#include <linux/btrfs.h>
#include <linux/blkdev.h>
#include <linux/posix_acl_xattr.h>
+#include <linux/uio.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "backref.h"
#include "hash.h"
#include "props.h"
+#include "qgroup.h"
struct btrfs_iget_args {
struct btrfs_key *location;
static int btrfs_dirty_inode(struct inode *inode);
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode)
+{
+ BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
+}
+#endif
+
static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
struct inode *inode, struct inode *dir,
const struct qstr *qstr)
*/
if (inode_need_compress(inode)) {
WARN_ON(pages);
- pages = kzalloc(sizeof(struct page *) * nr_pages, GFP_NOFS);
+ pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
if (!pages) {
/* just bail out to the uncompressed code */
goto cont;
}
goto out_free;
}
-
/*
* here we're doing allocation and writeback of the
* compressed pages
u64 new_size;
/*
- * We need the largest size of the remaining extent to see if we
- * need to add a new outstanding extent. Think of the following
- * case
- *
- * [MEAX_EXTENT_SIZEx2 - 4k][4k]
- *
- * The new_size would just be 4k and we'd think we had enough
- * outstanding extents for this if we only took one side of the
- * split, same goes for the other direction. We need to see if
- * the larger size still is the same amount of extents as the
- * original size, because if it is we need to add a new
- * outstanding extent. But if we split up and the larger size
- * is less than the original then we are good to go since we've
- * already accounted for the extra extent in our original
- * accounting.
+ * See the explanation in btrfs_merge_extent_hook, the same
+ * applies here, just in reverse.
*/
new_size = orig->end - split + 1;
- if ((split - orig->start) > new_size)
- new_size = split - orig->start;
-
- num_extents = div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+ num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+ new_size = split - orig->start;
+ num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
BTRFS_MAX_EXTENT_SIZE);
- if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
- BTRFS_MAX_EXTENT_SIZE) < num_extents)
+ if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE) >= num_extents)
return;
}
if (!(other->state & EXTENT_DELALLOC))
return;
- old_size = other->end - other->start + 1;
- new_size = old_size + (new->end - new->start + 1);
+ if (new->start > other->start)
+ new_size = new->end - other->start + 1;
+ else
+ new_size = other->end - new->start + 1;
/* we're not bigger than the max, unreserve the space and go */
if (new_size <= BTRFS_MAX_EXTENT_SIZE) {
}
/*
- * If we grew by another max_extent, just return, we want to keep that
- * reserved amount.
+ * We have to add up either side to figure out how many extents were
+ * accounted for before we merged into one big extent. If the number of
+ * extents we accounted for is <= the amount we need for the new range
+ * then we can return, otherwise drop. Think of it like this
+ *
+ * [ 4k][MAX_SIZE]
+ *
+ * So we've grown the extent by a MAX_SIZE extent, this would mean we
+ * need 2 outstanding extents, on one side we have 1 and the other side
+ * we have 1 so they are == and we can return. But in this case
+ *
+ * [MAX_SIZE+4k][MAX_SIZE+4k]
+ *
+ * Each range on their own accounts for 2 extents, but merged together
+ * they are only 3 extents worth of accounting, so we need to drop in
+ * this case.
*/
+ old_size = other->end - other->start + 1;
num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
BTRFS_MAX_EXTENT_SIZE);
+ old_size = new->end - new->start + 1;
+ num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+
if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
- BTRFS_MAX_EXTENT_SIZE) > num_extents)
+ BTRFS_MAX_EXTENT_SIZE) >= num_extents)
return;
spin_lock(&BTRFS_I(inode)->lock);
spin_unlock(&BTRFS_I(inode)->lock);
}
+ /* For sanity tests */
+ if (btrfs_test_is_dummy_root(root))
+ return;
+
__percpu_counter_add(&root->fs_info->delalloc_bytes, len,
root->fs_info->delalloc_batch);
spin_lock(&BTRFS_I(inode)->lock);
root != root->fs_info->tree_root)
btrfs_delalloc_release_metadata(inode, len);
+ /* For sanity tests. */
+ if (btrfs_test_is_dummy_root(root))
+ return;
+
if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
&& do_list && !(state->state & EXTENT_NORESERVE))
btrfs_free_reserved_data_space(inode, len);
if (empty)
return;
+ down_read(&fs_info->delayed_iput_sem);
+
spin_lock(&fs_info->delayed_iput_lock);
list_splice_init(&fs_info->delayed_iputs, &list);
spin_unlock(&fs_info->delayed_iput_lock);
iput(delayed->inode);
kfree(delayed);
}
+
+ up_read(&root->fs_info->delayed_iput_sem);
}
/*
BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item);
+ inode->i_version = btrfs_inode_sequence(leaf, inode_item);
+ inode->i_generation = BTRFS_I(inode)->generation;
+ inode->i_rdev = 0;
+ rdev = btrfs_inode_rdev(leaf, inode_item);
+
+ BTRFS_I(inode)->index_cnt = (u64)-1;
+ BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
+
+cache_index:
/*
* If we were modified in the current generation and evicted from memory
* and then re-read we need to do a full sync since we don't have any
* idea about which extents were modified before we were evicted from
* cache.
+ *
+ * This is required for both inode re-read from disk and delayed inode
+ * in delayed_nodes_tree.
*/
if (BTRFS_I(inode)->last_trans == root->fs_info->generation)
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
- inode->i_version = btrfs_inode_sequence(leaf, inode_item);
- inode->i_generation = BTRFS_I(inode)->generation;
- inode->i_rdev = 0;
- rdev = btrfs_inode_rdev(leaf, inode_item);
-
- BTRFS_I(inode)->index_cnt = (u64)-1;
- BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
-
-cache_index:
path->slots[0]++;
if (inode->i_nlink != 1 ||
path->slots[0] >= btrfs_header_nritems(leaf))
return err;
}
+static int truncate_space_check(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ u64 bytes_deleted)
+{
+ int ret;
+
+ bytes_deleted = btrfs_csum_bytes_to_leaves(root, bytes_deleted);
+ ret = btrfs_block_rsv_add(root, &root->fs_info->trans_block_rsv,
+ bytes_deleted, BTRFS_RESERVE_NO_FLUSH);
+ if (!ret)
+ trans->bytes_reserved += bytes_deleted;
+ return ret;
+
+}
+
/*
* this can truncate away extent items, csum items and directory items.
* It starts at a high offset and removes keys until it can't find
int ret;
int err = 0;
u64 ino = btrfs_ino(inode);
+ u64 bytes_deleted = 0;
+ bool be_nice = 0;
+ bool should_throttle = 0;
+ bool should_end = 0;
BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);
+ /*
+ * for non-free space inodes and ref cows, we want to back off from
+ * time to time
+ */
+ if (!btrfs_is_free_space_inode(inode) &&
+ test_bit(BTRFS_ROOT_REF_COWS, &root->state))
+ be_nice = 1;
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
key.type = (u8)-1;
search_again:
+ /*
+ * with a 16K leaf size and 128MB extents, you can actually queue
+ * up a huge file in a single leaf. Most of the time that
+ * bytes_deleted is > 0, it will be huge by the time we get here
+ */
+ if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+ if (btrfs_should_end_transaction(trans, root)) {
+ err = -EAGAIN;
+ goto error;
+ }
+ }
+
+
path->leave_spinning = 1;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
if (ret < 0) {
} else {
break;
}
+ should_throttle = 0;
+
if (found_extent &&
(test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
root == root->fs_info->tree_root)) {
btrfs_set_path_blocking(path);
+ bytes_deleted += extent_num_bytes;
ret = btrfs_free_extent(trans, root, extent_start,
extent_num_bytes, 0,
btrfs_header_owner(leaf),
ino, extent_offset, 0);
BUG_ON(ret);
+ if (btrfs_should_throttle_delayed_refs(trans, root))
+ btrfs_async_run_delayed_refs(root,
+ trans->delayed_ref_updates * 2, 0);
+ if (be_nice) {
+ if (truncate_space_check(trans, root,
+ extent_num_bytes)) {
+ should_end = 1;
+ }
+ if (btrfs_should_throttle_delayed_refs(trans,
+ root)) {
+ should_throttle = 1;
+ }
+ }
}
if (found_type == BTRFS_INODE_ITEM_KEY)
break;
if (path->slots[0] == 0 ||
- path->slots[0] != pending_del_slot) {
+ path->slots[0] != pending_del_slot ||
+ should_throttle || should_end) {
if (pending_del_nr) {
ret = btrfs_del_items(trans, root, path,
pending_del_slot,
pending_del_nr = 0;
}
btrfs_release_path(path);
+ if (should_throttle) {
+ unsigned long updates = trans->delayed_ref_updates;
+ if (updates) {
+ trans->delayed_ref_updates = 0;
+ ret = btrfs_run_delayed_refs(trans, root, updates * 2);
+ if (ret && !err)
+ err = ret;
+ }
+ }
+ /*
+ * if we failed to refill our space rsv, bail out
+ * and let the transaction restart
+ */
+ if (should_end) {
+ err = -EAGAIN;
+ goto error;
+ }
goto search_again;
} else {
path->slots[0]--;
if (last_size != (u64)-1 &&
root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
btrfs_ordered_update_i_size(inode, last_size, NULL);
+
btrfs_free_path(path);
+
+ if (be_nice && bytes_deleted > 32 * 1024 * 1024) {
+ unsigned long updates = trans->delayed_ref_updates;
+ if (updates) {
+ trans->delayed_ref_updates = 0;
+ ret = btrfs_run_delayed_refs(trans, root, updates * 2);
+ if (ret && !err)
+ err = ret;
+ }
+ }
return err;
}
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_block_rsv *rsv, *global_rsv;
+ int steal_from_global = 0;
u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
int ret;
* hard as possible to get this to work.
*/
if (ret)
- ret = btrfs_block_rsv_migrate(global_rsv, rsv, min_size);
+ steal_from_global++;
+ else
+ steal_from_global = 0;
+ ret = 0;
- if (ret) {
+ /*
+ * steal_from_global == 0: we reserved stuff, hooray!
+ * steal_from_global == 1: we didn't reserve stuff, boo!
+ * steal_from_global == 2: we've committed, still not a lot of
+ * room but maybe we'll have room in the global reserve this
+ * time.
+ * steal_from_global == 3: abandon all hope!
+ */
+ if (steal_from_global > 2) {
btrfs_warn(root->fs_info,
"Could not get space for a delete, will truncate on mount %d",
ret);
goto no_delete;
}
+ /*
+ * We can't just steal from the global reserve, we need tomake
+ * sure there is room to do it, if not we need to commit and try
+ * again.
+ */
+ if (steal_from_global) {
+ if (!btrfs_check_space_for_delayed_refs(trans, root))
+ ret = btrfs_block_rsv_migrate(global_rsv, rsv,
+ min_size);
+ else
+ ret = -ENOSPC;
+ }
+
+ /*
+ * Couldn't steal from the global reserve, we have too much
+ * pending stuff built up, commit the transaction and try it
+ * again.
+ */
+ if (ret) {
+ ret = btrfs_commit_transaction(trans, root);
+ if (ret) {
+ btrfs_orphan_del(NULL, inode);
+ btrfs_free_block_rsv(root, rsv);
+ goto no_delete;
+ }
+ continue;
+ } else {
+ steal_from_global = 0;
+ }
+
trans->block_rsv = rsv;
ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0);
- if (ret != -ENOSPC)
+ if (ret != -ENOSPC && ret != -EAGAIN)
break;
trans->block_rsv = &root->fs_info->trans_block_rsv;
u64 start = iblock << inode->i_blkbits;
u64 lockstart, lockend;
u64 len = bh_result->b_size;
- u64 orig_len = len;
+ u64 *outstanding_extents = NULL;
int unlock_bits = EXTENT_LOCKED;
int ret = 0;
lockstart = start;
lockend = start + len - 1;
+ if (current->journal_info) {
+ /*
+ * Need to pull our outstanding extents and set journal_info to NULL so
+ * that anything that needs to check if there's a transction doesn't get
+ * confused.
+ */
+ outstanding_extents = current->journal_info;
+ current->journal_info = NULL;
+ }
+
/*
* If this errors out it's because we couldn't invalidate pagecache for
* this range and we need to fallback to buffered.
if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
- if (len < orig_len) {
+ /*
+ * If we have an outstanding_extents count still set then we're
+ * within our reservation, otherwise we need to adjust our inode
+ * counter appropriately.
+ */
+ if (*outstanding_extents) {
+ (*outstanding_extents)--;
+ } else {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
}
+
+ current->journal_info = outstanding_extents;
btrfs_free_reserved_data_space(inode, len);
}
unlock_err:
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
+ if (outstanding_extents)
+ current->journal_info = outstanding_extents;
return ret;
}
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ u64 outstanding_extents = 0;
size_t count = 0;
int flags = 0;
bool wakeup = true;
ret = btrfs_delalloc_reserve_space(inode, count);
if (ret)
goto out;
+ outstanding_extents = div64_u64(count +
+ BTRFS_MAX_EXTENT_SIZE - 1,
+ BTRFS_MAX_EXTENT_SIZE);
+
+ /*
+ * We need to know how many extents we reserved so that we can
+ * do the accounting properly if we go over the number we
+ * originally calculated. Abuse current->journal_info for this.
+ */
+ current->journal_info = &outstanding_extents;
} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags)) {
inode_dio_done(inode);
iter, offset, btrfs_get_blocks_direct, NULL,
btrfs_submit_direct, flags);
if (rw & WRITE) {
+ current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED)
btrfs_delalloc_release_space(inode, count);
else if (ret >= 0 && (size_t)ret < count)
ret = btrfs_truncate_inode_items(trans, root, inode,
inode->i_size,
BTRFS_EXTENT_DATA_KEY);
- if (ret != -ENOSPC) {
+ if (ret != -ENOSPC && ret != -EAGAIN) {
err = ret;
break;
}
btrfs_end_transaction(trans, root);
break;
}
+
btrfs_drop_extent_cache(inode, cur_offset,
cur_offset + ins.offset -1, 0);
projects / deliverable / linux.git / blobdiff