[PATCH 1/4] Add ioctl FITRIM.

[PATCH 1/4] Add ioctl FITRIM.

[Lukas Czerner]

Adds an filesystem independent ioctl to allow implementation of file
system batched discard support.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ioctl.c         |   31 +++++++++++++++++++++++++++++++
 include/linux/fs.h |    2 ++
 2 files changed, 33 insertions(+), 0 deletions(-)

diff --git a/fs/ioctl.c b/fs/ioctl.c
index 2d140a7..6c01c3c 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -540,6 +540,33 @@ static int ioctl_fsthaw(struct file *filp)
 	return thaw_super(sb);
 }
 
+static int ioctl_fstrim(struct file *filp, unsigned long arg)
+{
+	struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
+	unsigned int minlen;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* If filesystem doesn't support trim feature, return. */
+	if (sb->s_op->trim_fs == NULL)
+		return -EOPNOTSUPP;
+
+	/* If a blockdevice-backed filesystem isn't specified, return EINVAL. */
+	if (sb->s_bdev == NULL)
+		return -EINVAL;
+
+	err = get_user(minlen, (unsigned int __user *) arg);
+	if (err)
+		return err;
+
+	err = sb->s_op->trim_fs(minlen, sb);
+	if (err)
+		return err;
+	return 0;
+}
+
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -590,6 +617,10 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		error = ioctl_fsthaw(filp);
 		break;
 
+	case FITRIM:
+		error = ioctl_fstrim(filp, arg);
+		break;
+
 	case FS_IOC_FIEMAP:
 		return ioctl_fiemap(filp, arg);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 68ca1b0..01632e4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -315,6 +315,7 @@ struct inodes_stat_t {
 #define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */
 #define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
 #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
+#define FITRIM		_IOWR('X', 121, int)	/* Trim */
 
 #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
 #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
@@ -1580,6 +1581,7 @@ struct super_operations {
 	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
 #endif
 	int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
+	int (*trim_fs) (unsigned int, struct super_block *);
 };
 
 /*
-- 
1.7.2

[PATCH 2/4] Add batched discard support for ext3

[Lukas Czerner]

Walk through each allocation group 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 each allocation group. When the free
extent is found, blocks are marked as used and then trimmed. Afterwards
these blocks are marked as free in per-group bitmap.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/ext3/balloc.c        |  220 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ext3/super.c         |    1 +
 include/linux/ext3_fs.h |    1 +
 3 files changed, 222 insertions(+), 0 deletions(-)

diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c
index 4a32511..b1a43d2 100644
--- a/fs/ext3/balloc.c
+++ b/fs/ext3/balloc.c
@@ -20,6 +20,7 @@
 #include <linux/ext3_jbd.h>
 #include <linux/quotaops.h>
 #include <linux/buffer_head.h>
+#include <linux/blkdev.h>
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines
@@ -1882,3 +1883,222 @@ unsigned long ext3_bg_num_gdb(struct super_block *sb, int group)
 	return ext3_bg_num_gdb_meta(sb,group);
 
 }
+
+/**
+ * ext3_trim_all_free -- function to trim all free space in alloc. group
+ * @sb:			super block for file system
+ * @group:		allocation group to trim
+ * @gdp:		allocation group description structure
+ * @minblocks:		minimum extent block count
+ *
+ * ext3_trim_all_free walks through group's block bitmap searching for free
+ * blocks. When the free block is found, it tries to allocate this block and
+ * consequent free block to get the biggest free extent possible, until it
+ * reaches any used block. Then issue a TRIM command on this extent and free
+ * the extent in the block bitmap. This is done until whole group is scanned.
+ */
+ext3_grpblk_t ext3_trim_all_free(struct super_block *sb,
+			unsigned int group, ext3_grpblk_t minblocks)
+{
+	handle_t *handle;
+	ext3_grpblk_t max = EXT3_BLOCKS_PER_GROUP(sb);
+	ext3_grpblk_t next, count = 0, start, bit;
+	struct ext3_sb_info *sbi;
+	ext3_fsblk_t discard_block;
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gdp_bh;
+	ext3_grpblk_t free_blocks;
+	struct ext3_group_desc *gdp;
+	int err = 0, ret = 0;
+	ext3_grpblk_t freed;
+
+	/*
+	 * We will update one block bitmap, and one group descriptor
+	 */
+	handle = ext3_journal_start_sb(sb, 2);
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		return err;
+	}
+
+	bitmap_bh = read_block_bitmap(sb, group);
+	if (!bitmap_bh)
+		goto err_out;
+
+	BUFFER_TRACE(bitmap_bh, "getting undo access");
+	err = ext3_journal_get_undo_access(handle, bitmap_bh);
+	if (err)
+		goto err_out;
+
+	gdp = ext3_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		goto err_out;
+
+	BUFFER_TRACE(gdp_bh, "get_write_access");
+	err = ext3_journal_get_write_access(handle, gdp_bh);
+	if (err)
+		goto err_out;
+
+	free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+	sbi = EXT3_SB(sb);
+
+	 /* Walk through the whole group */
+	start = 0;
+	while (start < max) {
+
+		start = bitmap_search_next_usable_block(start, bitmap_bh, max);
+		if (start < 0)
+			break;
+		next = start;
+
+		/*
+		 * Allocate contiguous free extents by setting bits in the
+		 * block bitmap
+		 */
+		while (next < max
+			&& claim_block(sb_bgl_lock(sbi, group),
+					next, bitmap_bh)) {
+			next++;
+		}
+
+		 /* We did not claim any blocks */
+		if (next == start)
+			continue;
+
+		discard_block = (ext3_fsblk_t)start +
+				ext3_group_first_block_no(sb, group);
+
+		/* Update counters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, start - next);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_sub(&sbi->s_freeblocks_counter, next - start);
+
+		/* Do not issue a TRIM on extents smaller than minblocks */
+		if ((next - start) < minblocks)
+			goto free_extent;
+
+		 /* Send the TRIM command down to the device */
+		ret = sb_issue_discard(sb, discard_block, next - start);
+		count += (next - start);
+
+free_extent:
+		freed = 0;
+
+		/*
+		 * Clear bits in the bitmap
+		 */
+		for (bit = start; bit < next; bit++) {
+			BUFFER_TRACE(bitmap_bh, "clear bit");
+			if (!ext3_clear_bit_atomic(sb_bgl_lock(sbi, group),
+						bit, bitmap_bh->b_data)) {
+				ext3_error(sb, __func__,
+					"bit already cleared for block "E3FSBLK,
+					 (unsigned long)bit);
+				BUFFER_TRACE(bitmap_bh, "bit already cleared");
+			} else {
+				freed++;
+			}
+		}
+
+		/* Update couters */
+		spin_lock(sb_bgl_lock(sbi, group));
+		le16_add_cpu(&gdp->bg_free_blocks_count, freed);
+		spin_unlock(sb_bgl_lock(sbi, group));
+		percpu_counter_add(&sbi->s_freeblocks_counter, next - start);
+
+		start = next;
+
+		if (ret < 0) {
+			if (ret == -EOPNOTSUPP) {
+				ext3_warning(sb, __func__,
+					"discard not supported!");
+				count = ret;
+				break;
+			}
+			err = ret;
+			break;
+		}
+
+		if (signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		cond_resched();
+
+		/* No more suitable extents */
+		if ((free_blocks - count) < minblocks)
+			break;
+	}
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext3_journal_dirty_metadata(handle, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gdp_bh, "dirtied group descriptor block");
+	ret = ext3_journal_dirty_metadata(handle, gdp_bh);
+	if (!err)
+		err = ret;
+
+	ext3_debug("trimmed %d blocks in the group %d\n",
+		count, group);
+
+err_out:
+	if (err) {
+		ext3_std_error(sb, err);
+		count = err;
+	}
+
+	ext3_journal_stop(handle);
+	brelse(bitmap_bh);
+
+	return count;
+}
+
+/**
+ * ext3_trim_fs() -- trim ioctl handle function
+ * @minlen:		minimum extent length in Bytes
+ * @sb:			superblock for filesystem
+ *
+ * ext3_trim_fs goes through all allocation group searching for groups with more
+ * free space than minlen. For such a group ext3_trim_all_free function is
+ * invoked to trim all free space.
+ */
+int ext3_trim_fs(unsigned int minlen, struct super_block *sb)
+{
+	ext3_grpblk_t minblocks;
+	unsigned long ngroups;
+	unsigned int group;
+	struct ext3_group_desc *gdp;
+	ext3_grpblk_t free_blocks;
+	int ret = 0;
+
+	minblocks = DIV_ROUND_UP(minlen, sb->s_blocksize);
+	if (unlikely(minblocks > EXT3_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+
+	ngroups = EXT3_SB(sb)->s_groups_count;
+	smp_rmb();
+
+	for (group = 0; group < ngroups; group++) {
+
+		gdp = ext3_get_group_desc(sb, group, NULL);
+		if (!gdp)
+			break;
+
+		free_blocks = le16_to_cpu(gdp->bg_free_blocks_count);
+		if (free_blocks < minblocks)
+			continue;
+
+		ret = ext3_trim_all_free(sb, group, minblocks);
+		if (ret < 0)
+			break;
+	}
+
+	if (ret >= 0)
+		ret = 0;
+
+	return ret;
+}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 6c953bb..b172c88 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -797,6 +797,7 @@ static const struct super_operations ext3_sops = {
 	.quota_write	= ext3_quota_write,
 #endif
 	.bdev_try_to_free_page = bdev_try_to_free_page,
+	.trim_fs	= ext3_trim_fs,
 };
 
 static const struct export_operations ext3_export_ops = {
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 7fc62d4..9083e16 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -857,6 +857,7 @@ extern struct ext3_group_desc * ext3_get_group_desc(struct super_block * sb,
 extern int ext3_should_retry_alloc(struct super_block *sb, int *retries);
 extern void ext3_init_block_alloc_info(struct inode *);
 extern void ext3_rsv_window_add(struct super_block *sb, struct ext3_reserve_window_node *rsv);
+extern int ext3_trim_fs(unsigned int minlen, struct super_block *sb);
 
 /* dir.c */
 extern int ext3_check_dir_entry(const char *, struct inode *,
-- 
1.7.2

[PATCH 3/4] Add batched discard support for ext4

[Lukas Czerner]

Walk through each allocation group and trim all free extents. It can be
invoked through TRIM 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 fro free extents in each allocation group. When the free
extent is found, blocks are marked as used in the buddy bitmap and then
trimmed. Afterwards these blocks are marked as free in per-group buddy
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>
---
 fs/ext4/ext4.h    |    2 +
 fs/ext4/mballoc.c |  158 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ext4/super.c   |    1 +
 3 files changed, 161 insertions(+), 0 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 19a4de5..a3447d7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1558,6 +1558,8 @@ 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(unsigned int, struct super_block *);
+
 /* 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 12b3bc0..a16a813 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4690,3 +4690,161 @@ error_return:
 		kmem_cache_free(ext4_ac_cachep, ac);
 	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)
+{
+	ext4_fsblk_t discard_block;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+	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);
+
+	discard_block = (ext4_fsblk_t)group *
+			EXT4_BLOCKS_PER_GROUP(sb)
+			+ start
+			+ le32_to_cpu(es->s_first_data_block);
+	trace_ext4_discard_blocks(sb,
+			(unsigned long long)discard_block,
+			count);
+	ret = sb_issue_discard(sb, discard_block, count);
+	if (ret == -EOPNOTSUPP) {
+		ext4_warning(sb,
+			"discard not supported!");
+	} else if (ret < 0) {
+		ext4_std_error(sb, ret);
+	}
+	cond_resched();
+
+	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
+ * @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_grpblk_t ext4_trim_all_free(struct super_block *sb, struct ext4_buddy *e4b,
+		ext4_grpblk_t minblocks)
+{
+	void *bitmap;
+	ext4_grpblk_t max = EXT4_BLOCKS_PER_GROUP(sb);
+	ext4_grpblk_t start, 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;
+	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 (signal_pending(current)) {
+			count = -ERESTARTSYS;
+			break;
+		}
+
+		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
+ * @minlen:		minimum extent length in Bytes
+ * @sb:			superblock for filesystem
+ *
+ * ext4_trim_fs goes through all allocation group searching for groups with more
+ * free space than minlen. For such a group ext4_trim_all_free function is
+ * invoked to trim all free space.
+ */
+int ext4_trim_fs(unsigned int minlen, struct super_block *sb)
+{
+	struct ext4_buddy e4b;
+	ext4_group_t group;
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	ext4_grpblk_t minblocks, cnt;
+	int ret = 0;
+
+	minblocks = DIV_ROUND_UP(minlen, sb->s_blocksize);
+	if (unlikely(minblocks > EXT4_BLOCKS_PER_GROUP(sb)))
+		return -EINVAL;
+
+	for (group = 0; group < ngroups; group++) {
+
+		ret = ext4_mb_load_buddy(sb, group, &e4b);
+		if (ret) {
+			ext4_error(sb, "Error in loading buddy "
+					"information for %u", group);
+			break;
+		}
+
+		if (e4b.bd_info->bb_free >= minblocks) {
+			cnt = ext4_trim_all_free(sb, &e4b, minblocks);
+			if (cnt < 0) {
+				ret = cnt;
+				ext4_mb_unload_buddy(&e4b);
+				break;
+			}
+		}
+		ext4_mb_unload_buddy(&e4b);
+	}
+	return ret;
+}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4e8983a..995989b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1114,6 +1114,7 @@ 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 = {
-- 
1.7.2

[PATCH 4/4] Ext4 check for negative err from sb_issue_discard

[Lukas Czerner]

sb_issue_discard is returning negative error code, so check for
negative value instead of positive.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/mballoc.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index a16a813..a8fe7f1 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2589,7 +2589,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 					(unsigned long long)discard_block,
 					entry->count);
 			ret = sb_issue_discard(sb, discard_block, entry->count);
-			if (ret == EOPNOTSUPP) {
+			if (ret == -EOPNOTSUPP) {
 				ext4_warning(sb,
 					"discard not supported, disabling");
 				clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);
-- 
1.7.2

Re: [PATCH 3/4] Add batched discard support for ext4

[Jan Kara]

On Wed 04-08-10 17:30:12, Lukas Czerner wrote:
> Walk through each allocation group and trim all free extents. It can be
> invoked through TRIM 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 fro free extents in each allocation group. When the free
> extent is found, blocks are marked as used in the buddy bitmap and then
> trimmed. Afterwards these blocks are marked as free in per-group buddy
> 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>
  Looks good now. So you can add:
Reviewed-by: Jan Kara <jack@suse.cz>

								Honza
-- 
Jan Kara <jack@suse.cz>
SUSE Labs, CR

Re: [PATCH 4/4] Ext4 check for negative err from sb_issue_discard

[Eric Sandeen]

Lukas Czerner wrote:
> sb_issue_discard is returning negative error code, so check for
> negative value instead of positive.
> 
> Signed-off-by: Lukas Czerner <lczerner@redhat.com>
> ---
>  fs/ext4/mballoc.c |    2 +-
>  1 files changed, 1 insertions(+), 1 deletions(-)
> 
> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> index a16a813..a8fe7f1 100644
> --- a/fs/ext4/mballoc.c
> +++ b/fs/ext4/mballoc.c
> @@ -2589,7 +2589,7 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
>  					(unsigned long long)discard_block,
>  					entry->count);
>  			ret = sb_issue_discard(sb, discard_block, entry->count);
> -			if (ret == EOPNOTSUPP) {
> +			if (ret == -EOPNOTSUPP) {
>  				ext4_warning(sb,
>  					"discard not supported, disabling");
>  				clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);

Thanks for fixing that, Lukas.  Dumb thinko on my part, too much
XFS (and weird positive-error usage) on the brain ;)

Ted, this can/should go in at any time, regardless of other discard
changes.

Thanks,
-Eric