From: "Darrick J. Wong" djwong@kernel.org

commit e014f37db1a2d109afa750042ac4d69cf3e3d88e upsream.

Filipe Manana pointed out that XFS' behavior w.r.t. setuid/setgid revocation isn't consistent with btrfs[1] or ext4. Those two filesystems use the VFS function setattr_copy to convey certain attributes from struct iattr into the VFS inode structure.

Andrey Zhadchenko reported[2] that XFS uses the wrong user namespace to decide if it should clear setgid and setuid on a file attribute update. This is a second symptom of the problem that Filipe noticed.

XFS, on the other hand, open-codes setattr_copy in xfs_setattr_mode, xfs_setattr_nonsize, and xfs_setattr_time. Regrettably, setattr_copy is /not/ a simple copy function; it contains additional logic to clear the setgid bit when setting the mode, and XFS' version no longer matches.

The VFS implements its own setuid/setgid stripping logic, which establishes consistent behavior. It's a tad unfortunate that it's scattered across notify_change, should_remove_suid, and setattr_copy but XFS should really follow the Linux VFS. Adapt XFS to use the VFS functions and get rid of the old functions.

[1] https://lore.kernel.org/fstests/CAL3q7H47iNQ=Wmk83WcGB-KBJVOEtR9+qGczzCeXJ9Y... [2] https://lore.kernel.org/linux-xfs/20220221182218.748084-1-andrey.zhadchenko@...

Fixes: 7fa294c8991c ("userns: Allow chown and setgid preservation") Signed-off-by: Darrick J. Wong djwong@kernel.org Reviewed-by: Dave Chinner dchinner@redhat.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Christian Brauner brauner@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_iops.c | 56 +++-------------------------------------------- fs/xfs/xfs_pnfs.c | 3 ++- 2 files changed, 5 insertions(+), 54 deletions(-)

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index a607d6aca5c4..1eb71275e5b0 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -634,37 +634,6 @@ xfs_vn_getattr( return 0; }

-static void -xfs_setattr_mode( - struct xfs_inode *ip, - struct iattr *iattr) -{ - struct inode *inode = VFS_I(ip); - umode_t mode = iattr->ia_mode; - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - inode->i_mode &= S_IFMT; - inode->i_mode |= mode & ~S_IFMT; -} - -void -xfs_setattr_time( - struct xfs_inode *ip, - struct iattr *iattr) -{ - struct inode *inode = VFS_I(ip); - - ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); - - if (iattr->ia_valid & ATTR_ATIME) - inode->i_atime = iattr->ia_atime; - if (iattr->ia_valid & ATTR_CTIME) - inode->i_ctime = iattr->ia_ctime; - if (iattr->ia_valid & ATTR_MTIME) - inode->i_mtime = iattr->ia_mtime; -} - static int xfs_vn_change_ok( struct user_namespace *mnt_userns, @@ -763,16 +732,6 @@ xfs_setattr_nonsize( gid = (mask & ATTR_GID) ? iattr->ia_gid : igid; uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;

- /* - * CAP_FSETID overrides the following restrictions: - * - * The set-user-ID and set-group-ID bits of a file will be - * cleared upon successful return from chown() - */ - if ((inode->i_mode & (S_ISUID|S_ISGID)) && - !capable(CAP_FSETID)) - inode->i_mode &= ~(S_ISUID|S_ISGID); - /* * Change the ownerships and register quota modifications * in the transaction. @@ -784,7 +743,6 @@ xfs_setattr_nonsize( olddquot1 = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp); } - inode->i_uid = uid; } if (!gid_eq(igid, gid)) { if (XFS_IS_GQUOTA_ON(mp)) { @@ -795,15 +753,10 @@ xfs_setattr_nonsize( olddquot2 = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp); } - inode->i_gid = gid; } }

- if (mask & ATTR_MODE) - xfs_setattr_mode(ip, iattr); - if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) - xfs_setattr_time(ip, iattr); - + setattr_copy(mnt_userns, inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

XFS_STATS_INC(mp, xs_ig_attrchg); @@ -1028,11 +981,8 @@ xfs_setattr_size( xfs_inode_clear_eofblocks_tag(ip); }

- if (iattr->ia_valid & ATTR_MODE) - xfs_setattr_mode(ip, iattr); - if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME)) - xfs_setattr_time(ip, iattr); - + ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); + setattr_copy(mnt_userns, inode, iattr); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

XFS_STATS_INC(mp, xs_ig_attrchg); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 5e1d29d8b2e7..8865f7d4404a 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -283,7 +283,8 @@ xfs_fs_commit_blocks( xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);

- xfs_setattr_time(ip, iattr); + ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID))); + setattr_copy(&init_user_ns, inode, iattr); if (update_isize) { i_size_write(inode, iattr->ia_size); ip->i_disk_size = iattr->ia_size;

From: Dave Chinner dchinner@redhat.com

commit 472c6e46f589c26057596dcba160712a5b3e02c5 upstream.

[partial backport for dependency - xfs_ioc_space() still uses XFS_PREALLOC_SYNC]

Callers can acheive the same thing by calling xfs_log_force_inode() after making their modifications. There is no need for xfs_update_prealloc_flags() to do this.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_file.c | 13 +++++++------ fs/xfs/xfs_pnfs.c | 6 ++++-- 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 240eb932c014..752b676c92e3 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -95,8 +95,6 @@ xfs_update_prealloc_flags( ip->i_diflags &= ~XFS_DIFLAG_PREALLOC;

xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - if (flags & XFS_PREALLOC_SYNC) - xfs_trans_set_sync(tp); return xfs_trans_commit(tp); }

@@ -1059,9 +1057,6 @@ xfs_file_fallocate( } }

- if (file->f_flags & O_DSYNC) - flags |= XFS_PREALLOC_SYNC; - error = xfs_update_prealloc_flags(ip, flags); if (error) goto out_unlock; @@ -1084,8 +1079,14 @@ xfs_file_fallocate( * leave shifted extents past EOF and hence losing access to * the data that is contained within them. */ - if (do_file_insert) + if (do_file_insert) { error = xfs_insert_file_space(ip, offset, len); + if (error) + goto out_unlock; + } + + if (file->f_flags & O_DSYNC) + error = xfs_log_force_inode(ip);

out_unlock: xfs_iunlock(ip, iolock); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 8865f7d4404a..3a82a13d880c 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -164,10 +164,12 @@ xfs_fs_map_blocks( * that the blocks allocated and handed out to the client are * guaranteed to be present even after a server crash. */ - error = xfs_update_prealloc_flags(ip, - XFS_PREALLOC_SET | XFS_PREALLOC_SYNC); + error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); + if (!error) + error = xfs_log_force_inode(ip); if (error) goto out_unlock; + } else { xfs_iunlock(ip, lock_flags); }

From: Dave Chinner dchinner@redhat.com

commit 0b02c8c0d75a738c98c35f02efb36217c170d78c upsream.

Now that we only call xfs_update_prealloc_flags() from xfs_file_fallocate() in the case where we need to set the preallocation flag, do this in xfs_alloc_file_space() where we already have the inode joined into a transaction and get rid of the call to xfs_update_prealloc_flags() from the fallocate code.

This also means that we now correctly avoid setting the XFS_DIFLAG_PREALLOC flag when xfs_is_always_cow_inode() is true, as these inodes will never have preallocated extents.

Signed-off-by: Dave Chinner dchinner@redhat.com Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/xfs/xfs_bmap_util.c | 9 +++------ fs/xfs/xfs_file.c | 8 -------- 2 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 73a36b7be3bd..fd2ad6a3019c 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -851,9 +851,6 @@ xfs_alloc_file_space( rblocks = 0; }

- /* - * Allocate and setup the transaction. - */ error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks, rblocks, false, &tp); if (error) @@ -870,9 +867,9 @@ xfs_alloc_file_space( if (error) goto error;

- /* - * Complete the transaction - */ + ip->i_diflags |= XFS_DIFLAG_PREALLOC; + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + error = xfs_trans_commit(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); if (error) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 020e0a412287..8cd0c3df253f 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -909,7 +909,6 @@ xfs_file_fallocate( struct inode *inode = file_inode(file); struct xfs_inode *ip = XFS_I(inode); long error; - enum xfs_prealloc_flags flags = 0; uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL; loff_t new_size = 0; bool do_file_insert = false; @@ -1007,8 +1006,6 @@ xfs_file_fallocate( } do_file_insert = true; } else { - flags |= XFS_PREALLOC_SET; - if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > i_size_read(inode)) { new_size = offset + len; @@ -1059,11 +1056,6 @@ xfs_file_fallocate( if (error) goto out_unlock; } - - error = xfs_update_prealloc_flags(ip, XFS_PREALLOC_SET); - if (error) - goto out_unlock; - }

/* Change file size if needed */

From: Yang Xu xuyang2018.jy@fujitsu.com

commit 1639a49ccdce58ea248841ed9b23babcce6dbb0b upsream.

Move setgid handling out of individual filesystems and into the VFS itself to stop the proliferation of setgid inheritance bugs.

Creating files that have both the S_IXGRP and S_ISGID bit raised in directories that themselves have the S_ISGID bit set requires additional privileges to avoid security issues.

When a filesystem creates a new inode it needs to take care that the caller is either in the group of the newly created inode or they have CAP_FSETID in their current user namespace and are privileged over the parent directory of the new inode. If any of these two conditions is true then the S_ISGID bit can be raised for an S_IXGRP file and if not it needs to be stripped.

However, there are several key issues with the current implementation:

* S_ISGID stripping logic is entangled with umask stripping.

If a filesystem doesn't support or enable POSIX ACLs then umask stripping is done directly in the vfs before calling into the filesystem. If the filesystem does support POSIX ACLs then unmask stripping may be done in the filesystem itself when calling posix_acl_create().

Since umask stripping has an effect on S_ISGID inheritance, e.g., by stripping the S_IXGRP bit from the file to be created and all relevant filesystems have to call posix_acl_create() before inode_init_owner() where we currently take care of S_ISGID handling S_ISGID handling is order dependent. IOW, whether or not you get a setgid bit depends on POSIX ACLs and umask and in what order they are called.

Note that technically filesystems are free to impose their own ordering between posix_acl_create() and inode_init_owner() meaning that there's additional ordering issues that influence S_SIGID inheritance.

* Filesystems that don't rely on inode_init_owner() don't get S_ISGID stripping logic.

While that may be intentional (e.g. network filesystems might just defer setgid stripping to a server) it is often just a security issue.

This is not just ugly it's unsustainably messy especially since we do still have bugs in this area years after the initial round of setgid bugfixes.

So the current state is quite messy and while we won't be able to make it completely clean as posix_acl_create() is still a filesystem specific call we can improve the S_SIGD stripping situation quite a bit by hoisting it out of inode_init_owner() and into the vfs creation operations. This means we alleviate the burden for filesystems to handle S_ISGID stripping correctly and can standardize the ordering between S_ISGID and umask stripping in the vfs.

We add a new helper vfs_prepare_mode() so S_ISGID handling is now done in the VFS before umask handling. This has S_ISGID handling is unaffected unaffected by whether umask stripping is done by the VFS itself (if no POSIX ACLs are supported or enabled) or in the filesystem in posix_acl_create() (if POSIX ACLs are supported).

The vfs_prepare_mode() helper is called directly in vfs_*() helpers that create new filesystem objects. We need to move them into there to make sure that filesystems like overlayfs hat have callchains like:

sys_mknod() -> do_mknodat(mode) -> .mknod = ovl_mknod(mode) -> ovl_create(mode) -> vfs_mknod(mode)

get S_ISGID stripping done when calling into lower filesystems via vfs_*() creation helpers. Moving vfs_prepare_mode() into e.g. vfs_mknod() takes care of that. This is in any case semantically cleaner because S_ISGID stripping is VFS security requirement.

Security hooks so far have seen the mode with the umask applied but without S_ISGID handling done. The relevant hooks are called outside of vfs_*() creation helpers so by calling vfs_prepare_mode() from vfs_*() helpers the security hooks would now see the mode without umask stripping applied. For now we fix this by passing the mode with umask settings applied to not risk any regressions for LSM hooks. IOW, nothing changes for LSM hooks. It is worth pointing out that security hooks never saw the mode that is seen by the filesystem when actually creating the file. They have always been completely misplaced for that to work.

The following filesystems use inode_init_owner() and thus relied on S_ISGID stripping: spufs, 9p, bfs, btrfs, ext2, ext4, f2fs, hfsplus, hugetlbfs, jfs, minix, nilfs2, ntfs3, ocfs2, omfs, overlayfs, ramfs, reiserfs, sysv, ubifs, udf, ufs, xfs, zonefs, bpf, tmpfs.

All of the above filesystems end up calling inode_init_owner() when new filesystem objects are created through the ->mkdir(), ->mknod(), ->create(), ->tmpfile(), ->rename() inode operations.

Since directories always inherit the S_ISGID bit with the exception of xfs when irix_sgid_inherit mode is turned on S_ISGID stripping doesn't apply. The ->symlink() and ->link() inode operations trivially inherit the mode from the target and the ->rename() inode operation inherits the mode from the source inode. All other creation inode operations will get S_ISGID handling via vfs_prepare_mode() when called from their relevant vfs_*() helpers.

In addition to this there are filesystems which allow the creation of filesystem objects through ioctl()s or - in the case of spufs - circumventing the vfs in other ways. If filesystem objects are created through ioctl()s the vfs doesn't know about it and can't apply regular permission checking including S_ISGID logic. Therfore, a filesystem relying on S_ISGID stripping in inode_init_owner() in their ioctl() callpath will be affected by moving this logic into the vfs. We audited those filesystems:

* btrfs allows the creation of filesystem objects through various ioctls(). Snapshot creation literally takes a snapshot and so the mode is fully preserved and S_ISGID stripping doesn't apply.

Creating a new subvolum relies on inode_init_owner() in btrfs_new_subvol_inode() but only creates directories and doesn't raise S_ISGID.

* ocfs2 has a peculiar implementation of reflinks. In contrast to e.g. xfs and btrfs FICLONE/FICLONERANGE ioctl() that is only concerned with the actual extents ocfs2 uses a separate ioctl() that also creates the target file.

Iow, ocfs2 circumvents the vfs entirely here and did indeed rely on inode_init_owner() to strip the S_ISGID bit. This is the only place where a filesystem needs to call mode_strip_sgid() directly but this is self-inflicted pain.

* spufs doesn't go through the vfs at all and doesn't use ioctl()s either. Instead it has a dedicated system call spufs_create() which allows the creation of filesystem objects. But spufs only creates directories and doesn't allo S_SIGID bits, i.e. it specifically only allows 0777 bits.

* bpf uses vfs_mkobj() but also doesn't allow S_ISGID bits to be created.

The patch will have an effect on ext2 when the EXT2_MOUNT_GRPID mount option is used, on ext4 when the EXT4_MOUNT_GRPID mount option is used, and on xfs when the XFS_FEAT_GRPID mount option is used. When any of these filesystems are mounted with their respective GRPID option then newly created files inherit the parent directories group unconditionally. In these cases non of the filesystems call inode_init_owner() and thus did never strip the S_ISGID bit for newly created files. Moving this logic into the VFS means that they now get the S_ISGID bit stripped. This is a user visible change. If this leads to regressions we will either need to figure out a better way or we need to revert. However, given the various setgid bugs that we found just in the last two years this is a regression risk we should take.

Associated with this change is a new set of fstests to enforce the semantics for all new filesystems.

Link: https://lore.kernel.org/ceph-devel/20220427092201.wvsdjbnc7b4dttaw@wittgenst... [1] Link: e014f37db1a2 ("xfs: use setattr_copy to set vfs inode attributes") [2] Link: 01ea173e103e ("xfs: fix up non-directory creation in SGID directories") [3] Link: fd84bfdddd16 ("ceph: fix up non-directory creation in SGID directories") [4] Link: https://lore.kernel.org/r/1657779088-2242-3-git-send-email-xuyang2018.jy@fuj... Suggested-by: Dave Chinner david@fromorbit.com Suggested-by: Christian Brauner (Microsoft) brauner@kernel.org Reviewed-by: Darrick J. Wong djwong@kernel.org Reviewed-and-Tested-by: Jeff Layton jlayton@kernel.org Signed-off-by: Yang Xu xuyang2018.jy@fujitsu.com [brauner@kernel.org: rewrote commit message] Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/inode.c | 2 -- fs/namei.c | 82 ++++++++++++++++++++++++++++++++++++++++-------- fs/ocfs2/namei.c | 1 + 3 files changed, 70 insertions(+), 15 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c index 3740102c9bd5..957b2d18ec29 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2165,8 +2165,6 @@ void inode_init_owner(struct user_namespace *mnt_userns, struct inode *inode, /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; - else - mode = mode_strip_sgid(mnt_userns, dir, mode); } else inode_fsgid_set(inode, mnt_userns); inode->i_mode = mode; diff --git a/fs/namei.c b/fs/namei.c index 81b31d9a063f..02e99606c65b 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3000,6 +3000,65 @@ void unlock_rename(struct dentry *p1, struct dentry *p2) } EXPORT_SYMBOL(unlock_rename);

+/** + * mode_strip_umask - handle vfs umask stripping + * @dir: parent directory of the new inode + * @mode: mode of the new inode to be created in @dir + * + * Umask stripping depends on whether or not the filesystem supports POSIX + * ACLs. If the filesystem doesn't support it umask stripping is done directly + * in here. If the filesystem does support POSIX ACLs umask stripping is + * deferred until the filesystem calls posix_acl_create(). + * + * Returns: mode + */ +static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode) +{ + if (!IS_POSIXACL(dir)) + mode &= ~current_umask(); + return mode; +} + +/** + * vfs_prepare_mode - prepare the mode to be used for a new inode + * @mnt_userns: user namespace of the mount the inode was found from + * @dir: parent directory of the new inode + * @mode: mode of the new inode + * @mask_perms: allowed permission by the vfs + * @type: type of file to be created + * + * This helper consolidates and enforces vfs restrictions on the @mode of a new + * object to be created. + * + * Umask stripping depends on whether the filesystem supports POSIX ACLs (see + * the kernel documentation for mode_strip_umask()). Moving umask stripping + * after setgid stripping allows the same ordering for both non-POSIX ACL and + * POSIX ACL supporting filesystems. + * + * Note that it's currently valid for @type to be 0 if a directory is created. + * Filesystems raise that flag individually and we need to check whether each + * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a + * non-zero type. + * + * Returns: mode to be passed to the filesystem + */ +static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns, + const struct inode *dir, umode_t mode, + umode_t mask_perms, umode_t type) +{ + mode = mode_strip_sgid(mnt_userns, dir, mode); + mode = mode_strip_umask(dir, mode); + + /* + * Apply the vfs mandated allowed permission mask and set the type of + * file to be created before we call into the filesystem. + */ + mode &= (mask_perms & ~S_IFMT); + mode |= (type & S_IFMT); + + return mode; +} + /** * vfs_create - create new file * @mnt_userns: user namespace of the mount the inode was found from @@ -3025,8 +3084,8 @@ int vfs_create(struct user_namespace *mnt_userns, struct inode *dir,

if (!dir->i_op->create) return -EACCES; /* shouldn't it be ENOSYS? */ - mode &= S_IALLUGO; - mode |= S_IFREG; + + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IALLUGO, S_IFREG); error = security_inode_create(dir, dentry, mode); if (error) return error; @@ -3291,8 +3350,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (open_flag & O_CREAT) { if (open_flag & O_EXCL) open_flag &= ~O_TRUNC; - if (!IS_POSIXACL(dir->d_inode)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(mnt_userns, dir->d_inode, mode, mode, mode); if (likely(got_write)) create_error = may_o_create(mnt_userns, &nd->path, dentry, mode); @@ -3525,8 +3583,7 @@ struct dentry *vfs_tmpfile(struct user_namespace *mnt_userns, child = d_alloc(dentry, &slash_name); if (unlikely(!child)) goto out_err; - if (!IS_POSIXACL(dir)) - mode &= ~current_umask(); + mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = dir->i_op->tmpfile(mnt_userns, dir, child, mode); if (error) goto out_err; @@ -3804,6 +3861,7 @@ int vfs_mknod(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mknod) return -EPERM;

+ mode = vfs_prepare_mode(mnt_userns, dir, mode, mode, mode); error = devcgroup_inode_mknod(mode, dev); if (error) return error; @@ -3854,9 +3912,8 @@ static int do_mknodat(int dfd, struct filename *name, umode_t mode, if (IS_ERR(dentry)) goto out1;

- if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mknod(&path, dentry, mode, dev); + error = security_path_mknod(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode), dev); if (error) goto out2;

@@ -3926,7 +3983,7 @@ int vfs_mkdir(struct user_namespace *mnt_userns, struct inode *dir, if (!dir->i_op->mkdir) return -EPERM;

- mode &= (S_IRWXUGO|S_ISVTX); + mode = vfs_prepare_mode(mnt_userns, dir, mode, S_IRWXUGO | S_ISVTX, 0); error = security_inode_mkdir(dir, dentry, mode); if (error) return error; @@ -3954,9 +4011,8 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode) if (IS_ERR(dentry)) goto out_putname;

- if (!IS_POSIXACL(path.dentry->d_inode)) - mode &= ~current_umask(); - error = security_path_mkdir(&path, dentry, mode); + error = security_path_mkdir(&path, dentry, + mode_strip_umask(path.dentry->d_inode, mode)); if (!error) { struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(path.mnt); diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 11807034dd48..5b8237ceb8cc 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -197,6 +197,7 @@ static struct inode *ocfs2_get_init_inode(struct inode *dir, umode_t mode) * callers. */ if (S_ISDIR(mode)) set_nlink(inode, 2); + mode = mode_strip_sgid(&init_user_ns, dir, mode); inode_init_owner(&init_user_ns, inode, dir, mode); status = dquot_initialize(inode); if (status)

From: Christian Brauner brauner@kernel.org

commit e243e3f94c804ecca9a8241b5babe28f35258ef4 upstream.

Move the helper from inode.c to attr.c. This keeps the the core of the set{g,u}id stripping logic in one place when we add follow-up changes. It is the better place anyway, since should_remove_suid() returns ATTR_KILL_S{G,U}ID flags.

Reviewed-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- fs/attr.c | 29 +++++++++++++++++++++++++++++ fs/inode.c | 29 ----------------------------- 2 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c index 686840aa91c8..f045431bab1a 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -20,6 +20,35 @@

#include "internal.h"

+/* + * The logic we want is + * + * if suid or (sgid and xgrp) + * remove privs + */ +int should_remove_suid(struct dentry *dentry) +{ + umode_t mode = d_inode(dentry)->i_mode; + int kill = 0; + + /* suid always must be killed */ + if (unlikely(mode & S_ISUID)) + kill = ATTR_KILL_SUID; + + /* + * sgid without any exec bits is just a mandatory locking mark; leave + * it alone. If some exec bits are set, it's a real sgid; kill it. + */ + if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) + kill |= ATTR_KILL_SGID; + + if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) + return kill; + + return 0; +} +EXPORT_SYMBOL(should_remove_suid); + /** * chown_ok - verify permissions to chown inode * @mnt_userns: user namespace of the mount @inode was found from diff --git a/fs/inode.c b/fs/inode.c index a71fb82279bb..3811269259e1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1864,35 +1864,6 @@ void touch_atime(const struct path *path) } EXPORT_SYMBOL(touch_atime);

-/* - * The logic we want is - * - * if suid or (sgid and xgrp) - * remove privs - */ -int should_remove_suid(struct dentry *dentry) -{ - umode_t mode = d_inode(dentry)->i_mode; - int kill = 0; - - /* suid always must be killed */ - if (unlikely(mode & S_ISUID)) - kill = ATTR_KILL_SUID; - - /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; - - if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) - return kill; - - return 0; -} -EXPORT_SYMBOL(should_remove_suid); - /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed.

From: Christian Brauner brauner@kernel.org

commit ed5a7047d2011cb6b2bf84ceb6680124cc6a7d95 upstream.

[backport to 5.15.y, prior to vfsgid_t]

Currently setgid stripping in file_remove_privs()'s should_remove_suid() helper is inconsistent with other parts of the vfs. Specifically, it only raises ATTR_KILL_SGID if the inode is S_ISGID and S_IXGRP but not if the inode isn't in the caller's groups and the caller isn't privileged over the inode although we require this already in setattr_prepare() and setattr_copy() and so all filesystem implement this requirement implicitly because they have to use setattr_{prepare,copy}() anyway.

But the inconsistency shows up in setgid stripping bugs for overlayfs in xfstests (e.g., generic/673, generic/683, generic/685, generic/686, generic/687). For example, we test whether suid and setgid stripping works correctly when performing various write-like operations as an unprivileged user (fallocate, reflink, write, etc.):

echo "Test 1 - qa_user, non-exec file $verb" setup_testfile chmod a+rws $junk_file commit_and_check "$qa_user" "$verb" 64k 64k

The test basically creates a file with 6666 permissions. While the file has the S_ISUID and S_ISGID bits set it does not have the S_IXGRP set. On a regular filesystem like xfs what will happen is:

sys_fallocate() -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> setattr_copy()

In should_remove_suid() we can see that ATTR_KILL_SUID is raised unconditionally because the file in the test has S_ISUID set.

But we also see that ATTR_KILL_SGID won't be set because while the file is S_ISGID it is not S_IXGRP (see above) which is a condition for ATTR_KILL_SGID being raised.

So by the time we call notify_change() we have attr->ia_valid set to ATTR_KILL_SUID | ATTR_FORCE. Now notify_change() sees that ATTR_KILL_SUID is set and does:

ia_valid = attr->ia_valid |= ATTR_MODE attr->ia_mode = (inode->i_mode & ~S_ISUID);

which means that when we call setattr_copy() later we will definitely update inode->i_mode. Note that attr->ia_mode still contains S_ISGID.

Now we call into the filesystem's ->setattr() inode operation which will end up calling setattr_copy(). Since ATTR_MODE is set we will hit:

if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; vfsgid_t vfsgid = i_gid_into_vfsgid(mnt_userns, inode); if (!vfsgid_in_group_p(vfsgid) && !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; }

and since the caller in the test is neither capable nor in the group of the inode the S_ISGID bit is stripped.

But assume the file isn't suid then ATTR_KILL_SUID won't be raised which has the consequence that neither the setgid nor the suid bits are stripped even though it should be stripped because the inode isn't in the caller's groups and the caller isn't privileged over the inode.

If overlayfs is in the mix things become a bit more complicated and the bug shows up more clearly. When e.g., ovl_setattr() is hit from ovl_fallocate()'s call to file_remove_privs() then ATTR_KILL_SUID and ATTR_KILL_SGID might be raised but because the check in notify_change() is questioning the ATTR_KILL_SGID flag again by requiring S_IXGRP for it to be stripped the S_ISGID bit isn't removed even though it should be stripped:

sys_fallocate() -> vfs_fallocate() -> ovl_fallocate() -> file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = ATTR_FORCE | kill; -> notify_change() -> ovl_setattr() // TAKE ON MOUNTER'S CREDS -> ovl_do_notify_change() -> notify_change() // GIVE UP MOUNTER'S CREDS // TAKE ON MOUNTER'S CREDS -> vfs_fallocate() -> xfs_file_fallocate() -> file_modified() -> __file_remove_privs() -> dentry_needs_remove_privs() -> should_remove_suid() -> __remove_privs() newattrs.ia_valid = attr_force | kill; -> notify_change()

The fix for all of this is to make file_remove_privs()'s should_remove_suid() helper to perform the same checks as we already require in setattr_prepare() and setattr_copy() and have notify_change() not pointlessly requiring S_IXGRP again. It doesn't make any sense in the first place because the caller must calculate the flags via should_remove_suid() anyway which would raise ATTR_KILL_SGID.

While we're at it we move should_remove_suid() from inode.c to attr.c where it belongs with the rest of the iattr helpers. Especially since it returns ATTR_KILL_S{G,U}ID flags. We also rename it to setattr_should_drop_suidgid() to better reflect that it indicates both setuid and setgid bit removal and also that it returns attr flags.

Running xfstests with this doesn't report any regressions. We should really try and use consistent checks.

Reviewed-by: Amir Goldstein amir73il@gmail.com Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Amir Goldstein amir73il@gmail.com Tested-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: Darrick J. Wong djwong@kernel.org --- Documentation/trace/ftrace.rst | 2 +- fs/attr.c | 33 +++++++++++++++++++-------------- fs/fuse/file.c | 2 +- fs/inode.c | 7 ++++--- fs/internal.h | 2 +- fs/ocfs2/file.c | 4 ++-- fs/open.c | 8 ++++---- include/linux/fs.h | 2 +- 8 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index 4e5b26f03d5b..d036946bce7a 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -2929,7 +2929,7 @@ Produces:: bash-1994 [000] .... 4342.324898: ima_get_action <-process_measurement bash-1994 [000] .... 4342.324898: ima_match_policy <-ima_get_action bash-1994 [000] .... 4342.324899: do_truncate <-do_last - bash-1994 [000] .... 4342.324899: should_remove_suid <-do_truncate + bash-1994 [000] .... 4342.324899: setattr_should_drop_suidgid <-do_truncate bash-1994 [000] .... 4342.324899: notify_change <-do_truncate bash-1994 [000] .... 4342.324900: current_fs_time <-notify_change bash-1994 [000] .... 4342.324900: current_kernel_time <-current_fs_time diff --git a/fs/attr.c b/fs/attr.c index 965be68ed8fa..0ca14cbd4b8b 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -48,34 +48,39 @@ int setattr_should_drop_sgid(struct user_namespace *mnt_userns, return 0; }

-/* - * The logic we want is +/** + * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to + * be dropped + * @mnt_userns: user namespace of the mount @inode was found from + * @inode: inode to check * - * if suid or (sgid and xgrp) - * remove privs + * This function determines whether the set{g,u}id bits need to be removed. + * If the setuid bit needs to be removed ATTR_KILL_SUID is returned. If the + * setgid bit needs to be removed ATTR_KILL_SGID is returned. If both + * set{g,u}id bits need to be removed the corresponding mask of both flags is + * returned. + * + * Return: A mask of ATTR_KILL_S{G,U}ID indicating which - if any - setid bits + * to remove, 0 otherwise. */ -int should_remove_suid(struct dentry *dentry) +int setattr_should_drop_suidgid(struct user_namespace *mnt_userns, + struct inode *inode) { - umode_t mode = d_inode(dentry)->i_mode; + umode_t mode = inode->i_mode; int kill = 0;

/* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID;

- /* - * sgid without any exec bits is just a mandatory locking mark; leave - * it alone. If some exec bits are set, it's a real sgid; kill it. - */ - if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) - kill |= ATTR_KILL_SGID; + kill |= setattr_should_drop_sgid(mnt_userns, inode);

if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill;

return 0; } -EXPORT_SYMBOL(should_remove_suid); +EXPORT_SYMBOL(setattr_should_drop_suidgid);

/** * chown_ok - verify permissions to chown inode @@ -440,7 +445,7 @@ int notify_change(struct user_namespace *mnt_userns, struct dentry *dentry, } } if (ia_valid & ATTR_KILL_SGID) { - if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { + if (mode & S_ISGID) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index cc95a1c37644..2b19d281351e 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1295,7 +1295,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from) return err;

if (fc->handle_killpriv_v2 && - should_remove_suid(file_dentry(file))) { + setattr_should_drop_suidgid(&init_user_ns, file_inode(file))) { goto writethrough; }

diff --git a/fs/inode.c b/fs/inode.c index 3811269259e1..079b64f9b756 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1869,7 +1869,8 @@ EXPORT_SYMBOL(touch_atime); * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ -int dentry_needs_remove_privs(struct dentry *dentry) +int dentry_needs_remove_privs(struct user_namespace *mnt_userns, + struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; @@ -1878,7 +1879,7 @@ int dentry_needs_remove_privs(struct dentry *dentry) if (IS_NOSEC(inode)) return 0;

- mask = should_remove_suid(dentry); + mask = setattr_should_drop_suidgid(mnt_userns, inode); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; @@ -1920,7 +1921,7 @@ int file_remove_privs(struct file *file) if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0;

- kill = dentry_needs_remove_privs(dentry); + kill = dentry_needs_remove_privs(file_mnt_user_ns(file), dentry); if (kill < 0) return kill; if (kill) diff --git a/fs/internal.h b/fs/internal.h index 45cf31d7380b..46df4ce58e87 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -149,7 +149,7 @@ extern int vfs_open(const struct path *, struct file *); */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); extern void inode_add_lru(struct inode *inode); -extern int dentry_needs_remove_privs(struct dentry *dentry); +int dentry_needs_remove_privs(struct user_namespace *, struct dentry *dentry); bool in_group_or_capable(struct user_namespace *mnt_userns, const struct inode *inode, kgid_t gid);

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index fc5f780fa235..92182d4be247 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1994,7 +1994,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode, } }

- if (file && should_remove_suid(file->f_path.dentry)) { + if (file && setattr_should_drop_suidgid(&init_user_ns, file_inode(file))) { ret = __ocfs2_write_remove_suid(inode, di_bh); if (ret) { mlog_errno(ret); @@ -2282,7 +2282,7 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * inode. There's also the dinode i_size state which * can be lost via setattr during extending writes (we * set inode->i_size at the end of a write. */ - if (should_remove_suid(dentry)) { + if (setattr_should_drop_suidgid(&init_user_ns, inode)) { if (meta_level == 0) { ocfs2_inode_unlock_for_extent_tree(inode, &di_bh, diff --git a/fs/open.c b/fs/open.c index 5e322f188e83..e93c33069055 100644 --- a/fs/open.c +++ b/fs/open.c @@ -54,7 +54,7 @@ int do_truncate(struct user_namespace *mnt_userns, struct dentry *dentry, }

/* Remove suid, sgid, and file capabilities on truncate too */ - ret = dentry_needs_remove_privs(dentry); + ret = dentry_needs_remove_privs(mnt_userns, dentry); if (ret < 0) return ret; if (ret) @@ -671,10 +671,10 @@ int chown_common(const struct path *path, uid_t user, gid_t group) newattrs.ia_valid |= ATTR_GID; newattrs.ia_gid = gid; } - if (!S_ISDIR(inode->i_mode)) - newattrs.ia_valid |= - ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV; inode_lock(inode); + if (!S_ISDIR(inode->i_mode)) + newattrs.ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV | + setattr_should_drop_sgid(mnt_userns, inode); error = security_path_chown(path, uid, gid); if (!error) error = notify_change(mnt_userns, path->dentry, &newattrs, diff --git a/include/linux/fs.h b/include/linux/fs.h index be9be4a7216c..9601c2d774c8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3133,7 +3133,7 @@ extern void __destroy_inode(struct inode *); extern struct inode *new_inode_pseudo(struct super_block *sb); extern struct inode *new_inode(struct super_block *sb); extern void free_inode_nonrcu(struct inode *inode); -extern int should_remove_suid(struct dentry *); +extern int setattr_should_drop_suidgid(struct user_namespace *, struct inode *); extern int file_remove_privs(struct file *);

extern void __insert_inode_hash(struct inode *, unsigned long hashval);