| From d5ce4c31d6df518dd8f63bbae20d7423c5018a6c Mon Sep 17 00:00:00 2001 |
| From: Ilya Dryomov <idryomov@gmail.com> |
| Date: Mon, 16 Oct 2017 15:59:10 +0200 |
| Subject: block: cope with WRITE ZEROES failing in blkdev_issue_zeroout() |
| |
| From: Ilya Dryomov <idryomov@gmail.com> |
| |
| commit d5ce4c31d6df518dd8f63bbae20d7423c5018a6c upstream. |
| |
| sd_config_write_same() ignores ->max_ws_blocks == 0 and resets it to |
| permit trying WRITE SAME on older SCSI devices, unless ->no_write_same |
| is set. Because REQ_OP_WRITE_ZEROES is implemented in terms of WRITE |
| SAME, blkdev_issue_zeroout() may fail with -EREMOTEIO: |
| |
| $ fallocate -zn -l 1k /dev/sdg |
| fallocate: fallocate failed: Remote I/O error |
| $ fallocate -zn -l 1k /dev/sdg # OK |
| $ fallocate -zn -l 1k /dev/sdg # OK |
| |
| The following calls succeed because sd_done() sets ->no_write_same in |
| response to a sense that would become BLK_STS_TARGET/-EREMOTEIO, causing |
| __blkdev_issue_zeroout() to fall back to generating ZERO_PAGE bios. |
| |
| This means blkdev_issue_zeroout() must cope with WRITE ZEROES failing |
| and fall back to manually zeroing, unless BLKDEV_ZERO_NOFALLBACK is |
| specified. For BLKDEV_ZERO_NOFALLBACK case, return -EOPNOTSUPP if |
| sd_done() has just set ->no_write_same thus indicating lack of offload |
| support. |
| |
| Fixes: c20cfc27a473 ("block: stop using blkdev_issue_write_same for zeroing") |
| Cc: Hannes Reinecke <hare@suse.com> |
| Reviewed-by: Christoph Hellwig <hch@lst.de> |
| Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> |
| Signed-off-by: Ilya Dryomov <idryomov@gmail.com> |
| Signed-off-by: Jens Axboe <axboe@kernel.dk> |
| Cc: Janne Huttunen <janne.huttunen@nokia.com> |
| Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
| |
| --- |
| block/blk-lib.c | 45 +++++++++++++++++++++++++++++++++++---------- |
| 1 file changed, 35 insertions(+), 10 deletions(-) |
| |
| --- a/block/blk-lib.c |
| +++ b/block/blk-lib.c |
| @@ -322,12 +322,6 @@ static int __blkdev_issue_zero_pages(str |
| * Zero-fill a block range, either using hardware offload or by explicitly |
| * writing zeroes to the device. |
| * |
| - * Note that this function may fail with -EOPNOTSUPP if the driver signals |
| - * zeroing offload support, but the device fails to process the command (for |
| - * some devices there is no non-destructive way to verify whether this |
| - * operation is actually supported). In this case the caller should call |
| - * retry the call to blkdev_issue_zeroout() and the fallback path will be used. |
| - * |
| * If a device is using logical block provisioning, the underlying space will |
| * not be released if %flags contains BLKDEV_ZERO_NOUNMAP. |
| * |
| @@ -371,18 +365,49 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout); |
| int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, |
| sector_t nr_sects, gfp_t gfp_mask, unsigned flags) |
| { |
| - int ret; |
| - struct bio *bio = NULL; |
| + int ret = 0; |
| + sector_t bs_mask; |
| + struct bio *bio; |
| struct blk_plug plug; |
| + bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev); |
| |
| + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; |
| + if ((sector | nr_sects) & bs_mask) |
| + return -EINVAL; |
| + |
| +retry: |
| + bio = NULL; |
| blk_start_plug(&plug); |
| - ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, |
| - &bio, flags); |
| + if (try_write_zeroes) { |
| + ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, |
| + gfp_mask, &bio, flags); |
| + } else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { |
| + ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects, |
| + gfp_mask, &bio); |
| + } else { |
| + /* No zeroing offload support */ |
| + ret = -EOPNOTSUPP; |
| + } |
| if (ret == 0 && bio) { |
| ret = submit_bio_wait(bio); |
| bio_put(bio); |
| } |
| blk_finish_plug(&plug); |
| + if (ret && try_write_zeroes) { |
| + if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { |
| + try_write_zeroes = false; |
| + goto retry; |
| + } |
| + if (!bdev_write_zeroes_sectors(bdev)) { |
| + /* |
| + * Zeroing offload support was indicated, but the |
| + * device reported ILLEGAL REQUEST (for some devices |
| + * there is no non-destructive way to verify whether |
| + * WRITE ZEROES is actually supported). |
| + */ |
| + ret = -EOPNOTSUPP; |
| + } |
| + } |
| |
| return ret; |
| } |