#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
+#include "raid56.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
static void free_fs_root(struct btrfs_root *root);
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only);
-static void btrfs_destroy_ordered_operations(struct btrfs_root *root);
+static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
+ struct btrfs_root *root);
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_destroy_pending_snapshots(struct btrfs_transaction *t);
+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,
btree_readahead_hook(root, eb, eb->start, ret);
}
- if (ret)
+ if (ret) {
+ /*
+ * our io error hook is going to dec the io pages
+ * again, we have to make sure it has something
+ * to decrement
+ */
+ atomic_inc(&eb->io_pages);
clear_extent_buffer_uptodate(eb);
+ }
free_extent_buffer(eb);
out:
return ret;
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
eb->read_mirror = failed_mirror;
+ atomic_dec(&eb->io_pages);
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
end_io_wq->work.flags = 0;
if (bio->bi_rw & REQ_WRITE) {
- if (end_io_wq->metadata == 1)
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
btrfs_queue_worker(&fs_info->endio_meta_write_workers,
&end_io_wq->work);
- else if (end_io_wq->metadata == 2)
+ else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
btrfs_queue_worker(&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);
else
btrfs_queue_worker(&fs_info->endio_write_workers,
&end_io_wq->work);
} else {
- if (end_io_wq->metadata)
+ if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
+ btrfs_queue_worker(&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);
else
* 0 - if data
* 1 - if normal metadta
* 2 - if writing to the free space cache area
+ * 3 - raid parity work
*/
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
int metadata)
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
INIT_LIST_HEAD(&fs_info->delalloc_inodes);
- INIT_LIST_HEAD(&fs_info->ordered_operations);
INIT_LIST_HEAD(&fs_info->caching_block_groups);
spin_lock_init(&fs_info->delalloc_lock);
spin_lock_init(&fs_info->trans_lock);
init_waitqueue_head(&fs_info->transaction_blocked_wait);
init_waitqueue_head(&fs_info->async_submit_wait);
+ ret = btrfs_alloc_stripe_hash_table(fs_info);
+ if (ret) {
+ err = ret;
+ goto fail_alloc;
+ }
+
__setup_root(4096, 4096, 4096, 4096, tree_root,
fs_info, BTRFS_ROOT_TREE_OBJECTID);
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);
*/
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;
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);
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (strncmp((char *)(&disk_super->magic), BTRFS_MAGIC,
- sizeof(disk_super->magic))) {
+ if (disk_super->magic != cpu_to_le64(BTRFS_MAGIC)) {
printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
* kthreads
*/
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
- invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
fail_block_groups:
btrfs_free_block_groups(fs_info);
fail_tree_roots:
free_root_pointers(fs_info, 1);
+ invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
fail_sb_buffer:
btrfs_stop_workers(&fs_info->generic_worker);
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);
fail_iput:
btrfs_mapping_tree_free(&fs_info->mapping_tree);
- invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
iput(fs_info->btree_inode);
fail_delalloc_bytes:
percpu_counter_destroy(&fs_info->delalloc_bytes);
fail_srcu:
cleanup_srcu_struct(&fs_info->subvol_srcu);
fail:
+ btrfs_free_stripe_hash_table(fs_info);
btrfs_close_devices(fs_info->fs_devices);
return err;
super = (struct btrfs_super_block *)bh->b_data;
if (btrfs_super_bytenr(super) != bytenr ||
- strncmp((char *)(&super->magic), BTRFS_MAGIC,
- sizeof(super->magic))) {
+ super->magic != cpu_to_le64(BTRFS_MAGIC)) {
brelse(bh);
continue;
}
((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK)
== 0)))
num_tolerated_disk_barrier_failures = 0;
- else if (num_tolerated_disk_barrier_failures > 1
- &&
- (flags & (BTRFS_BLOCK_GROUP_RAID1 |
- BTRFS_BLOCK_GROUP_RAID10)))
- num_tolerated_disk_barrier_failures = 1;
+ else if (num_tolerated_disk_barrier_failures > 1) {
+ if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
+ BTRFS_BLOCK_GROUP_RAID5 |
+ BTRFS_BLOCK_GROUP_RAID10)) {
+ num_tolerated_disk_barrier_failures = 1;
+ } else if (flags &
+ BTRFS_BLOCK_GROUP_RAID5) {
+ num_tolerated_disk_barrier_failures = 2;
+ }
+ }
}
}
up_read(&sinfo->groups_sem);
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)) {
+ 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);
free_fs_root(root);
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);
bdi_destroy(&fs_info->bdi);
cleanup_srcu_struct(&fs_info->subvol_srcu);
+ btrfs_free_stripe_hash_table(fs_info);
+
return 0;
}
ret = percpu_counter_compare(&root->fs_info->dirty_metadata_bytes,
BTRFS_DIRTY_METADATA_THRESH);
if (ret > 0) {
- balance_dirty_pages_ratelimited_nr(
- root->fs_info->btree_inode->i_mapping, 1);
+ balance_dirty_pages_ratelimited(
+ root->fs_info->btree_inode->i_mapping);
}
return;
}
btrfs_cleanup_transaction(root);
}
-static void btrfs_destroy_ordered_operations(struct btrfs_root *root)
+static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
+ struct btrfs_root *root)
{
struct btrfs_inode *btrfs_inode;
struct list_head splice;
mutex_lock(&root->fs_info->ordered_operations_mutex);
spin_lock(&root->fs_info->ordered_extent_lock);
- list_splice_init(&root->fs_info->ordered_operations, &splice);
+ list_splice_init(&t->ordered_operations, &splice);
while (!list_empty(&splice)) {
btrfs_inode = list_entry(splice.next, struct btrfs_inode,
ordered_operations);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
{
- struct list_head splice;
struct btrfs_ordered_extent *ordered;
- struct inode *inode;
-
- INIT_LIST_HEAD(&splice);
spin_lock(&root->fs_info->ordered_extent_lock);
-
- list_splice_init(&root->fs_info->ordered_extents, &splice);
- while (!list_empty(&splice)) {
- ordered = list_entry(splice.next, struct btrfs_ordered_extent,
- root_extent_list);
-
- list_del_init(&ordered->root_extent_list);
- atomic_inc(&ordered->refs);
-
- /* the inode may be getting freed (in sys_unlink path). */
- inode = igrab(ordered->inode);
-
- spin_unlock(&root->fs_info->ordered_extent_lock);
- if (inode)
- iput(inode);
-
- atomic_set(&ordered->refs, 1);
- btrfs_put_ordered_extent(ordered);
-
- spin_lock(&root->fs_info->ordered_extent_lock);
- }
-
+ /*
+ * This will just short circuit the ordered completion stuff which will
+ * make sure the ordered extent gets properly cleaned up.
+ */
+ list_for_each_entry(ordered, &root->fs_info->ordered_extents,
+ root_extent_list)
+ set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
spin_unlock(&root->fs_info->ordered_extent_lock);
}
}
while ((node = rb_first(&delayed_refs->root)) != NULL) {
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+ struct btrfs_delayed_ref_head *head = NULL;
+ ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
atomic_set(&ref->refs, 1);
if (btrfs_delayed_ref_is_head(ref)) {
- struct btrfs_delayed_ref_head *head;
head = btrfs_delayed_node_to_head(ref);
if (!mutex_trylock(&head->mutex)) {
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--;
-
+ if (head)
+ mutex_unlock(&head->mutex);
spin_unlock(&delayed_refs->lock);
btrfs_put_delayed_ref(ref);
return ret;
}
-static void btrfs_destroy_pending_snapshots(struct btrfs_transaction *t)
+static void btrfs_evict_pending_snapshots(struct btrfs_transaction *t)
{
struct btrfs_pending_snapshot *snapshot;
struct list_head splice;
snapshot = list_entry(splice.next,
struct btrfs_pending_snapshot,
list);
-
+ snapshot->error = -ECANCELED;
list_del_init(&snapshot->list);
-
- kfree(snapshot);
}
}
cur_trans->blocked = 1;
wake_up(&root->fs_info->transaction_blocked_wait);
+ btrfs_evict_pending_snapshots(cur_trans);
+
cur_trans->blocked = 0;
wake_up(&root->fs_info->transaction_wait);
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
- btrfs_destroy_pending_snapshots(cur_trans);
-
btrfs_destroy_marked_extents(root, &cur_trans->dirty_pages,
EXTENT_DIRTY);
btrfs_destroy_pinned_extent(root,
while (!list_empty(&list)) {
t = list_entry(list.next, struct btrfs_transaction, list);
- if (!t)
- break;
- btrfs_destroy_ordered_operations(root);
+ btrfs_destroy_ordered_operations(t, root);
btrfs_destroy_ordered_extents(root);
if (waitqueue_active(&root->fs_info->transaction_blocked_wait))
wake_up(&root->fs_info->transaction_blocked_wait);
+ btrfs_evict_pending_snapshots(t);
+
t->blocked = 0;
smp_mb();
if (waitqueue_active(&root->fs_info->transaction_wait))
btrfs_destroy_delayed_inodes(root);
btrfs_assert_delayed_root_empty(root);
- btrfs_destroy_pending_snapshots(t);
-
btrfs_destroy_delalloc_inodes(root);
spin_lock(&root->fs_info->trans_lock);
projects / deliverable / linux.git / blobdiff