[tip: ras/core] x86/mce: Check whether writes to MCA_STATUS are getting ignored

From: tip-bot2 for Smita Koralahalli
Date: Tue Jun 28 2022 - 06:17:56 EST


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

Commit-ID: 891e465a1bd8798d5f97c3afb99393f123817fef
Gitweb: https://git.kernel.org/tip/891e465a1bd8798d5f97c3afb99393f123817fef
Author: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>
AuthorDate: Mon, 27 Jun 2022 20:56:46
Committer: Borislav Petkov <bp@xxxxxxx>
CommitterDate: Tue, 28 Jun 2022 12:08:10 +02:00

x86/mce: Check whether writes to MCA_STATUS are getting ignored

The platform can sometimes - depending on its settings - cause writes
to MCA_STATUS MSRs to get ignored, regardless of HWCR[McStatusWrEn]'s
value.

For further info see

PPR for AMD Family 19h, Model 01h, Revision B1 Processors, doc ID 55898

at https://bugzilla.kernel.org/show_bug.cgi?id=206537.

Therefore, probe for ignored writes to MCA_STATUS to determine if hardware
error injection is at all possible.

[ bp: Heavily massage commit message and patch. ]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Link: https://lore.kernel.org/r/20220214233640.70510-2-Smita.KoralahalliChannabasappa@xxxxxxx
---
arch/x86/kernel/cpu/mce/inject.c | 47 +++++++++++++++++++++++++++++-
arch/x86/kernel/cpu/mce/internal.h | 2 +-
2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5fbd7ff..12cf2e7 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -33,6 +33,8 @@

#include "internal.h"

+static bool hw_injection_possible = true;
+
/*
* Collect all the MCi_XXX settings
*/
@@ -339,6 +341,8 @@ static int __set_inj(const char *buf)

for (i = 0; i < N_INJ_TYPES; i++) {
if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) {
+ if (i > SW_INJ && !hw_injection_possible)
+ continue;
inj_type = i;
return 0;
}
@@ -717,11 +721,54 @@ static void __init debugfs_init(void)
&i_mce, dfs_fls[i].fops);
}

+static void check_hw_inj_possible(void)
+{
+ int cpu;
+ u8 bank;
+
+ /*
+ * This behavior exists only on SMCA systems though its not directly
+ * related to SMCA.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_SMCA))
+ return;
+
+ cpu = get_cpu();
+
+ for (bank = 0; bank < MAX_NR_BANKS; ++bank) {
+ u64 status = MCI_STATUS_VAL, ipid;
+
+ /* Check whether bank is populated */
+ rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+ if (!ipid)
+ continue;
+
+ toggle_hw_mce_inject(cpu, true);
+
+ wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
+ rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+
+ if (!status) {
+ hw_injection_possible = false;
+ pr_warn("Platform does not allow *hardware* error injection."
+ "Try using APEI EINJ instead.\n");
+ }
+
+ toggle_hw_mce_inject(cpu, false);
+
+ break;
+ }
+
+ put_cpu();
+}
+
static int __init inject_init(void)
{
if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
return -ENOMEM;

+ check_hw_inj_possible();
+
debugfs_init();

register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify");
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 4ae0e60..7e03f5b 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -211,7 +211,7 @@ noinstr u64 mce_rdmsrl(u32 msr);

static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
{
- if (mce_flags.smca) {
+ if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
switch (reg) {
case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank);
case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank);