swap: change swap_list_head to plist, add swap_avail_head

Originally get_swap_page() started iterating through the singly-linked
list of swap_info_structs using swap_list.next or highest_priority_index,
which both were intended to point to the highest priority active swap
target that was not full.  The first patch in this series changed the
singly-linked list to a doubly-linked list, and removed the logic to start
at the highest priority non-full entry; it starts scanning at the highest
priority entry each time, even if the entry is full.

Replace the manually ordered swap_list_head with a plist, swap_active_head.
Add a new plist, swap_avail_head.  The original swap_active_head plist
contains all active swap_info_structs, as before, while the new
swap_avail_head plist contains only swap_info_structs that are active and
available, i.e. not full.  Add a new spinlock, swap_avail_lock, to protect
the swap_avail_head list.

Mel Gorman suggested using plists since they internally handle ordering
the list entries based on priority, which is exactly what swap was doing
manually.  All the ordering code is now removed, and swap_info_struct
entries and simply added to their corresponding plist and automatically
ordered correctly.

Using a new plist for available swap_info_structs simplifies and
optimizes get_swap_page(), which no longer has to iterate over full
swap_info_structs.  Using a new spinlock for swap_avail_head plist
allows each swap_info_struct to add or remove themselves from the
plist when they become full or not-full; previously they could not
do so because the swap_info_struct->lock is held when they change
from full<->not-full, and the swap_lock protecting the main
swap_active_head must be ordered before any swap_info_struct->lock.

Signed-off-by: Dan Streetman <ddstreet@ieee.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 91 insertions, 54 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6c95a8c63b1a..beeeef8a1b2d 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -61,7 +61,22 @@ static const char Unused_offset[] = "Unused swap offset entry ";
  * all active swap_info_structs
  * protected with swap_lock, and ordered by priority.
  */
-LIST_HEAD(swap_list_head);
+PLIST_HEAD(swap_active_head);
+
+/*
+ * all available (active, not full) swap_info_structs
+ * protected with swap_avail_lock, ordered by priority.
+ * This is used by get_swap_page() instead of swap_active_head
+ * because swap_active_head includes all swap_info_structs,
+ * but get_swap_page() doesn't need to look at full ones.
+ * This uses its own lock instead of swap_lock because when a
+ * swap_info_struct changes between not-full/full, it needs to
+ * add/remove itself to/from this list, but the swap_info_struct->lock
+ * is held and the locking order requires swap_lock to be taken
+ * before any swap_info_struct->lock.
+ */
+static PLIST_HEAD(swap_avail_head);
+static DEFINE_SPINLOCK(swap_avail_lock);
 
 struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
@@ -594,6 +609,9 @@ checks:
 	if (si->inuse_pages == si->pages) {
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
+		spin_lock(&swap_avail_lock);
+		plist_del(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 	}
 	si->swap_map[offset] = usage;
 	inc_cluster_info_page(si, si->cluster_info, offset);
@@ -645,57 +663,63 @@ swp_entry_t get_swap_page(void)
 {
 	struct swap_info_struct *si, *next;
 	pgoff_t offset;
-	struct list_head *tmp;
 
-	spin_lock(&swap_lock);
 	if (atomic_long_read(&nr_swap_pages) <= 0)
 		goto noswap;
 	atomic_long_dec(&nr_swap_pages);
 
-	list_for_each(tmp, &swap_list_head) {
-		si = list_entry(tmp, typeof(*si), list);
+	spin_lock(&swap_avail_lock);
+
+start_over:
+	plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) {
+		/* requeue si to after same-priority siblings */
+		plist_requeue(&si->avail_list, &swap_avail_head);
+		spin_unlock(&swap_avail_lock);
 		spin_lock(&si->lock);
 		if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) {
+			spin_lock(&swap_avail_lock);
+			if (plist_node_empty(&si->avail_list)) {
+				spin_unlock(&si->lock);
+				goto nextsi;
+			}
+			WARN(!si->highest_bit,
+			     "swap_info %d in list but !highest_bit\n",
+			     si->type);
+			WARN(!(si->flags & SWP_WRITEOK),
+			     "swap_info %d in list but !SWP_WRITEOK\n",
+			     si->type);
+			plist_del(&si->avail_list, &swap_avail_head);
 			spin_unlock(&si->lock);
-			continue;
+			goto nextsi;
 		}
 
-		/*
-		 * rotate the current swap_info that we're going to use
-		 * to after any other swap_info that have the same prio,
-		 * so that all equal-priority swap_info get used equally
-		 */
-		next = si;
-		list_for_each_entry_continue(next, &swap_list_head, list) {
-			if (si->prio != next->prio)
-				break;
-			list_rotate_left(&si->list);
-			next = si;
-		}
-
-		spin_unlock(&swap_lock);
 		/* This is called for allocating swap entry for cache */
 		offset = scan_swap_map(si, SWAP_HAS_CACHE);
 		spin_unlock(&si->lock);
 		if (offset)
 			return swp_entry(si->type, offset);
-		spin_lock(&swap_lock);
+		pr_debug("scan_swap_map of si %d failed to find offset\n",
+		       si->type);
+		spin_lock(&swap_avail_lock);
+nextsi:
 		/*
 		 * if we got here, it's likely that si was almost full before,
 		 * and since scan_swap_map() can drop the si->lock, multiple
 		 * callers probably all tried to get a page from the same si
-		 * and it filled up before we could get one.  So we need to
-		 * try again.  Since we dropped the swap_lock, there may now
-		 * be non-full higher priority swap_infos, and this si may have
-		 * even been removed from the list (although very unlikely).
-		 * Let's start over.
+		 * and it filled up before we could get one; or, the si filled
+		 * up between us dropping swap_avail_lock and taking si->lock.
+		 * Since we dropped the swap_avail_lock, the swap_avail_head
+		 * list may have been modified; so if next is still in the
+		 * swap_avail_head list then try it, otherwise start over.
 		 */
-		tmp = &swap_list_head;
+		if (plist_node_empty(&next->avail_list))
+			goto start_over;
 	}
 
+	spin_unlock(&swap_avail_lock);
+
 	atomic_long_inc(&nr_swap_pages);
 noswap:
-	spin_unlock(&swap_lock);
 	return (swp_entry_t) {0};
 }
 
@@ -798,8 +822,18 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 		dec_cluster_info_page(p, p->cluster_info, offset);
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
-		if (offset > p->highest_bit)
+		if (offset > p->highest_bit) {
+			bool was_full = !p->highest_bit;
 			p->highest_bit = offset;
+			if (was_full && (p->flags & SWP_WRITEOK)) {
+				spin_lock(&swap_avail_lock);
+				WARN_ON(!plist_node_empty(&p->avail_list));
+				if (plist_node_empty(&p->avail_list))
+					plist_add(&p->avail_list,
+						  &swap_avail_head);
+				spin_unlock(&swap_avail_lock);
+			}
+		}
 		atomic_long_inc(&nr_swap_pages);
 		p->inuse_pages--;
 		frontswap_invalidate_page(p->type, offset);
@@ -1734,12 +1768,16 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info)
 {
-	struct swap_info_struct *si;
-
 	if (prio >= 0)
 		p->prio = prio;
 	else
 		p->prio = --least_priority;
+	/*
+	 * the plist prio is negated because plist ordering is
+	 * low-to-high, while swap ordering is high-to-low
+	 */
+	p->list.prio = -p->prio;
+	p->avail_list.prio = -p->prio;
 	p->swap_map = swap_map;
 	p->cluster_info = cluster_info;
 	p->flags |= SWP_WRITEOK;
@@ -1747,27 +1785,20 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	total_swap_pages += p->pages;
 
 	assert_spin_locked(&swap_lock);
-	BUG_ON(!list_empty(&p->list));
-	/*
-	 * insert into swap list; the list is in priority order,
-	 * so that get_swap_page() can get a page from the highest
-	 * priority swap_info_struct with available page(s), and
-	 * swapoff can adjust the auto-assigned (i.e. negative) prio
-	 * values for any lower-priority swap_info_structs when
-	 * removing a negative-prio swap_info_struct
-	 */
-	list_for_each_entry(si, &swap_list_head, list) {
-		if (p->prio >= si->prio) {
-			list_add_tail(&p->list, &si->list);
-			return;
-		}
-	}
 	/*
-	 * this covers two cases:
-	 * 1) p->prio is less than all existing prio
-	 * 2) the swap list is empty
+	 * both lists are plists, and thus priority ordered.
+	 * swap_active_head needs to be priority ordered for swapoff(),
+	 * which on removal of any swap_info_struct with an auto-assigned
+	 * (i.e. negative) priority increments the auto-assigned priority
+	 * of any lower-priority swap_info_structs.
+	 * swap_avail_head needs to be priority ordered for get_swap_page(),
+	 * which allocates swap pages from the highest available priority
+	 * swap_info_struct.
 	 */
-	list_add_tail(&p->list, &swap_list_head);
+	plist_add(&p->list, &swap_active_head);
+	spin_lock(&swap_avail_lock);
+	plist_add(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 }
 
 static void enable_swap_info(struct swap_info_struct *p, int prio,
@@ -1821,7 +1852,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	mapping = victim->f_mapping;
 	spin_lock(&swap_lock);
-	list_for_each_entry(p, &swap_list_head, list) {
+	plist_for_each_entry(p, &swap_active_head, list) {
 		if (p->flags & SWP_WRITEOK) {
 			if (p->swap_file->f_mapping == mapping) {
 				found = 1;
@@ -1841,16 +1872,21 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 		spin_unlock(&swap_lock);
 		goto out_dput;
 	}
+	spin_lock(&swap_avail_lock);
+	plist_del(&p->avail_list, &swap_avail_head);
+	spin_unlock(&swap_avail_lock);
 	spin_lock(&p->lock);
 	if (p->prio < 0) {
 		struct swap_info_struct *si = p;
 
-		list_for_each_entry_continue(si, &swap_list_head, list) {
+		plist_for_each_entry_continue(si, &swap_active_head, list) {
 			si->prio++;
+			si->list.prio--;
+			si->avail_list.prio--;
 		}
 		least_priority++;
 	}
-	list_del_init(&p->list);
+	plist_del(&p->list, &swap_active_head);
 	atomic_long_sub(p->pages, &nr_swap_pages);
 	total_swap_pages -= p->pages;
 	p->flags &= ~SWP_WRITEOK;
@@ -2115,7 +2151,8 @@ static struct swap_info_struct *alloc_swap_info(void)
 		 */
 	}
 	INIT_LIST_HEAD(&p->first_swap_extent.list);
-	INIT_LIST_HEAD(&p->list);
+	plist_node_init(&p->list, 0);
+	plist_node_init(&p->avail_list, 0);
 	p->flags = SWP_USED;
 	spin_unlock(&swap_lock);
 	spin_lock_init(&p->lock);