[PATCH v5 3/5] x86/mce: Introduce mce_handle_storm() to deal with begin/end of storms

From: Tony Luck
Date: Tue Apr 11 2023 - 13:39:08 EST


From: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>

Intel and AMD need to take different actions when a storm begins or
ends. Prepare for the storm code moving from intel.c into core.c by
adding a function that checks CPU vendor to pick the right action.

No functional changes.

[Tony: Changed from function pointer to regular function]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Reviewed-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
Tested-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---
arch/x86/kernel/cpu/mce/internal.h | 3 +++
arch/x86/kernel/cpu/mce/core.c | 9 +++++++++
arch/x86/kernel/cpu/mce/intel.c | 12 ++++++++++--
3 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 1e8e0706a4e8..e0d76378c116 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -41,6 +41,7 @@ struct dentry *mce_get_debugfs_dir(void);
extern mce_banks_t mce_banks_ce_disabled;

#ifdef CONFIG_X86_MCE_INTEL
+void mce_intel_handle_storm(int bank, bool on);
void cmci_disable_bank(int bank);
void intel_init_cmci(void);
void intel_init_lmce(void);
@@ -48,6 +49,7 @@ void intel_clear_lmce(void);
bool intel_filter_mce(struct mce *m);
void track_cmci_storm(int bank, u64 status);
#else
+static inline void mce_intel_handle_storm(int bank, bool on) { }
static inline void cmci_disable_bank(int bank) { }
static inline void intel_init_cmci(void) { }
static inline void intel_init_lmce(void) { }
@@ -57,6 +59,7 @@ static inline void track_cmci_storm(int bank, u64 status) { }
#endif

void mce_timer_kick(bool storm);
+void mce_handle_storm(int bank, bool on);

#ifdef CONFIG_ACPI_APEI
int apei_write_mce(struct mce *m);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 20347eb65b8b..099d8444aca4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1975,6 +1975,15 @@ static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c)
intel_clear_lmce();
}

+void mce_handle_storm(int bank, bool on)
+{
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_INTEL:
+ mce_intel_handle_storm(bank, on);
+ break;
+ }
+}
+
static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c)
{
switch (c->x86_vendor) {
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 4106877de028..a8248514a689 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -152,6 +152,14 @@ static void cmci_set_threshold(int bank, int thresh)
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}

+void mce_intel_handle_storm(int bank, bool on)
+{
+ if (on)
+ cmci_set_threshold(bank, CMCI_STORM_THRESHOLD);
+ else
+ cmci_set_threshold(bank, cmci_threshold[bank]);
+}
+
static void cmci_storm_begin(int bank)
{
__set_bit(bank, this_cpu_ptr(mce_poll_banks));
@@ -211,13 +219,13 @@ void track_cmci_storm(int bank, u64 status)
if (history & GENMASK_ULL(STORM_END_POLL_THRESHOLD - 1, 0))
return;
pr_notice("CPU%d BANK%d CMCI storm subsided\n", smp_processor_id(), bank);
- cmci_set_threshold(bank, cmci_threshold[bank]);
+ mce_handle_storm(bank, false);
cmci_storm_end(bank);
} else {
if (hweight64(history) < STORM_BEGIN_THRESHOLD)
return;
pr_notice("CPU%d BANK%d CMCI storm detected\n", smp_processor_id(), bank);
- cmci_set_threshold(bank, CMCI_STORM_THRESHOLD);
+ mce_handle_storm(bank, true);
cmci_storm_begin(bank);
}
}
--
2.39.2