summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/backref.c2
-rw-r--r--fs/btrfs/ctree.h6
-rw-r--r--fs/btrfs/disk-io.c78
-rw-r--r--fs/btrfs/disk-io.h2
-rw-r--r--fs/btrfs/extent-io-tree.h2
-rw-r--r--fs/btrfs/extent-tree.c31
-rw-r--r--fs/btrfs/extent_io.c20
-rw-r--r--fs/btrfs/file.c12
-rw-r--r--fs/btrfs/free-space-cache.c4
-rw-r--r--fs/btrfs/inode.c64
-rw-r--r--fs/btrfs/ioctl.c67
-rw-r--r--fs/btrfs/ref-verify.c2
-rw-r--r--fs/btrfs/relocation.c12
-rw-r--r--fs/btrfs/scrub.c2
-rw-r--r--fs/btrfs/space-info.c2
-rw-r--r--fs/btrfs/super.c51
-rw-r--r--fs/btrfs/sysfs.c3
-rw-r--r--fs/btrfs/transaction.c7
-rw-r--r--fs/btrfs/transaction.h2
-rw-r--r--fs/btrfs/tree-log.c43
-rw-r--r--fs/btrfs/volumes.c48
21 files changed, 350 insertions, 110 deletions
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index ea10f7bc99ab..ea1c28ccb44f 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -2303,7 +2303,7 @@ struct btrfs_backref_iter *btrfs_backref_iter_alloc(
return NULL;
ret->path = btrfs_alloc_path();
- if (!ret) {
+ if (!ret->path) {
kfree(ret);
return NULL;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d404cce8ae40..6fdb3392a06d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1059,8 +1059,10 @@ struct btrfs_root {
wait_queue_head_t log_writer_wait;
wait_queue_head_t log_commit_wait[2];
struct list_head log_ctxs[2];
+ /* Used only for log trees of subvolumes, not for the log root tree */
atomic_t log_writers;
atomic_t log_commit[2];
+ /* Used only for log trees of subvolumes, not for the log root tree */
atomic_t log_batch;
int log_transid;
/* No matter the commit succeeds or not*/
@@ -2982,6 +2984,8 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
size_t num_pages, loff_t pos, size_t write_bytes,
struct extent_state **cached);
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
+int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos,
+ size_t *write_bytes, bool nowait);
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
@@ -3194,7 +3198,7 @@ do { \
/* Report first abort since mount */ \
if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
&((trans)->fs_info->fs_state))) { \
- if ((errno) != -EIO) { \
+ if ((errno) != -EIO && (errno) != -EROFS) { \
WARN(1, KERN_DEBUG \
"BTRFS: Transaction aborted (error %d)\n", \
(errno)); \
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b1a148058773..66618a1794ea 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1395,7 +1395,12 @@ alloc_fail:
goto out;
}
-static int btrfs_init_fs_root(struct btrfs_root *root)
+/*
+ * Initialize subvolume root in-memory structure
+ *
+ * @anon_dev: anonymous device to attach to the root, if zero, allocate new
+ */
+static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
{
int ret;
unsigned int nofs_flag;
@@ -1428,9 +1433,20 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
spin_lock_init(&root->ino_cache_lock);
init_waitqueue_head(&root->ino_cache_wait);
- ret = get_anon_bdev(&root->anon_dev);
- if (ret)
- goto fail;
+ /*
+ * Don't assign anonymous block device to roots that are not exposed to
+ * userspace, the id pool is limited to 1M
+ */
+ if (is_fstree(root->root_key.objectid) &&
+ btrfs_root_refs(&root->root_item) > 0) {
+ if (!anon_dev) {
+ ret = get_anon_bdev(&root->anon_dev);
+ if (ret)
+ goto fail;
+ } else {
+ root->anon_dev = anon_dev;
+ }
+ }
mutex_lock(&root->objectid_mutex);
ret = btrfs_find_highest_objectid(root,
@@ -1534,8 +1550,27 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
}
-struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
- u64 objectid, bool check_ref)
+/*
+ * Get an in-memory reference of a root structure.
+ *
+ * For essential trees like root/extent tree, we grab it from fs_info directly.
+ * For subvolume trees, we check the cached filesystem roots first. If not
+ * found, then read it from disk and add it to cached fs roots.
+ *
+ * Caller should release the root by calling btrfs_put_root() after the usage.
+ *
+ * NOTE: Reloc and log trees can't be read by this function as they share the
+ * same root objectid.
+ *
+ * @objectid: root id
+ * @anon_dev: preallocated anonymous block device number for new roots,
+ * pass 0 for new allocation.
+ * @check_ref: whether to check root item references, If true, return -ENOENT
+ * for orphan roots
+ */
+static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev,
+ bool check_ref)
{
struct btrfs_root *root;
struct btrfs_path *path;
@@ -1564,6 +1599,8 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
again:
root = btrfs_lookup_fs_root(fs_info, objectid);
if (root) {
+ /* Shouldn't get preallocated anon_dev for cached roots */
+ ASSERT(!anon_dev);
if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
btrfs_put_root(root);
return ERR_PTR(-ENOENT);
@@ -1583,7 +1620,7 @@ again:
goto fail;
}
- ret = btrfs_init_fs_root(root);
+ ret = btrfs_init_fs_root(root, anon_dev);
if (ret)
goto fail;
@@ -1616,6 +1653,33 @@ fail:
return ERR_PTR(ret);
}
+/*
+ * Get in-memory reference of a root structure
+ *
+ * @objectid: tree objectid
+ * @check_ref: if set, verify that the tree exists and the item has at least
+ * one reference
+ */
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, bool check_ref)
+{
+ return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+}
+
+/*
+ * Get in-memory reference of a root structure, created as new, optionally pass
+ * the anonymous block device id
+ *
+ * @objectid: tree objectid
+ * @anon_dev: if zero, allocate a new anonymous block device or use the
+ * parameter value
+ */
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev)
+{
+ return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
+}
+
static int btrfs_congested_fn(void *congested_data, int bdi_bits)
{
struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index bf43245406c4..00dc39d47ed3 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -67,6 +67,8 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info);
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
u64 objectid, bool check_ref);
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+ u64 objectid, dev_t anon_dev);
void btrfs_free_fs_info(struct btrfs_fs_info *fs_info);
int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-io-tree.h b/fs/btrfs/extent-io-tree.h
index b6561455b3c4..8bbb734f3f51 100644
--- a/fs/btrfs/extent-io-tree.h
+++ b/fs/btrfs/extent-io-tree.h
@@ -34,6 +34,8 @@ struct io_failure_record;
*/
#define CHUNK_ALLOCATED EXTENT_DIRTY
#define CHUNK_TRIMMED EXTENT_DEFRAG
+#define CHUNK_STATE_MASK (CHUNK_ALLOCATED | \
+ CHUNK_TRIMMED)
enum {
IO_TREE_FS_PINNED_EXTENTS,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c0bc35f932bf..de6fe176fdfb 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -33,6 +33,7 @@
#include "delalloc-space.h"
#include "block-group.h"
#include "discard.h"
+#include "rcu-string.h"
#undef SCRAMBLE_DELAYED_REFS
@@ -5298,7 +5299,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
goto out;
}
- trans = btrfs_start_transaction(tree_root, 0);
+ /*
+ * Use join to avoid potential EINTR from transaction start. See
+ * wait_reserve_ticket and the whole reservation callchain.
+ */
+ if (for_reloc)
+ trans = btrfs_join_transaction(tree_root);
+ else
+ trans = btrfs_start_transaction(tree_root, 0);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_free;
@@ -5466,6 +5474,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
}
}
+ /*
+ * This subvolume is going to be completely dropped, and won't be
+ * recorded as dirty roots, thus pertrans meta rsv will not be freed at
+ * commit transaction time. So free it here manually.
+ */
+ btrfs_qgroup_convert_reserved_meta(root, INT_MAX);
+ btrfs_qgroup_free_meta_all_pertrans(root);
+
if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state))
btrfs_add_dropped_root(trans, root);
else
@@ -5653,6 +5669,19 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
&start, &end,
CHUNK_TRIMMED | CHUNK_ALLOCATED);
+ /* Check if there are any CHUNK_* bits left */
+ if (start > device->total_bytes) {
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ btrfs_warn_in_rcu(fs_info,
+"ignoring attempt to trim beyond device size: offset %llu length %llu device %s device size %llu",
+ start, end - start + 1,
+ rcu_str_deref(device->name),
+ device->total_bytes);
+ mutex_unlock(&fs_info->chunk_mutex);
+ ret = 0;
+ break;
+ }
+
/* Ensure we skip the reserved area in the first 1M */
start = max_t(u64, start, SZ_1M);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 60278e52c37a..8ba8788461ae 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4127,7 +4127,7 @@ retry:
if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
ret = flush_write_bio(&epd);
} else {
- ret = -EUCLEAN;
+ ret = -EROFS;
end_write_bio(&epd, ret);
}
return ret;
@@ -4502,20 +4502,32 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
free_extent_map(em);
break;
}
- if (!test_range_bit(tree, em->start,
- extent_map_end(em) - 1,
- EXTENT_LOCKED, 0, NULL)) {
+ if (test_range_bit(tree, em->start,
+ extent_map_end(em) - 1,
+ EXTENT_LOCKED, 0, NULL))
+ goto next;
+ /*
+ * If it's not in the list of modified extents, used
+ * by a fast fsync, we can remove it. If it's being
+ * logged we can safely remove it since fsync took an
+ * extra reference on the em.
+ */
+ if (list_empty(&em->list) ||
+ test_bit(EXTENT_FLAG_LOGGING, &em->flags)) {
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&btrfs_inode->runtime_flags);
remove_extent_mapping(map, em);
/* once for the rb tree */
free_extent_map(em);
}
+next:
start = extent_map_end(em);
write_unlock(&map->lock);
/* once for us */
free_extent_map(em);
+
+ cond_resched(); /* Allow large-extent preemption. */
}
}
return try_release_extent_state(tree, page, mask);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b0d2c976587e..1523aa4eaff0 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1532,8 +1532,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
return ret;
}
-static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
- size_t *write_bytes, bool nowait)
+int btrfs_check_can_nocow(struct btrfs_inode *inode, loff_t pos,
+ size_t *write_bytes, bool nowait)
{
struct btrfs_fs_info *fs_info = inode->root->fs_info;
struct btrfs_root *root = inode->root;
@@ -1648,8 +1648,8 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
if (ret < 0) {
if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
BTRFS_INODE_PREALLOC)) &&
- check_can_nocow(BTRFS_I(inode), pos,
- &write_bytes, false) > 0) {
+ btrfs_check_can_nocow(BTRFS_I(inode), pos,
+ &write_bytes, false) > 0) {
/*
* For nodata cow case, no need to reserve
* data space.
@@ -1928,8 +1928,8 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
*/
if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
BTRFS_INODE_PREALLOC)) ||
- check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes,
- true) <= 0) {
+ btrfs_check_can_nocow(BTRFS_I(inode), pos, &nocow_bytes,
+ true) <= 0) {
inode_unlock(inode);
return -EAGAIN;
}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 55955bd424d7..6f7b6bca6dc5 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2281,7 +2281,7 @@ out:
static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
struct btrfs_free_space *info, bool update_stat)
{
- struct btrfs_free_space *left_info;
+ struct btrfs_free_space *left_info = NULL;
struct btrfs_free_space *right_info;
bool merged = false;
u64 offset = info->offset;
@@ -2297,7 +2297,7 @@ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl,
if (right_info && rb_prev(&right_info->offset_index))
left_info = rb_entry(rb_prev(&right_info->offset_index),
struct btrfs_free_space, offset_index);
- else
+ else if (!right_info)
left_info = tree_search_offset(ctl, offset - 1, 0, 0);
/* See try_merge_free_space() comment. */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6862cd7e21a9..7ba1218b1630 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -650,12 +650,18 @@ cont:
page_error_op |
PAGE_END_WRITEBACK);
- for (i = 0; i < nr_pages; i++) {
- WARN_ON(pages[i]->mapping);
- put_page(pages[i]);
+ /*
+ * Ensure we only free the compressed pages if we have
+ * them allocated, as we can still reach here with
+ * inode_need_compress() == false.
+ */
+ if (pages) {
+ for (i = 0; i < nr_pages; i++) {
+ WARN_ON(pages[i]->mapping);
+ put_page(pages[i]);
+ }
+ kfree(pages);
}
- kfree(pages);
-
return 0;
}
}
@@ -4041,6 +4047,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
}
}
+ free_anon_bdev(dest->anon_dev);
+ dest->anon_dev = 0;
out_end_trans:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
@@ -4511,11 +4519,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
char *kaddr;
+ bool only_release_metadata = false;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
+ size_t write_bytes = blocksize;
int ret = 0;
u64 block_start;
u64 block_end;
@@ -4527,11 +4537,27 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
block_start = round_down(from, blocksize);
block_end = block_start + blocksize - 1;
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
- block_start, blocksize);
- if (ret)
- goto out;
+ ret = btrfs_check_data_free_space(inode, &data_reserved, block_start,
+ blocksize);
+ if (ret < 0) {
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ btrfs_check_can_nocow(BTRFS_I(inode), block_start,
+ &write_bytes, false) > 0) {
+ /* For nocow case, no need to reserve data space */
+ only_release_metadata = true;
+ } else {
+ goto out;
+ }
+ }
+ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize);
+ if (ret < 0) {
+ if (!only_release_metadata)
+ btrfs_free_reserved_data_space(inode, data_reserved,
+ block_start, blocksize);
+ goto out;
+ }
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
@@ -4600,14 +4626,26 @@ again:
set_page_dirty(page);
unlock_extent_cached(io_tree, block_start, block_end, &cached_state);
+ if (only_release_metadata)
+ set_extent_bit(&BTRFS_I(inode)->io_tree, block_start,
+ block_end, EXTENT_NORESERVE, NULL, NULL,
+ GFP_NOFS);
+
out_unlock:
- if (ret)
- btrfs_delalloc_release_space(inode, data_reserved, block_start,
- blocksize, true);
+ if (ret) {
+ if (only_release_metadata)
+ btrfs_delalloc_release_metadata(BTRFS_I(inode),
+ blocksize, true);
+ else
+ btrfs_delalloc_release_space(inode, data_reserved,
+ block_start, blocksize, true);
+ }
btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
unlock_page(page);
put_page(page);
out:
+ if (only_release_metadata)
+ btrfs_drew_write_unlock(&BTRFS_I(inode)->root->snapshot_lock);
extent_changeset_free(data_reserved);
return ret;
}
@@ -6595,7 +6633,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
/* Only regular file could have regular/prealloc extent */
if (!S_ISREG(inode->vfs_inode.i_mode)) {
- ret = -EUCLEAN;
+ err = -EUCLEAN;
btrfs_crit(fs_info,
"regular/prealloc extent found for non-regular inode %llu",
btrfs_ino(inode));
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index e8f7c5f00894..1448bc43561c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -164,8 +164,11 @@ static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
return 0;
}
-/* Check if @flags are a supported and valid set of FS_*_FL flags */
-static int check_fsflags(unsigned int flags)
+/*
+ * Check if @flags are a supported and valid set of FS_*_FL flags and that
+ * the old and new flags are not conflicting
+ */
+static int check_fsflags(unsigned int old_flags, unsigned int flags)
{
if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
FS_NOATIME_FL | FS_NODUMP_FL | \
@@ -174,9 +177,19 @@ static int check_fsflags(unsigned int flags)
FS_NOCOW_FL))
return -EOPNOTSUPP;
+ /* COMPR and NOCOMP on new/old are valid */
if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
return -EINVAL;
+ if ((flags & FS_COMPR_FL) && (flags & FS_NOCOW_FL))
+ return -EINVAL;
+
+ /* NOCOW and compression options are mutually exclusive */
+ if ((old_flags & FS_NOCOW_FL) && (flags & (FS_COMPR_FL | FS_NOCOMP_FL)))
+ return -EINVAL;
+ if ((flags & FS_NOCOW_FL) && (old_flags & (FS_COMPR_FL | FS_NOCOMP_FL)))
+ return -EINVAL;
+
return 0;
}
@@ -190,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
unsigned int fsflags, old_fsflags;
int ret;
const char *comp = NULL;
- u32 binode_flags = binode->flags;
+ u32 binode_flags;
if (!inode_owner_or_capable(inode))
return -EPERM;
@@ -201,22 +214,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (copy_from_user(&fsflags, arg, sizeof(fsflags)))
return -EFAULT;
- ret = check_fsflags(fsflags);
- if (ret)
- return ret;
-
ret = mnt_want_write_file(file);
if (ret)
return ret;
inode_lock(inode);
-
fsflags = btrfs_mask_fsflags_for_type(inode, fsflags);
old_fsflags = btrfs_inode_flags_to_fsflags(binode->flags);
+
ret = vfs_ioc_setflags_prepare(inode, old_fsflags, fsflags);
if (ret)
goto out_unlock;
+ ret = check_fsflags(old_fsflags, fsflags);
+ if (ret)
+ goto out_unlock;
+
+ binode_flags = binode->flags;
if (fsflags & FS_SYNC_FL)
binode_flags |= BTRFS_INODE_SYNC;
else
@@ -566,6 +580,7 @@ static noinline int create_subvol(struct inode *dir,
struct inode *inode;
int ret;
int err;
+ dev_t anon_dev = 0;
u64 objectid;
u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
u64 index = 0;
@@ -578,6 +593,10 @@ static noinline int create_subvol(struct inode *dir,
if (ret)
goto fail_free;
+ ret = get_anon_bdev(&anon_dev);
+ if (ret < 0)
+ goto fail_free;
+
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
* screwed up since it assumes subvolume qgroup's level to be 0.
@@ -660,12 +679,15 @@ static noinline int create_subvol(struct inode *dir,
goto fail;
key.offset = (u64)-1;
- new_root = btrfs_get_fs_root(fs_info, objectid, true);
+ new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev);
if (IS_ERR(new_root)) {
+ free_anon_bdev(anon_dev);
ret = PTR_ERR(new_root);
btrfs_abort_transaction(trans, ret);
goto fail;
}
+ /* Freeing will be done in btrfs_put_root() of new_root */
+ anon_dev = 0;
btrfs_record_root_in_trans(trans, new_root);
@@ -735,6 +757,8 @@ fail:
return ret;
fail_free:
+ if (anon_dev)
+ free_anon_bdev(anon_dev);
kfree(root_item);
return ret;
}
@@ -762,6 +786,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
if (!pending_snapshot)
return -ENOMEM;
+ ret = get_anon_bdev(&pending_snapshot->anon_dev);
+ if (ret < 0)
+ goto free_pending;
pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
GFP_KERNEL);
pending_snapshot->path = btrfs_alloc_path();
@@ -823,10 +850,16 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
d_instantiate(dentry, inode);
ret = 0;
+ pending_snapshot->anon_dev = 0;
fail:
+ /* Prevent double freeing of anon_dev */
+ if (ret && pending_snapshot->snap)
+ pending_snapshot->snap->anon_dev = 0;
btrfs_put_root(pending_snapshot->snap);
btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
free_pending:
+ if (pending_snapshot->anon_dev)
+ free_anon_bdev(pending_snapshot->anon_dev);
kfree(pending_snapshot->root_item);
btrfs_free_path(pending_snapshot->path);
kfree(pending_snapshot);
@@ -3198,11 +3231,15 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_fs_info_args *fi_args;
struct btrfs_device *device;
struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+ u64 flags_in;
int ret = 0;
- fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
- if (!fi_args)
- return -ENOMEM;
+ fi_args = memdup_user(arg, sizeof(*fi_args));
+ if (IS_ERR(fi_args))
+ return PTR_ERR(fi_args);
+
+ flags_in = fi_args->flags;
+ memset(fi_args, 0, sizeof(*fi_args));
rcu_read_lock();
fi_args->num_devices = fs_devices->num_devices;
@@ -3218,6 +3255,12 @@ static long btrfs_ioctl_fs_info(struct btrfs_fs_info *fs_info,
fi_args->sectorsize = fs_info->sectorsize;
fi_args->clone_alignment = fs_info->sectorsize;
+ if (flags_in & BTRFS_FS_INFO_FLAG_CSUM_INFO) {
+ fi_args->csum_type = btrfs_super_csum_type(fs_info->super_copy);
+ fi_args->csum_size = btrfs_super_csum_size(fs_info->super_copy);
+ fi_args->flags |= BTRFS_FS_INFO_FLAG_CSUM_INFO;
+ }
+
if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
ret = -EFAULT;
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index af92525dbb16..7f03dbe5b609 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -286,6 +286,8 @@ static struct block_entry *add_block_entry(struct btrfs_fs_info *fs_info,
exist_re = insert_root_entry(&exist->roots, re);
if (exist_re)
kfree(re);
+ } else {
+ kfree(re);
}
kfree(be);
return exist;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 3bbae80c752f..5740ed51a1e8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1686,12 +1686,20 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
btrfs_unlock_up_safe(path, 0);
}
- min_reserved = fs_info->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
+ /*
+ * In merge_reloc_root(), we modify the upper level pointer to swap the
+ * tree blocks between reloc tree and subvolume tree. Thus for tree
+ * block COW, we COW at most from level 1 to root level for each tree.
+ *
+ * Thus the needed metadata size is at most root_level * nodesize,
+ * and * 2 since we have two trees to COW.
+ */
+ min_reserved = fs_info->nodesize * btrfs_root_level(root_item) * 2;
memset(&next_key, 0, sizeof(next_key));
while (1) {
ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved,
- BTRFS_RESERVE_FLUSH_ALL);
+ BTRFS_RESERVE_FLUSH_LIMIT);
if (ret) {
err = ret;
goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 016a025e36c7..5f5b21e389db 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3758,7 +3758,7 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx,
struct btrfs_fs_info *fs_info = sctx->fs_info;
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
- return -EIO;
+ return -EROFS;
/* Seed devices of a new filesystem has their own generation. */
if (scrub_dev->fs_devices != fs_info->fs_devices)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index c7bd3fdd7792..475968ccbd1d 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -468,8 +468,8 @@ again:
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
cache->start, cache->length, cache->used, cache->pinned,
cache->reserved, cache->ro ? "[readonly]" : "");
- btrfs_dump_free_space(cache, bytes);
spin_unlock(&cache->lock);
+ btrfs_dump_free_space(cache, bytes);
}
if (++index < BTRFS_NR_RAID_TYPES)
goto again;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index c3826ae883f0..56cd2cf57158 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -449,6 +449,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
char *compress_type;
bool compress_force = false;
enum btrfs_compression_type saved_compress_type;
+ int saved_compress_level;
bool saved_compress_force;
int no_compress = 0;
@@ -531,6 +532,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
info->compress_type : BTRFS_COMPRESS_NONE;
saved_compress_force =
btrfs_test_opt(info, FORCE_COMPRESS);
+ saved_compress_level = info->compress_level;
if (token == Opt_compress ||
token == Opt_compress_force ||
strncmp(args[0].from, "zlib", 4) == 0) {
@@ -575,6 +577,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
+ info->compress_level = 0;
+ info->compress_type = 0;
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
compress_force = false;
@@ -595,11 +599,11 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
*/
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
}
- if ((btrfs_test_opt(info, COMPRESS) &&
- (info->compress_type != saved_compress_type ||
- compress_force != saved_compress_force)) ||
- (!btrfs_test_opt(info, COMPRESS) &&
- no_compress == 1)) {
+ if (no_compress == 1) {
+ btrfs_info(info, "use no compression");
+ } else if ((info->compress_type != saved_compress_type) ||
+ (compress_force != saved_compress_force) ||
+ (info->compress_level != saved_compress_level)) {
btrfs_info(info, "%s %s compression, level %d",
(compress_force) ? "force" : "use",
compress_type, info->compress_level);
@@ -1312,6 +1316,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
{
struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
const char *compress_type;
+ const char *subvol_name;
if (btrfs_test_opt(info, DEGRADED))
seq_puts(seq, ",degraded");
@@ -1398,8 +1403,13 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
seq_puts(seq, ",ref_verify");
seq_printf(seq, ",subvolid=%llu",
BTRFS_I(d_inode(dentry))->root->root_key.objectid);
- seq_puts(seq, ",subvol=");
- seq_dentry(seq, dentry, " \t\n\\");
+ subvol_name = btrfs_get_subvol_name_from_objectid(info,
+ BTRFS_I(d_inode(dentry))->root->root_key.objectid);
+ if (!IS_ERR(subvol_name)) {
+ seq_puts(seq, ",subvol=");
+ seq_escape(seq, subvol_name, " \t\n\\");
+ kfree(subvol_name);
+ }
return 0;
}
@@ -1887,6 +1897,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
set_bit(BTRFS_FS_OPEN, &fs_info->flags);
}
out:
+ /*
+ * We need to set SB_I_VERSION here otherwise it'll get cleared by VFS,
+ * since the absence of the flag means it can be toggled off by remount.
+ */
+ *flags |= SB_I_VERSION;
+
wake_up_process(fs_info->transaction_kthread);
btrfs_remount_cleanup(fs_info, old_opts);
return 0;
@@ -2296,9 +2312,7 @@ static int btrfs_unfreeze(struct super_block *sb)
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
- struct btrfs_fs_devices *cur_devices;
struct btrfs_device *dev, *first_dev = NULL;
- struct list_head *head;
/*
* Lightweight locking of the devices. We should not need
@@ -2308,18 +2322,13 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
* least until the rcu_read_unlock.
*/
rcu_read_lock();
- cur_devices = fs_info->fs_devices;
- while (cur_devices) {
- head = &cur_devices->devices;
- list_for_each_entry_rcu(dev, head, dev_list) {
- if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
- continue;
- if (!dev->name)
- continue;
- if (!first_dev || dev->devid < first_dev->devid)
- first_dev = dev;
- }
- cur_devices = cur_devices->seed;
+ list_for_each_entry_rcu(dev, &fs_info->fs_devices->devices, dev_list) {
+ if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
+ continue;
+ if (!dev->name)
+ continue;
+ if (!first_dev || dev->devid < first_dev->devid)
+ first_dev = dev;
}
if (first_dev)
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a39bff64ff24..abc4a8fd6df6 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1273,7 +1273,9 @@ int btrfs_sysfs_add_devices_dir(struct btrfs_fs_devices *fs_devices,
{
int error = 0;
struct btrfs_device *dev;
+ unsigned int nofs_flag;
+ nofs_flag = memalloc_nofs_save();
list_for_each_entry(dev, &fs_devices->devices, dev_list) {
if (one_device && one_device != dev)
@@ -1301,6 +1303,7 @@ int btrfs_sysfs_add_devices_dir(struct btrfs_fs_devices *fs_devices,
break;
}
}
+ memalloc_nofs_restore(nofs_flag);
return error;
}
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index b359d4b17658..2710f8ddb95f 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -937,7 +937,10 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
if (TRANS_ABORTED(trans) ||
test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) {
wake_up_process(info->transaction_kthread);
- err = -EIO;
+ if (TRANS_ABORTED(trans))
+ err = trans->aborted;
+ else
+ err = -EROFS;
}
kmem_cache_free(btrfs_trans_handle_cachep, trans);
@@ -1630,7 +1633,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
}
key.offset = (u64)-1;
- pending->snap = btrfs_get_fs_root(fs_info, objectid, true);
+ pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev);
if (IS_ERR(pending->snap)) {
ret = PTR_ERR(pending->snap);
btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index bf102e64bfb2..a122a712f5cc 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -151,6 +151,8 @@ struct btrfs_pending_snapshot {
struct btrfs_block_rsv block_rsv;
/* extra metadata reservation for relocation */
int error;
+ /* Preallocated anonymous block device number */
+ dev_t anon_dev;
bool readonly;
struct list_head list;
};
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index cd5348f352dd..d22ff1e0963c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3116,29 +3116,17 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
btrfs_init_log_ctx(&root_log_ctx, NULL);
mutex_lock(&log_root_tree->log_mutex);
- atomic_inc(&log_root_tree->log_batch);
- atomic_inc(&log_root_tree->log_writers);
index2 = log_root_tree->log_transid % 2;
list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
root_log_ctx.log_transid = log_root_tree->log_transid;
- mutex_unlock(&log_root_tree->log_mutex);
-
- mutex_lock(&log_root_tree->log_mutex);
-
/*
* Now we are safe to update the log_root_tree because we're under the
* log_mutex, and we're a current writer so we're holding the commit
* open until we drop the log_mutex.
*/
ret = update_log_root(trans, log, &new_root_item);
-
- if (atomic_dec_and_test(&log_root_tree->log_writers)) {
- /* atomic_dec_and_test implies a barrier */
- cond_wake_up_nomb(&log_root_tree->log_writer_wait);
- }
-
if (ret) {
if (!list_empty(&root_log_ctx.list))
list_del_init(&root_log_ctx.list);
@@ -3184,8 +3172,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
root_log_ctx.log_transid - 1);
}
- wait_for_writer(log_root_tree);
-
/*
* now that we've moved on to the tree of log tree roots,
* check the full commit flag again
@@ -4041,11 +4027,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
fs_info->csum_root,
ds + cs, ds + cs + cl - 1,
&ordered_sums, 0);
- if (ret) {
- btrfs_release_path(dst_path);
- kfree(ins_data);
- return ret;
- }
+ if (ret)
+ break;
}
}
}
@@ -4058,7 +4041,6 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
* we have to do this after the loop above to avoid changing the
* log tree while trying to change the log tree.
*/
- ret = 0;
while (!list_empty(&ordered_sums)) {
struct btrfs_ordered_sum *sums = list_entry(ordered_sums.next,
struct btrfs_ordered_sum,
@@ -5123,14 +5105,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
const loff_t end,
struct btrfs_log_ctx *ctx)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_path *path;
struct btrfs_path *dst_path;
struct btrfs_key min_key;
struct btrfs_key max_key;
struct btrfs_root *log = root->log_root;
int err = 0;
- int ret;
+ int ret = 0;
bool fast_search = false;
u64 ino = btrfs_ino(inode);
struct extent_map_tree *em_tree = &inode->extent_tree;
@@ -5166,15 +5147,19 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
max_key.offset = (u64)-1;
/*
- * Only run delayed items if we are a dir or a new file.
- * Otherwise commit the delayed inode only, which is needed in
- * order for the log replay code to mark inodes for link count
- * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items).
+ * Only run delayed items if we are a directory. We want to make sure
+ * all directory indexes hit the fs/subvolume tree so we can find them
+ * and figure out which index ranges have to be logged.
+ *
+ * Otherwise commit the delayed inode only if the full sync flag is set,
+ * as we want to make sure an up to date version is in the subvolume
+ * tree so copy_inode_items_to_log() / copy_items() can find it and copy
+ * it to the log tree. For a non full sync, we always log the inode item
+ * based on the in-memory struct btrfs_inode which is always up to date.
*/
- if (S_ISDIR(inode->vfs_inode.i_mode) ||
- inode->generation > fs_info->last_trans_committed)
+ if (S_ISDIR(inode->vfs_inode.i_mode))
ret = btrfs_commit_inode_delayed_items(trans, inode);
- else
+ else if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
ret = btrfs_commit_inode_delayed_inode(inode);
if (ret) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f403fb1e6d37..0fecf1e4d8f6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -245,7 +245,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
*
* global::fs_devs - add, remove, updates to the global list
*
- * does not protect: manipulation of the fs_devices::devices list!
+ * does not protect: manipulation of the fs_devices::devices list in general
+ * but in mount context it could be used to exclude list modifications by eg.
+ * scan ioctl
*
* btrfs_device::name - renames (write side), read is RCU
*
@@ -258,6 +260,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
* may be used to exclude some operations from running concurrently without any
* modifications to the list (see write_all_supers)
*
+ * Is not required at mount and close times, because our device list is
+ * protected by the uuid_mutex at that point.
+ *
* balance_mutex
* -------------
* protects balance structures (status, state) and context accessed from
@@ -602,6 +607,11 @@ static int btrfs_free_stale_devices(const char *path,
return ret;
}
+/*
+ * This is only used on mount, and we are protected from competing things
+ * messing with our fs_devices by the uuid_mutex, thus we do not need the
+ * fs_devices->device_list_mutex here.
+ */
static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
struct btrfs_device *device, fmode_t flags,
void *holder)
@@ -1229,8 +1239,14 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
int ret;
lockdep_assert_held(&uuid_mutex);
+ /*
+ * The device_list_mutex cannot be taken here in case opening the
+ * underlying device takes further locks like bd_mutex.
+ *
+ * We also don't need the lock here as this is called during mount and
+ * exclusion is provided by uuid_mutex
+ */
- mutex_lock(&fs_devices->device_list_mutex);
if (fs_devices->opened) {
fs_devices->opened++;
ret = 0;
@@ -1238,7 +1254,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
list_sort(NULL, &fs_devices->devices, devid_cmp);
ret = open_fs_devices(fs_devices, flags, holder);
}
- mutex_unlock(&fs_devices->device_list_mutex);
return ret;
}
@@ -3231,7 +3246,7 @@ static int del_balance_item(struct btrfs_fs_info *fs_info)
if (!path)
return -ENOMEM;
- trans = btrfs_start_transaction(root, 0);
+ trans = btrfs_start_transaction_fallback_global_rsv(root, 0);
if (IS_ERR(trans)) {
btrfs_free_path(path);
return PTR_ERR(trans);
@@ -4135,7 +4150,22 @@ int btrfs_balance(struct btrfs_fs_info *fs_info,
mutex_lock(&fs_info->balance_mutex);
if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req))
btrfs_info(fs_info, "balance: paused");
- else if (ret == -ECANCELED && atomic_read(&fs_info->balance_cancel_req))
+ /*
+ * Balance can be canceled by:
+ *
+ * - Regular cancel request
+ * Then ret == -ECANCELED and balance_cancel_req > 0
+ *
+ * - Fatal signal to "btrfs" process
+ * Either the signal caught by wait_reserve_ticket() and callers
+ * got -EINTR, or caught by btrfs_should_cancel_balance() and
+ * got -ECANCELED.
+ * Either way, in this case balance_cancel_req = 0, and
+ * ret == -EINTR or ret == -ECANCELED.
+ *
+ * So here we only check the return value to catch canceled balance.
+ */
+ else if (ret == -ECANCELED || ret == -EINTR)
btrfs_info(fs_info, "balance: canceled");
else
btrfs_info(fs_info, "balance: ended with status: %d", ret);
@@ -4690,6 +4720,10 @@ again:
}
mutex_lock(&fs_info->chunk_mutex);
+ /* Clear all state bits beyond the shrunk device size */
+ clear_extent_bits(&device->alloc_state, new_size, (u64)-1,
+ CHUNK_STATE_MASK);
+
btrfs_device_set_disk_total_bytes(device, new_size);
if (list_empty(&device->post_commit_list))
list_add_tail(&device->post_commit_list,
@@ -7049,7 +7083,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
* otherwise we don't need it.
*/
mutex_lock(&uuid_mutex);
- mutex_lock(&fs_info->chunk_mutex);
/*
* It is possible for mount and umount to race in such a way that
@@ -7094,7 +7127,9 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+ mutex_lock(&fs_info->chunk_mutex);
ret = read_one_chunk(&found_key, leaf, chunk);
+ mutex_unlock(&fs_info->chunk_mutex);
if (ret)
goto error;
}
@@ -7124,7 +7159,6 @@ int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info)
}
ret = 0;
error:
- mutex_unlock(&fs_info->chunk_mutex);
mutex_unlock(&uuid_mutex);
btrfs_free_path(path);
generated by cgit v1.2.3 (git 2.39.0) at 2024-09-30 19:12:18 +0300