From: Tejun Heo <tj@xxxxxxxxxx> commit e57457641613fef0d147ede8bd6a3047df588b95 upstream. cgroup process migration permission checks are performed at write time as whether a given operation is allowed or not is dependent on the content of the write - the PID. This currently uses current's cgroup namespace which is a potential security weakness as it may allow scenarios where a less privileged process tricks a more privileged one into writing into a fd that it created. This patch makes cgroup remember the cgroup namespace at the time of open and uses it for migration permission checks instad of current's. Note that this only applies to cgroup2 as cgroup1 doesn't have namespace support. This also fixes a use-after-free bug on cgroupns reported in https://lore.kernel.org/r/00000000000048c15c05d0083397@xxxxxxxxxx Note that backporting this fix also requires the preceding patch. Reported-by: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx> Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxx> Cc: Michal Koutný <mkoutny@xxxxxxxx> Cc: Oleg Nesterov <oleg@xxxxxxxxxx> Reviewed-by: Michal Koutný <mkoutny@xxxxxxxx> Reported-by: syzbot+50f5cf33a284ce738b62@xxxxxxxxxxxxxxxxxxxxxxxxx Link: https://lore.kernel.org/r/00000000000048c15c05d0083397@xxxxxxxxxx Fixes: 5136f6365ce3 ("cgroup: implement "nsdelegate" mount option") Signed-off-by: Tejun Heo <tj@xxxxxxxxxx> [mkoutny: v5.10: duplicate ns check in procs/threads write handler, adjust context] Signed-off-by: Michal Koutný <mkoutny@xxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> [OP: backport to v4.14: drop changes to cgroup_attach_permissions() and cgroup_css_set_fork(), adjust cgroup_procs_write_permission() calls] Signed-off-by: Ovidiu Panait <ovidiu.panait@xxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- kernel/cgroup/cgroup-internal.h | 2 ++ kernel/cgroup/cgroup.c | 24 +++++++++++++++++------- 2 files changed, 19 insertions(+), 7 deletions(-) --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -11,6 +11,8 @@ struct cgroup_pidlist; struct cgroup_file_ctx { + struct cgroup_namespace *ns; + struct { void *trigger; } psi; --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3370,14 +3370,19 @@ static int cgroup_file_open(struct kernf ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; + + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); - if (ret) + if (ret) { + put_cgroup_ns(ctx->ns); kfree(ctx); + } return ret; } @@ -3388,13 +3393,14 @@ static void cgroup_file_release(struct k if (cft->release) cft->release(of); + put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of->kn->priv; struct cgroup_subsys_state *css; @@ -3408,7 +3414,7 @@ static ssize_t cgroup_file_write(struct */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && - ns != &init_cgroup_ns && ns->root_cset->dfl_cgrp == cgrp) + ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) @@ -4351,9 +4357,9 @@ static int cgroup_procs_show(struct seq_ static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, - struct super_block *sb) + struct super_block *sb, + struct cgroup_namespace *ns) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup *com_cgrp = src_cgrp; struct inode *inode; int ret; @@ -4389,6 +4395,7 @@ static int cgroup_procs_write_permission static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; @@ -4415,7 +4422,8 @@ static ssize_t cgroup_procs_write(struct */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + of->file->f_path.dentry->d_sb, + ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; @@ -4438,6 +4446,7 @@ static void *cgroup_threads_start(struct static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { + struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; @@ -4466,7 +4475,8 @@ static ssize_t cgroup_threads_write(stru */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, - of->file->f_path.dentry->d_sb); + of->file->f_path.dentry->d_sb, + ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish;
