Merge tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm and dax updates from Dan Williams:
 "Save for a few late fixes, all of these commits have shipped in -next
  releases since before the merge window opened, and 0day has given a
  build success notification.

  The ext4 touches came from Jan, and the xfs touches have Darrick's
  reviewed-by. An xfstest for the MAP_SYNC feature has been through
  a few round of reviews and is on track to be merged.

   - Introduce MAP_SYNC and MAP_SHARED_VALIDATE, a mechanism to enable
     'userspace flush' of persistent memory updates via filesystem-dax
     mappings. It arranges for any filesystem metadata updates that may
     be required to satisfy a write fault to also be flushed ("on disk")
     before the kernel returns to userspace from the fault handler.
     Effectively every write-fault that dirties metadata completes an
     fsync() before returning from the fault handler. The new
     MAP_SHARED_VALIDATE mapping type guarantees that the MAP_SYNC flag
     is validated as supported by the filesystem's ->mmap() file
     operation.

   - Add support for the standard ACPI 6.2 label access methods that
     replace the NVDIMM_FAMILY_INTEL (vendor specific) label methods.
     This enables interoperability with environments that only implement
     the standardized methods.

   - Add support for the ACPI 6.2 NVDIMM media error injection methods.

   - Add support for the NVDIMM_FAMILY_INTEL v1.6 DIMM commands for
     latch last shutdown status, firmware update, SMART error injection,
     and SMART alarm threshold control.

   - Cleanup physical address information disclosures to be root-only.

   - Fix revalidation of the DIMM "locked label area" status to support
     dynamic unlock of the label area.

   - Expand unit test infrastructure to mock the ACPI 6.2 Translate SPA
     (system-physical-address) command and error injection commands.

  Acknowledgements that came after the commits were pushed to -next:

   - 957ac8c421ad ("dax: fix PMD faults on zero-length files"):
       Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>

   - a39e596baa07 ("xfs: support for synchronous DAX faults") and
     7b565c9f965b ("xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()")
        Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>"

* tag 'libnvdimm-for-4.15' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (49 commits)
  acpi, nfit: add 'Enable Latch System Shutdown Status' command support
  dax: fix general protection fault in dax_alloc_inode
  dax: fix PMD faults on zero-length files
  dax: stop requiring a live device for dax_flush()
  brd: remove dax support
  dax: quiet bdev_dax_supported()
  fs, dax: unify IOMAP_F_DIRTY read vs write handling policy in the dax core
  tools/testing/nvdimm: unit test clear-error commands
  acpi, nfit: validate commands against the device type
  tools/testing/nvdimm: stricter bounds checking for error injection commands
  xfs: support for synchronous DAX faults
  xfs: Implement xfs_filemap_pfn_mkwrite() using __xfs_filemap_fault()
  ext4: Support for synchronous DAX faults
  ext4: Simplify error handling in ext4_dax_huge_fault()
  dax: Implement dax_finish_sync_fault()
  dax, iomap: Add support for synchronous faults
  mm: Define MAP_SYNC and VM_SYNC flags
  dax: Allow tuning whether dax_insert_mapping_entry() dirties entry
  dax: Allow dax_iomap_fault() to return pfn
  dax: Fix comment describing dax_iomap_fault()
  ...

19 files changed, 659 insertions, 382 deletions

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 9c2c49b6a240..ff2580e7611d 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -183,13 +183,33 @@ 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)
+#define ACPI_LABELS_LOCKED 3
+
+static int xlat_nvdimm_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd,
+		u32 status)
 {
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
+
 	switch (cmd) {
 	case ND_CMD_GET_CONFIG_SIZE:
+		/*
+		 * In the _LSI, _LSR, _LSW case the locked status is
+		 * communicated via the read/write commands
+		 */
+		if (nfit_mem->has_lsi)
+			break;
+
 		if (status >> 16 & ND_CONFIG_LOCKED)
 			return -EACCES;
 		break;
+	case ND_CMD_GET_CONFIG_DATA:
+		if (nfit_mem->has_lsr && status == ACPI_LABELS_LOCKED)
+			return -EACCES;
+		break;
+	case ND_CMD_SET_CONFIG_DATA:
+		if (nfit_mem->has_lsw && status == ACPI_LABELS_LOCKED)
+			return -EACCES;
+		break;
 	default:
 		break;
 	}
@@ -205,13 +225,182 @@ static int xlat_status(struct nvdimm *nvdimm, void *buf, unsigned int cmd,
 {
 	if (!nvdimm)
 		return xlat_bus_status(buf, cmd, status);
-	return xlat_nvdimm_status(buf, cmd, status);
+	return xlat_nvdimm_status(nvdimm, buf, cmd, status);
+}
+
+/* convert _LS{I,R} packages to the buffer object acpi_nfit_ctl expects */
+static union acpi_object *pkg_to_buf(union acpi_object *pkg)
+{
+	int i;
+	void *dst;
+	size_t size = 0;
+	union acpi_object *buf = NULL;
+
+	if (pkg->type != ACPI_TYPE_PACKAGE) {
+		WARN_ONCE(1, "BIOS bug, unexpected element type: %d\n",
+				pkg->type);
+		goto err;
+	}
+
+	for (i = 0; i < pkg->package.count; i++) {
+		union acpi_object *obj = &pkg->package.elements[i];
+
+		if (obj->type == ACPI_TYPE_INTEGER)
+			size += 4;
+		else if (obj->type == ACPI_TYPE_BUFFER)
+			size += obj->buffer.length;
+		else {
+			WARN_ONCE(1, "BIOS bug, unexpected element type: %d\n",
+					obj->type);
+			goto err;
+		}
+	}
+
+	buf = ACPI_ALLOCATE(sizeof(*buf) + size);
+	if (!buf)
+		goto err;
+
+	dst = buf + 1;
+	buf->type = ACPI_TYPE_BUFFER;
+	buf->buffer.length = size;
+	buf->buffer.pointer = dst;
+	for (i = 0; i < pkg->package.count; i++) {
+		union acpi_object *obj = &pkg->package.elements[i];
+
+		if (obj->type == ACPI_TYPE_INTEGER) {
+			memcpy(dst, &obj->integer.value, 4);
+			dst += 4;
+		} else if (obj->type == ACPI_TYPE_BUFFER) {
+			memcpy(dst, obj->buffer.pointer, obj->buffer.length);
+			dst += obj->buffer.length;
+		}
+	}
+err:
+	ACPI_FREE(pkg);
+	return buf;
+}
+
+static union acpi_object *int_to_buf(union acpi_object *integer)
+{
+	union acpi_object *buf = ACPI_ALLOCATE(sizeof(*buf) + 4);
+	void *dst = NULL;
+
+	if (!buf)
+		goto err;
+
+	if (integer->type != ACPI_TYPE_INTEGER) {
+		WARN_ONCE(1, "BIOS bug, unexpected element type: %d\n",
+				integer->type);
+		goto err;
+	}
+
+	dst = buf + 1;
+	buf->type = ACPI_TYPE_BUFFER;
+	buf->buffer.length = 4;
+	buf->buffer.pointer = dst;
+	memcpy(dst, &integer->integer.value, 4);
+err:
+	ACPI_FREE(integer);
+	return buf;
+}
+
+static union acpi_object *acpi_label_write(acpi_handle handle, u32 offset,
+		u32 len, void *data)
+{
+	acpi_status rc;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_object_list input = {
+		.count = 3,
+		.pointer = (union acpi_object []) {
+			[0] = {
+				.integer.type = ACPI_TYPE_INTEGER,
+				.integer.value = offset,
+			},
+			[1] = {
+				.integer.type = ACPI_TYPE_INTEGER,
+				.integer.value = len,
+			},
+			[2] = {
+				.buffer.type = ACPI_TYPE_BUFFER,
+				.buffer.pointer = data,
+				.buffer.length = len,
+			},
+		},
+	};
+
+	rc = acpi_evaluate_object(handle, "_LSW", &input, &buf);
+	if (ACPI_FAILURE(rc))
+		return NULL;
+	return int_to_buf(buf.pointer);
+}
+
+static union acpi_object *acpi_label_read(acpi_handle handle, u32 offset,
+		u32 len)
+{
+	acpi_status rc;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_object_list input = {
+		.count = 2,
+		.pointer = (union acpi_object []) {
+			[0] = {
+				.integer.type = ACPI_TYPE_INTEGER,
+				.integer.value = offset,
+			},
+			[1] = {
+				.integer.type = ACPI_TYPE_INTEGER,
+				.integer.value = len,
+			},
+		},
+	};
+
+	rc = acpi_evaluate_object(handle, "_LSR", &input, &buf);
+	if (ACPI_FAILURE(rc))
+		return NULL;
+	return pkg_to_buf(buf.pointer);
+}
+
+static union acpi_object *acpi_label_info(acpi_handle handle)
+{
+	acpi_status rc;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+
+	rc = acpi_evaluate_object(handle, "_LSI", NULL, &buf);
+	if (ACPI_FAILURE(rc))
+		return NULL;
+	return pkg_to_buf(buf.pointer);
+}
+
+static u8 nfit_dsm_revid(unsigned family, unsigned func)
+{
+	static const u8 revid_table[NVDIMM_FAMILY_MAX+1][32] = {
+		[NVDIMM_FAMILY_INTEL] = {
+			[NVDIMM_INTEL_GET_MODES] = 2,
+			[NVDIMM_INTEL_GET_FWINFO] = 2,
+			[NVDIMM_INTEL_START_FWUPDATE] = 2,
+			[NVDIMM_INTEL_SEND_FWUPDATE] = 2,
+			[NVDIMM_INTEL_FINISH_FWUPDATE] = 2,
+			[NVDIMM_INTEL_QUERY_FWUPDATE] = 2,
+			[NVDIMM_INTEL_SET_THRESHOLD] = 2,
+			[NVDIMM_INTEL_INJECT_ERROR] = 2,
+		},
+	};
+	u8 id;
+
+	if (family > NVDIMM_FAMILY_MAX)
+		return 0;
+	if (func > 31)
+		return 0;
+	id = revid_table[family][func];
+	if (id == 0)
+		return 1; /* default */
+	return id;
 }
 
 int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc)
 {
 	struct acpi_nfit_desc *acpi_desc = to_acpi_nfit_desc(nd_desc);
+	struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 	union acpi_object in_obj, in_buf, *out_obj;
 	const struct nd_cmd_desc *desc = NULL;
 	struct device *dev = acpi_desc->dev;
@@ -235,7 +424,6 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	}
 
 	if (nvdimm) {
-		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_device *adev = nfit_mem->adev;
 
 		if (!adev)
@@ -294,7 +482,29 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 			in_buf.buffer.pointer,
 			min_t(u32, 256, in_buf.buffer.length), true);
 
-	out_obj = acpi_evaluate_dsm(handle, guid, 1, func, &in_obj);
+	/* call the BIOS, prefer the named methods over _DSM if available */
+	if (nvdimm && cmd == ND_CMD_GET_CONFIG_SIZE && nfit_mem->has_lsi)
+		out_obj = acpi_label_info(handle);
+	else if (nvdimm && cmd == ND_CMD_GET_CONFIG_DATA && nfit_mem->has_lsr) {
+		struct nd_cmd_get_config_data_hdr *p = buf;
+
+		out_obj = acpi_label_read(handle, p->in_offset, p->in_length);
+	} else if (nvdimm && cmd == ND_CMD_SET_CONFIG_DATA
+			&& nfit_mem->has_lsw) {
+		struct nd_cmd_set_config_hdr *p = buf;
+
+		out_obj = acpi_label_write(handle, p->in_offset, p->in_length,
+				p->in_buf);
+	} else {
+		u8 revid;
+
+		if (nvdimm)
+			revid = nfit_dsm_revid(nfit_mem->family, func);
+		else
+			revid = 1;
+		out_obj = acpi_evaluate_dsm(handle, guid, revid, func, &in_obj);
+	}
+
 	if (!out_obj) {
 		dev_dbg(dev, "%s:%s _DSM failed cmd: %s\n", __func__, dimm_name,
 				cmd_name);
@@ -356,8 +566,10 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	 * Set fw_status for all the commands with a known format to be
 	 * later interpreted by xlat_status().
 	 */
-	if (i >= 1 && ((cmd >= ND_CMD_ARS_CAP && cmd <= ND_CMD_CLEAR_ERROR)
-			|| (cmd >= ND_CMD_SMART && cmd <= ND_CMD_VENDOR)))
+	if (i >= 1 && ((!nvdimm && cmd >= ND_CMD_ARS_CAP
+					&& cmd <= ND_CMD_CLEAR_ERROR)
+				|| (nvdimm && cmd >= ND_CMD_SMART
+					&& cmd <= ND_CMD_VENDOR)))
 		fw_status = *(u32 *) out_obj->buffer.pointer;
 
 	if (offset + in_buf.buffer.length < buf_len) {
@@ -1431,6 +1643,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 {
 	struct acpi_device *adev, *adev_dimm;
 	struct device *dev = acpi_desc->dev;
+	union acpi_object *obj;
 	unsigned long dsm_mask;
 	const guid_t *guid;
 	int i;
@@ -1463,7 +1676,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	 * different command sets.  Note, that checking for function0 (bit0)
 	 * tells us if any commands are reachable through this GUID.
 	 */
-	for (i = NVDIMM_FAMILY_INTEL; i <= NVDIMM_FAMILY_MSFT; i++)
+	for (i = 0; i <= NVDIMM_FAMILY_MAX; i++)
 		if (acpi_check_dsm(adev_dimm->handle, to_nfit_uuid(i), 1, 1))
 			if (family < 0 || i == default_dsm_family)
 				family = i;
@@ -1473,7 +1686,7 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	if (override_dsm_mask && !disable_vendor_specific)
 		dsm_mask = override_dsm_mask;
 	else if (nfit_mem->family == NVDIMM_FAMILY_INTEL) {
-		dsm_mask = 0x3fe;
+		dsm_mask = NVDIMM_INTEL_CMDMASK;
 		if (disable_vendor_specific)
 			dsm_mask &= ~(1 << ND_CMD_VENDOR);
 	} else if (nfit_mem->family == NVDIMM_FAMILY_HPE1) {
@@ -1493,9 +1706,32 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 
 	guid = to_nfit_uuid(nfit_mem->family);
 	for_each_set_bit(i, &dsm_mask, BITS_PER_LONG)
-		if (acpi_check_dsm(adev_dimm->handle, guid, 1, 1ULL << i))
+		if (acpi_check_dsm(adev_dimm->handle, guid,
+					nfit_dsm_revid(nfit_mem->family, i),
+					1ULL << i))
 			set_bit(i, &nfit_mem->dsm_mask);
 
+	obj = acpi_label_info(adev_dimm->handle);
+	if (obj) {
+		ACPI_FREE(obj);
+		nfit_mem->has_lsi = 1;
+		dev_dbg(dev, "%s: has _LSI\n", dev_name(&adev_dimm->dev));
+	}
+
+	obj = acpi_label_read(adev_dimm->handle, 0, 0);
+	if (obj) {
+		ACPI_FREE(obj);
+		nfit_mem->has_lsr = 1;
+		dev_dbg(dev, "%s: has _LSR\n", dev_name(&adev_dimm->dev));
+	}
+
+	obj = acpi_label_write(adev_dimm->handle, 0, 0, NULL);
+	if (obj) {
+		ACPI_FREE(obj);
+		nfit_mem->has_lsw = 1;
+		dev_dbg(dev, "%s: has _LSW\n", dev_name(&adev_dimm->dev));
+	}
+
 	return 0;
 }
 
@@ -1571,8 +1807,21 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 		 * userspace interface.
 		 */
 		cmd_mask = 1UL << ND_CMD_CALL;
-		if (nfit_mem->family == NVDIMM_FAMILY_INTEL)
-			cmd_mask |= nfit_mem->dsm_mask;
+		if (nfit_mem->family == NVDIMM_FAMILY_INTEL) {
+			/*
+			 * These commands have a 1:1 correspondence
+			 * between DSM payload and libnvdimm ioctl
+			 * payload format.
+			 */
+			cmd_mask |= nfit_mem->dsm_mask & NVDIMM_STANDARD_CMDMASK;
+		}
+
+		if (nfit_mem->has_lsi)
+			set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask);
+		if (nfit_mem->has_lsr)
+			set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask);
+		if (nfit_mem->has_lsw)
+			set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask);
 
 		flush = nfit_mem->nfit_flush ? nfit_mem->nfit_flush->flush
 			: NULL;
@@ -1645,6 +1894,7 @@ static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
 	int i;
 
 	nd_desc->cmd_mask = acpi_desc->bus_cmd_force_en;
+	nd_desc->bus_dsm_mask = acpi_desc->bus_nfit_cmd_force_en;
 	adev = to_acpi_dev(acpi_desc);
 	if (!adev)
 		return;
@@ -2239,7 +2489,7 @@ static int ars_status_process_records(struct acpi_nfit_desc *acpi_desc,
 		if (ars_status->out_length
 				< 44 + sizeof(struct nd_ars_record) * (i + 1))
 			break;
-		rc = nvdimm_bus_add_poison(nvdimm_bus,
+		rc = nvdimm_bus_add_badrange(nvdimm_bus,
 				ars_status->records[i].err_address,
 				ars_status->records[i].length);
 		if (rc)
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index feeb95d574fa..b92921439657 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -67,7 +67,7 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 			continue;
 
 		/* If this fails due to an -ENOMEM, there is little we can do */
-		nvdimm_bus_add_poison(acpi_desc->nvdimm_bus,
+		nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
 				ALIGN(mce->addr, L1_CACHE_BYTES),
 				L1_CACHE_BYTES);
 		nvdimm_region_notify(nfit_spa->nd_region,
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 54292db61262..f0cf18b2da8b 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -24,7 +24,7 @@
 /* ACPI 6.1 */
 #define UUID_NFIT_BUS "2f10e7a4-9e91-11e4-89d3-123b93f75cba"
 
-/* http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf */
+/* http://pmem.io/documents/NVDIMM_DSM_Interface-V1.6.pdf */
 #define UUID_NFIT_DIMM "4309ac30-0d11-11e4-9191-0800200c9a66"
 
 /* https://github.com/HewlettPackard/hpe-nvm/blob/master/Documentation/ */
@@ -38,6 +38,37 @@
 		| ACPI_NFIT_MEM_RESTORE_FAILED | ACPI_NFIT_MEM_FLUSH_FAILED \
 		| ACPI_NFIT_MEM_NOT_ARMED | ACPI_NFIT_MEM_MAP_FAILED)
 
+#define NVDIMM_FAMILY_MAX NVDIMM_FAMILY_MSFT
+
+#define NVDIMM_STANDARD_CMDMASK \
+(1 << ND_CMD_SMART | 1 << ND_CMD_SMART_THRESHOLD | 1 << ND_CMD_DIMM_FLAGS \
+ | 1 << ND_CMD_GET_CONFIG_SIZE | 1 << ND_CMD_GET_CONFIG_DATA \
+ | 1 << ND_CMD_SET_CONFIG_DATA | 1 << ND_CMD_VENDOR_EFFECT_LOG_SIZE \
+ | 1 << ND_CMD_VENDOR_EFFECT_LOG | 1 << ND_CMD_VENDOR)
+
+/*
+ * Command numbers that the kernel needs to know about to handle
+ * non-default DSM revision ids
+ */
+enum nvdimm_family_cmds {
+	NVDIMM_INTEL_LATCH_SHUTDOWN = 10,
+	NVDIMM_INTEL_GET_MODES = 11,
+	NVDIMM_INTEL_GET_FWINFO = 12,
+	NVDIMM_INTEL_START_FWUPDATE = 13,
+	NVDIMM_INTEL_SEND_FWUPDATE = 14,
+	NVDIMM_INTEL_FINISH_FWUPDATE = 15,
+	NVDIMM_INTEL_QUERY_FWUPDATE = 16,
+	NVDIMM_INTEL_SET_THRESHOLD = 17,
+	NVDIMM_INTEL_INJECT_ERROR = 18,
+};
+
+#define NVDIMM_INTEL_CMDMASK \
+(NVDIMM_STANDARD_CMDMASK | 1 << NVDIMM_INTEL_GET_MODES \
+ | 1 << NVDIMM_INTEL_GET_FWINFO | 1 << NVDIMM_INTEL_START_FWUPDATE \
+ | 1 << NVDIMM_INTEL_SEND_FWUPDATE | 1 << NVDIMM_INTEL_FINISH_FWUPDATE \
+ | 1 << NVDIMM_INTEL_QUERY_FWUPDATE | 1 << NVDIMM_INTEL_SET_THRESHOLD \
+ | 1 << NVDIMM_INTEL_INJECT_ERROR | 1 << NVDIMM_INTEL_LATCH_SHUTDOWN)
+
 enum nfit_uuids {
 	/* for simplicity alias the uuid index with the family id */
 	NFIT_DEV_DIMM = NVDIMM_FAMILY_INTEL,
@@ -140,6 +171,9 @@ struct nfit_mem {
 	struct resource *flush_wpq;
 	unsigned long dsm_mask;
 	int family;
+	u32 has_lsi:1;
+	u32 has_lsr:1;
+	u32 has_lsw:1;
 };
 
 struct acpi_nfit_desc {
@@ -167,6 +201,7 @@ struct acpi_nfit_desc {
 	unsigned int init_complete:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
+	unsigned long bus_nfit_cmd_force_en;
 	int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa,
 			void *iobuf, u64 len, int rw);
 };
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 923b417eaf4c..40579d0cb3d1 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -302,7 +302,6 @@ config BLK_DEV_SX8
 
 config BLK_DEV_RAM
 	tristate "RAM block device support"
-	select DAX if BLK_DEV_RAM_DAX
 	---help---
 	  Saying Y here will allow you to use a portion of your RAM memory as
 	  a block device, so that you can make file systems on it, read and
@@ -338,17 +337,6 @@ config BLK_DEV_RAM_SIZE
 	  The default value is 4096 kilobytes. Only change this if you know
 	  what you are doing.
 
-config BLK_DEV_RAM_DAX
-	bool "Support Direct Access (DAX) to RAM block devices"
-	depends on BLK_DEV_RAM && FS_DAX
-	default n
-	help
-	  Support filesystems using DAX to access RAM block devices.  This
-	  avoids double-buffering data in the page cache before copying it
-	  to the block device.  Answering Y will slightly enlarge the kernel,
-	  and will prevent RAM block device backing store memory from being
-	  allocated from highmem (only a problem for highmem systems).
-
 config CDROM_PKTCDVD
 	tristate "Packet writing on CD/DVD media (DEPRECATED)"
 	depends on !UML
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 588360d79fca..8028a3a7e7fd 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -21,11 +21,6 @@
 #include <linux/fs.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-#include <linux/pfn_t.h>
-#include <linux/dax.h>
-#include <linux/uio.h>
-#endif
 
 #include <linux/uaccess.h>
 
@@ -45,9 +40,6 @@ struct brd_device {
 
 	struct request_queue	*brd_queue;
 	struct gendisk		*brd_disk;
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-	struct dax_device	*dax_dev;
-#endif
 	struct list_head	brd_list;
 
 	/*
@@ -112,9 +104,6 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 	 * restriction might be able to be lifted.
 	 */
 	gfp_flags = GFP_NOIO | __GFP_ZERO;
-#ifndef CONFIG_BLK_DEV_RAM_DAX
-	gfp_flags |= __GFP_HIGHMEM;
-#endif
 	page = alloc_page(gfp_flags);
 	if (!page)
 		return NULL;
@@ -334,43 +323,6 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 	return err;
 }
 
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-static long __brd_direct_access(struct brd_device *brd, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
-{
-	struct page *page;
-
-	if (!brd)
-		return -ENODEV;
-	page = brd_insert_page(brd, (sector_t)pgoff << PAGE_SECTORS_SHIFT);
-	if (!page)
-		return -ENOSPC;
-	*kaddr = page_address(page);
-	*pfn = page_to_pfn_t(page);
-
-	return 1;
-}
-
-static long brd_dax_direct_access(struct dax_device *dax_dev,
-		pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn)
-{
-	struct brd_device *brd = dax_get_private(dax_dev);
-
-	return __brd_direct_access(brd, pgoff, nr_pages, kaddr, pfn);
-}
-
-static size_t brd_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static const struct dax_operations brd_dax_ops = {
-	.direct_access = brd_dax_direct_access,
-	.copy_from_iter = brd_dax_copy_from_iter,
-};
-#endif
-
 static const struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
 	.rw_page =		brd_rw_page,
@@ -451,21 +403,8 @@ static struct brd_device *brd_alloc(int i)
 	set_capacity(disk, rd_size * 2);
 	disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO;
 
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
-	brd->dax_dev = alloc_dax(brd, disk->disk_name, &brd_dax_ops);
-	if (!brd->dax_dev)
-		goto out_free_inode;
-#endif
-
-
 	return brd;
 
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-out_free_inode:
-	kill_dax(brd->dax_dev);
-	put_dax(brd->dax_dev);
-#endif
 out_free_queue:
 	blk_cleanup_queue(brd->brd_queue);
 out_free_dev:
@@ -505,10 +444,6 @@ out:
 static void brd_del_one(struct brd_device *brd)
 {
 	list_del(&brd->brd_list);
-#ifdef CONFIG_BLK_DEV_RAM_DAX
-	kill_dax(brd->dax_dev);
-	put_dax(brd->dax_dev);
-#endif
 	del_gendisk(brd->brd_disk);
 	brd_free(brd);
 }
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index e9f3b3e4bbf4..6833ada237ab 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -222,7 +222,8 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
 	struct resource *res;
-	phys_addr_t phys;
+	/* gcc-4.6.3-nolibc for i386 complains that this is uninitialized */
+	phys_addr_t uninitialized_var(phys);
 	int i;
 
 	for (i = 0; i < dev_dax->num_resources; i++) {
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 557b93703532..3ec804672601 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -92,21 +92,21 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	long len;
 
 	if (blocksize != PAGE_SIZE) {
-		pr_err("VFS (%s): error: unsupported blocksize for dax\n",
+		pr_debug("VFS (%s): error: unsupported blocksize for dax\n",
 				sb->s_id);
 		return -EINVAL;
 	}
 
 	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
 	if (err) {
-		pr_err("VFS (%s): error: unaligned partition for dax\n",
+		pr_debug("VFS (%s): error: unaligned partition for dax\n",
 				sb->s_id);
 		return err;
 	}
 
 	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
 	if (!dax_dev) {
-		pr_err("VFS (%s): error: device does not support dax\n",
+		pr_debug("VFS (%s): error: device does not support dax\n",
 				sb->s_id);
 		return -EOPNOTSUPP;
 	}
@@ -118,7 +118,7 @@ int __bdev_dax_supported(struct super_block *sb, int blocksize)
 	put_dax(dax_dev);
 
 	if (len < 1) {
-		pr_err("VFS (%s): error: dax access failed (%ld)",
+		pr_debug("VFS (%s): error: dax access failed (%ld)\n",
 				sb->s_id, len);
 		return len < 0 ? len : -EIO;
 	}
@@ -273,9 +273,6 @@ EXPORT_SYMBOL_GPL(dax_copy_from_iter);
 void arch_wb_cache_pmem(void *addr, size_t size);
 void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
 {
-	if (unlikely(!dax_alive(dax_dev)))
-		return;
-
 	if (unlikely(!test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags)))
 		return;
 
@@ -344,6 +341,9 @@ static struct inode *dax_alloc_inode(struct super_block *sb)
 	struct inode *inode;
 
 	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
+	if (!dax_dev)
+		return NULL;
+
 	inode = &dax_dev->inode;
 	inode->i_rdev = 0;
 	return inode;
diff --git a/drivers/nvdimm/Makefile b/drivers/nvdimm/Makefile
index 447e0e14f3b6..70d5f3ad9909 100644
--- a/drivers/nvdimm/Makefile
+++ b/drivers/nvdimm/Makefile
@@ -21,6 +21,7 @@ libnvdimm-y += region_devs.o
 libnvdimm-y += region.o
 libnvdimm-y += namespace_devs.o
 libnvdimm-y += label.o
+libnvdimm-y += badrange.o
 libnvdimm-$(CONFIG_ND_CLAIM) += claim.o
 libnvdimm-$(CONFIG_BTT) += btt_devs.o
 libnvdimm-$(CONFIG_NVDIMM_PFN) += pfn_devs.o
diff --git a/drivers/nvdimm/badrange.c b/drivers/nvdimm/badrange.c
new file mode 100644
index 000000000000..e068d72b4357
--- /dev/null
+++ b/drivers/nvdimm/badrange.c
@@ -0,0 +1,293 @@
+/*
+ * Copyright(c) 2017 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/libnvdimm.h>
+#include <linux/badblocks.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/device.h>
+#include <linux/ctype.h>
+#include <linux/ndctl.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include "nd-core.h"
+#include "nd.h"
+
+void badrange_init(struct badrange *badrange)
+{
+	INIT_LIST_HEAD(&badrange->list);
+	spin_lock_init(&badrange->lock);
+}
+EXPORT_SYMBOL_GPL(badrange_init);
+
+static void append_badrange_entry(struct badrange *badrange,
+		struct badrange_entry *bre, u64 addr, u64 length)
+{
+	lockdep_assert_held(&badrange->lock);
+	bre->start = addr;
+	bre->length = length;
+	list_add_tail(&bre->list, &badrange->list);
+}
+
+static int alloc_and_append_badrange_entry(struct badrange *badrange,
+		u64 addr, u64 length, gfp_t flags)
+{
+	struct badrange_entry *bre;
+
+	bre = kzalloc(sizeof(*bre), flags);
+	if (!bre)
+		return -ENOMEM;
+
+	append_badrange_entry(badrange, bre, addr, length);
+	return 0;
+}
+
+static int add_badrange(struct badrange *badrange, u64 addr, u64 length)
+{
+	struct badrange_entry *bre, *bre_new;
+
+	spin_unlock(&badrange->lock);
+	bre_new = kzalloc(sizeof(*bre_new), GFP_KERNEL);
+	spin_lock(&badrange->lock);
+
+	if (list_empty(&badrange->list)) {
+		if (!bre_new)
+			return -ENOMEM;
+		append_badrange_entry(badrange, bre_new, addr, length);
+		return 0;
+	}
+
+	/*
+	 * There is a chance this is a duplicate, check for those first.
+	 * This will be the common case as ARS_STATUS returns all known
+	 * errors in the SPA space, and we can't query it per region
+	 */
+	list_for_each_entry(bre, &badrange->list, list)
+		if (bre->start == addr) {
+			/* If length has changed, update this list entry */
+			if (bre->length != length)
+				bre->length = length;
+			kfree(bre_new);
+			return 0;
+		}
+
+	/*
+	 * If not a duplicate or a simple length update, add the entry as is,
+	 * as any overlapping ranges will get resolved when the list is consumed
+	 * and converted to badblocks
+	 */
+	if (!bre_new)
+		return -ENOMEM;
+	append_badrange_entry(badrange, bre_new, addr, length);
+
+	return 0;
+}
+
+int badrange_add(struct badrange *badrange, u64 addr, u64 length)
+{
+	int rc;
+
+	spin_lock(&badrange->lock);
+	rc = add_badrange(badrange, addr, length);
+	spin_unlock(&badrange->lock);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(badrange_add);
+
+void badrange_forget(struct badrange *badrange, phys_addr_t start,
+		unsigned int len)
+{
+	struct list_head *badrange_list = &badrange->list;
+	u64 clr_end = start + len - 1;
+	struct badrange_entry *bre, *next;
+
+	spin_lock(&badrange->lock);
+
+	/*
+	 * [start, clr_end] is the badrange interval being cleared.
+	 * [bre->start, bre_end] is the badrange_list entry we're comparing
+	 * the above interval against. The badrange list entry may need
+	 * to be modified (update either start or length), deleted, or
+	 * split into two based on the overlap characteristics
+	 */
+
+	list_for_each_entry_safe(bre, next, badrange_list, list) {
+		u64 bre_end = bre->start + bre->length - 1;
+
+		/* Skip intervals with no intersection */
+		if (bre_end < start)
+			continue;
+		if (bre->start >  clr_end)
+			continue;
+		/* Delete completely overlapped badrange entries */
+		if ((bre->start >= start) && (bre_end <= clr_end)) {
+			list_del(&bre->list);
+			kfree(bre);
+			continue;
+		}
+		/* Adjust start point of partially cleared entries */
+		if ((start <= bre->start) && (clr_end > bre->start)) {
+			bre->length -= clr_end - bre->start + 1;
+			bre->start = clr_end + 1;
+			continue;
+		}
+		/* Adjust bre->length for partial clearing at the tail end */
+		if ((bre->start < start) && (bre_end <= clr_end)) {
+			/* bre->start remains the same */
+			bre->length = start - bre->start;
+			continue;
+		}
+		/*
+		 * If clearing in the middle of an entry, we split it into
+		 * two by modifying the current entry to represent one half of
+		 * the split, and adding a new entry for the second half.
+		 */
+		if ((bre->start < start) && (bre_end > clr_end)) {
+			u64 new_start = clr_end + 1;
+			u64 new_len = bre_end - new_start + 1;
+
+			/* Add new entry covering the right half */
+			alloc_and_append_badrange_entry(badrange, new_start,
+					new