Merge tag 'locks-v4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux
Pull file locking updates from Jeff Layton:
"This pile just has a few file locking fixes from Ben Coddington. There
are a couple of cleanup patches + an attempt to bring sanity to the
l_pid value that is reported back to userland on an F_GETLK request.
After a few gyrations, he came up with a way for filesystems to
communicate to the VFS layer code whether the pid should be translated
according to the namespace or presented as-is to userland"
* tag 'locks-v4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/jlayton/linux:
locks: restore a warn for leaked locks on close
fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks
fs/locks: Use allocation rather than the stack in fcntl_getlk()
diff --git a/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c b/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
index d571b8b..cb826e9 100644
--- a/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
+++ b/drivers/staging/lustre/lustre/ldlm/ldlm_flock.c
@@ -596,7 +596,7 @@
default:
getlk->fl_type = F_UNLCK;
}
- getlk->fl_pid = (pid_t)lock->l_policy_data.l_flock.pid;
+ getlk->fl_pid = -(pid_t)lock->l_policy_data.l_flock.pid;
getlk->fl_start = (loff_t)lock->l_policy_data.l_flock.start;
getlk->fl_end = (loff_t)lock->l_policy_data.l_flock.end;
} else {
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3de3b4a8..43c242e 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -288,7 +288,7 @@
fl->fl_end = OFFSET_MAX;
else
fl->fl_end = glock.start + glock.length - 1;
- fl->fl_pid = glock.proc_id;
+ fl->fl_pid = -glock.proc_id;
}
kfree(glock.client_id);
return res;
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 64ae7447..8cd63e8 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -79,7 +79,7 @@
err = ceph_mdsc_do_request(mdsc, inode, req);
if (operation == CEPH_MDS_OP_GETFILELOCK) {
- fl->fl_pid = le64_to_cpu(req->r_reply_info.filelock_reply->pid);
+ fl->fl_pid = -le64_to_cpu(req->r_reply_info.filelock_reply->pid);
if (CEPH_LOCK_SHARED == req->r_reply_info.filelock_reply->type)
fl->fl_type = F_RDLCK;
else if (CEPH_LOCK_EXCL == req->r_reply_info.filelock_reply->type)
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 72a53bd..118a63e 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2522,7 +2522,7 @@
pLockData->fl_start = le64_to_cpu(parm_data->start);
pLockData->fl_end = pLockData->fl_start +
le64_to_cpu(parm_data->length) - 1;
- pLockData->fl_pid = le32_to_cpu(parm_data->pid);
+ pLockData->fl_pid = -le32_to_cpu(parm_data->pid);
}
}
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index d401425..e631b16 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -367,7 +367,7 @@
locks_init_lock(fl);
fl->fl_type = (op->info.ex) ? F_WRLCK : F_RDLCK;
fl->fl_flags = FL_POSIX;
- fl->fl_pid = op->info.pid;
+ fl->fl_pid = -op->info.pid;
fl->fl_start = op->info.start;
fl->fl_end = op->info.end;
rv = 0;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index ab60051..0273029 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2102,11 +2102,11 @@
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), &init_pid_ns);
rcu_read_unlock();
break;
diff --git a/fs/locks.c b/fs/locks.c
index afefeb4..1bd71c4 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)
{
@@ -270,6 +271,22 @@
}
}
+static void
+locks_check_ctx_file_list(struct file *filp, struct list_head *list,
+ char *list_type)
+{
+ struct file_lock *fl;
+ struct inode *inode = locks_inode(filp);
+
+ list_for_each_entry(fl, list, fl_list)
+ if (fl->fl_file == filp)
+ pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx "
+ " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n",
+ list_type, MAJOR(inode->i_sb->s_dev),
+ MINOR(inode->i_sb->s_dev), inode->i_ino,
+ fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid);
+}
+
void
locks_free_lock_context(struct inode *inode)
{
@@ -733,7 +750,6 @@
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->fl_list, before);
locks_insert_global_locks(fl);
}
@@ -743,10 +759,6 @@
{
locks_delete_global_locks(fl);
list_del_init(&fl->fl_list);
- if (fl->fl_nspid) {
- put_pid(fl->fl_nspid);
- fl->fl_nspid = NULL;
- }
locks_wake_up_blocks(fl);
}
@@ -823,8 +835,6 @@
list_for_each_entry(cfl, &ctx->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 +2058,33 @@
}
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, &init_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)
{
- flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid;
+ flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
#if BITS_PER_LONG == 32
/*
* Make sure we can represent the posix lock via
@@ -2072,7 +2106,7 @@
#if BITS_PER_LONG == 32
static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
{
- flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid;
+ flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current));
flock->l_start = fl->fl_start;
flock->l_len = fl->fl_end == OFFSET_MAX ? 0 :
fl->fl_end - fl->fl_start + 1;
@@ -2086,14 +2120,17 @@
*/
int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
{
- struct file_lock file_lock;
+ struct file_lock *fl;
int error;
+ fl = locks_alloc_lock();
+ if (fl == NULL)
+ return -ENOMEM;
error = -EINVAL;
if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK)
goto out;
- error = flock_to_posix_lock(filp, &file_lock, flock);
+ error = flock_to_posix_lock(filp, fl, flock);
if (error)
goto out;
@@ -2103,23 +2140,22 @@
goto out;
cmd = F_GETLK;
- file_lock.fl_flags |= FL_OFDLCK;
- file_lock.fl_owner = filp;
+ fl->fl_flags |= FL_OFDLCK;
+ fl->fl_owner = filp;
}
- error = vfs_test_lock(filp, &file_lock);
+ error = vfs_test_lock(filp, fl);
if (error)
goto out;
- flock->l_type = file_lock.fl_type;
- if (file_lock.fl_type != F_UNLCK) {
- error = posix_lock_to_flock(flock, &file_lock);
+ flock->l_type = fl->fl_type;
+ if (fl->fl_type != F_UNLCK) {
+ error = posix_lock_to_flock(flock, fl);
if (error)
- goto rel_priv;
+ goto out;
}
-rel_priv:
- locks_release_private(&file_lock);
out:
+ locks_free_lock(fl);
return error;
}
@@ -2298,14 +2334,18 @@
*/
int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
{
- struct file_lock file_lock;
+ struct file_lock *fl;
int error;
+ fl = locks_alloc_lock();
+ if (fl == NULL)
+ return -ENOMEM;
+
error = -EINVAL;
if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK)
goto out;
- error = flock64_to_posix_lock(filp, &file_lock, flock);
+ error = flock64_to_posix_lock(filp, fl, flock);
if (error)
goto out;
@@ -2315,20 +2355,20 @@
goto out;
cmd = F_GETLK64;
- file_lock.fl_flags |= FL_OFDLCK;
- file_lock.fl_owner = filp;
+ fl->fl_flags |= FL_OFDLCK;
+ fl->fl_owner = filp;
}
- error = vfs_test_lock(filp, &file_lock);
+ error = vfs_test_lock(filp, fl);
if (error)
goto out;
- flock->l_type = file_lock.fl_type;
- if (file_lock.fl_type != F_UNLCK)
- posix_lock_to_flock64(flock, &file_lock);
+ flock->l_type = fl->fl_type;
+ if (fl->fl_type != F_UNLCK)
+ posix_lock_to_flock64(flock, fl);
- locks_release_private(&file_lock);
out:
+ locks_free_lock(fl);
return error;
}
@@ -2525,6 +2565,12 @@
/* remove any leases */
locks_remove_lease(filp, ctx);
+
+ spin_lock(&ctx->flc_lock);
+ locks_check_ctx_file_list(filp, &ctx->flc_posix, "POSIX");
+ locks_check_ctx_file_list(filp, &ctx->flc_flock, "FLOCK");
+ locks_check_ctx_file_list(filp, &ctx->flc_lease, "LEASE");
+ spin_unlock(&ctx->flc_lock);
}
/**
@@ -2578,22 +2624,16 @@
{
struct inode *inode = NULL;
unsigned int fl_pid;
+ struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
- if (fl->fl_nspid) {
- struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info;
-
- /* Don't let fl_pid change based on who is reading the file */
- fl_pid = pid_nr_ns(fl->fl_nspid, proc_pidns);
-
- /*
- * If there isn't a fl_pid don't display who is waiting on
- * the lock if we are called from locks_show, or if we are
- * called from __show_fd_info - skip lock entirely
- */
- if (fl_pid == 0)
- return;
- } else
- fl_pid = fl->fl_pid;
+ fl_pid = locks_translate_pid(fl, proc_pidns);
+ /*
+ * If there isn't a fl_pid don't display who is waiting on
+ * the lock if we are called from locks_show, or if we are
+ * called from __show_fd_info - skip lock entirely
+ */
+ if (fl_pid == 0)
+ return;
if (fl->fl_file != NULL)
inode = locks_inode(fl->fl_file);
@@ -2668,7 +2708,7 @@
fl = hlist_entry(v, struct file_lock, fl_link);
- if (fl->fl_nspid && !pid_nr_ns(fl->fl_nspid, proc_pidns))
+ if (locks_translate_pid(fl, proc_pidns) == 0)
return 0;
lock_get_status(f, fl, iter->li_pos, "");
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 495b5c2..0a51a8b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1002,7 +1002,6 @@
unsigned char fl_type;
unsigned int fl_pid;
int fl_link_cpu; /* what cpu's list is this on? */
- struct pid *fl_nspid;
wait_queue_head_t fl_wait;
struct file *fl_file;
loff_t fl_start;