Linus Torvalds writes: (Summary) wrote:
Yeah, it's the "lock xadd" as suspected:
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
25: 74 1d je 0x44
(that first "nop" is a 5-byte nop that is used for the function tracing placeholder).
tracing placeholder).
And %rax contains garbage (the value "1", rather than a valid kernel pointer).
[...]
74 1dYeah, it's the "lock xadd" as suspected:
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
25: 74 1d je 0x44
(that first "nop" is a 5-byte nop that is used for the function tracing placeholder).
tracing placeholder).
And %rax contains garbage (the value "1", rather than a valid kernel pointer).