Percpu allocator recorded the cpus which map to the first and last
units in pcpu_first/last_unit_cpu respectively and used them to
determine the address range of a chunk - e.g. it assumed that the
first unit has the lowest address in a chunk while the last unit has
the highest address.

This simply isn't true.  Groups in a chunk can have arbitrary positive
or negative offsets from the previous one and there is no guarantee
that the first unit occupies the lowest offset while the last one the
highest.

Fix it by actually comparing unit offsets to determine cpus occupying
the lowest and highest offsets.  Also, rename pcu_first/last_unit_cpu
to pcpu_low/high_unit_cpu to avoid confusion.

The chunk address range is used to flush cache on vmalloc area
map/unmap and decide whether a given address is in the first chunk by
per_cpu_ptr_to_phys() and the bug was discovered by invalid
per_cpu_ptr_to_phys() translation for crash_note.

Kudos to Dave Young for tracking down the problem.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NWANG Cong <xiyou.wangcong@gmail.com>
Reported-by: NDave Young <dyoung@redhat.com>
Tested-by: NDave Young <dyoung@redhat.com>
LKML-Reference: <4EC21F67.10905@redhat.com>
Cc: stable @kernel.org