] tls: splice_read: fix record type check We don't support splicing control records. TLS 1.3 changes moved the record type check into the decrypt if(). The skb may already be decrypted and still be an alert. Note that decrypt_skb_update() is idempotent and updates ctx->decrypted so the if() is pointless. Reorder the check for decryption errors with the content type check while touching them. This part is not really a bug, because if decryption failed in TLS 1.3 content type will be DATA, and for TLS 1.2 it will be correct. Nevertheless its strange to touch output before checking if the function has failed. Fixes: fedf201e1296 ("net: tls: Refactor control message handling on recv") Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 25 +++++++++++-------------- 1 file changed, 11 insertions(+), 14 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d81564078557..2f11f1db917a 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2018,21 +2018,18 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (!skb) goto splice_read_end; - if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -EINVAL; - goto splice_read_end; - } - - if (err < 0) { - tls_err_abort(sk, -EBADMSG); - goto splice_read_end; - } - ctx->decrypted = 1; + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + if (err < 0) { + tls_err_abort(sk, -EBADMSG); + goto splice_read_end; } + + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -EINVAL; + goto splice_read_end; + } + rxm = strp_msg(skb); chunk = min_t(unsigned int, rxm->full_len, len); From d87d67fd61ef4e7619eb24ab20cba3250a6444e8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:53 -0800 Subject: [PATCH 72/94] selftests: tls: test splicing cmsgs Make sure we correctly reject splicing non-data records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 40 +++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 2108b197d3f6..3dfa9d7dd4cc 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -639,6 +639,46 @@ TEST_F(tls, splice_to_pipe) EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } +TEST_F(tls, splice_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + +TEST_F(tls, splice_dec_cmsg_to_pipe) +{ + char *test_str = "test_read"; + char record_type = 100; + int send_len = 10; + char buf[10]; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, test_str, send_len, 0), 10); + EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); + EXPECT_EQ(errno, EIO); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, send_len, 0), -1); + EXPECT_EQ(errno, EINVAL); + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, record_type, + buf, sizeof(buf), MSG_WAITALL), + send_len); + EXPECT_EQ(memcmp(test_str, buf, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; From e062fe99cccd9ff9f232e593d163ecabd244fae8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:54 -0800 Subject: [PATCH 73/94] tls: splice_read: fix accessing pre-processed records recvmsg() will put peek()ed and partially read records onto the rx_list. splice_read() needs to consult that list otherwise it may miss data. Align with recvmsg() and also put partially-read records onto rx_list. tls_sw_advance_skb() is pretty pointless now and will be removed in net-next. Fixes: 692d7b5d1f91 ("tls: Fix recvmsg() to be able to peek across multiple records") Signed-off-by: Jakub Kicinski --- net/tls/tls_sw.c | 33 +++++++++++++++++++++++++-------- 1 file changed, 25 insertions(+), 8 deletions(-) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 2f11f1db917a..d3e7ff90889e 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2005,6 +2005,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct sock *sk = sock->sk; struct sk_buff *skb; ssize_t copied = 0; + bool from_queue; int err = 0; long timeo; int chunk; @@ -2014,14 +2015,20 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, timeo = sock_rcvtimeo(sk, flags & SPLICE_F_NONBLOCK); - skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, &err); - if (!skb) - goto splice_read_end; + from_queue = !skb_queue_empty(&ctx->rx_list); + if (from_queue) { + skb = __skb_dequeue(&ctx->rx_list); + } else { + skb = tls_wait_data(sk, NULL, flags & SPLICE_F_NONBLOCK, timeo, + &err); + if (!skb) + goto splice_read_end; - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); - if (err < 0) { - tls_err_abort(sk, -EBADMSG); - goto splice_read_end; + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + if (err < 0) { + tls_err_abort(sk, -EBADMSG); + goto splice_read_end; + } } /* splice does not support reading control messages */ @@ -2037,7 +2044,17 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (copied < 0) goto splice_read_end; - tls_sw_advance_skb(sk, skb, copied); + if (!from_queue) { + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + } + if (chunk < rxm->full_len) { + __skb_queue_head(&ctx->rx_list, skb); + rxm->offset += len; + rxm->full_len -= len; + } else { + consume_skb(skb); + } splice_read_end: release_sock(sk); From 274af0f9e2799da22a866139d9bd203cc0baacff Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:55 -0800 Subject: [PATCH 74/94] selftests: tls: test splicing decrypted records Add tests for half-received and peeked records. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 49 +++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 3dfa9d7dd4cc..6e78d7207cc1 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -679,6 +679,55 @@ TEST_F(tls, splice_dec_cmsg_to_pipe) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int half = send_len / 2; + int p[2]; + + ASSERT_GE(pipe(p), 0); + EXPECT_EQ(send(self->fd, mem_send, send_len, 0), send_len); + /* Recv hald of the record, splice the other half */ + EXPECT_EQ(recv(self->cfd, mem_recv, half, MSG_WAITALL), half); + EXPECT_EQ(splice(self->cfd, NULL, p[1], NULL, half, SPLICE_F_NONBLOCK), + half); + EXPECT_EQ(read(p[0], &mem_recv[half], half), half); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + +TEST_F(tls, peek_and_splice) +{ + int send_len = TLS_PAYLOAD_MAX_LEN; + char mem_send[TLS_PAYLOAD_MAX_LEN]; + char mem_recv[TLS_PAYLOAD_MAX_LEN]; + int chunk = TLS_PAYLOAD_MAX_LEN / 4; + int n, i, p[2]; + + memrnd(mem_send, sizeof(mem_send)); + + ASSERT_GE(pipe(p), 0); + for (i = 0; i < 4; i++) + EXPECT_EQ(send(self->fd, &mem_send[chunk * i], chunk, 0), + chunk); + + EXPECT_EQ(recv(self->cfd, mem_recv, chunk * 5 / 2, + MSG_WAITALL | MSG_PEEK), + chunk * 5 / 2); + EXPECT_EQ(memcmp(mem_send, mem_recv, chunk * 5 / 2), 0); + + n = 0; + while (n < send_len) { + i = splice(self->cfd, NULL, p[1], NULL, send_len - n, 0); + EXPECT_GT(i, 0); + n += i; + } + EXPECT_EQ(n, send_len); + EXPECT_EQ(read(p[0], mem_recv, send_len), send_len); + EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); +} + TEST_F(tls, recvmsg_single) { char const *test_str = "test_recvmsg_single"; From f3911f73f51d1534f4db70b516cc1fcb6be05bae Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:56 -0800 Subject: [PATCH 75/94] tls: fix replacing proto_ops We replace proto_ops whenever TLS is configured for RX. But our replacement also overrides sendpage_locked, which will crash unless TX is also configured. Similarly we plug both of those in for TLS_HW (NIC crypto offload) even tho TLS_HW has a completely different implementation for TX. Last but not least we always plug in something based on inet_stream_ops even though a few of the callbacks differ for IPv6 (getname, release, bind). Use a callback building method similar to what we do for struct proto. Fixes: c46234ebb4d1 ("tls: RX path for ktls") Fixes: d4ffb02dee2f ("net/tls: enable sk_msg redirect to tls socket egress") Signed-off-by: Jakub Kicinski --- net/tls/tls_main.c | 47 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 40 insertions(+), 7 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index acfba9f1ba72..6bc2879ba637 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -61,7 +61,7 @@ static DEFINE_MUTEX(tcpv6_prot_mutex); static const struct proto *saved_tcpv4_prot; static DEFINE_MUTEX(tcpv4_prot_mutex); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; -static struct proto_ops tls_sw_proto_ops; +static struct proto_ops tls_proto_ops[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], const struct proto *base); @@ -71,6 +71,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) WRITE_ONCE(sk->sk_prot, &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]); + WRITE_ONCE(sk->sk_socket->ops, + &tls_proto_ops[ip_ver][ctx->tx_conf][ctx->rx_conf]); } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -669,8 +671,6 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, if (tx) { ctx->sk_write_space = sk->sk_write_space; sk->sk_write_space = tls_write_space; - } else { - sk->sk_socket->ops = &tls_sw_proto_ops; } goto out; @@ -728,6 +728,39 @@ struct tls_context *tls_ctx_create(struct sock *sk) return ctx; } +static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + const struct proto_ops *base) +{ + ops[TLS_BASE][TLS_BASE] = *base; + + ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; + + ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; + + ops[TLS_SW ][TLS_SW ] = ops[TLS_SW ][TLS_BASE]; + ops[TLS_SW ][TLS_SW ].splice_read = tls_sw_splice_read; + +#ifdef CONFIG_TLS_DEVICE + ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; + ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; + + ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; + ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; + + ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; + + ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; + + ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; + ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; +#endif +#ifdef CONFIG_TLS_TOE + ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; +#endif +} + static void tls_build_proto(struct sock *sk) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; @@ -739,6 +772,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv6_prot_mutex); if (likely(prot != saved_tcpv6_prot)) { build_protos(tls_prots[TLSV6], prot); + build_proto_ops(tls_proto_ops[TLSV6], + sk->sk_socket->ops); smp_store_release(&saved_tcpv6_prot, prot); } mutex_unlock(&tcpv6_prot_mutex); @@ -749,6 +784,8 @@ static void tls_build_proto(struct sock *sk) mutex_lock(&tcpv4_prot_mutex); if (likely(prot != saved_tcpv4_prot)) { build_protos(tls_prots[TLSV4], prot); + build_proto_ops(tls_proto_ops[TLSV4], + sk->sk_socket->ops); smp_store_release(&saved_tcpv4_prot, prot); } mutex_unlock(&tcpv4_prot_mutex); @@ -959,10 +996,6 @@ static int __init tls_register(void) if (err) return err; - tls_sw_proto_ops = inet_stream_ops; - tls_sw_proto_ops.splice_read = tls_sw_splice_read; - tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked; - tls_device_init(); tcp_register_ulp(&tcp_tls_ulp_ops); From f884a3426291b3f368231c0ac0e50a6a061f6aca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Nov 2021 15:25:57 -0800 Subject: [PATCH 76/94] selftests: tls: test for correct proto_ops Previous patch fixes overriding callbacks incorrectly. Triggering the crash in sendpage_locked would be more spectacular but it's hard to get to, so take the easier path of proving this is broken and call getname. We're currently getting IPv4 socket info on an IPv6 socket. Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/tls.c | 55 +++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 6e78d7207cc1..8a22db0cca49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1617,4 +1617,59 @@ TEST(keysizes) { close(cfd); } +TEST(tls_v6ops) { + struct tls_crypto_info_keys tls12; + struct sockaddr_in6 addr, addr2; + int sfd, ret, fd; + socklen_t len, len2; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_GCM_128, &tls12); + + addr.sin6_family = AF_INET6; + addr.sin6_addr = in6addr_any; + addr.sin6_port = 0; + + fd = socket(AF_INET6, SOCK_STREAM, 0); + sfd = socket(AF_INET6, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + len = sizeof(addr); + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + len = sizeof(addr); + ret = getsockname(fd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret) { + ASSERT_EQ(errno, ENOENT); + SKIP(return, "no TLS support"); + } + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, SOL_TLS, TLS_RX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + len2 = sizeof(addr2); + ret = getsockname(fd, &addr2, &len2); + ASSERT_EQ(ret, 0); + + EXPECT_EQ(len2, len); + EXPECT_EQ(memcmp(&addr, &addr2, len), 0); + + close(fd); + close(sfd); +} + TEST_HARNESS_MAIN From b270bfe697367776eca2e6759a71d700fb8d82a2 Mon Sep 17 00:00:00 2001 From: Yannick Vignon Date: Wed, 24 Nov 2021 16:47:31 +0100 Subject: [PATCH 77/94] net: stmmac: Disable Tx queues when reconfiguring the interface The Tx queues were not disabled in situations where the driver needed to stop the interface to apply a new configuration. This could result in a kernel panic when doing any of the 3 following actions: * reconfiguring the number of queues (ethtool -L) * reconfiguring the size of the ring buffers (ethtool -G) * installing/removing an XDP program (ip l set dev ethX xdp) Prevent the panic by making sure netif_tx_disable is called when stopping an interface. Without this patch, the following kernel panic can be observed when doing any of the actions above: Unable to handle kernel paging request at virtual address ffff80001238d040 [....] Call trace: dwmac4_set_addr+0x8/0x10 dev_hard_start_xmit+0xe4/0x1ac sch_direct_xmit+0xe8/0x39c __dev_queue_xmit+0x3ec/0xaf0 dev_queue_xmit+0x14/0x20 [...] [ end trace 0000000000000002 ]--- Fixes: 5fabb01207a2d ("net: stmmac: Add initial XDP support") Fixes: aa042f60e4961 ("net: stmmac: Add support to Ethtool get/set ring parameters") Fixes: 0366f7e06a6be ("net: stmmac: add ethtool support for get/set channels") Signed-off-by: Yannick Vignon Link: https://lore.kernel.org/r/20211124154731.1676949-1-yannick.vignon@oss.nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index f12097c8a485..748195697e5a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3802,6 +3802,8 @@ int stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; + netif_tx_disable(dev); + if (device_may_wakeup(priv->device)) phylink_speed_down(priv->phylink, false); /* Stop and disconnect the PHY */ From de6d25924c2a8c2988c6a385990cafbe742061bf Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Wed, 24 Nov 2021 17:14:40 +0100 Subject: [PATCH 78/94] net/sched: sch_ets: don't peek at classes beyond 'nbands' when the number of DRR classes decreases, the round-robin active list can contain elements that have already been freed in ets_qdisc_change(). As a consequence, it's possible to see a NULL dereference crash, caused by the attempt to call cl->qdisc->ops->peek(cl->qdisc) when cl->qdisc is NULL: BUG: kernel NULL pointer dereference, address: 0000000000000018 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 910 Comm: mausezahn Not tainted 5.16.0-rc1+ #475 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:ets_qdisc_dequeue+0x129/0x2c0 [sch_ets] Code: c5 01 41 39 ad e4 02 00 00 0f 87 18 ff ff ff 49 8b 85 c0 02 00 00 49 39 c4 0f 84 ba 00 00 00 49 8b ad c0 02 00 00 48 8b 7d 10 <48> 8b 47 18 48 8b 40 38 0f ae e8 ff d0 48 89 c3 48 85 c0 0f 84 9d RSP: 0000:ffffbb36c0b5fdd8 EFLAGS: 00010287 RAX: ffff956678efed30 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000002 RSI: ffffffff9b938dc9 RDI: 0000000000000000 RBP: ffff956678efed30 R08: e2f3207fe360129c R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff956678efeac0 R13: ffff956678efe800 R14: ffff956611545000 R15: ffff95667ac8f100 FS: 00007f2aa9120740(0000) GS:ffff95667b800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000018 CR3: 000000011070c000 CR4: 0000000000350ee0 Call Trace: qdisc_peek_dequeued+0x29/0x70 [sch_ets] tbf_dequeue+0x22/0x260 [sch_tbf] __qdisc_run+0x7f/0x630 net_tx_action+0x290/0x4c0 __do_softirq+0xee/0x4f8 irq_exit_rcu+0xf4/0x130 sysvec_apic_timer_interrupt+0x52/0xc0 asm_sysvec_apic_timer_interrupt+0x12/0x20 RIP: 0033:0x7f2aa7fc9ad4 Code: b9 ff ff 48 8b 54 24 18 48 83 c4 08 48 89 ee 48 89 df 5b 5d e9 ed fc ff ff 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa <53> 48 83 ec 10 48 8b 05 10 64 33 00 48 8b 00 48 85 c0 0f 85 84 00 RSP: 002b:00007ffe5d33fab8 EFLAGS: 00000202 RAX: 0000000000000002 RBX: 0000561f72c31460 RCX: 0000561f72c31720 RDX: 0000000000000002 RSI: 0000561f72c31722 RDI: 0000561f72c31720 RBP: 000000000000002a R08: 00007ffe5d33fa40 R09: 0000000000000014 R10: 0000000000000000 R11: 0000000000000246 R12: 0000561f7187e380 R13: 0000000000000000 R14: 0000000000000000 R15: 0000561f72c31460 Modules linked in: sch_ets sch_tbf dummy rfkill iTCO_wdt intel_rapl_msr iTCO_vendor_support intel_rapl_common joydev virtio_balloon lpc_ich i2c_i801 i2c_smbus pcspkr ip_tables xfs libcrc32c crct10dif_pclmul crc32_pclmul crc32c_intel ahci libahci ghash_clmulni_intel serio_raw libata virtio_blk virtio_console virtio_net net_failover failover sunrpc dm_mirror dm_region_hash dm_log dm_mod CR2: 0000000000000018 Ensuring that 'alist' was never zeroed [1] was not sufficient, we need to remove from the active list those elements that are no more SP nor DRR. [1] https://lore.kernel.org/netdev/60d274838bf09777f0371253416e8af71360bc08.1633609148.git.dcaratti@redhat.com/ v3: fix race between ets_qdisc_change() and ets_qdisc_dequeue() delisting DRR classes beyond 'nbands' in ets_qdisc_change() with the qdisc lock acquired, thanks to Cong Wang. v2: when a NULL qdisc is found in the DRR active list, try to dequeue skb from the next list item. Reported-by: Hangbin Liu Fixes: dcc68b4d8084 ("net: sch_ets: Add a new Qdisc") Signed-off-by: Davide Caratti Link: https://lore.kernel.org/r/7a5c496eed2d62241620bdbb83eb03fb9d571c99.1637762721.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski --- net/sched/sch_ets.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 0eae9ff5edf6..e007fc75ef2f 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -665,12 +665,14 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt, q->classes[i].deficit = quanta[i]; } } + for (i = q->nbands; i < oldbands; i++) { + qdisc_tree_flush_backlog(q->classes[i].qdisc); + if (i >= q->nstrict) + list_del(&q->classes[i].alist); + } q->nstrict = nstrict; memcpy(q->prio2band, priomap, sizeof(priomap)); - for (i = q->nbands; i < oldbands; i++) - qdisc_tree_flush_backlog(q->classes[i].qdisc); - for (i = 0; i < q->nbands; i++) q->classes[i].quantum = quanta[i]; From c26381f97e2a7df43826150dc7d4c207bd6794a5 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Thu, 25 Nov 2021 11:14:57 -0300 Subject: [PATCH 79/94] nfc: virtual_ncidev: change default device permissions Device permissions is S_IALLUGO, with many unnecessary bits. Remove them and also remove read and write permissions from group and others. Before the change: crwsrwsrwt 1 0 0 10, 125 Nov 25 13:59 /dev/virtual_nci After the change: crw------- 1 0 0 10, 125 Nov 25 14:05 /dev/virtual_nci Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Krzysztof Kozlowski Reviewed-by: Bongsu Jeon Link: https://lore.kernel.org/r/20211125141457.716921-1-cascardo@canonical.com Signed-off-by: Jakub Kicinski --- drivers/nfc/virtual_ncidev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index 221fa3bb8705..f577449e4935 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -202,7 +202,7 @@ static int __init virtual_ncidev_init(void) miscdev.minor = MISC_DYNAMIC_MINOR; miscdev.name = "virtual_nci"; miscdev.fops = &virtual_ncidev_fops; - miscdev.mode = S_IALLUGO; + miscdev.mode = 0600; return misc_register(&miscdev); } From 0276af2176c78771da7f311621a25d7608045827 Mon Sep 17 00:00:00 2001 From: Julian Wiedmann Date: Fri, 26 Nov 2021 18:55:43 +0100 Subject: [PATCH 80/94] ethtool: ioctl: fix potential NULL deref in ethtool_set_coalesce() ethtool_set_coalesce() now uses both the .get_coalesce() and .set_coalesce() callbacks. But the check for their availability is buggy, so changing the coalesce settings on a device where the driver provides only _one_ of the callbacks results in a NULL pointer dereference instead of an -EOPNOTSUPP. Fix the condition so that the availability of both callbacks is ensured. This also matches the netlink code. Note that reproducing this requires some effort - it only affects the legacy ioctl path, and needs a specific combination of driver options: - have .get_coalesce() and .coalesce_supported but no .set_coalesce(), or - have .set_coalesce() but no .get_coalesce(). Here eg. ethtool doesn't cause the crash as it first attempts to call ethtool_get_coalesce() and bails out on error. Fixes: f3ccfda19319 ("ethtool: extend coalesce setting uAPI with CQE mode") Cc: Yufeng Mo Cc: Huazhong Tan Cc: Andrew Lunn Cc: Heiner Kallweit Signed-off-by: Julian Wiedmann Link: https://lore.kernel.org/r/20211126175543.28000-1-jwi@linux.ibm.com Signed-off-by: Jakub Kicinski --- net/ethtool/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 65e9bc1058b5..20bcf86970ff 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1719,7 +1719,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, struct ethtool_coalesce coalesce; int ret; - if (!dev->ethtool_ops->set_coalesce && !dev->ethtool_ops->get_coalesce) + if (!dev->ethtool_ops->set_coalesce || !dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; ret = dev->ethtool_ops->get_coalesce(dev, &coalesce, &kernel_coalesce, From cbb91dcbfb751f887bfcba790a94c153c5005c19 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 25 Nov 2021 19:19:21 -0800 Subject: [PATCH 81/94] ptp: fix filter names in the documentation All the filter names are missing _PTP in them. Signed-off-by: Jakub Kicinski Acked-by: Richard Cochran Link: https://lore.kernel.org/r/20211126031921.2466944-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/timestamping.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index a722eb30e014..80b13353254a 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -486,8 +486,8 @@ of packets. Drivers are free to use a more permissive configuration than the requested configuration. It is expected that drivers should only implement directly the most generic mode that can be supported. For example if the hardware can -support HWTSTAMP_FILTER_V2_EVENT, then it should generally always upscale -HWTSTAMP_FILTER_V2_L2_SYNC_MESSAGE, and so forth, as HWTSTAMP_FILTER_V2_EVENT +support HWTSTAMP_FILTER_PTP_V2_EVENT, then it should generally always upscale +HWTSTAMP_FILTER_PTP_V2_L2_SYNC, and so forth, as HWTSTAMP_FILTER_PTP_V2_EVENT is more generic (and more useful to applications). A driver which supports hardware time stamping shall update the struct From 01d9cc2dea3fde3bad6d27f464eff463496e2b00 Mon Sep 17 00:00:00 2001 From: Ziyang Xuan Date: Fri, 26 Nov 2021 09:59:42 +0800 Subject: [PATCH 82/94] net: vlan: fix underflow for the real_dev refcnt Inject error before dev_hold(real_dev) in register_vlan_dev(), and execute the following testcase: ip link add dev dummy1 type dummy ip link add name dummy1.100 link dummy1 type vlan id 100 ip link del dev dummy1 When the dummy netdevice is removed, we will get a WARNING as following: ======================================================================= refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 2 PID: 0 at lib/refcount.c:31 refcount_warn_saturate+0xbf/0x1e0 and an endless loop of: ======================================================================= unregister_netdevice: waiting for dummy1 to become free. Usage count = -1073741824 That is because dev_put(real_dev) in vlan_dev_free() be called without dev_hold(real_dev) in register_vlan_dev(). It makes the refcnt of real_dev underflow. Move the dev_hold(real_dev) to vlan_dev_init() which is the call-back of ndo_init(). That makes dev_hold() and dev_put() for vlan's real_dev symmetrical. Fixes: 563bcbae3ba2 ("net: vlan: fix a UAF in vlan_dev_real_dev()") Reported-by: Petr Machata Suggested-by: Jakub Kicinski Signed-off-by: Ziyang Xuan Link: https://lore.kernel.org/r/20211126015942.2918542-1-william.xuanziyang@huawei.com Signed-off-by: Jakub Kicinski --- net/8021q/vlan.c | 3 --- net/8021q/vlan_dev.c | 3 +++ 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a3a0a5e994f5..abaa5d96ded2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -184,9 +184,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack) if (err) goto out_unregister_netdev; - /* Account for reference in struct vlan_dev_priv */ - dev_hold(real_dev); - vlan_stacked_transfer_operstate(real_dev, dev, vlan); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ab6dee28536d..a54535cbcf4c 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -615,6 +615,9 @@ static int vlan_dev_init(struct net_device *dev) if (!vlan->vlan_pcpu_stats) return -ENOMEM; + /* Get vlan's reference to real_dev */ + dev_hold(real_dev); + return 0; } From bacb6c1e47691cda4a95056c21b5487fb7199fcc Mon Sep 17 00:00:00 2001 From: Tony Lu Date: Fri, 26 Nov 2021 10:41:35 +0800 Subject: [PATCH 83/94] net/smc: Don't call clcsock shutdown twice when smc shutdown When applications call shutdown() with SHUT_RDWR in userspace, smc_close_active() calls kernel_sock_shutdown(), and it is called twice in smc_shutdown(). This fixes this by checking sk_state before do clcsock shutdown, and avoids missing the application's call of smc_shutdown(). Link: https://lore.kernel.org/linux-s390/1f67548e-cbf6-0dce-82b5-10288a4583bd@linux.ibm.com/ Fixes: 606a63c9783a ("net/smc: Ensure the active closing peer first closes clcsock") Signed-off-by: Tony Lu Reviewed-by: Wen Gu Acked-by: Karsten Graul Link: https://lore.kernel.org/r/20211126024134.45693-1-tonylu@linux.alibaba.com Signed-off-by: Jakub Kicinski --- net/smc/af_smc.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 4b62c925a13e..230072f9ec48 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2370,8 +2370,10 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, static int smc_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; + bool do_shutdown = true; struct smc_sock *smc; int rc = -EINVAL; + int old_state; int rc1 = 0; smc = smc_sk(sk); @@ -2398,7 +2400,11 @@ static int smc_shutdown(struct socket *sock, int how) } switch (how) { case SHUT_RDWR: /* shutdown in both directions */ + old_state = sk->sk_state; rc = smc_close_active(smc); + if (old_state == SMC_ACTIVE && + sk->sk_state == SMC_PEERCLOSEWAIT1) + do_shutdown = false; break; case SHUT_WR: rc = smc_close_shutdown_write(smc); @@ -2408,7 +2414,7 @@ static int smc_shutdown(struct socket *sock, int how) /* nothing more to do because peer is not involved */ break; } - if (smc->clcsock) + if (do_shutdown && smc->clcsock) rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; From 0435a4d08032c8fba2966cebdac870e22238cacc Mon Sep 17 00:00:00 2001 From: zhangyue Date: Thu, 25 Nov 2021 19:36:10 +0800 Subject: [PATCH 84/94] net: qed: fix the array may be out of bound If the variable 'p_bit->flags' is always 0, the loop condition is always 0. The variable 'j' may be greater than or equal to 32. At this time, the array 'p_aeu->bits[32]' may be out of bound. Signed-off-by: zhangyue Link: https://lore.kernel.org/r/20211125113610.273841-1-zhangyue1@kylinos.cn Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_int.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index a97f691839e0..6958adeca86d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -1045,7 +1045,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, if (!parities) continue; - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_bit = &p_aeu->bits[j]; if (qed_int_is_parity_flag(p_hwfn, p_bit) && @@ -1083,7 +1083,7 @@ static int qed_int_deassertion(struct qed_hwfn *p_hwfn, * to current group, making them responsible for the * previous assertion. */ - for (j = 0, bit_idx = 0; bit_idx < 32; j++) { + for (j = 0, bit_idx = 0; bit_idx < 32 && j < 32; j++) { long unsigned int bitmask; u8 bit, bit_len; @@ -1382,7 +1382,7 @@ static void qed_int_sb_attn_init(struct qed_hwfn *p_hwfn, memset(sb_info->parity_mask, 0, sizeof(u32) * NUM_ATTN_REGS); for (i = 0; i < NUM_ATTN_REGS; i++) { /* j is array index, k is bit index */ - for (j = 0, k = 0; k < 32; j++) { + for (j = 0, k = 0; k < 32 && j < 32; j++) { struct aeu_invert_reg_bit *p_aeu; p_aeu = &aeu_descs[i].bits[j]; From 8d2ad993aa05c0768f00c886c9d369cd97a337ac Mon Sep 17 00:00:00 2001 From: Guangbin Huang Date: Fri, 26 Nov 2021 20:03:15 +0800 Subject: [PATCH 85/94] net: hns3: fix VF RSS failed problem after PF enable multi-TCs When PF is set to multi-TCs and configured mapping relationship between priorities and TCs, the hardware will active these settings for this PF and its VFs. In this case when VF just uses one TC and its rx packets contain priority, and if the priority is not mapped to TC0, as other TCs of VF is not valid, hardware always put this kind of packets to the queue 0. It cause this kind of packets of VF can not be used RSS function. To fix this problem, set tc mode of all unused TCs of VF to the setting of TC0, then rx packet with priority which map to unused TC will be direct to TC0. Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support") Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 25c419d40066..41afaeea881b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -703,9 +703,9 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev, u16 rss_size) roundup_size = ilog2(roundup_size); for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) { - tc_valid[i] = !!(hdev->hw_tc_map & BIT(i)); + tc_valid[i] = 1; tc_size[i] = roundup_size; - tc_offset[i] = rss_size * i; + tc_offset[i] = (hdev->hw_tc_map & BIT(i)) ? rss_size * i : 0; } hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false); From b8af344cfea189cdc0fef41345e55aed76723615 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Fri, 26 Nov 2021 20:03:16 +0800 Subject: [PATCH 86/94] net: hns3: add check NULL address for page pool When page pool is not enabled, its address value is still NULL and page pool should not be accessed, so add a check for it. Fixes: 850bfb912a6d ("net: hns3: debugfs add support dumping page pool info") Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 67364ab63a1f..fbb8a5f08222 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1106,6 +1106,11 @@ hns3_dbg_page_pool_info(struct hnae3_handle *h, char *buf, int len) return -EFAULT; } + if (!priv->ring[h->kinfo.num_tqps].page_pool) { + dev_err(&h->pdev->dev, "page pool is not initialized\n"); + return -EFAULT; + } + for (i = 0; i < ARRAY_SIZE(page_pool_info_items); i++) result[i] = &data_str[i][0]; From 9c14791748708d87c4d02ba74eb7e281e141d6e4 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Fri, 26 Nov 2021 20:03:17 +0800 Subject: [PATCH 87/94] net: hns3: fix one incorrect value of page pool info when queried by debugfs Currently, when user queries page pool info by debugfs command "cat page_pool_info", the cnt of allocated page for page pool may be incorrect because of memory inconsistency problem caused by compiler optimization. So this patch uses READ_ONCE() to read value of pages_state_hold_cnt to fix this problem. Fixes: 850bfb912a6d ("net: hns3: debugfs add support dumping page pool info") Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index fbb8a5f08222..081295bff765 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1081,7 +1081,8 @@ static void hns3_dump_page_pool_info(struct hns3_enet_ring *ring, u32 j = 0; sprintf(result[j++], "%u", index); - sprintf(result[j++], "%u", ring->page_pool->pages_state_hold_cnt); + sprintf(result[j++], "%u", + READ_ONCE(ring->page_pool->pages_state_hold_cnt)); sprintf(result[j++], "%u", atomic_read(&ring->page_pool->pages_state_release_cnt)); sprintf(result[j++], "%u", ring->page_pool->p.pool_size); From 82229c4dbb8a2780f05fa1bab29c97ef7bcd21bb Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 26 Nov 2021 20:03:18 +0800 Subject: [PATCH 88/94] net: hns3: fix incorrect components info of ethtool --reset command Currently, HNS3 driver doesn't clear the reset flags of components after successfully executing reset, it causes userspace info of "Components reset" and "Components not reset" is incorrect. So fix this problem by clear corresponding reset flag after reset process. Fixes: ddccc5e368a3 ("net: hns3: add support for triggering reset by ethtool") Signed-off-by: Jie Wang Signed-off-by: Guangbin Huang Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index c8442b86df94..c9b4568d7a8d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -987,6 +987,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev); const struct hnae3_ae_ops *ops = h->ae_algo->ops; const struct hns3_reset_type_map *rst_type_map; + enum ethtool_reset_flags rst_flags; u32 i, size; if (ops->ae_dev_resetting && ops->ae_dev_resetting(h)) @@ -1006,6 +1007,7 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) for (i = 0; i < size; i++) { if (rst_type_map[i].rst_flags == *flags) { rst_type = rst_type_map[i].rst_type; + rst_flags = rst_type_map[i].rst_flags; break; } } @@ -1021,6 +1023,8 @@ static int hns3_set_reset(struct net_device *netdev, u32 *flags) ops->reset_event(h->pdev, h); + *flags &= ~rst_flags; + return 0; } From 8a075464d1e9317ffae0973dfe538a7511291a06 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:41 +0200 Subject: [PATCH 89/94] net: mscc: ocelot: don't downgrade timestamping RX filters in SIOCSHWTSTAMP The ocelot driver, when asked to timestamp all receiving packets, 1588 v1 or NTP, says "nah, here's 1588 v2 for you". According to this discussion: https://patchwork.kernel.org/project/netdevbpf/patch/20211104133204.19757-8-martin.kaistra@linutronix.de/#24577647 drivers that downgrade from a wider request to a narrower response (or even a response where the intersection with the request is empty) are buggy, and should return -ERANGE instead. This patch fixes that. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Suggested-by: Richard Cochran Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 6 ------ 1 file changed, 6 deletions(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index e6c18b598d5c..bcc4f2f74ccc 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1320,12 +1320,6 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) switch (cfg.rx_filter) { case HWTSTAMP_FILTER_NONE: break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: From 95706be13b9f755d93b5b82bdc782af439f1ec22 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:42 +0200 Subject: [PATCH 90/94] net: mscc: ocelot: create a function that replaces an existing VCAP filter VCAP (Versatile Content Aware Processor) is the TCAM-based engine behind tc flower offload on ocelot, among other things. The ingress port mask on which VCAP rules match is present as a bit field in the actual key of the rule. This means that it is possible for a rule to be shared among multiple source ports. When the rule is added one by one on each desired port, that the ingress port mask of the key must be edited and rewritten to hardware. But the API in ocelot_vcap.c does not allow for this. For one thing, ocelot_vcap_filter_add() and ocelot_vcap_filter_del() are not symmetric, because ocelot_vcap_filter_add() works with a preallocated and prepopulated filter and programs it to hardware, and ocelot_vcap_filter_del() does both the job of removing the specified filter from hardware, as well as kfreeing it. That is to say, the only option of editing a filter in place, which is to delete it, modify the structure and add it back, does not work because it results in use-after-free. This patch introduces ocelot_vcap_filter_replace, which trivially reprograms a VCAP entry to hardware, at the exact same index at which it existed before, without modifying any list or allocating any memory. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot_vcap.c | 16 ++++++++++++++++ include/soc/mscc/ocelot_vcap.h | 2 ++ 2 files changed, 18 insertions(+) diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 99d7376a70a7..337cd08b1a54 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -1217,6 +1217,22 @@ int ocelot_vcap_filter_del(struct ocelot *ocelot, } EXPORT_SYMBOL(ocelot_vcap_filter_del); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter) +{ + struct ocelot_vcap_block *block = &ocelot->block[filter->block_id]; + int index; + + index = ocelot_vcap_block_get_filter_index(block, filter); + if (index < 0) + return index; + + vcap_entry_set(ocelot, index, filter); + + return 0; +} +EXPORT_SYMBOL(ocelot_vcap_filter_replace); + int ocelot_vcap_filter_stats_update(struct ocelot *ocelot, struct ocelot_vcap_filter *filter) { diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index eeb1142aa1b1..4d1dfa1136b2 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -703,6 +703,8 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, struct netlink_ext_ack *extack); int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); +int ocelot_vcap_filter_replace(struct ocelot *ocelot, + struct ocelot_vcap_filter *filter); struct ocelot_vcap_filter * ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, unsigned long cookie, bool tc_offload); From ec15baec3272bbec576f2ce7ce47765a8e9b7b1c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:43 +0200 Subject: [PATCH 91/94] net: ptp: add a definition for the UDP port for IEEE 1588 general messages As opposed to event messages (Sync, PdelayReq etc) which require timestamping, general messages (Announce, FollowUp etc) do not. In PTP they are part of different streams of data. IEEE 1588-2008 Annex D.2 "UDP port numbers" states that the UDP destination port assigned by IANA is 319 for event messages, and 320 for general messages. Yet the kernel seems to be missing the definition for general messages. This patch adds it. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- include/linux/ptp_classify.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index ae04968a3a47..9afd34a2d36c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -37,6 +37,7 @@ #define PTP_MSGTYPE_PDELAY_RESP 0x3 #define PTP_EV_PORT 319 +#define PTP_GEN_PORT 320 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ From 96ca08c05838d1f5501003f0a6201824e4eede70 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:44 +0200 Subject: [PATCH 92/94] net: mscc: ocelot: set up traps for PTP packets IEEE 1588 support was declared too soon for the Ocelot switch. Out of reset, this switch does not apply any special treatment for PTP packets, i.e. when an event message is received, the natural tendency is to forward it by MAC DA/VLAN ID. This poses a problem when the ingress port is under a bridge, since user space application stacks (written primarily for endpoint ports, not switches) like ptp4l expect that PTP messages are always received on AF_PACKET / AF_INET sockets (depending on the PTP transport being used), and never being autonomously forwarded. Any forwarding, if necessary (for example in Transparent Clock mode) is handled in software by ptp4l. Having the hardware forward these packets too will cause duplicates which will confuse endpoints connected to these switches. So PTP over L2 barely works, in the sense that PTP packets reach the CPU port, but they reach it via flooding, and therefore reach lots of other unwanted destinations too. But PTP over IPv4/IPv6 does not work at all. This is because the Ocelot switch have a separate destination port mask for unknown IP multicast (which PTP over IP is) flooding compared to unknown non-IP multicast (which PTP over L2 is) flooding. Specifically, the driver allows the CPU port to be in the PGID_MC port group, but not in PGID_MCIPV4 and PGID_MCIPV6. There are several presentations from Allan Nielsen which explain that the embedded MIPS CPU on Ocelot switches is not very powerful at all, so every penny they could save by not allowing flooding to the CPU port module matters. Unknown IP multicast did not make it. The de facto consensus is that when a switch is PTP-aware and an application stack for PTP is running, switches should have some sort of trapping mechanism for PTP packets, to extract them from the hardware data path. This avoids both problems: (a) PTP packets are no longer flooded to unwanted destinations (b) PTP over IP packets are no longer denied from reaching the CPU since they arrive there via a trap and not via flooding It is not the first time when this change is attempted. Last time, the feedback from Allan Nielsen and Andrew Lunn was that the traps should not be installed by default, and that PTP-unaware switching may be desired for some use cases: https://patchwork.ozlabs.org/project/netdev/patch/20190813025214.18601-5-yangbo.lu@nxp.com/ To address that feedback, the present patch adds the necessary packet traps according to the RX filter configuration transmitted by user space through the SIOCSHWTSTAMP ioctl. Trapping is done via VCAP IS2, where we keep 5 filters, which are amended each time RX timestamping is enabled or disabled on a port: - 1 for PTP over L2 - 2 for PTP over IPv4 (UDP ports 319 and 320) - 2 for PTP over IPv6 (UDP ports 319 and 320) The cookie by which these filters (invisible to tc) are identified is strategically chosen such that it does not collide with the filters used for the ocelot-8021q tagging protocol by the Felix driver, or with the MRP traps set up by the Ocelot library. Other alternatives were considered, like patching user space to do something, but there are so many ways in which PTP packets could be made to reach the CPU, generically speaking, that "do what?" is a very valid question. The ptp4l program from the linuxptp stack already attempts to do something: it calls setsockopt(IP_ADD_MEMBERSHIP) (and PACKET_ADD_MEMBERSHIP, respectively) which translates in both cases into a dev_mc_add() on the interface, in the kernel: https://github.com/richardcochran/linuxptp/blob/v3.1.1/udp.c#L73 https://github.com/richardcochran/linuxptp/blob/v3.1.1/raw.c Reality shows that this is not sufficient in case the interface belongs to a switchdev driver, as dev_mc_add() does not show the intention to trap a packet to the CPU, but rather the intention to not drop it (it is strictly for RX filtering, same as promiscuous does not mean to send all traffic to the CPU, but to not drop traffic with unknown MAC DA). This topic is a can of worms in itself, and it would be great if user space could just stay out of it. On the other hand, setting up PTP traps privately within the driver is not new by any stretch of the imagination: https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c#L833 https://elixir.bootlin.com/linux/v5.16-rc2/source/drivers/net/dsa/hirschmann/hellcreek.c#L1050 https://elixir.bootlin.com/linux/v5.16-rc2/source/include/linux/dsa/sja1105.h#L21 So this is the approach taken here as well. The difference here being that we prepare and destroy the traps per port, dynamically at runtime, as opposed to driver init time, because apparently, PTP-unaware forwarding is a use case. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Reported-by: Po Liu Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 241 ++++++++++++++++++++++++++++- 1 file changed, 240 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index bcc4f2f74ccc..9b7be93cbb0d 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1278,6 +1278,225 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, } EXPORT_SYMBOL(ocelot_fdb_dump); +static void ocelot_populate_l2_ptp_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_ETYPE; + *(__be16 *)trap->key.etype.etype.value = htons(ETH_P_1588); + *(__be16 *)trap->key.etype.etype.mask = htons(0xffff); +} + +static void +ocelot_populate_ipv4_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_EV_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_EV_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv4_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV4; + trap->key.ipv4.dport.value = PTP_GEN_PORT; + trap->key.ipv4.dport.mask = 0xffff; +} + +static void +ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) +{ + trap->key_type = OCELOT_VCAP_KEY_IPV6; + trap->key.ipv6.dport.value = PTP_GEN_PORT; + trap->key.ipv6.dport.mask = 0xffff; +} + +static int ocelot_trap_add(struct ocelot *ocelot, int port, + unsigned long cookie, + void (*populate)(struct ocelot_vcap_filter *f)) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + bool new = false; + int err; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) { + trap = kzalloc(sizeof(*trap), GFP_KERNEL); + if (!trap) + return -ENOMEM; + + populate(trap); + trap->prio = 1; + trap->id.cookie = cookie; + trap->id.tc_offload = false; + trap->block_id = VCAP_IS2; + trap->type = OCELOT_VCAP_FILTER_OFFLOAD; + trap->lookup = 0; + trap->action.cpu_copy_ena = true; + trap->action.mask_mode = OCELOT_MASK_MODE_PERMIT_DENY; + trap->action.port_mask = 0; + new = true; + } + + trap->ingress_port_mask |= BIT(port); + + if (new) + err = ocelot_vcap_filter_add(ocelot, trap, NULL); + else + err = ocelot_vcap_filter_replace(ocelot, trap); + if (err) { + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + kfree(trap); + return err; + } + + return 0; +} + +static int ocelot_trap_del(struct ocelot *ocelot, int port, + unsigned long cookie) +{ + struct ocelot_vcap_block *block_vcap_is2; + struct ocelot_vcap_filter *trap; + + block_vcap_is2 = &ocelot->block[VCAP_IS2]; + + trap = ocelot_vcap_block_find_filter_by_id(block_vcap_is2, cookie, + false); + if (!trap) + return 0; + + trap->ingress_port_mask &= ~BIT(port); + if (!trap->ingress_port_mask) + return ocelot_vcap_filter_del(ocelot, trap); + + return ocelot_vcap_filter_replace(ocelot, trap); +} + +static int ocelot_l2_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_add(ocelot, port, l2_cookie, + ocelot_populate_l2_ptp_trap_key); +} + +static int ocelot_l2_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long l2_cookie = ocelot->num_phys_ports + 1; + + return ocelot_trap_del(ocelot, port, l2_cookie); +} + +static int ocelot_ipv4_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_add(ocelot, port, ipv4_ev_cookie, + ocelot_populate_ipv4_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv4_gen_cookie, + ocelot_populate_ipv4_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + + return err; +} + +static int ocelot_ipv4_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv4_gen_cookie = ocelot->num_phys_ports + 2; + unsigned long ipv4_ev_cookie = ocelot->num_phys_ports + 3; + int err; + + err = ocelot_trap_del(ocelot, port, ipv4_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv4_gen_cookie); + return err; +} + +static int ocelot_ipv6_ptp_trap_add(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_add(ocelot, port, ipv6_ev_cookie, + ocelot_populate_ipv6_ptp_event_trap_key); + if (err) + return err; + + err = ocelot_trap_add(ocelot, port, ipv6_gen_cookie, + ocelot_populate_ipv6_ptp_general_trap_key); + if (err) + ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + + return err; +} + +static int ocelot_ipv6_ptp_trap_del(struct ocelot *ocelot, int port) +{ + unsigned long ipv6_gen_cookie = ocelot->num_phys_ports + 4; + unsigned long ipv6_ev_cookie = ocelot->num_phys_ports + 5; + int err; + + err = ocelot_trap_del(ocelot, port, ipv6_ev_cookie); + err |= ocelot_trap_del(ocelot, port, ipv6_gen_cookie); + return err; +} + +static int ocelot_setup_ptp_traps(struct ocelot *ocelot, int port, + bool l2, bool l4) +{ + int err; + + if (l2) + err = ocelot_l2_ptp_trap_add(ocelot, port); + else + err = ocelot_l2_ptp_trap_del(ocelot, port); + if (err) + return err; + + if (l4) { + err = ocelot_ipv4_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv4; + + err = ocelot_ipv6_ptp_trap_add(ocelot, port); + if (err) + goto err_ipv6; + } else { + err = ocelot_ipv4_ptp_trap_del(ocelot, port); + + err |= ocelot_ipv6_ptp_trap_del(ocelot, port); + } + if (err) + return err; + + return 0; + +err_ipv6: + ocelot_ipv4_ptp_trap_del(ocelot, port); +err_ipv4: + if (l2) + ocelot_l2_ptp_trap_del(ocelot, port); + return err; +} + int ocelot_hwstamp_get(struct ocelot *ocelot, int port, struct ifreq *ifr) { return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config, @@ -1288,7 +1507,9 @@ EXPORT_SYMBOL(ocelot_hwstamp_get); int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + bool l2 = false, l4 = false; struct hwtstamp_config cfg; + int err; if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) return -EFAULT; @@ -1323,19 +1544,37 @@ int ocelot_hwstamp_set(struct ocelot *ocelot, int port, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + l4 = true; + break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + l2 = true; + break; case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + l2 = true; + l4 = true; break; default: mutex_unlock(&ocelot->ptp_lock); return -ERANGE; } + err = ocelot_setup_ptp_traps(ocelot, port, l2, l4); + if (err) + return err; + + if (l2 && l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + else if (l2) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; + else if (l4) + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + else + cfg.rx_filter = HWTSTAMP_FILTER_NONE; + /* Commit back the result & save it */ memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg)); mutex_unlock(&ocelot->ptp_lock); From c49a35eedfef08bffd46b53c25dbf9d6016a86ff Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:45 +0200 Subject: [PATCH 93/94] net: mscc: ocelot: correctly report the timestamping RX filters in ethtool The driver doesn't support RX timestamping for non-PTP packets, but it declares that it does. Restrict the reported RX filters to PTP v2 over L2 and over L4. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 9b7be93cbb0d..409cde1e59c6 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1677,7 +1677,10 @@ int ocelot_get_ts_info(struct ocelot *ocelot, int port, SOF_TIMESTAMPING_RAW_HARDWARE; info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | BIT(HWTSTAMP_TX_ONESTEP_SYNC); - info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT); return 0; } From b3612ccdf2841c64ae7a8dd9e780c91240093fe6 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 26 Nov 2021 13:39:26 +0100 Subject: [PATCH 94/94] net: dsa: microchip: implement multi-bridge support Current driver version is able to handle only one bridge at time. Configuring two bridges on two different ports would end up shorting this bridges by HW. To reproduce it: ip l a name br0 type bridge ip l a name br1 type bridge ip l s dev br0 up ip l s dev br1 up ip l s lan1 master br0 ip l s dev lan1 up ip l s lan2 master br1 ip l s dev lan2 up Ping on lan1 and get response on lan2, which should not happen. This happened, because current driver version is storing one global "Port VLAN Membership" and applying it to all ports which are members of any bridge. To solve this issue, we need to handle each port separately. This patch is dropping the global port member storage and calculating membership dynamically depending on STP state and bridge participation. Note: STP support was broken before this patch and should be fixed separately. Fixes: c2e866911e25 ("net: dsa: microchip: break KSZ9477 DSA driver into two files") Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Link: https://lore.kernel.org/r/20211126123926.2981028-1-o.rempel@pengutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/dsa/microchip/ksz8795.c | 56 +++------------------- drivers/net/dsa/microchip/ksz9477.c | 66 ++++---------------------- drivers/net/dsa/microchip/ksz_common.c | 50 ++++++++++--------- drivers/net/dsa/microchip/ksz_common.h | 4 -- 4 files changed, 43 insertions(+), 133 deletions(-) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 43fc3087aeb3..013e9c02be71 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -1002,57 +1002,32 @@ static void ksz8_cfg_port_member(struct ksz_device *dev, int port, u8 member) data &= ~PORT_VLAN_MEMBERSHIP; data |= (member & dev->port_mask); ksz_pwrite8(dev, port, P_MIRROR_CTRL, data); - dev->ports[port].member = member; } static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) { struct ksz_device *dev = ds->priv; - int forward = dev->member; struct ksz_port *p; - int member = -1; u8 data; - p = &dev->ports[port]; - ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - /* Port is a member of a bridge. */ - if (dev->br_member & BIT(port)) { - dev->member |= BIT(port); - member = dev->member; - } else { - member = dev->host_mask | p->vid_member; - } break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port < dev->phy_port_cnt && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -1060,22 +1035,11 @@ static void ksz8_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) } ksz_pwrite8(dev, port, P_STP_CTRL, data); + + p = &dev->ports[port]; p->stp_state = state; - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz8_cfg_port_member(dev, port, (u8)member); - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & BIT(port)) - dev->member &= ~BIT(port); - } - - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); + ksz_update_port_member(dev, port); } static void ksz8_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1341,7 +1305,7 @@ static void ksz8795_cpu_interface_select(struct ksz_device *dev, int port) static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; struct ksz8 *ksz8 = dev->priv; const u32 *masks; u8 member; @@ -1368,10 +1332,11 @@ static void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port) if (!ksz_is_ksz88x3(dev)) ksz8795_cpu_interface_select(dev, port); - member = dev->port_mask; + member = dsa_user_ports(ds); } else { - member = dev->host_mask | p->vid_member; + member = BIT(dsa_upstream_port(ds, port)); } + ksz8_cfg_port_member(dev, port, member); } @@ -1392,20 +1357,13 @@ static void ksz8_config_cpu_port(struct dsa_switch *ds) ksz_cfg(dev, regs[S_TAIL_TAG_CTRL], masks[SW_TAIL_TAG_ENABLE], true); p = &dev->ports[dev->cpu_port]; - p->vid_member = dev->port_mask; p->on = 1; ksz8_port_setup(dev, dev->cpu_port, true); - dev->member = dev->host_mask; for (i = 0; i < dev->phy_port_cnt; i++) { p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = BIT(i); - p->member = dev->port_mask; ksz8_port_stp_state_set(ds, i, BR_STATE_DISABLED); /* Last port may be disabled. */ diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 854e25f43fa7..353b5f981740 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -391,7 +391,6 @@ static void ksz9477_cfg_port_member(struct ksz_device *dev, int port, u8 member) { ksz_pwrite32(dev, port, REG_PORT_VLAN_MEMBERSHIP__4, member); - dev->ports[port].member = member; } static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, @@ -400,8 +399,6 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, struct ksz_device *dev = ds->priv; struct ksz_port *p = &dev->ports[port]; u8 data; - int member = -1; - int forward = dev->member; ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); @@ -409,40 +406,18 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, switch (state) { case BR_STATE_DISABLED: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port) - member = 0; break; case BR_STATE_LISTENING: data |= (PORT_RX_ENABLE | PORT_LEARN_DISABLE); - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; case BR_STATE_LEARNING: data |= PORT_RX_ENABLE; break; case BR_STATE_FORWARDING: data |= (PORT_TX_ENABLE | PORT_RX_ENABLE); - - /* This function is also used internally. */ - if (port == dev->cpu_port) - break; - - member = dev->host_mask | p->vid_member; - mutex_lock(&dev->dev_mutex); - - /* Port is a member of a bridge. */ - if (dev->br_member & (1 << port)) { - dev->member |= (1 << port); - member = dev->member; - } - mutex_unlock(&dev->dev_mutex); break; case BR_STATE_BLOCKING: data |= PORT_LEARN_DISABLE; - if (port != dev->cpu_port && - p->stp_state == BR_STATE_DISABLED) - member = dev->host_mask | p->vid_member; break; default: dev_err(ds->dev, "invalid STP state: %d\n", state); @@ -451,23 +426,8 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, ksz_pwrite8(dev, port, P_STP_CTRL, data); p->stp_state = state; - mutex_lock(&dev->dev_mutex); - /* Port membership may share register with STP state. */ - if (member >= 0 && member != p->member) - ksz9477_cfg_port_member(dev, port, (u8)member); - /* Check if forwarding needs to be updated. */ - if (state != BR_STATE_FORWARDING) { - if (dev->br_member & (1 << port)) - dev->member &= ~(1 << port); - } - - /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. - */ - if (forward != dev->member) - ksz_update_port_member(dev, port); - mutex_unlock(&dev->dev_mutex); + ksz_update_port_member(dev, port); } static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) @@ -1168,10 +1128,10 @@ static void ksz9477_phy_errata_setup(struct ksz_device *dev, int port) static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) { - u8 data8; - u8 member; - u16 data16; struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 data8, member; + u16 data16; /* enable tag tail for host port */ if (cpu_port) @@ -1250,12 +1210,12 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_pwrite8(dev, port, REG_PORT_XMII_CTRL_1, data8); p->phydev.duplex = 1; } - mutex_lock(&dev->dev_mutex); + if (cpu_port) - member = dev->port_mask; + member = dsa_user_ports(ds); else - member = dev->host_mask | p->vid_member; - mutex_unlock(&dev->dev_mutex); + member = BIT(dsa_upstream_port(ds, port)); + ksz9477_cfg_port_member(dev, port, member); /* clear pending interrupts */ @@ -1276,8 +1236,6 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) const char *prev_mode; dev->cpu_port = i; - dev->host_mask = (1 << dev->cpu_port); - dev->port_mask |= dev->host_mask; p = &dev->ports[i]; /* Read from XMII register to determine host port @@ -1312,23 +1270,15 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) /* enable cpu port */ ksz9477_port_setup(dev, i, true); - p->vid_member = dev->port_mask; p->on = 1; } } - dev->member = dev->host_mask; - for (i = 0; i < dev->port_cnt; i++) { if (i == dev->cpu_port) continue; p = &dev->ports[i]; - /* Initialize to non-zero so that ksz_cfg_port_member() will - * be called. - */ - p->vid_member = (1 << i); - p->member = dev->port_mask; ksz9477_port_stp_state_set(ds, i, BR_STATE_DISABLED); p->on = 1; if (i < dev->phy_port_cnt) diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 7c2968a639eb..8a04302018dc 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -22,21 +22,40 @@ void ksz_update_port_member(struct ksz_device *dev, int port) { - struct ksz_port *p; + struct ksz_port *p = &dev->ports[port]; + struct dsa_switch *ds = dev->ds; + u8 port_member = 0, cpu_port; + const struct dsa_port *dp; int i; - for (i = 0; i < dev->port_cnt; i++) { - if (i == port || i == dev->cpu_port) + if (!dsa_is_user_port(ds, port)) + return; + + dp = dsa_to_port(ds, port); + cpu_port = BIT(dsa_upstream_port(ds, port)); + + for (i = 0; i < ds->num_ports; i++) { + const struct dsa_port *other_dp = dsa_to_port(ds, i); + struct ksz_port *other_p = &dev->ports[i]; + u8 val = 0; + + if (!dsa_is_user_port(ds, i)) continue; - p = &dev->ports[i]; - if (!(dev->member & (1 << i))) + if (port == i) + continue; + if (!dp->bridge_dev || dp->bridge_dev != other_dp->bridge_dev) continue; - /* Port is a member of the bridge and is forwarding. */ - if (p->stp_state == BR_STATE_FORWARDING && - p->member != dev->member) - dev->dev_ops->cfg_port_member(dev, i, dev->member); + if (other_p->stp_state == BR_STATE_FORWARDING && + p->stp_state == BR_STATE_FORWARDING) { + val |= BIT(port); + port_member |= BIT(i); + } + + dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } + + dev->dev_ops->cfg_port_member(dev, port, port_member | cpu_port); } EXPORT_SYMBOL_GPL(ksz_update_port_member); @@ -175,12 +194,6 @@ EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats); int ksz_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member |= (1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * appropriate state so there is no need to do anything. */ @@ -192,13 +205,6 @@ EXPORT_SYMBOL_GPL(ksz_port_bridge_join); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) { - struct ksz_device *dev = ds->priv; - - mutex_lock(&dev->dev_mutex); - dev->br_member &= ~(1 << port); - dev->member &= ~(1 << port); - mutex_unlock(&dev->dev_mutex); - /* port_stp_state_set() will be called after to put the port in * forwarding state so there is no need to do anything. */ diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 1597c63988b4..54b456bc8972 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -25,8 +25,6 @@ struct ksz_port_mib { }; struct ksz_port { - u16 member; - u16 vid_member; bool remove_tag; /* Remove Tag flag set, for ksz8795 only */ int stp_state; struct phy_device phydev; @@ -83,8 +81,6 @@ struct ksz_device { struct ksz_port *ports; struct delayed_work mib_read; unsigned long mib_read_interval; - u16 br_member; - u16 member; u16 mirror_rx; u16 mirror_tx; u32 features; /* chip specific features */