Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2023-07-13

We've added 67 non-merge commits during the last 15 day(s) which contain
a total of 106 files changed, 4444 insertions(+), 619 deletions(-).

The main changes are:

1) Fix bpftool build in presence of stale vmlinux.h,
   from Alexander Lobakin.

2) Introduce bpf_me_mcache_free_rcu() and fix OOM under stress,
   from Alexei Starovoitov.

3) Teach verifier actual bounds of bpf_get_smp_processor_id()
   and fix perf+libbpf issue related to custom section handling,
   from Andrii Nakryiko.

4) Introduce bpf map element count, from Anton Protopopov.

5) Check skb ownership against full socket, from Kui-Feng Lee.

6) Support for up to 12 arguments in BPF trampoline, from Menglong Dong.

7) Export rcu_request_urgent_qs_task, from Paul E. McKenney.

8) Fix BTF walking of unions, from Yafang Shao.

9) Extend link_info for kprobe_multi and perf_event links,
   from Yafang Shao.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (67 commits)
  selftests/bpf: Add selftest for PTR_UNTRUSTED
  bpf: Fix an error in verifying a field in a union
  selftests/bpf: Add selftests for nested_trust
  bpf: Fix an error around PTR_UNTRUSTED
  selftests/bpf: add testcase for TRACING with 6+ arguments
  bpf, x86: allow function arguments up to 12 for TRACING
  bpf, x86: save/restore regs with BPF_DW size
  bpftool: Use "fallthrough;" keyword instead of comments
  bpf: Add object leak check.
  bpf: Convert bpf_cpumask to bpf_mem_cache_free_rcu.
  bpf: Introduce bpf_mem_free_rcu() similar to kfree_rcu().
  selftests/bpf: Improve test coverage of bpf_mem_alloc.
  rcu: Export rcu_request_urgent_qs_task()
  bpf: Allow reuse from waiting_for_gp_ttrace list.
  bpf: Add a hint to allocated objects.
  bpf: Change bpf_mem_cache draining process.
  bpf: Further refactor alloc_bulk().
  bpf: Factor out inc/dec of active flag into helpers.
  bpf: Refactor alloc_bulk().
  bpf: Let free_all() return the number of freed elements.
  ...
====================

Link: https://lore.kernel.org/r/20230714020910.80794-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

67 files changed, 3201 insertions, 99 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-gen.rst b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
index 68454ef28f58..5006e724d1bc 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-gen.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-gen.rst
@@ -260,9 +260,9 @@ EXAMPLES
 This is example BPF application with two BPF programs and a mix of BPF maps
 and global variables. Source code is split across two source code files.
 
-**$ clang -target bpf -g example1.bpf.c -o example1.bpf.o**
+**$ clang --target=bpf -g example1.bpf.c -o example1.bpf.o**
 
-**$ clang -target bpf -g example2.bpf.c -o example2.bpf.o**
+**$ clang --target=bpf -g example2.bpf.c -o example2.bpf.o**
 
 **$ bpftool gen object example.bpf.o example1.bpf.o example2.bpf.o**
 
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 681fbcc5ed50..e9154ace80ff 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -216,7 +216,7 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 		-I$(srctree)/tools/include/uapi/ \
 		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
 		-g -O2 -Wall -fno-stack-protector \
-		-target bpf -c $< -o $@
+		--target=bpf -c $< -o $@
 	$(Q)$(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index 294de231db99..1b7f69714604 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -835,7 +835,7 @@ static void dotlabel_puts(const char *s)
 		case '|':
 		case ' ':
 			putchar('\\');
-			/* fallthrough */
+			fallthrough;
 		default:
 			putchar(*s);
 		}
diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 0675d6a46413..edda4fc2c4d0 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -757,7 +757,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type,
 		case BPF_FUNC_probe_write_user:
 			if (!full_mode)
 				continue;
-			/* fallthrough */
+			fallthrough;
 		default:
 			probe_res |= probe_helper_for_progtype(prog_type, supported_type,
 						  define_prefix, id, prog_type_str,
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2d786072ed0d..65a168df63bc 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -5,6 +5,7 @@
 #include <linux/err.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_arp.h>
+#include <linux/perf_event.h>
 #include <net/if.h>
 #include <stdio.h>
 #include <unistd.h>
@@ -14,8 +15,78 @@
 
 #include "json_writer.h"
 #include "main.h"
+#include "xlated_dumper.h"
+
+#define PERF_HW_CACHE_LEN 128
 
 static struct hashmap *link_table;
+static struct dump_data dd;
+
+static const char *perf_type_name[PERF_TYPE_MAX] = {
+	[PERF_TYPE_HARDWARE]			= "hardware",
+	[PERF_TYPE_SOFTWARE]			= "software",
+	[PERF_TYPE_TRACEPOINT]			= "tracepoint",
+	[PERF_TYPE_HW_CACHE]			= "hw-cache",
+	[PERF_TYPE_RAW]				= "raw",
+	[PERF_TYPE_BREAKPOINT]			= "breakpoint",
+};
+
+const char *event_symbols_hw[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= "cpu-cycles",
+	[PERF_COUNT_HW_INSTRUCTIONS]		= "instructions",
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= "cache-references",
+	[PERF_COUNT_HW_CACHE_MISSES]		= "cache-misses",
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= "branch-instructions",
+	[PERF_COUNT_HW_BRANCH_MISSES]		= "branch-misses",
+	[PERF_COUNT_HW_BUS_CYCLES]		= "bus-cycles",
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= "stalled-cycles-frontend",
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= "stalled-cycles-backend",
+	[PERF_COUNT_HW_REF_CPU_CYCLES]		= "ref-cycles",
+};
+
+const char *event_symbols_sw[PERF_COUNT_SW_MAX] = {
+	[PERF_COUNT_SW_CPU_CLOCK]		= "cpu-clock",
+	[PERF_COUNT_SW_TASK_CLOCK]		= "task-clock",
+	[PERF_COUNT_SW_PAGE_FAULTS]		= "page-faults",
+	[PERF_COUNT_SW_CONTEXT_SWITCHES]	= "context-switches",
+	[PERF_COUNT_SW_CPU_MIGRATIONS]		= "cpu-migrations",
+	[PERF_COUNT_SW_PAGE_FAULTS_MIN]		= "minor-faults",
+	[PERF_COUNT_SW_PAGE_FAULTS_MAJ]		= "major-faults",
+	[PERF_COUNT_SW_ALIGNMENT_FAULTS]	= "alignment-faults",
+	[PERF_COUNT_SW_EMULATION_FAULTS]	= "emulation-faults",
+	[PERF_COUNT_SW_DUMMY]			= "dummy",
+	[PERF_COUNT_SW_BPF_OUTPUT]		= "bpf-output",
+	[PERF_COUNT_SW_CGROUP_SWITCHES]		= "cgroup-switches",
+};
+
+const char *evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX] = {
+	[PERF_COUNT_HW_CACHE_L1D]		= "L1-dcache",
+	[PERF_COUNT_HW_CACHE_L1I]		= "L1-icache",
+	[PERF_COUNT_HW_CACHE_LL]		= "LLC",
+	[PERF_COUNT_HW_CACHE_DTLB]		= "dTLB",
+	[PERF_COUNT_HW_CACHE_ITLB]		= "iTLB",
+	[PERF_COUNT_HW_CACHE_BPU]		= "branch",
+	[PERF_COUNT_HW_CACHE_NODE]		= "node",
+};
+
+const char *evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX] = {
+	[PERF_COUNT_HW_CACHE_OP_READ]		= "load",
+	[PERF_COUNT_HW_CACHE_OP_WRITE]		= "store",
+	[PERF_COUNT_HW_CACHE_OP_PREFETCH]	= "prefetch",
+};
+
+const char *evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[PERF_COUNT_HW_CACHE_RESULT_ACCESS]	= "refs",
+	[PERF_COUNT_HW_CACHE_RESULT_MISS]	= "misses",
+};
+
+#define perf_event_name(array, id) ({			\
+	const char *event_str = NULL;			\
+							\
+	if ((id) >= 0 && (id) < ARRAY_SIZE(array))	\
+		event_str = array[id];			\
+	event_str;					\
+})
 
 static int link_parse_fd(int *argc, char ***argv)
 {
@@ -166,6 +237,154 @@ static int get_prog_info(int prog_id, struct bpf_prog_info *info)
 	return err;
 }
 
+static int cmp_u64(const void *A, const void *B)
+{
+	const __u64 *a = A, *b = B;
+
+	return *a - *b;
+}
+
+static void
+show_kprobe_multi_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	__u32 i, j = 0;
+	__u64 *addrs;
+
+	jsonw_bool_field(json_wtr, "retprobe",
+			 info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN);
+	jsonw_uint_field(json_wtr, "func_cnt", info->kprobe_multi.count);
+	jsonw_name(json_wtr, "funcs");
+	jsonw_start_array(json_wtr);
+	addrs = u64_to_ptr(info->kprobe_multi.addrs);
+	qsort(addrs, info->kprobe_multi.count, sizeof(addrs[0]), cmp_u64);
+
+	/* Load it once for all. */
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	for (i = 0; i < dd.sym_count; i++) {
+		if (dd.sym_mapping[i].address != addrs[j])
+			continue;
+		jsonw_start_object(json_wtr);
+		jsonw_uint_field(json_wtr, "addr", dd.sym_mapping[i].address);
+		jsonw_string_field(json_wtr, "func", dd.sym_mapping[i].name);
+		/* Print null if it is vmlinux */
+		if (dd.sym_mapping[i].module[0] == '\0') {
+			jsonw_name(json_wtr, "module");
+			jsonw_null(json_wtr);
+		} else {
+			jsonw_string_field(json_wtr, "module", dd.sym_mapping[i].module);
+		}
+		jsonw_end_object(json_wtr);
+		if (j++ == info->kprobe_multi.count)
+			break;
+	}
+	jsonw_end_array(json_wtr);
+}
+
+static void
+show_perf_event_kprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_KRETPROBE);
+	jsonw_uint_field(wtr, "addr", info->perf_event.kprobe.addr);
+	jsonw_string_field(wtr, "func",
+			   u64_to_ptr(info->perf_event.kprobe.func_name));
+	jsonw_uint_field(wtr, "offset", info->perf_event.kprobe.offset);
+}
+
+static void
+show_perf_event_uprobe_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_bool_field(wtr, "retprobe", info->perf_event.type == BPF_PERF_EVENT_URETPROBE);
+	jsonw_string_field(wtr, "file",
+			   u64_to_ptr(info->perf_event.uprobe.file_name));
+	jsonw_uint_field(wtr, "offset", info->perf_event.uprobe.offset);
+}
+
+static void
+show_perf_event_tracepoint_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	jsonw_string_field(wtr, "tracepoint",
+			   u64_to_ptr(info->perf_event.tracepoint.tp_name));
+}
+
+static char *perf_config_hw_cache_str(__u64 config)
+{
+	const char *hw_cache, *result, *op;
+	char *str = malloc(PERF_HW_CACHE_LEN);
+
+	if (!str) {
+		p_err("mem alloc failed");
+		return NULL;
+	}
+
+	hw_cache = perf_event_name(evsel__hw_cache, config & 0xff);
+	if (hw_cache)
+		snprintf(str, PERF_HW_CACHE_LEN, "%s-", hw_cache);
+	else
+		snprintf(str, PERF_HW_CACHE_LEN, "%lld-", config & 0xff);
+
+	op = perf_event_name(evsel__hw_cache_op, (config >> 8) & 0xff);
+	if (op)
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%s-", op);
+	else
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%lld-", (config >> 8) & 0xff);
+
+	result = perf_event_name(evsel__hw_cache_result, config >> 16);
+	if (result)
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%s", result);
+	else
+		snprintf(str + strlen(str), PERF_HW_CACHE_LEN - strlen(str),
+			 "%lld", config >> 16);
+	return str;
+}
+
+static const char *perf_config_str(__u32 type, __u64 config)
+{
+	const char *perf_config;
+
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+		perf_config = perf_event_name(event_symbols_hw, config);
+		break;
+	case PERF_TYPE_SOFTWARE:
+		perf_config = perf_event_name(event_symbols_sw, config);
+		break;
+	case PERF_TYPE_HW_CACHE:
+		perf_config = perf_config_hw_cache_str(config);
+		break;
+	default:
+		perf_config = NULL;
+		break;
+	}
+	return perf_config;
+}
+
+static void
+show_perf_event_event_json(struct bpf_link_info *info, json_writer_t *wtr)
+{
+	__u64 config = info->perf_event.event.config;
+	__u32 type = info->perf_event.event.type;
+	const char *perf_type, *perf_config;
+
+	perf_type = perf_event_name(perf_type_name, type);
+	if (perf_type)
+		jsonw_string_field(wtr, "event_type", perf_type);
+	else
+		jsonw_uint_field(wtr, "event_type", type);
+
+	perf_config = perf_config_str(type, config);
+	if (perf_config)
+		jsonw_string_field(wtr, "event_config", perf_config);
+	else
+		jsonw_uint_field(wtr, "event_config", config);
+
+	if (type == PERF_TYPE_HW_CACHE && perf_config)
+		free((void *)perf_config);
+}
+
 static int show_link_close_json(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -218,6 +437,29 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		jsonw_uint_field(json_wtr, "map_id",
 				 info->struct_ops.map_id);
 		break;
+	case BPF_LINK_TYPE_KPROBE_MULTI:
+		show_kprobe_multi_json(info, json_wtr);
+		break;
+	case BPF_LINK_TYPE_PERF_EVENT:
+		switch (info->perf_event.type) {
+		case BPF_PERF_EVENT_EVENT:
+			show_perf_event_event_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_TRACEPOINT:
+			show_perf_event_tracepoint_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			show_perf_event_kprobe_json(info, json_wtr);
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			show_perf_event_uprobe_json(info, json_wtr);
+			break;
+		default:
+			break;
+		}
+		break;
 	default:
 		break;
 	}
@@ -351,6 +593,113 @@ void netfilter_dump_plain(const struct bpf_link_info *info)
 		printf(" flags 0x%x", info->netfilter.flags);
 }
 
+static void show_kprobe_multi_plain(struct bpf_link_info *info)
+{
+	__u32 i, j = 0;
+	__u64 *addrs;
+
+	if (!info->kprobe_multi.count)
+		return;
+
+	if (info->kprobe_multi.flags & BPF_F_KPROBE_MULTI_RETURN)
+		printf("\n\tkretprobe.multi  ");
+	else
+		printf("\n\tkprobe.multi  ");
+	printf("func_cnt %u  ", info->kprobe_multi.count);
+	addrs = (__u64 *)u64_to_ptr(info->kprobe_multi.addrs);
+	qsort(addrs, info->kprobe_multi.count, sizeof(__u64), cmp_u64);
+
+	/* Load it once for all. */
+	if (!dd.sym_count)
+		kernel_syms_load(&dd);
+	if (!dd.sym_count)
+		return;
+
+	printf("\n\t%-16s %s", "addr", "func [module]");
+	for (i = 0; i < dd.sym_count; i++) {
+		if (dd.sym_mapping[i].address != addrs[j])
+			continue;
+		printf("\n\t%016lx %s",
+		       dd.sym_mapping[i].address, dd.sym_mapping[i].name);
+		if (dd.sym_mapping[i].module[0] != '\0')
+			printf(" [%s]  ", dd.sym_mapping[i].module);
+		else
+			printf("  ");
+
+		if (j++ == info->kprobe_multi.count)
+			break;
+	}
+}
+
+static void show_perf_event_kprobe_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.kprobe.func_name);
+	if (buf[0] == '\0' && !info->perf_event.kprobe.addr)
+		return;
+
+	if (info->perf_event.type == BPF_PERF_EVENT_KRETPROBE)
+		printf("\n\tkretprobe ");
+	else
+		printf("\n\tkprobe ");
+	if (info->perf_event.kprobe.addr)
+		printf("%llx ", info->perf_event.kprobe.addr);
+	printf("%s", buf);
+	if (info->perf_event.kprobe.offset)
+		printf("+%#x", info->perf_event.kprobe.offset);
+	printf("  ");
+}
+
+static void show_perf_event_uprobe_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.uprobe.file_name);
+	if (buf[0] == '\0')
+		return;
+
+	if (info->perf_event.type == BPF_PERF_EVENT_URETPROBE)
+		printf("\n\turetprobe ");
+	else
+		printf("\n\tuprobe ");
+	printf("%s+%#x  ", buf, info->perf_event.uprobe.offset);
+}
+
+static void show_perf_event_tracepoint_plain(struct bpf_link_info *info)
+{
+	const char *buf;
+
+	buf = u64_to_ptr(info->perf_event.tracepoint.tp_name);
+	if (buf[0] == '\0')
+		return;
+
+	printf("\n\ttracepoint %s  ", buf);
+}
+
+static void show_perf_event_event_plain(struct bpf_link_info *info)
+{
+	__u64 config = info->perf_event.event.config;
+	__u32 type = info->perf_event.event.type;
+	const char *perf_type, *perf_config;
+
+	printf("\n\tevent ");
+	perf_type = perf_event_name(perf_type_name, type);
+	if (perf_type)
+		printf("%s:", perf_type);
+	else
+		printf("%u :", type);
+
+	perf_config = perf_config_str(type, config);
+	if (perf_config)
+		printf("%s  ", perf_config);
+	else
+		printf("%llu  ", config);
+
+	if (type == PERF_TYPE_HW_CACHE && perf_config)
+		free((void *)perf_config);
+}
+
 static int show_link_close_plain(int fd, struct bpf_link_info *info)
 {
 	struct bpf_prog_info prog_info;
@@ -396,6 +745,29 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 	case BPF_LINK_TYPE_NETFILTER:
 		netfilter_dump_plain(info);
 		break;
+	case BPF_LINK_TYPE_KPROBE_MULTI:
+		show_kprobe_multi_plain(info);
+		break;
+	case BPF_LINK_TYPE_PERF_EVENT:
+		switch (info->perf_event.type) {
+		case BPF_PERF_EVENT_EVENT:
+			show_perf_event_event_plain(info);
+			break;
+		case BPF_PERF_EVENT_TRACEPOINT:
+			show_perf_event_tracepoint_plain(info);
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			show_perf_event_kprobe_plain(info);
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			show_perf_event_uprobe_plain(info);
+			break;
+		default:
+			break;
+		}
+		break;
 	default:
 		break;
 	}
@@ -417,10 +789,13 @@ static int do_show_link(int fd)
 {
 	struct bpf_link_info info;
 	__u32 len = sizeof(info);
-	char buf[256];
+	__u64 *addrs = NULL;
+	char buf[PATH_MAX];
+	int count;
 	int err;
 
 	memset(&info, 0, sizeof(info));
+	buf[0] = '\0';
 again:
 	err = bpf_link_get_info_by_fd(fd, &info, &len);
 	if (err) {
@@ -431,22 +806,67 @@ again:
 	}
 	if (info.type == BPF_LINK_TYPE_RAW_TRACEPOINT &&
 	    !info.raw_tracepoint.tp_name) {
-		info.raw_tracepoint.tp_name = (unsigned long)&buf;
+		info.raw_tracepoint.tp_name = ptr_to_u64(&buf);
 		info.raw_tracepoint.tp_name_len = sizeof(buf);
 		goto again;
 	}
 	if (info.type == BPF_LINK_TYPE_ITER &&
 	    !info.iter.target_name) {
-		info.iter.target_name = (unsigned long)&buf;
+		info.iter.target_name = ptr_to_u64(&buf);
 		info.iter.target_name_len = sizeof(buf);
 		goto again;
 	}
+	if (info.type == BPF_LINK_TYPE_KPROBE_MULTI &&
+	    !info.kprobe_multi.addrs) {
+		count = info.kprobe_multi.count;
+		if (count) {
+			addrs = calloc(count, sizeof(__u64));
+			if (!addrs) {
+				p_err("mem alloc failed");
+				close(fd);
+				return -ENOMEM;
+			}
+			info.kprobe_multi.addrs = ptr_to_u64(addrs);
+			goto again;
+		}
+	}
+	if (info.type == BPF_LINK_TYPE_PERF_EVENT) {
+		switch (info.perf_event.type) {
+		case BPF_PERF_EVENT_TRACEPOINT:
+			if (!info.perf_event.tracepoint.tp_name) {
+				info.perf_event.tracepoint.tp_name = ptr_to_u64(&buf);
+				info.perf_event.tracepoint.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		case BPF_PERF_EVENT_KPROBE:
+		case BPF_PERF_EVENT_KRETPROBE:
+			if (!info.perf_event.kprobe.func_name) {
+				info.perf_event.kprobe.func_name = ptr_to_u64(&buf);
+				info.perf_event.kprobe.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		case BPF_PERF_EVENT_UPROBE:
+		case BPF_PERF_EVENT_URETPROBE:
+			if (!info.perf_event.uprobe.file_name) {
+				info.perf_event.uprobe.file_name = ptr_to_u64(&buf);
+				info.perf_event.uprobe.name_len = sizeof(buf);
+				goto again;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	if (json_output)
 		show_link_close_json(fd, &info);
 	else
 		show_link_close_plain(fd, &info);
 
+	if (addrs)
+		free(addrs);
 	close(fd);
 	return 0;
 }
@@ -471,7 +891,8 @@ static int do_show(int argc, char **argv)
 		fd = link_parse_fd(&argc, &argv);
 		if (fd < 0)
 			return fd;
-		return do_show_link(fd);
+		do_show_link(fd);
+		goto out;
 	}
 
 	if (argc)
@@ -510,6 +931,9 @@ static int do_show(int argc, char **argv)
 	if (show_pinned)
 		delete_pinned_obj_table(link_table);
 
+out:
+	if (dd.sym_count)
+		kernel_syms_destroy(&dd);
 	return errno == ENOENT ? 0 : -1;
 }
 
diff --git a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
index eb05ea53afb1..26004f0c5a6a 100644
--- a/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
+++ b/tools/bpf/bpftool/skeleton/pid_iter.bpf.c
@@ -15,6 +15,19 @@ enum bpf_obj_type {
 	BPF_OBJ_BTF,
 };
 
+struct bpf_perf_link___local {
+	struct bpf_link link;
+	struct file *perf_file;
+} __attribute__((preserve_access_index));
+
+struct perf_event___local {
+	u64 bpf_cookie;
+} __attribute__((preserve_access_index));
+
+enum bpf_link_type___local {
+	BPF_LINK_TYPE_PERF_EVENT___local = 7,
+};
+
 extern const void bpf_link_fops __ksym;
 extern const void bpf_map_fops __ksym;
 extern const void bpf_prog_fops __ksym;
@@ -41,10 +54,10 @@ static __always_inline __u32 get_obj_id(void *ent, enum bpf_obj_type type)
 /* could be used only with BPF_LINK_TYPE_PERF_EVENT links */
 static __u64 get_bpf_cookie(struct bpf_link *link)
 {
-	struct bpf_perf_link *perf_link;
-	struct perf_event *event;
+	struct bpf_perf_link___local *perf_link;
+	struct perf_event___local *event;
 
-	perf_link = container_of(link, struct bpf_perf_link, link);
+	perf_link = container_of(link, struct bpf_perf_link___local, link);
 	event = BPF_CORE_READ(perf_link, perf_file, private_data);
 	return BPF_CORE_READ(event, bpf_cookie);
 }
@@ -84,10 +97,13 @@ int iter(struct bpf_iter__task_file *ctx)
 	e.pid = task->tgid;
 	e.id = get_obj_id(file->private_data, obj_type);
 
-	if (obj_type == BPF_OBJ_LINK) {
+	if (obj_type == BPF_OBJ_LINK &&
+	    bpf_core_enum_value_exists(enum bpf_link_type___local,
+				       BPF_LINK_TYPE_PERF_EVENT___local)) {
 		struct bpf_link *link = (struct bpf_link *) file->private_data;
 
-		if (BPF_CORE_READ(link, type) == BPF_LINK_TYPE_PERF_EVENT) {
+		if (link->type == bpf_core_enum_value(enum bpf_link_type___local,
+						      BPF_LINK_TYPE_PERF_EVENT___local)) {
 			e.has_bpf_cookie = true;
 			e.bpf_cookie = get_bpf_cookie(link);
 		}
diff --git a/tools/bpf/bpftool/skeleton/profiler.bpf.c b/tools/bpf/bpftool/skeleton/profiler.bpf.c
index ce5b65e07ab1..2f80edc682f1 100644
--- a/tools/bpf/bpftool/skeleton/profiler.bpf.c
+++ b/tools/bpf/bpftool/skeleton/profiler.bpf.c
@@ -4,6 +4,12 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+struct bpf_perf_event_value___local {
+	__u64 counter;
+	__u64 enabled;
+	__u64 running;
+} __attribute__((preserve_access_index));
+
 /* map of perf event fds, num_cpu * num_metric entries */
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
@@ -15,14 +21,14 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
 } fentry_readings SEC(".maps");
 
 /* accumulated readings */
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(key_size, sizeof(u32));
-	__uint(value_size, sizeof(struct bpf_perf_event_value));
+	__uint(value_size, sizeof(struct bpf_perf_event_value___local));
 } accum_readings SEC(".maps");
 
 /* sample counts, one per cpu */
@@ -39,7 +45,7 @@ const volatile __u32 num_metric = 1;
 SEC("fentry/XXX")
 int BPF_PROG(fentry_XXX)
 {
-	struct bpf_perf_event_value *ptrs[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local *ptrs[MAX_NUM_MATRICS];
 	u32 key = bpf_get_smp_processor_id();
 	u32 i;
 
@@ -53,10 +59,10 @@ int BPF_PROG(fentry_XXX)
 	}
 
 	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
-		struct bpf_perf_event_value reading;
+		struct bpf_perf_event_value___local reading;
 		int err;
 
-		err = bpf_perf_event_read_value(&events, key, &reading,
+		err = bpf_perf_event_read_value(&events, key, (void *)&reading,
 						sizeof(reading));
 		if (err)
 			return 0;
@@ -68,14 +74,14 @@ int BPF_PROG(fentry_XXX)
 }
 
 static inline void
-fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
+fexit_update_maps(u32 id, struct bpf_perf_event_value___local *after)
 {
-	struct bpf_perf_event_value *before, diff;
+	struct bpf_perf_event_value___local *before, diff;
 
 	before = bpf_map_lookup_elem(&fentry_readings, &id);
 	/* only account samples with a valid fentry_reading */
 	if (before && before->counter) {
-		struct bpf_perf_event_value *accum;
+		struct bpf_perf_event_value___local *accum;
 
 		diff.counter = after->counter - before->counter;
 		diff.enabled = after->enabled - before->enabled;
@@ -93,7 +99,7 @@ fexit_update_maps(u32 id, struct bpf_perf_event_value *after)
 SEC("fexit/XXX")
 int BPF_PROG(fexit_XXX)
 {
-	struct bpf_perf_event_value readings[MAX_NUM_MATRICS];
+	struct bpf_perf_event_value___local readings[MAX_NUM_MATRICS];
 	u32 cpu = bpf_get_smp_processor_id();
 	u32 i, zero = 0;
 	int err;
@@ -102,7 +108,8 @@ int BPF_PROG(fexit_XXX)
 	/* read all events before updating the maps, to reduce error */
 	for (i = 0; i < num_metric && i < MAX_NUM_MATRICS; i++) {
 		err = bpf_perf_event_read_value(&events, cpu + i * num_cpu,
-						readings + i, sizeof(*readings));
+						(void *)(readings + i),
+						sizeof(*readings));
 		if (err)
 			return 0;
 	}
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index da608e10c843..567f56dfd9f1 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -46,7 +46,11 @@ out:
 		}
 		dd->sym_mapping = tmp;
 		sym = &dd->sym_mapping[dd->sym_count];
-		if (sscanf(buff, "%p %*c %s", &address, sym->name) != 2)
+
+		/* module is optional */
+		sym->module[0] = '\0';
+		/* trim the square brackets around the module name */
+		if (sscanf(buff, "%p %*c %s [%[^]]s", &address, sym->name, sym->module) < 2)
 			continue;
 		sym->address = (unsigned long)address;
 		if (!strcmp(sym->name, "__bpf_call_base")) {
diff --git a/tools/bpf/bpftool/xlated_dumper.h b/tools/bpf/bpftool/xlated_dumper.h
index 9a946377b0e6..db3ba0671501 100644
--- a/tools/bpf/bpftool/xlated_dumper.h
+++ b/tools/bpf/bpftool/xlated_dumper.h
@@ -5,12 +5,14 @@
 #define __BPF_TOOL_XLATED_DUMPER_H
 
 #define SYM_MAX_NAME	256
+#define MODULE_MAX_NAME	64
 
 struct bpf_prog_linfo;
 
 struct kernel_sym {
 	unsigned long address;
 	char name[SYM_MAX_NAME];
+	char module[MODULE_MAX_NAME];
 };
 
 struct dump_data {
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index 47acf6936516..d8288936c912 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -62,7 +62,7 @@ $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
 	$(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@
 
 $(OUTPUT)/%.bpf.o: %.bpf.c $(BPFOBJ) | $(OUTPUT)
-	$(QUIET_GEN)$(CLANG) -g -O2 -target bpf $(INCLUDES)		      \
+	$(QUIET_GEN)$(CLANG) -g -O2 --target=bpf $(INCLUDES)		      \
 		 -c $(filter %.c,$^) -o $@ &&				      \
 	$(LLVM_STRIP) -g $@
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0f0aa9b7d7b5..6654b1a35ab3 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -372,7 +372,7 @@ $(OUTPUT)test-libzstd.bin:
 	$(BUILD) -lzstd
 
 $(OUTPUT)test-clang-bpf-co-re.bin:
-	$(CLANG) -S -g -target bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
+	$(CLANG) -S -g --target=bpf -o - $(patsubst %.bin,%.c,$(@F)) |	\
 		grep BTF_KIND_VAR
 
 $(OUTPUT)test-file-handle.bin:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 60a9d59beeab..600d0caebbd8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1057,6 +1057,16 @@ enum bpf_link_type {
 	MAX_BPF_LINK_TYPE,
 };
 
+enum bpf_perf_event_type {
+	BPF_PERF_EVENT_UNSPEC = 0,
+	BPF_PERF_EVENT_UPROBE = 1,
+	BPF_PERF_EVENT_URETPROBE = 2,
+	BPF_PERF_EVENT_KPROBE = 3,
+	BPF_PERF_EVENT_KRETPROBE = 4,
+	BPF_PERF_EVENT_TRACEPOINT = 5,
+	BPF_PERF_EVENT_EVENT = 6,
+};
+
 /* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
  *
  * NONE(default): No further bpf programs allowed in the subtree.
@@ -6439,6 +6449,36 @@ struct bpf_link_info {
 			__s32 priority;
 			__u32 flags;
 		} netfilter;
+		struct {
+			__aligned_u64 addrs;
+			__u32 count; /* in/out: kprobe_multi function count */
+			__u32 flags;
+		} kprobe_multi;
+		struct {
+			__u32 type; /* enum bpf_perf_event_type */
+			__u32 :32;
+			union {
+				struct {
+					__aligned_u64 file_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from file_name */
+				} uprobe; /* BPF_PERF_EVENT_UPROBE, BPF_PERF_EVENT_URETPROBE */
+				struct {
+					__aligned_u64 func_name; /* in/out */
+					__u32 name_len;
+					__u32 offset; /* offset from func_name */
+					__u64 addr;
+				} kprobe; /* BPF_PERF_EVENT_KPROBE, BPF_PERF_EVENT_KRETPROBE */
+				struct {
+					__aligned_u64 tp_name;   /* in/out */
+					__u32 name_len;
+				} tracepoint; /* BPF_PERF_EVENT_TRACEPOINT */
+				struct {
+					__u64 config;
+					__u32 type;
+				} event; /* BPF_PERF_EVENT_EVENT */
+			};
+		} perf_event;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index ed86b37d8024..3b0da19715e1 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -741,6 +741,14 @@ int bpf_link_create(int prog_fd, int target_fd,
 		if (!OPTS_ZEROED(opts, tracing))
 			return libbpf_err(-EINVAL);
 		break;
+	case BPF_NETFILTER:
+		attr.link_create.netfilter.pf = OPTS_GET(opts, netfilter.pf, 0);
+		attr.link_create.netfilter.hooknum = OPTS_GET(opts, netfilter.hooknum, 0);
+		attr.link_create.netfilter.priority = OPTS_GET(opts, netfilter.priority, 0);
+		attr.link_create.netfilter.flags = OPTS_GET(opts, netfilter.flags, 0);
+		if (!OPTS_ZEROED(opts, netfilter))
+			return libbpf_err(-EINVAL);
+		break;
 	default:
 		if (!OPTS_ZEROED(opts, flags))
 			return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 9aa0ee473754..c676295ab9bf 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -349,6 +349,12 @@ struct bpf_link_create_opts {
 		struct {
 			__u64 cookie;
 		} tracing;
+		struct {
+			__u32 pf;
+			__u32 hooknum;
+			__s32 priority;
+			__u32 flags;
+		} netfilter;
 	};
 	size_t :0;
 };
diff --git a/tools/lib/bpf/hashmap.h b/tools/lib/bpf/hashmap.h
index 0a5bf1937a7c..c12f8320e668 100644
--- a/tools/lib/bpf/hashmap.h
+++ b/tools/lib/bpf/hashmap.h
@@ -80,16 +80,6 @@ struct hashmap {
 	size_t sz;
 };
 
-#define HASHMAP_INIT(hash_fn, equal_fn, ctx) {	\
-	.hash_fn = (hash_fn),			\
-	.equal_fn = (equal_fn),			\
-	.ctx = (ctx),				\
-	.buckets = NULL,			\
-	.cap = 0,				\
-	.cap_bits = 0,				\
-	.sz = 0,				\
-}
-
 void hashmap__init(struct hashmap *map, hashmap_hash_fn hash_fn,
 		   hashmap_equal_fn equal_fn, void *ctx);
 struct hashmap *hashmap__new(hashmap_hash_fn hash_fn,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 214f828ece6b..63311a73c16d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5471,6 +5471,10 @@ static int load_module_btfs(struct bpf_object *obj)
 		err = bpf_btf_get_next_id(id, &id);
 		if (err && errno == ENOENT)
 			return 0;
+		if (err && errno == EPERM) {
+			pr_debug("skipping module BTFs loading, missing privileges\n");
+			return 0;
+		}
 		if (err) {
 			err = -errno;
 			pr_warn("failed to iterate BTF objects: %d\n", err);
@@ -6157,7 +6161,11 @@ static int append_subprog_relos(struct bpf_program *main_prog, struct bpf_progra
 	if (main_prog == subprog)
 		return 0;
 	relos = libbpf_reallocarray(main_prog->reloc_desc, new_cnt, sizeof(*relos));
-	if (!relos)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (!relos && new_cnt)
 		return -ENOMEM;
 	if (subprog->nr_reloc)
 		memcpy(relos + main_prog->nr_reloc, subprog->reloc_desc,
@@ -8528,7 +8536,8 @@ int bpf_program__set_insns(struct bpf_program *prog,
 		return -EBUSY;
 
 	insns = libbpf_reallocarray(prog->insns, new_insn_cnt, sizeof(*insns));
-	if (!insns) {
+	/* NULL is a valid return from reallocarray if the new count is zero */
+	if (!insns && new_insn_cnt) {
 		pr_warn("prog '%s': failed to realloc prog code\n", prog->name);
 		return -ENOMEM;
 	}
@@ -8558,13 +8567,31 @@ enum bpf_prog_type bpf_program__type(const struct bpf_program *prog)
 	return prog->type;
 }
 
+static size_t custom_sec_def_cnt;
+static struct bpf_sec_def *custom_sec_defs;
+static struct bpf_sec_def custom_fallback_def;
+static bool has_custom_fallback_def;
+static int last_custom_sec_def_handler_id;
+
 int bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type)
 {
 	if (prog->obj->loaded)
 		return libbpf_err(-EBUSY);
 
+	/* if type is not changed, do nothing */
+	if (prog->type == type)
+		return 0;
+
 	prog->type = type;
-	prog->sec_def = NULL;
+
+	/* If a program type was changed, we need to reset associated SEC()
+	 * handler, as it will be invalid now. The only exception is a generic
+	 * fallback handler, which by definition is program type-agnostic and
+	 * is a catch-all custom handler, optionally set by the application,
+	 * so should be able to handle any type of BPF program.
+	 */
+	if (prog->sec_def != &custom_fallback_def)
+		prog->sec_def = NULL;
 	return 0;
 }
 
@@ -8740,13 +8767,6 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("netfilter",		NETFILTER, BPF_NETFILTER, SEC_NONE),
 };
 
-static size_t custom_sec_def_cnt;
-static struct bpf_sec_def *custom_sec_defs;
-static struct bpf_sec_def custom_fallback_def;
-static bool has_custom_fallback_def;
-
-static int last_custom_sec_def_handler_id;
-
 int libbpf_register_prog_handler(const char *sec,
 				 enum bpf_prog_type prog_type,
 				 enum bpf_attach_type exp_attach_type,
@@ -8826,7 +8846,11 @@ int libbpf_unregister_prog_handler(int handler_id)
 
 	/* try to shrink the array, but it's ok if we couldn't */
 	sec_defs = libbpf_reallocarray(custom_sec_defs, custom_sec_def_cnt, sizeof(*sec_defs));
-	if (sec_defs)
+	/* if new count is zero, reallocarray can return a valid NULL result;
+	 * in this case the previous pointer will be freed, so we *have to*
+	 * reassign old pointer to the new value (even if it's NULL)
+	 */
+	if (sec_defs || custom_sec_def_cnt == 0)
 		custom_sec_defs = sec_defs;
 
 	return 0;
@@ -10224,6 +10248,18 @@ static const char *tracefs_uprobe_events(void)
 	return use_debugfs() ? DEBUGFS"/uprobe_events" : TRACEFS"/uprobe_events";
 }
 
+static const char *tracefs_available_filter_functions(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions"
+			     : TRACEFS"/available_filter_functions";
+}
+
+static const char *tracefs_available_filter_functions_addrs(void)
+{
+	return use_debugfs() ? DEBUGFS"/available_filter_functions_addrs"
+			     : TRACEFS"/available_filter_functions_addrs";
+}
+
 static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
 					 const char *kfunc_name, size_t offset)
 {
@@ -10539,25 +10575,158 @@ struct kprobe_multi_resolve {
 	size_t cnt;
 };
 
-static int
-resolve_kprobe_multi_cb(unsigned long long sym_addr, char sym_type,
-			const char *sym_name, void *ctx)
+struct avail_kallsyms_data {
+	char **syms;
+	size_t cnt;
+	struct kprobe_multi_resolve *res;
+};
+
+static int avail_func_cmp(const void *a, const void *b)
 {
-	struct kprobe_multi_resolve *res = ctx;
+	return strcmp(*(const char **)a, *(const char **)b);
+}
+
+static int avail_kallsyms_cb(unsigned long long sym_addr, char sym_type,
+			     const char *sym_name, void *ctx)
+{
+	struct avail_kallsyms_data *data = ctx;
+	struct kprobe_multi_resolve *res = data->res;
 	int err;
 
-	if (!glob_match(sym_name, res->pattern))
+	if (!bsearch(&sym_name, data->syms, data->cnt, sizeof(*data->syms), avail_func_cmp))
 		return 0;
 
-	err = libbpf_ensure_mem((void **) &res->addrs, &res->cap, sizeof(unsigned long),
-				res->cnt + 1);
+	err = libbpf_ensure_mem((void **)&res->addrs, &res->cap, sizeof(*res->addrs), res->cnt + 1);
 	if (err)
 		return err;
 
-	res->addrs[res->cnt++] = (unsigned long) sym_addr;
+	res->addrs[res->cnt++] = (unsigned long)sym_addr;
 	return 0;
 }
 
+static int libbpf_available_kallsyms_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_functions_file = tracefs_available_filter_functions();
+	struct avail_kallsyms_data data;
+	char sym_name[500];
+	FILE *f;
+	int err = 0, ret, i;
+	char **syms = NULL;
+	size_t cap = 0, cnt = 0;
+
+	f = fopen(available_functions_file, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_functions_file, err);
+		return err;
+	}
+
+	while (true) {
+		char *name;
+
+		ret = fscanf(f, "%499s%*[^\n]\n", sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 1) {
+			pr_warn("failed to parse available_filter_functions entry: %d\n", ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&syms, &cap, sizeof(*syms), cnt + 1);
+		if (err)
+			goto cleanup;
+
+		name = strdup(sym_name);
+		if (!name) {
+			err = -errno;
+			goto cleanup;
+		}
+
+		syms[cnt++] = name;
+	}
+
+	/* no entries found, bail out */
+	if (cnt == 0) {
+		err = -ENOENT;
+		goto cleanup;
+	}
+
+	/* sort available functions */
+	qsort(syms, cnt, sizeof(*syms), avail_func_cmp);
+
+	data.syms = syms;
+	data.res = res;
+	data.cnt = cnt;
+	libbpf_kallsyms_parse(avail_kallsyms_cb, &data);
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	for (i = 0; i < cnt; i++)
+		free((char *)syms[i]);
+	free(syms);
+
+	fclose(f);
+	return err;
+}
+
+static bool has_available_filter_functions_addrs(void)
+{
+	return access(tracefs_available_filter_functions_addrs(), R_OK) != -1;
+}
+
+static int libbpf_available_kprobes_parse(struct kprobe_multi_resolve *res)
+{
+	const char *available_path = tracefs_available_filter_functions_addrs();
+	char sym_name[500];
+	FILE *f;
+	int ret, err = 0;
+	unsigned long long sym_addr;
+
+	f = fopen(available_path, "re");
+	if (!f) {
+		err = -errno;
+		pr_warn("failed to open %s: %d\n", available_path, err);
+		return err;
+	}
+
+	while (true) {
+		ret = fscanf(f, "%llx %499s%*[^\n]\n", &sym_addr, sym_name);
+		if (ret == EOF && feof(f))
+			break;
+
+		if (ret != 2) {
+			pr_warn("failed to parse available_filter_functions_addrs entry: %d\n",
+				ret);
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (!glob_match(sym_name, res->pattern))
+			continue;
+
+		err = libbpf_ensure_mem((void **)&res->addrs, &res->cap,
+					sizeof(*res->addrs), res->cnt + 1);
+		if (err)
+			goto cleanup;
+
+		res->addrs[res->cnt++] = (unsigned long)sym_addr;
+	}
+
+	if (res->cnt == 0)
+		err = -ENOENT;
+
+cleanup:
+	fclose(f);
+	return err;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 				      const char *pattern,
@@ -10594,13 +10763,12 @@ bpf_program__attach_kprobe_multi_opts(const struct bpf_program *prog,
 		return libbpf_err_ptr(-EINVAL);
 
 	if (pattern) {
-		err = libbpf_kallsyms_parse(resolve_kprobe_multi_cb, &res);
+		if (has_available_filter_functions_addrs())
+			err = libbpf_available_kprobes_parse(&res);
+		else
+			err = libbpf_available_kallsyms_parse(&res);
 		if (err)
 			goto error;
-		if (!res.cnt) {
-			err = -ENOENT;
-			goto error;
-		}
 		addrs = res.addrs;
 		cnt = res.cnt;
 	}
@@ -11811,6 +11979,48 @@ static int attach_iter(const struct bpf_program *prog, long cookie, struct bpf_l
 	return libbpf_get_error(*link);
 }
 
+struct bpf_link *bpf_program__attach_netfilter(const struct bpf_program *prog,
+					       const struct bpf_netfilter_opts *opts)
+{
+	LIBBPF_OPTS(bpf_link_create_opts, lopts);
+	struct bpf_link *link;
+	int prog_fd, link_fd;
+
+	if (!OPTS_VALID(opts, bpf_netfilter_opts))
+		return libbpf_err_ptr(-EINVAL);
+
+	prog_fd = bpf_program__fd(prog);
+	if (prog_fd < 0) {
+		pr_warn("prog '%s': can't attach before loaded\n", prog->name);
+		return libbpf_err_ptr(-EINVAL);
+	}
+
+	link = calloc(1, sizeof(*link));
+	if (!link)
+		return libbpf_err_ptr(-ENOMEM);
+
+	link->detach = &bpf_link__detach_fd;
+
+	lopts.netfilter.pf = OPTS_GET(opts, pf, 0);
+	lopts.netfilter.hooknum = OPTS_GET(opts, hooknum, 0);
+	lopts.netfilter.priority = OPTS_GET(opts, priority, 0);
+	lopts.netfilter.flags = OPTS_GET(opts, flags, 0);
+
+	link_fd = bpf_link_create(prog_fd, 0, BPF_NETFILTER, &lopts);
+	if (link_fd < 0) {
+		char errmsg[STRERR_BUFSIZE];
+
+		link_fd = -errno;
+		free(link);
+		pr_warn("prog '%s': failed to attach to netfilter: %s\n",
+			prog->name, libbpf_strerror_r(link_fd, errmsg, sizeof(errmsg)));
+		return libbpf_err_ptr(link_fd);
+	}
+	link->fd = link_fd;
+
+	return link;
+}
+
 struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 {
 	struct bpf_link *link = NULL;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 754da73c643b..10642ad69d76 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -718,6 +718,21 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
+struct bpf_netfilter_opts {
+	/* size of this struct, for forward/backward compatibility */
+	size_t sz;
+
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+};
+#define bpf_netfilter_opts__last_field flags
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_netfilter(const struct bpf_program *prog,
+			      const struct bpf_netfilter_opts *opts);
+
 struct bpf_map;
 
 LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 7521a2fb7626..d9ec4407befa 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,4 +395,5 @@ LIBBPF_1.2.0 {
 LIBBPF_1.3.0 {
 	global:
 		bpf_obj_pin_opts;
+		bpf_program__attach_netfilter;
 } LIBBPF_1.2.0;
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index f1a141555f08..37455d00b239 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -852,8 +852,11 @@ static int bpf_link_usdt_detach(struct bpf_link *link)
 		 * system is so exhausted on memory, it's the least of user's
 		 * concerns, probably.
 		 * So just do our best here to return those IDs to usdt_manager.
+		 * Another edge case when we can legitimately get NULL is when
+		 * new_cnt is zero, which can happen in some edge cases, so we
+		 * need to be careful about that.
 		 */
-		if (new_free_ids) {
+		if (new_free_ids || new_cnt == 0) {
 			memcpy(new_free_ids + man->free_spec_cnt, usdt_link->spec_ids,
 			       usdt_link->spec_cnt * sizeof(*usdt_link->spec_ids));
 			man->free_spec_ids = new_free_ids;
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index 08adc805878b..3b61e8b35d62 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -10,3 +10,5 @@ kprobe_multi_test/link_api_addrs                 # link_fd unexpected link_fd: a
 kprobe_multi_test/link_api_syms                  # link_fd unexpected link_fd: actual -95 < expected 0
 kprobe_multi_test/skel_api                       # libbpf: failed to load BPF skeleton 'kprobe_multi': -3
 module_attach                                    # prog 'kprobe_multi': failed to auto-attach: -95
+fentry_test/fentry_many_args                     # fentry_many_args:FAIL:fentry_many_args_attach unexpected error: -524
+fexit_test/fexit_many_args                       # fexit_many_args:FAIL:fexit_many_args_attach unexpected error: -524
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 538df8fb8c42..882be03b179f 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -12,7 +12,11 @@ BPFDIR := $(LIBDIR)/bpf
 TOOLSINCDIR := $(TOOLSDIR)/include
 BPFTOOLDIR := $(TOOLSDIR)/bpf/bpftool
 APIDIR := $(TOOLSINCDIR)/uapi
+ifneq ($(O),)
+GENDIR := $(O)/include/generated
+else
 GENDIR := $(abspath ../../../../include/generated)
+endif
 GENHDR := $(GENDIR)/autoconf.h
 HOSTPKG_CONFIG := pkg-config
 
@@ -331,7 +335,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -372,12 +376,12 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
 # $3 - CFLAGS
 define CLANG_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
@@ -644,11 +648,13 @@ $(OUTPUT)/bench_local_storage.o: $(OUTPUT)/local_storage_bench.skel.h
 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o: $(OUTPUT)/local_storage_rcu_tasks_trace_bench.skel.h
 $(OUTPUT)/bench_local_storage_create.o: $(OUTPUT)/bench_local_storage_create.skel.h
 $(OUTPUT)/bench_bpf_hashmap_lookup.o: $(OUTPUT)/bpf_hashmap_lookup.skel.h
+$(OUTPUT)/bench_htab_mem.o: $(OUTPUT)/htab_mem_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(TESTING_HELPERS) \
 		 $(TRACE_HELPERS) \
+		 $(CGROUP_HELPERS) \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
 		 $(OUTPUT)/bench_trigger.o \
@@ -661,6 +667,7 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_local_storage_rcu_tasks_trace.o \
 		 $(OUTPUT)/bench_bpf_hashmap_lookup.o \
 		 $(OUTPUT)/bench_local_storage_create.o \
+		 $(OUTPUT)/bench_htab_mem.o \
 		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 41fe5a82b88b..73ce11b0547d 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -279,6 +279,7 @@ extern struct argp bench_local_storage_rcu_tasks_trace_argp;
 extern struct argp bench_strncmp_argp;
 extern struct argp bench_hashmap_lookup_argp;
 extern struct argp bench_local_storage_create_argp;
+extern struct argp bench_htab_mem_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
@@ -290,6 +291,7 @@ static const struct argp_child bench_parsers[] = {
 		"local_storage RCU Tasks Trace slowdown benchmark", 0 },
 	{ &bench_hashmap_lookup_argp, 0, "Hashmap lookup benchmark", 0 },
 	{ &bench_local_storage_create_argp, 0, "local-storage-create benchmark", 0 },
+	{ &bench_htab_mem_argp, 0, "hash map memory benchmark", 0 },
 	{},
 };
 
@@ -520,6 +522,7 @@ extern const struct bench bench_local_storage_cache_hashmap_control;
 extern const struct bench bench_local_storage_tasks_trace;
 extern const struct bench bench_bpf_hashmap_lookup;
 extern const struct bench bench_local_storage_create;
+extern const struct bench bench_htab_mem;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -561,6 +564,7 @@ static const struct bench *benchs[] = {
 	&bench_local_storage_tasks_trace,
 	&bench_bpf_hashmap_lookup,
 	&bench_local_storage_create,
+	&bench_htab_mem,
 };
 
 static void find_benchmark(void)
diff --git a/tools/testing/selftests/bpf/benchs/bench_htab_mem.c b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
new file mode 100644
index 000000000000..9146d3f414d2
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_htab_mem.c
@@ -0,0 +1,350 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <argp.h>
+#include <stdbool.h>
+#include <pthread.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/param.h>
+#include <fcntl.h>
+
+#include "bench.h"
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+#include "htab_mem_bench.skel.h"
+
+struct htab_mem_use_case {
+	const char *name;
+	const char **progs;
+	/* Do synchronization between addition thread and deletion thread */
+	bool need_sync;
+};
+
+static struct htab_mem_ctx {
+	const struct htab_mem_use_case *uc;
+	struct htab_mem_bench *skel;
+	pthread_barrier_t *notify;
+	int fd;
+} ctx;
+
+const char *ow_progs[] = {"overwrite", NULL};
+const char *batch_progs[] = {"batch_add_batch_del", NULL};
+const char *add_del_progs[] = {"add_only", "del_only", NULL};
+const static struct htab_mem_use_case use_cases[] = {
+	{ .name = "overwrite", .progs = ow_progs },
+	{ .name = "batch_add_batch_del", .progs = batch_progs },
+	{ .name = "add_del_on_diff_cpu", .progs = add_del_progs, .need_sync = true },
+};
+
+static struct htab_mem_args {
+	u32 value_size;
+	const char *use_case;
+	bool preallocated;
+} args = {
+	.value_size = 8,
+	.use_case = "overwrite",
+	.preallocated = false,
+};
+
+enum {
+	ARG_VALUE_SIZE = 10000,
+	ARG_USE_CASE = 10001,
+	ARG_PREALLOCATED = 10002,
+};
+
+static const struct argp_option opts[] = {
+	{ "value-size", ARG_VALUE_SIZE, "VALUE_SIZE", 0,
+	  "Set the value size of hash map (default 8)" },
+	{ "use-case", ARG_USE_CASE, "USE_CASE", 0,
+	  "Set the use case of hash map: overwrite|batch_add_batch_del|add_del_on_diff_cpu" },
+	{ "preallocated", ARG_PREALLOCATED, NULL, 0, "use preallocated hash map" },
+	{},
+};
+
+static error_t htab_mem_parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_VALUE_SIZE:
+		args.value_size = strtoul(arg, NULL, 10);
+		if (args.value_size > 4096) {
+			fprintf(stderr, "too big value size %u\n", args.value_size);
+			argp_usage(state);
+		}
+		break;
+	case ARG_USE_CASE:
+		args.use_case = strdup(arg);
+		if (!args.use_case) {
+			fprintf(stderr, "no mem for use-case\n");
+			argp_usage(state);
+		}
+		break;
+	case ARG_PREALLOCATED:
+		args.preallocated = true;
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+const struct argp bench_htab_mem_argp = {
+	.options = opts,
+	.parser = htab_mem_parse_arg,
+};
+
+static void htab_mem_validate(void)
+{
+	if (!strcmp(use_cases[2].name, args.use_case) && env.producer_cnt % 2) {
+		fprintf(stderr, "%s needs an even number of producers\n", args.use_case);
+		exit(1);
+	}
+}
+
+static int htab_mem_bench_init_barriers(void)
+{
+	pthread_barrier_t *barriers;
+	unsigned int i, nr;
+
+	if (!ctx.uc->need_sync)
+		return 0;
+
+	nr = (env.producer_cnt + 1) / 2;
+	barriers = calloc(nr, sizeof(*barriers));
+	if (!barriers)
+		return -1;
+
+	/* Used for synchronization between two threads */
+	for (i = 0; i < nr; i++)
+		pthread_barrier_init(&barriers[i], NULL, 2);
+
+	ctx.notify = barriers;
+	return 0;
+}
+
+static void htab_mem_bench_exit_barriers(void)
+{
+	unsigned int i, nr;
+
+	if (!ctx.notify)
+		return;
+
+	nr = (env.producer_cnt + 1) / 2;
+	for (i = 0; i < nr; i++)
+		pthread_barrier_destroy(&ctx.notify[i]);
+	free(ctx.notify);
+}
+
+static const struct htab_mem_use_case *htab_mem_find_use_case_or_exit(const char *name)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++) {
+		if (!strcmp(name, use_cases[i].name))
+			return &use_cases[i];
+	}
+
+	fprintf(stderr, "no such use-case: %s\n", name);
+	fprintf(stderr, "available use case:");
+	for (i = 0; i < ARRAY_SIZE(use_cases); i++)
+		fprintf(stderr, " %s", use_cases[i].name);
+	fprintf(stderr, "\n");
+	exit(1);
+}
+
+static void htab_mem_setup(void)
+{
+	struct bpf_map *map;
+	const char **names;
+	int err;
+
+	setup_libbpf();
+
+	ctx.uc = htab_mem_find_use_case_or_exit(args.use_case);
+	err = htab_mem_bench_init_barriers();
+	if (err) {
+		fprintf(stderr, "failed to init barrier\n");
+		exit(1);
+	}
+
+	ctx.fd = cgroup_setup_and_join("/htab_mem");
+	if (ctx.fd < 0)
+		goto cleanup;
+
+	ctx.skel = htab_mem_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		goto cleanup;
+	}
+
+	map = ctx.skel->maps.htab;
+	bpf_map__set_value_size(map, args.value_size);
+	/* Ensure that different CPUs can operate on different subset */
+	bpf_map__set_max_entries(map, MAX(8192, 64 * env.nr_cpus));
+	if (args.preallocated)
+		bpf_map__set_map_flags(map, bpf_map__map_flags(map) & ~BPF_F_NO_PREALLOC);
+
+	names = ctx.uc->progs;
+	while (*names) {
+		struct bpf_program *prog;
+
+		prog = bpf_object__find_program_by_name(ctx.skel->obj, *names);
+		if (!prog) {
+			fprintf(stderr, "no such program %s\n", *names);
+			goto cleanup;
+		}
+		bpf_program__set_autoload(prog, true);
+		names++;
+	}
+	ctx.skel->bss->nr_thread = env.producer_cnt;
+
+	err = htab_mem_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		goto cleanup;
+	}
+	err = htab_mem_bench__attach(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to attach skeleton\n");
+		goto cleanup;
+	}
+	return;
+
+cleanup:
+	htab_mem_bench__destroy(ctx.skel);
+	htab_mem_bench_exit_barriers();
+	if (ctx.fd >= 0) {
+		close(ctx.fd);
+		cleanup_cgroup_environment();
+	}
+	exit(1);
+}
+
+static void htab_mem_add_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Do addition */
+		(void)syscall(__NR_getpgid, 0);
+		/* Notify deletion thread to do deletion */
+		pthread_barrier_wait(notify);
+		/* Wait for deletion to complete */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void htab_mem_delete_fn(pthread_barrier_t *notify)
+{
+	while (true) {
+		/* Wait for addition to complete */
+		pthread_barrier_wait(notify);
+		/* Do deletion */
+		(void)syscall(__NR_getppid);
+		/* Notify addition thread to do addition */
+		pthread_barrier_wait(notify);
+	}
+}
+
+static void *htab_mem_producer(void *arg)
+{
+	pthread_barrier_t *notify;
+	int seq;
+
+	if (!ctx.uc->need_sync) {
+		while (true)
+			(void)syscall(__NR_getpgid, 0);
+		return NULL;
+	}
+
+	seq = (long)arg;
+	notify = &ctx.notify[seq / 2];
+	if (seq & 1)
+		htab_mem_delete_fn(notify);
+	else
+		htab_mem_add_fn(notify);
+	return NULL;
+}
+
+static void htab_mem_read_mem_cgrp_file(const char *name, unsigned long *value)
+{
+	char buf[32];
+	ssize_t got;
+	int fd;
+
+	fd = openat(ctx.fd, name, O_RDONLY);
+	if (fd < 0) {
+		/* cgroup v1 ? */
+		fprintf(stderr, "no %s\n", name);
+		*value = 0;
+		return;
+	}
+
+	got = read(fd, buf, sizeof(buf) - 1);
+	if (got <= 0) {
+		*value = 0;
+		return;
+	}
+	buf[got] = 0;
+
+	*value = strtoull(buf, NULL, 0);
+
+	close(fd);
+}
+
+static void htab_mem_measure(struct bench_res *res)
+{
+	res->hits = atomic_swap(&ctx.skel->bss->op_cnt, 0) / env.producer_cnt;
+	htab_mem_read_mem_cgrp_file("memory.current", &res->gp_ct);
+}
+
+static void htab_mem_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	double loop, mem;
+
+	loop = res->hits / 1000.0 / (delta_ns / 1000000000.0);
+	mem = res->gp_ct / 1048576.0;
+	printf("Iter %3d (%7.3lfus): ", iter, (delta_ns - 1000000000) / 1000.0);
+	printf("per-prod-op %7.2lfk/s, memory usage %7.2lfMiB\n", loop, mem);
+}
+
+static void htab_mem_report_final(struct bench_res res[], int res_cnt)
+{
+	double mem_mean = 0.0, mem_stddev = 0.0;
+	double loop_mean = 0.0, loop_stddev = 0.0;
+	unsigned long peak_mem;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		loop_mean += res[i].hits / 1000.0 / (0.0 + res_cnt);
+		mem_mean += res[i].gp_ct / 1048576.0 / (0.0 + res_cnt);
+	}
+	if (res_cnt > 1)  {
+		for (i = 0; i < res_cnt; i++) {
+			loop_stddev += (loop_mean - res[i].hits / 1000.0) *
+				       (loop_mean - res[i].hits / 1000.0) /
+				       (res_cnt - 1.0);
+			mem_stddev += (mem_mean - res[i].gp_ct / 1048576.0) *
+				      (mem_mean - res[i].gp_ct / 1048576.0) /
+				      (res_cnt - 1.0);
+		}
+		loop_stddev = sqrt(loop_stddev);
+		mem_stddev = sqrt(mem_stddev);
+	}
+
+	htab_mem_read_mem_cgrp_file("memory.peak", &peak_mem);
+	printf("Summary: per-prod-op %7.2lf \u00B1 %7.2lfk/s, memory usage %7.2lf \u00B1 %7.2lfMiB,"
+	       " peak memory usage %7.2lfMiB\n",
+	       loop_mean, loop_stddev, mem_mean, mem_stddev, peak_mem / 1048576.0);
+
+	cleanup_cgroup_environment();
+}
+
+const struct bench bench_htab_mem = {
+	.name = "htab-mem",
+	.argp = &bench_htab_mem_argp,
+	.validate = htab_mem_validate,
+	.setup = htab_mem_setup,
+	.producer_thread = htab_mem_producer,
+	.measure = htab_mem_measure,
+	.report_progress = htab_mem_report_progress,
+	.report_final = htab_mem_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
index 3ca14ad36607..e1ee979e6acc 100644
--- a/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
+++ b/tools/testing/selftests/bpf/benchs/bench_ringbufs.c
@@ -399,7 +399,7 @@ static void perfbuf_libbpf_setup(void)
 	ctx->skel = perfbuf_setup_skeleton();
 
 	memset(&attr, 0, sizeof(attr));
-	attr.config = PERF_COUNT_SW_BPF_OUTPUT,
+	attr.config = PERF_COUNT_SW_BPF_OUTPUT;
 	attr.type = PERF_TYPE_SOFTWARE;
 	attr.sample_type = PERF_SAMPLE_RAW;
 	/* notify only every Nth sample */
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
new file mode 100755
index 000000000000..9ff5832463a2
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_htab_mem.sh
@@ -0,0 +1,40 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+htab_mem()
+{
+	echo -n "per-prod-op: "
+	echo -n "$*" | sed -E "s/.* per-prod-op\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+k\/s).*/\1/"
+	echo -n -e ", avg mem: "
+	echo -n "$*" | sed -E "s/.* memory usage\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+MiB).*/\1/"
+	echo -n ", peak mem: "
+	echo "$*" | sed -E "s/.* peak memory usage\s+([0-9]+\.[0-9]+MiB).*/\1/"
+}
+
+summarize_htab_mem()
+{
+	local bench="$1"
+	local summary=$(echo $2 | tail -n1)
+
+	printf "%-20s %s\n" "$bench" "$(htab_mem $summary)"
+}
+
+htab_mem_bench()
+{
+	local name
+
+	for name in overwrite batch_add_batch_del add_del_on_diff_cpu
+	do
+		summarize_htab_mem "$name" "$($RUN_BENCH htab-mem --use-case $name -p8 "$@")"
+	done
+}
+
+header "preallocated"
+htab_mem_bench "--preallocated"
+
+header "normal bpf ma"
+htab_mem_bench
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index aaf6ef1201c7..a6f991b56345 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -34,6 +34,11 @@ struct bpf_testmod_struct_arg_3 {
 	int b[];
 };
 
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
 __diag_push();
 __diag_ignore_all("-Wmissing-prototypes",
 		  "Global functions as their definitions will be in bpf_testmod.ko BTF");
@@ -75,6 +80,24 @@ bpf_testmod_test_struct_arg_6(struct bpf_testmod_struct_arg_3 *a) {
 	return bpf_testmod_test_struct_arg_result;
 }
 
+noinline int
+bpf_testmod_test_struct_arg_7(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b;
+	return bpf_testmod_test_struct_arg_result;
+}
+
+noinline int
+bpf_testmod_test_struct_arg_8(u64 a, void *b, short c, int d, void *e,
+			      struct bpf_testmod_struct_arg_4 f, int g)
+{
+	bpf_testmod_test_struct_arg_result = a + (long)b + c + d +
+		(long)e + f.a + f.b + g;
+	return bpf_testmod_test_struct_arg_result;
+}
+
 __bpf_kfunc void
 bpf_testmod_test_mod_kfunc(int i)
 {
@@ -191,6 +214,20 @@ noinline int bpf_testmod_fentry_test3(char a, int b, u64 c)
 	return a + b + c;
 }
 
+noinline int bpf_testmod_fentry_test7(u64 a, void *b, short c, int d,
+				      void *e, char f, int g)
+{
+	return a + (long)b + c + d + (long)e + f + g;
+}
+
+noinline int bpf_testmod_fentry_test11(u64 a, void *b, short c, int d,
+				       void *e, char f, int g,
+				       unsigned int h, long i, __u64 j,
+				       unsigned long k)
+{
+	return a + (long)b + c + d + (long)e + f + g + h + i + j + k;
+}
+
 int bpf_testmod_fentry_ok;
 
 noinline ssize_t
@@ -206,6 +243,7 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	struct bpf_testmod_struct_arg_1 struct_arg1 = {10};
 	struct bpf_testmod_struct_arg_2 struct_arg2 = {2, 3};
 	struct bpf_testmod_struct_arg_3 *struct_arg3;
+	struct bpf_testmod_struct_arg_4 struct_arg4 = {21, 22};
 	int i = 1;
 
 	while (bpf_testmod_return_ptr(i))
@@ -216,6 +254,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	(void)bpf_testmod_test_struct_arg_3(1, 4, struct_arg2);
 	(void)bpf_testmod_test_struct_arg_4(struct_arg1, 1, 2, 3, struct_arg2);
 	(void)bpf_testmod_test_struct_arg_5();
+	(void)bpf_testmod_test_struct_arg_7(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4);
+	(void)bpf_testmod_test_struct_arg_8(16, (void *)17, 18, 19,
+					    (void *)20, struct_arg4, 23);
+
 
 	struct_arg3 = kmalloc((sizeof(struct bpf_testmod_struct_arg_3) +
 				sizeof(int)), GFP_KERNEL);
@@ -243,7 +286,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 
 	if (bpf_testmod_fentry_test1(1) != 2 ||
 	    bpf_testmod_fentry_test2(2, 3) != 5 ||
-	    bpf_testmod_fentry_test3(4, 5, 6) != 15)
+	    bpf_testmod_fentry_test3(4, 5, 6) != 15 ||
+	    bpf_testmod_fentry_test7(16, (void *)17, 18, 19, (void *)20,
+			21, 22) != 133 ||
+	    bpf_testmod_fentry_test11(16, (void *)17, 18, 19, (void *)20,
+			21, 22, 23, 24, 25, 26) != 231)
 		goto out;
 
 	bpf_testmod_fentry_ok = 1;
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 9e95b37a7dff..2caee8423ee0 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -278,6 +278,18 @@ int join_cgroup(const char *relative_path)
 }
 
 /**
+ * join_root_cgroup() - Join the root cgroup
+ *
+ * This function joins the root cgroup.
+ *
+ * On success, it returns 0, otherwise on failure it returns 1.
+ */
+int join_root_cgroup(void)
+{
+	return join_cgroup_from_top(CGROUP_MOUNT_PATH);
+}
+
+/**
  * join_parent_cgroup() - Join a cgroup in the parent process workdir
  * @relative_path: The cgroup path, relative to parent process workdir, to join
  *
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index f099a166c94d..5c2cb9c8b546 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -22,6 +22,7 @@ void remove_cgroup(const char *relative_path);
 unsigned long long get_cgroup_id(const char *relative_path);
 
 int join_cgroup(const char *relative_path);
+int join_root_cgroup(void);
 int join_parent_cgroup(const char *relative_path);
 
 int setup_cgroup_environment(void);
diff --git a/tools/testing/selftests/bpf/cgroup_tcp_skb.h b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
new file mode 100644
index 000000000000..7f6b24f102fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/cgroup_tcp_skb.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+
+/* Define states of a socket to tracking messages sending to and from the
+ * socket.
+ *
+ * These states are based on rfc9293 with some modifications to support
+ * tracking of messages sent out from a socket. For example, when a SYN is
+ * received, a new socket is transiting to the SYN_RECV state defined in
+ * rfc9293. But, we put it in SYN_RECV_SENDING_SYN_ACK state and when
+ * SYN-ACK is sent out, it moves to SYN_RECV state. With this modification,
+ * we can track the message sent out from a socket.
+ */
+
+#ifndef __CGROUP_TCP_SKB_H__
+#define __CGROUP_TCP_SKB_H__
+
+enum {
+	INIT,
+	CLOSED,
+	SYN_SENT,
+	SYN_RECV_SENDING_SYN_ACK,
+	SYN_RECV,
+	ESTABLISHED,
+	FIN_WAIT1,
+	FIN_WAIT2,
+	CLOSE_WAIT_SENDING_ACK,
+	CLOSE_WAIT,
+	CLOSING,
+	LAST_ACK,
+	TIME_WAIT_SENDING_ACK,
+	TIME_WAIT,
+};
+
+#endif /* __CGROUP_TCP_SKB_H__ */
diff --git a/tools/testing/selftests/bpf/gnu/stubs.h b/tools/testing/selftests/bpf/gnu/stubs.h
index 719225b16626..1c638d9dce1a 100644
--- a/tools/testing/selftests/bpf/gnu/stubs.h
+++ b/tools/testing/selftests/bpf/gnu/stubs.h
@@ -1 +1 @@
-/* dummy .h to trick /usr/include/features.h to work with 'clang -target bpf' */
+/* dummy .h to trick /usr/include/features.h to work with 'clang --target=bpf' */
diff --git a/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
new file mode 100644
index 000000000000..1a9eeefda9a8
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/map_percpu_stats.c
@@ -0,0 +1,447 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include <errno.h>
+#include <unistd.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <bpf_util.h>
+#include <test_maps.h>
+
+#include "map_percpu_stats.skel.h"
+
+#define MAX_ENTRIES			16384
+#define MAX_ENTRIES_HASH_OF_MAPS	64
+#define N_THREADS			8
+#define MAX_MAP_KEY_SIZE		4
+
+static void map_info(int map_fd, struct bpf_map_info *info)
+{
+	__u32 len = sizeof(*info);
+	int ret;
+
+	memset(info, 0, sizeof(*info));
+
+	ret = bpf_obj_get_info_by_fd(map_fd, info, &len);
+	CHECK(ret < 0, "bpf_obj_get_info_by_fd", "error: %s\n", strerror(errno));
+}
+
+static const char *map_type_to_s(__u32 type)
+{
+	switch (type) {
+	case BPF_MAP_TYPE_HASH:
+		return "HASH";
+	case BPF_MAP_TYPE_PERCPU_HASH:
+		return "PERCPU_HASH";
+	case BPF_MAP_TYPE_LRU_HASH:
+		return "LRU_HASH";
+	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
+		return "LRU_PERCPU_HASH";
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+		return "BPF_MAP_TYPE_HASH_OF_MAPS";
+	default:
+		return "<define-me>";
+	}
+}
+
+static __u32 map_count_elements(__u32 type, int map_fd)
+{
+	__u32 key = -1;
+	int n = 0;
+
+	while (!bpf_map_get_next_key(map_fd, &key, &key))
+		n++;
+	return n;
+}
+
+#define BATCH	true
+
+static void delete_and_lookup_batch(int map_fd, void *keys, __u32 count)
+{
+	static __u8 values[(8 << 10) * MAX_ENTRIES];
+	void *in_batch = NULL, *out_batch;
+	__u32 save_count = count;
+	int ret;
+
+	ret = bpf_map_lookup_and_delete_batch(map_fd,
+					      &in_batch, &out_batch,
+					      keys, values, &count,
+					      NULL);
+
+	/*
+	 * Despite what uapi header says, lookup_and_delete_batch will return
+	 * -ENOENT in case we successfully have deleted all elements, so check
+	 * this separately
+	 */
+	CHECK(ret < 0 && (errno != ENOENT || !count), "bpf_map_lookup_and_delete_batch",
+		       "error: %s\n", strerror(errno));
+
+	CHECK(count != save_count,
+			"bpf_map_lookup_and_delete_batch",
+			"deleted not all elements: removed=%u expected=%u\n",
+			count, save_count);
+}
+
+static void delete_all_elements(__u32 type, int map_fd, bool batch)
+{
+	static __u8 val[8 << 10]; /* enough for 1024 CPUs */
+	__u32 key = -1;
+	void *keys;
+	__u32 i, n;
+	int ret;
+
+	keys = calloc(MAX_MAP_KEY_SIZE, MAX_ENTRIES);
+	CHECK(!keys, "calloc", "error: %s\n", strerror(errno));
+
+	for (n = 0; !bpf_map_get_next_key(map_fd, &key, &key); n++)
+		memcpy(keys + n*MAX_MAP_KEY_SIZE, &key, MAX_MAP_KEY_SIZE);
+
+	if (batch) {
+		/* Can't mix delete_batch and delete_and_lookup_batch because
+		 * they have different semantics in relation to the keys
+		 * argument. However, delete_batch utilize map_delete_elem,
+		 * so we actually test it in non-batch scenario */
+		delete_and_lookup_batch(map_fd, keys, n);
+	} else {
+		/* Intentionally mix delete and lookup_and_delete so we can test both */
+		for (i = 0; i < n; i++) {
+			void *keyp = keys + i*MAX_MAP_KEY_SIZE;
+
+			if (i % 2 || type == BPF_MAP_TYPE_HASH_OF_MAPS) {
+				ret = bpf_map_delete_elem(map_fd, keyp);
+				CHECK(ret < 0, "bpf_map_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			} else {
+				ret = bpf_map_lookup_and_delete_elem(map_fd, keyp, val);
+				CHECK(ret < 0, "bpf_map_lookup_and_delete_elem",
+					       "error: key %u: %s\n", i, strerror(errno));
+			}
+		}
+	}
+
+	free(keys);
+}
+
+static bool is_lru(__u32 map_type)
+{
+	return map_type == BPF_MAP_TYPE_LRU_HASH ||
+	       map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
+}
+
+struct upsert_opts {
+	__u32 map_type;
+	int map_fd;
+	__u32 n;
+};
+
+static int create_small_hash(void)
+{
+	int map_fd;
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_HASH, "small", 4, 4, 4, NULL);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), "small");
+
+	return map_fd;
+}
+
+static void *patch_map_thread(void *arg)
+{
+	struct upsert_opts *opts = arg;
+	int val;
+	int ret;
+	int i;
+
+	for (i = 0; i < opts->n; i++) {
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+			val = create_small_hash();
+		else
+			val = rand();
+		ret = bpf_map_update_elem(opts->map_fd, &i, &val, 0);
+		CHECK(ret < 0, "bpf_map_update_elem", "key=%d error: %s\n", i, strerror(errno));
+
+		if (opts->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
+			close(val);
+	}
+	return NULL;
+}
+
+static void upsert_elements(struct upsert_opts *opts)
+{
+	pthread_t threads[N_THREADS];
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_create(&i[threads], NULL, patch_map_thread, opts);
+		CHECK(ret != 0, "pthread_create", "error: %s\n", strerror(ret));
+	}
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++) {
+		ret = pthread_join(i[threads], NULL);
+		CHECK(ret != 0, "pthread_join", "error: %s\n", strerror(ret));
+	}
+}
+
+static __u32 read_cur_elements(int iter_fd)
+{
+	char buf[64];
+	ssize_t n;
+	__u32 ret;
+
+	n = read(iter_fd, buf, sizeof(buf)-1);
+	CHECK(n <= 0, "read", "error: %s\n", strerror(errno));
+	buf[n] = '\0';
+
+	errno = 0;
+	ret = (__u32)strtol(buf, NULL, 10);
+	CHECK(errno != 0, "strtol", "error: %s\n", strerror(errno));
+
+	return ret;
+}
+
+static __u32 get_cur_elements(int map_id)
+{
+	struct map_percpu_stats *skel;
+	struct bpf_link *link;
+	__u32 n_elements;
+	int iter_fd;
+	int ret;
+
+	skel = map_percpu_stats__open();
+	CHECK(skel == NULL, "map_percpu_stats__open", "error: %s", strerror(errno));
+
+	skel->bss->target_id = map_id;
+
+	ret = map_percpu_stats__load(skel);
+	CHECK(ret != 0, "map_percpu_stats__load", "error: %s", strerror(errno));
+
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_map, NULL);
+	CHECK(!link, "bpf_program__attach_iter", "error: %s\n", strerror(errno));
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	CHECK(iter_fd < 0, "bpf_iter_create", "error: %s\n", strerror(errno));
+
+	n_elements = read_cur_elements(iter_fd);
+
+	close(iter_fd);
+	bpf_link__destroy(link);
+	map_percpu_stats__destroy(skel);
+
+	return n_elements;
+}
+
+static void check_expected_number_elements(__u32 n_inserted, int map_fd,
+					   struct bpf_map_info *info)
+{
+	__u32 n_real;
+	__u32 n_iter;
+
+	/* Count the current number of elements in the map by iterating through
+	 * all the map keys via bpf_get_next_key
+	 */
+	n_real = map_count_elements(info->type, map_fd);
+
+	/* The "real" number of elements should be the same as the inserted
+	 * number of elements in all cases except LRU maps, where some elements
+	 * may have been evicted
+	 */
+	if (n_inserted == 0 || !is_lru(info->type))
+		CHECK(n_inserted != n_real, "map_count_elements",
+		      "n_real(%u) != n_inserted(%u)\n", n_real, n_inserted);
+
+	/* Count the current number of elements in the map using an iterator */
+	n_iter = get_cur_elements(info->id);
+
+	/* Both counts should be the same, as all updates are over */
+	CHECK(n_iter != n_real, "get_cur_elements",
+	      "n_iter=%u, expected %u (map_type=%s,map_flags=%08x)\n",
+	      n_iter, n_real, map_type_to_s(info->type), info->map_flags);
+}
+
+static void __test(int map_fd)
+{
+	struct upsert_opts opts = {
+		.map_fd = map_fd,
+	};
+	struct bpf_map_info info;
+
+	map_info(map_fd, &info);
+	opts.map_type = info.type;
+	opts.n = info.max_entries;
+
+	/* Reduce the number of elements we are updating such that we don't
+	 * bump into -E2BIG from non-preallocated hash maps, but still will
+	 * have some evictions for LRU maps  */
+	if (opts.map_type != BPF_MAP_TYPE_HASH_OF_MAPS)
+		opts.n -= 512;
+	else
+		opts.n /= 2;
+
+	/*
+	 * Upsert keys [0, n) under some competition: with random values from
+	 * N_THREADS threads. Check values, then delete all elements and check
+	 * values again.
+	 */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, !BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	/* Now do the same, but using batch delete operations */
+	upsert_elements(&opts);
+	check_expected_number_elements(opts.n, map_fd, &info);
+	delete_all_elements(info.type, map_fd, BATCH);
+	check_expected_number_elements(0, map_fd, &info);
+
+	close(map_fd);
+}
+
+static int map_create_opts(__u32 type, const char *name,
+			   struct bpf_map_create_opts *map_opts,
+			   __u32 key_size, __u32 val_size)
+{
+	int max_entries;
+	int map_fd;
+
+	if (type == BPF_MAP_TYPE_HASH_OF_MAPS)
+		max_entries = MAX_ENTRIES_HASH_OF_MAPS;
+	else
+		max_entries = MAX_ENTRIES;
+
+	map_fd = bpf_map_create(type, name, key_size, val_size, max_entries, map_opts);
+	CHECK(map_fd < 0, "bpf_map_create()", "error:%s (name=%s)\n",
+			strerror(errno), name);
+
+	return map_fd;
+}
+
+static int map_create(__u32 type, const char *name, struct bpf_map_create_opts *map_opts)
+{
+	return map_create_opts(type, name, map_opts, sizeof(int), sizeof(int));
+}
+
+static int create_hash(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+
+	return map_create(BPF_MAP_TYPE_HASH, "hash", &map_opts);
+}
+
+static int create_percpu_hash(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+	};
+
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash", &map_opts);
+}
+
+static int create_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_HASH, "hash", NULL);
+}
+
+static int create_percpu_hash_prealloc(void)
+{
+	return map_create(BPF_MAP_TYPE_PERCPU_HASH, "percpu_hash_prealloc", NULL);
+}
+
+static int create_lru_hash(__u32 type, __u32 map_flags)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = map_flags,
+	};
+
+	return map_create(type, "lru_hash", &map_opts);
+}
+
+static int create_hash_of_maps(void)
+{
+	struct bpf_map_create_opts map_opts = {
+		.sz = sizeof(map_opts),
+		.map_flags = BPF_F_NO_PREALLOC,
+		.inner_map_fd = create_small_hash(),
+	};
+	int ret;
+
+	ret = map_create_opts(BPF_MAP_TYPE_HASH_OF_MAPS, "hash_of_maps",
+			      &map_opts, sizeof(int), sizeof(int));
+	close(map_opts.inner_map_fd);
+	return ret;
+}
+
+static void map_percpu_stats_hash(void)
+{
+	__test(create_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash(void)
+{
+	__test(create_percpu_hash());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_prealloc(void)
+{
+	__test(create_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_hash_prealloc(void)
+{
+	__test(create_percpu_hash_prealloc());
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, 0));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_percpu_lru_hash_no_common(void)
+{
+	__test(create_lru_hash(BPF_MAP_TYPE_LRU_PERCPU_HASH, BPF_F_NO_COMMON_LRU));
+	printf("test_%s:PASS\n", __func__);
+}
+
+static void map_percpu_stats_hash_of_maps(void)
+{
+	__test(create_hash_of_maps());
+	printf("test_%s:PASS\n", __func__);
+}
+
+void test_map_percpu_stats(void)
+{
+	map_percpu_stats_hash();
+	map_percpu_stats_percpu_hash();
+	map_percpu_stats_hash_prealloc();
+	map_percpu_stats_percpu_hash_prealloc();
+	map_percpu_stats_lru_hash();
+	map_percpu_stats_lru_hash_no_common();
+	map_percpu_stats_percpu_lru_hash();
+	map_percpu_stats_percpu_lru_hash_no_common();
+	map_percpu_stats_hash_of_maps();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
index c8ba4009e4ab..b30ff6b3b81a 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_nf.c
@@ -123,12 +123,13 @@ static void test_bpf_nf_ct(int mode)
 	ASSERT_EQ(skel->data->test_snat_addr, 0, "Test for source natting");
 	ASSERT_EQ(skel->data->test_dnat_addr, 0, "Test for destination natting");
 end:
-	if (srv_client_fd != -1)
-		close(srv_client_fd);
 	if (client_fd != -1)
 		close(client_fd);
+	if (srv_client_fd != -1)
+		close(srv_client_fd);
 	if (srv_fd != -1)
 		close(srv_fd);
+
 	snprintf(cmd, sizeof(cmd), iptables, "-D");
 	system(cmd);
 	test_bpf_nf__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
new file mode 100644
index 000000000000..95bab61a1e57
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_tcp_skb.c
@@ -0,0 +1,402 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Facebook */
+#include <test_progs.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <sched.h>
+#include <unistd.h>
+#include "cgroup_helpers.h"
+#include "testing_helpers.h"
+#include "cgroup_tcp_skb.skel.h"
+#include "cgroup_tcp_skb.h"
+
+#define CGROUP_TCP_SKB_PATH "/test_cgroup_tcp_skb"
+
+static int install_filters(int cgroup_fd,
+			   struct bpf_link **egress_link,
+			   struct bpf_link **ingress_link,
+			   struct bpf_program *egress_prog,
+			   struct bpf_program *ingress_prog,
+			   struct cgroup_tcp_skb *skel)
+{
+	/* Prepare filters */
+	skel->bss->g_sock_state = 0;
+	skel->bss->g_unexpected = 0;
+	*egress_link =
+		bpf_program__attach_cgroup(egress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(egress_link, "egress_link"))
+		return -1;
+	*ingress_link =
+		bpf_program__attach_cgroup(ingress_prog,
+					   cgroup_fd);
+	if (!ASSERT_OK_PTR(ingress_link, "ingress_link"))
+		return -1;
+
+	return 0;
+}
+
+static void uninstall_filters(struct bpf_link **egress_link,
+			      struct bpf_link **ingress_link)
+{
+	bpf_link__destroy(*egress_link);
+	*egress_link = NULL;
+	bpf_link__destroy(*ingress_link);
+	*ingress_link = NULL;
+}
+
+static int create_client_sock_v6(void)
+{
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	return fd;
+}
+
+static int create_server_sock_v6(void)
+{
+	struct sockaddr_in6 addr = {
+		.sin6_family = AF_INET6,
+		.sin6_port = htons(0),
+		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
+	};
+	int fd, err;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd < 0) {
+		perror("socket");
+		return -1;
+	}
+
+	err = bind(fd, (struct sockaddr *)&addr, sizeof(addr));
+	if (err < 0) {
+		perror("bind");
+		return -1;
+	}
+
+	err = listen(fd, 1);
+	if (err < 0) {
+		perror("listen");
+		return -1;
+	}
+
+	return fd;
+}
+
+static int get_sock_port_v6(int fd)
+{
+	struct sockaddr_in6 addr;
+	socklen_t len;
+	int err;
+
+	len = sizeof(addr);
+	err = getsockname(fd, (struct sockaddr *)&addr, &len);
+	if (err < 0) {
+		perror("getsockname");
+		return -1;
+	}
+
+	return ntohs(addr.sin6_port);
+}
+
+static int connect_client_server_v6(int client_fd, int listen_fd)
+{
+	struct sockaddr_in6 addr = {
+		.sin6_family = AF_INET6,
+		.sin6_addr = IN6ADDR_LOOPBACK_INIT,
+	};
+	int err;
+
+	addr.sin6_port = htons(get_sock_port_v6(listen_fd));
+	if (addr.sin6_port < 0)
+		return -1;
+
+	err = connect(client_fd, (struct sockaddr *)&addr, sizeof(addr));
+	if (err < 0) {
+		perror("connect");
+		return -1;
+	}
+
+	return 0;
+}
+
+/* Connect to the server in a cgroup from the outside of the cgroup. */
+static int talk_to_cgroup(int *client_fd, int *listen_fd, int *service_fd,
+			  struct cgroup_tcp_skb *skel)
+{
+	int err, cp;
+	char buf[5];
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*listen_fd = create_server_sock_v6();
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+
+	/* Connect client to server */
+	err = connect_client_server_v6(*client_fd, *listen_fd);
+	if (!ASSERT_OK(err, "connect_client_server_v6"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+/* Connect to the server out of a cgroup from inside the cgroup. */
+static int talk_to_outside(int *client_fd, int *listen_fd, int *service_fd,
+			   struct cgroup_tcp_skb *skel)
+
+{
+	int err, cp;
+	char buf[5];
+
+	/* Create client & server socket */
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	*listen_fd = create_server_sock_v6();
+	if (!ASSERT_GE(*listen_fd, 0, "listen_fd"))
+		return -1;
+	err = join_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_OK(err, "join_cgroup"))
+		return -1;
+	*client_fd = create_client_sock_v6();
+	if (!ASSERT_GE(*client_fd, 0, "client_fd"))
+		return -1;
+	err = join_root_cgroup();
+	if (!ASSERT_OK(err, "join_root_cgroup"))
+		return -1;
+	skel->bss->g_sock_port = get_sock_port_v6(*listen_fd);
+
+	/* Connect client to server */
+	err = connect_client_server_v6(*client_fd, *listen_fd);
+	if (!ASSERT_OK(err, "connect_client_server_v6"))
+		return -1;
+	*service_fd = accept(*listen_fd, NULL, NULL);
+	if (!ASSERT_GE(*service_fd, 0, "service_fd"))
+		return -1;
+	cp = write(*client_fd, "hello", 5);
+	if (!ASSERT_EQ(cp, 5, "write"))
+		return -1;
+	cp = read(*service_fd, buf, 5);
+	if (!ASSERT_EQ(cp, 5, "read"))
+		return -1;
+
+	return 0;
+}
+
+static int close_connection(int *closing_fd, int *peer_fd, int *listen_fd,
+			    struct cgroup_tcp_skb *skel)
+{
+	__u32 saved_packet_count = 0;
+	int err;
+	int i;
+
+	/* Wait for ACKs to be sent */
+	saved_packet_count = skel->bss->g_packet_count;
+	usleep(100000);		/* 0.1s */
+	for (i = 0;
+	     skel->bss->g_packet_count != saved_packet_count && i < 10;
+	     i++) {
+		saved_packet_count = skel->bss->g_packet_count;
+		usleep(100000);	/* 0.1s */
+	}
+	if (!ASSERT_EQ(skel->bss->g_packet_count, saved_packet_count,
+		       "packet_count"))
+		return -1;
+
+	skel->bss->g_packet_count = 0;
+	saved_packet_count = 0;
+
+	/* Half shutdown to make sure the closing socket having a chance to
+	 * receive a FIN from the peer.
+	 */
+	err = shutdown(*closing_fd, SHUT_WR);
+	if (!ASSERT_OK(err, "shutdown closing_fd"))
+		return -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	saved_packet_count = skel->bss->g_packet_count;
+
+	/* Fully shutdown the connection */
+	err = close(*peer_fd);
+	if (!ASSERT_OK(err, "close peer_fd"))
+		return -1;
+	*peer_fd = -1;
+
+	/* Wait for FIN and the ACK of the FIN to be observed */
+	for (i = 0;
+	     skel->bss->g_packet_count < saved_packet_count + 2 && i < 10;
+	     i++)
+		usleep(100000);	/* 0.1s */
+	if (!ASSERT_GE(skel->bss->g_packet_count, saved_packet_count + 2,
+		       "packet_count"))
+		return -1;
+
+	err = close(*closing_fd);
+	if (!ASSERT_OK(err, "close closing_fd"))
+		return -1;
+	*closing_fd = -1;
+
+	close(*listen_fd);
+	*listen_fd = -1;
+
+	return 0;
+}
+
+/* This test case includes four scenarios:
+ * 1. Connect to the server from outside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 2. Connect to the server from outside the cgroup and close the connection
+ *    from inside the cgroup.
+ * 3. Connect to the server from inside the cgroup and close the connection
+ *    from outside the cgroup.
+ * 4. Connect to the server from inside the cgroup and close the connection
+ *    from inside the cgroup.
+ *
+ * The test case is to verify that cgroup_skb/{egress,ingress} filters
+ * receive expected packets including SYN, SYN/ACK, ACK, FIN, and FIN/ACK.
+ */
+void test_cgroup_tcp_skb(void)
+{
+	struct bpf_link *ingress_link = NULL;
+	struct bpf_link *egress_link = NULL;
+	int client_fd = -1, listen_fd = -1;
+	struct cgroup_tcp_skb *skel;
+	int service_fd = -1;
+	int cgroup_fd = -1;
+	int err;
+
+	skel = cgroup_tcp_skb__open_and_load();
+	if (!ASSERT_OK(!skel, "skel_open_load"))
+		return;
+
+	err = setup_cgroup_environment();
+	if (!ASSERT_OK(err, "setup_cgroup_environment"))
+		goto cleanup;
+
+	cgroup_fd = create_and_get_cgroup(CGROUP_TCP_SKB_PATH);
+	if (!ASSERT_GE(cgroup_fd, 0, "cgroup_fd"))
+		goto cleanup;
+
+	/* Scenario 1 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress,
+			      skel->progs.server_ingress,
+			      skel);
+	if (!ASSERT_OK(err, "install_filters"))
+		goto cleanup;
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 2 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.server_egress_srv,
+			      skel->progs.server_ingress_srv,
+			      skel);
+
+	err = talk_to_cgroup(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_cgroup"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 3 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress_srv,
+			      skel->progs.client_ingress_srv,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&service_fd, &client_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, CLOSED, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+	/* Scenario 4 */
+	err = install_filters(cgroup_fd, &egress_link, &ingress_link,
+			      skel->progs.client_egress,
+			      skel->progs.client_ingress,
+			      skel);
+
+	err = talk_to_outside(&client_fd, &listen_fd, &service_fd, skel);
+	if (!ASSERT_OK(err, "talk_to_outside"))
+		goto cleanup;
+
+	err = close_connection(&client_fd, &service_fd, &listen_fd, skel);
+	if (!ASSERT_OK(err, "close_connection"))
+		goto cleanup;
+
+	ASSERT_EQ(skel->bss->g_unexpected, 0, "g_unexpected");
+	ASSERT_EQ(skel->bss->g_sock_state, TIME_WAIT, "g_sock_state");
+
+	uninstall_filters(&egress_link, &ingress_link);
+
+cleanup:
+	close(client_fd);
+	close(listen_fd);
+	close(service_fd);
+	close(cgroup_fd);
+	bpf_link__destroy(egress_link);
+	bpf_link__destroy(ingress_link);
+	cleanup_cgroup_environment();
+	cgroup_tcp_skb__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index c0d1d61d5f66..aee1bc77a17f 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fentry_test.lskel.h"
+#include "fentry_many_args.skel.h"
 
-static int fentry_test(struct fentry_test_lskel *fentry_skel)
+static int fentry_test_common(struct fentry_test_lskel *fentry_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,7 +38,7 @@ static int fentry_test(struct fentry_test_lskel *fentry_skel)
 	return 0;
 }
 
-void test_fentry_test(void)
+static void fentry_test(void)
 {
 	struct fentry_test_lskel *fentry_skel = NULL;
 	int err;
@@ -46,13 +47,47 @@ void test_fentry_test(void)
 	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_first_attach"))
 		goto cleanup;
 
-	err = fentry_test(fentry_skel);
+	err = fentry_test_common(fentry_skel);
 	ASSERT_OK(err, "fentry_second_attach");
 
 cleanup:
 	fentry_test_lskel__destroy(fentry_skel);
 }
+
+static void fentry_many_args(void)
+{
+	struct fentry_many_args *fentry_skel = NULL;
+	int err;
+
+	fentry_skel = fentry_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fentry_skel, "fentry_many_args_skel_load"))
+		goto cleanup;
+
+	err = fentry_many_args__attach(fentry_skel);
+	if (!ASSERT_OK(err, "fentry_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fentry_skel->bss->test1_result, 1,
+		  "fentry_many_args_result1");
+	ASSERT_EQ(fentry_skel->bss->test2_result, 1,
+		  "fentry_many_args_result2");
+	ASSERT_EQ(fentry_skel->bss->test3_result, 1,
+		  "fentry_many_args_result3");
+
+cleanup:
+	fentry_many_args__destroy(fentry_skel);
+}
+
+void test_fentry_test(void)
+{
+	if (test__start_subtest("fentry"))
+		fentry_test();
+	if (test__start_subtest("fentry_many_args"))
+		fentry_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index 101b7343036b..1c13007e37dd 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -2,8 +2,9 @@
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
 #include "fexit_test.lskel.h"
+#include "fexit_many_args.skel.h"
 
-static int fexit_test(struct fexit_test_lskel *fexit_skel)
+static int fexit_test_common(struct fexit_test_lskel *fexit_skel)
 {
 	int err, prog_fd, i;
 	int link_fd;
@@ -37,7 +38,7 @@ static int fexit_test(struct fexit_test_lskel *fexit_skel)
 	return 0;
 }
 
-void test_fexit_test(void)
+static void fexit_test(void)
 {
 	struct fexit_test_lskel *fexit_skel = NULL;
 	int err;
@@ -46,13 +47,47 @@ void test_fexit_test(void)
 	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	if (!ASSERT_OK(err, "fexit_first_attach"))
 		goto cleanup;
 
-	err = fexit_test(fexit_skel);
+	err = fexit_test_common(fexit_skel);
 	ASSERT_OK(err, "fexit_second_attach");
 
 cleanup:
 	fexit_test_lskel__destroy(fexit_skel);
 }
+
+static void fexit_many_args(void)
+{
+	struct fexit_many_args *fexit_skel = NULL;
+	int err;
+
+	fexit_skel = fexit_many_args__open_and_load();
+	if (!ASSERT_OK_PTR(fexit_skel, "fexit_many_args_skel_load"))
+		goto cleanup;
+
+	err = fexit_many_args__attach(fexit_skel);
+	if (!ASSERT_OK(err, "fexit_many_args_attach"))
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+
+	ASSERT_EQ(fexit_skel->bss->test1_result, 1,
+		  "fexit_many_args_result1");
+	ASSERT_EQ(fexit_skel->bss->test2_result, 1,
+		  "fexit_many_args_result2");
+	ASSERT_EQ(fexit_skel->bss->test3_result, 1,
+		  "fexit_many_args_result3");
+
+cleanup:
+	fexit_many_args__destroy(fexit_skel);
+}
+
+void test_fexit_test(void)
+{
+	if (test__start_subtest("fexit"))
+		fexit_test();
+	if (test__start_subtest("fexit_many_args"))
+		fexit_many_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
index 28cf63963cb7..64a9c95d4acf 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_func_args_test.c
@@ -30,7 +30,9 @@ void test_get_func_args_test(void)
 	prog_fd = bpf_program__fd(skel->progs.fmod_ret_test);
 	err = bpf_prog_test_run_opts(prog_fd, &topts);
 	ASSERT_OK(err, "test_run");
-	ASSERT_EQ(topts.retval, 1234, "test_run");
+
+	ASSERT_EQ(topts.retval >> 16, 1, "test_run");
+	ASSERT_EQ(topts.retval & 0xffff, 1234 + 29, "test_run");
 
 	ASSERT_EQ(skel->bss->test1_result, 1, "test1_result");
 	ASSERT_EQ(skel->bss->test2_result, 1, "test2_result");
diff --git a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
index fd41425d2e5c..56b5baef35c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_map_resize.c
@@ -22,7 +22,7 @@ static void global_map_resize_bss_subtest(void)
 	struct test_global_map_resize *skel;
 	struct bpf_map *map;
 	const __u32 desired_sz = sizeof(skel->bss->sum) + sysconf(_SC_PAGE_SIZE) * 2;
-	size_t array_len, actual_sz;
+	size_t array_len, actual_sz, new_sz;
 
 	skel = test_global_map_resize__open();
 	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
@@ -42,6 +42,10 @@ static void global_map_resize_bss_subtest(void)
 	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
 		goto teardown;
 
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
 	/* set the expected number of elements based on the resized array */
 	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->bss->array[0]);
 	if (!ASSERT_GT(array_len, 1, "array_len"))
@@ -84,11 +88,11 @@ teardown:
 
 static void global_map_resize_data_subtest(void)
 {
-	int err;
 	struct test_global_map_resize *skel;
 	struct bpf_map *map;
 	const __u32 desired_sz = sysconf(_SC_PAGE_SIZE) * 2;
-	size_t array_len, actual_sz;
+	size_t array_len, actual_sz, new_sz;
+	int err;
 
 	skel = test_global_map_resize__open();
 	if (!ASSERT_OK_PTR(skel, "test_global_map_resize__open"))
@@ -108,6 +112,10 @@ static void global_map_resize_data_subtest(void)
 	if (!ASSERT_EQ(bpf_map__value_size(map), desired_sz, "resize"))
 		goto teardown;
 
+	new_sz = sizeof(skel->data_percpu_arr->percpu_arr[0]) * libbpf_num_possible_cpus();
+	err = bpf_map__set_value_size(skel->maps.data_percpu_arr, new_sz);
+	ASSERT_OK(err, "percpu_arr_resize");
+
 	/* set the expected number of elements based on the resized array */
 	array_len = (desired_sz - sizeof(skel->bss->sum)) / sizeof(skel->data_custom->my_array[0]);
 	if (!ASSERT_GT(array_len, 1, "array_len"))
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
index 5d9955af6247..a70c99c2f8c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/modify_return.c
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -41,6 +41,10 @@ static void run_test(__u32 input_retval, __u16 want_side_effect, __s16 want_ret)
 	ASSERT_EQ(skel->bss->fexit_result, 1, "modify_return fexit_result");
 	ASSERT_EQ(skel->bss->fmod_ret_result, 1, "modify_return fmod_ret_result");
 
+	ASSERT_EQ(skel->bss->fentry_result2, 1, "modify_return fentry_result2");
+	ASSERT_EQ(skel->bss->fexit_result2, 1, "modify_return fexit_result2");
+	ASSERT_EQ(skel->bss->fmod_ret_result2, 1, "modify_return fmod_ret_result2");
+
 cleanup:
 	modify_return__destroy(skel);
 }
@@ -49,9 +53,9 @@ cleanup:
 void serial_test_modify_return(void)
 {
 	run_test(0 /* input_retval */,
-		 1 /* want_side_effect */,
-		 4 /* want_ret */);
+		 2 /* want_side_effect */,
+		 33 /* want_ret */);
 	run_test(-EINVAL /* input_retval */,
 		 0 /* want_side_effect */,
-		 -EINVAL /* want_ret */);
+		 -EINVAL * 2 /* want_ret */);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
new file mode 100644
index 000000000000..4297a2a4cb11
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/netfilter_link_attach.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <netinet/in.h>
+#include <linux/netfilter.h>
+
+#include "test_progs.h"
+#include "test_netfilter_link_attach.skel.h"
+
+struct nf_link_test {
+	__u32 pf;
+	__u32 hooknum;
+	__s32 priority;
+	__u32 flags;
+
+	bool expect_success;
+	const char * const name;
+};
+
+static const struct nf_link_test nf_hook_link_tests[] = {
+	{ .name = "allzero", },
+	{ .pf = NFPROTO_NUMPROTO, .name = "invalid-pf", },
+	{ .pf = NFPROTO_IPV4, .hooknum = 42, .name = "invalid-hooknum", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MIN, .name = "invalid-priority-min", },
+	{ .pf = NFPROTO_IPV4, .priority = INT_MAX, .name = "invalid-priority-max", },
+	{ .pf = NFPROTO_IPV4, .flags = UINT_MAX, .name = "invalid-flags", },
+
+	{ .pf = NFPROTO_INET, .priority = 1, .name = "invalid-inet-not-supported", },
+
+	{ .pf = NFPROTO_IPV4, .priority = -10000, .expect_success = true, .name = "attach ipv4", },
+	{ .pf = NFPROTO_IPV6, .priority =  10001, .expect_success = true, .name = "attach ipv6", },
+};
+
+void test_netfilter_link_attach(void)
+{
+	struct test_netfilter_link_attach *skel;
+	struct bpf_program *prog;
+	LIBBPF_OPTS(bpf_netfilter_opts, opts);
+	int i;
+
+	skel = test_netfilter_link_attach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_netfilter_link_attach__open_and_load"))
+		goto out;
+
+	prog = skel->progs.nf_link_attach_test;
+	if (!ASSERT_OK_PTR(prog, "attach program"))
+		goto out;
+
+	for (i = 0; i < ARRAY_SIZE(nf_hook_link_tests); i++) {
+		struct bpf_link *link;
+
+		if (!test__start_subtest(nf_hook_link_tests[i].name))
+			continue;
+
+#define X(opts, m, i)	opts.m = nf_hook_link_tests[(i)].m
+		X(opts, pf, i);
+		X(opts, hooknum, i);
+		X(opts, priority, i);
+		X(opts, flags, i);
+#undef X
+		link = bpf_program__attach_netfilter(prog, &opts);
+		if (nf_hook_link_tests[i].expect_success) {
+			struct bpf_link *link2;
+
+			if (!ASSERT_OK_PTR(link, "program attach successful"))
+				continue;
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			ASSERT_ERR_PTR(link2, "attach program with same pf/hook/priority");
+
+			if (!ASSERT_OK(bpf_link__destroy(link), "link destroy"))
+				break;
+
+			link2 = bpf_program__attach_netfilter(prog, &opts);
+			if (!ASSERT_OK_PTR(link2, "program reattach successful"))
+				continue;
+			if (!ASSERT_OK(bpf_link__destroy(link2), "link destroy"))
+				break;
+		} else {
+			ASSERT_ERR_PTR(link, "program load failure");
+		}
+	}
+
+out:
+	test_netfilter_link_attach__destroy(skel);
+}
+
diff --git a/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
new file mode 100644
index 000000000000..8d077d150c56
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ptr_untrusted.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include <string.h>
+#include <linux/bpf.h>
+#include <test_progs.h>
+#include "test_ptr_untrusted.skel.h"
+
+#define TP_NAME "sched_switch"
+
+void serial_test_ptr_untrusted(void)
+{
+	struct test_ptr_untrusted *skel;
+	int err;
+
+	skel = test_ptr_untrusted__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		goto cleanup;
+
+	/* First, attach lsm prog */
+	skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run);
+	if (!ASSERT_OK_PTR(skel->links.lsm_run, "lsm_attach"))
+		goto cleanup;
+
+	/* Second, attach raw_tp prog. The lsm prog will be triggered. */
+	skel->links.raw_tp_run = bpf_program__attach_raw_tracepoint(skel->progs.raw_tp_run,
+								    TP_NAME);
+	if (!ASSERT_OK_PTR(skel->links.raw_tp_run, "raw_tp_attach"))
+		goto cleanup;
+
+	err = strncmp(skel->bss->tp_name, TP_NAME, strlen(TP_NAME));
+	ASSERT_EQ(err, 0, "cmp_tp_name");
+
+cleanup:
+	test_ptr_untrusted__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index 13bcaeb028b8..56685fc03c7e 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -347,7 +347,7 @@ static void syncookie_estab(void)
 	exp_active_estab_in.max_delack_ms = 22;
 
 	exp_passive_hdr_stg.syncookie = true;
-	exp_active_hdr_stg.resend_syn = true,
+	exp_active_hdr_stg.resend_syn = true;
 
 	prepare_out();
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
index 1c75a32186d6..fe0fb0c9849a 100644
--- a/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
+++ b/tools/testing/selftests/bpf/prog_tests/tracing_struct.c
@@ -55,6 +55,25 @@ static void test_fentry(void)
 
 	ASSERT_EQ(skel->bss->t6, 1, "t6 ret");
 
+	ASSERT_EQ(skel->bss->t7_a, 16, "t7:a");
+	ASSERT_EQ(skel->bss->t7_b, 17, "t7:b");
+	ASSERT_EQ(skel->bss->t7_c, 18, "t7:c");
+	ASSERT_EQ(skel->bss->t7_d, 19, "t7:d");
+	ASSERT_EQ(skel->bss->t7_e, 20, "t7:e");
+	ASSERT_EQ(skel->bss->t7_f_a, 21, "t7:f.a");
+	ASSERT_EQ(skel->bss->t7_f_b, 22, "t7:f.b");
+	ASSERT_EQ(skel->bss->t7_ret, 133, "t7 ret");
+
+	ASSERT_EQ(skel->bss->t8_a, 16, "t8:a");
+	ASSERT_EQ(skel->bss->t8_b, 17, "t8:b");
+	ASSERT_EQ(skel->bss->t8_c, 18, "t8:c");
+	ASSERT_EQ(skel->bss->t8_d, 19, "t8:d");
+	ASSERT_EQ(skel->bss->t8_e, 20, "t8:e");
+	ASSERT_EQ(skel->bss->t8_f_a, 21, "t8:f.a");
+	ASSERT_EQ(skel->bss->t8_f_b, 22, "t8:f.b");
+	ASSERT_EQ(skel->bss->t8_g, 23, "t8:g");
+	ASSERT_EQ(skel->bss->t8_ret, 156, "t8 ret");
+
 	tracing_struct__detach(skel);
 destroy_skel:
 	tracing_struct__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index e91d0d1769f1..6cd7349d4a2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -88,8 +88,8 @@ void serial_test_trampoline_count(void)
 	if (!ASSERT_OK(err, "bpf_prog_test_run_opts"))
 		goto cleanup;
 
-	ASSERT_EQ(opts.retval & 0xffff, 4, "bpf_modify_return_test.result");
-	ASSERT_EQ(opts.retval >> 16, 1, "bpf_modify_return_test.side_effect");
+	ASSERT_EQ(opts.retval & 0xffff, 33, "bpf_modify_return_test.result");
+	ASSERT_EQ(opts.retval >> 16, 2, "bpf_modify_return_test.side_effect");
 
 cleanup:
 	for (; i >= 0; i--) {
diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index 070a13833c3f..c375e59ff28d 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -58,6 +58,7 @@
 #include "verifier_stack_ptr.skel.h"
 #include "verifier_subprog_precision.skel.h"
 #include "verifier_subreg.skel.h"
+#include "verifier_typedef.skel.h"
 #include "verifier_uninit.skel.h"
 #include "verifier_unpriv.skel.h"
 #include "verifier_unpriv_perf.skel.h"
@@ -159,6 +160,7 @@ void test_verifier_spin_lock(void)            { RUN(verifier_spin_lock); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
 void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
 void test_verifier_subreg(void)               { RUN(verifier_subreg); }
+void test_verifier_typedef(void)              { RUN(verifier_typedef); }
 void test_verifier_uninit(void)               { RUN(verifier_uninit); }
 void test_verifier_unpriv(void)               { RUN(verifier_unpriv); }
 void test_verifier_unpriv_perf(void)          { RUN(verifier_unpriv_perf); }
diff --git a/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
new file mode 100644
index 000000000000..1e2e73f3b749
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_tcp_skb.c
@@ -0,0 +1,382 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include "cgroup_tcp_skb.h"
+
+char _license[] SEC("license") = "GPL";
+
+__u16 g_sock_port = 0;
+__u32 g_sock_state = 0;
+int g_unexpected = 0;
+__u32 g_packet_count = 0;
+
+int needed_tcp_pkt(struct __sk_buff *skb, struct tcphdr *tcph)
+{
+	struct ipv6hdr ip6h;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return 0;
+	if (bpf_skb_load_bytes(skb, 0, &ip6h, sizeof(ip6h)))
+		return 0;
+
+	if (ip6h.nexthdr != IPPROTO_TCP)
+		return 0;
+
+	if (bpf_skb_load_bytes(skb, sizeof(ip6h), tcph, sizeof(*tcph)))
+		return 0;
+
+	if (tcph->source != bpf_htons(g_sock_port) &&
+	    tcph->dest != bpf_htons(g_sock_port))
+		return 0;
+
+	return 1;
+}
+
+/* Run accept() on a socket in the cgroup to receive a new connection. */
+static int egress_accept(struct tcphdr *tcph)
+{
+	if (g_sock_state ==  SYN_RECV_SENDING_SYN_ACK) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_accept(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case INIT:
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_RECV_SENDING_SYN_ACK;
+		break;
+	case SYN_RECV:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Run connect() on a socket in the cgroup to start a new connection. */
+static int egress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == INIT) {
+		if (!tcph->syn || tcph->fin || tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = SYN_SENT;
+		return 1;
+	}
+
+	return 0;
+}
+
+static int ingress_connect(struct tcphdr *tcph)
+{
+	if (g_sock_state == SYN_SENT) {
+		if (tcph->fin || !tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = ESTABLISHED;
+		return 1;
+	}
+
+	return 0;
+}
+
+/* The connection is closed by the peer outside the cgroup. */
+static int egress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case CLOSE_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSE_WAIT;
+		break;
+	case CLOSE_WAIT:
+		if (!tcph->fin)
+			g_unexpected++;
+		else
+			g_sock_state = LAST_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_remote(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = CLOSE_WAIT_SENDING_ACK;
+		break;
+	case LAST_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = CLOSED;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* The connection is closed by the endpoint inside the cgroup. */
+static int egress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		if (tcph->fin)
+			g_sock_state = FIN_WAIT1;
+		break;
+	case TIME_WAIT_SENDING_ACK:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static int ingress_close_local(struct tcphdr *tcph)
+{
+	switch (g_sock_state) {
+	case ESTABLISHED:
+		break;
+	case FIN_WAIT1:
+		if (tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = FIN_WAIT2;
+		break;
+	case FIN_WAIT2:
+		if (!tcph->fin || tcph->syn || !tcph->ack)
+			g_unexpected++;
+		else
+			g_sock_state = TIME_WAIT_SENDING_ACK;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int server_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_accept(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a server socket to make sure they
+ * are consistent with the state of the server socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int server_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_accept(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the server side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress_srv(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_remote(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of outgoing packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/egress")
+int client_egress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Egress of the server socket. */
+	if (egress_connect(&tcph) || egress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
+
+/* Check the types of incoming packets of a client socket to make sure they
+ * are consistent with the state of the client socket.
+ *
+ * The connection is closed by the client side.
+ */
+SEC("cgroup_skb/ingress")
+int client_ingress(struct __sk_buff *skb)
+{
+	struct tcphdr tcph;
+
+	if (!needed_tcp_pkt(skb, &tcph))
+		return 1;
+
+	g_packet_count++;
+
+	/* Ingress of the server socket. */
+	if (ingress_connect(&tcph) || ingress_close_local(&tcph))
+		return 1;
+
+	g_unexpected++;
+	return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/fentry_many_args.c b/tools/testing/selftests/bpf/progs/fentry_many_args.c
new file mode 100644
index 000000000000..b61bb92fee2c
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fentry_many_args.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fentry/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fentry/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/fexit_many_args.c b/tools/testing/selftests/bpf/progs/fexit_many_args.c
new file mode 100644
index 000000000000..53b335c2dafb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/fexit_many_args.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Tencent */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_result = 0;
+SEC("fexit/bpf_testmod_fentry_test7")
+int BPF_PROG(test1, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	test1_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && ret == 133;
+	return 0;
+}
+
+__u64 test2_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test2, __u64 a, void *b, short c, int d, void *e, char f,
+	     int g, unsigned int h, long i, __u64 j, unsigned long k,
+	     int ret)
+{
+	test2_result = a == 16 && b == (void *)17 && c == 18 && d == 19 &&
+		e == (void *)20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
+
+__u64 test3_result = 0;
+SEC("fexit/bpf_testmod_fentry_test11")
+int BPF_PROG(test3, __u64 a, __u64 b, __u64 c, __u64 d, __u64 e, __u64 f,
+	     __u64 g, __u64 h, __u64 i, __u64 j, __u64 k, __u64 ret)
+{
+	test3_result = a == 16 && b == 17 && c == 18 && d == 19 &&
+		e == 20 && f == 21 && g == 22 && h == 23 &&
+		i == 24 && j == 25 && k == 26 && ret == 231;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/htab_mem_bench.c b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
new file mode 100644
index 000000000000..b1b721b14d67
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/htab_mem_bench.c
@@ -0,0 +1,105 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023. Huawei Technologies Co., Ltd */
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define OP_BATCH 64
+
+struct update_ctx {
+	unsigned int from;
+	unsigned int step;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, 4);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} htab SEC(".maps");
+
+char _license[] SEC("license") = "GPL";
+
+unsigned char zeroed_value[4096];
+unsigned int nr_thread = 0;
+long op_cnt = 0;
+
+static int write_htab(unsigned int i, struct update_ctx *ctx, unsigned int flags)
+{
+	bpf_map_update_elem(&htab, &ctx->from, zeroed_value, flags);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+static int overwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, 0);
+}
+
+static int newwrite_htab(unsigned int i, struct update_ctx *ctx)
+{
+	return write_htab(i, ctx, BPF_NOEXIST);
+}
+
+static int del_htab(unsigned int i, struct update_ctx *ctx)
+{
+	bpf_map_delete_elem(&htab, &ctx->from);
+	ctx->from += ctx->step;
+
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int overwrite(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int batch_add_batch_del(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id();
+	update.step = nr_thread;
+	bpf_loop(OP_BATCH, overwrite_htab, &update, 0);
+
+	update.from = bpf_get_smp_processor_id();
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+
+	__sync_fetch_and_add(&op_cnt, 2);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getpgid")
+int add_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, newwrite_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
+
+SEC("?tp/syscalls/sys_enter_getppid")
+int del_only(void *ctx)
+{
+	struct update_ctx update;
+
+	update.from = bpf_get_smp_processor_id() / 2;
+	update.step = nr_thread / 2;
+	bpf_loop(OP_BATCH, del_htab, &update, 0);
+	__sync_fetch_and_add(&op_cnt, 1);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/linked_list.c b/tools/testing/selftests/bpf/progs/linked_list.c
index 57440a554304..84d1777a9e6c 100644
--- a/tools/testing/selftests/bpf/progs/linked_list.c
+++ b/tools/testing/selftests/bpf/progs/linked_list.c
@@ -96,7 +96,7 @@ static __always_inline
 int list_push_pop_multiple(struct bpf_spin_lock *lock, struct bpf_list_head *head, bool leave_in_map)
 {
 	struct bpf_list_node *n;
-	struct foo *f[8], *pf;
+	struct foo *f[200], *pf;
 	int i;
 
 	/* Loop following this check adds nodes 2-at-a-time in order to
diff --git a/tools/testing/selftests/bpf/progs/map_percpu_stats.c b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
new file mode 100644
index 000000000000..10b2325c1720
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/map_percpu_stats.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+__u32 target_id;
+
+__s64 bpf_map_sum_elem_count(struct bpf_map *map) __ksym;
+
+SEC("iter/bpf_map")
+int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
+{
+	struct seq_file *seq = ctx->meta->seq;
+	struct bpf_map *map = ctx->map;
+
+	if (map && map->id == target_id)
+		BPF_SEQ_PRINTF(seq, "%lld", bpf_map_sum_elem_count(map));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/modify_return.c b/tools/testing/selftests/bpf/progs/modify_return.c
index 8b7466a15c6b..3376d4849f58 100644
--- a/tools/testing/selftests/bpf/progs/modify_return.c
+++ b/tools/testing/selftests/bpf/progs/modify_return.c
@@ -47,3 +47,43 @@ int BPF_PROG(fexit_test, int a, __u64 b, int ret)
 
 	return 0;
 }
+
+static int sequence2;
+
+__u64 fentry_result2 = 0;
+SEC("fentry/bpf_modify_return_test2")
+int BPF_PROG(fentry_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g)
+{
+	sequence2++;
+	fentry_result2 = (sequence2 == 1);
+	return 0;
+}
+
+__u64 fmod_ret_result2 = 0;
+SEC("fmod_ret/bpf_modify_return_test2")
+int BPF_PROG(fmod_ret_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* This is the first fmod_ret program, the ret passed should be 0 */
+	fmod_ret_result2 = (sequence2 == 2 && ret == 0);
+	return input_retval;
+}
+
+__u64 fexit_result2 = 0;
+SEC("fexit/bpf_modify_return_test2")
+int BPF_PROG(fexit_test2, int a, int *b, short c, int d, void *e, char f,
+	     int g, int ret)
+{
+	sequence2++;
+	/* If the input_reval is non-zero a successful modification should have
+	 * occurred.
+	 */
+	if (input_retval)
+		fexit_result2 = (sequence2 == 3 && ret == input_retval);
+	else
+		fexit_result2 = (sequence2 == 3 && ret == 29);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_failure.c b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
index 0d1aa6bbace4..ea39497f11ed 100644
--- a/tools/testing/selftests/bpf/progs/nested_trust_failure.c
+++ b/tools/testing/selftests/bpf/progs/nested_trust_failure.c
@@ -10,6 +10,13 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
 /* Prototype for all of the program trace events below:
  *
  * TRACE_EVENT(task_newtask,
@@ -31,3 +38,12 @@ int BPF_PROG(test_invalid_nested_offset, struct task_struct *task, u64 clone_fla
 	bpf_cpumask_first_zero(&task->cpus_mask);
 	return 0;
 }
+
+/* Although R2 is of type sk_buff but sock_common is expected, we will hit untrusted ptr first. */
+SEC("tp_btf/tcp_probe")
+__failure __msg("R2 type=untrusted_ptr_ expected=ptr_, trusted_ptr_, rcu_ptr_")
+int BPF_PROG(test_invalid_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->next, 0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/nested_trust_success.c b/tools/testing/selftests/bpf/progs/nested_trust_success.c
index 886ade4aa99d..833840bffd3b 100644
--- a/tools/testing/selftests/bpf/progs/nested_trust_success.c
+++ b/tools/testing/selftests/bpf/progs/nested_trust_success.c
@@ -10,6 +10,13 @@
 
 char _license[] SEC("license") = "GPL";
 
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, u64);
+} sk_storage_map SEC(".maps");
+
 SEC("tp_btf/task_newtask")
 __success
 int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
@@ -17,3 +24,11 @@ int BPF_PROG(test_read_cpumask, struct task_struct *task, u64 clone_flags)
 	bpf_cpumask_test_cpu(0, task->cpus_ptr);
 	return 0;
 }
+
+SEC("tp_btf/tcp_probe")
+__success
+int BPF_PROG(test_skb_field, struct sock *sk, struct sk_buff *skb)
+{
+	bpf_sk_storage_get(&sk_storage_map, skb->sk, 0, 0);
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
index 2588f2384246..1fbb73d3e5d5 100644
--- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -29,13 +29,16 @@ int my_int SEC(".data.non_array");
 int my_array_first[1] SEC(".data.array_not_last");
 int my_int_last SEC(".data.array_not_last");
 
+int percpu_arr[1] SEC(".data.percpu_arr");
+
 SEC("tp/syscalls/sys_enter_getpid")
 int bss_array_sum(void *ctx)
 {
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
-	sum = 0;
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
 
 	for (size_t i = 0; i < bss_array_len; ++i)
 		sum += array[i];
@@ -49,7 +52,8 @@ int data_array_sum(void *ctx)
 	if (pid != (bpf_get_current_pid_tgid() >> 32))
 		return 0;
 
-	sum = 0;
+	/* this will be zero, we just rely on verifier not rejecting this */
+	sum = percpu_arr[bpf_get_smp_processor_id()];
 
 	for (size_t i = 0; i < data_array_len; ++i)
 		sum += my_array[i];
diff --git a/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
new file mode 100644
index 000000000000..03a475160abe
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_netfilter_link_attach.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+
+#define NF_ACCEPT 1
+
+SEC("netfilter")
+int nf_link_attach_test(struct bpf_nf_ctx *ctx)
+{
+	return NF_ACCEPT;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
new file mode 100644
index 000000000000..4bdd65b5aa2d
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_ptr_untrusted.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2023 Yafang Shao <laoar.shao@gmail.com> */
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+
+char tp_name[128];
+
+SEC("lsm/bpf")
+int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size)
+{
+	switch (cmd) {
+	case BPF_RAW_TRACEPOINT_OPEN:
+		bpf_probe_read_user_str(tp_name, sizeof(tp_name) - 1,
+					(void *)attr->raw_tracepoint.name);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+SEC("raw_tracepoint")
+int BPF_PROG(raw_tp_run)
+{
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/tracing_struct.c b/tools/testing/selftests/bpf/progs/tracing_struct.c
index c435a3a8328a..515daef3c84b 100644
--- a/tools/testing/selftests/bpf/progs/tracing_struct.c
+++ b/tools/testing/selftests/bpf/progs/tracing_struct.c
@@ -18,6 +18,11 @@ struct bpf_testmod_struct_arg_3 {
 	int b[];
 };
 
+struct bpf_testmod_struct_arg_4 {
+	u64 a;
+	int b;
+};
+
 long t1_a_a, t1_a_b, t1_b, t1_c, t1_ret, t1_nregs;
 __u64 t1_reg0, t1_reg1, t1_reg2, t1_reg3;
 long t2_a, t2_b_a, t2_b_b, t2_c, t2_ret;
@@ -25,6 +30,9 @@ long t3_a, t3_b, t3_c_a, t3_c_b, t3_ret;
 long t4_a_a, t4_b, t4_c, t4_d, t4_e_a, t4_e_b, t4_ret;
 long t5_ret;
 int t6;
+long t7_a, t7_b, t7_c, t7_d, t7_e, t7_f_a, t7_f_b, t7_ret;
+long t8_a, t8_b, t8_c, t8_d, t8_e, t8_f_a, t8_f_b, t8_g, t8_ret;
+
 
 SEC("fentry/bpf_testmod_test_struct_arg_1")
 int BPF_PROG2(test_struct_arg_1, struct bpf_testmod_struct_arg_2, a, int, b, int, c)
@@ -130,4 +138,50 @@ int BPF_PROG2(test_struct_arg_11, struct bpf_testmod_struct_arg_3 *, a)
 	return 0;
 }
 
+SEC("fentry/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_arg_12, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f)
+{
+	t7_a = a;
+	t7_b = (long)b;
+	t7_c = c;
+	t7_d = d;
+	t7_e = (long)e;
+	t7_f_a = f.a;
+	t7_f_b = f.b;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_7")
+int BPF_PROG2(test_struct_arg_13, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, ret)
+{
+	t7_ret = ret;
+	return 0;
+}
+
+SEC("fentry/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_arg_14, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g)
+{
+	t8_a = a;
+	t8_b = (long)b;
+	t8_c = c;
+	t8_d = d;
+	t8_e = (long)e;
+	t8_f_a = f.a;
+	t8_f_b = f.b;
+	t8_g = g;
+	return 0;
+}
+
+SEC("fexit/bpf_testmod_test_struct_arg_8")
+int BPF_PROG2(test_struct_arg_15, __u64, a, void *, b, short, c, int, d,
+	      void *, e, struct bpf_testmod_struct_arg_4, f, int, g,
+	      int, ret)
+{
+	t8_ret = ret;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_typedef.c b/tools/testing/selftests/bpf/progs/verifier_typedef.c
new file mode 100644
index 000000000000..08481cfaac4b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_typedef.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+SEC("fentry/bpf_fentry_test_sinfo")
+__description("typedef: resolve")
+__success __retval(0)
+__naked void resolve_typedef(void)
+{
+	asm volatile ("					\
+	r1 = *(u64 *)(r1 +0);				\
+	r2 = *(u64 *)(r1 +%[frags_offs]);		\
+	r0 = 0;						\
+	exit;						\
+"	:
+	: __imm_const(frags_offs,
+		      offsetof(struct skb_shared_info, frags))
+	: __clobber_all);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 9b070cdf44ac..f83d9f65c65b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -18,7 +18,7 @@
 #define TRACEFS_PIPE	"/sys/kernel/tracing/trace_pipe"
 #define DEBUGFS_PIPE	"/sys/kernel/debug/tracing/trace_pipe"
 
-#define MAX_SYMS 300000
+#define MAX_SYMS 400000
 static struct ksym syms[MAX_SYMS];
 static int sym_cnt;
 
@@ -46,6 +46,9 @@ int load_kallsyms_refresh(void)
 			break;
 		if (!addr)
 			continue;
+		if (i >= MAX_SYMS)
+			return -EFBIG;
+
 		syms[i].addr = (long) addr;
 		syms[i].name = strdup(func);
 		i++;
diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index b39665f33524..319337bdcfc8 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -242,4 +242,5 @@
 	.result = REJECT,
 	.errstr = "R0 invalid mem access",
 	.errstr_unpriv = "R10 partial copy of pointer",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 83cecfbd6739..0b394a7f7a2d 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1169,6 +1169,7 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
        "pkt_end < pkt taken check",
@@ -1190,4 +1191,5 @@
        },
        .result = ACCEPT,
        .prog_type = BPF_PROG_TYPE_SK_SKB,
+       .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index 1a27a6210554..43776f6f92f4 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -290,6 +290,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: BPF_K",
@@ -360,6 +361,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jle32: BPF_K",
@@ -430,6 +432,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jlt32: BPF_K",
@@ -500,6 +503,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsge32: BPF_K",
@@ -570,6 +574,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsgt32: BPF_K",
@@ -640,6 +645,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jsle32: BPF_K",
@@ -710,6 +716,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jslt32: BPF_K",
@@ -780,6 +787,7 @@
 	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"jgt32: range bound deduction, reg op imm",
diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c
index a0cfc06d75bc..d25c3e9605f1 100644
--- a/tools/testing/selftests/bpf/verifier/map_kptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_kptr.c
@@ -68,6 +68,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access cannot have variable offset",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: bpf_kptr_xchg non-const var_off",
@@ -121,6 +122,7 @@
 	.fixup_map_kptr = { 1 },
 	.result = REJECT,
 	.errstr = "kptr access misaligned expected=0 off=7",
+	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"map_kptr: reject var_off != 0",
diff --git a/tools/testing/selftests/bpf/verifier/precise.c b/tools/testing/selftests/bpf/verifier/precise.c
index 99272bb890da..0d84dd1f38b6 100644
--- a/tools/testing/selftests/bpf/verifier/precise.c
+++ b/tools/testing/selftests/bpf/verifier/precise.c
@@ -216,7 +216,7 @@
 	},
 	.fixup_map_ringbuf = { 1 },
 	.prog_type = BPF_PROG_TYPE_XDP,
-	.flags = BPF_F_TEST_STATE_FREQ,
+	.flags = BPF_F_TEST_STATE_FREQ | F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	.errstr = "invalid access to memory, mem_size=1 off=42 size=8",
 	.result = REJECT,
 },
diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile
index 01c0491d64da..2e986cbf1a46 100644
--- a/tools/testing/selftests/hid/Makefile
+++ b/tools/testing/selftests/hid/Makefile
@@ -167,7 +167,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -196,12 +196,12 @@ CLANG_CFLAGS = $(CLANG_SYS_INCLUDES) \
 # $3 - CFLAGS
 define CLANG_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v3 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
 endef
 # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
 define CLANG_NOALU32_BPF_BUILD_RULE
 	$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
-	$(Q)$(CLANG) $3 -O2 -target bpf -c $1 -mcpu=v2 -o $2
+	$(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
 endef
 # Build BPF object using GCC
 define GCC_BPF_BUILD_RULE
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 7f3ab2a93ed6..2f69f7274e3d 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -113,7 +113,7 @@ $(MAKE_DIRS):
 	mkdir -p $@
 
 # Get Clang's default includes on this system, as opposed to those seen by
-# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# '--target=bpf'. This fixes "missing" files on some architectures/distros,
 # such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
 #
 # Use '-idirafter': Don't interfere with include mechanics except where the
@@ -131,7 +131,7 @@ endif
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
 $(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
-	$(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
+	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   $(APIDIR)/linux/bpf.h					       \
diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile
index cb553eac9f41..3c4b7fa05075 100644
--- a/tools/testing/selftests/tc-testing/Makefile
+++ b/tools/testing/selftests/tc-testing/Makefile
@@ -24,7 +24,7 @@ CLANG_FLAGS = -I. -I$(APIDIR) \
 
 $(OUTPUT)/%.o: %.c
 	$(CLANG) $(CLANG_FLAGS) \
-		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+		 -O2 --target=bpf -emit-llvm -c $< -o - |      \
 	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
 
 TEST_PROGS += ./tdc.sh