Merge tag 'perf-tools-for-v6.6-1-2023-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools

Pull perf tools updates from Arnaldo Carvalho de Melo:
 "perf tools maintainership:

   - Add git information for perf-tools and perf-tools-next trees and
     branches to the MAINTAINERS file. That is where development now
     takes place and myself and Namhyung Kim have write access, more
     people to come as we emulate other maintainer groups.

  perf record:

   - Record kernel data maps when 'perf record --data' is used, so that
     global variables can be resolved and used in tools that do data
     profiling.

  perf trace:

   - Remove the old, experimental support for BPF events in which a .c
     file was passed as an event: "perf trace -e hello.c" to then get
     compiled and loaded.

     The only known usage for that, that shipped with the kernel as an
     example for such events, augmented the raw_syscalls tracepoints and
     was converted to a libbpf skeleton, reusing all the user space
     components and the BPF code connected to the syscalls.

     In the end just the way to glue the BPF part and the user space
     type beautifiers changed, now being performed by libbpf skeletons.

     The next step is to use BTF to do pretty printing of all syscall
     types, as discussed with Alan Maguire and others.

     Now, on a perf built with BUILD_BPF_SKEL=1 we get most if not all
     path/filenames/strings, some of the networking data structures,
     perf_event_attr, etc, i.e. systemwide tracing of nanosleep calls
     and perf_event_open syscalls while 'perf stat' runs 'sleep' for 5
     seconds:

      # perf trace -a -e *nanosleep,perf* perf stat -e cycles,instructions sleep 5
         0.000 (   9.034 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0 (PERF_COUNT_HW_CPU_CYCLES), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
         9.039 (   0.006 ms): perf/327641 perf_event_open(attr_uptr: { type: 0 (PERF_TYPE_HARDWARE), size: 136, config: 0x1 (PERF_COUNT_HW_INSTRUCTIONS), sample_type: IDENTIFIER, read_format: TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING, disabled: 1, inherit: 1, enable_on_exec: 1, exclude_guest: 1 }, pid: 327642 (perf-exec), cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = 4
             ? (           ): gpm/991  ... [continued]: clock_nanosleep())               = 0
        10.133 (           ): sleep/327642 clock_nanosleep(rqtp: { .tv_sec: 5, .tv_nsec: 0 }, rmtp: 0x7ffd36f83ed0) ...
             ? (           ): pool-gsd-smart/3051  ... [continued]: clock_nanosleep())   = 0
        30.276 (           ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
       223.215 (1000.430 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
        30.276 (2000.394 ms): gpm/991  ... [continued]: clock_nanosleep())               = 0
      1230.814 (           ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
      1230.814 (1000.404 ms): pool-gsd-smart/3051  ... [continued]: clock_nanosleep())   = 0
      2030.886 (           ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
      2237.709 (1000.153 ms): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) = 0
             ? (           ): crond/1172  ... [continued]: clock_nanosleep())            = 0
      3242.699 (           ): pool-gsd-smart/3051 clock_nanosleep(rqtp: { .tv_sec: 1, .tv_nsec: 0 }, rmtp: 0x7f6e7fffec90) ...
      2030.886 (2000.385 ms): gpm/991  ... [continued]: clock_nanosleep())               = 0
      3728.078 (           ): crond/1172 clock_nanosleep(rqtp: { .tv_sec: 60, .tv_nsec: 0 }, rmtp: 0x7ffe0971dcf0) ...
      3242.699 (1000.158 ms): pool-gsd-smart/3051  ... [continued]: clock_nanosleep())   = 0
      4031.409 (           ): gpm/991 clock_nanosleep(rqtp: { .tv_sec: 2, .tv_nsec: 0 }, rmtp: 0x7ffcc6f73710) ...
        10.133 (5000.375 ms): sleep/327642  ... [continued]: clock_nanosleep())          = 0

      Performance counter stats for 'sleep 5':

             2,617,347      cycles
             1,855,997      instructions                     #    0.71  insn per cycle

           5.002282128 seconds time elapsed

           0.000855000 seconds user
           0.000852000 seconds sys

  perf annotate:

   - Building with binutils' libopcode now is opt-in (BUILD_NONDISTRO=1)
     for licensing reasons, and we missed a build test on
     tools/perf/tests makefile.

     Since we now default to NDEBUG=1, we ended up segfaulting when
     building with BUILD_NONDISTRO=1 because a needed initialization
     routine was being "error checked" via an assert.

     Fix it by explicitly checking the result and aborting instead if it
     fails.

     We better back propagate the error, but at least 'perf annotate' on
     samples collected for a BPF program is back working when perf is
     built with BUILD_NONDISTRO=1.

  perf report/top:

   - Add back TUI hierarchy mode header, that is seen when using 'perf
     report/top --hierarchy'.

   - Fix the number of entries for 'e' key in the TUI that was
     preventing navigation of lines when expanding an entry.

  perf report/script:

   - Support cross platform register handling, allowing a perf.data file
     collected on one architecture to have registers sampled correctly
     displayed when analysis tools such as 'perf report' and 'perf
     script' are used on a different architecture.

   - Fix handling of event attributes in pipe mode, i.e. when one uses:

  	perf record -o - | perf report -i -

     When no perf.data files are used.

   - Handle files generated via pipe mode with a version of perf and
     then read also via pipe mode with a different version of perf,
     where the event attr record may have changed, use the record size
     field to properly support this version mismatch.

  perf probe:

   - Accessing global variables from uprobes isn't supported, make the
     error message state that instead of stating that some minimal
     kernel version is needed to have that feature. This seems just a
     tool limitation, the kernel probably has all that is needed.

  perf tests:

   - Fix a reference count related leak in the dlfilter v0 API where the
     result of a thread__find_symbol_fb() is not matched with an
     addr_location__exit() to drop the reference counts of the resolved
     components (machine, thread, map, symbol, etc). Add a dlfilter test
     to make sure that doesn't regresses.

   - Lots of fixes for the 'perf test' written in shell script related
     to problems found with the shellcheck utility.

   - Fixes for 'perf test' shell scripts testing features enabled when
     perf is built with BUILD_BPF_SKEL=1, such as 'perf stat' bpf
     counters.

   - Add perf record sample filtering test, things like the following
     example, that gets implemented as a BPF filter attached to the
     event:

       # perf record -e task-clock -c 10000 --filter 'ip < 0xffffffff00000000'

   - Improve the way the task_analyzer test checks if libtraceevent is
     linked, using 'perf version --build-options' instead of the more
     expensinve 'perf record -e "sched:sched_switch"'.

   - Add support for riscv in the mmap-basic test. (This went as well
     via the RiscV tree, same contents).

  libperf:

   - Implement riscv mmap support (This went as well via the RiscV tree,
     same contents).

  perf script:

   - New tool that converts perf.data files to the firefox profiler
     format so that one can use the visualizer at
     https://profiler.firefox.com/. Done by Anup Sharma as part of this
     year's Google Summer of Code.

     One can generate the output and upload it to the web interface but
     Anup also automated everything:

       perf script gecko -F 99 -a sleep 60

   - Support syscall name parsing on arm64.

   - Print "cgroup" field on the same line as "comm".

  perf bench:

   - Add new 'uprobe' benchmark to measure the overhead of uprobes
     with/without BPF programs attached to it.

   - breakpoints are not available on power9, skip that test.

  perf stat:

   - Add #num_cpus_online literal to be used in 'perf stat' metrics, and
     add this extra 'perf test' check that exemplifies its purpose:

  	TEST_ASSERT_VAL("#num_cpus_online",
                         expr__parse(&num_cpus_online, ctx, "#num_cpus_online") == 0);
  	TEST_ASSERT_VAL("#num_cpus", expr__parse(&num_cpus, ctx, "#num_cpus") == 0);
  	TEST_ASSERT_VAL("#num_cpus >= #num_cpus_online", num_cpus >= num_cpus_online);

  Miscellaneous:

   - Improve tool startup time by lazily reading PMU, JSON, sysfs data.

   - Improve error reporting in the parsing of events, passing YYLTYPE
     to error routines, so that the output can show were the parsing
     error was found.

   - Add 'perf test' entries to check the parsing of events
     improvements.

   - Fix various leak for things detected by -fsanitize=address, mostly
     things that would be freed at tool exit, including:

       - Free evsel->filter on the destructor.

       - Allow tools to register a thread->priv destructor and use it in
         'perf trace'.

       - Free evsel->priv in 'perf trace'.

       - Free string returned by synthesize_perf_probe_point() when the
         caller fails to do all it needs.

   - Adjust various compiler options to not consider errors some
     warnings when building with broken headers found in things like
     python, flex, bison, as we otherwise build with -Werror. Some for
     gcc, some for clang, some for some specific version of those, some
     for some specific version of flex or bison, or some specific
     combination of these components, bah.

   - Allow customization of clang options for BPF target, this helps
     building on gentoo where there are other oddities where BPF targets
     gets passed some compiler options intended for the native build, so
     building with WERROR=0 helps while these oddities are fixed.

   - Dont pass ERR_PTR() values to perf_session__delete() in 'perf top'
     and 'perf lock', fixing some segfaults when handling some odd
     failures.

   - Add LTO build option.

   - Fix format of unordered lists in the perf docs
     (tools/perf/Documentation)

   - Overhaul the bison files, using constructs such as YYNOMEM.

   - Remove unused tokens from the bison .y files.

   - Add more comments to various structs.

   - A few LoongArch enablement patches.

  Vendor events (JSON):

   - Add JSON metrics for Yitian 710 DDR (aarch64). Things like:

  	EventName, BriefDescription
  	visible_window_limit_reached_rd, "At least one entry in read queue reaches the visible window limit.",
  	visible_window_limit_reached_wr, "At least one entry in write queue reaches the visible window limit.",
  	op_is_dqsosc_mpc	       , "A DQS Oscillator MPC command to DRAM.",
  	op_is_dqsosc_mrr	       , "A DQS Oscillator MRR command to DRAM.",
  	op_is_tcr_mrr		       , "A Temperature Compensated Refresh(TCR) MRR command to DRAM.",

   - Add AmpereOne metrics (aarch64).

   - Update N2 and V2 metrics (aarch64) and events using Arm telemetry
     repo.

   - Update scale units and descriptions of common topdown metrics on
     aarch64. Things like:
       - "MetricExpr": "stall_slot_frontend / (#slots * cpu_cycles)",
       - "BriefDescription": "Frontend bound L1 topdown metric",
       + "MetricExpr": "100 * (stall_slot_frontend / (#slots * cpu_cycles))",
       + "BriefDescription": "This metric is the percentage of total slots that were stalled due to resource constraints in the frontend of the processor.",

   - Update events for intel: meteorlake to 1.04, sapphirerapids to
     1.15, Icelake+ metric constraints.

   - Update files for the power10 platform"

* tag 'perf-tools-for-v6.6-1-2023-09-05' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (217 commits)
  perf parse-events: Fix driver config term
  perf parse-events: Fixes relating to no_value terms
  perf parse-events: Fix propagation of term's no_value when cloning
  perf parse-events: Name the two term enums
  perf list: Don't print Unit for "default_core"
  perf vendor events intel: Fix modifier in tma_info_system_mem_parallel_reads for skylake
  perf dlfilter: Avoid leak in v0 API test use of resolve_address()
  perf metric: Add #num_cpus_online literal
  perf pmu: Remove str from perf_pmu_alias
  perf parse-events: Make common term list to strbuf helper
  perf parse-events: Minor help message improvements
  perf pmu: Avoid uninitialized use of alias->str
  perf jevents: Use "default_core" for events with no Unit
  perf test stat_bpf_counters_cgrp: Enhance perf stat cgroup BPF counter test
  perf test shell stat_bpf_counters: Fix test on Intel
  perf test shell record_bpf_filter: Skip 6.2 kernel
  libperf: Get rid of attr.id field
  perf tools: Convert to perf_record_header_attr_id()
  libperf: Add perf_record_header_attr_id()
  perf tools: Handle old data in PERF_RECORD_ATTR
  ...

5 files changed, 225 insertions, 9 deletions

diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 07bbc449329e..c2ab30907ae7 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -17,6 +17,7 @@ perf-y += inject-buildid.o
 perf-y += evlist-open-close.o
 perf-y += breakpoint.o
 perf-y += pmu-scan.o
+perf-y += uprobe.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index a0625c77bea3..faa18e6d2467 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -43,6 +43,9 @@ int bench_inject_build_id(int argc, const char **argv);
 int bench_evlist_open_close(int argc, const char **argv);
 int bench_breakpoint_thread(int argc, const char **argv);
 int bench_breakpoint_enable(int argc, const char **argv);
+int bench_uprobe_baseline(int argc, const char **argv);
+int bench_uprobe_empty(int argc, const char **argv);
+int bench_uprobe_trace_printk(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/breakpoint.c b/tools/perf/bench/breakpoint.c
index 41385f89ffc7..dfd18f5db97d 100644
--- a/tools/perf/bench/breakpoint.c
+++ b/tools/perf/bench/breakpoint.c
@@ -47,6 +47,7 @@ struct breakpoint {
 static int breakpoint_setup(void *addr)
 {
 	struct perf_event_attr attr = { .size = 0, };
+	int fd;
 
 	attr.type = PERF_TYPE_BREAKPOINT;
 	attr.size = sizeof(attr);
@@ -56,7 +57,12 @@ static int breakpoint_setup(void *addr)
 	attr.bp_addr = (unsigned long)addr;
 	attr.bp_type = HW_BREAKPOINT_RW;
 	attr.bp_len = HW_BREAKPOINT_LEN_1;
-	return syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0);
+	fd = syscall(SYS_perf_event_open, &attr, 0, -1, -1, 0);
+
+	if (fd < 0)
+		fd = -errno;
+
+	return fd;
 }
 
 static void *passive_thread(void *arg)
@@ -122,8 +128,14 @@ int bench_breakpoint_thread(int argc, const char **argv)
 
 	for (i = 0; i < thread_params.nbreakpoints; i++) {
 		breakpoints[i].fd = breakpoint_setup(&breakpoints[i].watched);
-		if (breakpoints[i].fd == -1)
+
+		if (breakpoints[i].fd < 0) {
+			if (breakpoints[i].fd == -ENODEV) {
+				printf("Skipping perf bench breakpoint thread: No hardware support\n");
+				return 0;
+			}
 			exit((perror("perf_event_open"), EXIT_FAILURE));
+		}
 	}
 	gettimeofday(&start, NULL);
 	for (i = 0; i < thread_params.nparallel; i++) {
@@ -196,8 +208,14 @@ int bench_breakpoint_enable(int argc, const char **argv)
 		exit(EXIT_FAILURE);
 	}
 	fd = breakpoint_setup(&watched);
-	if (fd == -1)
+
+	if (fd < 0) {
+		if (fd == -ENODEV) {
+			printf("Skipping perf bench breakpoint enable: No hardware support\n");
+			return 0;
+		}
 		exit((perror("perf_event_open"), EXIT_FAILURE));
+	}
 	nthreads = enable_params.npassive + enable_params.nactive;
 	threads = calloc(nthreads, sizeof(threads[0]));
 	if (!threads)
diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c
index c7d207f8e13c..9e4d36486f62 100644
--- a/tools/perf/bench/pmu-scan.c
+++ b/tools/perf/bench/pmu-scan.c
@@ -57,9 +57,7 @@ static int save_result(void)
 		r->is_core = pmu->is_core;
 		r->nr_caps = pmu->nr_caps;
 
-		r->nr_aliases = 0;
-		list_for_each(list, &pmu->aliases)
-			r->nr_aliases++;
+		r->nr_aliases = perf_pmu__num_events(pmu);
 
 		r->nr_formats = 0;
 		list_for_each(list, &pmu->format)
@@ -98,9 +96,7 @@ static int check_result(bool core_only)
 			return -1;
 		}
 
-		nr = 0;
-		list_for_each(list, &pmu->aliases)
-			nr++;
+		nr = perf_pmu__num_events(pmu);
 		if (nr != r->nr_aliases) {
 			pr_err("Unmatched number of event aliases in %s: expect %d vs got %d\n",
 				pmu->name, r->nr_aliases, nr);
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
new file mode 100644
index 000000000000..914c0817fe8a
--- /dev/null
+++ b/tools/perf/bench/uprobe.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/*
+ * uprobe.c
+ *
+ * uprobe benchmarks
+ *
+ *  Copyright (C) 2023, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+#include "../perf.h"
+#include "../util/util.h"
+#include <subcmd/parse-options.h>
+#include "../builtin.h"
+#include "bench.h"
+#include <linux/compiler.h>
+#include <linux/time64.h>
+
+#include <inttypes.h>
+#include <stdio.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdlib.h>
+
+#define LOOPS_DEFAULT 1000
+static int loops = LOOPS_DEFAULT;
+
+enum bench_uprobe {
+        BENCH_UPROBE__BASELINE,
+        BENCH_UPROBE__EMPTY,
+        BENCH_UPROBE__TRACE_PRINTK,
+};
+
+static const struct option options[] = {
+	OPT_INTEGER('l', "loop",	&loops,		"Specify number of loops"),
+	OPT_END()
+};
+
+static const char * const bench_uprobe_usage[] = {
+	"perf bench uprobe <options>",
+	NULL
+};
+
+#ifdef HAVE_BPF_SKEL
+#include "bpf_skel/bench_uprobe.skel.h"
+
+#define bench_uprobe__attach_uprobe(prog) \
+	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
+							   /*pid=*/-1, \
+							   /*binary_path=*/"/lib64/libc.so.6", \
+							   /*func_offset=*/0, \
+							   /*opts=*/&uprobe_opts); \
+	if (!skel->links.prog) { \
+		err = -errno; \
+		fprintf(stderr, "Failed to attach bench uprobe \"%s\": %s\n", #prog, strerror(errno)); \
+		goto cleanup; \
+	}
+
+struct bench_uprobe_bpf *skel;
+
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench)
+{
+	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	int err;
+
+	/* Load and verify BPF application */
+	skel = bench_uprobe_bpf__open();
+	if (!skel) {
+		fprintf(stderr, "Failed to open and load uprobes bench BPF skeleton\n");
+		return -1;
+	}
+
+	err = bench_uprobe_bpf__load(skel);
+	if (err) {
+		fprintf(stderr, "Failed to load and verify BPF skeleton\n");
+		goto cleanup;
+	}
+
+	uprobe_opts.func_name = "usleep";
+	switch (bench) {
+	case BENCH_UPROBE__BASELINE:							break;
+	case BENCH_UPROBE__EMPTY:	 bench_uprobe__attach_uprobe(empty);		break;
+	case BENCH_UPROBE__TRACE_PRINTK: bench_uprobe__attach_uprobe(trace_printk);	break;
+	default:
+		fprintf(stderr, "Invalid bench: %d\n", bench);
+		goto cleanup;
+	}
+
+	return err;
+cleanup:
+	bench_uprobe_bpf__destroy(skel);
+	return err;
+}
+
+static void bench_uprobe__teardown_bpf_skel(void)
+{
+	if (skel) {
+		bench_uprobe_bpf__destroy(skel);
+		skel = NULL;
+	}
+}
+#else
+static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench __maybe_unused) { return 0; }
+static void bench_uprobe__teardown_bpf_skel(void) {};
+#endif
+
+static int bench_uprobe_format__default_fprintf(const char *name, const char *unit, u64 diff, FILE *fp)
+{
+	static u64 baseline, previous;
+	s64 diff_to_baseline = diff - baseline,
+	    diff_to_previous = diff - previous;
+	int printed = fprintf(fp, "# Executed %'d %s calls\n", loops, name);
+
+	printed += fprintf(fp, " %14s: %'" PRIu64 " %ss", "Total time", diff, unit);
+
+	if (baseline) {
+		printed += fprintf(fp, " %s%'" PRId64 " to baseline", diff_to_baseline > 0 ? "+" : "", diff_to_baseline);
+
+		if (previous != baseline)
+			fprintf(stdout, " %s%'" PRId64 " to previous", diff_to_previous > 0 ? "+" : "", diff_to_previous);
+	}
+
+	printed += fprintf(fp, "\n\n %'.3f %ss/op", (double)diff / (double)loops, unit);
+
+	if (baseline) {
+		printed += fprintf(fp, " %'.3f %ss/op to baseline", (double)diff_to_baseline / (double)loops, unit);
+
+		if (previous != baseline)
+			printed += fprintf(fp, " %'.3f %ss/op to previous", (double)diff_to_previous / (double)loops, unit);
+	} else {
+		baseline = diff;
+	}
+
+	fputc('\n', fp);
+
+	previous = diff;
+
+	return printed + 1;
+}
+
+static int bench_uprobe(int argc, const char **argv, enum bench_uprobe bench)
+{
+	const char *name = "usleep(1000)", *unit = "usec";
+	struct timespec start, end;
+	u64 diff;
+	int i;
+
+	argc = parse_options(argc, argv, options, bench_uprobe_usage, 0);
+
+	if (bench != BENCH_UPROBE__BASELINE && bench_uprobe__setup_bpf_skel(bench) < 0)
+		return 0;
+
+        clock_gettime(CLOCK_REALTIME, &start);
+
+	for (i = 0; i < loops; i++) {
+		usleep(USEC_PER_MSEC);
+	}
+
+	clock_gettime(CLOCK_REALTIME, &end);
+
+	diff = end.tv_sec * NSEC_PER_SEC + end.tv_nsec - (start.tv_sec * NSEC_PER_SEC + start.tv_nsec);
+	diff /= NSEC_PER_USEC;
+
+	switch (bench_format) {
+	case BENCH_FORMAT_DEFAULT:
+		bench_uprobe_format__default_fprintf(name, unit, diff, stdout);
+		break;
+
+	case BENCH_FORMAT_SIMPLE:
+		printf("%" PRIu64 "\n", diff);
+		break;
+
+	default:
+		/* reaching here is something of a disaster */
+		fprintf(stderr, "Unknown format:%d\n", bench_format);
+		exit(1);
+	}
+
+	if (bench != BENCH_UPROBE__BASELINE)
+		bench_uprobe__teardown_bpf_skel();
+
+	return 0;
+}
+
+int bench_uprobe_baseline(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__BASELINE);
+}
+
+int bench_uprobe_empty(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY);
+}
+
+int bench_uprobe_trace_printk(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK);
+}