Btrfs: Batched discard support for btrfs

Thanks for your comments, here is the updated patch.
I've tested it with xfstests 251(thanks to Lukas), and it looks fine to me.

Signed-off-by Li Dongyang <[email protected]>

Reviewed-by David Sterba <[email protected]>

Reviewed-by Kurt Garloff <[email protected]>

---
Changelog V2:
*Check if we have devices support trim before trying to trim the fs, also adjust
minlen according to the discard_granularity.
*Update reserved extent calculations in btrfs_trim_block_group().
*Call cond_resched() without checking need_resched()
*Use bitmap_clear_bits() and unlink_free_space() instead of btrfs_remove_free_space(),
so we won't search the same extent for twice.
*Try harder in btrfs_discard_extent(), now we won't report errors
if it's not a EOPNOTSUPP.
*make sure the block group is cached before trimming it,or we'll see an empty caching
tree if the block group is not cached.
*Minor return value fix in btrfs_discard_block_group().

---
 fs/btrfs/ctree.h            |    5 ++-
 fs/btrfs/disk-io.c          |    5 ++-
 fs/btrfs/extent-tree.c      |  102 +++++++++++++++++++++++++++++++++----------
 fs/btrfs/free-space-cache.c |   92 ++++++++++++++++++++++++++++++++++++++
 fs/btrfs/free-space-cache.h |    2 +
 fs/btrfs/ioctl.c            |   47 ++++++++++++++++++++
 6 files changed, 227 insertions(+), 26 deletions(-)

fs/btrfs/ctree.h +4 -1

index 2c98b3a..5cbc05c 100644
@@ -2147,6 +2147,8 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      u64 root_objectid, u64 owner, u64 offset);
 
 int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len);
+int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
+				u64 num_bytes, int reserve, int sinfo);
 int btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,

@@ -2217,7 +2219,8 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_root *root,
 				   u64 start, u64 end);
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
-			       u64 num_bytes);
+			       u64 num_bytes, u64 *actual_bytes);
+int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,

fs/btrfs/disk-io.c +4 -1

index e1aa8d6..bcb9451 100644
@@ -2947,7 +2947,10 @@ static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
 			break;
 
 		/* opt_discard */
-		ret = btrfs_error_discard_extent(root, start, end + 1 - start);
+		if (btrfs_test_opt(root, DISCARD))
+			ret = btrfs_error_discard_extent(root, start,
+							 end + 1 - start,
+							 NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		btrfs_error_unpin_extent_range(root, start, end);

fs/btrfs/extent-tree.c +78 -24

index f3c96fc..38100c8 100644
@@ -36,8 +36,6 @@
 static int update_block_group(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      u64 bytenr, u64 num_bytes, int alloc);
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				 u64 num_bytes, int reserve, int sinfo);
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
 				u64 bytenr, u64 num_bytes, u64 parent,

@@ -442,7 +440,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	 * allocate blocks for the tree root we can't do the fast caching since
 	 * we likely hold important locks.
 	 */
-	if (!trans->transaction->in_commit &&
+	if (trans && (!trans->transaction->in_commit) &&
 	    (root && root != root->fs_info->tree_root)) {
 		spin_lock(&cache->lock);
 		if (cache->cached != BTRFS_CACHE_NO) {

@@ -1740,24 +1738,22 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static void btrfs_issue_discard(struct block_device *bdev,
+static int btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
 {
-	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
+	return blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL, 0);
 }
 
 static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
-				u64 num_bytes)
+				u64 num_bytes, u64 *actual_bytes)
 {
 	int ret;
 	u64 map_length = num_bytes;
+	u64 discarded_bytes = 0;
 	struct btrfs_multi_bio *multi = NULL;
 
-	if (!btrfs_test_opt(root, DISCARD))
-		return 0;
-
 	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(&root->fs_info->mapping_tree, READ,
+	ret = btrfs_map_block(&root->fs_info->mapping_tree, WRITE,
 			      bytenr, &map_length, &multi, 0);
 	if (!ret) {
 		struct btrfs_bio_stripe *stripe = multi->stripes;

@@ -1767,13 +1763,21 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 			map_length = num_bytes;
 
 		for (i = 0; i < multi->num_stripes; i++, stripe++) {
-			btrfs_issue_discard(stripe->dev->bdev,
-					    stripe->physical,
-					    map_length);
+			ret = btrfs_issue_discard(stripe->dev->bdev,
+						  stripe->physical,
+						  map_length);
+			if (!ret)
+				discarded_bytes += map_length;
 		}
 		kfree(multi);
 	}
 
+	if (discarded_bytes || ret == -EOPNOTSUPP)
+		ret = 0;
+
+	if (actual_bytes)
+		*actual_bytes = discarded_bytes;
+
 	return ret;
 }
 

@@ -4214,8 +4218,8 @@ int btrfs_pin_extent(struct btrfs_root *root,
  * update size of reserved extents. this function may return -EAGAIN
  * if 'reserve' is true or 'sinfo' is false.
  */
-static int update_reserved_bytes(struct btrfs_block_group_cache *cache,
-				 u64 num_bytes, int reserve, int sinfo)
+int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache,
+				u64 num_bytes, int reserve, int sinfo)
 {
 	int ret = 0;
 	if (sinfo) {

@@ -4353,7 +4357,8 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 		if (ret)
 			break;
 
-		ret = btrfs_discard_extent(root, start, end + 1 - start);
+		if (btrfs_test_opt(root, DISCARD))
+			ret = btrfs_discard_extent(root, start, end + 1 - start, NULL);
 
 		clear_extent_dirty(unpin, start, end, GFP_NOFS);
 		unpin_extent_range(root, start, end);

@@ -4694,10 +4699,10 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));
 
 		btrfs_add_free_space(cache, buf->start, buf->len);
-		ret = update_reserved_bytes(cache, buf->len, 0, 0);
+		ret = btrfs_update_reserved_bytes(cache, buf->len, 0, 0);
 		if (ret == -EAGAIN) {
 			/* block group became read-only */
-			update_reserved_bytes(cache, buf->len, 0, 1);
+			btrfs_update_reserved_bytes(cache, buf->len, 0, 1);
 			goto out;
 		}
 

@@ -5180,7 +5185,7 @@ checks:
 					     search_start - offset);
 		BUG_ON(offset > search_start);
 
-		ret = update_reserved_bytes(block_group, num_bytes, 1,
+		ret = btrfs_update_reserved_bytes(block_group, num_bytes, 1,
 					    (data & BTRFS_BLOCK_GROUP_DATA));
 		if (ret == -EAGAIN) {
 			btrfs_add_free_space(block_group, offset, num_bytes);

@@ -5401,10 +5406,11 @@ int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len)
 		return -ENOSPC;
 	}
 
-	ret = btrfs_discard_extent(root, start, len);
+	if (btrfs_test_opt(root, DISCARD))
+		ret = btrfs_discard_extent(root, start, len, NULL);
 
 	btrfs_add_free_space(cache, start, len);
-	update_reserved_bytes(cache, len, 0, 1);
+	btrfs_update_reserved_bytes(cache, len, 0, 1);
 	btrfs_put_block_group(cache);
 
 	return ret;

@@ -5603,7 +5609,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 		put_caching_control(caching_ctl);
 	}
 
-	ret = update_reserved_bytes(block_group, ins->offset, 1, 1);
+	ret = btrfs_update_reserved_bytes(block_group, ins->offset, 1, 1);
 	BUG_ON(ret);
 	btrfs_put_block_group(block_group);
 	ret = alloc_reserved_file_extent(trans, root, 0, root_objectid,

@@ -8712,7 +8718,55 @@ int btrfs_error_unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 }
 
 int btrfs_error_discard_extent(struct btrfs_root *root, u64 bytenr,
-			       u64 num_bytes)
+			       u64 num_bytes, u64 *actual_bytes)
 {
-	return btrfs_discard_extent(root, bytenr, num_bytes);
+	return btrfs_discard_extent(root, bytenr, num_bytes, actual_bytes);
+}
+
+int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)
+{
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_block_group_cache *cache = NULL;
+	u64 group_trimmed;
+	u64 start;
+	u64 end;
+	u64 trimmed = 0;
+	int ret = 0;
+
+	cache = btrfs_lookup_block_group(fs_info, range->start);
+
+	while (cache) {
+		if (cache->key.objectid >= (range->start + range->len)) {
+			btrfs_put_block_group(cache);
+			break;
+		}
+
+		start = max(range->start, cache->key.objectid);
+		end = min(range->start + range->len,
+				cache->key.objectid + cache->key.offset);
+
+		if (end - start >= range->minlen) {
+			if (!block_group_cache_done(cache)) {
+				ret = cache_block_group(cache, NULL, root, 0);
+				if (!ret)
+					wait_block_group_cache_done(cache);
+			}
+			ret = btrfs_trim_block_group(cache,
+						     &group_trimmed,
+						     start,
+						     end,
+						     range->minlen);
+
+			trimmed += group_trimmed;
+			if (ret < 0) {
+				btrfs_put_block_group(cache);
+				break;
+			}
+		}
+
+		cache = next_block_group(fs_info->tree_root, cache);
+	}
+
+	range->len = trimmed;
+	return ret;
 }

fs/btrfs/free-space-cache.c +92 -0

index a039065..84801ee 100644
@@ -2154,3 +2154,95 @@ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
 	cluster->block_group = NULL;
 }
 
+int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+			   u64 *trimmed, u64 start, u64 end, u64 minlen)
+{
+	struct btrfs_free_space *entry = NULL;
+	struct btrfs_fs_info *fs_info = block_group->fs_info;
+	u64 bytes = 0;
+	u64 actually_trimmed;
+	int ret = 0;
+
+	*trimmed = 0;
+
+	while (start < end) {
+		spin_lock(&block_group->tree_lock);
+
+		if (block_group->free_space < minlen) {
+			spin_unlock(&block_group->tree_lock);
+			break;
+		}
+
+		entry = tree_search_offset(block_group, start, 0, 1);
+		if (!entry)
+			entry = tree_search_offset(block_group,
+						   offset_to_bitmap(block_group,
+								    start),
+						   1, 1);
+
+		if (!entry || entry->offset >= end) {
+			spin_unlock(&block_group->tree_lock);
+			break;
+		}
+
+		if (entry->bitmap) {
+			ret = search_bitmap(block_group, entry, &start, &bytes);
+			if (!ret) {
+				if (start >= end ) {
+					spin_unlock(&block_group->tree_lock);
+					break;
+				}
+				bytes = min(bytes, end - start);
+				bitmap_clear_bits(block_group, entry,
+						  start, bytes);
+				if (entry->bytes == 0)
+					free_bitmap(block_group, entry);
+			} else {
+				start = entry->offset + BITS_PER_BITMAP *
+					block_group->sectorsize;
+				spin_unlock(&block_group->tree_lock);
+				ret = 0;
+				continue;
+			}
+		} else {
+			start = entry->offset;
+			bytes = min(entry->bytes, end - start);
+			unlink_free_space(block_group, entry);
+			kfree(entry);
+		}
+
+		spin_unlock(&block_group->tree_lock);
+
+		if (bytes >= minlen) {
+			int update_ret;
+			update_ret = btrfs_update_reserved_bytes(block_group,
+								 bytes, 1, 1);
+
+			ret = btrfs_error_discard_extent(fs_info->extent_root,
+							 start,
+							 bytes,
+							 &actually_trimmed);
+
+			btrfs_add_free_space(block_group,
+					     start, bytes);
+			if (!update_ret)
+				btrfs_update_reserved_bytes(block_group,
+							    bytes, 0, 1);
+
+			if (ret)
+				break;
+			*trimmed += actually_trimmed;
+		}
+		start += bytes;
+		bytes = 0;
+
+		if (fatal_signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
+		}
+
+		cond_resched();
+	}
+
+	return ret;
+}

fs/btrfs/free-space-cache.h +2 -0

index e49ca5c..65c3b93 100644
@@ -68,4 +68,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 int btrfs_return_cluster_to_free_space(
 			       struct btrfs_block_group_cache *block_group,
 			       struct btrfs_free_cluster *cluster);
+int btrfs_trim_block_group(struct btrfs_block_group_cache *block_group,
+			   u64 *trimmed, u64 start, u64 end, u64 minlen);
 #endif

fs/btrfs/ioctl.c +47 -0

index be2d4f6..f0220c5 100644
@@ -40,6 +40,7 @@
 #include <linux/xattr.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/blkdev.h>
 #include "compat.h"
 #include "ctree.h"
 #include "disk-io.h"

@@ -225,6 +226,50 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
 	return put_user(inode->i_generation, arg);
 }
 
+static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
+{
+	struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info;
+	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_device *device;
+	struct request_queue *q;
+	struct fstrim_range range;
+	u64 minlen = ULLONG_MAX;
+	u64 num_devices = 0;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
+		if (!device->bdev)
+			continue;
+		q = bdev_get_queue(device->bdev);
+		if (blk_queue_discard(q)) {
+			num_devices++;
+			minlen = min((u64)q->limits.discard_granularity,
+				     minlen);
+		}
+	}
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	if (!num_devices) {
+		return -EOPNOTSUPP;
+	}
+
+	if (copy_from_user(&range, arg, sizeof(range)))
+		return -EFAULT;
+
+	range.minlen = max(range.minlen, minlen);
+	ret = btrfs_trim_fs(root, &range);
+	if (ret < 0)
+		return ret;
+
+	if (copy_to_user(arg, &range, sizeof(range)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static noinline int create_subvol(struct btrfs_root *root,
 				  struct dentry *dentry,
 				  char *name, int namelen,

@@ -2385,6 +2430,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_setflags(file, argp);
 	case FS_IOC_GETVERSION:
 		return btrfs_ioctl_getversion(file, argp);
+	case FITRIM:
+		return btrfs_ioctl_fitrim(file, argp);
 	case BTRFS_IOC_SNAP_CREATE:
 		return btrfs_ioctl_snap_create(file, argp, 0);
 	case BTRFS_IOC_SNAP_CREATE_V2: