[PATCH 07/26] r/o bind mounts: elevate write count for some ioctls

[Dave Hansen <haveblue@us.ibm.com>]

Some ioctl()s can cause writes to the filesystem.  Take
these, and make them use mnt_want/drop_write() instead.

We need to pass the filp one layer deeper in XFS, but
somebody _just_ pulled it out in February because nobody
was using it, so I don't feel guilty for adding it back.

Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
---

 lxc-dave/fs/ext2/ioctl.c              |   46 +++++++++-----
 lxc-dave/fs/ext3/ioctl.c              |  100 +++++++++++++++++++++-----------
 lxc-dave/fs/ext4/ioctl.c              |  105 +++++++++++++++++++++-------------
 lxc-dave/fs/fat/file.c                |   10 +--
 lxc-dave/fs/hfsplus/ioctl.c           |   39 +++++++-----
 lxc-dave/fs/jfs/ioctl.c               |   33 ++++++----
 lxc-dave/fs/ocfs2/ioctl.c             |   11 +--
 lxc-dave/fs/reiserfs/ioctl.c          |   53 +++++++++++------
 lxc-dave/fs/xfs/linux-2.6/xfs_ioctl.c |   15 +++-
 lxc-dave/fs/xfs/linux-2.6/xfs_iops.c  |    7 --
 lxc-dave/fs/xfs/linux-2.6/xfs_lrw.c   |    9 ++
 11 files changed, 272 insertions(+), 156 deletions(-)

diff -puN fs/ext2/ioctl.c~05-24-ioctl-mnt-takers fs/ext2/ioctl.c
--- lxc/fs/ext2/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/ext2/ioctl.c	2007-06-22 10:58:25.000000000 -0700
@@ -12,6 +12,7 @@
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <linux/compat.h>
+#include <linux/mount.h>
 #include <linux/smp_lock.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
@@ -22,6 +23,7 @@ int ext2_ioctl (struct inode * inode, st
 {
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	unsigned int flags;
+	int ret;
 
 	ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
 
@@ -32,14 +34,19 @@ int ext2_ioctl (struct inode * inode, st
 	case EXT2_IOC_SETFLAGS: {
 		unsigned int oldflags;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
+		ret = mnt_want_write(filp->f_vfsmnt);
+		if (ret)
+			return ret;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			ret = -EACCES;
+			goto setflags_out;
+		}
 
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
+		if (get_user(flags, (int __user *) arg)) {
+			ret = -EFAULT;
+			goto setflags_out;
+		}
 
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~EXT2_DIRSYNC_FL;
@@ -56,7 +63,8 @@ int ext2_ioctl (struct inode * inode, st
 		if ((flags ^ oldflags) & (EXT2_APPEND_FL | EXT2_IMMUTABLE_FL)) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				ret = -EPERM;
+				goto setflags_out;
 			}
 		}
 
@@ -68,20 +76,26 @@ int ext2_ioctl (struct inode * inode, st
 		ext2_set_inode_flags(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return ret;
 	}
 	case EXT2_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *) arg);
 	case EXT2_IOC_SETVERSION:
 		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(inode->i_generation, (int __user *) arg))
-			return -EFAULT;	
-		inode->i_ctime = CURRENT_TIME_SEC;
-		mark_inode_dirty(inode);
-		return 0;
+		ret = mnt_want_write(filp->f_vfsmnt);
+		if (ret)
+			return ret;
+		if (get_user(inode->i_generation, (int __user *) arg)) {
+			ret = -EFAULT;
+		} else {
+			inode->i_ctime = CURRENT_TIME_SEC;
+			mark_inode_dirty(inode);
+		}
+		mnt_drop_write(filp->f_vfsmnt);
+		return ret;
 	default:
 		return -ENOTTY;
 	}
diff -puN fs/ext3/ioctl.c~05-24-ioctl-mnt-takers fs/ext3/ioctl.c
--- lxc/fs/ext3/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/ext3/ioctl.c	2007-06-22 10:59:02.000000000 -0700
@@ -12,6 +12,7 @@
 #include <linux/capability.h>
 #include <linux/ext3_fs.h>
 #include <linux/ext3_jbd.h>
+#include <linux/mount.h>
 #include <linux/time.h>
 #include <linux/compat.h>
 #include <linux/smp_lock.h>
@@ -37,14 +38,19 @@ int ext3_ioctl (struct inode * inode, st
 		unsigned int oldflags;
 		unsigned int jflag;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto flags_out;
+		}
 
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
+		if (get_user(flags, (int __user *) arg)) {
+			err = -EFAULT;
+			goto flags_out;
+		}
 
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~EXT3_DIRSYNC_FL;
@@ -64,7 +70,8 @@ int ext3_ioctl (struct inode * inode, st
 		if ((flags ^ oldflags) & (EXT3_APPEND_FL | EXT3_IMMUTABLE_FL)) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto flags_out;
 			}
 		}
 
@@ -75,7 +82,8 @@ int ext3_ioctl (struct inode * inode, st
 		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) {
 			if (!capable(CAP_SYS_RESOURCE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto flags_out;
 			}
 		}
 
@@ -83,7 +91,8 @@ int ext3_ioctl (struct inode * inode, st
 		handle = ext3_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
 			mutex_unlock(&inode->i_mutex);
-			return PTR_ERR(handle);
+			err = PTR_ERR(handle);
+			goto flags_out;
 		}
 		if (IS_SYNC(inode))
 			handle->h_sync = 1;
@@ -109,6 +118,8 @@ flags_err:
 		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL))
 			err = ext3_change_inode_journal_flag(inode, jflag);
 		mutex_unlock(&inode->i_mutex);
+flags_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 	case EXT3_IOC_GETVERSION:
@@ -123,14 +134,18 @@ flags_err:
 
 		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(generation, (int __user *) arg))
-			return -EFAULT;
-
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
+		if (get_user(generation, (int __user *) arg)) {
+			err = -EFAULT;
+			goto setversion_out;
+		}
 		handle = ext3_journal_start(inode, 1);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto setversion_out;
+		}
 		err = ext3_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
 			inode->i_ctime = CURRENT_TIME_SEC;
@@ -138,6 +153,8 @@ flags_err:
 			err = ext3_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext3_journal_stop(handle);
+setversion_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 #ifdef CONFIG_JBD_DEBUG
@@ -173,18 +190,24 @@ flags_err:
 		}
 		return -ENOTTY;
 	case EXT3_IOC_SETRSVSZ: {
+		int err;
 
 		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
 			return -ENOTTY;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto setrsvsz_out;
+		}
 
-		if (get_user(rsv_window_size, (int __user *)arg))
-			return -EFAULT;
+		if (get_user(rsv_window_size, (int __user *)arg)) {
+			err = -EFAULT;
+			goto setrsvsz_out;
+		}
 
 		if (rsv_window_size > EXT3_MAX_RESERVE_BLOCKS)
 			rsv_window_size = EXT3_MAX_RESERVE_BLOCKS;
@@ -202,7 +225,9 @@ flags_err:
 			rsv->rsv_goal_size = rsv_window_size;
 		}
 		mutex_unlock(&ei->truncate_mutex);
-		return 0;
+setrsvsz_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return err;
 	}
 	case EXT3_IOC_GROUP_EXTEND: {
 		ext3_fsblk_t n_blocks_count;
@@ -212,17 +237,20 @@ flags_err:
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if (get_user(n_blocks_count, (__u32 __user *)arg))
-			return -EFAULT;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
+		if (get_user(n_blocks_count, (__u32 __user *)arg)) {
+			err = -EFAULT;
+			goto group_extend_out;
+		}
 		err = ext3_group_extend(sb, EXT3_SB(sb)->s_es, n_blocks_count);
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
 		journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
-
+group_extend_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 	case EXT3_IOC_GROUP_ADD: {
@@ -233,18 +261,22 @@ flags_err:
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
 		if (copy_from_user(&input, (struct ext3_new_group_input __user *)arg,
-				sizeof(input)))
-			return -EFAULT;
+				sizeof(input))) {
+			err = -EFAULT;
+			goto group_add_out;
+		}
 
 		err = ext3_group_add(sb, &input);
 		journal_lock_updates(EXT3_SB(sb)->s_journal);
 		journal_flush(EXT3_SB(sb)->s_journal);
 		journal_unlock_updates(EXT3_SB(sb)->s_journal);
-
+group_add_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 
diff -puN fs/ext4/ioctl.c~05-24-ioctl-mnt-takers fs/ext4/ioctl.c
--- lxc/fs/ext4/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/ext4/ioctl.c	2007-06-22 11:00:03.000000000 -0700
@@ -12,6 +12,7 @@
 #include <linux/capability.h>
 #include <linux/ext4_fs.h>
 #include <linux/ext4_jbd2.h>
+#include <linux/mount.h>
 #include <linux/time.h>
 #include <linux/compat.h>
 #include <linux/smp_lock.h>
@@ -37,15 +38,19 @@ int ext4_ioctl (struct inode * inode, st
 		unsigned int oldflags;
 		unsigned int jflag;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto flags_out;
+		}
 
+		if (get_user(flags, (int __user *) arg)) {
+			err = -EFAULT;
+			goto flags_out;
+		}
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~EXT4_DIRSYNC_FL;
 
@@ -64,7 +69,8 @@ int ext4_ioctl (struct inode * inode, st
 		if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto flags_out;
 			}
 		}
 
@@ -75,7 +81,8 @@ int ext4_ioctl (struct inode * inode, st
 		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
 			if (!capable(CAP_SYS_RESOURCE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto flags_out;
 			}
 		}
 
@@ -83,7 +90,8 @@ int ext4_ioctl (struct inode * inode, st
 		handle = ext4_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
 			mutex_unlock(&inode->i_mutex);
-			return PTR_ERR(handle);
+			err = PTR_ERR(handle);
+			goto flags_out;
 		}
 		if (IS_SYNC(inode))
 			handle->h_sync = 1;
@@ -103,12 +111,14 @@ flags_err:
 		ext4_journal_stop(handle);
 		if (err) {
 			mutex_unlock(&inode->i_mutex);
-			return err;
+			goto flags_out;
 		}
 
 		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
 			err = ext4_change_inode_journal_flag(inode, jflag);
 		mutex_unlock(&inode->i_mutex);
+flags_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 	case EXT4_IOC_GETVERSION:
@@ -123,14 +133,18 @@ flags_err:
 
 		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(generation, (int __user *) arg))
-			return -EFAULT;
-
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
+		if (get_user(generation, (int __user *) arg)) {
+			err = -EFAULT;
+			goto setversion_out;
+		}
 		handle = ext4_journal_start(inode, 1);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
+		if (IS_ERR(handle)) {
+			err = PTR_ERR(handle);
+			goto setversion_out;
+		}
 		err = ext4_reserve_inode_write(handle, inode, &iloc);
 		if (err == 0) {
 			inode->i_ctime = CURRENT_TIME_SEC;
@@ -138,6 +152,8 @@ flags_err:
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext4_journal_stop(handle);
+setversion_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 #ifdef CONFIG_JBD_DEBUG
@@ -173,19 +189,23 @@ flags_err:
 		}
 		return -ENOTTY;
 	case EXT4_IOC_SETRSVSZ: {
+		int err;
 
 		if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
 			return -ENOTTY;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
-
-		if (get_user(rsv_window_size, (int __user *)arg))
-			return -EFAULT;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto setrsvsz_out;
+		}
+		if (get_user(rsv_window_size, (int __user *)arg)) {
+			err = -EFAULT;
+			goto setrsvsz_out;
+		}
 		if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS)
 			rsv_window_size = EXT4_MAX_RESERVE_BLOCKS;
 
@@ -202,7 +222,9 @@ flags_err:
 			rsv->rsv_goal_size = rsv_window_size;
 		}
 		mutex_unlock(&ei->truncate_mutex);
-		return 0;
+setrsvsz_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return err;
 	}
 	case EXT4_IOC_GROUP_EXTEND: {
 		ext4_fsblk_t n_blocks_count;
@@ -212,17 +234,21 @@ flags_err:
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if (get_user(n_blocks_count, (__u32 __user *)arg))
-			return -EFAULT;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
+		if (get_user(n_blocks_count, (__u32 __user *)arg)) {
+			err = -EFAULT;
+			goto group_extend_out;
+		}
 		err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
 
+group_extend_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 	case EXT4_IOC_GROUP_ADD: {
@@ -233,18 +259,21 @@ flags_err:
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
 
 		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
-				sizeof(input)))
-			return -EFAULT;
-
+				sizeof(input))) {
+			err = -EFAULT;
+			goto group_add_out;
+		}
 		err = ext4_group_add(sb, &input);
 		jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 		jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
-
+group_add_out:
+		mnt_drop_write(filp->f_vfsmnt);
 		return err;
 	}
 
diff -puN fs/fat/file.c~05-24-ioctl-mnt-takers fs/fat/file.c
--- lxc/fs/fat/file.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/fat/file.c	2007-06-22 10:05:25.000000000 -0700
@@ -8,6 +8,7 @@
 
 #include <linux/capability.h>
 #include <linux/module.h>
+#include <linux/mount.h>
 #include <linux/time.h>
 #include <linux/msdos_fs.h>
 #include <linux/smp_lock.h>
@@ -46,10 +47,9 @@ int fat_generic_ioctl(struct inode *inod
 
 		mutex_lock(&inode->i_mutex);
 
-		if (IS_RDONLY(inode)) {
-			err = -EROFS;
-			goto up;
-		}
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			goto up_no_drop_write;
 
 		/*
 		 * ATTR_VOLUME and ATTR_DIR cannot be changed; this also
@@ -106,6 +106,8 @@ int fat_generic_ioctl(struct inode *inod
 		MSDOS_I(inode)->i_attrs = attr & ATTR_UNUSED;
 		mark_inode_dirty(inode);
 	up:
+		mnt_drop_write(filp->f_vfsmnt);
+	up_no_drop_write:
 		mutex_unlock(&inode->i_mutex);
 		return err;
 	}
diff -puN fs/hfsplus/ioctl.c~05-24-ioctl-mnt-takers fs/hfsplus/ioctl.c
--- lxc/fs/hfsplus/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/hfsplus/ioctl.c	2007-06-22 11:02:23.000000000 -0700
@@ -35,25 +35,32 @@ int hfsplus_ioctl(struct inode *inode, s
 			flags |= FS_NODUMP_FL; /* EXT2_NODUMP_FL */
 		return put_user(flags, (int __user *)arg);
 	case HFSPLUS_IOC_EXT2_SETFLAGS: {
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
-
-		if (get_user(flags, (int __user *)arg))
-			return -EFAULT;
-
+		int err = 0;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto setflags_out;
+		}
+		if (get_user(flags, (int __user *)arg)) {
+			err = -EFAULT;
+			goto setflags_out;
+		}
 		if (flags & (FS_IMMUTABLE_FL|FS_APPEND_FL) ||
 		    HFSPLUS_I(inode).rootflags & (HFSPLUS_FLG_IMMUTABLE|HFSPLUS_FLG_APPEND)) {
-			if (!capable(CAP_LINUX_IMMUTABLE))
-				return -EPERM;
+			if (!capable(CAP_LINUX_IMMUTABLE)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
 		}
 
 		/* don't silently ignore unsupported ext2 flags */
-		if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL))
-			return -EOPNOTSUPP;
-
+		if (flags & ~(FS_IMMUTABLE_FL|FS_APPEND_FL|FS_NODUMP_FL)) {
+			err = -EOPNOTSUPP;
+			goto setflags_out;
+		}
 		if (flags & FS_IMMUTABLE_FL) { /* EXT2_IMMUTABLE_FL */
 			inode->i_flags |= S_IMMUTABLE;
 			HFSPLUS_I(inode).rootflags |= HFSPLUS_FLG_IMMUTABLE;
@@ -75,7 +82,9 @@ int hfsplus_ioctl(struct inode *inode, s
 
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return err;
 	}
 	default:
 		return -ENOTTY;
diff -puN fs/jfs/ioctl.c~05-24-ioctl-mnt-takers fs/jfs/ioctl.c
--- lxc/fs/jfs/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/jfs/ioctl.c	2007-06-22 11:02:32.000000000 -0700
@@ -8,6 +8,7 @@
 #include <linux/fs.h>
 #include <linux/ctype.h>
 #include <linux/capability.h>
+#include <linux/mount.h>
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <asm/current.h>
@@ -64,16 +65,20 @@ int jfs_ioctl(struct inode * inode, stru
 		return put_user(flags, (int __user *) arg);
 	case JFS_IOC_SETFLAGS: {
 		unsigned int oldflags;
+		int err;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
-			return -EACCES;
-
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
-
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
+
+		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER)) {
+			err = -EACCES;
+			goto setflags_out;
+		}
+		if (get_user(flags, (int __user *) arg)) {
+			err = -EFAULT;
+			goto setflags_out;
+		}
 		flags = jfs_map_ext2(flags, 1);
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~JFS_DIRSYNC_FL;
@@ -87,8 +92,10 @@ int jfs_ioctl(struct inode * inode, stru
 		if ((oldflags & JFS_IMMUTABLE_FL) ||
 			((flags ^ oldflags) &
 			(JFS_APPEND_FL | JFS_IMMUTABLE_FL))) {
-			if (!capable(CAP_LINUX_IMMUTABLE))
-				return -EPERM;
+			if (!capable(CAP_LINUX_IMMUTABLE)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
 		}
 
 		flags = flags & JFS_FL_USER_MODIFIABLE;
@@ -98,7 +105,9 @@ int jfs_ioctl(struct inode * inode, stru
 		jfs_set_inode_flags(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return err;
 	}
 	default:
 		return -ENOTTY;
diff -puN fs/ocfs2/ioctl.c~05-24-ioctl-mnt-takers fs/ocfs2/ioctl.c
--- lxc/fs/ocfs2/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/ocfs2/ioctl.c	2007-06-22 10:05:25.000000000 -0700
@@ -56,10 +56,6 @@ static int ocfs2_set_inode_attr(struct i
 		goto bail;
 	}
 
-	status = -EROFS;
-	if (IS_RDONLY(inode))
-		goto bail_unlock;
-
 	status = -EACCES;
 	if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
 		goto bail_unlock;
@@ -127,8 +123,13 @@ int ocfs2_ioctl(struct inode * inode, st
 		if (get_user(flags, (int __user *) arg))
 			return -EFAULT;
 
-		return ocfs2_set_inode_attr(inode, flags,
+		status = mnt_want_write(filp->f_vfsmnt);
+		if (status)
+			return status;
+		status = ocfs2_set_inode_attr(inode, flags,
 			OCFS2_FL_MODIFIABLE);
+		mnt_drop_write(filp->f_vfsmnt);
+		return status;
 	default:
 		return -ENOTTY;
 	}
diff -puN fs/reiserfs/ioctl.c~05-24-ioctl-mnt-takers fs/reiserfs/ioctl.c
--- lxc/fs/reiserfs/ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/reiserfs/ioctl.c	2007-06-22 11:04:42.000000000 -0700
@@ -4,6 +4,7 @@
 
 #include <linux/capability.h>
 #include <linux/fs.h>
+#include <linux/mount.h>
 #include <linux/reiserfs_fs.h>
 #include <linux/time.h>
 #include <asm/uaccess.h>
@@ -25,6 +26,7 @@ int reiserfs_ioctl(struct inode *inode, 
 		   unsigned long arg)
 {
 	unsigned int flags;
+	int err = 0;
 
 	switch (cmd) {
 	case REISERFS_IOC_UNPACK:
@@ -48,48 +50,61 @@ int reiserfs_ioctl(struct inode *inode, 
 			if (!reiserfs_attrs(inode->i_sb))
 				return -ENOTTY;
 
-			if (IS_RDONLY(inode))
-				return -EROFS;
+			err = mnt_want_write(filp->f_vfsmnt);
+			if (err)
+				return err;
 
 			if ((current->fsuid != inode->i_uid)
-			    && !capable(CAP_FOWNER))
-				return -EPERM;
-
-			if (get_user(flags, (int __user *)arg))
-				return -EFAULT;
-
+			    && !capable(CAP_FOWNER)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
+			if (get_user(flags, (int __user *)arg)) {
+				err = -EFAULT;
+				goto setflags_out;
+			}
 			if (((flags ^ REISERFS_I(inode)->
 			      i_attrs) & (REISERFS_IMMUTABLE_FL |
 					  REISERFS_APPEND_FL))
-			    && !capable(CAP_LINUX_IMMUTABLE))
-				return -EPERM;
-
+			    && !capable(CAP_LINUX_IMMUTABLE)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
 			if ((flags & REISERFS_NOTAIL_FL) &&
 			    S_ISREG(inode->i_mode)) {
 				int result;
 
 				result = reiserfs_unpack(inode, filp);
-				if (result)
-					return result;
+				if (result) {
+					err = result;
+					goto setflags_out;
+				}
 			}
 			sd_attrs_to_i_attrs(flags, inode);
 			REISERFS_I(inode)->i_attrs = flags;
 			inode->i_ctime = CURRENT_TIME_SEC;
 			mark_inode_dirty(inode);
-			return 0;
+setflags_out:
+			mnt_drop_write(filp->f_vfsmnt);
+			return err;
 		}
 	case REISERFS_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *)arg);
 	case REISERFS_IOC_SETVERSION:
 		if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(inode->i_generation, (int __user *)arg))
-			return -EFAULT;
+		err = mnt_want_write(filp->f_vfsmnt);
+		if (err)
+			return err;
+		if (get_user(inode->i_generation, (int __user *)arg)) {
+			err = -EFAULT;
+			goto setversion_out;
+		}
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setversion_out:
+		mnt_drop_write(filp->f_vfsmnt);
+		return err;
 	default:
 		return -ENOTTY;
 	}
diff -puN fs/xfs/linux-2.6/xfs_ioctl.c~05-24-ioctl-mnt-takers fs/xfs/linux-2.6/xfs_ioctl.c
--- lxc/fs/xfs/linux-2.6/xfs_ioctl.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/xfs/linux-2.6/xfs_ioctl.c	2007-06-22 10:05:25.000000000 -0700
@@ -526,8 +526,6 @@ xfs_attrmulti_attr_set(
 	char			*kbuf;
 	int			error = EFAULT;
 
-	if (IS_RDONLY(&vp->v_inode))
-		return -EROFS;
 	if (IS_IMMUTABLE(&vp->v_inode) || IS_APPEND(&vp->v_inode))
 		return EPERM;
 	if (len > XATTR_SIZE_MAX)
@@ -553,8 +551,6 @@ xfs_attrmulti_attr_remove(
 	char			*name,
 	__uint32_t		flags)
 {
-	if (IS_RDONLY(&vp->v_inode))
-		return -EROFS;
 	if (IS_IMMUTABLE(&vp->v_inode) || IS_APPEND(&vp->v_inode))
 		return EPERM;
 	return bhv_vop_attr_remove(vp, name, flags, NULL);
@@ -564,6 +560,7 @@ STATIC int
 xfs_attrmulti_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
+	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -618,13 +615,21 @@ xfs_attrmulti_by_handle(
 					&ops[i].am_length, ops[i].am_flags);
 			break;
 		case ATTR_OP_SET:
+			ops[i].am_error = mnt_want_write(parfilp->f_vfsmnt);
+			if (ops[i].am_error)
+				break;
 			ops[i].am_error = xfs_attrmulti_attr_set(vp,
 					attr_name, ops[i].am_attrvalue,
 					ops[i].am_length, ops[i].am_flags);
+			mnt_drop_write(parfilp->f_vfsmnt);
 			break;
 		case ATTR_OP_REMOVE:
+			ops[i].am_error = mnt_want_write(parfilp->f_vfsmnt);
+			if (ops[i].am_error)
+				break;
 			ops[i].am_error = xfs_attrmulti_attr_remove(vp,
 					attr_name, ops[i].am_flags);
+			mnt_drop_write(parfilp->f_vfsmnt);
 			break;
 		default:
 			ops[i].am_error = EINVAL;
@@ -804,7 +809,7 @@ xfs_ioctl(
 		return xfs_attrlist_by_handle(mp, arg, inode);
 
 	case XFS_IOC_ATTRMULTI_BY_HANDLE:
-		return xfs_attrmulti_by_handle(mp, arg, inode);
+		return xfs_attrmulti_by_handle(mp, arg, filp, inode);
 
 	case XFS_IOC_SWAPEXT: {
 		error = xfs_swapext((struct xfs_swapext __user *)arg);
diff -puN fs/xfs/linux-2.6/xfs_iops.c~05-24-ioctl-mnt-takers fs/xfs/linux-2.6/xfs_iops.c
--- lxc/fs/xfs/linux-2.6/xfs_iops.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/xfs/linux-2.6/xfs_iops.c	2007-06-22 10:05:25.000000000 -0700
@@ -156,13 +156,6 @@ xfs_ichgtime_fast(
 	 */
 	ASSERT((flags & XFS_ICHGTIME_ACC) == 0);
 
-	/*
-	 * We're not supposed to change timestamps in readonly-mounted
-	 * filesystems.  Throw it away if anyone asks us.
-	 */
-	if (unlikely(IS_RDONLY(inode)))
-		return;
-
 	if (flags & XFS_ICHGTIME_MOD) {
 		tvp = &inode->i_mtime;
 		ip->i_d.di_mtime.t_sec = (__int32_t)tvp->tv_sec;
diff -puN fs/xfs/linux-2.6/xfs_lrw.c~05-24-ioctl-mnt-takers fs/xfs/linux-2.6/xfs_lrw.c
--- lxc/fs/xfs/linux-2.6/xfs_lrw.c~05-24-ioctl-mnt-takers	2007-06-22 10:05:25.000000000 -0700
+++ lxc-dave/fs/xfs/linux-2.6/xfs_lrw.c	2007-06-22 10:05:25.000000000 -0700
@@ -50,6 +50,7 @@
 #include "xfs_iomap.h"
 
 #include <linux/capability.h>
+#include <linux/mount.h>
 #include <linux/writeback.h>
 
 
@@ -762,10 +763,16 @@ start:
 		}
 	}
 
-	if (likely(!(ioflags & IO_INVIS))) {
+	/*
+	 * We're not supposed to change timestamps in readonly-mounted
+	 * filesystems.  Throw it away if anyone asks us.
+	 */
+	if (likely(!(ioflags & IO_INVIS) &&
+		   !mnt_want_write(file->f_vfsmnt))) {
 		file_update_time(file);
 		xfs_ichgtime_fast(xip, inode,
 				  XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+		mnt_drop_write(file->f_vfsmnt);
 	}
 
 	/*
_