DAX error handling for 4.7

- Until now, dax has been disabled if media errors were found on
   any device. This enables the use of DAX in the presence of these
   errors by making all sector-aligned zeroing go through the driver.
 - The driver (already) has the ability to clear errors on writes that
   are sent through the block layer using 'DSMs' defined in ACPI 6.1.
 
 Other misc changes:
 
 - When mounting DAX filesystems, check to make sure the partition
   is page aligned. This is a requirement for DAX, and previously, we
   allowed such unaligned mounts to succeed, but subsequent reads/writes
   would fail.
 
 - Misc/cleanup fixes from Jan that remove unused code from DAX related to
   zeroing, writeback, and some size checks.
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABAgAGBQJXQ4GKAAoJEHr6Yb6juE3/zowP/iclIhgXXXMQJRUHJlePMXC8
 15sGZ32JS1ak9g7vrsmNVEDNynfNtiMYdBxtUyRuj6xqgwdZvFk3F55KOCPtaeA1
 +yADkgeRkTAcwzmHw9WQVEzBCqyzSisdrwtEfH817qdq9FJdH66x2Kos6i+HeAVr
 5Q/e4gs7lKrjf384/QBl+wxNZOndJaQAPd2VRHQqx2A9F33v0ljdwRaUG1r4fjK2
 dtmhcZCqdQyuAGXW3piTnZc5ZFc3DPqO4FkEfqkEK3lFOflK0fd8wMsAZRp/Jd0j
 GJsgnVSWSqG0Dz476djlG0w8t2p5Jv1g9cKChV+ZZEdFLKWHCOUFqXNj8uI8I4k5
 cOEKCHyJ3IwfSHhNQqktEWrQN4T8ZXhWtuc9GuV4UZYuqJqHci6EdR/YsWsJjV+L
 lm/qvK4ipDS1pivxOy8KX/iN0z7Io8J9GXpStDx3g8iWjLlh4YYlbJLWeeRepo/z
 aPlV/QAKcHiGY6jzLExrZIyCWkzwo6O+0p1Kxerv9/7K/32HWbOodZ+tC8eD+N25
 pV69nCGf+u50T2TtIx1+iann4NC1r7zg5yqnT9AgpyZpiwR5joCDzI5sXW+D0rcS
 vPtfM84Ccdeq/e6mvfIpZgR0/npQapKnrmUest0J7P2BFPHiFPji1KzZ7M+1aFOo
 9R6JdrAj0Sc+FBa+cGzH
 =v6Of
 -----END PGP SIGNATURE-----

Merge tag 'dax-misc-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull misc DAX updates from Vishal Verma:
 "DAX error handling for 4.7

   - Until now, dax has been disabled if media errors were found on any
     device.  This enables the use of DAX in the presence of these
     errors by making all sector-aligned zeroing go through the driver.

   - The driver (already) has the ability to clear errors on writes that
     are sent through the block layer using 'DSMs' defined in ACPI 6.1.

  Other misc changes:

   - When mounting DAX filesystems, check to make sure the partition is
     page aligned.  This is a requirement for DAX, and previously, we
     allowed such unaligned mounts to succeed, but subsequent
     reads/writes would fail.

   - Misc/cleanup fixes from Jan that remove unused code from DAX
     related to zeroing, writeback, and some size checks"

* tag 'dax-misc-for-4.7' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm:
  dax: fix a comment in dax_zero_page_range and dax_truncate_page
  dax: for truncate/hole-punch, do zeroing through the driver if possible
  dax: export a low-level __dax_zero_page_range helper
  dax: use sb_issue_zerout instead of calling dax_clear_sectors
  dax: enable dax in the presence of known media errors (badblocks)
  dax: fallback from pmd to pte on error
  block: Update blkdev_dax_capable() for consistency
  xfs: Add alignment check for DAX mount
  ext2: Add alignment check for DAX mount
  ext4: Add alignment check for DAX mount
  block: Add bdev_dax_supported() for dax mount checks
  block: Add vfs_msg() interface
  dax: Remove redundant inode size checks
  dax: Remove pointless writeback from dax_do_io()
  dax: Remove zeroing from dax_io()
  dax: Remove dead zeroing code from fault handlers
  ext2: Avoid DAX zeroing to corrupt data
  ext2: Fix block zeroing in ext2_get_blocks() for DAX
  dax: Remove complete_unwritten argument
  DAX: move RADIX_DAX_ definitions to dax.c

Documentation/filesystems/dax.txt

@@ -79,6 +79,38 @@ These filesystems may be used for inspiration:
 - ext4: the fourth extended filesystem, see Documentation/filesystems/ext4.txt
 
 
+Handling Media Errors
+---------------------
+
+The libnvdimm subsystem stores a record of known media error locations for
+each pmem block device (in gendisk->badblocks). If we fault at such location,
+or one with a latent error not yet discovered, the application can expect
+to receive a SIGBUS. Libnvdimm also allows clearing of these errors by simply
+writing the affected sectors (through the pmem driver, and if the underlying
+NVDIMM supports the clear_poison DSM defined by ACPI).
+
+Since DAX IO normally doesn't go through the driver/bio path, applications or
+sysadmins have an option to restore the lost data from a prior backup/inbuilt
+redundancy in the following ways:
+
+1. Delete the affected file, and restore from a backup (sysadmin route):
+   This will free the file system blocks that were being used by the file,
+   and the next time they're allocated, they will be zeroed first, which
+   happens through the driver, and will clear bad sectors.
+
+2. Truncate or hole-punch the part of the file that has a bad-block (at least
+   an entire aligned sector has to be hole-punched, but not necessarily an
+   entire filesystem block).
+
+These are the two basic paths that allow DAX filesystems to continue operating
+in the presence of media errors. More robust error recovery mechanisms can be
+built on top of this in the future, for example, involving redundancy/mirroring
+provided at the block layer through DM, or additionally, at the filesystem
+level. These would have to rely on the above two tenets, that error clearing
+can happen either by sending an IO through the driver, or zeroing (also through
+the driver).
+
+
 Shortcomings
 ------------
 

arch/powerpc/sysdev/axonram.c

@@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
  */
 static long
 axon_ram_direct_access(struct block_device *device, sector_t sector,
-		       void __pmem **kaddr, pfn_t *pfn)
+		       void __pmem **kaddr, pfn_t *pfn, long size)
 {
 	struct axon_ram_bank *bank = device->bd_disk->private_data;
 	loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT;

block/ioctl.c

@@ -4,7 +4,6 @@
 #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>

drivers/block/brd.c

@@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector,
 
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 static long brd_direct_access(struct block_device *bdev, sector_t sector,
-			void __pmem **kaddr, pfn_t *pfn)
+			void __pmem **kaddr, pfn_t *pfn, long size)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	struct page *page;

drivers/nvdimm/pmem.c

@@ -164,14 +164,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 }
 
 static long pmem_direct_access(struct block_device *bdev, sector_t sector,
-		      void __pmem **kaddr, pfn_t *pfn)
+		      void __pmem **kaddr, pfn_t *pfn, long size)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	resource_size_t offset = sector * 512 + pmem->data_offset;
 
+	if (unlikely(is_bad_pmem(&pmem->bb, sector, size)))
+		return -EIO;
 	*kaddr = pmem->virt_addr + offset;
 	*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
 
+	/*
+	 * If badblocks are present, limit known good range to the
+	 * requested range.
+	 */
+	if (unlikely(pmem->bb.count))
+		return size;
 	return pmem->size - pmem->pfn_pad - offset;
 }
 

drivers/s390/block/dcssblk.c

@@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode);
 static blk_qc_t dcssblk_make_request(struct request_queue *q,
 						struct bio *bio);
 static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum,
-			 void __pmem **kaddr, pfn_t *pfn);
+			 void __pmem **kaddr, pfn_t *pfn, long size);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -884,7 +884,7 @@ fail:
 
 static long
 dcssblk_direct_access (struct block_device *bdev, sector_t secnum,
-			void __pmem **kaddr, pfn_t *pfn)
+			void __pmem **kaddr, pfn_t *pfn, long size)
 {
 	struct dcssblk_dev_info *dev_info;
 	unsigned long offset, dev_sz;

fs/block_dev.c

@@ -51,6 +51,18 @@ struct block_device *I_BDEV(struct inode *inode)
 }
 EXPORT_SYMBOL(I_BDEV);
 
+void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf);
+	va_end(args);
+}
+
 static void bdev_write_inode(struct block_device *bdev)
 {
 	struct inode *inode = bdev->bd_inode;
@@ -489,7 +501,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 	sector += get_start_sect(bdev);
 	if (sector % (PAGE_SIZE / 512))
 		return -EINVAL;
-	avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn);
+	avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
 	if (!avail)
 		return -ERANGE;
 	if (avail > 0 && avail & ~PAGE_MASK)
@@ -498,6 +510,75 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
 }
 EXPORT_SYMBOL_GPL(bdev_direct_access);
 
+/**
+ * bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @sb: The superblock of the device
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: negative errno if unsupported, 0 if supported.
+ */
+int bdev_dax_supported(struct super_block *sb, int blocksize)
+{
+	struct blk_dax_ctl dax = {
+		.sector = 0,
+		.size = PAGE_SIZE,
+	};
+	int err;
+
+	if (blocksize != PAGE_SIZE) {
+		vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
+		return -EINVAL;
+	}
+
+	err = bdev_direct_access(sb->s_bdev, &dax);
+	if (err < 0) {
+		switch (err) {
+		case -EOPNOTSUPP:
+			vfs_msg(sb, KERN_ERR,
+				"error: device does not support dax");
+			break;
+		case -EINVAL:
+			vfs_msg(sb, KERN_ERR,
+				"error: unaligned partition for dax");
+			break;
+		default:
+			vfs_msg(sb, KERN_ERR,
+				"error: dax access failed (%d)", err);
+		}
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bdev_dax_supported);
+
+/**
+ * bdev_dax_capable() - Return if the raw device is capable for dax
+ * @bdev: The device for raw block device access
+ */
+bool bdev_dax_capable(struct block_device *bdev)
+{
+	struct blk_dax_ctl dax = {
+		.size = PAGE_SIZE,
+	};
+
+	if (!IS_ENABLED(CONFIG_FS_DAX))
+		return false;
+
+	dax.sector = 0;
+	if (bdev_direct_access(bdev, &dax) < 0)
+		return false;
+
+	dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512);
+	if (bdev_direct_access(bdev, &dax) < 0)
+		return false;
+
+	return true;
+}
+
 /*
  * pseudo-fs
  */
@@ -1160,33 +1241,6 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static bool blkdev_dax_capable(struct block_device *bdev)
-{
-	struct gendisk *disk = bdev->bd_disk;
-
-	if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
-		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 void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
@@ -1266,7 +1320,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 
 			if (!ret) {
 				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
-				if (!blkdev_dax_capable(bdev))
+				if (!bdev_dax_capable(bdev))
 					bdev->bd_inode->i_flags &= ~S_DAX;
 			}
 
@@ -1303,7 +1357,7 @@ 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 (!blkdev_dax_capable(bdev))
+			if (!bdev_dax_capable(bdev))
 				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {

fs/dax.c

@@ -87,50 +87,6 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n)
 	return page;
 }
 
-/*
- * dax_clear_sectors() is called from within transaction context from XFS,
- * and hence this means the stack from this point must follow GFP_NOFS
- * semantics for all operations.
- */
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size)
-{
-	struct blk_dax_ctl dax = {
-		.sector = _sector,
-		.size = _size,
-	};
-
-	might_sleep();
-	do {
-		long count, sz;
-
-		count = dax_map_atomic(bdev, &dax);
-		if (count < 0)
-			return count;
-		sz = min_t(long, count, SZ_128K);
-		clear_pmem(dax.addr, sz);
-		dax.size -= sz;
-		dax.sector += sz / 512;
-		dax_unmap_atomic(bdev, &dax);
-		cond_resched();
-	} while (dax.size);
-
-	wmb_pmem();
-	return 0;
-}
-EXPORT_SYMBOL_GPL(dax_clear_sectors);
-
-/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
-static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
-		loff_t pos, loff_t end)
-{
-	loff_t final = end - pos + first; /* The final byte of the buffer */
-
-	if (first > 0)
-		clear_pmem(addr, first);
-	if (final < size)
-		clear_pmem(addr + final, size - final);
-}
-
 static bool buffer_written(struct buffer_head *bh)
 {
 	return buffer_mapped(bh) && !buffer_unwritten(bh);
@@ -169,6 +125,9 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 	struct blk_dax_ctl dax = {
 		.addr = (void __pmem *) ERR_PTR(-EIO),
 	};
+	unsigned blkbits = inode->i_blkbits;
+	sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1)
+								>> blkbits;
 
 	if (rw == READ)
 		end = min(end, i_size_read(inode));
@@ -176,7 +135,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 	while (pos < end) {
 		size_t len;
 		if (pos == max) {
-			unsigned blkbits = inode->i_blkbits;
 			long page = pos >> PAGE_SHIFT;
 			sector_t block = page << (PAGE_SHIFT - blkbits);
 			unsigned first = pos - (block << blkbits);
@@ -192,6 +150,13 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 					bh->b_size = 1 << blkbits;
 				bh_max = pos - first + bh->b_size;
 				bdev = bh->b_bdev;
+				/*
+				 * We allow uninitialized buffers for writes
+				 * beyond EOF as those cannot race with faults
+				 */
+				WARN_ON_ONCE(
+					(buffer_new(bh) && block < file_blks) ||
+					(rw == WRITE && buffer_unwritten(bh)));
 			} else {
 				unsigned done = bh->b_size -
 						(bh_max - (pos - first));
@@ -211,11 +176,6 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 					rc = map_len;
 					break;
 				}
-				if (buffer_unwritten(bh) || buffer_new(bh)) {
-					dax_new_buf(dax.addr, map_len, first,
-							pos, end);
-					need_wmb = true;
-				}
 				dax.addr += first;
 				size = map_len - first;
 			}
@@ -276,15 +236,8 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 	memset(&bh, 0, sizeof(bh));
 	bh.b_bdev = inode->i_sb->s_bdev;
 
-	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
+	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
-		struct address_space *mapping = inode->i_mapping;
 		inode_lock(inode);
-		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
-		if (retval) {
-			inode_unlock(inode);
-			goto out;
-		}
-	}
 
 	/* Protects against truncate */
 	if (!(flags & DIO_SKIP_DIO_COUNT))
@@ -305,7 +258,6 @@ ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
 
 	if (!(flags & DIO_SKIP_DIO_COUNT))
 		inode_dio_end(inode);
- out:
 	return retval;
 }
 EXPORT_SYMBOL_GPL(dax_do_io);
@@ -321,20 +273,11 @@ EXPORT_SYMBOL_GPL(dax_do_io);
 static int dax_load_hole(struct address_space *mapping, struct page *page,
 							struct vm_fault *vmf)
 {
-	unsigned long size;
-	struct inode *inode = mapping->host;
 	if (!page)
 		page = find_or_create_page(mapping, vmf->pgoff,
 						GFP_KERNEL | __GFP_ZERO);
 	if (!page)
 		return VM_FAULT_OOM;
-	/* Recheck i_size under page lock to avoid truncate race */
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (vmf->pgoff >= size) {
-		unlock_page(page);
-		put_page(page);
-		return VM_FAULT_SIGBUS;
-	}
 
 	vmf->page = page;
 	return VM_FAULT_LOCKED;
@@ -565,33 +508,14 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
 		.sector = to_sector(bh, inode),
 		.size = bh->b_size,
 	};
-	pgoff_t size;
 	int error;
 
 	i_mmap_lock_read(mapping);
 
-	/*
-	 * Check truncate didn't happen while we were allocating a block.
-	 * If it did, this block may or may not be still allocated to the
-	 * file.  We can't tell the filesystem to free it because we can't
-	 * take i_mutex here.  In the worst case, the file still has blocks
-	 * allocated past the end of the file.
-	 */
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (unlikely(vmf->pgoff >= size)) {
-		error = -EIO;
-		goto out;
-	}
-
 	if (dax_map_atomic(bdev, &dax) < 0) {
 		error = PTR_ERR(dax.addr);
 		goto out;
 	}
-
-	if (buffer_unwritten(bh) || buffer_new(bh)) {
-		clear_pmem(dax.addr, PAGE_SIZE);
-		wmb_pmem();
-	}
 	dax_unmap_atomic(bdev, &dax);
 
 	error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
@@ -612,19 +536,13 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
- * @complete_unwritten: The filesystem method used to convert unwritten blocks
- *	to written so the data written to them is exposed. This is required for
- *	required by write faults for filesystems that will return unwritten
- *	extent mappings from @get_block, but it is optional for reads as
- *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
- *	not support unwritten extents, the it should pass NULL.
  *
  * When a page fault occurs, filesystems may call this helper in their
  * fault handler for DAX files. __dax_fault() assumes the caller has done all
  * the necessary locking for the page fault to proceed successfully.
  */
 int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-			get_block_t get_block, dax_iodone_t complete_unwritten)
+			get_block_t get_block)
 {
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
@@ -659,15 +577,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			put_page(page);
 			goto repeat;
 		}
-		size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		if (unlikely(vmf->pgoff >= size)) {
-			/*
-			 * We have a struct page covering a hole in the file
-			 * from a read fault and we've raced with a truncate
-			 */
-			error = -EIO;
-			goto unlock_page;
-		}
 	}
 
 	error = get_block(inode, block, &bh, 0);
@@ -700,17 +609,8 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		if (error)
 			goto unlock_page;
 		vmf->page = page;
-		if (!page) {
+		if (!page)
 			i_mmap_lock_read(mapping);
-			/* Check we didn't race with truncate */
-			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
-								PAGE_SHIFT;
-			if (vmf->pgoff >= size) {
-				i_mmap_unlock_read(mapping);
-				error = -EIO;
-				goto out;
-			}
-		}
 		return VM_FAULT_LOCKED;
 	}
 
@@ -727,23 +627,9 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		page = NULL;
 	}
 
-	/*
+	/* Filesystem should not return unwritten buffers to us! */
-	 * If we successfully insert the new mapping over an unwritten extent,
+	WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
-	 * we need to ensure we convert the unwritten extent. If there is an
-	 * error inserting the mapping, the filesystem needs to leave it as
-	 * unwritten to prevent exposure of the stale underlying data to
-	 * userspace, but we still need to call the completion function so
-	 * the private resources on the mapping buffer can be released. We
-	 * indicate what the callback should do via the uptodate variable, same
-	 * as for normal BH based IO completions.
-	 */
 	error = dax_insert_mapping(inode, &bh, vma, vmf);
-	if (buffer_unwritten(&bh)) {
-		if (complete_unwritten)
-			complete_unwritten(&bh, !error);
-		else
-			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
-	}
 
  out:
 	if (error == -ENOMEM)
@@ -772,7 +658,7 @@ EXPORT_SYMBOL(__dax_fault);
  * fault handler for DAX files.
  */
 int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-	      get_block_t get_block, dax_iodone_t complete_unwritten)
+	      get_block_t get_block)
 {
 	int result;
 	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -781,7 +667,7 @@ int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
-	result = __dax_fault(vma, vmf, get_block, complete_unwritten);
+	result = __dax_fault(vma, vmf, get_block);
 	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(sb);
 
@@ -815,8 +701,7 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
 #define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
 
 int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, get_block_t get_block,
+		pmd_t *pmd, unsigned int flags, get_block_t get_block)
-		dax_iodone_t complete_unwritten)
 {
 	struct file *file = vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
@@ -875,6 +760,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		if (get_block(inode, block, &bh, 1) != 0)
 			return VM_FAULT_SIGBUS;
 		alloc = true;
+		WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh));
 	}
 
 	bdev = bh.b_bdev;
@@ -902,23 +788,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 
 	i_mmap_lock_read(mapping);
 
-	/*
-	 * If a truncate happened while we were allocating blocks, we may
-	 * leave blocks allocated to the file that are beyond EOF.  We can't
-	 * take i_mutex here, so just leave them hanging; they'll be freed
-	 * when the file is deleted.
-	 */
-	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (pgoff >= size) {
-		result = VM_FAULT_SIGBUS;
-		goto out;
-	}
-	if ((pgoff | PG_PMD_COLOUR) >= size) {
-		dax_pmd_dbg(&bh, address,
-				"offset + huge page size > file size");
-		goto fallback;
-	}
-
 	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
 		spinlock_t *ptl;
 		pmd_t entry;
@@ -954,8 +823,8 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		long length = dax_map_atomic(bdev, &dax);
 
 		if (length < 0) {
-			result = VM_FAULT_SIGBUS;
+			dax_pmd_dbg(&bh, address, "dax-error fallback");
-			goto out;
+			goto fallback;
 		}
 		if (length < PMD_SIZE) {
 			dax_pmd_dbg(&bh, address, "dax-length too small");
@@ -973,14 +842,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 			dax_pmd_dbg(&bh, address, "pfn not in memmap");
 			goto fallback;
 		}
-
-		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
-			clear_pmem(dax.addr, PMD_SIZE);
-			wmb_pmem();
-			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
-			result |= VM_FAULT_MAJOR;
-		}
 		dax_unmap_atomic(bdev, &dax);
 
 		/*
@@ -1020,9 +881,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
  out:
 	i_mmap_unlock_read(mapping);
 
-	if (buffer_unwritten(&bh))
-		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
-
 	return result;
 
  fallback:
@@ -1042,8 +900,7 @@ EXPORT_SYMBOL_GPL(__dax_pmd_fault);
  * pmd_fault handler for DAX files.
  */
 int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-			pmd_t *pmd, unsigned int flags, get_block_t get_block,
+			pmd_t *pmd, unsigned int flags, get_block_t get_block)
-			dax_iodone_t complete_unwritten)
 {
 	int result;
 	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
@@ -1052,8 +909,7 @@ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		sb_start_pagefault(sb);
 		file_update_time(vma->vm_file);
 	}
-	result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
+	result = __dax_pmd_fault(vma, address, pmd, flags, get_block);
-				complete_unwritten);
 	if (flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(sb);
 
@@ -1091,6 +947,43 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
 
+static bool dax_range_is_aligned(struct block_device *bdev,
+				 unsigned int offset, unsigned int length)
+{
+	unsigned short sector_size = bdev_logical_block_size(bdev);
+
+	if (!IS_ALIGNED(offset, sector_size))
+		return false;
+	if (!IS_ALIGNED(length, sector_size))
+		return false;
+
+	return true;
+}
+
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+		unsigned int offset, unsigned int length)
+{
+	struct blk_dax_ctl dax = {
+		.sector		= sector,
+		.size		= PAGE_SIZE,
+	};
+
+	if (dax_range_is_aligned(bdev, offset, length)) {
+		sector_t start_sector = dax.sector + (offset >> 9);
+
+		return blkdev_issue_zeroout(bdev, start_sector,
+				length >> 9, GFP_NOFS, true);
+	} else {
+		if (dax_map_atomic(bdev, &dax) < 0)
+			return PTR_ERR(dax.addr);
+		clear_pmem(dax.addr + offset, length);
+		wmb_pmem();
+		dax_unmap_atomic(bdev, &dax);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__dax_zero_page_range);
+
 /**
  * dax_zero_page_range - zero a range within a page of a DAX file
  * @inode: The file being truncated
@@ -1102,12 +995,6 @@ EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
  * page in a DAX file.  This is intended for hole-punch operations.  If
  * you are truncating a file, the helper function dax_truncate_page() may be
  * more convenient.
- *
- * We work in terms of PAGE_SIZE here for commonality with
- * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
- * took care of disposing of the unnecessary blocks.  Even if the filesystem
- * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
- * since the file might be mmapped.
  */
 int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 							get_block_t get_block)
@@ -1126,23 +1013,11 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 	bh.b_bdev = inode->i_sb->s_bdev;
 	bh.b_size = PAGE_SIZE;
 	err = get_block(inode, index, &bh, 0);
-	if (err < 0)
+	if (err < 0 || !buffer_written(&bh))
 		return err;
-	if (buffer_written(&bh)) {
-		struct block_device *bdev = bh.b_bdev;
-		struct blk_dax_ctl dax = {
-			.sector = to_sector(&bh, inode),
-			.size = PAGE_SIZE,
-		};
 
-		if (dax_map_atomic(bdev, &dax) < 0)
+	return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode),
-			return PTR_ERR(dax.addr);
+			offset, length);
-		clear_pmem(dax.addr + offset, length);
-		wmb_pmem();
-		dax_unmap_atomic(bdev, &dax);
-	}
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
@@ -1154,12 +1029,6 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range);
  *
  * Similar to block_truncate_page(), this function can be called by a
  * filesystem when it is truncating a DAX file to handle the partial page.
- *
- * We work in terms of PAGE_SIZE here for commonality with
- * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
- * took care of disposing of the unnecessary blocks.  Even if the filesystem
- * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
- * since the file might be mmapped.
  */
 int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
 {

fs/ext2/file.c

@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_fault(vma, vmf, ext2_get_block, NULL);
+	ret = __dax_fault(vma, vmf, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -72,7 +72,7 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block, NULL);
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (flags & FAULT_FLAG_WRITE)

fs/ext2/inode.c

@@ -26,6 +26,7 @@
 #include <linux/highuid.h>
 #include <linux/pagemap.h>
 #include <linux/dax.h>
+#include <linux/blkdev.h>
 #include <linux/quotaops.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
@@ -737,19 +738,18 @@ static int ext2_get_blocks(struct inode *inode,
 		 * so that it's not found by another thread before it's
 		 * initialised
 		 */
-		err = dax_clear_sectors(inode->i_sb->s_bdev,
+		err = sb_issue_zeroout(inode->i_sb,
-				le32_to_cpu(chain[depth-1].key) <<
+				le32_to_cpu(chain[depth-1].key), count,
-				(inode->i_blkbits - 9),
+				GFP_NOFS);
-				1 << inode->i_blkbits);
 		if (err) {
 			mutex_unlock(&ei->truncate_mutex);
 			goto cleanup;
 		}
-	}
+	} else
+		set_buffer_new(bh_result);
 
 	ext2_splice_branch(inode, iblock, partial, indirect_blks, count);
 	mutex_unlock(&ei->truncate_mutex);
-	set_buffer_new(bh_result);
 got_it:
 	map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
 	if (count > blocks_to_boundary)

fs/ext2/super.c

@@ -922,16 +922,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
-		if (blocksize != PAGE_SIZE) {
+		err = bdev_dax_supported(sb, blocksize);
-			ext2_msg(sb, KERN_ERR,
+		if (err)
-					"error: unsupported blocksize for dax");
 			goto failed_mount;
-		}
-		if (!sb->s_bdev->bd_disk->fops->direct_access) {
-			ext2_msg(sb, KERN_ERR,
-					"error: device does not support dax");
-			goto failed_mount;
-		}
 	}
 
 	/* If the blocksize doesn't match, re-read the thing.. */

fs/ext4/file.c

@@ -202,7 +202,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_fault(vma, vmf, ext4_dax_get_block, NULL);
+		result = __dax_fault(vma, vmf, ext4_dax_get_block);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -238,7 +238,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 		result = VM_FAULT_SIGBUS;
 	else
 		result = __dax_pmd_fault(vma, addr, pmd, flags,
-					 ext4_dax_get_block, NULL);
+					 ext4_dax_get_block);
 
 	if (write) {
 		if (!IS_ERR(handle))

fs/ext4/super.c

@@ -3417,16 +3417,9 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
-		if (blocksize != PAGE_SIZE) {
+		err = bdev_dax_supported(sb, blocksize);
-			ext4_msg(sb, KERN_ERR,
+		if (err)
-					"error: unsupported blocksize for dax");
 			goto failed_mount;
-		}
-		if (!sb->s_bdev->bd_disk->fops->direct_access) {
-			ext4_msg(sb, KERN_ERR,
-					"error: device does not support dax");
-			goto failed_mount;
-		}
 	}
 
 	if (ext4_has_feature_encrypt(sb) && es->s_encryption_level) {

fs/xfs/xfs_bmap_util.c

@@ -72,18 +72,11 @@ xfs_zero_extent(
 	struct xfs_mount *mp = ip->i_mount;
 	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
 	sector_t	block = XFS_BB_TO_FSBT(mp, sector);
-	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
-
-	if (IS_DAX(VFS_I(ip)))
-		return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)),
-				sector, size);
-
-	/*
-	 * let the block layer decide on the fastest method of
-	 * implementing the zeroing.
-	 */
-	return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
 
+	return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
+		block << (mp->m_super->s_blocksize_bits - 9),
+		count_fsb << (mp->m_super->s_blocksize_bits - 9),
+		GFP_NOFS, true);
 }
 
 /*

fs/xfs/xfs_file.c

@@ -1551,7 +1551,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
 	} else {
 		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
@@ -1585,7 +1585,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1622,8 +1622,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
-			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)

fs/xfs/xfs_super.c

@@ -1555,14 +1555,12 @@ xfs_fs_fill_super(
 
 	if (mp->m_flags & XFS_MOUNT_DAX) {
 		xfs_warn(mp,
-	"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-		if (sb->s_blocksize != PAGE_SIZE) {
+
+		error = bdev_dax_supported(sb, sb->s_blocksize);
+		if (error) {
 			xfs_alert(mp,
-		"Filesystem block size invalid for DAX Turning DAX off.");
+			"DAX unsupported by block device. Turning off DAX.");
-			mp->m_flags &= ~XFS_MOUNT_DAX;
-		} else if (!sb->s_bdev->bd_disk->fops->direct_access) {
-			xfs_alert(mp,
-		"Block device does not support DAX Turning DAX off.");
 			mp->m_flags &= ~XFS_MOUNT_DAX;
 		}
 	}

include/linux/blkdev.h

@@ -768,6 +768,17 @@ static inline void rq_flush_dcache_pages(struct request *rq)
 }
 #endif
 
+#ifdef CONFIG_PRINTK
+#define vfs_msg(sb, level, fmt, ...)				\
+	__vfs_msg(sb, level, fmt, ##__VA_ARGS__)
+#else
+#define vfs_msg(sb, level, fmt, ...)				\
+do {								\
+	no_printk(fmt, ##__VA_ARGS__);				\
+	__vfs_msg(sb, "", " ");					\
+} while (0)
+#endif
+
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 extern blk_qc_t generic_make_request(struct bio *bio);
@@ -1660,7 +1671,7 @@ struct block_device_operations {
 	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 __pmem **,
-			pfn_t *);
+			pfn_t *, long);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	/* ->media_changed() is DEPRECATED, use ->check_events() instead */
@@ -1680,6 +1691,8 @@ 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 *);
 #else /* CONFIG_BLOCK */
 
 struct block_device;

include/linux/dax.h

@@ -7,41 +7,44 @@
 
 ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *,
 		  get_block_t, dio_iodone_t, int flags);
-int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size);
 int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t);
 int dax_truncate_page(struct inode *, loff_t from, get_block_t);
-int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
+int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
-		dax_iodone_t);
+int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t);
-int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
-		dax_iodone_t);
 
 #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,
+		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)
+{
+	return -ENXIO;
+}
 #endif
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
+				unsigned int flags, get_block_t);
 int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *,
-				unsigned int flags, get_block_t, dax_iodone_t);
+				unsigned int flags, get_block_t);
 #else
 static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-				pmd_t *pmd, unsigned int flags, get_block_t gb,
+				pmd_t *pmd, unsigned int flags, get_block_t gb)
-				dax_iodone_t di)
 {
 	return VM_FAULT_FALLBACK;
 }
 #define __dax_pmd_fault dax_pmd_fault
 #endif
 int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *);
-#define dax_mkwrite(vma, vmf, gb, iod)		dax_fault(vma, vmf, gb, iod)
+#define dax_mkwrite(vma, vmf, gb)	dax_fault(vma, vmf, gb)
-#define __dax_mkwrite(vma, vmf, gb, iod)	__dax_fault(vma, vmf, gb, iod)
+#define __dax_mkwrite(vma, vmf, gb)	__dax_fault(vma, vmf, gb)
 
 static inline bool vma_is_dax(struct vm_area_struct *vma)
 {

include/linux/fs.h

@@ -74,7 +74,6 @@ typedef int (get_block_t)(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh_result, int create);
 typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 			ssize_t bytes, void *private);
-typedef void (dax_iodone_t)(struct buffer_head *bh_map, int uptodate);
 
 #define MAY_EXEC		0x00000001
 #define MAY_WRITE		0x00000002