AM3352 core hang-up

Hello,

We are encountering the core hang-up of unknown origin in our mass-produced board using TI's AM3352 and Linux Kernel 3.13.4.
Regarding the reproducibility of the test, some units had the hang-up to take about 2000 hours after a system start,
and others had about 24 hours at the earliest from a system start.
And also the core hang-ups have occurred by 21 units out of 232 units.

Here is a trace log of ETB (Embedded Trace Buffer) acquired via JTAG (CoreSight).

0284.trace_log_20180104.zip

Trace log result summary
It stops by just before the core hang-up with the following processing sequence.

1. Undefined instruction exception (VFP)
2. Processing of userland Process
3. Data abortion exception

The trace log is acquired by total of 5 times of core hang-up. It stops by the same processing in all trace log.

And from checking the last processing of all trace log; log_file, acquired at the hang-up,
it is set the value in a system control register of CP15, and it seems to make the MPU hung state.
Is there a possibility which will be in the MPU hung state by this processing?

ldr r0,0xC05E3420
ldr r0,[r0]
mcr p15,0x0,r0,c1,c0,0x0; p15,0,r0,c1,c0,0 (system control)

And so, please advise us the effective way to investigate this hang-up.

Best reards,
Takashi