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>

1 files changed, 428 insertions, 4 deletions

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 2d786072ed0d0..65a168df63bc1 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;
 }