[PATCH] papr/scm: Add bad memory ranges to nvdimm bad ranges

* [PATCH] papr/scm: Add bad memory ranges to nvdimm bad ranges
@ 2020-04-01  7:47 Santosh Sivaraj
  2020-04-09  7:40 ` Santosh Sivaraj
                   ` (3 more replies)
  0 siblings, 4 replies; 10+ messages in thread
From: Santosh Sivaraj @ 2020-04-01  7:47 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Ganesh Goudar, Oliver, Mahesh Salgaonkar, Aneesh Kumar K.V

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

Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---

This patch depends on "powerpc/mce: Add MCE notification chain" [1].

Unlike the previous series[2], the patch adds badblock registration only for
pseries scm driver. Handling badblocks for baremetal (powernv) PMEM will be done
later and if possible get the badblock handling as a common code.

[1] https://lore.kernel.org/linuxppc-dev/20200330071219.12284-1-ganeshgr@linux.ibm.com/
[2] https://lore.kernel.org/linuxppc-dev/20190820023030.18232-1-santosh@fossix.org/

arch/powerpc/platforms/pseries/papr_scm.c | 96 ++++++++++++++++++++++-
 1 file changed, 95 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 0b4467e378e5..5012cbf4606e 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 region_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];
@@ -372,6 +378,10 @@ 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->region_list, &papr_nd_regions);
+	mutex_unlock(&papr_ndr_lock);
+
 	return 0;
 
 err:	nvdimm_bus_unregister(p->bus);
@@ -379,6 +389,68 @@ err:	nvdimm_bus_unregister(p->bus);
 	return -ENXIO;
 }
 
+void papr_scm_add_badblock(struct nd_region *region, struct nvdimm_bus *bus,
+			   u64 phys_addr)
+{
+	u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES);
+
+	if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) {
+		pr_err("Bad block registration for 0x%llx failed\n", phys_addr);
+		return;
+	}
+
+	pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n",
+		 aligned_addr, aligned_addr + L1_CACHE_BYTES);
+
+	nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON);
+}
+
+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;
+	bool found = false;
+
+	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;
+
+	/* mce notifier is called from a process context, so mutex is safe */
+	mutex_lock(&papr_ndr_lock);
+	list_for_each_entry(p, &papr_nd_regions, region_list) {
+		struct resource res = p->res;
+
+		if (phys_addr >= res.start && phys_addr <= res.end) {
+			found = true;
+			break;
+		}
+	}
+
+	mutex_unlock(&papr_ndr_lock);
+
+	if (!found)
+		return NOTIFY_DONE;
+
+	papr_scm_add_badblock(p->region, p->bus, phys_addr);
+
+	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;
@@ -476,6 +548,10 @@ static int papr_scm_remove(struct platform_device *pdev)
 {
 	struct papr_scm_priv *p = platform_get_drvdata(pdev);
 
+	mutex_lock(&papr_ndr_lock);
+	list_del(&(p->region_list));
+	mutex_unlock(&papr_ndr_lock);
+
 	nvdimm_bus_unregister(p->bus);
 	drc_pmem_unbind(p);
 	kfree(p->bus_desc.provider_name);
@@ -498,7 +574,25 @@ static struct platform_driver papr_scm_driver = {
 	},
 };
 
-module_platform_driver(papr_scm_driver);
+static int __init papr_scm_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&papr_scm_driver);
+	if (!ret)
+		mce_register_notifier(&mce_ue_nb);
+
+	return ret;
+}
+module_init(papr_scm_init);
+
+static void __exit papr_scm_exit(void)
+{
+	mce_unregister_notifier(&mce_ue_nb);
+	platform_driver_unregister(&papr_scm_driver);
+}
+module_exit(papr_scm_exit);
+
 MODULE_DEVICE_TABLE(of, papr_scm_match);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("IBM Corporation");
-- 
2.25.1


^ permalink raw reply related	[flat|nested] 10+ messages in thread