x86: Ignore NMIs that come in during early boot
authorH. Peter Anvin <hpa@linux.intel.com>
Fri, 7 Mar 2014 23:05:20 +0000 (15:05 -0800)
committerH. Peter Anvin <hpa@linux.intel.com>
Fri, 7 Mar 2014 23:08:14 +0000 (15:08 -0800)
commit5fa10196bdb5f190f595ebd048490ee52dddea0f
tree8cf99655866414d49f4529ae591965d259e1beb8
parentd4078e232267ff53f3b030b9698a3c001db4dbec
x86: Ignore NMIs that come in during early boot

Don Zickus reports:

A customer generated an external NMI using their iLO to test kdump
worked.  Unfortunately, the machine hung.  Disabling the nmi_watchdog
made things work.

I speculated the external NMI fired, caused the machine to panic (as
expected) and the perf NMI from the watchdog came in and was latched.
My guess was this somehow caused the hang.

   ----

It appears that the latched NMI stays latched until the early page
table generation on 64 bits, which causes exceptions to happen which
end in IRET, which re-enable NMI.  Therefore, ignore NMIs that come in
during early execution, until we have proper exception handling.

Reported-and-tested-by: Don Zickus <dzickus@redhat.com>
Link: http://lkml.kernel.org/r/1394221143-29713-1-git-send-email-dzickus@redhat.com
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: <stable@vger.kernel.org> # v3.5+, older with some backport effort
arch/x86/kernel/head_32.S
arch/x86/kernel/head_64.S