Merge tag 'dlm-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm

Pull dlm updates from David Teigland:
 "These patches include the usual cleanups and minor fixes, the removal
  of code that is no longer needed due to recent improvements, and
  improvements to processing large volumes of messages during heavy
  locking activity.

  Summary:

   - Misc code cleanup

   - Fix a couple of socket handling bugs: a double release on an error
     path and a data-ready race in an accept loop

   - Remove code for resending dir-remove messages. This code is no
     longer needed since the midcomms layer now ensures the messages are
     resent if needed

   - Add tracepoints for dlm messages

   - Improve callback queueing by replacing the fixed array with a list

   - Simplify the handling of a remove message followed by a lookup
     message by sending both without releasing a spinlock in between

   - Improve the concurrency of sending and receiving messages by
     holding locks for a shorter time, and changing how workqueues are
     used

   - Remove old code for shutting down sockets, which is no longer
     needed with the reliable connection handling that was recently
     added"

* tag 'dlm-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/linux-dlm: (37 commits)
  fs: dlm: fix building without lockdep
  fs: dlm: parallelize lowcomms socket handling
  fs: dlm: don't init error value
  fs: dlm: use saved sk_error_report()
  fs: dlm: use sock2con without checking null
  fs: dlm: remove dlm_node_addrs lookup list
  fs: dlm: don't put dlm_local_addrs on heap
  fs: dlm: cleanup listen sock handling
  fs: dlm: remove socket shutdown handling
  fs: dlm: use listen sock as dlm running indicator
  fs: dlm: use list_first_entry_or_null
  fs: dlm: remove twice INIT_WORK
  fs: dlm: add midcomms init/start functions
  fs: dlm: add dst nodeid for msg tracing
  fs: dlm: rename seq to h_seq for msg tracing
  fs: dlm: rename DLM_IFL_NEED_SCHED to DLM_IFL_CB_PENDING
  fs: dlm: ast do WARN_ON_ONCE() on hotpath
  fs: dlm: drop lkb ref in bug case
  fs: dlm: avoid false-positive checker warning
  fs: dlm: use WARN_ON_ONCE() instead of WARN_ON()
  ...

1 files changed, 36 insertions, 154 deletions

diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 94a72ede5764..e1adfa5aed05 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1209,6 +1209,7 @@ static int _create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret,
 	if (!lkb)
 		return -ENOMEM;
 
+	lkb->lkb_last_bast_mode = -1;
 	lkb->lkb_nodeid = -1;
 	lkb->lkb_grmode = DLM_LOCK_IV;
 	kref_init(&lkb->lkb_ref);
@@ -1218,7 +1219,8 @@ static int _create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret,
 	INIT_LIST_HEAD(&lkb->lkb_time_list);
 #endif
 	INIT_LIST_HEAD(&lkb->lkb_cb_list);
-	mutex_init(&lkb->lkb_cb_mutex);
+	INIT_LIST_HEAD(&lkb->lkb_callbacks);
+	spin_lock_init(&lkb->lkb_cb_lock);
 	INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
 
 	idr_preload(GFP_NOFS);
@@ -1587,37 +1589,6 @@ static int remove_from_waiters_ms(struct dlm_lkb *lkb, struct dlm_message *ms)
 	return error;
 }
 
-/* If there's an rsb for the same resource being removed, ensure
- * that the remove message is sent before the new lookup message.
- */
-
-#define DLM_WAIT_PENDING_COND(ls, r)		\
-	(ls->ls_remove_len &&			\
-	 !rsb_cmp(r, ls->ls_remove_name,	\
-		  ls->ls_remove_len))
-
-static void wait_pending_remove(struct dlm_rsb *r)
-{
-	struct dlm_ls *ls = r->res_ls;
- restart:
-	spin_lock(&ls->ls_remove_spin);
-	if (DLM_WAIT_PENDING_COND(ls, r)) {
-		log_debug(ls, "delay lookup for remove dir %d %s",
-			  r->res_dir_nodeid, r->res_name);
-		spin_unlock(&ls->ls_remove_spin);
-		wait_event(ls->ls_remove_wait, !DLM_WAIT_PENDING_COND(ls, r));
-		goto restart;
-	}
-	spin_unlock(&ls->ls_remove_spin);
-}
-
-/*
- * ls_remove_spin protects ls_remove_name and ls_remove_len which are
- * read by other threads in wait_pending_remove.  ls_remove_names
- * and ls_remove_lens are only used by the scan thread, so they do
- * not need protection.
- */
-
 static void shrink_bucket(struct dlm_ls *ls, int b)
 {
 	struct rb_node *n, *next;
@@ -1699,11 +1670,6 @@ static void shrink_bucket(struct dlm_ls *ls, int b)
 	 * list and sending the removal.  Keeping this gap small is
 	 * important to keep us (the master node) from being out of sync
 	 * with the remote dir node for very long.
-	 *
-	 * From the time the rsb is removed from toss until just after
-	 * send_remove, the rsb name is saved in ls_remove_name.  A new
-	 * lookup checks this to ensure that a new lookup message for the
-	 * same resource name is not sent just before the remove message.
 	 */
 
 	for (i = 0; i < remote_count; i++) {
@@ -1750,22 +1716,8 @@ static void shrink_bucket(struct dlm_ls *ls, int b)
 		}
 
 		rb_erase(&r->res_hashnode, &ls->ls_rsbtbl[b].toss);
-
-		/* block lookup of same name until we've sent remove */
-		spin_lock(&ls->ls_remove_spin);
-		ls->ls_remove_len = len;
-		memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN);
-		spin_unlock(&ls->ls_remove_spin);
-		spin_unlock(&ls->ls_rsbtbl[b].lock);
-
 		send_remove(r);
-
-		/* allow lookup of name again */
-		spin_lock(&ls->ls_remove_spin);
-		ls->ls_remove_len = 0;
-		memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
-		spin_unlock(&ls->ls_remove_spin);
-		wake_up(&ls->ls_remove_wait);
+		spin_unlock(&ls->ls_rsbtbl[b].lock);
 
 		dlm_free_rsb(r);
 	}
@@ -2716,8 +2668,6 @@ static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
 		return 0;
 	}
 
-	wait_pending_remove(r);
-
 	r->res_first_lkid = lkb->lkb_id;
 	send_lookup(r, lkb);
 	return 1;
@@ -3552,7 +3502,8 @@ int dlm_unlock(dlm_lockspace_t *lockspace,
 static int _create_message(struct dlm_ls *ls, int mb_len,
 			   int to_nodeid, int mstype,
 			   struct dlm_message **ms_ret,
-			   struct dlm_mhandle **mh_ret)
+			   struct dlm_mhandle **mh_ret,
+			   gfp_t allocation)
 {
 	struct dlm_message *ms;
 	struct dlm_mhandle *mh;
@@ -3562,7 +3513,7 @@ static int _create_message(struct dlm_ls *ls, int mb_len,
 	   pass into midcomms_commit and a message buffer (mb) that we
 	   write our data into */
 
-	mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, GFP_NOFS, &mb);
+	mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, allocation, &mb);
 	if (!mh)
 		return -ENOBUFS;
 
@@ -3584,7 +3535,8 @@ static int _create_message(struct dlm_ls *ls, int mb_len,
 static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
 			  int to_nodeid, int mstype,
 			  struct dlm_message **ms_ret,
-			  struct dlm_mhandle **mh_ret)
+			  struct dlm_mhandle **mh_ret,
+			  gfp_t allocation)
 {
 	int mb_len = sizeof(struct dlm_message);
 
@@ -3605,15 +3557,16 @@ static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
 	}
 
 	return _create_message(r->res_ls, mb_len, to_nodeid, mstype,
-			       ms_ret, mh_ret);
+			       ms_ret, mh_ret, allocation);
 }
 
 /* further lowcomms enhancements or alternate implementations may make
    the return value from this function useful at some point */
 
-static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms)
+static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms,
+			const void *name, int namelen)
 {
-	dlm_midcomms_commit_mhandle(mh);
+	dlm_midcomms_commit_mhandle(mh, name, namelen);
 	return 0;
 }
 
@@ -3673,13 +3626,13 @@ static int send_common(struct dlm_rsb *r, struct dlm_lkb *lkb, int mstype)
 	if (error)
 		return error;
 
-	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh);
+	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh, GFP_NOFS);
 	if (error)
 		goto fail;
 
 	send_args(r, lkb, ms);
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
 	if (error)
 		goto fail;
 	return 0;
@@ -3734,7 +3687,8 @@ static int send_grant(struct dlm_rsb *r, struct dlm_lkb *lkb)
 
 	to_nodeid = lkb->lkb_nodeid;
 
-	error = create_message(r, lkb, to_nodeid, DLM_MSG_GRANT, &ms, &mh);
+	error = create_message(r, lkb, to_nodeid, DLM_MSG_GRANT, &ms, &mh,
+			       GFP_NOFS);
 	if (error)
 		goto out;
 
@@ -3742,7 +3696,7 @@ static int send_grant(struct dlm_rsb *r, struct dlm_lkb *lkb)
 
 	ms->m_result = 0;
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
  out:
 	return error;
 }
@@ -3755,7 +3709,8 @@ static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode)
 
 	to_nodeid = lkb->lkb_nodeid;
 
-	error = create_message(r, NULL, to_nodeid, DLM_MSG_BAST, &ms, &mh);
+	error = create_message(r, NULL, to_nodeid, DLM_MSG_BAST, &ms, &mh,
+			       GFP_NOFS);
 	if (error)
 		goto out;
 
@@ -3763,7 +3718,7 @@ static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode)
 
 	ms->m_bastmode = cpu_to_le32(mode);
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
  out:
 	return error;
 }
@@ -3780,13 +3735,14 @@ static int send_lookup(struct dlm_rsb *r, struct dlm_lkb *lkb)
 	if (error)
 		return error;
 
-	error = create_message(r, NULL, to_nodeid, DLM_MSG_LOOKUP, &ms, &mh);
+	error = create_message(r, NULL, to_nodeid, DLM_MSG_LOOKUP, &ms, &mh,
+			       GFP_NOFS);
 	if (error)
 		goto fail;
 
 	send_args(r, lkb, ms);
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
 	if (error)
 		goto fail;
 	return 0;
@@ -3804,14 +3760,15 @@ static int send_remove(struct dlm_rsb *r)
 
 	to_nodeid = dlm_dir_nodeid(r);
 
-	error = create_message(r, NULL, to_nodeid, DLM_MSG_REMOVE, &ms, &mh);
+	error = create_message(r, NULL, to_nodeid, DLM_MSG_REMOVE, &ms, &mh,
+			       GFP_ATOMIC);
 	if (error)
 		goto out;
 
 	memcpy(ms->m_extra, r->res_name, r->res_length);
 	ms->m_hash = cpu_to_le32(r->res_hash);
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
  out:
 	return error;
 }
@@ -3825,7 +3782,7 @@ static int send_common_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
 
 	to_nodeid = lkb->lkb_nodeid;
 
-	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh);
+	error = create_message(r, lkb, to_nodeid, mstype, &ms, &mh, GFP_NOFS);
 	if (error)
 		goto out;
 
@@ -3833,7 +3790,7 @@ static int send_common_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
 
 	ms->m_result = cpu_to_le32(to_dlm_errno(rv));
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, r->res_name, r->res_length);
  out:
 	return error;
 }
@@ -3866,7 +3823,8 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in,
 	struct dlm_mhandle *mh;
 	int error, nodeid = le32_to_cpu(ms_in->m_header.h_nodeid);
 
-	error = create_message(r, NULL, nodeid, DLM_MSG_LOOKUP_REPLY, &ms, &mh);
+	error = create_message(r, NULL, nodeid, DLM_MSG_LOOKUP_REPLY, &ms, &mh,
+			       GFP_NOFS);
 	if (error)
 		goto out;
 
@@ -3874,7 +3832,7 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in,
 	ms->m_result = cpu_to_le32(to_dlm_errno(rv));
 	ms->m_nodeid = cpu_to_le32(ret_nodeid);
 
-	error = send_message(mh, ms);
+	error = send_message(mh, ms, ms_in->m_extra, receive_extralen(ms_in));
  out:
 	return error;
 }
@@ -4044,66 +4002,6 @@ out:
 	return error;
 }
 
-static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len)
-{
-	char name[DLM_RESNAME_MAXLEN + 1];
-	struct dlm_message *ms;
-	struct dlm_mhandle *mh;
-	struct dlm_rsb *r;
-	uint32_t hash, b;
-	int rv, dir_nodeid;
-
-	memset(name, 0, sizeof(name));
-	memcpy(name, ms_name, len);
-
-	hash = jhash(name, len, 0);
-	b = hash & (ls->ls_rsbtbl_size - 1);
-
-	dir_nodeid = dlm_hash2nodeid(ls, hash);
-
-	log_error(ls, "send_repeat_remove dir %d %s", dir_nodeid, name);
-
-	spin_lock(&ls->ls_rsbtbl[b].lock);
-	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
-	if (!rv) {
-		spin_unlock(&ls->ls_rsbtbl[b].lock);
-		log_error(ls, "repeat_remove on keep %s", name);
-		return;
-	}
-
-	rv = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
-	if (!rv) {
-		spin_unlock(&ls->ls_rsbtbl[b].lock);
-		log_error(ls, "repeat_remove on toss %s", name);
-		return;
-	}
-
-	/* use ls->remove_name2 to avoid conflict with shrink? */
-
-	spin_lock(&ls->ls_remove_spin);
-	ls->ls_remove_len = len;
-	memcpy(ls->ls_remove_name, name, DLM_RESNAME_MAXLEN);
-	spin_unlock(&ls->ls_remove_spin);
-	spin_unlock(&ls->ls_rsbtbl[b].lock);
-
-	rv = _create_message(ls, sizeof(struct dlm_message) + len,
-			     dir_nodeid, DLM_MSG_REMOVE, &ms, &mh);
-	if (rv)
-		goto out;
-
-	memcpy(ms->m_extra, name, len);
-	ms->m_hash = cpu_to_le32(hash);
-
-	send_message(mh, ms);
-
-out:
-	spin_lock(&ls->ls_remove_spin);
-	ls->ls_remove_len = 0;
-	memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
-	spin_unlock(&ls->ls_remove_spin);
-	wake_up(&ls->ls_remove_wait);
-}
-
 static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
 {
 	struct dlm_lkb *lkb;
@@ -4173,25 +4071,11 @@ static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
 	   ENOTBLK request failures when the lookup reply designating us
 	   as master is delayed. */
 
-	/* We could repeatedly return -EBADR here if our send_remove() is
-	   delayed in being sent/arriving/being processed on the dir node.
-	   Another node would repeatedly lookup up the master, and the dir
-	   node would continue returning our nodeid until our send_remove
-	   took effect.
-
-	   We send another remove message in case our previous send_remove
-	   was lost/ignored/missed somehow. */
-
 	if (error != -ENOTBLK) {
 		log_limit(ls, "receive_request %x from %d %d",
 			  le32_to_cpu(ms->m_lkid), from_nodeid, error);
 	}
 
-	if (namelen && error == -EBADR) {
-		send_repeat_remove(ls, ms->m_extra, namelen);
-		msleep(1000);
-	}
-
 	setup_stub_lkb(ls, ms);
 	send_request_reply(&ls->ls_stub_rsb, &ls->ls_stub_lkb, error);
 	return error;
@@ -6294,8 +6178,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
 	}
 
 	list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) {
-		memset(&lkb->lkb_callbacks, 0,
-		       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
+		dlm_purge_lkb_callbacks(lkb);
 		list_del_init(&lkb->lkb_cb_list);
 		dlm_put_lkb(lkb);
 	}
@@ -6336,8 +6219,7 @@ static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
 
 	spin_lock(&proc->asts_spin);
 	list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_cb_list) {
-		memset(&lkb->lkb_callbacks, 0,
-		       sizeof(struct dlm_callback) * DLM_CALLBACKS_SIZE);
+		dlm_purge_lkb_callbacks(lkb);
 		list_del_init(&lkb->lkb_cb_list);
 		dlm_put_lkb(lkb);
 	}
@@ -6368,13 +6250,13 @@ static int send_purge(struct dlm_ls *ls, int nodeid, int pid)
 	int error;
 
 	error = _create_message(ls, sizeof(struct dlm_message), nodeid,
-				DLM_MSG_PURGE, &ms, &mh);
+				DLM_MSG_PURGE, &ms, &mh, GFP_NOFS);
 	if (error)
 		return error;
 	ms->m_nodeid = cpu_to_le32(nodeid);
 	ms->m_pid = cpu_to_le32(pid);
 
-	return send_message(mh, ms);
+	return send_message(mh, ms, NULL, 0);
 }
 
 int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,