[PATCH RESEND 2/2] papr/scm: Add bad memory ranges to nvdimm bad ranges

Christophe Leroy christophe.leroy at csgroup.eu
Thu Jul 9 18:17:36 AEST 2020



Le 09/07/2020 à 09:56, Santosh Sivaraj a écrit :
> Subscribe to the MCE notification and add the physical address which
> generated a memory error to nvdimm bad range.
> 
> Reviewed-by: Mahesh Salgaonkar <mahesh at linux.ibm.com>
> Signed-off-by: Santosh Sivaraj <santosh at 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 9c569078a09fd..5ebb1c797795d 100644
> --- a/arch/powerpc/platforms/pseries/papr_scm.c
> +++ b/arch/powerpc/platforms/pseries/papr_scm.c
> @@ -13,9 +13,11 @@
>   #include <linux/platform_device.h>
>   #include <linux/delay.h>
>   #include <linux/seq_buf.h>
> +#include <linux/nd.h>
>   
>   #include <asm/plpar_wrappers.h>
>   #include <asm/papr_pdsm.h>
> +#include <asm/mce.h>
>   
>   #define BIND_ANY_ADDR (~0ul)
>   
> @@ -80,6 +82,7 @@ struct papr_scm_priv {
>   	struct resource res;
>   	struct nd_region *region;
>   	struct nd_interleave_set nd_set;
> +	struct list_head region_list;
>   
>   	/* Protect dimm health data from concurrent read/writes */
>   	struct mutex health_mutex;
> @@ -91,6 +94,9 @@ struct papr_scm_priv {
>   	u64 health_bitmap;
>   };
>   
> +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];
> @@ -759,6 +765,10 @@ 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);
> @@ -766,6 +776,70 @@ err:	nvdimm_bus_unregister(p->bus);
>   	return -ENXIO;
>   }
>   
> +static 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);

Not properly aligned

> +
> +	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;

Is this local struct really worth it ? Why not use p->res below directly ?

> +
> +		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;
> @@ -866,6 +940,10 @@ 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);
> @@ -888,7 +966,25 @@ 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;

Not properly aligned.

> +}
> +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");
> 

Christophe


More information about the Linuxppc-dev mailing list