* [PATCH 01/12] vfs: pull ext4's double-i_mutex-locking into common code
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
@ 2012-10-16 22:01 ` J. Bruce Fields
2012-10-16 22:01 ` [PATCH 03/12] vfs: rename I_MUTEX_QUOTA now that it's not used for quotas J. Bruce Fields
` (4 subsequent siblings)
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields,
Theodore Ts'o, Andreas Dilger
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
We want to do this elsewhere as well.
Cc: "Theodore Ts'o" <tytso-3s7WtUTddSA@public.gmane.org>
Cc: Andreas Dilger <adilger.kernel-m1MBpc4rdrD3fQ9qLvQP4Q@public.gmane.org>
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
fs/ext4/move_extent.c | 40 ++--------------------------------------
fs/inode.c | 29 +++++++++++++++++++++++++++++
include/linux/fs.h | 3 +++
3 files changed, 34 insertions(+), 38 deletions(-)
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 292daee..ee02681 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -1197,42 +1197,6 @@ mext_check_arguments(struct inode *orig_inode,
}
/**
- * mext_inode_double_lock - Lock i_mutex on both @inode1 and @inode2
- *
- * @inode1: the inode structure
- * @inode2: the inode structure
- *
- * Lock two inodes' i_mutex
- */
-static void
-mext_inode_double_lock(struct inode *inode1, struct inode *inode2)
-{
- BUG_ON(inode1 == inode2);
- if (inode1 < inode2) {
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
- } else {
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
- }
-}
-
-/**
- * mext_inode_double_unlock - Release i_mutex on both @inode1 and @inode2
- *
- * @inode1: the inode that is released first
- * @inode2: the inode that is released second
- *
- */
-
-static void
-mext_inode_double_unlock(struct inode *inode1, struct inode *inode2)
-{
- mutex_unlock(&inode1->i_mutex);
- mutex_unlock(&inode2->i_mutex);
-}
-
-/**
* ext4_move_extents - Exchange the specified range of a file
*
* @o_filp: file structure of the original file
@@ -1321,7 +1285,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp,
return -EINVAL;
}
/* Protect orig and donor inodes against a truncate */
- mext_inode_double_lock(orig_inode, donor_inode);
+ lock_two_nondirectories(orig_inode, donor_inode);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(orig_inode);
@@ -1529,7 +1493,7 @@ out:
double_up_write_data_sem(orig_inode, donor_inode);
ext4_inode_resume_unlocked_dio(orig_inode);
ext4_inode_resume_unlocked_dio(donor_inode);
- mext_inode_double_unlock(orig_inode, donor_inode);
+ unlock_two_nondirectories(orig_inode, donor_inode);
return ret;
}
diff --git a/fs/inode.c b/fs/inode.c
index b03c719..9d5b6bd 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -969,6 +969,35 @@ void unlock_new_inode(struct inode *inode)
EXPORT_SYMBOL(unlock_new_inode);
/**
+ * lock_two_nondirectories - take two i_mutexes on non-directory objects
+ * @inode1: first inode to lock
+ * @inode2: second inode to lock
+ */
+void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+ if (inode1 < inode2) {
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+ } else {
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+ }
+}
+EXPORT_SYMBOL(lock_two_nondirectories);
+
+/**
+ * unlock_two_nondirectories - release locks from lock_two_nondirectories()
+ * @inode1: first inode to unlock
+ * @inode2: second inode to unlock
+ */
+void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2)
+{
+ mutex_unlock(&inode1->i_mutex);
+ mutex_unlock(&inode2->i_mutex);
+}
+EXPORT_SYMBOL(unlock_two_nondirectories);
+
+/**
* iget5_locked - obtain an inode from a mounted file system
* @sb: super block of file system
* @hashval: hash value (usually inode number) to get
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 001c7cf..83da035 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -568,6 +568,9 @@ enum inode_i_mutex_lock_class
I_MUTEX_QUOTA
};
+void lock_two_nondirectories(struct inode *, struct inode*);
+void unlock_two_nondirectories(struct inode *, struct inode*);
+
/*
* NOTE: in a 32bit arch with a preemptable kernel and
* an UP compile the i_size_read/write must be atomic
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 03/12] vfs: rename I_MUTEX_QUOTA now that it's not used for quotas
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-10-16 22:01 ` [PATCH 01/12] vfs: pull ext4's double-i_mutex-locking into common code J. Bruce Fields
@ 2012-10-16 22:01 ` J. Bruce Fields
2012-10-16 22:01 ` [PATCH 04/12] vfs: take i_mutex on renamed file J. Bruce Fields
` (3 subsequent siblings)
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
I_MUTEX_QUOTA is now just being used whenever we want to lock two
non-directories. So the name isn't right. I_MUTEX_NONDIR2 isn't
especially elegant but it's the best I could think of.
Also fix some outdated documentation.
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
fs/inode.c | 4 ++--
include/linux/fs.h | 9 ++++++---
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/fs/inode.c b/fs/inode.c
index 413b043..2cffc18 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -977,10 +977,10 @@ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2)
{
if (inode1 < inode2) {
mutex_lock(&inode1->i_mutex);
- mutex_lock_nested(&inode2->i_mutex, I_MUTEX_QUOTA);
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_NONDIR2);
} else {
mutex_lock(&inode2->i_mutex);
- mutex_lock_nested(&inode1->i_mutex, I_MUTEX_QUOTA);
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_NONDIR2);
}
}
EXPORT_SYMBOL(lock_two_nondirectories);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 83da035..7ffc865 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -554,10 +554,13 @@ static inline int inode_unhashed(struct inode *inode)
* 0: the object of the current VFS operation
* 1: parent
* 2: child/target
- * 3: quota file
+ * 3: xattr
+ * 4: second non-directory
+ * The last is for certain operations (such as rename) which lock two
+ * non-directories at once.
*
* The locking order between these classes is
- * parent -> child -> normal -> xattr -> quota
+ * parent -> child -> normal -> xattr -> second non-directory
*/
enum inode_i_mutex_lock_class
{
@@ -565,7 +568,7 @@ enum inode_i_mutex_lock_class
I_MUTEX_PARENT,
I_MUTEX_CHILD,
I_MUTEX_XATTR,
- I_MUTEX_QUOTA
+ I_MUTEX_NONDIR2
};
void lock_two_nondirectories(struct inode *, struct inode*);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 04/12] vfs: take i_mutex on renamed file
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2012-10-16 22:01 ` [PATCH 01/12] vfs: pull ext4's double-i_mutex-locking into common code J. Bruce Fields
2012-10-16 22:01 ` [PATCH 03/12] vfs: rename I_MUTEX_QUOTA now that it's not used for quotas J. Bruce Fields
@ 2012-10-16 22:01 ` J. Bruce Fields
2012-10-16 22:01 ` [PATCH 08/12] locks: break delegations on unlink J. Bruce Fields
` (2 subsequent siblings)
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
A read delegation is used by NFSv4 as a guarantee that a client can
perform local read opens without informing the server.
The open operation takes the last component of the pathname as an
argument, thus is also a lookup operation, and giving the client the
above guarantee means informing the client before we allow anything that
would change the set of names pointing to the inode.
Therefore, we need to break delegations on rename, link, and unlink.
We also need to prevent new delegations from being acquired while one of
these operations is in progress.
We could add some completely new locking for that purpose, but it's
simpler to use the i_mutex, since that's already taken by all the
operations we care about.
The single exception is rename. So, modify rename to take the i_mutex
on the file that is being renamed.
Also fix up lockdep and Documentation/filesystems/directory-locking to
reflect the change.
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
Documentation/filesystems/directory-locking | 31 +++++++++++++++++++--------
fs/namei.c | 12 ++++++++---
2 files changed, 31 insertions(+), 12 deletions(-)
diff --git a/Documentation/filesystems/directory-locking b/Documentation/filesystems/directory-locking
index ff7b611..09bbf9a 100644
--- a/Documentation/filesystems/directory-locking
+++ b/Documentation/filesystems/directory-locking
@@ -2,6 +2,10 @@
kinds of locks - per-inode (->i_mutex) and per-filesystem
(->s_vfs_rename_mutex).
+ When taking the i_mutex on multiple non-directory objects, we
+always acquire the locks in order by increasing address. We'll call
+that "inode pointer" order in the following.
+
For our purposes all operations fall in 5 classes:
1) read access. Locking rules: caller locks directory we are accessing.
@@ -12,8 +16,9 @@ kinds of locks - per-inode (->i_mutex) and per-filesystem
locks victim and calls the method.
4) rename() that is _not_ cross-directory. Locking rules: caller locks
-the parent, finds source and target, if target already exists - locks it
-and then calls the method.
+the parent and finds source and target. If target already exists, lock
+it. If source is a non-directory, lock it. If that means we need to
+lock both, lock them in inode pointer order.
5) link creation. Locking rules:
* lock parent
@@ -30,7 +35,9 @@ rules:
fail with -ENOTEMPTY
* if new parent is equal to or is a descendent of source
fail with -ELOOP
- * if target exists - lock it.
+ * If target exists, lock it. If source is a non-directory, lock
+ it. In case that means we need to lock both source and target,
+ do so in inode pointer order.
* call the method.
@@ -56,9 +63,11 @@ objects - A < B iff A is an ancestor of B.
renames will be blocked on filesystem lock and we don't start changing
the order until we had acquired all locks).
-(3) any operation holds at most one lock on non-directory object and
- that lock is acquired after all other locks. (Proof: see descriptions
- of operations).
+(3) locks on non-directory objects are acquired only after locks on
+ directory objects, and are acquired in inode pointer order.
+ (Proof: all operations but renames take lock on at most one
+ non-directory object, except renames, which take locks on source and
+ target in inode pointer order in the case they are not directories.)
Now consider the minimal deadlock. Each process is blocked on
attempt to acquire some lock and already holds at least one lock. Let's
@@ -66,9 +75,13 @@ consider the set of contended locks. First of all, filesystem lock is
not contended, since any process blocked on it is not holding any locks.
Thus all processes are blocked on ->i_mutex.
- Non-directory objects are not contended due to (3). Thus link
-creation can't be a part of deadlock - it can't be blocked on source
-and it means that it doesn't hold any locks.
+ By (3), any process holding a non-directory lock can only be
+waiting on another non-directory lock with a larger address. Therefore
+the process holding the "largest" such lock can always make progress, and
+non-directory objects are not included in the set of contended locks.
+
+ Thus link creation can't be a part of deadlock - it can't be
+blocked on source and it means that it doesn't hold any locks.
Any contended object is either held by cross-directory rename or
has a child that is also contended. Indeed, suppose that it is held by
diff --git a/fs/namei.c b/fs/namei.c
index d1895f3..921a1ee 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3650,7 +3650,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
* That's where 4.4 screws up. Current fix: serialization on
* sb->s_vfs_rename_mutex. We might be more accurate, but that's another
* story.
- * c) we have to lock _three_ objects - parents and victim (if it exists).
+ * c) we have to lock _four_ objects - parents and victim (if it exists),
+ * and source (if it is not a directory).
* And that - after we got ->i_mutex on parents (until then we don't know
* whether the target exists). Solution: try to be smart with locking
* order for inodes. We rely on the fact that tree topology may change
@@ -3726,6 +3727,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
struct inode *target = new_dentry->d_inode;
+ struct inode *source = old_dentry->d_inode;
int error;
error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
@@ -3734,7 +3736,9 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
dget(new_dentry);
if (target)
- mutex_lock(&target->i_mutex);
+ lock_two_nondirectories(source, target);
+ else
+ mutex_lock(&source->i_mutex);
error = -EBUSY;
if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
@@ -3750,7 +3754,9 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
d_move(old_dentry, new_dentry);
out:
if (target)
- mutex_unlock(&target->i_mutex);
+ unlock_two_nondirectories(source, target);
+ else
+ mutex_unlock(&source->i_mutex);
dput(new_dentry);
return error;
}
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 08/12] locks: break delegations on unlink
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
` (2 preceding siblings ...)
2012-10-16 22:01 ` [PATCH 04/12] vfs: take i_mutex on renamed file J. Bruce Fields
@ 2012-10-16 22:01 ` J. Bruce Fields
2012-10-16 22:01 ` [PATCH 10/12] locks: break delegations on rename J. Bruce Fields
2012-10-16 22:01 ` [PATCH 11/12] locks: break delegations on link J. Bruce Fields
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields,
David Howells, Tyler Hicks, Dustin Kirkland
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
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-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Tyler Hicks <tyhicks-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
Cc: Dustin Kirkland <dustin.kirkland-Bv2LyzZ6GzxBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
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-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 10/12] locks: break delegations on rename
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
` (3 preceding siblings ...)
2012-10-16 22:01 ` [PATCH 08/12] locks: break delegations on unlink J. Bruce Fields
@ 2012-10-16 22:01 ` J. Bruce Fields
2012-10-16 22:01 ` [PATCH 11/12] locks: break delegations on link J. Bruce Fields
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields,
David Howells
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: David Howells <dhowells-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
fs/cachefiles/namei.c | 2 +-
fs/namei.c | 30 ++++++++++++++++++++++++------
fs/nfsd/vfs.c | 2 +-
include/linux/fs.h | 2 +-
4 files changed, 27 insertions(+), 9 deletions(-)
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 10cf5c6..ef23d2a 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -397,7 +397,7 @@ try_again:
cachefiles_io_error(cache, "Rename security error %d", ret);
} else {
ret = vfs_rename(dir->d_inode, rep,
- cache->graveyard->d_inode, grave);
+ cache->graveyard->d_inode, grave, NULL);
if (ret != 0 && ret != -ENOMEM)
cachefiles_io_error(cache,
"Rename failed with error %d", ret);
diff --git a/fs/namei.c b/fs/namei.c
index 66228a8..4d0982b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3735,7 +3735,8 @@ out:
}
static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ struct inode **delegated_inode)
{
struct inode *target = new_dentry->d_inode;
struct inode *source = old_dentry->d_inode;
@@ -3755,6 +3756,14 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
goto out;
+ error = try_break_deleg(source, delegated_inode);
+ if (error)
+ goto out;
+ if (target) {
+ error = try_break_deleg(target, delegated_inode);
+ if (error)
+ goto out;
+ }
error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
if (error)
goto out;
@@ -3773,7 +3782,8 @@ out:
}
int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ struct inode **delegated_inode)
{
int error;
int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
@@ -3801,7 +3811,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (is_dir)
error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
else
- error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
+ error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry,delegated_inode);
if (!error)
fsnotify_move(old_dir, new_dir, old_name, is_dir,
new_dentry->d_inode, old_dentry);
@@ -3817,8 +3827,9 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
struct dentry *old_dentry, *new_dentry;
struct dentry *trap;
struct nameidata oldnd, newnd;
- struct filename *from;
- struct filename *to;
+ struct inode *delegated_inode = NULL;
+ char *from;
+ char *to;
int error;
from = user_path_parent(olddfd, oldname, &oldnd);
@@ -3854,6 +3865,7 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
newnd.flags &= ~LOOKUP_PARENT;
newnd.flags |= LOOKUP_RENAME_TARGET;
+retry_deleg:
trap = lock_rename(new_dir, old_dir);
old_dentry = lookup_hash(&oldnd);
@@ -3890,13 +3902,19 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
if (error)
goto exit5;
error = vfs_rename(old_dir->d_inode, old_dentry,
- new_dir->d_inode, new_dentry);
+ new_dir->d_inode, new_dentry,
+ &delegated_inode);
exit5:
dput(new_dentry);
exit4:
dput(old_dentry);
exit3:
unlock_rename(new_dir, old_dir);
+ if (delegated_inode) {
+ error = break_deleg_wait(&delegated_inode);
+ if (!error)
+ goto retry_deleg;
+ }
mnt_drop_write(oldnd.path.mnt);
exit2:
path_put(&newnd.path);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c51f4c9..903fae1 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1820,7 +1820,7 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
if (host_err)
goto out_dput_new;
}
- host_err = vfs_rename(fdir, odentry, tdir, ndentry);
+ host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
if (!host_err) {
host_err = commit_metadata(tfhp);
if (!host_err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0e761e7..84183db 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1400,7 +1400,7 @@ 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 *, struct inode **);
-extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
+extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **);
/*
* VFS dentry helper functions.
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread* [PATCH 11/12] locks: break delegations on link
[not found] ` <1350424897-26894-1-git-send-email-bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
` (4 preceding siblings ...)
2012-10-16 22:01 ` [PATCH 10/12] locks: break delegations on rename J. Bruce Fields
@ 2012-10-16 22:01 ` J. Bruce Fields
5 siblings, 0 replies; 13+ messages in thread
From: J. Bruce Fields @ 2012-10-16 22:01 UTC (permalink / raw)
To: Al Viro
Cc: linux-nfs-u79uwXL29TY76Z2rM5mHXA,
linux-fsdevel-u79uwXL29TY76Z2rM5mHXA, J. Bruce Fields,
Tyler Hicks, Dustin Kirkland
From: "J. Bruce Fields" <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Cc: Tyler Hicks <tyhicks-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
Cc: Dustin Kirkland <dustin.kirkland-Bv2LyzZ6GzxBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: J. Bruce Fields <bfields-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
fs/ecryptfs/inode.c | 2 +-
fs/namei.c | 18 ++++++++++++++----
fs/nfsd/vfs.c | 2 +-
include/linux/fs.h | 2 +-
4 files changed, 17 insertions(+), 7 deletions(-)
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 30d7e59..a3b2b08 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -475,7 +475,7 @@ static int ecryptfs_link(struct dentry *old_dentry, struct inode *dir,
dget(lower_new_dentry);
lower_dir_dentry = lock_parent(lower_new_dentry);
rc = vfs_link(lower_old_dentry, lower_dir_dentry->d_inode,
- lower_new_dentry);
+ lower_new_dentry, NULL);
if (rc || !lower_new_dentry->d_inode)
goto out_lock;
rc = ecryptfs_interpose(lower_new_dentry, new_dentry, dir->i_sb);
diff --git a/fs/namei.c b/fs/namei.c
index 4d0982b..85d77c1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3543,7 +3543,7 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
return sys_symlinkat(oldname, AT_FDCWD, newname);
}
-int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
+int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode)
{
struct inode *inode = old_dentry->d_inode;
unsigned max_links = dir->i_sb->s_max_links;
@@ -3579,8 +3579,11 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
error = -ENOENT;
else if (max_links && inode->i_nlink >= max_links)
error = -EMLINK;
- else
- error = dir->i_op->link(old_dentry, dir, new_dentry);
+ else {
+ error = try_break_deleg(inode, delegated_inode);
+ if (!error)
+ error = dir->i_op->link(old_dentry, dir, new_dentry);
+ }
mutex_unlock(&inode->i_mutex);
if (!error)
fsnotify_link(dir, inode, new_dentry);
@@ -3601,6 +3604,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
{
struct dentry *new_dentry;
struct path old_path, new_path;
+ struct inode *delegated_inode = NULL;
int how = 0;
int error;
@@ -3624,6 +3628,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
if (error)
return error;
+retry_deleg:
new_dentry = user_path_create(newdfd, newname, &new_path, 0);
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
@@ -3638,9 +3643,14 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
error = security_path_link(old_path.dentry, &new_path, new_dentry);
if (error)
goto out_dput;
- error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
+ error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry, &delegated_inode);
out_dput:
done_path_create(&new_path, new_dentry);
+ if (delegated_inode) {
+ error = break_deleg_wait(&delegated_inode);
+ if (!error)
+ goto retry_deleg;
+ }
out:
path_put(&old_path);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 903fae1..5e36961 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1717,7 +1717,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
err = nfserrno(host_err);
goto out_dput;
}
- host_err = vfs_link(dold, dirp, dnew);
+ host_err = vfs_link(dold, dirp, dnew, NULL);
if (!host_err) {
err = nfserrno(commit_metadata(ffhp));
if (!err)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 84183db..f12a380 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1397,7 +1397,7 @@ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool);
extern int vfs_mkdir(struct inode *, struct dentry *, umode_t);
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_link(struct dentry *, struct inode *, struct dentry *, struct inode **);
extern int vfs_rmdir(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 *, struct inode **);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 13+ messages in thread