From: "J. Bruce Fields" <bfields@xxxxxxxxxx>
We need to break delegations on any operation that changes the set of
links pointing to an inode. Start with unlink.
Such operations also hold the i_mutex on a parent directory. Breaking a
delegation may require waiting for a timeout (by default 90 seconds) in
the case of a unresponsive NFS client. To avoid blocking all directory
operations, we therefore drop locks before waiting for the delegation.
The logic then looks like:
acquire locks
...
test for delegation; if found:
take reference on inode
release locks
wait for delegation break
drop reference on inode
retry
It is possible this could never terminate. (Even if we take precautions
to prevent another delegation being acquired on the same inode, we could
get a different inode on each retry.) But this seems very unlikely.
The initial test for a delegation happens after the lock on the target
inode is acquired, but the directory inode may have been acquired
further up the call stack. We therefore add a "struct inode **"
argument to any intervening functions, which we use to pass the inode
back up to the caller in the case it needs a delegation synchronously
broken.
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Tyler Hicks <tyhicks@xxxxxxxxxxxxx>
Cc: Dustin Kirkland <dustin.kirkland@xxxxxxxxxxx>
Signed-off-by: J. Bruce Fields <bfields@xxxxxxxxxx>
---
drivers/base/devtmpfs.c | 2 +-
fs/cachefiles/namei.c | 2 +-
fs/ecryptfs/inode.c | 2 +-
fs/namei.c | 23 ++++++++++++++++++++---
fs/nfsd/vfs.c | 2 +-
include/linux/fs.h | 2 +-
ipc/mqueue.c | 2 +-
7 files changed, 26 insertions(+), 9 deletions(-)
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 147d1a4..21099da 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -317,7 +317,7 @@ static int handle_remove(const char *nodename, struct device *dev)
mutex_lock(&dentry->d_inode->i_mutex);
notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
- err = vfs_unlink(parent.dentry->d_inode, dentry);
+ err = vfs_unlink(parent.dentry->d_inode, dentry, NULL);
if (!err || err == -ENOENT)
deleted = 1;
}
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index b0b5f7c..10cf5c6 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -295,7 +295,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache,
if (ret < 0) {
cachefiles_io_error(cache, "Unlink security error");
} else {
- ret = vfs_unlink(dir->d_inode, rep);
+ ret = vfs_unlink(dir->d_inode, rep, NULL);
if (preemptive)
cachefiles_mark_object_buried(cache, rep);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index cc7709e..30d7e59 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -153,7 +153,7 @@ static int ecryptfs_do_unlink(struct inode *dir, struct dentry *dentry,
dget(lower_dentry);
lower_dir_dentry = lock_parent(lower_dentry);
- rc = vfs_unlink(lower_dir_inode, lower_dentry);
+ rc = vfs_unlink(lower_dir_inode, lower_dentry, NULL);
if (rc) {
printk(KERN_ERR "Error in vfs_unlink; rc = [%d]\n", rc);
goto out_unlock;
diff --git a/fs/namei.c b/fs/namei.c
index 7dddff6..ed57a97 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3373,7 +3373,7 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
return do_rmdir(AT_FDCWD, pathname);
}
-int vfs_unlink(struct inode *dir, struct dentry *dentry)
+int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegated_inode)
{
struct inode *target = dentry->d_inode;
int error = may_delete(dir, dentry, 0);
@@ -3390,11 +3390,20 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry)
else {
error = security_inode_unlink(dir, dentry);
if (!error) {
+ error = break_deleg(target, O_WRONLY|O_NONBLOCK);
+ if (error) {
+ if (error == -EWOULDBLOCK && delegated_inode) {
+ *delegated_inode = target;
+ ihold(target);
+ }
+ goto out;
+ }
error = dir->i_op->unlink(dir, dentry);
if (!error)
dont_mount(dentry);
}
}
+out:
mutex_unlock(&target->i_mutex);
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
@@ -3419,6 +3428,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
struct dentry *dentry;
struct nameidata nd;
struct inode *inode = NULL;
+ struct inode *delegated_inode = NULL;
name = user_path_parent(dfd, pathname, &nd);
if (IS_ERR(name))
@@ -3432,7 +3442,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
error = mnt_want_write(nd.path.mnt);
if (error)
goto exit1;
-
+retry_deleg:
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
error = PTR_ERR(dentry);
@@ -3447,13 +3457,20 @@ static long do_unlinkat(int dfd, const char __user *pathname)
error = security_path_unlink(&nd.path, dentry);
if (error)
goto exit2;
- error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+ error = vfs_unlink(nd.path.dentry->d_inode, dentry, &delegated_inode);
exit2:
dput(dentry);
}
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
if (inode)
iput(inode); /* truncate the inode here */
+ if (delegated_inode) {
+ error = break_deleg(delegated_inode, O_WRONLY);
+ iput(delegated_inode);
+ delegated_inode = NULL;
+ if (!error)
+ goto retry_deleg;
+ }
mnt_drop_write(nd.path.mnt);
exit1:
path_put(&nd.path);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c120b48..c51f4c9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1893,7 +1893,7 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (host_err)
goto out_put;
if (type != S_IFDIR)
- host_err = vfs_unlink(dirp, rdentry);
+ host_err = vfs_unlink(dirp, rdentry, NULL);
else
host_err = vfs_rmdir(dirp, rdentry);
if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a05ac23..5ea5f5f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1399,7 +1399,7 @@ extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
-extern int vfs_unlink(struct inode *, struct dentry *);
+extern int vfs_unlink(struct inode *, struct dentry *, struct inode **);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
/*
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 71a3ca1..733cc8d 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -875,7 +875,7 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name)
err = -ENOENT;
} else {
ihold(inode);
- err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+ err = vfs_unlink(dentry->d_parent->d_inode, dentry, NULL);
}
dput(dentry);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
