lkml.org 
[lkml]   [2016]   [Sep]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:ras/core] x86/mce/AMD: Read MSRs on the CPU allocating the threshold blocks
Commit-ID:  cfee4f6f0b2026380c6bc6913dbd27943df17371
Gitweb: http://git.kernel.org/tip/cfee4f6f0b2026380c6bc6913dbd27943df17371
Author: Yazen Ghannam <Yazen.Ghannam@amd.com>
AuthorDate: Mon, 12 Sep 2016 09:59:31 +0200
Committer: Thomas Gleixner <tglx@linutronix.de>
CommitDate: Tue, 13 Sep 2016 15:23:08 +0200

x86/mce/AMD: Read MSRs on the CPU allocating the threshold blocks

Scalable MCA systems allow non-core MCA banks to only be accessible by
certain CPUs. The MSRs for these banks are Read-as-Zero on other CPUs.

During allocate_threshold_blocks(), get_block_address() can be scheduled
on CPUs other than the one allocating the block. This causes the MSRs to
be read on the wrong CPU and results in incorrect behavior.

Add a @cpu parameter to get_block_address() and pass this in to ensure
that the MSRs are only read on the CPU that is allocating the block.

Signed-off-by: Yazen Ghannam <Yazen.Ghannam@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: http://lkml.kernel.org/r/1472673994-12235-2-git-send-email-Yazen.Ghannam@amd.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

---
arch/x86/kernel/cpu/mcheck/mce_amd.c | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 419e0ee..9da92fb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -293,7 +293,7 @@ static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
wrmsr(MSR_CU_DEF_ERR, low, high);
}

-static u32 get_block_address(u32 current_addr, u32 low, u32 high,
+static u32 get_block_address(unsigned int cpu, u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block)
{
u32 addr = 0, offset = 0;
@@ -309,13 +309,13 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
*/
u32 low, high;

- if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
+ if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high))
return addr;

if (!(low & MCI_CONFIG_MCAX))
return addr;

- if (!rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
+ if (!rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high) &&
(low & MASK_BLKPTR_LO))
addr = MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1);
}
@@ -421,12 +421,12 @@ out:
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
u32 low = 0, high = 0, address = 0;
- unsigned int bank, block;
+ unsigned int bank, block, cpu = smp_processor_id();
int offset = -1;

for (bank = 0; bank < mca_cfg.banks; ++bank) {
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(address, low, high, bank, block);
+ address = get_block_address(cpu, address, low, high, bank, block);
if (!address)
break;

@@ -544,15 +544,14 @@ static void amd_deferred_error_interrupt(void)
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
- int cpu = smp_processor_id();
- unsigned int bank, block;
+ unsigned int bank, block, cpu = smp_processor_id();

/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
if (!(per_cpu(bank_map, cpu) & (1 << bank)))
continue;
for (block = 0; block < NR_BLOCKS; ++block) {
- address = get_block_address(address, low, high, bank, block);
+ address = get_block_address(cpu, address, low, high, bank, block);
if (!address)
break;

@@ -774,7 +773,7 @@ static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
if (err)
goto out_free;
recurse:
- address = get_block_address(address, low, high, bank, ++block);
+ address = get_block_address(cpu, address, low, high, bank, ++block);
if (!address)
return 0;

\
 
 \ /
  Last update: 2016-09-17 09:59    [W:0.024 / U:0.732 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site