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
  ...

5 files changed, 81 insertions, 0 deletions

diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h
new file mode 100644
index 0000000..c3bdf8c
--- /dev/null
+++ b/include/linux/badblocks.h
@@ -0,0 +1,65 @@
+#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
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 731262c..eb73d74 100644
--- a/include/linux/fs.h
+++ b/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;
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 847cc1d..5c70676 100644
--- a/include/linux/genhd.h
+++ b/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)
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 3f021dc..bed40df 100644
--- a/include/linux/libnvdimm.h
+++ b/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) \
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index b38e647..b8a5b3b 100644
--- a/include/uapi/linux/fs.h
+++ b/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 */