[tip:ras/core] x86/mce/AMD, EDAC/mce_amd: Enumerate Reserved SMCA bank type

From: tip-bot for Yazen Ghannam
Date: Wed Feb 21 2018 - 13:02:15 EST


Commit-ID: 68627a697c195937672ce07683094c72b1174786
Gitweb: https://git.kernel.org/tip/68627a697c195937672ce07683094c72b1174786
Author: Yazen Ghannam <yazen.ghannam@xxxxxxx>
AuthorDate: Wed, 21 Feb 2018 11:18:58 +0100
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 21 Feb 2018 17:00:54 +0100

x86/mce/AMD, EDAC/mce_amd: Enumerate Reserved SMCA bank type

Currently, bank 4 is reserved on Fam17h, so we chose not to initialize
bank 4 in the smca_banks array. This means that when we check if a bank
is initialized, like during boot or resume, we will see that bank 4 is
not initialized and try to initialize it.

This will cause a call trace, when resuming from suspend, due to
rdmsr_*on_cpu() calls in the init path. The rdmsr_*on_cpu() calls issue
an IPI but we're running with interrupts disabled. This triggers:

WARNING: CPU: 0 PID: 11523 at kernel/smp.c:291 smp_call_function_single+0xdc/0xe0
...

Reserved banks will be read-as-zero, so their MCA_IPID register will be
zero. So, like the smca_banks array, the threshold_banks array will not
have an entry for a reserved bank since all its MCA_MISC* registers will
be zero.

Enumerate a "Reserved" bank type that matches on a HWID_MCATYPE of 0,0.

Use the "Reserved" type when checking if a bank is reserved. It's
possible that other bank numbers may be reserved on future systems.

Don't try to find the block address on reserved banks.

Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # 4.14.x
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: linux-edac <linux-edac@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20180221101900.10326-7-bp@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/include/asm/mce.h | 1 +
arch/x86/kernel/cpu/mcheck/mce_amd.c | 7 +++++++
drivers/edac/mce_amd.c | 11 +++++++----
3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c3fb9a7..8c7b3e5 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -294,6 +294,7 @@ enum smca_bank_types {
SMCA_IF, /* Instruction Fetch */
SMCA_L2_CACHE, /* L2 Cache */
SMCA_DE, /* Decoder Unit */
+ SMCA_RESERVED, /* Reserved */
SMCA_EX, /* Execution Unit */
SMCA_FP, /* Floating Point */
SMCA_L3_CACHE, /* L3 Cache */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 7fbb19c..d8ba9d0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -82,6 +82,7 @@ static struct smca_bank_name smca_names[] = {
[SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" },
[SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" },
[SMCA_DE] = { "decode_unit", "Decode Unit" },
+ [SMCA_RESERVED] = { "reserved", "Reserved" },
[SMCA_EX] = { "execution_unit", "Execution Unit" },
[SMCA_FP] = { "floating_point", "Floating Point Unit" },
[SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" },
@@ -127,6 +128,9 @@ static enum smca_bank_types smca_get_bank_type(unsigned int bank)
static struct smca_hwid smca_hwid_mcatypes[] = {
/* { bank_type, hwid_mcatype, xec_bitmap } */

+ /* Reserved type */
+ { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0), 0x0 },
+
/* ZN Core (HWID=0xB0) MCA types */
{ SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFEF },
{ SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF },
@@ -433,6 +437,9 @@ static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 hi
u32 addr = 0, offset = 0;

if (mce_flags.smca) {
+ if (smca_get_bank_type(bank) == SMCA_RESERVED)
+ return addr;
+
if (!block) {
addr = MSR_AMD64_SMCA_MCx_MISC(bank);
} else {
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index a11a671..2ab4d61 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -854,21 +854,24 @@ static void decode_mc6_mce(struct mce *m)
static void decode_smca_error(struct mce *m)
{
struct smca_hwid *hwid;
- unsigned int bank_type;
+ enum smca_bank_types bank_type;
const char *ip_name;
u8 xec = XEC(m->status, xec_mask);

if (m->bank >= ARRAY_SIZE(smca_banks))
return;

- if (x86_family(m->cpuid) >= 0x17 && m->bank == 4)
- pr_emerg(HW_ERR "Bank 4 is reserved on Fam17h.\n");
-
hwid = smca_banks[m->bank].hwid;
if (!hwid)
return;

bank_type = hwid->bank_type;
+
+ if (bank_type == SMCA_RESERVED) {
+ pr_emerg(HW_ERR "Bank %d is reserved.\n", m->bank);
+ return;
+ }
+
ip_name = smca_get_long_name(bank_type);

pr_emerg(HW_ERR "%s Extended Error Code: %d\n", ip_name, xec);