[PATCH v2] fs: Add new pre-allocation ioctls to vfs for compatibility with legacy xfs ioctls

[PATCH v2] fs: Add new pre-allocation ioctls to vfs for compatibility with legacy xfs ioctls

[Ankit Jain]

This patch adds ioctls to vfs for compatibility with legacy XFS
pre-allocation ioctls (XFS_IOC_*RESVP*). The implementation
effectively invokes sys_fallocate for the new ioctls.
Note: These legacy ioctls are also implemented by OCFS2.

Changes in v2:
- Dropped the incorrect handling of *UNRESVSP* ioctl.
- Made the ioctl and argument structure kernel only (__KERNEL__)

Signed-off-by: Ankit Jain <me@ankitjain.org>
---
 fs/ioctl.c             |   35 ++++++++++++++++++++++++++
 fs/open.c              |   51 ++++++++++++++++++-------------------
 include/linux/falloc.h |   21 +++++++++++++++
 include/linux/fs.h     |    2 +
 4 files changed, 83 insertions(+), 26 deletions(-)

diff --git a/fs/ioctl.c b/fs/ioctl.c
index 43e8b2c..2b3fae7 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,7 @@
 #include <linux/uaccess.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
+#include <linux/falloc.h>
 
 #include <asm/ioctls.h>
 
@@ -346,6 +347,37 @@ EXPORT_SYMBOL(generic_block_fiemap);
 
 #endif  /*  CONFIG_BLOCK  */
 
+/*
+ * This provides compatibility with legacy XFS pre-allocation ioctls
+ * which predate the fallocate syscall.
+ *
+ * Only the l_start, l_len and l_whence fields of the 'struct space_resv'
+ * are used here, rest are ignored.
+ */
+static int ioctl_preallocate(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct space_resv sr;
+
+	if (copy_from_user(&sr, (struct space_resv __user *) arg, sizeof(sr)))
+		return -EFAULT;
+
+	switch (sr.l_whence) {
+	case SEEK_SET:
+		break;
+	case SEEK_CUR:
+		sr.l_start += filp->f_pos;
+		break;
+	case SEEK_END:
+		sr.l_start += i_size_read(inode);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return do_fallocate(filp, FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len);
+}
+
 static int file_ioctl(struct file *filp, unsigned int cmd,
 		unsigned long arg)
 {
@@ -361,6 +393,9 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
 		return put_user(inode->i_sb->s_blocksize, p);
 	case FIONREAD:
 		return put_user(i_size_read(inode) - filp->f_pos, p);
+	case F_IOC_RESVSP:
+	case F_IOC_RESVSP64:
+		return ioctl_preallocate(filp, arg);
 	}
 
 	return vfs_ioctl(filp, cmd, arg);
diff --git a/fs/open.c b/fs/open.c
index 83cdb9d..0703bcb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -360,62 +360,61 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length)
 }
 #endif
 
-asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
+long do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
-	struct file *file;
 	struct inode *inode;
-	long ret = -EINVAL;
+	long ret;
 
 	if (offset < 0 || len <= 0)
-		goto out;
+		return -EINVAL;
 
 	/* Return error if mode is not supported */
-	ret = -EOPNOTSUPP;
 	if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
-		goto out;
+		return -EOPNOTSUPP;
 
-	ret = -EBADF;
-	file = fget(fd);
-	if (!file)
-		goto out;
-	if (!(file->f_mode & FMODE_WRITE))
-		goto out_fput;
+	if (!file || !(file->f_mode & FMODE_WRITE))
+		return -EBADF;
 	/*
 	 * Revalidate the write permissions, in case security policy has
 	 * changed since the files were opened.
 	 */
 	ret = security_file_permission(file, MAY_WRITE);
 	if (ret)
-		goto out_fput;
+		return ret;
 
 	inode = file->f_path.dentry->d_inode;
-
-	ret = -ESPIPE;
 	if (S_ISFIFO(inode->i_mode))
-		goto out_fput;
+		return -ESPIPE;
 
-	ret = -ENODEV;
 	/*
 	 * Let individual file system decide if it supports preallocation
 	 * for directories or not.
 	 */
 	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
-		goto out_fput;
+		return -ENODEV;
 
-	ret = -EFBIG;
 	/* Check for wrap through zero too */
 	if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
-		goto out_fput;
+		return -EFBIG;
 
 	if (inode->i_op && inode->i_op->fallocate)
-		ret = inode->i_op->fallocate(inode, mode, offset, len);
+		return inode->i_op->fallocate(inode, mode, offset, len);
 	else
-		ret = -EOPNOTSUPP;
+		return -EOPNOTSUPP;
+}
 
-out_fput:
-	fput(file);
-out:
-	return ret;
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
+{
+	struct file *file;
+	int error = -EBADF;
+
+	file = fget(fd);
+	if (file) {
+		error = do_fallocate(file, mode, offset, len);
+		fput(file);
+	}
+
+	return error;
 }
 
 /*
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
index 8e912ab..c4bf904 100644
--- a/include/linux/falloc.h
+++ b/include/linux/falloc.h
@@ -3,4 +3,25 @@
 
 #define FALLOC_FL_KEEP_SIZE	0x01 /* default is extend size */
 
+#ifdef __KERNEL__
+
+/*
+ * Space reservation ioctls and argument structure
+ * are designed to be compatible with the legacy XFS ioctls.
+ */
+struct space_resv {
+	__s16		l_type;
+	__s16		l_whence;
+	__s64		l_start;
+	__s64		l_len;		/* len == 0 means until end of file */
+	__s32		l_sysid;
+	__u32		l_pid;
+	__s32		l_pad[4];	/* reserve area			    */
+};
+
+#define F_IOC_RESVSP		_IOW('X', 40, struct space_resv)
+#define F_IOC_RESVSP64		_IOW('X', 42, struct space_resv)
+
+#endif
+
 #endif /* _FALLOC_H_ */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4a853ef..b1d8f12 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1671,6 +1671,8 @@ static inline int break_lease(struct inode *inode, unsigned int mode)
 
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
+extern long do_fallocate(struct file *file, int mode, loff_t offset,
+			loff_t len);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			int mode);
 extern struct file *filp_open(const char *, int, int);

Re: [PATCH v2] fs: Add new pre-allocation ioctls to vfs for compatibility with legacy xfs ioctls

[Dave Chinner]

On Fri, Dec 19, 2008 at 02:51:00AM +0530, Ankit Jain wrote:
> This patch adds ioctls to vfs for compatibility with legacy XFS
> pre-allocation ioctls (XFS_IOC_*RESVP*). The implementation
> effectively invokes sys_fallocate for the new ioctls.
> Note: These legacy ioctls are also implemented by OCFS2.
> 
> Changes in v2:
> - Dropped the incorrect handling of *UNRESVSP* ioctl.
> - Made the ioctl and argument structure kernel only (__KERNEL__)
> 
> Signed-off-by: Ankit Jain <me@ankitjain.org>
.....
> @@ -361,6 +393,9 @@ static int file_ioctl(struct file *filp, unsigned int cmd,
>  		return put_user(inode->i_sb->s_blocksize, p);
>  	case FIONREAD:
>  		return put_user(i_size_read(inode) - filp->f_pos, p);
> +	case F_IOC_RESVSP:
> +	case F_IOC_RESVSP64:
> +		return ioctl_preallocate(filp, arg);
>  	}
>  
>  	return vfs_ioctl(filp, cmd, arg);

Adding this here breaks XFS_IOC_RESVSP in subtle and interesting
ways.

XFS_IOC_RESVSP supports invisible I/O, and that means
XFS_IOC_RESVSP needs to be passed through to vfs_ioctl()
to vector to XFS to handle.

This happenѕ because:

> +struct space_resv {
> +	__s16		l_type;
> +	__s16		l_whence;
> +	__s64		l_start;
> +	__s64		l_len;		/* len == 0 means until end of file */
> +	__s32		l_sysid;
> +	__u32		l_pid;
> +	__s32		l_pad[4];	/* reserve area			    */
> +};
> +
> +#define F_IOC_RESVSP		_IOW('X', 40, struct space_resv)
> +#define F_IOC_RESVSP64		_IOW('X', 42, struct space_resv)

Is the same as:

#define XFS_IOC_RESVSP          _IOW ('X', 40, struct xfs_flock64)
#define XFS_IOC_RESVSP64        _IOW ('X', 42, struct xfs_flock64)

because:

typedef struct xfs_flock64 {
        __s16           l_type;
        __s16           l_whence;
        __s64           l_start;
        __s64           l_len;          /* len == 0 means until end of file */
        __s32           l_sysid;
        __u32           l_pid;
        __s32           l_pad[4];       /* reserve area                     */
} xfs_flock64_t;


is the same size as struct space_resv. Hence existing calls to
XFS_IOC_RESVSP will now vector incorrectly down the fallocate path
resulting in invisible operations will now be visible....

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2] fs: Add new pre-allocation ioctls to vfs for compatibility with legacy xfs ioctls

[Christoph Hellwig]

On Fri, Dec 19, 2008 at 03:37:44PM +1100, Dave Chinner wrote:
> XFS_IOC_RESVSP supports invisible I/O, and that means
> XFS_IOC_RESVSP needs to be passed through to vfs_ioctl()
> to vector to XFS to handle.

When the current XFS git tree gets merged to mainline before this
patch.  invisible I/O handling is now FMODE_NOCMTIME in file->f_flags
which this patch will pass through to the filesystem.  We just need
to chage xfs_vn_fallocate ot honour it.