Merge tag 'libnvdimm-for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "Aside from the recently added pmem sub-division support these have
  been in -next for several releases with no reported issues. The sub-
  division support was included in next-20161010 with no reported
  issues. It passes all unit tests including new tests for all the new
  functionality below.

  Summary:

   - PMEM sub-division support: Allow a single PMEM region to be divided
     into multiple namespaces. Originally, ~2 years ago, it was thought
     that partitions of a /dev/pmemX block device could handle
     sub-allocations of persistent memory for different use cases. With
     the decision to not support DAX mappings of raw block-devices, and
     the genesis of device-dax, the need for having multiple
     pmem-namespace per region has grown.

   - Device-DAX unified inode: In support of dynamic-resizing of a
     device-dax instance the kernel arranges for all mappings of a
     device-dax node to share the same inode. This allows unmap /
     truncate / invalidation events to affect all instances of the
     device similar to the behavior of mmap on block devices.

   - Hardware error scrubbing reworks: The original address-range-scrub
     and badblocks tracking solution allowed clearing entries at the
     individual namespace level, but it failed to clear the internal
     list of media errors maintained at the bus level. The result was
     that the next scrub or namespace disable/re-enable event would
     restore the cleared badblocks, but now that is fixed. The v4.8
     kernel introduced an auto-scrub-on-machine-check behavior to
     repopulate the badblocks list. Now, in v4.9, the auto-scrub
     behavior can be disabled and simply arrange for the error reported
     in the machine-check to be added to the list.

   - DIMM health-event notification support: ACPI 6.1 defines a
     notification event code that can be send to ACPI NVDIMM devices. A
     poll(2) capable file descriptor for these events can be obtained
     from the nmemX/nfit/flags sysfs-attribute of a libnvdimm memory
     device.

   - Miscellaneous fixes: NVDIMM-N probe error, device-dax build error,
     and a change to dedup the flush hint list to not flush the memory
     controller more than necessary"

* tag 'libnvdimm-for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (39 commits)
  /dev/dax: fix Kconfig dependency build breakage
  dax: use correct dev_t value
  dax: convert devm_create_dax_dev to PTR_ERR
  libnvdimm, namespace: allow creation of multiple pmem-namespaces per region
  libnvdimm, namespace: lift single pmem limit in scan_labels()
  libnvdimm, namespace: filter out of range labels in scan_labels()
  libnvdimm, namespace: enable allocation of multiple pmem namespaces
  libnvdimm, namespace: update label implementation for multi-pmem
  libnvdimm, namespace: expand pmem device naming scheme for multi-pmem
  libnvdimm, region: update nd_region_available_dpa() for multi-pmem support
  libnvdimm, namespace: sort namespaces by dpa at init
  libnvdimm, namespace: allow multiple pmem-namespaces per region at scan time
  tools/testing/nvdimm: support for sub-dividing a pmem region
  libnvdimm, namespace: unify blk and pmem label scanning
  libnvdimm, namespace: refactor uuid_show() into a namespace_to_uuid() helper
  libnvdimm, label: convert label tracking to a linked list
  libnvdimm, region: move region-mapping input-paramters to nd_mapping_desc
  nvdimm: reduce duplicated wpq flushes
  libnvdimm: clear the internal poison_list when clearing badblocks
  pmem: reduce kmap_atomic sections to the memcpys only
  ...

3 files changed, 216 insertions, 35 deletions

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index e1d5ea6d5e40..71a7d07c28c9 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -886,6 +886,58 @@ static ssize_t revision_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(revision);
 
+static ssize_t hw_error_scrub_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	return sprintf(buf, "%d\n", acpi_desc->scrub_mode);
+}
+
+/*
+ * The 'hw_error_scrub' attribute can have the following values written to it:
+ * '0': Switch to the default mode where an exception will only insert
+ *      the address of the memory error into the poison and badblocks lists.
+ * '1': Enable a full scrub to happen if an exception for a memory error is
+ *      received.
+ */
+static ssize_t hw_error_scrub_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct nvdimm_bus_descriptor *nd_desc;
+	ssize_t rc;
+	long val;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	device_lock(dev);
+	nd_desc = dev_get_drvdata(dev);
+	if (nd_desc) {
+		struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+		switch (val) {
+		case HW_ERROR_SCRUB_ON:
+			acpi_desc->scrub_mode = HW_ERROR_SCRUB_ON;
+			break;
+		case HW_ERROR_SCRUB_OFF:
+			acpi_desc->scrub_mode = HW_ERROR_SCRUB_OFF;
+			break;
+		default:
+			rc = -EINVAL;
+			break;
+		}
+	}
+	device_unlock(dev);
+	if (rc)
+		return rc;
+	return size;
+}
+static DEVICE_ATTR_RW(hw_error_scrub);
+
 /*
  * This shows the number of full Address Range Scrubs that have been
  * completed since driver load time. Userspace can wait on this using
@@ -958,6 +1010,7 @@ static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
 static struct attribute *acpi_nfit_attributes[] = {
 	&dev_attr_revision.attr,
 	&dev_attr_scrub.attr,
+	&dev_attr_hw_error_scrub.attr,
 	NULL,
 };
 
@@ -1256,6 +1309,44 @@ static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc,
 	return NULL;
 }
 
+void __acpi_nvdimm_notify(struct device *dev, u32 event)
+{
+	struct nfit_mem *nfit_mem;
+	struct acpi_nfit_desc *acpi_desc;
+
+	dev_dbg(dev->parent, "%s: %s: event: %d\n", dev_name(dev), __func__,
+			event);
+
+	if (event != NFIT_NOTIFY_DIMM_HEALTH) {
+		dev_dbg(dev->parent, "%s: unknown event: %d\n", dev_name(dev),
+				event);
+		return;
+	}
+
+	acpi_desc = dev_get_drvdata(dev->parent);
+	if (!acpi_desc)
+		return;
+
+	/*
+	 * If we successfully retrieved acpi_desc, then we know nfit_mem data
+	 * is still valid.
+	 */
+	nfit_mem = dev_get_drvdata(dev);
+	if (nfit_mem && nfit_mem->flags_attr)
+		sysfs_notify_dirent(nfit_mem->flags_attr);
+}
+EXPORT_SYMBOL_GPL(__acpi_nvdimm_notify);
+
+static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct acpi_device *adev = data;
+	struct device *dev = &adev->dev;
+
+	device_lock(dev->parent);
+	__acpi_nvdimm_notify(dev, event);
+	device_unlock(dev->parent);
+}
+
 static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, u32 device_handle)
 {
@@ -1280,6 +1371,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		return force_enable_dimms ? 0 : -ENODEV;
 	}
 
+	if (ACPI_FAILURE(acpi_install_notify_handler(adev_dimm->handle,
+		ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify, adev_dimm))) {
+		dev_err(dev, "%s: notification registration failed\n",
+				dev_name(&adev_dimm->dev));
+		return -ENXIO;
+	}
+
 	/*
 	 * Until standardization materializes we need to consider 4
 	 * different command sets.  Note, that checking for function0 (bit0)
@@ -1318,18 +1416,41 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
+static void shutdown_dimm_notify(void *data)
+{
+	struct acpi_nfit_desc *acpi_desc = data;
+	struct nfit_mem *nfit_mem;
+
+	mutex_lock(&acpi_desc->init_mutex);
+	/*
+	 * Clear out the nfit_mem->flags_attr and shut down dimm event
+	 * notifications.
+	 */
+	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		struct acpi_device *adev_dimm = nfit_mem->adev;
+
+		if (nfit_mem->flags_attr) {
+			sysfs_put(nfit_mem->flags_attr);
+			nfit_mem->flags_attr = NULL;
+		}
+		if (adev_dimm)
+			acpi_remove_notify_handler(adev_dimm->handle,
+					ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify);
+	}
+	mutex_unlock(&acpi_desc->init_mutex);
+}
+
 static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nfit_mem *nfit_mem;
-	int dimm_count = 0;
+	int dimm_count = 0, rc;
+	struct nvdimm *nvdimm;
 
 	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
 		struct acpi_nfit_flush_address *flush;
 		unsigned long flags = 0, cmd_mask;
-		struct nvdimm *nvdimm;
 		u32 device_handle;
 		u16 mem_flags;
-		int rc;
 
 		device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
 		nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle);
@@ -1382,7 +1503,30 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 
 	}
 
-	return nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
+	rc = nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
+	if (rc)
+		return rc;
+
+	/*
+	 * Now that dimms are successfully registered, and async registration
+	 * is flushed, attempt to enable event notification.
+	 */
+	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		struct kernfs_node *nfit_kernfs;
+
+		nvdimm = nfit_mem->nvdimm;
+		nfit_kernfs = sysfs_get_dirent(nvdimm_kobj(nvdimm)->sd, "nfit");
+		if (nfit_kernfs)
+			nfit_mem->flags_attr = sysfs_get_dirent(nfit_kernfs,
+					"flags");
+		sysfs_put(nfit_kernfs);
+		if (!nfit_mem->flags_attr)
+			dev_warn(acpi_desc->dev, "%s: notifications disabled\n",
+					nvdimm_name(nvdimm));
+	}
+
+	return devm_add_action_or_reset(acpi_desc->dev, shutdown_dimm_notify,
+			acpi_desc);
 }
 
 static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
@@ -1491,9 +1635,9 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 	if (!info)
 		return -ENOMEM;
 	for (i = 0; i < nr; i++) {
-		struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
 		struct nfit_set_info_map *map = &info->mapping[i];
-		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+		struct nvdimm *nvdimm = mapping->nvdimm;
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
 				spa->range_index, i);
@@ -1917,7 +2061,7 @@ static int acpi_nfit_insert_resource(struct acpi_nfit_desc *acpi_desc,
 }
 
 static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
-		struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
+		struct nd_mapping_desc *mapping, struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_memory_map *memdev,
 		struct nfit_spa *nfit_spa)
 {
@@ -1934,12 +2078,12 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		return -ENODEV;
 	}
 
-	nd_mapping->nvdimm = nvdimm;
+	mapping->nvdimm = nvdimm;
 	switch (nfit_spa_type(spa)) {
 	case NFIT_SPA_PM:
 	case NFIT_SPA_VOLATILE:
-		nd_mapping->start = memdev->address;
-		nd_mapping->size = memdev->region_size;
+		mapping->start = memdev->address;
+		mapping->size = memdev->region_size;
 		break;
 	case NFIT_SPA_DCR:
 		nfit_mem = nvdimm_provider_data(nvdimm);
@@ -1947,13 +2091,13 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 			dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n",
 					spa->range_index, nvdimm_name(nvdimm));
 		} else {
-			nd_mapping->size = nfit_mem->bdw->capacity;
-			nd_mapping->start = nfit_mem->bdw->start_address;
+			mapping->size = nfit_mem->bdw->capacity;
+			mapping->start = nfit_mem->bdw->start_address;
 			ndr_desc->num_lanes = nfit_mem->bdw->windows;
 			blk_valid = 1;
 		}
 
-		ndr_desc->nd_mapping = nd_mapping;
+		ndr_desc->mapping = mapping;
 		ndr_desc->num_mappings = blk_valid;
 		ndbr_desc = to_blk_region_desc(ndr_desc);
 		ndbr_desc->enable = acpi_nfit_blk_region_enable;
@@ -1979,7 +2123,7 @@ static bool nfit_spa_is_virtual(struct acpi_nfit_system_address *spa)
 static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_spa *nfit_spa)
 {
-	static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS];
+	static struct nd_mapping_desc mappings[ND_MAX_MAPPINGS];
 	struct acpi_nfit_system_address *spa = nfit_spa->spa;
 	struct nd_blk_region_desc ndbr_desc;
 	struct nd_region_desc *ndr_desc;
@@ -1998,7 +2142,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	memset(&res, 0, sizeof(res));
-	memset(&nd_mappings, 0, sizeof(nd_mappings));
+	memset(&mappings, 0, sizeof(mappings));
 	memset(&ndbr_desc, 0, sizeof(ndbr_desc));
 	res.start = spa->address;
 	res.end = res.start + spa->length - 1;
@@ -2014,7 +2158,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
 		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
-		struct nd_mapping *nd_mapping;
+		struct nd_mapping_desc *mapping;
 
 		if (memdev->range_index != spa->range_index)
 			continue;
@@ -2023,14 +2167,14 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 					spa->range_index, ND_MAX_MAPPINGS);
 			return -ENXIO;
 		}
-		nd_mapping = &nd_mappings[count++];
-		rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, ndr_desc,
+		mapping = &mappings[count++];
+		rc = acpi_nfit_init_mapping(acpi_desc, mapping, ndr_desc,
 				memdev, nfit_spa);
 		if (rc)
 			goto out;
 	}
 
-	ndr_desc->nd_mapping = nd_mappings;
+	ndr_desc->mapping = mappings;
 	ndr_desc->num_mappings = count;
 	rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa);
 	if (rc)
@@ -2678,29 +2822,30 @@ static int acpi_nfit_remove(struct acpi_device *adev)
 	return 0;
 }
 
-static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
+void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
 {
-	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
+	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	struct device *dev = &adev->dev;
 	union acpi_object *obj;
 	acpi_status status;
 	int ret;
 
 	dev_dbg(dev, "%s: event: %d\n", __func__, event);
 
-	device_lock(dev);
+	if (event != NFIT_NOTIFY_UPDATE)
+		return;
+
 	if (!dev->driver) {
 		/* dev->driver may be null if we're being removed */
 		dev_dbg(dev, "%s: no driver found for dev\n", __func__);
-		goto out_unlock;
+		return;
 	}
 
 	if (!acpi_desc) {
 		acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
 		if (!acpi_desc)
-			goto out_unlock;
-		acpi_nfit_desc_init(acpi_desc, &adev->dev);
+			return;
+		acpi_nfit_desc_init(acpi_desc, dev);
 	} else {
 		/*
 		 * Finish previous registration before considering new
@@ -2710,10 +2855,10 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	}
 
 	/* Evaluate _FIT */
-	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
+	status = acpi_evaluate_object(handle, "_FIT", NULL, &buf);
 	if (ACPI_FAILURE(status)) {
 		dev_err(dev, "failed to evaluate _FIT\n");
-		goto out_unlock;
+		return;
 	}
 
 	obj = buf.pointer;
@@ -2725,9 +2870,14 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	} else
 		dev_err(dev, "Invalid _FIT\n");
 	kfree(buf.pointer);
+}
+EXPORT_SYMBOL_GPL(__acpi_nfit_notify);
 
- out_unlock:
-	device_unlock(dev);
+static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
+{
+	device_lock(&adev->dev);
+	__acpi_nfit_notify(&adev->dev, adev->handle, event);
+	device_unlock(&adev->dev);
 }
 
 static const struct acpi_device_id acpi_nfit_ids[] = {
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index 161f91539ae6..e5ce81c38eed 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -14,6 +14,7 @@
  */
 #include <linux/notifier.h>
 #include <linux/acpi.h>
+#include <linux/nd.h>
 #include <asm/mce.h>
 #include "nfit.h"
 
@@ -62,12 +63,25 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 		}
 		mutex_unlock(&acpi_desc->init_mutex);
 
-		/*
-		 * We can ignore an -EBUSY here because if an ARS is already
-		 * in progress, just let that be the last authoritative one
-		 */
-		if (found_match)
+		if (!found_match)
+			continue;
+
+		/* If this fails due to an -ENOMEM, there is little we can do */
+		nvdimm_bus_add_poison(acpi_desc->nvdimm_bus,
+				ALIGN(mce->addr, L1_CACHE_BYTES),
+				L1_CACHE_BYTES);
+		nvdimm_region_notify(nfit_spa->nd_region,
+				NVDIMM_REVALIDATE_POISON);
+
+		if (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) {
+			/*
+			 * We can ignore an -EBUSY here because if an ARS is
+			 * already in progress, just let that be the last
+			 * authoritative one
+			 */
 			acpi_nfit_ars_rescan(acpi_desc);
+		}
+		break;
 	}
 
 	mutex_unlock(&acpi_desc_lock);
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index e894ded24d99..14296f5267c8 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -78,6 +78,14 @@ enum {
 	NFIT_ARS_TIMEOUT = 90,
 };
 
+enum nfit_root_notifiers {
+	NFIT_NOTIFY_UPDATE = 0x80,
+};
+
+enum nfit_dimm_notifiers {
+	NFIT_NOTIFY_DIMM_HEALTH = 0x81,
+};
+
 struct nfit_spa {
 	struct list_head list;
 	struct nd_region *nd_region;
@@ -124,6 +132,7 @@ struct nfit_mem {
 	struct acpi_nfit_system_address *spa_bdw;
 	struct acpi_nfit_interleave *idt_dcr;
 	struct acpi_nfit_interleave *idt_bdw;
+	struct kernfs_node *flags_attr;
 	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
@@ -152,6 +161,7 @@ struct acpi_nfit_desc {
 	struct list_head list;
 	struct kernfs_node *scrub_count_state;
 	unsigned int scrub_count;
+	unsigned int scrub_mode;
 	unsigned int cancel:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
@@ -159,6 +169,11 @@ struct acpi_nfit_desc {
 			void *iobuf, u64 len, int rw);
 };
 
+enum scrub_mode {
+	HW_ERROR_SCRUB_OFF,
+	HW_ERROR_SCRUB_ON,
+};
+
 enum nd_blk_mmio_selector {
 	BDW,
 	DCR,
@@ -223,5 +238,7 @@ static inline struct acpi_nfit_desc *to_acpi_desc(
 
 const u8 *to_nfit_uuid(enum nfit_uuids id);
 int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz);
+void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event);
+void __acpi_nvdimm_notify(struct device *dev, u32 event);
 void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev);
 #endif /* __NFIT_H__ */