bianbu-linux-6.6/tools/testing/selftests/bpf/progs/test_global_func1.c
Yonghong Song f1f5553d91 selftests/bpf: Fix selftest test_global_funcs/global_func1 failure with latest clang
The selftest test_global_funcs/global_func1 failed with the latest clang17.
The reason is due to upstream ArgumentPromotionPass ([1]),
which may manipulate static function parameters and cause inlining
although the funciton is marked as noinline.

The original code:
  static __attribute__ ((noinline))
  int f0(int var, struct __sk_buff *skb)
  {
        return skb->len;
  }

  __attribute__ ((noinline))
  int f1(struct __sk_buff *skb)
  {
	...
        return f0(0, skb) + skb->len;
  }

  ...

  SEC("tc")
  __failure __msg("combined stack size of 4 calls is 544")
  int global_func1(struct __sk_buff *skb)
  {
        return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
  }

After ArgumentPromotionPass, the code is translated to
  static __attribute__ ((noinline))
  int f0(int var, int skb_len)
  {
        return skb_len;
  }

  __attribute__ ((noinline))
  int f1(struct __sk_buff *skb)
  {
	...
        return f0(0, skb->len) + skb->len;
  }

  ...

  SEC("tc")
  __failure __msg("combined stack size of 4 calls is 544")
  int global_func1(struct __sk_buff *skb)
  {
        return f0(1, skb->len) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
  }

And later llvm InstCombine phase recognized that f0()
simplify returns the value of the second argument and removed f0()
completely and the final code looks like:
  __attribute__ ((noinline))
  int f1(struct __sk_buff *skb)
  {
	...
        return skb->len + skb->len;
  }

  ...

  SEC("tc")
  __failure __msg("combined stack size of 4 calls is 544")
  int global_func1(struct __sk_buff *skb)
  {
        return skb->len + f1(skb) + f2(2, skb) + f3(3, skb, 4);
  }

If f0() is not inlined, the verification will fail with stack size
544 for a particular callchain. With f0() inlined, the maximum
stack size is 512 which is in the limit.

Let us add a `asm volatile ("")` in f0() to prevent ArgumentPromotionPass
from hoisting the code to its caller, and this fixed the test failure.

  [1] https://reviews.llvm.org/D148269

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20230425174744.1758515-1-yhs@fb.com
2023-04-27 14:47:16 -07:00

51 lines
984 B
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2020 Facebook */
#include <stddef.h>
#include <linux/bpf.h>
#include <bpf/bpf_helpers.h>
#include "bpf_misc.h"
#define MAX_STACK (512 - 3 * 32 + 8)
static __attribute__ ((noinline))
int f0(int var, struct __sk_buff *skb)
{
asm volatile ("");
return skb->len;
}
__attribute__ ((noinline))
int f1(struct __sk_buff *skb)
{
volatile char buf[MAX_STACK] = {};
__sink(buf[MAX_STACK - 1]);
return f0(0, skb) + skb->len;
}
int f3(int, struct __sk_buff *skb, int);
__attribute__ ((noinline))
int f2(int val, struct __sk_buff *skb)
{
return f1(skb) + f3(val, skb, 1);
}
__attribute__ ((noinline))
int f3(int val, struct __sk_buff *skb, int var)
{
volatile char buf[MAX_STACK] = {};
__sink(buf[MAX_STACK - 1]);
return skb->ifindex * val * var;
}
SEC("tc")
__failure __msg("combined stack size of 4 calls is 544")
int global_func1(struct __sk_buff *skb)
{
return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
}