selftests/bpf: Give the 512-byte stack boundary tests a 2 KiB twin

A number of tests pin the 512-byte stack limit: accesses just past it,
call chains that add up to more than it, private stack frames and
async callbacks that exceed it. Once a JIT raises the budget to 2 KiB
those programs load, so mark them __load_if_no_large_stack() and add a
counterpart at the 2 KiB boundary under __load_if_large_stack(), so
that each kernel runs the pair that matches its budget. The
combined-depth tests that were built from frames of a few hundred
bytes now chain five 480-byte frames, which exceeds both budgets and
keeps them valid on every architecture; the number of frames reported
in the error then differs, so those messages match any count. The C
tests are limited to 512 bytes per function by the compiler, hence the
chains. The callx stack depth tests, whose callee frames add up to 608
bytes, chain four 480-byte frames behind the callx target for the same
reason.

No kernel grants the larger budget yet, so the 512-byte tests still run
everywhere and the 2 KiB twins are skipped.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://patch.msgid.link/20260924165740.2146806-16-memxor@gmail.com

1 files changed, 75 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c
index 36734683acbd..9cd874a90b39 100644
--- a/tools/testing/selftests/bpf/progs/async_stack_depth.c
+++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c
@@ -29,7 +29,49 @@ static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer)
 	return buf[255] + timer_cb(NULL, NULL, NULL);
 }
 
+/*
+ * The same shapes scaled to the 2 KiB budget of JITs with large stacks. The
+ * compiler caps a single function at 512 bytes, so the depth comes from a
+ * chain of 480-byte frames.
+ */
+__attribute__((noinline))
+static int timer_cb_large_0(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[480] = {};
+	return buf[69];
+}
+
+__attribute__((noinline))
+static int timer_cb_large_1(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[480] = {};
+	return buf[69] + timer_cb_large_0(map, key, timer);
+}
+
+__attribute__((noinline))
+static int timer_cb_large_2(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[480] = {};
+	return buf[69] + timer_cb_large_1(map, key, timer);
+}
+
+__attribute__((noinline))
+static int timer_cb_large_3(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[480] = {};
+	return buf[69] + timer_cb_large_2(map, key, timer);
+}
+
+/* 5 * 480 = 2400 bytes on its own */
+__attribute__((noinline))
+static int bad_timer_cb_large(void *map, int *key, struct bpf_timer *timer)
+{
+	volatile char buf[480] = {};
+	return buf[255] + timer_cb_large_3(map, key, timer);
+}
+
 SEC("tc")
+__load_if_no_large_stack()
 __failure __msg("combined stack size of 2 calls is")
 int pseudo_call_check(struct __sk_buff *ctx)
 {
@@ -44,7 +86,25 @@ int pseudo_call_check(struct __sk_buff *ctx)
 	return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0];
 }
 
+/* main plus the four frames under timer_cb_large_3: 2400 bytes */
 SEC("tc")
+__load_if_large_stack()
+__failure __msg("combined stack size of 5 calls is")
+int pseudo_call_check_large(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+	volatile char buf[480] = {};
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+
+	timer_cb_large_3(NULL, NULL, NULL);
+	return bpf_timer_set_callback(&elem->timer, timer_cb_large_3) + buf[0];
+}
+
+SEC("tc")
+__load_if_no_large_stack()
 __failure __msg("combined stack size of 2 calls is")
 int async_call_root_check(struct __sk_buff *ctx)
 {
@@ -58,4 +118,19 @@ int async_call_root_check(struct __sk_buff *ctx)
 	return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0];
 }
 
+SEC("tc")
+__load_if_large_stack()
+__failure __msg("combined stack size of 5 calls is")
+int async_call_root_check_large(struct __sk_buff *ctx)
+{
+	struct hmap_elem *elem;
+	volatile char buf[480] = {};
+
+	elem = bpf_map_lookup_elem(&hmap, &(int){0});
+	if (!elem)
+		return 0;
+
+	return bpf_timer_set_callback(&elem->timer, bad_timer_cb_large) + buf[0];
+}
+
 char _license[] SEC("license") = "GPL";