I don't think this is userspace visible but SIGKILL does not have
any si_codes that use the fault member of the siginfo union. Correct
this the simple way and call force_sig instead of force_sig_fault when
the signal is SIGKILL.
The two know places where synchronous SIGKILL are generated are
do_bad_area and fpsimd_save. The call paths to force_sig_fault are:
do_bad_area
arm64_force_sig_fault
force_sig_fault
force_signal_inject
arm64_notify_die
arm64_force_sig_fault
force_sig_fault
Which means correcting this in arm64_force_sig_fault is enough
to ensure the arm64 code is not misusing the generic code, which
could lead to maintenance problems later.
Cc: stable@xxxxxxxxxxxxxxx
Cc: Dave Martin <Dave.Martin@xxxxxxx>
Cc: James Morse <james.morse@xxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Fixes: af40ff687bc9 ("arm64: signal: Ensure si_code is valid for all fault signals")
Signed-off-by: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
---
I have also made the corresponding changes to:
09/26 signal: Remove task parameter from force_sig
21/26 signal: Remove the task parameter from force_sig_fault
But I will leave off reposting those as for now as the changes
are obvious.
arch/arm64/kernel/traps.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index ade32046f3fe..e45d5b440fb1 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -256,7 +256,10 @@ void arm64_force_sig_fault(int signo, int code, void __user *addr,
const char *str)
{
arm64_show_signal(signo, str);
- force_sig_fault(signo, code, addr, current);
+ if (signo == SIGKILL)
+ force_sig(SIGKILL, current);
+ else
+ force_sig_fault(signo, code, addr, current);
}
void arm64_force_sig_mceerr(int code, void __user *addr, short lsb,
--
2.21.0.dirty
