fs: dlm: use a non-static queue for callbacks

This patch will introducde a queue implementation for callbacks by using
the Linux lists. The current callback queue handling is implemented by a
static limit of 6 entries, see DLM_CALLBACKS_SIZE. The sequence number
inside the callback structure was used to see if the entries inside the
static entry is valid or not. We don't need any sequence numbers anymore
with a dynamic datastructure with grows and shrinks during runtime to
offer such functionality.

We assume that every callback will be delivered to the DLM user if once
queued. Therefore the callback flag DLM_CB_SKIP was dropped and the
check for skipping bast was moved before worker handling and not skip
while the callback worker executes. This will reduce unnecessary queues
of the callback worker.

All last callback saves are pointers now and don't need to copied over.
There is a reference counter for callback structures which will care
about to free the callback structures at the right time if they are not
referenced anymore.
Signed-off-by: Alexander Aring <aahringo@redhat.com>
Signed-off-by: David Teigland <teigland@redhat.com>

fs/dlm/ast.h

@@ -11,13 +11,22 @@
 #ifndef __ASTD_DOT_H__
 #define __ASTD_DOT_H__
 
-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,
-                         struct dlm_callback *cb, int *resid);
+#define DLM_ENQUEUE_CALLBACK_NEED_SCHED	1
+#define DLM_ENQUEUE_CALLBACK_SUCCESS	0
+#define DLM_ENQUEUE_CALLBACK_FAILURE	-1
+int dlm_enqueue_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
+			     int status, uint32_t sbflags);
+#define DLM_DEQUEUE_CALLBACK_EMPTY	2
+#define DLM_DEQUEUE_CALLBACK_LAST	1
+#define DLM_DEQUEUE_CALLBACK_SUCCESS	0
+int dlm_dequeue_lkb_callback(struct dlm_lkb *lkb, struct dlm_callback **cb);
 void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
                 uint32_t sbflags);
+void dlm_callback_set_last_ptr(struct dlm_callback **from,
+			       struct dlm_callback *to);
 
+void dlm_release_callback(struct kref *ref);
+void dlm_purge_lkb_callbacks(struct dlm_lkb *lkb);
 void dlm_callback_work(struct work_struct *work);
 int dlm_callback_start(struct dlm_ls *ls);
 void dlm_callback_stop(struct dlm_ls *ls);

fs/dlm/debug_fs.c

@@ -246,7 +246,7 @@ static void print_format3_lock(struct seq_file *s, struct dlm_lkb *lkb,
 		   lkb->lkb_status,
 		   lkb->lkb_grmode,
 		   lkb->lkb_rqmode,
-		   lkb->lkb_last_bast.mode,
+		   lkb->lkb_last_bast_mode,
 		   rsb_lookup,
 		   lkb->lkb_wait_type,
 		   lkb->lkb_lvbseq,

fs/dlm/dlm_internal.h

@@ -211,6 +211,7 @@ struct dlm_args {
 #endif
 #define DLM_IFL_DEADLOCK_CANCEL	0x01000000
 #define DLM_IFL_STUB_MS		0x02000000 /* magic number for m_flags */
+#define DLM_IFL_NEED_SCHED	0x04000000
 /* least significant 2 bytes are message changed, they are full transmitted
  * but at receive side only the 2 bytes LSB will be set.
  *
@@ -222,18 +223,17 @@ struct dlm_args {
 #define DLM_IFL_USER		0x00000001
 #define DLM_IFL_ORPHAN		0x00000002
 
-#define DLM_CALLBACKS_SIZE	6
-
 #define DLM_CB_CAST		0x00000001
 #define DLM_CB_BAST		0x00000002
-#define DLM_CB_SKIP		0x00000004
 
 struct dlm_callback {
-	uint64_t		seq;
 	uint32_t		flags;		/* DLM_CBF_ */
 	int			sb_status;	/* copy to lksb status */
 	uint8_t			sb_flags;	/* copy to lksb flags */
 	int8_t			mode; /* rq mode of bast, gr mode of cast */
+
+	struct list_head	list;
+	struct kref		ref;
 };
 
 struct dlm_lkb {
@@ -271,9 +271,10 @@ struct dlm_lkb {
 	spinlock_t		lkb_cb_lock;
 	struct work_struct	lkb_cb_work;
 	struct list_head	lkb_cb_list; /* for ls_cb_delay or proc->asts */
-	struct dlm_callback	lkb_callbacks[DLM_CALLBACKS_SIZE];
-	struct dlm_callback	lkb_last_cast;
-	struct dlm_callback	lkb_last_bast;
+	struct list_head	lkb_callbacks;
+	struct dlm_callback	*lkb_last_cast;
+	struct dlm_callback	*lkb_last_cb;
+	int			lkb_last_bast_mode;
 	ktime_t			lkb_last_cast_time;	/* for debugging */
 	ktime_t			lkb_last_bast_time;	/* for debugging */
 

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);
@@ -1218,6 +1219,7 @@ 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);
+	INIT_LIST_HEAD(&lkb->lkb_callbacks);
 	spin_lock_init(&lkb->lkb_cb_lock);
 	INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
 
@@ -6221,8 +6223,7 @@ 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);
 	}
@@ -6263,8 +6264,7 @@ 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);
 	}

fs/dlm/memory.c

@@ -14,12 +14,14 @@
 #include "lowcomms.h"
 #include "config.h"
 #include "memory.h"
+#include "ast.h"
 
 static struct kmem_cache *writequeue_cache;
 static struct kmem_cache *mhandle_cache;
 static struct kmem_cache *msg_cache;
 static struct kmem_cache *lkb_cache;
 static struct kmem_cache *rsb_cache;
+static struct kmem_cache *cb_cache;
 
 
 int __init dlm_memory_init(void)
@@ -46,8 +48,16 @@ int __init dlm_memory_init(void)
 	if (!rsb_cache)
 		goto rsb;
 
+	cb_cache = kmem_cache_create("dlm_cb", sizeof(struct dlm_callback),
+				     __alignof__(struct dlm_callback), 0,
+				     NULL);
+	if (!rsb_cache)
+		goto cb;
+
 	return 0;
 
+cb:
+	kmem_cache_destroy(rsb_cache);
 rsb:
 	kmem_cache_destroy(msg_cache);
 msg:
@@ -67,6 +77,7 @@ void dlm_memory_exit(void)
 	kmem_cache_destroy(msg_cache);
 	kmem_cache_destroy(lkb_cache);
 	kmem_cache_destroy(rsb_cache);
+	kmem_cache_destroy(cb_cache);
 }
 
 char *dlm_allocate_lvb(struct dlm_ls *ls)
@@ -115,6 +126,11 @@ void dlm_free_lkb(struct dlm_lkb *lkb)
 			kfree(ua);
 		}
 	}
+
+	/* drop references if they are set */
+	dlm_callback_set_last_ptr(&lkb->lkb_last_cast, NULL);
+	dlm_callback_set_last_ptr(&lkb->lkb_last_cb, NULL);
+
 	kmem_cache_free(lkb_cache, lkb);
 }
 
@@ -147,3 +163,13 @@ void dlm_free_msg(struct dlm_msg *msg)
 {
 	kmem_cache_free(msg_cache, msg);
 }
+
+struct dlm_callback *dlm_allocate_cb(void)
+{
+	return kmem_cache_alloc(cb_cache, GFP_ATOMIC);
+}
+
+void dlm_free_cb(struct dlm_callback *cb)
+{
+	kmem_cache_free(cb_cache, cb);
+}

fs/dlm/memory.h

@@ -26,6 +26,8 @@ struct writequeue_entry *dlm_allocate_writequeue(void);
 void dlm_free_writequeue(struct writequeue_entry *writequeue);
 struct dlm_msg *dlm_allocate_msg(gfp_t allocation);
 void dlm_free_msg(struct dlm_msg *msg);
+struct dlm_callback *dlm_allocate_cb(void);
+void dlm_free_cb(struct dlm_callback *cb);
 
 #endif		/* __MEMORY_DOT_H__ */
 

fs/dlm/user.c

@@ -25,6 +25,7 @@
 #include "user.h"
 #include "ast.h"
 #include "config.h"
+#include "memory.h"
 
 static const char name_prefix[] = "dlm";
 static const struct file_operations device_fops;
@@ -175,7 +176,7 @@ static int lkb_is_endoflife(int mode, int status)
    being removed and then remove that lkb from the orphans list and free it */
 
 void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
-		      int status, uint32_t sbflags, uint64_t seq)
+		      int status, uint32_t sbflags)
 {
 	struct dlm_ls *ls;
 	struct dlm_user_args *ua;
@@ -209,16 +210,22 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
 
 	spin_lock(&proc->asts_spin);
 
-	rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, seq);
-	if (rv < 0) {
+	rv = dlm_enqueue_lkb_callback(lkb, flags, mode, status, sbflags);
+	switch (rv) {
+	case DLM_ENQUEUE_CALLBACK_FAILURE:
 		spin_unlock(&proc->asts_spin);
+		WARN_ON(1);
 		goto out;
-	}
-
-	if (list_empty(&lkb->lkb_cb_list)) {
+	case DLM_ENQUEUE_CALLBACK_NEED_SCHED:
 		kref_get(&lkb->lkb_ref);
 		list_add_tail(&lkb->lkb_cb_list, &proc->asts);
 		wake_up_interruptible(&proc->wait);
+		break;
+	case DLM_ENQUEUE_CALLBACK_SUCCESS:
+		break;
+	default:
+		WARN_ON(1);
+		break;
 	}
 	spin_unlock(&proc->asts_spin);
 
@@ -800,8 +807,8 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 	struct dlm_user_proc *proc = file->private_data;
 	struct dlm_lkb *lkb;
 	DECLARE_WAITQUEUE(wait, current);
-	struct dlm_callback cb;
-	int rv, resid, copy_lvb = 0;
+	struct dlm_callback *cb;
+	int rv, copy_lvb = 0;
 	int old_mode, new_mode;
 
 	if (count == sizeof(struct dlm_device_version)) {
@@ -860,50 +867,56 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
 	lkb = list_first_entry(&proc->asts, struct dlm_lkb, lkb_cb_list);
 
 	/* rem_lkb_callback sets a new lkb_last_cast */
-	old_mode = lkb->lkb_last_cast.mode;
+	old_mode = lkb->lkb_last_cast->mode;
 
-	rv = dlm_rem_lkb_callback(lkb->lkb_resource->res_ls, lkb, &cb, &resid);
-	if (rv < 0) {
+	rv = dlm_dequeue_lkb_callback(lkb, &cb);
+	switch (rv) {
+	case DLM_DEQUEUE_CALLBACK_EMPTY:
 		/* this shouldn't happen; lkb should have been removed from
-		   list when resid was zero */
+		 * list when last item was dequeued
+		 */
 		log_print("dlm_rem_lkb_callback empty %x", lkb->lkb_id);
 		list_del_init(&lkb->lkb_cb_list);
 		spin_unlock(&proc->asts_spin);
 		/* removes ref for proc->asts, may cause lkb to be freed */
 		dlm_put_lkb(lkb);
+		WARN_ON(1);
 		goto try_another;
-	}
-	if (!resid)
+	case DLM_DEQUEUE_CALLBACK_LAST:
 		list_del_init(&lkb->lkb_cb_list);
-	spin_unlock(&proc->asts_spin);
-
-	if (cb.flags & DLM_CB_SKIP) {
-		/* removes ref for proc->asts, may cause lkb to be freed */
-		if (!resid)
-			dlm_put_lkb(lkb);
-		goto try_another;
+		/* TODO */
+		lkb->lkb_flags &= ~DLM_IFL_NEED_SCHED;
+		break;
+	case DLM_DEQUEUE_CALLBACK_SUCCESS:
+		break;
+	default:
+		WARN_ON(1);
+		break;
 	}
+	spin_unlock(&proc->asts_spin);
 
-	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->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 &&
+		if (!cb->sb_status && lkb->lkb_lksb->sb_lvbptr &&
 		    dlm_lvb_operations[old_mode + 1][new_mode + 1])
 			copy_lvb = 1;
 
-		lkb->lkb_lksb->sb_status = cb.sb_status;
-		lkb->lkb_lksb->sb_flags = cb.sb_flags;
+		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,
 				 test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags),
-				 cb.flags, cb.mode, copy_lvb, buf, count);
+				 cb->flags, cb->mode, copy_lvb, buf, count);
+
+	kref_put(&cb->ref, dlm_release_callback);
 
 	/* removes ref for proc->asts, may cause lkb to be freed */
-	if (!resid)
+	if (rv == DLM_DEQUEUE_CALLBACK_LAST)
 		dlm_put_lkb(lkb);
 
 	return rv;

fs/dlm/user.h

@@ -7,7 +7,7 @@
 #define __USER_DOT_H__
 
 void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
-                      int status, uint32_t sbflags, uint64_t seq);
+		      int status, uint32_t sbflags);
 int dlm_user_init(void);
 void dlm_user_exit(void);
 int dlm_device_deregister(struct dlm_ls *ls);