1 files changed, 149 insertions, 96 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index dd13eb81ee40..c7367ae5a3e6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -33,17 +33,6 @@
 #include "volumes.h"
 #include "async-thread.h"
 
-struct map_lookup {
-	u64 type;
-	int io_align;
-	int io_width;
-	int stripe_len;
-	int sector_size;
-	int num_stripes;
-	int sub_stripes;
-	struct btrfs_bio_stripe stripes[];
-};
-
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				struct btrfs_device *device);
@@ -162,22 +151,25 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	struct bio *cur;
 	int again = 0;
 	unsigned long num_run;
-	unsigned long num_sync_run;
 	unsigned long batch_run = 0;
 	unsigned long limit;
 	unsigned long last_waited = 0;
 	int force_reg = 0;
+	struct blk_plug plug;
+
+	/*
+	 * this function runs all the bios we've collected for
+	 * a particular device.  We don't want to wander off to
+	 * another device without first sending all of these down.
+	 * So, setup a plug here and finish it off before we return
+	 */
+	blk_start_plug(&plug);
 
 	bdi = blk_get_backing_dev_info(device->bdev);
 	fs_info = device->dev_root->fs_info;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
-	/* we want to make sure that every time we switch from the sync
-	 * list to the normal list, we unplug
-	 */
-	num_sync_run = 0;
-
 loop:
 	spin_lock(&device->io_lock);
 
@@ -223,15 +215,6 @@ loop_lock:
 
 	spin_unlock(&device->io_lock);
 
-	/*
-	 * if we're doing the regular priority list, make sure we unplug
-	 * for any high prio bios we've sent down
-	 */
-	if (pending_bios == &device->pending_bios && num_sync_run > 0) {
-		num_sync_run = 0;
-		blk_run_backing_dev(bdi, NULL);
-	}
-
 	while (pending) {
 
 		rmb();
@@ -259,19 +242,11 @@ loop_lock:
 
 		BUG_ON(atomic_read(&cur->bi_cnt) == 0);
 
-		if (cur->bi_rw & REQ_SYNC)
-			num_sync_run++;
-
 		submit_bio(cur->bi_rw, cur);
 		num_run++;
 		batch_run++;
-		if (need_resched()) {
-			if (num_sync_run) {
-				blk_run_backing_dev(bdi, NULL);
-				num_sync_run = 0;
-			}
+		if (need_resched())
 			cond_resched();
-		}
 
 		/*
 		 * we made progress, there is more work to do and the bdi
@@ -304,13 +279,8 @@ loop_lock:
 				 * against it before looping
 				 */
 				last_waited = ioc->last_waited;
-				if (need_resched()) {
-					if (num_sync_run) {
-						blk_run_backing_dev(bdi, NULL);
-						num_sync_run = 0;
-					}
+				if (need_resched())
 					cond_resched();
-				}
 				continue;
 			}
 			spin_lock(&device->io_lock);
@@ -323,22 +293,6 @@ loop_lock:
 		}
 	}
 
-	if (num_sync_run) {
-		num_sync_run = 0;
-		blk_run_backing_dev(bdi, NULL);
-	}
-	/*
-	 * IO has already been through a long path to get here.  Checksumming,
-	 * async helper threads, perhaps compression.  We've done a pretty
-	 * good job of collecting a batch of IO and should just unplug
-	 * the device right away.
-	 *
-	 * This will help anyone who is waiting on the IO, they might have
-	 * already unplugged, but managed to do so before the bio they
-	 * cared about found its way down here.
-	 */
-	blk_run_backing_dev(bdi, NULL);
-
 	cond_resched();
 	if (again)
 		goto loop;
@@ -349,6 +303,7 @@ loop_lock:
 	spin_unlock(&device->io_lock);
 
 done:
+	blk_finish_plug(&plug);
 	return 0;
 }
 
@@ -1923,6 +1878,8 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
 
 	BUG_ON(ret);
 
+	trace_btrfs_chunk_free(root, map, chunk_offset, em->len);
+
 	if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		ret = btrfs_del_sys_chunk(root, chunk_objectid, chunk_offset);
 		BUG_ON(ret);
@@ -2650,6 +2607,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	*num_bytes = chunk_bytes_by_type(type, calc_size,
 					 map->num_stripes, sub_stripes);
 
+	trace_btrfs_chunk_alloc(info->chunk_root, map, start, *num_bytes);
+
 	em = alloc_extent_map(GFP_NOFS);
 	if (!em) {
 		ret = -ENOMEM;
@@ -2758,6 +2717,7 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans,
 					     item_size);
 		BUG_ON(ret);
 	}
+
 	kfree(chunk);
 	return 0;
 }
@@ -2955,14 +2915,17 @@ static int find_live_mirror(struct map_lookup *map, int first, int num,
 static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 			     u64 logical, u64 *length,
 			     struct btrfs_multi_bio **multi_ret,
-			     int mirror_num, struct page *unplug_page)
+			     int mirror_num)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
 	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	u64 offset;
 	u64 stripe_offset;
+	u64 stripe_end_offset;
 	u64 stripe_nr;
+	u64 stripe_nr_orig;
+	u64 stripe_nr_end;
 	int stripes_allocated = 8;
 	int stripes_required = 1;
 	int stripe_index;
@@ -2971,7 +2934,7 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 	int max_errors = 0;
 	struct btrfs_multi_bio *multi = NULL;
 
-	if (multi_ret && !(rw & REQ_WRITE))
+	if (multi_ret && !(rw & (REQ_WRITE | REQ_DISCARD)))
 		stripes_allocated = 1;
 again:
 	if (multi_ret) {
@@ -2987,11 +2950,6 @@ again:
 	em = lookup_extent_mapping(em_tree, logical, *length);
 	read_unlock(&em_tree->lock);
 
-	if (!em && unplug_page) {
-		kfree(multi);
-		return 0;
-	}
-
 	if (!em) {
 		printk(KERN_CRIT "unable to find logical %llu len %llu\n",
 		       (unsigned long long)logical,
@@ -3017,7 +2975,15 @@ again:
 			max_errors = 1;
 		}
 	}
-	if (multi_ret && (rw & REQ_WRITE) &&
+	if (rw & REQ_DISCARD) {
+		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+				 BTRFS_BLOCK_GROUP_RAID1 |
+				 BTRFS_BLOCK_GROUP_DUP |
+				 BTRFS_BLOCK_GROUP_RAID10)) {
+			stripes_required = map->num_stripes;
+		}
+	}
+	if (multi_ret && (rw & (REQ_WRITE | REQ_DISCARD)) &&
 	    stripes_allocated < stripes_required) {
 		stripes_allocated = map->num_stripes;
 		free_extent_map(em);
@@ -3037,23 +3003,37 @@ again:
 	/* stripe_offset is the offset of this block in its stripe*/
 	stripe_offset = offset - stripe_offset;
 
-	if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 |
-			 BTRFS_BLOCK_GROUP_RAID10 |
-			 BTRFS_BLOCK_GROUP_DUP)) {
+	if (rw & REQ_DISCARD)
+		*length = min_t(u64, em->len - offset, *length);
+	else if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+			      BTRFS_BLOCK_GROUP_RAID1 |
+			      BTRFS_BLOCK_GROUP_RAID10 |
+			      BTRFS_BLOCK_GROUP_DUP)) {
 		/* we limit the length of each bio to what fits in a stripe */
 		*length = min_t(u64, em->len - offset,
-			      map->stripe_len - stripe_offset);
+				map->stripe_len - stripe_offset);
 	} else {
 		*length = em->len - offset;
 	}
 
-	if (!multi_ret && !unplug_page)
+	if (!multi_ret)
 		goto out;
 
 	num_stripes = 1;
 	stripe_index = 0;
-	if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
-		if (unplug_page || (rw & REQ_WRITE))
+	stripe_nr_orig = stripe_nr;
+	stripe_nr_end = (offset + *length + map->stripe_len - 1) &
+			(~(map->stripe_len - 1));
+	do_div(stripe_nr_end, map->stripe_len);
+	stripe_end_offset = stripe_nr_end * map->stripe_len -
+			    (offset + *length);
+	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+		if (rw & REQ_DISCARD)
+			num_stripes = min_t(u64, map->num_stripes,
+					    stripe_nr_end - stripe_nr_orig);
+		stripe_index = do_div(stripe_nr, map->num_stripes);
+	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
+		if (rw & (REQ_WRITE | REQ_DISCARD))
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -3064,7 +3044,7 @@ again:
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (rw & REQ_WRITE)
+		if (rw & (REQ_WRITE | REQ_DISCARD))
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -3075,8 +3055,12 @@ again:
 		stripe_index = do_div(stripe_nr, factor);
 		stripe_index *= map->sub_stripes;
 
-		if (unplug_page || (rw & REQ_WRITE))
+		if (rw & REQ_WRITE)
 			num_stripes = map->sub_stripes;
+		else if (rw & REQ_DISCARD)
+			num_stripes = min_t(u64, map->sub_stripes *
+					    (stripe_nr_end - stripe_nr_orig),
+					    map->num_stripes);
 		else if (mirror_num)
 			stripe_index += mirror_num - 1;
 		else {
@@ -3094,24 +3078,101 @@ again:
 	}
 	BUG_ON(stripe_index >= map->num_stripes);
 
-	for (i = 0; i < num_stripes; i++) {
-		if (unplug_page) {
-			struct btrfs_device *device;
-			struct backing_dev_info *bdi;
-
-			device = map->stripes[stripe_index].dev;
-			if (device->bdev) {
-				bdi = blk_get_backing_dev_info(device->bdev);
-				if (bdi->unplug_io_fn)
-					bdi->unplug_io_fn(bdi, unplug_page);
-			}
-		} else {
+	if (rw & REQ_DISCARD) {
+		for (i = 0; i < num_stripes; i++) {
 			multi->stripes[i].physical =
 				map->stripes[stripe_index].physical +
 				stripe_offset + stripe_nr * map->stripe_len;
 			multi->stripes[i].dev = map->stripes[stripe_index].dev;
+
+			if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
+				u64 stripes;
+				u32 last_stripe = 0;
+				int j;
+
+				div_u64_rem(stripe_nr_end - 1,
+					    map->num_stripes,
+					    &last_stripe);
+
+				for (j = 0; j < map->num_stripes; j++) {
+					u32 test;
+
+					div_u64_rem(stripe_nr_end - 1 - j,
+						    map->num_stripes, &test);
+					if (test == stripe_index)
+						break;
+				}
+				stripes = stripe_nr_end - 1 - j;
+				do_div(stripes, map->num_stripes);
+				multi->stripes[i].length = map->stripe_len *
+					(stripes - stripe_nr + 1);
+
+				if (i == 0) {
+					multi->stripes[i].length -=
+						stripe_offset;
+					stripe_offset = 0;
+				}
+				if (stripe_index == last_stripe)
+					multi->stripes[i].length -=
+						stripe_end_offset;
+			} else if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
+				u64 stripes;
+				int j;
+				int factor = map->num_stripes /
+					     map->sub_stripes;
+				u32 last_stripe = 0;
+
+				div_u64_rem(stripe_nr_end - 1,
+					    factor, &last_stripe);
+				last_stripe *= map->sub_stripes;
+
+				for (j = 0; j < factor; j++) {
+					u32 test;
+
+					div_u64_rem(stripe_nr_end - 1 - j,
+						    factor, &test);
+
+					if (test ==
+					    stripe_index / map->sub_stripes)
+						break;
+				}
+				stripes = stripe_nr_end - 1 - j;
+				do_div(stripes, factor);
+				multi->stripes[i].length = map->stripe_len *
+					(stripes - stripe_nr + 1);
+
+				if (i < map->sub_stripes) {
+					multi->stripes[i].length -=
+						stripe_offset;
+					if (i == map->sub_stripes - 1)
+						stripe_offset = 0;
+				}
+				if (stripe_index >= last_stripe &&
+				    stripe_index <= (last_stripe +
+						     map->sub_stripes - 1)) {
+					multi->stripes[i].length -=
+						stripe_end_offset;
+				}
+			} else
+				multi->stripes[i].length = *length;
+
+			stripe_index++;
+			if (stripe_index == map->num_stripes) {
+				/* This could only happen for RAID0/10 */
+				stripe_index = 0;
+				stripe_nr++;
+			}
+		}
+	} else {
+		for (i = 0; i < num_stripes; i++) {
+			multi->stripes[i].physical =
+				map->stripes[stripe_index].physical +
+				stripe_offset +
+				stripe_nr * map->stripe_len;
+			multi->stripes[i].dev =
+				map->stripes[stripe_index].dev;
+			stripe_index++;
 		}
-		stripe_index++;
 	}
 	if (multi_ret) {
 		*multi_ret = multi;
@@ -3128,7 +3189,7 @@ int btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw,
 		      struct btrfs_multi_bio **multi_ret, int mirror_num)
 {
 	return __btrfs_map_block(map_tree, rw, logical, length, multi_ret,
-				 mirror_num, NULL);
+				 mirror_num);
 }
 
 int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
@@ -3196,14 +3257,6 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
 	return 0;
 }
 
-int btrfs_unplug_page(struct btrfs_mapping_tree *map_tree,
-		      u64 logical, struct page *page)
-{
-	u64 length = PAGE_CACHE_SIZE;
-	return __btrfs_map_block(map_tree, READ, logical, &length,
-				 NULL, 0, page);
-}
-
 static void end_bio_multi_stripe(struct bio *bio, int err)
 {
 	struct btrfs_multi_bio *multi = bio->bi_private;