EDAC/igen6: Skip absent memory controllers

Some BIOS versions may fuse off certain memory controllers and set the
registers of these absent memory controllers to ~0. The current igen6_edac
mistakenly enumerates these absent memory controllers and registers them
with the EDAC core.

Skip the absent memory controllers to avoid mistakenly enumerating them.

Signed-off-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/r/20250408132455.489046-2-qiuxu.zhuo@intel.com

diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 5807517ee32dec441db1219d1464ca70792c8e51..ec64bff8236f621a8583df433ed84c93c22b052a 100644 (file)
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -127,6 +127,7 @@
 
 static const struct res_config {
        bool machine_check;
+       /* The number of present memory controllers. */
        int num_imc;
        u32 imc_base;
        u32 cmf_base;
@@ -1201,23 +1202,21 @@ static void igen6_check(struct mem_ctl_info *mci)
                irq_work_queue(&ecclog_irq_work);
 }
 
-static int igen6_register_mci(int mc, u64 mchbar, struct pci_dev *pdev)
+/* Check whether the memory controller is absent. */
+static bool igen6_imc_absent(void __iomem *window)
+{
+       return readl(window + MAD_INTER_CHANNEL_OFFSET) == ~0;
+}
+
+static int igen6_register_mci(int mc, void __iomem *window, struct pci_dev *pdev)
 {
        struct edac_mc_layer layers[2];
        struct mem_ctl_info *mci;
        struct igen6_imc *imc;
-       void __iomem *window;
        int rc;
 
        edac_dbg(2, "\n");
 
-       mchbar += mc * MCHBAR_SIZE;
-       window = ioremap(mchbar, MCHBAR_SIZE);
-       if (!window) {
-               igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx\n", mchbar);
-               return -ENODEV;
-       }
-
        layers[0].type = EDAC_MC_LAYER_CHANNEL;
        layers[0].size = NUM_CHANNELS;
        layers[0].is_virt_csrow = false;
@@ -1283,7 +1282,6 @@ fail3:
 fail2:
        edac_mc_free(mci);
 fail:
-       iounmap(window);
        return rc;
 }
 
@@ -1309,6 +1307,56 @@ static void igen6_unregister_mcis(void)
        }
 }
 
+static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar)
+{
+       void __iomem *window;
+       int lmc, pmc, rc;
+       u64 base;
+
+       for (lmc = 0, pmc = 0; pmc < NUM_IMC; pmc++) {
+               base   = mchbar + pmc * MCHBAR_SIZE;
+               window = ioremap(base, MCHBAR_SIZE);
+               if (!window) {
+                       igen6_printk(KERN_ERR, "Failed to ioremap 0x%llx for mc%d\n", base, pmc);
+                       rc = -ENOMEM;
+                       goto out_unregister_mcis;
+               }
+
+               if (igen6_imc_absent(window)) {
+                       iounmap(window);
+                       edac_dbg(2, "Skip absent mc%d\n", pmc);
+                       continue;
+               }
+
+               rc = igen6_register_mci(lmc, window, pdev);
+               if (rc)
+                       goto out_iounmap;
+
+               /* Done, if all present MCs are detected and registered. */
+               if (++lmc >= res_cfg->num_imc)
+                       break;
+       }
+
+       if (!lmc) {
+               igen6_printk(KERN_ERR, "No mc found.\n");
+               return -ENODEV;
+       }
+
+       if (lmc < res_cfg->num_imc)
+               igen6_printk(KERN_WARNING, "Expected %d mcs, but only %d detected.",
+                            res_cfg->num_imc, lmc);
+
+       return 0;
+
+out_iounmap:
+       iounmap(window);
+
+out_unregister_mcis:
+       igen6_unregister_mcis();
+
+       return rc;
+}
+
 static int igen6_mem_slice_setup(u64 mchbar)
 {
        struct igen6_imc *imc = &igen6_pvt->imc[0];
@@ -1405,7 +1453,7 @@ static void opstate_set(const struct res_config *cfg, const struct pci_device_id
 static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
        u64 mchbar;
-       int i, rc;
+       int rc;
 
        edac_dbg(2, "\n");
 
@@ -1421,11 +1469,9 @@ static int igen6_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
        opstate_set(res_cfg, ent);
 
-       for (i = 0; i < res_cfg->num_imc; i++) {
-               rc = igen6_register_mci(i, mchbar, pdev);
-               if (rc)
-                       goto fail2;
-       }
+       rc = igen6_register_mcis(pdev, mchbar);
+       if (rc)
+               goto fail;
 
        if (res_cfg->num_imc > 1) {
                rc = igen6_mem_slice_setup(mchbar);