Since block layer will advance bio::bi_iter, at endio time we can no
longer rely on bio::bi_iter for split bio.
But for the incoming btrfs_bio split at btrfs_map_bio() time, we have to
ensure endio function is only executed for the split range, not the
whole original bio.
Thus this patch will introduce a new helper, btrfs_bio_save_iter(), to
save bi_iter into btrfs_bio::iter.
The following call sites need this helper call:
- btrfs_submit_compressed_read()
For compressed read. For compressed write it doesn't really care as
they use ordered extent.
- raid56_parity_write()
- raid56_parity_recovery()
For RAID56.
- submit_stripe_bio()
For all other cases.
Signed-off-by: Qu Wenruo <wqu@xxxxxxxx>
---
fs/btrfs/compression.c | 3 +++
fs/btrfs/raid56.c | 2 ++
fs/btrfs/volumes.c | 11 +++++++++++
fs/btrfs/volumes.h | 19 +++++++++++++++++++
4 files changed, 35 insertions(+)
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 64f931fc11f0..943e5898fa87 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -867,6 +867,9 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
/* include any pages we added in add_ra-bio_pages */
cb->len = bio->bi_iter.bi_size;
+ /* Save bi_iter so that end_bio_extent_readpage() won't freak out. */
+ btrfs_bio_save_iter(btrfs_bio(bio));
+
while (cur_disk_byte < disk_bytenr + compressed_len) {
u64 offset = cur_disk_byte - disk_bytenr;
unsigned int index = offset >> PAGE_SHIFT;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0e239a4c3b26..13e726c88a81 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1731,6 +1731,7 @@ int raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc,
return PTR_ERR(rbio);
}
bio_list_add(&rbio->bio_list, bio);
+ btrfs_bio_save_iter(btrfs_bio(bio));
rbio->bio_list_bytes = bio->bi_iter.bi_size;
rbio->operation = BTRFS_RBIO_WRITE;
@@ -2135,6 +2136,7 @@ int raid56_parity_recover(struct bio *bio, struct btrfs_io_context *bioc,
rbio->operation = BTRFS_RBIO_READ_REBUILD;
bio_list_add(&rbio->bio_list, bio);
+ btrfs_bio_save_iter(btrfs_bio(bio));
rbio->bio_list_bytes = bio->bi_iter.bi_size;
rbio->faila = find_logical_bio_stripe(rbio, bio);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f7449bf7a595..e6ed71195e18 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6771,6 +6771,17 @@ static int submit_stripe_bio(struct btrfs_io_context *bioc, struct bio *bio,
dev->devid, bio->bi_iter.bi_size);
bio_set_dev(bio, dev->bdev);
+ /*
+ * At endio time, bi_iter is no longer reliable, thus we have to save
+ * current bi_iter into btrfs_bio so that even for split bio we can
+ * iterate only the split part.
+ *
+ * For bio create by btrfs_bio_slit() or btrfs_bio_clone*(), it's
+ * already set, but we can still have original bio which has its
+ * iter not initialized.
+ */
+ btrfs_bio_save_iter(btrfs_bio(bio));
+
/* Do the final endio remap if needed */
ret = btrfs_bio_final_endio_remap(fs_info, bio);
if (ret < 0)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 358fc546d611..baccf895a544 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -378,6 +378,13 @@ struct btrfs_bio {
bio_end_io_t *orig_endio;
};
};
+
+ /*
+ * Saved bio::bi_iter before submission.
+ *
+ * This allows us to interate the cloned/split bio properly, as at
+ * endio time bio::bi_iter is no longer reliable.
+ */
struct bvec_iter iter;
/*
@@ -400,6 +407,18 @@ static inline void btrfs_bio_free_csum(struct btrfs_bio *bbio)
}
}
+/*
+ * To save bbio::bio->bi_iter into bbio::iter so for callers who need the
+ * original bi_iter can access the original part of the bio.
+ * This is especially important for the incoming split btrfs_bio, which needs
+ * to call its endio for and only for the split range.
+ */
+static inline void btrfs_bio_save_iter(struct btrfs_bio *bbio)
+{
+ if (!bbio->iter.bi_size)
+ bbio->iter = bbio->bio.bi_iter;
+}
+
struct btrfs_io_stripe {
struct btrfs_device *dev;
u64 physical;
--
2.34.0
