Merge tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - gro: initialize network_offset in network layer

   - tcp: reduce accepted window in NEW_SYN_RECV state

  Current release - new code bugs:

   - eth: mlx5e: do not use ptp structure for tx ts stats when not
     initialized

   - eth: ice: check for unregistering correct number of devlink params

  Previous releases - regressions:

   - bpf: Allow delete from sockmap/sockhash only if update is allowed

   - sched: taprio: extend minimum interval restriction to entire cycle
     too

   - netfilter: ipset: add list flush to cancel_gc

   - ipv4: fix address dump when IPv4 is disabled on an interface

   - sock_map: avoid race between sock_map_close and sk_psock_put

   - eth: mlx5: use mlx5_ipsec_rx_status_destroy to correctly delete
     status rules

  Previous releases - always broken:

   - core: fix __dst_negative_advice() race

   - bpf:
       - fix multi-uprobe PID filtering logic
       - fix pkt_type override upon netkit pass verdict

   - netfilter: tproxy: bail out if IP has been disabled on the device

   - af_unix: annotate data-race around unix_sk(sk)->addr

   - eth: mlx5e: fix UDP GSO for encapsulated packets

   - eth: idpf: don't enable NAPI and interrupts prior to allocating Rx
     buffers

   - eth: i40e: fully suspend and resume IO operations in EEH case

   - eth: octeontx2-pf: free send queue buffers incase of leaf to inner

   - eth: ipvlan: dont Use skb->sk in ipvlan_process_v{4,6}_outbound"

* tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  netdev: add qstat for csum complete
  ipvlan: Dont Use skb->sk in ipvlan_process_v{4,6}_outbound
  net: ena: Fix redundant device NUMA node override
  ice: check for unregistering correct number of devlink params
  ice: fix 200G PHY types to link speed mapping
  i40e: Fully suspend and resume IO operations in EEH case
  i40e: factoring out i40e_suspend/i40e_resume
  e1000e: move force SMBUS near the end of enable_ulp function
  net: dsa: microchip: fix RGMII error in KSZ DSA driver
  ipv4: correctly iterate over the target netns in inet_dump_ifaddr()
  net: fix __dst_negative_advice() race
  nfc/nci: Add the inconsistency check between the input data length and count
  MAINTAINERS: dwmac: starfive: update Maintainer
  net/sched: taprio: extend minimum interval restriction to entire cycle too
  net/sched: taprio: make q->picos_per_byte available to fill_sched_entry()
  netfilter: nft_fib: allow from forward/input without iif selector
  netfilter: tproxy: bail out if IP has been disabled on the device
  netfilter: nft_payload: skbuff vlan metadata mangle support
  net: ti: icssg-prueth: Fix start counter for ft1 filter
  sock_map: avoid race between sock_map_close and sk_psock_put
  ...

14 files changed, 607 insertions, 21 deletions

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index d9520cb826b3..af393c7dee1f 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -728,7 +728,7 @@ static int sets_patch(struct object *obj)
 
 static int symbols_patch(struct object *obj)
 {
-	int err;
+	off_t err;
 
 	if (__symbols_patch(obj, &obj->structs)  ||
 	    __symbols_patch(obj, &obj->unions)   ||
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index a8188202413e..43742ac5b00d 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -148,6 +148,7 @@ enum {
 	NETDEV_A_QSTATS_RX_ALLOC_FAIL,
 	NETDEV_A_QSTATS_RX_HW_DROPS,
 	NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS,
+	NETDEV_A_QSTATS_RX_CSUM_COMPLETE,
 	NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY,
 	NETDEV_A_QSTATS_RX_CSUM_NONE,
 	NETDEV_A_QSTATS_RX_CSUM_BAD,
diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index a336786a22a3..3df0125ed5fa 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -392,11 +392,40 @@ static int probe_uprobe_multi_link(int token_fd)
 	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
 	err = -errno; /* close() can clobber errno */
 
+	if (link_fd >= 0 || err != -EBADF) {
+		close(link_fd);
+		close(prog_fd);
+		return 0;
+	}
+
+	/* Initial multi-uprobe support in kernel didn't handle PID filtering
+	 * correctly (it was doing thread filtering, not process filtering).
+	 * So now we'll detect if PID filtering logic was fixed, and, if not,
+	 * we'll pretend multi-uprobes are not supported, if not.
+	 * Multi-uprobes are used in USDT attachment logic, and we need to be
+	 * conservative here, because multi-uprobe selection happens early at
+	 * load time, while the use of PID filtering is known late at
+	 * attachment time, at which point it's too late to undo multi-uprobe
+	 * selection.
+	 *
+	 * Creating uprobe with pid == -1 for (invalid) '/' binary will fail
+	 * early with -EINVAL on kernels with fixed PID filtering logic;
+	 * otherwise -ESRCH would be returned if passed correct binary path
+	 * (but we'll just get -BADF, of course).
+	 */
+	link_opts.uprobe_multi.pid = -1; /* invalid PID */
+	link_opts.uprobe_multi.path = "/"; /* invalid path */
+	link_opts.uprobe_multi.offsets = &offset;
+	link_opts.uprobe_multi.cnt = 1;
+
+	link_fd = bpf_link_create(prog_fd, -1, BPF_TRACE_UPROBE_MULTI, &link_opts);
+	err = -errno; /* close() can clobber errno */
+
 	if (link_fd >= 0)
 		close(link_fd);
 	close(prog_fd);
 
-	return link_fd < 0 && err == -EBADF;
+	return link_fd < 0 && err == -EINVAL;
 }
 
 static int probe_kern_bpf_cookie(int token_fd)
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
index 15ee7b2fc410..b9135720024c 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c
@@ -73,6 +73,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 			 "up primary");
 	ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"),
 			 "addr primary");
+
+	if (mode == NETKIT_L3) {
+		ASSERT_EQ(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd 2> /dev/null"), 512,
+				 "set hwaddress");
+	} else {
+		ASSERT_OK(system("ip link set dev " netkit_name
+				 " addr ee:ff:bb:cc:aa:dd"),
+				 "set hwaddress");
+	}
 	if (same_netns) {
 		ASSERT_OK(system("ip link set dev " netkit_peer " up"),
 				 "up peer");
@@ -89,6 +99,16 @@ static int create_netkit(int mode, int policy, int peer_policy, int *ifindex,
 	return err;
 }
 
+static void move_netkit(void)
+{
+	ASSERT_OK(system("ip link set " netkit_peer " netns foo"),
+			 "move peer");
+	ASSERT_OK(system("ip netns exec foo ip link set dev "
+			 netkit_peer " up"), "up peer");
+	ASSERT_OK(system("ip netns exec foo ip addr add dev "
+			 netkit_peer " 10.0.0.2/24"), "addr peer");
+}
+
 static void destroy_netkit(void)
 {
 	ASSERT_OK(system("ip link del dev " netkit_name), "del primary");
@@ -685,3 +705,77 @@ void serial_test_tc_netkit_neigh_links(void)
 	serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY);
 	serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY);
 }
+
+static void serial_test_tc_netkit_pkt_type_mode(int mode)
+{
+	LIBBPF_OPTS(bpf_netkit_opts, optl_nk);
+	LIBBPF_OPTS(bpf_tcx_opts, optl_tcx);
+	int err, ifindex, ifindex2;
+	struct test_tc_link *skel;
+	struct bpf_link *link;
+
+	err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS,
+			    &ifindex, true);
+	if (err)
+		return;
+
+	ifindex2 = if_nametoindex(netkit_peer);
+	ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2");
+
+	skel = test_tc_link__open();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1,
+		  BPF_NETKIT_PRIMARY), 0, "tc1_attach_type");
+	ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc7,
+		  BPF_TCX_INGRESS), 0, "tc7_attach_type");
+
+	err = test_tc_link__load(skel);
+	if (!ASSERT_OK(err, "skel_load"))
+		goto cleanup;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl_nk);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc1 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 0);
+
+	link = bpf_program__attach_tcx(skel->progs.tc7, ifindex2, &optl_tcx);
+	if (!ASSERT_OK_PTR(link, "link_attach"))
+		goto cleanup;
+
+	skel->links.tc7 = link;
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 1);
+	assert_mprog_count_ifindex(ifindex2, BPF_TCX_INGRESS, 1);
+
+	move_netkit();
+
+	tc_skel_reset_all_seen(skel);
+	skel->bss->set_type = true;
+	ASSERT_EQ(send_icmp(), 0, "icmp_pkt");
+
+	ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1");
+	ASSERT_EQ(skel->bss->seen_tc7, true, "seen_tc7");
+
+	ASSERT_EQ(skel->bss->seen_host,  true, "seen_host");
+	ASSERT_EQ(skel->bss->seen_mcast, true, "seen_mcast");
+cleanup:
+	test_tc_link__destroy(skel);
+
+	assert_mprog_count_ifindex(ifindex,  BPF_NETKIT_PRIMARY, 0);
+	destroy_netkit();
+}
+
+void serial_test_tc_netkit_pkt_type(void)
+{
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L2);
+	serial_test_tc_netkit_pkt_type_mode(NETKIT_L3);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
index 8269cdee33ae..bf6ca8e3eb13 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c
@@ -1,12 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <unistd.h>
+#include <pthread.h>
 #include <test_progs.h>
 #include "uprobe_multi.skel.h"
 #include "uprobe_multi_bench.skel.h"
 #include "uprobe_multi_usdt.skel.h"
 #include "bpf/libbpf_internal.h"
 #include "testing_helpers.h"
+#include "../sdt.h"
 
 static char test_data[] = "test_data";
 
@@ -25,9 +27,17 @@ noinline void uprobe_multi_func_3(void)
 	asm volatile ("");
 }
 
+noinline void usdt_trigger(void)
+{
+	STAP_PROBE(test, pid_filter_usdt);
+}
+
 struct child {
 	int go[2];
+	int c2p[2]; /* child -> parent channel */
 	int pid;
+	int tid;
+	pthread_t thread;
 };
 
 static void release_child(struct child *child)
@@ -38,6 +48,10 @@ static void release_child(struct child *child)
 		return;
 	close(child->go[1]);
 	close(child->go[0]);
+	if (child->thread)
+		pthread_join(child->thread, NULL);
+	close(child->c2p[0]);
+	close(child->c2p[1]);
 	if (child->pid > 0)
 		waitpid(child->pid, &child_status, 0);
 }
@@ -63,7 +77,7 @@ static struct child *spawn_child(void)
 	if (pipe(child.go))
 		return NULL;
 
-	child.pid = fork();
+	child.pid = child.tid = fork();
 	if (child.pid < 0) {
 		release_child(&child);
 		errno = EINVAL;
@@ -82,6 +96,7 @@ static struct child *spawn_child(void)
 		uprobe_multi_func_1();
 		uprobe_multi_func_2();
 		uprobe_multi_func_3();
+		usdt_trigger();
 
 		exit(errno);
 	}
@@ -89,6 +104,67 @@ static struct child *spawn_child(void)
 	return &child;
 }
 
+static void *child_thread(void *ctx)
+{
+	struct child *child = ctx;
+	int c = 0, err;
+
+	child->tid = syscall(SYS_gettid);
+
+	/* let parent know we are ready */
+	err = write(child->c2p[1], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	/* wait for parent's kick */
+	err = read(child->go[0], &c, 1);
+	if (err != 1)
+		pthread_exit(&err);
+
+	uprobe_multi_func_1();
+	uprobe_multi_func_2();
+	uprobe_multi_func_3();
+	usdt_trigger();
+
+	err = 0;
+	pthread_exit(&err);
+}
+
+static struct child *spawn_thread(void)
+{
+	static struct child child;
+	int c, err;
+
+	/* pipe to notify child to execute the trigger functions */
+	if (pipe(child.go))
+		return NULL;
+	/* pipe to notify parent that child thread is ready */
+	if (pipe(child.c2p)) {
+		close(child.go[0]);
+		close(child.go[1]);
+		return NULL;
+	}
+
+	child.pid = getpid();
+
+	err = pthread_create(&child.thread, NULL, child_thread, &child);
+	if (err) {
+		err = -errno;
+		close(child.go[0]);
+		close(child.go[1]);
+		close(child.c2p[0]);
+		close(child.c2p[1]);
+		errno = -err;
+		return NULL;
+	}
+
+	err = read(child.c2p[0], &c, 1);
+	if (!ASSERT_EQ(err, 1, "child_thread_ready"))
+		return NULL;
+
+	return &child;
+}
+
 static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child)
 {
 	skel->bss->uprobe_multi_func_1_addr = (__u64) uprobe_multi_func_1;
@@ -103,15 +179,23 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 	 * passed at the probe attach.
 	 */
 	skel->bss->pid = child ? 0 : getpid();
+	skel->bss->expect_pid = child ? child->pid : 0;
+
+	/* trigger all probes, if we are testing child *process*, just to make
+	 * sure that PID filtering doesn't let through activations from wrong
+	 * PIDs; when we test child *thread*, we don't want to do this to
+	 * avoid double counting number of triggering events
+	 */
+	if (!child || !child->thread) {
+		uprobe_multi_func_1();
+		uprobe_multi_func_2();
+		uprobe_multi_func_3();
+		usdt_trigger();
+	}
 
 	if (child)
 		kick_child(child);
 
-	/* trigger all probes */
-	uprobe_multi_func_1();
-	uprobe_multi_func_2();
-	uprobe_multi_func_3();
-
 	/*
 	 * There are 2 entry and 2 exit probe called for each uprobe_multi_func_[123]
 	 * function and each slepable probe (6) increments uprobe_multi_sleep_result.
@@ -126,8 +210,12 @@ static void uprobe_multi_test_run(struct uprobe_multi *skel, struct child *child
 
 	ASSERT_EQ(skel->bss->uprobe_multi_sleep_result, 6, "uprobe_multi_sleep_result");
 
-	if (child)
+	ASSERT_FALSE(skel->bss->bad_pid_seen, "bad_pid_seen");
+
+	if (child) {
 		ASSERT_EQ(skel->bss->child_pid, child->pid, "uprobe_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid, child->tid, "uprobe_multi_child_tid");
+	}
 }
 
 static void test_skel_api(void)
@@ -190,8 +278,24 @@ __test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_mul
 	if (!ASSERT_OK_PTR(skel->links.uprobe_extra, "bpf_program__attach_uprobe_multi"))
 		goto cleanup;
 
+	/* Attach (uprobe-backed) USDTs */
+	skel->links.usdt_pid = bpf_program__attach_usdt(skel->progs.usdt_pid, pid, binary,
+							"test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_pid, "attach_usdt_pid"))
+		goto cleanup;
+
+	skel->links.usdt_extra = bpf_program__attach_usdt(skel->progs.usdt_extra, -1, binary,
+							  "test", "pid_filter_usdt", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_extra, "attach_usdt_extra"))
+		goto cleanup;
+
 	uprobe_multi_test_run(skel, child);
 
+	ASSERT_FALSE(skel->bss->bad_pid_seen_usdt, "bad_pid_seen_usdt");
+	if (child) {
+		ASSERT_EQ(skel->bss->child_pid_usdt, child->pid, "usdt_multi_child_pid");
+		ASSERT_EQ(skel->bss->child_tid_usdt, child->tid, "usdt_multi_child_tid");
+	}
 cleanup:
 	uprobe_multi__destroy(skel);
 }
@@ -210,6 +314,13 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi
 		return;
 
 	__test_attach_api(binary, pattern, opts, child);
+
+	/* pid filter (thread) */
+	child = spawn_thread();
+	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+		return;
+
+	__test_attach_api(binary, pattern, opts, child);
 }
 
 static void test_attach_api_pattern(void)
@@ -397,7 +508,7 @@ static void test_attach_api_fails(void)
 	link_fd = bpf_link_create(prog_fd, 0, BPF_TRACE_UPROBE_MULTI, &opts);
 	if (!ASSERT_ERR(link_fd, "link_fd"))
 		goto cleanup;
-	ASSERT_EQ(link_fd, -ESRCH, "pid_is_wrong");
+	ASSERT_EQ(link_fd, -EINVAL, "pid_is_wrong");
 
 cleanup:
 	if (link_fd >= 0)
@@ -495,6 +606,13 @@ static void test_link_api(void)
 		return;
 
 	__test_link_api(child);
+
+	/* pid filter (thread) */
+	child = spawn_thread();
+	if (!ASSERT_OK_PTR(child, "spawn_thread"))
+		return;
+
+	__test_link_api(child);
 }
 
 static void test_bench_attach_uprobe(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index c60db8beeb73..1c9c4ec1be11 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -67,6 +67,7 @@
 #include "verifier_search_pruning.skel.h"
 #include "verifier_sock.skel.h"
 #include "verifier_sock_addr.skel.h"
+#include "verifier_sockmap_mutate.skel.h"
 #include "verifier_spill_fill.skel.h"
 #include "verifier_spin_lock.skel.h"
 #include "verifier_stack_ptr.skel.h"
@@ -183,6 +184,7 @@ void test_verifier_sdiv(void)                 { RUN(verifier_sdiv); }
 void test_verifier_search_pruning(void)       { RUN(verifier_search_pruning); }
 void test_verifier_sock(void)                 { RUN(verifier_sock); }
 void test_verifier_sock_addr(void)            { RUN(verifier_sock_addr); }
+void test_verifier_sockmap_mutate(void)       { RUN(verifier_sockmap_mutate); }
 void test_verifier_spill_fill(void)           { RUN(verifier_spill_fill); }
 void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c
index 992400acb957..ab3eae3d6af8 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_link.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_link.c
@@ -4,7 +4,8 @@
 
 #include <linux/bpf.h>
 #include <linux/if_ether.h>
-
+#include <linux/stddef.h>
+#include <linux/if_packet.h>
 #include <bpf/bpf_endian.h>
 #include <bpf/bpf_helpers.h>
 
@@ -16,7 +17,13 @@ bool seen_tc3;
 bool seen_tc4;
 bool seen_tc5;
 bool seen_tc6;
+bool seen_tc7;
+
+bool set_type;
+
 bool seen_eth;
+bool seen_host;
+bool seen_mcast;
 
 SEC("tc/ingress")
 int tc1(struct __sk_buff *skb)
@@ -28,8 +35,16 @@ int tc1(struct __sk_buff *skb)
 	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
 		goto out;
 	seen_eth = eth.h_proto == bpf_htons(ETH_P_IP);
+	seen_host = skb->pkt_type == PACKET_HOST;
+	if (seen_host && set_type) {
+		eth.h_dest[0] = 4;
+		if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0))
+			goto fail;
+		bpf_skb_change_type(skb, PACKET_MULTICAST);
+	}
 out:
 	seen_tc1 = true;
+fail:
 	return TCX_NEXT;
 }
 
@@ -67,3 +82,21 @@ int tc6(struct __sk_buff *skb)
 	seen_tc6 = true;
 	return TCX_PASS;
 }
+
+SEC("tc/ingress")
+int tc7(struct __sk_buff *skb)
+{
+	struct ethhdr eth = {};
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		goto out;
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)))
+		goto out;
+	if (eth.h_dest[0] == 4 && set_type) {
+		seen_mcast = skb->pkt_type == PACKET_MULTICAST;
+		bpf_skb_change_type(skb, PACKET_HOST);
+	}
+out:
+	seen_tc7 = true;
+	return TCX_PASS;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_multi.c b/tools/testing/selftests/bpf/progs/uprobe_multi.c
index 419d9aa28fce..44190efcdba2 100644
--- a/tools/testing/selftests/bpf/progs/uprobe_multi.c
+++ b/tools/testing/selftests/bpf/progs/uprobe_multi.c
@@ -1,8 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
-#include <stdbool.h>
+#include <bpf/usdt.bpf.h>
 
 char _license[] SEC("license") = "GPL";
 
@@ -22,6 +22,13 @@ __u64 uprobe_multi_sleep_result = 0;
 
 int pid = 0;
 int child_pid = 0;
+int child_tid = 0;
+int child_pid_usdt = 0;
+int child_tid_usdt = 0;
+
+int expect_pid = 0;
+bool bad_pid_seen = false;
+bool bad_pid_seen_usdt = false;
 
 bool test_cookie = false;
 void *user_ptr = 0;
@@ -36,11 +43,19 @@ static __always_inline bool verify_sleepable_user_copy(void)
 
 static void uprobe_multi_check(void *ctx, bool is_return, bool is_sleep)
 {
-	child_pid = bpf_get_current_pid_tgid() >> 32;
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
 
-	if (pid && child_pid != pid)
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
 		return;
 
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen = true;
+
+	child_pid = cur_pid_tgid >> 32;
+	child_tid = (__u32)cur_pid_tgid;
+
 	__u64 cookie = test_cookie ? bpf_get_attach_cookie(ctx) : 0;
 	__u64 addr = bpf_get_func_ip(ctx);
 
@@ -97,5 +112,32 @@ int uretprobe_sleep(struct pt_regs *ctx)
 SEC("uprobe.multi//proc/self/exe:uprobe_multi_func_*")
 int uprobe_extra(struct pt_regs *ctx)
 {
+	/* we need this one just to mix PID-filtered and global uprobes */
+	return 0;
+}
+
+SEC("usdt")
+int usdt_pid(struct pt_regs *ctx)
+{
+	__u64 cur_pid_tgid = bpf_get_current_pid_tgid();
+	__u32 cur_pid;
+
+	cur_pid = cur_pid_tgid >> 32;
+	if (pid && cur_pid != pid)
+		return 0;
+
+	if (expect_pid && cur_pid != expect_pid)
+		bad_pid_seen_usdt = true;
+
+	child_pid_usdt = cur_pid_tgid >> 32;
+	child_tid_usdt = (__u32)cur_pid_tgid;
+
+	return 0;
+}
+
+SEC("usdt")
+int usdt_extra(struct pt_regs *ctx)
+{
+	/* we need this one just to mix PID-filtered and global USDT probes */
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
new file mode 100644
index 000000000000..fe4b123187b8
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_sockmap_mutate.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#include "bpf_misc.h"
+
+#define __always_unused __attribute__((unused))
+
+char _license[] SEC("license") = "GPL";
+
+struct sock {
+} __attribute__((preserve_access_index));
+
+struct bpf_iter__sockmap {
+	union {
+		struct sock *sk;
+	};
+} __attribute__((preserve_access_index));
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKHASH);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockhash SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, int);
+	__type(value, int);
+} sockmap SEC(".maps");
+
+enum { CG_OK = 1 };
+
+int zero = 0;
+
+static __always_inline void test_sockmap_delete(void)
+{
+	bpf_map_delete_elem(&sockmap, &zero);
+	bpf_map_delete_elem(&sockhash, &zero);
+}
+
+static __always_inline void test_sockmap_update(void *sk)
+{
+	if (sk) {
+		bpf_map_update_elem(&sockmap, &zero, sk, BPF_ANY);
+		bpf_map_update_elem(&sockhash, &zero, sk, BPF_ANY);
+	}
+}
+
+static __always_inline void test_sockmap_lookup_and_update(void)
+{
+	struct bpf_sock *sk = bpf_map_lookup_elem(&sockmap, &zero);
+
+	if (sk) {
+		test_sockmap_update(sk);
+		bpf_sk_release(sk);
+	}
+}
+
+static __always_inline void test_sockmap_mutate(void *sk)
+{
+	test_sockmap_delete();
+	test_sockmap_update(sk);
+}
+
+static __always_inline void test_sockmap_lookup_and_mutate(void)
+{
+	test_sockmap_delete();
+	test_sockmap_lookup_and_update();
+}
+
+SEC("action")
+__success
+int test_sched_act(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("classifier")
+__success
+int test_sched_cls(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("flow_dissector")
+__success
+int test_flow_dissector_delete(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("flow_dissector")
+__failure __msg("program of this type cannot use helper bpf_sk_release")
+int test_flow_dissector_update(struct __sk_buff *skb __always_unused)
+{
+	test_sockmap_lookup_and_update(); /* no access to skb->sk */
+	return 0;
+}
+
+SEC("iter/sockmap")
+__success
+int test_trace_iter(struct bpf_iter__sockmap *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_delete(const void *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return 0;
+}
+
+SEC("raw_tp/kfree")
+__failure __msg("cannot update sockmap in this context")
+int test_raw_tp_update(const void *ctx __always_unused)
+{
+	test_sockmap_lookup_and_update();
+	return 0;
+}
+
+SEC("sk_lookup")
+__success
+int test_sk_lookup(struct bpf_sk_lookup *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("sk_reuseport")
+__success
+int test_sk_reuseport(struct sk_reuseport_md *ctx)
+{
+	test_sockmap_mutate(ctx->sk);
+	return 0;
+}
+
+SEC("socket")
+__success
+int test_socket_filter(struct __sk_buff *skb)
+{
+	test_sockmap_mutate(skb->sk);
+	return 0;
+}
+
+SEC("sockops")
+__success
+int test_sockops_delete(struct bpf_sock_ops *ctx __always_unused)
+{
+	test_sockmap_delete();
+	return CG_OK;
+}
+
+SEC("sockops")
+__failure __msg("cannot update sockmap in this context")
+int test_sockops_update(struct bpf_sock_ops *ctx)
+{
+	test_sockmap_update(ctx->sk);
+	return CG_OK;
+}
+
+SEC("sockops")
+__success
+int test_sockops_update_dedicated(struct bpf_sock_ops *ctx)
+{
+	bpf_sock_map_update(ctx, &sockmap, &zero, BPF_ANY);
+	bpf_sock_hash_update(ctx, &sockhash, &zero, BPF_ANY);
+	return CG_OK;
+}
+
+SEC("xdp")
+__success
+int test_xdp(struct xdp_md *ctx __always_unused)
+{
+	test_sockmap_lookup_and_mutate();
+	return XDP_PASS;
+}
diff --git a/tools/testing/selftests/net/hsr/hsr_ping.sh b/tools/testing/selftests/net/hsr/hsr_ping.sh
index 790294c8af83..3684b813b0f6 100755
--- a/tools/testing/selftests/net/hsr/hsr_ping.sh
+++ b/tools/testing/selftests/net/hsr/hsr_ping.sh
@@ -174,6 +174,8 @@ trap cleanup_all_ns EXIT
 setup_hsr_interfaces 0
 do_complete_ping_test
 
+setup_ns ns1 ns2 ns3
+
 setup_hsr_interfaces 1
 do_complete_ping_test
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fefa9173bdaa..2b66c5fa71eb 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -261,6 +261,8 @@ reset()
 
 	TEST_NAME="${1}"
 
+	MPTCP_LIB_SUBTEST_FLAKY=0 # reset if modified
+
 	if skip_test; then
 		MPTCP_LIB_TEST_COUNTER=$((MPTCP_LIB_TEST_COUNTER+1))
 		last_test_ignored=1
@@ -448,7 +450,9 @@ reset_with_tcp_filter()
 # $1: err msg
 fail_test()
 {
-	ret=${KSFT_FAIL}
+	if ! mptcp_lib_subtest_is_flaky; then
+		ret=${KSFT_FAIL}
+	fi
 
 	if [ ${#} -gt 0 ]; then
 		print_fail "${@}"
@@ -3069,6 +3073,7 @@ fullmesh_tests()
 fastclose_tests()
 {
 	if reset_check_counter "fastclose test" "MPTcpExtMPFastcloseTx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=client \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0
@@ -3077,6 +3082,7 @@ fastclose_tests()
 	fi
 
 	if reset_check_counter "fastclose server test" "MPTcpExtMPFastcloseRx"; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=1024 fastclose=server \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 0 0 0 1
@@ -3095,6 +3101,7 @@ fail_tests()
 {
 	# single subflow
 	if reset_with_fail "Infinite map" 1; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		test_linkfail=128 \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)"
@@ -3103,6 +3110,7 @@ fail_tests()
 
 	# multiple subflows
 	if reset_with_fail "MP_FAIL MP_RST" 2; then
+		MPTCP_LIB_SUBTEST_FLAKY=1
 		tc -n $ns2 qdisc add dev ns2eth1 root netem rate 1mbit delay 5ms
 		pm_nl_set_limits $ns1 0 1
 		pm_nl_set_limits $ns2 0 1
diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
index ad2ebda5cb64..6ffa9b7a3260 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
@@ -21,6 +21,7 @@ declare -rx MPTCP_LIB_AF_INET6=10
 
 MPTCP_LIB_SUBTESTS=()
 MPTCP_LIB_SUBTESTS_DUPLICATED=0
+MPTCP_LIB_SUBTEST_FLAKY=0
 MPTCP_LIB_TEST_COUNTER=0
 MPTCP_LIB_TEST_FORMAT="%02u %-50s"
 MPTCP_LIB_IP_MPTCP=0
@@ -41,6 +42,16 @@ else
 	readonly MPTCP_LIB_COLOR_RESET=
 fi
 
+# SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY env var can be set not to ignore errors
+# from subtests marked as flaky
+mptcp_lib_override_flaky() {
+	[ "${SELFTESTS_MPTCP_LIB_OVERRIDE_FLAKY:-}" = 1 ]
+}
+
+mptcp_lib_subtest_is_flaky() {
+	[ "${MPTCP_LIB_SUBTEST_FLAKY}" = 1 ] && ! mptcp_lib_override_flaky
+}
+
 # $1: color, $2: text
 mptcp_lib_print_color() {
 	echo -e "${MPTCP_LIB_START_PRINT:-}${*}${MPTCP_LIB_COLOR_RESET}"
@@ -72,7 +83,16 @@ mptcp_lib_pr_skip() {
 }
 
 mptcp_lib_pr_fail() {
-	mptcp_lib_print_err "[FAIL]${1:+ ${*}}"
+	local title cmt
+
+	if mptcp_lib_subtest_is_flaky; then
+		title="IGNO"
+		cmt=" (flaky)"
+	else
+		title="FAIL"
+	fi
+
+	mptcp_lib_print_err "[${title}]${cmt}${1:+ ${*}}"
 }
 
 mptcp_lib_pr_info() {
@@ -208,7 +228,13 @@ mptcp_lib_result_pass() {
 
 # $1: test name
 mptcp_lib_result_fail() {
-	__mptcp_lib_result_add "not ok" "${1}"
+	if mptcp_lib_subtest_is_flaky; then
+		# It might sound better to use 'not ok # TODO' or 'ok # SKIP',
+		# but some CIs don't understand 'TODO' and treat SKIP as errors.
+		__mptcp_lib_result_add "ok" "${1} # IGNORE Flaky"
+	else
+		__mptcp_lib_result_add "not ok" "${1}"
+	fi
 }
 
 # $1: test name
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 4b14b4412166..f74e1c3c126d 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -244,7 +244,7 @@ run_test()
 	do_transfer $small $large $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -254,7 +254,7 @@ run_test()
 	do_transfer $large $small $time
 	lret=$?
 	mptcp_lib_result_code "${lret}" "${msg}"
-	if [ $lret -ne 0 ]; then
+	if [ $lret -ne 0 ] && ! mptcp_lib_subtest_is_flaky; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
@@ -290,7 +290,7 @@ run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 10 3 0 0 "unbalanced bwidth"
+MPTCP_LIB_SUBTEST_FLAKY=1 run_test 10 3 0 0 "unbalanced bwidth"
 run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
 run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
index 12da0a939e3e..557fb074acf0 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json
@@ -133,6 +133,50 @@
         ]
     },
     {
+        "id": "6f62",
+        "name": "Add taprio Qdisc with too short interval",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 300 sched-entry S 02 1700 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
+        "id": "831f",
+        "name": "Add taprio Qdisc with too short cycle-time",
+        "category": [
+            "qdisc",
+            "taprio"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "echo \"1 1 8\" > /sys/bus/netdevsim/new_device"
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $ETH root handle 1: taprio num_tc 2 queues 1@0 1@1 sched-entry S 01 200000 sched-entry S 02 200000 cycle-time 100 clockid CLOCK_TAI",
+        "expExitCode": "2",
+        "verifyCmd": "$TC qdisc show dev $ETH",
+        "matchPattern": "qdisc taprio 1: root refcnt",
+        "matchCount": "0",
+        "teardown": [
+            "echo \"1\" > /sys/bus/netdevsim/del_device"
+        ]
+    },
+    {
         "id": "3e1e",
         "name": "Add taprio Qdisc with an invalid cycle-time",
         "category": [