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>

9 files changed, 478 insertions, 25 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 {