Btrfs: change how we iterate bios in endio

Since dio submit has used bio_clone_fast, the submitted bio may not have a
reliable bi_vcnt, for the bio vector iterations in checksum related
functions, bio->bi_iter is not modified yet and it's safe to use
bio_for_each_segment, while for those bio vector iterations in dio read's
endio, we now save a copy of bvec_iter in struct btrfs_io_bio when cloning
bios and use the helper __bio_for_each_segment with the saved bvec_iter to
access each bvec.

Also for dio reads which don't get split, we also need to save a copy of
bio iterator in btrfs_bio_clone to let __bio_for_each_segments to access
each bvec in dio read's endio.  Note that it doesn't affect other calls of
btrfs_bio_clone() because they don't need to use this iterator.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index db2bbf9..acb8c1d 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2700,6 +2700,7 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
                btrfs_bio->csum = NULL;
                btrfs_bio->csum_allocated = NULL;
                btrfs_bio->end_io = NULL;
+               btrfs_bio->iter = bio->bi_iter;
        }
        return new;
 }
@@ -2736,6 +2737,7 @@ struct bio *btrfs_bio_clone_partial(struct bio *orig, gfp_t gfp_mask,
        btrfs_bio->end_io = NULL;
 
        bio_trim(bio, offset >> 9, size >> 9);
+       btrfs_bio->iter = bio->bi_iter;
        return bio;
 }
 

diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 64fcb31..9f6062c 100644 (file)
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -164,7 +164,8 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
                                   u64 logical_offset, u32 *dst, int dio)
 {
        struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-       struct bio_vec *bvec;
+       struct bio_vec bvec;
+       struct bvec_iter iter;
        struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
        struct btrfs_csum_item *item = NULL;
        struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -177,7 +178,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
        u64 page_bytes_left;
        u32 diff;
        int nblocks;
-       int count = 0, i;
+       int count = 0;
        u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
        path = btrfs_alloc_path();
@@ -206,8 +207,6 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
        if (bio->bi_iter.bi_size > PAGE_SIZE * 8)
                path->reada = READA_FORWARD;
 
-       WARN_ON(bio->bi_vcnt <= 0);
-
        /*
         * the free space stuff is only read when it hasn't been
         * updated in the current transaction.  So, we can safely
@@ -223,13 +222,13 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
        if (dio)
                offset = logical_offset;
 
-       bio_for_each_segment_all(bvec, bio, i) {
-               page_bytes_left = bvec->bv_len;
+       bio_for_each_segment(bvec, bio, iter) {
+               page_bytes_left = bvec.bv_len;
                if (count)
                        goto next;
 
                if (!dio)
-                       offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+                       offset = page_offset(bvec.bv_page) + bvec.bv_offset;
                count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
                                               (u32 *)csum, nblocks);
                if (count)
@@ -440,15 +439,15 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
        struct btrfs_ordered_sum *sums;
        struct btrfs_ordered_extent *ordered = NULL;
        char *data;
-       struct bio_vec *bvec;
+       struct bvec_iter iter;
+       struct bio_vec bvec;
        int index;
        int nr_sectors;
-       int i, j;
        unsigned long total_bytes = 0;
        unsigned long this_sum_bytes = 0;
+       int i;
        u64 offset;
 
-       WARN_ON(bio->bi_vcnt <= 0);
        sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
                       GFP_NOFS);
        if (!sums)
@@ -465,19 +464,19 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
        sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
        index = 0;
 
-       bio_for_each_segment_all(bvec, bio, j) {
+       bio_for_each_segment(bvec, bio, iter) {
                if (!contig)
-                       offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+                       offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 
                if (!ordered) {
                        ordered = btrfs_lookup_ordered_extent(inode, offset);
                        BUG_ON(!ordered); /* Logic error */
                }
 
-               data = kmap_atomic(bvec->bv_page);
+               data = kmap_atomic(bvec.bv_page);
 
                nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info,
-                                                bvec->bv_len + fs_info->sectorsize
+                                                bvec.bv_len + fs_info->sectorsize
                                                 - 1);
 
                for (i = 0; i < nr_sectors; i++) {
@@ -504,12 +503,12 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
                                        + total_bytes;
                                index = 0;
 
-                               data = kmap_atomic(bvec->bv_page);
+                               data = kmap_atomic(bvec.bv_page);
                        }
 
                        sums->sums[index] = ~(u32)0;
                        sums->sums[index]
-                               = btrfs_csum_data(data + bvec->bv_offset
+                               = btrfs_csum_data(data + bvec.bv_offset
                                                + (i * fs_info->sectorsize),
                                                sums->sums[index],
                                                fs_info->sectorsize);

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c2e9c51..ce6a9b2 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7989,6 +7989,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
        struct bio *bio;
        int isector;
        int read_mode = 0;
+       int segs;
        int ret;
 
        BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -8004,9 +8005,9 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
                return -EIO;
        }
 
-       if ((failed_bio->bi_vcnt > 1)
-               || (failed_bio->bi_io_vec->bv_len
-                       > btrfs_inode_sectorsize(inode)))
+       segs = bio_segments(failed_bio);
+       if (segs > 1 ||
+           (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
                read_mode |= REQ_FAILFAST_DEV;
 
        isector = start - btrfs_io_bio(failed_bio)->logical;
@@ -8069,13 +8070,13 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
                                       struct btrfs_io_bio *io_bio)
 {
        struct btrfs_fs_info *fs_info;
-       struct bio_vec *bvec;
+       struct bio_vec bvec;
+       struct bvec_iter iter;
        struct btrfs_retry_complete done;
        u64 start;
        unsigned int pgoff;
        u32 sectorsize;
        int nr_sectors;
-       int i;
        int ret;
 
        fs_info = BTRFS_I(inode)->root->fs_info;
@@ -8083,17 +8084,18 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
 
        start = io_bio->logical;
        done.inode = inode;
+       io_bio->bio.bi_iter = io_bio->iter;
 
-       bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-               nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-               pgoff = bvec->bv_offset;
+       bio_for_each_segment(bvec, &io_bio->bio, iter) {
+               nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
+               pgoff = bvec.bv_offset;
 
 next_block_or_try_again:
                done.uptodate = 0;
                done.start = start;
                init_completion(&done.done);
 
-               ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+               ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
                                pgoff, start, start + sectorsize - 1,
                                io_bio->mirror_num,
                                btrfs_retry_endio_nocsum, &done);
@@ -8166,7 +8168,8 @@ static int __btrfs_subio_endio_read(struct inode *inode,
                                    struct btrfs_io_bio *io_bio, int err)
 {
        struct btrfs_fs_info *fs_info;
-       struct bio_vec *bvec;
+       struct bio_vec bvec;
+       struct bvec_iter iter;
        struct btrfs_retry_complete done;
        u64 start;
        u64 offset = 0;
@@ -8174,7 +8177,6 @@ static int __btrfs_subio_endio_read(struct inode *inode,
        int nr_sectors;
        unsigned int pgoff;
        int csum_pos;
-       int i;
        int ret;
 
        fs_info = BTRFS_I(inode)->root->fs_info;
@@ -8183,15 +8185,16 @@ static int __btrfs_subio_endio_read(struct inode *inode,
        err = 0;
        start = io_bio->logical;
        done.inode = inode;
+       io_bio->bio.bi_iter = io_bio->iter;
 
-       bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-               nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+       bio_for_each_segment(bvec, &io_bio->bio, iter) {
+               nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
 
-               pgoff = bvec->bv_offset;
+               pgoff = bvec.bv_offset;
 next_block:
                csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
                ret = __readpage_endio_check(inode, io_bio, csum_pos,
-                                       bvec->bv_page, pgoff, start,
+                                       bvec.bv_page, pgoff, start,
                                        sectorsize);
                if (likely(!ret))
                        goto next;
@@ -8200,7 +8203,7 @@ try_again:
                done.start = start;
                init_completion(&done.done);
 
-               ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+               ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
                                pgoff, start, start + sectorsize - 1,
                                io_bio->mirror_num,
                                btrfs_retry_endio, &done);

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 0945217..58b97b6 100644 (file)
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -280,6 +280,7 @@ struct btrfs_io_bio {
        u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
        u8 *csum_allocated;
        btrfs_io_bio_end_io_t *end_io;
+       struct bvec_iter iter;
        struct bio bio;
 };