[PATCH bpf 1/2] bpf: Fix use-after-free of arena VMA on fork

[Weiming Shi <bestswngs@gmail.com>]

arena_vm_open() only increments a refcount on the shared vma_list entry
but never registers the new VMA or updates the stored vma pointer. When
the original VMA is unmapped while a forked/split copy still exists,
arena_vm_close() drops the refcount without freeing the vma_list entry.
The entry's vma pointer now refers to a freed vm_area_struct. A
subsequent bpf_arena_free_pages() call iterates vma_list and passes
the dangling pointer to zap_page_range_single(), causing a
use-after-free.

The bug is reachable by any process with CAP_BPF and CAP_PERFMON that
can create a BPF_MAP_TYPE_ARENA, mmap it, and fork. It triggers
deterministically -- no race condition is involved.

 BUG: KASAN: slab-use-after-free in zap_page_range_single (mm/memory.c:2234)
 Call Trace:
  <TASK>
  zap_page_range_single+0x101/0x110   mm/memory.c:2234
  zap_pages+0x80/0xf0                 kernel/bpf/arena.c:658
  arena_free_pages+0x67a/0x860        kernel/bpf/arena.c:712
  bpf_prog_test_run_syscall+0x3da     net/bpf/test_run.c:1640
  __sys_bpf+0x1662/0x50b0             kernel/bpf/syscall.c:6267
  __x64_sys_bpf+0x73/0xb0             kernel/bpf/syscall.c:6360
  do_syscall_64+0xf1/0x530            arch/x86/entry/syscall_64.c:63
  entry_SYSCALL_64_after_hwframe+0x77  arch/x86/entry/entry_64.S:130
  </TASK>

Fix this by giving each VMA its own vma_list entry, following the
HugeTLB vma_lock pattern (hugetlb_vm_op_open). arena_vm_open() now
detects an inherited vm_private_data pointer via the vma_lock->vma !=
vma check, clears it, and allocates a fresh entry for the new VMA.
arena_vm_close() unconditionally removes and frees the entry. The
shared refcount is no longer needed and is removed.

Fixes: b90d77e5fd78 ("bpf: Fix remap of arena.")
Cc: stable@vger.kernel.org
Signed-off-by: Weiming Shi <bestswngs@gmail.com>
---
 kernel/bpf/arena.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index f355cf1c1a16..3a156ec473a8 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -317,7 +317,6 @@ static u64 arena_map_mem_usage(const struct bpf_map *map)
 struct vma_list {
 	struct vm_area_struct *vma;
 	struct list_head head;
-	refcount_t mmap_count;
 };
 
 static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
@@ -327,7 +326,6 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
 	vml = kmalloc_obj(*vml);
 	if (!vml)
 		return -ENOMEM;
-	refcount_set(&vml->mmap_count, 1);
 	vma->vm_private_data = vml;
 	vml->vma = vma;
 	list_add(&vml->head, &arena->vma_list);
@@ -336,9 +334,28 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
 
 static void arena_vm_open(struct vm_area_struct *vma)
 {
+	struct bpf_map *map = vma->vm_file->private_data;
+	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
 	struct vma_list *vml = vma->vm_private_data;
 
-	refcount_inc(&vml->mmap_count);
+	/*
+	 * If vm_private_data points to a vma_list for a different VMA, it was
+	 * inherited via vm_area_dup (fork or split). Clear it and allocate a
+	 * fresh entry for this VMA, following the HugeTLB vma_lock pattern.
+	 */
+	if (vml && vml->vma != vma)
+		vma->vm_private_data = NULL;
+
+	if (vma->vm_private_data)
+		return;
+
+	vml = kmalloc_obj(*vml);
+	if (!vml)
+		return;
+	vml->vma = vma;
+	vma->vm_private_data = vml;
+	guard(mutex)(&arena->lock);
+	list_add(&vml->head, &arena->vma_list);
 }
 
 static void arena_vm_close(struct vm_area_struct *vma)
@@ -347,10 +364,9 @@ static void arena_vm_close(struct vm_area_struct *vma)
 	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
 	struct vma_list *vml = vma->vm_private_data;
 
-	if (!refcount_dec_and_test(&vml->mmap_count))
+	if (!vml)
 		return;
 	guard(mutex)(&arena->lock);
-	/* update link list under lock */
 	list_del(&vml->head);
 	vma->vm_private_data = NULL;
 	kfree(vml);
-- 
2.43.0