x86/mce: Fix all mce notifiers to update the mce->kflags bitmask

If the handler took any action to log or deal with the error, set a bit
in mce->kflags so that the default handler on the end of the machine
check chain can see what has been done.

Get rid of NOTIFY_STOP returns. Make the EDAC and dev-mcelog handlers
skip over errors already processed by CEC.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200214222720.13168-5-tony.luck@intel.com

5 files changed, 19 insertions, 6 deletions

diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index b3135b208f9a..5860ca41185c 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1815,7 +1815,7 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 	struct mem_ctl_info *mci;
 
 	i7_dev = get_i7core_dev(mce->socketid);
-	if (!i7_dev)
+	if (!i7_dev || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
 
 	mci = i7_dev->mci;
@@ -1834,7 +1834,8 @@ static int i7core_mce_check_error(struct notifier_block *nb, unsigned long val,
 	i7core_check_error(mci, mce);
 
 	/* Advise mcelog that the errors were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block i7_mce_dec = {
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index e58644d9c92b..2b5401db56ad 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1046,6 +1046,9 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
+	if (m->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
+
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
 
 	pr_emerg(HW_ERR "CPU:%d (%x:%x:%x) MC%d_STATUS[%s|%s|%s|%s|%s",
@@ -1146,7 +1149,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
  err_code:
 	amd_decode_err_code(m->status & 0xffff);
 
-	return NOTIFY_STOP;
+	m->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block amd_mce_dec_nb = {
diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c
index bc47328eb485..1929a5dc8f94 100644
--- a/drivers/edac/pnd2_edac.c
+++ b/drivers/edac/pnd2_edac.c
@@ -1400,7 +1400,7 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
 		return NOTIFY_DONE;
 
 	mci = pnd2_mci;
-	if (!mci)
+	if (!mci || (mce->kflags & MCE_HANDLED_CEC))
 		return NOTIFY_DONE;
 
 	/*
@@ -1429,7 +1429,8 @@ static int pnd2_mce_check_error(struct notifier_block *nb, unsigned long val, vo
 	pnd2_mce_output_error(mci, mce, &daddr);
 
 	/* Advice mcelog that the error were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block pnd2_mce_dec = {
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 7d51c82be62b..f790f7d08688 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -3136,6 +3136,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
+	if (mce->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
 
 	/*
 	 * Just let mcelog handle it if the error is
@@ -3183,7 +3185,8 @@ static int sbridge_mce_check_error(struct notifier_block *nb, unsigned long val,
 	sbridge_mce_output_error(mci, mce);
 
 	/* Advice mcelog that the error were handled */
-	return NOTIFY_STOP;
+	mce->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block sbridge_mce_dec = {
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 99bbaf629b8d..6f08a12f6b11 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -577,6 +577,9 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 	if (edac_get_report_status() == EDAC_REPORTING_DISABLED)
 		return NOTIFY_DONE;
 
+	if (mce->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
+
 	/* ignore unless this is memory related with an address */
 	if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV))
 		return NOTIFY_DONE;
@@ -616,6 +619,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 	skx_mce_output_error(mci, mce, &res);
 
+	mce->kflags |= MCE_HANDLED_EDAC;
 	return NOTIFY_DONE;
 }