[PATCH bpf v4 3/3] bpf: return VMA snapshot from task_vma iterator

[Puranjay Mohan <puranjay@kernel.org>]

Holding the per-VMA lock across the BPF program body creates a lock
ordering problem when helpers acquire locks that depend on mmap_lock:

  vm_lock -> i_rwsem -> mmap_lock -> vm_lock

Snapshot the VMA under the per-VMA lock in _next() via memcpy(), then
drop the lock before returning. The BPF program accesses only the
snapshot.

The verifier only trusts vm_mm and vm_file pointers (see
BTF_TYPE_SAFE_TRUSTED_OR_NULL in verifier.c). vm_file is reference-
counted with get_file() under the lock and released via fput() on the
next iteration or in _destroy(). vm_mm is already correct because
lock_vma_under_rcu() verifies vma->vm_mm == mm. All other pointers
are left as-is by memcpy() since the verifier treats them as untrusted.

Fixes: 4ac454682158 ("bpf: Introduce task_vma open-coded iterator kfuncs")
Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
---
 kernel/bpf/task_iter.c | 42 ++++++++++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 12 deletions(-)

diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index ddaf1cf0ecae..5795c5ba2a71 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -799,7 +799,7 @@ const struct bpf_func_proto bpf_find_vma_proto = {
 struct bpf_iter_task_vma_kern_data {
 	struct task_struct *task;
 	struct mm_struct *mm;
-	struct vm_area_struct *locked_vma;
+	struct vm_area_struct snapshot;
 	u64 next_addr;
 };
 
@@ -833,7 +833,7 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 
 	/*
 	 * Reject irqs-disabled contexts including NMI. Operations used
-	 * by _next() and _destroy() (vma_end_read, mmput_async)
+	 * by _next() and _destroy() (vma_end_read, fput, mmput_async)
 	 * can take spinlocks with IRQs disabled (pi_lock, pool->lock).
 	 * Running from NMI or from a tracepoint that fires with those
 	 * locks held could deadlock.
@@ -863,7 +863,7 @@ __bpf_kfunc int bpf_iter_task_vma_new(struct bpf_iter_task_vma *it,
 		goto err_cleanup_iter;
 	}
 
-	kit->data->locked_vma = NULL;
+	kit->data->snapshot.vm_file = NULL;
 	kit->data->next_addr = addr;
 	return 0;
 
@@ -925,26 +925,45 @@ bpf_iter_task_vma_find_next(struct bpf_iter_task_vma_kern_data *data)
 	return vma;
 }
 
+static void bpf_iter_task_vma_snapshot_reset(struct vm_area_struct *snap)
+{
+	if (snap->vm_file) {
+		fput(snap->vm_file);
+		snap->vm_file = NULL;
+	}
+}
+
 __bpf_kfunc struct vm_area_struct *bpf_iter_task_vma_next(struct bpf_iter_task_vma *it)
 {
 	struct bpf_iter_task_vma_kern *kit = (void *)it;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *snap, *vma;
 
 	if (!kit->data) /* bpf_iter_task_vma_new failed */
 		return NULL;
 
-	if (kit->data->locked_vma) {
-		vma_end_read(kit->data->locked_vma);
-		kit->data->locked_vma = NULL;
-	}
+	snap = &kit->data->snapshot;
+
+	bpf_iter_task_vma_snapshot_reset(snap);
 
 	vma = bpf_iter_task_vma_find_next(kit->data);
 	if (!vma)
 		return NULL;
 
-	kit->data->locked_vma = vma;
+	memcpy(snap, vma, sizeof(*snap));
+
+	/*
+	 * The verifier only trusts vm_mm and vm_file (see
+	 * BTF_TYPE_SAFE_TRUSTED_OR_NULL in verifier.c). Take a reference
+	 * on vm_file; vm_mm is already correct because lock_vma_under_rcu()
+	 * verifies vma->vm_mm == mm. All other pointers are untrusted by
+	 * the verifier and left as-is.
+	 */
+	if (snap->vm_file)
+		get_file(snap->vm_file);
+
 	kit->data->next_addr = vma->vm_end;
-	return vma;
+	vma_end_read(vma);
+	return snap;
 }
 
 __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
@@ -952,8 +971,7 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it)
 	struct bpf_iter_task_vma_kern *kit = (void *)it;
 
 	if (kit->data) {
-		if (kit->data->locked_vma)
-			vma_end_read(kit->data->locked_vma);
+		bpf_iter_task_vma_snapshot_reset(&kit->data->snapshot);
 		put_task_struct(kit->data->task);
 		mmput_async(kit->data->mm);
 		bpf_mem_free(&bpf_global_ma, kit->data);
-- 
2.52.0