Merge tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "The bulk of this has appeared in -next and independently received a
  build success notification from the kbuild robot.  The 'for-4.5/block-
  dax' topic branch was rebased over the weekend to drop the "block
  device end-of-life" rework that Al would like to see re-implemented
  with a notifier, and to address bug reports against the badblocks
  integration.

  There is pending feedback against "libnvdimm: Add a poison list and
  export badblocks" received last week.  Linda identified some localized
  fixups that we will handle incrementally.

  Summary:

   - Media error handling: The 'badblocks' implementation that
     originated in md-raid is up-levelled to a generic capability of a
     block device.  This initial implementation is limited to being
     consulted in the pmem block-i/o path.  Later, 'badblocks' will be
     consulted when creating dax mappings.

   - Raw block device dax: For virtualization and other cases that want
     large contiguous mappings of persistent memory, add the capability
     to dax-mmap a block device directly.

   - Increased /dev/mem restrictions: Add an option to treat all
     io-memory as IORESOURCE_EXCLUSIVE, i.e. disable /dev/mem access
     while a driver is actively using an address range.  This behavior
     is controlled via the new CONFIG_IO_STRICT_DEVMEM option and can be
     overridden by the existing "iomem=relaxed" kernel command line
     option.

   - Miscellaneous fixes include a 'pfn'-device huge page alignment fix,
     block device shutdown crash fix, and other small libnvdimm fixes"

* tag 'libnvdimm-for-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (32 commits)
  block: kill disk_{check|set|clear|alloc}_badblocks
  libnvdimm, pmem: nvdimm_read_bytes() badblocks support
  pmem, dax: disable dax in the presence of bad blocks
  pmem: fail io-requests to known bad blocks
  libnvdimm: convert to statically allocated badblocks
  libnvdimm: don't fail init for full badblocks list
  block, badblocks: introduce devm_init_badblocks
  block: clarify badblocks lifetime
  badblocks: rename badblocks_free to badblocks_exit
  libnvdimm, pmem: move definition of nvdimm_namespace_add_poison to nd.h
  libnvdimm: Add a poison list and export badblocks
  nfit_test: Enable DSMs for all test NFITs
  md: convert to use the generic badblocks code
  block: Add badblock management for gendisks
  badblocks: Add core badblock management code
  block: fix del_gendisk() vs blkdev_ioctl crash
  block: enable dax for raw block devices
  block: introduce bdev_file_inode()
  restrict /dev/mem to idle io memory ranges
  arch: consolidate CONFIG_STRICT_DEVM in lib/Kconfig.debug
  ...

arch/arm/Kconfig

@@ -2,6 +2,7 @@ config ARM
 	bool
 	default y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H

arch/arm/Kconfig.debug

@@ -15,20 +15,6 @@ config ARM_PTDUMP
 	  kernel.
 	  If in doubt, say "N"
 
-config STRICT_DEVMEM
-	bool "Filter access to /dev/mem"
-	depends on MMU
-	---help---
-	  If this option is disabled, you allow userspace (root) access to all
-	  of memory, including kernel and userspace memory. Accidental
-	  access to this is obviously disastrous, but specific access can
-	  be used by people debugging the kernel.
-
-	  If this option is switched on, the /dev/mem file only allows
-	  userspace access to memory mapped peripherals.
-
-          If in doubt, say Y.
-
 # RMK wants arm kernels compiled with frame pointers or stack unwinding.
 # If you know what you are doing and are willing to live without stack
 # traces, you can get a slightly smaller kernel by setting this option to

arch/arm64/Kconfig

@@ -3,6 +3,7 @@ config ARM64
 	select ACPI_CCA_REQUIRED if ACPI
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL

arch/arm64/Kconfig.debug

@@ -14,20 +14,6 @@ config ARM64_PTDUMP
 	  kernel.
 	  If in doubt, say "N"
 
-config STRICT_DEVMEM
-	bool "Filter access to /dev/mem"
-	depends on MMU
-	help
-	  If this option is disabled, you allow userspace (root) access to all
-	  of memory, including kernel and userspace memory. Accidental
-	  access to this is obviously disastrous, but specific access can
-	  be used by people debugging the kernel.
-
-	  If this option is switched on, the /dev/mem file only allows
-	  userspace access to memory mapped peripherals.
-
-	  If in doubt, say Y.
-
 config PID_IN_CONTEXTIDR
 	bool "Write the current PID to the CONTEXTIDR register"
 	help

arch/frv/Kconfig

@@ -10,6 +10,7 @@ config FRV
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CPU_DEVICES
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION

arch/m32r/Kconfig

@@ -13,6 +13,7 @@ config M32R
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_ATOMIC64
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_USES_GETTIMEOFFSET
 	select MODULES_USE_ELF_RELA
 	select HAVE_DEBUG_STACKOVERFLOW

arch/powerpc/Kconfig

@@ -159,6 +159,7 @@ config PPC
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select HAVE_ARCH_SECCOMP_FILTER
 
 config GENERIC_CSUM

arch/powerpc/Kconfig.debug

@@ -335,18 +335,6 @@ config PPC_EARLY_DEBUG_CPM_ADDR
 	  platform probing is done, all platforms selected must
 	  share the same address.
 
-config STRICT_DEVMEM
-	def_bool y
-	prompt "Filter access to /dev/mem"
-	help
-	  This option restricts access to /dev/mem.  If this option is
-	  disabled, you allow userspace access to all memory, including
-	  kernel and userspace memory. Accidental memory access is likely
-	  to be disastrous.
-	  Memory access is required for experts who want to debug the kernel.
-
-	  If you are unsure, say Y.
-
 config FAIL_IOMMU
 	bool "Fault-injection capability for IOMMU"
 	depends on FAULT_INJECTION

arch/s390/Kconfig

@@ -66,6 +66,7 @@ config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN

arch/s390/Kconfig.debug

@@ -5,18 +5,6 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config STRICT_DEVMEM
-	def_bool y
-	prompt "Filter access to /dev/mem"
-	---help---
-	  This option restricts access to /dev/mem.  If this option is
-	  disabled, you allow userspace access to all memory, including
-	  kernel and userspace memory. Accidental memory access is likely
-	  to be disastrous.
-	  Memory access is required for experts who want to debug the kernel.
-
-	  If you are unsure, say Y.
-
 config S390_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL

arch/tile/Kconfig

@@ -19,6 +19,7 @@ config TILE
 	select VIRT_TO_BUS
 	select SYS_HYPERVISOR
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
@@ -116,9 +117,6 @@ config ARCH_DISCONTIGMEM_DEFAULT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config STRICT_DEVMEM
-	def_bool y
-
 # SMP is required for Tilera Linux.
 config SMP
 	def_bool y

arch/unicore32/Kconfig

 config UNICORE32
 	def_bool y
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_MEMBLOCK

arch/unicore32/Kconfig.debug

@@ -2,20 +2,6 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config STRICT_DEVMEM
-	bool "Filter access to /dev/mem"
-	depends on MMU
-	---help---
-	  If this option is disabled, you allow userspace (root) access to all
-	  of memory, including kernel and userspace memory. Accidental
-	  access to this is obviously disastrous, but specific access can
-	  be used by people debugging the kernel.
-
-	  If this option is switched on, the /dev/mem file only allows
-	  userspace access to memory mapped peripherals.
-
-          If in doubt, say Y.
-
 config EARLY_PRINTK
 	def_bool DEBUG_OCD
 	help

arch/x86/Kconfig

@@ -24,6 +24,7 @@ config X86
 	select ARCH_DISCARD_MEMBLOCK
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_GCOV_PROFILE_ALL

arch/x86/Kconfig.debug

@@ -5,23 +5,6 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config STRICT_DEVMEM
-	bool "Filter access to /dev/mem"
-	---help---
-	  If this option is disabled, you allow userspace (root) access to all
-	  of memory, including kernel and userspace memory. Accidental
-	  access to this is obviously disastrous, but specific access can
-	  be used by people debugging the kernel. Note that with PAT support
-	  enabled, even in this case there are restrictions on /dev/mem
-	  use due to the cache aliasing requirements.
-
-	  If this option is switched on, the /dev/mem file only allows
-	  userspace access to PCI space and the BIOS code and data regions.
-	  This is sufficient for dosemu and X and all common users of
-	  /dev/mem.
-
-	  If in doubt, say Y.
-
 config X86_VERBOSE_BOOTUP
 	bool "Enable verbose x86 bootup info messages"
 	default y

block/Makefile

@@ -8,7 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \
 			blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \
 			genhd.o scsi_ioctl.o partition-generic.o ioprio.o \
-			partitions/
+			badblocks.o partitions/
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o

block/genhd.c

@@ -20,6 +20,7 @@
 #include <linux/idr.h>
 #include <linux/log2.h>
 #include <linux/pm_runtime.h>
+#include <linux/badblocks.h>
 
 #include "blk.h"
 
@@ -664,7 +665,6 @@ void del_gendisk(struct gendisk *disk)
 
 	kobject_put(disk->part0.holder_dir);
 	kobject_put(disk->slave_dir);
-	disk->driverfs_dev = NULL;
 	if (!sysfs_deprecated)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
@@ -672,6 +672,31 @@ void del_gendisk(struct gendisk *disk)
 }
 EXPORT_SYMBOL(del_gendisk);
 
+/* sysfs access to bad-blocks list. */
+static ssize_t disk_badblocks_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return sprintf(page, "\n");
+
+	return badblocks_show(disk->bb, page, 0);
+}
+
+static ssize_t disk_badblocks_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *page, size_t len)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (!disk->bb)
+		return -ENXIO;
+
+	return badblocks_store(disk->bb, page, len, 0);
+}
+
 /**
  * get_gendisk - get partitioning information for a given device
  * @devt: device to get partitioning information for
@@ -990,6 +1015,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show,
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
+static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
+		disk_badblocks_store);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
@@ -1011,6 +1038,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 	&dev_attr_inflight.attr,
+	&dev_attr_badblocks.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
 #endif

block/ioctl.c

@@ -4,6 +4,7 @@
 #include <linux/gfp.h>
 #include <linux/blkpg.h>
 #include <linux/hdreg.h>
+#include <linux/badblocks.h>
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
 #include <linux/blktrace_api.h>
@@ -406,6 +407,71 @@ static inline int is_unrecognized_ioctl(int ret)
 		ret == -ENOIOCTLCMD;
 }
 
+#ifdef CONFIG_FS_DAX
+bool blkdev_dax_capable(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (!disk->fops->direct_access)
+		return false;
+
+	/*
+	 * If the partition is not aligned on a page boundary, we can't
+	 * do dax I/O to it.
+	 */
+	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+		return false;
+
+	/*
+	 * If the device has known bad blocks, force all I/O through the
+	 * driver / page cache.
+	 *
+	 * TODO: support finer grained dax error handling
+	 */
+	if (disk->bb && disk->bb->count)
+		return false;
+
+	return true;
+}
+
+static int blkdev_daxset(struct block_device *bdev, unsigned long argp)
+{
+	unsigned long arg;
+	int rc = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	if (get_user(arg, (int __user *)(argp)))
+		return -EFAULT;
+	arg = !!arg;
+	if (arg == !!(bdev->bd_inode->i_flags & S_DAX))
+		return 0;
+
+	if (arg)
+		arg = S_DAX;
+
+	if (arg && !blkdev_dax_capable(bdev))
+		return -ENOTTY;
+
+	mutex_lock(&bdev->bd_inode->i_mutex);
+	if (bdev->bd_map_count == 0)
+		inode_set_flags(bdev->bd_inode, arg, S_DAX);
+	else
+		rc = -EBUSY;
+	mutex_unlock(&bdev->bd_inode->i_mutex);
+	return rc;
+}
+#else
+static int blkdev_daxset(struct block_device *bdev, int arg)
+{
+	if (arg)
+		return -ENOTTY;
+	return 0;
+}
+#endif
+
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
 		unsigned cmd, unsigned long arg)
 {
@@ -568,6 +634,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
+	case BLKDAXSET:
+		return blkdev_daxset(bdev, arg);
+	case BLKDAXGET:
+		return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
+		break;
 	case IOC_PR_REGISTER:
 		return blkdev_pr_register(bdev, argp);
 	case IOC_PR_RESERVE:

drivers/acpi/nfit.c

@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/ndctl.h>
+#include <linux/delay.h>
 #include <linux/list.h>
 #include <linux/acpi.h>
 #include <linux/sort.h>
@@ -1473,6 +1474,201 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus,
 	/* devm will free nfit_blk */
 }
 
+static int ars_get_cap(struct nvdimm_bus_descriptor *nd_desc,
+		struct nd_cmd_ars_cap *cmd, u64 addr, u64 length)
+{
+	cmd->address = addr;
+	cmd->length = length;
+
+	return nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd,
+			sizeof(*cmd));
+}
+
+static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc,
+		struct nd_cmd_ars_start *cmd, u64 addr, u64 length)
+{
+	int rc;
+
+	cmd->address = addr;
+	cmd->length = length;
+	cmd->type = ND_ARS_PERSISTENT;
+
+	while (1) {
+		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, cmd,
+				sizeof(*cmd));
+		if (rc)
+			return rc;
+		switch (cmd->status) {
+		case 0:
+			return 0;
+		case 1:
+			/* ARS unsupported, but we should never get here */
+			return 0;
+		case 2:
+			return -EINVAL;
+		case 3:
+			/* ARS is in progress */
+			msleep(1000);
+			break;
+		default:
+			return -ENXIO;
+		}
+	}
+}
+
+static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc,
+		struct nd_cmd_ars_status *cmd)
+{
+	int rc;
+
+	while (1) {
+		rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd,
+			sizeof(*cmd));
+		if (rc || cmd->status & 0xffff)
+			return -ENXIO;
+
+		/* Check extended status (Upper two bytes) */
+		switch (cmd->status >> 16) {
+		case 0:
+			return 0;
+		case 1:
+			/* ARS is in progress */
+			msleep(1000);
+			break;
+		case 2:
+			/* No ARS performed for the current boot */
+			return 0;
+		default:
+			return -ENXIO;
+		}
+	}
+}
+
+static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus,
+		struct nd_cmd_ars_status *ars_status, u64 start)
+{
+	int rc;
+	u32 i;
+
+	/*
+	 * The address field returned by ars_status should be either
+	 * less than or equal to the address we last started ARS for.
+	 * The (start, length) returned by ars_status should also have
+	 * non-zero overlap with the range we started ARS for.
+	 * If this is not the case, bail.
+	 */
+	if (ars_status->address > start ||
+			(ars_status->address + ars_status->length < start))
+		return -ENXIO;
+
+	for (i = 0; i < ars_status->num_records; i++) {
+		rc = nvdimm_bus_add_poison(nvdimm_bus,
+				ars_status->records[i].err_address,
+				ars_status->records[i].length);
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc,
+		struct nd_region_desc *ndr_desc)
+{
+	struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc;
+	struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus;
+	struct nd_cmd_ars_status *ars_status = NULL;
+	struct nd_cmd_ars_start *ars_start = NULL;
+	struct nd_cmd_ars_cap *ars_cap = NULL;
+	u64 start, len, cur, remaining;
+	int rc;
+
+	ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL);
+	if (!ars_cap)
+		return -ENOMEM;
+
+	start = ndr_desc->res->start;
+	len = ndr_desc->res->end - ndr_desc->res->start + 1;
+
+	rc = ars_get_cap(nd_desc, ars_cap, start, len);
+	if (rc)
+		goto out;
+
+	/*
+	 * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in
+	 * extended status is not set, skip this but continue initialization
+	 */
+	if ((ars_cap->status & 0xffff) ||
+		!(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) {
+		dev_warn(acpi_desc->dev,
+			"ARS unsupported (status: 0x%x), won't create an error list\n",
+			ars_cap->status);
+		goto out;
+	}
+
+	/*
+	 * Check if a full-range ARS has been run. If so, use those results
+	 * without having to start a new ARS.
+	 */
+	ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status),
+			GFP_KERNEL);
+	if (!ars_status) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	rc = ars_get_status(nd_desc, ars_status);
+	if (rc)
+		goto out;
+
+	if (ars_status->address <= start &&
+		(ars_status->address + ars_status->length >= start + len)) {
+		rc = ars_status_process_records(nvdimm_bus, ars_status, start);
+		goto out;
+	}
+
+	/*
+	 * ARS_STATUS can overflow if the number of poison entries found is
+	 * greater than the maximum buffer size (ars_cap->max_ars_out)
+	 * To detect overflow, check if the length field of ars_status
+	 * is less than the length we supplied. If so, process the
+	 * error entries we got, adjust the start point, and start again
+	 */
+	ars_start = kzalloc(sizeof(*ars_start), GFP_KERNEL);
+	if (!ars_start)
+		return -ENOMEM;
+
+	cur = start;
+	remaining = len;
+	do {
+		u64 done, end;
+
+		rc = ars_do_start(nd_desc, ars_start, cur, remaining);
+		if (rc)
+			goto out;
+
+		rc = ars_get_status(nd_desc, ars_status);
+		if (rc)
+			goto out;
+
+		rc = ars_status_process_records(nvdimm_bus, ars_status, cur);
+		if (rc)
+			goto out;
+
+		end = min(cur + remaining,
+			ars_status->address + ars_status->length);
+		done = end - cur;
+		cur += done;
+		remaining -= done;
+	} while (remaining);
+
+ out:
+	kfree(ars_cap);
+	kfree(ars_start);
+	kfree(ars_status);
+	return rc;
+}
+
 static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_memory_map *memdev,
@@ -1585,6 +1781,13 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 
 	nvdimm_bus = acpi_desc->nvdimm_bus;
 	if (nfit_spa_type(spa) == NFIT_SPA_PM) {
+		rc = acpi_nfit_find_poison(acpi_desc, ndr_desc);
+		if (rc) {
+			dev_err(acpi_desc->dev,
+				"error while performing ARS to find poison: %d\n",
+				rc);
+			return rc;
+		}
 		if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc))
 			return -ENOMEM;
 	} else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) {

drivers/md/md.h

@@ -17,6 +17,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
+#include <linux/badblocks.h>
 #include <linux/kobject.h>
 #include <linux/list.h>
 #include <linux/mm.h>
@@ -28,13 +29,6 @@
 
 #define MaxSector (~(sector_t)0)
 
-/* Bad block numbers are stored sorted in a single page.
- * 64bits is used for each block or extent.
- * 54 bits are sector number, 9 bits are extent size,
- * 1 bit is an 'acknowledged' flag.
- */
-#define MD_MAX_BADBLOCKS	(PAGE_SIZE/8)
-
 /*
  * MD's 'extended' device
  */
@@ -117,22 +111,7 @@ struct md_rdev {
 	struct kernfs_node *sysfs_state; /* handle for 'state'
 					   * sysfs entry */
 
-	struct badblocks {
-		int	count;		/* count of bad blocks */
-		int	unacked_exist;	/* there probably are unacknowledged
-					 * bad blocks.  This is only cleared
-					 * when a read discovers none
-					 */
-		int	shift;		/* shift from sectors to block size
-					 * a -ve shift means badblocks are
-					 * disabled.*/
-		u64	*page;		/* badblock list */
-		int	changed;
-		seqlock_t lock;
-
-		sector_t sector;
-		sector_t size;		/* in sectors */
-	} badblocks;
+	struct badblocks badblocks;
 };
 enum flag_bits {
 	Faulty,			/* device is known to have a fault */
@@ -185,22 +164,11 @@ enum flag_bits {
 				 */
 };
 
-#define BB_LEN_MASK	(0x00000000000001FFULL)
-#define BB_OFFSET_MASK	(0x7FFFFFFFFFFFFE00ULL)
-#define BB_ACK_MASK	(0x8000000000000000ULL)
-#define BB_MAX_LEN	512
-#define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
-#define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
-#define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
-#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
-
-extern int md_is_badblock(struct badblocks *bb, sector_t s, int sectors,
-			  sector_t *first_bad, int *bad_sectors);
 static inline int is_badblock(struct md_rdev *rdev, sector_t s, int sectors,
 			      sector_t *first_bad, int *bad_sectors)
 {
 	if (unlikely(rdev->badblocks.count)) {
-		int rv = md_is_badblock(&rdev->badblocks, rdev->data_offset + s,
+		int rv = badblocks_check(&rdev->badblocks, rdev->data_offset + s,
 					sectors,
 					first_bad, bad_sectors);
 		if (rv)
@@ -213,8 +181,6 @@ extern int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 			      int is_new);
 extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 				int is_new);
-extern void md_ack_all_badblocks(struct badblocks *bb);
-
 struct md_cluster_info;
 
 struct mddev {

drivers/nvdimm/core.c

@@ -11,6 +11,7 @@
  * 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>
@@ -325,6 +326,7 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent,
 	if (!nvdimm_bus)
 		return NULL;
 	INIT_LIST_HEAD(&nvdimm_bus->list);
+	INIT_LIST_HEAD(&nvdimm_bus->poison_list);
 	init_waitqueue_head(&nvdimm_bus->probe_wait);
 	nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL);
 	mutex_init(&nvdimm_bus->reconfig_mutex);
@@ -359,6 +361,172 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent,
 }
 EXPORT_SYMBOL_GPL(__nvdimm_bus_register);
 
+static void set_badblock(struct badblocks *bb, sector_t s, int num)
+{
+	dev_dbg(bb->dev, "Found a poison range (0x%llx, 0x%llx)\n",
+			(u64) s * 512, (u64) num * 512);
+	/* this isn't an error as the hardware will still throw an exception */
+	if (badblocks_set(bb, s, num, 1))
+		dev_info_once(bb->dev, "%s: failed for sector %llx\n",
+				__func__, (u64) s);
+}
+
+/**
+ * __add_badblock_range() - Convert a physical address range to bad sectors
+ * @bb:		badblocks instance to populate
+ * @ns_offset:	namespace offset where the error range begins (in bytes)
+ * @len:	number of bytes of poison to be added
+ *
+ * This assumes that the range provided with (ns_offset, len) is within
+ * the bounds of physical addresses for this namespace, i.e. lies in the
+ * interval [ns_start, ns_start + ns_size)
+ */
+static void __add_badblock_range(struct badblocks *bb, u64 ns_offset, u64 len)
+{
+	const unsigned int sector_size = 512;
+	sector_t start_sector;
+	u64 num_sectors;
+	u32 rem;
+
+	start_sector = div_u64(ns_offset, sector_size);
+	num_sectors = div_u64_rem(len, sector_size, &rem);
+	if (rem)
+		num_sectors++;
+
+	if (unlikely(num_sectors > (u64)INT_MAX)) {
+		u64 remaining = num_sectors;
+		sector_t s = start_sector;
+
+		while (remaining) {
+			int done = min_t(u64, remaining, INT_MAX);
+
+			set_badblock(bb, s, done);
+			remaining -= done;
+			s += done;
+		}
+	} else
+		set_badblock(bb, start_sector, num_sectors);
+}
+
+/**
+ * nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks
+ * @ndns:	the namespace containing poison ranges
+ * @bb:		badblocks instance to populate
+ * @offset:	offset at the start of the namespace before 'sector 0'
+ *
+ * The poison list generated during NFIT initialization may contain multiple,
+ * possibly overlapping ranges in the SPA (System Physical Address) space.
+ * Compare each of these ranges to the namespace currently being initialized,
+ * and add badblocks to the gendisk for all matching sub-ranges
+ */
+void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
+		struct badblocks *bb, resource_size_t offset)
+{
+	struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
+	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+	struct nvdimm_bus *nvdimm_bus;
+	struct list_head *poison_list;
+	u64 ns_start, ns_end, ns_size;
+	struct nd_poison *pl;
+
+	ns_size = nvdimm_namespace_capacity(ndns) - offset;
+	ns_start = nsio->res.start + offset;
+	ns_end = nsio->res.end;
+
+	nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent);
+	poison_list = &nvdimm_bus->poison_list;
+	if (list_empty(poison_list))
+		return;
+
+	list_for_each_entry(pl, poison_list, list) {
+		u64 pl_end = pl->start + pl->length - 1;
+
+		/* Discard intervals with no intersection */
+		if (pl_end < ns_start)
+			continue;
+		if (pl->start > ns_end)
+			continue;
+		/* Deal with any overlap after start of the namespace */
+		if (pl->start >= ns_start) {
+			u64 start = pl->start;
+			u64 len;
+
+			if (pl_end <= ns_end)
+				len = pl->length;
+			else
+				len = ns_start + ns_size - pl->start;
+			__add_badblock_range(bb, start - ns_start, len);
+			continue;
+		}
+		/* Deal with overlap for poison starting before the namespace */
+		if (pl->start < ns_start) {
+			u64 len;
+
+			if (pl_end < ns_end)
+				len = pl->start + pl->length - ns_start;
+			else
+				len = ns_size;
+			__add_badblock_range(bb, 0, len);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(nvdimm_namespace_add_poison);
+
+static int __add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+{
+	struct nd_poison *pl;
+
+	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
+	if (!pl)
+		return -ENOMEM;
+
+	pl->start = addr;
+	pl->length = length;
+	list_add_tail(&pl->list, &nvdimm_bus->poison_list);
+
+	return 0;
+}
+
+int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+{
+	struct nd_poison *pl;
+
+	if (list_empty(&nvdimm_bus->poison_list))
+		return __add_poison(nvdimm_bus, addr, length);
+
+	/*
+	 * 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(pl, &nvdimm_bus->poison_list, list)
+		if (pl->start == addr) {
+			/* If length has changed, update this list entry */
+			if (pl->length != length)
+				pl->length = length;
+			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
+	 */
+	return __add_poison(nvdimm_bus, addr, length);
+}
+EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
+
+static void free_poison_list(struct list_head *poison_list)
+{
+	struct nd_poison *pl, *next;
+
+	list_for_each_entry_safe(pl, next, poison_list, list) {
+		list_del(&pl->list);
+		kfree(pl);
+	}
+	list_del_init(poison_list);
+}
+
 static int child_unregister(struct device *dev, void *data)
 {
 	/*
@@ -385,6 +553,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
 
 	nd_synchronize();
 	device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister);
+	free_poison_list(&nvdimm_bus->poison_list);
 	nvdimm_bus_destroy_ndctl(nvdimm_bus);
 
 	device_unregister(&nvdimm_bus->dev);

drivers/nvdimm/namespace_devs.c

@@ -77,6 +77,59 @@ static bool is_namespace_io(struct device *dev)
 	return dev ? dev->type == &namespace_io_device_type : false;
 }
 
+static int is_uuid_busy(struct device *dev, void *data)
+{
+	u8 *uuid1 = data, *uuid2 = NULL;
+
+	if (is_namespace_pmem(dev)) {
+		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+
+		uuid2 = nspm->uuid;
+	} else if (is_namespace_blk(dev)) {
+		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
+
+		uuid2 = nsblk->uuid;
+	} else if (is_nd_btt(dev)) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
+		uuid2 = nd_btt->uuid;
+	} else if (is_nd_pfn(dev)) {
+		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+		uuid2 = nd_pfn->uuid;
+	}
+
+	if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0)
+		return -EBUSY;
+
+	return 0;
+}
+
+static int is_namespace_uuid_busy(struct device *dev, void *data)
+{
+	if (is_nd_pmem(dev) || is_nd_blk(dev))
+		return device_for_each_child(dev, data, is_uuid_busy);
+	return 0;
+}
+
+/**
+ * nd_is_uuid_unique - verify that no other namespace has @uuid
+ * @dev: any device on a nvdimm_bus
+ * @uuid: uuid to check
+ */
+bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
+
+	if (!nvdimm_bus)
+		return false;
+	WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
+	if (device_for_each_child(&nvdimm_bus->dev, uuid,
+				is_namespace_uuid_busy) != 0)
+		return false;
+	return true;
+}
+
 bool pmem_should_map_pages(struct device *dev)
 {
 	struct nd_region *nd_region = to_nd_region(dev->parent);
@@ -104,20 +157,10 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
 	const char *suffix = NULL;
 
-	if (ndns->claim) {
-		if (is_nd_btt(ndns->claim))
-			suffix = "s";
-		else if (is_nd_pfn(ndns->claim))
-			suffix = "m";
-		else
-			dev_WARN_ONCE(&ndns->dev, 1,
-					"unknown claim type by %s\n",
-					dev_name(ndns->claim));
-	}
+	if (ndns->claim && is_nd_btt(ndns->claim))
+		suffix = "s";
 
 	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
-		if (!suffix && pmem_should_map_pages(&ndns->dev))
-			suffix = "m";
 		sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
 	} else if (is_namespace_blk(&ndns->dev)) {
 		struct nd_namespace_blk *nsblk;
@@ -791,6 +834,15 @@ static void nd_namespace_pmem_set_size(struct nd_region *nd_region,
 	res->end = nd_region->ndr_start + size - 1;
 }
 
+static bool uuid_not_set(const u8 *uuid, struct device *dev, const char *where)
+{
+	if (!uuid) {
+		dev_dbg(dev, "%s: uuid not set\n", where);
+		return true;
+	}
+	return false;
+}
+
 static ssize_t __size_store(struct device *dev, unsigned long long val)
 {
 	resource_size_t allocated = 0, available = 0;
@@ -820,8 +872,12 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 	 * We need a uuid for the allocation-label and dimm(s) on which
 	 * to store the label.
 	 */
-	if (!uuid || nd_region->ndr_mappings == 0)
+	if (uuid_not_set(uuid, dev, __func__))
 		return -ENXIO;
+	if (nd_region->ndr_mappings == 0) {
+		dev_dbg(dev, "%s: not associated with dimm(s)\n", __func__);
+		return -ENXIO;
+	}
 
 	div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder);
 	if (remainder) {
@@ -1211,6 +1267,29 @@ static ssize_t holder_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(holder);
 
+static ssize_t mode_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_namespace_common *ndns = to_ndns(dev);
+	struct device *claim;
+	char *mode;
+	ssize_t rc;
+
+	device_lock(dev);
+	claim = ndns->claim;
+	if (pmem_should_map_pages(dev) || (claim && is_nd_pfn(claim)))
+		mode = "memory";
+	else if (claim && is_nd_btt(claim))
+		mode = "safe";
+	else
+		mode = "raw";
+	rc = sprintf(buf, "%s\n", mode);
+	device_unlock(dev);
+
+	return rc;
+}
+static DEVICE_ATTR_RO(mode);
+
 static ssize_t force_raw_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t len)
 {
@@ -1234,6 +1313,7 @@ static DEVICE_ATTR_RW(force_raw);
 static struct attribute *nd_namespace_attributes[] = {
 	&dev_attr_nstype.attr,
 	&dev_attr_size.attr,
+	&dev_attr_mode.attr,
 	&dev_attr_uuid.attr,
 	&dev_attr_holder.attr,
 	&dev_attr_resource.attr,
@@ -1267,7 +1347,8 @@ static umode_t namespace_visible(struct kobject *kobj,
 
 	if (a == &dev_attr_nstype.attr || a == &dev_attr_size.attr
 			|| a == &dev_attr_holder.attr
-			|| a == &dev_attr_force_raw.attr)
+			|| a == &dev_attr_force_raw.attr
+			|| a == &dev_attr_mode.attr)
 		return a->mode;
 
 	return 0;
@@ -1343,14 +1424,19 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
 		struct nd_namespace_pmem *nspm;
 
 		nspm = to_nd_namespace_pmem(&ndns->dev);
-		if (!nspm->uuid) {
-			dev_dbg(&ndns->dev, "%s: uuid not set\n", __func__);
+		if (uuid_not_set(nspm->uuid, &ndns->dev, __func__))
 			return ERR_PTR(-ENODEV);
-		}
 	} else if (is_namespace_blk(&ndns->dev)) {
 		struct nd_namespace_blk *nsblk;
 
 		nsblk = to_nd_namespace_blk(&ndns->dev);
+		if (uuid_not_set(nsblk->uuid, &ndns->dev, __func__))
+			return ERR_PTR(-ENODEV);
+		if (!nsblk->lbasize) {
+			dev_dbg(&ndns->dev, "%s: sector size not set\n",
+				__func__);
+			return ERR_PTR(-ENODEV);
+		}
 		if (!nd_namespace_blk_validate(nsblk))
 			return ERR_PTR(-ENODEV);
 	}
@@ -1689,6 +1775,18 @@ void nd_region_create_blk_seed(struct nd_region *nd_region)
 		nd_device_register(nd_region->ns_seed);
 }
 
+void nd_region_create_pfn_seed(struct nd_region *nd_region)
+{
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	nd_region->pfn_seed = nd_pfn_create(nd_region);
+	/*
+	 * Seed creation failures are not fatal, provisioning is simply
+	 * disabled until memory becomes available
+	 */
+	if (!nd_region->pfn_seed)
+		dev_err(&nd_region->dev, "failed to create pfn namespace\n");
+}
+
 void nd_region_create_btt_seed(struct nd_region *nd_region)
 {
 	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));

drivers/nvdimm/nd-core.h

@@ -30,6 +30,7 @@ struct nvdimm_bus {
 	struct list_head list;
 	struct device dev;
 	int id, probe_active;
+	struct list_head poison_list;
 	struct mutex reconfig_mutex;
 };
 
@@ -52,6 +53,7 @@ void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 struct nd_region;
 void nd_region_create_blk_seed(struct nd_region *nd_region);
 void nd_region_create_btt_seed(struct nd_region *nd_region);
+void nd_region_create_pfn_seed(struct nd_region *nd_region);
 void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 int nvdimm_bus_create_ndctl(struct nvdimm_bus *nvdimm_bus);
 void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus);

drivers/nvdimm/nd.h

@@ -29,13 +29,12 @@ enum {
 	ND_MAX_LANES = 256,
 	SECTOR_SHIFT = 9,
 	INT_LBASIZE_ALIGNMENT = 64,
-#if IS_ENABLED(CONFIG_NVDIMM_PFN)
-	ND_PFN_ALIGN = PAGES_PER_SECTION * PAGE_SIZE,
-	ND_PFN_MASK = ND_PFN_ALIGN - 1,
-#else
-	ND_PFN_ALIGN = 0,
-	ND_PFN_MASK = 0,
-#endif
+};
+
+struct nd_poison {
+	u64 start;
+	u64 length;
+	struct list_head list;
 };
 
 struct nvdimm_drvdata {
@@ -153,6 +152,7 @@ struct nd_pfn {
 	int id;
 	u8 *uuid;
 	struct device dev;
+	unsigned long align;
 	unsigned long npfns;
 	enum nd_pfn_mode mode;
 	struct nd_pfn_sb *pfn_sb;
@@ -262,6 +262,8 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns);
 int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns);
 const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
 		char *name);
+void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
+		struct badblocks *bb, resource_size_t offset);
 int nd_blk_region_init(struct nd_region *nd_region);
 void __nd_iostat_start(struct bio *bio, unsigned long *start);
 static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)

drivers/nvdimm/pfn_devs.c

@@ -103,6 +103,52 @@ static ssize_t mode_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(mode);
 
+static ssize_t align_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
+	return sprintf(buf, "%lx\n", nd_pfn->align);
+}
+
+static ssize_t __align_store(struct nd_pfn *nd_pfn, const char *buf)
+{
+	unsigned long val;
+	int rc;
+
+	rc = kstrtoul(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	if (!is_power_of_2(val) || val < PAGE_SIZE || val > SZ_1G)
+		return -EINVAL;
+
+	if (nd_pfn->dev.driver)
+		return -EBUSY;
+	else
+		nd_pfn->align = val;
+
+	return 0;
+}
+
+static ssize_t align_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	ssize_t rc;
+
+	device_lock(dev);
+	nvdimm_bus_lock(dev);
+	rc = __align_store(nd_pfn, buf);
+	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
+			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
+	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_RW(align);
+
 static ssize_t uuid_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -164,6 +210,7 @@ static struct attribute *nd_pfn_attributes[] = {
 	&dev_attr_mode.attr,
 	&dev_attr_namespace.attr,
 	&dev_attr_uuid.attr,
+	&dev_attr_align.attr,
 	NULL,
 };
 
@@ -179,7 +226,6 @@ static const struct attribute_group *nd_pfn_attribute_groups[] = {
 };
 
 static struct device *__nd_pfn_create(struct nd_region *nd_region,
-		u8 *uuid, enum nd_pfn_mode mode,
 		struct nd_namespace_common *ndns)
 {
 	struct nd_pfn *nd_pfn;
@@ -199,10 +245,8 @@ static struct device *__nd_pfn_create(struct nd_region *nd_region,
 		return NULL;
 	}
 
-	nd_pfn->mode = mode;
-	if (uuid)
-		uuid = kmemdup(uuid, 16, GFP_KERNEL);
-	nd_pfn->uuid = uuid;
+	nd_pfn->mode = PFN_MODE_NONE;
+	nd_pfn->align = HPAGE_SIZE;
 	dev = &nd_pfn->dev;
 	dev_set_name(dev, "pfn%d.%d", nd_region->id, nd_pfn->id);
 	dev->parent = &nd_region->dev;
@@ -220,8 +264,7 @@ static struct device *__nd_pfn_create(struct nd_region *nd_region,
 
 struct device *nd_pfn_create(struct nd_region *nd_region)
 {
-	struct device *dev = __nd_pfn_create(nd_region, NULL, PFN_MODE_NONE,
-			NULL);
+	struct device *dev = __nd_pfn_create(nd_region, NULL);
 
 	if (dev)
 		__nd_device_register(dev);
@@ -230,10 +273,11 @@ struct device *nd_pfn_create(struct nd_region *nd_region)
 
 int nd_pfn_validate(struct nd_pfn *nd_pfn)
 {
-	struct nd_namespace_common *ndns = nd_pfn->ndns;
-	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
-	struct nd_namespace_io *nsio;
 	u64 checksum, offset;
+	struct nd_namespace_io *nsio;
+	struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
+	struct nd_namespace_common *ndns = nd_pfn->ndns;
+	const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);
 
 	if (!pfn_sb || !ndns)
 		return -ENODEV;
@@ -241,10 +285,6 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	if (!is_nd_pmem(nd_pfn->dev.parent))
 		return -ENODEV;
 
-	/* section alignment for simple hotplug */
-	if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN)
-		return -ENODEV;
-
 	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
 		return -ENXIO;
 
@@ -257,6 +297,9 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 		return -ENODEV;
 	pfn_sb->checksum = cpu_to_le64(checksum);
 
+	if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
+		return -ENODEV;
+
 	switch (le32_to_cpu(pfn_sb->mode)) {
 	case PFN_MODE_RAM:
 		break;
@@ -278,6 +321,12 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 			return -EINVAL;
 	}
 
+	if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) {
+		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
+				nd_pfn->align, nvdimm_namespace_capacity(ndns));
+		return -EINVAL;
+	}
+
 	/*
 	 * These warnings are verbose because they can only trigger in
 	 * the case where the physical address alignment of the
@@ -286,17 +335,19 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn)
 	 */
 	offset = le64_to_cpu(pfn_sb->dataoff);
 	nsio = to_nd_namespace_io(&ndns->dev);
-	if (nsio->res.start & ND_PFN_MASK) {
-		dev_err(&nd_pfn->dev,
-				"init failed: %s not section aligned\n",
-				dev_name(&ndns->dev));
-		return -EBUSY;
-	} else if (offset >= resource_size(&nsio->res)) {
+	if (offset >= resource_size(&nsio->res)) {
 		dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
 				dev_name(&ndns->dev));
 		return -EBUSY;
 	}
 
+	nd_pfn->align = 1UL << ilog2(offset);
+	if (!is_power_of_2(offset) || offset < PAGE_SIZE) {
+		dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n",
+				offset);
+		return -ENXIO;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(nd_pfn_validate);
@@ -313,7 +364,7 @@ int nd_pfn_probe(struct nd_namespace_common *ndns, void *drvdata)
 		return -ENODEV;
 
 	nvdimm_bus_lock(&ndns->dev);
-	dev = __nd_pfn_create(nd_region, NULL, PFN_MODE_NONE, ndns);
+	dev = __nd_pfn_create(nd_region, ndns);
 	nvdimm_bus_unlock(&ndns->dev);
 	if (!dev)
 		return -ENOMEM;

drivers/nvdimm/pmem.c

@@ -23,6 +23,7 @@
 #include <linux/module.h>
 #include <linux/memory_hotplug.h>
 #include <linux/moduleparam.h>
+#include <linux/badblocks.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/pmem.h>
@@ -41,11 +42,25 @@ struct pmem_device {
 	phys_addr_t		data_offset;
 	void __pmem		*virt_addr;
 	size_t			size;
+	struct badblocks	bb;
 };
 
 static int pmem_major;
 
-static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
+static bool is_bad_pmem(struct badblocks *bb, sector_t sector, unsigned int len)
+{
+	if (bb->count) {
+		sector_t first_bad;
+		int num_bad;
+
+		return !!badblocks_check(bb, sector, len / 512, &first_bad,
+				&num_bad);
+	}
+
+	return false;
+}
+
+static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 			unsigned int len, unsigned int off, int rw,
 			sector_t sector)
 {
@@ -54,6 +69,8 @@ static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	void __pmem *pmem_addr = pmem->virt_addr + pmem_off;
 
 	if (rw == READ) {
+		if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
+			return -EIO;
 		memcpy_from_pmem(mem + off, pmem_addr, len);
 		flush_dcache_page(page);
 	} else {
@@ -62,10 +79,12 @@ static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	}
 
 	kunmap_atomic(mem);
+	return 0;
 }
 
 static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 {
+	int rc = 0;
 	bool do_acct;
 	unsigned long start;
 	struct bio_vec bvec;
@@ -74,9 +93,15 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 
 	do_acct = nd_iostat_start(bio, &start);
-	bio_for_each_segment(bvec, bio, iter)
-		pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
-				bio_data_dir(bio), iter.bi_sector);
+	bio_for_each_segment(bvec, bio, iter) {
+		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
+				bvec.bv_offset, bio_data_dir(bio),
+				iter.bi_sector);
+		if (rc) {
+			bio->bi_error = rc;
+			break;
+		}
+	}
 	if (do_acct)
 		nd_iostat_end(bio, start);
 
@@ -91,13 +116,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 		       struct page *page, int rw)
 {
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
+	int rc;
 
-	pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	rc = pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
 	if (rw & WRITE)
 		wmb_pmem();
-	page_endio(page, rw & WRITE, 0);
 
-	return 0;
+	/*
+	 * The ->rw_page interface is subtle and tricky.  The core
+	 * retries on any error, so we can only invoke page_endio() in
+	 * the successful completion case.  Otherwise, we'll see crashes
+	 * caused by double completion.
+	 */
+	if (rc == 0)
+		page_endio(page, rw & WRITE, 0);
+
+	return rc;
 }
 
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
@@ -195,7 +229,12 @@ static int pmem_attach_disk(struct device *dev,
 	disk->driverfs_dev = dev;
 	set_capacity(disk, (pmem->size - pmem->data_offset) / 512);
 	pmem->pmem_disk = disk;
+	devm_exit_badblocks(dev, &pmem->bb);
+	if (devm_init_badblocks(dev, &pmem->bb))
+		return -ENOMEM;
+	nvdimm_namespace_add_poison(ndns, &pmem->bb, pmem->data_offset);
 
+	disk->bb = &pmem->bb;
 	add_disk(disk);
 	revalidate_disk(disk);
 
@@ -212,9 +251,13 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
 		return -EFAULT;
 	}
 
-	if (rw == READ)
+	if (rw == READ) {
+		unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
+
+		if (unlikely(is_bad_pmem(&pmem->bb, offset / 512, sz_align)))
+			return -EIO;
 		memcpy_from_pmem(buf, pmem->virt_addr + offset, size);
-	else {
+	} else {
 		memcpy_to_pmem(pmem->virt_addr + offset, buf, size);
 		wmb_pmem();
 	}
@@ -238,14 +281,11 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 
 	nd_pfn->pfn_sb = pfn_sb;
 	rc = nd_pfn_validate(nd_pfn);
-	if (rc == 0 || rc == -EBUSY)
+	if (rc == -ENODEV)
+		/* no info block, do init */;
+	else
 		return rc;
 
-	/* section alignment for simple hotplug */
-	if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN
-			|| pmem->phys_addr & ND_PFN_MASK)
-		return -ENODEV;
-
 	nd_region = to_nd_region(nd_pfn->dev.parent);
 	if (nd_region->ro) {
 		dev_info(&nd_pfn->dev,
@@ -263,9 +303,9 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	 * ->direct_access() to those that are included in the memmap.
 	 */
 	if (nd_pfn->mode == PFN_MODE_PMEM)
-		offset = ALIGN(SZ_8K + 64 * npfns, PMD_SIZE);
+		offset = ALIGN(SZ_8K + 64 * npfns, nd_pfn->align);
 	else if (nd_pfn->mode == PFN_MODE_RAM)
-		offset = SZ_8K;
+		offset = ALIGN(SZ_8K, nd_pfn->align);
 	else
 		goto err;
 
@@ -275,6 +315,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn)
 	pfn_sb->npfns = cpu_to_le64(npfns);
 	memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
 	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
+	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);
 	checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
 	pfn_sb->checksum = cpu_to_le64(checksum);
@@ -326,21 +367,11 @@ static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
 	if (rc)
 		return rc;
 
-	if (PAGE_SIZE != SZ_4K) {
-		dev_err(dev, "only supported on systems with 4K PAGE_SIZE\n");
-		return -ENXIO;
-	}
-	if (nsio->res.start & ND_PFN_MASK) {
-		dev_err(dev, "%s not memory hotplug section aligned\n",
-				dev_name(&ndns->dev));
-		return -ENXIO;
-	}
-
 	pfn_sb = nd_pfn->pfn_sb;
 	offset = le64_to_cpu(pfn_sb->dataoff);
 	nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
 	if (nd_pfn->mode == PFN_MODE_RAM) {
-		if (offset != SZ_8K)
+		if (offset < SZ_8K)
 			return -EINVAL;
 		nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
 		altmap = NULL;
@@ -389,6 +420,9 @@ static int nd_pmem_probe(struct device *dev)
 	pmem->ndns = ndns;
 	dev_set_drvdata(dev, pmem);
 	ndns->rw_bytes = pmem_rw_bytes;
+	if (devm_init_badblocks(dev, &pmem->bb))
+		return -ENOMEM;
+	nvdimm_namespace_add_poison(ndns, &pmem->bb, 0);
 
 	if (is_nd_btt(dev))
 		return nvdimm_namespace_attach_btt(ndns);

drivers/nvdimm/region_devs.c

@@ -134,62 +134,6 @@ int nd_region_to_nstype(struct nd_region *nd_region)
 }
 EXPORT_SYMBOL(nd_region_to_nstype);
 
-static int is_uuid_busy(struct device *dev, void *data)
-{
-	struct nd_region *nd_region = to_nd_region(dev->parent);
-	u8 *uuid = data;
-
-	switch (nd_region_to_nstype(nd_region)) {
-	case ND_DEVICE_NAMESPACE_PMEM: {
-		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
-
-		if (!nspm->uuid)
-			break;
-		if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0)
-			return -EBUSY;
-		break;
-	}
-	case ND_DEVICE_NAMESPACE_BLK: {
-		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
-
-		if (!nsblk->uuid)
-			break;
-		if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) == 0)
-			return -EBUSY;
-		break;
-	}
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static int is_namespace_uuid_busy(struct device *dev, void *data)
-{
-	if (is_nd_pmem(dev) || is_nd_blk(dev))
-		return device_for_each_child(dev, data, is_uuid_busy);
-	return 0;
-}
-
-/**
- * nd_is_uuid_unique - verify that no other namespace has @uuid
- * @dev: any device on a nvdimm_bus
- * @uuid: uuid to check
- */
-bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
-{
-	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-
-	if (!nvdimm_bus)
-		return false;
-	WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
-	if (device_for_each_child(&nvdimm_bus->dev, uuid,
-				is_namespace_uuid_busy) != 0)
-		return false;
-	return true;
-}
-
 static ssize_t size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -406,6 +350,9 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
 	struct nd_interleave_set *nd_set = nd_region->nd_set;
 	int type = nd_region_to_nstype(nd_region);
 
+	if (!is_nd_pmem(dev) && a == &dev_attr_pfn_seed.attr)
+		return 0;
+
 	if (a != &dev_attr_set_cookie.attr
 			&& a != &dev_attr_available_size.attr)
 		return a->mode;
@@ -487,6 +434,13 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			nd_region_create_blk_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
+	if (is_nd_pfn(dev) && probe) {
+		nd_region = to_nd_region(dev->parent);
+		nvdimm_bus_lock(dev);
+		if (nd_region->pfn_seed == dev)
+			nd_region_create_pfn_seed(nd_region);
+		nvdimm_bus_unlock(dev);
+	}
 }
 
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev)

fs/block_dev.c

@@ -156,11 +156,16 @@ blkdev_get_block(struct inode *inode, sector_t iblock,
 	return 0;
 }
 
+static struct inode *bdev_file_inode(struct file *file)
+{
+	return file->f_mapping->host;
+}
+
 static ssize_t
 blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
+	struct inode *inode = bdev_file_inode(file);
 
 	if (IS_DAX(inode))
 		return dax_do_io(iocb, inode, iter, offset, blkdev_get_block,
@@ -338,7 +343,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
  */
 static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 {
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t retval;
 
 	mutex_lock(&bd_inode->i_mutex);
@@ -349,7 +354,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int whence)
 	
 int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 {
-	struct inode *bd_inode = filp->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(filp);
 	struct block_device *bdev = I_BDEV(bd_inode);
 	int error;
 	
@@ -1224,8 +1229,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				}
 			}
 
-			if (!ret)
+			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
+				if (!blkdev_dax_capable(bdev))
+					bdev->bd_inode->i_flags &= ~S_DAX;
+			}
 
 			/*
 			 * If the device is invalidated, rescan partition
@@ -1239,6 +1247,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				else if (ret == -ENOMEDIUM)
 					invalidate_partitions(disk, bdev);
 			}
+
 			if (ret)
 				goto out_clear;
 		} else {
@@ -1259,12 +1268,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
-			/*
-			 * If the partition is not aligned on a page
-			 * boundary, we can't do dax I/O to it.
-			 */
-			if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
-			    (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+			if (!blkdev_dax_capable(bdev))
 				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {
@@ -1599,14 +1603,14 @@ EXPORT_SYMBOL(blkdev_put);
 
 static int blkdev_close(struct inode * inode, struct file * filp)
 {
-	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
+	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
 	blkdev_put(bdev, filp->f_mode);
 	return 0;
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
 	fmode_t mode = file->f_mode;
 
 	/*
@@ -1631,7 +1635,7 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	struct blk_plug plug;
 	ssize_t ret;
@@ -1663,7 +1667,7 @@ EXPORT_SYMBOL_GPL(blkdev_write_iter);
 ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
 	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = file->f_mapping->host;
+	struct inode *bd_inode = bdev_file_inode(file);
 	loff_t size = i_size_read(bd_inode);
 	loff_t pos = iocb->ki_pos;
 
@@ -1702,13 +1706,101 @@ static const struct address_space_operations def_blk_aops = {
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
+#ifdef CONFIG_FS_DAX
+/*
+ * In the raw block case we do not need to contend with truncation nor
+ * unwritten file extents.  Without those concerns there is no need for
+ * additional locking beyond the mmap_sem context that these routines
+ * are already executing under.
+ *
+ * Note, there is no protection if the block device is dynamically
+ * resized (partition grow/shrink) during a fault. A stable block device
+ * size is already not enforced in the blkdev_direct_IO path.
+ *
+ * For DAX, it is the responsibility of the block device driver to
+ * ensure the whole-disk device size is stable while requests are in
+ * flight.
+ *
+ * Finally, unlike the filemap_page_mkwrite() case there is no
+ * filesystem superblock to sync against freezing.  We still include a
+ * pfn_mkwrite callback for dax drivers to receive write fault
+ * notifications.
+ */
+static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
+}
+
+static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
+{
+	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
+}
+
+static void blkdev_vm_open(struct vm_area_struct *vma)
+{
+	struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+	struct block_device *bdev = I_BDEV(bd_inode);
+
+	mutex_lock(&bd_inode->i_mutex);
+	bdev->bd_map_count++;
+	mutex_unlock(&bd_inode->i_mutex);
+}
+
+static void blkdev_vm_close(struct vm_area_struct *vma)
+{
+	struct inode *bd_inode = bdev_file_inode(vma->vm_file);
+	struct block_device *bdev = I_BDEV(bd_inode);
+
+	mutex_lock(&bd_inode->i_mutex);
+	bdev->bd_map_count--;
+	mutex_unlock(&bd_inode->i_mutex);
+}
+
+static const struct vm_operations_struct blkdev_dax_vm_ops = {
+	.open		= blkdev_vm_open,
+	.close		= blkdev_vm_close,
+	.fault		= blkdev_dax_fault,
+	.pmd_fault	= blkdev_dax_pmd_fault,
+	.pfn_mkwrite	= blkdev_dax_fault,
+};
+
+static const struct vm_operations_struct blkdev_default_vm_ops = {
+	.open		= blkdev_vm_open,
+	.close		= blkdev_vm_close,
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+};
+
+static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct inode *bd_inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(bd_inode);
+
+	file_accessed(file);
+	mutex_lock(&bd_inode->i_mutex);
+	bdev->bd_map_count++;
+	if (IS_DAX(bd_inode)) {
+		vma->vm_ops = &blkdev_dax_vm_ops;
+		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
+	} else {
+		vma->vm_ops = &blkdev_default_vm_ops;
+	}
+	mutex_unlock(&bd_inode->i_mutex);
+
+	return 0;
+}
+#else
+#define blkdev_mmap generic_file_mmap
+#endif
+
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.mmap		= generic_file_mmap,
+	.mmap		= blkdev_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT

include/linux/badblocks.h

+#ifndef _LINUX_BADBLOCKS_H
+#define _LINUX_BADBLOCKS_H
+
+#include <linux/seqlock.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+#define BB_LEN_MASK	(0x00000000000001FFULL)
+#define BB_OFFSET_MASK	(0x7FFFFFFFFFFFFE00ULL)
+#define BB_ACK_MASK	(0x8000000000000000ULL)
+#define BB_MAX_LEN	512
+#define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
+#define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
+#define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
+#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
+
+/* Bad block numbers are stored sorted in a single page.
+ * 64bits is used for each block or extent.
+ * 54 bits are sector number, 9 bits are extent size,
+ * 1 bit is an 'acknowledged' flag.
+ */
+#define MAX_BADBLOCKS	(PAGE_SIZE/8)
+
+struct badblocks {
+	struct device *dev;	/* set by devm_init_badblocks */
+	int count;		/* count of bad blocks */
+	int unacked_exist;	/* there probably are unacknowledged
+				 * bad blocks.  This is only cleared
+				 * when a read discovers none
+				 */
+	int shift;		/* shift from sectors to block size
+				 * a -ve shift means badblocks are
+				 * disabled.*/
+	u64 *page;		/* badblock list */
+	int changed;
+	seqlock_t lock;
+	sector_t sector;
+	sector_t size;		/* in sectors */
+};
+
+int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
+		   sector_t *first_bad, int *bad_sectors);
+int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
+			int acknowledged);
+int badblocks_clear(struct badblocks *bb, sector_t s, int sectors);
+void ack_all_badblocks(struct badblocks *bb);
+ssize_t badblocks_show(struct badblocks *bb, char *page, int unack);
+ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
+			int unack);
+int badblocks_init(struct badblocks *bb, int enable);
+void badblocks_exit(struct badblocks *bb);
+struct device;
+int devm_init_badblocks(struct device *dev, struct badblocks *bb);
+static inline void devm_exit_badblocks(struct device *dev, struct badblocks *bb)
+{
+	if (bb->dev != dev) {
+		dev_WARN_ONCE(dev, 1, "%s: badblocks instance not associated\n",
+				__func__);
+		return;
+	}
+	badblocks_exit(bb);
+}
+#endif

include/linux/fs.h

@@ -483,6 +483,9 @@ struct block_device {
 	int			bd_fsfreeze_count;
 	/* Mutex for freeze */
 	struct mutex		bd_fsfreeze_mutex;
+#ifdef CONFIG_FS_DAX
+	int			bd_map_count;
+#endif
 };
 
 /*
@@ -2280,6 +2283,14 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
+#ifdef CONFIG_FS_DAX
+extern bool blkdev_dax_capable(struct block_device *bdev);
+#else
+static inline bool blkdev_dax_capable(struct block_device *bdev)
+{
+	return false;
+}
+#endif
 
 extern struct super_block *blockdev_superblock;
 

include/linux/genhd.h

@@ -162,6 +162,7 @@ struct disk_part_tbl {
 };
 
 struct disk_events;
+struct badblocks;
 
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
@@ -213,6 +214,7 @@ struct gendisk {
 	struct kobject integrity_kobj;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
 	int node_id;
+	struct badblocks *bb;
 };
 
 static inline struct gendisk *part_to_disk(struct hd_struct *part)

include/linux/libnvdimm.h

@@ -116,6 +116,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 
 }
 
+int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
 struct nvdimm_bus *__nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc, struct module *module);
 #define nvdimm_bus_register(parent, desc) \

include/uapi/linux/fs.h

@@ -188,6 +188,8 @@ struct inodes_stat_t {
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
+#define BLKDAXSET _IO(0x12,128)
+#define BLKDAXGET _IO(0x12,129)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */

kernel/resource.c

@@ -1498,8 +1498,15 @@ int iomem_is_exclusive(u64 addr)
 			break;
 		if (p->end < addr)
 			continue;
-		if (p->flags & IORESOURCE_BUSY &&
-		     p->flags & IORESOURCE_EXCLUSIVE) {
+		/*
+		 * A resource is exclusive if IORESOURCE_EXCLUSIVE is set
+		 * or CONFIG_IO_STRICT_DEVMEM is enabled and the
+		 * resource is busy.
+		 */
+		if ((p->flags & IORESOURCE_BUSY) == 0)
+			continue;
+		if (IS_ENABLED(CONFIG_IO_STRICT_DEVMEM)
+				|| p->flags & IORESOURCE_EXCLUSIVE) {
 			err = 1;
 			break;
 		}

lib/Kconfig.debug

@@ -1886,3 +1886,42 @@ source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
 
+config ARCH_HAS_DEVMEM_IS_ALLOWED
+	bool
+
+config STRICT_DEVMEM
+	bool "Filter access to /dev/mem"
+	depends on MMU
+	depends on ARCH_HAS_DEVMEM_IS_ALLOWED
+	default y if TILE || PPC
+	---help---
+	  If this option is disabled, you allow userspace (root) access to all
+	  of memory, including kernel and userspace memory. Accidental
+	  access to this is obviously disastrous, but specific access can
+	  be used by people debugging the kernel. Note that with PAT support
+	  enabled, even in this case there are restrictions on /dev/mem
+	  use due to the cache aliasing requirements.
+
+	  If this option is switched on, and IO_STRICT_DEVMEM=n, the /dev/mem
+	  file only allows userspace access to PCI space and the BIOS code and
+	  data regions.  This is sufficient for dosemu and X and all common
+	  users of /dev/mem.
+
+	  If in doubt, say Y.
+
+config IO_STRICT_DEVMEM
+	bool "Filter I/O access to /dev/mem"
+	depends on STRICT_DEVMEM
+	default STRICT_DEVMEM
+	---help---
+	  If this option is disabled, you allow userspace (root) access to all
+	  io-memory regardless of whether a driver is actively using that
+	  range.  Accidental access to this is obviously disastrous, but
+	  specific access can be used by people debugging kernel drivers.
+
+	  If this option is switched on, the /dev/mem file only allows
+	  userspace access to *idle* io-memory ranges (see /proc/iomem) This
+	  may break traditional users of /dev/mem (dosemu, legacy X, etc...)
+	  if the driver using a given range cannot be disabled.
+
+	  If in doubt, say Y.

tools/testing/nvdimm/Kbuild

@@ -9,6 +9,8 @@ ldflags-y += --wrap=memunmap
 ldflags-y += --wrap=__devm_request_region
 ldflags-y += --wrap=__request_region
 ldflags-y += --wrap=__release_region
+ldflags-y += --wrap=devm_memremap_pages
+ldflags-y += --wrap=phys_to_pfn_t
 
 DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm

tools/testing/nvdimm/test/iomap.c

@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/io.h>
+#include <linux/mm.h>
 #include "nfit_test.h"
 
 static LIST_HEAD(iomap_head);
@@ -41,7 +42,7 @@ void nfit_test_teardown(void)
 }
 EXPORT_SYMBOL(nfit_test_teardown);
 
-static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
+static struct nfit_test_resource *__get_nfit_res(resource_size_t resource)
 {
 	struct iomap_ops *ops;
 
@@ -51,14 +52,22 @@ static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
 	return NULL;
 }
 
-void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
-		void __iomem *(*fallback_fn)(resource_size_t, unsigned long))
+static struct nfit_test_resource *get_nfit_res(resource_size_t resource)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *res;
 
 	rcu_read_lock();
-	nfit_res = get_nfit_res(offset);
+	res = __get_nfit_res(resource);
 	rcu_read_unlock();
+
+	return res;
+}
+
+void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
+		void __iomem *(*fallback_fn)(resource_size_t, unsigned long))
+{
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
 	if (nfit_res)
 		return (void __iomem *) nfit_res->buf + offset
 			- nfit_res->res->start;
@@ -68,11 +77,8 @@ void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
 void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
 		resource_size_t offset, unsigned long size)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	rcu_read_lock();
-	nfit_res = get_nfit_res(offset);
-	rcu_read_unlock();
 	if (nfit_res)
 		return (void __iomem *) nfit_res->buf + offset
 			- nfit_res->res->start;
@@ -83,25 +89,58 @@ EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
 void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
 		size_t size, unsigned long flags)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	rcu_read_lock();
-	nfit_res = get_nfit_res(offset);
-	rcu_read_unlock();
 	if (nfit_res)
 		return nfit_res->buf + offset - nfit_res->res->start;
 	return devm_memremap(dev, offset, size, flags);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap);
 
+#ifdef __HAVE_ARCH_PTE_DEVMAP
+#include <linux/memremap.h>
+#include <linux/pfn_t.h>
+
+void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
+		struct percpu_ref *ref, struct vmem_altmap *altmap)
+{
+	resource_size_t offset = res->start;
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
+	if (nfit_res)
+		return nfit_res->buf + offset - nfit_res->res->start;
+	return devm_memremap_pages(dev, res, ref, altmap);
+}
+EXPORT_SYMBOL(__wrap_devm_memremap_pages);
+
+pfn_t __wrap_phys_to_pfn_t(dma_addr_t addr, unsigned long flags)
+{
+	struct nfit_test_resource *nfit_res = get_nfit_res(addr);
+
+	if (nfit_res)
+		flags &= ~PFN_MAP;
+        return phys_to_pfn_t(addr, flags);
+}
+EXPORT_SYMBOL(__wrap_phys_to_pfn_t);
+#else
+/* to be removed post 4.5-rc1 */
+void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res)
+{
+	resource_size_t offset = res->start;
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
+
+	if (nfit_res)
+		return nfit_res->buf + offset - nfit_res->res->start;
+	return devm_memremap_pages(dev, res);
+}
+EXPORT_SYMBOL(__wrap_devm_memremap_pages);
+#endif
+
 void *__wrap_memremap(resource_size_t offset, size_t size,
 		unsigned long flags)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
-	rcu_read_lock();
-	nfit_res = get_nfit_res(offset);
-	rcu_read_unlock();
 	if (nfit_res)
 		return nfit_res->buf + offset - nfit_res->res->start;
 	return memremap(offset, size, flags);
@@ -110,11 +149,8 @@ EXPORT_SYMBOL(__wrap_memremap);
 
 void __wrap_devm_memunmap(struct device *dev, void *addr)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
 
-	rcu_read_lock();
-	nfit_res = get_nfit_res((unsigned long) addr);
-	rcu_read_unlock();
 	if (nfit_res)
 		return;
 	return devm_memunmap(dev, addr);
@@ -135,11 +171,7 @@ EXPORT_SYMBOL(__wrap_ioremap_wc);
 
 void __wrap_iounmap(volatile void __iomem *addr)
 {
-	struct nfit_test_resource *nfit_res;
-
-	rcu_read_lock();
-	nfit_res = get_nfit_res((unsigned long) addr);
-	rcu_read_unlock();
+	struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
 	if (nfit_res)
 		return;
 	return iounmap(addr);
@@ -148,11 +180,8 @@ EXPORT_SYMBOL(__wrap_iounmap);
 
 void __wrap_memunmap(void *addr)
 {
-	struct nfit_test_resource *nfit_res;
+	struct nfit_test_resource *nfit_res = get_nfit_res((long) addr);
 
-	rcu_read_lock();
-	nfit_res = get_nfit_res((unsigned long) addr);
-	rcu_read_unlock();
 	if (nfit_res)
 		return;
 	return memunmap(addr);
@@ -166,9 +195,7 @@ static struct resource *nfit_test_request_region(struct device *dev,
 	struct nfit_test_resource *nfit_res;
 
 	if (parent == &iomem_resource) {
-		rcu_read_lock();
 		nfit_res = get_nfit_res(start);
-		rcu_read_unlock();
 		if (nfit_res) {
 			struct resource *res = nfit_res->res + 1;
 
@@ -218,9 +245,7 @@ void __wrap___release_region(struct resource *parent, resource_size_t start,
 	struct nfit_test_resource *nfit_res;
 
 	if (parent == &iomem_resource) {
-		rcu_read_lock();
 		nfit_res = get_nfit_res(start);
-		rcu_read_unlock();
 		if (nfit_res) {
 			struct resource *res = nfit_res->res + 1;
 

tools/testing/nvdimm/test/nfit.c

@@ -248,6 +248,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd,
 
 	nd_cmd->out_length = 256;
 	nd_cmd->num_records = 0;
+	nd_cmd->address = 0;
+	nd_cmd->length = -1ULL;
 	nd_cmd->status = 0;
 
 	return 0;
@@ -1088,6 +1090,8 @@ static void nfit_test1_setup(struct nfit_test *t)
 	struct acpi_nfit_memory_map *memdev;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_system_address *spa;
+	struct nvdimm_bus_descriptor *nd_desc;
+	struct acpi_nfit_desc *acpi_desc;
 
 	offset = 0;
 	/* spa0 (flat range with no bdw aliasing) */
@@ -1135,6 +1139,13 @@ static void nfit_test1_setup(struct nfit_test *t)
 	dcr->command_size = 0;
 	dcr->status_offset = 0;
 	dcr->status_size = 0;
+
+	acpi_desc = &t->acpi_desc;
+	set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_dsm_force_en);
+	set_bit(ND_CMD_ARS_START, &acpi_desc->bus_dsm_force_en);
+	set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_dsm_force_en);
+	nd_desc = &acpi_desc->nd_desc;
+	nd_desc->ndctl = nfit_test_ctl;
 }
 
 static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,