Use X86_FEATURE_SMCA when detecting if SMCA is available instead of
directly using CPUID 0x80000007_EBX.
Signed-off-by: NYazen Ghannam <Yazen.Ghannam@amd.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1462971509-3856-7-git-send-email-bp@alien8.deSigned-off-by: NIngo Molnar <mingo@kernel.org>

For Scalable MCA enabled processors, errors are listed per IP block. And
since it is not required for an IP to map to a particular bank, we need
to use HWID and McaType values from the MCx_IPID register to figure out
which IP a given bank represents.

We also have a new bit (TCC) in the MCx_STATUS register to indicate Task
context is corrupt.

Add logic here to decode errors from all known IP blocks for Fam17h
Model 00-0fh and to print TCC errors.

[ Minor fixups. ]
Signed-off-by: NAravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1457021458-2522-3-git-send-email-Aravind.Gopalakrishnan@amd.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

This used to flush out MCEs logged during early boot and which
were in the MCA registers from a previous system run. No need
for that now, since we've moved to a genpool.
Suggested-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1439396985-12812-7-git-send-email-bp@alien8.deSigned-off-by: NIngo Molnar <mingo@kernel.org>

Use unified genpool to save Action Optional error events and put
Action Optional error handling in the same notification chain as
MCE error decoding.
Signed-off-by: NChen, Gong <gong.chen@linux.intel.com>
[ Fold in subsequent patch from Boris for early boot logging. ]
Signed-off-by: NTony Luck <tony.luck@intel.com>
[ Correct a lot. ]
Signed-off-by: NBorislav Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1439396985-12812-5-git-send-email-bp@alien8.deSigned-off-by: NIngo Molnar <mingo@kernel.org>

Currently, when decoding an MCE, we display 'CE' for a Deferred error, like
this:

[Hardware Error]: CPU:0 (15:2:0) MC4_STATUS[Over|CE|MiscV|-|AddrV|Deferred|-|UECC]: 0xdc04b00095080813

When the 'UC' bit in the MCx_STATUS register is clear, the error status
is either a Corrected error or Deferred error as determined by the
'Deferred' bit. So do not print 'CE' on a deferred error.

Refer to AMD Error Scope Hierarchy table in a newer BKDG (example:
49125_15h_Models_30h-3Fh_BKDG.pdf, section "RAS Features").
Signed-off-by: NAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Cc: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1436788382-6463-1-git-send-email-aravind.gopalakrishnan@amd.comSigned-off-by: NBorislav Petkov <bp@suse.de>

Write out MCx_ADDR into the more humanly readable "MCx Error Address"
and remove double colon in the output.

Cc: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>

Extended error code meanings are tabulated for other banks. Extend that
tradition for MC6 too.
Signed-off-by: NAravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1415122868-10969-1-git-send-email-aravind.gopalakrishnan@amd.comSigned-off-by: NBorislav Petkov <bp@suse.de>

Add decoding logic for new Fam15h model 60h.

Tested using mce_amd_inj module and works fine.
Signed-off-by: NAravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1405098795-4678-1-git-send-email-Aravind.Gopalakrishnan@amd.com
[ Boris: simplify a bit. ]
Signed-off-by: NBorislav Petkov <bp@suse.de>

295d8cda ("EDAC, MCE, AMD: Drop local coreid reporting") removed the
code snippet which used that mask but forgot to drop the mask itself. Do
that now.
Signed-off-by: NBorislav Petkov <bp@suse.de>

We want to still be able to issue some error information on systems for
which there is no decoding support (think older distro kernels here,
for example). Therefore, we allow module registration but skip the
per-family bank-specific decoders and issue the general information
only, i.e.:

[   46.822828] [Hardware Error]: Error Status: Uncorrected, software containable error.
[   46.822846] [Hardware Error]: CPU:0 (15:30:0) MC0_STATUS[-|UE|-|-|-|-|-]: 0xa000000000010f0f
[   46.822858] [Hardware Error]: cache level: L3/GEN, mem/io: GEN, mem-tx: GEN, part-proc: GEN (timed out)

with the hope that it still contains helpful useful bits.
Suggested-by: NAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Tested-by: NAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Link: http://lkml.kernel.org/r/1392659391-2411-1-git-send-email-Aravind.Gopalakrishnan@amd.comSigned-off-by: NBorislav Petkov <bp@suse.de>

Add a new error signature for Family 15h, models 30h-3fh. Patch has been
tested on Fam15h using mce_amd_inj facility and has been verified to
work correctly.
Signed-off-by: NAravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
 [ cleanup commit message and error string ]
Signed-off-by: NBorislav Petkov <bp@suse.de>

Initially, those strings describing different parts of an MCE message
were shared with amd64_edac and were therefore exported to modules.
However, all except pp_msgs are used only in one place right now so hide
them and make them static.

No functionality change.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NBorislav Petkov <bp@alien8.de>

Add MCE decoding logic for AMD Family 16h processors.

Boris:

- drop unneeded uu_msgs export
- exit early in cat_mc1_mce and save us an indentation level
Signed-off-by: NJacob Shin <jacob.shin@amd.com>
Signed-off-by: NBorislav Petkov <bp@alien8.de>

Currently only AMD Family 15h processors have special handling for MC2
errors. Since upcoming Family 16h will also need unique handling, let's
make MC2 handling part of amd_decoder_ops.
Signed-off-by: NJacob Shin <jacob.shin@amd.com>
Signed-off-by: NBorislav Petkov <bp@alien8.de>

Dump error status after decoding the error which describes the error
disposition.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Instead of starting with the error details, report the decoded, readable
error type first.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

It is very useful to have the family/model/stepping with the reported
error so dump it. This saves us asking the bug reporter about it.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Having the functional unit names in each bank decode is only misleading
as this code supports multiple families and there's no guarantee the
mapping between FUs and MCE banks will stay the same.

And also, knowing the functional unit name doesn't help much since you
end up looking at the respective BKDG anyway.

So drop all FU references and use the MC bank numbers instead.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

MCA details seldom change inbetween the models of a family so don't
be too conservative and enable decoding on everything starting from
K8 onwards. Minor adjustments can come in later but most importantly,
we have some decoding infrastructure in place for upcoming models by
default.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

... so that checkpatch can chill out.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

... and remove superfluous ErrorCodeExt check.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

Correct their formulation, replace per-family functions with a single,
unified lookup table.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

Sync with latest BKDG error types.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

This MC1 error signature is called differently now, fix it.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

Use "System Read Data Error" as a more general name for MC0 bus errors
on F15h and update some error definitions.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>
Reviewed-by: NAndreas Herrmann <andreas.herrmann3@amd.com>

No functionality change, this is done so that in a follow-on patch all
queued-up MCEs can be decoded after registering on the chain.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Drop third nbcfg argument which is old remains and not required anymore.

No functionality change.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

MCE decoding code is reporting the core which encountered the error
unconditionally now so drop this piece. Besides, it reported the
coreid in the local processor package which is not that valuable as a
datapoint.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

The MCi_STATUS bank has a AddrV bit which, when set, denotes that the
corresponding MCi_ADDR MSR contains a valid address belonging to the
MCE currently being reported. Dump it since it is definitely relevant
information.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Currently, correctable ECCs go through mcelog and do not print the scary
MCE banner. In that case, however, reporting the core where the CECC
happened is important information so dump it along with the decoded
string albeit at risk of having a minor redundancy.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Add the PCI device ids required for driver registration. Remove
pvt->ctl_name and use the family descriptor directly, instead. Then,
bump driver version and fixup its format. Finally, enable DRAM ECC
decoding on F15h.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Remove reporting of errors with UC bit set - this is done by the MCE
decoding code anyway and this driver deals with DRAM ECC errors only. UC
(NB uncorrectable error) doesn't necessarily mean it is a DRAM error.
Remove unused macros while at it.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Minor formatting fixup since the information which core was associated
with the MCE is not always valid.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Building for X86_32 produces shift count warnings, so use BIT_64() to
eliminate the warnings.

drivers/edac/mce_amd.c:778: warning: left shift count >= width of type
drivers/edac/mce_amd.c:778: warning: left shift count >= width of type
Signed-off-by: NRandy Dunlap <randy.dunlap@oracle.com>
Cc: Doug Thompson <dougthompson@xmission.com>
Cc: bluesmoke-devel@lists.sourceforge.net
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Now that everything is inplace, enable MCE decoding on F15h. Make
initcall routine a bit more readable.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Shorten up MCi_STATUS flags and add BD's new deferred and poison types.
Also, simplify formatting.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Make macro names shorter thus making code shorter and more clear.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Add decoder for FP MCEs.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

Integrate the single FIROB signature into an expanded table along with
the new BD MCE types.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>

by (almost) reusing the F10h one since the signatures are the same.
Signed-off-by: NBorislav Petkov <borislav.petkov@amd.com>