[PATCH v2] sched/mmcid: Synchronize exec MM teardown with affinity updates

[Weiming Shi]

set_cpus_allowed_common() passes a remote task's p->mm to
mm_update_cpus_allowed(), but the scheduler locks do not stabilize that
pointer against exec. A same-owner sched_setaffinity() can race the target
replacing and freeing its old mm. Current kernels are only incidentally
serialized by futex_exec_done() taking p->pi_lock when CONFIG_FUTEX=y;
valid CONFIG_FUTEX=n builds remain vulnerable.

  BUG: KASAN: slab-use-after-free in set_cpus_allowed_common (kernel/sched/core.c:10835 kernel/sched/core.c:2829)
  Read of size 4 at addr ffff88810991b04c by task poc/5127
  Call Trace:
   set_cpus_allowed_common (kernel/sched/core.c:10835 kernel/sched/core.c:2829)
   set_cpus_allowed_fair (kernel/sched/fair.c:10046)
   __set_cpus_allowed_ptr_locked (kernel/sched/core.c:2842 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 5128:
   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_execve (fs/exec.c:2036)
   do_syscall_64 (arch/x86/entry/syscall_64.c:84)
   entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:121)

After exec publishes the new p->mm, acquire and release the task's runqueue
lock before the old mm can be dropped. Affinity updates already hold that
lock across set_cpus_allowed_common(), so the barrier waits for any update
that loaded the old mm. Updates that start afterwards observe the new mm.

This keeps allowed-mask updates synchronous, including transient affinity
expansions, without changing the MM-CID fork, exit, or scheduling paths.

This change was developed with assistance from an LLM.

Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: <co+cab19e2ebe4d535a@xxxxxxx>
Signed-off-by: Weiming Shi <bestswngs@xxxxxxxxx>
---
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/sched/core.c   | 6 ++++++
 3 files changed, 9 insertions(+)

diff --git a/fs/exec.c b/fs/exec.c
index 8d2b14e1d455..2e1cac6a3de7 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_exec_mmap(tsk);
 	} else {
 		mmdrop_lazy_tlb(active_mm);
 	}
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1c93da75226e..9b3d4d609273 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_exec_mmap(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_exec_mmap(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/sched/core.c b/kernel/sched/core.c
index 04b62c16fa8c..c9fc8c1cd46f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11128,6 +11128,12 @@ void sched_mm_cid_after_execve(struct task_struct *t)
 		sched_mm_cid_fork(t);
 }
 
+/* Wait for affinity updates that may still be using the old MM. */
+void sched_mm_cid_exec_mmap(struct task_struct *t)
+{
+	guard(task_rq_lock)(t);
+}
+
 static void mm_cid_work_fn(struct work_struct *work)
 {
 	struct mm_struct *mm = container_of(work, struct mm_struct, mm_cid.work);
-- 
2.56.0