Merge tag 'dlm-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm

Pull dlm updates from David Teigland:
 "This includes several large patches to improve endian handling and
  remove sparse warnings. The code previously used in/out, in-place
  endianness conversion functions.

  Other code cleanup includes the list iterator changes.

  Finally, a long standing bug was found and fixed, caused by missed
  decrement on an lock struct ref count"

* tag 'dlm-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm: (28 commits)
  dlm: use kref_put_lock in __put_lkb
  dlm: use kref_put_lock in put_rsb
  dlm: remove unnecessary error assign
  dlm: fix missing lkb refcount handling
  fs: dlm: cast resource pointer to uintptr_t
  dlm: replace usage of found with dedicated list iterator variable
  dlm: remove usage of list iterator for list_add() after the loop body
  dlm: fix pending remove if msg allocation fails
  dlm: fix wake_up() calls for pending remove
  dlm: check required context while close
  dlm: cleanup lock handling in dlm_master_lookup
  dlm: remove found label in dlm_master_lookup
  dlm: remove __user conversion warnings
  dlm: move conversion to compile time
  dlm: use __le types for dlm messages
  dlm: use __le types for rcom messages
  dlm: use __le types for dlm header
  dlm: use __le types for options header
  dlm: add __CHECKER__ for false positives
  dlm: move global to static inits
  ...

fs/dlm/dir.c

@@ -101,7 +101,7 @@ int dlm_recover_directory(struct dlm_ls *ls)
 			 */
 
 			b = ls->ls_recover_buf->rc_buf;
-			left = ls->ls_recover_buf->rc_header.h_length;
+			left = le16_to_cpu(ls->ls_recover_buf->rc_header.h_length);
 			left -= sizeof(struct dlm_rcom);
 
 			for (;;) {

fs/dlm/dlm_internal.h

@@ -379,15 +379,15 @@ static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
 #define DLM_FIN			5
 
 struct dlm_header {
-	uint32_t		h_version;
+	__le32			h_version;
 	union {
 		/* for DLM_MSG and DLM_RCOM */
-		uint32_t	h_lockspace;
+		__le32		h_lockspace;
 		/* for DLM_ACK and DLM_OPTS */
-		uint32_t	h_seq;
+		__le32		h_seq;
 	} u;
-	uint32_t		h_nodeid;	/* nodeid of sender */
-	uint16_t		h_length;
+	__le32			h_nodeid;	/* nodeid of sender */
+	__le16			h_length;
 	uint8_t			h_cmd;		/* DLM_MSG, DLM_RCOM */
 	uint8_t			h_pad;
 };
@@ -409,24 +409,24 @@ struct dlm_header {
 
 struct dlm_message {
 	struct dlm_header	m_header;
-	uint32_t		m_type;		/* DLM_MSG_ */
-	uint32_t		m_nodeid;
-	uint32_t		m_pid;
-	uint32_t		m_lkid;		/* lkid on sender */
-	uint32_t		m_remid;	/* lkid on receiver */
-	uint32_t		m_parent_lkid;
-	uint32_t		m_parent_remid;
-	uint32_t		m_exflags;
-	uint32_t		m_sbflags;
-	uint32_t		m_flags;
-	uint32_t		m_lvbseq;
-	uint32_t		m_hash;
-	int			m_status;
-	int			m_grmode;
-	int			m_rqmode;
-	int			m_bastmode;
-	int			m_asts;
-	int			m_result;	/* 0 or -EXXX */
+	__le32			m_type;		/* DLM_MSG_ */
+	__le32			m_nodeid;
+	__le32			m_pid;
+	__le32			m_lkid;		/* lkid on sender */
+	__le32			m_remid;	/* lkid on receiver */
+	__le32			m_parent_lkid;
+	__le32			m_parent_remid;
+	__le32			m_exflags;
+	__le32			m_sbflags;
+	__le32			m_flags;
+	__le32			m_lvbseq;
+	__le32			m_hash;
+	__le32			m_status;
+	__le32			m_grmode;
+	__le32			m_rqmode;
+	__le32			m_bastmode;
+	__le32			m_asts;
+	__le32			m_result;	/* 0 or -EXXX */
 	char			m_extra[];	/* name or lvb */
 };
 
@@ -451,18 +451,18 @@ struct dlm_message {
 
 struct dlm_rcom {
 	struct dlm_header	rc_header;
-	uint32_t		rc_type;	/* DLM_RCOM_ */
-	int			rc_result;	/* multi-purpose */
-	uint64_t		rc_id;		/* match reply with request */
-	uint64_t		rc_seq;		/* sender's ls_recover_seq */
-	uint64_t		rc_seq_reply;	/* remote ls_recover_seq */
+	__le32			rc_type;	/* DLM_RCOM_ */
+	__le32			rc_result;	/* multi-purpose */
+	__le64			rc_id;		/* match reply with request */
+	__le64			rc_seq;		/* sender's ls_recover_seq */
+	__le64			rc_seq_reply;	/* remote ls_recover_seq */
 	char			rc_buf[];
 };
 
 struct dlm_opt_header {
-	uint16_t	t_type;
-	uint16_t	t_length;
-	uint32_t	t_pad;
+	__le16		t_type;
+	__le16		t_length;
+	__le32		t_pad;
 	/* need to be 8 byte aligned */
 	char		t_value[];
 };
@@ -472,8 +472,8 @@ struct dlm_opts {
 	struct dlm_header	o_header;
 	uint8_t			o_nextcmd;
 	uint8_t			o_pad;
-	uint16_t		o_optlen;
-	uint32_t		o_pad2;
+	__le16			o_optlen;
+	__le32			o_pad2;
 	char			o_opts[];
 };
 

fs/dlm/lockspace.c

@@ -922,3 +922,15 @@ void dlm_stop_lockspaces(void)
 		log_print("dlm user daemon left %d lockspaces", count);
 }
 
+void dlm_stop_lockspaces_check(void)
+{
+	struct dlm_ls *ls;
+
+	spin_lock(&lslist_lock);
+	list_for_each_entry(ls, &lslist, ls_list) {
+		if (WARN_ON(!rwsem_is_locked(&ls->ls_in_recovery) ||
+			    !dlm_locking_stopped(ls)))
+			break;
+	}
+	spin_unlock(&lslist_lock);
+}

fs/dlm/lockspace.h

@@ -19,6 +19,7 @@ struct dlm_ls *dlm_find_lockspace_local(void *id);
 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);
 
 #endif				/* __LOCKSPACE_DOT_H__ */
 

fs/dlm/lowcomms.c

@@ -1303,6 +1303,10 @@ static struct dlm_msg *dlm_lowcomms_new_msg_con(struct connection *con, int len,
 	return msg;
 }
 
+/* avoid false positive for nodes_srcu, unlock happens in
+ * dlm_lowcomms_commit_msg which is a must call if success
+ */
+#ifndef __CHECKER__
 struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
 				     char **ppc, void (*cb)(void *data),
 				     void *data)
@@ -1336,6 +1340,7 @@ struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
 	msg->idx = idx;
 	return msg;
 }
+#endif
 
 static void _dlm_lowcomms_commit_msg(struct dlm_msg *msg)
 {
@@ -1362,11 +1367,16 @@ static void _dlm_lowcomms_commit_msg(struct dlm_msg *msg)
 	return;
 }
 
+/* avoid false positive for nodes_srcu, lock was happen in
+ * dlm_lowcomms_new_msg
+ */
+#ifndef __CHECKER__
 void dlm_lowcomms_commit_msg(struct dlm_msg *msg)
 {
 	_dlm_lowcomms_commit_msg(msg);
 	srcu_read_unlock(&connections_srcu, msg->idx);
 }
+#endif
 
 void dlm_lowcomms_put_msg(struct dlm_msg *msg)
 {
@@ -1789,7 +1799,7 @@ static int dlm_listen_for_all(void)
 				  SOCK_STREAM, dlm_proto_ops->proto, &sock);
 	if (result < 0) {
 		log_print("Can't create comms socket: %d", result);
-		goto out;
+		return result;
 	}
 
 	sock_set_mark(sock->sk, dlm_config.ci_mark);

fs/dlm/member.c

@@ -20,7 +20,7 @@
 
 int dlm_slots_version(struct dlm_header *h)
 {
-	if ((h->h_version & 0x0000FFFF) < DLM_HEADER_SLOTS)
+	if ((le32_to_cpu(h->h_version) & 0x0000FFFF) < DLM_HEADER_SLOTS)
 		return 0;
 	return 1;
 }
@@ -120,18 +120,13 @@ int dlm_slots_copy_in(struct dlm_ls *ls)
 
 	ro0 = (struct rcom_slot *)(rc->rc_buf + sizeof(struct rcom_config));
 
-	for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
-		ro->ro_nodeid = le32_to_cpu(ro->ro_nodeid);
-		ro->ro_slot = le16_to_cpu(ro->ro_slot);
-	}
-
 	log_slots(ls, gen, num_slots, ro0, NULL, 0);
 
 	list_for_each_entry(memb, &ls->ls_nodes, list) {
 		for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
-			if (ro->ro_nodeid != memb->nodeid)
+			if (le32_to_cpu(ro->ro_nodeid) != memb->nodeid)
 				continue;
-			memb->slot = ro->ro_slot;
+			memb->slot = le16_to_cpu(ro->ro_slot);
 			memb->slot_prev = memb->slot;
 			break;
 		}

fs/dlm/midcomms.c

@@ -135,6 +135,7 @@
 #include <net/tcp.h>
 
 #include "dlm_internal.h"
+#include "lockspace.h"
 #include "lowcomms.h"
 #include "config.h"
 #include "memory.h"
@@ -380,13 +381,12 @@ static int dlm_send_ack(int nodeid, uint32_t seq)
 
 	m_header = (struct dlm_header *)ppc;
 
-	m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
-	m_header->h_nodeid = dlm_our_nodeid();
-	m_header->h_length = mb_len;
+	m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid());
+	m_header->h_length = cpu_to_le16(mb_len);
 	m_header->h_cmd = DLM_ACK;
-	m_header->u.h_seq = seq;
+	m_header->u.h_seq = cpu_to_le32(seq);
 
-	header_out(m_header);
 	dlm_lowcomms_commit_msg(msg);
 	dlm_lowcomms_put_msg(msg);
 
@@ -409,13 +409,11 @@ static int dlm_send_fin(struct midcomms_node *node,
 
 	m_header = (struct dlm_header *)ppc;
 
-	m_header->h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
-	m_header->h_nodeid = dlm_our_nodeid();
-	m_header->h_length = mb_len;
+	m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid());
+	m_header->h_length = cpu_to_le16(mb_len);
 	m_header->h_cmd = DLM_FIN;
 
-	header_out(m_header);
-
 	pr_debug("sending fin msg to node %d\n", node->nodeid);
 	dlm_midcomms_commit_mhandle(mh);
 	set_bit(DLM_NODE_FLAG_STOP_TX, &node->flags);
@@ -574,14 +572,14 @@ dlm_midcomms_recv_node_lookup(int nodeid, const union dlm_packet *p,
 			return NULL;
 		}
 
-		switch (le32_to_cpu(p->rcom.rc_type)) {
-		case DLM_RCOM_NAMES:
+		switch (p->rcom.rc_type) {
+		case cpu_to_le32(DLM_RCOM_NAMES):
 			fallthrough;
-		case DLM_RCOM_NAMES_REPLY:
+		case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
 			fallthrough;
-		case DLM_RCOM_STATUS:
+		case cpu_to_le32(DLM_RCOM_STATUS):
 			fallthrough;
-		case DLM_RCOM_STATUS_REPLY:
+		case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
 			node = nodeid2node(nodeid, 0);
 			if (node) {
 				spin_lock(&node->state_lock);
@@ -741,14 +739,14 @@ static void dlm_midcomms_receive_buffer_3_2(union dlm_packet *p, int nodeid)
 		 *
 		 * length already checked.
 		 */
-		switch (le32_to_cpu(p->rcom.rc_type)) {
-		case DLM_RCOM_NAMES:
+		switch (p->rcom.rc_type) {
+		case cpu_to_le32(DLM_RCOM_NAMES):
 			fallthrough;
-		case DLM_RCOM_NAMES_REPLY:
+		case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
 			fallthrough;
-		case DLM_RCOM_STATUS:
+		case cpu_to_le32(DLM_RCOM_STATUS):
 			fallthrough;
-		case DLM_RCOM_STATUS_REPLY:
+		case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
 			break;
 		default:
 			log_print("unsupported rcom type received: %u, will skip this message from node %d",
@@ -1020,11 +1018,10 @@ static void dlm_fill_opts_header(struct dlm_opts *opts, uint16_t inner_len,
 				 uint32_t seq)
 {
 	opts->o_header.h_cmd = DLM_OPTS;
-	opts->o_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
-	opts->o_header.h_nodeid = dlm_our_nodeid();
-	opts->o_header.h_length = DLM_MIDCOMMS_OPT_LEN + inner_len;
-	opts->o_header.u.h_seq = seq;
-	header_out(&opts->o_header);
+	opts->o_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+	opts->o_header.h_nodeid = cpu_to_le32(dlm_our_nodeid());
+	opts->o_header.h_length = cpu_to_le16(DLM_MIDCOMMS_OPT_LEN + inner_len);
+	opts->o_header.u.h_seq = cpu_to_le32(seq);
 }
 
 static void midcomms_new_msg_cb(void *data)
@@ -1062,6 +1059,10 @@ static struct dlm_msg *dlm_midcomms_get_msg_3_2(struct dlm_mhandle *mh, int node
 	return msg;
 }
 
+/* avoid false positive for nodes_srcu, unlock happens in
+ * dlm_midcomms_commit_mhandle which is a must call if success
+ */
+#ifndef __CHECKER__
 struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len,
 					     gfp_t allocation, char **ppc)
 {
@@ -1127,6 +1128,7 @@ struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len,
 	srcu_read_unlock(&nodes_srcu, idx);
 	return NULL;
 }
+#endif
 
 static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh)
 {
@@ -1136,6 +1138,10 @@ static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh)
 	dlm_lowcomms_commit_msg(mh->msg);
 }
 
+/* avoid false positive for nodes_srcu, lock was happen in
+ * dlm_midcomms_get_mhandle
+ */
+#ifndef __CHECKER__
 void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh)
 {
 	switch (mh->node->version) {
@@ -1157,6 +1163,7 @@ void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh)
 		break;
 	}
 }
+#endif
 
 int dlm_midcomms_start(void)
 {
@@ -1406,6 +1413,8 @@ int dlm_midcomms_close(int nodeid)
 	if (nodeid == dlm_our_nodeid())
 		return 0;
 
+	dlm_stop_lockspaces_check();
+
 	idx = srcu_read_lock(&nodes_srcu);
 	/* Abort pending close/remove operation */
 	node = nodeid2node(nodeid, 0);
@@ -1455,7 +1464,7 @@ static void midcomms_new_rawmsg_cb(void *data)
 		switch (h->h_cmd) {
 		case DLM_OPTS:
 			if (!h->u.h_seq)
-				h->u.h_seq = rd->node->seq_send++;
+				h->u.h_seq = cpu_to_le32(rd->node->seq_send++);
 			break;
 		default:
 			break;

fs/dlm/plock.c

@@ -13,26 +13,26 @@
 #include "dlm_internal.h"
 #include "lockspace.h"
 
-static spinlock_t ops_lock;
-static struct list_head send_list;
-static struct list_head recv_list;
-static wait_queue_head_t send_wq;
-static wait_queue_head_t recv_wq;
+static DEFINE_SPINLOCK(ops_lock);
+static LIST_HEAD(send_list);
+static LIST_HEAD(recv_list);
+static DECLARE_WAIT_QUEUE_HEAD(send_wq);
+static DECLARE_WAIT_QUEUE_HEAD(recv_wq);
 
-struct plock_op {
-	struct list_head list;
-	int done;
-	struct dlm_plock_info info;
-};
-
-struct plock_xop {
-	struct plock_op xop;
-	int (*callback)(struct file_lock *fl, int result);
+struct plock_async_data {
 	void *fl;
 	void *file;
 	struct file_lock flc;
+	int (*callback)(struct file_lock *fl, int result);
 };
 
+struct plock_op {
+	struct list_head list;
+	int done;
+	struct dlm_plock_info info;
+	/* if set indicates async handling */
+	struct plock_async_data *data;
+};
 
 static inline void set_version(struct dlm_plock_info *info)
 {
@@ -58,10 +58,15 @@ static int check_version(struct dlm_plock_info *info)
 	return 0;
 }
 
+static void dlm_release_plock_op(struct plock_op *op)
+{
+	kfree(op->data);
+	kfree(op);
+}
+
 static void send_op(struct plock_op *op)
 {
 	set_version(&op->info);
-	INIT_LIST_HEAD(&op->list);
 	spin_lock(&ops_lock);
 	list_add_tail(&op->list, &send_list);
 	spin_unlock(&ops_lock);
@@ -101,22 +106,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
 int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		   int cmd, struct file_lock *fl)
 {
+	struct plock_async_data *op_data;
 	struct dlm_ls *ls;
 	struct plock_op *op;
-	struct plock_xop *xop;
 	int rv;
 
 	ls = dlm_find_lockspace_local(lockspace);
 	if (!ls)
 		return -EINVAL;
 
-	xop = kzalloc(sizeof(*xop), GFP_NOFS);
-	if (!xop) {
+	op = kzalloc(sizeof(*op), GFP_NOFS);
+	if (!op) {
 		rv = -ENOMEM;
 		goto out;
 	}
 
-	op = &xop->xop;
 	op->info.optype		= DLM_PLOCK_OP_LOCK;
 	op->info.pid		= fl->fl_pid;
 	op->info.ex		= (fl->fl_type == F_WRLCK);
@@ -125,46 +129,49 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	op->info.number		= number;
 	op->info.start		= fl->fl_start;
 	op->info.end		= fl->fl_end;
+	/* async handling */
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
+		op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+		if (!op_data) {
+			dlm_release_plock_op(op);
+			rv = -ENOMEM;
+			goto out;
+		}
+
 		/* fl_owner is lockd which doesn't distinguish
 		   processes on the nfs client */
 		op->info.owner	= (__u64) fl->fl_pid;
-		xop->callback	= fl->fl_lmops->lm_grant;
-		locks_init_lock(&xop->flc);
-		locks_copy_lock(&xop->flc, fl);
-		xop->fl		= fl;
-		xop->file	= file;
+		op_data->callback = fl->fl_lmops->lm_grant;
+		locks_init_lock(&op_data->flc);
+		locks_copy_lock(&op_data->flc, fl);
+		op_data->fl		= fl;
+		op_data->file	= file;
+
+		op->data = op_data;
+
+		send_op(op);
+		rv = FILE_LOCK_DEFERRED;
+		goto out;
 	} else {
 		op->info.owner	= (__u64)(long) fl->fl_owner;
-		xop->callback	= NULL;
 	}
 
 	send_op(op);
 
-	if (xop->callback == NULL) {
 	rv = wait_event_interruptible(recv_wq, (op->done != 0));
 	if (rv == -ERESTARTSYS) {
-			log_debug(ls, "dlm_posix_lock: wait killed %llx",
-				  (unsigned long long)number);
 		spin_lock(&ops_lock);
 		list_del(&op->list);
 		spin_unlock(&ops_lock);
-			kfree(xop);
+		log_print("%s: wait interrupted %x %llx, op removed",
+			  __func__, ls->ls_global_id,
+			  (unsigned long long)number);
+		dlm_release_plock_op(op);
 		do_unlock_close(ls, number, file, fl);
 		goto out;
 	}
-	} else {
-		rv = FILE_LOCK_DEFERRED;
-		goto out;
-	}
 
-	spin_lock(&ops_lock);
-	if (!list_empty(&op->list)) {
-		log_error(ls, "dlm_posix_lock: op on list %llx",
-			  (unsigned long long)number);
-		list_del(&op->list);
-	}
-	spin_unlock(&ops_lock);
+	WARN_ON(!list_empty(&op->list));
 
 	rv = op->info.rv;
 
@@ -174,7 +181,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 				  (unsigned long long)number);
 	}
 
-	kfree(xop);
+	dlm_release_plock_op(op);
 out:
 	dlm_put_lockspace(ls);
 	return rv;
@@ -184,26 +191,20 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock);
 /* Returns failure iff a successful lock operation should be canceled */
 static int dlm_plock_callback(struct plock_op *op)
 {
+	struct plock_async_data *op_data = op->data;
 	struct file *file;
 	struct file_lock *fl;
 	struct file_lock *flc;
 	int (*notify)(struct file_lock *fl, int result) = NULL;
-	struct plock_xop *xop = (struct plock_xop *)op;
 	int rv = 0;
 
-	spin_lock(&ops_lock);
-	if (!list_empty(&op->list)) {
-		log_print("dlm_plock_callback: op on list %llx",
-			  (unsigned long long)op->info.number);
-		list_del(&op->list);
-	}
-	spin_unlock(&ops_lock);
+	WARN_ON(!list_empty(&op->list));
 
 	/* check if the following 2 are still valid or make a copy */
-	file = xop->file;
-	flc = &xop->flc;
-	fl = xop->fl;
-	notify = xop->callback;
+	file = op_data->file;
+	flc = &op_data->flc;
+	fl = op_data->fl;
+	notify = op_data->callback;
 
 	if (op->info.rv) {
 		notify(fl, op->info.rv);
@@ -234,7 +235,7 @@ static int dlm_plock_callback(struct plock_op *op)
 	}
 
 out:
-	kfree(xop);
+	dlm_release_plock_op(op);
 	return rv;
 }
 
@@ -290,13 +291,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
 
-	spin_lock(&ops_lock);
-	if (!list_empty(&op->list)) {
-		log_error(ls, "dlm_posix_unlock: op on list %llx",
-			  (unsigned long long)number);
-		list_del(&op->list);
-	}
-	spin_unlock(&ops_lock);
+	WARN_ON(!list_empty(&op->list));
 
 	rv = op->info.rv;
 
@@ -304,7 +299,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		rv = 0;
 
 out_free:
-	kfree(op);
+	dlm_release_plock_op(op);
 out:
 	dlm_put_lockspace(ls);
 	fl->fl_flags = fl_flags;
@@ -344,13 +339,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 	send_op(op);
 	wait_event(recv_wq, (op->done != 0));
 
-	spin_lock(&ops_lock);
-	if (!list_empty(&op->list)) {
-		log_error(ls, "dlm_posix_get: op on list %llx",
-			  (unsigned long long)number);
-		list_del(&op->list);
-	}
-	spin_unlock(&ops_lock);
+	WARN_ON(!list_empty(&op->list));
 
 	/* info.rv from userspace is 1 for conflict, 0 for no-conflict,
 	   -ENOENT if there are no locks on the file */
@@ -370,7 +359,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		rv = 0;
 	}
 
-	kfree(op);
+	dlm_release_plock_op(op);
 out:
 	dlm_put_lockspace(ls);
 	return rv;
@@ -406,7 +395,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
 	   (the process did not make an unlock call). */
 
 	if (op->info.flags & DLM_PLOCK_FL_CLOSE)
-		kfree(op);
+		dlm_release_plock_op(op);
 
 	if (copy_to_user(u, &info, sizeof(info)))
 		return -EFAULT;
@@ -418,9 +407,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
 static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 			 loff_t *ppos)
 {
+	struct plock_op *op = NULL, *iter;
 	struct dlm_plock_info info;
-	struct plock_op *op;
-	int found = 0, do_callback = 0;
+	int do_callback = 0;
 
 	if (count != sizeof(info))
 		return -EINVAL;
@@ -432,31 +421,30 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
 		return -EINVAL;
 
 	spin_lock(&ops_lock);
-	list_for_each_entry(op, &recv_list, list) {
-		if (op->info.fsid == info.fsid &&
-		    op->info.number == info.number &&
-		    op->info.owner == info.owner) {
-			struct plock_xop *xop = (struct plock_xop *)op;
-			list_del_init(&op->list);
-			memcpy(&op->info, &info, sizeof(info));
-			if (xop->callback)
+	list_for_each_entry(iter, &recv_list, list) {
+		if (iter->info.fsid == info.fsid &&
+		    iter->info.number == info.number &&
+		    iter->info.owner == info.owner) {
+			list_del_init(&iter->list);
+			memcpy(&iter->info, &info, sizeof(info));
+			if (iter->data)
 				do_callback = 1;
 			else
-				op->done = 1;
-			found = 1;
+				iter->done = 1;
+			op = iter;
 			break;
 		}
 	}
 	spin_unlock(&ops_lock);
 
-	if (found) {
+	if (op) {
 		if (do_callback)
 			dlm_plock_callback(op);
 		else
 			wake_up(&recv_wq);
 	} else
-		log_print("dev_write no op %x %llx", info.fsid,
-			  (unsigned long long)info.number);
+		log_print("%s: no op %x %llx - may got interrupted?", __func__,
+			  info.fsid, (unsigned long long)info.number);
 	return count;
 }
 
@@ -492,12 +480,6 @@ int dlm_plock_init(void)
 {
 	int rv;
 
-	spin_lock_init(&ops_lock);
-	INIT_LIST_HEAD(&send_list);
-	INIT_LIST_HEAD(&recv_list);
-	init_waitqueue_head(&send_wq);
-	init_waitqueue_head(&recv_wq);
-
 	rv = misc_register(&plock_dev_misc);
 	if (rv)
 		log_print("dlm_plock_init: misc_register failed %d", rv);

fs/dlm/recover.c

@@ -114,7 +114,7 @@ static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status,
 			if (save_slots)
 				dlm_slot_save(ls, rc, memb);
 
-			if (rc->rc_result & wait_status)
+			if (le32_to_cpu(rc->rc_result) & wait_status)
 				break;
 			if (delay < 1000)
 				delay += 20;
@@ -141,7 +141,7 @@ static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status,
 		if (error)
 			break;
 
-		if (rc->rc_result & wait_status)
+		if (le32_to_cpu(rc->rc_result) & wait_status)
 			break;
 		if (delay < 1000)
 			delay += 20;
@@ -568,14 +568,14 @@ int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc)
 	struct dlm_rsb *r;
 	int ret_nodeid, new_master;
 
-	r = recover_idr_find(ls, rc->rc_id);
+	r = recover_idr_find(ls, le64_to_cpu(rc->rc_id));
 	if (!r) {
 		log_error(ls, "dlm_recover_master_reply no id %llx",
-			  (unsigned long long)rc->rc_id);
+			  (unsigned long long)le64_to_cpu(rc->rc_id));
 		goto out;
 	}
 
-	ret_nodeid = rc->rc_result;
+	ret_nodeid = le32_to_cpu(rc->rc_result);
 
 	if (ret_nodeid == dlm_our_nodeid())
 		new_master = 0;
@@ -732,10 +732,9 @@ void dlm_recovered_lock(struct dlm_rsb *r)
 
 static void recover_lvb(struct dlm_rsb *r)
 {
-	struct dlm_lkb *lkb, *high_lkb = NULL;
+	struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL;
 	uint32_t high_seq = 0;
 	int lock_lvb_exists = 0;
-	int big_lock_exists = 0;
 	int lvblen = r->res_ls->ls_lvblen;
 
 	if (!rsb_flag(r, RSB_NEW_MASTER2) &&
@@ -751,37 +750,37 @@ static void recover_lvb(struct dlm_rsb *r)
 	/* we are the new master, so figure out if VALNOTVALID should
 	   be set, and set the rsb lvb from the best lkb available. */
 
-	list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
-		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+	list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) {
+		if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
 			continue;
 
 		lock_lvb_exists = 1;
 
-		if (lkb->lkb_grmode > DLM_LOCK_CR) {
-			big_lock_exists = 1;
+		if (iter->lkb_grmode > DLM_LOCK_CR) {
+			big_lkb = iter;
 			goto setflag;
 		}
 
-		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
-			high_lkb = lkb;
-			high_seq = lkb->lkb_lvbseq;
+		if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = iter;
+			high_seq = iter->lkb_lvbseq;
 		}
 	}
 
-	list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
-		if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+	list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) {
+		if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
 			continue;
 
 		lock_lvb_exists = 1;
 
-		if (lkb->lkb_grmode > DLM_LOCK_CR) {
-			big_lock_exists = 1;
+		if (iter->lkb_grmode > DLM_LOCK_CR) {
+			big_lkb = iter;
 			goto setflag;
 		}
 
-		if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
-			high_lkb = lkb;
-			high_seq = lkb->lkb_lvbseq;
+		if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+			high_lkb = iter;
+			high_seq = iter->lkb_lvbseq;
 		}
 	}
 
@@ -790,7 +789,7 @@ static void recover_lvb(struct dlm_rsb *r)
 		goto out;
 
 	/* lvb is invalidated if only NL/CR locks remain */
-	if (!big_lock_exists)
+	if (!big_lkb)
 		rsb_set_flag(r, RSB_VALNOTVALID);
 
 	if (!r->res_lvbptr) {
@@ -799,9 +798,9 @@ static void recover_lvb(struct dlm_rsb *r)
 			goto out;
 	}
 
-	if (big_lock_exists) {
-		r->res_lvbseq = lkb->lkb_lvbseq;
-		memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen);
+	if (big_lkb) {
+		r->res_lvbseq = big_lkb->lkb_lvbseq;
+		memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen);
 	} else if (high_lkb) {
 		r->res_lvbseq = high_lkb->lkb_lvbseq;
 		memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen);

fs/dlm/requestqueue.c

@@ -14,6 +14,7 @@
 #include "dir.h"
 #include "config.h"
 #include "requestqueue.h"
+#include "util.h"
 
 struct rq_entry {
 	struct list_head list;
@@ -32,7 +33,8 @@ struct rq_entry {
 void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
 {
 	struct rq_entry *e;
-	int length = ms->m_header.h_length - sizeof(struct dlm_message);
+	int length = le16_to_cpu(ms->m_header.h_length) -
+		sizeof(struct dlm_message);
 
 	e = kmalloc(sizeof(struct rq_entry) + length, GFP_NOFS);
 	if (!e) {
@@ -42,7 +44,7 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
 
 	e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF;
 	e->nodeid = nodeid;
-	memcpy(&e->request, ms, ms->m_header.h_length);
+	memcpy(&e->request, ms, le16_to_cpu(ms->m_header.h_length));
 
 	atomic_inc(&ls->ls_requestqueue_cnt);
 	mutex_lock(&ls->ls_requestqueue_mutex);
@@ -82,8 +84,10 @@ int dlm_process_requestqueue(struct dlm_ls *ls)
 
 		log_limit(ls, "dlm_process_requestqueue msg %d from %d "
 			  "lkid %x remid %x result %d seq %u",
-			  ms->m_type, ms->m_header.h_nodeid,
-			  ms->m_lkid, ms->m_remid, ms->m_result,
+			  le32_to_cpu(ms->m_type),
+			  le32_to_cpu(ms->m_header.h_nodeid),
+			  le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid),
+			  from_dlm_errno(le32_to_cpu(ms->m_result)),
 			  e->recover_seq);
 
 		dlm_receive_message_saved(ls, &e->request, e->recover_seq);
@@ -124,7 +128,7 @@ void dlm_wait_requestqueue(struct dlm_ls *ls)
 
 static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
 {
-	uint32_t type = ms->m_type;
+	__le32 type = ms->m_type;
 
 	/* the ls is being cleaned up and freed by release_lockspace */
 	if (!atomic_read(&ls->ls_count))
@@ -136,9 +140,9 @@ static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
 	/* directory operations are always purged because the directory is
 	   always rebuilt during recovery and the lookups resent */
 
-	if (type == DLM_MSG_REMOVE ||
-	    type == DLM_MSG_LOOKUP ||
-	    type == DLM_MSG_LOOKUP_REPLY)
+	if (type == cpu_to_le32(DLM_MSG_REMOVE) ||
+	    type == cpu_to_le32(DLM_MSG_LOOKUP) ||
+	    type == cpu_to_le32(DLM_MSG_LOOKUP_REPLY))
 		return 1;
 
 	if (!dlm_no_directory(ls))

fs/dlm/user.c

@@ -108,11 +108,11 @@ static void compat_input(struct dlm_write_request *kb,
 		kb->i.lock.parent = kb32->i.lock.parent;
 		kb->i.lock.xid = kb32->i.lock.xid;
 		kb->i.lock.timeout = kb32->i.lock.timeout;
-		kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam;
-		kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr;
-		kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam;
-		kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
-		kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
+		kb->i.lock.castparam = (__user void *)(long)kb32->i.lock.castparam;
+		kb->i.lock.castaddr = (__user void *)(long)kb32->i.lock.castaddr;
+		kb->i.lock.bastparam = (__user void *)(long)kb32->i.lock.bastparam;
+		kb->i.lock.bastaddr = (__user void *)(long)kb32->i.lock.bastaddr;
+		kb->i.lock.lksb = (__user void *)(long)kb32->i.lock.lksb;
 		memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
 		memcpy(kb->i.lock.name, kb32->i.lock.name, namelen);
 	}
@@ -127,9 +127,9 @@ static void compat_output(struct dlm_lock_result *res,
 	res32->version[1] = res->version[1];
 	res32->version[2] = res->version[2];
 
-	res32->user_astaddr = (__u32)(long)res->user_astaddr;
-	res32->user_astparam = (__u32)(long)res->user_astparam;
-	res32->user_lksb = (__u32)(long)res->user_lksb;
+	res32->user_astaddr = (__u32)(__force long)res->user_astaddr;
+	res32->user_astparam = (__u32)(__force long)res->user_astparam;
+	res32->user_lksb = (__u32)(__force long)res->user_lksb;
 	res32->bast_mode = res->bast_mode;
 
 	res32->lvb_offset = res->lvb_offset;

fs/dlm/util.c

@@ -20,28 +20,10 @@
 #define DLM_ERRNO_ETIMEDOUT	       110
 #define DLM_ERRNO_EINPROGRESS	       115
 
-void header_out(struct dlm_header *hd)
-{
-	hd->h_version		= cpu_to_le32(hd->h_version);
-	/* does it for others u32 in union as well */
-	hd->u.h_lockspace	= cpu_to_le32(hd->u.h_lockspace);
-	hd->h_nodeid		= cpu_to_le32(hd->h_nodeid);
-	hd->h_length		= cpu_to_le16(hd->h_length);
-}
-
-void header_in(struct dlm_header *hd)
-{
-	hd->h_version		= le32_to_cpu(hd->h_version);
-	/* does it for others u32 in union as well */
-	hd->u.h_lockspace	= le32_to_cpu(hd->u.h_lockspace);
-	hd->h_nodeid		= le32_to_cpu(hd->h_nodeid);
-	hd->h_length		= le16_to_cpu(hd->h_length);
-}
-
 /* higher errno values are inconsistent across architectures, so select
    one set of values for on the wire */
 
-static int to_dlm_errno(int err)
+int to_dlm_errno(int err)
 {
 	switch (err) {
 	case -EDEADLK:
@@ -62,7 +44,7 @@ static int to_dlm_errno(int err)
 	return err;
 }
 
-static int from_dlm_errno(int err)
+int from_dlm_errno(int err)
 {
 	switch (err) {
 	case -DLM_ERRNO_EDEADLK:
@@ -82,73 +64,3 @@ static int from_dlm_errno(int err)
 	}
 	return err;
 }
-
-void dlm_message_out(struct dlm_message *ms)
-{
-	header_out(&ms->m_header);
-
-	ms->m_type		= cpu_to_le32(ms->m_type);
-	ms->m_nodeid		= cpu_to_le32(ms->m_nodeid);
-	ms->m_pid		= cpu_to_le32(ms->m_pid);
-	ms->m_lkid		= cpu_to_le32(ms->m_lkid);
-	ms->m_remid		= cpu_to_le32(ms->m_remid);
-	ms->m_parent_lkid	= cpu_to_le32(ms->m_parent_lkid);
-	ms->m_parent_remid	= cpu_to_le32(ms->m_parent_remid);
-	ms->m_exflags		= cpu_to_le32(ms->m_exflags);
-	ms->m_sbflags		= cpu_to_le32(ms->m_sbflags);
-	ms->m_flags		= cpu_to_le32(ms->m_flags);
-	ms->m_lvbseq		= cpu_to_le32(ms->m_lvbseq);
-	ms->m_hash		= cpu_to_le32(ms->m_hash);
-	ms->m_status		= cpu_to_le32(ms->m_status);
-	ms->m_grmode		= cpu_to_le32(ms->m_grmode);
-	ms->m_rqmode		= cpu_to_le32(ms->m_rqmode);
-	ms->m_bastmode		= cpu_to_le32(ms->m_bastmode);
-	ms->m_asts		= cpu_to_le32(ms->m_asts);
-	ms->m_result		= cpu_to_le32(to_dlm_errno(ms->m_result));
-}
-
-void dlm_message_in(struct dlm_message *ms)
-{
-	header_in(&ms->m_header);
-
-	ms->m_type		= le32_to_cpu(ms->m_type);
-	ms->m_nodeid		= le32_to_cpu(ms->m_nodeid);
-	ms->m_pid		= le32_to_cpu(ms->m_pid);
-	ms->m_lkid		= le32_to_cpu(ms->m_lkid);
-	ms->m_remid		= le32_to_cpu(ms->m_remid);
-	ms->m_parent_lkid	= le32_to_cpu(ms->m_parent_lkid);
-	ms->m_parent_remid	= le32_to_cpu(ms->m_parent_remid);
-	ms->m_exflags		= le32_to_cpu(ms->m_exflags);
-	ms->m_sbflags		= le32_to_cpu(ms->m_sbflags);
-	ms->m_flags		= le32_to_cpu(ms->m_flags);
-	ms->m_lvbseq		= le32_to_cpu(ms->m_lvbseq);
-	ms->m_hash		= le32_to_cpu(ms->m_hash);
-	ms->m_status		= le32_to_cpu(ms->m_status);
-	ms->m_grmode		= le32_to_cpu(ms->m_grmode);
-	ms->m_rqmode		= le32_to_cpu(ms->m_rqmode);
-	ms->m_bastmode		= le32_to_cpu(ms->m_bastmode);
-	ms->m_asts		= le32_to_cpu(ms->m_asts);
-	ms->m_result		= from_dlm_errno(le32_to_cpu(ms->m_result));
-}
-
-void dlm_rcom_out(struct dlm_rcom *rc)
-{
-	header_out(&rc->rc_header);
-
-	rc->rc_type		= cpu_to_le32(rc->rc_type);
-	rc->rc_result		= cpu_to_le32(rc->rc_result);
-	rc->rc_id		= cpu_to_le64(rc->rc_id);
-	rc->rc_seq		= cpu_to_le64(rc->rc_seq);
-	rc->rc_seq_reply	= cpu_to_le64(rc->rc_seq_reply);
-}
-
-void dlm_rcom_in(struct dlm_rcom *rc)
-{
-	header_in(&rc->rc_header);
-
-	rc->rc_type		= le32_to_cpu(rc->rc_type);
-	rc->rc_result		= le32_to_cpu(rc->rc_result);
-	rc->rc_id		= le64_to_cpu(rc->rc_id);
-	rc->rc_seq		= le64_to_cpu(rc->rc_seq);
-	rc->rc_seq_reply	= le64_to_cpu(rc->rc_seq_reply);
-}

fs/dlm/util.h

@@ -11,12 +11,8 @@
 #ifndef __UTIL_DOT_H__
 #define __UTIL_DOT_H__
 
-void dlm_message_out(struct dlm_message *ms);
-void dlm_message_in(struct dlm_message *ms);
-void dlm_rcom_out(struct dlm_rcom *rc);
-void dlm_rcom_in(struct dlm_rcom *rc);
-void header_out(struct dlm_header *hd);
-void header_in(struct dlm_header *hd);
+int to_dlm_errno(int err);
+int from_dlm_errno(int err);
 
 #endif