@@ -2741,10 +2741,9 @@ static blk_status_t submit_read_repair(struct inode *inode,
ASSERT(error_bitmap);
/*
- * We only get called on buffered IO, thus page must be mapped and bio
- * must not be cloned.
- */
- ASSERT(page->mapping && !bio_flagged(failed_bio, BIO_CLONED));
+ * We only get called on buffered IO, thus page must be mapped
+ */
+ ASSERT(page->mapping);
/* Iterate through all the sectors in the range */
for (i = 0; i < nr_bits; i++) {
@@ -2998,7 +2997,8 @@ static struct extent_buffer *find_extent_buffer_readpage(
*/
static void end_bio_extent_readpage(struct bio *bio)
{
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
struct btrfs_bio *bbio = btrfs_bio(bio);
struct extent_io_tree *tree, *failure_tree;
struct processed_extent processed = { 0 };
@@ -3009,11 +3009,15 @@ static void end_bio_extent_readpage(struct bio *bio)
u32 bio_offset = 0;
int mirror;
int ret;
- struct bvec_iter_all iter_all;
- bio_for_each_segment_all(bvec, bio, iter_all) {
+ /*
+ * We should have saved the orignal bi_iter, and then start iterating
+ * using that saved iter, as at endio time bi_iter is not reliable.
+ */
+ ASSERT(bbio->iter.bi_size);
+ __bio_for_each_segment(bvec, bio, iter, bbio->iter) {
bool uptodate = !bio->bi_status;
- struct page *page = bvec->bv_page;
+ struct page *page = bvec.bv_page;
struct inode *inode = page->mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
@@ -3036,19 +3040,19 @@ static void end_bio_extent_readpage(struct bio *bio)
* for unaligned offsets, and an error if they don't add up to
* a full sector.
*/
- if (!IS_ALIGNED(bvec->bv_offset, sectorsize))
+ if (!IS_ALIGNED(bvec.bv_offset, sectorsize))
btrfs_err(fs_info,
"partial page read in btrfs with offset %u and length %u",
- bvec->bv_offset, bvec->bv_len);
- else if (!IS_ALIGNED(bvec->bv_offset + bvec->bv_len,
+ bvec.bv_offset, bvec.bv_len);
+ else if (!IS_ALIGNED(bvec.bv_offset + bvec.bv_len,
sectorsize))
btrfs_info(fs_info,
"incomplete page read with offset %u and length %u",
- bvec->bv_offset, bvec->bv_len);
+ bvec.bv_offset, bvec.bv_len);
- start = page_offset(page) + bvec->bv_offset;
- end = start + bvec->bv_len - 1;
- len = bvec->bv_len;
+ start = page_offset(page) + bvec.bv_offset;
+ end = start + bvec.bv_len - 1;
+ len = bvec.bv_len;
mirror = bbio->mirror_num;
if (likely(uptodate)) {
@@ -3225,6 +3225,24 @@ void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
finish_ordered_fn, uptodate);
}
+static u8 *bbio_get_real_csum(struct btrfs_fs_info *fs_info,
+ struct btrfs_bio *bbio)
+{
+ u8 *ret;
+
+ /* Split bbio needs to grab csum from its parent */
+ if (bbio->is_split_bio)
+ ret = btrfs_bio(bbio->parent)->csum;
+ else
+ ret = bbio->csum;
+
+ if (ret == NULL)
+ return ret;
+
+ return ret + (bbio->offset_to_original >> fs_info->sectorsize_bits) *
+ fs_info->csum_size;
+}
+
/*
* check_data_csum - verify checksum of one sector of uncompressed data
* @inode: inode
@@ -3252,7 +3270,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_bio *bbio,
ASSERT(pgoff + len <= PAGE_SIZE);
offset_sectors = bio_offset >> fs_info->sectorsize_bits;
- csum_expected = ((u8 *)bbio->csum) + offset_sectors * csum_size;
+ csum_expected = bbio_get_real_csum(fs_info, bbio) +
+ offset_sectors * csum_size;
kaddr = kmap_atomic(page);
shash->tfm = fs_info->csum_shash;
@@ -3310,7 +3329,7 @@ unsigned int btrfs_verify_data_csum(struct btrfs_bio *bbio,
* Normally this should be covered by above check for compressed read
* or the next check for NODATASUM. Just do a quicker exit here.
*/
- if (bbio->csum == NULL)
+ if (bbio_get_real_csum(fs_info, bbio) == NULL)
return 0;
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
@@ -400,7 +400,8 @@ static inline struct btrfs_bio *btrfs_bio(struct bio *bio)
static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
{
- if (bbio->csum != bbio->csum_inline) {
+ /* Only free the csum if we're not a split bio */
+ if (!bbio->is_split_bio && bbio->csum != bbio->csum_inline) {
kfree(bbio->csum);
bbio->csum = NULL;
}
This involves the following modifications: - Use bio_for_each_segment() instead of bio_for_each_segment_all() bio_for_each_segment_all() will iterate all bvecs, even if they are not referred by current bi_iter. *_all() variant can only be used if the bio is never split. Change it to __bio_for_each_segment() call so we won't have endio called on the same range by both split and parent bios, and it can handle both split and unsplit bios. - Make check_data_csum() to take bbio->offset_to_original into consideration Since btrfs bio can be split now, split/original bio can all start with some offset to the original logical bytenr. Take btrfs_bio::offset_to_original into consideration to get correct checksum offset. - Remove the BIO_CLONED ASSERT() in submit_read_repair() Signed-off-by: Qu Wenruo <wqu@suse.com> --- fs/btrfs/extent_io.c | 34 +++++++++++++++++++--------------- fs/btrfs/inode.c | 23 +++++++++++++++++++++-- fs/btrfs/volumes.h | 3 ++- 3 files changed, 42 insertions(+), 18 deletions(-)