Merge tag 'net-6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - phy: fix null-deref in phy_attach_direct

   - mac802154: fix possible double free upon parsing error

  Previous releases - regressions:

   - bpf: preserve reg parent/live fields when copying range info,
     prevent mis-verification of programs as safe

   - ip6: fix GRE tunnels not generating IPv6 link local addresses

   - phy: dp83822: fix null-deref on DP83825/DP83826 devices

   - sctp: do not check hb_timer.expires when resetting hb_timer

   - eth: mtk_sock: fix SGMII configuration after phylink conversion

  Previous releases - always broken:

   - eth: xdp: execute xdp_do_flush() before napi_complete_done()

   - skb: do not mix page pool and page referenced frags in GRO

   - bpf:
      - fix a possible task gone issue with bpf_send_signal[_thread]()
      - fix an off-by-one bug in bpf_mem_cache_idx() to select the right
        cache
      - add missing btf_put to register_btf_id_dtor_kfuncs
      - sockmap: fon't let sock_map_{close,destroy,unhash} call itself

   - gso: fix null-deref in skb_segment_list()

   - mctp: purge receive queues on sk destruction

   - fix UaF caused by accept on already connected socket in exotic
     socket families

   - tls: don't treat list head as an entry in tls_is_tx_ready()

   - netfilter: br_netfilter: disable sabotage_in hook after first
     suppression

   - wwan: t7xx: fix runtime PM implementation

  Misc:

   - MAINTAINERS: spring cleanup of networking maintainers"

* tag 'net-6.2-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (65 commits)
  mtk_sgmii: enable PCS polling to allow SFP work
  net: mediatek: sgmii: fix duplex configuration
  net: mediatek: sgmii: ensure the SGMII PHY is powered down on configuration
  MAINTAINERS: update SCTP maintainers
  MAINTAINERS: ipv6: retire Hideaki Yoshifuji
  mailmap: add John Crispin's entry
  MAINTAINERS: bonding: move Veaceslav Falico to CREDITS
  net: openvswitch: fix flow memory leak in ovs_flow_cmd_new
  net: ethernet: mtk_eth_soc: disable hardware DSA untagging for second MAC
  virtio-net: Keep stop() to follow mirror sequence of open()
  selftests: net: udpgso_bench_tx: Cater for pending datagrams zerocopy benchmarking
  selftests: net: udpgso_bench: Fix racing bug between the rx/tx programs
  selftests: net: udpgso_bench_rx/tx: Stop when wrong CLI args are provided
  selftests: net: udpgso_bench_rx: Fix 'used uninitialized' compiler warning
  can: mcp251xfd: mcp251xfd_ring_set_ringparam(): assign missing tx_obj_num_coalesce_irq
  can: isotp: split tx timer into transmission and timeout
  can: isotp: handle wait_event_interruptible() return values
  can: raw: fix CAN FD frame transmissions over CAN XL devices
  can: j1939: fix errant WARN_ON_ONCE in j1939_session_deactivate
  hv_netvsc: Fix missed pagebuf entries in netvsc_dma_map/unmap()
  ...

6 files changed, 152 insertions, 31 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 2cf0c7a3fe23..567e07c19ecc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -30,6 +30,8 @@
 #define MAX_STRERR_LEN 256
 #define MAX_TEST_NAME 80
 
+#define __always_unused	__attribute__((__unused__))
+
 #define _FAIL(errnum, fmt...)                                                  \
 	({                                                                     \
 		error_at_line(0, (errnum), __func__, __LINE__, fmt);           \
@@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype)
 	return socket_loopback_reuseport(family, sotype, -1);
 }
 
-static void test_insert_invalid(int family, int sotype, int mapfd)
+static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused,
+				int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_update: expected EBADF");
 }
 
-static void test_insert_opened(int family, int sotype, int mapfd)
+static void test_insert_opened(struct test_sockmap_listen *skel __always_unused,
+			       int family, int sotype, int mapfd)
 {
 	u32 key = 0;
 	u64 value;
@@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_insert_bound(int family, int sotype, int mapfd)
+static void test_insert_bound(struct test_sockmap_listen *skel __always_unused,
+			      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -386,7 +391,8 @@ close:
 	xclose(s);
 }
 
-static void test_insert(int family, int sotype, int mapfd)
+static void test_insert(struct test_sockmap_listen *skel __always_unused,
+			int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_insert(int family, int sotype, int mapfd)
+static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 value;
 	u32 key;
@@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_delete_after_close(int family, int sotype, int mapfd)
+static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd)
 		FAIL_ERRNO("map_delete: expected EINVAL/EINVAL");
 }
 
-static void test_lookup_after_insert(int family, int sotype, int mapfd)
+static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u64 cookie, value;
 	socklen_t len;
@@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_after_delete(int family, int sotype, int mapfd)
+static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	int err, s;
 	u64 value;
@@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd)
 	xclose(s);
 }
 
-static void test_lookup_32_bit_value(int family, int sotype, int mapfd)
+static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	u32 key, value32;
 	int err, s;
@@ -523,7 +534,8 @@ close:
 	xclose(s);
 }
 
-static void test_update_existing(int family, int sotype, int mapfd)
+static void test_update_existing(struct test_sockmap_listen *skel __always_unused,
+				 int family, int sotype, int mapfd)
 {
 	int s1, s2;
 	u64 value;
@@ -551,7 +563,7 @@ close_s1:
 /* Exercise the code path where we destroy child sockets that never
  * got accept()'ed, aka orphans, when parent socket gets closed.
  */
-static void test_destroy_orphan_child(int family, int sotype, int mapfd)
+static void do_destroy_orphan_child(int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -582,10 +594,38 @@ close_srv:
 	xclose(s);
 }
 
+static void test_destroy_orphan_child(struct test_sockmap_listen *skel,
+				      int family, int sotype, int mapfd)
+{
+	int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict);
+	int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+	const struct test {
+		int progfd;
+		enum bpf_attach_type atype;
+	} tests[] = {
+		{ -1, -1 },
+		{ msg_verdict, BPF_SK_MSG_VERDICT },
+		{ skb_verdict, BPF_SK_SKB_VERDICT },
+	};
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		if (t->progfd != -1 &&
+		    xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0)
+			return;
+
+		do_destroy_orphan_child(family, sotype, mapfd);
+
+		if (t->progfd != -1)
+			xbpf_prog_detach2(t->progfd, mapfd, t->atype);
+	}
+}
+
 /* Perform a passive open after removing listening socket from SOCKMAP
  * to ensure that callbacks get restored properly.
  */
-static void test_clone_after_delete(int family, int sotype, int mapfd)
+static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused,
+				    int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	socklen_t len;
@@ -621,7 +661,8 @@ close_srv:
  * SOCKMAP, but got accept()'ed only after the parent has been removed
  * from SOCKMAP, gets cloned without parent psock state or callbacks.
  */
-static void test_accept_after_delete(int family, int sotype, int mapfd)
+static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused,
+				     int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0;
@@ -675,7 +716,8 @@ close_srv:
 /* Check that child socket that got created and accepted while parent
  * was in a SOCKMAP is cloned without parent psock state or callbacks.
  */
-static void test_accept_before_delete(int family, int sotype, int mapfd)
+static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused,
+				      int family, int sotype, int mapfd)
 {
 	struct sockaddr_storage addr;
 	const u32 zero = 0, one = 1;
@@ -784,7 +826,8 @@ done:
 	return NULL;
 }
 
-static void test_syn_recv_insert_delete(int family, int sotype, int mapfd)
+static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused,
+					int family, int sotype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	struct sockaddr_storage addr;
@@ -847,7 +890,8 @@ static void *listen_thread(void *arg)
 	return NULL;
 }
 
-static void test_race_insert_listen(int family, int socktype, int mapfd)
+static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused,
+				    int family, int socktype, int mapfd)
 {
 	struct connect_accept_ctx ctx = { 0 };
 	const u32 zero = 0;
@@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		     int family, int sotype)
 {
 	const struct op_test {
-		void (*fn)(int family, int sotype, int mapfd);
+		void (*fn)(struct test_sockmap_listen *skel,
+			   int family, int sotype, int mapfd);
 		const char *name;
 		int sotype;
 	} tests[] = {
@@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map,
 		if (!test__start_subtest(s))
 			continue;
 
-		t->fn(family, sotype, map_fd);
+		t->fn(skel, family, sotype, map_fd);
 		test_ops_cleanup(map);
 	}
 }
diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c
index 68b14fdfebdb..d63fd8991b03 100644
--- a/tools/testing/selftests/bpf/verifier/search_pruning.c
+++ b/tools/testing/selftests/bpf/verifier/search_pruning.c
@@ -225,3 +225,39 @@
 	.result_unpriv = ACCEPT,
 	.insn_processed = 15,
 },
+/* The test performs a conditional 64-bit write to a stack location
+ * fp[-8], this is followed by an unconditional 8-bit write to fp[-8],
+ * then data is read from fp[-8]. This sequence is unsafe.
+ *
+ * The test would be mistakenly marked as safe w/o dst register parent
+ * preservation in verifier.c:copy_register_state() function.
+ *
+ * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the
+ * checkpoint state after conditional 64-bit assignment.
+ */
+{
+	"write tracking and register parent chain bug",
+	.insns = {
+	/* r6 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	/* r0 = ktime_get_ns() */
+	BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+	/* if r0 > r6 goto +1 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1),
+	/* *(u64 *)(r10 - 8) = 0xdeadbeef */
+	BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef),
+	/* r1 = 42 */
+	BPF_MOV64_IMM(BPF_REG_1, 42),
+	/* *(u8 *)(r10 - 8) = r1 */
+	BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8),
+	/* r2 = *(u64 *)(r10 - 8) */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8),
+	/* exit(0) */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.flags = BPF_F_TEST_STATE_FREQ,
+	.errstr = "invalid read from stack off -8+1 size 8",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index 2d89cb0ad288..330d0b1ceced 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -6,7 +6,7 @@ ksft_skip=4
 NS=ns
 IP6=2001:db8:1::1/64
 TGT6=2001:db8:1::2
-TMPF=`mktemp`
+TMPF=$(mktemp --suffix ".pcap")
 
 cleanup()
 {
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index dc932fd65363..640bc43452fa 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m'
 readonly YELLOW='\033[0;33m'
 readonly RED='\033[0;31m'
 readonly NC='\033[0m' # No Color
+readonly TESTPORT=8000
 
 readonly KSFT_PASS=0
 readonly KSFT_FAIL=1
@@ -56,11 +57,26 @@ trap wake_children EXIT
 
 run_one() {
 	local -r args=$@
+	local nr_socks=0
+	local i=0
+	local -r timeout=10
+
+	./udpgso_bench_rx -p "$TESTPORT" &
+	./udpgso_bench_rx -p "$TESTPORT" -t &
+
+	# Wait for the above test program to get ready to receive connections.
+	while [ "$i" -lt "$timeout" ]; do
+		nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")"
+		[ "$nr_socks" -eq 2 ] && break
+		i=$((i + 1))
+		sleep 1
+	done
+	if [ "$nr_socks" -ne 2 ]; then
+		echo "timed out while waiting for udpgso_bench_rx"
+		exit 1
+	fi
 
-	./udpgso_bench_rx &
-	./udpgso_bench_rx -t &
-
-	./udpgso_bench_tx ${args}
+	./udpgso_bench_tx -p "$TESTPORT" ${args}
 }
 
 run_in_netns() {
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index 6a193425c367..4058c7451e70 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size)
 static void do_flush_udp(int fd)
 {
 	static char rbuf[ETH_MAX_MTU];
-	int ret, len, gso_size, budget = 256;
+	int ret, len, gso_size = 0, budget = 256;
 
 	len = cfg_read_all ? sizeof(rbuf) : 0;
 	while (budget--) {
@@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv)
 			cfg_verify = true;
 			cfg_read_all = true;
 			break;
+		default:
+			exit(1);
 		}
 	}
 
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
index f1fdaa270291..477392715a9a 100644
--- a/tools/testing/selftests/net/udpgso_bench_tx.c
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -62,6 +62,7 @@ static int	cfg_payload_len	= (1472 * 42);
 static int	cfg_port	= 8000;
 static int	cfg_runtime_ms	= -1;
 static bool	cfg_poll;
+static int	cfg_poll_loop_timeout_ms = 2000;
 static bool	cfg_segment;
 static bool	cfg_sendmmsg;
 static bool	cfg_tcp;
@@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd)
 	}
 }
 
-static void flush_errqueue(int fd, const bool do_poll)
+static void flush_errqueue(int fd, const bool do_poll,
+			   unsigned long poll_timeout, const bool poll_err)
 {
 	if (do_poll) {
 		struct pollfd fds = {0};
 		int ret;
 
 		fds.fd = fd;
-		ret = poll(&fds, 1, 500);
+		ret = poll(&fds, 1, poll_timeout);
 		if (ret == 0) {
-			if (cfg_verbose)
+			if ((cfg_verbose) && (poll_err))
 				fprintf(stderr, "poll timeout\n");
 		} else if (ret < 0) {
 			error(1, errno, "poll");
@@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll)
 	flush_errqueue_recv(fd);
 }
 
+static void flush_errqueue_retry(int fd, unsigned long num_sends)
+{
+	unsigned long tnow, tstop;
+	bool first_try = true;
+
+	tnow = gettimeofday_ms();
+	tstop = tnow + cfg_poll_loop_timeout_ms;
+	do {
+		flush_errqueue(fd, true, tstop - tnow, first_try);
+		first_try = false;
+		tnow = gettimeofday_ms();
+	} while ((stat_zcopies != num_sends) && (tnow < tstop));
+}
+
 static int send_tcp(int fd, char *data)
 {
 	int ret, done = 0, count = 0;
@@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data)
 
 static void usage(const char *filepath)
 {
-	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
+	error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] "
+		    "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]",
 		    filepath);
 }
 
@@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv)
 	int max_len, hdrlen;
 	int c;
 
-	while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) {
+	while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) {
 		switch (c) {
 		case '4':
 			if (cfg_family != PF_UNSPEC)
@@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv)
 		case 'l':
 			cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
 			break;
+		case 'L':
+			cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000;
+			break;
 		case 'm':
 			cfg_sendmmsg = true;
 			break;
@@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv)
 		case 'z':
 			cfg_zerocopy = true;
 			break;
+		default:
+			exit(1);
 		}
 	}
 
@@ -677,7 +699,7 @@ int main(int argc, char **argv)
 			num_sends += send_udp(fd, buf[i]);
 		num_msgs++;
 		if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp)
-			flush_errqueue(fd, cfg_poll);
+			flush_errqueue(fd, cfg_poll, 500, true);
 
 		if (cfg_msg_nr && num_msgs >= cfg_msg_nr)
 			break;
@@ -696,7 +718,7 @@ int main(int argc, char **argv)
 	} while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
 
 	if (cfg_zerocopy || cfg_tx_tstamp)
-		flush_errqueue(fd, true);
+		flush_errqueue_retry(fd, num_sends);
 
 	if (close(fd))
 		error(1, errno, "close");