Merge tag 'libnvdimm-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:

 - Replace pcommit with ADR / directed-flushing.

   The pcommit instruction, which has not shipped on any product, is
   deprecated.  Instead, the requirement is that platforms implement
   either ADR, or provide one or more flush addresses per nvdimm.

   ADR (Asynchronous DRAM Refresh) flushes data in posted write buffers
   to the memory controller on a power-fail event.

   Flush addresses are defined in ACPI 6.x as an NVDIMM Firmware
   Interface Table (NFIT) sub-structure: "Flush Hint Address Structure".
   A flush hint is an mmio address that when written and fenced assures
   that all previous posted writes targeting a given dimm have been
   flushed to media.

 - On-demand ARS (address range scrub).

   Linux uses the results of the ACPI ARS commands to track bad blocks
   in pmem devices.  When latent errors are detected we re-scrub the
   media to refresh the bad block list, userspace can also request a
   re-scrub at any time.

 - Support for the Microsoft DSM (device specific method) command
   format.

 - Support for EDK2/OVMF virtual disk device memory ranges.

 - Various fixes and cleanups across the subsystem.

* tag 'libnvdimm-for-4.8' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (41 commits)
  libnvdimm-btt: Delete an unnecessary check before the function call "__nd_device_register"
  nfit: do an ARS scrub on hitting a latent media error
  nfit: move to nfit/ sub-directory
  nfit, libnvdimm: allow an ARS scrub to be triggered on demand
  libnvdimm: register nvdimm_bus devices with an nd_bus driver
  pmem: clarify a debug print in pmem_clear_poison
  x86/insn: remove pcommit
  Revert "KVM: x86: add pcommit support"
  nfit, tools/testing/nvdimm/: unify shutdown paths
  libnvdimm: move ->module to struct nvdimm_bus_descriptor
  nfit: cleanup acpi_nfit_init calling convention
  nfit: fix _FIT evaluation memory leak + use after free
  tools/testing/nvdimm: add manufacturing_{date|location} dimm properties
  tools/testing/nvdimm: add virtual ramdisk range
  acpi, nfit: treat virtual ramdisk SPA as pmem region
  pmem: kill __pmem address space
  pmem: kill wmb_pmem()
  libnvdimm, pmem: use nvdimm_flush() for namespace I/O writes
  fs/dax: remove wmb_pmem()
  libnvdimm, pmem: flush posted-write queues on shutdown
  ...

7 files changed, 511 insertions, 343 deletions

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index acad70a0bb0d..aebd944bdaa1 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -454,32 +454,7 @@ config ACPI_REDUCED_HARDWARE_ONLY
 
 	  If you are unsure what to do, do not enable this option.
 
-config ACPI_NFIT
-	tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
-	depends on PHYS_ADDR_T_64BIT
-	depends on BLK_DEV
-	depends on ARCH_HAS_MMIO_FLUSH
-	select LIBNVDIMM
-	help
-	  Infrastructure to probe ACPI 6 compliant platforms for
-	  NVDIMMs (NFIT) and register a libnvdimm device tree.  In
-	  addition to storage devices this also enables libnvdimm to pass
-	  ACPI._DSM messages for platform/dimm configuration.
-
-	  To compile this driver as a module, choose M here:
-	  the module will be called nfit.
-
-config ACPI_NFIT_DEBUG
-	bool "NFIT DSM debug"
-	depends on ACPI_NFIT
-	depends on DYNAMIC_DEBUG
-	default n
-	help
-	  Enabling this option causes the nfit driver to dump the
-	  input and output buffers of _DSM operations on the ACPI0012
-	  device and its children.  This can be very verbose, so leave
-	  it disabled unless you are debugging a hardware / firmware
-	  issue.
+source "drivers/acpi/nfit/Kconfig"
 
 source "drivers/acpi/apei/Kconfig"
 source "drivers/acpi/dptf/Kconfig"
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 88f54f03e3d2..35a6ccbe3025 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -69,7 +69,7 @@ obj-$(CONFIG_ACPI_PCI_SLOT)	+= pci_slot.o
 obj-$(CONFIG_ACPI_PROCESSOR)	+= processor.o
 obj-$(CONFIG_ACPI)		+= container.o
 obj-$(CONFIG_ACPI_THERMAL)	+= thermal.o
-obj-$(CONFIG_ACPI_NFIT)		+= nfit.o
+obj-$(CONFIG_ACPI_NFIT)		+= nfit/
 obj-$(CONFIG_ACPI)		+= acpi_memhotplug.o
 obj-$(CONFIG_ACPI_HOTPLUG_IOAPIC) += ioapic.o
 obj-$(CONFIG_ACPI_BATTERY)	+= battery.o
diff --git a/drivers/acpi/nfit/Kconfig b/drivers/acpi/nfit/Kconfig
new file mode 100644
index 000000000000..dd0d53c52552
--- /dev/null
+++ b/drivers/acpi/nfit/Kconfig
@@ -0,0 +1,26 @@
+config ACPI_NFIT
+	tristate "ACPI NVDIMM Firmware Interface Table (NFIT)"
+	depends on PHYS_ADDR_T_64BIT
+	depends on BLK_DEV
+	depends on ARCH_HAS_MMIO_FLUSH
+	select LIBNVDIMM
+	help
+	  Infrastructure to probe ACPI 6 compliant platforms for
+	  NVDIMMs (NFIT) and register a libnvdimm device tree.  In
+	  addition to storage devices this also enables libnvdimm to pass
+	  ACPI._DSM messages for platform/dimm configuration.
+
+	  To compile this driver as a module, choose M here:
+	  the module will be called nfit.
+
+config ACPI_NFIT_DEBUG
+	bool "NFIT DSM debug"
+	depends on ACPI_NFIT
+	depends on DYNAMIC_DEBUG
+	default n
+	help
+	  Enabling this option causes the nfit driver to dump the
+	  input and output buffers of _DSM operations on the ACPI0012
+	  device and its children.  This can be very verbose, so leave
+	  it disabled unless you are debugging a hardware / firmware
+	  issue.
diff --git a/drivers/acpi/nfit/Makefile b/drivers/acpi/nfit/Makefile
new file mode 100644
index 000000000000..a407e769f103
--- /dev/null
+++ b/drivers/acpi/nfit/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_ACPI_NFIT) := nfit.o
+nfit-y := core.o
+nfit-$(CONFIG_X86_MCE) += mce.o
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit/core.c
index 1f0e06065ae6..8c234dd9b8bc 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit/core.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/ndctl.h>
+#include <linux/sysfs.h>
 #include <linux/delay.h>
 #include <linux/list.h>
 #include <linux/acpi.h>
@@ -50,6 +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 {
@@ -360,7 +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;
 
@@ -374,22 +378,25 @@ static bool add_spa(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_system_address *spa)
 {
-	size_t length = min_t(size_t, sizeof(*spa), spa->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_spa *nfit_spa;
 
+	if (spa->header.length != sizeof(*spa))
+		return false;
+
 	list_for_each_entry(nfit_spa, &prev->spas, list) {
-		if (memcmp(nfit_spa->spa, spa, length) == 0) {
+		if (memcmp(nfit_spa->spa, spa, sizeof(*spa)) == 0) {
 			list_move_tail(&nfit_spa->list, &acpi_desc->spas);
 			return true;
 		}
 	}
 
-	nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa), GFP_KERNEL);
+	nfit_spa = devm_kzalloc(dev, sizeof(*nfit_spa) + sizeof(*spa),
+			GFP_KERNEL);
 	if (!nfit_spa)
 		return false;
 	INIT_LIST_HEAD(&nfit_spa->list);
-	nfit_spa->spa = spa;
+	memcpy(nfit_spa->spa, spa, sizeof(*spa));
 	list_add_tail(&nfit_spa->list, &acpi_desc->spas);
 	dev_dbg(dev, "%s: spa index: %d type: %s\n", __func__,
 			spa->range_index,
@@ -401,21 +408,24 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_memory_map *memdev)
 {
-	size_t length = min_t(size_t, sizeof(*memdev), memdev->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_memdev *nfit_memdev;
 
+	if (memdev->header.length != sizeof(*memdev))
+		return false;
+
 	list_for_each_entry(nfit_memdev, &prev->memdevs, list)
-		if (memcmp(nfit_memdev->memdev, memdev, length) == 0) {
+		if (memcmp(nfit_memdev->memdev, memdev, sizeof(*memdev)) == 0) {
 			list_move_tail(&nfit_memdev->list, &acpi_desc->memdevs);
 			return true;
 		}
 
-	nfit_memdev = devm_kzalloc(dev, sizeof(*nfit_memdev), GFP_KERNEL);
+	nfit_memdev = devm_kzalloc(dev, sizeof(*nfit_memdev) + sizeof(*memdev),
+			GFP_KERNEL);
 	if (!nfit_memdev)
 		return false;
 	INIT_LIST_HEAD(&nfit_memdev->list);
-	nfit_memdev->memdev = memdev;
+	memcpy(nfit_memdev->memdev, memdev, sizeof(*memdev));
 	list_add_tail(&nfit_memdev->list, &acpi_desc->memdevs);
 	dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d\n",
 			__func__, memdev->device_handle, memdev->range_index,
@@ -423,25 +433,42 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
 	return true;
 }
 
+/*
+ * An implementation may provide a truncated control region if no block windows
+ * are defined.
+ */
+static size_t sizeof_dcr(struct acpi_nfit_control_region *dcr)
+{
+	if (dcr->header.length < offsetof(struct acpi_nfit_control_region,
+				window_size))
+		return 0;
+	if (dcr->windows)
+		return sizeof(*dcr);
+	return offsetof(struct acpi_nfit_control_region, window_size);
+}
+
 static bool add_dcr(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_control_region *dcr)
 {
-	size_t length = min_t(size_t, sizeof(*dcr), dcr->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_dcr *nfit_dcr;
 
+	if (!sizeof_dcr(dcr))
+		return false;
+
 	list_for_each_entry(nfit_dcr, &prev->dcrs, list)
-		if (memcmp(nfit_dcr->dcr, dcr, length) == 0) {
+		if (memcmp(nfit_dcr->dcr, dcr, sizeof_dcr(dcr)) == 0) {
 			list_move_tail(&nfit_dcr->list, &acpi_desc->dcrs);
 			return true;
 		}
 
-	nfit_dcr = devm_kzalloc(dev, sizeof(*nfit_dcr), GFP_KERNEL);
+	nfit_dcr = devm_kzalloc(dev, sizeof(*nfit_dcr) + sizeof(*dcr),
+			GFP_KERNEL);
 	if (!nfit_dcr)
 		return false;
 	INIT_LIST_HEAD(&nfit_dcr->list);
-	nfit_dcr->dcr = dcr;
+	memcpy(nfit_dcr->dcr, dcr, sizeof_dcr(dcr));
 	list_add_tail(&nfit_dcr->list, &acpi_desc->dcrs);
 	dev_dbg(dev, "%s: dcr index: %d windows: %d\n", __func__,
 			dcr->region_index, dcr->windows);
@@ -452,71 +479,102 @@ static bool add_bdw(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_data_region *bdw)
 {
-	size_t length = min_t(size_t, sizeof(*bdw), bdw->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_bdw *nfit_bdw;
 
+	if (bdw->header.length != sizeof(*bdw))
+		return false;
 	list_for_each_entry(nfit_bdw, &prev->bdws, list)
-		if (memcmp(nfit_bdw->bdw, bdw, length) == 0) {
+		if (memcmp(nfit_bdw->bdw, bdw, sizeof(*bdw)) == 0) {
 			list_move_tail(&nfit_bdw->list, &acpi_desc->bdws);
 			return true;
 		}
 
-	nfit_bdw = devm_kzalloc(dev, sizeof(*nfit_bdw), GFP_KERNEL);
+	nfit_bdw = devm_kzalloc(dev, sizeof(*nfit_bdw) + sizeof(*bdw),
+			GFP_KERNEL);
 	if (!nfit_bdw)
 		return false;
 	INIT_LIST_HEAD(&nfit_bdw->list);
-	nfit_bdw->bdw = bdw;
+	memcpy(nfit_bdw->bdw, bdw, sizeof(*bdw));
 	list_add_tail(&nfit_bdw->list, &acpi_desc->bdws);
 	dev_dbg(dev, "%s: bdw dcr: %d windows: %d\n", __func__,
 			bdw->region_index, bdw->windows);
 	return true;
 }
 
+static size_t sizeof_idt(struct acpi_nfit_interleave *idt)
+{
+	if (idt->header.length < sizeof(*idt))
+		return 0;
+	return sizeof(*idt) + sizeof(u32) * (idt->line_count - 1);
+}
+
 static bool add_idt(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_interleave *idt)
 {
-	size_t length = min_t(size_t, sizeof(*idt), idt->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_idt *nfit_idt;
 
-	list_for_each_entry(nfit_idt, &prev->idts, list)
-		if (memcmp(nfit_idt->idt, idt, length) == 0) {
+	if (!sizeof_idt(idt))
+		return false;
+
+	list_for_each_entry(nfit_idt, &prev->idts, list) {
+		if (sizeof_idt(nfit_idt->idt) != sizeof_idt(idt))
+			continue;
+
+		if (memcmp(nfit_idt->idt, idt, sizeof_idt(idt)) == 0) {
 			list_move_tail(&nfit_idt->list, &acpi_desc->idts);
 			return true;
 		}
+	}
 
-	nfit_idt = devm_kzalloc(dev, sizeof(*nfit_idt), GFP_KERNEL);
+	nfit_idt = devm_kzalloc(dev, sizeof(*nfit_idt) + sizeof_idt(idt),
+			GFP_KERNEL);
 	if (!nfit_idt)
 		return false;
 	INIT_LIST_HEAD(&nfit_idt->list);
-	nfit_idt->idt = idt;
+	memcpy(nfit_idt->idt, idt, sizeof_idt(idt));
 	list_add_tail(&nfit_idt->list, &acpi_desc->idts);
 	dev_dbg(dev, "%s: idt index: %d num_lines: %d\n", __func__,
 			idt->interleave_index, idt->line_count);
 	return true;
 }
 
+static size_t sizeof_flush(struct acpi_nfit_flush_address *flush)
+{
+	if (flush->header.length < sizeof(*flush))
+		return 0;
+	return sizeof(*flush) + sizeof(u64) * (flush->hint_count - 1);
+}
+
 static bool add_flush(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_table_prev *prev,
 		struct acpi_nfit_flush_address *flush)
 {
-	size_t length = min_t(size_t, sizeof(*flush), flush->header.length);
 	struct device *dev = acpi_desc->dev;
 	struct nfit_flush *nfit_flush;
 
-	list_for_each_entry(nfit_flush, &prev->flushes, list)
-		if (memcmp(nfit_flush->flush, flush, length) == 0) {
+	if (!sizeof_flush(flush))
+		return false;
+
+	list_for_each_entry(nfit_flush, &prev->flushes, list) {
+		if (sizeof_flush(nfit_flush->flush) != sizeof_flush(flush))
+			continue;
+
+		if (memcmp(nfit_flush->flush, flush,
+					sizeof_flush(flush)) == 0) {
 			list_move_tail(&nfit_flush->list, &acpi_desc->flushes);
 			return true;
 		}
+	}
 
-	nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush), GFP_KERNEL);
+	nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush)
+			+ sizeof_flush(flush), GFP_KERNEL);
 	if (!nfit_flush)
 		return false;
 	INIT_LIST_HEAD(&nfit_flush->list);
-	nfit_flush->flush = flush;
+	memcpy(nfit_flush->flush, flush, sizeof_flush(flush));
 	list_add_tail(&nfit_flush->list, &acpi_desc->flushes);
 	dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__,
 			flush->device_handle, flush->hint_count);
@@ -614,7 +672,6 @@ static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
-	struct nfit_flush *nfit_flush;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
 	u16 idt_idx, range_index;
@@ -647,14 +704,6 @@ static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
 			nfit_mem->idt_bdw = nfit_idt->idt;
 			break;
 		}
-
-		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
-			if (nfit_flush->flush->device_handle !=
-					nfit_memdev->memdev->device_handle)
-				continue;
-			nfit_mem->nfit_flush = nfit_flush;
-			break;
-		}
 		break;
 	}
 }
@@ -675,6 +724,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+		struct nfit_flush *nfit_flush;
 		struct nfit_dcr *nfit_dcr;
 		u32 device_handle;
 		u16 dcr;
@@ -721,6 +771,28 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 			break;
 		}
 
+		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
+			struct acpi_nfit_flush_address *flush;
+			u16 i;
+
+			if (nfit_flush->flush->device_handle != device_handle)
+				continue;
+			nfit_mem->nfit_flush = nfit_flush;
+			flush = nfit_flush->flush;
+			nfit_mem->flush_wpq = devm_kzalloc(acpi_desc->dev,
+					flush->hint_count
+					* sizeof(struct resource), GFP_KERNEL);
+			if (!nfit_mem->flush_wpq)
+				return -ENOMEM;
+			for (i = 0; i < flush->hint_count; i++) {
+				struct resource *res = &nfit_mem->flush_wpq[i];
+
+				res->start = flush->hint_address[i];
+				res->end = res->start + 8 - 1;
+			}
+			break;
+		}
+
 		if (dcr && !nfit_mem->dcr) {
 			dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n",
 					spa->range_index, dcr);
@@ -806,14 +878,85 @@ static ssize_t revision_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(revision);
 
+/*
+ * This shows the number of full Address Range Scrubs that have been
+ * completed since driver load time. Userspace can wait on this using
+ * select/poll etc. A '+' at the end indicates an ARS is in progress
+ */
+static ssize_t scrub_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus_descriptor *nd_desc;
+	ssize_t rc = -ENXIO;
+
+	device_lock(dev);
+	nd_desc = dev_get_drvdata(dev);
+	if (nd_desc) {
+		struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+		rc = sprintf(buf, "%d%s", acpi_desc->scrub_count,
+				(work_busy(&acpi_desc->work)) ? "+\n" : "\n");
+	}
+	device_unlock(dev);
+	return rc;
+}
+
+static ssize_t 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;
+	if (val != 1)
+		return -EINVAL;
+
+	device_lock(dev);
+	nd_desc = dev_get_drvdata(dev);
+	if (nd_desc) {
+		struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+		rc = acpi_nfit_ars_rescan(acpi_desc);
+	}
+	device_unlock(dev);
+	if (rc)
+		return rc;
+	return size;
+}
+static DEVICE_ATTR_RW(scrub);
+
+static bool ars_supported(struct nvdimm_bus *nvdimm_bus)
+{
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	const unsigned long mask = 1 << ND_CMD_ARS_CAP | 1 << ND_CMD_ARS_START
+		| 1 << ND_CMD_ARS_STATUS;
+
+	return (nd_desc->cmd_mask & mask) == mask;
+}
+
+static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+
+	if (a == &dev_attr_scrub.attr && !ars_supported(nvdimm_bus))
+		return 0;
+	return a->mode;
+}
+
 static struct attribute *acpi_nfit_attributes[] = {
 	&dev_attr_revision.attr,
+	&dev_attr_scrub.attr,
 	NULL,
 };
 
 static struct attribute_group acpi_nfit_attribute_group = {
 	.name = "nfit",
 	.attrs = acpi_nfit_attributes,
+	.is_visible = nfit_visible,
 };
 
 static const struct attribute_group *acpi_nfit_attribute_groups[] = {
@@ -1130,11 +1273,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	/*
-	 * Until standardization materializes we need to consider up to 3
+	 * Until standardization materializes we need to consider 4
 	 * different command sets.  Note, that checking for function0 (bit0)
 	 * tells us if any commands are reachable through this uuid.
 	 */
-	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_HPE2; i++)
+	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++)
 		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
 			break;
 
@@ -1144,12 +1287,14 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		dsm_mask = 0x3fe;
 		if (disable_vendor_specific)
 			dsm_mask &= ~(1 << ND_CMD_VENDOR);
-	} else if (nfit_mem->family == NVDIMM_FAMILY_HPE1)
+	} else if (nfit_mem->family == NVDIMM_FAMILY_HPE1) {
 		dsm_mask = 0x1c3c76;
-	else if (nfit_mem->family == NVDIMM_FAMILY_HPE2) {
+	} else if (nfit_mem->family == NVDIMM_FAMILY_HPE2) {
 		dsm_mask = 0x1fe;
 		if (disable_vendor_specific)
 			dsm_mask &= ~(1 << 8);
+	} else if (nfit_mem->family == NVDIMM_FAMILY_MSFT) {
+		dsm_mask = 0xffffffff;
 	} else {
 		dev_dbg(dev, "unknown dimm command family\n");
 		nfit_mem->family = -1;
@@ -1171,6 +1316,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 	int dimm_count = 0;
 
 	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;
@@ -1204,9 +1350,12 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		if (nfit_mem->family == NVDIMM_FAMILY_INTEL)
 			cmd_mask |= nfit_mem->dsm_mask;
 
+		flush = nfit_mem->nfit_flush ? nfit_mem->nfit_flush->flush
+			: NULL;
 		nvdimm = nvdimm_create(acpi_desc->nvdimm_bus, nfit_mem,
 				acpi_nfit_dimm_attribute_groups,
-				flags, cmd_mask);
+				flags, cmd_mask, flush ? flush->hint_count : 0,
+				nfit_mem->flush_wpq);
 		if (!nvdimm)
 			return -ENOMEM;
 
@@ -1374,24 +1523,6 @@ static u64 to_interleave_offset(u64 offset, struct nfit_blk_mmio *mmio)
 	return mmio->base_offset + line_offset + table_offset + sub_line_offset;
 }
 
-static void wmb_blk(struct nfit_blk *nfit_blk)
-{
-
-	if (nfit_blk->nvdimm_flush) {
-		/*
-		 * The first wmb() is needed to 'sfence' all previous writes
-		 * such that they are architecturally visible for the platform
-		 * buffer flush.  Note that we've already arranged for pmem
-		 * writes to avoid the cache via arch_memcpy_to_pmem().  The
-		 * final wmb() ensures ordering for the NVDIMM flush write.
-		 */
-		wmb();
-		writeq(1, nfit_blk->nvdimm_flush);
-		wmb();
-	} else
-		wmb_pmem();
-}
-
 static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 {
 	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
@@ -1426,7 +1557,7 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw,
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->addr.base + offset);
-	wmb_blk(nfit_blk);
+	nvdimm_flush(nfit_blk->nd_region);
 
 	if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH)
 		readq(mmio->addr.base + offset);
@@ -1477,7 +1608,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 	}
 
 	if (rw)
-		wmb_blk(nfit_blk);
+		nvdimm_flush(nfit_blk->nd_region);
 
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;
@@ -1509,125 +1640,6 @@ static int acpi_nfit_blk_region_do_io(struct nd_blk_region *ndbr,
 	return rc;
 }
 
-static void nfit_spa_mapping_release(struct kref *kref)
-{
-	struct nfit_spa_mapping *spa_map = to_spa_map(kref);
-	struct acpi_nfit_system_address *spa = spa_map->spa;
-	struct acpi_nfit_desc *acpi_desc = spa_map->acpi_desc;
-
-	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
-	dev_dbg(acpi_desc->dev, "%s: SPA%d\n", __func__, spa->range_index);
-	if (spa_map->type == SPA_MAP_APERTURE)
-		memunmap((void __force *)spa_map->addr.aperture);
-	else
-		iounmap(spa_map->addr.base);
-	release_mem_region(spa->address, spa->length);
-	list_del(&spa_map->list);
-	kfree(spa_map);
-}
-
-static struct nfit_spa_mapping *find_spa_mapping(
-		struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
-{
-	struct nfit_spa_mapping *spa_map;
-
-	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
-	list_for_each_entry(spa_map, &acpi_desc->spa_maps, list)
-		if (spa_map->spa == spa)
-			return spa_map;
-
-	return NULL;
-}
-
-static void nfit_spa_unmap(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
-{
-	struct nfit_spa_mapping *spa_map;
-
-	mutex_lock(&acpi_desc->spa_map_mutex);
-	spa_map = find_spa_mapping(acpi_desc, spa);
-
-	if (spa_map)
-		kref_put(&spa_map->kref, nfit_spa_mapping_release);
-	mutex_unlock(&acpi_desc->spa_map_mutex);
-}
-
-static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa, enum spa_map_type type)
-{
-	resource_size_t start = spa->address;
-	resource_size_t n = spa->length;
-	struct nfit_spa_mapping *spa_map;
-	struct resource *res;
-
-	WARN_ON(!mutex_is_locked(&acpi_desc->spa_map_mutex));
-
-	spa_map = find_spa_mapping(acpi_desc, spa);
-	if (spa_map) {
-		kref_get(&spa_map->kref);
-		return spa_map->addr.base;
-	}
-
-	spa_map = kzalloc(sizeof(*spa_map), GFP_KERNEL);
-	if (!spa_map)
-		return NULL;
-
-	INIT_LIST_HEAD(&spa_map->list);
-	spa_map->spa = spa;
-	kref_init(&spa_map->kref);
-	spa_map->acpi_desc = acpi_desc;
-
-	res = request_mem_region(start, n, dev_name(acpi_desc->dev));
-	if (!res)
-		goto err_mem;
-
-	spa_map->type = type;
-	if (type == SPA_MAP_APERTURE)
-		spa_map->addr.aperture = (void __pmem *)memremap(start, n,
-							ARCH_MEMREMAP_PMEM);
-	else
-		spa_map->addr.base = ioremap_nocache(start, n);
-
-
-	if (!spa_map->addr.base)
-		goto err_map;
-
-	list_add_tail(&spa_map->list, &acpi_desc->spa_maps);
-	return spa_map->addr.base;
-
- err_map:
-	release_mem_region(start, n);
- err_mem:
-	kfree(spa_map);
-	return NULL;
-}
-
-/**
- * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges
- * @nvdimm_bus: NFIT-bus that provided the spa table entry
- * @nfit_spa: spa table to map
- * @type: aperture or control region
- *
- * In the case where block-data-window apertures and
- * dimm-control-regions are interleaved they will end up sharing a
- * single request_mem_region() + ioremap() for the address range.  In
- * the style of devm nfit_spa_map() mappings are automatically dropped
- * when all region devices referencing the same mapping are disabled /
- * unbound.
- */
-static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa, enum spa_map_type type)
-{
-	void __iomem *iomem;
-
-	mutex_lock(&acpi_desc->spa_map_mutex);
-	iomem = __nfit_spa_map(acpi_desc, spa, type);
-	mutex_unlock(&acpi_desc->spa_map_mutex);
-
-	return iomem;
-}
-
 static int nfit_blk_init_interleave(struct nfit_blk_mmio *mmio,
 		struct acpi_nfit_interleave *idt, u16 interleave_ways)
 {
@@ -1669,9 +1681,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		struct device *dev)
 {
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
-	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
-	struct nfit_flush *nfit_flush;
 	struct nfit_blk_mmio *mmio;
 	struct nfit_blk *nfit_blk;
 	struct nfit_mem *nfit_mem;
@@ -1697,8 +1707,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
-			SPA_MAP_APERTURE);
+	mmio->addr.base = devm_nvdimm_memremap(dev, nfit_mem->spa_bdw->address,
+                        nfit_mem->spa_bdw->length, ARCH_MEMREMAP_PMEM);
 	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1720,8 +1730,8 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->addr.base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
-			SPA_MAP_CONTROL);
+	mmio->addr.base = devm_nvdimm_ioremap(dev, nfit_mem->spa_dcr->address,
+			nfit_mem->spa_dcr->length);
 	if (!mmio->addr.base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1746,15 +1756,7 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		return rc;
 	}
 
-	nfit_flush = nfit_mem->nfit_flush;
-	if (nfit_flush && nfit_flush->flush->hint_count != 0) {
-		nfit_blk->nvdimm_flush = devm_ioremap_nocache(dev,
-				nfit_flush->flush->hint_address[0], 8);
-		if (!nfit_blk->nvdimm_flush)
-			return -ENOMEM;
-	}
-
-	if (!arch_has_wmb_pmem() && !nfit_blk->nvdimm_flush)
+	if (nvdimm_has_flush(nfit_blk->nd_region) < 0)
 		dev_warn(dev, "unable to guarantee persistence of writes\n");
 
 	if (mmio->line_size == 0)
@@ -1773,29 +1775,6 @@ static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 	return 0;
 }
 
-static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
-		struct device *dev)
-{
-	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
-	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
-	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
-	struct nfit_blk *nfit_blk = nd_blk_region_provider_data(ndbr);
-	int i;
-
-	if (!nfit_blk)
-		return; /* never enabled */
-
-	/* auto-free BLK spa mappings */
-	for (i = 0; i < 2; i++) {
-		struct nfit_blk_mmio *mmio = &nfit_blk->mmio[i];
-
-		if (mmio->addr.base)
-			nfit_spa_unmap(acpi_desc, mmio->spa);
-	}
-	nd_blk_region_set_provider_data(ndbr, NULL);
-	/* devm will free nfit_blk */
-}
-
 static int ars_get_cap(struct acpi_nfit_desc *acpi_desc,
 		struct nd_cmd_ars_cap *cmd, struct nfit_spa *nfit_spa)
 {
@@ -1919,11 +1898,11 @@ static int acpi_nfit_insert_resource(struct acpi_nfit_desc *acpi_desc,
 	if (ret)
 		return ret;
 
-	ret = devm_add_action(acpi_desc->dev, acpi_nfit_remove_resource, res);
-	if (ret) {
-		remove_resource(res);
+	ret = devm_add_action_or_reset(acpi_desc->dev,
+					acpi_nfit_remove_resource,
+					res);
+	if (ret)
 		return ret;
-	}
 
 	return 0;
 }
@@ -1969,7 +1948,6 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		ndr_desc->num_mappings = blk_valid;
 		ndbr_desc = to_blk_region_desc(ndr_desc);
 		ndbr_desc->enable = acpi_nfit_blk_region_enable;
-		ndbr_desc->disable = acpi_nfit_blk_region_disable;
 		ndbr_desc->do_io = acpi_desc->blk_do_io;
 		nfit_spa->nd_region = nvdimm_blk_region_create(acpi_desc->nvdimm_bus,
 				ndr_desc);
@@ -1981,6 +1959,14 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
+static bool nfit_spa_is_virtual(struct acpi_nfit_system_address *spa)
+{
+	return (nfit_spa_type(spa) == NFIT_SPA_VDISK ||
+		nfit_spa_type(spa) == NFIT_SPA_VCD   ||
+		nfit_spa_type(spa) == NFIT_SPA_PDISK ||
+		nfit_spa_type(spa) == NFIT_SPA_PCD);
+}
+
 static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_spa *nfit_spa)
 {
@@ -1996,7 +1982,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	if (nfit_spa->nd_region)
 		return 0;
 
-	if (spa->range_index == 0) {
+	if (spa->range_index == 0 && !nfit_spa_is_virtual(spa)) {
 		dev_dbg(acpi_desc->dev, "%s: detected invalid spa index\n",
 				__func__);
 		return 0;
@@ -2060,6 +2046,11 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 				ndr_desc);
 		if (!nfit_spa->nd_region)
 			rc = -ENOMEM;
+	} else if (nfit_spa_is_virtual(spa)) {
+		nfit_spa->nd_region = nvdimm_pmem_region_create(nvdimm_bus,
+				ndr_desc);
+		if (!nfit_spa->nd_region)
+			rc = -ENOMEM;
 	}
 
  out:
@@ -2139,7 +2130,7 @@ 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)
+	if (!nfit_spa->ars_required || !nfit_spa->nd_region)
 		return;
 
 	rc = ars_start(acpi_desc, nfit_spa);
@@ -2228,7 +2219,9 @@ 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.
 	 */
 
 	/* process platform firmware initiated scrubs */
@@ -2331,14 +2324,17 @@ static void acpi_nfit_scrub(struct work_struct *work)
 		 * Flag all the ranges that still need scrubbing, but
 		 * register them now to make data available.
 		 */
-		if (nfit_spa->nd_region)
-			nfit_spa->ars_done = 1;
-		else
+		if (!nfit_spa->nd_region) {
+			nfit_spa->ars_required = 1;
 			acpi_nfit_register_region(acpi_desc, nfit_spa);
+		}
 	}
 
 	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
 		acpi_nfit_async_scrub(acpi_desc, nfit_spa);
+	acpi_desc->scrub_count++;
+	if (acpi_desc->scrub_count_state)
+		sysfs_notify_dirent(acpi_desc->scrub_count_state);
 	mutex_unlock(&acpi_desc->init_mutex);
 }
 
@@ -2376,14 +2372,89 @@ static int acpi_nfit_check_deletions(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
-int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
+static int acpi_nfit_desc_init_scrub_attr(struct acpi_nfit_desc *acpi_desc)
+{
+	struct device *dev = acpi_desc->dev;
+	struct kernfs_node *nfit;
+	struct device *bus_dev;
+
+	if (!ars_supported(acpi_desc->nvdimm_bus))
+		return 0;
+
+	bus_dev = to_nvdimm_bus_dev(acpi_desc->nvdimm_bus);
+	nfit = sysfs_get_dirent(bus_dev->kobj.sd, "nfit");
+	if (!nfit) {
+		dev_err(dev, "sysfs_get_dirent 'nfit' failed\n");
+		return -ENODEV;
+	}
+	acpi_desc->scrub_count_state = sysfs_get_dirent(nfit, "scrub");
+	sysfs_put(nfit);
+	if (!acpi_desc->scrub_count_state) {
+		dev_err(dev, "sysfs_get_dirent 'scrub' failed\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+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
+	 * acpi_nfit_ars_rescan() submissions have had a chance to
+	 * either submit or see ->cancel set.
+	 */
+	device_lock(bus_dev);
+	device_unlock(bus_dev);
+
+	flush_workqueue(nfit_wq);
+	if (acpi_desc->scrub_count_state)
+		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)
 {
 	struct device *dev = acpi_desc->dev;
 	struct nfit_table_prev prev;
 	const void *end;
-	u8 *data;
 	int rc;
 
+	if (!acpi_desc->nvdimm_bus) {
+		acpi_nfit_init_dsms(acpi_desc);
+
+		acpi_desc->nvdimm_bus = nvdimm_bus_register(dev,
+				&acpi_desc->nd_desc);
+		if (!acpi_desc->nvdimm_bus)
+			return -ENOMEM;
+
+		rc = devm_add_action_or_reset(dev, acpi_nfit_destruct,
+				acpi_desc);
+		if (rc)
+			return rc;
+
+		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);
 
 	INIT_LIST_HEAD(&prev.spas);
@@ -2406,7 +2477,6 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 	list_cut_position(&prev.flushes, &acpi_desc->flushes,
 				acpi_desc->flushes.prev);
 
-	data = (u8 *) acpi_desc->nfit;
 	end = data + sz;
 	while (!IS_ERR_OR_NULL(data))
 		data = add_table(acpi_desc, &prev, data, end);
@@ -2422,12 +2492,9 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, acpi_size sz)
 	if (rc)
 		goto out_unlock;
 
-	if (nfit_mem_init(acpi_desc) != 0) {
-		rc = -ENOMEM;
+	rc = nfit_mem_init(acpi_desc);
+	if (rc)
 		goto out_unlock;
-	}
-
-	acpi_nfit_init_dsms(acpi_desc);
 
 	rc = acpi_nfit_register_dimms(acpi_desc);
 	if (rc)
@@ -2496,6 +2563,33 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
 	return 0;
 }
 
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
+{
+	struct device *dev = acpi_desc->dev;
+	struct nfit_spa *nfit_spa;
+
+	if (work_busy(&acpi_desc->work))
+		return -EBUSY;
+
+	if (acpi_desc->cancel)
+		return 0;
+
+	mutex_lock(&acpi_desc->init_mutex);
+	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_required = 1;
+	}
+	queue_work(nfit_wq, &acpi_desc->work);
+	dev_dbg(dev, "%s: ars_scan triggered\n", __func__);
+	mutex_unlock(&acpi_desc->init_mutex);
+
+	return 0;
+}
+
 void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
 {
 	struct nvdimm_bus_descriptor *nd_desc;
@@ -2505,12 +2599,12 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
 	acpi_desc->blk_do_io = acpi_nfit_blk_region_do_io;
 	nd_desc = &acpi_desc->nd_desc;
 	nd_desc->provider_name = "ACPI.NFIT";
+	nd_desc->module = THIS_MODULE;
 	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->attr_groups = acpi_nfit_attribute_groups;
 
-	INIT_LIST_HEAD(&acpi_desc->spa_maps);
 	INIT_LIST_HEAD(&acpi_desc->spas);
 	INIT_LIST_HEAD(&acpi_desc->dcrs);
 	INIT_LIST_HEAD(&acpi_desc->bdws);
@@ -2518,7 +2612,7 @@ 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);
-	mutex_init(&acpi_desc->spa_map_mutex);
+	INIT_LIST_HEAD(&acpi_desc->list);
 	mutex_init(&acpi_desc->init_mutex);
 	INIT_WORK(&acpi_desc->work, acpi_nfit_scrub);
 }
@@ -2532,7 +2626,7 @@ static int acpi_nfit_add(struct acpi_device *adev)
 	struct acpi_table_header *tbl;
 	acpi_status status = AE_OK;
 	acpi_size sz;
-	int rc;
+	int rc = 0;
 
 	status = acpi_get_table_with_size(ACPI_SIG_NFIT, 0, &tbl, &sz);
 	if (ACPI_FAILURE(status)) {
@@ -2545,50 +2639,33 @@ static int acpi_nfit_add(struct acpi_device *adev)
 	if (!acpi_desc)
 		return -ENOMEM;
 	acpi_nfit_desc_init(acpi_desc, &adev->dev);
-	acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, &acpi_desc->nd_desc);
-	if (!acpi_desc->nvdimm_bus)
-		return -ENOMEM;
 
-	/*
-	 * Save the acpi header for later and then skip it,
-	 * making nfit point to the first nfit table header.
-	 */
+	/* Save the acpi header for exporting the revision via sysfs */
 	acpi_desc->acpi_header = *tbl;
-	acpi_desc->nfit = (void *) tbl + sizeof(struct acpi_table_nfit);
-	sz -= sizeof(struct acpi_table_nfit);
 
 	/* Evaluate _FIT and override with that if present */
 	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
 	if (ACPI_SUCCESS(status) && buf.length > 0) {
-		union acpi_object *obj;
-		/*
-		 * Adjust for the acpi_object header of the _FIT
-		 */
-		obj = buf.pointer;
-		if (obj->type == ACPI_TYPE_BUFFER) {
-			acpi_desc->nfit =
-				(struct acpi_nfit_header *)obj->buffer.pointer;
-			sz = obj->buffer.length;
-		} else
+		union acpi_object *obj = buf.pointer;
+
+		if (obj->type == ACPI_TYPE_BUFFER)
+			rc = acpi_nfit_init(acpi_desc, obj->buffer.pointer,
+					obj->buffer.length);
+		else
 			dev_dbg(dev, "%s invalid type %d, ignoring _FIT\n",
 				 __func__, (int) obj->type);
-	}
-
-	rc = acpi_nfit_init(acpi_desc, sz);
-	if (rc) {
-		nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
-		return rc;
-	}
-	return 0;
+		kfree(buf.pointer);
+	} else
+		/* skip over the lead-in header table */
+		rc = acpi_nfit_init(acpi_desc, (void *) tbl
+				+ sizeof(struct acpi_table_nfit),
+				sz - sizeof(struct acpi_table_nfit));
+	return rc;
 }
 
 static int acpi_nfit_remove(struct acpi_device *adev)
 {
-	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
-
-	acpi_desc->cancel = 1;
-	flush_workqueue(nfit_wq);
-	nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
+	/* see acpi_nfit_destruct */
 	return 0;
 }
 
@@ -2596,9 +2673,8 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 {
 	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	struct acpi_nfit_header *nfit_saved;
-	union acpi_object *obj;
 	struct device *dev = &adev->dev;
+	union acpi_object *obj;
 	acpi_status status;
 	int ret;
 
@@ -2616,9 +2692,6 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 		if (!acpi_desc)
 			goto out_unlock;
 		acpi_nfit_desc_init(acpi_desc, &adev->dev);
-		acpi_desc->nvdimm_bus = nvdimm_bus_register(dev, &acpi_desc->nd_desc);
-		if (!acpi_desc->nvdimm_bus)
-			goto out_unlock;
 	} else {
 		/*
 		 * Finish previous registration before considering new
@@ -2634,21 +2707,14 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 		goto out_unlock;
 	}
 
-	nfit_saved = acpi_desc->nfit;
 	obj = buf.pointer;
 	if (obj->type == ACPI_TYPE_BUFFER) {
-		acpi_desc->nfit =
-			(struct acpi_nfit_header *)obj->buffer.pointer;
-		ret = acpi_nfit_init(acpi_desc, obj->buffer.length);
-		if (ret) {
-			/* Merge failed, restore old nfit, and exit */
-			acpi_desc->nfit = nfit_saved;
+		ret = acpi_nfit_init(acpi_desc, obj->buffer.pointer,
+				obj->buffer.length);
+		if (ret)
 			dev_err(dev, "failed to merge updated NFIT\n");
-		}
-	} else {
-		/* Bad _FIT, restore old nfit */
+	} else
 		dev_err(dev, "Invalid _FIT\n");
-	}
 	kfree(buf.pointer);
 
  out_unlock:
@@ -2693,18 +2759,23 @@ static __init int nfit_init(void)
 	acpi_str_to_uuid(UUID_NFIT_DIMM, nfit_uuid[NFIT_DEV_DIMM]);
 	acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE1, nfit_uuid[NFIT_DEV_DIMM_N_HPE1]);
 	acpi_str_to_uuid(UUID_NFIT_DIMM_N_HPE2, nfit_uuid[NFIT_DEV_DIMM_N_HPE2]);
+	acpi_str_to_uuid(UUID_NFIT_DIMM_N_MSFT, nfit_uuid[NFIT_DEV_DIMM_N_MSFT]);
 
 	nfit_wq = create_singlethread_workqueue("nfit");
 	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);
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
new file mode 100644
index 000000000000..4c745bf389fe
--- /dev/null
+++ b/drivers/acpi/nfit/mce.c
@@ -0,0 +1,89 @@
+/*
+ * NFIT - Machine Check Handler
+ *
+ * Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/notifier.h>
+#include <linux/acpi.h>
+#include <asm/mce.h>
+#include "nfit.h"
+
+static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
+			void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	struct acpi_nfit_desc *acpi_desc;
+	struct nfit_spa *nfit_spa;
+
+	/* We only care about memory errors */
+	if (!(mce->status & MCACOD))
+		return NOTIFY_DONE;
+
+	/*
+	 * mce->addr contains the physical addr accessed that caused the
+	 * machine check. We need to walk through the list of NFITs, and see
+	 * if any of them matches that address, and only then start a scrub.
+	 */
+	mutex_lock(&acpi_desc_lock);
+	list_for_each_entry(acpi_desc, &acpi_descs, list) {
+		struct device *dev = acpi_desc->dev;
+		int found_match = 0;
+
+		mutex_lock(&acpi_desc->init_mutex);
+		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;
+			/* find the spa that covers the mce addr */
+			if (spa->address > mce->addr)
+				continue;
+			if ((spa->address + spa->length - 1) < mce->addr)
+				continue;
+			found_match = 1;
+			dev_dbg(dev, "%s: addr in SPA %d (0x%llx, 0x%llx)\n",
+				__func__, spa->range_index, spa->address,
+				spa->length);
+			/*
+			 * We can break at the first match because we're going
+			 * to rescan all the SPA ranges. There shouldn't be any
+			 * aliasing anyway.
+			 */
+			break;
+		}
+		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)
+			acpi_nfit_ars_rescan(acpi_desc);
+	}
+
+	mutex_unlock(&acpi_desc_lock);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block nfit_mce_dec = {
+	.notifier_call	= nfit_handle_mce,
+};
+
+void nfit_mce_register(void)
+{
+	mce_register_decode_chain(&nfit_mce_dec);
+}
+
+void nfit_mce_unregister(void)
+{
+	mce_unregister_decode_chain(&nfit_mce_dec);
+}
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit/nfit.h
index 02b9ea1e8d2e..e894ded24d99 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -16,6 +16,7 @@
 #define __NFIT_H__
 #include <linux/workqueue.h>
 #include <linux/libnvdimm.h>
+#include <linux/ndctl.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
 #include <linux/acpi.h>
@@ -31,6 +32,9 @@
 #define UUID_NFIT_DIMM_N_HPE1 "9002c334-acf3-4c0e-9642-a235f0d53bc6"
 #define UUID_NFIT_DIMM_N_HPE2 "5008664b-b758-41a0-a03c-27c2f2d04f7e"
 
+/* https://msdn.microsoft.com/library/windows/hardware/mt604741 */
+#define UUID_NFIT_DIMM_N_MSFT "1ee68b36-d4bd-4a1a-9a16-4f8e53d46e05"
+
 #define ACPI_NFIT_MEM_FAILED_MASK (ACPI_NFIT_MEM_SAVE_FAILED \
 		| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
 		| ACPI_NFIT_MEM_NOT_ARMED)
@@ -40,6 +44,7 @@ enum nfit_uuids {
 	NFIT_DEV_DIMM = NVDIMM_FAMILY_INTEL,
 	NFIT_DEV_DIMM_N_HPE1 = NVDIMM_FAMILY_HPE1,
 	NFIT_DEV_DIMM_N_HPE2 = NVDIMM_FAMILY_HPE2,
+	NFIT_DEV_DIMM_N_MSFT = NVDIMM_FAMILY_MSFT,
 	NFIT_SPA_VOLATILE,
 	NFIT_SPA_PM,
 	NFIT_SPA_DCR,
@@ -74,37 +79,37 @@ enum {
 };
 
 struct nfit_spa {
-	struct acpi_nfit_system_address *spa;
 	struct list_head list;
 	struct nd_region *nd_region;
-	unsigned int ars_done:1;
+	unsigned int ars_required:1;
 	u32 clear_err_unit;
 	u32 max_ars;
+	struct acpi_nfit_system_address spa[0];
 };
 
 struct nfit_dcr {
-	struct acpi_nfit_control_region *dcr;
 	struct list_head list;
+	struct acpi_nfit_control_region dcr[0];
 };
 
 struct nfit_bdw {
-	struct acpi_nfit_data_region *bdw;
 	struct list_head list;
+	struct acpi_nfit_data_region bdw[0];
 };
 
 struct nfit_idt {
-	struct acpi_nfit_interleave *idt;
 	struct list_head list;
+	struct acpi_nfit_interleave idt[0];
 };
 
 struct nfit_flush {
-	struct acpi_nfit_flush_address *flush;
 	struct list_head list;
+	struct acpi_nfit_flush_address flush[0];
 };
 
 struct nfit_memdev {
-	struct acpi_nfit_memory_map *memdev;
 	struct list_head list;
+	struct acpi_nfit_memory_map memdev[0];
 };
 
 /* assembled tables for a given dimm/memory-device */
@@ -123,6 +128,7 @@ struct nfit_mem {
 	struct list_head list;
 	struct acpi_device *adev;
 	struct acpi_nfit_desc *acpi_desc;
+	struct resource *flush_wpq;
 	unsigned long dsm_mask;
 	int family;
 };
@@ -130,10 +136,7 @@ struct nfit_mem {
 struct acpi_nfit_desc {
 	struct nvdimm_bus_descriptor nd_desc;
 	struct acpi_table_header acpi_header;
-	struct acpi_nfit_header *nfit;
-	struct mutex spa_map_mutex;
 	struct mutex init_mutex;
-	struct list_head spa_maps;
 	struct list_head memdevs;
 	struct list_head flushes;
 	struct list_head dimms;
@@ -146,6 +149,9 @@ struct acpi_nfit_desc {
 	struct nd_cmd_ars_status *ars_status;
 	size_t ars_status_size;
 	struct work_struct work;
+	struct list_head list;
+	struct kernfs_node *scrub_count_state;
+	unsigned int scrub_count;
 	unsigned int cancel:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
@@ -161,7 +167,7 @@ enum nd_blk_mmio_selector {
 struct nd_blk_addr {
 	union {
 		void __iomem *base;
-		void __pmem  *aperture;
+		void *aperture;
 	};
 };
 
@@ -180,28 +186,26 @@ struct nfit_blk {
 	u64 bdw_offset; /* post interleave offset */
 	u64 stat_offset;
 	u64 cmd_offset;
-	void __iomem *nvdimm_flush;
 	u32 dimm_flags;
 };
 
-enum spa_map_type {
-	SPA_MAP_CONTROL,
-	SPA_MAP_APERTURE,
-};
-
-struct nfit_spa_mapping {
-	struct acpi_nfit_desc *acpi_desc;
-	struct acpi_nfit_system_address *spa;
-	struct list_head list;
-	struct kref kref;
-	enum spa_map_type type;
-	struct nd_blk_addr addr;
-};
+extern struct list_head acpi_descs;
+extern struct mutex acpi_desc_lock;
+int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc);
 
-static inline struct nfit_spa_mapping *to_spa_map(struct kref *kref)
+#ifdef CONFIG_X86_MCE
+void nfit_mce_register(void);
+void nfit_mce_unregister(void);
+#else
+static inline void nfit_mce_register(void)
 {
-	return container_of(kref, struct nfit_spa_mapping, kref);
 }
+static inline void nfit_mce_unregister(void)
+{
+}
+#endif
+
+int nfit_spa_type(struct acpi_nfit_system_address *spa);
 
 static inline struct acpi_nfit_memory_map *__to_nfit_memdev(
 		struct nfit_mem *nfit_mem)
@@ -218,6 +222,6 @@ 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 *nfit, acpi_size sz);
+int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz);
 void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev);
 #endif /* __NFIT_H__ */