selftests/bpf: Extend uprobe/uretprobe triggering benchmarks

Settle on three "flavors" of uprobe/uretprobe, installed on different
kinds of instruction: nop, push, and ret. All three are testing
different internal code paths emulating or single-stepping instructions,
so are interesting to compare and benchmark separately.

To ensure `push rbp` instruction we ensure that uprobe_target_push() is
not a leaf function by calling (global __weak) noop function and
returning something afterwards (if we don't do that, compiler will just
do a tail call optimization).

Also, we need to make sure that compiler isn't skipping frame pointer
generation, so let's add `-fno-omit-frame-pointers` to Makefile.

Just to give an idea of where we currently stand in terms of relative
performance of different uprobe/uretprobe cases vs a cheap syscall
(getpgid()) baseline, here are results from my local machine:

$ benchs/run_bench_uprobes.sh
base           :    1.561 ± 0.020M/s
uprobe-nop     :    0.947 ± 0.007M/s
uprobe-push    :    0.951 ± 0.004M/s
uprobe-ret     :    0.443 ± 0.007M/s
uretprobe-nop  :    0.471 ± 0.013M/s
uretprobe-push :    0.483 ± 0.004M/s
uretprobe-ret  :    0.306 ± 0.007M/s

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20240301214551.1686095-1-andrii@kernel.org

4 files changed, 103 insertions, 46 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 84cb5500e8ef..3b9eb40d6343 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -34,7 +34,7 @@ LIBELF_CFLAGS	:= $(shell $(PKG_CONFIG) libelf --cflags 2>/dev/null)
 LIBELF_LIBS	:= $(shell $(PKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf)
 
 CFLAGS += -g $(OPT_FLAGS) -rdynamic					\
-	  -Wall -Werror 						\
+	  -Wall -Werror -fno-omit-frame-pointer				\
 	  $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS)			\
 	  -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR)		\
 	  -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT)
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 1724d50ba942..60df99b6ac72 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -499,10 +499,12 @@ extern const struct bench bench_trig_fentry;
 extern const struct bench bench_trig_fentry_sleep;
 extern const struct bench bench_trig_fmodret;
 extern const struct bench bench_trig_uprobe_base;
-extern const struct bench bench_trig_uprobe_with_nop;
-extern const struct bench bench_trig_uretprobe_with_nop;
-extern const struct bench bench_trig_uprobe_without_nop;
-extern const struct bench bench_trig_uretprobe_without_nop;
+extern const struct bench bench_trig_uprobe_nop;
+extern const struct bench bench_trig_uretprobe_nop;
+extern const struct bench bench_trig_uprobe_push;
+extern const struct bench bench_trig_uretprobe_push;
+extern const struct bench bench_trig_uprobe_ret;
+extern const struct bench bench_trig_uretprobe_ret;
 extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
 extern const struct bench bench_pb_libbpf;
@@ -541,10 +543,12 @@ static const struct bench *benchs[] = {
 	&bench_trig_fentry_sleep,
 	&bench_trig_fmodret,
 	&bench_trig_uprobe_base,
-	&bench_trig_uprobe_with_nop,
-	&bench_trig_uretprobe_with_nop,
-	&bench_trig_uprobe_without_nop,
-	&bench_trig_uretprobe_without_nop,
+	&bench_trig_uprobe_nop,
+	&bench_trig_uretprobe_nop,
+	&bench_trig_uprobe_push,
+	&bench_trig_uretprobe_push,
+	&bench_trig_uprobe_ret,
+	&bench_trig_uretprobe_ret,
 	&bench_rb_libbpf,
 	&bench_rb_custom,
 	&bench_pb_libbpf,
diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c
index dbd362771d6a..064a1ef7a6fb 100644
--- a/tools/testing/selftests/bpf/benchs/bench_trigger.c
+++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c
@@ -113,12 +113,25 @@ static void trigger_fmodret_setup(void)
  * GCC doesn't generate stack setup preample for these functions due to them
  * having no input arguments and doing nothing in the body.
  */
-__weak void uprobe_target_with_nop(void)
+__weak void uprobe_target_nop(void)
 {
 	asm volatile ("nop");
 }
 
-__weak void uprobe_target_without_nop(void)
+__weak void opaque_noop_func(void)
+{
+}
+
+__weak int uprobe_target_push(void)
+{
+	/* overhead of function call is negligible compared to uprobe
+	 * triggering, so this shouldn't affect benchmark results much
+	 */
+	opaque_noop_func();
+	return 1;
+}
+
+__weak void uprobe_target_ret(void)
 {
 	asm volatile ("");
 }
@@ -126,27 +139,34 @@ __weak void uprobe_target_without_nop(void)
 static void *uprobe_base_producer(void *input)
 {
 	while (true) {
-		uprobe_target_with_nop();
+		uprobe_target_nop();
 		atomic_inc(&base_hits.value);
 	}
 	return NULL;
 }
 
-static void *uprobe_producer_with_nop(void *input)
+static void *uprobe_producer_nop(void *input)
+{
+	while (true)
+		uprobe_target_nop();
+	return NULL;
+}
+
+static void *uprobe_producer_push(void *input)
 {
 	while (true)
-		uprobe_target_with_nop();
+		uprobe_target_push();
 	return NULL;
 }
 
-static void *uprobe_producer_without_nop(void *input)
+static void *uprobe_producer_ret(void *input)
 {
 	while (true)
-		uprobe_target_without_nop();
+		uprobe_target_ret();
 	return NULL;
 }
 
-static void usetup(bool use_retprobe, bool use_nop)
+static void usetup(bool use_retprobe, void *target_addr)
 {
 	size_t uprobe_offset;
 	struct bpf_link *link;
@@ -159,11 +179,7 @@ static void usetup(bool use_retprobe, bool use_nop)
 		exit(1);
 	}
 
-	if (use_nop)
-		uprobe_offset = get_uprobe_offset(&uprobe_target_with_nop);
-	else
-		uprobe_offset = get_uprobe_offset(&uprobe_target_without_nop);
-
+	uprobe_offset = get_uprobe_offset(target_addr);
 	link = bpf_program__attach_uprobe(ctx.skel->progs.bench_trigger_uprobe,
 					  use_retprobe,
 					  -1 /* all PIDs */,
@@ -176,24 +192,34 @@ static void usetup(bool use_retprobe, bool use_nop)
 	ctx.skel->links.bench_trigger_uprobe = link;
 }
 
-static void uprobe_setup_with_nop(void)
+static void uprobe_setup_nop(void)
+{
+	usetup(false, &uprobe_target_nop);
+}
+
+static void uretprobe_setup_nop(void)
+{
+	usetup(true, &uprobe_target_nop);
+}
+
+static void uprobe_setup_push(void)
 {
-	usetup(false, true);
+	usetup(false, &uprobe_target_push);
 }
 
-static void uretprobe_setup_with_nop(void)
+static void uretprobe_setup_push(void)
 {
-	usetup(true, true);
+	usetup(true, &uprobe_target_push);
 }
 
-static void uprobe_setup_without_nop(void)
+static void uprobe_setup_ret(void)
 {
-	usetup(false, false);
+	usetup(false, &uprobe_target_ret);
 }
 
-static void uretprobe_setup_without_nop(void)
+static void uretprobe_setup_ret(void)
 {
-	usetup(true, false);
+	usetup(true, &uprobe_target_ret);
 }
 
 const struct bench bench_trig_base = {
@@ -274,37 +300,55 @@ const struct bench bench_trig_uprobe_base = {
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uprobe_with_nop = {
-	.name = "trig-uprobe-with-nop",
-	.setup = uprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
+const struct bench bench_trig_uprobe_nop = {
+	.name = "trig-uprobe-nop",
+	.setup = uprobe_setup_nop,
+	.producer_thread = uprobe_producer_nop,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uretprobe_nop = {
+	.name = "trig-uretprobe-nop",
+	.setup = uretprobe_setup_nop,
+	.producer_thread = uprobe_producer_nop,
+	.measure = trigger_measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_trig_uprobe_push = {
+	.name = "trig-uprobe-push",
+	.setup = uprobe_setup_push,
+	.producer_thread = uprobe_producer_push,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uretprobe_with_nop = {
-	.name = "trig-uretprobe-with-nop",
-	.setup = uretprobe_setup_with_nop,
-	.producer_thread = uprobe_producer_with_nop,
+const struct bench bench_trig_uretprobe_push = {
+	.name = "trig-uretprobe-push",
+	.setup = uretprobe_setup_push,
+	.producer_thread = uprobe_producer_push,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uprobe_without_nop = {
-	.name = "trig-uprobe-without-nop",
-	.setup = uprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
+const struct bench bench_trig_uprobe_ret = {
+	.name = "trig-uprobe-ret",
+	.setup = uprobe_setup_ret,
+	.producer_thread = uprobe_producer_ret,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
 };
 
-const struct bench bench_trig_uretprobe_without_nop = {
-	.name = "trig-uretprobe-without-nop",
-	.setup = uretprobe_setup_without_nop,
-	.producer_thread = uprobe_producer_without_nop,
+const struct bench bench_trig_uretprobe_ret = {
+	.name = "trig-uretprobe-ret",
+	.setup = uretprobe_setup_ret,
+	.producer_thread = uprobe_producer_ret,
 	.measure = trigger_measure,
 	.report_progress = hits_drops_report_progress,
 	.report_final = hits_drops_report_final,
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
new file mode 100755
index 000000000000..9bdcc74e03a4
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -eufo pipefail
+
+for i in base {uprobe,uretprobe}-{nop,push,ret}
+do
+	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
+	printf "%-15s: %s\n" $i "$summary"
+done