* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (62 commits)
Btrfs: use larger system chunks
Btrfs: add a delalloc mutex to inodes for delalloc reservations
Btrfs: space leak tracepoints
Btrfs: protect orphan block rsv with spin_lock
Btrfs: add allocator tracepoints
Btrfs: don't call btrfs_throttle in file write
Btrfs: release space on error in page_mkwrite
Btrfs: fix btrfsck error 400 when truncating a compressed
Btrfs: do not use btrfs_end_transaction_throttle everywhere
Btrfs: add balance progress reporting
Btrfs: allow for resuming restriper after it was paused
Btrfs: allow for canceling restriper
Btrfs: allow for pausing restriper
Btrfs: add skip_balance mount option
Btrfs: recover balance on mount
Btrfs: save balance parameters to disk
Btrfs: soft profile changing mode (aka soft convert)
Btrfs: implement online profile changing
Btrfs: do not reduce profile in do_chunk_alloc()
Btrfs: virtual address space subset filter
...
Fix up trivial conflict in fs/btrfs/ioctl.c due to the use of the new
mnt_drop_write_file() helper.
#include "tree-log.h"
#include "free-space-cache.h"
#include "inode-map.h"
+ #include "check-integrity.h"
static struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
/*
* we can't safely write a btree page from here,
if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page);
+ return migrate_page(mapping, newpage, page, mode);
}
#endif
root->ref_cows = 0;
leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
- BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0);
+ BTRFS_TREE_LOG_OBJECTID, NULL,
+ 0, 0, 0, 0);
if (IS_ERR(leaf)) {
kfree(root);
return ERR_CAST(leaf);
btrfs_run_defrag_inodes(root->fs_info);
}
- if (freezing(current)) {
- refrigerator();
- } else {
+ if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop())
schedule();
wake_up_process(root->fs_info->cleaner_kthread);
mutex_unlock(&root->fs_info->transaction_kthread_mutex);
- if (freezing(current)) {
- refrigerator();
- } else {
+ if (!try_to_freeze()) {
set_current_state(TASK_INTERRUPTIBLE);
if (!kthread_should_stop() &&
!btrfs_transaction_blocked(root->fs_info))
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;
+ #endif
+
+ spin_lock_init(&fs_info->balance_lock);
+ mutex_init(&fs_info->balance_mutex);
+ atomic_set(&fs_info->balance_running, 0);
+ atomic_set(&fs_info->balance_pause_req, 0);
+ atomic_set(&fs_info->balance_cancel_req, 0);
+ fs_info->balance_ctl = NULL;
+ init_waitqueue_head(&fs_info->balance_wait_q);
sb->s_blocksize = 4096;
sb->s_blocksize_bits = blksize_bits(4096);
(unsigned long)btrfs_header_chunk_tree_uuid(chunk_root->node),
BTRFS_UUID_SIZE);
- mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_chunk_tree(chunk_root);
- mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n",
sb->s_id);
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
- fs_info->data_alloc_profile = (u64)-1;
- fs_info->metadata_alloc_profile = (u64)-1;
- fs_info->system_alloc_profile = fs_info->metadata_alloc_profile;
ret = btrfs_init_space_info(fs_info);
if (ret) {
btrfs_set_opt(fs_info->mount_opt, SSD);
}
+ #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
+ ret = btrfsic_mount(tree_root, fs_devices,
+ btrfs_test_opt(tree_root,
+ CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ?
+ 1 : 0,
+ fs_info->check_integrity_print_mask);
+ if (ret)
+ printk(KERN_WARNING "btrfs: failed to initialize"
+ " integrity check module %s\n", sb->s_id);
+ }
+ #endif
+
/* do not make disk changes in broken FS */
if (btrfs_super_log_root(disk_super) != 0 &&
!(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) {
if (!err)
err = btrfs_orphan_cleanup(fs_info->tree_root);
up_read(&fs_info->cleanup_work_sem);
+
+ if (!err)
+ err = btrfs_recover_balance(fs_info->tree_root);
+
if (err) {
close_ctree(tree_root);
return ERR_PTR(err);
* we fua the first super. The others we allow
* to go down lazy.
*/
- ret = submit_bh(WRITE_FUA, bh);
+ ret = btrfsic_submit_bh(WRITE_FUA, bh);
if (ret)
errors++;
}
device->flush_bio = bio;
bio_get(bio);
- submit_bio(WRITE_FLUSH, bio);
+ btrfsic_submit_bio(WRITE_FLUSH, bio);
return 0;
}
fs_info->closing = 1;
smp_mb();
+ /* pause restriper - we want to resume on mount */
+ btrfs_pause_balance(root->fs_info);
+
btrfs_scrub_cancel(root);
/* wait for any defraggers to finish */
btrfs_stop_workers(&fs_info->caching_workers);
btrfs_stop_workers(&fs_info->readahead_workers);
+ #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ if (btrfs_test_opt(root, CHECK_INTEGRITY))
+ btrfsic_unmount(root, fs_info->fs_devices);
+ #endif
+
btrfs_close_devices(fs_info->fs_devices);
btrfs_mapping_tree_free(&fs_info->mapping_tree);
disk_bytenr, num_bytes, 0,
root->root_key.objectid,
new_key.objectid,
- start - extent_offset);
+ start - extent_offset, 0);
BUG_ON(ret);
*hint_byte = disk_bytenr;
}
disk_bytenr, num_bytes, 0,
root->root_key.objectid,
key.objectid, key.offset -
- extent_offset);
+ extent_offset, 0);
BUG_ON(ret);
inode_sub_bytes(inode,
extent_end - key.offset);
ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
root->root_key.objectid,
- ino, orig_offset);
+ ino, orig_offset, 0);
BUG_ON(ret);
if (split == start) {
del_nr++;
ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
0, root->root_key.objectid,
- ino, orig_offset);
+ ino, orig_offset, 0);
BUG_ON(ret);
}
other_start = 0;
del_nr++;
ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
0, root->root_key.objectid,
- ino, orig_offset);
+ ino, orig_offset, 0);
BUG_ON(ret);
}
if (del_nr == 0) {
again:
for (i = 0; i < num_pages; i++) {
pages[i] = find_or_create_page(inode->i_mapping, index + i,
- mask);
+ mask | __GFP_WRITE);
if (!pages[i]) {
faili = i - 1;
err = -ENOMEM;
GFP_NOFS);
}
for (i = 0; i < num_pages; i++) {
- clear_page_dirty_for_io(pages[i]);
+ if (clear_page_dirty_for_io(pages[i]))
+ account_page_redirty(pages[i]);
set_page_extent_mapped(pages[i]);
WARN_ON(!PageLocked(pages[i]));
}
dirty_pages);
if (dirty_pages < (root->leafsize >> PAGE_CACHE_SHIFT) + 1)
btrfs_btree_balance_dirty(root, 1);
- btrfs_throttle(root);
pos += copied;
num_written += copied;
io_ctl_unmap_page(io_ctl);
for (i = 0; i < io_ctl->num_pages; i++) {
- ClearPageChecked(io_ctl->pages[i]);
- unlock_page(io_ctl->pages[i]);
- page_cache_release(io_ctl->pages[i]);
+ if (io_ctl->pages[i]) {
+ ClearPageChecked(io_ctl->pages[i]);
+ unlock_page(io_ctl->pages[i]);
+ page_cache_release(io_ctl->pages[i]);
+ }
}
}
}
if (index == 0)
- offset = sizeof(u32) * io_ctl->num_pages;;
+ offset = sizeof(u32) * io_ctl->num_pages;
crc = btrfs_csum_data(io_ctl->root, io_ctl->orig + offset, crc,
PAGE_CACHE_SIZE - offset);
if (!num_entries)
return 0;
- io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root);
+ if (ret)
+ return ret;
+
ret = readahead_cache(inode);
if (ret)
goto out;
struct io_ctl io_ctl;
struct list_head bitmap_list;
struct btrfs_key key;
- u64 start, end, len;
+ u64 start, extent_start, extent_end, len;
int entries = 0;
int bitmaps = 0;
int ret;
if (!i_size_read(inode))
return -1;
- io_ctl_init(&io_ctl, inode, root);
+ ret = io_ctl_init(&io_ctl, inode, root);
+ if (ret)
+ return -1;
/* Get the cluster for this block_group if it exists */
if (block_group && !list_empty(&block_group->cluster_list))
struct btrfs_free_cluster,
block_group_list);
- /*
- * We shouldn't have switched the pinned extents yet so this is the
- * right one
- */
- unpin = root->fs_info->pinned_extents;
-
/* Lock all pages first so we can lock the extent safely. */
io_ctl_prepare_pages(&io_ctl, inode, 0);
lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
0, &cached_state, GFP_NOFS);
- /*
- * When searching for pinned extents, we need to start at our start
- * offset.
- */
- if (block_group)
- start = block_group->key.objectid;
-
node = rb_first(&ctl->free_space_offset);
if (!node && cluster) {
node = rb_first(&cluster->root);
* We want to add any pinned extents to our free space cache
* so we don't leak the space
*/
+
+ /*
+ * We shouldn't have switched the pinned extents yet so this is the
+ * right one
+ */
+ unpin = root->fs_info->pinned_extents;
+
+ if (block_group)
+ start = block_group->key.objectid;
+
while (block_group && (start < block_group->key.objectid +
block_group->key.offset)) {
- ret = find_first_extent_bit(unpin, start, &start, &end,
+ ret = find_first_extent_bit(unpin, start,
+ &extent_start, &extent_end,
EXTENT_DIRTY);
if (ret) {
ret = 0;
}
/* This pinned extent is out of our range */
- if (start >= block_group->key.objectid +
+ if (extent_start >= block_group->key.objectid +
block_group->key.offset)
break;
- len = block_group->key.objectid +
- block_group->key.offset - start;
- len = min(len, end + 1 - start);
+ extent_start = max(extent_start, start);
+ extent_end = min(block_group->key.objectid +
+ block_group->key.offset, extent_end + 1);
+ len = extent_end - extent_start;
entries++;
- ret = io_ctl_add_entry(&io_ctl, start, len, NULL);
+ ret = io_ctl_add_entry(&io_ctl, extent_start, len, NULL);
if (ret)
goto out_nospc;
- start = end + 1;
+ start = extent_end;
}
/* Write out the bitmaps */
static int btrfs_bitmap_cluster(struct btrfs_block_group_cache *block_group,
struct btrfs_free_space *entry,
struct btrfs_free_cluster *cluster,
- u64 offset, u64 bytes, u64 min_bytes)
+ u64 offset, u64 bytes,
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
unsigned long next_zero;
unsigned long i;
- unsigned long search_bits;
- unsigned long total_bits;
+ unsigned long want_bits;
+ unsigned long min_bits;
unsigned long found_bits;
unsigned long start = 0;
unsigned long total_found = 0;
int ret;
- bool found = false;
i = offset_to_bit(entry->offset, block_group->sectorsize,
max_t(u64, offset, entry->offset));
- search_bits = bytes_to_bits(bytes, block_group->sectorsize);
- total_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
+ want_bits = bytes_to_bits(bytes, block_group->sectorsize);
+ min_bits = bytes_to_bits(min_bytes, block_group->sectorsize);
again:
found_bits = 0;
i = find_next_bit(entry->bitmap, BITS_PER_BITMAP, i + 1)) {
next_zero = find_next_zero_bit(entry->bitmap,
BITS_PER_BITMAP, i);
- if (next_zero - i >= search_bits) {
+ if (next_zero - i >= min_bits) {
found_bits = next_zero - i;
break;
}
if (!found_bits)
return -ENOSPC;
- if (!found) {
+ if (!total_found) {
start = i;
cluster->max_size = 0;
- found = true;
}
total_found += found_bits;
if (cluster->max_size < found_bits * block_group->sectorsize)
cluster->max_size = found_bits * block_group->sectorsize;
- if (total_found < total_bits) {
- i = find_next_bit(entry->bitmap, BITS_PER_BITMAP, next_zero);
- if (i - start > total_bits * 2) {
- total_found = 0;
- cluster->max_size = 0;
- found = false;
- }
+ if (total_found < want_bits || cluster->max_size < cont1_bytes) {
+ i = next_zero + 1;
goto again;
}
&entry->offset_index, 1);
BUG_ON(ret);
+ trace_btrfs_setup_cluster(block_group, cluster,
+ total_found * block_group->sectorsize, 1);
return 0;
}
/*
* This searches the block group for just extents to fill the cluster with.
+ * Try to find a cluster with at least bytes total bytes, at least one
+ * extent of cont1_bytes, and other clusters of at least min_bytes.
*/
static noinline int
setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
- u64 min_bytes)
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *first = NULL;
struct btrfs_free_space *entry = NULL;
- struct btrfs_free_space *prev = NULL;
struct btrfs_free_space *last;
struct rb_node *node;
u64 window_start;
u64 window_free;
u64 max_extent;
- u64 max_gap = 128 * 1024;
+ u64 total_size = 0;
entry = tree_search_offset(ctl, offset, 0, 1);
if (!entry)
* We don't want bitmaps, so just move along until we find a normal
* extent entry.
*/
- while (entry->bitmap) {
- if (list_empty(&entry->list))
+ while (entry->bitmap || entry->bytes < min_bytes) {
+ if (entry->bitmap && list_empty(&entry->list))
list_add_tail(&entry->list, bitmaps);
node = rb_next(&entry->offset_index);
if (!node)
max_extent = entry->bytes;
first = entry;
last = entry;
- prev = entry;
- while (window_free <= min_bytes) {
- node = rb_next(&entry->offset_index);
- if (!node)
- return -ENOSPC;
+ for (node = rb_next(&entry->offset_index); node;
+ node = rb_next(&entry->offset_index)) {
entry = rb_entry(node, struct btrfs_free_space, offset_index);
if (entry->bitmap) {
continue;
}
- /*
- * we haven't filled the empty size and the window is
- * very large. reset and try again
- */
- if (entry->offset - (prev->offset + prev->bytes) > max_gap ||
- entry->offset - window_start > (min_bytes * 2)) {
- first = entry;
- window_start = entry->offset;
- window_free = entry->bytes;
- last = entry;
+ if (entry->bytes < min_bytes)
+ continue;
+
+ last = entry;
+ window_free += entry->bytes;
+ if (entry->bytes > max_extent)
max_extent = entry->bytes;
- } else {
- last = entry;
- window_free += entry->bytes;
- if (entry->bytes > max_extent)
- max_extent = entry->bytes;
- }
- prev = entry;
}
+ if (window_free < bytes || max_extent < cont1_bytes)
+ return -ENOSPC;
+
cluster->window_start = first->offset;
node = &first->offset_index;
entry = rb_entry(node, struct btrfs_free_space, offset_index);
node = rb_next(&entry->offset_index);
- if (entry->bitmap)
+ if (entry->bitmap || entry->bytes < min_bytes)
continue;
rb_erase(&entry->offset_index, &ctl->free_space_offset);
ret = tree_insert_offset(&cluster->root, entry->offset,
&entry->offset_index, 0);
+ total_size += entry->bytes;
BUG_ON(ret);
} while (node && entry != last);
cluster->max_size = max_extent;
-
+ trace_btrfs_setup_cluster(block_group, cluster, total_size, 0);
return 0;
}
setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_cluster *cluster,
struct list_head *bitmaps, u64 offset, u64 bytes,
- u64 min_bytes)
+ u64 cont1_bytes, u64 min_bytes)
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *entry;
if (entry->bytes < min_bytes)
continue;
ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
- bytes, min_bytes);
+ bytes, cont1_bytes, min_bytes);
if (!ret)
return 0;
}
/*
* here we try to find a cluster of blocks in a block group. The goal
- * is to find at least bytes free and up to empty_size + bytes free.
+ * is to find at least bytes+empty_size.
* We might not find them all in one contiguous area.
*
* returns zero and sets up cluster if things worked out, otherwise
struct btrfs_free_space *entry, *tmp;
LIST_HEAD(bitmaps);
u64 min_bytes;
+ u64 cont1_bytes;
int ret;
- /* for metadata, allow allocates with more holes */
+ /*
+ * Choose the minimum extent size we'll require for this
+ * cluster. For SSD_SPREAD, don't allow any fragmentation.
+ * For metadata, allow allocates with smaller extents. For
+ * data, keep it dense.
+ */
if (btrfs_test_opt(root, SSD_SPREAD)) {
- min_bytes = bytes + empty_size;
+ cont1_bytes = min_bytes = bytes + empty_size;
} else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
- /*
- * we want to do larger allocations when we are
- * flushing out the delayed refs, it helps prevent
- * making more work as we go along.
- */
- if (trans->transaction->delayed_refs.flushing)
- min_bytes = max(bytes, (bytes + empty_size) >> 1);
- else
- min_bytes = max(bytes, (bytes + empty_size) >> 4);
- } else
- min_bytes = max(bytes, (bytes + empty_size) >> 2);
+ cont1_bytes = bytes;
+ min_bytes = block_group->sectorsize;
+ } else {
+ cont1_bytes = max(bytes, (bytes + empty_size) >> 2);
+ min_bytes = block_group->sectorsize;
+ }
spin_lock(&ctl->tree_lock);
* If we know we don't have enough space to make a cluster don't even
* bother doing all the work to try and find one.
*/
- if (ctl->free_space < min_bytes) {
+ if (ctl->free_space < bytes) {
spin_unlock(&ctl->tree_lock);
return -ENOSPC;
}
goto out;
}
+ trace_btrfs_find_cluster(block_group, offset, bytes, empty_size,
+ min_bytes);
+
+ INIT_LIST_HEAD(&bitmaps);
ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
- bytes, min_bytes);
+ bytes + empty_size,
+ cont1_bytes, min_bytes);
if (ret)
ret = setup_cluster_bitmap(block_group, cluster, &bitmaps,
- offset, bytes, min_bytes);
+ offset, bytes + empty_size,
+ cont1_bytes, min_bytes);
/* Clear our temporary list */
list_for_each_entry_safe(entry, tmp, &bitmaps, list)
list_add_tail(&cluster->block_group_list,
&block_group->cluster_list);
cluster->block_group = block_group;
+ } else {
+ trace_btrfs_failed_cluster_setup(block_group);
}
out:
spin_unlock(&cluster->lock);
cluster->block_group = NULL;
}
- int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
- u64 *trimmed, u64 start, u64 end, u64 minlen)
+ static int do_trimming(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 bytes,
+ u64 reserved_start, u64 reserved_bytes)
{
- struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
- struct btrfs_free_space *entry = NULL;
+ struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_fs_info *fs_info = block_group->fs_info;
- u64 bytes = 0;
- u64 actually_trimmed;
- int ret = 0;
+ int ret;
+ int update = 0;
+ u64 trimmed = 0;
- *trimmed = 0;
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ if (!block_group->ro) {
+ block_group->reserved += reserved_bytes;
+ space_info->bytes_reserved += reserved_bytes;
+ update = 1;
+ }
+ spin_unlock(&block_group->lock);
+ spin_unlock(&space_info->lock);
+
+ ret = btrfs_error_discard_extent(fs_info->extent_root,
+ start, bytes, &trimmed);
+ if (!ret)
+ *total_trimmed += trimmed;
+
+ btrfs_add_free_space(block_group, reserved_start, reserved_bytes);
+
+ if (update) {
+ spin_lock(&space_info->lock);
+ spin_lock(&block_group->lock);
+ if (block_group->ro)
+ space_info->bytes_readonly += reserved_bytes;
+ block_group->reserved -= reserved_bytes;
+ space_info->bytes_reserved -= reserved_bytes;
+ spin_unlock(&space_info->lock);
+ spin_unlock(&block_group->lock);
+ }
+
+ return ret;
+ }
+
+ static int trim_no_bitmap(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 end, u64 minlen)
+ {
+ struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+ struct btrfs_free_space *entry;
+ struct rb_node *node;
+ int ret = 0;
+ u64 extent_start;
+ u64 extent_bytes;
+ u64 bytes;
while (start < end) {
spin_lock(&ctl->tree_lock);
}
entry = tree_search_offset(ctl, start, 0, 1);
- if (!entry)
- entry = tree_search_offset(ctl,
- offset_to_bitmap(ctl, start),
- 1, 1);
-
- if (!entry || entry->offset >= end) {
+ if (!entry) {
spin_unlock(&ctl->tree_lock);
break;
}
- if (entry->bitmap) {
- ret = search_bitmap(ctl, entry, &start, &bytes);
- if (!ret) {
- if (start >= end) {
- spin_unlock(&ctl->tree_lock);
- break;
- }
- bytes = min(bytes, end - start);
- bitmap_clear_bits(ctl, entry, start, bytes);
- if (entry->bytes == 0)
- free_bitmap(ctl, entry);
- } else {
- start = entry->offset + BITS_PER_BITMAP *
- block_group->sectorsize;
+ /* skip bitmaps */
+ while (entry->bitmap) {
+ node = rb_next(&entry->offset_index);
+ if (!node) {
spin_unlock(&ctl->tree_lock);
- ret = 0;
- continue;
+ goto out;
}
- } else {
- start = entry->offset;
- bytes = min(entry->bytes, end - start);
- unlink_free_space(ctl, entry);
- kmem_cache_free(btrfs_free_space_cachep, entry);
+ entry = rb_entry(node, struct btrfs_free_space,
+ offset_index);
}
+ if (entry->offset >= end) {
+ spin_unlock(&ctl->tree_lock);
+ break;
+ }
+
+ extent_start = entry->offset;
+ extent_bytes = entry->bytes;
+ start = max(start, extent_start);
+ bytes = min(extent_start + extent_bytes, end) - start;
+ if (bytes < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ goto next;
+ }
+
+ unlink_free_space(ctl, entry);
+ kmem_cache_free(btrfs_free_space_cachep, entry);
+
spin_unlock(&ctl->tree_lock);
- if (bytes >= minlen) {
- struct btrfs_space_info *space_info;
- int update = 0;
-
- space_info = block_group->space_info;
- spin_lock(&space_info->lock);
- spin_lock(&block_group->lock);
- if (!block_group->ro) {
- block_group->reserved += bytes;
- space_info->bytes_reserved += bytes;
- update = 1;
- }
- spin_unlock(&block_group->lock);
- spin_unlock(&space_info->lock);
-
- ret = btrfs_error_discard_extent(fs_info->extent_root,
- start,
- bytes,
- &actually_trimmed);
-
- btrfs_add_free_space(block_group, start, bytes);
- if (update) {
- spin_lock(&space_info->lock);
- spin_lock(&block_group->lock);
- if (block_group->ro)
- space_info->bytes_readonly += bytes;
- block_group->reserved -= bytes;
- space_info->bytes_reserved -= bytes;
- spin_unlock(&space_info->lock);
- spin_unlock(&block_group->lock);
- }
+ ret = do_trimming(block_group, total_trimmed, start, bytes,
+ extent_start, extent_bytes);
+ if (ret)
+ break;
+ next:
+ start += bytes;
- if (ret)
- break;
- *trimmed += actually_trimmed;
+ if (fatal_signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ cond_resched();
+ }
+ out:
+ return ret;
+ }
+
+ static int trim_bitmaps(struct btrfs_block_group_cache *block_group,
+ u64 *total_trimmed, u64 start, u64 end, u64 minlen)
+ {
+ struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
+ struct btrfs_free_space *entry;
+ int ret = 0;
+ int ret2;
+ u64 bytes;
+ u64 offset = offset_to_bitmap(ctl, start);
+
+ while (offset < end) {
+ bool next_bitmap = false;
+
+ spin_lock(&ctl->tree_lock);
+
+ if (ctl->free_space < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ break;
+ }
+
+ entry = tree_search_offset(ctl, offset, 1, 0);
+ if (!entry) {
+ spin_unlock(&ctl->tree_lock);
+ next_bitmap = true;
+ goto next;
+ }
+
+ bytes = minlen;
+ ret2 = search_bitmap(ctl, entry, &start, &bytes);
+ if (ret2 || start >= end) {
+ spin_unlock(&ctl->tree_lock);
+ next_bitmap = true;
+ goto next;
+ }
+
+ bytes = min(bytes, end - start);
+ if (bytes < minlen) {
+ spin_unlock(&ctl->tree_lock);
+ goto next;
+ }
+
+ bitmap_clear_bits(ctl, entry, start, bytes);
+ if (entry->bytes == 0)
+ free_bitmap(ctl, entry);
+
+ spin_unlock(&ctl->tree_lock);
+
+ ret = do_trimming(block_group, total_trimmed, start, bytes,
+ start, bytes);
+ if (ret)
+ break;
+ next:
+ if (next_bitmap) {
+ offset += BITS_PER_BITMAP * ctl->unit;
+ } else {
+ start += bytes;
+ if (start >= offset + BITS_PER_BITMAP * ctl->unit)
+ offset += BITS_PER_BITMAP * ctl->unit;
}
- start += bytes;
- bytes = 0;
if (fatal_signal_pending(current)) {
ret = -ERESTARTSYS;
return ret;
}
+ int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+ u64 *trimmed, u64 start, u64 end, u64 minlen)
+ {
+ int ret;
+
+ *trimmed = 0;
+
+ ret = trim_no_bitmap(block_group, trimmed, start, end, minlen);
+ if (ret)
+ return ret;
+
+ ret = trim_bitmaps(block_group, trimmed, start, end, minlen);
+
+ return ret;
+ }
+
/*
* Find the left-most item in the cache tree, and then return the
* smallest inode number in the item.
};
/*
- * This is called in transaction commmit time. If there are no orphan
+ * This is called in transaction commit time. If there are no orphan
* files in the subvolume, it removes orphan item and frees block_rsv
* structure.
*/
void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
+ struct btrfs_block_rsv *block_rsv;
int ret;
if (!list_empty(&root->orphan_list) ||
root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE)
return;
+ spin_lock(&root->orphan_lock);
+ if (!list_empty(&root->orphan_list)) {
+ spin_unlock(&root->orphan_lock);
+ return;
+ }
+
+ if (root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) {
+ spin_unlock(&root->orphan_lock);
+ return;
+ }
+
+ block_rsv = root->orphan_block_rsv;
+ root->orphan_block_rsv = NULL;
+ spin_unlock(&root->orphan_lock);
+
if (root->orphan_item_inserted &&
btrfs_root_refs(&root->root_item) > 0) {
ret = btrfs_del_orphan_item(trans, root->fs_info->tree_root,
root->orphan_item_inserted = 0;
}
- if (root->orphan_block_rsv) {
- WARN_ON(root->orphan_block_rsv->size > 0);
- btrfs_free_block_rsv(root, root->orphan_block_rsv);
- root->orphan_block_rsv = NULL;
+ if (block_rsv) {
+ WARN_ON(block_rsv->size > 0);
+ btrfs_free_block_rsv(root, block_rsv);
}
}
continue;
}
nr_truncate++;
- /*
- * Need to hold the imutex for reservation purposes, not
- * a huge deal here but I have a WARN_ON in
- * btrfs_delalloc_reserve_space to catch offenders.
- */
- mutex_lock(&inode->i_mutex);
ret = btrfs_truncate(inode);
- mutex_unlock(&inode->i_mutex);
} else {
nr_unlink++;
}
BUG_ON(!root->fs_info->enospc_unlink);
root->fs_info->enospc_unlink = 0;
}
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
int pending_del_nr = 0;
int pending_del_slot = 0;
int extent_type = -1;
- int encoding;
int ret;
int err = 0;
u64 ino = btrfs_ino(inode);
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
- encoding = 0;
if (found_key.objectid != ino)
break;
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
extent_type = btrfs_file_extent_type(leaf, fi);
- encoding = btrfs_file_extent_compression(leaf, fi);
- encoding |= btrfs_file_extent_encryption(leaf, fi);
- encoding |= btrfs_file_extent_other_encoding(leaf, fi);
-
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
item_end +=
btrfs_file_extent_num_bytes(leaf, fi);
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
u64 num_dec;
extent_start = btrfs_file_extent_disk_bytenr(leaf, fi);
- if (!del_item && !encoding) {
+ if (!del_item) {
u64 orig_num_bytes =
btrfs_file_extent_num_bytes(leaf, fi);
extent_num_bytes = new_size -
ret = btrfs_free_extent(trans, root, extent_start,
extent_num_bytes, 0,
btrfs_header_owner(leaf),
- ino, extent_offset);
+ ino, extent_offset, 0);
BUG_ON(ret);
}
i_size_write(inode, newsize);
btrfs_ordered_update_i_size(inode, i_size_read(inode), NULL);
ret = btrfs_update_inode(trans, root, inode);
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
} else {
/*
struct btrfs_root *root,
struct inode *dir,
const char *name, int name_len,
- u64 ref_objectid, u64 objectid, int mode,
- u64 *index)
+ u64 ref_objectid, u64 objectid,
+ umode_t mode, u64 *index)
{
struct inode *inode;
struct btrfs_inode_item *inode_item;
}
static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
- int mode, dev_t rdev)
+ umode_t mode, dev_t rdev)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
}
out_unlock:
nr = trans->blocks_used;
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root, nr);
if (drop_inode) {
inode_dec_link_count(inode);
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
- int mode, struct nameidata *nd)
+ umode_t mode, struct nameidata *nd)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
}
out_unlock:
nr = trans->blocks_used;
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
}
nr = trans->blocks_used;
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
fail:
if (drop_inode) {
inode_dec_link_count(inode);
return err;
}
-static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode = NULL;
struct btrfs_trans_handle *trans;
out_fail:
nr = trans->blocks_used;
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
if (drop_on_err)
iput(inode);
btrfs_btree_balance_dirty(root, nr);
}
flush_dcache_page(page);
} else if (create && PageUptodate(page)) {
- WARN_ON(1);
+ BUG();
if (!trans) {
kunmap(page);
free_extent_map(em);
u64 page_start;
u64 page_end;
- /* Need this to keep space reservations serialized */
- mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
- mutex_unlock(&inode->i_mutex);
if (!ret)
ret = btrfs_update_time(vma->vm_file);
if (ret) {
if (!ret)
return VM_FAULT_LOCKED;
unlock_page(page);
- btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
out:
+ btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
return ret;
}
err = ret;
nr = trans->blocks_used;
- ret = btrfs_end_transaction_throttle(trans, root);
+ ret = btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root, nr);
}
extent_io_tree_init(&ei->io_tree, &inode->i_data);
extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
mutex_init(&ei->log_mutex);
+ mutex_init(&ei->delalloc_mutex);
btrfs_ordered_inode_tree_init(&ei->ordered_tree);
INIT_LIST_HEAD(&ei->i_orphan);
INIT_LIST_HEAD(&ei->delalloc_inodes);
static void btrfs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}
btrfs_end_log_trans(root);
}
out_fail:
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
up_read(&root->fs_info->subvol_sem);
if (!err)
d_instantiate(dentry, inode);
nr = trans->blocks_used;
- btrfs_end_transaction_throttle(trans, root);
+ btrfs_end_transaction(trans, root);
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
struct btrfs_trans_handle *trans;
unsigned int flags, oldflags;
int ret;
+ u64 ip_oldflags;
+ unsigned int i_oldflags;
if (btrfs_root_readonly(root))
return -EROFS;
mutex_lock(&inode->i_mutex);
+ ip_oldflags = ip->flags;
+ i_oldflags = inode->i_flags;
+
flags = btrfs_mask_flags(inode->i_mode, flags);
oldflags = btrfs_flags_to_ioctl(ip->flags);
if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
}
}
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
goto out_unlock;
ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
- trans = btrfs_join_transaction(root);
- BUG_ON(IS_ERR(trans));
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_drop;
+ }
btrfs_update_iflags(inode);
inode->i_ctime = CURRENT_TIME;
ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
btrfs_end_transaction(trans, root);
+ out_drop:
+ if (ret) {
+ ip->flags = ip_oldflags;
+ inode->i_flags = i_oldflags;
+ }
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
-
- ret = 0;
out_unlock:
mutex_unlock(&inode->i_mutex);
return ret;
return PTR_ERR(trans);
leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
- 0, objectid, NULL, 0, 0, 0);
+ 0, objectid, NULL, 0, 0, 0, 0);
if (IS_ERR(leaf)) {
ret = PTR_ERR(leaf);
goto fail;
return 0;
file_end = (isize - 1) >> PAGE_CACHE_SHIFT;
- mutex_lock(&inode->i_mutex);
ret = btrfs_delalloc_reserve_space(inode,
num_pages << PAGE_CACHE_SHIFT);
- mutex_unlock(&inode->i_mutex);
if (ret)
return ret;
again:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
- mutex_lock(&root->fs_info->volume_mutex);
sizestr = vol_args->name;
devstr = strchr(sizestr, ':');
if (devstr) {
printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
(unsigned long long)devid);
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
if (!strcmp(sizestr, "max"))
new_size = device->bdev->bd_inode->i_size;
new_size = memparse(sizestr, NULL);
if (new_size == 0) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
}
if (mod < 0) {
if (new_size > old_size) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
new_size = old_size - new_size;
} else if (mod > 0) {
if (new_size < 256 * 1024 * 1024) {
ret = -EINVAL;
- goto out_unlock;
+ goto out_free;
}
if (new_size > device->bdev->bd_inode->i_size) {
ret = -EFBIG;
- goto out_unlock;
+ goto out_free;
}
do_div(new_size, root->sectorsize);
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- goto out_unlock;
+ goto out_free;
}
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
ret = btrfs_shrink_device(device, new_size);
}
- out_unlock:
- mutex_unlock(&root->fs_info->volume_mutex);
+ out_free:
kfree(vol_args);
+ out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
goto out;
}
- err = mnt_want_write(file->f_path.mnt);
+ err = mnt_want_write_file(file);
if (err)
goto out;
dput(dentry);
out_unlock_dir:
mutex_unlock(&dir->i_mutex);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
out:
kfree(vol_args);
return err;
if (btrfs_root_readonly(root))
return -EROFS;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
return ret;
ret = -EINVAL;
}
out:
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return ret;
}
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
ret = btrfs_init_new_device(root, vol_args->name);
kfree(vol_args);
+ out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
if (root->fs_info->sb->s_flags & MS_RDONLY)
return -EROFS;
+ mutex_lock(&root->fs_info->volume_mutex);
+ if (root->fs_info->balance_ctl) {
+ printk(KERN_INFO "btrfs: balance in progress\n");
+ ret = -EINVAL;
+ goto out;
+ }
+
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args))
- return PTR_ERR(vol_args);
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
ret = btrfs_rm_device(root, vol_args->name);
kfree(vol_args);
+ out:
+ mutex_unlock(&root->fs_info->volume_mutex);
return ret;
}
if (btrfs_root_readonly(root))
return -EROFS;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
return ret;
disko, diskl, 0,
root->root_key.objectid,
btrfs_ino(inode),
- new_key.offset - datao);
+ new_key.offset - datao,
+ 0);
BUG_ON(ret);
}
} else if (type == BTRFS_FILE_EXTENT_INLINE) {
out_fput:
fput(src_file);
out_drop_write:
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return ret;
}
if (btrfs_root_readonly(root))
goto out;
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
goto out;
out_drop:
atomic_dec(&root->fs_info->open_ioctl_trans);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
out:
return ret;
}
atomic_dec(&root->fs_info->open_ioctl_trans);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return 0;
}
{
int ret = 0;
int size;
- u64 extent_offset;
+ u64 extent_item_pos;
struct btrfs_ioctl_logical_ino_args *loi;
struct btrfs_data_container *inodes = NULL;
struct btrfs_path *path = NULL;
}
ret = extent_from_logical(root->fs_info, loi->logical, path, &key);
+ btrfs_release_path(path);
if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK)
ret = -ENOENT;
if (ret < 0)
goto out;
- extent_offset = loi->logical - key.objectid;
+ extent_item_pos = loi->logical - key.objectid;
ret = iterate_extent_inodes(root->fs_info, path, key.objectid,
- extent_offset, build_ino_list, inodes);
+ extent_item_pos, build_ino_list,
+ inodes);
if (ret < 0)
goto out;
return ret;
}
+ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
+ struct btrfs_ioctl_balance_args *bargs)
+ {
+ struct btrfs_balance_control *bctl = fs_info->balance_ctl;
+
+ bargs->flags = bctl->flags;
+
+ if (atomic_read(&fs_info->balance_running))
+ bargs->state |= BTRFS_BALANCE_STATE_RUNNING;
+ if (atomic_read(&fs_info->balance_pause_req))
+ bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ;
+ if (atomic_read(&fs_info->balance_cancel_req))
+ bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ;
+
+ memcpy(&bargs->data, &bctl->data, sizeof(bargs->data));
+ memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta));
+ memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys));
+
+ if (lock) {
+ spin_lock(&fs_info->balance_lock);
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ spin_unlock(&fs_info->balance_lock);
+ } else {
+ memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat));
+ }
+ }
+
+ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg)
+ {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_ioctl_balance_args *bargs;
+ struct btrfs_balance_control *bctl;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (fs_info->sb->s_flags & MS_RDONLY)
+ return -EROFS;
+
+ mutex_lock(&fs_info->volume_mutex);
+ mutex_lock(&fs_info->balance_mutex);
+
+ if (arg) {
+ bargs = memdup_user(arg, sizeof(*bargs));
+ if (IS_ERR(bargs)) {
+ ret = PTR_ERR(bargs);
+ goto out;
+ }
+
+ if (bargs->flags & BTRFS_BALANCE_RESUME) {
+ if (!fs_info->balance_ctl) {
+ ret = -ENOTCONN;
+ goto out_bargs;
+ }
+
+ bctl = fs_info->balance_ctl;
+ spin_lock(&fs_info->balance_lock);
+ bctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
+ goto do_balance;
+ }
+ } else {
+ bargs = NULL;
+ }
+
+ if (fs_info->balance_ctl) {
+ ret = -EINPROGRESS;
+ goto out_bargs;
+ }
+
+ bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
+ if (!bctl) {
+ ret = -ENOMEM;
+ goto out_bargs;
+ }
+
+ bctl->fs_info = fs_info;
+ if (arg) {
+ memcpy(&bctl->data, &bargs->data, sizeof(bctl->data));
+ memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta));
+ memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys));
+
+ bctl->flags = bargs->flags;
+ } else {
+ /* balance everything - no filters */
+ bctl->flags |= BTRFS_BALANCE_TYPE_MASK;
+ }
+
+ do_balance:
+ ret = btrfs_balance(bctl, bargs);
+ /*
+ * bctl is freed in __cancel_balance or in free_fs_info if
+ * restriper was paused all the way until unmount
+ */
+ if (arg) {
+ if (copy_to_user(arg, bargs, sizeof(*bargs)))
+ ret = -EFAULT;
+ }
+
+ out_bargs:
+ kfree(bargs);
+ out:
+ mutex_unlock(&fs_info->balance_mutex);
+ mutex_unlock(&fs_info->volume_mutex);
+ return ret;
+ }
+
+ static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd)
+ {
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ switch (cmd) {
+ case BTRFS_BALANCE_CTL_PAUSE:
+ return btrfs_pause_balance(root->fs_info);
+ case BTRFS_BALANCE_CTL_CANCEL:
+ return btrfs_cancel_balance(root->fs_info);
+ }
+
+ return -EINVAL;
+ }
+
+ static long btrfs_ioctl_balance_progress(struct btrfs_root *root,
+ void __user *arg)
+ {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_ioctl_balance_args *bargs;
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ mutex_lock(&fs_info->balance_mutex);
+ if (!fs_info->balance_ctl) {
+ ret = -ENOTCONN;
+ goto out;
+ }
+
+ bargs = kzalloc(sizeof(*bargs), GFP_NOFS);
+ if (!bargs) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ update_ioctl_balance_args(fs_info, 1, bargs);
+
+ if (copy_to_user(arg, bargs, sizeof(*bargs)))
+ ret = -EFAULT;
+
+ kfree(bargs);
+ out:
+ mutex_unlock(&fs_info->balance_mutex);
+ return ret;
+ }
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
case BTRFS_IOC_DEV_INFO:
return btrfs_ioctl_dev_info(root, argp);
case BTRFS_IOC_BALANCE:
- return btrfs_balance(root->fs_info->dev_root);
+ return btrfs_ioctl_balance(root, NULL);
case BTRFS_IOC_CLONE:
return btrfs_ioctl_clone(file, arg, 0, 0, 0);
case BTRFS_IOC_CLONE_RANGE:
return btrfs_ioctl_scrub_cancel(root, argp);
case BTRFS_IOC_SCRUB_PROGRESS:
return btrfs_ioctl_scrub_progress(root, argp);
+ case BTRFS_IOC_BALANCE_V2:
+ return btrfs_ioctl_balance(root, argp);
+ case BTRFS_IOC_BALANCE_CTL:
+ return btrfs_ioctl_balance_ctl(root, arg);
+ case BTRFS_IOC_BALANCE_PROGRESS:
+ return btrfs_ioctl_balance_progress(root, argp);
}
return -ENOTTY;
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/cleancache.h>
-#include <linux/mnt_namespace.h>
#include <linux/ratelimit.h>
#include "compat.h"
#include "delayed-inode.h"
Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
- Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
- Opt_inode_cache, Opt_no_space_cache, Opt_recovery, Opt_err,
+ Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_inode_cache,
+ Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
+ Opt_check_integrity, Opt_check_integrity_including_extent_data,
+ Opt_check_integrity_print_mask,
+ Opt_err,
};
static match_table_t tokens = {
{Opt_inode_cache, "inode_cache"},
{Opt_no_space_cache, "nospace_cache"},
{Opt_recovery, "recovery"},
+ {Opt_skip_balance, "skip_balance"},
+ {Opt_check_integrity, "check_int"},
+ {Opt_check_integrity_including_extent_data, "check_int_data"},
+ {Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
{Opt_err, NULL},
};
printk(KERN_INFO "btrfs: enabling auto recovery");
btrfs_set_opt(info->mount_opt, RECOVERY);
break;
+ case Opt_skip_balance:
+ btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
+ break;
+ #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
+ case Opt_check_integrity_including_extent_data:
+ printk(KERN_INFO "btrfs: enabling check integrity"
+ " including extent data\n");
+ btrfs_set_opt(info->mount_opt,
+ CHECK_INTEGRITY_INCLUDING_EXTENT_DATA);
+ btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
+ break;
+ case Opt_check_integrity:
+ printk(KERN_INFO "btrfs: enabling check integrity\n");
+ btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
+ break;
+ case Opt_check_integrity_print_mask:
+ intarg = 0;
+ match_int(&args[0], &intarg);
+ if (intarg) {
+ info->check_integrity_print_mask = intarg;
+ printk(KERN_INFO "btrfs:"
+ " check_integrity_print_mask 0x%x\n",
+ info->check_integrity_print_mask);
+ }
+ break;
+ #else
+ case Opt_check_integrity_including_extent_data:
+ case Opt_check_integrity:
+ case Opt_check_integrity_print_mask:
+ printk(KERN_ERR "btrfs: support for check_integrity*"
+ " not compiled in!\n");
+ ret = -EINVAL;
+ goto out;
+ #endif
case Opt_err:
printk(KERN_INFO "btrfs: unrecognized mount option "
"'%s'\n", p);
return ret;
}
-static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
+static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
{
- struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
+ struct btrfs_root *root = btrfs_sb(dentry->d_sb);
struct btrfs_fs_info *info = root->fs_info;
char *compress_type;
seq_puts(seq, ",autodefrag");
if (btrfs_test_opt(root, INODE_MAP_CACHE))
seq_puts(seq, ",inode_cache");
+ if (btrfs_test_opt(root, SKIP_BALANCE))
+ seq_puts(seq, ",skip_balance");
return 0;
}