On Thu, Jan 4, 2018 at 1:48 PM, Pavel Tatashin
<pasha.tatashin@xxxxxxxxxx> wrote:
> [ 6.159992] Code: 89 83 78 06 01 00 b8 01 00 00 00 5b 41 5c 41 5d
> 5d c3 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 31 d2 48 8b 87 c8 00 00
> 00 48 89 e5 <f0> 0f c1 50 0c 89 97 d0 00 00 00 83 e2 01 b8 01 00 00 00
> 74 1d
Yeah, it's the "lock xadd" as suspected:
0: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1)
5: 55 push %rbp
6: 31 d2 xor %edx,%edx
8: 48 8b 87 c8 00 00 00 mov 0xc8(%rdi),%rax
f: 48 89 e5 mov %rsp,%rbp
12:* f0 0f c1 50 0c lock xadd %edx,0xc(%rax)
<-- trapping instruction
17: 89 97 d0 00 00 00 mov %edx,0xd0(%rdi)
1d: 83 e2 01 and $0x1,%edx
20: b8 01 00 00 00 mov $0x1,%eax
25: 74 1d je 0x44
(that first "nop" is a 5-byte nop that is used for the function
tracing placeholder).
And %rax contains garbage (the value "1", rather than a valid kernel pointer).
Sadly, I have no idea about how that garbage came about.
Linus