Merge branch 'ro-bind.b6' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'ro-bind.b6' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (24 commits)
  [PATCH] r/o bind mounts: debugging for missed calls
  [PATCH] r/o bind mounts: honor mount writer counts at remount
  [PATCH] r/o bind mounts: track numbers of writers to mounts
  [PATCH] r/o bind mounts: check mnt instead of superblock directly
  [PATCH] r/o bind mounts: elevate count for xfs timestamp updates
  [PATCH] r/o bind mounts: make access() use new r/o helper
  [PATCH] r/o bind mounts: write counts for truncate()
  [PATCH] r/o bind mounts: elevate write count for chmod/chown callers
  [PATCH] r/o bind mounts: elevate write count for open()s
  [PATCH] r/o bind mounts: elevate write count for ioctls()
  [PATCH] r/o bind mounts: write count for file_update_time()
  [PATCH] r/o bind mounts: elevate write count for do_utimes()
  [PATCH] r/o bind mounts: write counts for touch_atime()
  [PATCH] r/o bind mounts: elevate write count for ncp_ioctl()
  [PATCH] r/o bind mounts: elevate write count for xattr_permission() callers
  [PATCH] r/o bind mounts: get write access for vfs_rename() callers
  [PATCH] r/o bind mounts: write counts for link/symlink
  [PATCH] r/o bind mounts: get callers of vfs_mknod/create/mkdir()
  [PATCH] r/o bind mounts: elevate write count for rmdir and unlink.
  [PATCH] r/o bind mounts: drop write during emergency remount
  ...

fs/ext2/ioctl.c

@@ -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>
@@ -23,6 +24,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	unsigned int flags;
 	unsigned short rsv_window_size;
+	int ret;
 
 	ext2_debug ("cmd = %u, arg = %lu\n", cmd, arg);
 
@@ -34,14 +36,19 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	case EXT2_IOC_SETFLAGS: {
 		unsigned int oldflags;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		ret = mnt_want_write(filp->f_path.mnt);
+		if (ret)
+			return ret;
 
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
+		if (!is_owner_or_cap(inode)) {
+			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;
@@ -50,7 +57,8 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		/* Is it quota file? Do not allow user to mess with it */
 		if (IS_NOQUOTA(inode)) {
 			mutex_unlock(&inode->i_mutex);
-			return -EPERM;
+			ret = -EPERM;
+			goto setflags_out;
 		}
 		oldflags = ei->i_flags;
 
@@ -63,7 +71,8 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		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;
 			}
 		}
 
@@ -75,20 +84,26 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		ext2_set_inode_flags(inode);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return ret;
 	}
 	case EXT2_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *) arg);
 	case EXT2_IOC_SETVERSION:
 		if (!is_owner_or_cap(inode))
 			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_path.mnt);
+		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_path.mnt);
+		return ret;
 	case EXT2_IOC_GETRSVSZ:
 		if (test_opt(inode->i_sb, RESERVATION)
 			&& S_ISREG(inode->i_mode)
@@ -102,15 +117,16 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		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))
+		if (!is_owner_or_cap(inode))
 			return -EACCES;
 
 		if (get_user(rsv_window_size, (int __user *)arg))
 			return -EFAULT;
 
+		ret = mnt_want_write(filp->f_path.mnt);
+		if (ret)
+			return ret;
+
 		if (rsv_window_size > EXT2_MAX_RESERVE_BLOCKS)
 			rsv_window_size = EXT2_MAX_RESERVE_BLOCKS;
 
@@ -131,6 +147,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			rsv->rsv_goal_size = rsv_window_size;
 		}
 		mutex_unlock(&ei->truncate_mutex);
+		mnt_drop_write(filp->f_path.mnt);
 		return 0;
 	}
 	default:

fs/ext3/ioctl.c

@@ -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>
@@ -38,14 +39,19 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		unsigned int oldflags;
 		unsigned int jflag;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
 
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
+		if (!is_owner_or_cap(inode)) {
+			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;
@@ -54,7 +60,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		/* Is it quota file? Do not allow user to mess with it */
 		if (IS_NOQUOTA(inode)) {
 			mutex_unlock(&inode->i_mutex);
-			return -EPERM;
+			err = -EPERM;
+			goto flags_out;
 		}
 		oldflags = ei->i_flags;
 
@@ -70,7 +77,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		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;
 			}
 		}
 
@@ -81,7 +89,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) {
 			if (!capable(CAP_SYS_RESOURCE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto flags_out;
 			}
 		}
 
@@ -89,7 +98,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		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;
@@ -115,6 +125,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		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_path.mnt);
 		return err;
 	}
 	case EXT3_IOC_GETVERSION:
@@ -129,14 +141,18 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 
 		if (!is_owner_or_cap(inode))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(generation, (int __user *) arg))
-			return -EFAULT;
-
+		err = mnt_want_write(filp->f_path.mnt);
+		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;
@@ -144,6 +160,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 			err = ext3_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext3_journal_stop(handle);
+setversion_out:
+		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
 #ifdef CONFIG_JBD_DEBUG
@@ -179,18 +197,24 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		}
 		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_path.mnt);
+		if (err)
+			return err;
 
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
+		if (!is_owner_or_cap(inode)) {
+			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;
@@ -208,7 +232,9 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 			rsv->rsv_goal_size = rsv_window_size;
 		}
 		mutex_unlock(&ei->truncate_mutex);
-		return 0;
+setrsvsz_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
 	}
 	case EXT3_IOC_GROUP_EXTEND: {
 		ext3_fsblk_t n_blocks_count;
@@ -218,17 +244,20 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		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_path.mnt);
+		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_path.mnt);
 		return err;
 	}
 	case EXT3_IOC_GROUP_ADD: {
@@ -239,18 +268,22 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_path.mnt);
+		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_path.mnt);
 		return err;
 	}
 

fs/ext4/ioctl.c

@@ -15,6 +15,7 @@
 #include <linux/time.h>
 #include <linux/compat.h>
 #include <linux/smp_lock.h>
+#include <linux/mount.h>
 #include <asm/uaccess.h>
 
 int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
@@ -38,24 +39,25 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		unsigned int oldflags;
 		unsigned int jflag;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
 		if (!is_owner_or_cap(inode))
 			return -EACCES;
 
 		if (get_user(flags, (int __user *) arg))
 			return -EFAULT;
 
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~EXT4_DIRSYNC_FL;
 
+		err = -EPERM;
 		mutex_lock(&inode->i_mutex);
 		/* Is it quota file? Do not allow user to mess with it */
-		if (IS_NOQUOTA(inode)) {
-			mutex_unlock(&inode->i_mutex);
-			return -EPERM;
-		}
+		if (IS_NOQUOTA(inode))
+			goto flags_out;
+
 		oldflags = ei->i_flags;
 
 		/* The JOURNAL_DATA flag is modifiable only by root */
@@ -68,10 +70,8 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * This test looks nicer. Thanks to Pauline Middelink
 		 */
 		if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
-			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
-			}
+			if (!capable(CAP_LINUX_IMMUTABLE))
+				goto flags_out;
 		}
 
 		/*
@@ -79,17 +79,14 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * the relevant capability.
 		 */
 		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
-			if (!capable(CAP_SYS_RESOURCE)) {
-				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
-			}
+			if (!capable(CAP_SYS_RESOURCE))
+				goto flags_out;
 		}
 
-
 		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;
@@ -107,14 +104,14 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 flags_err:
 		ext4_journal_stop(handle);
-		if (err) {
-			mutex_unlock(&inode->i_mutex);
-			return err;
-		}
+		if (err)
+			goto flags_out;
 
 		if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
 			err = ext4_change_inode_journal_flag(inode, jflag);
+flags_out:
 		mutex_unlock(&inode->i_mutex);
+		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
 	case EXT4_IOC_GETVERSION:
@@ -129,14 +126,20 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 
 		if (!is_owner_or_cap(inode))
 			return -EPERM;
-		if (IS_RDONLY(inode))
-			return -EROFS;
-		if (get_user(generation, (int __user *) arg))
-			return -EFAULT;
+
+		err = mnt_want_write(filp->f_path.mnt);
+		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 = ext4_current_time(inode);
@@ -144,6 +147,8 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 			err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 		}
 		ext4_journal_stop(handle);
+setversion_out:
+		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
 #ifdef CONFIG_JBD2_DEBUG
@@ -179,19 +184,21 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		}
 		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 (!is_owner_or_cap(inode))
 			return -EACCES;
 
 		if (get_user(rsv_window_size, (int __user *)arg))
 			return -EFAULT;
 
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
 		if (rsv_window_size > EXT4_MAX_RESERVE_BLOCKS)
 			rsv_window_size = EXT4_MAX_RESERVE_BLOCKS;
 
@@ -208,6 +215,7 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 			rsv->rsv_goal_size = rsv_window_size;
 		}
 		up_write(&ei->i_data_sem);
+		mnt_drop_write(filp->f_path.mnt);
 		return 0;
 	}
 	case EXT4_IOC_GROUP_EXTEND: {
@@ -218,16 +226,18 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		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_path.mnt);
+		if (err)
+			return err;
+
 		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);
+		mnt_drop_write(filp->f_path.mnt);
 
 		return err;
 	}
@@ -239,17 +249,19 @@ int ext4_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		if (!capable(CAP_SYS_RESOURCE))
 			return -EPERM;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
 		if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
 				sizeof(input)))
 			return -EFAULT;
 
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
 		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);
+		mnt_drop_write(filp->f_path.mnt);
 
 		return err;
 	}

fs/fat/file.c

@@ -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 *inode, struct file *filp,
 
 		mutex_lock(&inode->i_mutex);
 
-		if (IS_RDONLY(inode)) {
-			err = -EROFS;
-			goto up;
-		}
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			goto up_no_drop_write;
 
 		/*
 		 * ATTR_VOLUME and ATTR_DIR cannot be changed; this also
@@ -105,7 +105,9 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
 
 		MSDOS_I(inode)->i_attrs = attr & ATTR_UNUSED;
 		mark_inode_dirty(inode);
-	up:
+up:
+		mnt_drop_write(filp->f_path.mnt);
+up_no_drop_write:
 		mutex_unlock(&inode->i_mutex);
 		return err;
 	}

fs/file_table.c

@@ -42,6 +42,7 @@ static inline void file_free_rcu(struct rcu_head *head)
 static inline void file_free(struct file *f)
 {
 	percpu_counter_dec(&nr_files);
+	file_check_state(f);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
 
@@ -199,6 +200,18 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
 	file->f_mapping = dentry->d_inode->i_mapping;
 	file->f_mode = mode;
 	file->f_op = fop;
+
+	/*
+	 * These mounts don't really matter in practice
+	 * for r/o bind mounts.  They aren't userspace-
+	 * visible.  We do this for consistency, and so
+	 * that we can do debugging checks at __fput()
+	 */
+	if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+		file_take_write(file);
+		error = mnt_want_write(mnt);
+		WARN_ON(error);
+	}
 	return error;
 }
 EXPORT_SYMBOL(init_file);
@@ -211,6 +224,31 @@ void fput(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
+/**
+ * drop_file_write_access - give up ability to write to a file
+ * @file: the file to which we will stop writing
+ *
+ * This is a central place which will give up the ability
+ * to write to @file, along with access to write through
+ * its vfsmount.
+ */
+void drop_file_write_access(struct file *file)
+{
+	struct vfsmount *mnt = file->f_path.mnt;
+	struct dentry *dentry = file->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+
+	put_write_access(inode);
+
+	if (special_file(inode->i_mode))
+		return;
+	if (file_check_writeable(file) != 0)
+		return;
+	mnt_drop_write(mnt);
+	file_release_write(file);
+}
+EXPORT_SYMBOL_GPL(drop_file_write_access);
+
 /* __fput is called from task context when aio completion releases the last
  * last use of a struct file *.  Do not use otherwise.
  */
@@ -236,10 +274,10 @@ void __fput(struct file *file)
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL))
 		cdev_put(inode->i_cdev);
 	fops_put(file->f_op);
-	if (file->f_mode & FMODE_WRITE)
-		put_write_access(inode);
 	put_pid(file->f_owner.pid);
 	file_kill(file);
+	if (file->f_mode & FMODE_WRITE)
+		drop_file_write_access(file);
 	file->f_path.dentry = NULL;
 	file->f_path.mnt = NULL;
 	file_free(file);

fs/hfsplus/ioctl.c

@@ -14,6 +14,7 @@
 
 #include <linux/capability.h>
 #include <linux/fs.h>
+#include <linux/mount.h>
 #include <linux/sched.h>
 #include <linux/xattr.h>
 #include <asm/uaccess.h>
@@ -35,25 +36,32 @@ int hfsplus_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 			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 (!is_owner_or_cap(inode))
-			return -EACCES;
-
-		if (get_user(flags, (int __user *)arg))
-			return -EFAULT;
-
+		int err = 0;
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
+
+		if (!is_owner_or_cap(inode)) {
+			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 +83,9 @@ int hfsplus_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
 	}
 	default:
 		return -ENOTTY;

fs/inode.c

@@ -1199,42 +1199,37 @@ void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	struct timespec now;
 
-	if (inode->i_flags & S_NOATIME)
+	if (mnt_want_write(mnt))
 		return;
+	if (inode->i_flags & S_NOATIME)
+		goto out;
 	if (IS_NOATIME(inode))
-		return;
+		goto out;
 	if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
-		return;
+		goto out;
 
-	/*
-	 * We may have a NULL vfsmount when coming from NFSD
-	 */
-	if (mnt) {
-		if (mnt->mnt_flags & MNT_NOATIME)
-			return;
-		if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
-			return;
-
-		if (mnt->mnt_flags & MNT_RELATIME) {
-			/*
-			 * With relative atime, only update atime if the
-			 * previous atime is earlier than either the ctime or
-			 * mtime.
-			 */
-			if (timespec_compare(&inode->i_mtime,
-						&inode->i_atime) < 0 &&
-			    timespec_compare(&inode->i_ctime,
-						&inode->i_atime) < 0)
-				return;
-		}
+	if (mnt->mnt_flags & MNT_NOATIME)
+		goto out;
+	if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
+		goto out;
+	if (mnt->mnt_flags & MNT_RELATIME) {
+		/*
+		 * With relative atime, only update atime if the previous
+		 * atime is earlier than either the ctime or mtime.
+		 */
+		if (timespec_compare(&inode->i_mtime, &inode->i_atime) < 0 &&
+		    timespec_compare(&inode->i_ctime, &inode->i_atime) < 0)
+			goto out;
 	}
 
 	now = current_fs_time(inode->i_sb);
 	if (timespec_equal(&inode->i_atime, &now))
-		return;
+		goto out;
 
 	inode->i_atime = now;
 	mark_inode_dirty_sync(inode);
+out:
+	mnt_drop_write(mnt);
 }
 EXPORT_SYMBOL(touch_atime);
 
@@ -1255,10 +1250,13 @@ void file_update_time(struct file *file)
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct timespec now;
 	int sync_it = 0;
+	int err;
 
 	if (IS_NOCMTIME(inode))
 		return;
-	if (IS_RDONLY(inode))
+
+	err = mnt_want_write(file->f_path.mnt);
+	if (err)
 		return;
 
 	now = current_fs_time(inode->i_sb);
@@ -1279,6 +1277,7 @@ void file_update_time(struct file *file)
 
 	if (sync_it)
 		mark_inode_dirty_sync(inode);
+	mnt_drop_write(file->f_path.mnt);
 }
 
 EXPORT_SYMBOL(file_update_time);

fs/jfs/ioctl.c

@@ -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>
@@ -65,23 +66,30 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return put_user(flags, (int __user *) arg);
 	case JFS_IOC_SETFLAGS: {
 		unsigned int oldflags;
+		int err;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			return err;
 
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
-
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
+		if (!is_owner_or_cap(inode)) {
+			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;
 
 		/* Is it quota file? Do not allow user to mess with it */
-		if (IS_NOQUOTA(inode))
-			return -EPERM;
+		if (IS_NOQUOTA(inode)) {
+			err = -EPERM;
+			goto setflags_out;
+		}
 
 		/* Lock against other parallel changes of flags */
 		mutex_lock(&inode->i_mutex);
@@ -98,7 +106,8 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 			(JFS_APPEND_FL | JFS_IMMUTABLE_FL))) {
 			if (!capable(CAP_LINUX_IMMUTABLE)) {
 				mutex_unlock(&inode->i_mutex);
-				return -EPERM;
+				err = -EPERM;
+				goto setflags_out;
 			}
 		}
 
@@ -110,7 +119,9 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		mutex_unlock(&inode->i_mutex);
 		inode->i_ctime = CURRENT_TIME_SEC;
 		mark_inode_dirty(inode);
-		return 0;
+setflags_out:
+		mnt_drop_write(filp->f_path.mnt);
+		return err;
 	}
 	default:
 		return -ENOTTY;

fs/ncpfs/ioctl.c

@@ -14,6 +14,7 @@
 #include <linux/ioctl.h>
 #include <linux/time.h>
 #include <linux/mm.h>
+#include <linux/mount.h>
 #include <linux/highuid.h>
 #include <linux/smp_lock.h>
 #include <linux/vmalloc.h>
@@ -261,7 +262,7 @@ ncp_get_charsets(struct ncp_server* server, struct ncp_nls_ioctl __user *arg)
 }
 #endif /* CONFIG_NCPFS_NLS */
 
-int ncp_ioctl(struct inode *inode, struct file *filp,
+static int __ncp_ioctl(struct inode *inode, struct file *filp,
 	      unsigned int cmd, unsigned long arg)
 {
 	struct ncp_server *server = NCP_SERVER(inode);
@@ -822,6 +823,57 @@ int ncp_ioctl(struct inode *inode, struct file *filp,
 	return -EINVAL;
 }
 
+static int ncp_ioctl_need_write(unsigned int cmd)
+{
+	switch (cmd) {
+	case NCP_IOC_GET_FS_INFO:
+	case NCP_IOC_GET_FS_INFO_V2:
+	case NCP_IOC_NCPREQUEST:
+	case NCP_IOC_SETDENTRYTTL:
+	case NCP_IOC_SIGN_INIT:
+	case NCP_IOC_LOCKUNLOCK:
+	case NCP_IOC_SET_SIGN_WANTED:
+		return 1;
+	case NCP_IOC_GETOBJECTNAME:
+	case NCP_IOC_SETOBJECTNAME:
+	case NCP_IOC_GETPRIVATEDATA:
+	case NCP_IOC_SETPRIVATEDATA:
+	case NCP_IOC_SETCHARSETS:
+	case NCP_IOC_GETCHARSETS:
+	case NCP_IOC_CONN_LOGGED_IN:
+	case NCP_IOC_GETDENTRYTTL:
+	case NCP_IOC_GETMOUNTUID2:
+	case NCP_IOC_SIGN_WANTED:
+	case NCP_IOC_GETROOT:
+	case NCP_IOC_SETROOT:
+		return 0;
+	default:
+		/* unkown IOCTL command, assume write */
+		return 1;
+	}
+}
+
+int ncp_ioctl(struct inode *inode, struct file *filp,
+	      unsigned int cmd, unsigned long arg)
+{
+	int ret;
+
+	if (ncp_ioctl_need_write(cmd)) {
+		/*
+		 * inside the ioctl(), any failures which
+		 * are because of file_permission() are
+		 * -EACCESS, so it seems consistent to keep
+		 *  that here.
+		 */
+		if (mnt_want_write(filp->f_path.mnt))
+			return -EACCES;
+	}
+	ret = __ncp_ioctl(inode, filp, cmd, arg);
+	if (ncp_ioctl_need_write(cmd))
+		mnt_drop_write(filp->f_path.mnt);
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 long ncp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {

fs/nfs/dir.c

@@ -967,7 +967,8 @@ static int is_atomic_open(struct inode *dir, struct nameidata *nd)
 	if (nd->flags & LOOKUP_DIRECTORY)
 		return 0;
 	/* Are we trying to write to a read only partition? */
-	if (IS_RDONLY(dir) && (nd->intent.open.flags & (O_CREAT|O_TRUNC|FMODE_WRITE)))
+	if (__mnt_is_readonly(nd->path.mnt) &&
+	    (nd->intent.open.flags & (O_CREAT|O_TRUNC|FMODE_WRITE)))
 		return 0;
 	return 1;
 }

fs/nfsd/nfs4proc.c

@@ -658,14 +658,19 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			return status;
 		}
 	}
+	status = mnt_want_write(cstate->current_fh.fh_export->ex_path.mnt);
+	if (status)
+		return status;
 	status = nfs_ok;
 	if (setattr->sa_acl != NULL)
 		status = nfsd4_set_nfs4_acl(rqstp, &cstate->current_fh,
 					    setattr->sa_acl);
 	if (status)
-		return status;
+		goto out;
 	status = nfsd_setattr(rqstp, &cstate->current_fh, &setattr->sa_iattr,
 				0, (time_t)0);
+out:
+	mnt_drop_write(cstate->current_fh.fh_export->ex_path.mnt);
 	return status;
 }
 

fs/nfsd/nfs4recover.c

@@ -46,6 +46,7 @@
 #include <linux/scatterlist.h>
 #include <linux/crypto.h>
 #include <linux/sched.h>
+#include <linux/mount.h>
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -154,7 +155,11 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		dprintk("NFSD: nfsd4_create_clid_dir: DIRECTORY EXISTS\n");
 		goto out_put;
 	}
+	status = mnt_want_write(rec_dir.path.mnt);
+	if (status)
+		goto out_put;
 	status = vfs_mkdir(rec_dir.path.dentry->d_inode, dentry, S_IRWXU);
+	mnt_drop_write(rec_dir.path.mnt);
 out_put:
 	dput(dentry);
 out_unlock:
@@ -313,12 +318,17 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp)
 	if (!rec_dir_init || !clp->cl_firststate)
 		return;
 
+	status = mnt_want_write(rec_dir.path.mnt);
+	if (status)
+		goto out;
 	clp->cl_firststate = 0;
 	nfs4_save_user(&uid, &gid);
 	status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1);
 	nfs4_reset_user(uid, gid);
 	if (status == 0)
 		nfsd4_sync_rec_dir();
+	mnt_drop_write(rec_dir.path.mnt);
+out:
 	if (status)
 		printk("NFSD: Failed to remove expired client state directory"
 				" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
@@ -347,13 +357,17 @@ nfsd4_recdir_purge_old(void) {
 
 	if (!rec_dir_init)
 		return;
+	status = mnt_want_write(rec_dir.path.mnt);
+	if (status)
+		goto out;
 	status = nfsd4_list_rec_dir(rec_dir.path.dentry, purge_old);
 	if (status == 0)
 		nfsd4_sync_rec_dir();
+	mnt_drop_write(rec_dir.path.mnt);
+out:
 	if (status)
 		printk("nfsd4: failed to purge old clients from recovery"
 			" directory %s\n", rec_dir.path.dentry->d_name.name);
-	return;
 }
 
 static int

fs/nfsd/nfs4state.c

@@ -41,6 +41,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/cache.h>
+#include <linux/file.h>
 #include <linux/mount.h>
 #include <linux/workqueue.h>
 #include <linux/smp_lock.h>
@@ -1239,7 +1240,7 @@ static inline void
 nfs4_file_downgrade(struct file *filp, unsigned int share_access)
 {
 	if (share_access & NFS4_SHARE_ACCESS_WRITE) {
-		put_write_access(filp->f_path.dentry->d_inode);
+		drop_file_write_access(filp);
 		filp->f_mode = (filp->f_mode | FMODE_READ) & ~FMODE_WRITE;
 	}
 }

fs/nfsd/vfs.c

@@ -1255,23 +1255,35 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = 0;
 	switch (type) {
 	case S_IFREG:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
 		break;
 	case S_IFDIR:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_mkdir(dirp, dchild, iap->ia_mode);
 		break;
 	case S_IFCHR:
 	case S_IFBLK:
 	case S_IFIFO:
 	case S_IFSOCK:
+		host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+		if (host_err)
+			goto out_nfserr;
 		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
 		break;
 	default:
 	        printk("nfsd: bad file type %o in nfsd_create\n", type);
 		host_err = -EINVAL;
+		goto out_nfserr;
 	}
-	if (host_err < 0)
+	if (host_err < 0) {
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
 		goto out_nfserr;
+	}
 
 	if (EX_ISSYNC(fhp->fh_export)) {
 		err = nfserrno(nfsd_sync_dir(dentry));
@@ -1282,6 +1294,7 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err2 = nfsd_create_setattr(rqstp, resfhp, iap);
 	if (err2)
 		err = err2;
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 	/*
 	 * Update the file handle to get the new inode info.
 	 */
@@ -1359,6 +1372,9 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		v_atime = verifier[1]&0x7fffffff;
 	}
 	
+	host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (host_err)
+		goto out_nfserr;
 	if (dchild->d_inode) {
 		err = 0;
 
@@ -1390,12 +1406,15 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		case NFS3_CREATE_GUARDED:
 			err = nfserr_exist;
 		}
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
 		goto out;
 	}
 
 	host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
-	if (host_err < 0)
+	if (host_err < 0) {
+		mnt_drop_write(fhp->fh_export->ex_path.mnt);
 		goto out_nfserr;
+	}
 	if (created)
 		*created = 1;
 
@@ -1420,6 +1439,7 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (err2)
 		err = err2;
 
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 	/*
 	 * Update the filehandle to get the new inode info.
 	 */
@@ -1522,6 +1542,10 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	if (iap && (iap->ia_valid & ATTR_MODE))
 		mode = iap->ia_mode & S_IALLUGO;
 
+	host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (host_err)
+		goto out_nfserr;
+
 	if (unlikely(path[plen] != 0)) {
 		char *path_alloced = kmalloc(plen+1, GFP_KERNEL);
 		if (path_alloced == NULL)
@@ -1542,6 +1566,8 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = nfserrno(host_err);
 	fh_unlock(fhp);
 
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
+
 	cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp);
 	dput(dnew);
 	if (err==0) err = cerr;
@@ -1592,6 +1618,11 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 	dold = tfhp->fh_dentry;
 	dest = dold->d_inode;
 
+	host_err = mnt_want_write(tfhp->fh_export->ex_path.mnt);
+	if (host_err) {
+		err = nfserrno(host_err);
+		goto out_dput;
+	}
 	host_err = vfs_link(dold, dirp, dnew);
 	if (!host_err) {
 		if (EX_ISSYNC(ffhp->fh_export)) {
@@ -1605,7 +1636,8 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
 		else
 			err = nfserrno(host_err);
 	}
-
+	mnt_drop_write(tfhp->fh_export->ex_path.mnt);
+out_dput:
 	dput(dnew);
 out_unlock:
 	fh_unlock(ffhp);
@@ -1678,13 +1710,20 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 	if (ndentry == trap)
 		goto out_dput_new;
 
-#ifdef MSNFS
-	if ((ffhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
+	if (svc_msnfs(ffhp) &&
 		((atomic_read(&odentry->d_count) > 1)
 		 || (atomic_read(&ndentry->d_count) > 1))) {
 			host_err = -EPERM;
-	} else
-#endif
+			goto out_dput_new;
+	}
+
+	host_err = -EXDEV;
+	if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt)
+		goto out_dput_new;
+	host_err = mnt_want_write(ffhp->fh_export->ex_path.mnt);
+	if (host_err)
+		goto out_dput_new;
+
 	host_err = vfs_rename(fdir, odentry, tdir, ndentry);
 	if (!host_err && EX_ISSYNC(tfhp->fh_export)) {
 		host_err = nfsd_sync_dir(tdentry);
@@ -1692,6 +1731,8 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 			host_err = nfsd_sync_dir(fdentry);
 	}
 
+	mnt_drop_write(ffhp->fh_export->ex_path.mnt);
+
  out_dput_new:
 	dput(ndentry);
  out_dput_old:
@@ -1750,6 +1791,10 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	if (!type)
 		type = rdentry->d_inode->i_mode & S_IFMT;
 
+	host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (host_err)
+		goto out_nfserr;
+
 	if (type != S_IFDIR) { /* It's UNLINK */
 #ifdef MSNFS
 		if ((fhp->fh_export->ex_flags & NFSEXP_MSNFS) &&
@@ -1765,10 +1810,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
 	dput(rdentry);
 
 	if (host_err)
-		goto out_nfserr;
+		goto out_drop;
 	if (EX_ISSYNC(fhp->fh_export))
 		host_err = nfsd_sync_dir(dentry);
 
+out_drop:
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 out_nfserr:
 	err = nfserrno(host_err);
 out:
@@ -1865,7 +1912,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 		inode->i_mode,
 		IS_IMMUTABLE(inode)?	" immut" : "",
 		IS_APPEND(inode)?	" append" : "",
-		IS_RDONLY(inode)?	" ro" : "");
+		__mnt_is_readonly(exp->ex_path.mnt)?	" ro" : "");
 	dprintk("      owner %d/%d user %d/%d\n",
 		inode->i_uid, inode->i_gid, current->fsuid, current->fsgid);
 #endif
@@ -1876,7 +1923,8 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
 	 */
 	if (!(acc & MAY_LOCAL_ACCESS))
 		if (acc & (MAY_WRITE | MAY_SATTR | MAY_TRUNC)) {
-			if (exp_rdonly(rqstp, exp) || IS_RDONLY(inode))
+			if (exp_rdonly(rqstp, exp) ||
+			    __mnt_is_readonly(exp->ex_path.mnt))
 				return nfserr_rofs;
 			if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
 				return nfserr_perm;
@@ -2039,6 +2087,9 @@ nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *acl)
 	} else
 		size = 0;
 
+	error = mnt_want_write(fhp->fh_export->ex_path.mnt);
+	if (error)
+		goto getout;
 	if (size)
 		error = vfs_setxattr(fhp->fh_dentry, name, value, size, 0);
 	else {
@@ -2050,6 +2101,7 @@ nfsd_set_posix_acl(struct svc_fh *fhp, int type, struct posix_acl *acl)
 				error = 0;
 		}
 	}
+	mnt_drop_write(fhp->fh_export->ex_path.mnt);
 
 getout:
 	kfree(value);

fs/ocfs2/ioctl.c

@@ -60,10 +60,6 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 		goto bail;
 	}
 
-	status = -EROFS;
-	if (IS_RDONLY(inode))
-		goto bail_unlock;
-
 	status = -EACCES;
 	if (!is_owner_or_cap(inode))
 		goto bail_unlock;
@@ -134,8 +130,13 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (get_user(flags, (int __user *) arg))
 			return -EFAULT;
 
-		return ocfs2_set_inode_attr(inode, flags,
+		status = mnt_want_write(filp->f_path.mnt);
+		if (status)
+			return status;
+		status = ocfs2_set_inode_attr(inode, flags,
 			OCFS2_FL_MODIFIABLE);
+		mnt_drop_write(filp->f_path.mnt);
+		return status;
 	case OCFS2_IOC_RESVSP:
 	case OCFS2_IOC_RESVSP64:
 	case OCFS2_IOC_UNRESVSP:

fs/open.c

@@ -244,21 +244,21 @@ static long do_sys_truncate(const char __user * path, loff_t length)
 	if (!S_ISREG(inode->i_mode))
 		goto dput_and_out;
 
-	error = vfs_permission(&nd, MAY_WRITE);
+	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto dput_and_out;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
-		goto dput_and_out;
+	error = vfs_permission(&nd, MAY_WRITE);
+	if (error)
+		goto mnt_drop_write_and_out;
 
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto dput_and_out;
+		goto mnt_drop_write_and_out;
 
 	error = get_write_access(inode);
 	if (error)
-		goto dput_and_out;
+		goto mnt_drop_write_and_out;
 
 	/*
 	 * Make sure that there are no leases.  get_write_access() protects
@@ -276,6 +276,8 @@ static long do_sys_truncate(const char __user * path, loff_t length)
 
 put_write_and_out:
 	put_write_access(inode);
+mnt_drop_write_and_out:
+	mnt_drop_write(nd.path.mnt);
 dput_and_out:
 	path_put(&nd.path);
 out:
@@ -457,8 +459,17 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
 	if(res || !(mode & S_IWOTH) ||
 	   special_file(nd.path.dentry->d_inode->i_mode))
 		goto out_path_release;
-
-	if(IS_RDONLY(nd.path.dentry->d_inode))
+	/*
+	 * This is a rare case where using __mnt_is_readonly()
+	 * is OK without a mnt_want/drop_write() pair.  Since
+	 * no actual write to the fs is performed here, we do
+	 * not need to telegraph to that to anyone.
+	 *
+	 * By doing this, we accept that this access is
+	 * inherently racy and know that the fs may change
+	 * state before we even see this result.
+	 */
+	if (__mnt_is_readonly(nd.path.mnt))
 		res = -EROFS;
 
 out_path_release:
@@ -567,12 +578,12 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
 
 	audit_inode(NULL, dentry);
 
-	err = -EROFS;
-	if (IS_RDONLY(inode))
+	err = mnt_want_write(file->f_path.mnt);
+	if (err)
 		goto out_putf;
 	err = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto out_putf;
+		goto out_drop_write;
 	mutex_lock(&inode->i_mutex);
 	if (mode == (mode_t) -1)
 		mode = inode->i_mode;
@@ -581,6 +592,8 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
 	err = notify_change(dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(file->f_path.mnt);
 out_putf:
 	fput(file);
 out:
@@ -600,13 +613,13 @@ asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
 		goto out;
 	inode = nd.path.dentry->d_inode;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
 		goto dput_and_out;
 
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		goto dput_and_out;
+		goto out_drop_write;
 
 	mutex_lock(&inode->i_mutex);
 	if (mode == (mode_t) -1)
@@ -616,6 +629,8 @@ asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
 	error = notify_change(nd.path.dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(nd.path.mnt);
 dput_and_out:
 	path_put(&nd.path);
 out:
@@ -638,9 +653,6 @@ static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
 		printk(KERN_ERR "chown_common: NULL inode\n");
 		goto out;
 	}
-	error = -EROFS;
-	if (IS_RDONLY(inode))
-		goto out;
 	error = -EPERM;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		goto out;
@@ -671,7 +683,12 @@ asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group)
 	error = user_path_walk(filename, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
 	path_put(&nd.path);
 out:
 	return error;
@@ -691,7 +708,12 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
 	error = __user_walk_fd(dfd, filename, follow, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
 	path_put(&nd.path);
 out:
 	return error;
@@ -705,7 +727,12 @@ asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group
 	error = user_path_walk_link(filename, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.path.dentry, user, group);
+	mnt_drop_write(nd.path.mnt);
+out_release:
 	path_put(&nd.path);
 out:
 	return error;
@@ -722,14 +749,48 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group)
 	if (!file)
 		goto out;
 
+	error = mnt_want_write(file->f_path.mnt);
+	if (error)
+		goto out_fput;
 	dentry = file->f_path.dentry;
 	audit_inode(NULL, dentry);
 	error = chown_common(dentry, user, group);
+	mnt_drop_write(file->f_path.mnt);
+out_fput:
 	fput(file);
 out:
 	return error;
 }
 
+/*
+ * You have to be very careful that these write
+ * counts get cleaned up in error cases and
+ * upon __fput().  This should probably never
+ * be called outside of __dentry_open().
+ */
+static inline int __get_file_write_access(struct inode *inode,
+					  struct vfsmount *mnt)
+{
+	int error;
+	error = get_write_access(inode);
+	if (error)
+		return error;
+	/*
+	 * Do not take mount writer counts on
+	 * special files since no writes to
+	 * the mount itself will occur.
+	 */
+	if (!special_file(inode->i_mode)) {
+		/*
+		 * Balanced in __fput()
+		 */
+		error = mnt_want_write(mnt);
+		if (error)
+			put_write_access(inode);
+	}
+	return error;
+}
+
 static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 					int flags, struct file *f,
 					int (*open)(struct inode *, struct file *))
@@ -742,9 +803,11 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 				FMODE_PREAD | FMODE_PWRITE;
 	inode = dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
-		error = get_write_access(inode);
+		error = __get_file_write_access(inode, mnt);
 		if (error)
 			goto cleanup_file;
+		if (!special_file(inode->i_mode))
+			file_take_write(f);
 	}
 
 	f->f_mapping = inode->i_mapping;
@@ -784,8 +847,19 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 
 cleanup_all:
 	fops_put(f->f_op);
-	if (f->f_mode & FMODE_WRITE)
+	if (f->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
+		if (!special_file(inode->i_mode)) {
+			/*
+			 * We don't consider this a real
+			 * mnt_want/drop_write() pair
+			 * because it all happenend right
+			 * here, so just reset the state.
+			 */
+			file_reset_write(f);
+			mnt_drop_write(mnt);
+		}
+	}
 	file_kill(f);
 	f->f_path.dentry = NULL;
 	f->f_path.mnt = NULL;
@@ -796,43 +870,6 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	return ERR_PTR(error);
 }
 
-/*
- * Note that while the flag value (low two bits) for sys_open means:
- *	00 - read-only
- *	01 - write-only
- *	10 - read-write
- *	11 - special
- * it is changed into
- *	00 - no permissions needed
- *	01 - read-permission
- *	10 - write-permission
- *	11 - read-write
- * for the internal routines (ie open_namei()/follow_link() etc). 00 is
- * used by symlinks.
- */
-static struct file *do_filp_open(int dfd, const char *filename, int flags,
-				 int mode)
-{
-	int namei_flags, error;
-	struct nameidata nd;
-
-	namei_flags = flags;
-	if ((namei_flags+1) & O_ACCMODE)
-		namei_flags++;
-
-	error = open_namei(dfd, filename, namei_flags, mode, &nd);
-	if (!error)
-		return nameidata_to_filp(&nd, flags);
-
-	return ERR_PTR(error);
-}
-
-struct file *filp_open(const char *filename, int flags, int mode)
-{
-	return do_filp_open(AT_FDCWD, filename, flags, mode);
-}
-EXPORT_SYMBOL(filp_open);
-
 /**
  * lookup_instantiate_filp - instantiates the open intent filp
  * @nd: pointer to nameidata

fs/reiserfs/ioctl.c

@@ -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, struct file *filp, unsigned int cmd,
 		   unsigned long arg)
 {
 	unsigned int flags;
+	int err = 0;
 
 	switch (cmd) {
 	case REISERFS_IOC_UNPACK:
@@ -48,50 +50,67 @@ int reiserfs_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 			if (!reiserfs_attrs(inode->i_sb))
 				return -ENOTTY;
 
-			if (IS_RDONLY(inode))
-				return -EROFS;
+			err = mnt_want_write(filp->f_path.mnt);
+			if (err)
+				return err;
 
-			if (!is_owner_or_cap(inode))
-				return -EPERM;
-
-			if (get_user(flags, (int __user *)arg))
-				return -EFAULT;
-
-			/* Is it quota file? Do not allow user to mess with it. */
-			if (IS_NOQUOTA(inode))
-				return -EPERM;
+			if (!is_owner_or_cap(inode)) {
+				err = -EPERM;
+				goto setflags_out;
+			}
+			if (get_user(flags, (int __user *)arg)) {
+				err = -EFAULT;
+				goto setflags_out;
+			}
+			/*
+			 * Is it quota file? Do not allow user to mess with it
+			 */
+			if (IS_NOQUOTA(inode)) {
+				err = -EPERM;
+				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_path.mnt);
+			return err;
 		}
 	case REISERFS_IOC_GETVERSION:
 		return put_user(inode->i_generation, (int __user *)arg);
 	case REISERFS_IOC_SETVERSION:
 		if (!is_owner_or_cap(inode))
 			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_path.mnt);
+		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_path.mnt);
+		return err;
 	default:
 		return -ENOTTY;
 	}

fs/super.c

@@ -37,6 +37,7 @@
 #include <linux/idr.h>
 #include <linux/kobject.h>
 #include <linux/mutex.h>
+#include <linux/file.h>
 #include <asm/uaccess.h>
 
 
@@ -567,10 +568,29 @@ static void mark_files_ro(struct super_block *sb)
 {
 	struct file *f;
 
+retry:
 	file_list_lock();
 	list_for_each_entry(f, &sb->s_files, f_u.fu_list) {
-		if (S_ISREG(f->f_path.dentry->d_inode->i_mode) && file_count(f))
-			f->f_mode &= ~FMODE_WRITE;
+		struct vfsmount *mnt;
+		if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
+		       continue;
+		if (!file_count(f))
+			continue;
+		if (!(f->f_mode & FMODE_WRITE))
+			continue;
+		f->f_mode &= ~FMODE_WRITE;
+		if (file_check_writeable(f) != 0)
+			continue;
+		file_release_write(f);
+		mnt = mntget(f->f_path.mnt);
+		file_list_unlock();
+		/*
+		 * This can sleep, so we can't hold
+		 * the file_list_lock() spinlock.
+		 */
+		mnt_drop_write(mnt);
+		mntput(mnt);
+		goto retry;
 	}
 	file_list_unlock();
 }

fs/utimes.c

@@ -2,6 +2,7 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/linkage.h>
+#include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
 #include <linux/stat.h>
@@ -59,6 +60,7 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 	struct inode *inode;
 	struct iattr newattrs;
 	struct file *f = NULL;
+	struct vfsmount *mnt;
 
 	error = -EINVAL;
 	if (times && (!nsec_valid(times[0].tv_nsec) ||
@@ -79,18 +81,20 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 		if (!f)
 			goto out;
 		dentry = f->f_path.dentry;
+		mnt = f->f_path.mnt;
 	} else {
 		error = __user_walk_fd(dfd, filename, (flags & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW, &nd);
 		if (error)
 			goto out;
 
 		dentry = nd.path.dentry;
+		mnt = nd.path.mnt;
 	}
 
 	inode = dentry->d_inode;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
+	error = mnt_want_write(mnt);
+	if (error)
 		goto dput_and_out;
 
 	/* Don't worry, the checks are done in inode_change_ok() */
@@ -98,7 +102,7 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 	if (times) {
 		error = -EPERM;
                 if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-                        goto dput_and_out;
+			goto mnt_drop_write_and_out;
 
 		if (times[0].tv_nsec == UTIME_OMIT)
 			newattrs.ia_valid &= ~ATTR_ATIME;
@@ -118,22 +122,24 @@ long do_utimes(int dfd, char __user *filename, struct timespec *times, int flags
 	} else {
 		error = -EACCES;
                 if (IS_IMMUTABLE(inode))
-                        goto dput_and_out;
+			goto mnt_drop_write_and_out;
 
 		if (!is_owner_or_cap(inode)) {
 			if (f) {
 				if (!(f->f_mode & FMODE_WRITE))
-					goto dput_and_out;
+					goto mnt_drop_write_and_out;
 			} else {
 				error = vfs_permission(&nd, MAY_WRITE);
 				if (error)
-					goto dput_and_out;
+					goto mnt_drop_write_and_out;
 			}
 		}
 	}
 	mutex_lock(&inode->i_mutex);
 	error = notify_change(dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
+mnt_drop_write_and_out:
+	mnt_drop_write(mnt);
 dput_and_out:
 	if (f)
 		fput(f);

fs/xattr.c

@@ -11,6 +11,7 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/xattr.h>
+#include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
@@ -32,8 +33,6 @@ xattr_permission(struct inode *inode, const char *name, int mask)
 	 * filesystem  or on an immutable / append-only inode.
 	 */
 	if (mask & MAY_WRITE) {
-		if (IS_RDONLY(inode))
-			return -EROFS;
 		if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 			return -EPERM;
 	}
@@ -262,7 +261,11 @@ sys_setxattr(char __user *path, char __user *name, void __user *value,
 	error = user_path_walk(path, &nd);
 	if (error)
 		return error;
-	error = setxattr(nd.path.dentry, name, value, size, flags);
+	error = mnt_want_write(nd.path.mnt);
+	if (!error) {
+		error = setxattr(nd.path.dentry, name, value, size, flags);
+		mnt_drop_write(nd.path.mnt);
+	}
 	path_put(&nd.path);
 	return error;
 }
@@ -277,7 +280,11 @@ sys_lsetxattr(char __user *path, char __user *name, void __user *value,
 	error = user_path_walk_link(path, &nd);
 	if (error)
 		return error;
-	error = setxattr(nd.path.dentry, name, value, size, flags);
+	error = mnt_want_write(nd.path.mnt);
+	if (!error) {
+		error = setxattr(nd.path.dentry, name, value, size, flags);
+		mnt_drop_write(nd.path.mnt);
+	}
 	path_put(&nd.path);
 	return error;
 }
@@ -295,7 +302,12 @@ sys_fsetxattr(int fd, char __user *name, void __user *value,
 		return error;
 	dentry = f->f_path.dentry;
 	audit_inode(NULL, dentry);
-	error = setxattr(dentry, name, value, size, flags);
+	error = mnt_want_write(f->f_path.mnt);
+	if (!error) {
+		error = setxattr(dentry, name, value, size, flags);
+		mnt_drop_write(f->f_path.mnt);
+	}
+out_fput:
 	fput(f);
 	return error;
 }
@@ -482,7 +494,11 @@ sys_removexattr(char __user *path, char __user *name)
 	error = user_path_walk(path, &nd);
 	if (error)
 		return error;
-	error = removexattr(nd.path.dentry, name);
+	error = mnt_want_write(nd.path.mnt);
+	if (!error) {
+		error = removexattr(nd.path.dentry, name);
+		mnt_drop_write(nd.path.mnt);
+	}
 	path_put(&nd.path);
 	return error;
 }
@@ -496,7 +512,11 @@ sys_lremovexattr(char __user *path, char __user *name)
 	error = user_path_walk_link(path, &nd);
 	if (error)
 		return error;
-	error = removexattr(nd.path.dentry, name);
+	error = mnt_want_write(nd.path.mnt);
+	if (!error) {
+		error = removexattr(nd.path.dentry, name);
+		mnt_drop_write(nd.path.mnt);
+	}
 	path_put(&nd.path);
 	return error;
 }
@@ -513,7 +533,11 @@ sys_fremovexattr(int fd, char __user *name)
 		return error;
 	dentry = f->f_path.dentry;
 	audit_inode(NULL, dentry);
-	error = removexattr(dentry, name);
+	error = mnt_want_write(f->f_path.mnt);
+	if (!error) {
+		error = removexattr(dentry, name);
+		mnt_drop_write(f->f_path.mnt);
+	}
 	fput(f);
 	return error;
 }

fs/xfs/linux-2.6/xfs_ioctl.c

@@ -535,8 +535,6 @@ xfs_attrmulti_attr_set(
 	char			*kbuf;
 	int			error = EFAULT;
 
-	if (IS_RDONLY(inode))
-		return -EROFS;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return EPERM;
 	if (len > XATTR_SIZE_MAX)
@@ -562,8 +560,6 @@ xfs_attrmulti_attr_remove(
 	char			*name,
 	__uint32_t		flags)
 {
-	if (IS_RDONLY(inode))
-		return -EROFS;
 	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
 		return EPERM;
 	return xfs_attr_remove(XFS_I(inode), name, flags);
@@ -573,6 +569,7 @@ STATIC int
 xfs_attrmulti_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
+	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;
@@ -626,13 +623,21 @@ 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_path.mnt);
+			if (ops[i].am_error)
+				break;
 			ops[i].am_error = xfs_attrmulti_attr_set(inode,
 					attr_name, ops[i].am_attrvalue,
 					ops[i].am_length, ops[i].am_flags);
+			mnt_drop_write(parfilp->f_path.mnt);
 			break;
 		case ATTR_OP_REMOVE:
+			ops[i].am_error = mnt_want_write(parfilp->f_path.mnt);
+			if (ops[i].am_error)
+				break;
 			ops[i].am_error = xfs_attrmulti_attr_remove(inode,
 					attr_name, ops[i].am_flags);
+			mnt_drop_write(parfilp->f_path.mnt);
 			break;
 		default:
 			ops[i].am_error = EINVAL;
@@ -1133,7 +1138,7 @@ 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);

fs/xfs/linux-2.6/xfs_iops.c

@@ -155,13 +155,6 @@ 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;

fs/xfs/linux-2.6/xfs_lrw.c

@@ -51,6 +51,7 @@
 #include "xfs_vnodeops.h"
 
 #include <linux/capability.h>
+#include <linux/mount.h>
 #include <linux/writeback.h>
 
 
@@ -670,10 +671,16 @@ xfs_write(
 	if (new_size > xip->i_size)
 		xip->i_new_size = new_size;
 
-	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_path.mnt))) {
 		file_update_time(file);
 		xfs_ichgtime_fast(xip, inode,
 				  XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+		mnt_drop_write(file->f_path.mnt);
 	}
 
 	/*

include/linux/file.h

@@ -61,6 +61,7 @@ extern struct kmem_cache *filp_cachep;
 
 extern void __fput(struct file *);
 extern void fput(struct file *);
+extern void drop_file_write_access(struct file *file);
 
 struct file_operations;
 struct vfsmount;

include/linux/fs.h

@@ -776,6 +776,9 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
+#define FILE_MNT_WRITE_TAKEN	1
+#define FILE_MNT_WRITE_RELEASED	2
+
 struct file {
 	/*
 	 * fu_list becomes invalid after file_free is called and queued via
@@ -810,6 +813,9 @@ struct file {
 	spinlock_t		f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
+#ifdef CONFIG_DEBUG_WRITECOUNT
+	unsigned long f_mnt_write_state;
+#endif
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);
@@ -818,6 +824,49 @@ extern spinlock_t files_lock;
 #define get_file(x)	atomic_inc(&(x)->f_count)
 #define file_count(x)	atomic_read(&(x)->f_count)
 
+#ifdef CONFIG_DEBUG_WRITECOUNT
+static inline void file_take_write(struct file *f)
+{
+	WARN_ON(f->f_mnt_write_state != 0);
+	f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
+}
+static inline void file_release_write(struct file *f)
+{
+	f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED;
+}
+static inline void file_reset_write(struct file *f)
+{
+	f->f_mnt_write_state = 0;
+}
+static inline void file_check_state(struct file *f)
+{
+	/*
+	 * At this point, either both or neither of these bits
+	 * should be set.
+	 */
+	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN);
+	WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED);
+}
+static inline int file_check_writeable(struct file *f)
+{
+	if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN)
+		return 0;
+	printk(KERN_WARNING "writeable file with no "
+			    "mnt_want_write()\n");
+	WARN_ON(1);
+	return -EINVAL;
+}
+#else /* !CONFIG_DEBUG_WRITECOUNT */
+static inline void file_take_write(struct file *filp) {}
+static inline void file_release_write(struct file *filp) {}
+static inline void file_reset_write(struct file *filp) {}
+static inline void file_check_state(struct file *filp) {}
+static inline int file_check_writeable(struct file *filp)
+{
+	return 0;
+}
+#endif /* CONFIG_DEBUG_WRITECOUNT */
+
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
 /* Page cache limit. The filesystems should put that into their s_maxbytes 
@@ -1735,7 +1784,8 @@ extern struct file *create_read_pipe(struct file *f);
 extern struct file *create_write_pipe(void);
 extern void free_write_pipe(struct file *);
 
-extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
+extern struct file *do_filp_open(int dfd, const char *pathname,
+		int open_flag, int mode);
 extern int may_open(struct nameidata *, int, int);
 
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);

include/linux/mount.h

@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/list.h>
+#include <linux/nodemask.h>
 #include <linux/spinlock.h>
 #include <asm/atomic.h>
 
@@ -28,8 +29,10 @@ struct mnt_namespace;
 #define MNT_NOATIME	0x08
 #define MNT_NODIRATIME	0x10
 #define MNT_RELATIME	0x20
+#define MNT_READONLY	0x40	/* does the user want this to be r/o? */
 
 #define MNT_SHRINKABLE	0x100
+#define MNT_IMBALANCED_WRITE_COUNT	0x200 /* just for debugging */
 
 #define MNT_SHARED	0x1000	/* if the vfsmount is a shared mount */
 #define MNT_UNBINDABLE	0x2000	/* if the vfsmount is a unbindable mount */
@@ -62,6 +65,11 @@ struct vfsmount {
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
 	int mnt_ghosts;
+	/*
+	 * This value is not stable unless all of the mnt_writers[] spinlocks
+	 * are held, and all mnt_writer[]s on this mount have 0 as their ->count
+	 */
+	atomic_t __mnt_writers;
 };
 
 static inline struct vfsmount *mntget(struct vfsmount *mnt)
@@ -71,9 +79,12 @@ static inline struct vfsmount *mntget(struct vfsmount *mnt)
 	return mnt;
 }
 
+extern int mnt_want_write(struct vfsmount *mnt);
+extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mntput_no_expire(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
 extern void mnt_unpin(struct vfsmount *mnt);
+extern int __mnt_is_readonly(struct vfsmount *mnt);
 
 static inline void mntput(struct vfsmount *mnt)
 {

ipc/mqueue.c

@@ -598,6 +598,7 @@ static struct file *do_create(struct dentry *dir, struct dentry *dentry,
 			int oflag, mode_t mode, struct mq_attr __user *u_attr)
 {
 	struct mq_attr attr;
+	struct file *result;
 	int ret;
 
 	if (u_attr) {
@@ -612,13 +613,24 @@ static struct file *do_create(struct dentry *dir, struct dentry *dentry,
 	}
 
 	mode &= ~current->fs->umask;
+	ret = mnt_want_write(mqueue_mnt);
+	if (ret)
+		goto out;
 	ret = vfs_create(dir->d_inode, dentry, mode, NULL);
 	dentry->d_fsdata = NULL;
 	if (ret)
-		goto out;
-
-	return dentry_open(dentry, mqueue_mnt, oflag);
-
+		goto out_drop_write;
+
+	result = dentry_open(dentry, mqueue_mnt, oflag);
+	/*
+	 * dentry_open() took a persistent mnt_want_write(),
+	 * so we can now drop this one.
+	 */
+	mnt_drop_write(mqueue_mnt);
+	return result;
+
+out_drop_write:
+	mnt_drop_write(mqueue_mnt);
 out:
 	dput(dentry);
 	mntput(mqueue_mnt);
@@ -742,8 +754,11 @@ asmlinkage long sys_mq_unlink(const char __user *u_name)
 	inode = dentry->d_inode;
 	if (inode)
 		atomic_inc(&inode->i_count);
-
+	err = mnt_want_write(mqueue_mnt);
+	if (err)
+		goto out_err;
 	err = vfs_unlink(dentry->d_parent->d_inode, dentry);
+	mnt_drop_write(mqueue_mnt);
 out_err:
 	dput(dentry);
 

lib/Kconfig.debug

@@ -427,6 +427,16 @@ config DEBUG_VM
 
 	  If unsure, say N.
 
+config DEBUG_WRITECOUNT
+	bool "Debug filesystem writers count"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to catch wrong use of the writers count in struct
+	  vfsmount.  This will increase the size of each file struct by
+	  32 bits.
+
+	  If unsure, say N.
+
 config DEBUG_LIST
 	bool "Debug linked list manipulation"
 	depends on DEBUG_KERNEL

net/unix/af_unix.c

@@ -819,7 +819,11 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		 */
 		mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current->fs->umask);
+		err = mnt_want_write(nd.path.mnt);
+		if (err)
+			goto out_mknod_dput;
 		err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
+		mnt_drop_write(nd.path.mnt);
 		if (err)
 			goto out_mknod_dput;
 		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);