Until now, dax has been disabled if media errors were found on any device. This series attempts to address that. The first two patches from Dan re-enable dax even when media errors are present. The third patch from Matthew removes the zeroout path from dax entirely, making zeroout operations always go through the driver (The motivation is that if a backing device has media errors, and we create a sparse file on it, we don't want the initial zeroing to happen via dax, we want to give the block driver a chance to clear the errors). Patch 4 from Christoph exports a low level dax helper for zeroing Patch 5 reduces our calls to clear_pmem from dax in the truncate/hole-punch cases. We check if the range being truncated is sector aligned/sized, and if so, send blkdev_issue_zeroout instead of clear_pmem so that errors can be handled better by the driver. Patch 6 fixes a redundant comment in DAX and is mostly unrelated to the rest of this series. This series also depends on/is based on Jan Kara's Ext4 and DAX fixups series: http://marc.info/?l=linux-ext4&m=146295959100848&w=2 http://marc.info/?l=linux-ext4&m=146296078001307&w=2 v7: - Fix the dax alignment check to only check 'offset' and 'length' for alignment as that's all that is needed. (Jan) - Fix the blockdev_issue_zeroout call to zero the correct sector - Rebase to v4.6-rc7 + the two patch-series from Jan linked above - Add a patch from Christoph's iomap series: http://www.spinics.net/lists/xfs/msg39656.html v6: - Use IS_ALIGNED in dax_range_is_aligned instead of open coding an alignment check (Jan) - Collect all Reveiwed-by tags so far. v5: - Drop the patch that attempts to clear-errors-on-write till we reach consensus on how to handle that. - Don't pass blk_dax_ctl to direct_access, instead pass in all the required arguments individually (Christoph, Dan) v4: - Remove the dax->direct_IO fallbacks entirely. Instead, go through the usual direct_IO path when we're in O_DIRECT, and use dax_IO for other, non O_DIRECT IO. (Dan, Christoph) v3: - Wrapper-ize the direct_IO fallback again and make an exception for -EIOCBQUEUED (Jeff, Dan) - Reduce clear_pmem usage in DAX to the minimum Christoph Hellwig (1): dax: export a low-level __dax_zero_page_range helper Dan Williams (2): dax: fallback from pmd to pte on error dax: enable dax in the presence of known media errors (badblocks) Matthew Wilcox (1): dax: use sb_issue_zerout instead of calling dax_clear_sectors Vishal Verma (2): dax: for truncate/hole-punch, do zeroing through the driver if possible dax: fix a comment in dax_zero_page_range and dax_truncate_page Documentation/filesystems/dax.txt | 32 ++++++++++++ arch/powerpc/sysdev/axonram.c | 2 +- block/ioctl.c | 9 ---- drivers/block/brd.c | 2 +- drivers/nvdimm/pmem.c | 10 +++- drivers/s390/block/dcssblk.c | 2 +- fs/block_dev.c | 2 +- fs/dax.c | 104 ++++++++++++++++---------------------- fs/ext2/inode.c | 7 ++- fs/xfs/xfs_bmap_util.c | 15 ++---- include/linux/blkdev.h | 2 +- include/linux/dax.h | 8 ++- 12 files changed, 103 insertions(+), 92 deletions(-) -- 2.5.5 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>