Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "The bulk of this has been in multiple -next releases. There were a few
  late breaking fixes and small features that got added in the last
  couple days, but the whole set has received a build success
  notification from the kbuild robot.

  Change summary:

   - Region media error reporting: A libnvdimm region device is the
     parent to one or more namespaces. To date, media errors have been
     reported via the "badblocks" attribute attached to pmem block
     devices for namespaces in "raw" or "memory" mode. Given that
     namespaces can be in "device-dax" or "btt-sector" mode this new
     interface reports media errors generically, i.e. independent of
     namespace modes or state.

     This subsequently allows userspace tooling to craft "ACPI 6.1
     Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
     requests and submit them via the ioctl path for NVDIMM root bus
     devices.

   - Introduce 'struct dax_device' and 'struct dax_operations': Prompted
     by a request from Linus and feedback from Christoph this allows for
     dax capable drivers to publish their own custom dax operations.
     This fixes the broken assumption that all dax operations are
     related to a persistent memory device, and makes it easier for
     other architectures and platforms to add customized persistent
     memory support.

   - 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
     available for storage appliance applications to manually trigger
     memory controllers to drain write-pending buffers that would
     otherwise be flushed automatically by the platform ADR
     (asynchronous-DRAM-refresh) mechanism at a power loss event.
     Support for "locked" DIMMs is included to prevent namespaces from
     surfacing when the namespace label data area is locked. Finally,
     fixes for various reported deadlocks and crashes, also tagged for
     -stable.

   - ACPI / nfit driver updates: General updates of the nfit driver to
     add DSM command overrides, ACPI 6.1 health state flags support, DSM
     payload debug available by default, and various fixes.

  Acknowledgements that came after the branch was pushed:

   - commmit 565851c972b5 "device-dax: fix sysfs attribute deadlock":
     Tested-by: Yi Zhang <yizhan@redhat.com>

   - commit 23f498448362 "libnvdimm: rework region badblocks clearing"
     Tested-by: Toshi Kani <toshi.kani@hpe.com>"

* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
  libnvdimm, pfn: fix 'npfns' vs section alignment
  libnvdimm: handle locked label storage areas
  libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
  brd: fix uninitialized use of brd->dax_dev
  block, dax: use correct format string in bdev_dax_supported
  device-dax: fix sysfs attribute deadlock
  libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
  libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
  libnvdimm: rework region badblocks clearing
  acpi, nfit: kill ACPI_NFIT_DEBUG
  libnvdimm: fix clear length of nvdimm_forget_poison()
  libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
  libnvdimm, region: sysfs trigger for nvdimm_flush()
  libnvdimm: fix phys_addr for nvdimm_clear_poison
  x86, dax, pmem: remove indirection around memcpy_from_pmem()
  block: remove block_device_operations ->direct_access()
  block, dax: convert bdev_dax_supported() to dax_direct_access()
  filesystem-dax: convert to dax_direct_access()
  Revert "block: use DAX for partition table reads"
  ext2, ext4, xfs: retrieve dax_device for iomap operations
  ...

3 files changed, 168 insertions, 81 deletions

diff --git a/drivers/acpi/nfit/Kconfig b/drivers/acpi/nfit/Kconfig
index dd0d53c52552..6d3351452ea2 100644
--- a/drivers/acpi/nfit/Kconfig
+++ b/drivers/acpi/nfit/Kconfig
@@ -12,15 +12,3 @@ config ACPI_NFIT
 
 	  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/core.c b/drivers/acpi/nfit/core.c
index c8ea9d698cd0..656acb5d7166 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -49,7 +49,16 @@ MODULE_PARM_DESC(scrub_overflow_abort,
 static bool disable_vendor_specific;
 module_param(disable_vendor_specific, bool, S_IRUGO);
 MODULE_PARM_DESC(disable_vendor_specific,
-		"Limit commands to the publicly specified set\n");
+		"Limit commands to the publicly specified set");
+
+static unsigned long override_dsm_mask;
+module_param(override_dsm_mask, ulong, S_IRUGO);
+MODULE_PARM_DESC(override_dsm_mask, "Bitmask of allowed NVDIMM DSM functions");
+
+static int default_dsm_family = -1;
+module_param(default_dsm_family, int, S_IRUGO);
+MODULE_PARM_DESC(default_dsm_family,
+		"Try this DSM type first when identifying NVDIMM family");
 
 LIST_HEAD(acpi_descs);
 DEFINE_MUTEX(acpi_desc_lock);
@@ -175,14 +184,29 @@ static int xlat_bus_status(void *buf, unsigned int cmd, u32 status)
 	return 0;
 }
 
+static int xlat_nvdimm_status(void *buf, unsigned int cmd, u32 status)
+{
+	switch (cmd) {
+	case ND_CMD_GET_CONFIG_SIZE:
+		if (status >> 16 & ND_CONFIG_LOCKED)
+			return -EACCES;
+		break;
+	default:
+		break;
+	}
+
+	/* all other non-zero status results in an error */
+	if (status)
+		return -EIO;
+	return 0;
+}
+
 static int xlat_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd,
 		u32 status)
 {
 	if (!nvdimm)
 		return xlat_bus_status(buf, cmd, status);
-	if (status)
-		return -EIO;
-	return 0;
+	return xlat_nvdimm_status(buf, cmd, status);
 }
 
 int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
@@ -259,14 +283,11 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		in_buf.buffer.length = call_pkg->nd_size_in;
 	}
 
-	if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
-		dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n",
-				__func__, dimm_name, cmd, func,
-				in_buf.buffer.length);
-		print_hex_dump_debug("nvdimm in  ", DUMP_PREFIX_OFFSET, 4, 4,
+	dev_dbg(dev, "%s:%s cmd: %d: func: %d input length: %d\n",
+			__func__, dimm_name, cmd, func, in_buf.buffer.length);
+	print_hex_dump_debug("nvdimm in  ", DUMP_PREFIX_OFFSET, 4, 4,
 			in_buf.buffer.pointer,
 			min_t(u32, 256, in_buf.buffer.length), true);
-	}
 
 	out_obj = acpi_evaluate_dsm(handle, uuid, 1, func, &in_obj);
 	if (!out_obj) {
@@ -298,13 +319,11 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		goto out;
 	}
 
-	if (IS_ENABLED(CONFIG_ACPI_NFIT_DEBUG)) {
-		dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__,
-				dimm_name, cmd_name, out_obj->buffer.length);
-		print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4,
-				4, out_obj->buffer.pointer, min_t(u32, 128,
-					out_obj->buffer.length), true);
-	}
+	dev_dbg(dev, "%s:%s cmd: %s output length: %d\n", __func__, dimm_name,
+			cmd_name, out_obj->buffer.length);
+	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
+			out_obj->buffer.pointer,
+			min_t(u32, 128, out_obj->buffer.length), true);
 
 	for (i = 0, offset = 0; i < desc->out_num; i++) {
 		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
@@ -448,9 +467,9 @@ static bool add_memdev(struct acpi_nfit_desc *acpi_desc,
 	INIT_LIST_HEAD(&nfit_memdev->list);
 	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",
+	dev_dbg(dev, "%s: memdev handle: %#x spa: %d dcr: %d flags: %#x\n",
 			__func__, memdev->device_handle, memdev->range_index,
-			memdev->region_index);
+			memdev->region_index, memdev->flags);
 	return true;
 }
 
@@ -729,28 +748,38 @@ static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc,
 	}
 }
 
-static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
+static int __nfit_mem_init(struct acpi_nfit_desc *acpi_desc,
 		struct acpi_nfit_system_address *spa)
 {
 	struct nfit_mem *nfit_mem, *found;
 	struct nfit_memdev *nfit_memdev;
-	int type = nfit_spa_type(spa);
+	int type = spa ? nfit_spa_type(spa) : 0;
 
 	switch (type) {
 	case NFIT_SPA_DCR:
 	case NFIT_SPA_PM:
 		break;
 	default:
-		return 0;
+		if (spa)
+			return 0;
 	}
 
+	/*
+	 * This loop runs in two modes, when a dimm is mapped the loop
+	 * adds memdev associations to an existing dimm, or creates a
+	 * dimm. In the unmapped dimm case this loop sweeps for memdev
+	 * instances with an invalid / zero range_index and adds those
+	 * dimms without spa associations.
+	 */
 	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;
 
-		if (nfit_memdev->memdev->range_index != spa->range_index)
+		if (spa && nfit_memdev->memdev->range_index != spa->range_index)
+			continue;
+		if (!spa && nfit_memdev->memdev->range_index)
 			continue;
 		found = NULL;
 		dcr = nfit_memdev->memdev->region_index;
@@ -835,14 +864,15 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc,
 				break;
 			}
 			nfit_mem_init_bdw(acpi_desc, nfit_mem, spa);
-		} else {
+		} else if (type == NFIT_SPA_PM) {
 			/*
 			 * A single dimm may belong to multiple SPA-PM
 			 * ranges, record at least one in addition to
 			 * any SPA-DCR range.
 			 */
 			nfit_mem->memdev_pmem = nfit_memdev->memdev;
-		}
+		} else
+			nfit_mem->memdev_dcr = nfit_memdev->memdev;
 	}
 
 	return 0;
@@ -866,6 +896,8 @@ static int nfit_mem_cmp(void *priv, struct list_head *_a, struct list_head *_b)
 static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nfit_spa *nfit_spa;
+	int rc;
+
 
 	/*
 	 * For each SPA-DCR or SPA-PMEM address range find its
@@ -876,13 +908,20 @@ static int nfit_mem_init(struct acpi_nfit_desc *acpi_desc)
 	 * BDWs are optional.
 	 */
 	list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
-		int rc;
-
-		rc = nfit_mem_dcr_init(acpi_desc, nfit_spa->spa);
+		rc = __nfit_mem_init(acpi_desc, nfit_spa->spa);
 		if (rc)
 			return rc;
 	}
 
+	/*
+	 * If a DIMM has failed to be mapped into SPA there will be no
+	 * SPA entries above. Find and register all the unmapped DIMMs
+	 * for reporting and recovery purposes.
+	 */
+	rc = __nfit_mem_init(acpi_desc, NULL);
+	if (rc)
+		return rc;
+
 	list_sort(NULL, &acpi_desc->dimms, nfit_mem_cmp);
 
 	return 0;
@@ -1237,12 +1276,14 @@ static ssize_t flags_show(struct device *dev,
 {
 	u16 flags = to_nfit_memdev(dev)->flags;
 
-	return sprintf(buf, "%s%s%s%s%s\n",
+	return sprintf(buf, "%s%s%s%s%s%s%s\n",
 		flags & ACPI_NFIT_MEM_SAVE_FAILED ? "save_fail " : "",
 		flags & ACPI_NFIT_MEM_RESTORE_FAILED ? "restore_fail " : "",
 		flags & ACPI_NFIT_MEM_FLUSH_FAILED ? "flush_fail " : "",
 		flags & ACPI_NFIT_MEM_NOT_ARMED ? "not_armed " : "",
-		flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : "");
+		flags & ACPI_NFIT_MEM_HEALTH_OBSERVED ? "smart_event " : "",
+		flags & ACPI_NFIT_MEM_MAP_FAILED ? "map_fail " : "",
+		flags & ACPI_NFIT_MEM_HEALTH_ENABLED ? "smart_notify " : "");
 }
 static DEVICE_ATTR_RO(flags);
 
@@ -1290,8 +1331,16 @@ static umode_t acpi_nfit_dimm_attr_visible(struct kobject *kobj,
 	struct device *dev = container_of(kobj, struct device, kobj);
 	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	if (!to_nfit_dcr(dev))
+	if (!to_nfit_dcr(dev)) {
+		/* Without a dcr only the memdev attributes can be surfaced */
+		if (a == &dev_attr_handle.attr || a == &dev_attr_phys_id.attr
+				|| a == &dev_attr_flags.attr
+				|| a == &dev_attr_family.attr
+				|| a == &dev_attr_dsm_mask.attr)
+			return a->mode;
 		return 0;
+	}
+
 	if (a == &dev_attr_format1.attr && num_nvdimm_formats(nvdimm) <= 1)
 		return 0;
 	return a->mode;
@@ -1368,6 +1417,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	unsigned long dsm_mask;
 	const u8 *uuid;
 	int i;
+	int family = -1;
 
 	/* nfit test assumes 1:1 relationship between commands and dsms */
 	nfit_mem->dsm_mask = acpi_desc->dimm_cmd_force_en;
@@ -1398,11 +1448,14 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	 */
 	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++)
 		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
-			break;
+			if (family < 0 || i == default_dsm_family)
+				family = i;
 
 	/* limit the supported commands to those that are publicly documented */
-	nfit_mem->family = i;
-	if (nfit_mem->family == NVDIMM_FAMILY_INTEL) {
+	nfit_mem->family = family;
+	if (override_dsm_mask && !disable_vendor_specific)
+		dsm_mask = override_dsm_mask;
+	else if (nfit_mem->family == NVDIMM_FAMILY_INTEL) {
 		dsm_mask = 0x3fe;
 		if (disable_vendor_specific)
 			dsm_mask &= ~(1 << ND_CMD_VENDOR);
@@ -1462,6 +1515,7 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
 		struct acpi_nfit_flush_address *flush;
 		unsigned long flags = 0, cmd_mask;
+		struct nfit_memdev *nfit_memdev;
 		u32 device_handle;
 		u16 mem_flags;
 
@@ -1473,11 +1527,22 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		}
 
 		if (nfit_mem->bdw && nfit_mem->memdev_pmem)
-			flags |= NDD_ALIASING;
+			set_bit(NDD_ALIASING, &flags);
+
+		/* collate flags across all memdevs for this dimm */
+		list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
+			struct acpi_nfit_memory_map *dimm_memdev;
+
+			dimm_memdev = __to_nfit_memdev(nfit_mem);
+			if (dimm_memdev->device_handle
+					!= nfit_memdev->memdev->device_handle)
+				continue;
+			dimm_memdev->flags |= nfit_memdev->memdev->flags;
+		}
 
 		mem_flags = __to_nfit_memdev(nfit_mem)->flags;
 		if (mem_flags & ACPI_NFIT_MEM_NOT_ARMED)
-			flags |= NDD_UNARMED;
+			set_bit(NDD_UNARMED, &flags);
 
 		rc = acpi_nfit_add_dimm(acpi_desc, nfit_mem, device_handle);
 		if (rc)
@@ -1507,12 +1572,13 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		if ((mem_flags & ACPI_NFIT_MEM_FAILED_MASK) == 0)
 			continue;
 
-		dev_info(acpi_desc->dev, "%s flags:%s%s%s%s\n",
+		dev_info(acpi_desc->dev, "%s flags:%s%s%s%s%s\n",
 				nvdimm_name(nvdimm),
 		  mem_flags & ACPI_NFIT_MEM_SAVE_FAILED ? " save_fail" : "",
 		  mem_flags & ACPI_NFIT_MEM_RESTORE_FAILED ? " restore_fail":"",
 		  mem_flags & ACPI_NFIT_MEM_FLUSH_FAILED ? " flush_fail" : "",
-		  mem_flags & ACPI_NFIT_MEM_NOT_ARMED ? " not_armed" : "");
+		  mem_flags & ACPI_NFIT_MEM_NOT_ARMED ? " not_armed" : "",
+		  mem_flags & ACPI_NFIT_MEM_MAP_FAILED ? " map_fail" : "");
 
 	}
 
@@ -1783,8 +1849,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
 				mmio_flush_range((void __force *)
 					mmio->addr.aperture + offset, c);
 
-			memcpy_from_pmem(iobuf + copied,
-					mmio->addr.aperture + offset, c);
+			memcpy(iobuf + copied, mmio->addr.aperture + offset, c);
 		}
 
 		copied += c;
@@ -2525,6 +2590,7 @@ static void acpi_nfit_scrub(struct work_struct *work)
 			acpi_nfit_register_region(acpi_desc, nfit_spa);
 		}
 	}
+	acpi_desc->init_complete = 1;
 
 	list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
 		acpi_nfit_async_scrub(acpi_desc, nfit_spa);
@@ -2547,7 +2613,8 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
 				return rc;
 		}
 
-	queue_work(nfit_wq, &acpi_desc->work);
+	if (!acpi_desc->cancel)
+		queue_work(nfit_wq, &acpi_desc->work);
 	return 0;
 }
 
@@ -2593,32 +2660,11 @@ static int acpi_nfit_desc_init_scrub_attr(struct acpi_nfit_desc *acpi_desc)
 	return 0;
 }
 
-static void acpi_nfit_destruct(void *data)
+static void acpi_nfit_unregister(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)
@@ -2636,7 +2682,7 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
 		if (!acpi_desc->nvdimm_bus)
 			return -ENOMEM;
 
-		rc = devm_add_action_or_reset(dev, acpi_nfit_destruct,
+		rc = devm_add_action_or_reset(dev, acpi_nfit_unregister,
 				acpi_desc);
 		if (rc)
 			return rc;
@@ -2728,6 +2774,13 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	device_lock(dev);
 	device_unlock(dev);
 
+	/* bounce the init_mutex to make init_complete valid */
+	mutex_lock(&acpi_desc->init_mutex);
+	if (acpi_desc->cancel || acpi_desc->init_complete) {
+		mutex_unlock(&acpi_desc->init_mutex);
+		return 0;
+	}
+
 	/*
 	 * Scrub work could take 10s of seconds, userspace may give up so we
 	 * need to be interruptible while waiting.
@@ -2735,6 +2788,7 @@ static int acpi_nfit_flush_probe(struct nvdimm_bus_descriptor *nd_desc)
 	INIT_WORK_ONSTACK(&flush.work, flush_probe);
 	COMPLETION_INITIALIZER_ONSTACK(flush.cmp);
 	queue_work(nfit_wq, &flush.work);
+	mutex_unlock(&acpi_desc->init_mutex);
 
 	rc = wait_for_completion_interruptible(&flush.cmp);
 	cancel_work_sync(&flush.work);
@@ -2771,10 +2825,12 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
 	if (work_busy(&acpi_desc->work))
 		return -EBUSY;
 
-	if (acpi_desc->cancel)
+	mutex_lock(&acpi_desc->init_mutex);
+	if (acpi_desc->cancel) {
+		mutex_unlock(&acpi_desc->init_mutex);
 		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;
 
@@ -2818,6 +2874,40 @@ void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
 }
 EXPORT_SYMBOL_GPL(acpi_nfit_desc_init);
 
+static void acpi_nfit_put_table(void *table)
+{
+	acpi_put_table(table);
+}
+
+void acpi_nfit_shutdown(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);
+	list_del(&acpi_desc->list);
+	mutex_unlock(&acpi_desc_lock);
+
+	mutex_lock(&acpi_desc->init_mutex);
+	acpi_desc->cancel = 1;
+	mutex_unlock(&acpi_desc->init_mutex);
+
+	/*
+	 * 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);
+}
+EXPORT_SYMBOL_GPL(acpi_nfit_shutdown);
+
 static int acpi_nfit_add(struct acpi_device *adev)
 {
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -2834,6 +2924,10 @@ static int acpi_nfit_add(struct acpi_device *adev)
 		dev_dbg(dev, "failed to find NFIT at startup\n");
 		return 0;
 	}
+
+	rc = devm_add_action_or_reset(dev, acpi_nfit_put_table, tbl);
+	if (rc)
+		return rc;
 	sz = tbl->length;
 
 	acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
@@ -2861,12 +2955,15 @@ static int acpi_nfit_add(struct acpi_device *adev)
 		rc = acpi_nfit_init(acpi_desc, (void *) tbl
 				+ sizeof(struct acpi_table_nfit),
 				sz - sizeof(struct acpi_table_nfit));
-	return rc;
+
+	if (rc)
+		return rc;
+	return devm_add_action_or_reset(dev, acpi_nfit_shutdown, acpi_desc);
 }
 
 static int acpi_nfit_remove(struct acpi_device *adev)
 {
-	/* see acpi_nfit_destruct */
+	/* see acpi_nfit_unregister */
 	return 0;
 }
 
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index fc29c2e9832e..58fb7d68e04a 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -37,7 +37,7 @@
 
 #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)
+		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
 enum nfit_uuids {
 	/* for simplicity alias the uuid index with the family id */
@@ -163,6 +163,7 @@ struct acpi_nfit_desc {
 	unsigned int scrub_count;
 	unsigned int scrub_mode;
 	unsigned int cancel:1;
+	unsigned int init_complete:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -238,6 +239,7 @@ 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_shutdown(void *data);
 void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event);
 void __acpi_nvdimm_notify(struct device *dev, u32 event);
 int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,