On Mon, Jul 18, 2016 at 5:44 PM, Vishal Verma <vishal.l.verma@xxxxxxxxx> wrote:
> Normally, an ARS (Address Range Scrub) only happens at
> boot/initialization time. There can however arise situations where a
> bus-wide rescan is needed - notably, in the case of discovering a latent
> media error, we should do a full rescan to figure out what other sectors
> are bad, and thus potentially avoid triggering an mce on them in the
> future. Also provide a sysfs trigger to start a bus-wide rescan.
>
> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
> Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> Cc: <linux-acpi@xxxxxxxxxxxxxxx>
> Cc: <linux-nvdimm@xxxxxxxxxxxx>
> Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
> ---
> drivers/acpi/nfit.c | 36 ++++++++++++++++++++++++++++++++----
> drivers/acpi/nfit.h | 1 +
> drivers/nvdimm/core.c | 17 +++++++++++++++++
> include/linux/libnvdimm.h | 1 +
> 4 files changed, 51 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
> index ac6ddcc0..def9505 100644
> --- a/drivers/acpi/nfit.c
> +++ b/drivers/acpi/nfit.c
> @@ -2138,8 +2138,9 @@ static void acpi_nfit_async_scrub(struct acpi_nfit_desc *acpi_desc,
> unsigned int tmo = scrub_timeout;
> int rc;
>
> - if (nfit_spa->ars_done || !nfit_spa->nd_region)
> - return;
> + if (!nfit_spa->ars_rescan)
> + if (nfit_spa->ars_done || !nfit_spa->nd_region)
> + return;
Do we need a new flag? Why not just clear ->ars_done?
>
> rc = ars_start(acpi_desc, nfit_spa);
> /*
> @@ -2227,7 +2228,9 @@ static void acpi_nfit_scrub(struct work_struct *work)
> * firmware initiated scrubs to complete and then we go search for the
> * affected spa regions to mark them scanned. In the second phase we
> * initiate a directed scrub for every range that was not scrubbed in
> - * phase 1.
> + * phase 1. If we're called for a 'rescan', we harmlessly pass through
> + * the first phase, but really only care about running phase 2, where
> + * regions can be notified of new poison.
> */
I don't think we need to distinguish the initial scan case from the
re-scan case in acpi_nfit_scrub(). Whether it's a scan or a re-scan
doesn't matter to acpi_nfit_scrub().
>
> /* process platform firmware initiated scrubs */
> @@ -2336,8 +2339,10 @@ static void acpi_nfit_scrub(struct work_struct *work)
> acpi_nfit_register_region(acpi_desc, nfit_spa);
> }
>
> - list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
> + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
> acpi_nfit_async_scrub(acpi_desc, nfit_spa);
> + nfit_spa->ars_rescan = 0;
> + }
> mutex_unlock(&acpi_desc->init_mutex);
> }
>
> @@ -2495,6 +2500,28 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
> return 0;
> }
>
> +static int acpi_nfit_ars_rescan(struct nvdimm_bus_descriptor *nd_desc)
> +{
> + struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
> + struct device *dev = acpi_desc->dev;
> + struct nfit_spa *nfit_spa;
> +
> + if (work_busy(&acpi_desc->work))
> + return -EBUSY;
How does userspace figure out when the queue is not busy? See below
in the notes about the ars_rescan attribute.
> +
> + list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
> + struct acpi_nfit_system_address *spa = nfit_spa->spa;
> +
> + if (nfit_spa_type(spa) != NFIT_SPA_PM)
> + continue;
> +
> + nfit_spa->ars_rescan = 1;
> + }
> + queue_work(nfit_wq, &acpi_desc->work);
> + dev_info(dev, "%s: ars_rescan triggered\n", __func__);
> + return 0;
> +}
> +
> void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
> {
> struct nvdimm_bus_descriptor *nd_desc;
> @@ -2507,6 +2534,7 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
> nd_desc->ndctl = acpi_nfit_ctl;
> nd_desc->flush_probe = acpi_nfit_flush_probe;
> nd_desc->clear_to_send = acpi_nfit_clear_to_send;
> + nd_desc->ars_rescan = acpi_nfit_ars_rescan;
> nd_desc->attr_groups = acpi_nfit_attribute_groups;
>
> INIT_LIST_HEAD(&acpi_desc->spa_maps);
> diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
> index 02b9ea1..db95c5d 100644
> --- a/drivers/acpi/nfit.h
> +++ b/drivers/acpi/nfit.h
> @@ -78,6 +78,7 @@ struct nfit_spa {
> struct list_head list;
> struct nd_region *nd_region;
> unsigned int ars_done:1;
> + unsigned int ars_rescan:1;
> u32 clear_err_unit;
> u32 max_ars;
> };
> diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
> index be89764..54f6fd5 100644
> --- a/drivers/nvdimm/core.c
> +++ b/drivers/nvdimm/core.c
> @@ -313,10 +313,27 @@ static ssize_t wait_probe_show(struct device *dev,
> }
> static DEVICE_ATTR_RO(wait_probe);
>
> +static ssize_t ars_rescan_store(struct device *dev,
> + struct device_attribute *attr, const char *buf, size_t size)
> +{
> + struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
> + struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
> + int rc;
> +
> + if (nd_desc->ars_rescan) {
> + rc = nd_desc->ars_rescan(nd_desc);
> + if (rc)
> + return rc;
> + }
> + return size;
> +}
> +static DEVICE_ATTR_WO(ars_rescan);
A few notes:
1/ ARS is unique to the nfit driver so let's make this nfit specific,
i.e. add it to acpi_nfit_attribute_group.
2/ Let's just call the attribute scrub and not distinguish it as "re-"
3/ Userspace may want to know when scanning is complete so let's make
this attribute read/write and on read return a count of the number of
completed scans since the driver was loaded. For notification of last
completion use sysfs_notify_dirent_safe() to make this scrub attribute
select()/poll() capable.
> +
> static struct attribute *nvdimm_bus_attributes[] = {
> &dev_attr_commands.attr,
> &dev_attr_wait_probe.attr,
> &dev_attr_provider.attr,
> + &dev_attr_ars_rescan.attr,
> NULL,
> };
>
> diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
> index 0c3c30c..1c6867a 100644
> --- a/include/linux/libnvdimm.h
> +++ b/include/linux/libnvdimm.h
> @@ -74,6 +74,7 @@ struct nvdimm_bus_descriptor {
> int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc);
> int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc,
> struct nvdimm *nvdimm, unsigned int cmd);
> + int (*ars_rescan)(struct nvdimm_bus_descriptor *nd_desc);
> };
>
> struct nd_cmd_desc {
> --
> 2.7.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
