Subscribe to the MCE notification and add the physical address which
generated a memory error to nvdimm bad range.

Signed-off-by: Santosh Sivaraj <sant...@fossix.org>
---
 arch/powerpc/platforms/pseries/papr_scm.c | 65 +++++++++++++++++++++++
 1 file changed, 65 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c 
b/arch/powerpc/platforms/pseries/papr_scm.c
index a5ac371a3f06..4d25c98a9835 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -12,6 +12,8 @@
 #include <linux/libnvdimm.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
+#include <linux/nd.h>
+#include <asm/mce.h>
 
 #include <asm/plpar_wrappers.h>
 
@@ -39,8 +41,12 @@ struct papr_scm_priv {
        struct resource res;
        struct nd_region *region;
        struct nd_interleave_set nd_set;
+       struct list_head list;
 };
 
+LIST_HEAD(papr_nd_regions);
+DEFINE_MUTEX(papr_ndr_lock);
+
 static int drc_pmem_bind(struct papr_scm_priv *p)
 {
        unsigned long ret[PLPAR_HCALL_BUFSIZE];
@@ -364,6 +370,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
                dev_info(dev, "Region registered with target node %d and online 
node %d",
                         target_nid, online_nid);
 
+       mutex_lock(&papr_ndr_lock);
+       list_add_tail(&p->list, &papr_nd_regions);
+       mutex_unlock(&papr_ndr_lock);
+
        return 0;
 
 err:   nvdimm_bus_unregister(p->bus);
@@ -371,6 +381,60 @@ err:       nvdimm_bus_unregister(p->bus);
        return -ENXIO;
 }
 
+static int handle_mce_ue(struct notifier_block *nb, unsigned long val,
+                        void *data)
+{
+       struct machine_check_event *evt = data;
+       struct papr_scm_priv *p;
+       u64 phys_addr;
+
+       if (evt->error_type != MCE_ERROR_TYPE_UE)
+               return NOTIFY_DONE;
+
+       if (list_empty(&papr_nd_regions))
+               return NOTIFY_DONE;
+
+       phys_addr = evt->u.ue_error.physical_address +
+               (evt->u.ue_error.effective_address & ~PAGE_MASK);
+
+       if (!evt->u.ue_error.physical_address_provided ||
+           !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT)))
+               return NOTIFY_DONE;
+
+       mutex_lock(&papr_ndr_lock);
+       list_for_each_entry(p, &papr_nd_regions, list) {
+               struct resource res = p->res;
+               u64 aligned_addr;
+
+               if (res.start > phys_addr)
+                       continue;
+
+               if (res.end < phys_addr)
+                       continue;
+
+               aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);
+               pr_debug("Add memory range (0x%llx -- 0x%llx) as bad range\n",
+                        aligned_addr, aligned_addr + L1_CACHE_BYTES);
+
+               if (nvdimm_bus_add_badrange(p->bus,
+                                           aligned_addr, L1_CACHE_BYTES))
+                       pr_warn("Failed to add bad range (0x%llx -- 0x%llx)\n",
+                               aligned_addr, aligned_addr + L1_CACHE_BYTES);
+
+               nvdimm_region_notify(p->region,
+                                    NVDIMM_REVALIDATE_POISON);
+
+               break;
+       }
+       mutex_unlock(&papr_ndr_lock);
+
+       return NOTIFY_OK;
+}
+
+static struct notifier_block mce_ue_nb = {
+       .notifier_call = handle_mce_ue
+};
+
 static int papr_scm_probe(struct platform_device *pdev)
 {
        struct device_node *dn = pdev->dev.of_node;
@@ -456,6 +520,7 @@ static int papr_scm_probe(struct platform_device *pdev)
                goto err2;
 
        platform_set_drvdata(pdev, p);
+       mce_register_notifier(&mce_ue_nb);
 
        return 0;
 
-- 
2.21.0

Reply via email to