[PATCH bpf-next v7 6/6] selftests/bpf: Test subprogram instruction statistics

[Kumar Kartikeya Dwivedi <memxor@gmail.com>]

Add small verifier programs with deterministic instruction streams to
exercise per-subprogram self and inclusive instruction accounting. Use
assembly for normal call chains and straight-line callback bodies containing
only moves, calls, and returns or exits, so control-flow pruning does not make
the expected counts unstable. Pass callback arguments as explicit assembly
operands so the compiler keeps their registers live across the asm block.

Cover asynchronous callback attribution separately: main verification-root
totals include all callback exploration, while static and callback totals
remain local to their synchronous paths.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 .../selftests/bpf/prog_tests/verifier.c       |   2 +
 .../bpf/progs/verifier_subprog_insn_stats.c   | 228 ++++++++++++++++++
 2 files changed, 230 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/verifier_subprog_insn_stats.c

diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c
index b79bafca68f7..19d03f6d6525 100644
--- a/tools/testing/selftests/bpf/prog_tests/verifier.c
+++ b/tools/testing/selftests/bpf/prog_tests/verifier.c
@@ -100,6 +100,7 @@
 #include "verifier_stack_arg_order.skel.h"
 #include "verifier_stack_ptr.skel.h"
 #include "verifier_store_release.skel.h"
+#include "verifier_subprog_insn_stats.skel.h"
 #include "verifier_subprog_precision.skel.h"
 #include "verifier_subprog_topo.skel.h"
 #include "verifier_subreg.skel.h"
@@ -255,6 +256,7 @@ void test_verifier_stack_arg(void)            { RUN(verifier_stack_arg); }
 void test_verifier_stack_arg_order(void)      { RUN(verifier_stack_arg_order); }
 void test_verifier_stack_ptr(void)            { RUN(verifier_stack_ptr); }
 void test_verifier_store_release(void)        { RUN(verifier_store_release); }
+void test_verifier_subprog_insn_stats(void)   { RUN(verifier_subprog_insn_stats); }
 void test_verifier_subprog_precision(void)    { RUN(verifier_subprog_precision); }
 void test_verifier_subprog_topo(void)        { RUN(verifier_subprog_topo); }
 void test_verifier_subreg(void)               { RUN(verifier_subreg); }
diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_insn_stats.c b/tools/testing/selftests/bpf/progs/verifier_subprog_insn_stats.c
new file mode 100644
index 000000000000..cbf83ee9f8f2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/verifier_subprog_insn_stats.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+
+struct timer_value {
+	struct bpf_timer timer;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct timer_value);
+} timer_map SEC(".maps");
+
+SEC("?raw_tp")
+__success __log_level(4)
+__msg("subprog 0 (stats_main_only) main insns_self 2 insns_total 2 stack 0")
+__msg("processed 2 insns")
+__naked int stats_main_only(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"exit;"
+	);
+}
+
+__naked __noinline __used
+static int stats_chain_leaf(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"exit;"
+	);
+}
+
+__naked __noinline __used
+static int stats_chain_parent(void)
+{
+	asm volatile (
+		"call stats_chain_leaf;"
+		"exit;"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(4)
+/*
+ * self: 2 + 2 + 2 = 6
+ * totals: leaf 2, parent 2 + 2 = 4, main 2 + 4 = 6
+ */
+__msg("subprog 0 (stats_static_chain) main insns_self 2 insns_total 6 stack 0")
+__msg("subprog {{[0-9]+}} (stats_chain_parent) static insns_self 2 insns_total 4 stack 0")
+__msg("subprog {{[0-9]+}} (stats_chain_leaf) static insns_self 2 insns_total 2 stack 0")
+__msg("processed 6 insns")
+__naked int stats_static_chain(void)
+{
+	asm volatile (
+		"call stats_chain_parent;"
+		"exit;"
+	);
+}
+
+__naked __noinline __used
+static int stats_shared_leaf(void)
+{
+	asm volatile (
+		"r0 = 0;"
+		"exit;"
+	);
+}
+
+__naked __noinline __used
+int stats_global_root(void)
+{
+	asm volatile (
+		"call stats_shared_leaf;"
+		"exit;"
+	);
+}
+
+SEC("?raw_tp")
+__success __log_level(4)
+/*
+ * stats_shared_leaf is explored once under each independent root.
+ * self: main 3 + leaf 4 + global 2 = 9
+ * root totals: main 5 + global 4 = 9
+ */
+__msg("subprog 0 (stats_shared_roots) main insns_self 3 insns_total 5 stack 0")
+__msg("subprog {{[0-9]+}} (stats_shared_leaf) static insns_self 4 insns_total 4 stack 0")
+__msg("subprog {{[0-9]+}} (stats_global_root) global insns_self 2 insns_total 4 stack 0")
+__msg("processed 9 insns")
+__naked int stats_shared_roots(void)
+{
+	asm volatile (
+		"call stats_shared_leaf;"
+		"call stats_global_root;"
+		"exit;"
+	);
+}
+
+__noinline __used
+static int stats_async_leaf(void *map, __u32 *key, struct bpf_timer *timer)
+{
+	return 0;
+}
+
+__noinline __used
+static __u64 stats_async_schedule(struct bpf_map *map, __u32 *key,
+				  struct timer_value *value, void *ctx)
+{
+	asm volatile (
+		"r1 = %[timer];"
+		"r2 = %[stats_async_leaf];"
+		"call %[bpf_timer_set_callback];"
+		:
+		: [timer] "r" (value),
+		  __imm_ptr(stats_async_leaf),
+		  __imm(bpf_timer_set_callback)
+		: __clobber_common
+	);
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(4)
+/*
+ * self: 9 + 7 + 2 = 18
+ * totals: leaf 2, scheduler 7, main root 18
+ */
+__msg("subprog 0 (stats_async_direct) main insns_self 9 insns_total 18 stack 0")
+__msg("subprog {{[0-9]+}} (stats_async_schedule) static insns_self 7 "
+      "insns_total 7 stack 0")
+__msg("subprog {{[0-9]+}} (stats_async_leaf) static insns_self 2 "
+      "insns_total 2 stack 0")
+__msg("processed 18 insns")
+__naked int stats_async_direct(void)
+{
+	asm volatile (
+		"r1 = %[timer_map] ll;"
+		"r2 = %[stats_async_schedule];"
+		"r3 = 0;"
+		"r4 = 0;"
+		"call %[bpf_for_each_map_elem];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_addr(timer_map),
+		  __imm_ptr(stats_async_schedule),
+		  __imm(bpf_for_each_map_elem)
+		: __clobber_common
+	);
+}
+
+__noinline __used
+static int stats_async_nested_leaf(void *map, __u32 *key, struct bpf_timer *timer)
+{
+	return 0;
+}
+
+__noinline __used
+static int stats_async_outer(void *map, __u32 *key, struct bpf_timer *timer)
+{
+	asm volatile (
+		"r1 = %[timer];"
+		"r2 = %[stats_async_nested_leaf];"
+		"call %[bpf_timer_set_callback];"
+		:
+		: [timer] "r" (timer),
+		  __imm_ptr(stats_async_nested_leaf),
+		  __imm(bpf_timer_set_callback)
+		: __clobber_common
+	);
+	return 0;
+}
+
+__noinline __used
+static __u64 stats_async_nested_schedule(struct bpf_map *map, __u32 *key,
+					 struct timer_value *value, void *ctx)
+{
+	asm volatile (
+		"r1 = %[timer];"
+		"r2 = %[stats_async_outer];"
+		"call %[bpf_timer_set_callback];"
+		:
+		: [timer] "r" (value),
+		  __imm_ptr(stats_async_outer),
+		  __imm(bpf_timer_set_callback)
+		: __clobber_common
+	);
+	return 0;
+}
+
+SEC("?raw_tp")
+__success __log_level(4)
+/*
+ * self: 9 + 7 + 7 + 2 = 25
+ * totals: leaf 2, outer 7, scheduler 7, main root 25
+ */
+__msg("subprog 0 (stats_async_nested) main insns_self 9 insns_total 25 stack 0")
+__msg("subprog {{[0-9]+}} (stats_async_nested_schedule) static insns_self 7 "
+      "insns_total 7 stack 0")
+__msg("subprog {{[0-9]+}} (stats_async_outer) static insns_self 7 "
+      "insns_total 7 stack 0")
+__msg("subprog {{[0-9]+}} (stats_async_nested_leaf) static insns_self 2 "
+      "insns_total 2 stack 0")
+__msg("processed 25 insns")
+__naked int stats_async_nested(void)
+{
+	asm volatile (
+		"r1 = %[timer_map] ll;"
+		"r2 = %[stats_async_nested_schedule];"
+		"r3 = 0;"
+		"r4 = 0;"
+		"call %[bpf_for_each_map_elem];"
+		"r0 = 0;"
+		"exit;"
+		:
+		: __imm_addr(timer_map),
+		  __imm_ptr(stats_async_nested_schedule),
+		  __imm(bpf_for_each_map_elem)
+		: __clobber_common
+	);
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.53.0