swap: discard while swapping only if SWAP_FLAG_DISCARD_PAGES

Considering the use cases where the swap device supports discard:
a) and can do it quickly;
b) but it's slow to do in small granularities (or concurrent with other
   I/O);
c) but the implementation is so horrendous that you don't even want to
   send one down;

And assuming that the sysadmin considers it useful to send the discards down
at all, we would (probably) want the following solutions:

  i. do the fine-grained discards for freed swap pages, if device is
     capable of doing so optimally;
 ii. do single-time (batched) swap area discards, either at swapon
     or via something like fstrim (not implemented yet);
iii. allow doing both single-time and fine-grained discards; or
 iv. turn it off completely (default behavior)

As implemented today, one can only enable/disable discards for swap, but
one cannot select, for instance, solution (ii) on a swap device like (b)
even though the single-time discard is regarded to be interesting, or
necessary to the workload because it would imply (1), and the device is
not capable of performing it optimally.

This patch addresses the scenario depicted above by introducing a way to
ensure the (probably) wanted solutions (i, ii, iii and iv) can be flexibly
flagged through swapon(8) to allow a sysadmin to select the best suitable
swap discard policy accordingly to system constraints.

This patch introduces SWAP_FLAG_DISCARD_PAGES and SWAP_FLAG_DISCARD_ONCE
new flags to allow more flexibe swap discard policies being flagged
through swapon(8).  The default behavior is to keep both single-time, or
batched, area discards (SWAP_FLAG_DISCARD_ONCE) and fine-grained discards
for page-clusters (SWAP_FLAG_DISCARD_PAGES) enabled, in order to keep
consistentcy with older kernel behavior, as well as maintain compatibility
with older swapon(8).  However, through the new introduced flags the best
suitable discard policy can be selected accordingly to any given swap
device constraint.

[akpm@linux-foundation.org: tweak comments]
Signed-off-by: Rafael Aquini <aquini@redhat.com>
Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Karel Zak <kzak@redhat.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/swap.h

@@ -20,10 +20,13 @@ struct bio;
 #define SWAP_FLAG_PREFER	0x8000	/* set if swap priority specified */
 #define SWAP_FLAG_PRIO_MASK	0x7fff
 #define SWAP_FLAG_PRIO_SHIFT	0
-#define SWAP_FLAG_DISCARD	0x10000 /* discard swap cluster after use */
+#define SWAP_FLAG_DISCARD	0x10000 /* enable discard for swap */
+#define SWAP_FLAG_DISCARD_ONCE	0x20000 /* discard swap area at swapon-time */
+#define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */
 
 #define SWAP_FLAGS_VALID	(SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \
-				 SWAP_FLAG_DISCARD)
+				 SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \
+				 SWAP_FLAG_DISCARD_PAGES)
 
 static inline int current_is_kswapd(void)
 {
@@ -147,14 +150,16 @@ struct swap_extent {
 enum {
 	SWP_USED	= (1 << 0),	/* is slot in swap_info[] used? */
 	SWP_WRITEOK	= (1 << 1),	/* ok to write to this swap?	*/
-	SWP_DISCARDABLE = (1 << 2),	/* swapon+blkdev support discard */
+	SWP_DISCARDABLE = (1 << 2),	/* blkdev support discard */
 	SWP_DISCARDING	= (1 << 3),	/* now discarding a free cluster */
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
 	SWP_FILE	= (1 << 7),	/* set after swap_activate success */
+	SWP_AREA_DISCARD = (1 << 8),	/* single-time swap area discards */
+	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 8),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 10),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL

mm/swapfile.c

@@ -212,7 +212,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 			si->cluster_nr = SWAPFILE_CLUSTER - 1;
 			goto checks;
 		}
-		if (si->flags & SWP_DISCARDABLE) {
+		if (si->flags & SWP_PAGE_DISCARD) {
 			/*
 			 * Start range check on racing allocations, in case
 			 * they overlap the cluster we eventually decide on
@@ -322,7 +322,7 @@ static unsigned long scan_swap_map(struct swap_info_struct *si,
 
 	if (si->lowest_alloc) {
 		/*
-		 * Only set when SWP_DISCARDABLE, and there's a scan
+		 * Only set when SWP_PAGE_DISCARD, and there's a scan
 		 * for a free cluster in progress or just completed.
 		 */
 		if (found_free_cluster) {
@@ -2016,6 +2016,20 @@ static int setup_swap_map_and_extents(struct swap_info_struct *p,
 	return nr_extents;
 }
 
+/*
+ * Helper to sys_swapon determining if a given swap
+ * backing device queue supports DISCARD operations.
+ */
+static bool swap_discardable(struct swap_info_struct *si)
+{
+	struct request_queue *q = bdev_get_queue(si->bdev);
+
+	if (!q || !blk_queue_discard(q))
+		return false;
+
+	return true;
+}
+
 SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct *p;
@@ -2123,8 +2137,37 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 			p->flags |= SWP_SOLIDSTATE;
 			p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
 		}
-		if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0)
-			p->flags |= SWP_DISCARDABLE;
+
+		if ((swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
+			/*
+			 * When discard is enabled for swap with no particular
+			 * policy flagged, we set all swap discard flags here in
+			 * order to sustain backward compatibility with older
+			 * swapon(8) releases.
+			 */
+			p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
+				     SWP_PAGE_DISCARD);
+
+			/*
+			 * By flagging sys_swapon, a sysadmin can tell us to
+			 * either do single-time area discards only, or to just
+			 * perform discards for released swap page-clusters.
+			 * Now it's time to adjust the p->flags accordingly.
+			 */
+			if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
+				p->flags &= ~SWP_PAGE_DISCARD;
+			else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
+				p->flags &= ~SWP_AREA_DISCARD;
+
+			/* issue a swapon-time discard if it's still required */
+			if (p->flags & SWP_AREA_DISCARD) {
+				int err = discard_swap(p);
+				if (unlikely(err))
+					printk(KERN_ERR
+					       "swapon: discard_swap(%p): %d\n",
+						p, err);
+			}
+		}
 	}
 
 	mutex_lock(&swapon_mutex);
@@ -2135,11 +2178,13 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	enable_swap_info(p, prio, swap_map, frontswap_map);
 
 	printk(KERN_INFO "Adding %uk swap on %s.  "
-			"Priority:%d extents:%d across:%lluk %s%s%s\n",
+			"Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
 		p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
 		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
 		(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
 		(p->flags & SWP_DISCARDABLE) ? "D" : "",
+		(p->flags & SWP_AREA_DISCARD) ? "s" : "",
+		(p->flags & SWP_PAGE_DISCARD) ? "c" : "",
 		(frontswap_map) ? "FS" : "");
 
 	mutex_unlock(&swapon_mutex);