Read-only bind mounts (-mm resend)

diff -puN fs/namei.c~make-open_namei-return-a-filp fs/namei.c
@@ -1730,8 +1730,8 @@ static inline int sys_open_flags_to_name
  * system call.  See sys_open_flags_to_namei_flags().
  * SMP-safe
  */
-int open_namei(int dfd, const char *pathname, int sys_open_flag,
-		int mode, struct nameidata *nd)
+struct file *open_namei(int dfd, const char *pathname, int sys_open_flag,
+			int mode, struct nameidata *nd)
 {
 	int acc_mode, error;
 	struct path path;

@@ -1757,7 +1757,7 @@ int open_namei(int dfd, const char *path
 		error = path_lookup_open(dfd, pathname, lookup_flags(flag),
 					 nd, flag);
 		if (error)
-			return error;
+			return ERR_PTR(error);
 		goto ok;
 	}
 

@@ -1766,7 +1766,7 @@ int open_namei(int dfd, const char *path
 	 */
 	error = path_lookup_create(dfd,pathname,LOOKUP_PARENT,nd,flag,mode);
 	if (error)
-		return error;
+		return ERR_PTR(error);
 
 	/*
 	 * We have the parent and last component. First of all, check

@@ -1801,7 +1801,7 @@ do_last:
 		error = __open_namei_create(nd, &path, flag, mode);
 		if (error)
 			goto exit;
-		return 0;
+		return nameidata_to_filp(nd, sys_open_flag);
 	}
 
 	/*

@@ -1834,7 +1834,7 @@ ok:
 	error = may_open(nd, acc_mode, flag);
 	if (error)
 		goto exit;
-	return 0;
+	return nameidata_to_filp(nd, sys_open_flag);
 
 exit_dput:
 	dput_path(&path, nd);

@@ -1842,7 +1842,7 @@ exit:
 	if (!IS_ERR(nd->intent.open.file))
 		release_open_intent(nd);
 	path_release(nd);
-	return error;
+	return ERR_PTR(error);
 
 do_link:
 	error = -ELOOP;

@@ -1869,7 +1869,7 @@ do_link:
 		 * with "intent.open".
 		 */
 		release_open_intent(nd);
-		return error;
+		return ERR_PTR(error);
 	}
 	nd->flags &= ~LOOKUP_PARENT;
 	if (nd->last_type == LAST_BIND)

diff -puN fs/open.c~make-open_namei-return-a-filp fs/open.c
@@ -803,14 +803,9 @@ cleanup_file:
 static struct file *do_filp_open(int dfd, const char *filename, int flags,
 				 int mode)
 {
-	int error;
 	struct nameidata nd;
 
-	error = open_namei(dfd, filename, flags, mode, &nd);
-	if (!error)
-		return nameidata_to_filp(&nd, flags);
-
-	return ERR_PTR(error);
+	return open_namei(dfd, filename, flags, mode, &nd);
 }
 
 struct file *filp_open(const char *filename, int flags, int mode)

diff -puN include/linux/fs.h~make-open_namei-return-a-filp include/linux/fs.h
@@ -1714,7 +1714,7 @@ extern struct file *create_read_pipe(str
 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 *open_namei(int dfd, const char *, int, int, struct nameidata *);
 extern int may_open(struct nameidata *, int, int);
 
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);

diff -puN fs/open.c~kill-do_filp_open fs/open.c
@@ -800,17 +800,10 @@ cleanup_file:
 	return ERR_PTR(error);
 }
 
-static struct file *do_filp_open(int dfd, const char *filename, int flags,
-				 int mode)
-{
-	struct nameidata nd;
-
-	return open_namei(dfd, filename, flags, mode, &nd);
-}
-
 struct file *filp_open(const char *filename, int flags, int mode)
 {
-	return do_filp_open(AT_FDCWD, filename, flags, mode);
+	struct nameidata nd;
+	return open_namei(AT_FDCWD, filename, flags, mode, &nd);
 }
 EXPORT_SYMBOL(filp_open);
 

@@ -1009,20 +1002,24 @@ long do_sys_open(int dfd, const char __u
 	char *tmp = getname(filename);
 	int fd = PTR_ERR(tmp);
 
-	if (!IS_ERR(tmp)) {
-		fd = get_unused_fd_flags(flags);
-		if (fd >= 0) {
-			struct file *f = do_filp_open(dfd, tmp, flags, mode);
-			if (IS_ERR(f)) {
-				put_unused_fd(fd);
-				fd = PTR_ERR(f);
-			} else {
-				fsnotify_open(f->f_path.dentry);
-				fd_install(fd, f);
-			}
+	if (IS_ERR(tmp))
+		goto out;
+
+	fd = get_unused_fd_flags(flags);
+	if (fd >= 0) {
+		struct nameidata nd;
+		struct file *f = open_namei(dfd, tmp, flags, mode, &nd);
+
+		if (IS_ERR(f)) {
+			put_unused_fd(fd);
+			fd = PTR_ERR(f);
+		} else {
+			fsnotify_open(f->f_path.dentry);
+			fd_install(fd, f);
 		}
-		putname(tmp);
 	}
+	putname(tmp);
+out:
 	return fd;
 }
 

diff -puN drivers/usb/gadget/file_storage.c~kill-filp_open drivers/usb/gadget/file_storage.c
@@ -3468,16 +3468,17 @@ static int open_backing_file(struct lun 
 	struct inode			*inode = NULL;
 	loff_t				size;
 	loff_t				num_sectors;
+	int				mode = O_LARGEFILE;
 
 	/* R/W if we can, R/O if we must */
 	ro = curlun->ro;
 	if (!ro) {
-		filp = filp_open(filename, O_RDWR | O_LARGEFILE, 0);
+		filp = open_namei(AT_FDCWD, filename, O_RDWR | mode, 0);
 		if (-EROFS == PTR_ERR(filp))
 			ro = 1;
 	}
 	if (ro)
-		filp = filp_open(filename, O_RDONLY | O_LARGEFILE, 0);
+		filp = open_namei(AT_FDCWD, filename, O_RDONLY | mode, 0);
 	if (IS_ERR(filp)) {
 		LINFO(curlun, "unable to open backing file: %s\n", filename);
 		return PTR_ERR(filp);

diff -puN fs/exec.c~kill-filp_open fs/exec.c
@@ -1763,7 +1763,7 @@ int do_coredump(long signr, int exit_cod
  			goto fail_unlock;
  		}
  	} else
- 		file = filp_open(corename,
+		file = open_namei(AT_FDCWD, corename,
 				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
 				 0600);
 	if (IS_ERR(file))

155 lines not on this page · raw message

diff -puN fs/nfsctl.c~kill-filp_open fs/nfsctl.c
@@ -35,6 +35,11 @@ static struct file *do_open(char *name, 
 	if (error)
 		return ERR_PTR(error);
 
+	/*
+	 * If O_TRUNC is ever passed into may_open()
+	 * it will be necessary to take and release
+	 * mnt writer count around these calls.
+	 */
 	if (flags == O_RDWR)
 		error = may_open(&nd,MAY_READ|MAY_WRITE,FMODE_READ|FMODE_WRITE);
 	else

diff -puN fs/open.c~kill-filp_open fs/open.c
@@ -802,8 +802,7 @@ cleanup_file:
 
 struct file *filp_open(const char *filename, int flags, int mode)
 {
-	struct nameidata nd;
-	return open_namei(AT_FDCWD, filename, flags, mode, &nd);
+	return open_namei(AT_FDCWD, filename, flags, mode);
 }
 EXPORT_SYMBOL(filp_open);
 

@@ -1007,8 +1006,7 @@ long do_sys_open(int dfd, const char __u
 
 	fd = get_unused_fd_flags(flags);
 	if (fd >= 0) {
-		struct nameidata nd;
-		struct file *f = open_namei(dfd, tmp, flags, mode, &nd);
+		struct file *f = open_pathname(dfd, tmp, flags, mode);
 
 		if (IS_ERR(f)) {
 			put_unused_fd(fd);

diff -puN fs/reiserfs/journal.c~kill-filp_open fs/reiserfs/journal.c
@@ -2625,7 +2625,7 @@ static int journal_init_dev(struct super
 		return 0;
 	}
 
-	journal->j_dev_file = filp_open(jdev_name, 0, 0);
+	journal->j_dev_file = open_namei(AT_FDCWD, jdev_name, 0, 0);
 	if (!IS_ERR(journal->j_dev_file)) {
 		struct inode *jdev_inode = journal->j_dev_file->f_mapping->host;
 		if (!S_ISBLK(jdev_inode->i_mode)) {

diff -puN include/linux/fs.h~kill-filp_open include/linux/fs.h
@@ -1540,7 +1540,6 @@ extern int do_truncate(struct dentry *, 
 		       struct file *filp);
 extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			int mode);
-extern struct file *filp_open(const char *, int, int);
 extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);
 extern int filp_close(struct file *, fl_owner_t id);
 extern char * getname(const char __user *);

@@ -1714,7 +1713,7 @@ extern struct file *create_read_pipe(str
 extern struct file *create_write_pipe(void);
 extern void free_write_pipe(struct file *);
 
-extern struct file *open_namei(int dfd, const char *, int, int, struct nameidata *);
+extern struct file *open_pathname(int dfd, const char *, int, int);
 extern int may_open(struct nameidata *, int, int);
 
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);

diff -puN kernel/acct.c~kill-filp_open kernel/acct.c
@@ -208,7 +208,7 @@ static int acct_on(char *name)
 	int error;
 
 	/* Difference from BSD - they don't do O_APPEND */
-	file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+	file = open_namei(AT_FDCWD, name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 

diff -puN mm/swapfile.c~kill-filp_open mm/swapfile.c
@@ -1191,7 +1191,7 @@ asmlinkage long sys_swapoff(const char _
 	if (IS_ERR(pathname))
 		goto out;
 
-	victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
+	victim = open_namei(AT_FDCWD, pathname, O_RDWR|O_LARGEFILE, 0);
 	putname(pathname);
 	err = PTR_ERR(victim);
 	if (IS_ERR(victim))

@@ -1470,7 +1470,7 @@ asmlinkage long sys_swapon(const char __
 		name = NULL;
 		goto bad_swap_2;
 	}
-	swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
+	swap_file = open_namei(AT_FDCWD, name, O_RDWR|O_LARGEFILE, 0);
 	error = PTR_ERR(swap_file);
 	if (IS_ERR(swap_file)) {
 		swap_file = NULL;

diff -puN sound/sound_firmware.c~kill-filp_open sound/sound_firmware.c
@@ -14,7 +14,7 @@ static int do_mod_firmware_load(const ch
 	char *dp;
 	loff_t pos;
 
-	filp = filp_open(fn, 0, 0);
+	filp = open_namei(AT_FDCWD, fn, 0, 0);
 	if (IS_ERR(filp))
 	{
 		printk(KERN_INFO "Unable to load '%s'.\n", fn);

diff -puN drivers/usb/gadget/file_storage.c~rename-open_namei drivers/usb/gadget/file_storage.c
@@ -3473,12 +3473,12 @@ static int open_backing_file(struct lun 
 	/* R/W if we can, R/O if we must */
 	ro = curlun->ro;
 	if (!ro) {
-		filp = open_namei(AT_FDCWD, filename, O_RDWR | mode, 0);
+		filp = open_pathname(AT_FDCWD, filename, O_RDWR | mode, 0);
 		if (-EROFS == PTR_ERR(filp))
 			ro = 1;
 	}
 	if (ro)
-		filp = open_namei(AT_FDCWD, filename, O_RDONLY | mode, 0);
+		filp = open_pathname(AT_FDCWD, filename, O_RDONLY | mode, 0);
 	if (IS_ERR(filp)) {
 		LINFO(curlun, "unable to open backing file: %s\n", filename);
 		return PTR_ERR(filp);

diff -puN fs/exec.c~rename-open_namei fs/exec.c
@@ -1763,7 +1763,7 @@ int do_coredump(long signr, int exit_cod
  			goto fail_unlock;
  		}
  	} else
-		file = open_namei(AT_FDCWD, corename,
+		file = open_pathname(AT_FDCWD, corename,
 				 O_CREAT | 2 | O_NOFOLLOW | O_LARGEFILE | flag,
 				 0600);
 	if (IS_ERR(file))

diff -puN fs/namei.c~rename-open_namei fs/namei.c
@@ -81,7 +81,7 @@
  */
 
 /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
- * semantics.  See the comments in "open_namei" and "do_link" below.
+ * semantics.  See the comments in "open_pathname" and "do_link" below.
  *
  * [10-Sep-98 Alan Modra] Another symlink change.
  */

@@ -571,7 +571,7 @@ out:
 	if (nd->depth || res || nd->last_type!=LAST_NORM)
 		return res;
 	/*
-	 * If it is an iterative symlinks resolution in open_namei() we
+	 * If it is an iterative symlinks resolution in open_pathname() we
 	 * have to copy the last component. And all that crap because of
 	 * bloody create() on broken symlinks. Furrfu...
 	 */

@@ -1708,7 +1708,7 @@ static int __open_namei_create(struct na
  *	01 - read-permission
  *	10 - write-permission
  *	11 - read-write
- * for the internal routines (ie open_namei()/follow_link() etc)
+ * for the internal routines (ie open_pathname()/follow_link() etc)
  * This is more logical, and also allows the 00 "no perm needed"
  * to be used for symlinks (where the permissions are checked
  * later).

@@ -1722,7 +1722,7 @@ static inline int sys_open_flags_to_name
 }
 
 /*
- *	open_namei()
+ *	open_pathname()
  *
  * namei for open - this is in fact almost the whole open-routine.
  *

diff -puN fs/open.c~rename-open_namei fs/open.c
@@ -800,12 +800,6 @@ cleanup_file:
 	return ERR_PTR(error);
 }
 
-struct file *filp_open(const char *filename, int flags, int mode)
-{
-	return open_namei(AT_FDCWD, filename, flags, mode);
-}
-EXPORT_SYMBOL(filp_open);
-
 /**
  * lookup_instantiate_filp - instantiates the open intent filp
  * @nd: pointer to nameidata

diff -puN fs/reiserfs/journal.c~rename-open_namei fs/reiserfs/journal.c
@@ -2625,7 +2625,7 @@ static int journal_init_dev(struct super
 		return 0;
 	}
 
-	journal->j_dev_file = open_namei(AT_FDCWD, jdev_name, 0, 0);
+	journal->j_dev_file = open_pathname(AT_FDCWD, jdev_name, 0, 0);
 	if (!IS_ERR(journal->j_dev_file)) {
 		struct inode *jdev_inode = journal->j_dev_file->f_mapping->host;
 		if (!S_ISBLK(jdev_inode->i_mode)) {

diff -puN kernel/acct.c~rename-open_namei kernel/acct.c
@@ -208,7 +208,7 @@ static int acct_on(char *name)
 	int error;
 
 	/* Difference from BSD - they don't do O_APPEND */
-	file = open_namei(AT_FDCWD, name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
+	file = open_pathname(AT_FDCWD, name, O_WRONLY|O_APPEND|O_LARGEFILE, 0);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 

diff -puN mm/swapfile.c~rename-open_namei mm/swapfile.c
@@ -1191,7 +1191,7 @@ asmlinkage long sys_swapoff(const char _
 	if (IS_ERR(pathname))
 		goto out;
 
-	victim = open_namei(AT_FDCWD, pathname, O_RDWR|O_LARGEFILE, 0);
+	victim = open_pathname(AT_FDCWD, pathname, O_RDWR|O_LARGEFILE, 0);
 	putname(pathname);
 	err = PTR_ERR(victim);
 	if (IS_ERR(victim))

@@ -1470,7 +1470,7 @@ asmlinkage long sys_swapon(const char __
 		name = NULL;
 		goto bad_swap_2;
 	}
-	swap_file = open_namei(AT_FDCWD, name, O_RDWR|O_LARGEFILE, 0);
+	swap_file = open_pathname(AT_FDCWD, name, O_RDWR|O_LARGEFILE, 0);
 	error = PTR_ERR(swap_file);
 	if (IS_ERR(swap_file)) {
 		swap_file = NULL;

diff -puN sound/sound_firmware.c~rename-open_namei sound/sound_firmware.c
@@ -14,7 +14,7 @@ static int do_mod_firmware_load(const ch
 	char *dp;
 	loff_t pos;
 
-	filp = open_namei(AT_FDCWD, fn, 0, 0);
+	filp = open_pathname(AT_FDCWD, fn, 0, 0);
 	if (IS_ERR(filp))
 	{
 		printk(KERN_INFO "Unable to load '%s'.\n", fn);

diff -puN fs/namei.c~r-o-bind-mounts-elevate-mnt-writers-for-callers-of-vfs_mkdir fs/namei.c
@@ -2067,7 +2067,12 @@ asmlinkage long sys_mkdirat(int dfd, con
 
 	if (!IS_POSIXACL(nd.dentry->d_inode))
 		mode &= ~current->fs->umask;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_dput;
 	error = vfs_mkdir(nd.dentry->d_inode, dentry, mode);
+	mnt_drop_write(nd.mnt);
+out_dput:
 	dput(dentry);
 out_unlock:
 	mutex_unlock(&nd.dentry->d_inode->i_mutex);

diff -puN fs/nfsd/nfs4recover.c~r-o-bind-mounts-elevate-mnt-writers-for-callers-of-vfs_mkdir fs/nfsd/nfs4recover.c
@@ -41,6 +41,7 @@
 #include <linux/nfsd/xdr4.h>
 #include <linux/param.h>
 #include <linux/file.h>
+#include <linux/mount.h>
 #include <linux/namei.h>
 #include <asm/uaccess.h>
 #include <asm/scatterlist.h>

@@ -154,7 +155,11 @@ nfsd4_create_clid_dir(struct nfs4_client
 		dprintk("NFSD: nfsd4_create_clid_dir: DIRECTORY EXISTS\n");
 		goto out_put;
 	}
+	status = mnt_want_write(rec_dir.mnt);
+	if (status)
+		goto out_put;
 	status = vfs_mkdir(rec_dir.dentry->d_inode, dentry, S_IRWXU);
+	mnt_drop_write(rec_dir.mnt);
 out_put:
 	dput(dentry);
 out_unlock:

diff -puN fs/namespace.c~r-o-bind-mounts-stub-functions fs/namespace.c
@@ -77,6 +77,60 @@ struct vfsmount *alloc_vfsmnt(const char
 	return mnt;
 }
 
+/*
+ * Most r/o checks on a fs are for operations that take
+ * discrete amounts of time, like a write() or unlink().
+ * We must keep track of when those operations start
+ * (for permission checks) and when they end, so that
+ * we can determine when writes are able to occur to
+ * a filesystem.
+ */
+/**
+ * mnt_want_write - get write access to a mount
+ * @mnt: the mount on which to take a write
+ *
+ * This tells the low-level filesystem that a write is
+ * about to be performed to it, and makes sure that
+ * writes are allowed before returning success.  When
+ * the write operation is finished, mnt_drop_write()
+ * must be called.  This is effectively a refcount.
+ */
+int mnt_want_write(struct vfsmount *mnt)
+{
+	if (__mnt_is_readonly(mnt))
+		return -EROFS;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mnt_want_write);
+
+/**
+ * mnt_drop_write - give up write access to a mount
+ * @mnt: the mount on which to give up write access
+ *
+ * Tells the low-level filesystem that we are done
+ * performing writes to it.  Must be matched with
+ * mnt_want_write() call above.
+ */
+void mnt_drop_write(struct vfsmount *mnt)
+{
+}
+EXPORT_SYMBOL_GPL(mnt_drop_write);
+
+/*
+ * __mnt_is_readonly: check whether a mount is read-only
+ * @mnt: the mount to check for its write status
+ *
+ * This shouldn't be used directly ouside of the VFS.
+ * It does not guarantee that the filesystem will stay
+ * r/w, just that it is right *now*.  This can not and
+ * should not be used in place of IS_RDONLY(inode).
+ */
+int __mnt_is_readonly(struct vfsmount *mnt)
+{
+	return (mnt->mnt_sb->s_flags & MS_RDONLY);
+}
+EXPORT_SYMBOL_GPL(__mnt_is_readonly);
+
 int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
 {
 	mnt->mnt_sb = sb;

diff -puN include/linux/mount.h~r-o-bind-mounts-stub-functions include/linux/mount.h
@@ -70,9 +70,12 @@ static inline struct vfsmount *mntget(st
 	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)
 {

diff -puN fs/namei.c~r-o-bind-mounts-elevate-mnt-writers-for-vfs_unlink-callers fs/namei.c
@@ -2264,7 +2264,11 @@ static long do_unlinkat(int dfd, const c
 		inode = dentry->d_inode;
 		if (inode)
 			atomic_inc(&inode->i_count);
+		error = mnt_want_write(nd.mnt);
+		if (error)
+			goto exit2;
 		error = vfs_unlink(nd.dentry->d_inode, dentry);
+		mnt_drop_write(nd.mnt);
 	exit2:
 		dput(dentry);
 	}

diff -puN ipc/mqueue.c~r-o-bind-mounts-elevate-mnt-writers-for-vfs_unlink-callers ipc/mqueue.c
@@ -743,8 +743,11 @@ asmlinkage long sys_mq_unlink(const char
 	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);
 

diff -puN fs/nfsd/nfs4proc.c~r-o-bind-mounts-elevate-mount-count-for-extended-attributes fs/nfsd/nfs4proc.c
@@ -658,14 +658,19 @@ nfsd4_setattr(struct svc_rqst *rqstp, st
 			return status;
 		}
 	}
+	status = mnt_want_write(cstate->current_fh.fh_export->ex_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_mnt);
 	return status;
 }
 

diff -puN fs/xattr.c~r-o-bind-mounts-elevate-mount-count-for-extended-attributes 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, co
 	 * 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;
 	}

@@ -235,7 +234,11 @@ sys_setxattr(char __user *path, char __u
 	error = user_path_walk(path, &nd);
 	if (error)
 		return error;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		return error;
 	error = setxattr(nd.dentry, name, value, size, flags);
+	mnt_drop_write(nd.mnt);
 	path_release(&nd);
 	return error;
 }

@@ -250,7 +253,11 @@ sys_lsetxattr(char __user *path, char __
 	error = user_path_walk_link(path, &nd);
 	if (error)
 		return error;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		return error;
 	error = setxattr(nd.dentry, name, value, size, flags);
+	mnt_drop_write(nd.mnt);
 	path_release(&nd);
 	return error;
 }

@@ -266,9 +273,14 @@ sys_fsetxattr(int fd, char __user *name,
 	f = fget(fd);
 	if (!f)
 		return error;
+	error = mnt_want_write(f->f_vfsmnt);
+	if (error)
+		goto out_fput;
 	dentry = f->f_path.dentry;
 	audit_inode(NULL, dentry);
 	error = setxattr(dentry, name, value, size, flags);
+	mnt_drop_write(f->f_vfsmnt);
+out_fput:
 	fput(f);
 	return error;
 }

diff -puN fs/namei.c~do-namei_flags-calculation-inside-open_namei fs/namei.c
@@ -1674,7 +1674,12 @@ int may_open(struct nameidata *nd, int a
 	return 0;
 }
 
-static int open_namei_create(struct nameidata *nd, struct path *path,
+/*
+ * Be careful about ever adding any more callers of this
+ * function.  Its flags must be in the namei format, not
+ * what get passed to sys_open().
+ */
+static int __open_namei_create(struct nameidata *nd, struct path *path,
 				int flag, int mode)
 {
 	int error;

@@ -1693,26 +1698,46 @@ static int open_namei_create(struct name
 }
 
 /*
+ * 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)
+ * This is more logical, and also allows the 00 "no perm needed"
+ * to be used for symlinks (where the permissions are checked
+ * later).
+ *
+*/
+static inline int sys_open_flags_to_namei_flags(int flag)
+{
+	if ((flag+1) & O_ACCMODE)
+		flag++;
+	return flag;
+}
+
+/*
  *	open_namei()
  *
  * namei for open - this is in fact almost the whole open-routine.
  *
  * Note that the low bits of "flag" aren't the same as in the open
- * system call - they are 00 - no permissions needed
- *			  01 - read permission needed
- *			  10 - write permission needed
- *			  11 - read/write permissions needed
- * which is a lot more logical, and also allows the "no perm" needed
- * for symlinks (where the permissions are checked later).
+ * system call.  See sys_open_flags_to_namei_flags().
  * SMP-safe
  */
-int open_namei(int dfd, const char *pathname, int flag,
+int open_namei(int dfd, const char *pathname, int sys_open_flag,
 		int mode, struct nameidata *nd)
 {
 	int acc_mode, error;
 	struct path path;
 	struct dentry *dir;
 	int count = 0;
+	int flag = sys_open_flags_to_namei_flags(sys_open_flag);
 
 	acc_mode = ACC_MODE(flag);
 

@@ -1773,7 +1798,7 @@ do_last:
 
 	/* Negative dentry, just create the file */
 	if (!path.dentry->d_inode) {
-		error = open_namei_create(nd, &path, flag, mode);
+		error = __open_namei_create(nd, &path, flag, mode);
 		if (error)
 			goto exit;
 		return 0;

diff -puN fs/open.c~do-namei_flags-calculation-inside-open_namei fs/open.c
@@ -800,31 +800,13 @@ cleanup_file:
 	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;
+	int error;
 	struct nameidata nd;
 
-	namei_flags = flags;
-	if ((namei_flags+1) & O_ACCMODE)
-		namei_flags++;
-
-	error = open_namei(dfd, filename, namei_flags, mode, &nd);
+	error = open_namei(dfd, filename, flags, mode, &nd);
 	if (!error)
 		return nameidata_to_filp(&nd, flags);
 

diff -puN fs/namei.c~r-o-bind-mounts-do_rmdir-elevate-write-count fs/namei.c
@@ -2174,7 +2174,12 @@ static long do_rmdir(int dfd, const char
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit2;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto exit3;
 	error = vfs_rmdir(nd.dentry->d_inode, dentry);
+	mnt_drop_write(nd.mnt);
+exit3:
 	dput(dentry);
 exit2:
 	mutex_unlock(&nd.dentry->d_inode->i_mutex);

diff -puN fs/utimes.c~r-o-bind-mounts-elevate-write-count-for-do_utimes 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>

@@ -58,6 +59,7 @@ long do_utimes(int dfd, char __user *fil
 	struct inode *inode;
 	struct iattr newattrs;
 	struct file *f = NULL;
+	struct vfsmount *mnt;
 
 	error = -EINVAL;
 	if (times && (!nsec_valid(times[0].tv_nsec) ||

@@ -78,18 +80,20 @@ long do_utimes(int dfd, char __user *fil
 		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.dentry;
+		mnt = nd.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() */

@@ -97,7 +101,7 @@ long do_utimes(int dfd, char __user *fil
 	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;

@@ -117,22 +121,24 @@ long do_utimes(int dfd, char __user *fil
 	} 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);

diff -puN fs/inode.c~r-o-bind-mounts-elevate-write-count-for-file_update_time fs/inode.c
@@ -1263,10 +1263,19 @@ 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 = 0;
 
 	if (IS_NOCMTIME(inode))
 		return;
-	if (IS_RDONLY(inode))
+	/*
+	 * Ideally, we want to guarantee that 'f_vfsmnt'
+	 * is non-NULL here.  But, NFS exports need to
+	 * be fixed up before we can do that.  So, check
+	 * it for now. - Dave Hansen
+	 */
+	if (file->f_vfsmnt)
+		err = mnt_want_write(file->f_vfsmnt);
+	if (err)
 		return;
 
 	now = current_fs_time(inode->i_sb);

@@ -1282,6 +1291,8 @@ void file_update_time(struct file *file)
 
 	if (sync_it)
 		mark_inode_dirty_sync(inode);
+	if (file->f_vfsmnt)
+		mnt_drop_write(file->f_vfsmnt);
 }
 
 EXPORT_SYMBOL(file_update_time);

diff -puN fs/ncpfs/ioctl.c~r-o-bind-mounts-elevate-write-count-during-entire-ncp_ioctl 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* serv
 }
 #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);

@@ -817,11 +818,63 @@ outrel:			
 				return -EFAULT;
 			return 0;
 		}
-
+	default: /* unkown IOCTL command, assume write */
+		;
 	}
 	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_vfsmnt))
+			return -EACCES;
+	}
+	ret = __ncp_ioctl(inode, filp, cmd, arg);
+	if (ncp_ioctl_need_write(cmd))
+		mnt_drop_write(filp->f_vfsmnt);
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 long ncp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {

diff -puN fs/namei.c~r-o-bind-mounts-elevate-write-count-for-link-and-symlink-calls fs/namei.c
@@ -2349,7 +2349,12 @@ asmlinkage long sys_symlinkat(const char
 	if (IS_ERR(dentry))
 		goto out_unlock;
 
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_dput;
 	error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
+	mnt_drop_write(nd.mnt);
+out_dput:
 	dput(dentry);
 out_unlock:
 	mutex_unlock(&nd.dentry->d_inode->i_mutex);

@@ -2444,7 +2449,12 @@ asmlinkage long sys_linkat(int olddfd, c
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
 		goto out_unlock;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_dput;
 	error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry);
+	mnt_drop_write(nd.mnt);
+out_dput:
 	dput(new_dentry);
 out_unlock:
 	mutex_unlock(&nd.dentry->d_inode->i_mutex);

diff -puN fs/inode.c~r-o-bind-mounts-elevate-write-count-for-do_sys_utime-and-touch_atime fs/inode.c
@@ -1203,22 +1203,23 @@ void touch_atime(struct vfsmount *mnt, s
 	struct inode *inode = dentry->d_inode;
 	struct timespec now;
 
-	if (inode->i_flags & S_NOATIME)
+	if (mnt && 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;
+			goto out;
 		if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
-			return;
-
+			goto out;
 		if (mnt->mnt_flags & MNT_RELATIME) {
 			/*
 			 * With relative atime, only update atime if the

@@ -1229,16 +1230,19 @@ void touch_atime(struct vfsmount *mnt, s
 						&inode->i_atime) < 0 &&
 			    timespec_compare(&inode->i_ctime,
 						&inode->i_atime) < 0)
-				return;
+				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:
+	if (mnt)
+		mnt_drop_write(mnt);
 }
 EXPORT_SYMBOL(touch_atime);
 

diff -puN fs/ext2/ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls 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>

@@ -20,6 +21,7 @@
 int ext2_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		unsigned long arg)
 {
+	int ret;
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	unsigned int flags;
 	unsigned short rsv_window_size;

@@ -34,14 +36,19 @@ int ext2_ioctl (struct inode * inode, st
 	case EXT2_IOC_SETFLAGS: {
 		unsigned int oldflags;
 
-		if (IS_RDONLY(inode))
-			return -EROFS;
-
-		if (!is_owner_or_cap(inode))
-			return -EACCES;
+		ret = mnt_want_write(filp->f_vfsmnt);
+		if (ret)
+			return ret;
+
+		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;

@@ -58,7 +65,8 @@ 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;
 			}
 		}
 

@@ -70,20 +78,26 @@ 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 (!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_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;
 	case EXT2_IOC_GETRSVSZ:
 		if (test_opt(inode->i_sb, RESERVATION)
 			&& S_ISREG(inode->i_mode)

193 lines not on this page · raw message

202 lines not on this page · raw message

diff -puN fs/fat/file.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls 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 *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~r-o-bind-mounts-elevate-write-count-for-some-ioctls 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, 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 (!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_vfsmnt);
+		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, 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~r-o-bind-mounts-elevate-write-count-for-some-ioctls 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>

@@ -65,16 +66,20 @@ 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 (!is_owner_or_cap(inode))
-			return -EACCES;
-
-		if (get_user(flags, (int __user *) arg))
-			return -EFAULT;
-
+		err = mnt_want_write(filp->f_vfsmnt);
+		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;
+		}
 		flags = jfs_map_ext2(flags, 1);
 		if (!S_ISDIR(inode->i_mode))
 			flags &= ~JFS_DIRSYNC_FL;

@@ -89,8 +94,10 @@ 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;

@@ -100,7 +107,9 @@ 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~r-o-bind-mounts-elevate-write-count-for-some-ioctls fs/ocfs2/ioctl.c
@@ -58,10 +58,6 @@ static int ocfs2_set_inode_attr(struct i
 		goto bail;
 	}
 
-	status = -EROFS;
-	if (IS_RDONLY(inode))
-		goto bail_unlock;
-
 	status = -EACCES;
 	if (!is_owner_or_cap(inode))
 		goto bail_unlock;

@@ -130,8 +126,13 @@ 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;
 	case OCFS2_IOC_RESVSP:
 	case OCFS2_IOC_RESVSP64:
 	case OCFS2_IOC_UNRESVSP:

94 lines not on this page · raw message

diff -puN fs/xfs/linux-2.6/xfs_ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls fs/xfs/linux-2.6/xfs_ioctl.c
@@ -554,8 +554,6 @@ 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)

@@ -581,8 +579,6 @@ 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);

@@ -592,6 +588,7 @@ STATIC int
 xfs_attrmulti_by_handle(
 	xfs_mount_t		*mp,
 	void			__user *arg,
+	struct file		*parfilp,
 	struct inode		*parinode)
 {
 	int			error;

@@ -646,13 +643,21 @@ 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(inode,
 					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(inode,
 					attr_name, ops[i].am_flags);
+			mnt_drop_write(parfilp->f_vfsmnt);
 			break;
 		default:
 			ops[i].am_error = EINVAL;

@@ -834,7 +839,7 @@ 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~r-o-bind-mounts-elevate-write-count-for-some-ioctls fs/xfs/linux-2.6/xfs_iops.c
@@ -140,13 +140,6 @@ 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~r-o-bind-mounts-elevate-write-count-for-some-ioctls 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>
 
 

@@ -690,10 +691,16 @@ start:
 	if (new_size > xip->i_size)
 		io->io_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_vfsmnt))) {
 		file_update_time(file);
 		xfs_ichgtime_fast(xip, inode,
 				  XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+		mnt_drop_write(file->f_vfsmnt);
 	}
 
 	/*

diff -puN fs/file_table.c~r-o-bind-mounts-elevate-write-count-opend-files fs/file_table.c
@@ -193,6 +193,17 @@ int init_file(struct file *file, struct 
 	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()e
+	 */
+	if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+		error = mnt_want_write(mnt);
+		WARN_ON(error);
+	}
 	return error;
 }
 EXPORT_SYMBOL(init_file);

@@ -230,8 +241,11 @@ void fastcall __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)
+	if (file->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
+		if (!special_file(inode->i_mode))
+			mnt_drop_write(mnt);
+	}
 	put_pid(file->f_owner.pid);
 	file_kill(file);
 	file->f_path.dentry = NULL;

122 lines not on this page · raw message

diff -puN fs/open.c~r-o-bind-mounts-elevate-write-count-opend-files fs/open.c
@@ -734,6 +734,35 @@ 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 *))

@@ -746,7 +775,7 @@ static struct file *__dentry_open(struct
 				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;
 	}

@@ -788,8 +817,11 @@ static struct file *__dentry_open(struct
 
 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))
+			mnt_drop_write(mnt);
+	}
 	file_kill(f);
 	f->f_path.dentry = NULL;
 	f->f_path.mnt = NULL;

diff -puN ipc/mqueue.c~r-o-bind-mounts-elevate-write-count-opend-files ipc/mqueue.c
@@ -682,6 +682,9 @@ asmlinkage long sys_mq_open(const char _
 				goto out;
 			filp = do_open(dentry, oflag);
 		} else {
+			error = mnt_want_write(mqueue_mnt);
+			if (error)
+				goto out;
 			filp = do_create(mqueue_mnt->mnt_root, dentry,
 						oflag, mode, u_attr);
 		}

diff -puN fs/namei.c~r-o-bind-mounts-elevate-write-count-over-calls-to-vfs_rename fs/namei.c
@@ -2734,8 +2734,12 @@ static int do_rename(int olddfd, const c
 	if (new_dentry == trap)
 		goto exit5;
 
+	error = mnt_want_write(oldnd.mnt);
+	if (error)
+		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
 				   new_dir->d_inode, new_dentry);
+	mnt_drop_write(oldnd.mnt);
 exit5:
 	dput(new_dentry);
 exit4:

diff -puN fs/nfsd/vfs.c~r-o-bind-mounts-elevate-write-count-over-calls-to-vfs_rename fs/nfsd/vfs.c
@@ -1668,13 +1668,20 @@ nfsd_rename(struct svc_rqst *rqstp, stru
 	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_mnt != tfhp->fh_export->ex_mnt)
+		goto out_dput_new;
+	host_err = mnt_want_write(ffhp->fh_export->ex_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);

diff -puN fs/open.c~r-o-bind-mounts-elevate-writer-count-for-do_sys_truncate fs/open.c
@@ -244,21 +244,21 @@ static long do_sys_truncate(const char _
 	if (!S_ISREG(inode->i_mode))
 		goto dput_and_out;
 
-	error = vfs_permission(&nd, MAY_WRITE);
+	error = mnt_want_write(nd.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 _
 
 put_write_and_out:
 	put_write_access(inode);
+mnt_drop_write_and_out:
+	mnt_drop_write(nd.mnt);
 dput_and_out:
 	path_release(&nd);
 out:

diff -puN fs/open.c~r-o-bind-mounts-make-access-use-mnt-check fs/open.c
@@ -459,8 +459,17 @@ asmlinkage long sys_faccessat(int dfd, c
 	if(res || !(mode & S_IWOTH) ||
 	   special_file(nd.dentry->d_inode->i_mode))
 		goto out_path_release;
-
-	if(IS_RDONLY(nd.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.mnt))
 		res = -EROFS;
 
 out_path_release:

diff -puN fs/open.c~r-o-bind-mounts-elevate-writer-count-for-chown-and-friends fs/open.c
@@ -571,12 +571,12 @@ asmlinkage long sys_fchmod(unsigned int 
 
 	audit_inode(NULL, dentry);
 
-	err = -EROFS;
-	if (IS_RDONLY(inode))
+	err = mnt_want_write(file->f_vfsmnt);
+	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;

@@ -585,6 +585,8 @@ asmlinkage long sys_fchmod(unsigned int 
 	err = notify_change(dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(file->f_vfsmnt);
 out_putf:
 	fput(file);
 out:

@@ -604,13 +606,13 @@ asmlinkage long sys_fchmodat(int dfd, co
 		goto out;
 	inode = nd.dentry->d_inode;
 
-	error = -EROFS;
-	if (IS_RDONLY(inode))
+	error = mnt_want_write(nd.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)

@@ -620,6 +622,8 @@ asmlinkage long sys_fchmodat(int dfd, co
 	error = notify_change(nd.dentry, &newattrs);
 	mutex_unlock(&inode->i_mutex);
 
+out_drop_write:
+	mnt_drop_write(nd.mnt);
 dput_and_out:
 	path_release(&nd);
 out:

@@ -642,9 +646,6 @@ static int chown_common(struct dentry * 
 		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;

@@ -675,7 +676,12 @@ asmlinkage long sys_chown(const char __u
 	error = user_path_walk(filename, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.dentry, user, group);
+	mnt_drop_write(nd.mnt);
+out_release:
 	path_release(&nd);
 out:
 	return error;

@@ -695,7 +701,12 @@ asmlinkage long sys_fchownat(int dfd, co
 	error = __user_walk_fd(dfd, filename, follow, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.dentry, user, group);
+	mnt_drop_write(nd.mnt);
+out_release:
 	path_release(&nd);
 out:
 	return error;

@@ -709,7 +720,12 @@ asmlinkage long sys_lchown(const char __
 	error = user_path_walk_link(filename, &nd);
 	if (error)
 		goto out;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_release;
 	error = chown_common(nd.dentry, user, group);
+	mnt_drop_write(nd.mnt);
+out_release:
 	path_release(&nd);
 out:
 	return error;

@@ -726,9 +742,14 @@ asmlinkage long sys_fchown(unsigned int 
 	if (!file)
 		goto out;
 
+	error = mnt_want_write(file->f_vfsmnt);
+	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_vfsmnt);
+out_fput:
 	fput(file);
 out:
 	return error;

diff -puN fs/namei.c~r-o-bind-mounts-sys_mknodat-elevate-write-count-for-vfs_mknod-create fs/namei.c
@@ -2022,6 +2022,23 @@ int vfs_mknod(struct inode *dir, struct 
 	return error;
 }
 
+static int may_mknod(mode_t mode)
+{
+	switch (mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFCHR:
+	case S_IFBLK:
+	case S_IFIFO:
+	case S_IFSOCK:
+	case 0: /* zero mode translates to S_IFREG */
+		return 0;
+	case S_IFDIR:
+		return -EPERM;
+	default:
+		return -EINVAL;
+	}
+}
+
 asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
 				unsigned dev)
 {

@@ -2040,12 +2057,19 @@ asmlinkage long sys_mknodat(int dfd, con
 	if (error)
 		goto out;
 	dentry = lookup_create(&nd, 0);
-	error = PTR_ERR(dentry);
-
+	if (IS_ERR(dentry)) {
+		error = PTR_ERR(dentry);
+		goto out_unlock;
+	}
 	if (!IS_POSIXACL(nd.dentry->d_inode))
 		mode &= ~current->fs->umask;
-	if (!IS_ERR(dentry)) {
-		switch (mode & S_IFMT) {
+	error = may_mknod(mode);
+	if (error)
+		goto out_dput;
+	error = mnt_want_write(nd.mnt);
+	if (error)
+		goto out_dput;
+	switch (mode & S_IFMT) {
 		case 0: case S_IFREG:
 			error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd);
 			break;

@@ -2056,14 +2080,11 @@ asmlinkage long sys_mknodat(int dfd, con
 		case S_IFIFO: case S_IFSOCK:
 			error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0);
 			break;
-		case S_IFDIR:
-			error = -EPERM;
-			break;
-		default:
-			error = -EINVAL;
-		}
-		dput(dentry);
 	}
+	mnt_drop_write(nd.mnt);
+out_dput:
+	dput(dentry);
+out_unlock:
 	mutex_unlock(&nd.dentry->d_inode->i_mutex);
 	path_release(&nd);
 out:

diff -puN fs/nfsd/vfs.c~r-o-bind-mounts-sys_mknodat-elevate-write-count-for-vfs_mknod-create fs/nfsd/vfs.c
@@ -1242,7 +1242,11 @@ nfsd_create(struct svc_rqst *rqstp, stru
 	case S_IFBLK:
 	case S_IFIFO:
 	case S_IFSOCK:
+		host_err = mnt_want_write(fhp->fh_export->ex_mnt);
+		if (host_err)
+			break;
 		host_err = vfs_mknod(dirp, dchild, iap->ia_mode, rdev);
+		mnt_drop_write(fhp->fh_export->ex_mnt);
 		break;
 	default:
 	        printk("nfsd: bad file type %o in nfsd_create\n", type);

diff -puN net/unix/af_unix.c~r-o-bind-mounts-sys_mknodat-elevate-write-count-for-vfs_mknod-create net/unix/af_unix.c
@@ -838,7 +838,11 @@ static int unix_bind(struct socket *sock
 		 */
 		mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current->fs->umask);
+		err = mnt_want_write(nd.mnt);
+		if (err)
+			goto out_mknod_dput;
 		err = vfs_mknod(nd.dentry->d_inode, dentry, mode, 0);
+		mnt_drop_write(nd.mnt);
 		if (err)
 			goto out_mknod_dput;
 		mutex_unlock(&nd.dentry->d_inode->i_mutex);

diff -puN fs/namespace.c~r-o-bind-mounts-track-number-of-mount-writers fs/namespace.c
@@ -17,6 +17,7 @@
 #include <linux/quotaops.h>
 #include <linux/acct.h>
 #include <linux/capability.h>
+#include <linux/cpumask.h>
 #include <linux/module.h>
 #include <linux/sysfs.h>
 #include <linux/seq_file.h>

@@ -52,6 +53,8 @@ static inline unsigned long hash(struct 
 	return tmp & hash_mask;
 }
 
+#define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)
+
 struct vfsmount *alloc_vfsmnt(const char *name)
 {
 	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);

@@ -65,6 +68,7 @@ struct vfsmount *alloc_vfsmnt(const char
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
+		atomic_set(&mnt->__mnt_writers, 0);
 		if (name) {
 			int size = strlen(name) + 1;
 			char *newname = kmalloc(size, GFP_KERNEL);

@@ -85,6 +89,84 @@ struct vfsmount *alloc_vfsmnt(const char
  * we can determine when writes are able to occur to
  * a filesystem.
  */
+/*
+ * __mnt_is_readonly: check whether a mount is read-only
+ * @mnt: the mount to check for its write status
+ *
+ * This shouldn't be used directly ouside of the VFS.
+ * It does not guarantee that the filesystem will stay
+ * r/w, just that it is right *now*.  This can not and
+ * should not be used in place of IS_RDONLY(inode).
+ * mnt_want/drop_write() will _keep_ the filesystem
+ * r/w.
+ */
+int __mnt_is_readonly(struct vfsmount *mnt)
+{
+	return (mnt->mnt_sb->s_flags & MS_RDONLY);
+}
+EXPORT_SYMBOL_GPL(__mnt_is_readonly);
+
+struct mnt_writer {
+	/*
+	 * If holding multiple instances of this lock, they
+	 * must be ordered by cpu number.
+	 */
+	spinlock_t lock;
+	unsigned long count;
+	struct vfsmount *mnt;
+} ____cacheline_aligned_in_smp;
+static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);
+
+static int __init init_mnt_writers(void)
+{
+	int cpu;
+	for_each_possible_cpu(cpu) {
+		struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
+		spin_lock_init(&writer->lock);
+		writer->count = 0;
+	}
+	return 0;
+}
+fs_initcall(init_mnt_writers);
+
+static void mnt_unlock_cpus(void)
+{
+	int cpu;
+	struct mnt_writer *cpu_writer;
+
+	for_each_possible_cpu(cpu) {
+		cpu_writer = &per_cpu(mnt_writers, cpu);
+		spin_unlock(&cpu_writer->lock);
+	}
+}
+
+static inline void __clear_mnt_count(struct mnt_writer *cpu_writer)
+{
+	if (!cpu_writer->mnt)
+		return;
+	atomic_add(cpu_writer->count, &cpu_writer->mnt->__mnt_writers);
+	cpu_writer->count = 0;
+}
+ /*
+ * must hold cpu_writer->lock
+ */
+static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
+					  struct vfsmount *mnt)
+{
+	if (cpu_writer->mnt == mnt)
+		return;
+	__clear_mnt_count(cpu_writer);
+	cpu_writer->mnt = mnt;
+}
+
+/*
+ * Most r/o checks on a fs are for operations that take
+ * discrete amounts of time, like a write() or unlink().
+ * We must keep track of when those operations start
+ * (for permission checks) and when they end, so that
+ * we can determine when writes are able to occur to
+ * a filesystem.
+ */
 /**
  * mnt_want_write - get write access to a mount
  * @mnt: the mount on which to take a write

@@ -97,12 +179,58 @@ struct vfsmount *alloc_vfsmnt(const char
  */
 int mnt_want_write(struct vfsmount *mnt)
 {
-	if (__mnt_is_readonly(mnt))
-		return -EROFS;
-	return 0;
+	int ret = 0;
+	struct mnt_writer *cpu_writer;
+
+	cpu_writer = &get_cpu_var(mnt_writers);
+	spin_lock(&cpu_writer->lock);
+	if (__mnt_is_readonly(mnt)) {
+		ret = -EROFS;
+		goto out;
+	}
+	use_cpu_writer_for_mount(cpu_writer, mnt);
+	cpu_writer->count++;
+out:
+	spin_unlock(&cpu_writer->lock);
+	put_cpu_var(mnt_writers);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(mnt_want_write);
 
+static void lock_and_coalesce_cpu_mnt_writer_counts(void)
+{
+	int cpu;
+	struct mnt_writer *cpu_writer;
+
+	for_each_possible_cpu(cpu) {
+		cpu_writer = &per_cpu(mnt_writers, cpu);
+		spin_lock(&cpu_writer->lock);
+		__clear_mnt_count(cpu_writer);
+		cpu_writer->mnt = NULL;
+	}
+}
+
+/*
+ * These per-cpu write counts are not guaranteed to have
+ * matched increments and decrements on any given cpu.
+ * A file open()ed for write on one cpu and close()d on
+ * another cpu will imbalance this count.  Make sure it
+ * does not get too far out of whack.
+ */
+static void handle_write_count_underflow(struct vfsmount *mnt)
+{
+	while (atomic_read(&mnt->__mnt_writers) <
+		MNT_WRITER_UNDERFLOW_LIMIT) {
+		/*
+		 * It isn't necessary to hold all of the locks
+		 * at the same time, but doing it this way makes
+		 * us share a lot more code.
+		 */
+		lock_and_coalesce_cpu_mnt_writer_counts();
+		mnt_unlock_cpus();
+	}
+}
+
 /**
  * mnt_drop_write - give up write access to a mount
  * @mnt: the mount on which to give up write access

@@ -113,23 +241,61 @@ EXPORT_SYMBOL_GPL(mnt_want_write);
  */
 void mnt_drop_write(struct vfsmount *mnt)
 {
+	int must_check_underflow = 0;
+	struct mnt_writer *cpu_writer;
+
+	cpu_writer = &get_cpu_var(mnt_writers);
+	spin_lock(&cpu_writer->lock);
+
+	use_cpu_writer_for_mount(cpu_writer, mnt);
+	if (cpu_writer->count > 0) {
+		cpu_writer->count--;
+	} else {
+		must_check_underflow = 1;
+		atomic_dec(&mnt->__mnt_writers);
+	}
+
+	spin_unlock(&cpu_writer->lock);
+	/*
+	 * Logically, we could call this each time,
+	 * but the __mnt_writers cacheline tends to
+	 * be cold, and makes this expensive.
+	 */
+	if (must_check_underflow)
+		handle_write_count_underflow(mnt);
+	/*
+	 * This could be done right after the spinlock
+	 * is taken because the spinlock keeps us on
+	 * the cpu, and disables preemption.  However,
+	 * putting it here bounds the amount that
+	 * __mnt_writers can underflow.  Without it,
+	 * we could theoretically wrap __mnt_writers.
+	 */
+	put_cpu_var(mnt_writers);
 }
 EXPORT_SYMBOL_GPL(mnt_drop_write);
 
-/*
- * __mnt_is_readonly: check whether a mount is read-only
- * @mnt: the mount to check for its write status
- *
- * This shouldn't be used directly ouside of the VFS.
- * It does not guarantee that the filesystem will stay
- * r/w, just that it is right *now*.  This can not and
- * should not be used in place of IS_RDONLY(inode).
- */
-int __mnt_is_readonly(struct vfsmount *mnt)
+int mnt_make_readonly(struct vfsmount *mnt)
 {
-	return (mnt->mnt_sb->s_flags & MS_RDONLY);
+	int ret = 0;
+
+	lock_and_coalesce_cpu_mnt_writer_counts();
+	/*
+	 * With all the locks held, this value is stable
+	 */
+	if (atomic_read(&mnt->__mnt_writers) > 0) {
+		ret = -EBUSY;
+		goto out;
+	}
+	/*
+	 * actually set mount's r/o flag here to make
+	 * __mnt_is_readonly() true, which keeps anyone
+	 * from doing a successful mnt_want_write().
+	 */
+out:
+	mnt_unlock_cpus();
+	return ret;
 }
-EXPORT_SYMBOL_GPL(__mnt_is_readonly);
 
 int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
 {

@@ -325,6 +491,15 @@ static struct vfsmount *clone_mnt(struct
 static inline void __mntput(struct vfsmount *mnt)
 {
 	struct super_block *sb = mnt->mnt_sb;
+	lock_and_coalesce_cpu_mnt_writer_counts();
+	mnt_unlock_cpus();
+	/*
+	 * This probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this
+	 * happens, the filesystem was probably unable
+	 * to make r/w->r/o transitions.
+	 */
+	WARN_ON(atomic_read(&mnt->__mnt_writers));
 	dput(mnt->mnt_root);
 	free_vfsmnt(mnt);
 	deactivate_super(sb);

diff -puN include/linux/mount.h~r-o-bind-mounts-track-number-of-mount-writers 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>
 

@@ -61,6 +62,13 @@ struct vfsmount {
 	atomic_t mnt_count;
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	int mnt_pinned;
+	/*
+	 * 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)

diff -puN fs/nfs/dir.c~r-o-bind-mounts-nfs-check-mnt-instead-of-superblock-directly fs/nfs/dir.c
@@ -949,7 +949,8 @@ static int is_atomic_open(struct inode *
 	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->mnt) &&
+	    (nd->intent.open.flags & (O_CREAT|O_TRUNC|FMODE_WRITE)))
 		return 0;
 	return 1;
 }

diff -puN fs/nfsd/vfs.c~r-o-bind-mounts-nfs-check-mnt-instead-of-superblock-directly fs/nfsd/vfs.c
@@ -1862,7 +1862,7 @@ nfsd_permission(struct svc_rqst *rqstp, 
 		inode->i_mode,
 		IS_IMMUTABLE(inode)?	" immut" : "",
 		IS_APPEND(inode)?	" append" : "",
-		IS_RDONLY(inode)?	" ro" : "");
+		__mnt_is_readonly(exp->ex_mnt)?	" ro" : "");
 	dprintk("      owner %d/%d user %d/%d\n",
 		inode->i_uid, inode->i_gid, current->fsuid, current->fsgid);
 #endif

@@ -1873,7 +1873,7 @@ nfsd_permission(struct svc_rqst *rqstp, 
 	 */
 	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_mnt))
 				return nfserr_rofs;
 			if (/* (acc & MAY_WRITE) && */ IS_IMMUTABLE(inode))
 				return nfserr_perm;

diff -puN fs/namespace.c~r-o-bind-mounts-honor-r-w-changes-at-do_remount-time fs/namespace.c
@@ -102,7 +102,11 @@ struct vfsmount *alloc_vfsmnt(const char
  */
 int __mnt_is_readonly(struct vfsmount *mnt)
 {
-	return (mnt->mnt_sb->s_flags & MS_RDONLY);
+	if (mnt->mnt_flags & MNT_READONLY)
+		return 1;
+	if (mnt->mnt_sb->s_flags & MS_RDONLY)
+		return 1;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(__mnt_is_readonly);
 

@@ -277,7 +281,7 @@ void mnt_drop_write(struct vfsmount *mnt
 }
 EXPORT_SYMBOL_GPL(mnt_drop_write);
 
-int mnt_make_readonly(struct vfsmount *mnt)
+static int mnt_make_readonly(struct vfsmount *mnt)
 {
 	int ret = 0;
 

@@ -290,15 +294,21 @@ int mnt_make_readonly(struct vfsmount *m
 		goto out;
 	}
 	/*
-	 * actually set mount's r/o flag here to make
-	 * __mnt_is_readonly() true, which keeps anyone
-	 * from doing a successful mnt_want_write().
+	 * nobody can do a successful mnt_want_write() with all
+	 * of the counts in MNT_DENIED_WRITE and the locks held.
 	 */
+	if (!ret)
+		mnt->mnt_flags |= MNT_READONLY;
 out:
 	mnt_unlock_cpus();
 	return ret;
 }
 
+static void __mnt_unmake_readonly(struct vfsmount *mnt)
+{
+	mnt->mnt_flags &= ~MNT_READONLY;
+}
+
 int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
 {
 	mnt->mnt_sb = sb;

@@ -607,7 +617,7 @@ static int show_vfsmnt(struct seq_file *
 		seq_putc(m, '.');
 		mangle(m, mnt->mnt_sb->s_subtype);
 	}
-	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
+	seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
 	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
 		if (mnt->mnt_sb->s_flags & fs_infop->flag)
 			seq_puts(m, fs_infop->str);

@@ -1195,6 +1205,23 @@ out:
 	return err;
 }
 
+static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
+{
+	int error = 0;
+	int readonly_request = 0;
+
+	if (ms_flags & MS_RDONLY)
+		readonly_request = 1;
+	if (readonly_request == __mnt_is_readonly(mnt))
+		return 0;
+
+	if (readonly_request)
+		error = mnt_make_readonly(mnt);
+	else
+		__mnt_unmake_readonly(mnt);
+	return error;
+}
+
 /*
  * change filesystem flags. dir should be a physical root of filesystem.
  * If you've mounted a non-root directory somewhere and want to do remount

@@ -1216,7 +1243,10 @@ static int do_remount(struct nameidata *
 		return -EINVAL;
 
 	down_write(&sb->s_umount);
-	err = do_remount_sb(sb, flags, data, 0);
+	if (flags & MS_BIND)
+		err = change_mount_flags(nd->mnt, flags);
+	else
+		err = do_remount_sb(sb, flags, data, 0);
 	if (!err)
 		nd->mnt->mnt_flags = mnt_flags;
 	up_write(&sb->s_umount);

@@ -1660,6 +1690,8 @@ long do_mount(char *dev_name, char *dir_
 		mnt_flags |= MNT_NODIRATIME;
 	if (flags & MS_RELATIME)
 		mnt_flags |= MNT_RELATIME;
+	if (flags & MS_RDONLY)
+		mnt_flags |= MNT_READONLY;
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);

diff -puN include/linux/mount.h~r-o-bind-mounts-honor-r-w-changes-at-do_remount-time include/linux/mount.h
@@ -29,6 +29,7 @@ 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
 

diff -puN fs/namespace.c~r-o-bind-mounts-track-number-of-mount-writers-make-lockdep-happy-with-r-o-bind-mounts fs/namespace.c
@@ -112,6 +112,7 @@ struct mnt_writer {
 	 * must be ordered by cpu number.
 	 */
 	spinlock_t lock;
+	struct lock_class_key lock_class; /* compiles out with !lockdep */
 	unsigned long count;
 	struct vfsmount *mnt;
 } ____cacheline_aligned_in_smp;

@@ -123,6 +124,7 @@ static int __init init_mnt_writers(void)
 	for_each_possible_cpu(cpu) {
 		struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
 		spin_lock_init(&writer->lock);
+		lockdep_set_class(&writer->lock, &writer->lock_class);
 		writer->count = 0;
 	}
 	return 0;

diff -puN fs/file_table.c~keep-track-of-mnt_writer-state-of-struct-file fs/file_table.c
@@ -42,6 +42,12 @@ static inline void file_free_rcu(struct 
 static inline void file_free(struct file *f)
 {
 	percpu_counter_dec(&nr_files);
+	/*
+	 * 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);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
 

@@ -201,6 +207,7 @@ int init_file(struct file *file, struct 
 	 * that we can do debugging checks at __fput()e
 	 */
 	if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+		file->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
 		error = mnt_want_write(mnt);
 		WARN_ON(error);
 	}

@@ -243,8 +250,18 @@ void fastcall __fput(struct file *file)
 	fops_put(file->f_op);
 	if (file->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
-		if (!special_file(inode->i_mode))
-			mnt_drop_write(mnt);
+		if (!special_file(inode->i_mode)) {
+			if (file->f_mnt_write_state == FILE_MNT_WRITE_TAKEN) {
+				mnt_drop_write(mnt);
+				file->f_mnt_write_state |=
+					FILE_MNT_WRITE_RELEASED;
+			} else {
+				printk(KERN_WARNING "__fput() of writeable "
+						"file with no "
+						"mnt_want_write()\n");
+				WARN_ON(1);
+			}
+		}
 	}
 	put_pid(file->f_owner.pid);
 	file_kill(file);

diff -puN fs/open.c~keep-track-of-mnt_writer-state-of-struct-file fs/open.c
@@ -810,6 +810,10 @@ static struct file *__dentry_open(struct
 		error = __get_file_write_access(inode, mnt);
 		if (error)
 			goto cleanup_file;
+		if (!special_file(inode->i_mode)) {
+			WARN_ON(f->f_mnt_write_state != 0);
+			f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN;
+		}
 	}
 
 	f->f_mapping = inode->i_mapping;

@@ -851,8 +855,16 @@ cleanup_all:
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITE) {
 		put_write_access(inode);
-		if (!special_file(inode->i_mode))
+		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.
+			 */
+			f->f_mnt_write_state = 0;
 			mnt_drop_write(mnt);
+		}
 	}
 	file_kill(f);
 	f->f_path.dentry = NULL;

diff -puN include/linux/fs.h~keep-track-of-mnt_writer-state-of-struct-file include/linux/fs.h
@@ -774,6 +774,9 @@ static inline int ra_has_index(struct fi
 		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

@@ -808,6 +811,7 @@ struct file {
 	spinlock_t		f_ep_lock;
 #endif /* #ifdef CONFIG_EPOLL */
 	struct address_space	*f_mapping;
+	unsigned long f_mnt_write_state;
 };
 extern spinlock_t files_lock;
 #define file_list_lock() spin_lock(&files_lock);

diff -puN fs/ext2/ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls-vs-forbid-user-to-change-file-flags-on-quota-files fs/ext2/ioctl.c
@@ -57,7 +57,8 @@ int ext2_ioctl (struct inode * inode, st
 		/* 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;
 

diff -puN fs/ext3/ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls-vs-forbid-user-to-change-file-flags-on-quota-files fs/ext3/ioctl.c
@@ -60,7 +60,8 @@ int ext3_ioctl (struct inode * inode, st
 		/* 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;
 

diff -puN fs/ext4/ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls-vs-forbid-user-to-change-file-flags-on-quota-files fs/ext4/ioctl.c
@@ -59,7 +59,8 @@ int ext4_ioctl (struct inode * inode, st
 		/* 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;
 

diff -puN fs/jfs/ioctl.c~r-o-bind-mounts-elevate-write-count-for-some-ioctls-vs-forbid-user-to-change-file-flags-on-quota-files fs/jfs/ioctl.c
@@ -85,8 +85,10 @@ int jfs_ioctl(struct inode * inode, stru
 			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;
+		}
 		jfs_get_inode_flags(jfs_inode);
 		oldflags = jfs_inode->mode2;
 

diff -puN drivers/md/dm-loop.c~fix-dm-loop drivers/md/dm-loop.c
@@ -757,7 +757,7 @@ static int loop_get_file(struct dm_targe
 	int r = 0;
 
 	ti->error = "could not open backing file";
-	filp = filp_open(lc->path, flags, 0);
+	filp = open_namei(AT_FDCWD, lc->path, flags, 0);
 	if (IS_ERR(filp))
 		return PTR_ERR(filp);
 	lc->filp = filp;