Merge tag 'net-5.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf, netfilter, and ieee802154.

  Current release - regressions:

   - Partially revert "net/smc: Add netlink net namespace support", fix
     uABI breakage

   - netfilter:
      - nft_ct: fix use after free when attaching zone template
      - nft_byteorder: track register operations

  Previous releases - regressions:

   - ipheth: fix EOVERFLOW in ipheth_rcvbulk_callback

   - phy: qca8081: fix speeds lower than 2.5Gb/s

   - sched: fix use-after-free in tc_new_tfilter()

  Previous releases - always broken:

   - tcp: fix mem under-charging with zerocopy sendmsg()

   - tcp: add missing tcp_skb_can_collapse() test in
     tcp_shift_skb_data()

   - neigh: do not trigger immediate probes on NUD_FAILED from
     neigh_managed_work, avoid a deadlock

   - bpf: use VM_MAP instead of VM_ALLOC for ringbuf, avoid KASAN
     false-positives

   - netfilter: nft_reject_bridge: fix for missing reply from prerouting

   - smc: forward wakeup to smc socket waitqueue after fallback

   - ieee802154:
      - return meaningful error codes from the netlink helpers
      - mcr20a: fix lifs/sifs periods
      - at86rf230, ca8210: stop leaking skbs on error paths

   - macsec: add missing un-offload call for NETDEV_UNREGISTER of parent

   - ax25: add refcount in ax25_dev to avoid UAF bugs

   - eth: mlx5e:
      - fix SFP module EEPROM query
      - fix broken SKB allocation in HW-GRO
      - IPsec offload: fix tunnel mode crypto for non-TCP/UDP flows

   - eth: amd-xgbe:
      - fix skb data length underflow
      - ensure reset of the tx_timer_active flag, avoid Tx timeouts

   - eth: stmmac: fix runtime pm use in stmmac_dvr_remove()

   - eth: e1000e: handshake with CSME starts from Alder Lake platforms"

* tag 'net-5.17-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  ax25: fix reference count leaks of ax25_dev
  net: stmmac: ensure PTP time register reads are consistent
  net: ipa: request IPA register values be retained
  dt-bindings: net: qcom,ipa: add optional qcom,qmp property
  tools/resolve_btfids: Do not print any commands when building silently
  bpf: Use VM_MAP instead of VM_ALLOC for ringbuf
  net, neigh: Do not trigger immediate probes on NUD_FAILED from neigh_managed_work
  tcp: add missing tcp_skb_can_collapse() test in tcp_shift_skb_data()
  net: sparx5: do not refer to skb after passing it on
  Partially revert "net/smc: Add netlink net namespace support"
  net/mlx5e: Avoid field-overflowing memcpy()
  net/mlx5e: Use struct_group() for memcpy() region
  net/mlx5e: Avoid implicit modify hdr for decap drop rule
  net/mlx5e: IPsec: Fix tunnel mode crypto offload for non TCP/UDP traffic
  net/mlx5e: IPsec: Fix crypto offload for non TCP/UDP encapsulated traffic
  net/mlx5e: Don't treat small ceil values as unlimited in HTB offload
  net/mlx5: E-Switch, Fix uninitialized variable modact
  net/mlx5e: Fix handling of wrong devices during bond netevent
  net/mlx5e: Fix broken SKB allocation in HW-GRO
  net/mlx5e: Fix wrong calculation of header index in HW_GRO
  ...

4 files changed, 229 insertions, 8 deletions

diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
index ebf68dce5504..2893e9f2f1e0 100644
--- a/tools/testing/selftests/bpf/test_lirc_mode2_user.c
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -28,7 +28,6 @@
 // 5. We can read keycode from same /dev/lirc device
 
 #include <linux/bpf.h>
-#include <linux/lirc.h>
 #include <linux/input.h>
 #include <errno.h>
 #include <stdio.h>
diff --git a/tools/testing/selftests/netfilter/nft_concat_range.sh b/tools/testing/selftests/netfilter/nft_concat_range.sh
index ed61f6cab60f..df322e47a54f 100755
--- a/tools/testing/selftests/netfilter/nft_concat_range.sh
+++ b/tools/testing/selftests/netfilter/nft_concat_range.sh
@@ -27,7 +27,7 @@ TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
        net6_port_net6_port net_port_mac_proto_net"
 
 # Reported bugs, also described by TYPE_ variables below
-BUGS="flush_remove_add"
+BUGS="flush_remove_add reload"
 
 # List of possible paths to pktgen script from kernel tree for performance tests
 PKTGEN_SCRIPT_PATHS="
@@ -354,6 +354,23 @@ TYPE_flush_remove_add="
 display		Add two elements, flush, re-add
 "
 
+TYPE_reload="
+display		net,mac with reload
+type_spec	ipv4_addr . ether_addr
+chain_spec	ip daddr . ether saddr
+dst		addr4
+src		mac
+start		1
+count		1
+src_delta	2000
+tools		sendip nc bash
+proto		udp
+
+race_repeat	0
+
+perf_duration	0
+"
+
 # Set template for all tests, types and rules are filled in depending on test
 set_template='
 flush ruleset
@@ -1473,6 +1490,59 @@ test_bug_flush_remove_add() {
 	nft flush ruleset
 }
 
+# - add ranged element, check that packets match it
+# - reload the set, check packets still match
+test_bug_reload() {
+	setup veth send_"${proto}" set || return ${KSELFTEST_SKIP}
+	rstart=${start}
+
+	range_size=1
+	for i in $(seq "${start}" $((start + count))); do
+		end=$((start + range_size))
+
+		# Avoid negative or zero-sized port ranges
+		if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+			start=${end}
+			end=$((end + 1))
+		fi
+		srcstart=$((start + src_delta))
+		srcend=$((end + src_delta))
+
+		add "$(format)" || return 1
+		range_size=$((range_size + 1))
+		start=$((end + range_size))
+	done
+
+	# check kernel does allocate pcpu sctrach map
+	# for reload with no elemet add/delete
+	( echo flush set inet filter test ;
+	  nft list set inet filter test ) | nft -f -
+
+	start=${rstart}
+	range_size=1
+
+	for i in $(seq "${start}" $((start + count))); do
+		end=$((start + range_size))
+
+		# Avoid negative or zero-sized port ranges
+		if [ $((end / 65534)) -gt $((start / 65534)) ]; then
+			start=${end}
+			end=$((end + 1))
+		fi
+		srcstart=$((start + src_delta))
+		srcend=$((end + src_delta))
+
+		for j in $(seq ${start} $((range_size / 2 + 1)) ${end}); do
+			send_match "${j}" $((j + src_delta)) || return 1
+		done
+
+		range_size=$((range_size + 1))
+		start=$((end + range_size))
+	done
+
+	nft flush ruleset
+}
+
 test_reported_issues() {
 	eval test_bug_"${subtest}"
 }
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 349a319a9e51..79fe627b9e81 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -899,6 +899,144 @@ EOF
 	ip netns exec "$ns0" nft delete table $family nat
 }
 
+test_stateless_nat_ip()
+{
+	local lret=0
+
+	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
+
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping $ns1 from $ns2 before loading stateless rules"
+		return 1
+	fi
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table ip stateless {
+	map xlate_in {
+		typeof meta iifname . ip saddr . ip daddr : ip daddr
+		elements = {
+			"veth1" . 10.0.2.99 . 10.0.1.99 : 10.0.2.2,
+		}
+	}
+	map xlate_out {
+		typeof meta iifname . ip saddr . ip daddr : ip daddr
+		elements = {
+			"veth0" . 10.0.1.99 . 10.0.2.2 : 10.0.2.99
+		}
+	}
+
+	chain prerouting {
+		type filter hook prerouting priority -400; policy accept;
+		ip saddr set meta iifname . ip saddr . ip daddr map @xlate_in
+		ip daddr set meta iifname . ip saddr . ip daddr map @xlate_out
+	}
+}
+EOF
+	if [ $? -ne 0 ]; then
+		echo "SKIP: Could not add ip statless rules"
+		return $ksft_skip
+	fi
+
+	reset_counters
+
+	ip netns exec "$ns2" ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping $ns1 from $ns2 with stateless rules"
+		lret=1
+	fi
+
+	# ns1 should have seen packets from .2.2, due to stateless rewrite.
+	expect="packets 1 bytes 84"
+	cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter "$ns1" ns0insl "$expect" "test_stateless 1"
+		lret=1
+	fi
+
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec "$ns2" nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns2" ns1$dir "$expect" "test_stateless 2"
+			lret=1
+		fi
+	done
+
+	# ns1 should not have seen packets from ns2, due to masquerade
+	expect="packets 0 bytes 0"
+	for dir in "in" "out" ; do
+		cnt=$(ip netns exec "$ns1" nft list counter inet filter ns2${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns1" ns0$dir "$expect" "test_stateless 3"
+			lret=1
+		fi
+
+		cnt=$(ip netns exec "$ns0" nft list counter inet filter ns1${dir} | grep -q "$expect")
+		if [ $? -ne 0 ]; then
+			bad_counter "$ns0" ns1$dir "$expect" "test_stateless 4"
+			lret=1
+		fi
+	done
+
+	reset_counters
+
+	socat -h > /dev/null 2>&1
+	if [ $? -ne 0 ];then
+		echo "SKIP: Could not run stateless nat frag test without socat tool"
+		if [ $lret -eq 0 ]; then
+			return $ksft_skip
+		fi
+
+		ip netns exec "$ns0" nft delete table ip stateless
+		return $lret
+	fi
+
+	local tmpfile=$(mktemp)
+	dd if=/dev/urandom of=$tmpfile bs=4096 count=1 2>/dev/null
+
+	local outfile=$(mktemp)
+	ip netns exec "$ns1" timeout 3 socat -u UDP4-RECV:4233 OPEN:$outfile < /dev/null &
+	sc_r=$!
+
+	sleep 1
+	# re-do with large ping -> ip fragmentation
+	ip netns exec "$ns2" timeout 3 socat - UDP4-SENDTO:"10.0.1.99:4233" < "$tmpfile" > /dev/null
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: failed to test udp $ns1 to $ns2 with stateless ip nat" 1>&2
+		lret=1
+	fi
+
+	wait
+
+	cmp "$tmpfile" "$outfile"
+	if [ $? -ne 0 ]; then
+		ls -l "$tmpfile" "$outfile"
+		echo "ERROR: in and output file mismatch when checking udp with stateless nat" 1>&2
+		lret=1
+	fi
+
+	rm -f "$tmpfile" "$outfile"
+
+	# ns1 should have seen packets from 2.2, due to stateless rewrite.
+	expect="packets 3 bytes 4164"
+	cnt=$(ip netns exec "$ns1" nft list counter inet filter ns0insl | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		bad_counter "$ns1" ns0insl "$expect" "test_stateless 5"
+		lret=1
+	fi
+
+	ip netns exec "$ns0" nft delete table ip stateless
+	if [ $? -ne 0 ]; then
+		echo "ERROR: Could not delete table ip stateless" 1>&2
+		lret=1
+	fi
+
+	test $lret -eq 0 && echo "PASS: IP statless for $ns2"
+
+	return $lret
+}
+
 # ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
 for i in 0 1 2; do
 ip netns exec ns$i-$sfx nft -f /dev/stdin <<EOF
@@ -965,6 +1103,19 @@ table inet filter {
 EOF
 done
 
+# special case for stateless nat check, counter needs to
+# be done before (input) ip defragmentation
+ip netns exec ns1-$sfx nft -f /dev/stdin <<EOF
+table inet filter {
+	counter ns0insl {}
+
+	chain pre {
+		type filter hook prerouting priority -400; policy accept;
+		ip saddr 10.0.2.2 counter name "ns0insl"
+	}
+}
+EOF
+
 sleep 3
 # test basic connectivity
 for i in 1 2; do
@@ -1019,6 +1170,7 @@ $test_inet_nat && test_redirect inet
 $test_inet_nat && test_redirect6 inet
 
 test_port_shadowing
+test_stateless_nat_ip
 
 if [ $ret -ne 0 ];then
 	echo -n "FAIL: "
diff --git a/tools/testing/selftests/netfilter/nft_zones_many.sh b/tools/testing/selftests/netfilter/nft_zones_many.sh
index 04633119b29a..5a8db0b48928 100755
--- a/tools/testing/selftests/netfilter/nft_zones_many.sh
+++ b/tools/testing/selftests/netfilter/nft_zones_many.sh
@@ -9,7 +9,7 @@ ns="ns-$sfx"
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
-zones=20000
+zones=2000
 have_ct_tool=0
 ret=0
 
@@ -75,10 +75,10 @@ EOF
 
 	while [ $i -lt $max_zones ]; do
 		local start=$(date +%s%3N)
-		i=$((i + 10000))
+		i=$((i + 1000))
 		j=$((j + 1))
 		# nft rule in output places each packet in a different zone.
-		dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
+		dd if=/dev/zero of=/dev/stdout bs=8k count=1000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
 		if [ $? -ne 0 ] ;then
 			ret=1
 			break
@@ -86,7 +86,7 @@ EOF
 
 		stop=$(date +%s%3N)
 		local duration=$((stop-start))
-		echo "PASS: added 10000 entries in $duration ms (now $i total, loop $j)"
+		echo "PASS: added 1000 entries in $duration ms (now $i total, loop $j)"
 	done
 
 	if [ $have_ct_tool -eq 1 ]; then
@@ -128,11 +128,11 @@ test_conntrack_tool() {
 			break
 		fi
 
-		if [ $((i%10000)) -eq 0 ];then
+		if [ $((i%1000)) -eq 0 ];then
 			stop=$(date +%s%3N)
 
 			local duration=$((stop-start))
-			echo "PASS: added 10000 entries in $duration ms (now $i total)"
+			echo "PASS: added 1000 entries in $duration ms (now $i total)"
 			start=$stop
 		fi
 	done