Merge tag 'edac_urgent_for_v6.15_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/rasHEADmaster

Pull EDAC fixes from Borislav Petkov:
 "Two fixes to the AMD translation library for the MI300 side of things:

   - Use the row[13] bit when calculating the memory row to retire

   - Mask the physical row address in order to avoid creating duplicate
     error records"

* tag 'edac_urgent_for_v6.15_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  RAS/AMD/FMPM: Get masked address
  RAS/AMD/ATL: Include row[13] bit in row retirement

1 files changed, 8 insertions, 1 deletions

diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index 90de737fbc90..8877c6ff64c4 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -250,6 +250,13 @@ static bool rec_has_valid_entries(struct fru_rec *rec)
 	return true;
 }
 
+/*
+ * Row retirement is done on MI300 systems, and some bits are 'don't
+ * care' for comparing addresses with unique physical rows.  This
+ * includes all column bits and the row[13] bit.
+ */
+#define MASK_ADDR(addr)	((addr) & ~(MI300_UMC_MCA_ROW13 | MI300_UMC_MCA_COL))
+
 static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_desc *new)
 {
 	/*
@@ -258,7 +265,7 @@ static bool fpds_equal(struct cper_fru_poison_desc *old, struct cper_fru_poison_
 	 *
 	 * Also, order the checks from most->least likely to fail to shortcut the code.
 	 */
-	if (old->addr != new->addr)
+	if (MASK_ADDR(old->addr) != MASK_ADDR(new->addr))
 		return false;
 
 	if (old->hw_id != new->hw_id)