[PATCH 5/7] platform/x86/intel/bff: Reset bitfix filter when it overflows

[Tony Luck]

Get notifications for all errors logged in machine check banks. Skip any
that do not indicate a bitfix filter overflow.

Reset the bitfix filter using the CPU that reported the error to get
the right scoped machine check bank.

Co-developed-by: Qiuxu Zhuo <qiuxu.zhuo@xxxxxxxxx>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 drivers/platform/x86/intel/bff.c | 41 ++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/platform/x86/intel/bff.c b/drivers/platform/x86/intel/bff.c
index 6360bbc92347..8cc29d11e019 100644
--- a/drivers/platform/x86/intel/bff.c
+++ b/drivers/platform/x86/intel/bff.c
@@ -17,11 +17,13 @@
  */
 #define pr_fmt(fmt) "bff: " fmt
 
+#include <linux/bits.h>
 #include <linux/cpufeature.h>
 #include <linux/device-id/x86_cpu.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/printk.h>
 #include <linux/types.h>
 
@@ -32,6 +34,11 @@
 #include <asm/msr.h>
 #include <asm/msr-index.h>
 
+/* Intel bitfix filter control register defines */
+#define MSR_MC0_BFF_CTL		0x000006c0
+#define MSR_MCx_BFF_CTL(x)	(MSR_MC0_BFF_CTL + (x))
+#define  MCI_BFF_RESET		BIT_ULL(0)
+
 /* Machine check bank scope types */
 enum bff_type {
 	BFF_NONE = 0,
@@ -60,6 +67,37 @@ MODULE_DEVICE_TABLE(x86cpu, bff_cpu_ids);
 
 static const enum bff_type *bank_types;
 
+static void handle_bff(struct mce *mce)
+{
+	/* The bitfix filter overflowed, get the target CPU to reset it. */
+	if (wrmsrq_on_cpu(mce->extcpu, MSR_MCx_BFF_CTL(mce->bank), MCI_BFF_RESET))
+		pr_warn("Failed to reset bitfix filter for CPU %d Bank %d\n", mce->extcpu, mce->bank);
+}
+
+static int bff_mce_notify(struct notifier_block *nb, unsigned long val, void *data)
+{
+	struct mce *mce = (struct mce *)data;
+
+	/* TES is undefined for uncorrected errors. */
+	if (mce->status & MCI_STATUS_UC)
+		return NOTIFY_DONE;
+
+	if (MCI_STATUS_TES(mce->status) != MCI_STATUS_TES_YELLOW)
+		return NOTIFY_DONE;
+
+	if (mce->bank >= MAX_NR_BANKS || bank_types[mce->bank] == BFF_NONE)
+		return NOTIFY_DONE;
+
+	handle_bff(mce);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block bff_notifier = {
+	.notifier_call	= bff_mce_notify,
+	.priority	= MCE_PRIO_EARLY,
+};
+
 static int __init bff_init(void)
 {
 	const struct x86_cpu_id *m;
@@ -86,11 +124,14 @@ static int __init bff_init(void)
 
 	bank_types = (const enum bff_type *)m->driver_data;
 
+	mce_register_decode_chain(&bff_notifier);
+
 	return 0;
 }
 
 static void __exit bff_exit(void)
 {
+	mce_unregister_decode_chain(&bff_notifier);
 }
 
 module_init(bff_init);
-- 
2.55.0