fs: Add FITRIM ioctl

Adds an filesystem independent ioctl to allow implementation of file
system batched discard support. I takes fstrim_range structure as an
argument. fstrim_range is definec in the include/fs.h and its
definition is as follows.

struct fstrim_range {
	start;
	len;
	minlen;
}

start	- first Byte to trim
len	- number of Bytes to trim from start
minlen	- minimum extent length to trim, free extents shorter than this
	  number of Bytes will be ignored. This will be rounded up to fs
	  block size.

It is also possible to specify NULL as an argument. In this case the
arguments will set itself as follows:

start = 0;
len = ULLONG_MAX;
minlen = 0;

So it will trim the whole file system at one run.

After the FITRIM is done, the number of actually discarded Bytes is stored
in fstrim_range.len to give the user better insight on how much storage
space has been really released for wear-leveling.

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

diff --git a/fs/ioctl.c b/fs/ioctl.c
index f855ea4fc88895a13b53b075b9a3fb0dbcb53d8b..e92fdbb3bc3aebd5b52221d2b0e5ec4094a37fe9 100644 (file)
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -530,6 +530,41 @@ static int ioctl_fsthaw(struct file *filp)
        return thaw_super(sb);
 }
 
+static int ioctl_fstrim(struct file *filp, void __user *argp)
+{
+       struct super_block *sb = filp->f_path.dentry->d_inode->i_sb;
+       struct fstrim_range range;
+       int ret = 0;
+
+       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;
+
+       if (argp == NULL) {
+               range.start = 0;
+               range.len = ULLONG_MAX;
+               range.minlen = 0;
+       } else if (copy_from_user(&range, argp, sizeof(range)))
+               return -EFAULT;
+
+       ret = sb->s_op->trim_fs(sb, &range);
+       if (ret < 0)
+               return ret;
+
+       if ((argp != NULL) &&
+           (copy_to_user(argp, &range, sizeof(range))))
+               return -EFAULT;
+
+       return 0;
+}
+
 /*
  * When you add any new common ioctls to the switches above and below
  * please update compat_sys_ioctl() too.
@@ -580,6 +615,10 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
                error = ioctl_fsthaw(filp);
                break;
 
+       case FITRIM:
+               error = ioctl_fstrim(filp, argp);
+               break;
+
        case FS_IOC_FIEMAP:
                return ioctl_fiemap(filp, arg);
 

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 63d069bd80b702c392d4052bf2be937f90763692..7008268e9b5ade024f7f552b4afcf3c4610e1d26 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -32,6 +32,12 @@
 #define SEEK_END       2       /* seek relative to end of file */
 #define SEEK_MAX       SEEK_END
 
+struct fstrim_range {
+       uint64_t start;
+       uint64_t len;
+       uint64_t minlen;
+};
+
 /* And dynamically-tunable limits and defaults: */
 struct files_stat_struct {
        int nr_files;           /* read only */
@@ -316,6 +322,7 @@ 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, struct fstrim_range)    /* Trim */
 
 #define        FS_IOC_GETFLAGS                 _IOR('f', 1, long)
 #define        FS_IOC_SETFLAGS                 _IOW('f', 2, long)
@@ -1581,6 +1588,7 @@ 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) (struct super_block *, struct fstrim_range *);
 };
 
 /*