frontswap: get rid of swap_lock dependency

Frontswap initialization routine depends on swap_lock, which want to be
atomic about frontswap's first appearance.  IOW, frontswap is not present
and will fail all calls OR frontswap is fully functional but if new
swap_info_struct isn't registered by enable_swap_info, swap subsystem
doesn't start I/O so there is no race between init procedure and page I/O
working on frontswap.

So let's remove unnecessary swap_lock dependency.

Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
[v1: Rebased on my branch, reworked to work with backends loading late]
[v2: Added a check for !map]
[v3: Made the invalidate path follow the init path]
[v4: Address comments by Wanpeng Li <liwanp@linux.vnet.ibm.com>]
Signed-off-by: Konrad Rzeszutek Wilk <konrad@darnok.org>
Signed-off-by: Bob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/frontswap.h

@@ -23,7 +23,7 @@ extern void frontswap_writethrough(bool);
 extern void frontswap_tmem_exclusive_gets(bool);
 
 extern bool __frontswap_test(struct swap_info_struct *, pgoff_t);
-extern void __frontswap_init(unsigned type);
+extern void __frontswap_init(unsigned type, unsigned long *map);
 extern int __frontswap_store(struct page *page);
 extern int __frontswap_load(struct page *page);
 extern void __frontswap_invalidate_page(unsigned, pgoff_t);
@@ -98,10 +98,10 @@ static inline void frontswap_invalidate_area(unsigned type)
 		__frontswap_invalidate_area(type);
 }
 
-static inline void frontswap_init(unsigned type)
+static inline void frontswap_init(unsigned type, unsigned long *map)
 {
 	if (frontswap_enabled)
-		__frontswap_init(type);
+		__frontswap_init(type, map);
 }
 
 #endif /* _LINUX_FRONTSWAP_H */

mm/frontswap.c

@@ -121,9 +121,14 @@ struct frontswap_ops *frontswap_register_ops(struct frontswap_ops *ops)
 	int i;
 
 	for (i = 0; i < MAX_SWAPFILES; i++) {
-		if (test_and_clear_bit(i, need_init))
+		if (test_and_clear_bit(i, need_init)) {
+			struct swap_info_struct *sis = swap_info[i];
+			/* __frontswap_init _should_ have set it! */
+			if (!sis->frontswap_map)
+				return ERR_PTR(-EINVAL);
 			ops->init(i);
 		}
+	}
 	/*
 	 * We MUST have frontswap_ops set _after_ the frontswap_init's
 	 * have been called. Otherwise __frontswap_store might fail. Hence
@@ -156,20 +161,30 @@ EXPORT_SYMBOL(frontswap_tmem_exclusive_gets);
 /*
  * Called when a swap device is swapon'd.
  */
-void __frontswap_init(unsigned type)
+void __frontswap_init(unsigned type, unsigned long *map)
 {
 	struct swap_info_struct *sis = swap_info[type];
 
-	if (frontswap_ops) {
 	BUG_ON(sis == NULL);
-		if (sis->frontswap_map == NULL)
+
+	/*
+	 * p->frontswap is a bitmap that we MUST have to figure out which page
+	 * has gone in frontswap. Without it there is no point of continuing.
+	 */
+	if (WARN_ON(!map))
 		return;
+	/*
+	 * Irregardless of whether the frontswap backend has been loaded
+	 * before this function or it will be later, we _MUST_ have the
+	 * p->frontswap set to something valid to work properly.
+	 */
+	frontswap_map_set(sis, map);
+	if (frontswap_ops)
 		frontswap_ops->init(type);
-	} else {
+	else {
 		BUG_ON(type > MAX_SWAPFILES);
 		set_bit(type, need_init);
 	}
-
 }
 EXPORT_SYMBOL(__frontswap_init);
 

mm/swapfile.c

@@ -1509,8 +1509,7 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 }
 
 static void _enable_swap_info(struct swap_info_struct *p, int prio,
-				unsigned char *swap_map,
-				unsigned long *frontswap_map)
+				unsigned char *swap_map)
 {
 	int i, prev;
 
@@ -1519,7 +1518,6 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	else
 		p->prio = --least_priority;
 	p->swap_map = swap_map;
-	frontswap_map_set(p, frontswap_map);
 	p->flags |= SWP_WRITEOK;
 	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
@@ -1542,10 +1540,10 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				unsigned long *frontswap_map)
 {
+	frontswap_init(p->type, frontswap_map);
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	_enable_swap_info(p, prio, swap_map, frontswap_map);
-	frontswap_init(p->type);
+	 _enable_swap_info(p, prio, swap_map);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -1554,7 +1552,7 @@ static void reinsert_swap_info(struct swap_info_struct *p)
 {
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	_enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
+	_enable_swap_info(p, p->prio, p->swap_map);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -1563,6 +1561,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct *p = NULL;
 	unsigned char *swap_map;
+	unsigned long *frontswap_map;
 	struct file *swap_file, *victim;
 	struct address_space *mapping;
 	struct inode *inode;
@@ -1662,12 +1661,14 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	swap_map = p->swap_map;
 	p->swap_map = NULL;
 	p->flags = 0;
-	frontswap_invalidate_area(type);
+	frontswap_map = frontswap_map_get(p);
+	frontswap_map_set(p, NULL);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
+	frontswap_invalidate_area(type);
 	mutex_unlock(&swapon_mutex);
 	vfree(swap_map);
-	vfree(frontswap_map_get(p));
+	vfree(frontswap_map);
 	/* Destroy swap account informatin */
 	swap_cgroup_swapoff(type);