Merge tag 'dlm-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm

Pull dlm updates from David Teigland:

 - Fix a couple races found with a new torture test

 - Improve errors when api functions are used incorrectly

 - Improve tracing for lock requests from user space

 - Fix use after free in recently added tracing cod.

 - Small internal code cleanups

* tag 'dlm-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm:
  fs: dlm: fix possible use after free if tracing
  fs: dlm: const void resource name parameter
  fs: dlm: LSFL_CB_DELAY only for kernel lockspaces
  fs: dlm: remove DLM_LSFL_FS from uapi
  fs: dlm: trace user space callbacks
  fs: dlm: change ls_clear_proc_locks to spinlock
  fs: dlm: remove dlm_del_ast prototype
  fs: dlm: handle rcom in else if branch
  fs: dlm: allow lockspaces have zero lvblen
  fs: dlm: fix invalid derefence of sb_lvbptr
  fs: dlm: handle -EINVAL as log_error()
  fs: dlm: use __func__ for function name
  fs: dlm: handle -EBUSY first in unlock validation
  fs: dlm: handle -EBUSY first in lock arg validation
  fs: dlm: fix race between test_bit() and queue_work()
  fs: dlm: fix race in lowcomms

drivers/md/md-cluster.c

@@ -876,8 +876,8 @@ static int join(struct mddev *mddev, int nodes)
 	memset(str, 0, 64);
 	sprintf(str, "%pU", mddev->uuid);
 	ret = dlm_new_lockspace(str, mddev->bitmap_info.cluster_name,
-				DLM_LSFL_FS, LVB_SIZE,
-				&md_ls_ops, mddev, &ops_rv, &cinfo->lockspace);
+				0, LVB_SIZE, &md_ls_ops, mddev,
+				&ops_rv, &cinfo->lockspace);
 	if (ret)
 		goto err;
 	wait_for_completion(&cinfo->completion);

fs/dlm/ast.c

@@ -200,13 +200,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
 	if (!prev_seq) {
 		kref_get(&lkb->lkb_ref);
 
+		mutex_lock(&ls->ls_cb_mutex);
 		if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
-			mutex_lock(&ls->ls_cb_mutex);
 			list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
-			mutex_unlock(&ls->ls_cb_mutex);
 		} else {
 			queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
 		}
+		mutex_unlock(&ls->ls_cb_mutex);
 	}
  out:
 	mutex_unlock(&lkb->lkb_cb_mutex);
@@ -288,10 +288,13 @@ void dlm_callback_stop(struct dlm_ls *ls)
 
 void dlm_callback_suspend(struct dlm_ls *ls)
 {
-	set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+	if (ls->ls_callback_wq) {
+		mutex_lock(&ls->ls_cb_mutex);
+		set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+		mutex_unlock(&ls->ls_cb_mutex);
 
-	if (ls->ls_callback_wq)
 		flush_workqueue(ls->ls_callback_wq);
+	}
 }
 
 #define MAX_CB_QUEUE 25
@@ -302,11 +305,11 @@ void dlm_callback_resume(struct dlm_ls *ls)
 	int count = 0, sum = 0;
 	bool empty;
 
-	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
-
 	if (!ls->ls_callback_wq)
 		return;
 
+	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
 more:
 	mutex_lock(&ls->ls_cb_mutex);
 	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {

fs/dlm/ast.h

@@ -11,7 +11,6 @@
 #ifndef __ASTD_DOT_H__
 #define __ASTD_DOT_H__
 
-void dlm_del_ast(struct dlm_lkb *lkb);
 int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
                          int status, uint32_t sbflags, uint64_t seq);
 int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,

fs/dlm/dlm_internal.h

@@ -661,7 +661,7 @@ struct dlm_ls {
 	spinlock_t		ls_recover_idr_lock;
 	wait_queue_head_t	ls_wait_general;
 	wait_queue_head_t	ls_recover_lock_wait;
-	struct mutex		ls_clear_proc_locks;
+	spinlock_t		ls_clear_proc_locks;
 
 	struct list_head	ls_root_list;	/* root resources */
 	struct rw_semaphore	ls_root_sem;	/* protect root_list */

fs/dlm/lock.h

@@ -36,7 +36,7 @@ static inline void dlm_adjust_timeouts(struct dlm_ls *ls) { }
 int dlm_master_lookup(struct dlm_ls *ls, int nodeid, char *name, int len,
 		      unsigned int flags, int *r_nodeid, int *result);
 
-int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+int dlm_search_rsb_tree(struct rb_root *tree, const void *name, int len,
 			struct dlm_rsb **r_ret);
 
 void dlm_recover_purge(struct dlm_ls *ls);

fs/dlm/lockspace.c

@@ -416,7 +416,7 @@ static int new_lockspace(const char *name, const char *cluster,
 	if (namelen > DLM_LOCKSPACE_LEN || namelen == 0)
 		return -EINVAL;
 
-	if (!lvblen || (lvblen % 8))
+	if (lvblen % 8)
 		return -EINVAL;
 
 	if (!try_module_get(THIS_MODULE))
@@ -584,7 +584,7 @@ static int new_lockspace(const char *name, const char *cluster,
 	atomic_set(&ls->ls_requestqueue_cnt, 0);
 	init_waitqueue_head(&ls->ls_requestqueue_wait);
 	mutex_init(&ls->ls_requestqueue_mutex);
-	mutex_init(&ls->ls_clear_proc_locks);
+	spin_lock_init(&ls->ls_clear_proc_locks);
 
 	/* Due backwards compatibility with 3.1 we need to use maximum
 	 * possible dlm message size to be sure the message will fit and
@@ -703,10 +703,11 @@ static int new_lockspace(const char *name, const char *cluster,
 	return error;
 }
 
-int dlm_new_lockspace(const char *name, const char *cluster,
-		      uint32_t flags, int lvblen,
-		      const struct dlm_lockspace_ops *ops, void *ops_arg,
-		      int *ops_result, dlm_lockspace_t **lockspace)
+static int __dlm_new_lockspace(const char *name, const char *cluster,
+			       uint32_t flags, int lvblen,
+			       const struct dlm_lockspace_ops *ops,
+			       void *ops_arg, int *ops_result,
+			       dlm_lockspace_t **lockspace)
 {
 	int error = 0;
 
@@ -732,6 +733,25 @@ int dlm_new_lockspace(const char *name, const char *cluster,
 	return error;
 }
 
+int dlm_new_lockspace(const char *name, const char *cluster, uint32_t flags,
+		      int lvblen, const struct dlm_lockspace_ops *ops,
+		      void *ops_arg, int *ops_result,
+		      dlm_lockspace_t **lockspace)
+{
+	return __dlm_new_lockspace(name, cluster, flags | DLM_LSFL_FS, lvblen,
+				   ops, ops_arg, ops_result, lockspace);
+}
+
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+			   uint32_t flags, int lvblen,
+			   const struct dlm_lockspace_ops *ops,
+			   void *ops_arg, int *ops_result,
+			   dlm_lockspace_t **lockspace)
+{
+	return __dlm_new_lockspace(name, cluster, flags, lvblen, ops,
+				   ops_arg, ops_result, lockspace);
+}
+
 static int lkb_idr_is_local(int id, void *p, void *data)
 {
 	struct dlm_lkb *lkb = p;

fs/dlm/lockspace.h

@@ -12,6 +12,14 @@
 #ifndef __LOCKSPACE_DOT_H__
 #define __LOCKSPACE_DOT_H__
 
+/* DLM_LSFL_FS
+ *   The lockspace user is in the kernel (i.e. filesystem).  Enables
+ *   direct bast/cast callbacks.
+ *
+ * internal lockspace flag - will be removed in future
+ */
+#define DLM_LSFL_FS	0x00000004
+
 int dlm_lockspace_init(void);
 void dlm_lockspace_exit(void);
 struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
@@ -20,6 +28,11 @@ struct dlm_ls *dlm_find_lockspace_device(int minor);
 void dlm_put_lockspace(struct dlm_ls *ls);
 void dlm_stop_lockspaces(void);
 void dlm_stop_lockspaces_check(void);
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+			   uint32_t flags, int lvblen,
+			   const struct dlm_lockspace_ops *ops,
+			   void *ops_arg, int *ops_result,
+			   dlm_lockspace_t **lockspace);
 
 #endif				/* __LOCKSPACE_DOT_H__ */
 

fs/dlm/lowcomms.c

@@ -1336,6 +1336,8 @@ struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
 		return NULL;
 	}
 
+	/* for dlm_lowcomms_commit_msg() */
+	kref_get(&msg->ref);
 	/* we assume if successful commit must called */
 	msg->idx = idx;
 	return msg;
@@ -1375,6 +1377,8 @@ void dlm_lowcomms_commit_msg(struct dlm_msg *msg)
 {
 	_dlm_lowcomms_commit_msg(msg);
 	srcu_read_unlock(&connections_srcu, msg->idx);
+	/* because dlm_lowcomms_new_msg() */
+	kref_put(&msg->ref, dlm_msg_release);
 }
 #endif
 

fs/dlm/user.c

@@ -16,6 +16,8 @@
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
 
+#include <trace/events/dlm.h>
+
 #include "dlm_internal.h"
 #include "lockspace.h"
 #include "lock.h"
@@ -184,7 +186,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
 		return;
 
 	ls = lkb->lkb_resource->res_ls;
-	mutex_lock(&ls->ls_clear_proc_locks);
+	spin_lock(&ls->ls_clear_proc_locks);
 
 	/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast
 	   can't be delivered.  For ORPHAN's, dlm_clear_proc_locks() freed
@@ -230,7 +232,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
 		spin_unlock(&proc->locks_spin);
 	}
  out:
-	mutex_unlock(&ls->ls_clear_proc_locks);
+	spin_unlock(&ls->ls_clear_proc_locks);
 }
 
 static int device_user_lock(struct dlm_user_proc *proc,
@@ -421,9 +423,9 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags,
-				  DLM_USER_LVB_LEN, NULL, NULL, NULL,
-				  &lockspace);
+	error = dlm_new_user_lockspace(params->name, dlm_config.ci_cluster_name,
+				       params->flags, DLM_USER_LVB_LEN, NULL,
+				       NULL, NULL, &lockspace);
 	if (error)
 		return error;
 
@@ -882,7 +884,9 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 		goto try_another;
 	}
 
-	if (cb.flags & DLM_CB_CAST) {
+	if (cb.flags & DLM_CB_BAST) {
+		trace_dlm_bast(lkb->lkb_resource->res_ls, lkb, cb.mode);
+	} else if (cb.flags & DLM_CB_CAST) {
 		new_mode = cb.mode;
 
 		if (!cb.sb_status && lkb->lkb_lksb->sb_lvbptr &&
@@ -891,6 +895,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 
 		lkb->lkb_lksb->sb_status = cb.sb_status;
 		lkb->lkb_lksb->sb_flags = cb.sb_flags;
+		trace_dlm_ast(lkb->lkb_resource->res_ls, lkb);
 	}
 
 	rv = copy_result_to_user(lkb->lkb_ua,

fs/gfs2/lock_dlm.c

@@ -1302,7 +1302,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
 	memcpy(cluster, table, strlen(table) - strlen(fsname));
 	fsname++;
 
-	flags = DLM_LSFL_FS | DLM_LSFL_NEWEXCL;
+	flags = DLM_LSFL_NEWEXCL;
 
 	/*
 	 * create/join lockspace

fs/ocfs2/stack_user.c

@@ -991,7 +991,7 @@ static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
 	lc->oc_type = NO_CONTROLD;
 
 	rc = dlm_new_lockspace(conn->cc_name, conn->cc_cluster_name,
-			       DLM_LSFL_FS | DLM_LSFL_NEWEXCL, DLM_LVB_LEN,
+			       DLM_LSFL_NEWEXCL, DLM_LVB_LEN,
 			       &ocfs2_ls_ops, conn, &ops_rv, &fsdlm);
 	if (rc) {
 		if (rc == -EEXIST || rc == -EPROTO)

include/linux/dlm.h

@@ -56,9 +56,6 @@ struct dlm_lockspace_ops {
  * DLM_LSFL_TIMEWARN
  *   The dlm should emit netlink messages if locks have been waiting
  *   for a configurable amount of time.  (Unused.)
- * DLM_LSFL_FS
- *   The lockspace user is in the kernel (i.e. filesystem).  Enables
- *   direct bast/cast callbacks.
  * DLM_LSFL_NEWEXCL
  *   dlm_new_lockspace() should return -EEXIST if the lockspace exists.
  *
@@ -134,7 +131,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
 	     int mode,
 	     struct dlm_lksb *lksb,
 	     uint32_t flags,
-	     void *name,
+	     const void *name,
 	     unsigned int namelen,
 	     uint32_t parent_lkid,
 	     void (*lockast) (void *astarg),

include/trace/events/dlm.h

@@ -49,7 +49,7 @@
 /* note: we begin tracing dlm_lock_start() only if ls and lkb are found */
 TRACE_EVENT(dlm_lock_start,
 
-	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, void *name,
+	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, const void *name,
 		 unsigned int namelen, int mode, __u32 flags),
 
 	TP_ARGS(ls, lkb, name, namelen, mode, flags),
@@ -91,10 +91,11 @@ TRACE_EVENT(dlm_lock_start,
 
 TRACE_EVENT(dlm_lock_end,
 
-	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, void *name,
-		 unsigned int namelen, int mode, __u32 flags, int error),
+	TP_PROTO(struct dlm_ls *ls, struct dlm_lkb *lkb, const void *name,
+		 unsigned int namelen, int mode, __u32 flags, int error,
+		 bool kernel_lock),
 
-	TP_ARGS(ls, lkb, name, namelen, mode, flags, error),
+	TP_ARGS(ls, lkb, name, namelen, mode, flags, error, kernel_lock),
 
 	TP_STRUCT__entry(
 		__field(__u32, ls_id)
@@ -113,6 +114,7 @@ TRACE_EVENT(dlm_lock_end,
 		__entry->lkb_id = lkb->lkb_id;
 		__entry->mode = mode;
 		__entry->flags = flags;
+		__entry->error = error;
 
 		r = lkb->lkb_resource;
 		if (r)
@@ -122,14 +124,14 @@ TRACE_EVENT(dlm_lock_end,
 			memcpy(__get_dynamic_array(res_name), name,
 			       __get_dynamic_array_len(res_name));
 
-		/* return value will be zeroed in those cases by dlm_lock()
-		 * we do it here again to not introduce more overhead if
-		 * trace isn't running and error reflects the return value.
-		 */
-		if (error == -EAGAIN || error == -EDEADLK)
-			__entry->error = 0;
-		else
-			__entry->error = error;
+		if (kernel_lock) {
+			/* return value will be zeroed in those cases by dlm_lock()
+			 * we do it here again to not introduce more overhead if
+			 * trace isn't running and error reflects the return value.
+			 */
+			if (error == -EAGAIN || error == -EDEADLK)
+				__entry->error = 0;
+		}
 
 	),
 

include/uapi/linux/dlm.h

@@ -69,7 +69,6 @@ struct dlm_lksb {
 /* dlm_new_lockspace() flags */
 
 #define DLM_LSFL_TIMEWARN	0x00000002
-#define DLM_LSFL_FS     	0x00000004
 #define DLM_LSFL_NEWEXCL     	0x00000008