struct path root;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags, state;
- unsigned seq, m_seq, r_seq;
+ unsigned seq, next_seq, m_seq, r_seq;
int last_type;
unsigned depth;
int total_link_count;
}
}
+static void leave_rcu(struct nameidata *nd)
+{
+ nd->flags &= ~LOOKUP_RCU;
+ nd->seq = nd->next_seq = 0;
+ rcu_read_unlock();
+}
+
static void terminate_walk(struct nameidata *nd)
{
drop_links(nd);
nd->state &= ~ND_ROOT_GRABBED;
}
} else {
- nd->flags &= ~LOOKUP_RCU;
- rcu_read_unlock();
+ leave_rcu(nd);
}
nd->depth = 0;
nd->path.mnt = NULL;
BUG_ON(!(nd->flags & LOOKUP_RCU));
- nd->flags &= ~LOOKUP_RCU;
if (unlikely(!legitimize_links(nd)))
goto out1;
if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
goto out;
if (unlikely(!legitimize_root(nd)))
goto out;
- rcu_read_unlock();
+ leave_rcu(nd);
BUG_ON(nd->inode != parent->d_inode);
return true;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
out:
- rcu_read_unlock();
+ leave_rcu(nd);
return false;
}
* try_to_unlazy_next - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* @dentry: next dentry to step into
- * @seq: seq number to check @dentry against
* Returns: true on success, false on failure
*
* Similar to try_to_unlazy(), but here we have the next dentry already
* Nothing should touch nameidata between try_to_unlazy_next() failure and
* terminate_walk().
*/
-static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry)
{
+ int res;
BUG_ON(!(nd->flags & LOOKUP_RCU));
- nd->flags &= ~LOOKUP_RCU;
if (unlikely(!legitimize_links(nd)))
goto out2;
- if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
- goto out2;
+ res = __legitimize_mnt(nd->path.mnt, nd->m_seq);
+ if (unlikely(res)) {
+ if (res > 0)
+ goto out2;
+ goto out1;
+ }
if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
goto out1;
*/
if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
goto out;
- if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
+ if (read_seqcount_retry(&dentry->d_seq, nd->next_seq))
goto out_dput;
/*
* Sequence counts matched. Now make sure that the root is
*/
if (unlikely(!legitimize_root(nd)))
goto out_dput;
- rcu_read_unlock();
+ leave_rcu(nd);
return true;
out2:
out1:
nd->path.dentry = NULL;
out:
- rcu_read_unlock();
+ leave_rcu(nd);
return false;
out_dput:
- rcu_read_unlock();
+ leave_rcu(nd);
dput(dentry);
return false;
}
d = nd->path.dentry;
nd->inode = d->d_inode;
nd->seq = nd->root_seq;
- if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+ if (read_seqcount_retry(&d->d_seq, nd->seq))
return -ECHILD;
} else {
path_put(&nd->path);
* Try to skip to top of mountpoint pile in rcuwalk mode. Fail if
* we meet a managed dentry that would need blocking.
*/
-static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
- struct inode **inode, unsigned *seqp)
+static bool __follow_mount_rcu(struct nameidata *nd, struct path *path)
{
struct dentry *dentry = path->dentry;
unsigned int flags = dentry->d_flags;
path->mnt = &mounted->mnt;
dentry = path->dentry = mounted->mnt.mnt_root;
nd->state |= ND_JUMPED;
- *seqp = read_seqcount_begin(&dentry->d_seq);
- *inode = dentry->d_inode;
- /*
- * We don't need to re-check ->d_seq after this
- * ->d_inode read - there will be an RCU delay
- * between mount hash removal and ->mnt_root
- * becoming unpinned.
- */
+ nd->next_seq = read_seqcount_begin(&dentry->d_seq);
flags = dentry->d_flags;
+ // makes sure that non-RCU pathwalk could reach
+ // this state.
+ if (read_seqretry(&mount_lock, nd->m_seq))
+ return false;
continue;
}
if (read_seqretry(&mount_lock, nd->m_seq))
}
static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
- struct path *path, struct inode **inode,
- unsigned int *seqp)
+ struct path *path)
{
bool jumped;
int ret;
path->mnt = nd->path.mnt;
path->dentry = dentry;
if (nd->flags & LOOKUP_RCU) {
- unsigned int seq = *seqp;
- if (unlikely(!*inode))
- return -ENOENT;
- if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
+ unsigned int seq = nd->next_seq;
+ if (likely(__follow_mount_rcu(nd, path)))
return 0;
- if (!try_to_unlazy_next(nd, dentry, seq))
- return -ECHILD;
- // *path might've been clobbered by __follow_mount_rcu()
+ // *path and nd->next_seq might've been clobbered
path->mnt = nd->path.mnt;
path->dentry = dentry;
+ nd->next_seq = seq;
+ if (!try_to_unlazy_next(nd, dentry))
+ return -ECHILD;
}
ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags);
if (jumped) {
dput(path->dentry);
if (path->mnt != nd->path.mnt)
mntput(path->mnt);
- } else {
- *inode = d_backing_inode(path->dentry);
- *seqp = 0; /* out of RCU mode, so the value doesn't matter */
}
return ret;
}
return dentry;
}
-static struct dentry *lookup_fast(struct nameidata *nd,
- struct inode **inode,
- unsigned *seqp)
+static struct dentry *lookup_fast(struct nameidata *nd)
{
struct dentry *dentry, *parent = nd->path.dentry;
int status = 1;
* going to fall back to non-racy lookup.
*/
if (nd->flags & LOOKUP_RCU) {
- unsigned seq;
- dentry = __d_lookup_rcu(parent, &nd->last, &seq);
+ dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq);
if (unlikely(!dentry)) {
if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
return NULL;
}
- /*
- * This sequence count validates that the inode matches
- * the dentry name information from lookup.
- */
- *inode = d_backing_inode(dentry);
- if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
- return ERR_PTR(-ECHILD);
-
/*
* This sequence count validates that the parent had no
* changes while we did the lookup of the dentry above.
- *
- * The memory barrier in read_seqcount_begin of child is
- * enough, we can use __read_seqcount_retry here.
*/
- if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
+ if (read_seqcount_retry(&parent->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
- *seqp = seq;
status = d_revalidate(dentry, nd->flags);
if (likely(status > 0))
return dentry;
- if (!try_to_unlazy_next(nd, dentry, seq))
+ if (!try_to_unlazy_next(nd, dentry))
return ERR_PTR(-ECHILD);
if (status == -ECHILD)
/* we'd been told to redo it in non-rcu mode */
return inode_permission(mnt_userns, nd->inode, MAY_EXEC);
}
-static int reserve_stack(struct nameidata *nd, struct path *link, unsigned seq)
+static int reserve_stack(struct nameidata *nd, struct path *link)
{
if (unlikely(nd->total_link_count++ >= MAXSYMLINKS))
return -ELOOP;
if (nd->flags & LOOKUP_RCU) {
// we need to grab link before we do unlazy. And we can't skip
// unlazy even if we fail to grab the link - cleanup needs it
- bool grabbed_link = legitimize_path(nd, link, seq);
+ bool grabbed_link = legitimize_path(nd, link, nd->next_seq);
if (!try_to_unlazy(nd) || !grabbed_link)
return -ECHILD;
enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
static const char *pick_link(struct nameidata *nd, struct path *link,
- struct inode *inode, unsigned seq, int flags)
+ struct inode *inode, int flags)
{
struct saved *last;
const char *res;
- int error = reserve_stack(nd, link, seq);
+ int error = reserve_stack(nd, link);
if (unlikely(error)) {
if (!(nd->flags & LOOKUP_RCU))
last = nd->stack + nd->depth++;
last->link = *link;
clear_delayed_call(&last->done);
- last->seq = seq;
+ last->seq = nd->next_seq;
if (flags & WALK_TRAILING) {
error = may_follow_link(nd, inode);
* to do this check without having to look at inode->i_op,
* so we keep a cache of "no, this doesn't need follow_link"
* for the common case.
+ *
+ * NOTE: dentry must be what nd->next_seq had been sampled from.
*/
static const char *step_into(struct nameidata *nd, int flags,
- struct dentry *dentry, struct inode *inode, unsigned seq)
+ struct dentry *dentry)
{
struct path path;
- int err = handle_mounts(nd, dentry, &path, &inode, &seq);
+ struct inode *inode;
+ int err = handle_mounts(nd, dentry, &path);
if (err < 0)
return ERR_PTR(err);
+ inode = path.dentry->d_inode;
if (likely(!d_is_symlink(path.dentry)) ||
((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) ||
(flags & WALK_NOFOLLOW)) {
/* not a symlink or should not follow */
- if (!(nd->flags & LOOKUP_RCU)) {
+ if (nd->flags & LOOKUP_RCU) {
+ if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
+ return ERR_PTR(-ECHILD);
+ if (unlikely(!inode))
+ return ERR_PTR(-ENOENT);
+ } else {
dput(nd->path.dentry);
if (nd->path.mnt != path.mnt)
mntput(nd->path.mnt);
}
nd->path = path;
nd->inode = inode;
- nd->seq = seq;
+ nd->seq = nd->next_seq;
return NULL;
}
if (nd->flags & LOOKUP_RCU) {
/* make sure that d_is_symlink above matches inode */
- if (read_seqcount_retry(&path.dentry->d_seq, seq))
+ if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
return ERR_PTR(-ECHILD);
} else {
if (path.mnt == nd->path.mnt)
mntget(path.mnt);
}
- return pick_link(nd, &path, inode, seq, flags);
+ return pick_link(nd, &path, inode, flags);
}
-static struct dentry *follow_dotdot_rcu(struct nameidata *nd,
- struct inode **inodep,
- unsigned *seqp)
+static struct dentry *follow_dotdot_rcu(struct nameidata *nd)
{
struct dentry *parent, *old;
nd->path = path;
nd->inode = path.dentry->d_inode;
nd->seq = seq;
- if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ // makes sure that non-RCU pathwalk could reach this state
+ if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
/* we know that mountpoint was pinned */
}
old = nd->path.dentry;
parent = old->d_parent;
- *inodep = parent->d_inode;
- *seqp = read_seqcount_begin(&parent->d_seq);
- if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
+ nd->next_seq = read_seqcount_begin(&parent->d_seq);
+ // makes sure that non-RCU pathwalk could reach this state
+ if (read_seqcount_retry(&old->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
if (unlikely(!path_connected(nd->path.mnt, parent)))
return ERR_PTR(-ECHILD);
return parent;
in_root:
- if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
+ if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-ECHILD);
- return NULL;
+ nd->next_seq = nd->seq;
+ return nd->path.dentry;
}
-static struct dentry *follow_dotdot(struct nameidata *nd,
- struct inode **inodep,
- unsigned *seqp)
+static struct dentry *follow_dotdot(struct nameidata *nd)
{
struct dentry *parent;
dput(parent);
return ERR_PTR(-ENOENT);
}
- *seqp = 0;
- *inodep = parent->d_inode;
return parent;
in_root:
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-EXDEV);
- dget(nd->path.dentry);
- return NULL;
+ return dget(nd->path.dentry);
}
static const char *handle_dots(struct nameidata *nd, int type)
if (type == LAST_DOTDOT) {
const char *error = NULL;
struct dentry *parent;
- struct inode *inode;
- unsigned seq;
if (!nd->root.mnt) {
error = ERR_PTR(set_root(nd));
return error;
}
if (nd->flags & LOOKUP_RCU)
- parent = follow_dotdot_rcu(nd, &inode, &seq);
+ parent = follow_dotdot_rcu(nd);
else
- parent = follow_dotdot(nd, &inode, &seq);
+ parent = follow_dotdot(nd);
if (IS_ERR(parent))
return ERR_CAST(parent);
- if (unlikely(!parent))
- error = step_into(nd, WALK_NOFOLLOW,
- nd->path.dentry, nd->inode, nd->seq);
- else
- error = step_into(nd, WALK_NOFOLLOW,
- parent, inode, seq);
+ error = step_into(nd, WALK_NOFOLLOW, parent);
if (unlikely(error))
return error;
* some fallback).
*/
smp_rmb();
- if (unlikely(__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq)))
+ if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))
return ERR_PTR(-EAGAIN);
- if (unlikely(__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq)))
+ if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))
return ERR_PTR(-EAGAIN);
}
}
static const char *walk_component(struct nameidata *nd, int flags)
{
struct dentry *dentry;
- struct inode *inode;
- unsigned seq;
/*
* "." and ".." are special - ".." especially so because it has
* to be able to know about the current root directory and
put_link(nd);
return handle_dots(nd, nd->last_type);
}
- dentry = lookup_fast(nd, &inode, &seq);
+ dentry = lookup_fast(nd);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (unlikely(!dentry)) {
}
if (!(flags & WALK_MORE) && nd->depth)
put_link(nd);
- return step_into(nd, flags, dentry, inode, seq);
+ return step_into(nd, flags, dentry);
}
/*
flags &= ~LOOKUP_RCU;
if (flags & LOOKUP_RCU)
rcu_read_lock();
+ else
+ nd->seq = nd->next_seq = 0;
nd->flags = flags;
nd->state |= ND_JUMPED;
{
if (!(nd->flags & LOOKUP_RCU))
dget(nd->path.dentry);
- return PTR_ERR(step_into(nd, WALK_NOFOLLOW,
- nd->path.dentry, nd->inode, nd->seq));
+ nd->next_seq = nd->seq;
+ return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
struct dentry *dir = nd->path.dentry;
int open_flag = op->open_flag;
bool got_write = false;
- unsigned seq;
- struct inode *inode;
struct dentry *dentry;
const char *res;
if (nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
/* we _can_ be in RCU mode here */
- dentry = lookup_fast(nd, &inode, &seq);
+ dentry = lookup_fast(nd);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (likely(dentry))
finish_lookup:
if (nd->depth)
put_link(nd);
- res = step_into(nd, WALK_TRAILING, dentry, inode, seq);
+ res = step_into(nd, WALK_TRAILING, dentry);
if (unlikely(res))
nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
return res;
projects / linux-2.6-microblaze.git / blobdiff