> On Nov 6, 2019, at 10:21 PM, Yonghong Song <yhs@xxxxxx> wrote:
>
> With latest llvm compiler, running test_progs will have
> the following verifier failure for test_sysctl_loop1.o:
> libbpf: load bpf program failed: Permission denied
> libbpf: -- BEGIN DUMP LOG ---
> libbpf:
> invalid indirect read from stack var_off (0x0; 0xff)+196 size 7
> ...
> libbpf: -- END LOG --
> libbpf: failed to load program 'cgroup/sysctl'
> libbpf: failed to load object 'test_sysctl_loop1.o'
>
> The related bytecodes look below:
> 0000000000000308 LBB0_8:
> 97: r4 = r10
> 98: r4 += -288
> 99: r4 += r7
> 100: w8 &= 255
> 101: r1 = r10
> 102: r1 += -488
> 103: r1 += r8
> 104: r2 = 7
> 105: r3 = 0
> 106: call 106
> 107: w1 = w0
> 108: w1 += -1
> 109: if w1 > 6 goto -24 <LBB0_5>
> 110: w0 += w8
> 111: r7 += 8
> 112: w8 = w0
> 113: if r7 != 224 goto -17 <LBB0_8>
> and source code:
> for (i = 0; i < ARRAY_SIZE(tcp_mem); ++i) {
> ret = bpf_strtoul(value + off, MAX_ULONG_STR_LEN, 0,
> tcp_mem + i);
> if (ret <= 0 || ret > MAX_ULONG_STR_LEN)
> return 0;
> off += ret & MAX_ULONG_STR_LEN;
> }
> Current verifier is not able to conclude register w8 at
> insn 110 has a range of 1 to 7, which caused later
> verifier complaint.
>
> Let us workaound this issue until we found a compiler and/or
> verifier solution. The workaround in this patch is
> to make variable 'ret' volatile, which will force a reload
> and then '&' operation to ensure better value range.
> With this patch, I got:
> #3/17 test_sysctl_loop1.o:OK
>
> Signed-off-by: Yonghong Song <yhs@xxxxxx>
Could you please add the byte code after the patch to the commit
log?
Thanks,
Song
