[PATCH v3 3/3] nilfs2: implementation of NILFS_IOCTL_SET_SUINFO ioctl

[Andreas Rohner <andreas.rohner-hi6Y0CQ0nG0@public.gmane.org>]

With this ioctl the segment usage entries in the SUFILE can be
updated from userspace.

This is useful, because it allows the userspace GC to modify and update
segment usage entries for specific segments, which enables it to avoid
unnecessary write operations.

If a segment needs to be cleaned, but there is no or very little
reclaimable space in it, the cleaning operation basically degrades to
a useless moving operation. In the end the only thing that changes is
the location of the data and a timestamp in the segment usage
information. With this ioctl the GC can skip the cleaning and update
the segment usage entries directly instead.

This is basically a shortcut to cleaning the segment. It is still
necessary to read the segment summary information, but the writing of
the live blocks can be skipped if it's not worth it.

Signed-off-by: Andreas Rohner <andreas.rohner-hi6Y0CQ0nG0@public.gmane.org>
---
 fs/nilfs2/ioctl.c         | 61 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/nilfs2_fs.h |  2 ++
 2 files changed, 63 insertions(+)

diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index b44bdb2..e97df9c 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -767,6 +767,64 @@ out:
 	return ret;
 }
 
+static int nilfs_ioctl_set_suinfo(struct inode *inode, struct file *filp,
+				unsigned int cmd, void __user *argp)
+{
+	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+	struct nilfs_transaction_info ti;
+	struct nilfs_argv argv;
+	size_t len;
+	void __user *base;
+	void *kbuf;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	ret = -EFAULT;
+	if (copy_from_user(&argv, argp, sizeof(argv)))
+		goto out;
+
+	ret = -EINVAL;
+	if (argv.v_size < sizeof(struct nilfs_suinfo_update))
+		goto out;
+
+	if (argv.v_nmembs > nilfs->ns_nsegments)
+		goto out;
+
+	len = argv.v_size * argv.v_nmembs;
+	base = (void __user *)(unsigned long)argv.v_base;
+	kbuf = vmalloc(len);
+	if (!kbuf) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	if (copy_from_user(kbuf, base, len)) {
+		ret = -EFAULT;
+		goto out_free;
+	}
+
+	nilfs_transaction_begin(inode->i_sb, &ti, 0);
+	ret = nilfs_sufile_set_suinfo(nilfs->ns_sufile, kbuf, argv.v_size,
+			argv.v_nmembs);
+	if (unlikely(ret < 0))
+		nilfs_transaction_abort(inode->i_sb);
+	else
+		nilfs_transaction_commit(inode->i_sb); /* never fails */
+
+out_free:
+	vfree(kbuf);
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
+
 static int nilfs_ioctl_get_info(struct inode *inode, struct file *filp,
 				unsigned int cmd, void __user *argp,
 				size_t membsz,
@@ -820,6 +878,8 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return nilfs_ioctl_get_info(inode, filp, cmd, argp,
 					    sizeof(struct nilfs_suinfo),
 					    nilfs_ioctl_do_get_suinfo);
+	case NILFS_IOCTL_SET_SUINFO:
+		return nilfs_ioctl_set_suinfo(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_SUSTAT:
 		return nilfs_ioctl_get_sustat(inode, filp, cmd, argp);
 	case NILFS_IOCTL_GET_VINFO:
@@ -859,6 +919,7 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case NILFS_IOCTL_GET_CPINFO:
 	case NILFS_IOCTL_GET_CPSTAT:
 	case NILFS_IOCTL_GET_SUINFO:
+	case NILFS_IOCTL_SET_SUINFO:
 	case NILFS_IOCTL_GET_SUSTAT:
 	case NILFS_IOCTL_GET_VINFO:
 	case NILFS_IOCTL_GET_BDESCS:
diff --git a/include/linux/nilfs2_fs.h b/include/linux/nilfs2_fs.h
index 7b94449..4140f7f 100644
--- a/include/linux/nilfs2_fs.h
+++ b/include/linux/nilfs2_fs.h
@@ -904,5 +904,7 @@ struct nilfs_bdesc {
 	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
 #define NILFS_IOCTL_SET_ALLOC_RANGE  \
 	_IOW(NILFS_IOCTL_IDENT, 0x8C, __u64[2])
+#define NILFS_IOCTL_SET_SUINFO  \
+	_IOW(NILFS_IOCTL_IDENT, 0x8D, struct nilfs_argv)
 
 #endif	/* _LINUX_NILFS_FS_H */
-- 
1.8.5.3

--
To unsubscribe from this list: send the line "unsubscribe linux-nilfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html