ext4: Add batched discard support for ext4

Walk through allocation groups and trim all free extents. It can be
invoked through FITRIM ioctl on the file system. The main idea is to
provide a way to trim the whole file system if needed, since some SSD's
may suffer from performance loss after the whole device was filled (it
does not mean that fs is full!).

It search for free extents in allocation groups specified by Byte range
start -> start+len. When the free extent is within this range, blocks
are marked as used and then trimmed. Afterwards these blocks are marked
as free in per-group bitmap.

Since fstrim is a long operation it is good to have an ability to
interrupt it by a signal. This was added by Dmitry Monakhov.
Thanks Dimitry.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Dmitry Monakhov <dmonakhov@openvz.org>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

3 files changed, 188 insertions, 0 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ca9fda6..98dde2b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1694,6 +1694,8 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb,
 extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
 extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
 						ext4_group_t, int);
+extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+
 /* inode.c */
 struct buffer_head *ext4_getblk(handle_t *, struct inode *,
 						ext4_lblk_t, int, int *);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 11c2eec..e3bcc06 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4685,3 +4685,188 @@ error_return:
 	ext4_std_error(sb, err);
 	return;
 }
+
+/**
+ * ext4_trim_extent -- function to TRIM one single free extent in the group
+ * @sb:		super block for the file system
+ * @start:	starting block of the free extent in the alloc. group
+ * @count:	number of blocks to TRIM
+ * @group:	alloc. group we are working with
+ * @e4b:	ext4 buddy for the group
+ *
+ * Trim "count" blocks starting at "start" in the "group". To assure that no
+ * one will allocate those blocks, mark it as used in buddy bitmap. This must
+ * be called with under the group lock.
+ */
+static int ext4_trim_extent(struct super_block *sb, int start, int count,
+		ext4_group_t group, struct ext4_buddy *e4b)
+{
+	struct ext4_free_extent ex;
+	int ret = 0;
+
+	assert_spin_locked(ext4_group_lock_ptr(sb, group));
+
+	ex.fe_start = start;
+	ex.fe_group = group;
+	ex.fe_len = count;
+
+	/*
+	 * Mark blocks used, so no one can reuse them while
+	 * being trimmed.
+	 */
+	mb_mark_used(e4b, &ex);
+	ext4_unlock_group(sb, group);
+
+	ret = ext4_issue_discard(sb, group, start, count);
+	if (ret)
+		ext4_std_error(sb, ret);
+
+	ext4_lock_group(sb, group);
+	mb_free_blocks(NULL, e4b, start, ex.fe_len);
+	return ret;
+}
+
+/**
+ * ext4_trim_all_free -- function to trim all free space in alloc. group
+ * @sb:			super block for file system
+ * @e4b:		ext4 buddy
+ * @start:		first group block to examine
+ * @max:		last group block to examine
+ * @minblocks:		minimum extent block count
+ *
+ * ext4_trim_all_free walks through group's buddy bitmap searching for free
+ * extents. When the free block is found, ext4_trim_extent is called to TRIM
+ * the extent.
+ *
+ *
+ * ext4_trim_all_free walks through group's block bitmap searching for free
+ * extents. When the free extent is found, mark it as used in group buddy
+ * bitmap. Then issue a TRIM command on this extent and free the extent in
+ * the group buddy bitmap. This is done until whole group is scanned.
+ */
+ext4_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
+		ext4_grpblk_t start, ext4_grpblk_t max, ext4_grpblk_t minblocks)
+{
+	void *bitmap;
+	ext4_grpblk_t next, count = 0;
+	ext4_group_t group;
+	int ret = 0;
+
+	BUG_ON(e4b == NULL);
+
+	bitmap = e4b->bd_bitmap;
+	group = e4b->bd_group;
+	start = (e4b->bd_info->bb_first_free > start) ?
+		e4b->bd_info->bb_first_free : start;
+	ext4_lock_group(sb, group);
+
+	while (start < max) {
+		start = mb_find_next_zero_bit(bitmap, max, start);
+		if (start >= max)
+			break;
+		next = mb_find_next_bit(bitmap, max, start);
+
+		if ((next - start) >= minblocks) {
+			ret = ext4_trim_extent(sb, start,
+				next - start, group, e4b);
+			if (ret < 0)
+				break;
+			count += next - start;
+		}
+		start = next + 1;
+
+		if (fatal_signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		if (need_resched()) {
+			ext4_unlock_group(sb, group);
+			cond_resched();
+			ext4_lock_group(sb, group);
+		}
+
+		if ((e4b->bd_info->bb_free - count) < minblocks)
+			break;
+	}
+	ext4_unlock_group(sb, group);
+
+	ext4_debug("trimmed %d blocks in the group %d\n",
+		count, group);
+
+	if (ret < 0)
+		count = ret;
+
+	return count;
+}
+
+/**
+ * ext4_trim_fs() -- trim ioctl handle function
+ * @sb:			superblock for filesystem
+ * @range:		fstrim_range structure
+ *
+ * start:	First Byte to trim
+ * len:		number of Bytes to trim from start
+ * minlen:	minimum extent length in Bytes
+ * ext4_trim_fs goes through all allocation groups containing Bytes from
+ * start to start+len. For each such a group ext4_trim_all_free function
+ * is invoked to trim all free space.
+ */
+int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
+{
+	struct ext4_buddy e4b;
+	ext4_group_t first_group, last_group;
+	ext4_group_t group, ngroups = ext4_get_groups_count(sb);
+	ext4_grpblk_t cnt = 0, first_block, last_block;
+	uint64_t start, len, minlen, trimmed;
+	int ret = 0;
+
+	start = range->start >> sb->s_blocksize_bits;
+	len = range->len >> sb->s_blocksize_bits;
+	minlen = range->minlen >> sb->s_blocksize_bits;
+	trimmed = 0;
+
+	if (unlikely(minlen > EXT4_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+
+	/* Determine first and last group to examine based on start and len */
+	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) start,
+				     &first_group, &first_block);
+	ext4_get_group_no_and_offset(sb, (ext4_fsblk_t) (start + len),
+				     &last_group, &last_block);
+	last_group = (last_group > ngroups - 1) ? ngroups - 1 : last_group;
+	last_block = EXT4_BLOCKS_PER_GROUP(sb);
+
+	if (first_group > last_group)
+		return -EINVAL;
+
+	for (group = first_group; group <= last_group; group++) {
+		ret = ext4_mb_load_buddy(sb, group, &e4b);
+		if (ret) {
+			ext4_error(sb, "Error in loading buddy "
+					"information for %u", group);
+			break;
+		}
+
+		if (len >= EXT4_BLOCKS_PER_GROUP(sb))
+			len -= (EXT4_BLOCKS_PER_GROUP(sb) - first_block);
+		else
+			last_block = len;
+
+		if (e4b.bd_info->bb_free >= minlen) {
+			cnt = ext4_trim_all_free(sb, &e4b, first_block,
+						last_block, minlen);
+			if (cnt < 0) {
+				ret = cnt;
+				ext4_mb_unload_buddy(&e4b);
+				break;
+			}
+		}
+		ext4_mb_unload_buddy(&e4b);
+		trimmed += cnt;
+		first_block = 0;
+	}
+	range->len = trimmed * sb->s_blocksize;
+
+	return ret;
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e13b3c3..01e60aa 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1189,6 +1189,7 @@ static const struct super_operations ext4_sops = {
 	.quota_write	= ext4_quota_write,
 #endif
 	.bdev_try_to_free_page = bdev_try_to_free_page,
+	.trim_fs	= ext4_trim_fs
 };
 
 static const struct super_operations ext4_nojournal_sops = {