* [PATCH v2] papr/scm: Add bad memory ranges to nvdimm bad ranges
@ 2020-04-16 8:24 Santosh Sivaraj
2020-05-10 13:17 ` Vaibhav Jain
0 siblings, 1 reply; 2+ messages in thread
From: Santosh Sivaraj @ 2020-04-16 8:24 UTC (permalink / raw)
To: linuxppc-dev
Cc: Oliver, Santosh Sivaraj, Mahesh Salgaonkar, Ganesh Goudar,
Aneesh Kumar K.V, Vaibhav Jain
Subscribe to the MCE notification and add the physical address which
generated a memory error to nvdimm bad range.
Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
---
arch/powerpc/platforms/pseries/papr_scm.c | 98 ++++++++++++++++++++++-
1 file changed, 97 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index f35592423380..e23fd1399d5b 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];
@@ -356,6 +362,10 @@ 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);
@@ -363,6 +373,70 @@ 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;
+
+ /*
+ * The physical address obtained here is PAGE_SIZE aligned, so get the
+ * exact address from the effective address
+ */
+ 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;
+ }
+ }
+
+ if (found)
+ papr_scm_add_badblock(p->region, p->bus, phys_addr);
+
+ mutex_unlock(&papr_ndr_lock);
+
+ return found ? NOTIFY_OK : NOTIFY_DONE;
+}
+
+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;
@@ -460,6 +534,10 @@ 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);
@@ -482,7 +560,25 @@ 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");
--
2.25.2
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH v2] papr/scm: Add bad memory ranges to nvdimm bad ranges
2020-04-16 8:24 [PATCH v2] papr/scm: Add bad memory ranges to nvdimm bad ranges Santosh Sivaraj
@ 2020-05-10 13:17 ` Vaibhav Jain
0 siblings, 0 replies; 2+ messages in thread
From: Vaibhav Jain @ 2020-05-10 13:17 UTC (permalink / raw)
To: Santosh Sivaraj, linuxppc-dev
Cc: Santosh Sivaraj, Mahesh Salgaonkar, Ganesh Goudar,
Aneesh Kumar K.V, Oliver
Hi Santosh,
Thanks for the updated patch. Minor review comment below:
Santosh Sivaraj <santosh@fossix.org> writes:
> Subscribe to the MCE notification and add the physical address which
> generated a memory error to nvdimm bad range.
>
> Reviewed-by: Mahesh Salgaonkar <mahesh@linux.ibm.com>
> Signed-off-by: Santosh Sivaraj <santosh@fossix.org>
> ---
> arch/powerpc/platforms/pseries/papr_scm.c | 98 ++++++++++++++++++++++-
> 1 file changed, 97 insertions(+), 1 deletion(-)
>
> diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
> index f35592423380..e23fd1399d5b 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];
> @@ -356,6 +362,10 @@ 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);
> @@ -363,6 +373,70 @@ err: nvdimm_bus_unregister(p->bus);
> return -ENXIO;
> }
>
> +void papr_scm_add_badblock(struct nd_region *region, struct nvdimm_bus *bus,
> + u64 phys_addr)
> +{
Should mark this function as 'static'
> + 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;
> +
> + /*
> + * The physical address obtained here is PAGE_SIZE aligned, so get the
> + * exact address from the effective address
> + */
> + 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;
> + }
> + }
> +
> + if (found)
> + papr_scm_add_badblock(p->region, p->bus, phys_addr);
> +
> + mutex_unlock(&papr_ndr_lock);
> +
> + return found ? NOTIFY_OK : NOTIFY_DONE;
> +}
> +
> +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;
> @@ -460,6 +534,10 @@ 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);
> @@ -482,7 +560,25 @@ 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");
> --
> 2.25.2
~ Vaibhav
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2020-05-10 13:20 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-04-16 8:24 [PATCH v2] papr/scm: Add bad memory ranges to nvdimm bad ranges Santosh Sivaraj
2020-05-10 13:17 ` Vaibhav Jain
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.