#include "block-group.h"
#include "backref.h"
#include "misc.h"
+#include "subpage.h"
/*
* Relocation overview
num_bytes, parent);
ref.real_root = root->root_key.objectid;
btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
- key.objectid, key.offset);
+ key.objectid, key.offset,
+ root->root_key.objectid, false);
ret = btrfs_inc_extent_ref(trans, &ref);
if (ret) {
btrfs_abort_transaction(trans, ret);
num_bytes, parent);
ref.real_root = root->root_key.objectid;
btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
- key.objectid, key.offset);
+ key.objectid, key.offset,
+ root->root_key.objectid, false);
ret = btrfs_free_extent(trans, &ref);
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_release_path(path);
path->lowest_level = level;
+ set_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
+ clear_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &src->state);
path->lowest_level = 0;
if (ret) {
if (ret > 0)
btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr,
blocksize, path->nodes[level]->start);
ref.skip_qgroup = true;
- btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
+ btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
+ 0, true);
ret = btrfs_inc_extent_ref(trans, &ref);
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
blocksize, 0);
ref.skip_qgroup = true;
- btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
+ btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid, 0,
+ true);
ret = btrfs_inc_extent_ref(trans, &ref);
if (ret) {
btrfs_abort_transaction(trans, ret);
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr,
blocksize, path->nodes[level]->start);
- btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
+ btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid,
+ 0, true);
ref.skip_qgroup = true;
ret = btrfs_free_extent(trans, &ref);
if (ret) {
btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr,
blocksize, 0);
- btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
+ btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid,
+ 0, true);
ref.skip_qgroup = true;
ret = btrfs_free_extent(trans, &ref);
if (ret) {
upper->eb->start);
ref.real_root = root->root_key.objectid;
btrfs_init_tree_ref(&ref, node->level,
- btrfs_header_owner(upper->eb));
+ btrfs_header_owner(upper->eb),
+ root->root_key.objectid, false);
ret = btrfs_inc_extent_ref(trans, &ref);
if (!ret)
ret = btrfs_drop_subtree(trans, root, eb,
list_add_tail(&node->list, &rc->backref_cache.changed);
} else {
path->lowest_level = node->level;
+ if (root == root->fs_info->chunk_root)
+ btrfs_reserve_chunk_metadata(trans, false);
ret = btrfs_search_slot(trans, root, key, path, 0, 1);
btrfs_release_path(path);
+ if (root == root->fs_info->chunk_root)
+ btrfs_trans_release_chunk_metadata(trans);
if (ret > 0)
ret = 0;
}
u64 num_bytes;
int nr;
int ret = 0;
+ u64 i_size = i_size_read(&inode->vfs_inode);
u64 prealloc_start = cluster->start - offset;
u64 prealloc_end = cluster->end - offset;
u64 cur_offset = prealloc_start;
- BUG_ON(cluster->start != cluster->boundary[0]);
- ret = btrfs_alloc_data_chunk_ondemand(inode,
- prealloc_end + 1 - prealloc_start);
- if (ret)
- return ret;
-
/*
- * On a zoned filesystem, we cannot preallocate the file region.
- * Instead, we dirty and fiemap_write the region.
+ * For subpage case, previous i_size may not be aligned to PAGE_SIZE.
+ * This means the range [i_size, PAGE_END + 1) is filled with zeros by
+ * btrfs_do_readpage() call of previously relocated file cluster.
+ *
+ * If the current cluster starts in the above range, btrfs_do_readpage()
+ * will skip the read, and relocate_one_page() will later writeback
+ * the padding zeros as new data, causing data corruption.
+ *
+ * Here we have to manually invalidate the range (i_size, PAGE_END + 1).
*/
- if (btrfs_is_zoned(inode->root->fs_info)) {
- struct btrfs_root *root = inode->root;
- struct btrfs_trans_handle *trans;
-
- end = cluster->end - offset + 1;
- trans = btrfs_start_transaction(root, 1);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
- inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
- i_size_write(&inode->vfs_inode, end);
- ret = btrfs_update_inode(trans, root, inode);
- if (ret) {
- btrfs_abort_transaction(trans, ret);
- btrfs_end_transaction(trans);
+ if (!IS_ALIGNED(i_size, PAGE_SIZE)) {
+ struct address_space *mapping = inode->vfs_inode.i_mapping;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ const u32 sectorsize = fs_info->sectorsize;
+ struct page *page;
+
+ ASSERT(sectorsize < PAGE_SIZE);
+ ASSERT(IS_ALIGNED(i_size, sectorsize));
+
+ /*
+ * Subpage can't handle page with DIRTY but without UPTODATE
+ * bit as it can lead to the following deadlock:
+ *
+ * btrfs_readpage()
+ * | Page already *locked*
+ * |- btrfs_lock_and_flush_ordered_range()
+ * |- btrfs_start_ordered_extent()
+ * |- extent_write_cache_pages()
+ * |- lock_page()
+ * We try to lock the page we already hold.
+ *
+ * Here we just writeback the whole data reloc inode, so that
+ * we will be ensured to have no dirty range in the page, and
+ * are safe to clear the uptodate bits.
+ *
+ * This shouldn't cause too much overhead, as we need to write
+ * the data back anyway.
+ */
+ ret = filemap_write_and_wait(mapping);
+ if (ret < 0)
return ret;
- }
- return btrfs_end_transaction(trans);
+ clear_extent_bits(&inode->io_tree, i_size,
+ round_up(i_size, PAGE_SIZE) - 1,
+ EXTENT_UPTODATE);
+ page = find_lock_page(mapping, i_size >> PAGE_SHIFT);
+ /*
+ * If page is freed we don't need to do anything then, as we
+ * will re-read the whole page anyway.
+ */
+ if (page) {
+ btrfs_subpage_clear_uptodate(fs_info, page, i_size,
+ round_up(i_size, PAGE_SIZE) - i_size);
+ unlock_page(page);
+ put_page(page);
+ }
}
+ BUG_ON(cluster->start != cluster->boundary[0]);
+ ret = btrfs_alloc_data_chunk_ondemand(inode,
+ prealloc_end + 1 - prealloc_start);
+ if (ret)
+ return ret;
+
btrfs_inode_lock(&inode->vfs_inode, 0);
for (nr = 0; nr < cluster->nr; nr++) {
start = cluster->boundary[nr] - offset;
}
/*
- * Allow error injection to test balance cancellation
+ * Allow error injection to test balance/relocation cancellation
*/
noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
{
return atomic_read(&fs_info->balance_cancel_req) ||
+ atomic_read(&fs_info->reloc_cancel_req) ||
fatal_signal_pending(current);
}
ALLOW_ERROR_INJECTION(btrfs_should_cancel_balance, TRUE);
-static int relocate_file_extent_cluster(struct inode *inode,
- struct file_extent_cluster *cluster)
+static u64 get_cluster_boundary_end(struct file_extent_cluster *cluster,
+ int cluster_nr)
+{
+ /* Last extent, use cluster end directly */
+ if (cluster_nr >= cluster->nr - 1)
+ return cluster->end;
+
+ /* Use next boundary start*/
+ return cluster->boundary[cluster_nr + 1] - 1;
+}
+
+static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
+ struct file_extent_cluster *cluster,
+ int *cluster_nr, unsigned long page_index)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ u64 offset = BTRFS_I(inode)->index_cnt;
+ const unsigned long last_index = (cluster->end - offset) >> PAGE_SHIFT;
+ gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
+ struct page *page;
u64 page_start;
u64 page_end;
+ u64 cur;
+ int ret;
+
+ ASSERT(page_index <= last_index);
+ page = find_lock_page(inode->i_mapping, page_index);
+ if (!page) {
+ page_cache_sync_readahead(inode->i_mapping, ra, NULL,
+ page_index, last_index + 1 - page_index);
+ page = find_or_create_page(inode->i_mapping, page_index, mask);
+ if (!page)
+ return -ENOMEM;
+ }
+ ret = set_page_extent_mapped(page);
+ if (ret < 0)
+ goto release_page;
+
+ if (PageReadahead(page))
+ page_cache_async_readahead(inode->i_mapping, ra, NULL, page,
+ page_index, last_index + 1 - page_index);
+
+ if (!PageUptodate(page)) {
+ btrfs_readpage(NULL, page);
+ lock_page(page);
+ if (!PageUptodate(page)) {
+ ret = -EIO;
+ goto release_page;
+ }
+ }
+
+ page_start = page_offset(page);
+ page_end = page_start + PAGE_SIZE - 1;
+
+ /*
+ * Start from the cluster, as for subpage case, the cluster can start
+ * inside the page.
+ */
+ cur = max(page_start, cluster->boundary[*cluster_nr] - offset);
+ while (cur <= page_end) {
+ u64 extent_start = cluster->boundary[*cluster_nr] - offset;
+ u64 extent_end = get_cluster_boundary_end(cluster,
+ *cluster_nr) - offset;
+ u64 clamped_start = max(page_start, extent_start);
+ u64 clamped_end = min(page_end, extent_end);
+ u32 clamped_len = clamped_end + 1 - clamped_start;
+
+ /* Reserve metadata for this range */
+ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+ clamped_len);
+ if (ret)
+ goto release_page;
+
+ /* Mark the range delalloc and dirty for later writeback */
+ lock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end);
+ ret = btrfs_set_extent_delalloc(BTRFS_I(inode), clamped_start,
+ clamped_end, 0, NULL);
+ if (ret) {
+ clear_extent_bits(&BTRFS_I(inode)->io_tree,
+ clamped_start, clamped_end,
+ EXTENT_LOCKED | EXTENT_BOUNDARY);
+ btrfs_delalloc_release_metadata(BTRFS_I(inode),
+ clamped_len, true);
+ btrfs_delalloc_release_extents(BTRFS_I(inode),
+ clamped_len);
+ goto release_page;
+ }
+ btrfs_page_set_dirty(fs_info, page, clamped_start, clamped_len);
+
+ /*
+ * Set the boundary if it's inside the page.
+ * Data relocation requires the destination extents to have the
+ * same size as the source.
+ * EXTENT_BOUNDARY bit prevents current extent from being merged
+ * with previous extent.
+ */
+ if (in_range(cluster->boundary[*cluster_nr] - offset,
+ page_start, PAGE_SIZE)) {
+ u64 boundary_start = cluster->boundary[*cluster_nr] -
+ offset;
+ u64 boundary_end = boundary_start +
+ fs_info->sectorsize - 1;
+
+ set_extent_bits(&BTRFS_I(inode)->io_tree,
+ boundary_start, boundary_end,
+ EXTENT_BOUNDARY);
+ }
+ unlock_extent(&BTRFS_I(inode)->io_tree, clamped_start, clamped_end);
+ btrfs_delalloc_release_extents(BTRFS_I(inode), clamped_len);
+ cur += clamped_len;
+
+ /* Crossed extent end, go to next extent */
+ if (cur >= extent_end) {
+ (*cluster_nr)++;
+ /* Just finished the last extent of the cluster, exit. */
+ if (*cluster_nr >= cluster->nr)
+ break;
+ }
+ }
+ unlock_page(page);
+ put_page(page);
+
+ balance_dirty_pages_ratelimited(inode->i_mapping);
+ btrfs_throttle(fs_info);
+ if (btrfs_should_cancel_balance(fs_info))
+ ret = -ECANCELED;
+ return ret;
+
+release_page:
+ unlock_page(page);
+ put_page(page);
+ return ret;
+}
+
+static int relocate_file_extent_cluster(struct inode *inode,
+ struct file_extent_cluster *cluster)
+{
u64 offset = BTRFS_I(inode)->index_cnt;
unsigned long index;
unsigned long last_index;
- struct page *page;
struct file_ra_state *ra;
- gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
- int nr = 0;
+ int cluster_nr = 0;
int ret = 0;
if (!cluster->nr)
if (ret)
goto out;
- index = (cluster->start - offset) >> PAGE_SHIFT;
last_index = (cluster->end - offset) >> PAGE_SHIFT;
- while (index <= last_index) {
- ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
- PAGE_SIZE);
- if (ret)
- goto out;
-
- page = find_lock_page(inode->i_mapping, index);
- if (!page) {
- page_cache_sync_readahead(inode->i_mapping,
- ra, NULL, index,
- last_index + 1 - index);
- page = find_or_create_page(inode->i_mapping, index,
- mask);
- if (!page) {
- btrfs_delalloc_release_metadata(BTRFS_I(inode),
- PAGE_SIZE, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE);
- ret = -ENOMEM;
- goto out;
- }
- }
- ret = set_page_extent_mapped(page);
- if (ret < 0) {
- btrfs_delalloc_release_metadata(BTRFS_I(inode),
- PAGE_SIZE, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
- unlock_page(page);
- put_page(page);
- goto out;
- }
-
- if (PageReadahead(page)) {
- page_cache_async_readahead(inode->i_mapping,
- ra, NULL, page, index,
- last_index + 1 - index);
- }
-
- if (!PageUptodate(page)) {
- btrfs_readpage(NULL, page);
- lock_page(page);
- if (!PageUptodate(page)) {
- unlock_page(page);
- put_page(page);
- btrfs_delalloc_release_metadata(BTRFS_I(inode),
- PAGE_SIZE, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE);
- ret = -EIO;
- goto out;
- }
- }
-
- page_start = page_offset(page);
- page_end = page_start + PAGE_SIZE - 1;
-
- lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
-
- if (nr < cluster->nr &&
- page_start + offset == cluster->boundary[nr]) {
- set_extent_bits(&BTRFS_I(inode)->io_tree,
- page_start, page_end,
- EXTENT_BOUNDARY);
- nr++;
- }
-
- ret = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start,
- page_end, 0, NULL);
- if (ret) {
- unlock_page(page);
- put_page(page);
- btrfs_delalloc_release_metadata(BTRFS_I(inode),
- PAGE_SIZE, true);
- btrfs_delalloc_release_extents(BTRFS_I(inode),
- PAGE_SIZE);
-
- clear_extent_bits(&BTRFS_I(inode)->io_tree,
- page_start, page_end,
- EXTENT_LOCKED | EXTENT_BOUNDARY);
- goto out;
-
- }
- set_page_dirty(page);
-
- unlock_extent(&BTRFS_I(inode)->io_tree,
- page_start, page_end);
- unlock_page(page);
- put_page(page);
-
- index++;
- btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
- balance_dirty_pages_ratelimited(inode->i_mapping);
- btrfs_throttle(fs_info);
- if (btrfs_should_cancel_balance(fs_info)) {
- ret = -ECANCELED;
- goto out;
- }
- }
- WARN_ON(nr != cluster->nr);
- if (btrfs_is_zoned(fs_info) && !ret)
- ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+ for (index = (cluster->start - offset) >> PAGE_SHIFT;
+ index <= last_index && !ret; index++)
+ ret = relocate_one_page(inode, ra, cluster, &cluster_nr, index);
+ if (ret == 0)
+ WARN_ON(cluster_nr != cluster->nr);
out:
kfree(ra);
return ret;
*/
return PTR_ERR(trans);
}
- return btrfs_commit_transaction(trans);
+
+ ret = btrfs_commit_transaction(trans);
+ if (ret)
+ unset_reloc_control(rc);
+
+ return ret;
}
static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
struct btrfs_path *path;
struct btrfs_inode_item *item;
struct extent_buffer *leaf;
- u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC;
int ret;
- if (btrfs_is_zoned(trans->fs_info))
- flags &= ~BTRFS_INODE_PREALLOC;
-
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
btrfs_set_inode_generation(leaf, item, 1);
btrfs_set_inode_size(leaf, item, 0);
btrfs_set_inode_mode(leaf, item, S_IFREG | 0600);
- btrfs_set_inode_flags(leaf, item, flags);
+ btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS |
+ BTRFS_INODE_PREALLOC);
btrfs_mark_buffer_dirty(leaf);
out:
btrfs_free_path(path);
return inode;
}
+/*
+ * Mark start of chunk relocation that is cancellable. Check if the cancellation
+ * has been requested meanwhile and don't start in that case.
+ *
+ * Return:
+ * 0 success
+ * -EINPROGRESS operation is already in progress, that's probably a bug
+ * -ECANCELED cancellation request was set before the operation started
+ */
+static int reloc_chunk_start(struct btrfs_fs_info *fs_info)
+{
+ if (test_and_set_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags)) {
+ /* This should not happen */
+ btrfs_err(fs_info, "reloc already running, cannot start");
+ return -EINPROGRESS;
+ }
+
+ if (atomic_read(&fs_info->reloc_cancel_req) > 0) {
+ btrfs_info(fs_info, "chunk relocation canceled on start");
+ /*
+ * On cancel, clear all requests but let the caller mark
+ * the end after cleanup operations.
+ */
+ atomic_set(&fs_info->reloc_cancel_req, 0);
+ return -ECANCELED;
+ }
+ return 0;
+}
+
+/*
+ * Mark end of chunk relocation that is cancellable and wake any waiters.
+ */
+static void reloc_chunk_end(struct btrfs_fs_info *fs_info)
+{
+ /* Requested after start, clear bit first so any waiters can continue */
+ if (atomic_read(&fs_info->reloc_cancel_req) > 0)
+ btrfs_info(fs_info, "chunk relocation canceled during operation");
+ clear_and_wake_up_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags);
+ atomic_set(&fs_info->reloc_cancel_req, 0);
+}
+
static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
{
struct reloc_control *rc;
int rw = 0;
int err = 0;
+ /*
+ * This only gets set if we had a half-deleted snapshot on mount. We
+ * cannot allow relocation to start while we're still trying to clean up
+ * these pending deletions.
+ */
+ ret = wait_on_bit(&fs_info->flags, BTRFS_FS_UNFINISHED_DROPS, TASK_INTERRUPTIBLE);
+ if (ret)
+ return ret;
+
+ /* We may have been woken up by close_ctree, so bail if we're closing. */
+ if (btrfs_fs_closing(fs_info))
+ return -EINTR;
+
bg = btrfs_lookup_block_group(fs_info, group_start);
if (!bg)
return -ENOENT;
return -ENOMEM;
}
+ ret = reloc_chunk_start(fs_info);
+ if (ret < 0) {
+ err = ret;
+ goto out_put_bg;
+ }
+
rc->extent_root = extent_root;
rc->block_group = bg;
if (err && rw)
btrfs_dec_block_group_ro(rc->block_group);
iput(rc->data_inode);
- btrfs_put_block_group(rc->block_group);
+out_put_bg:
+ btrfs_put_block_group(bg);
+ reloc_chunk_end(fs_info);
free_reloc_control(rc);
return err;
}
goto out;
}
+ ret = reloc_chunk_start(fs_info);
+ if (ret < 0) {
+ err = ret;
+ goto out_end;
+ }
+
rc->extent_root = fs_info->extent_root;
set_reloc_control(rc);
err = ret;
out_unset:
unset_reloc_control(rc);
+out_end:
+ reloc_chunk_end(fs_info);
free_reloc_control(rc);
out:
free_reloc_roots(&reloc_roots);
if (!rc)
return 0;
- BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
- root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);
+ BUG_ON(rc->stage == UPDATE_DATA_PTRS && btrfs_is_data_reloc_root(root));
level = btrfs_header_level(buf);
if (btrfs_header_generation(buf) <=
projects / platform / kernel / linux-rpi.git / blobdiff