aboutsummaryrefslogtreecommitdiff
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.c973
1 files changed, 514 insertions, 459 deletions
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 4cbb00af92f..08e65e9cf2a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -26,16 +26,15 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
-#include <linux/crc32c.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
#include <asm/unaligned.h>
-#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
+#include "hash.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
@@ -49,6 +48,8 @@
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
+#include "sysfs.h"
+#include "qgroup.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
@@ -64,7 +65,6 @@ static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
struct btrfs_root *root);
-static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_root *root,
struct extent_io_tree *dirty_pages,
@@ -157,6 +157,7 @@ static struct btrfs_lockdep_keyset {
{ .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" },
{ .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" },
{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" },
+ { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" },
{ .id = 0, .name_stem = "tree" },
};
@@ -244,7 +245,7 @@ out:
u32 btrfs_csum_data(char *data, u32 seed, size_t len)
{
- return crc32c(seed, data, len);
+ return btrfs_crc32c(seed, data, len);
}
void btrfs_csum_final(u32 crc, char *result)
@@ -300,11 +301,11 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
- printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
- "failed on %llu wanted %X found %X "
- "level %d\n",
- root->fs_info->sb->s_id, buf->start,
- val, found, btrfs_header_level(buf));
+ printk_ratelimited(KERN_INFO
+ "BTRFS: %s checksum verify failed on %llu wanted %X found %X "
+ "level %d\n",
+ root->fs_info->sb->s_id, buf->start,
+ val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
return 1;
@@ -329,6 +330,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
{
struct extent_state *cached_state = NULL;
int ret;
+ bool need_lock = (current->journal_info ==
+ (void *)BTRFS_SEND_TRANS_STUB);
if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
return 0;
@@ -336,6 +339,11 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
if (atomic)
return -EAGAIN;
+ if (need_lock) {
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ }
+
lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
0, &cached_state);
if (extent_buffer_uptodate(eb) &&
@@ -347,10 +355,22 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
"found %llu\n",
eb->start, parent_transid, btrfs_header_generation(eb));
ret = 1;
- clear_extent_buffer_uptodate(eb);
+
+ /*
+ * 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
+ * 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.
+ */
+ if (!extent_buffer_under_io(eb))
+ clear_extent_buffer_uptodate(eb);
out:
unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
&cached_state, GFP_NOFS);
+ if (need_lock)
+ btrfs_tree_read_unlock_blocking(eb);
return ret;
}
@@ -383,13 +403,14 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
ret = 1;
if (ret && btrfs_super_generation(disk_sb) < 10) {
- printk(KERN_WARNING "btrfs: super block crcs don't match, older mkfs detected\n");
+ printk(KERN_WARNING
+ "BTRFS: super block crcs don't match, older mkfs detected\n");
ret = 0;
}
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
- printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n",
+ printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n",
csum_type);
ret = 1;
}
@@ -465,25 +486,16 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
- struct extent_io_tree *tree;
u64 start = page_offset(page);
u64 found_start;
struct extent_buffer *eb;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
-
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
return 0;
found_start = btrfs_header_bytenr(eb);
- if (found_start != start) {
- WARN_ON(1);
+ if (WARN_ON(found_start != start || !PageUptodate(page)))
return 0;
- }
- if (!PageUptodate(page)) {
- WARN_ON(1);
- return 0;
- }
csum_tree_block(root, eb, 0);
return 0;
}
@@ -495,7 +507,7 @@ static int check_tree_block_fsid(struct btrfs_root *root,
u8 fsid[BTRFS_UUID_SIZE];
int ret = 1;
- read_extent_buffer(eb, fsid, btrfs_header_fsid(eb), BTRFS_FSID_SIZE);
+ read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
while (fs_devices) {
if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
ret = 0;
@@ -507,8 +519,8 @@ static int check_tree_block_fsid(struct btrfs_root *root,
}
#define CORRUPT(reason, eb, root, slot) \
- printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \
- "root=%llu, slot=%d\n", reason, \
+ btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \
+ "root=%llu, slot=%d", reason, \
btrfs_header_bytenr(eb), root->objectid, slot)
static noinline int check_leaf(struct btrfs_root *root,
@@ -576,7 +588,6 @@ 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)
{
- struct extent_io_tree *tree;
u64 found_start;
int found_level;
struct extent_buffer *eb;
@@ -587,7 +598,6 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
if (!page->private)
goto out;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
eb = (struct extent_buffer *)page->private;
/* the pending IO might have been the only thing that kept this buffer
@@ -607,21 +617,21 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- printk_ratelimited(KERN_INFO "btrfs bad tree block start "
+ printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
"%llu %llu\n",
found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root, eb)) {
- printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
+ printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
eb->start);
ret = -EIO;
goto err;
}
found_level = btrfs_header_level(eb);
if (found_level >= BTRFS_MAX_LEVEL) {
- btrfs_info(root->fs_info, "bad tree block level %d\n",
+ btrfs_info(root->fs_info, "bad tree block level %d",
(int)btrfs_header_level(eb));
ret = -EIO;
goto err;
@@ -688,32 +698,31 @@ static void end_workqueue_bio(struct bio *bio, int err)
fs_info = end_io_wq->info;
end_io_wq->error = err;
- end_io_wq->work.func = end_workqueue_fn;
- end_io_wq->work.flags = 0;
+ btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
if (bio->bi_rw & REQ_WRITE) {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
- btrfs_queue_worker(&fs_info->endio_meta_write_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_meta_write_workers,
+ &end_io_wq->work);
else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
- btrfs_queue_worker(&fs_info->endio_freespace_worker,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_freespace_worker,
+ &end_io_wq->work);
else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_worker(&fs_info->endio_raid56_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_raid56_workers,
+ &end_io_wq->work);
else
- btrfs_queue_worker(&fs_info->endio_write_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_write_workers,
+ &end_io_wq->work);
} else {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
- btrfs_queue_worker(&fs_info->endio_raid56_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_raid56_workers,
+ &end_io_wq->work);
else if (end_io_wq->metadata)
- btrfs_queue_worker(&fs_info->endio_meta_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_meta_workers,
+ &end_io_wq->work);
else
- btrfs_queue_worker(&fs_info->endio_workers,
- &end_io_wq->work);
+ btrfs_queue_work(fs_info->endio_workers,
+ &end_io_wq->work);
}
}
@@ -748,7 +757,7 @@ int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
{
unsigned long limit = min_t(unsigned long,
- info->workers.max_workers,
+ info->thread_pool_size,
info->fs_devices->open_devices);
return 256 * limit;
}
@@ -821,11 +830,9 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
async->submit_bio_start = submit_bio_start;
async->submit_bio_done = submit_bio_done;
- async->work.func = run_one_async_start;
- async->work.ordered_func = run_one_async_done;
- async->work.ordered_free = run_one_async_free;
+ btrfs_init_work(&async->work, run_one_async_start,
+ run_one_async_done, run_one_async_free);
- async->work.flags = 0;
async->bio_flags = bio_flags;
async->bio_offset = bio_offset;
@@ -834,9 +841,9 @@ 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)
- btrfs_set_work_high_prio(&async->work);
+ btrfs_set_work_high_priority(&async->work);
- btrfs_queue_worker(&fs_info->workers, &async->work);
+ btrfs_queue_work(fs_info->workers, &async->work);
while (atomic_read(&fs_info->async_submit_draining) &&
atomic_read(&fs_info->nr_async_submits)) {
@@ -849,20 +856,17 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
static int btree_csum_one_bio(struct bio *bio)
{
- struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct bio_vec *bvec;
struct btrfs_root *root;
- int ret = 0;
+ int i, ret = 0;
- WARN_ON(bio->bi_vcnt <= 0);
- while (bio_index < bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, bio, i) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root, bvec->bv_page);
if (ret)
break;
- bio_index++;
- bvec++;
}
+
return ret;
}
@@ -974,11 +978,9 @@ static int btree_migratepage(struct address_space *mapping,
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct extent_io_tree *tree;
struct btrfs_fs_info *fs_info;
int ret;
- tree = &BTRFS_I(mapping->host)->io_tree;
if (wbc->sync_mode == WB_SYNC_NONE) {
if (wbc->for_kupdate)
@@ -1017,8 +1019,9 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
extent_invalidatepage(tree, page, offset);
btree_releasepage(page, GFP_NOFS);
if (PagePrivate(page)) {
- printk(KERN_WARNING "btrfs warning page private not zero "
- "on page %llu\n", (unsigned long long)page_offset(page));
+ btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
+ "page private not zero on page %llu",
+ (unsigned long long)page_offset(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
@@ -1102,22 +1105,18 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
- eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
- bytenr, blocksize);
- return eb;
+ return find_extent_buffer(root->fs_info, bytenr);
}
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
-
- eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
- bytenr, blocksize);
- return eb;
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+ return alloc_test_extent_buffer(root->fs_info, bytenr,
+ blocksize);
+#endif
+ return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
}
@@ -1172,6 +1171,32 @@ void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
}
}
+static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
+{
+ struct btrfs_subvolume_writers *writers;
+ int ret;
+
+ writers = kmalloc(sizeof(*writers), GFP_NOFS);
+ if (!writers)
+ return ERR_PTR(-ENOMEM);
+
+ ret = percpu_counter_init(&writers->counter, 0);
+ if (ret < 0) {
+ kfree(writers);
+ return ERR_PTR(ret);
+ }
+
+ init_waitqueue_head(&writers->wait);
+ return writers;
+}
+
+static void
+btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
+{
+ percpu_counter_destroy(&writers->counter);
+ kfree(writers);
+}
+
static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
u32 stripesize, struct btrfs_root *root,
struct btrfs_fs_info *fs_info,
@@ -1183,10 +1208,7 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
root->nodesize = nodesize;
root->leafsize = leafsize;
root->stripesize = stripesize;
- root->ref_cows = 0;
- root->track_dirty = 0;
- root->in_radix = 0;
- root->orphan_item_inserted = 0;
+ root->state = 0;
root->orphan_cleanup_state = 0;
root->objectid = objectid;
@@ -1217,27 +1239,36 @@ static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
spin_lock_init(&root->log_extents_lock[1]);
mutex_init(&root->objectid_mutex);
mutex_init(&root->log_mutex);
+ mutex_init(&root->ordered_extent_mutex);
+ mutex_init(&root->delalloc_mutex);
init_waitqueue_head(&root->log_writer_wait);
init_waitqueue_head(&root->log_commit_wait[0]);
init_waitqueue_head(&root->log_commit_wait[1]);
+ INIT_LIST_HEAD(&root->log_ctxs[0]);
+ INIT_LIST_HEAD(&root->log_ctxs[1]);
atomic_set(&root->log_commit[0], 0);
atomic_set(&root->log_commit[1], 0);
atomic_set(&root->log_writers, 0);
atomic_set(&root->log_batch, 0);
atomic_set(&root->orphan_inodes, 0);
atomic_set(&root->refs, 1);
+ atomic_set(&root->will_be_snapshoted, 0);
root->log_transid = 0;
+ root->log_transid_committed = -1;
root->last_log_commit = 0;
- extent_io_tree_init(&root->dirty_log_pages,
- fs_info->btree_inode->i_mapping);
+ if (fs_info)
+ 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));
memset(&root->root_kobj, 0, sizeof(root->root_kobj));
- root->defrag_trans_start = fs_info->generation;
+ if (fs_info)
+ root->defrag_trans_start = fs_info->generation;
+ else
+ root->defrag_trans_start = 0;
init_completion(&root->kobj_unregister);
- root->defrag_running = 0;
root->root_key.objectid = objectid;
root->anon_dev = 0;
@@ -1252,6 +1283,23 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
return root;
}
+#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 *root;
+
+ root = btrfs_alloc_root(NULL);
+ if (!root)
+ return ERR_PTR(-ENOMEM);
+ __setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
+ set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
+ root->alloc_bytenr = 0;
+
+ return root;
+}
+#endif
+
struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
u64 objectid)
@@ -1261,7 +1309,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root;
struct btrfs_key key;
int ret = 0;
- u64 bytenr;
uuid_le uuid;
root = btrfs_alloc_root(fs_info);
@@ -1283,7 +1330,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
goto fail;
}
- bytenr = leaf->start;
memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
btrfs_set_header_bytenr(leaf, leaf->start);
btrfs_set_header_generation(leaf, trans->transid);
@@ -1291,7 +1337,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
btrfs_set_header_owner(leaf, objectid);
root->node = leaf;
- write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(leaf),
+ write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(),
BTRFS_FSID_SIZE);
write_extent_buffer(leaf, fs_info->chunk_tree_uuid,
btrfs_header_chunk_tree_uuid(leaf),
@@ -1299,8 +1345,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
btrfs_mark_buffer_dirty(leaf);
root->commit_root = btrfs_root_node(root);
- root->track_dirty = 1;
-
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
root->root_item.flags = 0;
root->root_item.byte_limit = 0;
@@ -1329,6 +1374,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
fail:
if (leaf) {
btrfs_tree_unlock(leaf);
+ free_extent_buffer(root->commit_root);
free_extent_buffer(leaf);
}
kfree(root);
@@ -1354,13 +1400,15 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
root->root_key.type = BTRFS_ROOT_ITEM_KEY;
root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
+
/*
+ * DON'T set REF_COWS for log trees
+ *
* log trees do not get reference counted because they go away
* before a real commit is actually done. They do store pointers
* to file data extents, and those reference counts still get
* updated (along with back refs to the log tree).
*/
- root->ref_cows = 0;
leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
BTRFS_TREE_LOG_OBJECTID, NULL,
@@ -1378,7 +1426,7 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
root->node = leaf;
write_extent_buffer(root->node, root->fs_info->fsid,
- btrfs_header_fsid(root->node), BTRFS_FSID_SIZE);
+ btrfs_header_fsid(), BTRFS_FSID_SIZE);
btrfs_mark_buffer_dirty(root->node);
btrfs_tree_unlock(root->node);
return root;
@@ -1422,6 +1470,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
WARN_ON(root->log_root);
root->log_root = log_root;
root->log_transid = 0;
+ root->log_transid_committed = -1;
root->last_log_commit = 0;
return 0;
}
@@ -1493,7 +1542,7 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
return root;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
- root->ref_cows = 1;
+ set_bit(BTRFS_ROOT_REF_COWS, &root->state);
btrfs_check_and_init_root_item(&root->root_item);
}
@@ -1503,6 +1552,7 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
int btrfs_init_fs_root(struct btrfs_root *root)
{
int ret;
+ struct btrfs_subvolume_writers *writers;
root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
@@ -1512,15 +1562,24 @@ int btrfs_init_fs_root(struct btrfs_root *root)
goto fail;
}
+ writers = btrfs_alloc_subvolume_writers();
+ if (IS_ERR(writers)) {
+ ret = PTR_ERR(writers);
+ goto fail;
+ }
+ root->subv_writers = writers;
+
btrfs_init_free_ino_ctl(root);
- mutex_init(&root->fs_commit_mutex);
spin_lock_init(&root->cache_lock);
init_waitqueue_head(&root->cache_wait);
ret = get_anon_bdev(&root->anon_dev);
if (ret)
- goto fail;
+ goto free_writers;
return 0;
+
+free_writers:
+ btrfs_free_subvolume_writers(root->subv_writers);
fail:
kfree(root->free_ino_ctl);
kfree(root->free_ino_pinned);
@@ -1553,15 +1612,16 @@ int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
(unsigned long)root->root_key.objectid,
root);
if (ret == 0)
- root->in_radix = 1;
+ set_bit(BTRFS_ROOT_IN_RADIX, &root->state);
spin_unlock(&fs_info->fs_roots_radix_lock);
radix_tree_preload_end();
return ret;
}
-struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
- struct btrfs_key *location)
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+ struct btrfs_key *location,
+ bool check_ref)
{
struct btrfs_root *root;
int ret;
@@ -1585,7 +1645,7 @@ struct btrfs_root *btrfs_read_fs_root_no_name(struct btrfs_fs_info *fs_info,
again:
root = btrfs_lookup_fs_root(fs_info, location->objectid);
if (root) {
- if (btrfs_root_refs(&root->root_item) == 0)
+ if (check_ref && btrfs_root_refs(&root->root_item) == 0)
return ERR_PTR(-ENOENT);
return root;
}
@@ -1594,7 +1654,7 @@ again:
if (IS_ERR(root))
return root;
- if (btrfs_root_refs(&root->root_item) == 0) {
+ if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
ret = -ENOENT;
goto fail;
}
@@ -1603,11 +1663,12 @@ again:
if (ret)
goto fail;
- ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
+ ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
+ location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
if (ret < 0)
goto fail;
if (ret == 0)
- root->orphan_item_inserted = 1;
+ set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
ret = btrfs_insert_fs_root(fs_info, root);
if (ret) {
@@ -1671,18 +1732,16 @@ static void end_workqueue_fn(struct btrfs_work *work)
{
struct bio *bio;
struct end_io_wq *end_io_wq;
- struct btrfs_fs_info *fs_info;
int error;
end_io_wq = container_of(work, struct end_io_wq, work);
bio = end_io_wq->bio;
- fs_info = end_io_wq->info;
error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kfree(end_io_wq);
- bio_endio(bio, error);
+ bio_endio_nodec(bio, error);
}
static int cleaner_kthread(void *arg)
@@ -1778,6 +1837,9 @@ sleep:
wake_up_process(root->fs_info->cleaner_kthread);
mutex_unlock(&root->fs_info->transaction_kthread_mutex);
+ if (unlikely(test_bit(BTRFS_FS_STATE_ERROR,
+ &root->fs_info->fs_state)))
+ btrfs_cleanup_transaction(root);
if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop() &&
@@ -1992,72 +2054,50 @@ static noinline int next_root_backup(struct btrfs_fs_info *info,
/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
- btrfs_stop_workers(&fs_info->generic_worker);
- btrfs_stop_workers(&fs_info->fixup_workers);
- btrfs_stop_workers(&fs_info->delalloc_workers);
- btrfs_stop_workers(&fs_info->workers);
- btrfs_stop_workers(&fs_info->endio_workers);
- btrfs_stop_workers(&fs_info->endio_meta_workers);
- btrfs_stop_workers(&fs_info->endio_raid56_workers);
- btrfs_stop_workers(&fs_info->rmw_workers);
- btrfs_stop_workers(&fs_info->endio_meta_write_workers);
- btrfs_stop_workers(&fs_info->endio_write_workers);
- btrfs_stop_workers(&fs_info->endio_freespace_worker);
- btrfs_stop_workers(&fs_info->submit_workers);
- btrfs_stop_workers(&fs_info->delayed_workers);
- btrfs_stop_workers(&fs_info->caching_workers);
- btrfs_stop_workers(&fs_info->readahead_workers);
- btrfs_stop_workers(&fs_info->flush_workers);
- btrfs_stop_workers(&fs_info->qgroup_rescan_workers);
+ btrfs_destroy_workqueue(fs_info->fixup_workers);
+ btrfs_destroy_workqueue(fs_info->delalloc_workers);
+ btrfs_destroy_workqueue(fs_info->workers);
+ btrfs_destroy_workqueue(fs_info->endio_workers);
+ btrfs_destroy_workqueue(fs_info->endio_meta_workers);
+ btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+ btrfs_destroy_workqueue(fs_info->rmw_workers);
+ btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
+ btrfs_destroy_workqueue(fs_info->endio_write_workers);
+ btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
+ btrfs_destroy_workqueue(fs_info->submit_workers);
+ btrfs_destroy_workqueue(fs_info->delayed_workers);
+ btrfs_destroy_workqueue(fs_info->caching_workers);
+ btrfs_destroy_workqueue(fs_info->readahead_workers);
+ btrfs_destroy_workqueue(fs_info->flush_workers);
+ btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
+ btrfs_destroy_workqueue(fs_info->extent_workers);
+}
+
+static void free_root_extent_buffers(struct btrfs_root *root)
+{
+ if (root) {
+ free_extent_buffer(root->node);
+ free_extent_buffer(root->commit_root);
+ root->node = NULL;
+ root->commit_root = NULL;
+ }
}
/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
{
- free_extent_buffer(info->tree_root->node);
- free_extent_buffer(info->tree_root->commit_root);
- info->tree_root->node = NULL;
- info->tree_root->commit_root = NULL;
-
- if (info->dev_root) {
- free_extent_buffer(info->dev_root->node);
- free_extent_buffer(info->dev_root->commit_root);
- info->dev_root->node = NULL;
- info->dev_root->commit_root = NULL;
- }
- if (info->extent_root) {
- free_extent_buffer(info->extent_root->node);
- free_extent_buffer(info->extent_root->commit_root);
- info->extent_root->node = NULL;
- info->extent_root->commit_root = NULL;
- }
- if (info->csum_root) {
- free_extent_buffer(info->csum_root->node);
- free_extent_buffer(info->csum_root->commit_root);
- info->csum_root->node = NULL;
- info->csum_root->commit_root = NULL;
- }
- if (info->quota_root) {
- free_extent_buffer(info->quota_root->node);
- free_extent_buffer(info->quota_root->commit_root);
- info->quota_root->node = NULL;
- info->quota_root->commit_root = NULL;
- }
- if (info->uuid_root) {
- free_extent_buffer(info->uuid_root->node);
- free_extent_buffer(info->uuid_root->commit_root);
- info->uuid_root->node = NULL;
- info->uuid_root->commit_root = NULL;
- }
- if (chunk_root) {
- free_extent_buffer(info->chunk_root->node);
- free_extent_buffer(info->chunk_root->commit_root);
- info->chunk_root->node = NULL;
- info->chunk_root->commit_root = NULL;
- }
+ free_root_extent_buffers(info->tree_root);
+
+ free_root_extent_buffers(info->dev_root);
+ free_root_extent_buffers(info->extent_root);
+ free_root_extent_buffers(info->csum_root);
+ free_root_extent_buffers(info->quota_root);
+ free_root_extent_buffers(info->uuid_root);
+ if (chunk_root)
+ free_root_extent_buffers(info->chunk_root);
}
-static void del_fs_roots(struct btrfs_fs_info *fs_info)
+void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
int ret;
struct btrfs_root *gang[8];
@@ -2068,7 +2108,7 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
struct btrfs_root, root_list);
list_del(&gang[0]->root_list);
- if (gang[0]->in_radix) {
+ if (test_bit(BTRFS_ROOT_IN_RADIX, &gang[0]->state)) {
btrfs_drop_and_free_fs_root(fs_info, gang[0]);
} else {
free_extent_buffer(gang[0]->node);
@@ -2086,6 +2126,12 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
+
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ btrfs_free_log_root_tree(NULL, fs_info);
+ btrfs_destroy_pinned_extent(fs_info->tree_root,
+ fs_info->pinned_extents);
+ }
}
int open_ctree(struct super_block *sb,
@@ -2115,6 +2161,8 @@ int open_ctree(struct super_block *sb,
int err = -EINVAL;
int num_backups_tried = 0;
int backup_index = 0;
+ int max_active;
+ int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
bool create_uuid_tree;
bool check_uuid_tree;
@@ -2151,15 +2199,22 @@ int open_ctree(struct super_block *sb,
goto fail_dirty_metadata_bytes;
}
+ ret = percpu_counter_init(&fs_info->bio_counter, 0);
+ if (ret) {
+ err = ret;
+ goto fail_delalloc_bytes;
+ }
+
fs_info->btree_inode = new_inode(sb);
if (!fs_info->btree_inode) {
err = -ENOMEM;
- goto fail_delalloc_bytes;
+ goto fail_bio_counter;
}
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
@@ -2173,8 +2228,11 @@ int open_ctree(struct super_block *sb,
spin_lock_init(&fs_info->free_chunk_lock);
spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
+ spin_lock_init(&fs_info->qgroup_op_lock);
+ spin_lock_init(&fs_info->buffer_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
+ mutex_init(&fs_info->delalloc_root_mutex);
seqlock_init(&fs_info->profiles_lock);
init_completion(&fs_info->kobj_unregister);
@@ -2196,6 +2254,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->async_submit_draining, 0);
atomic_set(&fs_info->nr_async_bios, 0);
atomic_set(&fs_info->defrag_running, 0);
+ atomic_set(&fs_info->qgroup_op_seq, 0);
atomic64_set(&fs_info->tree_mod_seq, 0);
fs_info->sb = sb;
fs_info->max_inline = 8192 * 1024;
@@ -2204,7 +2263,7 @@ int open_ctree(struct super_block *sb,
fs_info->free_chunk_space = 0;
fs_info->tree_mod_log = RB_ROOT;
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
-
+ fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64);
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
spin_lock_init(&fs_info->reada_lock);
@@ -2227,8 +2286,8 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->scrub_pause_req, 0);
atomic_set(&fs_info->scrubs_paused, 0);
atomic_set(&fs_info->scrub_cancel_req, 0);
+ init_waitqueue_head(&fs_info->replace_wait);
init_waitqueue_head(&fs_info->scrub_pause_wait);
- init_rwsem(&fs_info->scrub_super_lock);
fs_info->scrub_workers_refcnt = 0;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
fs_info->check_integrity_print_mask = 0;
@@ -2241,6 +2300,7 @@ int open_ctree(struct super_block *sb,
atomic_set(&fs_info->balance_cancel_req, 0);
fs_info->balance_ctl = NULL;
init_waitqueue_head(&fs_info->balance_wait_q);
+ btrfs_init_async_reclaim_work(&fs_info->async_reclaim_work);
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
@@ -2270,7 +2330,7 @@ int open_ctree(struct super_block *sb,
sizeof(struct btrfs_key));
set_bit(BTRFS_INODE_DUMMY,
&BTRFS_I(fs_info->btree_inode)->runtime_flags);
- insert_inode_hash(fs_info->btree_inode);
+ btrfs_insert_inode_hash(fs_info->btree_inode);
spin_lock_init(&fs_info->block_group_cache_lock);
fs_info->block_group_cache_tree = RB_ROOT;
@@ -2291,7 +2351,7 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->transaction_kthread_mutex);
mutex_init(&fs_info->cleaner_mutex);
mutex_init(&fs_info->volume_mutex);
- init_rwsem(&fs_info->extent_commit_sem);
+ init_rwsem(&fs_info->commit_root_sem);
init_rwsem(&fs_info->cleanup_work_sem);
init_rwsem(&fs_info->subvol_sem);
sema_init(&fs_info->uuid_tree_rescan_sem, 1);
@@ -2304,6 +2364,7 @@ int open_ctree(struct super_block *sb,
spin_lock_init(&fs_info->qgroup_lock);
mutex_init(&fs_info->qgroup_ioctl_lock);
fs_info->qgroup_tree = RB_ROOT;
+ fs_info->qgroup_op_tree = RB_ROOT;
INIT_LIST_HEAD(&fs_info->dirty_qgroups);
fs_info->qgroup_seq = 1;
fs_info->quota_enabled = 0;
@@ -2344,7 +2405,7 @@ int open_ctree(struct super_block *sb,
* 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");
+ printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
err = -EINVAL;
goto fail_alloc;
}
@@ -2363,7 +2424,7 @@ 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");
+ printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
err = -EINVAL;
goto fail_alloc;
}
@@ -2428,7 +2489,7 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_ERR "btrfs: has skinny extents\n");
+ printk(KERN_ERR "BTRFS: has skinny extents\n");
/*
* flag our filesystem as having big metadata blocks if
@@ -2436,7 +2497,7 @@ int open_ctree(struct super_block *sb,
*/
if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "btrfs flagging fs with big metadata feature\n");
+ printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
@@ -2453,7 +2514,7 @@ int open_ctree(struct super_block *sb,
*/
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(sectorsize != leafsize)) {
- printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes "
+ printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
"are not allowed for mixed block groups on %s\n",
sb->s_id);
goto fail_alloc;
@@ -2475,104 +2536,73 @@ int open_ctree(struct super_block *sb,
goto fail_alloc;
}
- btrfs_init_workers(&fs_info->generic_worker,
- "genwork", 1, NULL);
-
- btrfs_init_workers(&fs_info->workers, "worker",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
+ max_active = fs_info->thread_pool_size;
- btrfs_init_workers(&fs_info->delalloc_workers, "delalloc",
- fs_info->thread_pool_size, NULL);
+ fs_info->workers =
+ btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
+ max_active, 16);
- btrfs_init_workers(&fs_info->flush_workers, "flush_delalloc",
- fs_info->thread_pool_size, NULL);
+ fs_info->delalloc_workers =
+ btrfs_alloc_workqueue("delalloc", flags, max_active, 2);
- btrfs_init_workers(&fs_info->submit_workers, "submit",
- min_t(u64, fs_devices->num_devices,
- fs_info->thread_pool_size), NULL);
+ fs_info->flush_workers =
+ btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);
- btrfs_init_workers(&fs_info->caching_workers, "cache",
- fs_info->thread_pool_size, NULL);
+ fs_info->caching_workers =
+ btrfs_alloc_workqueue("cache", flags, max_active, 0);
- /* a higher idle thresh on the submit workers makes it much more
+ /*
+ * a higher idle thresh on the submit workers makes it much more
* likely that bios will be send down in a sane order to the
* devices
*/
- fs_info->submit_workers.idle_thresh = 64;
-
- fs_info->workers.idle_thresh = 16;
- fs_info->workers.ordered = 1;
-
- fs_info->delalloc_workers.idle_thresh = 2;
- fs_info->delalloc_workers.ordered = 1;
-
- btrfs_init_workers(&fs_info->fixup_workers, "fixup", 1,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_workers, "endio",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_meta_workers, "endio-meta",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_meta_write_workers,
- "endio-meta-write", fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_raid56_workers,
- "endio-raid56", fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->rmw_workers,
- "rmw", fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_write_workers, "endio-write",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->endio_freespace_worker, "freespace-write",
- 1, &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->delayed_workers, "delayed-meta",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->readahead_workers, "readahead",
- fs_info->thread_pool_size,
- &fs_info->generic_worker);
- btrfs_init_workers(&fs_info->qgroup_rescan_workers, "qgroup-rescan", 1,
- &fs_info->generic_worker);
+ fs_info->submit_workers =
+ btrfs_alloc_workqueue("submit", flags,
+ min_t(u64, fs_devices->num_devices,
+ max_active), 64);
+
+ fs_info->fixup_workers =
+ btrfs_alloc_workqueue("fixup", flags, 1, 0);
/*
* endios are largely parallel and should have a very
* low idle thresh
*/
- fs_info->endio_workers.idle_thresh = 4;
- fs_info->endio_meta_workers.idle_thresh = 4;
- fs_info->endio_raid56_workers.idle_thresh = 4;
- fs_info->rmw_workers.idle_thresh = 2;
-
- fs_info->endio_write_workers.idle_thresh = 2;
- fs_info->endio_meta_write_workers.idle_thresh = 2;
- fs_info->readahead_workers.idle_thresh = 2;
-
- /*
- * btrfs_start_workers can really only fail because of ENOMEM so just
- * return -ENOMEM if any of these fail.
- */
- ret = btrfs_start_workers(&fs_info->workers);
- ret |= btrfs_start_workers(&fs_info->generic_worker);
- ret |= btrfs_start_workers(&fs_info->submit_workers);
- ret |= btrfs_start_workers(&fs_info->delalloc_workers);
- ret |= btrfs_start_workers(&fs_info->fixup_workers);
- ret |= btrfs_start_workers(&fs_info->endio_workers);
- ret |= btrfs_start_workers(&fs_info->endio_meta_workers);
- ret |= btrfs_start_workers(&fs_info->rmw_workers);
- ret |= btrfs_start_workers(&fs_info->endio_raid56_workers);
- ret |= btrfs_start_workers(&fs_info->endio_meta_write_workers);
- ret |= btrfs_start_workers(&fs_info->endio_write_workers);
- ret |= btrfs_start_workers(&fs_info->endio_freespace_worker);
- ret |= btrfs_start_workers(&fs_info->delayed_workers);
- ret |= btrfs_start_workers(&fs_info->caching_workers);
- ret |= btrfs_start_workers(&fs_info->readahead_workers);
- ret |= btrfs_start_workers(&fs_info->flush_workers);
- ret |= btrfs_start_workers(&fs_info->qgroup_rescan_workers);
- if (ret) {
+ fs_info->endio_workers =
+ btrfs_alloc_workqueue("endio", flags, max_active, 4);
+ fs_info->endio_meta_workers =
+ btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
+ fs_info->endio_meta_write_workers =
+ btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
+ fs_info->endio_raid56_workers =
+ btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+ fs_info->rmw_workers =
+ btrfs_alloc_workqueue("rmw", flags, max_active, 2);
+ fs_info->endio_write_workers =
+ btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
+ fs_info->endio_freespace_worker =
+ btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
+ fs_info->delayed_workers =
+ btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
+ fs_info->readahead_workers =
+ btrfs_alloc_workqueue("readahead", flags, max_active, 2);
+ fs_info->qgroup_rescan_workers =
+ btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);
+ fs_info->extent_workers =
+ btrfs_alloc_workqueue("extent-refs", flags,
+ min_t(u64, fs_devices->num_devices,
+ max_active), 8);
+
+ if (!(fs_info->workers && fs_info->delalloc_workers &&
+ fs_info->submit_workers && fs_info->flush_workers &&
+ fs_info->endio_workers && fs_info->endio_meta_workers &&
+ fs_info->endio_meta_write_workers &&
+ fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
+ fs_info->endio_freespace_worker && fs_info->rmw_workers &&
+ fs_info->caching_workers && fs_info->readahead_workers &&
+ fs_info->fixup_workers && fs_info->delayed_workers &&
+ fs_info->fixup_workers && fs_info->extent_workers &&
+ fs_info->qgroup_rescan_workers)) {
err = -ENOMEM;
goto fail_sb_buffer;
}
@@ -2590,12 +2620,12 @@ int open_ctree(struct super_block *sb,
sb->s_blocksize_bits = blksize_bits(sectorsize);
if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
+ printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
if (sectorsize != PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
"found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
@@ -2604,7 +2634,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read the system "
+ printk(KERN_WARNING "BTRFS: failed to read the system "
"array on %s\n", sb->s_id);
goto fail_sb_buffer;
}
@@ -2621,7 +2651,7 @@ int open_ctree(struct super_block *sb,
blocksize, generation);
if (!chunk_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2633,7 +2663,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2645,7 +2675,7 @@ int open_ctree(struct super_block *sb,
btrfs_close_extra_devices(fs_info, fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_CRIT "btrfs: failed to read devices on %s\n",
+ printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2660,7 +2690,7 @@ retry_root_backup:
blocksize, generation);
if (!tree_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read tree root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
sb->s_id);
goto recovery_tree_root;
@@ -2668,6 +2698,7 @@ retry_root_backup:
btrfs_set_root_node(&tree_root->root_item, tree_root->node);
tree_root->commit_root = btrfs_root_node(tree_root);
+ btrfs_set_root_refs(&tree_root->root_item, 1);
location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
location.type = BTRFS_ROOT_ITEM_KEY;
@@ -2678,7 +2709,7 @@ retry_root_backup:
ret = PTR_ERR(extent_root);
goto recovery_tree_root;
}
- extent_root->track_dirty = 1;
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &extent_root->state);
fs_info->extent_root = extent_root;
location.objectid = BTRFS_DEV_TREE_OBJECTID;
@@ -2687,7 +2718,7 @@ retry_root_backup:
ret = PTR_ERR(dev_root);
goto recovery_tree_root;
}
- dev_root->track_dirty = 1;
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &dev_root->state);
fs_info->dev_root = dev_root;
btrfs_init_devices_late(fs_info);
@@ -2697,13 +2728,13 @@ retry_root_backup:
ret = PTR_ERR(csum_root);
goto recovery_tree_root;
}
- csum_root->track_dirty = 1;
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &csum_root->state);
fs_info->csum_root = csum_root;
location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
quota_root = btrfs_read_tree_root(tree_root, &location);
if (!IS_ERR(quota_root)) {
- quota_root->track_dirty = 1;
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &quota_root->state);
fs_info->quota_enabled = 1;
fs_info->pending_quota_state = 1;
fs_info->quota_root = quota_root;
@@ -2718,7 +2749,7 @@ retry_root_backup:
create_uuid_tree = true;
check_uuid_tree = false;
} else {
- uuid_root->track_dirty = 1;
+ set_bit(BTRFS_ROOT_TRACK_DIRTY, &uuid_root->state);
fs_info->uuid_root = uuid_root;
create_uuid_tree = false;
check_uuid_tree =
@@ -2730,50 +2761,56 @@ retry_root_backup:
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to recover balance\n");
+ printk(KERN_WARNING "BTRFS: failed to recover balance\n");
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n",
+ printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
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);
+ pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
goto fail_block_groups;
}
btrfs_close_extra_devices(fs_info, fs_devices, 1);
- ret = btrfs_init_space_info(fs_info);
+ ret = btrfs_sysfs_add_one(fs_info);
if (ret) {
- printk(KERN_ERR "Failed to initial space info: %d\n", ret);
+ pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
goto fail_block_groups;
}
+ ret = btrfs_init_space_info(fs_info);
+ if (ret) {
+ printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+ goto fail_sysfs;
+ }
+
ret = btrfs_read_block_groups(extent_root);
if (ret) {
- printk(KERN_ERR "Failed to read block groups: %d\n", ret);
- goto fail_block_groups;
+ printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- printk(KERN_WARNING
- "Btrfs: too many missing devices, writeable mount is not allowed\n");
- goto fail_block_groups;
+ printk(KERN_WARNING "BTRFS: "
+ "too many missing devices, writeable mount is not allowed\n");
+ goto fail_sysfs;
}
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
if (IS_ERR(fs_info->cleaner_kthread))
- goto fail_block_groups;
+ goto fail_sysfs;
fs_info->transaction_kthread = kthread_run(transaction_kthread,
tree_root,
@@ -2784,11 +2821,15 @@ retry_root_backup:
if (!btrfs_test_opt(tree_root, SSD) &&
!btrfs_test_opt(tree_root, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD "
+ printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
"mode\n");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
+ /* Set the real inode map cache flag */
+ if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
+ btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);
+
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
ret = btrfsic_mount(tree_root, fs_devices,
@@ -2797,7 +2838,7 @@ retry_root_backup:
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "btrfs: failed to initialize"
+ printk(KERN_WARNING "BTRFS: failed to initialize"
" integrity check module %s\n", sb->s_id);
}
#endif
@@ -2810,7 +2851,7 @@ retry_root_backup:
u64 bytenr = btrfs_super_log_root(disk_super);
if (fs_devices->rw_devices == 0) {
- printk(KERN_WARNING "Btrfs log replay required "
+ printk(KERN_WARNING "BTRFS: log replay required "
"on RO media\n");
err = -EIO;
goto fail_qgroup;
@@ -2833,10 +2874,10 @@ retry_root_backup:
generation + 1);
if (!log_tree_root->node ||
!extent_buffer_uptodate(log_tree_root->node)) {
- printk(KERN_ERR "btrfs: failed to read log tree\n");
+ printk(KERN_ERR "BTRFS: failed to read log tree\n");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
- goto fail_trans_kthread;
+ goto fail_qgroup;
}
/* returns with log_tree_root freed on success */
ret = btrfs_recover_log_trees(log_tree_root);
@@ -2845,29 +2886,31 @@ retry_root_backup:
"Failed to recover log tree");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
- goto fail_trans_kthread;
+ goto fail_qgroup;
}
if (sb->s_flags & MS_RDONLY) {
ret = btrfs_commit_super(tree_root);
if (ret)
- goto fail_trans_kthread;
+ goto fail_qgroup;
}
}
ret = btrfs_find_orphan_roots(tree_root);
if (ret)
- goto fail_trans_kthread;
+ goto fail_qgroup;
if (!(sb->s_flags & MS_RDONLY)) {
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
- goto fail_trans_kthread;
+ goto fail_qgroup;
+ mutex_lock(&fs_info->cleaner_mutex);
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: failed to recover relocation\n");
err = -EINVAL;
goto fail_qgroup;
}
@@ -2897,14 +2940,14 @@ retry_root_backup:
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to resume balance\n");
+ printk(KERN_WARNING "BTRFS: failed to resume balance\n");
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");
+ pr_warn("BTRFS: failed to resume dev_replace\n");
close_ctree(tree_root);
return ret;
}
@@ -2912,20 +2955,20 @@ retry_root_backup:
btrfs_qgroup_rescan_resume(fs_info);
if (create_uuid_tree) {
- pr_info("btrfs: creating UUID tree\n");
+ pr_info("BTRFS: creating UUID tree\n");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to create the UUID tree %d\n",
+ pr_warn("BTRFS: failed to create the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
}
} else if (check_uuid_tree ||
btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
- pr_info("btrfs: checking UUID tree\n");
+ pr_info("BTRFS: checking UUID tree\n");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to check the UUID tree %d\n",
+ pr_warn("BTRFS: failed to check the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
@@ -2941,7 +2984,7 @@ fail_qgroup:
fail_trans_kthread:
kthread_stop(fs_info->transaction_kthread);
btrfs_cleanup_transaction(fs_info->tree_root);
- del_fs_roots(fs_info);
+ btrfs_free_fs_roots(fs_info);
fail_cleaner:
kthread_stop(fs_info->cleaner_kthread);
@@ -2951,6 +2994,9 @@ fail_cleaner:
*/
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
+fail_sysfs:
+ btrfs_sysfs_remove_one(fs_info);
+
fail_block_groups:
btrfs_put_block_group_cache(fs_info);
btrfs_free_block_groups(fs_info);
@@ -2966,6 +3012,8 @@ fail_iput:
btrfs_mapping_tree_free(&fs_info->mapping_tree);
iput(fs_info->btree_inode);
+fail_bio_counter:
+ percpu_counter_destroy(&fs_info->bio_counter);
fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_dirty_metadata_bytes:
@@ -3006,7 +3054,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
struct btrfs_device *device = (struct btrfs_device *)
bh->b_private;
- printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to "
+ printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to "
"I/O error on %s\n",
rcu_str_deref(device->name));
/* note, we dont' set_buffer_write_io_error because we have
@@ -3125,7 +3173,7 @@ static int write_dev_supers(struct btrfs_device *device,
bh = __getblk(device->bdev, bytenr / 4096,
BTRFS_SUPER_INFO_SIZE);
if (!bh) {
- printk(KERN_ERR "btrfs: couldn't get super "
+ printk(KERN_ERR "BTRFS: couldn't get super "
"buffer head for bytenr %Lu\n", bytenr);
errors++;
continue;
@@ -3146,7 +3194,10 @@ static int write_dev_supers(struct btrfs_device *device,
* we fua the first super. The others we allow
* to go down lazy.
*/
- ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ if (i == 0)
+ ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ else
+ ret = btrfsic_submit_bh(WRITE_SYNC, bh);
if (ret)
errors++;
}
@@ -3192,7 +3243,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
wait_for_completion(&device->flush_wait);
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
- printk_in_rcu("btrfs: disabling barriers on dev %s\n",
+ printk_in_rcu("BTRFS: disabling barriers on dev %s\n",
rcu_str_deref(device->name));
device->nobarriers = 1;
} else if (!bio_flagged(bio, BIO_UPTODATE)) {
@@ -3244,6 +3295,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
/* send down all the barriers */
head = &info->fs_devices->devices;
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_send++;
continue;
@@ -3258,6 +3311,8 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
/* wait for all the barriers */
list_for_each_entry_rcu(dev, head, dev_list) {
+ if (dev->missing)
+ continue;
if (!dev->bdev) {
errors_wait++;
continue;
@@ -3413,8 +3468,9 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
total_errors++;
}
if (total_errors > max_errors) {
- printk(KERN_ERR "btrfs: %d errors while writing supers\n",
+ btrfs_err(root->fs_info, "%d errors while writing supers",
total_errors);
+ mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
/* FUA is masked off if unsupported and can't be the reason */
btrfs_error(root->fs_info, -EIO,
@@ -3445,10 +3501,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
int write_ctree_super(struct btrfs_trans_handle *trans,
struct btrfs_root *root, int max_mirrors)
{
- int ret;
-
- ret = write_all_supers(root, max_mirrors);
- return ret;
+ return write_all_supers(root, max_mirrors);
}
/* Drop a fs root from the radix tree and free it. */
@@ -3463,13 +3516,13 @@ 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);
- btrfs_free_log_root_tree(NULL, fs_info);
- }
- __btrfs_remove_free_space_cache(root->free_ino_pinned);
- __btrfs_remove_free_space_cache(root->free_ino_ctl);
+ if (root->free_ino_pinned)
+ __btrfs_remove_free_space_cache(root->free_ino_pinned);
+ if (root->free_ino_ctl)
+ __btrfs_remove_free_space_cache(root->free_ino_ctl);
free_fs_root(root);
}
@@ -3481,6 +3534,8 @@ static void free_fs_root(struct btrfs_root *root)
root->orphan_block_rsv = NULL;
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
+ if (root->subv_writers)
+ btrfs_free_subvolume_writers(root->subv_writers);
free_extent_buffer(root->node);
free_extent_buffer(root->commit_root);
kfree(root->free_ino_ctl);
@@ -3498,34 +3553,56 @@ int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
u64 root_objectid = 0;
struct btrfs_root *gang[8];
- int i;
- int ret;
+ int i = 0;
+ int err = 0;
+ unsigned int ret = 0;
+ int index;
while (1) {
+ index = srcu_read_lock(&fs_info->subvol_srcu);
ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
(void **)gang, root_objectid,
ARRAY_SIZE(gang));
- if (!ret)
+ if (!ret) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
break;
-
+ }
root_objectid = gang[ret - 1]->root_key.objectid + 1;
+
for (i = 0; i < ret; i++) {
- int err;
+ /* Avoid to grab roots in dead_roots */
+ if (btrfs_root_refs(&gang[i]->root_item) == 0) {
+ gang[i] = NULL;
+ continue;
+ }
+ /* grab all the search result for later use */
+ gang[i] = btrfs_grab_fs_root(gang[i]);
+ }
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ for (i = 0; i < ret; i++) {
+ if (!gang[i])
+ continue;
root_objectid = gang[i]->root_key.objectid;
err = btrfs_orphan_cleanup(gang[i]);
if (err)
- return err;
+ break;
+ btrfs_put_fs_root(gang[i]);
}
root_objectid++;
}
- return 0;
+
+ /* release the uncleaned roots due to error */
+ for (; i < ret; i++) {
+ if (gang[i])
+ btrfs_put_fs_root(gang[i]);
+ }
+ return err;
}
int btrfs_commit_super(struct btrfs_root *root)
{
struct btrfs_trans_handle *trans;
- int ret;
mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_run_delayed_iputs(root);
@@ -3539,25 +3616,7 @@ int btrfs_commit_super(struct btrfs_root *root)
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
return PTR_ERR(trans);
- ret = btrfs_commit_transaction(trans, root);
- if (ret)
- return ret;
- /* run commit again to drop the original snapshot */
- trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
- ret = btrfs_commit_transaction(trans, root);
- if (ret)
- return ret;
- ret = btrfs_write_and_wait_transaction(NULL, root);
- if (ret) {
- btrfs_error(root->fs_info, ret,
- "Failed to sync btree inode to disk.");
- return ret;
- }
-
- ret = write_ctree_super(NULL, root, 0);
- return ret;
+ return btrfs_commit_transaction(trans, root);
}
int close_ctree(struct btrfs_root *root)
@@ -3587,17 +3646,17 @@ int close_ctree(struct btrfs_root *root)
/* clear out the rbtree of defraggable inodes */
btrfs_cleanup_defrag_inodes(fs_info);
+ cancel_work_sync(&fs_info->async_reclaim_work);
+
if (!(fs_info->sb->s_flags & MS_RDONLY)) {
ret = btrfs_commit_super(root);
if (ret)
- printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+ btrfs_err(root->fs_info, "commit super ret %d", ret);
}
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_error_commit_super(root);
- btrfs_put_block_group_cache(fs_info);
-
kthread_stop(fs_info->transaction_kthread);
kthread_stop(fs_info->cleaner_kthread);
@@ -3607,16 +3666,25 @@ int close_ctree(struct btrfs_root *root)
btrfs_free_qgroup_config(root->fs_info);
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
- printk(KERN_INFO "btrfs: at unmount delalloc count %lld\n",
+ btrfs_info(root->fs_info, "at unmount delalloc count %lld",
percpu_counter_sum(&fs_info->delalloc_bytes));
}
+ btrfs_sysfs_remove_one(fs_info);
+
+ btrfs_free_fs_roots(fs_info);
+
+ btrfs_put_block_group_cache(fs_info);
+
btrfs_free_block_groups(fs_info);
+ /*
+ * we must make sure there is not any read request to
+ * submit after we stopping all workers.
+ */
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
btrfs_stop_all_workers(fs_info);
- del_fs_roots(fs_info);
-
free_root_pointers(fs_info, 1);
iput(fs_info->btree_inode);
@@ -3631,6 +3699,7 @@ int close_ctree(struct btrfs_root *root)
percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
percpu_counter_destroy(&fs_info->delalloc_bytes);
+ percpu_counter_destroy(&fs_info->bio_counter);
bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
@@ -3666,10 +3735,20 @@ int btrfs_set_buffer_uptodate(struct extent_buffer *buf)
void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
{
- struct btrfs_root *root = BTRFS_I(buf->pages[0]->mapping->host)->root;
+ struct btrfs_root *root;
u64 transid = btrfs_header_generation(buf);
int was_dirty;
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ /*
+ * This is a fast path so only do this check if we have sanity tests
+ * enabled. Normal people shouldn't be marking dummy buffers as dirty
+ * outside of the sanity tests.
+ */
+ if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
+ return;
+#endif
+ 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, "
@@ -3680,6 +3759,12 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
__percpu_counter_add(&root->fs_info->dirty_metadata_bytes,
buf->len,
root->fs_info->dirty_metadata_batch);
+#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
+ btrfs_print_leaf(root, buf);
+ ASSERT(0);
+ }
+#endif
}
static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
@@ -3799,11 +3884,14 @@ static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
while (!list_empty(&splice)) {
root = list_first_entry(&splice, struct btrfs_root,
ordered_root);
- list_del_init(&root->ordered_root);
+ list_move_tail(&root->ordered_root,
+ &fs_info->ordered_roots);
+ spin_unlock(&fs_info->ordered_root_lock);
btrfs_destroy_ordered_extents(root);
- cond_resched_lock(&fs_info->ordered_root_lock);
+ cond_resched();
+ spin_lock(&fs_info->ordered_root_lock);
}
spin_unlock(&fs_info->ordered_root_lock);
}
@@ -3819,55 +3907,54 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
delayed_refs = &trans->delayed_refs;
spin_lock(&delayed_refs->lock);
- if (delayed_refs->num_entries == 0) {
+ if (atomic_read(&delayed_refs->num_entries) == 0) {
spin_unlock(&delayed_refs->lock);
- printk(KERN_INFO "delayed_refs has NO entry\n");
+ btrfs_info(root->fs_info, "delayed_refs has NO entry");
return ret;
}
- while ((node = rb_first(&delayed_refs->root)) != NULL) {
- struct btrfs_delayed_ref_head *head = NULL;
+ while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
+ struct btrfs_delayed_ref_head *head;
bool pin_bytes = false;
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- atomic_set(&ref->refs, 1);
- if (btrfs_delayed_ref_is_head(ref)) {
-
- head = btrfs_delayed_node_to_head(ref);
- if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&ref->refs);
- spin_unlock(&delayed_refs->lock);
-
- /* Need to wait for the delayed ref to run */
- mutex_lock(&head->mutex);
- mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(ref);
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ if (!mutex_trylock(&head->mutex)) {
+ atomic_inc(&head->node.refs);
+ spin_unlock(&delayed_refs->lock);
- spin_lock(&delayed_refs->lock);
- continue;
- }
-
- if (head->must_insert_reserved)
- pin_bytes = true;
- btrfs_free_delayed_extent_op(head->extent_op);
- delayed_refs->num_heads--;
- if (list_empty(&head->cluster))
- delayed_refs->num_heads_ready--;
- list_del_init(&head->cluster);
- }
-
- ref->in_tree = 0;
- rb_erase(&ref->rb_node, &delayed_refs->root);
- delayed_refs->num_entries--;
- spin_unlock(&delayed_refs->lock);
- if (head) {
- if (pin_bytes)
- btrfs_pin_extent(root, ref->bytenr,
- ref->num_bytes, 1);
+ mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref(&head->node);
+ spin_lock(&delayed_refs->lock);
+ continue;
}
- btrfs_put_delayed_ref(ref);
+ spin_lock(&head->lock);
+ while ((node = rb_first(&head->ref_root)) != NULL) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node,
+ rb_node);
+ ref->in_tree = 0;
+ rb_erase(&ref->rb_node, &head->ref_root);
+ atomic_dec(&delayed_refs->num_entries);
+ btrfs_put_delayed_ref(ref);
+ }
+ if (head->must_insert_reserved)
+ pin_bytes = true;
+ btrfs_free_delayed_extent_op(head->extent_op);
+ delayed_refs->num_heads--;
+ if (head->processing == 0)
+ delayed_refs->num_heads_ready--;
+ atomic_dec(&delayed_refs->num_entries);
+ head->node.in_tree = 0;
+ rb_erase(&head->href_node, &delayed_refs->href_root);
+ spin_unlock(&head->lock);
+ spin_unlock(&delayed_refs->lock);
+ mutex_unlock(&head->mutex);
+ if (pin_bytes)
+ btrfs_pin_extent(root, head->node.bytenr,
+ head->node.num_bytes, 1);
+ btrfs_put_delayed_ref(&head->node);
cond_resched();
spin_lock(&delayed_refs->lock);
}
@@ -3877,24 +3964,6 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
return ret;
}
-static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t)
-{
- struct btrfs_pending_snapshot *snapshot;
- struct list_head splice;
-
- INIT_LIST_HEAD(&splice);
-
- list_splice_init(&t->pending_snapshots, &splice);
-
- while (!list_empty(&splice)) {
- snapshot = list_entry(splice.next,
- struct btrfs_pending_snapshot,
- list);
- snapshot->error = -ECANCELED;
- list_del_init(&snapshot->list);
- }
-}
-
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
{
struct btrfs_inode *btrfs_inode;
@@ -4024,15 +4093,13 @@ again:
void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
struct btrfs_root *root)
{
+ btrfs_destroy_ordered_operations(cur_trans, root);
+
btrfs_destroy_delayed_refs(cur_trans, root);
- btrfs_block_rsv_release(root, &root->fs_info->trans_block_rsv,
- cur_trans->dirty_pages.dirty_bytes);
cur_trans->state = TRANS_STATE_COMMIT_START;
wake_up(&root->fs_info->transaction_blocked_wait);
- btrfs_evict_pending_snapshots(cur_trans);
-
cur_trans->state = TRANS_STATE_UNBLOCKED;
wake_up(&root->fs_info->transaction_wait);
@@ -4056,63 +4123,51 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
static int btrfs_cleanup_transaction(struct btrfs_root *root)
{
struct btrfs_transaction *t;
- LIST_HEAD(list);
mutex_lock(&root->fs_info->transaction_kthread_mutex);
spin_lock(&root->fs_info->trans_lock);
- list_splice_init(&root->fs_info->trans_list, &list);
- root->fs_info->running_transaction = NULL;
- spin_unlock(&root->fs_info->trans_lock);
-
- while (!list_empty(&list)) {
- t = list_entry(list.next, struct btrfs_transaction, list);
-
- btrfs_destroy_ordered_operations(t, root);
-
- btrfs_destroy_all_ordered_extents(root->fs_info);
-
- btrfs_destroy_delayed_refs(t, root);
-
- /*
- * FIXME: cleanup wait for commit
- * We needn't acquire the lock here, because we are during
- * the umount, there is no other task which will change it.
- */
- t->state = TRANS_STATE_COMMIT_START;
- smp_mb();
- if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
- wake_up(&root->fs_info->transaction_blocked_wait);
-
- btrfs_evict_pending_snapshots(t);
-
- t->state = TRANS_STATE_UNBLOCKED;
- smp_mb();
- if (waitqueue_active(&root->fs_info->transaction_wait))
- wake_up(&root->fs_info->transaction_wait);
-
- btrfs_destroy_delayed_inodes(root);
- btrfs_assert_delayed_root_empty(root);
-
- btrfs_destroy_all_delalloc_inodes(root->fs_info);
-
- btrfs_destroy_marked_extents(root, &t->dirty_pages,
- EXTENT_DIRTY);
-
- btrfs_destroy_pinned_extent(root,
- root->fs_info->pinned_extents);
-
- t->state = TRANS_STATE_COMPLETED;
- smp_mb();
- if (waitqueue_active(&t->commit_wait))
- wake_up(&t->commit_wait);
+ while (!list_empty(&root->fs_info->trans_list)) {
+ t = list_first_entry(&root->fs_info->trans_list,
+ struct btrfs_transaction, list);
+ if (t->state >= TRANS_STATE_COMMIT_START) {
+ atomic_inc(&t->use_count);
+ spin_unlock(&root->fs_info->trans_lock);
+ btrfs_wait_for_commit(root, t->transid);
+ btrfs_put_transaction(t);
+ spin_lock(&root->fs_info->trans_lock);
+ continue;
+ }
+ if (t == root->fs_info->running_transaction) {
+ t->state = TRANS_STATE_COMMIT_DOING;
+ spin_unlock(&root->fs_info->trans_lock);
+ /*
+ * We wait for 0 num_writers since we don't hold a trans
+ * handle open currently for this transaction.
+ */
+ wait_event(t->writer_wait,
+ atomic_read(&t->num_writers) == 0);
+ } else {
+ spin_unlock(&root->fs_info->trans_lock);
+ }
+ btrfs_cleanup_one_transaction(t, root);
- atomic_set(&t->use_count, 0);
+ spin_lock(&root->fs_info->trans_lock);
+ if (t == root->fs_info->running_transaction)
+ root->fs_info->running_transaction = NULL;
list_del_init(&t->list);
- memset(t, 0, sizeof(*t));
- kmem_cache_free(btrfs_transaction_cachep, t);
- }
+ spin_unlock(&root->fs_info->trans_lock);
+ btrfs_put_transaction(t);
+ trace_btrfs_transaction_commit(root);
+ spin_lock(&root->fs_info->trans_lock);
+ }
+ spin_unlock(&root->fs_info->trans_lock);
+ btrfs_destroy_all_ordered_extents(root->fs_info);
+ btrfs_destroy_delayed_inodes(root);
+ btrfs_assert_delayed_root_empty(root);
+ btrfs_destroy_pinned_extent(root, root->fs_info->pinned_extents);
+ btrfs_destroy_all_delalloc_inodes(root->fs_info);
mutex_unlock(&root->fs_info->transaction_kthread_mutex);
return 0;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 11:12:54 +0000