diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 63ae4a39e58b..c02dec97e1ce 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -22,9 +22,9 @@ struct btf_header {
 };
 
 /* Max # of type identifier */
-#define BTF_MAX_TYPE	0x0000ffff
+#define BTF_MAX_TYPE	0x000fffff
 /* Max offset into the string section */
-#define BTF_MAX_NAME_OFFSET	0x0000ffff
+#define BTF_MAX_NAME_OFFSET	0x00ffffff
 /* Max # of struct/union/enum members or func args */
 #define BTF_MAX_VLEN	0xffff
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index adb3adcebe3c..29c7c06c6bd6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2332,7 +2332,7 @@ static int btf_enum_check_kflag_member(struct btf_verifier_env *env,
 		if (BITS_PER_BYTE_MASKED(struct_bits_off)) {
 			btf_verifier_log_member(env, struct_type, member,
 						"Member is not byte aligned");
-				return -EINVAL;
+			return -EINVAL;
 		}
 
 		nr_bits = int_bitsize;
@@ -2377,9 +2377,8 @@ static s32 btf_enum_check_meta(struct btf_verifier_env *env,
 		return -EINVAL;
 	}
 
-	if (t->size != sizeof(int)) {
-		btf_verifier_log_type(env, t, "Expected size:%zu",
-				      sizeof(int));
+	if (t->size > 8 || !is_power_of_2(t->size)) {
+		btf_verifier_log_type(env, t, "Unexpected size");
 		return -EINVAL;
 	}
 
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index 942c662e2eed..82a1ffe15dfa 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -37,7 +37,7 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 
 	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
 	if (!node)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	err = xsk_map_inc(map);
 	if (err) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index ca1255d14576..3e38a010003c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -500,14 +500,17 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd);
+static DEFINE_PER_CPU(int, bpf_event_output_nest_level);
+struct bpf_nested_pt_regs {
+	struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_nested_pt_regs, bpf_pt_regs);
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_misc_sds);
 
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy)
 {
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd);
-	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+	int nest_level = this_cpu_inc_return(bpf_event_output_nest_level);
 	struct perf_raw_frag frag = {
 		.copy		= ctx_copy,
 		.size		= ctx_size,
@@ -522,12 +525,25 @@ u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 			.data	= meta,
 		},
 	};
+	struct perf_sample_data *sd;
+	struct pt_regs *regs;
+	u64 ret;
+
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bpf_misc_sds.sds))) {
+		ret = -EBUSY;
+		goto out;
+	}
+	sd = this_cpu_ptr(&bpf_misc_sds.sds[nest_level - 1]);
+	regs = this_cpu_ptr(&bpf_pt_regs.regs[nest_level - 1]);
 
 	perf_fetch_caller_regs(regs);
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, sd);
+	ret = __bpf_perf_event_output(regs, map, flags, sd);
+out:
+	this_cpu_dec(bpf_event_output_nest_level);
+	return ret;
 }
 
 BPF_CALL_0(bpf_get_current_task)
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 947b8ff0227e..cdaef54d48be 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -383,8 +383,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 			return -EINVAL;
 	}
 
-	headroom = ALIGN(headroom, 64);
-
 	size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM;
 	if (size_chk < 0)
 		return -EINVAL;
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 715967762312..ede55fec3618 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -48,6 +48,8 @@ struct btf_dump_type_aux_state {
 	__u8 fwd_emitted: 1;
 	/* whether unique non-duplicate name was already assigned */
 	__u8 name_resolved: 1;
+	/* whether type is referenced from any other type */
+	__u8 referenced: 1;
 };
 
 struct btf_dump {
@@ -173,6 +175,7 @@ void btf_dump__free(struct btf_dump *d)
 	free(d);
 }
 
+static int btf_dump_mark_referenced(struct btf_dump *d);
 static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr);
 static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id);
 
@@ -213,6 +216,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 		/* VOID is special */
 		d->type_states[0].order_state = ORDERED;
 		d->type_states[0].emit_state = EMITTED;
+
+		/* eagerly determine referenced types for anon enums */
+		err = btf_dump_mark_referenced(d);
+		if (err)
+			return err;
 	}
 
 	d->emit_queue_cnt = 0;
@@ -226,6 +234,79 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 	return 0;
 }
 
+/*
+ * Mark all types that are referenced from any other type. This is used to
+ * determine top-level anonymous enums that need to be emitted as an
+ * independent type declarations.
+ * Anonymous enums come in two flavors: either embedded in a struct's field
+ * definition, in which case they have to be declared inline as part of field
+ * type declaration; or as a top-level anonymous enum, typically used for
+ * declaring global constants. It's impossible to distinguish between two
+ * without knowning whether given enum type was referenced from other type:
+ * top-level anonymous enum won't be referenced by anything, while embedded
+ * one will.
+ */
+static int btf_dump_mark_referenced(struct btf_dump *d)
+{
+	int i, j, n = btf__get_nr_types(d->btf);
+	const struct btf_type *t;
+	__u16 vlen;
+
+	for (i = 1; i <= n; i++) {
+		t = btf__type_by_id(d->btf, i);
+		vlen = btf_vlen(t);
+
+		switch (btf_kind(t)) {
+		case BTF_KIND_INT:
+		case BTF_KIND_ENUM:
+		case BTF_KIND_FWD:
+			break;
+
+		case BTF_KIND_VOLATILE:
+		case BTF_KIND_CONST:
+		case BTF_KIND_RESTRICT:
+		case BTF_KIND_PTR:
+		case BTF_KIND_TYPEDEF:
+		case BTF_KIND_FUNC:
+		case BTF_KIND_VAR:
+			d->type_states[t->type].referenced = 1;
+			break;
+
+		case BTF_KIND_ARRAY: {
+			const struct btf_array *a = btf_array(t);
+
+			d->type_states[a->index_type].referenced = 1;
+			d->type_states[a->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_STRUCT:
+		case BTF_KIND_UNION: {
+			const struct btf_member *m = btf_members(t);
+
+			for (j = 0; j < vlen; j++, m++)
+				d->type_states[m->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_FUNC_PROTO: {
+			const struct btf_param *p = btf_params(t);
+
+			for (j = 0; j < vlen; j++, p++)
+				d->type_states[p->type].referenced = 1;
+			break;
+		}
+		case BTF_KIND_DATASEC: {
+			const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+			for (j = 0; j < vlen; j++, v++)
+				d->type_states[v->type].referenced = 1;
+			break;
+		}
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
 static int btf_dump_add_emit_queue_id(struct btf_dump *d, __u32 id)
 {
 	__u32 *new_queue;
@@ -395,7 +476,12 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	}
 	case BTF_KIND_ENUM:
 	case BTF_KIND_FWD:
-		if (t->name_off != 0) {
+		/*
+		 * non-anonymous or non-referenced enums are top-level
+		 * declarations and should be emitted. Same logic can be
+		 * applied to FWDs, it won't hurt anyways.
+		 */
+		if (t->name_off != 0 || !tstate->referenced) {
 			err = btf_dump_add_emit_queue_id(d, id);
 			if (err)
 				return err;
@@ -536,11 +622,6 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id)
 	t = btf__type_by_id(d->btf, id);
 	kind = btf_kind(t);
 
-	if (top_level_def && t->name_off == 0) {
-		pr_warning("unexpected nameless definition, id:[%u]\n", id);
-		return;
-	}
-
 	if (tstate->emit_state == EMITTING) {
 		if (tstate->fwd_emitted)
 			return;
@@ -1167,6 +1248,7 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
 				return;
 			}
 
+			next_id = decls->ids[decls->cnt - 1];
 			next_t = btf__type_by_id(d->btf, next_id);
 			multidim = btf_is_array(next_t);
 			/* we need space if we have named non-pointer */
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 842c4fd55859..24fa313524fb 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -65,7 +65,6 @@ struct xsk_socket {
 	int xsks_map_fd;
 	__u32 queue_id;
 	char ifname[IFNAMSIZ];
-	bool zc;
 };
 
 struct xsk_nl_info {
@@ -491,7 +490,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
-	struct xdp_options opts;
 	struct xsk_socket *xsk;
 	socklen_t optlen;
 	int err;
@@ -611,15 +609,6 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 
 	xsk->prog_fd = -1;
 
-	optlen = sizeof(opts);
-	err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen);
-	if (err) {
-		err = -errno;
-		goto out_mmap_tx;
-	}
-
-	xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY;
-
 	if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) {
 		err = xsk_setup_xdp_prog(xsk);
 		if (err)
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index fdc0b3614a9e..a82da555b1b0 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -203,14 +203,24 @@ static int start_server(void)
 	return fd;
 }
 
+static pthread_mutex_t server_started_mtx = PTHREAD_MUTEX_INITIALIZER;
+static pthread_cond_t server_started = PTHREAD_COND_INITIALIZER;
+
 static void *server_thread(void *arg)
 {
 	struct sockaddr_storage addr;
 	socklen_t len = sizeof(addr);
 	int fd = *(int *)arg;
 	int client_fd;
+	int err;
 
-	if (CHECK_FAIL(listen(fd, 1)) < 0) {
+	err = listen(fd, 1);
+
+	pthread_mutex_lock(&server_started_mtx);
+	pthread_cond_signal(&server_started);
+	pthread_mutex_unlock(&server_started_mtx);
+
+	if (CHECK_FAIL(err < 0)) {
 		perror("Failed to listed on socket");
 		return NULL;
 	}
@@ -248,7 +258,14 @@ void test_tcp_rtt(void)
 	if (CHECK_FAIL(server_fd < 0))
 		goto close_cgroup_fd;
 
-	pthread_create(&tid, NULL, server_thread, (void *)&server_fd);
+	if (CHECK_FAIL(pthread_create(&tid, NULL, server_thread,
+				      (void *)&server_fd)))
+		goto close_cgroup_fd;
+
+	pthread_mutex_lock(&server_started_mtx);
+	pthread_cond_wait(&server_started, &server_started_mtx);
+	pthread_mutex_unlock(&server_started_mtx);
+
 	CHECK_FAIL(run_test(cgroup_fd, server_fd));
 	close(server_fd);
 close_cgroup_fd:
diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 8a399bdfd920..067eb625d01c 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -413,7 +413,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 #else
 #pragma unroll
 #endif
-	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES && i < map.cnt; ++i) {
+	for (int i = 0; i < STROBE_MAX_MAP_ENTRIES; ++i) {
+		if (i >= map.cnt)
+			break;
+
 		descr->key_lens[i] = 0;
 		len = bpf_probe_read_str(payload, STROBE_MAX_STR_LEN,
 					 map.entries[i].key);
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index 4f8ec1f10a80..a320e3844b17 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -1385,7 +1385,6 @@ static int fixup_sysctl_value(const char *buf, size_t buf_len,
 		uint8_t raw[sizeof(uint64_t)];
 		uint64_t num;
 	} value = {};
-	uint8_t c, i;
 
 	if (buf_len > sizeof(value)) {
 		log_err("Value is too big (%zd) to use in fixup", buf_len);