Merge tag 'edac_updates_for_v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras

Pull intel EDAC fixes from Tony Luck:

 - Old igen6 driver could lose pending events during initialization

 - Sapphire Rapids workstations have fewer memory controllers than their
   bigger siblings. This confused the driver.

* tag 'edac_updates_for_v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras:
  EDAC/igen6: Fix the issue of no error events
  EDAC/i10nm: Skip the absent memory controllers

2 files changed, 53 insertions, 9 deletions

diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index 5abf997ca7c1..2b83d6de9352 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -658,13 +658,49 @@ static struct pci_dev *get_ddr_munit(struct skx_dev *d, int i, u32 *offset, unsi
 	return mdev;
 }
 
+/**
+ * i10nm_imc_absent() - Check whether the memory controller @imc is absent
+ *
+ * @imc    : The pointer to the structure of memory controller EDAC device.
+ *
+ * RETURNS : true if the memory controller EDAC device is absent, false otherwise.
+ */
+static bool i10nm_imc_absent(struct skx_imc *imc)
+{
+	u32 mcmtr;
+	int i;
+
+	switch (res_cfg->type) {
+	case SPR:
+		for (i = 0; i < res_cfg->ddr_chan_num; i++) {
+			mcmtr = I10NM_GET_MCMTR(imc, i);
+			edac_dbg(1, "ch%d mcmtr reg %x\n", i, mcmtr);
+			if (mcmtr != ~0)
+				return false;
+		}
+
+		/*
+		 * Some workstations' absent memory controllers still
+		 * appear as PCIe devices, misleading the EDAC driver.
+		 * By observing that the MMIO registers of these absent
+		 * memory controllers consistently hold the value of ~0.
+		 *
+		 * We identify a memory controller as absent by checking
+		 * if its MMIO register "mcmtr" == ~0 in all its channels.
+		 */
+		return true;
+	default:
+		return false;
+	}
+}
+
 static int i10nm_get_ddr_munits(void)
 {
 	struct pci_dev *mdev;
 	void __iomem *mbase;
 	unsigned long size;
 	struct skx_dev *d;
-	int i, j = 0;
+	int i, lmc, j = 0;
 	u32 reg, off;
 	u64 base;
 
@@ -690,7 +726,7 @@ static int i10nm_get_ddr_munits(void)
 		edac_dbg(2, "socket%d mmio base 0x%llx (reg 0x%x)\n",
 			 j++, base, reg);
 
-		for (i = 0; i < res_cfg->ddr_imc_num; i++) {
+		for (lmc = 0, i = 0; i < res_cfg->ddr_imc_num; i++) {
 			mdev = get_ddr_munit(d, i, &off, &size);
 
 			if (i == 0 && !mdev) {
@@ -700,8 +736,6 @@ static int i10nm_get_ddr_munits(void)
 			if (!mdev)
 				continue;
 
-			d->imc[i].mdev = mdev;
-
 			edac_dbg(2, "mc%d mmio base 0x%llx size 0x%lx (reg 0x%x)\n",
 				 i, base + off, size, reg);
 
@@ -712,7 +746,17 @@ static int i10nm_get_ddr_munits(void)
 				return -ENODEV;
 			}
 
-			d->imc[i].mbase = mbase;
+			d->imc[lmc].mbase = mbase;
+			if (i10nm_imc_absent(&d->imc[lmc])) {
+				pci_dev_put(mdev);
+				iounmap(mbase);
+				d->imc[lmc].mbase = NULL;
+				edac_dbg(2, "Skip absent mc%d\n", i);
+				continue;
+			} else {
+				d->imc[lmc].mdev = mdev;
+				lmc++;
+			}
 		}
 	}
 
diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 544dd19072ea..1a18693294db 100644
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -27,7 +27,7 @@
 #include "edac_mc.h"
 #include "edac_module.h"
 
-#define IGEN6_REVISION	"v2.5"
+#define IGEN6_REVISION	"v2.5.1"
 
 #define EDAC_MOD_STR	"igen6_edac"
 #define IGEN6_NMI_NAME	"igen6_ibecc"
@@ -1216,9 +1216,6 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&ecclog_work, ecclog_work_cb);
 	init_irq_work(&ecclog_irq_work, ecclog_irq_work_cb);
 
-	/* Check if any pending errors before registering the NMI handler */
-	ecclog_handler();
-
 	rc = register_err_handler();
 	if (rc)
 		goto fail3;
@@ -1230,6 +1227,9 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto fail4;
 	}
 
+	/* Check if any pending errors before/during the registration of the error handler */
+	ecclog_handler();
+
 	igen6_debug_setup();
 	return 0;
 fail4: