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

[Christoph Hellwig]

On Sat, Jun 20, 2009 at 08:13:59AM +0000, Arnd Bergmann wrote:
> I'd just define this using compat_s64 instead of __s64 __packed so we can
> use the same code on all architectures, even at the small cost of extra
> text size on non-x86 architectures.

I'm not a big fan of imposing the translation overhead to all
architectures, but doing it allows using the good old HANDLE_IOCTL
and futher simplifying things.



Index: linux-2.6/fs/compat_ioctl.c
===================================================================
--- linux-2.6.orig/fs/compat_ioctl.c	2009-06-20 20:19:47.035930201 +0200
+++ linux-2.6/fs/compat_ioctl.c	2009-06-20 20:20:43.821833210 +0200
@@ -31,6 +31,7 @@
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/vt.h>
+#include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/ppp_defs.h>
@@ -1820,6 +1821,38 @@ lp_timeout_trans(unsigned int fd, unsign
 	return sys_ioctl(fd, cmd, (unsigned long)tn);
 }
 
+/* on ia32 l_start is on a 32-bit boundary */
+struct space_resv_32 {
+	__s16		l_type;
+	__s16		l_whence;
+	compat_s64	l_start;
+	compat_s64	l_len;		/* len == 0 means until end of file */
+	__s32		l_sysid;
+	__u32		l_pid;
+	__s32		l_pad[4];	/* reserve area */
+};
+
+#define FS_IOC_RESVSP_32		_IOW ('X', 40, struct space_resv_32)
+#define FS_IOC_RESVSP64_32	_IOW ('X', 42, struct space_resv_32)
+
+/* just account for different alignment */
+static int compat_ioctl_resvsp(unsigned fd, unsigned cmd, unsigned long arg)
+{
+	struct space_resv_32	__user *p32 = (void __user *)arg;
+	struct space_resv	__user *p = compat_alloc_user_space(sizeof(*p));
+
+	if (copy_in_user(&p->l_type,	&p32->l_type,	sizeof(s16)) ||
+	    copy_in_user(&p->l_whence,	&p32->l_whence, sizeof(s16)) ||
+	    copy_in_user(&p->l_start,	&p32->l_start,	sizeof(s64)) ||
+	    copy_in_user(&p->l_len,	&p32->l_len,	sizeof(s64)) ||
+	    copy_in_user(&p->l_sysid,	&p32->l_sysid,	sizeof(s32)) ||
+	    copy_in_user(&p->l_pid,	&p32->l_pid,	sizeof(u32)) ||
+	    copy_in_user(&p->l_pad,	&p32->l_pad,	4*sizeof(u32)))
+		return -EFAULT;
+
+	return sys_ioctl(fd, FS_IOC_RESVSP, p);
+}
+
 
 typedef int (*ioctl_trans_handler_t)(unsigned int, unsigned int,
 					unsigned long, struct file *);
@@ -1915,6 +1948,8 @@ COMPATIBLE_IOCTL(FIGETBSZ)
 /* 'X' - originally XFS but some now in the VFS */
 COMPATIBLE_IOCTL(FIFREEZE)
 COMPATIBLE_IOCTL(FITHAW)
+HANDLE_IOCTL(FS_IOC_RESVSP_32, compat_ioctl_resvsp)
+HANDLE_IOCTL(FS_IOC_RESVSP64_32, compat_ioctl_resvsp)
 /* RAID */
 COMPATIBLE_IOCTL(RAID_VERSION)
 COMPATIBLE_IOCTL(GET_ARRAY_INFO)
Index: linux-2.6/fs/ioctl.c
===================================================================
--- linux-2.6.orig/fs/ioctl.c	2009-06-20 20:19:47.040930349 +0200
+++ linux-2.6/fs/ioctl.c	2009-06-20 20:20:43.821833210 +0200
@@ -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>
 
@@ -403,6 +404,37 @@ 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_resvsp(struct file *filp, void __user *argp)
+{
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	struct space_resv sr;
+
+	if (copy_from_user(&sr, argp, 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)
 {
@@ -414,6 +446,9 @@ static int file_ioctl(struct file *filp,
 		return ioctl_fibmap(filp, p);
 	case FIONREAD:
 		return put_user(i_size_read(inode) - filp->f_pos, p);
+	case FS_IOC_RESVSP:
+	case FS_IOC_RESVSP64:
+		return ioctl_resvsp(filp, p);
 	}
 
 	return vfs_ioctl(filp, cmd, arg);
Index: linux-2.6/fs/open.c
===================================================================
--- linux-2.6.orig/fs/open.c	2009-06-20 20:19:47.054929896 +0200
+++ linux-2.6/fs/open.c	2009-06-20 20:20:43.822836760 +0200
@@ -378,63 +378,63 @@ SYSCALL_ALIAS(sys_ftruncate64, SyS_ftrun
 #endif
 #endif /* BITS_PER_LONG == 32 */
 
-SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
+
+int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
-	struct file *file;
-	struct inode *inode;
-	long ret = -EINVAL;
+	struct inode *inode = file->f_path.dentry->d_inode;
+	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;
+		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->fallocate)
-		ret = inode->i_op->fallocate(inode, mode, offset, len);
-	else
-		ret = -EOPNOTSUPP;
+	if (!inode->i_op->fallocate)
+		return -EOPNOTSUPP;
 
-out_fput:
-	fput(file);
-out:
-	return ret;
+	return inode->i_op->fallocate(inode, mode, offset, len);
 }
+
+SYSCALL_DEFINE(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;
+}
+
 #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
 asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len)
 {
Index: linux-2.6/include/linux/falloc.h
===================================================================
--- linux-2.6.orig/include/linux/falloc.h	2009-06-20 20:19:47.059930323 +0200
+++ linux-2.6/include/linux/falloc.h	2009-06-20 20:20:43.822836760 +0200
@@ -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];	/* reserved area */
+};
+
+#define FS_IOC_RESVSP		_IOW('X', 40, struct space_resv)
+#define FS_IOC_RESVSP64		_IOW('X', 42, struct space_resv)
+
+#endif /* __KERNEL__ */
+
 #endif /* _FALLOC_H_ */
Index: linux-2.6/include/linux/fs.h
===================================================================
--- linux-2.6.orig/include/linux/fs.h	2009-06-20 20:19:47.065929969 +0200
+++ linux-2.6/include/linux/fs.h	2009-06-20 20:20:43.823832557 +0200
@@ -1905,6 +1905,8 @@ static inline int break_lease(struct ino
 
 extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
 		       struct file *filp);
+extern int 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);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/