[PATCH 2/3] fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks

[Benjamin Coddington]

Since commit c69899a17ca4 "NFSv4: Update of VFS byte range lock must be
atomic with the stateid update", NFSv4 has been inserting locks in rpciod
worker context.  The result is that the file_lock's fl_nspid is the
kworker's pid instead of the original userspace pid.

The fl_nspid is only used to represent the namespaced virtual pid number
when displaying locks or returning from F_GETLK.  There's no reason to set
it for every inserted lock, since we can usually just look it up from
fl_pid.  So, instead of looking up and holding struct pid for every lock,
let's just look up the virtual pid number from fl_pid when it is needed.
That means we can remove fl_nspid entirely.

The translaton and presentation of fl_pid should handle the following four
cases:

1 - F_GETLK on a remote file with a remote lock:
In this case, the filesystem should determine the l_pid to return here.
Filesystems should indicate that the fl_pid represents a non-local pid
value that should not be translated by returning an fl_pid <= 0.

2 - F_GETLK on a local file with a remote lock:
This should be the l_pid of the lock manager process, and translated.

3 - F_GETLK on a remote file with a local lock, and
4 - F_GETLK on a local file with a local lock:
These should be the translated l_pid of the local locking process.

Fuse was already doing the correct thing by translating the pid into the
caller's namespace.  With this change we must update fuse to translate to
init's pid namespace, so that the locks API can then translate from init's
pid namespace into the pid namespace of the caller.

Signed-off-by: Benjamin Coddington 
---
 fs/fuse/file.c |  6 +++---
 fs/locks.c | 62 --
 include/linux/fs.h |  2 +-
 3 files changed, 41 insertions(+), 29 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3ee4fdc3da9e..7cd692f51d1d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2101,11 +2101,11 @@ static int convert_fuse_file_lock(struct fuse_conn *fc,
fl->fl_end = ffl->end;
 
/*
-* Convert pid into the caller's pid namespace. If the pid
-* does not map into the namespace fl_pid will get set to 0.
+* Convert pid into init's pid namespace.  The locks API will
+* translate it into the caller's pid namespace.
 */
rcu_read_lock();
-   fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+   fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), 
_pid_ns);
rcu_read_unlock();
break;
 
diff --git a/fs/locks.c b/fs/locks.c
index d7daa6c8932f..6d0949880ebd 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,6 +137,7 @@
 #define IS_FLOCK(fl)   (fl->fl_flags & FL_FLOCK)
 #define IS_LEASE(fl)   (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)  (fl->fl_flags & FL_OFDLCK)
+#define IS_REMOTELCK(fl)   (fl->fl_pid <= 0)
 
 static inline bool is_remote_lock(struct file *filp)
 {
@@ -733,7 +734,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 static void
 locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
 {
-   fl->fl_nspid = get_pid(task_tgid(current));
list_add_tail(>fl_list, before);
locks_insert_global_locks(fl);
 }
@@ -743,10 +743,6 @@ locks_unlink_lock_ctx(struct file_lock *fl)
 {
locks_delete_global_locks(fl);
list_del_init(>fl_list);
-   if (fl->fl_nspid) {
-   put_pid(fl->fl_nspid);
-   fl->fl_nspid = NULL;
-   }
locks_wake_up_blocks(fl);
 }
 
@@ -823,8 +819,6 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
list_for_each_entry(cfl, >flc_posix, fl_list) {
if (posix_locks_conflict(fl, cfl)) {
locks_copy_conflock(fl, cfl);
-   if (cfl->fl_nspid)
-   fl->fl_pid = pid_vnr(cfl->fl_nspid);
goto out;
}
}
@@ -2048,9 +2042,33 @@ int vfs_test_lock(struct file *filp, struct file_lock 
*fl)
 }
 EXPORT_SYMBOL_GPL(vfs_test_lock);
 
+/**
+ * locks_translate_pid - translate a file_lock's fl_pid number into a namespace
+ * @fl: The file_lock who's fl_pid should be translated
+ * @ns: The namespace into which the pid should be translated
+ *
+ * Used to tranlate a fl_pid into a namespace virtual pid number
+ */
+static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace 
*ns)
+{
+   pid_t vnr;
+   struct pid *pid;
+
+   if (IS_OFDLCK(fl))
+   return -1;
+   if (IS_REMOTELCK(fl))
+   return fl->fl_pid;
+
+   rcu_read_lock();
+   pid = find_pid_ns(fl->fl_pid, _pid_ns);
+   vnr = pid_nr_ns(pid, ns);
+   rcu_read_unlock();
+   return vnr;
+}
+
 static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)

[PATCH 2/3] fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks

[Benjamin Coddington]

Since commit c69899a17ca4 "NFSv4: Update of VFS byte range lock must be
atomic with the stateid update", NFSv4 has been inserting locks in rpciod
worker context.  The result is that the file_lock's fl_nspid is the
kworker's pid instead of the original userspace pid.

The fl_nspid is only used to represent the namespaced virtual pid number
when displaying locks or returning from F_GETLK.  There's no reason to set
it for every inserted lock, since we can usually just look it up from
fl_pid.  So, instead of looking up and holding struct pid for every lock,
let's just look up the virtual pid number from fl_pid when it is needed.
That means we can remove fl_nspid entirely.

The translaton and presentation of fl_pid should handle the following four
cases:

1 - F_GETLK on a remote file with a remote lock:
In this case, the filesystem should determine the l_pid to return here.
Filesystems should indicate that the fl_pid represents a non-local pid
value that should not be translated by returning an fl_pid <= 0.

2 - F_GETLK on a local file with a remote lock:
This should be the l_pid of the lock manager process, and translated.

3 - F_GETLK on a remote file with a local lock, and
4 - F_GETLK on a local file with a local lock:
These should be the translated l_pid of the local locking process.

Fuse was already doing the correct thing by translating the pid into the
caller's namespace.  With this change we must update fuse to translate to
init's pid namespace, so that the locks API can then translate from init's
pid namespace into the pid namespace of the caller.

Signed-off-by: Benjamin Coddington 
---
 fs/fuse/file.c |  6 +++---
 fs/locks.c | 62 --
 include/linux/fs.h |  2 +-
 3 files changed, 41 insertions(+), 29 deletions(-)

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 3ee4fdc3da9e..7cd692f51d1d 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2101,11 +2101,11 @@ static int convert_fuse_file_lock(struct fuse_conn *fc,
fl->fl_end = ffl->end;
 
/*
-* Convert pid into the caller's pid namespace. If the pid
-* does not map into the namespace fl_pid will get set to 0.
+* Convert pid into init's pid namespace.  The locks API will
+* translate it into the caller's pid namespace.
 */
rcu_read_lock();
-   fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+   fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), 
_pid_ns);
rcu_read_unlock();
break;
 
diff --git a/fs/locks.c b/fs/locks.c
index d7daa6c8932f..6d0949880ebd 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -137,6 +137,7 @@
 #define IS_FLOCK(fl)   (fl->fl_flags & FL_FLOCK)
 #define IS_LEASE(fl)   (fl->fl_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT))
 #define IS_OFDLCK(fl)  (fl->fl_flags & FL_OFDLCK)
+#define IS_REMOTELCK(fl)   (fl->fl_pid <= 0)
 
 static inline bool is_remote_lock(struct file *filp)
 {
@@ -733,7 +734,6 @@ static void locks_wake_up_blocks(struct file_lock *blocker)
 static void
 locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before)
 {
-   fl->fl_nspid = get_pid(task_tgid(current));
list_add_tail(>fl_list, before);
locks_insert_global_locks(fl);
 }
@@ -743,10 +743,6 @@ locks_unlink_lock_ctx(struct file_lock *fl)
 {
locks_delete_global_locks(fl);
list_del_init(>fl_list);
-   if (fl->fl_nspid) {
-   put_pid(fl->fl_nspid);
-   fl->fl_nspid = NULL;
-   }
locks_wake_up_blocks(fl);
 }
 
@@ -823,8 +819,6 @@ posix_test_lock(struct file *filp, struct file_lock *fl)
list_for_each_entry(cfl, >flc_posix, fl_list) {
if (posix_locks_conflict(fl, cfl)) {
locks_copy_conflock(fl, cfl);
-   if (cfl->fl_nspid)
-   fl->fl_pid = pid_vnr(cfl->fl_nspid);
goto out;
}
}
@@ -2048,9 +2042,33 @@ int vfs_test_lock(struct file *filp, struct file_lock 
*fl)
 }
 EXPORT_SYMBOL_GPL(vfs_test_lock);
 
+/**
+ * locks_translate_pid - translate a file_lock's fl_pid number into a namespace
+ * @fl: The file_lock who's fl_pid should be translated
+ * @ns: The namespace into which the pid should be translated
+ *
+ * Used to tranlate a fl_pid into a namespace virtual pid number
+ */
+static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace 
*ns)
+{
+   pid_t vnr;
+   struct pid *pid;
+
+   if (IS_OFDLCK(fl))
+   return -1;
+   if (IS_REMOTELCK(fl))
+   return fl->fl_pid;
+
+   rcu_read_lock();
+   pid = find_pid_ns(fl->fl_pid, _pid_ns);
+   vnr = pid_nr_ns(pid, ns);
+   rcu_read_unlock();
+   return vnr;
+}
+
 static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl)
 {
-