summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ocfs2')
-rw-r--r--fs/ocfs2/aops.c7
-rw-r--r--fs/ocfs2/cluster/tcp.c5
-rw-r--r--fs/ocfs2/dir.c46
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c12
-rw-r--r--fs/ocfs2/export.c12
-rw-r--r--fs/ocfs2/inode.c2
-rw-r--r--fs/ocfs2/ioctl.c1
-rw-r--r--fs/ocfs2/journal.c17
-rw-r--r--fs/ocfs2/journal.h2
-rw-r--r--fs/ocfs2/localalloc.c15
-rw-r--r--fs/ocfs2/move_extents.c2
-rw-r--r--fs/ocfs2/ocfs2_fs.h3
-rw-r--r--fs/ocfs2/ocfs2_trace.h62
-rw-r--r--fs/ocfs2/refcounttree.c2
-rw-r--r--fs/ocfs2/resize.c8
-rw-r--r--fs/ocfs2/suballoc.c111
-rw-r--r--fs/ocfs2/suballoc.h6
17 files changed, 223 insertions, 90 deletions
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index b82185075d..6be175a1ab 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2283,8 +2283,6 @@ unlock:
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
out:
- if (ret < 0)
- ret = -EIO;
return ret;
}
@@ -2368,6 +2366,11 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
}
list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+ ret = ocfs2_assure_trans_credits(handle, credits);
+ if (ret < 0) {
+ mlog_errno(ret);
+ break;
+ }
ret = ocfs2_mark_extent_written(inode, &et, handle,
ue->ue_cpos, 1,
ue->ue_phys,
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 960080753d..2b8fa3e782 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1784,6 +1784,9 @@ static int o2net_accept_one(struct socket *sock, int *more)
struct o2nm_node *node = NULL;
struct o2nm_node *local_node = NULL;
struct o2net_sock_container *sc = NULL;
+ struct proto_accept_arg arg = {
+ .flags = O_NONBLOCK,
+ };
struct o2net_node *nn;
unsigned int nofs_flag;
@@ -1802,7 +1805,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
new_sock->type = sock->type;
new_sock->ops = sock->ops;
- ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
+ ret = sock->ops->accept(sock, new_sock, &arg);
if (ret < 0)
goto out;
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index d620d4c53c..f0beb173db 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -294,13 +294,16 @@ out:
* bh passed here can be an inode block or a dir data block, depending
* on the inode inline data flag.
*/
-static int ocfs2_check_dir_entry(struct inode * dir,
- struct ocfs2_dir_entry * de,
- struct buffer_head * bh,
+static int ocfs2_check_dir_entry(struct inode *dir,
+ struct ocfs2_dir_entry *de,
+ struct buffer_head *bh,
+ char *buf,
+ unsigned int size,
unsigned long offset)
{
const char *error_msg = NULL;
const int rlen = le16_to_cpu(de->rec_len);
+ const unsigned long next_offset = ((char *) de - buf) + rlen;
if (unlikely(rlen < OCFS2_DIR_REC_LEN(1)))
error_msg = "rec_len is smaller than minimal";
@@ -308,9 +311,11 @@ static int ocfs2_check_dir_entry(struct inode * dir,
error_msg = "rec_len % 4 != 0";
else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len)))
error_msg = "rec_len is too small for name_len";
- else if (unlikely(
- ((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize))
- error_msg = "directory entry across blocks";
+ else if (unlikely(next_offset > size))
+ error_msg = "directory entry overrun";
+ else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) &&
+ next_offset != size)
+ error_msg = "directory entry too close to end";
if (unlikely(error_msg != NULL))
mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
@@ -352,16 +357,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh,
de_buf = first_de;
dlimit = de_buf + bytes;
- while (de_buf < dlimit) {
+ while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) {
/* this code is executed quadratically often */
/* do minimal checking `by hand' */
de = (struct ocfs2_dir_entry *) de_buf;
- if (de_buf + namelen <= dlimit &&
+ if (de->name + namelen <= dlimit &&
ocfs2_match(namelen, name, de)) {
/* found a match - just to be sure, do a full check */
- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, first_de,
+ bytes, offset)) {
ret = -1;
goto bail;
}
@@ -1138,7 +1144,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
pde = NULL;
de = (struct ocfs2_dir_entry *) first_de;
while (i < bytes) {
- if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) {
status = -EIO;
mlog_errno(status);
goto bail;
@@ -1635,7 +1641,8 @@ int __ocfs2_add_entry(handle_t *handle,
/* These checks should've already been passed by the
* prepare function, but I guess we can leave them
* here anyway. */
- if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start,
+ size, offset)) {
retval = -ENOENT;
goto bail;
}
@@ -1774,7 +1781,8 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
}
de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
- if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) {
+ if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data,
+ i_size_read(inode), ctx->pos)) {
/* On error, skip the f_pos to the end. */
ctx->pos = i_size_read(inode);
break;
@@ -1867,7 +1875,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
while (ctx->pos < i_size_read(inode)
&& offset < sb->s_blocksize) {
de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
- if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data,
+ sb->s_blocksize, offset)) {
/* On error, skip the f_pos to the
next block. */
ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
@@ -3339,7 +3348,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
struct super_block *sb = dir->i_sb;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
struct ocfs2_dir_entry *de, *last_de = NULL;
- char *de_buf, *limit;
+ char *first_de, *de_buf, *limit;
unsigned long offset = 0;
unsigned int rec_len, new_rec_len, free_space;
@@ -3352,14 +3361,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
else
free_space = dir->i_sb->s_blocksize - i_size_read(dir);
- de_buf = di->id2.i_data.id_data;
+ first_de = di->id2.i_data.id_data;
+ de_buf = first_de;
limit = de_buf + i_size_read(dir);
rec_len = OCFS2_DIR_REC_LEN(namelen);
while (de_buf < limit) {
de = (struct ocfs2_dir_entry *)de_buf;
- if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de,
+ i_size_read(dir), offset)) {
ret = -ENOENT;
goto out;
}
@@ -3441,7 +3452,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
/* move to next block */
de = (struct ocfs2_dir_entry *) bh->b_data;
}
- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+ if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize,
+ offset)) {
status = -ENOENT;
goto bail;
}
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 5c04dde999..2018501b22 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1274,7 +1274,7 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
{
struct dlm_query_nodeinfo *qn;
struct dlm_ctxt *dlm = NULL;
- int locked = 0, status = -EINVAL;
+ int status = -EINVAL;
qn = (struct dlm_query_nodeinfo *) msg->buf;
@@ -1290,12 +1290,11 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
}
spin_lock(&dlm->spinlock);
- locked = 1;
if (dlm->joining_node != qn->qn_nodenum) {
mlog(ML_ERROR, "Node %d queried nodes on domain %s but "
"joining node is %d\n", qn->qn_nodenum, qn->qn_domain,
dlm->joining_node);
- goto bail;
+ goto unlock;
}
/* Support for node query was added in 1.1 */
@@ -1305,14 +1304,14 @@ static int dlm_query_nodeinfo_handler(struct o2net_msg *msg, u32 len,
"but active dlm protocol is %d.%d\n", qn->qn_nodenum,
qn->qn_domain, dlm->dlm_locking_proto.pv_major,
dlm->dlm_locking_proto.pv_minor);
- goto bail;
+ goto unlock;
}
status = dlm_match_nodes(dlm, qn);
+unlock:
+ spin_unlock(&dlm->spinlock);
bail:
- if (locked)
- spin_unlock(&dlm->spinlock);
spin_unlock(&dlm_domain_lock);
return status;
@@ -1528,7 +1527,6 @@ static void dlm_send_join_asserts(struct dlm_ctxt *dlm,
{
int status, node, live;
- status = 0;
node = -1;
while ((node = find_next_bit(node_map, O2NM_MAX_NODES,
node + 1)) < O2NM_MAX_NODES) {
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index b8b6a191b5..96b684763b 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -255,9 +255,9 @@ static struct dentry *ocfs2_fh_to_dentry(struct super_block *sb,
if (fh_len < 3 || fh_type > 2)
return NULL;
- handle.ih_blkno = (u64)le32_to_cpu(fid->raw[0]) << 32;
- handle.ih_blkno |= (u64)le32_to_cpu(fid->raw[1]);
- handle.ih_generation = le32_to_cpu(fid->raw[2]);
+ handle.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[0]) << 32;
+ handle.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[1]);
+ handle.ih_generation = le32_to_cpu((__force __le32)fid->raw[2]);
return ocfs2_get_dentry(sb, &handle);
}
@@ -269,9 +269,9 @@ static struct dentry *ocfs2_fh_to_parent(struct super_block *sb,
if (fh_type != 2 || fh_len < 6)
return NULL;
- parent.ih_blkno = (u64)le32_to_cpu(fid->raw[3]) << 32;
- parent.ih_blkno |= (u64)le32_to_cpu(fid->raw[4]);
- parent.ih_generation = le32_to_cpu(fid->raw[5]);
+ parent.ih_blkno = (u64)le32_to_cpu((__force __le32)fid->raw[3]) << 32;
+ parent.ih_blkno |= (u64)le32_to_cpu((__force __le32)fid->raw[4]);
+ parent.ih_generation = le32_to_cpu((__force __le32)fid->raw[5]);
return ocfs2_get_dentry(sb, &parent);
}
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 999111bfc2..2cc5c99fe9 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1621,6 +1621,7 @@ static struct super_block *ocfs2_inode_cache_get_super(struct ocfs2_caching_info
}
static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
+__acquires(&oi->ip_lock)
{
struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
@@ -1628,6 +1629,7 @@ static void ocfs2_inode_cache_lock(struct ocfs2_caching_info *ci)
}
static void ocfs2_inode_cache_unlock(struct ocfs2_caching_info *ci)
+__releases(&oi->ip_lock)
{
struct ocfs2_inode_info *oi = cache_info_to_inode(ci);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index b1550ba73f..71beef7f8a 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -125,6 +125,7 @@ int ocfs2_fileattr_set(struct mnt_idmap *idmap,
ocfs2_inode->ip_attr = flags;
ocfs2_set_inode_flags(inode);
+ inode_set_ctime_current(inode);
status = ocfs2_mark_inode_dirty(handle, inode, bh);
if (status < 0)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 86807086b2..530fba34f6 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -446,6 +446,23 @@ bail:
}
/*
+ * Make sure handle has at least 'nblocks' credits available. If it does not
+ * have that many credits available, we will try to extend the handle to have
+ * enough credits. If that fails, we will restart transaction to have enough
+ * credits. Similar notes regarding data consistency and locking implications
+ * as for ocfs2_extend_trans() apply here.
+ */
+int ocfs2_assure_trans_credits(handle_t *handle, int nblocks)
+{
+ int old_nblks = jbd2_handle_buffer_credits(handle);
+
+ trace_ocfs2_assure_trans_credits(old_nblks);
+ if (old_nblks >= nblocks)
+ return 0;
+ return ocfs2_extend_trans(handle, nblocks - old_nblks);
+}
+
+/*
* If we have fewer than thresh credits, extend by OCFS2_MAX_TRANS_DATA.
* If that fails, restart the transaction & regain write access for the
* buffer head which is used for metadata modifications.
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 41c9fe7e62..e3c3a35dc5 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -243,6 +243,8 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb,
int ocfs2_commit_trans(struct ocfs2_super *osb,
handle_t *handle);
int ocfs2_extend_trans(handle_t *handle, int nblocks);
+int ocfs2_assure_trans_credits(handle_t *handle,
+ int nblocks);
int ocfs2_allocate_extend_trans(handle_t *handle,
int thresh);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 33aeaaa056..5df34561c5 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -212,14 +212,15 @@ static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb)
void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
unsigned int num_clusters)
{
- spin_lock(&osb->osb_lock);
- if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
- osb->local_alloc_state == OCFS2_LA_THROTTLED)
- if (num_clusters >= osb->local_alloc_default_bits) {
+ if (num_clusters >= osb->local_alloc_default_bits) {
+ spin_lock(&osb->osb_lock);
+ if (osb->local_alloc_state == OCFS2_LA_DISABLED ||
+ osb->local_alloc_state == OCFS2_LA_THROTTLED) {
cancel_delayed_work(&osb->la_enable_wq);
osb->local_alloc_state = OCFS2_LA_ENABLED;
}
- spin_unlock(&osb->osb_lock);
+ spin_unlock(&osb->osb_lock);
+ }
}
void ocfs2_la_enable_worker(struct work_struct *work)
@@ -335,7 +336,7 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
"found = %u, set = %u, taken = %u, off = %u\n",
num_used, le32_to_cpu(alloc->id1.bitmap1.i_used),
le32_to_cpu(alloc->id1.bitmap1.i_total),
- OCFS2_LOCAL_ALLOC(alloc)->la_bm_off);
+ le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off));
status = -EINVAL;
goto bail;
@@ -1213,7 +1214,7 @@ retry_enospc:
OCFS2_LOCAL_ALLOC(alloc)->la_bitmap);
trace_ocfs2_local_alloc_new_window_result(
- OCFS2_LOCAL_ALLOC(alloc)->la_bm_off,
+ le32_to_cpu(OCFS2_LOCAL_ALLOC(alloc)->la_bm_off),
le32_to_cpu(alloc->id1.bitmap1.i_total));
bail:
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 1f9ed117e7..f9d6a4f9ca 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -685,7 +685,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
}
ret = ocfs2_block_group_set_bits(handle, gb_inode, gd, gd_bh,
- goal_bit, len);
+ goal_bit, len, 0, 0);
if (ret) {
ocfs2_rollback_alloc_dinode_counts(gb_inode, gb_bh, len,
le16_to_cpu(gd->bg_chain));
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 7aebdbf5cc..c93689b568 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -883,7 +883,8 @@ struct ocfs2_group_desc
__le16 bg_free_bits_count; /* Free bits count */
__le16 bg_chain; /* What chain I am in. */
/*10*/ __le32 bg_generation;
- __le32 bg_reserved1;
+ __le16 bg_contig_free_bits; /* max contig free bits length */
+ __le16 bg_reserved1;
__le64 bg_next_group; /* Next group in my list, in
blocks */
/*20*/ __le64 bg_parent_dinode; /* dinode which owns me, in
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 9898c11bdf..0511c69c9f 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -82,7 +82,7 @@ DECLARE_EVENT_CLASS(ocfs2__string,
__string(name,name)
),
TP_fast_assign(
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%s", __get_str(name))
);
@@ -1289,7 +1289,7 @@ DECLARE_EVENT_CLASS(ocfs2__file_ops,
__entry->dentry = dentry;
__entry->ino = ino;
__entry->d_len = d_len;
- __assign_str(d_name, d_name);
+ __assign_str(d_name);
__entry->para = para;
),
TP_printk("%p %p %p %llu %llu %.*s", __entry->inode, __entry->file,
@@ -1425,7 +1425,7 @@ TRACE_EVENT(ocfs2_setattr,
__entry->dentry = dentry;
__entry->ino = ino;
__entry->d_len = d_len;
- __assign_str(d_name, d_name);
+ __assign_str(d_name);
__entry->ia_valid = ia_valid;
__entry->ia_mode = ia_mode;
__entry->ia_uid = ia_uid;
@@ -1683,7 +1683,7 @@ TRACE_EVENT(ocfs2_parse_options,
),
TP_fast_assign(
__entry->is_remount = is_remount;
- __assign_str(options, options);
+ __assign_str(options);
),
TP_printk("%d %s", __entry->is_remount, __get_str(options))
);
@@ -1718,8 +1718,8 @@ TRACE_EVENT(ocfs2_initialize_super,
__field(int, cluster_bits)
),
TP_fast_assign(
- __assign_str(label, label);
- __assign_str(uuid_str, uuid_str);
+ __assign_str(label);
+ __assign_str(uuid_str);
__entry->root_dir = root_dir;
__entry->system_dir = system_dir;
__entry->cluster_bits = cluster_bits;
@@ -1746,7 +1746,7 @@ TRACE_EVENT(ocfs2_init_xattr_set_ctxt,
__field(int, credits)
),
TP_fast_assign(
- __assign_str(name, name);
+ __assign_str(name);
__entry->meta = meta;
__entry->clusters = clusters;
__entry->credits = credits;
@@ -1770,7 +1770,7 @@ DECLARE_EVENT_CLASS(ocfs2__xattr_find,
),
TP_fast_assign(
__entry->ino = ino;
- __assign_str(name, name);
+ __assign_str(name);
__entry->name_index = name_index;
__entry->hash = hash;
__entry->location = location;
@@ -2019,7 +2019,7 @@ TRACE_EVENT(ocfs2_sync_dquot_helper,
__entry->dq_id = dq_id;
__entry->dq_type = dq_type;
__entry->type = type;
- __assign_str(s_id, s_id);
+ __assign_str(s_id);
),
TP_printk("%u %u %lu %s", __entry->dq_id, __entry->dq_type,
__entry->type, __get_str(s_id))
@@ -2060,7 +2060,7 @@ TRACE_EVENT(ocfs2_dx_dir_search,
TP_fast_assign(
__entry->ino = ino;
__entry->namelen = namelen;
- __assign_str(name, name);
+ __assign_str(name);
__entry->major_hash = major_hash;
__entry->minor_hash = minor_hash;
__entry->blkno = blkno;
@@ -2088,7 +2088,7 @@ TRACE_EVENT(ocfs2_find_files_on_disk,
),
TP_fast_assign(
__entry->namelen = namelen;
- __assign_str(name, name);
+ __assign_str(name);
__entry->blkno = blkno;
__entry->dir = dir;
),
@@ -2107,7 +2107,7 @@ TRACE_EVENT(ocfs2_check_dir_for_entry,
TP_fast_assign(
__entry->dir = dir;
__entry->namelen = namelen;
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%llu %.*s", __entry->dir,
__entry->namelen, __get_str(name))
@@ -2135,7 +2135,7 @@ TRACE_EVENT(ocfs2_dx_dir_index_root_block,
__entry->major_hash = major_hash;
__entry->minor_hash = minor_hash;
__entry->namelen = namelen;
- __assign_str(name, name);
+ __assign_str(name);
__entry->num_used = num_used;
),
TP_printk("%llu %x %x %.*s %u", __entry->dir,
@@ -2171,7 +2171,7 @@ DECLARE_EVENT_CLASS(ocfs2__dentry_ops,
__entry->dir = dir;
__entry->dentry = dentry;
__entry->name_len = name_len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->dir_blkno = dir_blkno;
__entry->extra = extra;
),
@@ -2217,7 +2217,7 @@ TRACE_EVENT(ocfs2_mknod,
__entry->dir = dir;
__entry->dentry = dentry;
__entry->name_len = name_len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->dir_blkno = dir_blkno;
__entry->dev = dev;
__entry->mode = mode;
@@ -2241,9 +2241,9 @@ TRACE_EVENT(ocfs2_link,
TP_fast_assign(
__entry->ino = ino;
__entry->old_len = old_len;
- __assign_str(old_name, old_name);
+ __assign_str(old_name);
__entry->name_len = name_len;
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%llu %.*s %.*s", __entry->ino,
__entry->old_len, __get_str(old_name),
@@ -2279,9 +2279,9 @@ TRACE_EVENT(ocfs2_rename,
__entry->new_dir = new_dir;
__entry->new_dentry = new_dentry;
__entry->old_len = old_len;
- __assign_str(old_name, old_name);
+ __assign_str(old_name);
__entry->new_len = new_len;
- __assign_str(new_name, new_name);
+ __assign_str(new_name);
),
TP_printk("%p %p %p %p %.*s %.*s",
__entry->old_dir, __entry->old_dentry,
@@ -2301,7 +2301,7 @@ TRACE_EVENT(ocfs2_rename_target_exists,
),
TP_fast_assign(
__entry->new_len = new_len;
- __assign_str(new_name, new_name);
+ __assign_str(new_name);
),
TP_printk("%.*s", __entry->new_len, __get_str(new_name))
);
@@ -2344,7 +2344,7 @@ TRACE_EVENT(ocfs2_symlink_begin,
__entry->dentry = dentry;
__entry->symname = symname;
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%p %p %s %.*s", __entry->dir, __entry->dentry,
__entry->symname, __entry->len, __get_str(name))
@@ -2360,7 +2360,7 @@ TRACE_EVENT(ocfs2_blkno_stringify,
),
TP_fast_assign(
__entry->blkno = blkno;
- __assign_str(name, name);
+ __assign_str(name);
__entry->namelen = namelen;
),
TP_printk("%llu %s %d", __entry->blkno, __get_str(name),
@@ -2381,7 +2381,7 @@ TRACE_EVENT(ocfs2_orphan_del,
),
TP_fast_assign(
__entry->dir = dir;
- __assign_str(name, name);
+ __assign_str(name);
__entry->namelen = namelen;
),
TP_printk("%llu %s %d", __entry->dir, __get_str(name),
@@ -2403,7 +2403,7 @@ TRACE_EVENT(ocfs2_dentry_revalidate,
TP_fast_assign(
__entry->dentry = dentry;
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%p %.*s", __entry->dentry, __entry->len, __get_str(name))
);
@@ -2420,7 +2420,7 @@ TRACE_EVENT(ocfs2_dentry_revalidate_negative,
),
TP_fast_assign(
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->pgen = pgen;
__entry->gen = gen;
),
@@ -2445,7 +2445,7 @@ TRACE_EVENT(ocfs2_find_local_alias,
),
TP_fast_assign(
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
),
TP_printk("%.*s", __entry->len, __get_str(name))
);
@@ -2462,7 +2462,7 @@ TRACE_EVENT(ocfs2_dentry_attach_lock,
),
TP_fast_assign(
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->parent = parent;
__entry->fsdata = fsdata;
),
@@ -2480,7 +2480,7 @@ TRACE_EVENT(ocfs2_dentry_attach_lock_found,
__field(unsigned long long, ino)
),
TP_fast_assign(
- __assign_str(name, name);
+ __assign_str(name);
__entry->parent = parent;
__entry->ino = ino;
),
@@ -2527,7 +2527,7 @@ TRACE_EVENT(ocfs2_get_parent,
TP_fast_assign(
__entry->child = child;
__entry->len = len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->ino = ino;
),
TP_printk("%p %.*s %llu", __entry->child, __entry->len,
@@ -2551,7 +2551,7 @@ TRACE_EVENT(ocfs2_encode_fh_begin,
TP_fast_assign(
__entry->dentry = dentry;
__entry->name_len = name_len;
- __assign_str(name, name);
+ __assign_str(name);
__entry->fh = fh;
__entry->len = len;
__entry->connectable = connectable;
@@ -2577,6 +2577,8 @@ DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_commit_cache_end);
DEFINE_OCFS2_INT_INT_EVENT(ocfs2_extend_trans);
+DEFINE_OCFS2_INT_EVENT(ocfs2_assure_trans_credits);
+
DEFINE_OCFS2_INT_EVENT(ocfs2_extend_trans_restart);
DEFINE_OCFS2_INT_INT_EVENT(ocfs2_allocate_extend_trans);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 3f80a56d0d..1f303b1adf 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -630,7 +630,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
rb->rf_records.rl_count =
cpu_to_le16(ocfs2_refcount_recs_per_rb(osb->sb));
spin_lock(&osb->osb_lock);
- rb->rf_generation = osb->s_next_generation++;
+ rb->rf_generation = cpu_to_le32(osb->s_next_generation++);
spin_unlock(&osb->osb_lock);
ocfs2_journal_dirty(handle, new_bh);
diff --git a/fs/ocfs2/resize.c b/fs/ocfs2/resize.c
index d65d43c618..c4a4016d38 100644
--- a/fs/ocfs2/resize.c
+++ b/fs/ocfs2/resize.c
@@ -91,6 +91,8 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
u16 cl_bpc = le16_to_cpu(cl->cl_bpc);
u16 cl_cpg = le16_to_cpu(cl->cl_cpg);
u16 old_bg_clusters;
+ u16 contig_bits;
+ __le16 old_bg_contig_free_bits;
trace_ocfs2_update_last_group_and_inode(new_clusters,
first_new_cluster);
@@ -122,6 +124,11 @@ static int ocfs2_update_last_group_and_inode(handle_t *handle,
le16_add_cpu(&group->bg_free_bits_count, -1 * backups);
}
+ contig_bits = ocfs2_find_max_contig_free_bits(group->bg_bitmap,
+ le16_to_cpu(group->bg_bits), 0);
+ old_bg_contig_free_bits = group->bg_contig_free_bits;
+ group->bg_contig_free_bits = cpu_to_le16(contig_bits);
+
ocfs2_journal_dirty(handle, group_bh);
/* update the inode accordingly. */
@@ -160,6 +167,7 @@ out_rollback:
le16_add_cpu(&group->bg_free_bits_count, backups);
le16_add_cpu(&group->bg_bits, -1 * num_bits);
le16_add_cpu(&group->bg_free_bits_count, -1 * num_bits);
+ group->bg_contig_free_bits = old_bg_contig_free_bits;
}
out:
if (ret)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 9619984153..f7b483f0de 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -50,6 +50,10 @@ struct ocfs2_suballoc_result {
u64 sr_blkno; /* The first allocated block */
unsigned int sr_bit_offset; /* The bit in the bg */
unsigned int sr_bits; /* How many bits we claimed */
+ unsigned int sr_max_contig_bits; /* The length for contiguous
+ * free bits, only available
+ * for cluster group
+ */
};
static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
@@ -1272,6 +1276,26 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
return ret;
}
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+ u16 total_bits, u16 start)
+{
+ u16 offset, free_bits;
+ u16 contig_bits = 0;
+
+ while (start < total_bits) {
+ offset = ocfs2_find_next_zero_bit(bitmap, total_bits, start);
+ if (offset == total_bits)
+ break;
+
+ start = ocfs2_find_next_bit(bitmap, total_bits, offset);
+ free_bits = start - offset;
+ if (contig_bits < free_bits)
+ contig_bits = free_bits;
+ }
+
+ return contig_bits;
+}
+
static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
struct buffer_head *bg_bh,
unsigned int bits_wanted,
@@ -1280,6 +1304,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
{
void *bitmap;
u16 best_offset, best_size;
+ u16 prev_best_size = 0;
int offset, start, found, status = 0;
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
@@ -1306,6 +1331,7 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
/* got a zero after some ones */
found = 1;
start = offset + 1;
+ prev_best_size = best_size;
}
if (found > best_size) {
best_size = found;
@@ -1318,6 +1344,8 @@ static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
}
}
+ /* best_size will be allocated, we save prev_best_size */
+ res->sr_max_contig_bits = prev_best_size;
if (best_size) {
res->sr_bit_offset = best_offset;
res->sr_bits = best_size;
@@ -1335,11 +1363,16 @@ int ocfs2_block_group_set_bits(handle_t *handle,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
- unsigned int num_bits)
+ unsigned int num_bits,
+ unsigned int max_contig_bits,
+ int fastpath)
{
int status;
void *bitmap = bg->bg_bitmap;
int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
+ unsigned int start = bit_off + num_bits;
+ u16 contig_bits;
+ struct ocfs2_super *osb = OCFS2_SB(alloc_inode->i_sb);
/* All callers get the descriptor via
* ocfs2_read_group_descriptor(). Any corruption is a code bug. */
@@ -1371,6 +1404,29 @@ int ocfs2_block_group_set_bits(handle_t *handle,
while(num_bits--)
ocfs2_set_bit(bit_off++, bitmap);
+ /*
+ * this is optimize path, caller set old contig value
+ * in max_contig_bits to bypass finding action.
+ */
+ if (fastpath) {
+ bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+ } else if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+ /*
+ * Usually, the block group bitmap allocates only 1 bit
+ * at a time, while the cluster group allocates n bits
+ * each time. Therefore, we only save the contig bits for
+ * the cluster group.
+ */
+ contig_bits = ocfs2_find_max_contig_free_bits(bitmap,
+ le16_to_cpu(bg->bg_bits), start);
+ if (contig_bits > max_contig_bits)
+ max_contig_bits = contig_bits;
+ bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+ ocfs2_local_alloc_seen_free_bits(osb, max_contig_bits);
+ } else {
+ bg->bg_contig_free_bits = 0;
+ }
+
ocfs2_journal_dirty(handle, group_bh);
bail:
@@ -1484,7 +1540,12 @@ static int ocfs2_cluster_group_search(struct inode *inode,
BUG_ON(!ocfs2_is_cluster_bitmap(inode));
- if (gd->bg_free_bits_count) {
+ if (le16_to_cpu(gd->bg_contig_free_bits) &&
+ le16_to_cpu(gd->bg_contig_free_bits) < bits_wanted)
+ return -ENOSPC;
+
+ /* ->bg_contig_free_bits may un-initialized, so compare again */
+ if (le16_to_cpu(gd->bg_free_bits_count) >= bits_wanted) {
max_bits = le16_to_cpu(gd->bg_bits);
/* Tail groups in cluster bitmaps which aren't cpg
@@ -1528,13 +1589,6 @@ static int ocfs2_cluster_group_search(struct inode *inode,
* of bits. */
if (min_bits <= res->sr_bits)
search = 0; /* success */
- else if (res->sr_bits) {
- /*
- * Don't show bits which we'll be returning
- * for allocation to the local alloc bitmap.
- */
- ocfs2_local_alloc_seen_free_bits(osb, res->sr_bits);
- }
}
return search;
@@ -1553,7 +1607,7 @@ static int ocfs2_block_group_search(struct inode *inode,
BUG_ON(min_bits != 1);
BUG_ON(ocfs2_is_cluster_bitmap(inode));
- if (bg->bg_free_bits_count) {
+ if (le16_to_cpu(bg->bg_free_bits_count) >= bits_wanted) {
ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
group_bh, bits_wanted,
le16_to_cpu(bg->bg_bits),
@@ -1713,7 +1767,8 @@ static int ocfs2_search_one_group(struct ocfs2_alloc_context *ac,
}
ret = ocfs2_block_group_set_bits(handle, alloc_inode, gd, group_bh,
- res->sr_bit_offset, res->sr_bits);
+ res->sr_bit_offset, res->sr_bits,
+ res->sr_max_contig_bits, 0);
if (ret < 0) {
ocfs2_rollback_alloc_dinode_counts(alloc_inode, ac->ac_bh,
res->sr_bits,
@@ -1847,7 +1902,9 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac,
bg,
group_bh,
res->sr_bit_offset,
- res->sr_bits);
+ res->sr_bits,
+ res->sr_max_contig_bits,
+ 0);
if (status < 0) {
ocfs2_rollback_alloc_dinode_counts(alloc_inode,
ac->ac_bh, res->sr_bits, chain);
@@ -1949,7 +2006,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac,
for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i ++) {
if (i == victim)
continue;
- if (!cl->cl_recs[i].c_free)
+ if (le32_to_cpu(cl->cl_recs[i].c_free) < bits_wanted)
continue;
ac->ac_chain = i;
@@ -2161,7 +2218,9 @@ int ocfs2_claim_new_inode_at_loc(handle_t *handle,
bg,
bg_bh,
res->sr_bit_offset,
- res->sr_bits);
+ res->sr_bits,
+ res->sr_max_contig_bits,
+ 0);
if (ret < 0) {
ocfs2_rollback_alloc_dinode_counts(ac->ac_inode,
ac->ac_bh, res->sr_bits, chain);
@@ -2380,11 +2439,13 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
struct buffer_head *group_bh,
unsigned int bit_off,
unsigned int num_bits,
+ unsigned int max_contig_bits,
void (*undo_fn)(unsigned int bit,
unsigned long *bmap))
{
int status;
unsigned int tmp;
+ u16 contig_bits;
struct ocfs2_group_desc *undo_bg = NULL;
struct journal_head *jh;
@@ -2431,6 +2492,20 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
num_bits);
}
+ /*
+ * TODO: even 'num_bits == 1' (the worst case, release 1 cluster),
+ * we still need to rescan whole bitmap.
+ */
+ if (ocfs2_is_cluster_bitmap(alloc_inode)) {
+ contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap,
+ le16_to_cpu(bg->bg_bits), 0);
+ if (contig_bits > max_contig_bits)
+ max_contig_bits = contig_bits;
+ bg->bg_contig_free_bits = cpu_to_le16(max_contig_bits);
+ } else {
+ bg->bg_contig_free_bits = 0;
+ }
+
if (undo_fn)
spin_unlock(&jh->b_state_lock);
@@ -2457,6 +2532,7 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
struct ocfs2_chain_list *cl = &fe->id2.i_chain;
struct buffer_head *group_bh = NULL;
struct ocfs2_group_desc *group;
+ __le16 old_bg_contig_free_bits = 0;
/* The alloc_bh comes from ocfs2_free_dinode() or
* ocfs2_free_clusters(). The callers have all locked the
@@ -2481,9 +2557,11 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
BUG_ON((count + start_bit) > le16_to_cpu(group->bg_bits));
+ if (ocfs2_is_cluster_bitmap(alloc_inode))
+ old_bg_contig_free_bits = group->bg_contig_free_bits;
status = ocfs2_block_group_clear_bits(handle, alloc_inode,
group, group_bh,
- start_bit, count, undo_fn);
+ start_bit, count, 0, undo_fn);
if (status < 0) {
mlog_errno(status);
goto bail;
@@ -2494,7 +2572,8 @@ static int _ocfs2_free_suballoc_bits(handle_t *handle,
if (status < 0) {
mlog_errno(status);
ocfs2_block_group_set_bits(handle, alloc_inode, group, group_bh,
- start_bit, count);
+ start_bit, count,
+ le16_to_cpu(old_bg_contig_free_bits), 1);
goto bail;
}
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index 9c74eace3a..b481b83485 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -79,12 +79,16 @@ void ocfs2_rollback_alloc_dinode_counts(struct inode *inode,
struct buffer_head *di_bh,
u32 num_bits,
u16 chain);
+u16 ocfs2_find_max_contig_free_bits(void *bitmap,
+ u16 total_bits, u16 start);
int ocfs2_block_group_set_bits(handle_t *handle,
struct inode *alloc_inode,
struct ocfs2_group_desc *bg,
struct buffer_head *group_bh,
unsigned int bit_off,
- unsigned int num_bits);
+ unsigned int num_bits,
+ unsigned int max_contig_bits,
+ int fastpath);
int ocfs2_claim_metadata(handle_t *handle,
struct ocfs2_alloc_context *ac,
generated by cgit v1.2.3 (git 2.39.1) at 2024-08-24 15:41:49 +0000