summaryrefslogtreecommitdiffstats
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/btrfs_inode.h14
-rw-r--r--fs/btrfs/ctree.h57
-rw-r--r--fs/btrfs/delayed-inode.c23
-rw-r--r--fs/btrfs/delayed-inode.h2
-rw-r--r--fs/btrfs/disk-io.c10
-rw-r--r--fs/btrfs/export.c15
-rw-r--r--fs/btrfs/extent-tree.c238
-rw-r--r--fs/btrfs/extent_io.c58
-rw-r--r--fs/btrfs/file-item.c4
-rw-r--r--fs/btrfs/file.c2
-rw-r--r--fs/btrfs/free-space-cache.c9
-rw-r--r--fs/btrfs/inode.c89
-rw-r--r--fs/btrfs/ioctl.c97
-rw-r--r--fs/btrfs/ioctl.h13
-rw-r--r--fs/btrfs/locking.c14
-rw-r--r--fs/btrfs/relocation.c3
-rw-r--r--fs/btrfs/struct-funcs.c196
-rw-r--r--fs/btrfs/super.c27
-rw-r--r--fs/btrfs/transaction.c27
-rw-r--r--fs/btrfs/transaction.h1
-rw-r--r--fs/btrfs/tree-log.c4
-rw-r--r--fs/btrfs/volumes.c25
-rw-r--r--fs/btrfs/volumes.h4
23 files changed, 522 insertions, 410 deletions
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 12394a90d60f..5b2ad6bc4fe7 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -87,9 +87,6 @@ struct btrfs_inode {
/* node for the red-black tree that links inodes in subvolume root */
struct rb_node rb_node;
- /* the space_info for where this inode's data allocations are done */
- struct btrfs_space_info *space_info;
-
unsigned long runtime_flags;
/* full 64 bit generation number, struct vfs_inode doesn't have a big
@@ -191,11 +188,14 @@ static inline void btrfs_i_size_write(struct inode *inode, u64 size)
BTRFS_I(inode)->disk_i_size = size;
}
-static inline bool btrfs_is_free_space_inode(struct btrfs_root *root,
- struct inode *inode)
+static inline bool btrfs_is_free_space_inode(struct inode *inode)
{
- if (root == root->fs_info->tree_root ||
- BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+
+ if (root == root->fs_info->tree_root &&
+ btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
+ return true;
+ if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
return true;
return false;
}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2ba03b96fbe0..00f9a50f986d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1319,6 +1319,8 @@ struct btrfs_fs_info {
*/
struct list_head space_info;
+ struct btrfs_space_info *data_sinfo;
+
struct reloc_control *reloc_ctl;
spinlock_t delalloc_lock;
@@ -1747,13 +1749,54 @@ static inline void btrfs_init_map_token (struct btrfs_map_token *token)
offsetof(type, member), \
sizeof(((type *)0)->member)))
-#ifndef BTRFS_SETGET_FUNCS
+#define DECLARE_BTRFS_SETGET_BITS(bits) \
+u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off, \
+ struct btrfs_map_token *token); \
+void btrfs_set_token_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off, u##bits val, \
+ struct btrfs_map_token *token); \
+static inline u##bits btrfs_get_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off) \
+{ \
+ return btrfs_get_token_##bits(eb, ptr, off, NULL); \
+} \
+static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off, u##bits val) \
+{ \
+ btrfs_set_token_##bits(eb, ptr, off, val, NULL); \
+}
+
+DECLARE_BTRFS_SETGET_BITS(8)
+DECLARE_BTRFS_SETGET_BITS(16)
+DECLARE_BTRFS_SETGET_BITS(32)
+DECLARE_BTRFS_SETGET_BITS(64)
+
#define BTRFS_SETGET_FUNCS(name, type, member, bits) \
-u##bits btrfs_##name(struct extent_buffer *eb, type *s); \
-u##bits btrfs_token_##name(struct extent_buffer *eb, type *s, struct btrfs_map_token *token); \
-void btrfs_set_token_##name(struct extent_buffer *eb, type *s, u##bits val, struct btrfs_map_token *token);\
-void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val);
-#endif
+static inline u##bits btrfs_##name(struct extent_buffer *eb, type *s) \
+{ \
+ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
+ return btrfs_get_##bits(eb, s, offsetof(type, member)); \
+} \
+static inline void btrfs_set_##name(struct extent_buffer *eb, type *s, \
+ u##bits val) \
+{ \
+ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
+ btrfs_set_##bits(eb, s, offsetof(type, member), val); \
+} \
+static inline u##bits btrfs_token_##name(struct extent_buffer *eb, type *s, \
+ struct btrfs_map_token *token) \
+{ \
+ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
+ return btrfs_get_token_##bits(eb, s, offsetof(type, member), token); \
+} \
+static inline void btrfs_set_token_##name(struct extent_buffer *eb, \
+ type *s, u##bits val, \
+ struct btrfs_map_token *token) \
+{ \
+ BUILD_BUG_ON(sizeof(u##bits) != sizeof(((type *)0))->member); \
+ btrfs_set_token_##bits(eb, s, offsetof(type, member), val, token); \
+}
#define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \
static inline u##bits btrfs_##name(struct extent_buffer *eb) \
@@ -2776,7 +2819,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 group_start);
u64 btrfs_reduce_alloc_profile(struct btrfs_root *root, u64 flags);
u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
-void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *ionde);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
@@ -3166,7 +3208,6 @@ int btrfs_readpage(struct file *file, struct page *page);
void btrfs_evict_inode(struct inode *inode);
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
int btrfs_dirty_inode(struct inode *inode);
-int btrfs_update_time(struct file *file);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 2399f4086915..335605c8ceab 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -62,6 +62,7 @@ static inline void btrfs_init_delayed_node(
INIT_LIST_HEAD(&delayed_node->n_list);
INIT_LIST_HEAD(&delayed_node->p_list);
delayed_node->bytes_reserved = 0;
+ memset(&delayed_node->inode_item, 0, sizeof(delayed_node->inode_item));
}
static inline int btrfs_is_continuous_delayed_item(
@@ -1113,8 +1114,8 @@ static int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
* Returns < 0 on error and returns with an aborted transaction with any
* outstanding delayed items cleaned up.
*/
-int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
+static int __btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, int nr)
{
struct btrfs_root *curr_root = root;
struct btrfs_delayed_root *delayed_root;
@@ -1122,6 +1123,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
struct btrfs_path *path;
struct btrfs_block_rsv *block_rsv;
int ret = 0;
+ bool count = (nr > 0);
if (trans->aborted)
return -EIO;
@@ -1137,7 +1139,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
delayed_root = btrfs_get_delayed_root(root);
curr_node = btrfs_first_delayed_node(delayed_root);
- while (curr_node) {
+ while (curr_node && (!count || (count && nr--))) {
curr_root = curr_node->root;
ret = btrfs_insert_delayed_items(trans, path, curr_root,
curr_node);
@@ -1149,6 +1151,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
path, curr_node);
if (ret) {
btrfs_release_delayed_node(curr_node);
+ curr_node = NULL;
btrfs_abort_transaction(trans, root, ret);
break;
}
@@ -1158,12 +1161,26 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
btrfs_release_delayed_node(prev_node);
}
+ if (curr_node)
+ btrfs_release_delayed_node(curr_node);
btrfs_free_path(path);
trans->block_rsv = block_rsv;
return ret;
}
+int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ return __btrfs_run_delayed_items(trans, root, -1);
+}
+
+int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, int nr)
+{
+ return __btrfs_run_delayed_items(trans, root, nr);
+}
+
static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
struct btrfs_delayed_node *node)
{
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f5aa4023d3e1..4f808e1baeed 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -107,6 +107,8 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode);
int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, int nr);
void btrfs_balance_delayed_items(struct btrfs_root *root);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 87d9391c0576..05f4fb6e0607 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -407,7 +407,7 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
break;
}
- if (failed && !ret)
+ if (failed && !ret && failed_mirror)
repair_eb_io_failure(root, eb, failed_mirror);
return ret;
@@ -2342,7 +2342,7 @@ int open_ctree(struct super_block *sb,
ret |= btrfs_start_workers(&fs_info->caching_workers);
ret |= btrfs_start_workers(&fs_info->readahead_workers);
if (ret) {
- ret = -ENOMEM;
+ err = -ENOMEM;
goto fail_sb_buffer;
}
@@ -2578,8 +2578,8 @@ retry_root_backup:
if (!(sb->s_flags & MS_RDONLY)) {
ret = btrfs_cleanup_fs_roots(fs_info);
- if (ret) {
- }
+ if (ret)
+ goto fail_trans_kthread;
ret = btrfs_recover_relocation(tree_root);
if (ret < 0) {
@@ -2895,7 +2895,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
* one reference for us, and we leave it for the
* caller
*/
- device->flush_bio = NULL;;
+ device->flush_bio = NULL;
bio = bio_alloc(GFP_NOFS, 0);
if (!bio)
return -ENOMEM;
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index e887ee62b6d4..614f34a899c2 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -13,15 +13,14 @@
parent_root_objectid) / 4)
#define BTRFS_FID_SIZE_CONNECTABLE_ROOT (sizeof(struct btrfs_fid) / 4)
-static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
- int connectable)
+static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
+ struct inode *parent)
{
struct btrfs_fid *fid = (struct btrfs_fid *)fh;
- struct inode *inode = dentry->d_inode;
int len = *max_len;
int type;
- if (connectable && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
+ if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) {
*max_len = BTRFS_FID_SIZE_CONNECTABLE;
return 255;
} else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) {
@@ -36,19 +35,13 @@ static int btrfs_encode_fh(struct dentry *dentry, u32 *fh, int *max_len,
fid->root_objectid = BTRFS_I(inode)->root->objectid;
fid->gen = inode->i_generation;
- if (connectable && !S_ISDIR(inode->i_mode)) {
- struct inode *parent;
+ if (parent) {
u64 parent_root_id;
- spin_lock(&dentry->d_lock);
-
- parent = dentry->d_parent->d_inode;
fid->parent_objectid = BTRFS_I(parent)->location.objectid;
fid->parent_gen = parent->i_generation;
parent_root_id = BTRFS_I(parent)->root->objectid;
- spin_unlock(&dentry->d_lock);
-
if (parent_root_id != fid->root_objectid) {
fid->parent_root_objectid = parent_root_id;
len = BTRFS_FID_SIZE_CONNECTABLE_ROOT;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2ce16f97730a..44f06201f376 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2670,8 +2670,10 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
node = rb_prev(node);
if (node) {
+ int seq = ref->seq;
+
ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- if (ref->bytenr == bytenr)
+ if (ref->bytenr == bytenr && ref->seq == seq)
goto out_unlock;
}
@@ -2992,8 +2994,13 @@ again:
}
spin_lock(&block_group->lock);
- if (block_group->cached != BTRFS_CACHE_FINISHED) {
- /* We're not cached, don't bother trying to write stuff out */
+ if (block_group->cached != BTRFS_CACHE_FINISHED ||
+ !btrfs_test_opt(root, SPACE_CACHE)) {
+ /*
+ * don't bother trying to write stuff out _if_
+ * a) we're not cached,
+ * b) we're with nospace_cache mount option.
+ */
dcs = BTRFS_DC_WRITTEN;
spin_unlock(&block_group->lock);
goto out_put;
@@ -3223,6 +3230,8 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
init_waitqueue_head(&found->wait);
*space_info = found;
list_add_rcu(&found->list, &info->space_info);
+ if (flags & BTRFS_BLOCK_GROUP_DATA)
+ info->data_sinfo = found;
return 0;
}
@@ -3352,12 +3361,6 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
return get_alloc_profile(root, flags);
}
-void btrfs_set_inode_space_info(struct btrfs_root *root, struct inode *inode)
-{
- BTRFS_I(inode)->space_info = __find_space_info(root->fs_info,
- BTRFS_BLOCK_GROUP_DATA);
-}
-
/*
* This will check the space that the inode allocates from to make sure we have
* enough space for bytes.
@@ -3366,6 +3369,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
{
struct btrfs_space_info *data_sinfo;
struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_fs_info *fs_info = root->fs_info;
u64 used;
int ret = 0, committed = 0, alloc_chunk = 1;
@@ -3378,7 +3382,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes)
committed = 1;
}
- data_sinfo = BTRFS_I(inode)->space_info;
+ data_sinfo = fs_info->data_sinfo;
if (!data_sinfo)
goto alloc;
@@ -3419,10 +3423,9 @@ alloc:
goto commit_trans;
}
- if (!data_sinfo) {
- btrfs_set_inode_space_info(root, inode);
- data_sinfo = BTRFS_I(inode)->space_info;
- }
+ if (!data_sinfo)
+ data_sinfo = fs_info->data_sinfo;
+
goto again;
}
@@ -3469,7 +3472,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes)
/* make sure bytes are sectorsize aligned */
bytes = (bytes + root->sectorsize - 1) & ~((u64)root->sectorsize - 1);
- data_sinfo = BTRFS_I(inode)->space_info;
+ data_sinfo = root->fs_info->data_sinfo;
spin_lock(&data_sinfo->lock);
data_sinfo->bytes_may_use -= bytes;
trace_btrfs_space_reservation(root->fs_info, "space_info",
@@ -3675,89 +3678,58 @@ out:
/*
* shrink metadata reservation for delalloc
*/
-static int shrink_delalloc(struct btrfs_root *root, u64 to_reclaim,
- bool wait_ordered)
+static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
+ bool wait_ordered)
{
struct btrfs_block_rsv *block_rsv;
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
- u64 reserved;
+ u64 delalloc_bytes;
u64 max_reclaim;
- u64 reclaimed = 0;
long time_left;
unsigned long nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
int loops = 0;
- unsigned long progress;
trans = (struct btrfs_trans_handle *)current->journal_info;
block_rsv = &root->fs_info->delalloc_block_rsv;
space_info = block_rsv->space_info;
smp_mb();
- reserved = space_info->bytes_may_use;
- progress = space_info->reservation_progress;
-
- if (reserved == 0)
- return 0;
-
- smp_mb();
- if (root->fs_info->delalloc_bytes == 0) {
+ delalloc_bytes = root->fs_info->delalloc_bytes;
+ if (delalloc_bytes == 0) {
if (trans)
- return 0;
+ return;
btrfs_wait_ordered_extents(root, 0, 0);
- return 0;
+ return;
}
- max_reclaim = min(reserved, to_reclaim);
- nr_pages = max_t(unsigned long, nr_pages,
- max_reclaim >> PAGE_CACHE_SHIFT);
- while (loops < 1024) {
- /* have the flusher threads jump in and do some IO */
- smp_mb();
- nr_pages = min_t(unsigned long, nr_pages,
- root->fs_info->delalloc_bytes >> PAGE_CACHE_SHIFT);
+ while (delalloc_bytes && loops < 3) {
+ max_reclaim = min(delalloc_bytes, to_reclaim);
+ nr_pages = max_reclaim >> PAGE_CACHE_SHIFT;
writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages,
- WB_REASON_FS_FREE_SPACE);
+ WB_REASON_FS_FREE_SPACE);
spin_lock(&space_info->lock);
- if (reserved > space_info->bytes_may_use)
- reclaimed += reserved - space_info->bytes_may_use;
- reserved = space_info->bytes_may_use;
+ if (space_info->bytes_used + space_info->bytes_reserved +
+ space_info->bytes_pinned + space_info->bytes_readonly +
+ space_info->bytes_may_use + orig <=
+ space_info->total_bytes) {
+ spin_unlock(&space_info->lock);
+ break;
+ }
spin_unlock(&space_info->lock);
loops++;
-
- if (reserved == 0 || reclaimed >= max_reclaim)
- break;
-
- if (trans && trans->transaction->blocked)
- return -EAGAIN;
-
if (wait_ordered && !trans) {
btrfs_wait_ordered_extents(root, 0, 0);
} else {
- time_left = schedule_timeout_interruptible(1);
-
- /* We were interrupted, exit */
+ time_left = schedule_timeout_killable(1);
if (time_left)
break;
}
-
- /* we've kicked the IO a few times, if anything has been freed,
- * exit. There is no sense in looping here for a long time
- * when we really need to commit the transaction, or there are
- * just too many writers without enough free space
- */
-
- if (loops > 3) {
- smp_mb();
- if (progress != space_info->reservation_progress)
- break;
- }
-
+ smp_mb();
+ delalloc_bytes = root->fs_info->delalloc_bytes;
}
-
- return reclaimed >= to_reclaim;
}
/**
@@ -3817,6 +3789,58 @@ commit:
return btrfs_commit_transaction(trans, root);
}
+enum flush_state {
+ FLUSH_DELALLOC = 1,
+ FLUSH_DELALLOC_WAIT = 2,
+ FLUSH_DELAYED_ITEMS_NR = 3,
+ FLUSH_DELAYED_ITEMS = 4,
+ COMMIT_TRANS = 5,
+};
+
+static int flush_space(struct btrfs_root *root,
+ struct btrfs_space_info *space_info, u64 num_bytes,
+ u64 orig_bytes, int state)
+{
+ struct btrfs_trans_handle *trans;
+ int nr;
+ int ret = 0;
+
+ switch (state) {
+ case FLUSH_DELALLOC:
+ case FLUSH_DELALLOC_WAIT:
+ shrink_delalloc(root, num_bytes, orig_bytes,
+ state == FLUSH_DELALLOC_WAIT);
+ break;
+ case FLUSH_DELAYED_ITEMS_NR:
+ case FLUSH_DELAYED_ITEMS:
+ if (state == FLUSH_DELAYED_ITEMS_NR) {
+ u64 bytes = btrfs_calc_trans_metadata_size(root, 1);
+
+ nr = (int)div64_u64(num_bytes, bytes);
+ if (!nr)
+ nr = 1;
+ nr *= 2;
+ } else {
+ nr = -1;
+ }
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ break;
+ }
+ ret = btrfs_run_delayed_items_nr(trans, root, nr);
+ btrfs_end_transaction(trans, root);
+ break;
+ case COMMIT_TRANS:
+ ret = may_commit_transaction(root, space_info, orig_bytes, 0);
+ break;
+ default:
+ ret = -ENOSPC;
+ break;
+ }
+
+ return ret;
+}
/**
* reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
* @root - the root we're allocating for
@@ -3838,11 +3862,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root,
struct btrfs_space_info *space_info = block_rsv->space_info;
u64 used;
u64 num_bytes = orig_bytes;
- int retries = 0;
+ int flush_state = FLUSH_DELALLOC;
int ret = 0;
- bool committed = false;
bool flushing = false;
- bool wait_ordered = false;
+ bool committed = false;
again:
ret = 0;
@@ -3901,9 +3924,8 @@ again:
* amount plus the amount of bytes that we need for this
* reservation.
*/
- wait_ordered = true;
num_bytes = used - space_info->total_bytes +
- (orig_bytes * (retries + 1));
+ (orig_bytes * 2);
}
if (ret) {
@@ -3956,8 +3978,6 @@ again:
trace_btrfs_space_reservation(root->fs_info,
"space_info", space_info->flags, orig_bytes, 1);
ret = 0;
- } else {
- wait_ordered = true;
}
}
@@ -3976,36 +3996,13 @@ again:
if (!ret || !flush)
goto out;
- /*
- * We do synchronous shrinking since we don't actually unreserve
- * metadata until after the IO is completed.
- */
- ret = shrink_delalloc(root, num_bytes, wait_ordered);
- if (ret < 0)
- goto out;
-
- ret = 0;
-
- /*
- * So if we were overcommitted it's possible that somebody else flushed
- * out enough space and we simply didn't have enough space to reclaim,
- * so go back around and try again.
- */
- if (retries < 2) {
- wait_ordered = true;
- retries++;
+ ret = flush_space(root, space_info, num_bytes, orig_bytes,
+ flush_state);
+ flush_state++;
+ if (!ret)
goto again;
- }
-
- ret = -ENOSPC;
- if (committed)
- goto out;
-
- ret = may_commit_transaction(root, space_info, orig_bytes, 0);
- if (!ret) {
- committed = true;
+ else if (flush_state <= COMMIT_TRANS)
goto again;
- }
out:
if (flushing) {
@@ -4023,7 +4020,10 @@ static struct btrfs_block_rsv *get_block_rsv(
{
struct btrfs_block_rsv *block_rsv = NULL;
- if (root->ref_cows || root == root->fs_info->csum_root)
+ if (root->ref_cows)
+ block_rsv = trans->block_rsv;
+
+ if (root == root->fs_info->csum_root && trans->adding_csums)
block_rsv = trans->block_rsv;
if (!block_rsv)
@@ -4375,6 +4375,9 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
+ if (!trans->block_rsv)
+ return;
+
if (!trans->bytes_reserved)
return;
@@ -4533,7 +4536,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
int ret;
/* Need to be holding the i_mutex here if we aren't free space cache */
- if (btrfs_is_free_space_inode(root, inode))
+ if (btrfs_is_free_space_inode(inode))
flush = 0;
if (flush && btrfs_transaction_in_commit(root->fs_info))
@@ -5849,7 +5852,11 @@ loop:
ret = do_chunk_alloc(trans, root, num_bytes +
2 * 1024 * 1024, data,
CHUNK_ALLOC_LIMITED);
- if (ret < 0) {
+ /*
+ * Do not bail out on ENOSPC since we
+ * can do more things.
+ */
+ if (ret < 0 && ret != -ENOSPC) {
btrfs_abort_transaction(trans,
root, ret);
goto out;
@@ -5917,13 +5924,13 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
again:
list_for_each_entry(cache, &info->block_groups[index], list) {
spin_lock(&cache->lock);
- printk(KERN_INFO "block group %llu has %llu bytes, %llu used "
- "%llu pinned %llu reserved\n",
+ printk(KERN_INFO "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s\n",
(unsigned long long)cache->key.objectid,
(unsigned long long)cache->key.offset,
(unsigned long long)btrfs_block_group_used(&cache->item),
(unsigned long long)cache->pinned,
- (unsigned long long)cache->reserved);
+ (unsigned long long)cache->reserved,
+ cache->ro ? "[readonly]" : "");
btrfs_dump_free_space(cache, bytes);
spin_unlock(&cache->lock);
}
@@ -7711,8 +7718,21 @@ int btrfs_read_block_groups(struct btrfs_root *root)
INIT_LIST_HEAD(&cache->list);
INIT_LIST_HEAD(&cache->cluster_list);
- if (need_clear)
+ if (need_clear) {
+ /*
+ * When we mount with old space cache, we need to
+ * set BTRFS_DC_CLEAR and set dirty flag.
+ *
+ * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
+ * truncate the old free space cache inode and
+ * setup a new one.
+ * b) Setting 'dirty flag' makes sure that we flush
+ * the new space cache info onto disk.
+ */
cache->disk_cache_state = BTRFS_DC_CLEAR;
+ if (btrfs_test_opt(root, SPACE_CACHE))
+ cache->dirty = 1;
+ }
read_extent_buffer(leaf, &cache->item,
btrfs_item_ptr_offset(leaf, path->slots[0]),
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 01c21b6c6d43..3e7c9ed6505b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1918,7 +1918,7 @@ int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
return -EIO;
}
- printk_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu "
+ printk_ratelimited_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu "
"(dev %s sector %llu)\n", page->mapping->host->i_ino,
start, rcu_str_deref(dev->name), sector);
@@ -3077,8 +3077,15 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb,
}
}
+ /*
+ * We need to do this to prevent races in people who check if the eb is
+ * under IO since we can end up having no IO bits set for a short period
+ * of time.
+ */
+ spin_lock(&eb->refs_lock);
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) {
set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
+ spin_unlock(&eb->refs_lock);
btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
spin_lock(&fs_info->delalloc_lock);
if (fs_info->dirty_metadata_bytes >= eb->len)
@@ -3087,6 +3094,8 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb,
WARN_ON(1);
spin_unlock(&fs_info->delalloc_lock);
ret = 1;
+ } else {
+ spin_unlock(&eb->refs_lock);
}
btrfs_tree_unlock(eb);
@@ -3557,19 +3566,38 @@ int extent_readpages(struct extent_io_tree *tree,
struct bio *bio = NULL;
unsigned page_idx;
unsigned long bio_flags = 0;
+ struct page *pagepool[16];
+ struct page *page;
+ int i = 0;
+ int nr = 0;
for (page_idx = 0; page_idx < nr_pages; page_idx++) {
- struct page *page = list_entry(pages->prev, struct page, lru);
+ page = list_entry(pages->prev, struct page, lru);
prefetchw(&page->flags);
list_del(&page->lru);
- if (!add_to_page_cache_lru(page, mapping,
+ if (add_to_page_cache_lru(page, mapping,
page->index, GFP_NOFS)) {
- __extent_read_full_page(tree, page, get_extent,
- &bio, 0, &bio_flags);
+ page_cache_release(page);
+ continue;
}
- page_cache_release(page);
+
+ pagepool[nr++] = page;
+ if (nr < ARRAY_SIZE(pagepool))
+ continue;
+ for (i = 0; i < nr; i++) {
+ __extent_read_full_page(tree, pagepool[i], get_extent,
+ &bio, 0, &bio_flags);
+ page_cache_release(pagepool[i]);
+ }
+ nr = 0;
+ }
+ for (i = 0; i < nr; i++) {
+ __extent_read_full_page(tree, pagepool[i], get_extent,
+ &bio, 0, &bio_flags);
+ page_cache_release(pagepool[i]);
}
+
BUG_ON(!list_empty(pages));
if (bio)
return submit_one_bio(READ, bio, 0, bio_flags);
@@ -4123,11 +4151,10 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
* So bump the ref count first, then set the bit. If someone
* beat us to it, drop the ref we added.
*/
- if (!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) {
+ spin_lock(&eb->refs_lock);
+ if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
atomic_inc(&eb->refs);
- if (test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags))
- atomic_dec(&eb->refs);
- }
+ spin_unlock(&eb->refs_lock);
}
static void mark_extent_buffer_accessed(struct extent_buffer *eb)
@@ -4239,9 +4266,7 @@ again:
goto free_eb;
}
/* add one reference for the tree */
- spin_lock(&eb->refs_lock);
check_buffer_tree_ref(eb);
- spin_unlock(&eb->refs_lock);
spin_unlock(&tree->buffer_lock);
radix_tree_preload_end();
@@ -4300,7 +4325,7 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
}
/* Expects to have eb->eb_lock already held */
-static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask)
+static int release_extent_buffer(struct extent_buffer *eb, gfp_t mask)
{
WARN_ON(atomic_read(&eb->refs) == 0);
if (atomic_dec_and_test(&eb->refs)) {
@@ -4321,9 +4346,11 @@ static void release_extent_buffer(struct extent_buffer *eb, gfp_t mask)
btrfs_release_extent_buffer_page(eb, 0);
call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu);
- return;
+ return 1;
}
spin_unlock(&eb->refs_lock);
+
+ return 0;
}
void free_extent_buffer(struct extent_buffer *eb)
@@ -4962,7 +4989,6 @@ int try_release_extent_buffer(struct page *page, gfp_t mask)
spin_unlock(&eb->refs_lock);
return 0;
}
- release_extent_buffer(eb, mask);
- return 1;
+ return release_extent_buffer(eb, mask);
}
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 5d158d320233..b45b9de0c21d 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -183,7 +183,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
* read from the commit root and sidestep a nasty deadlock
* between reading the free space cache and updating the csum tree.
*/
- if (btrfs_is_free_space_inode(root, inode)) {
+ if (btrfs_is_free_space_inode(inode)) {
path->search_commit_root = 1;
path->skip_locking = 1;
}
@@ -690,6 +690,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
return -ENOMEM;
sector_sum = sums->sums;
+ trans->adding_csums = 1;
again:
next_offset = (u64)-1;
found_next = 0;
@@ -853,6 +854,7 @@ next_sector:
goto again;
}
out:
+ trans->adding_csums = 0;
btrfs_free_path(path);
return ret;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 248d20265249..9aa01ec2138d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1420,7 +1420,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
goto out;
}
- err = btrfs_update_time(file);
+ err = file_update_time(file);
if (err) {
mutex_unlock(&inode->i_mutex);
goto out;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index a70c54e2e1be..6b10acfc2f5c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -77,7 +77,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
return ERR_PTR(-ENOENT);
}
- inode->i_mapping->flags &= ~__GFP_FS;
+ mapping_set_gfp_mask(inode->i_mapping,
+ mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
return inode;
}
@@ -367,7 +368,7 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode,
static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation)
{
- u64 *val;
+ __le64 *val;
io_ctl_map_page(io_ctl, 1);
@@ -390,7 +391,7 @@ static void io_ctl_set_generation(struct io_ctl *io_ctl, u64 generation)
static int io_ctl_check_generation(struct io_ctl *io_ctl, u64 generation)
{
- u64 *gen;
+ __le64 *gen;
/*
* Skip the crc area. If we don't check crcs then we just have a 64bit
@@ -1967,7 +1968,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
info = rb_entry(n, struct btrfs_free_space, offset_index);
- if (info->bytes >= bytes)
+ if (info->bytes >= bytes && !block_group->ro)
count++;
printk(KERN_CRIT "entry offset %llu, bytes %llu, bitmap %s\n",
(unsigned long long)info->offset,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9f07bd121f66..144f4642b2a9 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -825,7 +825,7 @@ static noinline int cow_file_range(struct inode *inode,
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
int ret = 0;
- BUG_ON(btrfs_is_free_space_inode(root, inode));
+ BUG_ON(btrfs_is_free_space_inode(inode));
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
extent_clear_unlock_delalloc(inode,
@@ -1010,7 +1010,7 @@ static noinline void async_cow_submit(struct btrfs_work *work)
atomic_sub(nr_pages, &root->fs_info->async_delalloc_pages);
if (atomic_read(&root->fs_info->async_delalloc_pages) <
- 5 * 1042 * 1024 &&
+ 5 * 1024 * 1024 &&
waitqueue_active(&root->fs_info->async_submit_wait))
wake_up(&root->fs_info->async_submit_wait);
@@ -1035,7 +1035,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
struct btrfs_root *root = BTRFS_I(inode)->root;
unsigned long nr_pages;
u64 cur_end;
- int limit = 10 * 1024 * 1042;
+ int limit = 10 * 1024 * 1024;
clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
1, 0, NULL, GFP_NOFS);
@@ -1153,7 +1153,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
return -ENOMEM;
}
- nolock = btrfs_is_free_space_inode(root, inode);
+ nolock = btrfs_is_free_space_inode(inode);
if (nolock)
trans = btrfs_join_transaction_nolock(root);
@@ -1466,7 +1466,7 @@ static void btrfs_set_bit_hook(struct inode *inode,
if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 len = state->end + 1 - state->start;
- bool do_list = !btrfs_is_free_space_inode(root, inode);
+ bool do_list = !btrfs_is_free_space_inode(inode);
if (*bits & EXTENT_FIRST_DELALLOC) {
*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1501,7 +1501,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
struct btrfs_root *root = BTRFS_I(inode)->root;
u64 len = state->end + 1 - state->start;
- bool do_list = !btrfs_is_free_space_inode(root, inode);
+ bool do_list = !btrfs_is_free_space_inode(inode);
if (*bits & EXTENT_FIRST_DELALLOC) {
*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1612,7 +1612,7 @@ static int btrfs_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
- if (btrfs_is_free_space_inode(root, inode))
+ if (btrfs_is_free_space_inode(inode))
metadata = 2;
if (!(rw & REQ_WRITE)) {
@@ -1869,7 +1869,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
int ret;
bool nolock;
- nolock = btrfs_is_free_space_inode(root, inode);
+ nolock = btrfs_is_free_space_inode(inode);
if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
ret = -EIO;
@@ -2007,7 +2007,7 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
ordered_extent->work.func = finish_ordered_fn;
ordered_extent->work.flags = 0;
- if (btrfs_is_free_space_inode(root, inode))
+ if (btrfs_is_free_space_inode(inode))
workers = &root->fs_info->endio_freespace_worker;
else
workers = &root->fs_info->endio_write_workers;
@@ -2732,7 +2732,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
* The data relocation inode should also be directly updated
* without delay
*/
- if (!btrfs_is_free_space_inode(root, inode)
+ if (!btrfs_is_free_space_inode(inode)
&& root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_delayed_update_inode(trans, root, inode);
if (!ret)
@@ -2833,7 +2833,7 @@ err:
inode_inc_iversion(inode);
inode_inc_iversion(dir);
inode->i_ctime = dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- btrfs_update_inode(trans, root, dir);
+ ret = btrfs_update_inode(trans, root, dir);
out:
return ret;
}
@@ -3743,7 +3743,7 @@ void btrfs_evict_inode(struct inode *inode)
truncate_inode_pages(&inode->i_data, 0);
if (inode->i_nlink && (btrfs_root_refs(&root->root_item) != 0 ||
- btrfs_is_free_space_inode(root, inode)))
+ btrfs_is_free_space_inode(inode)))
goto no_delete;
if (is_bad_inode(inode)) {
@@ -3840,7 +3840,7 @@ void btrfs_evict_inode(struct inode *inode)
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root, nr);
no_delete:
- end_writeback(inode);
+ clear_inode(inode);
return;
}
@@ -4082,7 +4082,6 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
struct btrfs_iget_args *args = p;
inode->i_ino = args->ino;
BTRFS_I(inode)->root = args->root;
- btrfs_set_inode_space_info(args->root, inode);
return 0;
}
@@ -4457,7 +4456,7 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
return 0;
- if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(root, inode))
+ if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(inode))
nolock = true;
if (wbc->sync_mode == WB_SYNC_ALL) {
@@ -4515,46 +4514,23 @@ int btrfs_dirty_inode(struct inode *inode)
* This is a copy of file_update_time. We need this so we can return error on
* ENOSPC for updating the inode in the case of file write and mmap writes.
*/
-int btrfs_update_time(struct file *file)
+static int btrfs_update_time(struct inode *inode, struct timespec *now,
+ int flags)
{
- struct inode *inode = file->f_path.dentry->d_inode;
- struct timespec now;
- int ret;
- enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
-
- /* First try to exhaust all avenues to not sync */
- if (IS_NOCMTIME(inode))
- return 0;
-
- now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_mtime, &now))
- sync_it = S_MTIME;
-
- if (!timespec_equal(&inode->i_ctime, &now))
- sync_it |= S_CTIME;
-
- if (IS_I_VERSION(inode))
- sync_it |= S_VERSION;
-
- if (!sync_it)
- return 0;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
- /* Finally allowed to write? Takes lock. */
- if (mnt_want_write_file(file))
- return 0;
+ if (btrfs_root_readonly(root))
+ return -EROFS;
- /* Only change inode inside the lock region */
- if (sync_it & S_VERSION)
+ if (flags & S_VERSION)
inode_inc_iversion(inode);
- if (sync_it & S_CTIME)
- inode->i_ctime = now;
- if (sync_it & S_MTIME)
- inode->i_mtime = now;
- ret = btrfs_dirty_inode(inode);
- if (!ret)
- mark_inode_dirty_sync(inode);
- mnt_drop_write(file->f_path.mnt);
- return ret;
+ if (flags & S_CTIME)
+ inode->i_ctime = *now;
+ if (flags & S_MTIME)
+ inode->i_mtime = *now;
+ if (flags & S_ATIME)
+ inode->i_atime = *now;
+ return btrfs_dirty_inode(inode);
}
/*
@@ -4690,7 +4666,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
BTRFS_I(inode)->root = root;
BTRFS_I(inode)->generation = trans->transid;
inode->i_generation = BTRFS_I(inode)->generation;
- btrfs_set_inode_space_info(root, inode);
if (S_ISDIR(mode))
owner = 0;
@@ -4718,6 +4693,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_inode_item);
+ memset_extent_buffer(path->nodes[0], 0, (unsigned long)inode_item,
+ sizeof(*inode_item));
fill_inode_item(trans, path->nodes[0], inode_item, inode);
ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
@@ -6650,7 +6627,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
if (!ret) {
- ret = btrfs_update_time(vma->vm_file);
+ ret = file_update_time(vma->vm_file);
reserved = 1;
}
if (ret) {
@@ -6967,7 +6944,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
return NULL;
ei->root = NULL;
- ei->space_info = NULL;
ei->generation = 0;
ei->last_trans = 0;
ei->last_sub_trans = 0;
@@ -7074,7 +7050,7 @@ int btrfs_drop_inode(struct inode *inode)
struct btrfs_root *root = BTRFS_I(inode)->root;
if (btrfs_root_refs(&root->root_item) == 0 &&
- !btrfs_is_free_space_inode(root, inode))
+ !btrfs_is_free_space_inode(inode))
return 1;
else
return generic_drop_inode(inode);
@@ -7723,6 +7699,7 @@ static const struct inode_operations btrfs_file_inode_operations = {
.permission = btrfs_permission,
.fiemap = btrfs_fiemap,
.get_acl = btrfs_get_acl,
+ .update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
@@ -7733,6 +7710,7 @@ static const struct inode_operations btrfs_special_inode_operations = {
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.get_acl = btrfs_get_acl,
+ .update_time = btrfs_update_time,
};
static const struct inode_operations btrfs_symlink_inode_operations = {
.readlink = generic_readlink,
@@ -7746,6 +7724,7 @@ static const struct inode_operations btrfs_symlink_inode_operations = {
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
.get_acl = btrfs_get_acl,
+ .update_time = btrfs_update_time,
};
const struct dentry_operations btrfs_dentry_operations = {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 1dffd0adf975..e54b663fd3aa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -663,13 +663,9 @@ static noinline int btrfs_mksubvol(struct path *parent,
if (dentry->d_inode)
goto out_dput;
- error = mnt_want_write(parent->mnt);
- if (error)
- goto out_dput;
-
error = btrfs_may_create(dir, dentry);
if (error)
- goto out_drop_write;
+ goto out_dput;
down_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
@@ -687,8 +683,6 @@ static noinline int btrfs_mksubvol(struct path *parent,
fsnotify_mkdir(dir, dentry);
out_up_read:
up_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
-out_drop_write:
- mnt_drop_write(parent->mnt);
out_dput:
dput(dentry);
out_unlock:
@@ -843,7 +837,8 @@ static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
}
static int should_defrag_range(struct inode *inode, u64 start, int thresh,
- u64 *last_len, u64 *skip, u64 *defrag_end)
+ u64 *last_len, u64 *skip, u64 *defrag_end,
+ int compress)
{
struct extent_map *em;
int ret = 1;
@@ -874,7 +869,7 @@ static int should_defrag_range(struct inode *inode, u64 start, int thresh,
* we hit a real extent, if it is big or the next extent is not a
* real extent, don't bother defragging it
*/
- if ((*last_len == 0 || *last_len >= thresh) &&
+ if (!compress && (*last_len == 0 || *last_len >= thresh) &&
(em->len >= thresh || !next_mergeable))
ret = 0;
out:
@@ -1156,7 +1151,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
if (!should_defrag_range(inode, (u64)i << PAGE_CACHE_SHIFT,
extent_thresh, &last_len, &skip,
- &defrag_end)) {
+ &defrag_end, range->flags &
+ BTRFS_DEFRAG_RANGE_COMPRESS)) {
unsigned long next;
/*
* the should_defrag function tells us how much to skip
@@ -1394,24 +1390,24 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
u64 *transid, bool readonly,
struct btrfs_qgroup_inherit **inherit)
{
- struct btrfs_root *root = BTRFS_I(fdentry(file)->d_inode)->root;
struct file *src_file;
int namelen;
int ret = 0;
- if (root->fs_info->sb->s_flags & MS_RDONLY)
- return -EROFS;
+ ret = mnt_want_write_file(file);
+ if (ret)
+ goto out;
namelen = strlen(name);
if (strchr(name, '/')) {
ret = -EINVAL;
- goto out;
+ goto out_drop_write;
}
if (name[0] == '.' &&
(namelen == 1 || (name[1] == '.' && namelen == 2))) {
ret = -EEXIST;
- goto out;
+ goto out_drop_write;
}
if (subvol) {
@@ -1422,7 +1418,7 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
src_file = fget(fd);
if (!src_file) {
ret = -EINVAL;
- goto out;
+ goto out_drop_write;
}
src_inode = src_file->f_path.dentry->d_inode;
@@ -1431,13 +1427,15 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
"another FS\n");
ret = -EINVAL;
fput(src_file);
- goto out;
+ goto out_drop_write;
}
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
transid, readonly, inherit);
fput(src_file);
}
+out_drop_write:
+ mnt_drop_write_file(file);
out:
return ret;
}
@@ -1546,29 +1544,40 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
u64 flags;
int ret = 0;
- if (root->fs_info->sb->s_flags & MS_RDONLY)
- return -EROFS;
+ ret = mnt_want_write_file(file);
+ if (ret)
+ goto out;
- if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
- return -EINVAL;
+ if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
+ ret = -EINVAL;
+ goto out_drop_write;
+ }
- if (copy_from_user(&flags, arg, sizeof(flags)))
- return -EFAULT;
+ if (copy_from_user(&flags, arg, sizeof(flags))) {
+ ret = -EFAULT;
+ goto out_drop_write;
+ }
- if (flags & BTRFS_SUBVOL_CREATE_ASYNC)
- return -EINVAL;
+ if (flags & BTRFS_SUBVOL_CREATE_ASYNC) {
+ ret = -EINVAL;
+ goto out_drop_write;
+ }
- if (flags & ~BTRFS_SUBVOL_RDONLY)
- return -EOPNOTSUPP;
+ if (flags & ~BTRFS_SUBVOL_RDONLY) {
+ ret = -EOPNOTSUPP;
+ goto out_drop_write;
+ }
- if (!inode_owner_or_capable(inode))
- return -EACCES;
+ if (!inode_owner_or_capable(inode)) {
+ ret = -EACCES;
+ goto out_drop_write;
+ }
down_write(&root->fs_info->subvol_sem);
/* nothing to do */
if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
- goto out;
+ goto out_drop_sem;
root_flags = btrfs_root_flags(&root->root_item);
if (flags & BTRFS_SUBVOL_RDONLY)
@@ -1591,8 +1600,11 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
out_reset:
if (ret)
btrfs_set_root_flags(&root->root_item, root_flags);
-out:
+out_drop_sem:
up_write(&root->fs_info->subvol_sem);
+out_drop_write:
+ mnt_drop_write_file(file);
+out:
return ret;
}
@@ -3086,19 +3098,21 @@ static long btrfs_ioctl_scrub_progress(struct btrfs_root *root,
}
static long btrfs_ioctl_get_dev_stats(struct btrfs_root *root,
- void __user *arg, int reset_after_read)
+ void __user *arg)
{
struct btrfs_ioctl_get_dev_stats *sa;
int ret;
- if (reset_after_read && !capable(CAP_SYS_ADMIN))
- return -EPERM;
-
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa))
return PTR_ERR(sa);
- ret = btrfs_get_dev_stats(root, sa, reset_after_read);
+ if ((sa->flags & BTRFS_DEV_STATS_RESET) && !capable(CAP_SYS_ADMIN)) {
+ kfree(sa);
+ return -EPERM;
+ }
+
+ ret = btrfs_get_dev_stats(root, sa);
if (copy_to_user(arg, sa, sizeof(*sa)))
ret = -EFAULT;
@@ -3288,10 +3302,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (fs_info->sb->s_flags & MS_RDONLY)
- return -EROFS;
-
- ret = mnt_want_write(file->f_path.mnt);
+ ret = mnt_want_write_file(file);
if (ret)
return ret;
@@ -3361,7 +3372,7 @@ out_bargs:
out:
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
- mnt_drop_write(file->f_path.mnt);
+ mnt_drop_write_file(file);
return ret;
}
@@ -3675,9 +3686,7 @@ long btrfs_ioctl(struct file *file, unsigned int
case BTRFS_IOC_BALANCE_PROGRESS:
return btrfs_ioctl_balance_progress(root, argp);
case BTRFS_IOC_GET_DEV_STATS:
- return btrfs_ioctl_get_dev_stats(root, argp, 0);
- case BTRFS_IOC_GET_AND_RESET_DEV_STATS:
- return btrfs_ioctl_get_dev_stats(root, argp, 1);
+ return btrfs_ioctl_get_dev_stats(root, argp);
case BTRFS_IOC_QUOTA_CTL:
return btrfs_ioctl_quota_ctl(root, argp);
case BTRFS_IOC_QGROUP_ASSIGN:
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index cdda57f1c240..3f9701d571ea 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -316,9 +316,13 @@ enum btrfs_dev_stat_values {
BTRFS_DEV_STAT_VALUES_MAX
};
+/* Reset statistics after reading; needs SYS_ADMIN capability */
+#define BTRFS_DEV_STATS_RESET (1ULL << 0)
+
struct btrfs_ioctl_get_dev_stats {
__u64 devid; /* in */
__u64 nr_items; /* in/out */
+ __u64 flags; /* in/out */
/* out values: */
__u64 values[BTRFS_DEV_STAT_VALUES_MAX];
@@ -411,11 +415,8 @@ struct btrfs_ioctl_qgroup_create_args {
struct btrfs_ioctl_ino_path_args)
#define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
struct btrfs_ioctl_ino_path_args)
-#define BTRFS_IOC_GET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \
- struct btrfs_ioctl_get_dev_stats)
-#define BTRFS_IOC_GET_AND_RESET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 53, \
- struct btrfs_ioctl_get_dev_stats)
-
+#define BTRFS_IOC_DEVICES_READY _IOR(BTRFS_IOCTL_MAGIC, 39, \
+ struct btrfs_ioctl_vol_args)
#define BTRFS_IOC_QUOTA_CTL _IOWR(BTRFS_IOCTL_MAGIC, 40, \
struct btrfs_ioctl_quota_ctl_args)
#define BTRFS_IOC_QGROUP_ASSIGN _IOW(BTRFS_IOCTL_MAGIC, 41, \
@@ -424,4 +425,6 @@ struct btrfs_ioctl_qgroup_create_args {
struct btrfs_ioctl_qgroup_create_args)
#define BTRFS_IOC_QGROUP_LIMIT _IOR(BTRFS_IOCTL_MAGIC, 43, \
struct btrfs_ioctl_qgroup_limit_args)
+#define BTRFS_IOC_GET_DEV_STATS _IOWR(BTRFS_IOCTL_MAGIC, 52, \
+ struct btrfs_ioctl_get_dev_stats)
#endif
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 272f911203ff..a44eff074805 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -78,13 +78,15 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw)
write_lock(&eb->lock);
WARN_ON(atomic_read(&eb->spinning_writers));
atomic_inc(&eb->spinning_writers);
- if (atomic_dec_and_test(&eb->blocking_writers))
+ if (atomic_dec_and_test(&eb->blocking_writers) &&
+ waitqueue_active(&eb->write_lock_wq))
wake_up(&eb->write_lock_wq);
} else if (rw == BTRFS_READ_LOCK_BLOCKING) {
BUG_ON(atomic_read(&eb->blocking_readers) == 0);
read_lock(&eb->lock);
atomic_inc(&eb->spinning_readers);
- if (atomic_dec_and_test(&eb->blocking_readers))
+ if (atomic_dec_and_test(&eb->blocking_readers) &&
+ waitqueue_active(&eb->read_lock_wq))
wake_up(&eb->read_lock_wq);
}
return;
@@ -199,7 +201,8 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
}
btrfs_assert_tree_read_locked(eb);
WARN_ON(atomic_read(&eb->blocking_readers) == 0);
- if (atomic_dec_and_test(&eb->blocking_readers))
+ if (atomic_dec_and_test(&eb->blocking_readers) &&
+ waitqueue_active(&eb->read_lock_wq))
wake_up(&eb->read_lock_wq);
atomic_dec(&eb->read_locks);
}
@@ -247,8 +250,9 @@ void btrfs_tree_unlock(struct extent_buffer *eb)
if (blockers) {
WARN_ON(atomic_read(&eb->spinning_writers));
atomic_dec(&eb->blocking_writers);
- smp_wmb();
- wake_up(&eb->write_lock_wq);
+ smp_mb();
+ if (waitqueue_active(&eb->write_lock_wq))
+ wake_up(&eb->write_lock_wq);
} else {
WARN_ON(atomic_read(&eb->spinning_writers) != 1);
atomic_dec(&eb->spinning_writers);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 646ee21bb035..c5dbd9149679 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1239,10 +1239,11 @@ static int __must_check __add_reloc_root(struct btrfs_root *root)
node->bytenr, &node->rb_node);
spin_unlock(&rc->reloc_root_tree.lock);
if (rb_node) {
- kfree(node);
btrfs_panic(root->fs_info, -EEXIST, "Duplicate root found "
"for start=%llu while inserting into relocation "
"tree\n");
+ kfree(node);
+ return -EEXIST;
}
list_add_tail(&root->root_list, &rc->reloc_roots);
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index c6ffa5812419..b976597b0721 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -17,15 +17,27 @@
*/
#include <linux/highmem.h>
+#include <asm/unaligned.h>
-/* this is some deeply nasty code. ctree.h has a different
- * definition for this BTRFS_SETGET_FUNCS macro, behind a #ifndef
+#include "ctree.h"
+
+static inline u8 get_unaligned_le8(const void *p)
+{
+ return *(u8 *)p;
+}
+
+static inline void put_unaligned_le8(u8 val, void *p)
+{
+ *(u8 *)p = val;
+}
+
+/*
+ * this is some deeply nasty code.
*
* The end result is that anyone who #includes ctree.h gets a
- * declaration for the btrfs_set_foo functions and btrfs_foo functions
- *
- * This file declares the macros and then #includes ctree.h, which results
- * in cpp creating the function here based on the template below.
+ * declaration for the btrfs_set_foo functions and btrfs_foo functions,
+ * which are wappers of btrfs_set_token_#bits functions and
+ * btrfs_get_token_#bits functions, which are defined in this file.
*
* These setget functions do all the extent_buffer related mapping
* required to efficiently read and write specific fields in the extent
@@ -33,103 +45,93 @@
* an unsigned long offset into the extent buffer which has been
* cast to a specific type. This gives us all the gcc type checking.
*
- * The extent buffer api is used to do all the kmapping and page
- * spanning work required to get extent buffers in highmem and have
- * a metadata blocksize different from the page size.
- *
- * The macro starts with a simple function prototype declaration so that
- * sparse won't complain about it being static.
+ * The extent buffer api is used to do the page spanning work required to
+ * have a metadata blocksize different from the page size.
*/
-#define BTRFS_SETGET_FUNCS(name, type, member, bits) \
-u##bits btrfs_##name(struct extent_buffer *eb, type *s); \
-void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val); \
-void btrfs_set_token_##name(struct extent_buffer *eb, type *s, u##bits val, struct btrfs_map_token *token); \
-u##bits btrfs_token_##name(struct extent_buffer *eb, \
- type *s, struct btrfs_map_token *token) \
+#define DEFINE_BTRFS_SETGET_BITS(bits) \
+u##bits btrfs_get_token_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off, \
+ struct btrfs_map_token *token) \
{ \
- unsigned long part_offset = (unsigned long)s; \
- unsigned long offset = part_offset + offsetof(type, member); \
- type *p; \
- int err; \
- char *kaddr; \
- unsigned long map_start; \
- unsigned long map_len; \
- unsigned long mem_len = sizeof(((type *)0)->member); \
- u##bits res; \
- if (token && token->kaddr && token->offset <= offset && \
- token->eb == eb && \
- (token->offset + PAGE_CACHE_SIZE >= offset + mem_len)) { \
- kaddr = token->kaddr; \
- p = (type *)(kaddr + part_offset - token->offset); \
- res = le##bits##_to_cpu(p->member); \
- return res; \
- } \
- err = map_private_extent_buffer(eb, offset, \
- mem_len, \
- &kaddr, &map_start, &map_len); \
- if (err) { \
- __le##bits leres; \
- read_eb_member(eb, s, type, member, &leres); \
- return le##bits##_to_cpu(leres); \
- } \
- p = (type *)(kaddr + part_offset - map_start); \
- res = le##bits##_to_cpu(p->member); \
- if (token) { \
- token->kaddr = kaddr; \
- token->offset = map_start; \
- token->eb = eb; \
- } \
- return res; \
+ unsigned long part_offset = (unsigned long)ptr; \
+ unsigned long offset = part_offset + off; \
+ void *p; \
+ int err; \
+ char *kaddr; \
+ unsigned long map_start; \
+ unsigned long map_len; \
+ int size = sizeof(u##bits); \
+ u##bits res; \
+ \
+ if (token && token->kaddr && token->offset <= offset && \
+ token->eb == eb && \
+ (token->offset + PAGE_CACHE_SIZE >= offset + size)) { \
+ kaddr = token->kaddr; \
+ p = kaddr + part_offset - token->offset; \
+ res = get_unaligned_le##bits(p + off); \
+ return res; \
+ } \
+ err = map_private_extent_buffer(eb, offset, size, \
+ &kaddr, &map_start, &map_len); \
+ if (err) { \
+ __le##bits leres; \
+ \
+ read_extent_buffer(eb, &leres, offset, size); \
+ return le##bits##_to_cpu(leres); \
+ } \
+ p = kaddr + part_offset - map_start; \
+ res = get_unaligned_le##bits(p + off); \
+ if (token) { \
+ token->kaddr = kaddr; \
+ token->offset = map_start; \
+ token->eb = eb; \
+ } \
+ return res; \
} \
-void btrfs_set_token_##name(struct extent_buffer *eb, \
- type *s, u##bits val, struct btrfs_map_token *token) \
+void btrfs_set_token_##bits(struct extent_buffer *eb, \
+ void *ptr, unsigned long off, u##bits val, \
+ struct btrfs_map_token *token) \
{ \
- unsigned long part_offset = (unsigned long)s; \
- unsigned long offset = part_offset + offsetof(type, member); \
- type *p; \
- int err; \
- char *kaddr; \
- unsigned long map_start; \
- unsigned long map_len; \
- unsigned long mem_len = sizeof(((type *)0)->member); \
- if (token && token->kaddr && token->offset <= offset && \
- token->eb == eb && \
- (token->offset + PAGE_CACHE_SIZE >= offset + mem_len)) { \
- kaddr = token->kaddr; \
- p = (type *)(kaddr + part_offset - token->offset); \
- p->member = cpu_to_le##bits(val); \
- return; \
- } \
- err = map_private_extent_buffer(eb, offset, \
- mem_len, \
- &kaddr, &map_start, &map_len); \
- if (err) { \
- __le##bits val2; \
- val2 = cpu_to_le##bits(val); \
- write_eb_member(eb, s, type, member, &val2); \
- return; \
- } \
- p = (type *)(kaddr + part_offset - map_start); \
- p->member = cpu_to_le##bits(val); \
- if (token) { \
- token->kaddr = kaddr; \
- token->offset = map_start; \
- token->eb = eb; \
- } \
-} \
-void btrfs_set_##name(struct extent_buffer *eb, \
- type *s, u##bits val) \
-{ \
- btrfs_set_token_##name(eb, s, val, NULL); \
-} \
-u##bits btrfs_##name(struct extent_buffer *eb, \
- type *s) \
-{ \
- return btrfs_token_##name(eb, s, NULL); \
-} \
+ unsigned long part_offset = (unsigned long)ptr; \
+ unsigned long offset = part_offset + off; \
+ void *p; \
+ int err; \
+ char *kaddr; \
+ unsigned long map_start; \
+ unsigned long map_len; \
+ int size = sizeof(u##bits); \
+ \
+ if (token && token->kaddr && token->offset <= offset && \
+ token->eb == eb && \
+ (token->offset + PAGE_CACHE_SIZE >= offset + size)) { \
+ kaddr = token->kaddr; \
+ p = kaddr + part_offset - token->offset; \
+ put_unaligned_le##bits(val, p + off); \
+ return; \
+ } \
+ err = map_private_extent_buffer(eb, offset, size, \
+ &kaddr, &map_start, &map_len); \
+ if (err) { \
+ __le##bits val2; \
+ \
+ val2 = cpu_to_le##bits(val); \
+ write_extent_buffer(eb, &val2, offset, size); \
+ return; \
+ } \
+ p = kaddr + part_offset - map_start; \
+ put_unaligned_le##bits(val, p + off); \
+ if (token) { \
+ token->kaddr = kaddr; \
+ token->offset = map_start; \
+ token->eb = eb; \
+ } \
+}
-#include "ctree.h"
+DEFINE_BTRFS_SETGET_BITS(8)
+DEFINE_BTRFS_SETGET_BITS(16)
+DEFINE_BTRFS_SETGET_BITS(32)
+DEFINE_BTRFS_SETGET_BITS(64)
void btrfs_node_key(struct extent_buffer *eb,
struct btrfs_disk_key *disk_key, int nr)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e23991574fdf..26da344231ac 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -396,15 +396,22 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
strcmp(args[0].from, "zlib") == 0) {
compress_type = "zlib";
info->compress_type = BTRFS_COMPRESS_ZLIB;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
} else if (strcmp(args[0].from, "lzo") == 0) {
compress_type = "lzo";
info->compress_type = BTRFS_COMPRESS_LZO;
+ btrfs_set_opt(info->mount_opt, COMPRESS);
+ } else if (strncmp(args[0].from, "no", 2) == 0) {
+ compress_type = "no";
+ info->compress_type = BTRFS_COMPRESS_NONE;
+ btrfs_clear_opt(info->mount_opt, COMPRESS);
+ btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
+ compress_force = false;
} else {
ret = -EINVAL;
goto out;
}
- btrfs_set_opt(info->mount_opt, COMPRESS);
if (compress_force) {
btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
pr_info("btrfs: force %s compression\n",
@@ -1455,6 +1462,13 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
ret = btrfs_scan_one_device(vol->name, FMODE_READ,
&btrfs_fs_type, &fs_devices);
break;
+ case BTRFS_IOC_DEVICES_READY:
+ ret = btrfs_scan_one_device(vol->name, FMODE_READ,
+ &btrfs_fs_type, &fs_devices);
+ if (ret)
+ break;
+ ret = !(fs_devices->num_devices == fs_devices->total_devices);
+ break;
}
kfree(vol);
@@ -1477,16 +1491,6 @@ static int btrfs_unfreeze(struct super_block *sb)
return 0;
}
-static void btrfs_fs_dirty_inode(struct inode *inode, int flags)
-{
- int ret;
-
- ret = btrfs_dirty_inode(inode);
- if (ret)
- printk_ratelimited(KERN_ERR "btrfs: fail to dirty inode %Lu "
- "error %d\n", btrfs_ino(inode), ret);
-}
-
static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
@@ -1526,7 +1530,6 @@ static const struct super_operations btrfs_super_ops = {
.show_options = btrfs_show_options,
.show_devname = btrfs_show_devname,
.write_inode = btrfs_write_inode,
- .dirty_inode = btrfs_fs_dirty_inode,
.alloc_inode = btrfs_alloc_inode,
.destroy_inode = btrfs_destroy_inode,
.statfs = btrfs_statfs,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 127283913a42..cc20e95ea289 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -99,8 +99,8 @@ loop:
kmem_cache_free(btrfs_transaction_cachep, cur_trans);
cur_trans = fs_info->running_transaction;
goto loop;
- } else if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
- spin_unlock(&root->fs_info->trans_lock);
+ } else if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
+ spin_unlock(&fs_info->trans_lock);
kmem_cache_free(btrfs_transaction_cachep, cur_trans);
return -EROFS;
}
@@ -357,6 +357,7 @@ again:
h->root = root;
h->delayed_ref_updates = 0;
h->use_count = 1;
+ h->adding_csums = 0;
h->block_rsv = NULL;
h->orig_rsv = NULL;
h->aborted = 0;
@@ -482,7 +483,6 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_transaction *cur_trans = trans->transaction;
- struct btrfs_block_rsv *rsv = trans->block_rsv;
int updates;
int err;
@@ -490,12 +490,6 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
return 1;
- /*
- * We need to do this in case we're deleting csums so the global block
- * rsv get's used instead of the csum block rsv.
- */
- trans->block_rsv = NULL;
-
updates = trans->delayed_ref_updates;
trans->delayed_ref_updates = 0;
if (updates) {
@@ -504,8 +498,6 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
return err;
}
- trans->block_rsv = rsv;
-
return should_end_transaction(trans, root);
}
@@ -552,6 +544,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
}
count++;
}
+ btrfs_trans_release_metadata(trans, root);
+ trans->block_rsv = NULL;
if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
should_end_transaction(trans, root)) {
@@ -1310,9 +1304,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
btrfs_run_ordered_operations(root, 0);
- btrfs_trans_release_metadata(trans, root);
- trans->block_rsv = NULL;
-
if (cur_trans->aborted)
goto cleanup_transaction;
@@ -1323,6 +1314,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
if (ret)
goto cleanup_transaction;
+ btrfs_trans_release_metadata(trans, root);
+ trans->block_rsv = NULL;
+
cur_trans = trans->transaction;
/*
@@ -1371,7 +1365,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
spin_unlock(&root->fs_info->trans_lock);
}
- if (now < cur_trans->start_time || now - cur_trans->start_time < 1)
+ if (!btrfs_test_opt(root, SSD) &&
+ (now < cur_trans->start_time || now - cur_trans->start_time < 1))
should_grow = 1;
do {
@@ -1581,6 +1576,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
return ret;
cleanup_transaction:
+ btrfs_trans_release_metadata(trans, root);
+ trans->block_rsv = NULL;
btrfs_printk(root->fs_info, "Skipping commit of aborted transaction.\n");
// WARN_ON(1);
if (current->journal_info == trans)
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index cca315dcdfcd..e8b8416c688b 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -59,6 +59,7 @@ struct btrfs_trans_handle {
struct btrfs_block_rsv *block_rsv;
struct btrfs_block_rsv *orig_rsv;
int aborted;
+ int adding_csums;
/*
* this root is only needed to validate that the root passed to
* start_transaction is the same as the one passed to end_transaction.
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 8abeae4224f9..c86670f4f285 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -637,7 +637,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
}
inode_set_bytes(inode, saved_nbytes);
- btrfs_update_inode(trans, root, inode);
+ ret = btrfs_update_inode(trans, root, inode);
out:
if (inode)
iput(inode);
@@ -1133,7 +1133,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
btrfs_release_path(path);
if (ret == 0) {
btrfs_inc_nlink(inode);
- btrfs_update_inode(trans, root, inode);
+ ret = btrfs_update_inode(trans, root, inode);
} else if (ret == -EEXIST) {
ret = 0;
} else {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ecaad40e7ef4..b8708f994e67 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -429,6 +429,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
mutex_init(&fs_devices->device_list_mutex);
fs_devices->latest_devid = orig->latest_devid;
fs_devices->latest_trans = orig->latest_trans;
+ fs_devices->total_devices = orig->total_devices;
memcpy(fs_devices->fsid, orig->fsid, sizeof(fs_devices->fsid));
/* We have held the volume lock, it is safe to get the devices. */
@@ -739,6 +740,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
int ret;
u64 devid;
u64 transid;
+ u64 total_devices;
flags |= FMODE_EXCL;
bdev = blkdev_get_by_path(path, flags, holder);
@@ -760,6 +762,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
transid = btrfs_super_generation(disk_super);
+ total_devices = btrfs_super_num_devices(disk_super);
if (disk_super->label[0])
printk(KERN_INFO "device label %s ", disk_super->label);
else
@@ -767,7 +770,8 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
printk(KERN_CONT "devid %llu transid %llu %s\n",
(unsigned long long)devid, (unsigned long long)transid, path);
ret = device_list_add(path, disk_super, devid, fs_devices_ret);
-
+ if (!ret && fs_devices_ret)
+ (*fs_devices_ret)->total_devices = total_devices;
brelse(bh);
error_close:
mutex_unlock(&uuid_mutex);
@@ -1433,6 +1437,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
list_del_rcu(&device->dev_list);
device->fs_devices->num_devices--;
+ device->fs_devices->total_devices--;
if (device->missing)
root->fs_info->fs_devices->missing_devices--;
@@ -1550,6 +1555,7 @@ static int btrfs_prepare_sprout(struct btrfs_root *root)
fs_devices->seeding = 0;
fs_devices->num_devices = 0;
fs_devices->open_devices = 0;
+ fs_devices->total_devices = 0;
fs_devices->seed = seed_devices;
generate_random_uuid(fs_devices->fsid);
@@ -1749,6 +1755,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
root->fs_info->fs_devices->num_devices++;
root->fs_info->fs_devices->open_devices++;
root->fs_info->fs_devices->rw_devices++;
+ root->fs_info->fs_devices->total_devices++;
if (device->can_discard)
root->fs_info->fs_devices->num_can_discard++;
root->fs_info->fs_devices->total_rw_bytes += device->total_bytes;
@@ -4736,9 +4743,6 @@ int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info)
key.offset = device->devid;
ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
if (ret) {
- printk_in_rcu(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n",
- rcu_str_deref(device->name),
- (unsigned long long)device->devid);
__btrfs_reset_dev_stats(device);
device->dev_stats_valid = 1;
btrfs_release_path(path);
@@ -4880,6 +4884,14 @@ void btrfs_dev_stat_print_on_error(struct btrfs_device *dev)
static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
{
+ int i;
+
+ for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++)
+ if (btrfs_dev_stat_read(dev, i) != 0)
+ break;
+ if (i == BTRFS_DEV_STAT_VALUES_MAX)
+ return; /* all values == 0, suppress message */
+
printk_in_rcu(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
@@ -4890,8 +4902,7 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
}
int btrfs_get_dev_stats(struct btrfs_root *root,
- struct btrfs_ioctl_get_dev_stats *stats,
- int reset_after_read)
+ struct btrfs_ioctl_get_dev_stats *stats)
{
struct btrfs_device *dev;
struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
@@ -4909,7 +4920,7 @@ int btrfs_get_dev_stats(struct btrfs_root *root,
printk(KERN_WARNING
"btrfs: get dev_stats failed, not yet valid\n");
return -ENODEV;
- } else if (reset_after_read) {
+ } else if (stats->flags & BTRFS_DEV_STATS_RESET) {
for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
if (stats->nr_items > i)
stats->values[i] =
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 95f6637614db..5479325987b3 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -126,6 +126,7 @@ struct btrfs_fs_devices {
u64 missing_devices;
u64 total_rw_bytes;
u64 num_can_discard;
+ u64 total_devices;
struct block_device *latest_bdev;
/* all of the devices in the FS, protected by a mutex
@@ -293,8 +294,7 @@ struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root,
void btrfs_dev_stat_print_on_error(struct btrfs_device *device);
void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index);
int btrfs_get_dev_stats(struct btrfs_root *root,
- struct btrfs_ioctl_get_dev_stats *stats,
- int reset_after_read);
+ struct btrfs_ioctl_get_dev_stats *stats);
int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info);
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-13 18:59:49 +0000