bpf: Avoid get_kernel_nofault() to fetch kprobe entry IP
get_kernel_nofault() (or, rather, underlying copy_from_kernel_nofault()) is not free and it does pop up in performance profiles when kprobes are heavily utilized with CONFIG_X86_KERNEL_IBT=y config. Let's avoid using it if we know that fentry_ip - 4 can't cross page boundary. We do that by masking lowest 12 bits and checking if they are Another benefit (and actually what caused a closer look at this part of code) is that now LBR record is (typically) not wasted on copy_from_kernel_nofault() call and code, which helps tools like retsnoop that grab LBR records from inside BPF code in kretprobes. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org> Link: https://lore.kernel.org/bpf/20240319212013.1046779-1-andrii@kernel.org
This commit is contained in:
parent
c29083f3f5
commit
a8497506cd
|
@ -1053,9 +1053,15 @@ static unsigned long get_entry_ip(unsigned long fentry_ip)
|
|||
{
|
||||
u32 instr;
|
||||
|
||||
/* Being extra safe in here in case entry ip is on the page-edge. */
|
||||
if (get_kernel_nofault(instr, (u32 *) fentry_ip - 1))
|
||||
return fentry_ip;
|
||||
/* We want to be extra safe in case entry ip is on the page edge,
|
||||
* but otherwise we need to avoid get_kernel_nofault()'s overhead.
|
||||
*/
|
||||
if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) {
|
||||
if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE)))
|
||||
return fentry_ip;
|
||||
} else {
|
||||
instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE);
|
||||
}
|
||||
if (is_endbr(instr))
|
||||
fentry_ip -= ENDBR_INSN_SIZE;
|
||||
return fentry_ip;
|
||||
|
|
Loading…
Reference in New Issue