lookup_one_qstr_excl() is used for lookups prior to directory
modifications, whether create, unlink, rename, or whatever.
To prepare for allowing modification to happen in parallel, change
lookup_one_qstr_excl() to use d_alloc_parallel().
As a result, ->lookup is now only ever called with a d_in_lookup()
dentry. Consequently we can remove the d_in_lookup() check from
d_add_ci() which is only used in ->lookup.
If LOOKUP_EXCL or LOOKUP_RENAME_TARGET is passed, the caller must ensure
d_lookup_done() is called at an appropriate time, and must not assume
that it can test for positive or negative dentries without confirming
that the dentry is no longer d_in_lookup() - unless it is filesystem
code acting on itself and *knows* that ->lookup() always completes the
lookup (currently true for all filesystems other than NFS).
Signed-off-by: NeilBrown <n...@brown.name>
---
Documentation/filesystems/porting.rst | 14 +++++++++
fs/dcache.c | 16 +++-------
fs/namei.c | 45 +++++++++++++++++++++------
3 files changed, 53 insertions(+), 22 deletions(-)
diff --git a/Documentation/filesystems/porting.rst
b/Documentation/filesystems/porting.rst
index e4a326e8fa4c..c9210d3bd313 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1291,3 +1291,17 @@ parameters for the file system to set this state.
d_alloc_parallel() no longer requires a waitqueue_head. It uses one
from an internal table when needed.
+
+---
+
+** mandatory**
+
+All dentry_lookup* functions may return a d_in_lookup() dentry if passed
+"O_CREATE|O_EXCL" or "O_RENAME_TARGET". done_dentry_lookup() calls the
+necessary d_lookup_done(). If the caller *knows* which filesystem is
+being used, it may know that this is not possible. Otherwise it must be
+careful testing if the dentry is positive or negative as the lookup may
+not have been performed yet.
+
+inode_operations.lookup() is now only ever called with a d_in_lookup()
+dentry.
diff --git a/fs/dcache.c b/fs/dcache.c
index 5473d906783e..7e3eb5576fa4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2136,18 +2136,10 @@ struct dentry *d_add_ci(struct dentry *dentry, struct
inode *inode,
iput(inode);
return found;
}
- if (d_in_lookup(dentry)) {
- found = d_alloc_parallel(dentry->d_parent, name);
- if (IS_ERR(found) || !d_in_lookup(found)) {
- iput(inode);
- return found;
- }
- } else {
- found = d_alloc(dentry->d_parent, name);
- if (!found) {
- iput(inode);
- return ERR_PTR(-ENOMEM);
- }
+ found = d_alloc_parallel(dentry->d_parent, name);
+ if (IS_ERR(found) || !d_in_lookup(found)) {
+ iput(inode);
+ return found;
}
res = d_splice_alias(inode, found);
if (res) {
diff --git a/fs/namei.c b/fs/namei.c
index 2c98672fdb6a..6a645f3a2b20 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1666,13 +1666,14 @@ static struct dentry *lookup_dcache(const struct qstr
*name,
}
/*
- * Parent directory has inode locked exclusive. This is one
- * and only case when ->lookup() gets called on non in-lookup
- * dentries - as the matter of fact, this only gets called
- * when directory is guaranteed to have no in-lookup children
- * at all.
- * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
- * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
+ * Parent directory has inode locked.
+ * d_lookup_done() must be called before the dentry is dput()
+ * if LOOKUP_EXCL or LOOKUP_RENAME_TARGET is set.
+ * If the dentry is not d_in_lookup():
+ * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
+ * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
+ * If it is d_in_lookup() then these conditions can only be checked by the
+ * file system when carrying out the intent (create or rename).
*/
struct dentry *lookup_one_qstr_excl(const struct qstr *name,
struct dentry *base, unsigned int flags)
@@ -1690,18 +1691,27 @@ struct dentry *lookup_one_qstr_excl(const struct qstr
*name,
if (unlikely(IS_DEADDIR(dir)))
return ERR_PTR(-ENOENT);
- dentry = d_alloc(base, name);
- if (unlikely(!dentry))
- return ERR_PTR(-ENOMEM);
+ dentry = d_alloc_parallel(base, name);
+ if (unlikely(IS_ERR(dentry)))
+ return dentry;
+ if (unlikely(!d_in_lookup(dentry)))
+ /* Raced with another thread which did the lookup */
+ goto found;
old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
+ d_lookup_done(dentry);
dput(dentry);
dentry = old;
}
found:
if (IS_ERR(dentry))
return dentry;
+ if (d_in_lookup(dentry))
+ /* We cannot check for errors - the caller will have to
+ * wait for any create-etc attempt to get relevant errors.
+ */
+ return dentry;
if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) {
dput(dentry);
return ERR_PTR(-ENOENT);
@@ -1767,6 +1777,8 @@ static int lookup_one_common(struct mnt_idmap *idmap,
* This function is for VFS-internal use only.
*
* Returns: the dentry, suitably locked, or an ERR_PTR().
+ * The dentry may be d_in_lookup() if LOOKUP_EXCL or LOOKUP_RENAME_TARGET
+ * is given, depending on the filesystem.
*/
static struct dentry *__dentry_lookup(struct qstr *last,
struct dentry *base,
@@ -1796,7 +1808,10 @@ static struct dentry *__dentry_lookup(struct qstr *last,
* The "necessary locks" are currently the inode lock on @base.
* The name @last is NOT expected to have the hash calculated.
* No permission checks are performed.
+ *
* Returns: the dentry, suitably locked, or an ERR_PTR().
+ * The dentry may be d_in_lookup() if LOOKUP_EXCL or LOOKUP_RENAME_TARGET
+ * is given, depending on the filesystem.
*/
struct dentry *dentry_lookup_noperm(struct qstr *last,
struct dentry *base,
@@ -1825,6 +1840,8 @@ EXPORT_SYMBOL(dentry_lookup_noperm);
* Permission checks are performed to ensure %MAY_EXEC access to @base.
*
* Returns: the dentry, suitably locked, or an ERR_PTR().
+ * The dentry may be d_in_lookup() if LOOKUP_EXCL or LOOKUP_RENAME_TARGET
+ * is given, depending on the filesystem.
*/
struct dentry *dentry_lookup(struct mnt_idmap *idmap,
struct qstr *last,
@@ -1852,7 +1869,10 @@ EXPORT_SYMBOL(dentry_lookup);
* If a fatal signal arrives, or is already pending, the operation is aborted.
* The name @last is NOT expected to already have the hash calculated.
* Permission checks are performed to ensure %MAY_EXEC access to @base.
+ *
* Returns: the dentry, suitably locked, or an ERR_PTR().
+ * The dentry may be d_in_lookup() if LOOKUP_EXCL or LOOKUP_RENAME_TARGET
+ * is given, depending on the filesystem.
*/
struct dentry *dentry_lookup_killable(struct mnt_idmap *idmap,
struct qstr *last,
@@ -1937,6 +1957,7 @@ void done_dentry_lookup(struct dentry *dentry)
{
if (!IS_ERR(dentry)) {
inode_unlock(dentry->d_parent->d_inode);
+ d_lookup_done(dentry);
dput(dentry);
}
}
@@ -3613,9 +3634,11 @@ __rename_lookup(struct renamedata *rd, int lookup_flags)
return 0;
out_unlock_3:
+ d_lookup_done(d2);
dput(d2);
d2 = ERR_PTR(err);
out_unlock_2:
+ d_lookup_done(d1);
dput(d1);
d1 = d2;
out_unlock_1:
@@ -3732,6 +3755,8 @@ EXPORT_SYMBOL(rename_lookup);
*/
void done_rename_lookup(struct renamedata *rd)
{
+ d_lookup_done(rd->old_dentry);
+ d_lookup_done(rd->new_dentry);
unlock_rename(rd->old_parent, rd->new_parent);
dput(rd->old_parent);
dput(rd->old_dentry);
--
2.50.0.107.gf914562f5916.dirty
