summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/compression.c4
-rw-r--r--fs/btrfs/delayed-inode.c71
-rw-r--r--fs/btrfs/extent_io.c11
-rw-r--r--fs/btrfs/extent_io.h2
-rw-r--r--fs/btrfs/inode.c8
-rw-r--r--fs/btrfs/volumes.c1
6 files changed, 56 insertions, 41 deletions
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 5982c8a71f02..75610d23d197 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -411,7 +411,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
static u64 bio_end_offset(struct bio *bio)
{
- struct bio_vec *last = &bio->bi_io_vec[bio->bi_vcnt - 1];
+ struct bio_vec *last = bio_last_bvec_all(bio);
return page_offset(last->bv_page) + last->bv_len + last->bv_offset;
}
@@ -563,7 +563,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
/* we need the actual starting offset of this extent in the file */
read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree,
- page_offset(bio->bi_io_vec->bv_page),
+ page_offset(bio_first_page_all(bio)),
PAGE_SIZE);
read_unlock(&em_tree->lock);
if (!em)
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6a246ae2bcb2..d4db406e2d39 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -88,6 +88,7 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
spin_lock(&root->inode_lock);
node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
+
if (node) {
if (btrfs_inode->delayed_node) {
refcount_inc(&node->refs); /* can be accessed */
@@ -95,9 +96,30 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(
spin_unlock(&root->inode_lock);
return node;
}
- btrfs_inode->delayed_node = node;
- /* can be accessed and cached in the inode */
- refcount_add(2, &node->refs);
+
+ /*
+ * It's possible that we're racing into the middle of removing
+ * this node from the radix tree. In this case, the refcount
+ * was zero and it should never go back to one. Just return
+ * NULL like it was never in the radix at all; our release
+ * function is in the process of removing it.
+ *
+ * Some implementations of refcount_inc refuse to bump the
+ * refcount once it has hit zero. If we don't do this dance
+ * here, refcount_inc() may decide to just WARN_ONCE() instead
+ * of actually bumping the refcount.
+ *
+ * If this node is properly in the radix, we want to bump the
+ * refcount twice, once for the inode and once for this get
+ * operation.
+ */
+ if (refcount_inc_not_zero(&node->refs)) {
+ refcount_inc(&node->refs);
+ btrfs_inode->delayed_node = node;
+ } else {
+ node = NULL;
+ }
+
spin_unlock(&root->inode_lock);
return node;
}
@@ -255,17 +277,18 @@ static void __btrfs_release_delayed_node(
mutex_unlock(&delayed_node->mutex);
if (refcount_dec_and_test(&delayed_node->refs)) {
- bool free = false;
struct btrfs_root *root = delayed_node->root;
+
spin_lock(&root->inode_lock);
- if (refcount_read(&delayed_node->refs) == 0) {
- radix_tree_delete(&root->delayed_nodes_tree,
- delayed_node->inode_id);
- free = true;
- }
+ /*
+ * Once our refcount goes to zero, nobody is allowed to bump it
+ * back up. We can delete it now.
+ */
+ ASSERT(refcount_read(&delayed_node->refs) == 0);
+ radix_tree_delete(&root->delayed_nodes_tree,
+ delayed_node->inode_id);
spin_unlock(&root->inode_lock);
- if (free)
- kmem_cache_free(delayed_node_cache, delayed_node);
+ kmem_cache_free(delayed_node_cache, delayed_node);
}
}
@@ -1611,28 +1634,18 @@ void btrfs_readdir_put_delayed_items(struct inode *inode,
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index)
{
- struct btrfs_delayed_item *curr, *next;
- int ret;
-
- if (list_empty(del_list))
- return 0;
+ struct btrfs_delayed_item *curr;
+ int ret = 0;
- list_for_each_entry_safe(curr, next, del_list, readdir_list) {
+ list_for_each_entry(curr, del_list, readdir_list) {
if (curr->key.offset > index)
break;
-
- list_del(&curr->readdir_list);
- ret = (curr->key.offset == index);
-
- if (refcount_dec_and_test(&curr->refs))
- kfree(curr);
-
- if (ret)
- return 1;
- else
- continue;
+ if (curr->key.offset == index) {
+ ret = 1;
+ break;
+ }
}
- return 0;
+ return ret;
}
/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 012d63870b99..d43360b33ef6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2257,7 +2257,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
return 0;
}
-bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
struct io_failure_record *failrec, int failed_mirror)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2281,7 +2281,7 @@ bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
* a) deliver good data to the caller
* b) correct the bad sectors on disk
*/
- if (failed_bio->bi_vcnt > 1) {
+ if (failed_bio_pages > 1) {
/*
* to fulfill b), we need to know the exact failing sectors, as
* we don't want to rewrite any more than the failed ones. thus,
@@ -2374,6 +2374,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
int read_mode = 0;
blk_status_t status;
int ret;
+ unsigned failed_bio_pages = bio_pages_all(failed_bio);
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -2381,13 +2382,13 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
if (ret)
return ret;
- if (!btrfs_check_repairable(inode, failed_bio, failrec,
+ if (!btrfs_check_repairable(inode, failed_bio_pages, failrec,
failed_mirror)) {
free_io_failure(failure_tree, tree, failrec);
return -EIO;
}
- if (failed_bio->bi_vcnt > 1)
+ if (failed_bio_pages > 1)
read_mode |= REQ_FAILFAST_DEV;
phy_offset >>= inode->i_sb->s_blocksize_bits;
@@ -2724,7 +2725,7 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
unsigned long bio_flags)
{
blk_status_t ret = 0;
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec = bio_last_bvec_all(bio);
struct page *page = bvec->bv_page;
struct extent_io_tree *tree = bio->bi_private;
u64 start;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 93dcae0c3183..20854d63c75b 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -540,7 +540,7 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
u64 end);
int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
struct io_failure_record **failrec_ret);
-bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, unsigned failed_bio_pages,
struct io_failure_record *failrec, int fail_mirror);
struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
struct io_failure_record *failrec,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 76245323a7c8..734b37d9d459 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -8019,6 +8019,7 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
int segs;
int ret;
blk_status_t status;
+ struct bio_vec bvec;
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -8034,8 +8035,9 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
}
segs = bio_segments(failed_bio);
+ bio_get_first_bvec(failed_bio, &bvec);
if (segs > 1 ||
- (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
+ (bvec.bv_len > btrfs_inode_sectorsize(inode)))
read_mode |= REQ_FAILFAST_DEV;
isector = start - btrfs_io_bio(failed_bio)->logical;
@@ -8078,7 +8080,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
ASSERT(bio->bi_vcnt == 1);
io_tree = &BTRFS_I(inode)->io_tree;
failure_tree = &BTRFS_I(inode)->io_failure_tree;
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+ ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(inode));
done->uptodate = 1;
ASSERT(!bio_flagged(bio, BIO_CLONED));
@@ -8168,7 +8170,7 @@ static void btrfs_retry_endio(struct bio *bio)
uptodate = 1;
ASSERT(bio->bi_vcnt == 1);
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
+ ASSERT(bio_first_bvec_all(bio)->bv_len == btrfs_inode_sectorsize(done->inode));
io_tree = &BTRFS_I(inode)->io_tree;
failure_tree = &BTRFS_I(inode)->io_failure_tree;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 49810b70afd3..a25684287501 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -237,7 +237,6 @@ static struct btrfs_device *__alloc_device(void)
kfree(dev);
return ERR_PTR(-ENOMEM);
}
- bio_get(dev->flush_bio);
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_alloc_list);
generated by cgit v1.2.1 (git 2.18.0) at 2025-04-25 23:05:12 +0000