From: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>
Extend the logic of handling CMCI storms to AMD threshold interrupts.
Rely on the similar approach as of Intel's CMCI to mitigate storms per
CPU and per bank. But, unlike CMCI, do not set thresholds and reduce
interrupt rate on a storm. Rather, disable the interrupt on the
corresponding CPU and bank. Re-enable back the interrupts if enough
consecutive polls of the bank show no corrected errors (30, as
programmed by Intel).
Turning off the threshold interrupts would be a better solution on AMD
systems as other error severities will still be handled even if the
threshold interrupts are disabled.
[Tony: Small tweak because mce_handle_storm() isn't a pointer now]
[Yazen: Rebase and simplify]
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@xxxxxxxxx>
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@xxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---
Notes:
Link:
https://lore.kernel.org/r/20250624-wip-mca-updates-v4-21-236dd74f645f@xxxxxxx
v4->v5:
* No change.
v3->v4:
* Simplify based on new patches in this set.
v2->v3:
* Add tag from Qiuxu.
v1->v2:
* New in v2, but based on older patch.
* Rebased on current set and simplified.
* Kept old tags.
arch/x86/kernel/cpu/mce/amd.c | 5 +++++
arch/x86/kernel/cpu/mce/internal.h | 2 ++
arch/x86/kernel/cpu/mce/threshold.c | 3 +++
3 files changed, 10 insertions(+)
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 0c8ec431ebd2..d7b226a68ed3 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -832,6 +832,11 @@ static void amd_deferred_error_interrupt(void)
machine_check_poll(MCP_TIMESTAMP, &this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
}
+void mce_amd_handle_storm(unsigned int bank, bool on)
+{
+ threshold_restart_bank(bank, on);
+}
+
void amd_reset_thr_limit(unsigned int bank)
{
threshold_restart_bank(bank, true);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index e25ad0c005d5..09ebcf82df93 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -267,6 +267,7 @@ void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m);
#ifdef CONFIG_X86_MCE_AMD
void mce_threshold_create_device(unsigned int cpu);
void mce_threshold_remove_device(unsigned int cpu);
+void mce_amd_handle_storm(unsigned int bank, bool on);
extern bool amd_filter_mce(struct mce *m);
bool amd_mce_usable_address(struct mce *m);
void amd_reset_thr_limit(unsigned int bank);
@@ -299,6 +300,7 @@ void smca_bsp_init(void);
#else
static inline void mce_threshold_create_device(unsigned int cpu) { }
static inline void mce_threshold_remove_device(unsigned int cpu) { }
+static inline void mce_amd_handle_storm(unsigned int bank, bool on) { }
static inline bool amd_filter_mce(struct mce *m) { return false; }
static inline bool amd_mce_usable_address(struct mce *m) { return false; }
static inline void amd_reset_thr_limit(unsigned int bank) { }
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index f4a007616468..45144598ec74 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -63,6 +63,9 @@ static void mce_handle_storm(unsigned int bank, bool on)
case X86_VENDOR_INTEL:
mce_intel_handle_storm(bank, on);
break;
+ case X86_VENDOR_AMD:
+ mce_amd_handle_storm(bank, on);
+ break;
}
}
--
2.51.0
