#include "locking.h"
#include "free-space-cache.h"
+/* control flags for do_chunk_alloc's force field
+ * CHUNK_ALLOC_NO_FORCE means to only allocate a chunk
+ * if we really need one.
+ *
+ * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
+ * CHUNK_ALLOC_LIMITED means to only try and allocate one
+ * if we have very few chunks already allocated. This is
+ * used as part of the clustering code to help make sure
+ * we have a good pool of storage to cluster in, without
+ * filling the FS with empty chunks
+ *
+ */
+enum {
+ CHUNK_ALLOC_NO_FORCE = 0,
+ CHUNK_ALLOC_FORCE = 1,
+ CHUNK_ALLOC_LIMITED = 2,
+};
+
static int update_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 bytenr, u64 num_bytes, int alloc);
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve, int sinfo);
static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 bytenr, u64 num_bytes, u64 parent,
* allocate blocks for the tree root we can't do the fast caching since
* we likely hold important locks.
*/
- if (!trans->transaction->in_commit &&
+ if (trans && (!trans->transaction->in_commit) &&
(root && root != root->fs_info->tree_root)) {
spin_lock(&cache->lock);
if (cache->cached != BTRFS_CACHE_NO) {
if (load_cache_only)
return 0;
- caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_KERNEL);
+ caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
BUG_ON(!caching_ctl);
INIT_LIST_HEAD(&caching_ctl->list);
return ret;
}
-static void btrfs_issue_discard(struct block_device *bdev,
+static int btrfs_issue_discard(struct block_device *bdev,
u64 start, u64 len)
{
- blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
+ return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_NOFS, 0);
}
static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
- u64 num_bytes)
+ u64 num_bytes, u64 *actual_bytes)
{
int ret;
- u64 map_length = num_bytes;
+ u64 discarded_bytes = 0;
struct btrfs_multi_bio *multi = NULL;
- if (!btrfs_test_opt(root, DISCARD))
- return 0;
/* Tell the block device(s) that the sectors can be discarded */
- ret = btrfs_map_block(&root->fs_info->mapping_tree, READ,
- bytenr, &map_length, &multi, 0);
+ ret = btrfs_map_block(&root->fs_info->mapping_tree, REQ_DISCARD,
+ bytenr, &num_bytes, &multi, 0);
if (!ret) {
struct btrfs_bio_stripe *stripe = multi->stripes;
int i;
- if (map_length > num_bytes)
- map_length = num_bytes;
for (i = 0; i < multi->num_stripes; i++, stripe++) {
- btrfs_issue_discard(stripe->dev->bdev,
- stripe->physical,
- map_length);
+ ret = btrfs_issue_discard(stripe->dev->bdev,
+ stripe->physical,
+ stripe->length);
+ if (!ret)
+ discarded_bytes += stripe->length;
+ else if (ret != -EOPNOTSUPP)
+ break;
}
kfree(multi);
}
+ if (discarded_bytes && ret == -EOPNOTSUPP)
+ ret = 0;
+
+ if (actual_bytes)
+ *actual_bytes = discarded_bytes;
+
return ret;
}
found->bytes_readonly = 0;
found->bytes_may_use = 0;
found->full = 0;
- found->force_alloc = 0;
+ found->force_alloc = CHUNK_ALLOC_NO_FORCE;
+ found->chunk_alloc = 0;
*space_info = found;
list_add_rcu(&found->list, &info->space_info);
atomic_set(&found->caching_threads, 0);
if (!data_sinfo->full && alloc_chunk) {
u64 alloc_target;
- data_sinfo->force_alloc = 1;
+ data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
spin_unlock(&data_sinfo->lock);
alloc:
alloc_target = btrfs_get_alloc_profile(root, 1);
ret = do_chunk_alloc(trans, root->fs_info->extent_root,
bytes + 2 * 1024 * 1024,
- alloc_target, 0);
+ alloc_target,
+ CHUNK_ALLOC_NO_FORCE);
btrfs_end_transaction(trans, root);
if (ret < 0) {
if (ret != -ENOSPC)
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
- found->force_alloc = 1;
+ found->force_alloc = CHUNK_ALLOC_FORCE;
}
rcu_read_unlock();
}
static int should_alloc_chunk(struct btrfs_root *root,
- struct btrfs_space_info *sinfo, u64 alloc_bytes)
+ struct btrfs_space_info *sinfo, u64 alloc_bytes,
+ int force)
{
u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly;
+ u64 num_allocated = sinfo->bytes_used + sinfo->bytes_reserved;
u64 thresh;
- if (sinfo->bytes_used + sinfo->bytes_reserved +
- alloc_bytes + 256 * 1024 * 1024 < num_bytes)
+ if (force == CHUNK_ALLOC_FORCE)
+ return 1;
+
+ /*
+ * in limited mode, we want to have some free space up to
+ * about 1% of the FS size.
+ */
+ if (force == CHUNK_ALLOC_LIMITED) {
+ thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+ thresh = max_t(u64, 64 * 1024 * 1024,
+ div_factor_fine(thresh, 1));
+
+ if (num_bytes - num_allocated < thresh)
+ return 1;
+ }
+
+ /*
+ * we have two similar checks here, one based on percentage
+ * and once based on a hard number of 256MB. The idea
+ * is that if we have a good amount of free
+ * room, don't allocate a chunk. A good mount is
+ * less than 80% utilized of the chunks we have allocated,
+ * or more than 256MB free
+ */
+ if (num_allocated + alloc_bytes + 256 * 1024 * 1024 < num_bytes)
return 0;
- if (sinfo->bytes_used + sinfo->bytes_reserved +
- alloc_bytes < div_factor(num_bytes, 8))
+ if (num_allocated + alloc_bytes < div_factor(num_bytes, 8))
return 0;
thresh = btrfs_super_total_bytes(&root->fs_info->super_copy);
+
+ /* 256MB or 5% of the FS */
thresh = max_t(u64, 256 * 1024 * 1024, div_factor_fine(thresh, 5));
if (num_bytes > thresh && sinfo->bytes_used < div_factor(num_bytes, 3))
return 0;
-
return 1;
}
{
struct btrfs_space_info *space_info;
struct btrfs_fs_info *fs_info = extent_root->fs_info;
+ int wait_for_alloc = 0;
int ret = 0;
- mutex_lock(&fs_info->chunk_mutex);
-
flags = btrfs_reduce_alloc_profile(extent_root, flags);
space_info = __find_space_info(extent_root->fs_info, flags);
}
BUG_ON(!space_info);
+again:
spin_lock(&space_info->lock);
if (space_info->force_alloc)
- force = 1;
+ force = space_info->force_alloc;
if (space_info->full) {
spin_unlock(&space_info->lock);
- goto out;
+ return 0;
}
- if (!force && !should_alloc_chunk(extent_root, space_info,
- alloc_bytes)) {
+ if (!should_alloc_chunk(extent_root, space_info, alloc_bytes, force)) {
spin_unlock(&space_info->lock);
- goto out;
+ return 0;
+ } else if (space_info->chunk_alloc) {
+ wait_for_alloc = 1;
+ } else {
+ space_info->chunk_alloc = 1;
}
+
spin_unlock(&space_info->lock);
+ mutex_lock(&fs_info->chunk_mutex);
+
+ /*
+ * The chunk_mutex is held throughout the entirety of a chunk
+ * allocation, so once we've acquired the chunk_mutex we know that the
+ * other guy is done and we need to recheck and see if we should
+ * allocate.
+ */
+ if (wait_for_alloc) {
+ mutex_unlock(&fs_info->chunk_mutex);
+ wait_for_alloc = 0;
+ goto again;
+ }
+
/*
* If we have mixed data/metadata chunks we want to make sure we keep
* allocating mixed chunks instead of individual chunks.
space_info->full = 1;
else
ret = 1;
- space_info->force_alloc = 0;
+
+ space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+ space_info->chunk_alloc = 0;
spin_unlock(&space_info->lock);
-out:
mutex_unlock(&extent_root->fs_info->chunk_mutex);
return ret;
}
struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
u64 to_reserve;
int nr_extents;
+ int reserved_extents;
int ret;
if (btrfs_transaction_in_commit(root->fs_info))
num_bytes = ALIGN(num_bytes, root->sectorsize);
- spin_lock(&BTRFS_I(inode)->accounting_lock);
nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents) + 1;
- if (nr_extents > BTRFS_I(inode)->reserved_extents) {
- nr_extents -= BTRFS_I(inode)->reserved_extents;
+ reserved_extents = atomic_read(&BTRFS_I(inode)->reserved_extents);
+
+ if (nr_extents > reserved_extents) {
+ nr_extents -= reserved_extents;
to_reserve = calc_trans_metadata_size(root, nr_extents);
} else {
nr_extents = 0;
to_reserve = 0;
}
- spin_unlock(&BTRFS_I(inode)->accounting_lock);
+
to_reserve += calc_csum_metadata_size(inode, num_bytes);
ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
if (ret)
return ret;
- spin_lock(&BTRFS_I(inode)->accounting_lock);
- BTRFS_I(inode)->reserved_extents += nr_extents;
+ atomic_add(nr_extents, &BTRFS_I(inode)->reserved_extents);
atomic_inc(&BTRFS_I(inode)->outstanding_extents);
- spin_unlock(&BTRFS_I(inode)->accounting_lock);
block_rsv_add_bytes(block_rsv, to_reserve, 1);
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 to_free;
int nr_extents;
+ int reserved_extents;
num_bytes = ALIGN(num_bytes, root->sectorsize);
atomic_dec(&BTRFS_I(inode)->outstanding_extents);
WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents) < 0);
- spin_lock(&BTRFS_I(inode)->accounting_lock);
- nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
- if (nr_extents < BTRFS_I(inode)->reserved_extents) {
- nr_extents = BTRFS_I(inode)->reserved_extents - nr_extents;
- BTRFS_I(inode)->reserved_extents -= nr_extents;
- } else {
- nr_extents = 0;
- }
- spin_unlock(&BTRFS_I(inode)->accounting_lock);
+ reserved_extents = atomic_read(&BTRFS_I(inode)->reserved_extents);
+ do {
+ int old, new;
+
+ nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
+ if (nr_extents >= reserved_extents) {
+ nr_extents = 0;
+ break;
+ }
+ old = reserved_extents;
+ nr_extents = reserved_extents - nr_extents;
+ new = reserved_extents - nr_extents;
+ old = atomic_cmpxchg(&BTRFS_I(inode)->reserved_extents,
+ reserved_extents, new);
+ if (likely(old == reserved_extents))
+ break;
+ reserved_extents = old;
+ } while (1);
to_free = calc_csum_metadata_size(inode, num_bytes);
if (nr_extents > 0)
* update size of reserved extents. this function may return -EAGAIN
* if 'reserve' is true or 'sinfo' is false.
*/
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
- u64 num_bytes, int reserve, int sinfo)
+int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
+ u64 num_bytes, int reserve, int sinfo)
{
int ret = 0;
if (sinfo) {
if (ret)
break;
- ret = btrfs_discard_extent(root, start, end + 1 - start);
+ if (btrfs_test_opt(root, DISCARD))
+ ret = btrfs_discard_extent(root, start,
+ end + 1 - start, NULL);
clear_extent_dirty(unpin, start, end, GFP_NOFS);
unpin_extent_range(root, start, end);
WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
btrfs_add_free_space(cache, buf->start, buf->len);
- ret = update_reserved_bytes(cache, buf->len, 0, 0);
+ ret = btrfs_update_reserved_bytes(cache, buf->len, 0, 0);
if (ret == -EAGAIN) {
/* block group became read-only */
- update_reserved_bytes(cache, buf->len, 0, 1);
+ btrfs_update_reserved_bytes(cache, buf->len, 0, 1);
goto out;
}
}
}
out:
+ /*
+ * Deleting the buffer, clear the corrupt flag since it doesn't matter
+ * anymore.
+ */
+ clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
btrfs_put_block_group(cache);
}
search_start - offset);
BUG_ON(offset > search_start);
- ret = update_reserved_bytes(block_group, num_bytes, 1,
+ ret = btrfs_update_reserved_bytes(block_group, num_bytes, 1,
(data & BTRFS_BLOCK_GROUP_DATA));
if (ret == -EAGAIN) {
btrfs_add_free_space(block_group, offset, num_bytes);
if (allowed_chunk_alloc) {
ret = do_chunk_alloc(trans, root, num_bytes +
- 2 * 1024 * 1024, data, 1);
+ 2 * 1024 * 1024, data,
+ CHUNK_ALLOC_LIMITED);
allowed_chunk_alloc = 0;
done_chunk_alloc = 1;
- } else if (!done_chunk_alloc) {
- space_info->force_alloc = 1;
+ } else if (!done_chunk_alloc &&
+ space_info->force_alloc == CHUNK_ALLOC_NO_FORCE) {
+ space_info->force_alloc = CHUNK_ALLOC_LIMITED;
}
if (loop < LOOP_NO_EMPTY_SIZE) {
*/
if (empty_size || root->ref_cows)
ret = do_chunk_alloc(trans, root->fs_info->extent_root,
- num_bytes + 2 * 1024 * 1024, data, 0);
+ num_bytes + 2 * 1024 * 1024, data,
+ CHUNK_ALLOC_NO_FORCE);
WARN_ON(num_bytes < root->sectorsize);
ret = find_free_extent(trans, root, num_bytes, empty_size,
num_bytes = num_bytes & ~(root->sectorsize - 1);
num_bytes = max(num_bytes, min_alloc_size);
do_chunk_alloc(trans, root->fs_info->extent_root,
- num_bytes, data, 1);
+ num_bytes, data, CHUNK_ALLOC_FORCE);
goto again;
}
if (ret == -ENOSPC && btrfs_test_opt(root, ENOSPC_DEBUG)) {
dump_space_info(sinfo, num_bytes, 1);
}
+ trace_btrfs_reserved_extent_alloc(root, ins->objectid, ins->offset);
+
return ret;
}
return -ENOSPC;
}
- ret = btrfs_discard_extent(root, start, len);
+ if (btrfs_test_opt(root, DISCARD))
+ ret = btrfs_discard_extent(root, start, len, NULL);
btrfs_add_free_space(cache, start, len);
- update_reserved_bytes(cache, len, 0, 1);
+ btrfs_update_reserved_bytes(cache, len, 0, 1);
btrfs_put_block_group(cache);
+ trace_btrfs_reserved_extent_free(root, start, len);
+
return ret;
}
size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type);
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path)
+ return -ENOMEM;
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
put_caching_control(caching_ctl);
}
- ret = update_reserved_bytes(block_group, ins->offset, 1, 1);
+ ret = btrfs_update_reserved_bytes(block_group, ins->offset, 1, 1);
BUG_ON(ret);
btrfs_put_block_group(block_group);
ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,
if (reada && level == 1)
reada_walk_down(trans, root, wc, path);
next = read_tree_block(root, bytenr, blocksize, generation);
+ if (!next)
+ return -EIO;
btrfs_tree_lock(next);
btrfs_set_lock_blocking(next);
}
BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path)
+ return -ENOMEM;
wc = kzalloc(sizeof(*wc), GFP_NOFS);
- BUG_ON(!wc);
+ if (!wc) {
+ btrfs_free_path(path);
+ return -ENOMEM;
+ }
btrfs_assert_tree_locked(parent);
parent_level = btrfs_header_level(parent);
}
path = btrfs_alloc_path();
- BUG_ON(!path);
+ if (!path) {
+ if (exts != *extents)
+ kfree(exts);
+ return -ENOMEM;
+ }
cur_pos = extent_key->objectid - offset;
last_byte = extent_key->objectid + extent_key->offset;
struct disk_extent *old = exts;
max *= 2;
exts = kzalloc(sizeof(*exts) * max, GFP_NOFS);
+ if (!exts) {
+ ret = -ENOMEM;
+ goto out;
+ }
memcpy(exts, old, sizeof(*exts) * nr);
if (old != *extents)
kfree(old);
int ret;
new_extent = kmalloc(sizeof(*new_extent), GFP_NOFS);
- BUG_ON(!new_extent);
+ if (!new_extent)
+ return -ENOMEM;
ref = btrfs_lookup_leaf_ref(root, leaf->start);
BUG_ON(!ref);
reloc_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
BUG_ON(!reloc_root);
- btrfs_orphan_cleanup(reloc_root);
+ ret = btrfs_orphan_cleanup(reloc_root);
+ BUG_ON(ret);
return 0;
}
return 0;
root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
- BUG_ON(!root_item);
+ if (!root_item)
+ return -ENOMEM;
ret = btrfs_copy_root(trans, root, root->commit_root,
&eb, BTRFS_TREE_RELOC_OBJECTID);
reloc_root = btrfs_read_fs_root_no_radix(root->fs_info->tree_root,
&root_key);
- BUG_ON(!reloc_root);
+ BUG_ON(IS_ERR(reloc_root));
reloc_root->last_trans = trans->transid;
reloc_root->commit_root = NULL;
reloc_root->ref_tree = &root->fs_info->reloc_ref_tree;
eb = read_tree_block(found_root, block_start,
block_size, 0);
+ if (!eb) {
+ ret = -EIO;
+ goto out;
+ }
btrfs_tree_lock(eb);
BUG_ON(level != btrfs_header_level(eb));
u64 group_start = group->key.objectid;
new_extents = kmalloc(sizeof(*new_extents),
GFP_NOFS);
+ if (!new_extents) {
+ ret = -ENOMEM;
+ goto out;
+ }
nr_extents = 1;
ret = get_new_locations(reloc_inode,
extent_key,
alloc_flags = update_block_group_flags(root, cache->flags);
if (alloc_flags != cache->flags)
- do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+ do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+ CHUNK_ALLOC_FORCE);
ret = set_block_group_ro(cache);
if (!ret)
goto out;
alloc_flags = get_alloc_profile(root, cache->space_info->flags);
- ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+ ret = do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+ CHUNK_ALLOC_FORCE);
if (ret < 0)
goto out;
ret = set_block_group_ro(cache);
struct btrfs_root *root, u64 type)
{
u64 alloc_flags = get_alloc_profile(root, type);
- return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags, 1);
+ return do_chunk_alloc(trans, root, 2 * 1024 * 1024, alloc_flags,
+ CHUNK_ALLOC_FORCE);
}
/*
BUG_ON(!block_group);
BUG_ON(!block_group->ro);
+ /*
+ * Free the reserved super bytes from this block group before
+ * remove it.
+ */
+ free_excluded_extents(root, block_group);
+
memcpy(&key, &block_group->key, sizeof(key));
if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
BTRFS_BLOCK_GROUP_RAID1 |
return ret;
}
+int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_space_info *space_info;
+ int ret;
+
+ ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM, 0, 0,
+ &space_info);
+ if (ret)
+ return ret;
+
+ ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA, 0, 0,
+ &space_info);
+ if (ret)
+ return ret;
+
+ ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA, 0, 0,
+ &space_info);
+ if (ret)
+ return ret;
+
+ return ret;
+}
+
int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
{
return unpin_extent_range(root, start, end);
}
int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
- u64 num_bytes)
+ u64 num_bytes, u64 *actual_bytes)
+{
+ return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes);
+}
+
+int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
{
- return btrfs_discard_extent(root, bytenr, num_bytes);
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_block_group_cache *cache = NULL;
+ u64 group_trimmed;
+ u64 start;
+ u64 end;
+ u64 trimmed = 0;
+ int ret = 0;
+
+ cache = btrfs_lookup_block_group(fs_info, range->start);
+
+ while (cache) {
+ if (cache->key.objectid >= (range->start + range->len)) {
+ btrfs_put_block_group(cache);
+ break;
+ }
+
+ start = max(range->start, cache->key.objectid);
+ end = min(range->start + range->len,
+ cache->key.objectid + cache->key.offset);
+
+ if (end - start >= range->minlen) {
+ if (!block_group_cache_done(cache)) {
+ ret = cache_block_group(cache, NULL, root, 0);
+ if (!ret)
+ wait_block_group_cache_done(cache);
+ }
+ ret = btrfs_trim_block_group(cache,
+ &group_trimmed,
+ start,
+ end,
+ range->minlen);
+
+ trimmed += group_trimmed;
+ if (ret) {
+ btrfs_put_block_group(cache);
+ break;
+ }
+ }
+
+ cache = next_block_group(fs_info->tree_root, cache);
+ }
+
+ range->len = trimmed;
+ return ret;
}
git.openpandora.org / pandora-kernel.git / blobdiff