[patch v2 6/6] md: raid 10 supports TRIM

[Shaohua Li <shli@fusionio.com>]

[-- Attachment #1: md-raid10-discard-support.patch --]
[-- Type: text/plain, Size: 3859 bytes --]

This makes md raid 10 support TRIM.
If one disk supports discard and another not, or one has discard_zero_data and
another not, there could be inconsistent between data from such disks. But this
should not matter, discarded data is useless. This will add extra copy in rebuild
though.

Signed-off-by: Shaohua Li <shli@fusionio.com>
---
 drivers/md/raid10.c |   28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

Index: linux/drivers/md/raid10.c
===================================================================
--- linux.orig/drivers/md/raid10.c	2012-03-14 09:16:37.300435113 +0800
+++ linux/drivers/md/raid10.c	2012-03-14 09:33:44.017262275 +0800
@@ -800,7 +800,12 @@ static void flush_pending_writes(struct
 		while (bio) { /* submit pending writes */
 			struct bio *next = bio->bi_next;
 			bio->bi_next = NULL;
-			generic_make_request(bio);
+			if (unlikely((bio->bi_rw & REQ_DISCARD) &&
+			    !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+				/* Just ignore it */
+				bio_endio(bio, 0);
+			else
+				generic_make_request(bio);
 			bio = next;
 		}
 	} else
@@ -926,6 +931,7 @@ static void make_request(struct mddev *m
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
 	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
+	const unsigned long do_discard = (bio->bi_rw & (REQ_DISCARD | REQ_SECURE));
 	unsigned long flags;
 	struct md_rdev *blocked_rdev;
 	int plugged;
@@ -945,7 +951,7 @@ static void make_request(struct mddev *m
 		    conf->near_copies < conf->raid_disks)) {
 		struct bio_pair *bp;
 		/* Sanity check -- queue functions should prevent this happening */
-		if (bio->bi_vcnt != 1 ||
+		if ((bio->bi_vcnt != 1 && bio->bi_vcnt !=0) ||
 		    bio->bi_idx != 0)
 			goto bad_map;
 		/* This is a one page bio that upper layers
@@ -1241,7 +1247,7 @@ retry_write:
 				   conf->mirrors[d].rdev->data_offset);
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua;
+		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
@@ -1266,7 +1272,7 @@ retry_write:
 				   conf->mirrors[d].replacement->data_offset);
 		mbio->bi_bdev = conf->mirrors[d].replacement->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync | do_fua;
+		mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
@@ -1543,6 +1549,9 @@ static int raid10_add_disk(struct mddev
 	}
 
 	md_integrity_add_rdev(rdev, mddev);
+	if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
 	print_conf(conf);
 	return err;
 }
@@ -3214,6 +3223,7 @@ static int run(struct mddev *mddev)
 	struct mirror_info *disk;
 	struct md_rdev *rdev;
 	sector_t size;
+	bool discard_supported = false;
 
 	/*
 	 * copy the already verified devices into our private RAID10
@@ -3234,6 +3244,7 @@ static int run(struct mddev *mddev)
 	mddev->thread = conf->thread;
 	conf->thread = NULL;
 
+	blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
 	chunk_size = mddev->chunk_sectors << 9;
 	blk_queue_io_min(mddev->queue, chunk_size);
 	if (conf->raid_disks % conf->near_copies)
@@ -3273,7 +3284,16 @@ static int run(struct mddev *mddev)
 		}
 
 		disk->head_position = 0;
+
+		if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+			discard_supported = true;
 	}
+
+	if (discard_supported)
+		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	else
+		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+
 	/* need to check that every block has at least one working mirror */
 	if (!enough(conf, -1)) {
 		printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",