Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from David Miller:

 1) IPsec compat fixes, from Dmitry Safonov.

 2) Fix memory leak in xfrm_user_policy(). Fix from Yu Kuai.

 3) Fix polling in xsk sockets by using sk_poll_wait() instead of
    datagram_poll() which keys off of sk_wmem_alloc and such which xsk
    sockets do not update. From Xuan Zhuo.

 4) Missing init of rekey_data in cfgh80211, from Sara Sharon.

 5) Fix destroy of timer before init, from Davide Caratti.

 6) Missing CRYPTO_CRC32 selects in ethernet driver Kconfigs, from Arnd
    Bergmann.

 7) Missing error return in rtm_to_fib_config() switch case, from Zhang
    Changzhong.

 8) Fix some src/dest address handling in vrf and add a testcase. From
    Stephen Suryaputra.

 9) Fix multicast handling in Seville switches driven by mscc-ocelot
    driver. From Vladimir Oltean.

10) Fix proto value passed to skb delivery demux in udp, from Xin Long.

11) HW pkt counters not reported correctly in enetc driver, from Claudiu
    Manoil.

12) Fix deadlock in bridge, from Joseph Huang.

13) Missing of_node_pur() in dpaa2 driver, fromn Christophe JAILLET.

14) Fix pid fetching in bpftool when there are a lot of results, from
    Andrii Nakryiko.

15) Fix long timeouts in nft_dynset, from Pablo Neira Ayuso.

16) Various stymmac fixes, from Fugang Duan.

17) Fix null deref in tipc, from Cengiz Can.

18) When mss is biog, coose more resonable rcvq_space in tcp, fromn Eric
    Dumazet.

19) Revert a geneve change that likely isnt necessary, from Jakub
    Kicinski.

20) Avoid premature rx buffer reuse in various Intel driversm from Björn
    Töpel.

21) retain EcT bits during TIS reflection in tcp, from Wei Wang.

22) Fix Tso deferral wrt. cwnd limiting in tcp, from Neal Cardwell.

23) MPLS_OPT_LSE_LABEL attribute is 342 ot 8 bits, from Guillaume Nault

24) Fix propagation of 32-bit signed bounds in bpf verifier and add test
    cases, from Alexei Starovoitov.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (81 commits)
  selftests: fix poll error in udpgro.sh
  selftests/bpf: Fix "dubious pointer arithmetic" test
  selftests/bpf: Fix array access with signed variable test
  selftests/bpf: Add test for signed 32-bit bound check bug
  bpf: Fix propagation of 32-bit signed bounds from 64-bit bounds.
  MAINTAINERS: Add entry for Marvell Prestera Ethernet Switch driver
  net: sched: Fix dump of MPLS_OPT_LSE_LABEL attribute in cls_flower
  net/mlx4_en: Handle TX error CQE
  net/mlx4_en: Avoid scheduling restart task if it is already running
  tcp: fix cwnd-limited bug for TSO deferral where we send nothing
  net: flow_offload: Fix memory leak for indirect flow block
  tcp: Retain ECT bits for tos reflection
  ethtool: fix stack overflow in ethnl_parse_bitset()
  e1000e: fix S0ix flow to allow S0i3.2 subset entry
  ice: avoid premature Rx buffer reuse
  ixgbe: avoid premature Rx buffer reuse
  i40e: avoid premature Rx buffer reuse
  igb: avoid transmit queue timeout in xdp path
  igb: use xdp_do_flush
  igb: skb add metasize for xdp
  ...

8 files changed, 181 insertions, 31 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 52414058a627..5861446d0777 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -456,10 +456,10 @@ static struct bpf_align_test tests[] = {
 			 */
 			{7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
 			/* Checked s>=0 */
-			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+			{9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* packet pointer + nonnegative (4n+2) */
-			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
-			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+			{11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+			{13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
 			/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
 			 * We checked the bounds, but it might have been able
 			 * to overflow if the packet pointer started in the
@@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = {
 			 * So we did not get a 'range' on R6, and the access
 			 * attempt will fail.
 			 */
-			{15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+			{15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
 		}
 	},
 	{
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index c1650548433c..fddbc5db5d6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -217,9 +217,15 @@ void test_ringbuf(void)
 	if (CHECK(err, "join_bg", "err %d\n", err))
 		goto cleanup;
 
-	if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret))
+	if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret))
 		goto cleanup;
 
+	/* due to timing variations, there could still be non-notified
+	 * samples, so consume them here to collect all the samples
+	 */
+	err = ring_buffer__consume(ringbuf);
+	CHECK(err < 0, "rb_consume", "failed: %d\b", err);
+
 	/* 3 rounds, 2 samples each */
 	cnt = atomic_xchg(&sample_cnt, 0);
 	CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt);
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 78e450609803..d37161e59bb2 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -81,7 +81,7 @@ void test_ringbuf_multi(void)
 
 	/* poll for samples, should get 2 ringbufs back */
 	err = ring_buffer__poll(ringbuf, -1);
-	if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err))
+	if (CHECK(err != 2, "poll_res", "expected 2 records, got %d\n", err))
 		goto cleanup;
 
 	/* expect extra polling to return nothing */
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 43c9cda199b8..b99bb8ed3ed4 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -184,9 +184,7 @@ def bpftool_prog_list(expected=None, ns=""):
 def bpftool_map_list(expected=None, ns=""):
     _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
     # Remove the base maps
-    for m in base_maps:
-        if m in maps:
-            maps.remove(m)
+    maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names]
     if expected is not None:
         if len(maps) != expected:
             fail(True, "%d BPF maps loaded, expected %d" %
@@ -716,13 +714,11 @@ def test_multi_prog(simdev, sim, obj, modename, modeid):
     fail(ret == 0, "Replaced one of programs without -force")
     check_extack(err, "XDP program already attached.", args)
 
-    if modename == "" or modename == "drv":
-        othermode = "" if modename == "drv" else "drv"
-        start_test("Test multi-attachment XDP - detach...")
-        ret, _, err = sim.unset_xdp(othermode, force=True,
-                                    fail=False, include_stderr=True)
-        fail(ret == 0, "Removed program with a bad mode")
-        check_extack(err, "program loaded with different flags.", args)
+    start_test("Test multi-attachment XDP - remove without mode...")
+    ret, _, err = sim.unset_xdp("", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program without a mode flag")
+    check_extack(err, "More than one program loaded, unset mode is ambiguous.", args)
 
     sim.unset_xdp("offload")
     xdp = sim.ip_link_show(xdp=True)["xdp"]
@@ -772,6 +768,9 @@ ret, progs = bpftool("prog", fail=False)
 skip(ret != 0, "bpftool not installed")
 base_progs = progs
 _, base_maps = bpftool("map")
+base_map_names = [
+    'pid_iter.rodata' # created on each bpftool invocation
+]
 
 # Check netdevsim
 ret, out = cmd("modprobe netdevsim", fail=False)
@@ -913,11 +912,18 @@ try:
 
     sim.tc_flush_filters()
 
+    start_test("Test TC offloads failure...")
+    sim.dfs["dev/bpf_bind_verifier_accept"] = 0
+    ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True,
+                                         fail=False, include_stderr=True)
+    fail(ret == 0, "TC filter did not reject with TC offloads enabled")
+    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+    sim.dfs["dev/bpf_bind_verifier_accept"] = 1
+
     start_test("Test TC offloads work...")
     ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret != 0, "TC filter did not load with TC offloads enabled")
-    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
 
     start_test("Test TC offload basics...")
     dfs = simdev.dfs_get_bound_progs(expected=1)
@@ -941,6 +947,7 @@ try:
     start_test("Test disabling TC offloads is rejected while filters installed...")
     ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
     fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...")
+    sim.set_ethtool_tc_offloads(True)
 
     start_test("Test qdisc removal frees things...")
     sim.tc_flush_filters()
@@ -999,18 +1006,8 @@ try:
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
     check_extack(err,
-                 "native and generic XDP can't be active at the same time.",
+                 "Native and generic XDP can't be active at the same time.",
                  args)
-    ret, _, err = sim.set_xdp(obj, "", force=True,
-                              fail=False, include_stderr=True)
-    fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack(err, "program loaded with different flags.", args)
-
-    start_test("Test XDP prog remove with bad flags...")
-    ret, _, err = sim.unset_xdp("", force=True,
-                                fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode")
-    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test MTU restrictions...")
     ret, _ = sim.set_mtu(9000, fail=False)
@@ -1040,10 +1037,19 @@ try:
     offload = bpf_pinned("/sys/fs/bpf/offload")
     ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True)
     fail(ret == 0, "attached offloaded XDP program to drv")
-    check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args)
+    check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args)
     rm("/sys/fs/bpf/offload")
     sim.wait_for_flush()
 
+    start_test("Test XDP load failure...")
+    sim.dfs["dev/bpf_bind_verifier_accept"] = 0
+    ret, _, err = bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload",
+                                 dev=sim['ifname'], fail=False, include_stderr=True)
+    fail(ret == 0, "verifier should fail on load")
+    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+    sim.dfs["dev/bpf_bind_verifier_accept"] = 1
+    sim.wait_for_flush()
+
     start_test("Test XDP offload...")
     _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True)
     ipl = sim.ip_link_show(xdp=True)
@@ -1051,7 +1057,6 @@ try:
     progs = bpftool_prog_list(expected=1)
     prog = progs[0]
     fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID")
-    check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
 
     start_test("Test XDP offload is device bound...")
     dfs = simdev.dfs_get_bound_progs(expected=1)
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index 1c4b1939f5a8..bed53b561e04 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -68,7 +68,7 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
 	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
-	BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1),
+	BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1),
 	BPF_MOV32_IMM(BPF_REG_1, 0),
 	BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
 	BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index dac40de3f868..57ed67b86074 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -703,3 +703,44 @@
 	.fixup_map_hash_8b = { 3 },
 	.result = ACCEPT,
 },
+{
+	"bounds checks after 32-bit truncation. test 1",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+	/* This used to reduce the max bound to 0x7fffffff */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 3 },
+	.errstr_unpriv = "R0 leaks addr",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+},
+{
+	"bounds checks after 32-bit truncation. test 2",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+	BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1),
+	BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 3 },
+	.errstr_unpriv = "R0 leaks addr",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index fb5c55dd6df8..02b0b9ead40b 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -256,6 +256,28 @@ setup_cmd_nsb()
 	fi
 }
 
+setup_cmd_nsc()
+{
+	local cmd="$*"
+	local rc
+
+	run_cmd_nsc ${cmd}
+	rc=$?
+	if [ $rc -ne 0 ]; then
+		# show user the command if not done so already
+		if [ "$VERBOSE" = "0" ]; then
+			echo "setup command: $cmd"
+		fi
+		echo "failed. stopping tests"
+		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+			echo
+			echo "hit enter to continue"
+			read a
+		fi
+		exit $rc
+	fi
+}
+
 # set sysctl values in NS-A
 set_sysctl()
 {
@@ -471,6 +493,36 @@ setup()
 	sleep 1
 }
 
+setup_lla_only()
+{
+	# make sure we are starting with a clean slate
+	kill_procs
+	cleanup 2>/dev/null
+
+	log_debug "Configuring network namespaces"
+	set -e
+
+	create_ns ${NSA} "-" "-"
+	create_ns ${NSB} "-" "-"
+	create_ns ${NSC} "-" "-"
+	connect_ns ${NSA} ${NSA_DEV} "-" "-" \
+		   ${NSB} ${NSB_DEV} "-" "-"
+	connect_ns ${NSA} ${NSA_DEV2} "-" "-" \
+		   ${NSC} ${NSC_DEV}  "-" "-"
+
+	NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV})
+	NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV})
+	NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV})
+
+	create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-"
+	ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF}
+	ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF}
+
+	set +e
+
+	sleep 1
+}
+
 ################################################################################
 # IPv4
 
@@ -3787,10 +3839,53 @@ use_case_br()
 	setup_cmd_nsb ip li del vlan100 2>/dev/null
 }
 
+# VRF only.
+# ns-A device is connected to both ns-B and ns-C on a single VRF but only has
+# LLA on the interfaces
+use_case_ping_lla_multi()
+{
+	setup_lla_only
+	# only want reply from ns-A
+	setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1
+	setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1
+
+	log_start
+	run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+	log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B"
+
+	run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+	log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C"
+
+	# cycle/flap the first ns-A interface
+	setup_cmd ip link set ${NSA_DEV} down
+	setup_cmd ip link set ${NSA_DEV} up
+	sleep 1
+
+	log_start
+	run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+	log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B"
+	run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+	log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C"
+
+	# cycle/flap the second ns-A interface
+	setup_cmd ip link set ${NSA_DEV2} down
+	setup_cmd ip link set ${NSA_DEV2} up
+	sleep 1
+
+	log_start
+	run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+	log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B"
+	run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+	log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C"
+}
+
 use_cases()
 {
 	log_section "Use cases"
+	log_subsection "Device enslaved to bridge"
 	use_case_br
+	log_subsection "Ping LLA with multiple interfaces"
+	use_case_ping_lla_multi
 }
 
 ################################################################################
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index db3d4a8b5a4c..76a24052f4b4 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -113,6 +113,9 @@ static void do_poll(int fd, int timeout_ms)
 				interrupted = true;
 				break;
 			}
+
+			/* no events and more time to wait, do poll again */
+			continue;
 		}
 		if (pfd.revents != POLLIN)
 			error(1, errno, "poll: 0x%x expected 0x%x\n",