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

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

  Change summary:

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

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

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

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

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

  Acknowledgements that came after the branch was pushed:

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

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

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

8 files changed, 47 insertions, 55 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 83d28623645f..5493a66dc710 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1923,28 +1923,12 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-/**
- * struct blk_dax_ctl - control and output parameters for ->direct_access
- * @sector: (input) offset relative to a block_device
- * @addr: (output) kernel virtual address for @sector populated by driver
- * @pfn: (output) page frame number for @addr populated by driver
- * @size: (input) number of bytes requested
- */
-struct blk_dax_ctl {
-	sector_t sector;
-	void *addr;
-	long size;
-	pfn_t pfn;
-};
-
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
 	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	long (*direct_access)(struct block_device *, sector_t, void **, pfn_t *,
-			long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1963,9 +1947,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
 extern int bdev_read_page(struct block_device *, sector_t, struct page *);
 extern int bdev_write_page(struct block_device *, sector_t, struct page *,
 						struct writeback_control *);
-extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *);
 extern int bdev_dax_supported(struct super_block *, int);
-extern bool bdev_dax_capable(struct block_device *);
+int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
 #else /* CONFIG_BLOCK */
 
 struct block_device;
diff --git a/include/linux/dax.h b/include/linux/dax.h
index d8a3dc042e1c..d3158e74a59e 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -7,6 +7,28 @@
 #include <asm/pgtable.h>
 
 struct iomap_ops;
+struct dax_device;
+struct dax_operations {
+	/*
+	 * direct_access: translate a device-relative
+	 * logical-page-offset into an absolute physical pfn. Return the
+	 * number of pages available for DAX at that pfn.
+	 */
+	long (*direct_access)(struct dax_device *, pgoff_t, long,
+			void **, pfn_t *);
+};
+
+int dax_read_lock(void);
+void dax_read_unlock(int id);
+struct dax_device *dax_get_by_host(const char *host);
+struct dax_device *alloc_dax(void *private, const char *host,
+		const struct dax_operations *ops);
+void put_dax(struct dax_device *dax_dev);
+bool dax_alive(struct dax_device *dax_dev);
+void kill_dax(struct dax_device *dax_dev);
+void *dax_get_private(struct dax_device *dax_dev);
+long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
+		void **kaddr, pfn_t *pfn);
 
 /*
  * We use lowest available bit in exceptional entry for locking, one bit for
@@ -48,17 +70,13 @@ void dax_wake_mapping_entry_waiter(struct address_space *mapping,
 		pgoff_t index, void *entry, bool wake_all);
 
 #ifdef CONFIG_FS_DAX
-struct page *read_dax_sector(struct block_device *bdev, sector_t n);
-int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+int __dax_zero_page_range(struct block_device *bdev,
+		struct dax_device *dax_dev, sector_t sector,
 		unsigned int offset, unsigned int length);
 #else
-static inline struct page *read_dax_sector(struct block_device *bdev,
-		sector_t n)
-{
-	return ERR_PTR(-ENXIO);
-}
 static inline int __dax_zero_page_range(struct block_device *bdev,
-		sector_t sector, unsigned int offset, unsigned int length)
+		struct dax_device *dax_dev, sector_t sector,
+		unsigned int offset, unsigned int length)
 {
 	return -ENXIO;
 }
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 78ad0624cdae..f4c639c0c362 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -130,13 +130,15 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  *  < 0 : error
  * >= 0 : the number of bytes accessible at the address
  */
-typedef long (*dm_direct_access_fn) (struct dm_target *ti, sector_t sector,
-				     void **kaddr, pfn_t *pfn, long size);
+typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
+		long nr_pages, void **kaddr, pfn_t *pfn);
+#define PAGE_SECTORS (PAGE_SIZE / 512)
 
 void dm_error(const char *message);
 
 struct dm_dev {
 	struct block_device *bdev;
+	struct dax_device *dax_dev;
 	fmode_t mode;
 	char name[16];
 };
@@ -178,7 +180,7 @@ struct target_type {
 	dm_busy_fn busy;
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
-	dm_direct_access_fn direct_access;
+	dm_dax_direct_access_fn direct_access;
 
 	/* For internal device-mapper use. */
 	struct list_head list;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 7291810067eb..f753e788da31 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -41,6 +41,7 @@ struct iomap {
 	u16			type;	/* type of mapping */
 	u16			flags;	/* flags for mapping */
 	struct block_device	*bdev;	/* block device for I/O */
+	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 };
 
 /*
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 77e7af32543f..6c807017128d 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -20,9 +20,11 @@
 
 enum {
 	/* when a dimm supports both PMEM and BLK access a label is required */
-	NDD_ALIASING = 1 << 0,
+	NDD_ALIASING = 0,
 	/* unarmed memory devices may not persist writes */
-	NDD_UNARMED = 1 << 1,
+	NDD_UNARMED = 1,
+	/* locked memory devices should not be accessed */
+	NDD_LOCKED = 2,
 
 	/* need to set a limit somewhere, but yes, this is likely overkill */
 	ND_IOCTL_MAX_BUFLEN = SZ_4M,
@@ -120,7 +122,7 @@ 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);
-void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
+void nvdimm_forget_poison(struct nvdimm_bus *nvdimm_bus,
 		phys_addr_t start, unsigned int len);
 struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc);
diff --git a/include/linux/pmem.h b/include/linux/pmem.h
index e856c2cb0fe8..71ecf3d46aac 100644
--- a/include/linux/pmem.h
+++ b/include/linux/pmem.h
@@ -31,12 +31,6 @@ static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
 	BUG();
 }
 
-static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
-{
-	BUG();
-	return -EFAULT;
-}
-
 static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 		struct iov_iter *i)
 {
@@ -65,23 +59,6 @@ static inline bool arch_has_pmem_api(void)
 	return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API);
 }
 
-/*
- * memcpy_from_pmem - read from persistent memory with error handling
- * @dst: destination buffer
- * @src: source buffer
- * @size: transfer length
- *
- * Returns 0 on success negative error code on failure.
- */
-static inline int memcpy_from_pmem(void *dst, void const *src, size_t size)
-{
-	if (arch_has_pmem_api())
-		return arch_memcpy_from_pmem(dst, src, size);
-	else
-		memcpy(dst, src, size);
-	return 0;
-}
-
 /**
  * memcpy_to_pmem - copy data to persistent memory
  * @dst: destination buffer for the copy
diff --git a/include/linux/string.h b/include/linux/string.h
index c4011b28f3d8..537918f8a98e 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -114,6 +114,14 @@ extern int memcmp(const void *,const void *,__kernel_size_t);
 #ifndef __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
+#ifndef __HAVE_ARCH_MEMCPY_MCSAFE
+static inline __must_check int memcpy_mcsafe(void *dst, const void *src,
+		size_t cnt)
+{
+	memcpy(dst, src, cnt);
+	return 0;
+}
+#endif
 void *memchr_inv(const void *s, int c, size_t n);
 char *strreplace(char *s, char old, char new);
 
diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h
index ede5c6a62164..7ad3863cb88b 100644
--- a/include/uapi/linux/ndctl.h
+++ b/include/uapi/linux/ndctl.h
@@ -169,6 +169,7 @@ enum {
 enum {
 	ND_ARS_VOLATILE = 1,
 	ND_ARS_PERSISTENT = 2,
+	ND_CONFIG_LOCKED = 1,
 };
 
 static inline const char *nvdimm_bus_cmd_name(unsigned cmd)