[PATCH v2 16/16] x86/mce: Handle AMD threshold interrupt storms

[Yazen Ghannam]

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]

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/20230616182744.17632-4-tony.luck@xxxxxxxxx
    
    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       | 18 ++++++++++++++++++
 arch/x86/kernel/cpu/mce/internal.h  |  2 ++
 arch/x86/kernel/cpu/mce/threshold.c |  3 +++
 3 files changed, 23 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 404e0c38f9d8..a2d02f0c2153 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -1218,3 +1218,21 @@ void mce_threshold_create_device(unsigned int cpu)
 		mce_threshold_vector = amd_threshold_interrupt;
 	return;
 }
+
+void mce_amd_handle_storm(unsigned int bank, bool on)
+{
+	struct threshold_bank **thr_banks = this_cpu_read(threshold_banks);
+	struct threshold_block *block, *tmp;
+	struct thresh_restart tr;
+
+	if (!thr_banks || !thr_banks[bank])
+		return;
+
+	memset(&tr, 0, sizeof(tr));
+
+	list_for_each_entry_safe(block, tmp, &thr_banks[bank]->miscj, miscj) {
+		tr.b = block;
+		tr.b->interrupt_enable = on;
+		threshold_restart_bank(&tr);
+	}
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index fe519acfafcf..9d771db2bcae 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -266,6 +266,7 @@ 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_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);
@@ -297,6 +298,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m)
 void mce_smca_cpu_init(void);
 #else
 static inline void mce_threshold_create_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;
 	}
 }
 

-- 
2.43.0