From: NeilBrown <[email protected]> A proposed change will invert the lock ordering between d_alloc_parallel() and inode_lock() on the parent. When that happens it will not be safe to call d_alloc_parallel() while holding the parent lock - even shared.
We don't need to keep the parent lock held when d_add_ci() is run - the VFS doesn't need it as dentry is exclusively held due to DCACHE_PAR_LOOKUP and the filesystem has finished its work. So drop and reclaim the lock (shared or exclusive as determined by LOOKUP_SHARED) to avoid future deadlock. Signed-off-by: NeilBrown <[email protected]> --- fs/dcache.c | 18 +++++++++++++++++- fs/xfs/xfs_iops.c | 3 ++- include/linux/dcache.h | 3 ++- 3 files changed, 21 insertions(+), 3 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index c12319097d6e..a1219b446b74 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -2225,6 +2225,7 @@ EXPORT_SYMBOL(d_obtain_root); * @dentry: the negative dentry that was passed to the parent's lookup func * @inode: the inode case-insensitive lookup has found * @name: the case-exact name to be associated with the returned dentry + * @bool: %true if lookup was performed with LOOKUP_SHARED * * This is to avoid filling the dcache with case-insensitive names to the * same inode, only the actual correct case is stored in the dcache for @@ -2237,7 +2238,7 @@ EXPORT_SYMBOL(d_obtain_root); * the exact case, and return the spliced entry. */ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, - struct qstr *name) + struct qstr *name, bool shared) { struct dentry *found, *res; @@ -2250,6 +2251,17 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, iput(inode); return found; } + /* + * We are holding parent lock and so don't want to wait for a + * d_in_lookup() dentry. We can safely drop the parent lock and + * reclaim it as we have exclusive access to dentry as it is + * d_in_lookup() (so ->d_parent is stable) and we are near the + * end ->lookup() and will shortly drop the lock anyway. + */ + if (shared) + inode_unlock_shared(d_inode(dentry->d_parent)); + else + inode_unlock(d_inode(dentry->d_parent)); if (d_in_lookup(dentry)) { found = d_alloc_parallel(dentry->d_parent, name); if (IS_ERR(found) || !d_in_lookup(found)) { @@ -2263,6 +2275,10 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode, return ERR_PTR(-ENOMEM); } } + if (shared) + inode_lock_shared(d_inode(dentry->d_parent)); + else + inode_lock_nested(d_inode(dentry->d_parent), I_MUTEX_PARENT); res = d_splice_alias(inode, found); if (res) { d_lookup_done(found); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 208543e57eda..ec19d3ec7cf0 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -35,6 +35,7 @@ #include <linux/security.h> #include <linux/iversion.h> #include <linux/fiemap.h> +#include <linux/namei.h> // for LOOKUP_SHARED /* * Directories have different lock order w.r.t. mmap_lock compared to regular @@ -369,7 +370,7 @@ xfs_vn_ci_lookup( /* else case-insensitive match... */ dname.name = ci_name.name; dname.len = ci_name.len; - dentry = d_add_ci(dentry, VFS_I(ip), &dname); + dentry = d_add_ci(dentry, VFS_I(ip), &dname, !!(flags & LOOKUP_SHARED)); kfree(ci_name.name); return dentry; } diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 2a3ebd368ed9..a97eb151d9db 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -251,7 +251,8 @@ struct dentry *d_duplicate(struct dentry *dentry); /* weird procfs mess; *NOT* exported */ extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *, const struct dentry_operations *); -extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); +extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *, + bool); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); extern struct dentry *d_find_any_alias(struct inode *inode); -- 2.50.0.107.gf914562f5916.dirty
