| Message ID | 20200811222803.3224434-1-zwisler@google.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [v7] Add a "nosymfollow" mount option. | expand |
On 2020-08-11, Ross Zwisler <zwisler@chromium.org> wrote: > From: Mattias Nissler <mnissler@chromium.org> > > For mounts that have the new "nosymfollow" option, don't follow symlinks > when resolving paths. The new option is similar in spirit to the > existing "nodev", "noexec", and "nosuid" options, as well as to the > LOOKUP_NO_SYMLINKS resolve flag in the openat2(2) syscall. Various BSD > variants have been supporting the "nosymfollow" mount option for a long > time with equivalent implementations. > > Note that symlinks may still be created on file systems mounted with > the "nosymfollow" option present. readlink() remains functional, so > user space code that is aware of symlinks can still choose to follow > them explicitly. > > Setting the "nosymfollow" mount option helps prevent privileged > writers from modifying files unintentionally in case there is an > unexpected link along the accessed path. The "nosymfollow" option is > thus useful as a defensive measure for systems that need to deal with > untrusted file systems in privileged contexts. > > More information on the history and motivation for this patch can be > found here: > > https://sites.google.com/a/chromium.org/dev/chromium-os/chromiumos-design-docs/hardening-against-malicious-stateful-data#TOC-Restricting-symlink-traversal Looks good. Did you plan to add an in-tree test for this (you could shove it in tools/testing/selftests/mount)? Reviewed-by: Aleksa Sarai <cyphar@cyphar.com> > Signed-off-by: Mattias Nissler <mnissler@chromium.org> > Signed-off-by: Ross Zwisler <zwisler@google.com> > --- > Changes since v6 [1]: > * Rebased onto v5.8. > * Another round of testing including readlink(1), readlink(2), > realpath(1), realpath(3), statfs(2) and mount(2) to make sure > everything still works. > > After this lands I will upstream changes to util-linux[2] and man-pages > [3]. > > [1]: https://lkml.org/lkml/2020/3/4/770 > [2]: https://github.com/rzwisler/util-linux/commit/7f8771acd85edb70d97921c026c55e1e724d4e15 > [3]: https://github.com/rzwisler/man-pages/commit/b8fe8079f64b5068940c0144586e580399a71668 > --- > fs/namei.c | 3 ++- > fs/namespace.c | 2 ++ > fs/proc_namespace.c | 1 + > fs/statfs.c | 2 ++ > include/linux/mount.h | 3 ++- > include/linux/statfs.h | 1 + > include/uapi/linux/mount.h | 1 + > 7 files changed, 11 insertions(+), 2 deletions(-) > > diff --git a/fs/namei.c b/fs/namei.c > index 72d4219c93acb..ed68478fb1fb6 100644 > --- a/fs/namei.c > +++ b/fs/namei.c > @@ -1626,7 +1626,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link, > return ERR_PTR(error); > } > > - if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS)) > + if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || > + unlikely(nd->path.mnt->mnt_flags & MNT_NOSYMFOLLOW)) > return ERR_PTR(-ELOOP); > > if (!(nd->flags & LOOKUP_RCU)) { > diff --git a/fs/namespace.c b/fs/namespace.c > index 4a0f600a33285..1cbbf5a9b954f 100644 > --- a/fs/namespace.c > +++ b/fs/namespace.c > @@ -3167,6 +3167,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, > mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); > if (flags & MS_RDONLY) > mnt_flags |= MNT_READONLY; > + if (flags & MS_NOSYMFOLLOW) > + mnt_flags |= MNT_NOSYMFOLLOW; > > /* The default atime for remount is preservation */ > if ((flags & MS_REMOUNT) && > diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c > index 3059a9394c2d6..e59d4bb3a89e4 100644 > --- a/fs/proc_namespace.c > +++ b/fs/proc_namespace.c > @@ -70,6 +70,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) > { MNT_NOATIME, ",noatime" }, > { MNT_NODIRATIME, ",nodiratime" }, > { MNT_RELATIME, ",relatime" }, > + { MNT_NOSYMFOLLOW, ",nosymfollow" }, > { 0, NULL } > }; > const struct proc_fs_opts *fs_infop; > diff --git a/fs/statfs.c b/fs/statfs.c > index 2616424012ea7..59f33752c1311 100644 > --- a/fs/statfs.c > +++ b/fs/statfs.c > @@ -29,6 +29,8 @@ static int flags_by_mnt(int mnt_flags) > flags |= ST_NODIRATIME; > if (mnt_flags & MNT_RELATIME) > flags |= ST_RELATIME; > + if (mnt_flags & MNT_NOSYMFOLLOW) > + flags |= ST_NOSYMFOLLOW; > return flags; > } > > diff --git a/include/linux/mount.h b/include/linux/mount.h > index de657bd211fa6..aaf343b38671c 100644 > --- a/include/linux/mount.h > +++ b/include/linux/mount.h > @@ -30,6 +30,7 @@ struct fs_context; > #define MNT_NODIRATIME 0x10 > #define MNT_RELATIME 0x20 > #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ > +#define MNT_NOSYMFOLLOW 0x80 > > #define MNT_SHRINKABLE 0x100 > #define MNT_WRITE_HOLD 0x200 > @@ -46,7 +47,7 @@ struct fs_context; > #define MNT_SHARED_MASK (MNT_UNBINDABLE) > #define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ > | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ > - | MNT_READONLY) > + | MNT_READONLY | MNT_NOSYMFOLLOW) > #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) > > #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ > diff --git a/include/linux/statfs.h b/include/linux/statfs.h > index 9bc69edb8f188..fac4356ea1bfc 100644 > --- a/include/linux/statfs.h > +++ b/include/linux/statfs.h > @@ -40,6 +40,7 @@ struct kstatfs { > #define ST_NOATIME 0x0400 /* do not update access times */ > #define ST_NODIRATIME 0x0800 /* do not update directory access times */ > #define ST_RELATIME 0x1000 /* update atime relative to mtime/ctime */ > +#define ST_NOSYMFOLLOW 0x2000 /* do not follow symlinks */ > > struct dentry; > extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid); > diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h > index 96a0240f23fed..dd8306ea336c1 100644 > --- a/include/uapi/linux/mount.h > +++ b/include/uapi/linux/mount.h > @@ -16,6 +16,7 @@ > #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ > #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ > #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ > +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ > #define MS_NOATIME 1024 /* Do not update access times. */ > #define MS_NODIRATIME 2048 /* Do not update directory access times */ > #define MS_BIND 4096 > -- > 2.28.0.236.gb10cc79966-goog >
On Tue, Aug 11, 2020 at 7:43 PM Aleksa Sarai <cyphar@cyphar.com> wrote: > On 2020-08-11, Ross Zwisler <zwisler@chromium.org> wrote: > > From: Mattias Nissler <mnissler@chromium.org> > > > > For mounts that have the new "nosymfollow" option, don't follow symlinks > > when resolving paths. The new option is similar in spirit to the > > existing "nodev", "noexec", and "nosuid" options, as well as to the > > LOOKUP_NO_SYMLINKS resolve flag in the openat2(2) syscall. Various BSD > > variants have been supporting the "nosymfollow" mount option for a long > > time with equivalent implementations. > > > > Note that symlinks may still be created on file systems mounted with > > the "nosymfollow" option present. readlink() remains functional, so > > user space code that is aware of symlinks can still choose to follow > > them explicitly. > > > > Setting the "nosymfollow" mount option helps prevent privileged > > writers from modifying files unintentionally in case there is an > > unexpected link along the accessed path. The "nosymfollow" option is > > thus useful as a defensive measure for systems that need to deal with > > untrusted file systems in privileged contexts. > > > > More information on the history and motivation for this patch can be > > found here: > > > > https://sites.google.com/a/chromium.org/dev/chromium-os/chromiumos-design-docs/hardening-against-malicious-stateful-data#TOC-Restricting-symlink-traversal > > Looks good. Did you plan to add an in-tree test for this (you could > shove it in tools/testing/selftests/mount)? Sure, that sounds like a good idea. I'll take a look. > Reviewed-by: Aleksa Sarai <cyphar@cyphar.com> Thank you for the review.
On Tue, Aug 11, 2020 at 04:28:03PM -0600, Ross Zwisler wrote: > diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h > index 96a0240f23fed..dd8306ea336c1 100644 > --- a/include/uapi/linux/mount.h > +++ b/include/uapi/linux/mount.h > @@ -16,6 +16,7 @@ > #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ > #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ > #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ > +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ > #define MS_NOATIME 1024 /* Do not update access times. */ > #define MS_NODIRATIME 2048 /* Do not update directory access times */ > #define MS_BIND 4096 Does this need to be added to MS_RMT_MASK too?
On Wed, Aug 12, 2020 at 12:36 PM Matthew Wilcox <willy@infradead.org> wrote: > On Tue, Aug 11, 2020 at 04:28:03PM -0600, Ross Zwisler wrote: > > diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h > > index 96a0240f23fed..dd8306ea336c1 100644 > > --- a/include/uapi/linux/mount.h > > +++ b/include/uapi/linux/mount.h > > @@ -16,6 +16,7 @@ > > #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ > > #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ > > #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ > > +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ > > #define MS_NOATIME 1024 /* Do not update access times. */ > > #define MS_NODIRATIME 2048 /* Do not update directory access times */ > > #define MS_BIND 4096 > > Does this need to be added to MS_RMT_MASK too? I don't think so, because IIUC that is only for "superblock flags", i.e. flags which are part of the sb_flags definition in do_mount()/path_mount()? https://github.com/torvalds/linux/blob/master/fs/namespace.c#L3172 With the current code I'm able to remount and flip nosymfollow both directions without issue. Similarly, MS_NOEXEC can be turned on and off at will, and it's not part of MS_RMT_MASK nor sb_flags. Interestingly, though, if you change MS_RMT_MASK to be 0, I would expect us to be unable to twiddle all the flags which are currently part of it, but that isn't the case. I was still able to change between RO/RW, and turn on lazytime. So, I think this flag is working as expected, but that there is probably a bug in there somewhere WRT the handling of MS_RMT_MASK.
diff --git a/fs/namei.c b/fs/namei.c index 72d4219c93acb..ed68478fb1fb6 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1626,7 +1626,8 @@ static const char *pick_link(struct nameidata *nd, struct path *link, return ERR_PTR(error); } - if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS)) + if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) || + unlikely(nd->path.mnt->mnt_flags & MNT_NOSYMFOLLOW)) return ERR_PTR(-ELOOP); if (!(nd->flags & LOOKUP_RCU)) { diff --git a/fs/namespace.c b/fs/namespace.c index 4a0f600a33285..1cbbf5a9b954f 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3167,6 +3167,8 @@ long do_mount(const char *dev_name, const char __user *dir_name, mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME); if (flags & MS_RDONLY) mnt_flags |= MNT_READONLY; + if (flags & MS_NOSYMFOLLOW) + mnt_flags |= MNT_NOSYMFOLLOW; /* The default atime for remount is preservation */ if ((flags & MS_REMOUNT) && diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 3059a9394c2d6..e59d4bb3a89e4 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -70,6 +70,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) { MNT_NOATIME, ",noatime" }, { MNT_NODIRATIME, ",nodiratime" }, { MNT_RELATIME, ",relatime" }, + { MNT_NOSYMFOLLOW, ",nosymfollow" }, { 0, NULL } }; const struct proc_fs_opts *fs_infop; diff --git a/fs/statfs.c b/fs/statfs.c index 2616424012ea7..59f33752c1311 100644 --- a/fs/statfs.c +++ b/fs/statfs.c @@ -29,6 +29,8 @@ static int flags_by_mnt(int mnt_flags) flags |= ST_NODIRATIME; if (mnt_flags & MNT_RELATIME) flags |= ST_RELATIME; + if (mnt_flags & MNT_NOSYMFOLLOW) + flags |= ST_NOSYMFOLLOW; return flags; } diff --git a/include/linux/mount.h b/include/linux/mount.h index de657bd211fa6..aaf343b38671c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -30,6 +30,7 @@ struct fs_context; #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ +#define MNT_NOSYMFOLLOW 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 @@ -46,7 +47,7 @@ struct fs_context; #define MNT_SHARED_MASK (MNT_UNBINDABLE) #define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ - | MNT_READONLY) + | MNT_READONLY | MNT_NOSYMFOLLOW) #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ diff --git a/include/linux/statfs.h b/include/linux/statfs.h index 9bc69edb8f188..fac4356ea1bfc 100644 --- a/include/linux/statfs.h +++ b/include/linux/statfs.h @@ -40,6 +40,7 @@ struct kstatfs { #define ST_NOATIME 0x0400 /* do not update access times */ #define ST_NODIRATIME 0x0800 /* do not update directory access times */ #define ST_RELATIME 0x1000 /* update atime relative to mtime/ctime */ +#define ST_NOSYMFOLLOW 0x2000 /* do not follow symlinks */ struct dentry; extern int vfs_get_fsid(struct dentry *dentry, __kernel_fsid_t *fsid); diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 96a0240f23fed..dd8306ea336c1 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -16,6 +16,7 @@ #define MS_REMOUNT 32 /* Alter flags of a mounted FS */ #define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */ #define MS_DIRSYNC 128 /* Directory modifications are synchronous */ +#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */ #define MS_NOATIME 1024 /* Do not update access times. */ #define MS_NODIRATIME 2048 /* Do not update directory access times */ #define MS_BIND 4096