The MCA threshold limit must be reset after servicing the interrupt.

Currently, the restart function doesn't have an explicit check for this.
It makes some assumptions based on the current limit and what's in the
registers. These assumptions don't always hold, so the limit won't be
reset in some cases.

Make the reset condition explicit. Either an interrupt/overflow has
occurred. Or the bank is being initialized.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Cc: stable@vger.kernel.org
---

Notes:
    v3->v4:
    * New in v4.

 arch/x86/kernel/cpu/mce/amd.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6820ebce5d46..5c4eb28c3ac9 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 
 struct thresh_restart {
 	struct threshold_block	*b;
-	int			reset;
 	int			set_lvt_off;
 	int			lvt_off;
 	u16			old_limit;
@@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr)
 
 	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
-		tr->reset = 1;	/* limit cannot be lower than err count */
-
-	if (tr->reset) {		/* reset err count and overflow bit */
-		hi =
-		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
-		    (THRESHOLD_MAX - tr->b->threshold_limit);
+	/*
+	 * Reset error count and overflow bit.
+	 * This is done during init or after handling an interrupt.
+	 */
+	if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) {
+		hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI);
+		hi |= THRESHOLD_MAX - tr->b->threshold_limit;
 	} else if (tr->old_limit) {	/* change limit w/o reset */
 		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);

-- 
2.49.0

The following commit has been merged into the ras/urgent branch of tip:

Commit-ID:     5f6e3b720694ad771911f637a51930f511427ce1
Gitweb:        https://git.kernel.org/tip/5f6e3b720694ad771911f637a51930f511427ce1
Author:        Yazen Ghannam <yazen.ghannam@amd.com>
AuthorDate:    Tue, 24 Jun 2025 14:15:59 
Committer:     Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Fri, 27 Jun 2025 13:16:23 +02:00

x86/mce/amd: Fix threshold limit reset

The MCA threshold limit must be reset after servicing the interrupt.

Currently, the restart function doesn't have an explicit check for this.  It
makes some assumptions based on the current limit and what's in the registers.
These assumptions don't always hold, so the limit won't be reset in some
cases.

Make the reset condition explicit. Either an interrupt/overflow has occurred
or the bank is being initialized.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-4-236dd74f645f@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 6820ebc..5c4eb28 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 
 struct thresh_restart {
 	struct threshold_block	*b;
-	int			reset;
 	int			set_lvt_off;
 	int			lvt_off;
 	u16			old_limit;
@@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr)
 
 	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
-		tr->reset = 1;	/* limit cannot be lower than err count */
-
-	if (tr->reset) {		/* reset err count and overflow bit */
-		hi =
-		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
-		    (THRESHOLD_MAX - tr->b->threshold_limit);
+	/*
+	 * Reset error count and overflow bit.
+	 * This is done during init or after handling an interrupt.
+	 */
+	if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) {
+		hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI);
+		hi |= THRESHOLD_MAX - tr->b->threshold_limit;
 	} else if (tr->old_limit) {	/* change limit w/o reset */
 		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);