#include "ulist.h"
#include "transaction.h"
#include "delayed-ref.h"
+#include "locking.h"
/*
* this structure records all encountered refs on the way up to the root
s64 bytes_left = size - 1;
struct extent_buffer *eb = eb_in;
struct btrfs_key found_key;
+ int leave_spinning = path->leave_spinning;
if (bytes_left >= 0)
dest[bytes_left] = '\0';
+ path->leave_spinning = 1;
while (1) {
len = btrfs_inode_ref_name_len(eb, iref);
bytes_left -= len;
if (bytes_left >= 0)
read_extent_buffer(eb, dest + bytes_left,
(unsigned long)(iref + 1), len);
- if (eb != eb_in)
+ if (eb != eb_in) {
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
+ }
ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
if (ret > 0)
ret = -ENOENT;
slot = path->slots[0];
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
- if (eb != eb_in)
+ if (eb != eb_in) {
atomic_inc(&eb->refs);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ }
btrfs_release_path(path);
iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
}
btrfs_release_path(path);
+ path->leave_spinning = leave_spinning;
if (ret)
return ERR_PTR(ret);
struct btrfs_path *path,
iterate_irefs_t *iterate, void *ctx)
{
- int ret;
+ int ret = 0;
int slot;
u32 cur;
u32 len;
struct btrfs_inode_ref *iref;
struct btrfs_key found_key;
- while (1) {
+ while (!ret) {
+ path->leave_spinning = 1;
ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path,
&found_key);
if (ret < 0)
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
atomic_inc(&eb->refs);
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
btrfs_release_path(path);
item = btrfs_item_nr(eb, slot);
(unsigned long long)found_key.objectid,
(unsigned long long)fs_root->objectid);
ret = iterate(parent, iref, eb, ctx);
- if (ret) {
- free_extent_buffer(eb);
+ if (ret)
break;
- }
len = sizeof(*iref) + name_len;
iref = (struct btrfs_inode_ref *)((char *)iref + len);
}
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
}
void free_ipath(struct inode_fs_paths *ipath)
{
+ if (!ipath)
+ return;
kfree(ipath->fspath);
kfree(ipath);
}
* is required instead of the faster short fsync log commits
*/
u64 last_trans_log_full_commit;
- unsigned long mount_opt:21;
+ unsigned long mount_opt;
unsigned long compress_type:4;
u64 max_inline;
u64 alloc_start;
if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
break;
- if (!failed_mirror) {
- failed = 1;
- printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror);
- failed_mirror = eb->failed_mirror;
- }
-
num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
eb->start, eb->len);
if (num_copies == 1)
break;
+ if (!failed_mirror) {
+ failed = 1;
+ failed_mirror = eb->read_mirror;
+ }
+
mirror_num++;
if (mirror_num == failed_mirror)
mirror_num++;
}
static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
struct extent_io_tree *tree;
u64 found_start;
if (!reads_done)
goto err;
+ eb->read_mirror = mirror;
if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
ret = -EIO;
goto err;
eb = (struct extent_buffer *)page->private;
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- eb->failed_mirror = failed_mirror;
+ eb->read_mirror = failed_mirror;
if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
btree_readahead_hook(root, eb, eb->start, -EIO);
return -EIO; /* we fixed nothing */
goto fail_sb_buffer;
}
- if (sectorsize < PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size "
- "found on %s\n", sb->s_id);
+ if (sectorsize != PAGE_SIZE) {
+ printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ "found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
if (ret) {
printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret);
+ spin_lock(&delayed_refs->lock);
return ret;
}
if (ret) {
printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret);
+ spin_lock(&delayed_refs->lock);
return ret;
}
*/
if (current->journal_info)
return -EAGAIN;
- ret = wait_event_interruptible(space_info->wait,
- !space_info->flush);
- /* Must have been interrupted, return */
- if (ret) {
- printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__);
+ ret = wait_event_killable(space_info->wait, !space_info->flush);
+ /* Must have been killed, return */
+ if (ret)
return -EINTR;
- }
spin_lock(&space_info->lock);
}
num_bytes = calc_global_metadata_size(fs_info);
- spin_lock(&block_rsv->lock);
spin_lock(&sinfo->lock);
+ spin_lock(&block_rsv->lock);
block_rsv->size = num_bytes;
block_rsv->full = 1;
}
- spin_unlock(&sinfo->lock);
spin_unlock(&block_rsv->lock);
+ spin_unlock(&sinfo->lock);
}
static void init_global_block_rsv(struct btrfs_fs_info *fs_info)
return 0;
}
+static struct extent_state *next_state(struct extent_state *state)
+{
+ struct rb_node *next = rb_next(&state->rb_node);
+ if (next)
+ return rb_entry(next, struct extent_state, rb_node);
+ else
+ return NULL;
+}
+
/*
* utility function to clear some bits in an extent state struct.
- * it will optionally wake up any one waiting on this state (wake == 1), or
- * forcibly remove the state from the tree (delete == 1).
+ * it will optionally wake up any one waiting on this state (wake == 1)
*
* If no bits are set on the state struct after clearing things, the
* struct is freed and removed from the tree
*/
-static int clear_state_bit(struct extent_io_tree *tree,
- struct extent_state *state,
- int *bits, int wake)
+static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
+ struct extent_state *state,
+ int *bits, int wake)
{
+ struct extent_state *next;
int bits_to_clear = *bits & ~EXTENT_CTLBITS;
- int ret = state->state & bits_to_clear;
if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
u64 range = state->end - state->start + 1;
if (wake)
wake_up(&state->wq);
if (state->state == 0) {
+ next = next_state(state);
if (state->tree) {
rb_erase(&state->rb_node, &tree->state);
state->tree = NULL;
}
} else {
merge_state(tree, state);
+ next = next_state(state);
}
- return ret;
+ return next;
}
static struct extent_state *
struct extent_state *state;
struct extent_state *cached;
struct extent_state *prealloc = NULL;
- struct rb_node *next_node;
struct rb_node *node;
u64 last_end;
int err;
WARN_ON(state->end < start);
last_end = state->end;
- if (state->end < end && !need_resched())
- next_node = rb_next(&state->rb_node);
- else
- next_node = NULL;
-
/* the state doesn't have the wanted bits, go ahead */
- if (!(state->state & bits))
+ if (!(state->state & bits)) {
+ state = next_state(state);
goto next;
+ }
/*
* | ---- desired range ---- |
goto out;
}
- clear_state_bit(tree, state, &bits, wake);
+ state = clear_state_bit(tree, state, &bits, wake);
next:
if (last_end == (u64)-1)
goto out;
start = last_end + 1;
- if (start <= end && next_node) {
- state = rb_entry(next_node, struct extent_state,
- rb_node);
+ if (start <= end && state && !need_resched())
goto hit_next;
- }
goto search_again;
out:
u64 start;
u64 end;
int whole_page;
- int failed_mirror;
+ int mirror;
int ret;
if (err)
}
spin_unlock(&tree->lock);
+ mirror = (int)(unsigned long)bio->bi_bdev;
if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
ret = tree->ops->readpage_end_io_hook(page, start, end,
- state);
+ state, mirror);
if (ret)
uptodate = 0;
else
clean_io_failure(start, page);
}
- if (!uptodate)
- failed_mirror = (int)(unsigned long)bio->bi_bdev;
-
if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {
- ret = tree->ops->readpage_io_failed_hook(page, failed_mirror);
+ ret = tree->ops->readpage_io_failed_hook(page, mirror);
if (!ret && !err &&
test_bit(BIO_UPTODATE, &bio->bi_flags))
uptodate = 1;
* can't handle the error it will return -EIO and we
* remain responsible for that page.
*/
- ret = bio_readpage_error(bio, page, start, end,
- failed_mirror, NULL);
+ ret = bio_readpage_error(bio, page, start, end, mirror, NULL);
if (ret == 0) {
uptodate =
test_bit(BIO_UPTODATE, &bio->bi_flags);
}
clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
- eb->failed_mirror = 0;
+ eb->read_mirror = 0;
atomic_set(&eb->io_pages, num_reads);
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
u64 start, u64 end,
struct extent_state *state);
int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end,
- struct extent_state *state);
+ struct extent_state *state, int mirror);
int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
struct extent_state *state, int uptodate);
void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
spinlock_t refs_lock;
atomic_t refs;
atomic_t io_pages;
- int failed_mirror;
+ int read_mirror;
struct list_head leak_list;
struct rcu_head rcu_head;
pid_t lock_owner;
int extent_type;
int recow;
int ret;
+ int modify_tree = -1;
if (drop_cache)
btrfs_drop_extent_cache(inode, start, end - 1, 0);
if (!path)
return -ENOMEM;
+ if (start >= BTRFS_I(inode)->disk_i_size)
+ modify_tree = 0;
+
while (1) {
recow = 0;
ret = btrfs_lookup_file_extent(trans, root, path, ino,
- search_start, -1);
+ search_start, modify_tree);
if (ret < 0)
break;
if (ret > 0 && path->slots[0] > 0 && search_start == start) {
}
search_start = max(key.offset, start);
- if (recow) {
+ if (recow || !modify_tree) {
+ modify_tree = -1;
btrfs_release_path(path);
continue;
}
* extent_io.c will try to find good copies for us.
*/
static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
- struct extent_state *state)
+ struct extent_state *state, int mirror)
{
size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
struct inode *inode = page->mapping->host;
BTRFS_I(inode)->dummy_inode = 1;
inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
- inode->i_op = &simple_dir_inode_operations;
+ inode->i_op = &btrfs_dir_ro_inode_operations;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
static int btrfs_dentry_delete(const struct dentry *dentry)
{
struct btrfs_root *root;
+ struct inode *inode = dentry->d_inode;
- if (!dentry->d_inode && !IS_ROOT(dentry))
- dentry = dentry->d_parent;
+ if (!inode && !IS_ROOT(dentry))
+ inode = dentry->d_parent->d_inode;
- if (dentry->d_inode) {
- root = BTRFS_I(dentry->d_inode)->root;
+ if (inode) {
+ root = BTRFS_I(inode)->root;
if (btrfs_root_refs(&root->root_item) == 0)
return 1;
+
+ if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+ return 1;
}
return 0;
}
struct btrfs_path *path;
struct list_head ins_list;
struct list_head del_list;
- struct qstr q;
int ret;
struct extent_buffer *leaf;
int slot;
while (di_cur < di_total) {
struct btrfs_key location;
- struct dentry *tmp;
if (verify_dir_item(root, leaf, di))
break;
d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
btrfs_dir_item_key_to_cpu(leaf, di, &location);
- q.name = name_ptr;
- q.len = name_len;
- q.hash = full_name_hash(q.name, q.len);
- tmp = d_lookup(filp->f_dentry, &q);
- if (!tmp) {
- struct btrfs_key *newkey;
-
- newkey = kzalloc(sizeof(struct btrfs_key),
- GFP_NOFS);
- if (!newkey)
- goto no_dentry;
- tmp = d_alloc(filp->f_dentry, &q);
- if (!tmp) {
- kfree(newkey);
- dput(tmp);
- goto no_dentry;
- }
- memcpy(newkey, &location,
- sizeof(struct btrfs_key));
- tmp->d_fsdata = newkey;
- tmp->d_flags |= DCACHE_NEED_LOOKUP;
- d_rehash(tmp);
- dput(tmp);
- } else {
- dput(tmp);
- }
-no_dentry:
+
/* is this a reference to our own snapshot? If so
- * skip it
+ * skip it.
+ *
+ * In contrast to old kernels, we insert the snapshot's
+ * dir item and dir index after it has been created, so
+ * we won't find a reference to our own snapshot. We
+ * still keep the following code for backward
+ * compatibility.
*/
if (location.type == BTRFS_ROOT_ITEM_KEY &&
location.objectid == root->root_key.objectid) {
di_args->bytes_used = dev->bytes_used;
di_args->total_bytes = dev->total_bytes;
memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
- strncpy(di_args->path, dev->name, sizeof(di_args->path));
+ if (dev->name)
+ strncpy(di_args->path, dev->name, sizeof(di_args->path));
+ else
+ di_args->path[0] = '\0';
out:
if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
struct btrfs_bio *bbio)
{
int ret;
- int looped = 0;
struct reada_zone *zone;
struct btrfs_block_group_cache *cache = NULL;
u64 start;
u64 end;
int i;
-again:
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
spin_unlock(&fs_info->reada_lock);
}
- if (looped)
- return NULL;
-
cache = btrfs_lookup_block_group(fs_info, logical);
if (!cache)
return NULL;
ret = radix_tree_insert(&dev->reada_zones,
(unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
zone);
- spin_unlock(&fs_info->reada_lock);
- if (ret) {
+ if (ret == -EEXIST) {
kfree(zone);
- looped = 1;
- goto again;
+ ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
+ logical >> PAGE_CACHE_SHIFT, 1);
+ if (ret == 1)
+ kref_get(&zone->refcnt);
}
+ spin_unlock(&fs_info->reada_lock);
return zone;
}
struct btrfs_key *top, int level)
{
int ret;
- int looped = 0;
struct reada_extent *re = NULL;
+ struct reada_extent *re_exist = NULL;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct btrfs_bio *bbio = NULL;
struct btrfs_device *dev;
+ struct btrfs_device *prev_dev;
u32 blocksize;
u64 length;
int nzones = 0;
int i;
unsigned long index = logical >> PAGE_CACHE_SHIFT;
-again:
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree, index);
if (re)
kref_get(&re->refcnt);
spin_unlock(&fs_info->reada_lock);
- if (re || looped)
+ if (re)
return re;
re = kzalloc(sizeof(*re), GFP_NOFS);
/* insert extent in reada_tree + all per-device trees, all or nothing */
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&fs_info->reada_tree, index, re);
+ if (ret == -EEXIST) {
+ re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
+ BUG_ON(!re_exist);
+ kref_get(&re_exist->refcnt);
+ spin_unlock(&fs_info->reada_lock);
+ goto error;
+ }
if (ret) {
spin_unlock(&fs_info->reada_lock);
- if (ret != -ENOMEM) {
- /* someone inserted the extent in the meantime */
- looped = 1;
- }
goto error;
}
+ prev_dev = NULL;
for (i = 0; i < nzones; ++i) {
dev = bbio->stripes[i].dev;
+ if (dev == prev_dev) {
+ /*
+ * in case of DUP, just add the first zone. As both
+ * are on the same device, there's nothing to gain
+ * from adding both.
+ * Also, it wouldn't work, as the tree is per device
+ * and adding would fail with EEXIST
+ */
+ continue;
+ }
+ prev_dev = dev;
ret = radix_tree_insert(&dev->reada_extents, index, re);
if (ret) {
while (--i >= 0) {
}
kfree(bbio);
kfree(re);
- if (looped)
- goto again;
- return NULL;
+ return re_exist;
}
static void reada_kref_dummy(struct kref *kr)
if (rb_node)
backref_tree_panic(rb_node, -EEXIST, node->bytenr);
} else {
+ spin_lock(&root->fs_info->trans_lock);
list_del_init(&root->root_list);
+ spin_unlock(&root->fs_info->trans_lock);
kfree(node);
}
return 0;
ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 5);
if (ret < 0) {
- if (ret != -EAGAIN) {
+ if (ret != -ENOSPC) {
err = ret;
WARN_ON(1);
break;
if (memcmp(csum, on_disk_csum, sdev->csum_size))
fail = 1;
- if (fail) {
- spin_lock(&sdev->stat_lock);
- ++sdev->stat.csum_errors;
- spin_unlock(&sdev->stat_lock);
- }
-
return fail;
}
if (memcmp(calculated_csum, on_disk_csum, sdev->csum_size))
++crc_fail;
- if (crc_fail || fail) {
- spin_lock(&sdev->stat_lock);
- if (crc_fail)
- ++sdev->stat.csum_errors;
- if (fail)
- ++sdev->stat.verify_errors;
- spin_unlock(&sdev->stat_lock);
- }
-
return fail || crc_fail;
}
return 0;
}
- btrfs_start_delalloc_inodes(root, 0);
btrfs_wait_ordered_extents(root, 0, 0);
trans = btrfs_start_transaction(root, 0);
if (ret)
goto restore;
} else {
- if (fs_info->fs_devices->rw_devices == 0)
+ if (fs_info->fs_devices->rw_devices == 0) {
ret = -EACCES;
goto restore;
+ }
- if (btrfs_super_log_root(fs_info->super_copy) != 0)
+ if (btrfs_super_log_root(fs_info->super_copy) != 0) {
ret = -EINVAL;
goto restore;
+ }
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
cur_trans = root->fs_info->running_transaction;
if (cur_trans) {
- if (cur_trans->aborted)
+ if (cur_trans->aborted) {
+ spin_unlock(&root->fs_info->trans_lock);
return cur_trans->aborted;
+ }
atomic_inc(&cur_trans->use_count);
atomic_inc(&cur_trans->num_writers);
cur_trans->num_joined++;
ret = commit_fs_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
ret = commit_cowonly_roots(trans, root);
if (ret) {
mutex_unlock(&root->fs_info->tree_log_mutex);
+ mutex_unlock(&root->fs_info->reloc_mutex);
goto cleanup_transaction;
}
stripe_size = devices_info[ndevs-1].max_avail;
num_stripes = ndevs * dev_stripes;
- if (stripe_size * num_stripes > max_chunk_size * ncopies) {
+ if (stripe_size * ndevs > max_chunk_size * ncopies) {
stripe_size = max_chunk_size * ncopies;
- do_div(stripe_size, num_stripes);
+ do_div(stripe_size, ndevs);
}
do_div(stripe_size, dev_stripes);
+
+ /* align to BTRFS_STRIPE_LEN */
do_div(stripe_size, BTRFS_STRIPE_LEN);
stripe_size *= BTRFS_STRIPE_LEN;
else if (mirror_num)
stripe_index += mirror_num - 1;
else {
+ int old_stripe_index = stripe_index;
stripe_index = find_live_mirror(map, stripe_index,
map->sub_stripes, stripe_index +
current->pid % map->sub_stripes);
- mirror_num = stripe_index + 1;
+ mirror_num = stripe_index - old_stripe_index + 1;
}
} else {
/*
ret = __btrfs_open_devices(fs_devices, FMODE_READ,
root->fs_info->bdev_holder);
- if (ret)
+ if (ret) {
+ free_fs_devices(fs_devices);
goto out;
+ }
if (!fs_devices->seeding) {
__btrfs_close_devices(fs_devices);