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

…rnel/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 @@ 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)
 {
 	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 {