x86, mce: use 64bit machine check code on 32bit

The 64bit machine check code is in many ways much better than
the 32bit machine check code: it is more specification compliant,
is cleaner, only has a single code base versus one per CPU,
has better infrastructure for recovery, has a cleaner way to communicate
with user space etc. etc.

Use the 64bit code for 32bit too.

This is the second attempt to do this. There was one a couple of years
ago to unify this code for 32bit and 64bit.  Back then this ran into some
trouble with K7s and was reverted.

I believe this time the K7 problems (and some others) are addressed.
I went over the old handlers and was very careful to retain
all quirks.

But of course this needs a lot of testing on old systems. On newer
64bit capable systems I don't expect much problems because they have been
already tested with the 64bit kernel.

I made this a CONFIG for now that still allows to select the old
machine check code. This is mostly to make testing easier,
if someone runs into a problem we can ask them to try
with the CONFIG switched.

The new code is default y for more coverage.

Once there is confidence the 64bit code works well on older hardware
too the CONFIG_X86_OLD_MCE and the associated code can be easily
removed.

This causes a behaviour change for 32bit installations. They now
have to install the mcelog package to be able to log
corrected machine checks.

The 64bit machine check code only handles CPUs which support the
standard Intel machine check architecture described in the IA32 SDM.
The 32bit code has special support for some older CPUs which
have non standard machine check architectures, in particular
WinChip C3 and Intel P5.  I made those a separate CONFIG option
and kept them for now. The WinChip variant could be probably
removed without too much pain, it doesn't really do anything
interesting. P5 is also disabled by default (like it
was before) because many motherboards have it miswired, but
according to Alan Cox a few embedded setups use that one.

Forward ported/heavily changed version of old patch, original patch
included review/fixes from Thomas Gleixner, Bert Wesarg.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

1 files changed, 31 insertions, 2 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index a6efe0a2e9ae..c1c5ccd1937f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -789,6 +789,22 @@ config X86_MCE
           to disable it.  MCE support simply ignores non-MCE processors like
           the 386 and 486, so nearly everyone can say Y here.
 
+config X86_OLD_MCE
+        depends on X86_32 && X86_MCE
+        bool "Use legacy machine check code (will go away)"
+        default n
+        select X86_ANCIENT_MCE
+        ---help---
+          Use the old i386 machine check code. This is merely intended for
+          testing in a transition period. Try this if you run into any machine
+          check related software problems, but report the problem to
+          linux-kernel.  When in doubt say no.
+
+config X86_NEW_MCE
+        depends on X86_MCE
+        bool
+        default y if (!X86_OLD_MCE && X86_32) || X86_64
+
 config X86_MCE_INTEL
         def_bool y
         prompt "Intel MCE features"
@@ -805,6 +821,15 @@ config X86_MCE_AMD
            Additional support for AMD specific MCE features such as
            the DRAM Error Threshold.
 
+config X86_ANCIENT_MCE
+       def_bool n
+       depends on X86_32
+       prompt "Support for old Pentium 5 / WinChip machine checks"
+       ---help---
+         Include support for machine check handling on old Pentium 5 or WinChip
+         systems. These typically need to be enabled explicitely on the command
+         line.
+
 config X86_MCE_THRESHOLD
         depends on X86_MCE_AMD || X86_MCE_INTEL
         bool
@@ -812,7 +837,7 @@ config X86_MCE_THRESHOLD
 
 config X86_MCE_NONFATAL
         tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4"
-        depends on X86_32 && X86_MCE
+        depends on X86_OLD_MCE
         ---help---
           Enabling this feature starts a timer that triggers every 5 seconds which
           will look at the machine check registers to see if anything happened.
@@ -825,11 +850,15 @@ config X86_MCE_NONFATAL
 
 config X86_MCE_P4THERMAL
         bool "check for P4 thermal throttling interrupt."
-        depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP)
+        depends on X86_OLD_MCE && X86_MCE && (X86_UP_APIC || SMP)
         ---help---
           Enabling this feature will cause a message to be printed when the P4
           enters thermal throttling.
 
+config X86_THERMAL_VECTOR
+        def_bool y
+        depends on X86_MCE_P4THERMAL || X86_MCE_INTEL
+
 config VM86
         bool "Enable VM86 support" if EMBEDDED
         default y