Re: [RFC PATCH] security: Allow dropping bounding set process-wide

[Serge E. Hallyn]

On Tue, Sep 22, 2026 at 05:58:16PM +0800, Jinjie Ruan wrote:
> The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
> the calling thread, since its bounding set lives in the per-task struct
> cred.  User space that wants to drop capabilities for a whole process
> must therefore invoke PR_CAPBSET_DROP once per capability per thread,
> which on a many-threaded process is expensive, and from a Go runtime
> requires stopping the world and signalling every thread.
> 
> Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
> capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
> (high 32 bits), from the bounding set of every thread of the calling
> thread group in a single call.
> 
> The calling thread drops the capabilities synchronously, last; every
> sibling that still holds any of them is asked to drop them through a
> task_work item, so that it applies the drop in its own context.  This
> avoids racing with a sibling's concurrent credential updates such as
> setuid() or capset().  The call does not wait for the siblings: a
> sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
> (e.g. futex), so waiting could block for an unbounded time.  This is
> still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
> mode, so a sibling applies the drop before executing any further
> userspace code.  It does not synchronize against a sibling that is
> concurrently creating threads, so callers must keep the thread group
> quiescent while dropping.
> 
> Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
> guest (medians over repeated boots):
>   - 8 vCPUs:  ~1.6ms  -> ~0.10ms
>   - 32 vCPUs: ~3.5ms  -> ~0.11ms
>   - 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
>   - cost goes from O(capabilities * threads) stop-the-world prctls to a
>     single thread-group walk.

That is impressive, but please do detail the specific use case where
you need to drop from the bounding set after the go scheduler has started.
I can imagine some cases where you need to do some early setup and then
want to drop privileges, but you could also do that by re-exec'ing, so
I'd like to hear specifics.

This makes me nervous, reminding me of the 'sendmail capabilities bug'.
If some program specifically locks down one thread, I could imagine the
locked down thread forcing wrong behavior from the privileged threads
by calling this.

> 
> Cc: Serge Hallyn <serge@xxxxxxxxxx>
> Cc: Paul Moore <paul@xxxxxxxxxxxxxx>
> Cc: James Morris <jmorris@xxxxxxxxx>
> Cc: Paul Walmsley <pjw@xxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxx>
> Cc: Zong Li <zong.li@xxxxxxxxxx>
> Cc: Deepak Gupta <debug@xxxxxxxxxxxx>
> Cc: "Peter Zijlstra (Intel)" <peterz@xxxxxxxxxxxxx>
> Signed-off-by: Jinjie Ruan <ruanjinjie@xxxxxxxxxx>
> ---
>  include/uapi/linux/prctl.h |   1 +
>  security/commoncap.c       | 129 +++++++++++++++++++++++++++++++++++++
>  2 files changed, 130 insertions(+)
> 
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index b6ec6f693719..750a7824d3bc 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/include/uapi/linux/prctl.h
> @@ -70,6 +70,7 @@
>  /* Get/set the capability bounding set (as per security/commoncap.c) */
>  #define PR_CAPBSET_READ 23
>  #define PR_CAPBSET_DROP 24
> +#define PR_CAPBSET_DROP_MASK 83
>  
>  /* Get/set the process' ability to use the timestamp counter instruction */
>  #define PR_GET_TSC 25
> diff --git a/security/commoncap.c b/security/commoncap.c
> index 3399535808fe..ae7ce50a8151 100644
> --- a/security/commoncap.c
> +++ b/security/commoncap.c
> @@ -19,7 +19,14 @@
>  #include <linux/hugetlb.h>
>  #include <linux/mount.h>
>  #include <linux/sched.h>
> +#include <linux/cred.h>
> +#include <linux/rcupdate.h>
> +#include <linux/sched/signal.h>
> +#include <linux/sched/task.h>
> +#include <linux/slab.h>
> +#include <linux/task_work.h>
>  #include <linux/prctl.h>
> +#include <linux/printk.h>
>  #include <linux/securebits.h>
>  #include <linux/user_namespace.h>
>  #include <linux/binfmts.h>
> @@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
>  	return commit_creds(new);
>  }
>  
> +/*
> + * Structure used to queue process-wide bounding set drops via task_work.
> + */
> +struct cap_bset_drop_work {
> +	struct callback_head work;
> +	struct task_struct *task;
> +	kernel_cap_t mask;
> +	struct cap_bset_drop_work *next;
> +};
> +
> +static void cap_bset_drop_work_fn(struct callback_head *work)
> +{
> +	struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
> +	struct cred *new = prepare_creds();
> +
> +	if (!new) {
> +		/* Out of memory: bounding set drop failed silently for this thread. */
> +		pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
> +				    task_pid_nr(current), current->comm);
> +		goto out;
> +	}
> +
> +	new->cap_bset = cap_drop(new->cap_bset, w->mask);
> +	commit_creds(new);
> +
> +out:
> +	put_task_struct(w->task);
> +	kfree(w);
> +}
> +
> +/*
> + * cap_bset_drop_process - Drop capabilities from all threads in the group.
> + * @mask: Mask of capabilities to drop from the bounding set.
> + *
> + * Drops @mask from the calling thread synchronously, and queues a task_work
> + * item for each sibling thread to safely apply the drop in its own context.
> + *
> + * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
> + * racing with concurrent thread creation.
> + *
> + * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
> + */
> +static int cap_bset_drop_process(kernel_cap_t mask)
> +{
> +	struct cap_bset_drop_work *list = NULL, *w, *next;
> +	struct task_struct *thread;
> +	struct cred *new = NULL;
> +	int ret = 0;
> +
> +	rcu_read_lock();
> +	for_each_thread(current, thread) {
> +		const struct cred *cred;
> +
> +		if (thread == current || (thread->flags & PF_EXITING))
> +			continue;
> +
> +		cred = __task_cred(thread);
> +		if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
> +			continue;
> +
> +		w = kmalloc_obj(*w, GFP_ATOMIC);
> +		if (!w) {
> +			ret = -ENOMEM;
> +			break;
> +		}
> +
> +		w->task = get_task_struct(thread);
> +		w->mask = mask;
> +		w->next = list;
> +		list = w;
> +	}
> +	rcu_read_unlock();
> +
> +	if (!ret) {
> +		new = prepare_creds();
> +		if (!new)
> +			ret = -ENOMEM;
> +	}
> +
> +	if (ret) {
> +		while (list) {
> +			next = list->next;
> +			put_task_struct(list->task);
> +			kfree(list);
> +			list = next;
> +		}
> +		return ret;
> +	}
> +
> +	for (w = list; w; w = next) {
> +		next = w->next;
> +		init_task_work(&w->work, cap_bset_drop_work_fn);
> +		if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
> +			put_task_struct(w->task);
> +			kfree(w);
> +		}
> +	}
> +
> +	new->cap_bset = cap_drop(new->cap_bset, mask);
> +	commit_creds(new);
> +
> +	return 0;
> +}
> +
> +static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
> +{
> +	kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
> +
> +	if (cap_isclear(mask))
> +		return 0;
> +
> +	if (!ns_capable(current_user_ns(), CAP_SETPCAP))
> +		return -EPERM;
> +
> +	return cap_bset_drop_process(mask);
> +}
> +
>  /**
>   * cap_task_prctl - Implement process control functions for this security module
>   * @option: The process control function requested
> @@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
>  	case PR_CAPBSET_DROP:
>  		return cap_prctl_drop(arg2);
>  
> +	case PR_CAPBSET_DROP_MASK:
> +		if (arg4 || arg5)
> +			return -EINVAL;
> +		return cap_prctl_drop_mask(arg2, arg3);
> +
>  	/*
>  	 * The next four prctl's remain to assist with transitioning a
>  	 * system from legacy UID=0 based privilege (when filesystem
> -- 
> 2.34.1