GFS2: Fix inode deallocation race
This area of the code has always been a bit delicate due to the
subtleties of lock ordering. The problem is that for "normal"
alloc/dealloc, we always grab the inode locks first and the rgrp lock
later.
In order to ensure no races in looking up the unlinked, but still
allocated inodes, we need to hold the rgrp lock when we do the lookup,
which means that we can't take the inode glock.
The solution is to borrow the technique already used by NFS to solve
what is essentially the same problem (given an inode number, look up
the inode carefully, checking that it really is in the expected
state).
We cannot do that directly from the allocation code (lock ordering
again) so we give the job to the pre-existing delete workqueue and
carry on with the allocation as normal.
If we find there is no space, we do a journal flush (required anyway
if space from a deallocation is to be released) which should block
against the pending deallocations, so we should always get the space
back.
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 06d5827..5ab3839 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -138,10 +138,8 @@
struct gfs2_inum_host *inum)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
- struct gfs2_holder i_gh;
struct inode *inode;
struct dentry *dentry;
- int error;
inode = gfs2_ilookup(sb, inum->no_addr);
if (inode) {
@@ -152,52 +150,16 @@
goto out_inode;
}
- error = gfs2_glock_nq_num(sdp, inum->no_addr, &gfs2_inode_glops,
- LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
- if (error)
- return ERR_PTR(error);
-
- error = gfs2_check_blk_type(sdp, inum->no_addr, GFS2_BLKST_DINODE);
- if (error)
- goto fail;
-
- inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, 0);
- if (IS_ERR(inode)) {
- error = PTR_ERR(inode);
- goto fail;
- }
-
- error = gfs2_inode_refresh(GFS2_I(inode));
- if (error) {
- iput(inode);
- goto fail;
- }
-
- /* Pick up the works we bypass in gfs2_inode_lookup */
- if (inode->i_state & I_NEW)
- gfs2_set_iop(inode);
-
- if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
- iput(inode);
- goto fail;
- }
-
- error = -EIO;
- if (GFS2_I(inode)->i_diskflags & GFS2_DIF_SYSTEM) {
- iput(inode);
- goto fail;
- }
-
- gfs2_glock_dq_uninit(&i_gh);
+ inode = gfs2_lookup_by_inum(sdp, inum->no_addr, &inum->no_formal_ino,
+ GFS2_BLKST_DINODE);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
out_inode:
dentry = d_obtain_alias(inode);
if (!IS_ERR(dentry))
dentry->d_op = &gfs2_dops;
return dentry;
-fail:
- gfs2_glock_dq_uninit(&i_gh);
- return ERR_PTR(error);
}
static struct dentry *gfs2_fh_to_dentry(struct super_block *sb, struct fid *fid,