@@ -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
------------
@@ -947,6 +947,19 @@ 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)
{
@@ -955,11 +968,18 @@ int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
.size = PAGE_SIZE,
};
- 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);
+ 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);