Merge branch 'overlayfs-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs
Pull overlayfs updates from Miklos Szeredi:
"This relaxes the requirements on the lower layer filesystem: now ones
that implement .d_revalidate, such as NFS, can be used.
Upper layer filesystems still has the "no .d_revalidate" requirement.
Also a bad interaction with jffs2 locking has been fixed"
* 'overlayfs-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
ovl: lookup whiteouts outside iterate_dir()
ovl: allow distributed fs as lower layer
ovl: don't traverse automount points
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 907870e..70e9af5 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -23,6 +23,7 @@
u64 ino;
struct list_head l_node;
struct rb_node node;
+ struct ovl_cache_entry *next_maybe_whiteout;
bool is_whiteout;
char name[];
};
@@ -39,7 +40,7 @@
struct rb_root root;
struct list_head *list;
struct list_head middle;
- struct dentry *dir;
+ struct ovl_cache_entry *first_maybe_whiteout;
int count;
int err;
};
@@ -79,7 +80,7 @@
return NULL;
}
-static struct ovl_cache_entry *ovl_cache_entry_new(struct dentry *dir,
+static struct ovl_cache_entry *ovl_cache_entry_new(struct ovl_readdir_data *rdd,
const char *name, int len,
u64 ino, unsigned int d_type)
{
@@ -98,29 +99,8 @@
p->is_whiteout = false;
if (d_type == DT_CHR) {
- struct dentry *dentry;
- const struct cred *old_cred;
- struct cred *override_cred;
-
- override_cred = prepare_creds();
- if (!override_cred) {
- kfree(p);
- return NULL;
- }
-
- /*
- * CAP_DAC_OVERRIDE for lookup
- */
- cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
- old_cred = override_creds(override_cred);
-
- dentry = lookup_one_len(name, dir, len);
- if (!IS_ERR(dentry)) {
- p->is_whiteout = ovl_is_whiteout(dentry);
- dput(dentry);
- }
- revert_creds(old_cred);
- put_cred(override_cred);
+ p->next_maybe_whiteout = rdd->first_maybe_whiteout;
+ rdd->first_maybe_whiteout = p;
}
return p;
}
@@ -148,7 +128,7 @@
return 0;
}
- p = ovl_cache_entry_new(rdd->dir, name, len, ino, d_type);
+ p = ovl_cache_entry_new(rdd, name, len, ino, d_type);
if (p == NULL)
return -ENOMEM;
@@ -169,7 +149,7 @@
if (p) {
list_move_tail(&p->l_node, &rdd->middle);
} else {
- p = ovl_cache_entry_new(rdd->dir, name, namelen, ino, d_type);
+ p = ovl_cache_entry_new(rdd, name, namelen, ino, d_type);
if (p == NULL)
rdd->err = -ENOMEM;
else
@@ -219,6 +199,43 @@
return ovl_fill_lower(rdd, name, namelen, offset, ino, d_type);
}
+static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
+{
+ int err;
+ struct ovl_cache_entry *p;
+ struct dentry *dentry;
+ const struct cred *old_cred;
+ struct cred *override_cred;
+
+ override_cred = prepare_creds();
+ if (!override_cred)
+ return -ENOMEM;
+
+ /*
+ * CAP_DAC_OVERRIDE for lookup
+ */
+ cap_raise(override_cred->cap_effective, CAP_DAC_OVERRIDE);
+ old_cred = override_creds(override_cred);
+
+ err = mutex_lock_killable(&dir->d_inode->i_mutex);
+ if (!err) {
+ while (rdd->first_maybe_whiteout) {
+ p = rdd->first_maybe_whiteout;
+ rdd->first_maybe_whiteout = p->next_maybe_whiteout;
+ dentry = lookup_one_len(p->name, dir, p->len);
+ if (!IS_ERR(dentry)) {
+ p->is_whiteout = ovl_is_whiteout(dentry);
+ dput(dentry);
+ }
+ }
+ mutex_unlock(&dir->d_inode->i_mutex);
+ }
+ revert_creds(old_cred);
+ put_cred(override_cred);
+
+ return err;
+}
+
static inline int ovl_dir_read(struct path *realpath,
struct ovl_readdir_data *rdd)
{
@@ -229,7 +246,7 @@
if (IS_ERR(realfile))
return PTR_ERR(realfile);
- rdd->dir = realpath->dentry;
+ rdd->first_maybe_whiteout = NULL;
rdd->ctx.pos = 0;
do {
rdd->count = 0;
@@ -238,6 +255,10 @@
if (err >= 0)
err = rdd->err;
} while (!err && rdd->count);
+
+ if (!err && rdd->first_maybe_whiteout)
+ err = ovl_check_whiteouts(realpath->dentry, rdd);
+
fput(realfile);
return err;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index bf8537c..8a08c58 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -273,10 +273,57 @@
}
}
+static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ unsigned int i;
+ int ret = 1;
+
+ for (i = 0; i < oe->numlower; i++) {
+ struct dentry *d = oe->lowerstack[i].dentry;
+
+ if (d->d_flags & DCACHE_OP_REVALIDATE) {
+ ret = d->d_op->d_revalidate(d, flags);
+ if (ret < 0)
+ return ret;
+ if (!ret) {
+ if (!(flags & LOOKUP_RCU))
+ d_invalidate(d);
+ return -ESTALE;
+ }
+ }
+ }
+ return 1;
+}
+
+static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
+{
+ struct ovl_entry *oe = dentry->d_fsdata;
+ unsigned int i;
+ int ret = 1;
+
+ for (i = 0; i < oe->numlower; i++) {
+ struct dentry *d = oe->lowerstack[i].dentry;
+
+ if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) {
+ ret = d->d_op->d_weak_revalidate(d, flags);
+ if (ret <= 0)
+ break;
+ }
+ }
+ return ret;
+}
+
static const struct dentry_operations ovl_dentry_operations = {
.d_release = ovl_dentry_release,
};
+static const struct dentry_operations ovl_reval_dentry_operations = {
+ .d_release = ovl_dentry_release,
+ .d_revalidate = ovl_dentry_revalidate,
+ .d_weak_revalidate = ovl_dentry_weak_revalidate,
+};
+
static struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
{
size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
@@ -288,6 +335,20 @@
return oe;
}
+static bool ovl_dentry_remote(struct dentry *dentry)
+{
+ return dentry->d_flags &
+ (DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
+}
+
+static bool ovl_dentry_weird(struct dentry *dentry)
+{
+ return dentry->d_flags & (DCACHE_NEED_AUTOMOUNT |
+ DCACHE_MANAGE_TRANSIT |
+ DCACHE_OP_HASH |
+ DCACHE_OP_COMPARE);
+}
+
static inline struct dentry *ovl_lookup_real(struct dentry *dir,
struct qstr *name)
{
@@ -303,6 +364,10 @@
} else if (!dentry->d_inode) {
dput(dentry);
dentry = NULL;
+ } else if (ovl_dentry_weird(dentry)) {
+ dput(dentry);
+ /* Don't support traversing automounts and other weirdness */
+ dentry = ERR_PTR(-EREMOTE);
}
return dentry;
}
@@ -350,6 +415,11 @@
goto out;
if (this) {
+ if (unlikely(ovl_dentry_remote(this))) {
+ dput(this);
+ err = -EREMOTE;
+ goto out;
+ }
if (ovl_is_whiteout(this)) {
dput(this);
this = NULL;
@@ -694,25 +764,6 @@
}
}
-static bool ovl_is_allowed_fs_type(struct dentry *root)
-{
- const struct dentry_operations *dop = root->d_op;
-
- /*
- * We don't support:
- * - automount filesystems
- * - filesystems with revalidate (FIXME for lower layer)
- * - filesystems with case insensitive names
- */
- if (dop &&
- (dop->d_manage || dop->d_automount ||
- dop->d_revalidate || dop->d_weak_revalidate ||
- dop->d_compare || dop->d_hash)) {
- return false;
- }
- return true;
-}
-
static int ovl_mount_dir_noesc(const char *name, struct path *path)
{
int err = -EINVAL;
@@ -727,7 +778,7 @@
goto out;
}
err = -EINVAL;
- if (!ovl_is_allowed_fs_type(path->dentry)) {
+ if (ovl_dentry_weird(path->dentry)) {
pr_err("overlayfs: filesystem on '%s' not supported\n", name);
goto out_put;
}
@@ -751,13 +802,21 @@
if (tmp) {
ovl_unescape(tmp);
err = ovl_mount_dir_noesc(tmp, path);
+
+ if (!err)
+ if (ovl_dentry_remote(path->dentry)) {
+ pr_err("overlayfs: filesystem on '%s' not supported as upperdir\n",
+ tmp);
+ path_put(path);
+ err = -EINVAL;
+ }
kfree(tmp);
}
return err;
}
static int ovl_lower_dir(const char *name, struct path *path, long *namelen,
- int *stack_depth)
+ int *stack_depth, bool *remote)
{
int err;
struct kstatfs statfs;
@@ -774,6 +833,9 @@
*namelen = max(*namelen, statfs.f_namelen);
*stack_depth = max(*stack_depth, path->mnt->mnt_sb->s_stack_depth);
+ if (ovl_dentry_remote(path->dentry))
+ *remote = true;
+
return 0;
out_put:
@@ -827,6 +889,7 @@
unsigned int numlower;
unsigned int stacklen = 0;
unsigned int i;
+ bool remote = false;
int err;
err = -ENOMEM;
@@ -900,7 +963,8 @@
lower = lowertmp;
for (numlower = 0; numlower < stacklen; numlower++) {
err = ovl_lower_dir(lower, &stack[numlower],
- &ufs->lower_namelen, &sb->s_stack_depth);
+ &ufs->lower_namelen, &sb->s_stack_depth,
+ &remote);
if (err)
goto out_put_lowerpath;
@@ -958,7 +1022,10 @@
if (!ufs->upper_mnt)
sb->s_flags |= MS_RDONLY;
- sb->s_d_op = &ovl_dentry_operations;
+ if (remote)
+ sb->s_d_op = &ovl_reval_dentry_operations;
+ else
+ sb->s_d_op = &ovl_dentry_operations;
err = -ENOMEM;
oe = ovl_alloc_entry(numlower);