[PATCH v2 5/7] EDAC/intel-bff: Reset bitfix filter when it overflows

[Tony Luck <tony.luck@intel.com>]

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

Machine check banks are scoped to a hardware unit, so the reset has to be
issued from a CPU within that unit. Use the CPU that reported the error.

Co-developed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 drivers/edac/intel-bff.c | 48 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/drivers/edac/intel-bff.c b/drivers/edac/intel-bff.c
index f70c5e697dae..c46d5255f34b 100644
--- a/drivers/edac/intel-bff.c
+++ b/drivers/edac/intel-bff.c
@@ -17,11 +17,14 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitfield.h>
+#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 +35,11 @@
 #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 hardware unit types */
 enum bff_bank_type {
 	BFF_BANK_NONE = 0,
@@ -64,6 +72,38 @@ MODULE_DEVICE_TABLE(x86cpu, bff_cpu_ids);
 
 static const enum bff_bank_type *bff_bank_types;
 
+static void bff_reset_and_report(struct mce *mce)
+{
+	/* Reset bitfix filter using the CPU that logged the yellow status */
+	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 = 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 || bff_bank_types[mce->bank] == BFF_BANK_NONE)
+		return NOTIFY_DONE;
+
+	bff_reset_and_report(mce);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block bff_notifier = {
+	.notifier_call	= bff_mce_notify,
+	.priority	= MCE_PRIO_EDAC,
+};
+
 static int __init bff_init(void)
 {
 	const struct x86_cpu_id *m;
@@ -89,10 +129,18 @@ static int __init bff_init(void)
 
 	bff_bank_types = (const enum bff_bank_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);
+module_exit(bff_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Tony Luck");
-- 
2.55.0