summaryrefslogtreecommitdiff
path: root/fs/btrfs/disk-io.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/disk-io.c')
-rw-r--r--fs/btrfs/disk-io.c587
1 files changed, 371 insertions, 216 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4e47849d7427..e720d3e6ec20 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -101,7 +101,7 @@ int __init btrfs_end_io_wq_init(void)
btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
sizeof(struct btrfs_end_io_wq),
0,
- SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+ SLAB_MEM_SPREAD,
NULL);
if (!btrfs_end_io_wq_cache)
return -ENOMEM;
@@ -124,7 +124,6 @@ struct async_submit_bio {
struct list_head list;
extent_submit_bio_hook_t *submit_bio_start;
extent_submit_bio_hook_t *submit_bio_done;
- int rw;
int mirror_num;
unsigned long bio_flags;
/*
@@ -327,8 +326,7 @@ static int csum_tree_block(struct btrfs_fs_info *fs_info,
read_extent_buffer(buf, &val, 0, csum_size);
btrfs_warn_rl(fs_info,
- "%s checksum verify failed on %llu wanted %X found %X "
- "level %d",
+ "%s checksum verify failed on %llu wanted %X found %X level %d",
fs_info->sb->s_id, buf->start,
val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
@@ -384,7 +382,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
/*
* Things reading via commit roots that don't have normal protection,
* like send, can have a really old block in cache that may point at a
- * block that has been free'd and re-allocated. So don't clear uptodate
+ * block that has been freed and re-allocated. So don't clear uptodate
* if we find an eb that is under IO (dirty/writeback) because we could
* end up reading in the stale data and then writing it back out and
* making everybody very sad.
@@ -403,7 +401,8 @@ out:
* Return 0 if the superblock checksum type matches the checksum value of that
* algorithm. Pass the raw disk superblock data.
*/
-static int btrfs_check_super_csum(char *raw_disk_sb)
+static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
+ char *raw_disk_sb)
{
struct btrfs_super_block *disk_sb =
(struct btrfs_super_block *)raw_disk_sb;
@@ -418,7 +417,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
/*
* The super_block structure does not span the whole
* BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
- * is filled with zeros and is included in the checkum.
+ * is filled with zeros and is included in the checksum.
*/
crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
@@ -429,7 +428,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
- printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n",
+ btrfs_err(fs_info, "unsupported checksum algorithm %u",
csum_type);
ret = 1;
}
@@ -443,7 +442,7 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
*/
static int btree_read_extent_buffer_pages(struct btrfs_root *root,
struct extent_buffer *eb,
- u64 start, u64 parent_transid)
+ u64 parent_transid)
{
struct extent_io_tree *io_tree;
int failed = 0;
@@ -455,8 +454,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
while (1) {
- ret = read_extent_buffer_pages(io_tree, eb, start,
- WAIT_COMPLETE,
+ ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE,
btree_get_extent, mirror_num);
if (!ret) {
if (!verify_parent_transid(io_tree, eb,
@@ -548,9 +546,10 @@ static int check_tree_block_fsid(struct btrfs_fs_info *fs_info,
}
#define CORRUPT(reason, eb, root, slot) \
- btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \
- "root=%llu, slot=%d", reason, \
- btrfs_header_bytenr(eb), root->objectid, slot)
+ btrfs_crit(root->fs_info, "corrupt %s, %s: block=%llu," \
+ " root=%llu, slot=%d", \
+ btrfs_header_level(eb) == 0 ? "leaf" : "node",\
+ reason, btrfs_header_bytenr(eb), root->objectid, slot)
static noinline int check_leaf(struct btrfs_root *root,
struct extent_buffer *leaf)
@@ -560,8 +559,29 @@ static noinline int check_leaf(struct btrfs_root *root,
u32 nritems = btrfs_header_nritems(leaf);
int slot;
- if (nritems == 0)
+ if (nritems == 0) {
+ struct btrfs_root *check_root;
+
+ key.objectid = btrfs_header_owner(leaf);
+ key.type = BTRFS_ROOT_ITEM_KEY;
+ key.offset = (u64)-1;
+
+ check_root = btrfs_get_fs_root(root->fs_info, &key, false);
+ /*
+ * The only reason we also check NULL here is that during
+ * open_ctree() some roots has not yet been set up.
+ */
+ if (!IS_ERR_OR_NULL(check_root)) {
+ /* if leaf is the root, then it's fine */
+ if (leaf->start !=
+ btrfs_root_bytenr(&check_root->root_item)) {
+ CORRUPT("non-root leaf's nritems is 0",
+ leaf, root, 0);
+ return -EIO;
+ }
+ }
return 0;
+ }
/* Check the 0 item */
if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
@@ -600,7 +620,7 @@ static noinline int check_leaf(struct btrfs_root *root,
/*
* Check to make sure that we don't point outside of the leaf,
- * just incase all the items are consistent to eachother, but
+ * just in case all the items are consistent to each other, but
* all point outside of the leaf.
*/
if (btrfs_item_end_nr(leaf, slot) >
@@ -613,6 +633,42 @@ static noinline int check_leaf(struct btrfs_root *root,
return 0;
}
+static int check_node(struct btrfs_root *root, struct extent_buffer *node)
+{
+ unsigned long nr = btrfs_header_nritems(node);
+ struct btrfs_key key, next_key;
+ int slot;
+ u64 bytenr;
+ int ret = 0;
+
+ if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) {
+ btrfs_crit(root->fs_info,
+ "corrupt node: block %llu root %llu nritems %lu",
+ node->start, root->objectid, nr);
+ return -EIO;
+ }
+
+ for (slot = 0; slot < nr - 1; slot++) {
+ bytenr = btrfs_node_blockptr(node, slot);
+ btrfs_node_key_to_cpu(node, &key, slot);
+ btrfs_node_key_to_cpu(node, &next_key, slot + 1);
+
+ if (!bytenr) {
+ CORRUPT("invalid item slot", node, root, slot);
+ ret = -EIO;
+ goto out;
+ }
+
+ if (btrfs_comp_cpu_keys(&key, &next_key) >= 0) {
+ CORRUPT("bad key order", node, root, slot);
+ ret = -EIO;
+ goto out;
+ }
+ }
+out:
+ return ret;
+}
+
static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
@@ -683,6 +739,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
ret = -EIO;
}
+ if (found_level > 0 && check_node(root, eb))
+ ret = -EIO;
+
if (!ret)
set_extent_buffer_uptodate(eb);
err:
@@ -727,7 +786,7 @@ static void end_workqueue_bio(struct bio *bio)
fs_info = end_io_wq->info;
end_io_wq->error = bio->bi_error;
- if (bio->bi_rw & REQ_WRITE) {
+ if (bio_op(bio) == REQ_OP_WRITE) {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
wq = fs_info->endio_meta_write_workers;
func = btrfs_endio_meta_write_helper;
@@ -797,7 +856,7 @@ static void run_one_async_start(struct btrfs_work *work)
int ret;
async = container_of(work, struct async_submit_bio, work);
- ret = async->submit_bio_start(async->inode, async->rw, async->bio,
+ ret = async->submit_bio_start(async->inode, async->bio,
async->mirror_num, async->bio_flags,
async->bio_offset);
if (ret)
@@ -830,9 +889,8 @@ static void run_one_async_done(struct btrfs_work *work)
return;
}
- async->submit_bio_done(async->inode, async->rw, async->bio,
- async->mirror_num, async->bio_flags,
- async->bio_offset);
+ async->submit_bio_done(async->inode, async->bio, async->mirror_num,
+ async->bio_flags, async->bio_offset);
}
static void run_one_async_free(struct btrfs_work *work)
@@ -844,7 +902,7 @@ static void run_one_async_free(struct btrfs_work *work)
}
int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
- int rw, struct bio *bio, int mirror_num,
+ struct bio *bio, int mirror_num,
unsigned long bio_flags,
u64 bio_offset,
extent_submit_bio_hook_t *submit_bio_start,
@@ -857,7 +915,6 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
return -ENOMEM;
async->inode = inode;
- async->rw = rw;
async->bio = bio;
async->mirror_num = mirror_num;
async->submit_bio_start = submit_bio_start;
@@ -873,7 +930,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
atomic_inc(&fs_info->nr_async_submits);
- if (rw & REQ_SYNC)
+ if (bio->bi_opf & REQ_SYNC)
btrfs_set_work_high_priority(&async->work);
btrfs_queue_work(fs_info->workers, &async->work);
@@ -903,9 +960,8 @@ static int btree_csum_one_bio(struct bio *bio)
return ret;
}
-static int __btree_submit_bio_start(struct inode *inode, int rw,
- struct bio *bio, int mirror_num,
- unsigned long bio_flags,
+static int __btree_submit_bio_start(struct inode *inode, struct bio *bio,
+ int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
/*
@@ -915,7 +971,7 @@ static int __btree_submit_bio_start(struct inode *inode, int rw,
return btree_csum_one_bio(bio);
}
-static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
+static int __btree_submit_bio_done(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
@@ -925,7 +981,7 @@ static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
* when we're called for a write, we're already in the async
* submission context. Just jump into btrfs_map_bio
*/
- ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
+ ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 1);
if (ret) {
bio->bi_error = ret;
bio_endio(bio);
@@ -944,14 +1000,14 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
return 1;
}
-static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
+static int btree_submit_bio_hook(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
int async = check_async_write(inode, bio_flags);
int ret;
- if (!(rw & REQ_WRITE)) {
+ if (bio_op(bio) != REQ_OP_WRITE) {
/*
* called for a read, do the setup so that checksum validation
* can happen in the async kernel threads
@@ -960,21 +1016,19 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
bio, BTRFS_WQ_ENDIO_METADATA);
if (ret)
goto out_w_error;
- ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
- mirror_num, 0);
+ ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 0);
} else if (!async) {
ret = btree_csum_one_bio(bio);
if (ret)
goto out_w_error;
- ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
- mirror_num, 0);
+ ret = btrfs_map_bio(BTRFS_I(inode)->root, bio, mirror_num, 0);
} else {
/*
* kthread helpers are used to submit writes so that
* checksumming can happen in parallel across all CPUs
*/
ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
- inode, rw, bio, mirror_num, 0,
+ inode, bio, mirror_num, 0,
bio_offset,
__btree_submit_bio_start,
__btree_submit_bio_done);
@@ -1098,10 +1152,10 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
struct inode *btree_inode = root->fs_info->btree_inode;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return;
read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
- buf, 0, WAIT_NONE, btree_get_extent, 0);
+ buf, WAIT_NONE, btree_get_extent, 0);
free_extent_buffer(buf);
}
@@ -1114,12 +1168,12 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
+ if (IS_ERR(buf))
return 0;
set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
- ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
+ ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
btree_get_extent, mirror_num);
if (ret) {
free_extent_buffer(buf);
@@ -1146,8 +1200,9 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr)
{
- if (btrfs_test_is_dummy_root(root))
- return alloc_test_extent_buffer(root->fs_info, bytenr);
+ if (btrfs_is_testing(root->fs_info))
+ return alloc_test_extent_buffer(root->fs_info, bytenr,
+ root->nodesize);
return alloc_extent_buffer(root->fs_info, bytenr);
}
@@ -1171,10 +1226,10 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
int ret;
buf = btrfs_find_create_tree_block(root, bytenr);
- if (!buf)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(buf))
+ return buf;
- ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+ ret = btree_read_extent_buffer_pages(root, buf, parent_transid);
if (ret) {
free_extent_buffer(buf);
return ERR_PTR(ret);
@@ -1232,6 +1287,7 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
struct btrfs_root *root, struct btrfs_fs_info *fs_info,
u64 objectid)
{
+ bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
root->node = NULL;
root->commit_root = NULL;
root->sectorsize = sectorsize;
@@ -1286,14 +1342,14 @@ static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
root->log_transid = 0;
root->log_transid_committed = -1;
root->last_log_commit = 0;
- if (fs_info)
+ if (!dummy)
extent_io_tree_init(&root->dirty_log_pages,
fs_info->btree_inode->i_mapping);
memset(&root->root_key, 0, sizeof(root->root_key));
memset(&root->root_item, 0, sizeof(root->root_item));
memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
- if (fs_info)
+ if (!dummy)
root->defrag_trans_start = fs_info->generation;
else
root->defrag_trans_start = 0;
@@ -1314,15 +1370,20 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info,
+ u32 sectorsize, u32 nodesize)
{
struct btrfs_root *root;
- root = btrfs_alloc_root(NULL, GFP_KERNEL);
+ if (!fs_info)
+ return ERR_PTR(-EINVAL);
+
+ root = btrfs_alloc_root(fs_info, GFP_KERNEL);
if (!root)
return ERR_PTR(-ENOMEM);
- __setup_root(4096, 4096, 4096, root, NULL, 1);
- set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
+ /* We don't use the stripesize in selftest, set it as sectorsize */
+ __setup_root(nodesize, sectorsize, sectorsize, root, fs_info,
+ BTRFS_ROOT_TREE_OBJECTID);
root->alloc_bytenr = 0;
return root;
@@ -1597,14 +1658,14 @@ int btrfs_init_fs_root(struct btrfs_root *root)
ret = get_anon_bdev(&root->anon_dev);
if (ret)
- goto free_writers;
+ goto fail;
mutex_lock(&root->objectid_mutex);
ret = btrfs_find_highest_objectid(root,
&root->highest_objectid);
if (ret) {
mutex_unlock(&root->objectid_mutex);
- goto free_root_dev;
+ goto fail;
}
ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
@@ -1612,19 +1673,13 @@ int btrfs_init_fs_root(struct btrfs_root *root)
mutex_unlock(&root->objectid_mutex);
return 0;
-
-free_root_dev:
- free_anon_bdev(root->anon_dev);
-free_writers:
- btrfs_free_subvolume_writers(root->subv_writers);
fail:
- kfree(root->free_ino_ctl);
- kfree(root->free_ino_pinned);
+ /* the caller is responsible to call free_fs_root */
return ret;
}
-static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
- u64 root_id)
+struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
+ u64 root_id)
{
struct btrfs_root *root;
@@ -1640,7 +1695,7 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
{
int ret;
- ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+ ret = radix_tree_preload(GFP_NOFS);
if (ret)
return ret;
@@ -1803,6 +1858,13 @@ static int cleaner_kthread(void *arg)
if (btrfs_need_cleaner_sleep(root))
goto sleep;
+ /*
+ * Do not do anything if we might cause open_ctree() to block
+ * before we have finished mounting the filesystem.
+ */
+ if (!test_bit(BTRFS_FS_OPEN, &root->fs_info->flags))
+ goto sleep;
+
if (!mutex_trylock(&root->fs_info->cleaner_mutex))
goto sleep;
@@ -2293,9 +2355,8 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
fs_info->qgroup_op_tree = RB_ROOT;
INIT_LIST_HEAD(&fs_info->dirty_qgroups);
fs_info->qgroup_seq = 1;
- fs_info->quota_enabled = 0;
- fs_info->pending_quota_state = 0;
fs_info->qgroup_ulist = NULL;
+ fs_info->qgroup_rescan_running = false;
mutex_init(&fs_info->qgroup_rescan_lock);
}
@@ -2306,17 +2367,19 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
fs_info->workers =
- btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
- max_active, 16);
+ btrfs_alloc_workqueue(fs_info, "worker",
+ flags | WQ_HIGHPRI, max_active, 16);
fs_info->delalloc_workers =
- btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
+ btrfs_alloc_workqueue(fs_info, "delalloc",
+ flags, max_active, 2);
fs_info->flush_workers =
- btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
+ btrfs_alloc_workqueue(fs_info, "flush_delalloc",
+ flags, max_active, 0);
fs_info->caching_workers =
- btrfs_alloc_workqueue("cache", flags, max_active, 0);
+ btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);
/*
* a higher idle thresh on the submit workers makes it much more
@@ -2324,41 +2387,48 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
* devices
*/
fs_info->submit_workers =
- btrfs_alloc_workqueue("submit", flags,
+ btrfs_alloc_workqueue(fs_info, "submit", flags,
min_t(u64, fs_devices->num_devices,
max_active), 64);
fs_info->fixup_workers =
- btrfs_alloc_workqueue("fixup", flags, 1, 0);
+ btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);
/*
* endios are largely parallel and should have a very
* low idle thresh
*/
fs_info->endio_workers =
- btrfs_alloc_workqueue("endio", flags, max_active, 4);
+ btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
fs_info->endio_meta_workers =
- btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
+ btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
+ max_active, 4);
fs_info->endio_meta_write_workers =
- btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
+ btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
+ max_active, 2);
fs_info->endio_raid56_workers =
- btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+ btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
+ max_active, 4);
fs_info->endio_repair_workers =
- btrfs_alloc_workqueue("endio-repair", flags, 1, 0);
+ btrfs_alloc_workqueue(fs_info, "endio-repair", flags, 1, 0);
fs_info->rmw_workers =
- btrfs_alloc_workqueue("rmw", flags, max_active, 2);
+ btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2);
fs_info->endio_write_workers =
- btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
+ btrfs_alloc_workqueue(fs_info, "endio-write", flags,
+ max_active, 2);
fs_info->endio_freespace_worker =
- btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
+ btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
+ max_active, 0);
fs_info->delayed_workers =
- btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
+ btrfs_alloc_workqueue(fs_info, "delayed-meta", flags,
+ max_active, 0);
fs_info->readahead_workers =
- btrfs_alloc_workqueue("readahead", flags, max_active, 2);
+ btrfs_alloc_workqueue(fs_info, "readahead", flags,
+ max_active, 2);
fs_info->qgroup_rescan_workers =
- btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
+ btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
fs_info->extent_workers =
- btrfs_alloc_workqueue("extent-refs", flags,
+ btrfs_alloc_workqueue(fs_info, "extent-refs", flags,
min_t(u64, fs_devices->num_devices,
max_active), 8);
@@ -2417,7 +2487,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
if (ret) {
- btrfs_std_error(tree_root->fs_info, ret,
+ btrfs_handle_fs_error(tree_root->fs_info, ret,
"Failed to recover log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
@@ -2469,8 +2539,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info,
root = btrfs_read_tree_root(tree_root, &location);
if (!IS_ERR(root)) {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
- fs_info->quota_enabled = 1;
- fs_info->pending_quota_state = 1;
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
fs_info->quota_root = root;
}
@@ -2613,6 +2682,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->qgroup_op_seq, 0);
atomic_set(&fs_info->reada_works_cnt, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
+ fs_info->fs_frozen = 0;
fs_info->sb = sb;
fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
fs_info->metadata_ratio = 0;
@@ -2660,8 +2730,7 @@ int open_ctree(struct super_block *sb,
extent_io_tree_init(&fs_info->freed_extents[1],
fs_info->btree_inode->i_mapping);
fs_info->pinned_extents = &fs_info->freed_extents[0];
- fs_info->do_barriers = 1;
-
+ set_bit(BTRFS_FS_BARRIER, &fs_info->flags);
mutex_init(&fs_info->ordered_operations_mutex);
mutex_init(&fs_info->tree_log_mutex);
@@ -2712,8 +2781,8 @@ int open_ctree(struct super_block *sb,
* We want to check superblock checksum, the type is stored inside.
* Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/
- if (btrfs_check_super_csum(bh->b_data)) {
- printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
+ if (btrfs_check_super_csum(fs_info, bh->b_data)) {
+ btrfs_err(fs_info, "superblock checksum mismatch");
err = -EINVAL;
brelse(bh);
goto fail_alloc;
@@ -2733,7 +2802,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
- printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
+ btrfs_err(fs_info, "superblock contains fatal errors");
err = -EINVAL;
goto fail_alloc;
}
@@ -2768,9 +2837,9 @@ int open_ctree(struct super_block *sb,
features = btrfs_super_incompat_flags(disk_super) &
~BTRFS_FEATURE_INCOMPAT_SUPP;
if (features) {
- printk(KERN_ERR "BTRFS: couldn't mount because of "
- "unsupported optional features (%Lx).\n",
- features);
+ btrfs_err(fs_info,
+ "cannot mount because of unsupported optional features (%llx)",
+ features);
err = -EINVAL;
goto fail_alloc;
}
@@ -2781,7 +2850,7 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_INFO "BTRFS: has skinny extents\n");
+ btrfs_info(fs_info, "has skinny extents");
/*
* flag our filesystem as having big metadata blocks if
@@ -2789,13 +2858,14 @@ int open_ctree(struct super_block *sb,
*/
if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
+ btrfs_info(fs_info,
+ "flagging fs with big metadata feature");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
nodesize = btrfs_super_nodesize(disk_super);
sectorsize = btrfs_super_sectorsize(disk_super);
- stripesize = btrfs_super_stripesize(disk_super);
+ stripesize = sectorsize;
fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
@@ -2805,9 +2875,9 @@ int open_ctree(struct super_block *sb,
*/
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(sectorsize != nodesize)) {
- printk(KERN_ERR "BTRFS: unequal leaf/node/sector sizes "
- "are not allowed for mixed block groups on %s\n",
- sb->s_id);
+ btrfs_err(fs_info,
+"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
+ nodesize, sectorsize);
goto fail_alloc;
}
@@ -2820,8 +2890,8 @@ int open_ctree(struct super_block *sb,
features = btrfs_super_compat_ro_flags(disk_super) &
~BTRFS_FEATURE_COMPAT_RO_SUPP;
if (!(sb->s_flags & MS_RDONLY) && features) {
- printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
- "unsupported option features (%Lx).\n",
+ btrfs_err(fs_info,
+ "cannot mount read-write because of unsupported optional features (%llx)",
features);
err = -EINVAL;
goto fail_alloc;
@@ -2850,8 +2920,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to read the system "
- "array on %s\n", sb->s_id);
+ btrfs_err(fs_info, "failed to read the system array: %d", ret);
goto fail_sb_buffer;
}
@@ -2865,8 +2934,7 @@ int open_ctree(struct super_block *sb,
generation);
if (IS_ERR(chunk_root->node) ||
!extent_buffer_uptodate(chunk_root->node)) {
- printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read chunk root");
if (!IS_ERR(chunk_root->node))
free_extent_buffer(chunk_root->node);
chunk_root->node = NULL;
@@ -2880,8 +2948,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to read chunk tree on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read chunk tree: %d", ret);
goto fail_tree_roots;
}
@@ -2892,8 +2959,7 @@ int open_ctree(struct super_block *sb,
btrfs_close_extra_devices(fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_ERR "BTRFS: failed to read devices on %s\n",
- sb->s_id);
+ btrfs_err(fs_info, "failed to read devices");
goto fail_tree_roots;
}
@@ -2905,8 +2971,7 @@ retry_root_backup:
generation);
if (IS_ERR(tree_root->node) ||
!extent_buffer_uptodate(tree_root->node)) {
- printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
- sb->s_id);
+ btrfs_warn(fs_info, "failed to read tree root");
if (!IS_ERR(tree_root->node))
free_extent_buffer(tree_root->node);
tree_root->node = NULL;
@@ -2938,20 +3003,19 @@ retry_root_backup:
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to recover balance\n");
+ btrfs_err(fs_info, "failed to recover balance: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
- ret);
+ btrfs_err(fs_info, "failed to init dev_stats: %d", ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info);
if (ret) {
- pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
+ btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
goto fail_block_groups;
}
@@ -2959,31 +3023,33 @@ retry_root_backup:
ret = btrfs_sysfs_add_fsid(fs_devices, NULL);
if (ret) {
- pr_err("BTRFS: failed to init sysfs fsid interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
+ ret);
goto fail_block_groups;
}
ret = btrfs_sysfs_add_device(fs_devices);
if (ret) {
- pr_err("BTRFS: failed to init sysfs device interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs device interface: %d",
+ ret);
goto fail_fsdev_sysfs;
}
ret = btrfs_sysfs_add_mounted(fs_info);
if (ret) {
- pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
+ btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
goto fail_fsdev_sysfs;
}
ret = btrfs_init_space_info(fs_info);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+ btrfs_err(fs_info, "failed to initialize space info: %d", ret);
goto fail_sysfs;
}
ret = btrfs_read_block_groups(fs_info->extent_root);
if (ret) {
- printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ btrfs_err(fs_info, "failed to read block groups: %d", ret);
goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
@@ -2991,7 +3057,8 @@ retry_root_backup:
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n",
+ btrfs_warn(fs_info,
+"missing devices (%llu) exceeds the limit (%d), writeable mount is not allowed",
fs_info->fs_devices->missing_devices,
fs_info->num_tolerated_disk_barrier_failures);
goto fail_sysfs;
@@ -3008,30 +3075,30 @@ retry_root_backup:
if (IS_ERR(fs_info->transaction_kthread))
goto fail_cleaner;
- if (!btrfs_test_opt(tree_root, SSD) &&
- !btrfs_test_opt(tree_root, NOSSD) &&
+ if (!btrfs_test_opt(tree_root->fs_info, SSD) &&
+ !btrfs_test_opt(tree_root->fs_info, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
- "mode\n");
+ btrfs_info(fs_info, "detected SSD devices, enabling SSD mode");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
/*
- * Mount does not set all options immediatelly, we can do it now and do
+ * Mount does not set all options immediately, we can do it now and do
* not have to wait for transaction commit
*/
btrfs_apply_pending_changes(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
+ if (btrfs_test_opt(tree_root->fs_info, CHECK_INTEGRITY)) {
ret = btrfsic_mount(tree_root, fs_devices,
- btrfs_test_opt(tree_root,
+ btrfs_test_opt(tree_root->fs_info,
CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ?
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "BTRFS: failed to initialize"
- " integrity check module %s\n", sb->s_id);
+ btrfs_warn(fs_info,
+ "failed to initialize integrity check module: %d",
+ ret);
}
#endif
ret = btrfs_read_qgroup_config(fs_info);
@@ -3040,7 +3107,7 @@ retry_root_backup:
/* do not make disk changes in broken FS or nologreplay is given */
if (btrfs_super_log_root(disk_super) != 0 &&
- !btrfs_test_opt(tree_root, NOLOGREPLAY)) {
+ !btrfs_test_opt(tree_root->fs_info, NOLOGREPLAY)) {
ret = btrfs_replay_log(fs_info, fs_devices);
if (ret) {
err = ret;
@@ -3061,8 +3128,8 @@ retry_root_backup:
ret = btrfs_recover_relocation(tree_root);
mutex_unlock(&fs_info->cleaner_mutex);
if (ret < 0) {
- printk(KERN_WARNING
- "BTRFS: failed to recover relocation\n");
+ btrfs_warn(fs_info, "failed to recover relocation: %d",
+ ret);
err = -EINVAL;
goto fail_qgroup;
}
@@ -3081,13 +3148,13 @@ retry_root_backup:
if (sb->s_flags & MS_RDONLY)
return 0;
- if (btrfs_test_opt(tree_root, FREE_SPACE_TREE) &&
+ if (btrfs_test_opt(tree_root->fs_info, FREE_SPACE_TREE) &&
!btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- pr_info("BTRFS: creating free space tree\n");
+ btrfs_info(fs_info, "creating free space tree");
ret = btrfs_create_free_space_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create free space tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create free space tree: %d", ret);
close_ctree(tree_root);
return ret;
}
@@ -3104,57 +3171,56 @@ retry_root_backup:
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "BTRFS: failed to resume balance\n");
+ btrfs_warn(fs_info, "failed to resume balance: %d", ret);
close_ctree(tree_root);
return ret;
}
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to resume dev_replace\n");
+ btrfs_warn(fs_info, "failed to resume device replace: %d", ret);
close_ctree(tree_root);
return ret;
}
btrfs_qgroup_rescan_resume(fs_info);
- if (btrfs_test_opt(tree_root, CLEAR_CACHE) &&
+ if (btrfs_test_opt(tree_root->fs_info, CLEAR_CACHE) &&
btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
- pr_info("BTRFS: clearing free space tree\n");
+ btrfs_info(fs_info, "clearing free space tree");
ret = btrfs_clear_free_space_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to clear free space tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to clear free space tree: %d", ret);
close_ctree(tree_root);
return ret;
}
}
if (!fs_info->uuid_root) {
- pr_info("BTRFS: creating UUID tree\n");
+ btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to create the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to create the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
- } else if (btrfs_test_opt(tree_root, RESCAN_UUID_TREE) ||
+ } else if (btrfs_test_opt(tree_root->fs_info, RESCAN_UUID_TREE) ||
fs_info->generation !=
btrfs_super_uuid_tree_generation(disk_super)) {
- pr_info("BTRFS: checking UUID tree\n");
+ btrfs_info(fs_info, "checking UUID tree");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("BTRFS: failed to check the UUID tree %d\n",
- ret);
+ btrfs_warn(fs_info,
+ "failed to check the UUID tree: %d", ret);
close_ctree(tree_root);
return ret;
}
} else {
- fs_info->update_uuid_tree_gen = 1;
+ set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);
}
-
- fs_info->open = 1;
+ set_bit(BTRFS_FS_OPEN, &fs_info->flags);
/*
* backuproot only affect mount behavior, and if open_ctree succeeded,
@@ -3216,7 +3282,7 @@ fail:
return err;
recovery_tree_root:
- if (!btrfs_test_opt(tree_root, USEBACKUPROOT))
+ if (!btrfs_test_opt(tree_root->fs_info, USEBACKUPROOT))
goto fail_tree_roots;
free_root_pointers(fs_info, 0);
@@ -3245,7 +3311,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
btrfs_warn_rl_in_rcu(device->dev_root->fs_info,
"lost page write due to IO error on %s",
rcu_str_deref(device->name));
- /* note, we dont' set_buffer_write_io_error because we have
+ /* note, we don't set_buffer_write_io_error because we have
* our own ways of dealing with the IO errors
*/
clear_buffer_uptodate(bh);
@@ -3410,9 +3476,9 @@ static int write_dev_supers(struct btrfs_device *device,
* to go down lazy.
*/
if (i == 0)
- ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_FUA, bh);
else
- ret = btrfsic_submit_bh(WRITE_SYNC, bh);
+ ret = btrfsic_submit_bh(REQ_OP_WRITE, WRITE_SYNC, bh);
if (ret)
errors++;
}
@@ -3476,12 +3542,13 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
bio->bi_end_io = btrfs_end_empty_barrier;
bio->bi_bdev = device->bdev;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, WRITE_FLUSH);
init_completion(&device->flush_wait);
bio->bi_private = &device->flush_wait;
device->flush_bio = bio;
bio_get(bio);
- btrfsic_submit_bio(WRITE_FLUSH, bio);
+ btrfsic_submit_bio(bio);
return 0;
}
@@ -3558,7 +3625,7 @@ int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
}
if (min_tolerated == INT_MAX) {
- pr_warn("BTRFS: unknown raid flag: %llu\n", flags);
+ pr_warn("BTRFS: unknown raid flag: %llu", flags);
min_tolerated = 0;
}
@@ -3631,7 +3698,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
int total_errors = 0;
u64 flags;
- do_barriers = !btrfs_test_opt(root, NOBARRIER);
+ do_barriers = !btrfs_test_opt(root->fs_info, NOBARRIER);
backup_super_roots(root->fs_info);
sb = root->fs_info->super_for_commit;
@@ -3646,7 +3713,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
if (ret) {
mutex_unlock(
&root->fs_info->fs_devices->device_list_mutex);
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"errors while submitting device barriers.");
return ret;
}
@@ -3686,7 +3753,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
/* FUA is masked off if unsupported and can't be the reason */
- btrfs_std_error(root->fs_info, -EIO,
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
@@ -3704,7 +3771,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
}
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
if (total_errors > max_errors) {
- btrfs_std_error(root->fs_info, -EIO,
+ btrfs_handle_fs_error(root->fs_info, -EIO,
"%d errors while writing supers", total_errors);
return -EIO;
}
@@ -3729,8 +3796,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
btrfs_free_log(NULL, root);
+ if (root->reloc_root) {
+ free_extent_buffer(root->reloc_root->node);
+ free_extent_buffer(root->reloc_root->commit_root);
+ btrfs_put_fs_root(root->reloc_root);
+ root->reloc_root = NULL;
+ }
+ }
if (root->free_ino_pinned)
__btrfs_remove_free_space_cache(root->free_ino_pinned);
@@ -3837,11 +3911,10 @@ void close_ctree(struct btrfs_root *root)
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
- fs_info->closing = 1;
- smp_mb();
+ set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
/* wait for the qgroup rescan worker to stop */
- btrfs_qgroup_wait_for_completion(fs_info);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
/* wait for the uuid_scan task to finish */
down(&fs_info->uuid_tree_rescan_sem);
@@ -3883,8 +3956,7 @@ void close_ctree(struct btrfs_root *root)
kthread_stop(fs_info->transaction_kthread);
kthread_stop(fs_info->cleaner_kthread);
- fs_info->closing = 2;
- smp_mb();
+ set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
btrfs_free_qgroup_config(fs_info);
@@ -3909,13 +3981,13 @@ void close_ctree(struct btrfs_root *root)
invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
- fs_info->open = 0;
+ clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
free_root_pointers(fs_info, 1);
iput(fs_info->btree_inode);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_test_opt(root, CHECK_INTEGRITY))
+ if (btrfs_test_opt(root->fs_info, CHECK_INTEGRITY))
btrfsic_unmount(root, fs_info->fs_devices);
#endif
@@ -3980,8 +4052,7 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
root = BTRFS_I(buf->pages[0]->mapping->host)->root;
btrfs_assert_tree_locked(buf);
if (transid != root->fs_info->generation)
- WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, "
- "found %llu running %llu\n",
+ WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n",
buf->start, transid, root->fs_info->generation);
was_dirty = set_extent_buffer_dirty(buf);
if (!was_dirty)
@@ -4032,7 +4103,7 @@ void btrfs_btree_balance_dirty_nodelay(struct btrfs_root *root)
int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
{
struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
- return btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
+ return btree_read_extent_buffer_pages(root, buf, parent_transid);
}
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
@@ -4044,24 +4115,24 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int ret = 0;
if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
- printk(KERN_ERR "BTRFS: no valid FS found\n");
+ btrfs_err(fs_info, "no valid FS found");
ret = -EINVAL;
}
if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
- printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+ btrfs_warn(fs_info, "unrecognized super flag: %llu",
btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
- printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
+ btrfs_err(fs_info, "tree_root level too big: %d >= %d",
btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
- printk(KERN_ERR "BTRFS: chunk_root level too big: %d >= %d\n",
+ btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
- printk(KERN_ERR "BTRFS: log_root level too big: %d >= %d\n",
+ btrfs_err(fs_info, "log_root level too big: %d >= %d",
btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
ret = -EINVAL;
}
@@ -4072,47 +4143,48 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
*/
if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
- printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+ btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
ret = -EINVAL;
}
/* Only PAGE SIZE is supported yet */
if (sectorsize != PAGE_SIZE) {
- printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
- sectorsize, PAGE_SIZE);
+ btrfs_err(fs_info,
+ "sectorsize %llu not supported yet, only support %lu",
+ sectorsize, PAGE_SIZE);
ret = -EINVAL;
}
if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
- printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+ btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
ret = -EINVAL;
}
if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
- printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
- le32_to_cpu(sb->__unused_leafsize),
- nodesize);
+ btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
+ le32_to_cpu(sb->__unused_leafsize), nodesize);
ret = -EINVAL;
}
/* Root alignment check */
if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
- printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
- btrfs_super_root(sb));
+ btrfs_warn(fs_info, "tree_root block unaligned: %llu",
+ btrfs_super_root(sb));
ret = -EINVAL;
}
if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
- printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
- btrfs_super_chunk_root(sb));
+ btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
+ btrfs_super_chunk_root(sb));
ret = -EINVAL;
}
if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
- printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
- btrfs_super_log_root(sb));
+ btrfs_warn(fs_info, "log_root block unaligned: %llu",
+ btrfs_super_log_root(sb));
ret = -EINVAL;
}
if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
- printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
- fs_info->fsid, sb->dev_item.fsid);
+ btrfs_err(fs_info,
+ "dev_item UUID does not match fsid: %pU != %pU",
+ fs_info->fsid, sb->dev_item.fsid);
ret = -EINVAL;
}
@@ -4120,17 +4192,27 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
* Hint to catch really bogus numbers, bitflips or so, more exact checks are
* done later
*/
+ if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+ btrfs_err(fs_info, "bytes_used is too small %llu",
+ btrfs_super_bytes_used(sb));
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+ btrfs_err(fs_info, "invalid stripesize %u",
+ btrfs_super_stripesize(sb));
+ ret = -EINVAL;
+ }
if (btrfs_super_num_devices(sb) > (1UL << 31))
- printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
- btrfs_super_num_devices(sb));
+ btrfs_warn(fs_info, "suspicious number of devices: %llu",
+ btrfs_super_num_devices(sb));
if (btrfs_super_num_devices(sb) == 0) {
- printk(KERN_ERR "BTRFS: number of devices is 0\n");
+ btrfs_err(fs_info, "number of devices is 0");
ret = -EINVAL;
}
if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
- printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
- btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
+ btrfs_err(fs_info, "super offset mismatch %llu != %u",
+ btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
ret = -EINVAL;
}
@@ -4139,17 +4221,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
* and one chunk
*/
if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
- printk(KERN_ERR "BTRFS: system chunk array too big %u > %u\n",
- btrfs_super_sys_array_size(sb),
- BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
+ btrfs_err(fs_info, "system chunk array too big %u > %u",
+ btrfs_super_sys_array_size(sb),
+ BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
ret = -EINVAL;
}
if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
+ sizeof(struct btrfs_chunk)) {
- printk(KERN_ERR "BTRFS: system chunk array too small %u < %zu\n",
- btrfs_super_sys_array_size(sb),
- sizeof(struct btrfs_disk_key)
- + sizeof(struct btrfs_chunk));
+ btrfs_err(fs_info, "system chunk array too small %u < %zu",
+ btrfs_super_sys_array_size(sb),
+ sizeof(struct btrfs_disk_key)
+ + sizeof(struct btrfs_chunk));
ret = -EINVAL;
}
@@ -4158,14 +4240,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
* but it's still possible that it's the one that's wrong.
*/
if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
- printk(KERN_WARNING
- "BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
- btrfs_super_generation(sb), btrfs_super_chunk_root_generation(sb));
+ btrfs_warn(fs_info,
+ "suspicious: generation < chunk_root_generation: %llu < %llu",
+ btrfs_super_generation(sb),
+ btrfs_super_chunk_root_generation(sb));
if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
&& btrfs_super_cache_generation(sb) != (u64)-1)
- printk(KERN_WARNING
- "BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
- btrfs_super_generation(sb), btrfs_super_cache_generation(sb));
+ btrfs_warn(fs_info,
+ "suspicious: generation < cache_generation: %llu < %llu",
+ btrfs_super_generation(sb),
+ btrfs_super_cache_generation(sb));
return ret;
}
@@ -4357,7 +4441,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
if (ret)
break;
- clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
+ clear_extent_bits(dirty_pages, start, end, mark);
while (start <= end) {
eb = btrfs_find_tree_block(root->fs_info, start);
start += root->nodesize;
@@ -4392,7 +4476,7 @@ again:
if (ret)
break;
- clear_extent_dirty(unpin, start, end, GFP_NOFS);
+ clear_extent_dirty(unpin, start, end);
btrfs_error_unpin_extent_range(root, start, end);
cond_resched();
}
@@ -4409,9 +4493,80 @@ again:
return 0;
}
+static void btrfs_cleanup_bg_io(struct btrfs_block_group_cache *cache)
+{
+ struct inode *inode;
+
+ inode = cache->io_ctl.inode;
+ if (inode) {
+ invalidate_inode_pages2(inode->i_mapping);
+ BTRFS_I(inode)->generation = 0;
+ cache->io_ctl.inode = NULL;
+ iput(inode);
+ }
+ btrfs_put_block_group(cache);
+}
+
+void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
+ struct btrfs_root *root)
+{
+ struct btrfs_block_group_cache *cache;
+
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ while (!list_empty(&cur_trans->dirty_bgs)) {
+ cache = list_first_entry(&cur_trans->dirty_bgs,
+ struct btrfs_block_group_cache,
+ dirty_list);
+ if (!cache) {
+ btrfs_err(root->fs_info,
+ "orphan block group dirty_bgs list");
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ return;
+ }
+
+ if (!list_empty(&cache->io_list)) {
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ list_del_init(&cache->io_list);
+ btrfs_cleanup_bg_io(cache);
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ }
+
+ list_del_init(&cache->dirty_list);
+ spin_lock(&cache->lock);
+ cache->disk_cache_state = BTRFS_DC_ERROR;
+ spin_unlock(&cache->lock);
+
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+ btrfs_put_block_group(cache);
+ spin_lock(&cur_trans->dirty_bgs_lock);
+ }
+ spin_unlock(&cur_trans->dirty_bgs_lock);
+
+ while (!list_empty(&cur_trans->io_bgs)) {
+ cache = list_first_entry(&cur_trans->io_bgs,
+ struct btrfs_block_group_cache,
+ io_list);
+ if (!cache) {
+ btrfs_err(root->fs_info,
+ "orphan block group on io_bgs list");
+ return;
+ }
+
+ list_del_init(&cache->io_list);
+ spin_lock(&cache->lock);
+ cache->disk_cache_state = BTRFS_DC_ERROR;
+ spin_unlock(&cache->lock);
+ btrfs_cleanup_bg_io(cache);
+ }
+}
+
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
+ btrfs_cleanup_dirty_bgs(cur_trans, root);
+ ASSERT(list_empty(&cur_trans->dirty_bgs));
+ ASSERT(list_empty(&cur_trans->io_bgs));
+
btrfs_destroy_delayed_refs(cur_trans, root);
cur_trans->state = TRANS_STATE_COMMIT_START;
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-14 16:58:26 +0000