bpf_find_vma() reads task->mm and calls mmap_read_trylock(mm) without
holding a reference on the mm. On a foreign task, a concurrent exit_mm()
can free the mm_struct between the lockless read and the trylock,
resulting in a use-after-free. mm_struct is not SLAB_TYPESAFE_BY_RCU.

For the current task, task->mm is stable. For a foreign task, pin the mm
under task->alloc_lock and release it with mmput_async(), mirroring commit
d8e27d2d22b6 ("bpf: fix mm lifecycle in open-coded task_vma iterator").
Use spin_trylock() instead of get_task_mm() so BPF context does not block
on alloc_lock. Reject irqs-disabled contexts and !CONFIG_MMU on the
foreign-task path because dropping the mm reference is not safe there.

Race:

  CPU0 (BPF program)                  CPU1 (exiting task)
  ============================        ==========================
  bpf_find_vma(foreign_task):
    mm = task->mm
                                      exit_mm():
                                        task->mm = NULL
                                        mmput(mm) -> frees mm_struct
    mmap_read_trylock(mm)
	// UAF on mm

Fixes: 7c7e3d31e785 ("bpf: Introduce helper bpf_find_vma")
Signed-off-by: Sanghyun Park <sanghyun.park.cnu@gmail.com>
---
v4:
 - Use [PATCH bpf-next] subject as requested by Alexei.
 - Add the missing BPF maintainers/reviewers to Cc.
v3: https://lore.kernel.org/bpf/20260609105216.3536839-1-sanghyun.park.cnu@gmail.com/
 - Drop get_task_mm()+mmput(); mirror d8e27d2d22b6 with alloc_lock
   trylock + mmput_async(). (Yonghong Song)
 - Reject irqs-disabled contexts on the foreign-task path.
 - Reject foreign-task path when !CONFIG_MMU: bpf_iter_mmput_async()
   falls back to mmput() which may sleep, and bpf_find_vma() can run
   in non-sleepable context.
 - Shorten the foreign-task rationale comment and trim the changelog body.
 - Fix the v2's whitespace damage.
v2: https://lore.kernel.org/bpf/CAOrxSK5_7e4114VyfEU9htGi+UneuNt88fGVKOAa3_ZenPOFkA@mail.gmail.com/

 kernel/bpf/task_iter.c | 50 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index fc5f463ca5..baee813290 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -754,12 +754,22 @@ static struct bpf_iter_reg task_vma_reg_info = {
 	.show_fdinfo		= bpf_iter_task_show_fdinfo,
 };
 
+static inline void bpf_iter_mmput_async(struct mm_struct *mm)
+{
+#ifdef CONFIG_MMU
+	mmput_async(mm);
+#else
+	mmput(mm);
+#endif
+}
+
 BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
 	   bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags)
 {
 	struct mmap_unlock_irq_work *work = NULL;
 	struct vm_area_struct *vma;
 	bool irq_work_busy = false;
+	bool mmput_needed = false;
 	struct mm_struct *mm;
 	int ret = -ENOENT;
 
@@ -769,14 +779,38 @@ BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
 	if (!task)
 		return -ENOENT;
 
-	mm = task->mm;
+	if (task == current) {
+		mm = task->mm;
+	} else {
+		/*
+		 * Foreign task: pin task->mm against a concurrent exit_mm().
+		 * Use trylock on alloc_lock instead of get_task_mm()'s
+		 * blocking task_lock() to avoid deadlocking the target task.
+		 */
+		if (!IS_ENABLED(CONFIG_MMU))
+			return -EOPNOTSUPP;
+		if (irqs_disabled())
+			return -EBUSY;
+		if (!spin_trylock(&task->alloc_lock))
+			return -EBUSY;
+		mm = task->mm;
+		if (mm && !(task->flags & PF_KTHREAD)) {
+			mmget(mm);
+			mmput_needed = true;
+		} else {
+			mm = NULL;
+		}
+		spin_unlock(&task->alloc_lock);
+	}
 	if (!mm)
 		return -ENOENT;
 
 	irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
 
-	if (irq_work_busy || !mmap_read_trylock(mm))
-		return -EBUSY;
+	if (irq_work_busy || !mmap_read_trylock(mm)) {
+		ret = -EBUSY;
+		goto out;
+	}
 
 	vma = find_vma(mm, start);
 
@@ -786,6 +820,9 @@ BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
 		ret = 0;
 	}
 	bpf_mmap_unlock_mm(work, mm);
+out:
+	if (mmput_needed)
+		bpf_iter_mmput_async(mm);
 	return ret;
 }
 
@@ -800,15 +837,6 @@ const struct bpf_func_proto bpf_find_vma_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
-static inline void bpf_iter_mmput_async(struct mm_struct *mm)
-{
-#ifdef CONFIG_MMU
-	mmput_async(mm);
-#else
-	mmput(mm);
-#endif
-}
-
 struct bpf_iter_task_vma_kern_data {
 	struct task_struct *task;
 	struct mm_struct *mm;
-- 
2.48.1

> diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
> index e791ae065c39..77f90b887bf1 100644
> --- a/kernel/bpf/task_iter.c
> +++ b/kernel/bpf/task_iter.c

[ ... ]

> @@ -765,14 +775,38 @@ BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
>  	if (!task)
>  		return -ENOENT;
>
> -	mm = task->mm;
> +	if (task == current) {
> +		mm = task->mm;
> +	} else {
> +		/*
> +		 * Foreign task: pin task->mm against a concurrent exit_mm().
> +		 * Use trylock on alloc_lock instead of get_task_mm()'s
> +		 * blocking task_lock() to avoid deadlocking the target task.
> +		 */
> +		if (!IS_ENABLED(CONFIG_MMU))
> +			return -EOPNOTSUPP;
> +		if (irqs_disabled())
> +			return -EBUSY;
> +		if (!spin_trylock(&task->alloc_lock))
> +			return -EBUSY;
> +		mm = task->mm;
> +		if (mm && !(task->flags & PF_KTHREAD)) {
> +			mmget(mm);
> +			mmput_needed = true;
> +		} else {
> +			mm = NULL;
> +		}
> +		spin_unlock(&task->alloc_lock);
> +	}
>  	if (!mm)
>  		return -ENOENT;
>
>  	irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
>
> -	if (irq_work_busy || !mmap_read_trylock(mm))
> -		return -EBUSY;
> +	if (irq_work_busy || !mmap_read_trylock(mm)) {
> +		ret = -EBUSY;
> +		goto out;
> +	}
>
>  	vma = find_vma(mm, start);
                         ^^^^^^^^

sashiko-bot@kernel.org raised a concern about this in v4: bpf_find_vma()
traverses the VMA tree of an external mm_struct (from a foreign task) without
checking check_stable_address_space(mm).

When inspecting a foreign task, the mm_struct could be flagged with
MMF_UNSTABLE if it was subject to an OOM reap or a dup_mmap() failure. In this
state, the maple tree can contain XA_ZERO_ENTRY markers.

If find_vma() returns one of these markers, could the subsequent check using
vma->vm_start dereference an internal integer value and cause a kernel panic?

>
> @@ -782,6 +816,9 @@ BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
>  		ret = 0;
>  	}
>  	bpf_mmap_unlock_mm(work, mm);
> +out:
> +	if (mmput_needed)
> +		bpf_iter_mmput_async(mm);
>  	return ret;
>  }


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/27250036662

This looks like a separate pre-existing issue. This patch only fixes the
mm_struct lifetime/UAF bug by pinning the foreign task's mm before using it.

I can look into check_stable_address_space(mm) as a separate follow-up if
maintainers think it is needed here.

Thanks,
Sanghyun