1 files changed, 250 insertions, 143 deletions

diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 4314f0d48d8..dcea1e37a1b 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -16,192 +16,299 @@
 #include "user.h"
 #include "ast.h"
 
-#define WAKE_ASTS  0
+static uint64_t dlm_cb_seq;
+static DEFINE_SPINLOCK(dlm_cb_seq_spin);
 
-static struct list_head		ast_queue;
-static spinlock_t		ast_queue_lock;
-static struct task_struct *	astd_task;
-static unsigned long		astd_wakeflags;
-static struct mutex		astd_running;
-
-
-void dlm_del_ast(struct dlm_lkb *lkb)
+static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb)
 {
-	spin_lock(&ast_queue_lock);
-	if (lkb->lkb_ast_type & (AST_COMP | AST_BAST))
-		list_del(&lkb->lkb_astqueue);
-	spin_unlock(&ast_queue_lock);
+	int i;
+
+	log_print("last_bast %x %llu flags %x mode %d sb %d %x",
+		  lkb->lkb_id,
+		  (unsigned long long)lkb->lkb_last_bast.seq,
+		  lkb->lkb_last_bast.flags,
+		  lkb->lkb_last_bast.mode,
+		  lkb->lkb_last_bast.sb_status,
+		  lkb->lkb_last_bast.sb_flags);
+
+	log_print("last_cast %x %llu flags %x mode %d sb %d %x",
+		  lkb->lkb_id,
+		  (unsigned long long)lkb->lkb_last_cast.seq,
+		  lkb->lkb_last_cast.flags,
+		  lkb->lkb_last_cast.mode,
+		  lkb->lkb_last_cast.sb_status,
+		  lkb->lkb_last_cast.sb_flags);
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		log_print("cb %x %llu flags %x mode %d sb %d %x",
+			  lkb->lkb_id,
+			  (unsigned long long)lkb->lkb_callbacks[i].seq,
+			  lkb->lkb_callbacks[i].flags,
+			  lkb->lkb_callbacks[i].mode,
+			  lkb->lkb_callbacks[i].sb_status,
+			  lkb->lkb_callbacks[i].sb_flags);
+	}
 }
 
-void dlm_add_ast(struct dlm_lkb *lkb, int type, int mode)
+int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+			 int status, uint32_t sbflags, uint64_t seq)
 {
-	if (lkb->lkb_flags & DLM_IFL_USER) {
-		dlm_user_add_ast(lkb, type, mode);
-		return;
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	uint64_t prev_seq;
+	int prev_mode;
+	int i, rv;
+
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		if (lkb->lkb_callbacks[i].seq)
+			continue;
+
+		/*
+		 * Suppress some redundant basts here, do more on removal.
+		 * Don't even add a bast if the callback just before it
+		 * is a bast for the same mode or a more restrictive mode.
+		 * (the addional > PR check is needed for PR/CW inversion)
+		 */
+
+		if ((i > 0) && (flags & DLM_CB_BAST) &&
+		    (lkb->lkb_callbacks[i-1].flags & DLM_CB_BAST)) {
+
+			prev_seq = lkb->lkb_callbacks[i-1].seq;
+			prev_mode = lkb->lkb_callbacks[i-1].mode;
+
+			if ((prev_mode == mode) ||
+			    (prev_mode > mode && prev_mode > DLM_LOCK_PR)) {
+
+				log_debug(ls, "skip %x add bast %llu mode %d "
+					  "for bast %llu mode %d",
+					  lkb->lkb_id,
+					  (unsigned long long)seq,
+					  mode,
+					  (unsigned long long)prev_seq,
+					  prev_mode);
+				rv = 0;
+				goto out;
+			}
+		}
+
+		lkb->lkb_callbacks[i].seq = seq;
+		lkb->lkb_callbacks[i].flags = flags;
+		lkb->lkb_callbacks[i].mode = mode;
+		lkb->lkb_callbacks[i].sb_status = status;
+		lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF);
+		rv = 0;
+		break;
 	}
 
-	spin_lock(&ast_queue_lock);
-	if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
-		kref_get(&lkb->lkb_ref);
-		list_add_tail(&lkb->lkb_astqueue, &ast_queue);
-		lkb->lkb_ast_first = type;
+	if (i == DLM_CALLBACKS_SIZE) {
+		log_error(ls, "no callbacks %x %llu flags %x mode %d sb %d %x",
+			  lkb->lkb_id, (unsigned long long)seq,
+			  flags, mode, status, sbflags);
+		dlm_dump_lkb_callbacks(lkb);
+		rv = -1;
+		goto out;
+	}
+ out:
+	return rv;
+}
+
+int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
+			 struct dlm_callback *cb, int *resid)
+{
+	int i, rv;
+
+	*resid = 0;
+
+	if (!lkb->lkb_callbacks[0].seq) {
+		rv = -ENOENT;
+		goto out;
 	}
 
-	/* sanity check, this should not happen */
+	/* oldest undelivered cb is callbacks[0] */
+
+	memcpy(cb, &lkb->lkb_callbacks[0], sizeof(struct dlm_callback));
+	memset(&lkb->lkb_callbacks[0], 0, sizeof(struct dlm_callback));
+
+	/* shift others down */
 
-	if ((type == AST_COMP) && (lkb->lkb_ast_type & AST_COMP))
-		log_print("repeat cast %d castmode %d lock %x %s",
-			  mode, lkb->lkb_castmode,
-			  lkb->lkb_id, lkb->lkb_resource->res_name);
+	for (i = 1; i < DLM_CALLBACKS_SIZE; i++) {
+		if (!lkb->lkb_callbacks[i].seq)
+			break;
+		memcpy(&lkb->lkb_callbacks[i-1], &lkb->lkb_callbacks[i],
+		       sizeof(struct dlm_callback));
+		memset(&lkb->lkb_callbacks[i], 0, sizeof(struct dlm_callback));
+		(*resid)++;
+	}
 
-	lkb->lkb_ast_type |= type;
-	if (type == AST_BAST)
-		lkb->lkb_bastmode = mode;
-	else
-		lkb->lkb_castmode = mode;
-	spin_unlock(&ast_queue_lock);
+	/* if cb is a bast, it should be skipped if the blocking mode is
+	   compatible with the last granted mode */
+
+	if ((cb->flags & DLM_CB_BAST) && lkb->lkb_last_cast.seq) {
+		if (dlm_modes_compat(cb->mode, lkb->lkb_last_cast.mode)) {
+			cb->flags |= DLM_CB_SKIP;
+
+			log_debug(ls, "skip %x bast %llu mode %d "
+				  "for cast %llu mode %d",
+				  lkb->lkb_id,
+				  (unsigned long long)cb->seq,
+				  cb->mode,
+				  (unsigned long long)lkb->lkb_last_cast.seq,
+				  lkb->lkb_last_cast.mode);
+			rv = 0;
+			goto out;
+		}
+	}
 
-	set_bit(WAKE_ASTS, &astd_wakeflags);
-	wake_up_process(astd_task);
+	if (cb->flags & DLM_CB_CAST) {
+		memcpy(&lkb->lkb_last_cast, cb, sizeof(struct dlm_callback));
+		lkb->lkb_last_cast_time = ktime_get();
+	}
+
+	if (cb->flags & DLM_CB_BAST) {
+		memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback));
+		lkb->lkb_last_bast_time = ktime_get();
+	}
+	rv = 0;
+ out:
+	return rv;
 }
 
-static void process_asts(void)
+void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
+		uint32_t sbflags)
 {
-	struct dlm_ls *ls = NULL;
-	struct dlm_rsb *r = NULL;
-	struct dlm_lkb *lkb;
-	void (*castfn) (void *astparam);
-	void (*bastfn) (void *astparam, int mode);
-	int type, first, bastmode, castmode, do_bast, do_cast, last_castmode;
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	uint64_t new_seq, prev_seq;
+	int rv;
 
-repeat:
-	spin_lock(&ast_queue_lock);
-	list_for_each_entry(lkb, &ast_queue, lkb_astqueue) {
-		r = lkb->lkb_resource;
-		ls = r->res_ls;
+	spin_lock(&dlm_cb_seq_spin);
+	new_seq = ++dlm_cb_seq;
+	spin_unlock(&dlm_cb_seq_spin);
 
-		if (dlm_locking_stopped(ls))
-			continue;
+	if (lkb->lkb_flags & DLM_IFL_USER) {
+		dlm_user_add_ast(lkb, flags, mode, status, sbflags, new_seq);
+		return;
+	}
 
-		list_del(&lkb->lkb_astqueue);
-		type = lkb->lkb_ast_type;
-		lkb->lkb_ast_type = 0;
-		first = lkb->lkb_ast_first;
-		lkb->lkb_ast_first = 0;
-		bastmode = lkb->lkb_bastmode;
-		castmode = lkb->lkb_castmode;
-		castfn = lkb->lkb_astfn;
-		bastfn = lkb->lkb_bastfn;
-		spin_unlock(&ast_queue_lock);
-
-		do_cast = (type & AST_COMP) && castfn;
-		do_bast = (type & AST_BAST) && bastfn;
-
-		/* Skip a bast if its blocking mode is compatible with the
-		   granted mode of the preceding cast. */
-
-		if (do_bast) {
-			if (first == AST_COMP)
-				last_castmode = castmode;
-			else
-				last_castmode = lkb->lkb_castmode_done;
-			if (dlm_modes_compat(bastmode, last_castmode))
-				do_bast = 0;
-		}
+	mutex_lock(&lkb->lkb_cb_mutex);
+	prev_seq = lkb->lkb_callbacks[0].seq;
+
+	rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, new_seq);
+	if (rv < 0)
+		goto out;
+
+	if (!prev_seq) {
+		kref_get(&lkb->lkb_ref);
 
-		if (first == AST_COMP) {
-			if (do_cast)
-				castfn(lkb->lkb_astparam);
-			if (do_bast)
-				bastfn(lkb->lkb_astparam, bastmode);
-		} else if (first == AST_BAST) {
-			if (do_bast)
-				bastfn(lkb->lkb_astparam, bastmode);
-			if (do_cast)
-				castfn(lkb->lkb_astparam);
+		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 {
-			log_error(ls, "bad ast_first %d ast_type %d",
-				  first, type);
+			queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
 		}
+	}
+ out:
+	mutex_unlock(&lkb->lkb_cb_mutex);
+}
 
-		if (do_cast)
-			lkb->lkb_castmode_done = castmode;
-		if (do_bast)
-			lkb->lkb_bastmode_done = bastmode;
+void dlm_callback_work(struct work_struct *work)
+{
+	struct dlm_lkb *lkb = container_of(work, struct dlm_lkb, lkb_cb_work);
+	struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+	void (*castfn) (void *astparam);
+	void (*bastfn) (void *astparam, int mode);
+	struct dlm_callback callbacks[DLM_CALLBACKS_SIZE];
+	int i, rv, resid;
 
-		/* this removes the reference added by dlm_add_ast
-		   and may result in the lkb being freed */
-		dlm_put_lkb(lkb);
+	memset(&callbacks, 0, sizeof(callbacks));
 
-		cond_resched();
-		goto repeat;
+	mutex_lock(&lkb->lkb_cb_mutex);
+	if (!lkb->lkb_callbacks[0].seq) {
+		/* no callback work exists, shouldn't happen */
+		log_error(ls, "dlm_callback_work %x no work", lkb->lkb_id);
+		dlm_print_lkb(lkb);
+		dlm_dump_lkb_callbacks(lkb);
 	}
-	spin_unlock(&ast_queue_lock);
-}
 
-static inline int no_asts(void)
-{
-	int ret;
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid);
+		if (rv < 0)
+			break;
+	}
 
-	spin_lock(&ast_queue_lock);
-	ret = list_empty(&ast_queue);
-	spin_unlock(&ast_queue_lock);
-	return ret;
-}
+	if (resid) {
+		/* cbs remain, loop should have removed all, shouldn't happen */
+		log_error(ls, "dlm_callback_work %x resid %d", lkb->lkb_id,
+			  resid);
+		dlm_print_lkb(lkb);
+		dlm_dump_lkb_callbacks(lkb);
+	}
+	mutex_unlock(&lkb->lkb_cb_mutex);
 
-static int dlm_astd(void *data)
-{
-	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (!test_bit(WAKE_ASTS, &astd_wakeflags))
-			schedule();
-		set_current_state(TASK_RUNNING);
+	castfn = lkb->lkb_astfn;
+	bastfn = lkb->lkb_bastfn;
 
-		mutex_lock(&astd_running);
-		if (test_and_clear_bit(WAKE_ASTS, &astd_wakeflags))
-			process_asts();
-		mutex_unlock(&astd_running);
+	for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
+		if (!callbacks[i].seq)
+			break;
+		if (callbacks[i].flags & DLM_CB_SKIP) {
+			continue;
+		} else if (callbacks[i].flags & DLM_CB_BAST) {
+			bastfn(lkb->lkb_astparam, callbacks[i].mode);
+		} else if (callbacks[i].flags & DLM_CB_CAST) {
+			lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
+			lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
+			castfn(lkb->lkb_astparam);
+		}
 	}
-	return 0;
+
+	/* undo kref_get from dlm_add_callback, may cause lkb to be freed */
+	dlm_put_lkb(lkb);
 }
 
-void dlm_astd_wake(void)
+int dlm_callback_start(struct dlm_ls *ls)
 {
-	if (!no_asts()) {
-		set_bit(WAKE_ASTS, &astd_wakeflags);
-		wake_up_process(astd_task);
+	ls->ls_callback_wq = alloc_workqueue("dlm_callback",
+					     WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+	if (!ls->ls_callback_wq) {
+		log_print("can't start dlm_callback workqueue");
+		return -ENOMEM;
 	}
+	return 0;
 }
 
-int dlm_astd_start(void)
+void dlm_callback_stop(struct dlm_ls *ls)
 {
-	struct task_struct *p;
-	int error = 0;
-
-	INIT_LIST_HEAD(&ast_queue);
-	spin_lock_init(&ast_queue_lock);
-	mutex_init(&astd_running);
-
-	p = kthread_run(dlm_astd, NULL, "dlm_astd");
-	if (IS_ERR(p))
-		error = PTR_ERR(p);
-	else
-		astd_task = p;
-	return error;
+	if (ls->ls_callback_wq)
+		destroy_workqueue(ls->ls_callback_wq);
 }
 
-void dlm_astd_stop(void)
+void dlm_callback_suspend(struct dlm_ls *ls)
 {
-	kthread_stop(astd_task);
-}
+	set_bit(LSFL_CB_DELAY, &ls->ls_flags);
 
-void dlm_astd_suspend(void)
-{
-	mutex_lock(&astd_running);
+	if (ls->ls_callback_wq)
+		flush_workqueue(ls->ls_callback_wq);
 }
 
-void dlm_astd_resume(void)
+void dlm_callback_resume(struct dlm_ls *ls)
 {
-	mutex_unlock(&astd_running);
+	struct dlm_lkb *lkb, *safe;
+	int count = 0;
+
+	clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
+	if (!ls->ls_callback_wq)
+		return;
+
+	mutex_lock(&ls->ls_cb_mutex);
+	list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
+		list_del_init(&lkb->lkb_cb_list);
+		queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
+		count++;
+	}
+	mutex_unlock(&ls->ls_cb_mutex);
+
+	if (count)
+		log_rinfo(ls, "dlm_callback_resume %d", count);
 }