summaryrefslogtreecommitdiff
path: root/drivers/acpi/nfit/core.c
diff options
context:
space:
mode:
authorVishal Verma <vishal.l.verma@intel.com>2016-07-23 21:51:21 -0700
committerDan Williams <dan.j.williams@intel.com>2016-07-24 08:04:04 -0700
commit6839a6d96f4ea0254266d60208c1fbbd53ade546 (patch)
treeb1be166d2e7028ce5185e7ad642b5f1598a0cb07 /drivers/acpi/nfit/core.c
parentbdf97013ced5f263da0dc9d559f5c09e922d8423 (diff)
nfit: do an ARS scrub on hitting a latent media error
When a latent (unknown to 'badblocks') error is encountered, it will trigger a machine check exception. On a system with machine check recovery, this will only SIGBUS the process(es) which had the bad page mapped (as opposed to a kernel panic on platforms without machine check recovery features). In the former case, we want to trigger a full rescan of that nvdimm bus. This will allow any additional, new errors to be captured in the block devices' badblocks lists, and offending operations on them can be trapped early, avoiding machine checks. This is done by registering a callback function with the x86_mce_decoder_chain and calling the new ars_rescan functionality with the address in the mce notificatiion. Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers/acpi/nfit/core.c')
-rw-r--r--drivers/acpi/nfit/core.c26
1 files changed, 22 insertions, 4 deletions
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 19d0dfdf9633..69b35b7f97a1 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -51,6 +51,9 @@ module_param(disable_vendor_specific, bool, S_IRUGO);
MODULE_PARM_DESC(disable_vendor_specific,
"Limit commands to the publicly specified set\n");
+LIST_HEAD(acpi_descs);
+DEFINE_MUTEX(acpi_desc_lock);
+
static struct workqueue_struct *nfit_wq;
struct nfit_table_prev {
@@ -361,7 +364,7 @@ static const char *spa_type_name(u16 type)
return to_name[type];
}
-static int nfit_spa_type(struct acpi_nfit_system_address *spa)
+int nfit_spa_type(struct acpi_nfit_system_address *spa)
{
int i;
@@ -898,8 +901,6 @@ static ssize_t scrub_show(struct device *dev,
return rc;
}
-static int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc);
-
static ssize_t scrub_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t size)
{
@@ -2400,6 +2401,11 @@ static void acpi_nfit_destruct(void *data)
struct acpi_nfit_desc *acpi_desc = data;
struct device *bus_dev = to_nvdimm_bus_dev(acpi_desc->nvdimm_bus);
+ /*
+ * Destruct under acpi_desc_lock so that nfit_handle_mce does not
+ * race teardown
+ */
+ mutex_lock(&acpi_desc_lock);
acpi_desc->cancel = 1;
/*
* Bounce the nvdimm bus lock to make sure any in-flight
@@ -2414,6 +2420,8 @@ static void acpi_nfit_destruct(void *data)
sysfs_put(acpi_desc->scrub_count_state);
nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
acpi_desc->nvdimm_bus = NULL;
+ list_del(&acpi_desc->list);
+ mutex_unlock(&acpi_desc_lock);
}
int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
@@ -2439,6 +2447,11 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
rc = acpi_nfit_desc_init_scrub_attr(acpi_desc);
if (rc)
return rc;
+
+ /* register this acpi_desc for mce notifications */
+ mutex_lock(&acpi_desc_lock);
+ list_add_tail(&acpi_desc->list, &acpi_descs);
+ mutex_unlock(&acpi_desc_lock);
}
mutex_lock(&acpi_desc->init_mutex);
@@ -2549,7 +2562,7 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
return 0;
}
-static int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
{
struct device *dev = acpi_desc->dev;
struct nfit_spa *nfit_spa;
@@ -2598,6 +2611,7 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
INIT_LIST_HEAD(&acpi_desc->flushes);
INIT_LIST_HEAD(&acpi_desc->memdevs);
INIT_LIST_HEAD(&acpi_desc->dimms);
+ INIT_LIST_HEAD(&acpi_desc->list);
mutex_init(&acpi_desc->init_mutex);
INIT_WORK(&acpi_desc->work, acpi_nfit_scrub);
}
@@ -2750,13 +2764,17 @@ static __init int nfit_init(void)
if (!nfit_wq)
return -ENOMEM;
+ nfit_mce_register();
+
return acpi_bus_register_driver(&acpi_nfit_driver);
}
static __exit void nfit_exit(void)
{
+ nfit_mce_unregister();
acpi_bus_unregister_driver(&acpi_nfit_driver);
destroy_workqueue(nfit_wq);
+ WARN_ON(!list_empty(&acpi_descs));
}
module_init(nfit_init);