timekeeping: Adjust the leap state for the correct auxiliary timekeeper

In the Linux kernel, the following vulnerability has been resolved:

timekeeping: Adjust the leap state for the correct auxiliary timekeeper

When __do_ajdtimex() was introduced to handle adjtimex for any

timekeeper, this reference to tk_core was not updated. When called on an

auxiliary timekeeper, the core timekeeper would be updated incorrectly.

This gets caught by the lock debugging diagnostics because the

timekeepers sequence lock gets written to without holding its

associated spinlock:

WARNING: include/linux/seqlock.h:226 at __do_adjtimex+0x394/0x3b0, CPU#2: test/125

aux_clock_adj (kernel/time/timekeeping.c:2979)

__do_sys_clock_adjtime (kernel/time/posix-timers.c:1161 kernel/time/posix-timers.c:1173)

do_syscall_64 (arch/x86/entry/syscall_64.c:63 (discriminator 1) arch/x86/entry/syscall_64.c:94 (discriminator 1))

entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:131)

Update the correct auxiliary timekeeper.