[PATCH v3 2/2] nilfs2: add FITRIM ioctl support for nilfs2

[Andreas Rohner]

This patch adds support for the FITRIM ioctl, which enables user space
tools to issue TRIM/DISCARD requests to the underlying device. Every
clean segment within the specified range will be discarded.

Signed-off-by: Andreas Rohner <andreas.rohner-***@public.gmane.org>
---
fs/nilfs2/ioctl.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)

diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 2b34021..8051cb3 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1072,6 +1072,49 @@ out:
}

/**
+ * nilfs_ioctl_trim_fs() - trim ioctl handle function
+ * @inode: inode object
+ * @argp: pointer on argument from userspace
+ *
+ * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
+ * performs the actual trim operation.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
+{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+ struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
+ struct fstrim_range range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, argp, sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max_t(unsigned int, (unsigned int)range.minlen,
+ q->limits.discard_granularity);
+
+ down_read(&nilfs->ns_segctor_sem);
+ ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
+ up_read(&nilfs->ns_segctor_sem);
+
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(argp, &range, sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/**
* nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
* @inode: inode object
* @argp: pointer on argument from userspace
@@ -1205,6 +1248,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return nilfs_ioctl_resize(inode, filp, argp);
case NILFS_IOCTL_SET_ALLOC_RANGE:
return nilfs_ioctl_set_alloc_range(inode, argp);
+ case FITRIM:
+ return nilfs_ioctl_trim_fs(inode, argp);
default:
return -ENOTTY;
}
@@ -1235,6 +1280,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case NILFS_IOCTL_SYNC:
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
+ case FITRIM:
break;
default:
return -ENOIOCTLCMD;

[Andreas Rohner]

This patch adds the nilfs_sufile_trim_fs function, which takes a
fstrim_range structure and calls blkdev_issue_discard for every
clean segment in the specified range. The range is truncated to
file system block boundaries.

Signed-off-by: Andreas Rohner <andreas.rohner-***@public.gmane.org>
---
fs/nilfs2/sufile.c | 147 +++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/nilfs2/sufile.h | 1 +
2 files changed, 148 insertions(+)

diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 3127e9f..6c3b350 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -870,6 +870,153 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
}

/**
+ * nilfs_sufile_trim_fs() - trim ioctl handle function
+ * @sufile: inode of segment usage file
+ * @range: fstrim_range structure
+ *
+ * start: First Byte to trim
+ * len: number of Bytes to trim from start
+ * minlen: minimum extent length in Bytes
+ *
+ * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
+ * from start to start+len. start is rounded up to the next block boundary
+ * and start+len is rounded down. For each clean segment blkdev_issue_discard
+ * function is invoked.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
+{
+ struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+ struct buffer_head *su_bh;
+ struct nilfs_segment_usage *su;
+ void *kaddr;
+ size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
+ sector_t seg_start, seg_end, start_block, end_block;
+ sector_t start = 0, nblocks = 0;
+ u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
+ int ret = 0;
+ unsigned int sects_per_block;
+
+ sects_per_block = (1 << nilfs->ns_blocksize_bits) /
+ bdev_logical_block_size(nilfs->ns_bdev);
+ len = range->len >> nilfs->ns_blocksize_bits;
+ minlen = range->minlen >> nilfs->ns_blocksize_bits;
+ max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
+
+ if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
+ return -EINVAL;
+
+ start_block = (range->start + nilfs->ns_blocksize - 1) >>
+ nilfs->ns_blocksize_bits;
+
+ if (max_blocks - start_block < len)
+ end_block = max_blocks - 1;
+ else
+ end_block = start_block + len - 1;
+
+ segnum = nilfs_get_segnum_of_block(nilfs, start_block);
+ segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
+
+ down_read(&NILFS_MDT(sufile)->mi_sem);
+
+ while (segnum <= segnum_end) {
+ n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
+ segnum_end);
+
+ ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
+ &su_bh);
+ if (ret < 0) {
+ if (ret != -ENOENT)
+ goto out_sem;
+ /* hole */
+ segnum += n;
+ continue;
+ }
+
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
+ su_bh, kaddr);
+ for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
+ if (!nilfs_segment_usage_clean(su))
+ continue;
+
+ nilfs_get_segment_range(nilfs, segnum, &seg_start,
+ &seg_end);
+
+ if (!nblocks) {
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ continue;
+ }
+
+ if (start + nblocks == seg_start) {
+ /* add to previous extent */
+ nblocks += seg_end - seg_start + 1;
+ continue;
+ }
+
+ /* discard previous extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+
+ if (nblocks >= minlen) {
+ kunmap_atomic(kaddr);
+
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (ret < 0) {
+ put_bh(su_bh);
+ goto out_sem;
+ }
+
+ ndiscarded += nblocks;
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(
+ sufile, segnum, su_bh, kaddr);
+ }
+
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ }
+ kunmap_atomic(kaddr);
+ put_bh(su_bh);
+ }
+
+
+ if (nblocks) {
+ /* discard last extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+ if (start + nblocks > end_block + 1)
+ nblocks = end_block - start + 1;
+
+ if (nblocks >= minlen) {
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (!ret)
+ ndiscarded += nblocks;
+ }
+ }
+
+out_sem:
+ up_read(&NILFS_MDT(sufile)->mi_sem);
+
+ range->len = ndiscarded << nilfs->ns_blocksize_bits;
+ return ret;
+}
+
+/**
* nilfs_sufile_read - read or get sufile inode
* @sb: super block instance
* @susize: size of a segment usage entry
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index e84bc5b..2434abd 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -65,6 +65,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
int nilfs_sufile_read(struct super_block *sb, size_t susize,
struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);

/**
* nilfs_sufile_scrap - make a segment garbage

[Ryusuke Konishi]

Post by Andreas Rohner
This patch adds the nilfs_sufile_trim_fs function, which takes a
fstrim_range structure and calls blkdev_issue_discard for every
clean segment in the specified range. The range is truncated to
file system block boundaries.
---
fs/nilfs2/sufile.c | 147 +++++++++++++++++++++++++++++++++++++++++++++++++++++
fs/nilfs2/sufile.h | 1 +
2 files changed, 148 insertions(+)
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 3127e9f..6c3b350 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -870,6 +870,153 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
}
/**
+ * nilfs_sufile_trim_fs() - trim ioctl handle function
+ *
+ * start: First Byte to trim
+ * len: number of Bytes to trim from start
+ * minlen: minimum extent length in Bytes
+ *
+ * Decription: nilfs_sufile_trim_fs goes through all segments containing bytes
+ * from start to start+len. start is rounded up to the next block boundary
+ * and start+len is rounded down. For each clean segment blkdev_issue_discard
+ * function is invoked.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
+{
+ struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
+ struct buffer_head *su_bh;
+ struct nilfs_segment_usage *su;
+ void *kaddr;
+ size_t n, i, susz = NILFS_MDT(sufile)->mi_entry_size;
+ sector_t seg_start, seg_end, start_block, end_block;
+ sector_t start = 0, nblocks = 0;
+ u64 segnum, segnum_end, minlen, len, max_blocks, ndiscarded = 0;
+ int ret = 0;
+ unsigned int sects_per_block;
+
+ sects_per_block = (1 << nilfs->ns_blocksize_bits) /
+ bdev_logical_block_size(nilfs->ns_bdev);
+ len = range->len >> nilfs->ns_blocksize_bits;
+ minlen = range->minlen >> nilfs->ns_blocksize_bits;
+ max_blocks = ((u64)nilfs->ns_nsegments * nilfs->ns_blocks_per_segment);
+
+ if (!len || range->start >= max_blocks << nilfs->ns_blocksize_bits)
+ return -EINVAL;
+
+ start_block = (range->start + nilfs->ns_blocksize - 1) >>
+ nilfs->ns_blocksize_bits;
+
+ if (max_blocks - start_block < len)
+ end_block = max_blocks - 1;
+ else
+ end_block = start_block + len - 1;

This patch looks good to me. When you resubmit this series, please
add a comment to clarify why we do not simplify this as follows:

end_block = min_t(sector_t, max_blocks, start_block + len) - 1;

For example,

/*
* range->len can be very large (actually, it is set to
* ULLONG_MAX by default) - truncate upper end of the range
* carefully so as not to overflow.
*/
if (max_blocks - start_block < len)
end_block = max_blocks - 1;
else
end_block = start_block + len - 1;

Regards,
Ryusuke Konishi

Post by Andreas Rohner
+
+ segnum = nilfs_get_segnum_of_block(nilfs, start_block);
+ segnum_end = nilfs_get_segnum_of_block(nilfs, end_block);
+
+ down_read(&NILFS_MDT(sufile)->mi_sem);
+
+ while (segnum <= segnum_end) {
+ n = nilfs_sufile_segment_usages_in_block(sufile, segnum,
+ segnum_end);
+
+ ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0,
+ &su_bh);
+ if (ret < 0) {
+ if (ret != -ENOENT)
+ goto out_sem;
+ /* hole */
+ segnum += n;
+ continue;
+ }
+
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
+ su_bh, kaddr);
+ for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
+ if (!nilfs_segment_usage_clean(su))
+ continue;
+
+ nilfs_get_segment_range(nilfs, segnum, &seg_start,
+ &seg_end);
+
+ if (!nblocks) {
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ continue;
+ }
+
+ if (start + nblocks == seg_start) {
+ /* add to previous extent */
+ nblocks += seg_end - seg_start + 1;
+ continue;
+ }
+
+ /* discard previous extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+
+ if (nblocks >= minlen) {
+ kunmap_atomic(kaddr);
+
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (ret < 0) {
+ put_bh(su_bh);
+ goto out_sem;
+ }
+
+ ndiscarded += nblocks;
+ kaddr = kmap_atomic(su_bh->b_page);
+ su = nilfs_sufile_block_get_segment_usage(
+ sufile, segnum, su_bh, kaddr);
+ }
+
+ /* start new extent */
+ start = seg_start;
+ nblocks = seg_end - seg_start + 1;
+ }
+ kunmap_atomic(kaddr);
+ put_bh(su_bh);
+ }
+
+
+ if (nblocks) {
+ /* discard last extent */
+ if (start < start_block) {
+ nblocks -= start_block - start;
+ start = start_block;
+ }
+ if (start + nblocks > end_block + 1)
+ nblocks = end_block - start + 1;
+
+ if (nblocks >= minlen) {
+ ret = blkdev_issue_discard(nilfs->ns_bdev,
+ start * sects_per_block,
+ nblocks * sects_per_block,
+ GFP_NOFS, 0);
+ if (!ret)
+ ndiscarded += nblocks;
+ }
+ }
+
+ up_read(&NILFS_MDT(sufile)->mi_sem);
+
+ range->len = ndiscarded << nilfs->ns_blocksize_bits;
+ return ret;
+}
+
+/**
* nilfs_sufile_read - read or get sufile inode
diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h
index e84bc5b..2434abd 100644
--- a/fs/nilfs2/sufile.h
+++ b/fs/nilfs2/sufile.h
@@ -65,6 +65,7 @@ void nilfs_sufile_do_set_error(struct inode *, __u64, struct buffer_head *,
int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs);
int nilfs_sufile_read(struct super_block *sb, size_t susize,
struct nilfs_inode *raw_inode, struct inode **inodep);
+int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range);
/**
* nilfs_sufile_scrap - make a segment garbage
--
1.9.0
--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
the body of a message to majordomo-***@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html

[Ryusuke Konishi]

Hi Andreas,

Post by Andreas Rohner
This patch adds support for the FITRIM ioctl, which enables user space
tools to issue TRIM/DISCARD requests to the underlying device. Every
clean segment within the specified range will be discarded.
---
fs/nilfs2/ioctl.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 2b34021..8051cb3 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
}
/**
+ * nilfs_ioctl_trim_fs() - trim ioctl handle function
+ *
+ * Decription: nilfs_ioctl_trim_fs is the FITRIM ioctl handle function. It
+ * checks the arguments from userspace and calls nilfs_sufile_trim_fs, which
+ * performs the actual trim operation.
+ *
+ * Return Value: On success, 0 is returned or negative error code, otherwise.
+ */
+static int nilfs_ioctl_trim_fs(struct inode *inode, void __user *argp)
+{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+ struct request_queue *q = bdev_get_queue(nilfs->ns_bdev);
+ struct fstrim_range range;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!blk_queue_discard(q))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&range, argp, sizeof(range)))
+ return -EFAULT;
+
+ range.minlen = max_t(unsigned int, (unsigned int)range.minlen,
+ q->limits.discard_granularity);

I just noticed that this can overflow since range.minlen has __u64 type.
Should it be as follows ?

range.minlen = max_t(u64, range.minlen, q->limits.discard_granularity);

Regards,
Ryusuke Konishi

Post by Andreas Rohner
+
+ down_read(&nilfs->ns_segctor_sem);
+ ret = nilfs_sufile_trim_fs(nilfs->ns_sufile, &range);
+ up_read(&nilfs->ns_segctor_sem);
+
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(argp, &range, sizeof(range)))
+ return -EFAULT;
+
+ return 0;
+}
+
+/**
* nilfs_ioctl_set_alloc_range - limit range of segments to be allocated
@@ -1205,6 +1248,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return nilfs_ioctl_resize(inode, filp, argp);
return nilfs_ioctl_set_alloc_range(inode, argp);
+ return nilfs_ioctl_trim_fs(inode, argp);
return -ENOTTY;
}
@@ -1235,6 +1280,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
break;
return -ENOIOCTLCMD;
--
1.9.0
--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
More majordomo info at http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
the body of a message to majordomo-***@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html