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

[Mahesh J Salgaonkar]

On 2020-04-01 13:17:41 Wed, Santosh Sivaraj wrote:
> 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 at 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
[...]
> +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;

Do you really need this check ?

> +
> +	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
> +};
> +
[...]
> -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);

Rest Looks good to me.

Reviewed-by: Mahesh Salgaonkar <mahesh at linux.ibm.com>

Thanks,
-Mahesh.

> +
>  MODULE_DEVICE_TABLE(of, papr_scm_match);
>  MODULE_LICENSE("GPL");
>  MODULE_AUTHOR("IBM Corporation");
> -- 
> 2.25.1
> 

-- 
Mahesh J Salgaonkar