Re: [PATCH v3] sched/mmcid: Synchronize MM teardown with affinity updates

[Mathieu Desnoyers <mathieu.desnoyers@efficios.com>]

+CC tglx.

On 2026-11-10 13:38, Weiming Shi wrote:
> set_cpus_allowed_common() passes a remote task's p->mm to
> mm_update_cpus_allowed() while holding p->pi_lock, but that lock did not
> stabilize the pointer against MM replacement. A same-owner
> sched_setaffinity() caller can therefore retain the old pointer while exec
> replaces and frees it. On architectures which shoot down rather than
> refcount lazy TLB MMs, exit_mm() and kthread_unuse_mm() have the same
> lifetime gap.
> 
>    BUG: KASAN: slab-use-after-free in set_cpus_allowed_common
>    Read of size 4 at addr ffff888123155e4c by task poc/5132
>    Call Trace:
>     set_cpus_allowed_common (kernel/sched/core.c:10835)
>     set_cpus_allowed_fair (kernel/sched/fair.c:10046)
>     __set_cpus_allowed_ptr_locked (kernel/sched/core.c:3224)
>     __set_cpus_allowed_ptr (kernel/sched/core.c:3258)
>     __sched_setaffinity (kernel/sched/syscalls.c:1161)
>     sched_setaffinity (kernel/sched/syscalls.c:1239)
>     __x64_sys_sched_setaffinity (kernel/sched/syscalls.c:1275)
>     do_syscall_64 (arch/x86/entry/syscall_64.c:84)
>     entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121)
> 
>    Freed by task 5127:
>     kmem_cache_free (mm/slub.c:6757)
>     __mmput (kernel/fork.c:1204)
>     mmput (kernel/fork.c:1215)
>     setup_new_exec (fs/exec.c:1395)
>     load_elf_binary (fs/binfmt_elf.c:1024)
>     bprm_execve (fs/exec.c:1865)
>     do_execveat_common.isra.0 (fs/exec.c:1963)
>     __x64_sys_execveat (fs/exec.c:2047)
>     do_syscall_64 (arch/x86/entry/syscall_64.c:84)
>     entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121)
> 
>    Kernel panic - not syncing: KASAN: panic_on_warn set ...
> 
> Affinity paths hold p->pi_lock across the p->mm load and its complete use.
> After publishing a replacement or NULL p->mm, take and release that same
> lock before dropping the old MM reference. For an updater that is already
> using the old pointer, the ordering is:
> 
>    affinity updater                     MM teardown
>    ----------------                     -----------
>    raw_spin_lock(&p->pi_lock)
>    mm = p->mm            /* old_mm */
>                                         p->mm = new_mm or NULL
>                                         raw_spin_lock(&p->pi_lock)
>                                           /* waits */
>    mm_update_cpus_allowed(mm, mask)
>    raw_spin_unlock(&p->pi_lock) /* release */
>                                           /* acquire succeeds */
>                                         raw_spin_unlock(&p->pi_lock)
>                                         ...
>                                         mmput/mmdrop(old_mm)
> 
> The teardown-side acquire cannot complete until an updater ordered before
> it has released p->pi_lock, so old_mm remains alive throughout that
> updater's access. If teardown is ordered first instead, its unlock is a
> release that orders the preceding p->mm store before a later updater's lock
> acquire. The later updater therefore observes new_mm or NULL. An updater
> that acquired the lock before the store but has not loaded p->mm yet is
> still ordered before the teardown-side acquisition; it may observe either
> pointer, but teardown waits for its complete use before dropping old_mm.
> 
> All runtime callers of set_cpus_allowed_common() hold p->pi_lock across
> this access. The runqueue lock is not part of the p->mm lifetime ordering,
> so the grace period only needs p->pi_lock. Place it after publication and
> before the old reference drop in exec_mmap(), exit_mm(), and
> kthread_unuse_mm(). The last two paths matter on architectures which shoot
> down rather than refcount lazy TLB MMs.
> 
> This change was developed with assistance from an LLM.
> 
> Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
> Cc: stable@vger.kernel.org
> Reported-by: <co+cab19e2ebe4d535a@bugs.sh>
> Signed-off-by: Weiming Shi <bestswngs@gmail.com>
> ---
> Changes in v3:
> - Document the p->pi_lock grace period and acquire/release ordering.
> - Use p->pi_lock directly and cover exit_mm() and kthread_unuse_mm().
> - Refresh the KASAN trace and provide a standalone reproducer in reply.
> 
> Changes in v2:
> - Replace the schedule-in deferral with an exec-side runqueue-lock barrier.
> - Keep affinity expansions synchronous, including expansions narrowed before
>    the next schedule-in.
> - Avoid changes to the MM-CID fork, exit, and scheduling state machine.
> 
>   fs/exec.c             | 1 +
>   include/linux/sched.h | 2 ++
>   kernel/exit.c         | 1 +
>   kernel/kthread.c      | 1 +
>   kernel/sched/core.c   | 9 +++++++++
>   5 files changed, 14 insertions(+)
> 
> diff --git a/fs/exec.c b/fs/exec.c
> index 8d2b14e1d455..3196421cb81d 100644
> --- a/fs/exec.c
> +++ b/fs/exec.c
> @@ -905,6 +905,7 @@ static int exec_mmap(struct linux_binprm *bprm)
>   		BUG_ON(active_mm != old_mm);
>   		/* Defer teardown to setup_new_exec(), outside the exec locks. */
>   		bprm->old_mm = old_mm;
> +		sched_mm_cid_mm_barrier(tsk);
>   	} else {
>   		mmdrop_lazy_tlb(active_mm);
>   	}
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 1c93da75226e..f88ab0445be3 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -2358,6 +2358,7 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
>   #ifdef CONFIG_SCHED_MM_CID
>   void sched_mm_cid_before_execve(struct task_struct *t);
>   void sched_mm_cid_after_execve(struct task_struct *t);
> +void sched_mm_cid_mm_barrier(struct task_struct *t);
>   void sched_mm_cid_exit(struct task_struct *t);
>   static __always_inline int task_mm_cid(struct task_struct *t)
>   {
> @@ -2366,6 +2367,7 @@ static __always_inline int task_mm_cid(struct task_struct *t)
>   #else
>   static inline void sched_mm_cid_before_execve(struct task_struct *t) { }
>   static inline void sched_mm_cid_after_execve(struct task_struct *t) { }
> +static inline void sched_mm_cid_mm_barrier(struct task_struct *t) { }
>   static inline void sched_mm_cid_exit(struct task_struct *t) { }
>   static __always_inline int task_mm_cid(struct task_struct *t)
>   {
> diff --git a/kernel/exit.c b/kernel/exit.c
> index d5e7bc2af804..5f9979d6216c 100644
> --- a/kernel/exit.c
> +++ b/kernel/exit.c
> @@ -582,6 +582,7 @@ static void exit_mm(void)
>   	local_irq_enable();
>   	task_unlock(current);
>   	mmap_read_unlock(mm);
> +	sched_mm_cid_mm_barrier(current);
>   	mm_update_next_owner(mm);
>   	mmput(mm);
>   	if (test_thread_flag(TIF_MEMDIE))
> diff --git a/kernel/kthread.c b/kernel/kthread.c
> index fdb8fb07f40b..e7b393cfdcee 100644
> --- a/kernel/kthread.c
> +++ b/kernel/kthread.c
> @@ -1682,6 +1682,7 @@ void kthread_unuse_mm(struct mm_struct *mm)
>   	enter_lazy_tlb(mm, tsk);
>   	local_irq_enable();
>   	task_unlock(tsk);
> +	sched_mm_cid_mm_barrier(tsk);
>   
>   	mmdrop(mm);
>   }
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 04b62c16fa8c..d78a174b5405 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -11128,6 +11128,15 @@ void sched_mm_cid_after_execve(struct task_struct *t)
>   		sched_mm_cid_fork(t);
>   }
>   
> +/*
> + * Pair with set_cpus_allowed_common()'s p->pi_lock critical section. Call
> + * after publishing p->mm and before dropping the old MM reference.
> + */
> +void sched_mm_cid_mm_barrier(struct task_struct *t)
> +{
> +	guard(raw_spinlock_irq)(&t->pi_lock);
> +}
> +
>   static void mm_cid_work_fn(struct work_struct *work)
>   {
>   	struct mm_struct *mm = container_of(work, struct mm_struct, mm_cid.work);


-- 
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com