summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/async-thread.c2
-rw-r--r--fs/btrfs/backref.c10
-rw-r--r--fs/btrfs/ctree.h3
-rw-r--r--fs/btrfs/dev-replace.c2
-rw-r--r--fs/btrfs/disk-io.c131
-rw-r--r--fs/btrfs/extent-tree.c37
-rw-r--r--fs/btrfs/extent_map.c2
-rw-r--r--fs/btrfs/extent_map.h10
-rw-r--r--fs/btrfs/file.c48
-rw-r--r--fs/btrfs/free-space-tree.c18
-rw-r--r--fs/btrfs/inode-map.c9
-rw-r--r--fs/btrfs/inode-map.h1
-rw-r--r--fs/btrfs/inode.c64
-rw-r--r--fs/btrfs/ioctl.c42
-rw-r--r--fs/btrfs/raid56.c100
-rw-r--r--fs/btrfs/relocation.c7
-rw-r--r--fs/btrfs/scrub.c8
-rw-r--r--fs/btrfs/super.c29
-rw-r--r--fs/btrfs/sysfs.c35
-rw-r--r--fs/btrfs/sysfs.h5
-rw-r--r--fs/btrfs/tests/btrfs-tests.c10
-rw-r--r--fs/btrfs/tests/extent-io-tests.c12
-rw-r--r--fs/btrfs/tests/inode-tests.c8
-rw-r--r--fs/btrfs/tree-log.c14
-rw-r--r--fs/btrfs/volumes.c107
-rw-r--r--fs/btrfs/xattr.c2
26 files changed, 424 insertions, 292 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 88d9af3d4581..5fb60ea7eee2 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
list_add_tail(&work->ordered_list, &wq->ordered_list);
spin_unlock_irqrestore(&wq->list_lock, flags);
}
- queue_work(wq->normal_wq, &work->normal_work);
trace_btrfs_work_queued(work);
+ queue_work(wq->normal_wq, &work->normal_work);
}
void btrfs_queue_work(struct btrfs_workqueue *wq,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 08405a3da6b1..b90cd3776f8e 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -560,13 +560,13 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info,
*/
static void __merge_refs(struct list_head *head, int mode)
{
- struct __prelim_ref *ref1;
+ struct __prelim_ref *pos1;
- list_for_each_entry(ref1, head, list) {
- struct __prelim_ref *ref2 = ref1, *tmp;
+ list_for_each_entry(pos1, head, list) {
+ struct __prelim_ref *pos2 = pos1, *tmp;
- list_for_each_entry_safe_continue(ref2, tmp, head, list) {
- struct __prelim_ref *xchg;
+ list_for_each_entry_safe_continue(pos2, tmp, head, list) {
+ struct __prelim_ref *xchg, *ref1 = pos1, *ref2 = pos2;
struct extent_inode_elem *eie;
if (!ref_for_same_block(ref1, ref2))
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 97ad9bbeb35d..bfe4a337fb4d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1614,7 +1614,7 @@ struct btrfs_fs_info {
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct rw_semaphore delayed_iput_sem;
+ struct mutex cleaner_delayed_iput_mutex;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
@@ -3641,6 +3641,7 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
int __get_raid_index(u64 flags);
int btrfs_start_write_no_snapshoting(struct btrfs_root *root);
void btrfs_end_write_no_snapshoting(struct btrfs_root *root);
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
void check_system_chunk(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const u64 type);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1e668fb7dd4c..cbb7dbfb3fff 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -614,7 +614,7 @@ static void btrfs_dev_replace_update_device_in_mapping_tree(
em = lookup_extent_mapping(em_tree, start, (u64)-1);
if (!em)
break;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++)
if (srcdev == map->stripes[i].dev)
map->stripes[i].dev = tgtdev;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e99ccd6ffb2c..4545e2e2ad45 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -55,6 +55,12 @@
#include <asm/cpufeature.h>
#endif
+#define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\
+ BTRFS_HEADER_FLAG_RELOC |\
+ BTRFS_SUPER_FLAG_ERROR |\
+ BTRFS_SUPER_FLAG_SEEDING |\
+ BTRFS_SUPER_FLAG_METADUMP)
+
static const struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
@@ -176,6 +182,7 @@ static struct btrfs_lockdep_keyset {
{ .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" },
{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" },
{ .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" },
+ { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" },
{ .id = 0, .name_stem = "tree" },
};
@@ -1583,8 +1590,23 @@ int btrfs_init_fs_root(struct btrfs_root *root)
ret = get_anon_bdev(&root->anon_dev);
if (ret)
goto free_writers;
+
+ mutex_lock(&root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(root,
+ &root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&root->objectid_mutex);
+ goto free_root_dev;
+ }
+
+ ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&root->objectid_mutex);
+
return 0;
+free_root_dev:
+ free_anon_bdev(root->anon_dev);
free_writers:
btrfs_free_subvolume_writers(root->subv_writers);
fail:
@@ -1766,7 +1788,6 @@ static int cleaner_kthread(void *arg)
int again;
struct btrfs_trans_handle *trans;
- set_freezable();
do {
again = 0;
@@ -1786,7 +1807,10 @@ static int cleaner_kthread(void *arg)
goto sleep;
}
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(root);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&root->fs_info->cleaner_mutex);
@@ -2556,8 +2580,8 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
+ mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
- init_rwsem(&fs_info->delayed_iput_sem);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
@@ -2742,26 +2766,6 @@ int open_ctree(struct super_block *sb,
goto fail_alloc;
}
- /*
- * Leafsize and nodesize were always equal, this is only a sanity check.
- */
- if (le32_to_cpu(disk_super->__unused_leafsize) !=
- btrfs_super_nodesize(disk_super)) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksizes don't match. node %d leaf %d\n",
- btrfs_super_nodesize(disk_super),
- le32_to_cpu(disk_super->__unused_leafsize));
- err = -EINVAL;
- goto fail_alloc;
- }
- if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
- printk(KERN_ERR "BTRFS: couldn't mount because metadata "
- "blocksize (%d) was too large\n",
- btrfs_super_nodesize(disk_super));
- err = -EINVAL;
- goto fail_alloc;
- }
-
features = btrfs_super_incompat_flags(disk_super);
features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
@@ -2833,17 +2837,6 @@ int open_ctree(struct super_block *sb,
sb->s_blocksize = sectorsize;
sb->s_blocksize_bits = blksize_bits(sectorsize);
- if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_ERR "BTRFS: valid FS not found on %s\n", sb->s_id);
- goto fail_sb_buffer;
- }
-
- if (sectorsize != PAGE_SIZE) {
- printk(KERN_ERR "BTRFS: incompatible sector size (%lu) "
- "found on %s\n", (unsigned long)sectorsize, sb->s_id);
- goto fail_sb_buffer;
- }
-
mutex_lock(&fs_info->chunk_mutex);
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
@@ -2915,6 +2908,18 @@ retry_root_backup:
tree_root->commit_root = btrfs_root_node(tree_root);
btrfs_set_root_refs(&tree_root->root_item, 1);
+ mutex_lock(&tree_root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(tree_root,
+ &tree_root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&tree_root->objectid_mutex);
+ goto recovery_tree_root;
+ }
+
+ ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&tree_root->objectid_mutex);
+
ret = btrfs_read_roots(fs_info, tree_root);
if (ret)
goto recovery_tree_root;
@@ -4018,8 +4023,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
int read_only)
{
struct btrfs_super_block *sb = fs_info->super_copy;
+ u64 nodesize = btrfs_super_nodesize(sb);
+ u64 sectorsize = btrfs_super_sectorsize(sb);
int ret = 0;
+ if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
+ printk(KERN_ERR "BTRFS: no valid FS found\n");
+ ret = -EINVAL;
+ }
+ if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP)
+ printk(KERN_WARNING "BTRFS: unrecognized super flag: %llu\n",
+ btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
printk(KERN_ERR "BTRFS: tree_root level too big: %d >= %d\n",
btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
@@ -4037,31 +4051,46 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
}
/*
- * The common minimum, we don't know if we can trust the nodesize/sectorsize
- * items yet, they'll be verified later. Issue just a warning.
+ * Check sectorsize and nodesize first, other check will need it.
+ * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
*/
- if (!IS_ALIGNED(btrfs_super_root(sb), 4096))
+ if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
+ sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid sectorsize %llu\n", sectorsize);
+ ret = -EINVAL;
+ }
+ /* Only PAGE SIZE is supported yet */
+ if (sectorsize != PAGE_CACHE_SIZE) {
+ printk(KERN_ERR "BTRFS: sectorsize %llu not supported yet, only support %lu\n",
+ sectorsize, PAGE_CACHE_SIZE);
+ ret = -EINVAL;
+ }
+ if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
+ nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
+ printk(KERN_ERR "BTRFS: invalid nodesize %llu\n", nodesize);
+ ret = -EINVAL;
+ }
+ if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
+ printk(KERN_ERR "BTRFS: invalid leafsize %u, should be %llu\n",
+ le32_to_cpu(sb->__unused_leafsize),
+ nodesize);
+ ret = -EINVAL;
+ }
+
+ /* Root alignment check */
+ if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
btrfs_super_root(sb));
- if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096))
+ ret = -EINVAL;
+ }
+ if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n",
btrfs_super_chunk_root(sb));
- if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096))
- printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
- btrfs_super_log_root(sb));
-
- /*
- * Check the lower bound, the alignment and other constraints are
- * checked later.
- */
- if (btrfs_super_nodesize(sb) < 4096) {
- printk(KERN_ERR "BTRFS: nodesize too small: %u < 4096\n",
- btrfs_super_nodesize(sb));
ret = -EINVAL;
}
- if (btrfs_super_sectorsize(sb) < 4096) {
- printk(KERN_ERR "BTRFS: sectorsize too small: %u < 4096\n",
- btrfs_super_sectorsize(sb));
+ if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
+ printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n",
+ btrfs_super_log_root(sb));
ret = -EINVAL;
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 60cc1399c64f..e2287c7c10be 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4139,8 +4139,10 @@ commit_trans:
!atomic_read(&root->fs_info->open_ioctl_trans)) {
need_commit--;
- if (need_commit > 0)
+ if (need_commit > 0) {
+ btrfs_start_delalloc_roots(fs_info, 0, -1);
btrfs_wait_ordered_roots(fs_info, -1);
+ }
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
@@ -4153,11 +4155,12 @@ commit_trans:
if (ret)
return ret;
/*
- * make sure that all running delayed iput are
- * done
+ * The cleaner kthread might still be doing iput
+ * operations. Wait for it to finish so that
+ * more space is released.
*/
- down_write(&root->fs_info->delayed_iput_sem);
- up_write(&root->fs_info->delayed_iput_sem);
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
goto again;
} else {
btrfs_end_transaction(trans, root);
@@ -10399,7 +10402,7 @@ btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
* more device items and remove one chunk item), but this is done at
* btrfs_remove_chunk() through a call to check_system_chunk().
*/
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
num_items = 3 + map->num_stripes;
free_extent_map(em);
@@ -10586,7 +10589,7 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
disk_super = fs_info->super_copy;
if (!btrfs_super_root(disk_super))
- return 1;
+ return -EINVAL;
features = btrfs_super_incompat_flags(disk_super);
if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
@@ -10816,3 +10819,23 @@ int btrfs_start_write_no_snapshoting(struct btrfs_root *root)
}
return 1;
}
+
+static int wait_snapshoting_atomic_t(atomic_t *a)
+{
+ schedule();
+ return 0;
+}
+
+void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
+{
+ while (true) {
+ int ret;
+
+ ret = btrfs_start_write_no_snapshoting(root);
+ if (ret)
+ break;
+ wait_on_atomic_t(&root->will_be_snapshoted,
+ wait_snapshoting_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ }
+}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 6a98bddd8f33..84fb56d5c018 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -76,7 +76,7 @@ void free_extent_map(struct extent_map *em)
WARN_ON(extent_map_in_tree(em));
WARN_ON(!list_empty(&em->list));
if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
- kfree(em->bdev);
+ kfree(em->map_lookup);
kmem_cache_free(extent_map_cache, em);
}
}
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index b2991fd8583e..eb8b8fae036b 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -32,7 +32,15 @@ struct extent_map {
u64 block_len;
u64 generation;
unsigned long flags;
- struct block_device *bdev;
+ union {
+ struct block_device *bdev;
+
+ /*
+ * used for chunk mappings
+ * flags & EXTENT_FLAG_FS_MAPPING must be set
+ */
+ struct map_lookup *map_lookup;
+ };
atomic_t refs;
unsigned int compress_type;
struct list_head list;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 83d7859d7619..098bb8f690c9 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -406,8 +406,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
/* simple helper to fault in pages and copy. This should go away
* and be replaced with calls into generic code.
*/
-static noinline int btrfs_copy_from_user(loff_t pos, int num_pages,
- size_t write_bytes,
+static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes,
struct page **prepared_pages,
struct iov_iter *i)
{
@@ -1588,8 +1587,7 @@ again:
ret = 0;
}
- copied = btrfs_copy_from_user(pos, num_pages,
- write_bytes, pages, i);
+ copied = btrfs_copy_from_user(pos, write_bytes, pages, i);
/*
* if we have trouble faulting in the pages, fall
@@ -1764,17 +1762,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
loff_t pos;
size_t count;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
err = generic_write_checks(iocb, from);
if (err <= 0) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return err;
}
current->backing_dev_info = inode_to_bdi(inode);
err = file_remove_privs(file);
if (err) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out;
}
@@ -1785,7 +1783,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
* to stop this write operation to ensure FS consistency.
*/
if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
err = -EROFS;
goto out;
}
@@ -1806,7 +1804,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
end_pos = round_up(pos + count, root->sectorsize);
err = btrfs_cont_expand(inode, i_size_read(inode), end_pos);
if (err) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out;
}
}
@@ -1822,7 +1820,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
iocb->ki_pos = pos + num_written;
}
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
/*
* We also have to set last_sub_trans to the current log transid,
@@ -1911,7 +1909,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
return ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
atomic_inc(&root->log_batch);
full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
@@ -1963,7 +1961,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
ret = start_ordered_ops(inode, start, end);
}
if (ret) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out;
}
atomic_inc(&root->log_batch);
@@ -2009,7 +2007,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
&BTRFS_I(inode)->runtime_flags);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out;
}
@@ -2033,7 +2031,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out;
}
trans->sync = true;
@@ -2056,7 +2054,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
/*
* If any of the ordered extents had an error, just return it to user
@@ -2305,7 +2303,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
ino_size = round_up(inode->i_size, PAGE_CACHE_SIZE);
ret = find_first_non_hole(inode, &offset, &len);
if (ret < 0)
@@ -2345,7 +2343,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
truncated_page = true;
ret = btrfs_truncate_page(inode, offset, 0, 0);
if (ret) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return ret;
}
}
@@ -2421,7 +2419,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
ret = btrfs_wait_ordered_range(inode, lockstart,
lockend - lockstart + 1);
if (ret) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return ret;
}
}
@@ -2576,7 +2574,7 @@ out_only_mutex:
ret = btrfs_end_transaction(trans, root);
}
}
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
if (ret && !err)
err = ret;
return err;
@@ -2660,7 +2658,7 @@ static long btrfs_fallocate(struct file *file, int mode,
if (ret < 0)
return ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
ret = inode_newsize_ok(inode, alloc_end);
if (ret)
goto out;
@@ -2818,7 +2816,7 @@ out:
* So this is completely used as cleanup.
*/
btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
/* Let go of our reservation. */
btrfs_free_reserved_data_space(inode, alloc_start,
alloc_end - alloc_start);
@@ -2894,7 +2892,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
struct inode *inode = file->f_mapping->host;
int ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
switch (whence) {
case SEEK_END:
case SEEK_CUR:
@@ -2903,20 +2901,20 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
case SEEK_DATA:
case SEEK_HOLE:
if (offset >= i_size_read(inode)) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return -ENXIO;
}
ret = find_desired_extent(inode, &offset, whence);
if (ret) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return ret;
}
}
offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return offset;
}
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 393e36bd5845..53dbeaf6ce94 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -153,6 +153,20 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
static unsigned long *alloc_bitmap(u32 bitmap_size)
{
+ void *mem;
+
+ /*
+ * The allocation size varies, observed numbers were < 4K up to 16K.
+ * Using vmalloc unconditionally would be too heavy, we'll try
+ * contiguous allocations first.
+ */
+ if (bitmap_size <= PAGE_SIZE)
+ return kzalloc(bitmap_size, GFP_NOFS);
+
+ mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN);
+ if (mem)
+ return mem;
+
return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO,
PAGE_KERNEL);
}
@@ -289,7 +303,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
ret = 0;
out:
- vfree(bitmap);
+ kvfree(bitmap);
if (ret)
btrfs_abort_transaction(trans, root, ret);
return ret;
@@ -438,7 +452,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans,
ret = 0;
out:
- vfree(bitmap);
+ kvfree(bitmap);
if (ret)
btrfs_abort_transaction(trans, root, ret);
return ret;
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 8b57c17b3fb3..e50316c4af15 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -515,7 +515,7 @@ out:
return ret;
}
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
{
struct btrfs_path *path;
int ret;
@@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
int ret;
mutex_lock(&root->objectid_mutex);
- if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
- ret = btrfs_find_highest_objectid(root,
- &root->highest_objectid);
- if (ret)
- goto out;
- }
-
if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
ret = -ENOSPC;
goto out;
diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h
index ddb347bfee23..c8e864b2d530 100644
--- a/fs/btrfs/inode-map.h
+++ b/fs/btrfs/inode-map.h
@@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
struct btrfs_trans_handle *trans);
int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
#endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 247830107686..5f06eb1f4384 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3134,7 +3134,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
- down_read(&fs_info->delayed_iput_sem);
spin_lock(&fs_info->delayed_iput_lock);
while (!list_empty(&fs_info->delayed_iputs)) {
struct btrfs_inode *inode;
@@ -3153,7 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
spin_lock(&fs_info->delayed_iput_lock);
}
spin_unlock(&fs_info->delayed_iput_lock);
- up_read(&root->fs_info->delayed_iput_sem);
}
/*
@@ -4874,26 +4872,6 @@ next:
return err;
}
-static int wait_snapshoting_atomic_t(atomic_t *a)
-{
- schedule();
- return 0;
-}
-
-static void wait_for_snapshot_creation(struct btrfs_root *root)
-{
- while (true) {
- int ret;
-
- ret = btrfs_start_write_no_snapshoting(root);
- if (ret)
- break;
- wait_on_atomic_t(&root->will_be_snapshoted,
- wait_snapshoting_atomic_t,
- TASK_UNINTERRUPTIBLE);
- }
-}
-
static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -4925,7 +4903,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
* truncation, it must capture all writes that happened before
* this truncation.
*/
- wait_for_snapshot_creation(root);
+ btrfs_wait_for_snapshot_creation(root);
ret = btrfs_cont_expand(inode, oldsize, newsize);
if (ret) {
btrfs_end_write_no_snapshoting(root);
@@ -7138,21 +7116,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
if (ret)
return ERR_PTR(ret);
- em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
- ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em)) {
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- return em;
- }
-
+ /*
+ * Create the ordered extent before the extent map. This is to avoid
+ * races with the fast fsync path that would lead to it logging file
+ * extent items that point to disk extents that were not yet written to.
+ * The fast fsync path collects ordered extents into a local list and
+ * then collects all the new extent maps, so we must create the ordered
+ * extent first and make sure the fast fsync path collects any new
+ * ordered extents after collecting new extent maps as well.
+ * The fsync path simply can not rely on inode_dio_wait() because it
+ * causes deadlock with AIO.
+ */
ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
ins.offset, ins.offset, 0);
if (ret) {
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- free_extent_map(em);
return ERR_PTR(ret);
}
+ em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
+ ins.offset, ins.offset, ins.offset, 0);
+ if (IS_ERR(em)) {
+ struct btrfs_ordered_extent *oe;
+
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
+ oe = btrfs_lookup_ordered_extent(inode, start);
+ ASSERT(oe);
+ if (WARN_ON(!oe))
+ return em;
+ set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
+ set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
+ btrfs_remove_ordered_extent(inode, oe);
+ /* Once for our lookup and once for the ordered extents tree. */
+ btrfs_put_ordered_extent(oe);
+ btrfs_put_ordered_extent(oe);
+ }
return em;
}
@@ -8469,7 +8467,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
* not unlock the i_mutex at this case.
*/
if (offset + count <= inode->i_size) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
relock = true;
}
ret = btrfs_delalloc_reserve_space(inode, offset, count);
@@ -8526,7 +8524,7 @@ out:
if (wakeup)
inode_dio_end(inode);
if (relock)
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
return ret;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2a47a3148ec8..952172ca7e45 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -240,7 +240,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (ret)
return ret;
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
ip_oldflags = ip->flags;
i_oldflags = inode->i_flags;
@@ -358,7 +358,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
}
out_unlock:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
mnt_drop_write_file(file);
return ret;
}
@@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir,
goto fail;
}
+ mutex_lock(&new_root->objectid_mutex);
+ new_root->highest_objectid = new_dirid;
+ mutex_unlock(&new_root->objectid_mutex);
+
/*
* insert the directory item
*/
@@ -877,7 +881,7 @@ out_up_read:
out_dput:
dput(dentry);
out_unlock:
- mutex_unlock(&dir->i_mutex);
+ inode_unlock(dir);
return error;
}
@@ -1389,18 +1393,18 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
ra_index += cluster;
}
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
BTRFS_I(inode)->force_compress = compress_type;
ret = cluster_pages_for_defrag(inode, pages, i, cluster);
if (ret < 0) {
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
goto out_ra;
}
defrag_count += ret;
balance_dirty_pages_ratelimited(inode->i_mapping);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
if (newer_than) {
if (newer_off == (u64)-1)
@@ -1461,9 +1465,9 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
out_ra:
if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
}
if (!file)
kfree(ra);
@@ -2426,7 +2430,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
goto out_dput;
}
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
/*
* Don't allow to delete a subvolume with send in progress. This is
@@ -2539,7 +2543,7 @@ out_up_write:
spin_unlock(&dest->root_item_lock);
}
out_unlock_inode:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
if (!err) {
d_invalidate(dentry);
btrfs_invalidate_inodes(dest);
@@ -2555,7 +2559,7 @@ out_unlock_inode:
out_dput:
dput(dentry);
out_unlock_dir:
- mutex_unlock(&dir->i_mutex);
+ inode_unlock(dir);
out_drop_write:
mnt_drop_write_file(file);
out:
@@ -2853,8 +2857,8 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
{
- mutex_unlock(&inode1->i_mutex);
- mutex_unlock(&inode2->i_mutex);
+ inode_unlock(inode1);
+ inode_unlock(inode2);
}
static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
@@ -2862,8 +2866,8 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
if (inode1 < inode2)
swap(inode1, inode2);
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+ inode_lock_nested(inode1, I_MUTEX_PARENT);
+ inode_lock_nested(inode2, I_MUTEX_CHILD);
}
static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
@@ -3022,7 +3026,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
return 0;
if (same_inode) {
- mutex_lock(&src->i_mutex);
+ inode_lock(src);
ret = extent_same_check_offsets(src, loff, &len, olen);
if (ret)
@@ -3097,7 +3101,7 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
btrfs_cmp_data_free(&cmp);
out_unlock:
if (same_inode)
- mutex_unlock(&src->i_mutex);
+ inode_unlock(src);
else
btrfs_double_inode_unlock(src, dst);
@@ -3745,7 +3749,7 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
if (!same_inode) {
btrfs_double_inode_lock(src, inode);
} else {
- mutex_lock(&src->i_mutex);
+ inode_lock(src);
}
/* determine range to clone */
@@ -3816,7 +3820,7 @@ out_unlock:
if (!same_inode)
btrfs_double_inode_unlock(src, inode);
else
- mutex_unlock(&src->i_mutex);
+ inode_unlock(src);
return ret;
}
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 6d707545f775..55161369fab1 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -609,13 +609,28 @@ static int rbio_can_merge(struct btrfs_raid_bio *last,
return 1;
}
+static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe,
+ int index)
+{
+ return stripe * rbio->stripe_npages + index;
+}
+
+/*
+ * these are just the pages from the rbio array, not from anything
+ * the FS sent down to us
+ */
+static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe,
+ int index)
+{
+ return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)];
+}
+
/*
* helper to index into the pstripe
*/
static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
{
- index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
- return rbio->stripe_pages[index];
+ return rbio_stripe_page(rbio, rbio->nr_data, index);
}
/*
@@ -626,10 +641,7 @@ static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
{
if (rbio->nr_data + 1 == rbio->real_stripes)
return NULL;
-
- index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
- PAGE_CACHE_SHIFT;
- return rbio->stripe_pages[index];
+ return rbio_stripe_page(rbio, rbio->nr_data + 1, index);
}
/*
@@ -889,6 +901,7 @@ static void raid_write_end_io(struct bio *bio)
{
struct btrfs_raid_bio *rbio = bio->bi_private;
int err = bio->bi_error;
+ int max_errors;
if (err)
fail_bio_stripe(rbio, bio);
@@ -901,7 +914,9 @@ static void raid_write_end_io(struct bio *bio)
err = 0;
/* OK, we have read all the stripes we need to. */
- if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
+ max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
+ 0 : rbio->bbio->max_errors;
+ if (atomic_read(&rbio->error) > max_errors)
err = -EIO;
rbio_orig_end_io(rbio, err);
@@ -947,8 +962,7 @@ static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
*/
static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
{
- unsigned long nr = stripe_len * nr_stripes;
- return DIV_ROUND_UP(nr, PAGE_CACHE_SIZE);
+ return DIV_ROUND_UP(stripe_len, PAGE_CACHE_SIZE) * nr_stripes;
}
/*
@@ -966,8 +980,8 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_root *root,
void *p;
rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2 +
- DIV_ROUND_UP(stripe_npages, BITS_PER_LONG / 8),
- GFP_NOFS);
+ DIV_ROUND_UP(stripe_npages, BITS_PER_LONG) *
+ sizeof(long), GFP_NOFS);
if (!rbio)
return ERR_PTR(-ENOMEM);
@@ -1021,18 +1035,17 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
if (!page)
return -ENOMEM;
rbio->stripe_pages[i] = page;
- ClearPageUptodate(page);
}
return 0;
}
-/* allocate pages for just the p/q stripes */
+/* only allocate pages for p/q stripes */
static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
{
int i;
struct page *page;
- i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
+ i = rbio_stripe_page_index(rbio, rbio->nr_data, 0);
for (; i < rbio->nr_pages; i++) {
if (rbio->stripe_pages[i])
@@ -1121,18 +1134,6 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
}
/*
- * these are just the pages from the rbio array, not from anything
- * the FS sent down to us
- */
-static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe, int page)
-{
- int index;
- index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
- index += page;
- return rbio->stripe_pages[index];
-}
-
-/*
* helper function to walk our bio list and populate the bio_pages array with
* the result. This seems expensive, but it is faster than constantly
* searching through the bio list as we setup the IO in finish_rmw or stripe
@@ -1175,7 +1176,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
{
struct btrfs_bio *bbio = rbio->bbio;
void *pointers[rbio->real_stripes];
- int stripe_len = rbio->stripe_len;
int nr_data = rbio->nr_data;
int stripe;
int pagenr;
@@ -1183,7 +1183,6 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
int q_stripe = -1;
struct bio_list bio_list;
struct bio *bio;
- int pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
int ret;
bio_list_init(&bio_list);
@@ -1226,7 +1225,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
else
clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *p;
/* first collect one page from each data stripe */
for (stripe = 0; stripe < nr_data; stripe++) {
@@ -1268,7 +1267,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
* everything else.
*/
for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
if (stripe < rbio->nr_data) {
page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1292,7 +1291,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
if (!bbio->tgtdev_map[stripe])
continue;
- for (pagenr = 0; pagenr < pages_per_stripe; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
if (stripe < rbio->nr_data) {
page = page_in_rbio(rbio, stripe, pagenr, 1);
@@ -1506,7 +1505,6 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
int bios_to_read = 0;
struct bio_list bio_list;
int ret;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
int pagenr;
int stripe;
struct bio *bio;
@@ -1525,7 +1523,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
* stripe
*/
for (stripe = 0; stripe < rbio->nr_data; stripe++) {
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *page;
/*
* we want to find all the pages missing from
@@ -1801,7 +1799,6 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
int pagenr, stripe;
void **pointers;
int faila = -1, failb = -1;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
struct page *page;
int err;
int i;
@@ -1824,7 +1821,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
index_rbio_pages(rbio);
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
/*
* Now we just use bitmap to mark the horizontal stripes in
* which we have data when doing parity scrub.
@@ -1935,7 +1932,7 @@ pstripe:
* other endio functions will fiddle the uptodate bits
*/
if (rbio->operation == BTRFS_RBIO_WRITE) {
- for (i = 0; i < nr_pages; i++) {
+ for (i = 0; i < rbio->stripe_npages; i++) {
if (faila != -1) {
page = rbio_stripe_page(rbio, faila, i);
SetPageUptodate(page);
@@ -2031,7 +2028,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
int bios_to_read = 0;
struct bio_list bio_list;
int ret;
- int nr_pages = DIV_ROUND_UP(rbio->stripe_len, PAGE_CACHE_SIZE);
int pagenr;
int stripe;
struct bio *bio;
@@ -2055,7 +2051,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
continue;
}
- for (pagenr = 0; pagenr < nr_pages; pagenr++) {
+ for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
struct page *p;
/*
@@ -2279,37 +2275,11 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
if (!page)
return -ENOMEM;
rbio->stripe_pages[index] = page;
- ClearPageUptodate(page);
}
}
return 0;
}
-/*
- * end io function used by finish_rmw. When we finally
- * get here, we've written a full stripe
- */
-static void raid_write_parity_end_io(struct bio *bio)
-{
- struct btrfs_raid_bio *rbio = bio->bi_private;
- int err = bio->bi_error;
-
- if (bio->bi_error)
- fail_bio_stripe(rbio, bio);
-
- bio_put(bio);
-
- if (!atomic_dec_and_test(&rbio->stripes_pending))
- return;
-
- err = 0;
-
- if (atomic_read(&rbio->error))
- err = -EIO;
-
- rbio_orig_end_io(rbio, err);
-}
-
static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
int need_check)
{
@@ -2462,7 +2432,7 @@ submit_write:
break;
bio->bi_private = rbio;
- bio->bi_end_io = raid_write_parity_end_io;
+ bio->bi_end_io = raid_write_end_io;
submit_bio(WRITE, bio);
}
return;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ef6d8fc85853..2bd0011450df 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid)
root_objectid == BTRFS_TREE_LOG_OBJECTID ||
root_objectid == BTRFS_CSUM_TREE_OBJECTID ||
root_objectid == BTRFS_UUID_TREE_OBJECTID ||
- root_objectid == BTRFS_QUOTA_TREE_OBJECTID)
+ root_objectid == BTRFS_QUOTA_TREE_OBJECTID ||
+ root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
return 1;
return 0;
}
@@ -3030,7 +3031,7 @@ int prealloc_file_extent_cluster(struct inode *inode,
int ret = 0;
BUG_ON(cluster->start != cluster->boundary[0]);
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
ret = btrfs_check_data_free_space(inode, cluster->start,
cluster->end + 1 - cluster->start);
@@ -3057,7 +3058,7 @@ int prealloc_file_extent_cluster(struct inode *inode,
btrfs_free_reserved_data_space(inode, cluster->start,
cluster->end + 1 - cluster->start);
out:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
return ret;
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 0c981ebe2acb..92bf5ee732fb 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2813,7 +2813,7 @@ out:
static inline int scrub_calc_parity_bitmap_len(int nsectors)
{
- return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * (BITS_PER_LONG / 8);
+ return DIV_ROUND_UP(nsectors, BITS_PER_LONG) * sizeof(long);
}
static void scrub_parity_get(struct scrub_parity *sparity)
@@ -3458,7 +3458,7 @@ static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx,
return ret;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (em->start != chunk_offset)
goto out;
@@ -4279,7 +4279,7 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
return PTR_ERR(inode);
/* Avoid truncate/dio/punch hole.. */
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
inode_dio_wait(inode);
physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
@@ -4358,7 +4358,7 @@ next_page:
}
ret = COPY_COMPLETE;
out:
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
iput(inode);
return ret;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9b9eab6d048e..d41e09fe8e38 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -383,6 +383,9 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
int ret = 0;
char *compress_type;
bool compress_force = false;
+ enum btrfs_compression_type saved_compress_type;
+ bool saved_compress_force;
+ int no_compress = 0;
cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE))
@@ -462,6 +465,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
/* Fallthrough */
case Opt_compress:
case Opt_compress_type:
+ saved_compress_type = btrfs_test_opt(root, COMPRESS) ?
+ info->compress_type : BTRFS_COMPRESS_NONE;
+ saved_compress_force =
+ btrfs_test_opt(root, FORCE_COMPRESS);
if (token == Opt_compress ||
token == Opt_compress_force ||
strcmp(args[0].from, "zlib") == 0) {
@@ -470,6 +477,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
+ no_compress = 0;
} else if (strcmp(args[0].from, "lzo") == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
@@ -477,25 +485,21 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
btrfs_set_fs_incompat(info, COMPRESS_LZO);
+ no_compress = 0;
} else if (strncmp(args[0].from, "no", 2) == 0) {
compress_type = "no";
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
compress_force = false;
+ no_compress++;
} else {
ret = -EINVAL;
goto out;
}
if (compress_force) {
- btrfs_set_and_info(root, FORCE_COMPRESS,
- "force %s compression",
- compress_type);
+ btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
} else {
- if (!btrfs_test_opt(root, COMPRESS))
- btrfs_info(root->fs_info,
- "btrfs: use %s compression",
- compress_type);
/*
* If we remount from compress-force=xxx to
* compress=xxx, we need clear FORCE_COMPRESS
@@ -504,6 +508,17 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
*/
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
}
+ if ((btrfs_test_opt(root, COMPRESS) &&
+ (info->compress_type != saved_compress_type ||
+ compress_force != saved_compress_force)) ||
+ (!btrfs_test_opt(root, COMPRESS) &&
+ no_compress == 1)) {
+ btrfs_info(root->fs_info,
+ "%s %s compression",
+ (compress_force) ? "force" : "use",
+ compress_type);
+ }
+ compress_force = false;
break;
case Opt_ssd:
btrfs_set_and_info(root, SSD,
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index e0ac85949067..539e7b5e3f86 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
+BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE);
static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(mixed_backref),
@@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
BTRFS_FEAT_ATTR_PTR(raid56),
BTRFS_FEAT_ATTR_PTR(skinny_metadata),
BTRFS_FEAT_ATTR_PTR(no_holes),
+ BTRFS_FEAT_ATTR_PTR(free_space_tree),
NULL
};
@@ -780,6 +782,39 @@ failure:
return error;
}
+
+/*
+ * Change per-fs features in /sys/fs/btrfs/UUID/features to match current
+ * values in superblock. Call after any changes to incompat/compat_ro flags
+ */
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+ u64 bit, enum btrfs_feature_set set)
+{
+ struct btrfs_fs_devices *fs_devs;
+ struct kobject *fsid_kobj;
+ u64 features;
+ int ret;
+
+ if (!fs_info)
+ return;
+
+ features = get_features(fs_info, set);
+ ASSERT(bit & supported_feature_masks[set]);
+
+ fs_devs = fs_info->fs_devices;
+ fsid_kobj = &fs_devs->fsid_kobj;
+
+ if (!fsid_kobj->state_initialized)
+ return;
+
+ /*
+ * FIXME: this is too heavy to update just one value, ideally we'd like
+ * to use sysfs_update_group but some refactoring is needed first.
+ */
+ sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group);
+ ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group);
+}
+
static int btrfs_init_debugfs(void)
{
#ifdef CONFIG_DEBUG_FS
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9c09522125a6..d7da1a4c2f6c 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = { \
#define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
#define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
- BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature)
+ BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature)
#define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
@@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs,
struct kobject *parent);
int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs);
void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs);
+void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info,
+ u64 bit, enum btrfs_feature_set set);
+
#endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index b1d920b30070..0e1e61a7ec23 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -82,18 +82,18 @@ void btrfs_destroy_test_fs(void)
struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void)
{
struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info),
- GFP_NOFS);
+ GFP_KERNEL);
if (!fs_info)
return fs_info;
fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices),
- GFP_NOFS);
+ GFP_KERNEL);
if (!fs_info->fs_devices) {
kfree(fs_info);
return NULL;
}
fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block),
- GFP_NOFS);
+ GFP_KERNEL);
if (!fs_info->super_copy) {
kfree(fs_info->fs_devices);
kfree(fs_info);
@@ -180,11 +180,11 @@ btrfs_alloc_dummy_block_group(unsigned long length)
{
struct btrfs_block_group_cache *cache;
- cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ cache = kzalloc(sizeof(*cache), GFP_KERNEL);
if (!cache)
return NULL;
cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
- GFP_NOFS);
+ GFP_KERNEL);
if (!cache->free_space_ctl) {
kfree(cache);
return NULL;
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index e29fa297e053..669b58201e36 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -94,7 +94,7 @@ static int test_find_delalloc(void)
* test.
*/
for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) {
- page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+ page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
if (!page) {
test_msg("Failed to allocate test page\n");
ret = -ENOMEM;
@@ -113,7 +113,7 @@ static int test_find_delalloc(void)
* |--- delalloc ---|
* |--- search ---|
*/
- set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS);
+ set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL);
start = 0;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -144,7 +144,7 @@ static int test_find_delalloc(void)
test_msg("Couldn't find the locked page\n");
goto out_bits;
}
- set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS);
+ set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -199,7 +199,7 @@ static int test_find_delalloc(void)
*
* We are re-using our test_start from above since it works out well.
*/
- set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS);
+ set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -262,7 +262,7 @@ static int test_find_delalloc(void)
}
ret = 0;
out_bits:
- clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS);
+ clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL);
out:
if (locked_page)
page_cache_release(locked_page);
@@ -360,7 +360,7 @@ static int test_eb_bitmaps(void)
test_msg("Running extent buffer bitmap tests\n");
- bitmap = kmalloc(len, GFP_NOFS);
+ bitmap = kmalloc(len, GFP_KERNEL);
if (!bitmap) {
test_msg("Couldn't allocate test bitmap\n");
return -ENOMEM;
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 5de55fdd28bc..e2d3da02deee 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -974,7 +974,7 @@ static int test_extent_accounting(void)
(BTRFS_MAX_EXTENT_SIZE >> 1) + 4095,
EXTENT_DELALLOC | EXTENT_DIRTY |
EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0,
- NULL, GFP_NOFS);
+ NULL, GFP_KERNEL);
if (ret) {
test_msg("clear_extent_bit returned %d\n", ret);
goto out;
@@ -1045,7 +1045,7 @@ static int test_extent_accounting(void)
BTRFS_MAX_EXTENT_SIZE+8191,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
- NULL, GFP_NOFS);
+ NULL, GFP_KERNEL);
if (ret) {
test_msg("clear_extent_bit returned %d\n", ret);
goto out;
@@ -1079,7 +1079,7 @@ static int test_extent_accounting(void)
ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
- NULL, GFP_NOFS);
+ NULL, GFP_KERNEL);
if (ret) {
test_msg("clear_extent_bit returned %d\n", ret);
goto out;
@@ -1096,7 +1096,7 @@ out:
clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0,
- NULL, GFP_NOFS);
+ NULL, GFP_KERNEL);
iput(inode);
btrfs_free_dummy_root(root);
return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 323e12cc9d2f..978c3a810893 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4127,7 +4127,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
struct inode *inode,
struct btrfs_path *path,
struct list_head *logged_list,
- struct btrfs_log_ctx *ctx)
+ struct btrfs_log_ctx *ctx,
+ const u64 start,
+ const u64 end)
{
struct extent_map *em, *n;
struct list_head extents;
@@ -4166,7 +4168,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
}
list_sort(NULL, &extents, extent_cmp);
-
+ /*
+ * Collect any new ordered extents within the range. This is to
+ * prevent logging file extent items without waiting for the disk
+ * location they point to being written. We do this only to deal
+ * with races against concurrent lockless direct IO writes.
+ */
+ btrfs_get_logged_extents(inode, logged_list, start, end);
process:
while (!list_empty(&extents)) {
em = list_entry(extents.next, struct extent_map, list);
@@ -4701,7 +4709,7 @@ log_extents:
goto out_unlock;
}
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
- &logged_list, ctx);
+ &logged_list, ctx, start, end);
if (ret) {
err = ret;
goto out_unlock;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c32abbca9d77..366b335946fa 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -108,7 +108,7 @@ const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
},
};
-const u64 const btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
+const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
[BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
[BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
@@ -233,6 +233,7 @@ static struct btrfs_device *__alloc_device(void)
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
@@ -1183,7 +1184,7 @@ again:
struct map_lookup *map;
int i;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
u64 end;
@@ -2755,7 +2756,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
free_extent_map(em);
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
lock_chunks(root->fs_info->chunk_root);
check_system_chunk(trans, extent_root, map->type);
unlock_chunks(root->fs_info->chunk_root);
@@ -3751,7 +3752,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
btrfs_warn(fs_info,
- "metatdata profile 0x%llx has lower redundancy than data profile 0x%llx",
+ "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
bctl->meta.target, bctl->data.target);
}
@@ -4718,7 +4719,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
goto error;
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = start;
em->len = num_bytes;
em->block_start = 0;
@@ -4813,7 +4814,7 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
item_size = btrfs_chunk_item_size(map->num_stripes);
stripe_size = em->orig_block_len;
@@ -4968,7 +4969,7 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset)
if (!em)
return 1;
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
if (map->stripes[i].dev->missing) {
miss_ndevs++;
@@ -5048,7 +5049,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
return 1;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
ret = map->num_stripes;
else if (map->type & BTRFS_BLOCK_GROUP_RAID10)
@@ -5084,7 +5085,7 @@ unsigned long btrfs_full_stripe_len(struct btrfs_root *root,
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
len = map->stripe_len * nr_data_stripes(map);
free_extent_map(em);
@@ -5105,7 +5106,7 @@ int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
BUG_ON(!em);
BUG_ON(em->start > logical || em->start + em->len < logical);
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
ret = 1;
free_extent_map(em);
@@ -5264,7 +5265,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
return -EINVAL;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
offset = logical - em->start;
stripe_len = map->stripe_len;
@@ -5378,35 +5379,33 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int rw,
* target drive.
*/
for (i = 0; i < tmp_num_stripes; i++) {
- if (tmp_bbio->stripes[i].dev->devid == srcdev_devid) {
- /*
- * In case of DUP, in order to keep it
- * simple, only add the mirror with the
- * lowest physical address
- */
- if (found &&
- physical_of_found <=
- tmp_bbio->stripes[i].physical)
- continue;
- index_srcdev = i;
- found = 1;
- physical_of_found =
- tmp_bbio->stripes[i].physical;
- }
+ if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
+ continue;
+
+ /*
+ * In case of DUP, in order to keep it simple, only add
+ * the mirror with the lowest physical address
+ */
+ if (found &&
+ physical_of_found <= tmp_bbio->stripes[i].physical)
+ continue;
+
+ index_srcdev = i;
+ found = 1;
+ physical_of_found = tmp_bbio->stripes[i].physical;
}
- if (found) {
- mirror_num = index_srcdev + 1;
- patch_the_first_stripe_for_dev_replace = 1;
- physical_to_patch_in_first_stripe = physical_of_found;
- } else {
+ btrfs_put_bbio(tmp_bbio);
+
+ if (!found) {
WARN_ON(1);
ret = -EIO;
- btrfs_put_bbio(tmp_bbio);
goto out;
}
- btrfs_put_bbio(tmp_bbio);
+ mirror_num = index_srcdev + 1;
+ patch_the_first_stripe_for_dev_replace = 1;
+ physical_to_patch_in_first_stripe = physical_of_found;
} else if (mirror_num > map->num_stripes) {
mirror_num = 0;
}
@@ -5806,7 +5805,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
free_extent_map(em);
return -EIO;
}
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
length = em->len;
rmap_len = map->stripe_len;
@@ -6069,7 +6068,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
bbio->fs_info = root->fs_info;
atomic_set(&bbio->stripes_pending, bbio->num_stripes);
- if (bbio->raid_map) {
+ if ((bbio->map_type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
+ ((rw & WRITE) || (mirror_num > 1))) {
/* In this case, map_length has been set to the length of
a single stripe; not the whole write */
if (rw & WRITE) {
@@ -6210,6 +6210,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
struct extent_map *em;
u64 logical;
u64 length;
+ u64 stripe_len;
u64 devid;
u8 uuid[BTRFS_UUID_SIZE];
int num_stripes;
@@ -6218,6 +6219,37 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
+ stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
+ num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
+ /* Validation check */
+ if (!num_stripes) {
+ btrfs_err(root->fs_info, "invalid chunk num_stripes: %u",
+ num_stripes);
+ return -EIO;
+ }
+ if (!IS_ALIGNED(logical, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk logical %llu", logical);
+ return -EIO;
+ }
+ if (!length || !IS_ALIGNED(length, root->sectorsize)) {
+ btrfs_err(root->fs_info,
+ "invalid chunk length %llu", length);
+ return -EIO;
+ }
+ if (!is_power_of_2(stripe_len)) {
+ btrfs_err(root->fs_info, "invalid chunk stripe length: %llu",
+ stripe_len);
+ return -EIO;
+ }
+ if (~(BTRFS_BLOCK_GROUP_TYPE_MASK | BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk)) {
+ btrfs_err(root->fs_info, "unrecognized chunk type: %llu",
+ ~(BTRFS_BLOCK_GROUP_TYPE_MASK |
+ BTRFS_BLOCK_GROUP_PROFILE_MASK) &
+ btrfs_chunk_type(leaf, chunk));
+ return -EIO;
+ }
read_lock(&map_tree->map_tree.lock);
em = lookup_extent_mapping(&map_tree->map_tree, logical, 1);
@@ -6234,7 +6266,6 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
em = alloc_extent_map();
if (!em)
return -ENOMEM;
- num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
if (!map) {
free_extent_map(em);
@@ -6242,7 +6273,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key,
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
- em->bdev = (struct block_device *)map;
+ em->map_lookup = map;
em->start = logical;
em->len = length;
em->orig_start = 0;
@@ -6944,7 +6975,7 @@ void btrfs_update_commit_device_bytes_used(struct btrfs_root *root,
/* In order to kick the device replace finish process */
lock_chunks(root);
list_for_each_entry(em, &transaction->pending_chunks, list) {
- map = (struct map_lookup *)em->bdev;
+ map = em->map_lookup;
for (i = 0; i < map->num_stripes; i++) {
dev = map->stripes[i].dev;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index fd953c361a43..6c68d6356197 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -126,7 +126,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
* locks the inode's i_mutex before calling setxattr or removexattr.
*/
if (flags & XATTR_REPLACE) {
- ASSERT(mutex_is_locked(&inode->i_mutex));
+ ASSERT(inode_is_locked(inode));
di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
name, name_len, 0);
if (!di)
generated by cgit v1.2.3 (git 2.39.1) at 2025-02-06 13:24:28 +0100