[tip: ras/core] x86/mce/amd: Init thresholding machinery only on relevant vendors

From: tip-bot2 for Thomas Gleixner
Date: Wed Apr 15 2020 - 05:52:00 EST


The following commit has been merged into the ras/core branch of tip:

Commit-ID: c9bf318f77b3a78483e656e609d005c52aadc86d
Gitweb: https://git.kernel.org/tip/c9bf318f77b3a78483e656e609d005c52aadc86d
Author: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
AuthorDate: Wed, 12 Feb 2020 00:34:01 +01:00
Committer: Borislav Petkov <bp@xxxxxxx>
CommitterDate: Tue, 14 Apr 2020 15:47:11 +02:00

x86/mce/amd: Init thresholding machinery only on relevant vendors

... and not unconditionally.

[ bp: Add a new vendor_flags bit for that. ]

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Link: https://lkml.kernel.org/r/20200403161943.1458-3-bp@xxxxxxxxx
---
arch/x86/kernel/cpu/mce/amd.c | 12 ++++++++++--
arch/x86/kernel/cpu/mce/core.c | 1 +
arch/x86/kernel/cpu/mce/internal.h | 9 ++++++---
3 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 477cf77..c3b3326 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1442,15 +1442,20 @@ free_out:

int mce_threshold_remove_device(unsigned int cpu)
{
+ struct threshold_bank **bp = this_cpu_read(threshold_banks);
unsigned int bank;

+ if (!bp)
+ return 0;
+
for (bank = 0; bank < per_cpu(mce_num_banks, cpu); ++bank) {
if (!(per_cpu(bank_map, cpu) & (1 << bank)))
continue;
threshold_remove_bank(cpu, bank);
}
- kfree(per_cpu(threshold_banks, cpu));
- per_cpu(threshold_banks, cpu) = NULL;
+ /* Clear the pointer before freeing the memory */
+ this_cpu_write(threshold_banks, NULL);
+ kfree(bp);
return 0;
}

@@ -1461,6 +1466,9 @@ int mce_threshold_create_device(unsigned int cpu)
struct threshold_bank **bp;
int err = 0;

+ if (!mce_flags.amd_threshold)
+ return 0;
+
bp = per_cpu(threshold_banks, cpu);
if (bp)
return 0;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 54165f3..43ca91e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1756,6 +1756,7 @@ static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c)
mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV);
mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR);
mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA);
+ mce_flags.amd_threshold = 1;

if (mce_flags.smca) {
msr_ops.ctl = smca_ctl_reg;
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 3b00817..74a0182 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -148,7 +148,7 @@ struct mce_vendor_flags {
* Recovery. It indicates support for data poisoning in HW and deferred
* error interrupts.
*/
- succor : 1,
+ succor : 1,

/*
* (AMD) SMCA: This bit indicates support for Scalable MCA which expands
@@ -156,9 +156,12 @@ struct mce_vendor_flags {
* banks. Also, to accommodate the new banks and registers, the MCA
* register space is moved to a new MSR range.
*/
- smca : 1,
+ smca : 1,

- __reserved_0 : 61;
+ /* AMD-style error thresholding banks present. */
+ amd_threshold : 1,
+
+ __reserved_0 : 60;
};

extern struct mce_vendor_flags mce_flags;