[PATCH bpf 0/2] bpf: Fix arena VMA use-after-free on fork

[PATCH bpf 0/2] bpf: Fix arena VMA use-after-free on fork

[Weiming Shi]

arena_vm_open() only increments a refcount on the shared vma_list entry
but never registers the new VMA. After fork + parent munmap, vml->vma
becomes a dangling pointer. bpf_arena_free_pages -> zap_pages then
dereferences it, causing a slab-use-after-free in zap_page_range_single.

Patch 1 fixes the bug by giving each VMA its own vma_list entry,
following the HugeTLB vma_lock pattern (hugetlb_vm_op_open).
Patch 2 adds a selftest that reproduces the issue.

Weiming Shi (2):
  bpf: Fix use-after-free of arena VMA on fork
  selftests/bpf: Add test for arena VMA use-after-free on fork

 kernel/bpf/arena.c                            | 26 ++++--
 .../selftests/bpf/prog_tests/arena_fork.c     | 86 +++++++++++++++++++
 .../testing/selftests/bpf/progs/arena_fork.c  | 41 +++++++++
 3 files changed, 148 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_fork.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_fork.c

-- 
2.43.0

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

[Weiming Shi]

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

[PATCH bpf 2/2] selftests/bpf: Add test for arena VMA use-after-free on fork

[Weiming Shi]

Add a selftest that reproduces the arena VMA use-after-free fixed in
the previous commit. The test creates an arena, mmaps it, allocates
pages via BPF, forks, has the parent munmap the arena, then has the
child call bpf_arena_free_pages. Without the fix this triggers a
KASAN slab-use-after-free in zap_page_range_single.

Signed-off-by: Weiming Shi <bestswngs@gmail.com>
---
 .../selftests/bpf/prog_tests/arena_fork.c     | 86 +++++++++++++++++++
 .../testing/selftests/bpf/progs/arena_fork.c  | 41 +++++++++
 2 files changed, 127 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_fork.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_fork.c

diff --git a/tools/testing/selftests/bpf/prog_tests/arena_fork.c b/tools/testing/selftests/bpf/prog_tests/arena_fork.c
new file mode 100644
index 000000000000..445574827891
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/arena_fork.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 */
+
+/*
+ * Test that forking a process with an arena mmap does not cause a
+ * use-after-free when the parent unmaps and the child frees arena pages.
+ *
+ * The bug: arena_vm_open() only incremented a refcount but never registered
+ * the child's VMA. After parent munmap, vml->vma pointed to a freed
+ * vm_area_struct. bpf_arena_free_pages -> zap_pages would then UAF.
+ */
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include <sys/user.h>
+#ifndef PAGE_SIZE
+#define PAGE_SIZE getpagesize()
+#endif
+
+#include "arena_fork.skel.h"
+
+void test_arena_fork(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, opts);
+	struct bpf_map_info info = {};
+	__u32 info_len = sizeof(info);
+	struct arena_fork *skel;
+	size_t arena_sz;
+	void *arena_addr;
+	int arena_fd, ret, status;
+	pid_t pid;
+
+	skel = arena_fork__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	arena_fd = bpf_map__fd(skel->maps.arena);
+
+	/* libbpf mmaps the arena via initial_value */
+	arena_addr = bpf_map__initial_value(skel->maps.arena, &arena_sz);
+	if (!ASSERT_OK_PTR(arena_addr, "arena_mmap"))
+		goto out;
+
+	/* Get real arena byte size for munmap */
+	bpf_map_get_info_by_fd(arena_fd, &info, &info_len);
+	arena_sz = (size_t)info.max_entries * PAGE_SIZE;
+
+	/* Allocate 4 pages in the arena via BPF */
+	ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.arena_alloc),
+				     &opts);
+	if (!ASSERT_OK(ret, "alloc_run") ||
+	    !ASSERT_OK(opts.retval, "alloc_ret"))
+		goto out;
+
+	/* Fault in a page so zap_pages has work to do */
+	((char *)arena_addr)[0] = 'A';
+
+	/* Fork: child inherits the arena VMA */
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		goto out;
+
+	if (pid == 0) {
+		/* Child: parent will unmap first, then we free pages.
+		 * Without the fix, this triggers UAF in zap_pages.
+		 */
+		LIBBPF_OPTS(bpf_test_run_opts, child_opts);
+		int free_fd = bpf_program__fd(skel->progs.arena_free);
+
+		usleep(200000); /* let parent munmap first */
+
+		ret = bpf_prog_test_run_opts(free_fd, &child_opts);
+		_exit(ret || child_opts.retval);
+	}
+
+	/* Parent: unmap the arena, making vml->vma stale */
+	munmap(arena_addr, arena_sz);
+
+	/* Wait for child -- if kernel UAFs, child will crash/hang */
+	waitpid(pid, &status, 0);
+	ASSERT_TRUE(WIFEXITED(status), "child_exited");
+	ASSERT_EQ(WEXITSTATUS(status), 0, "child_exit_code");
+out:
+	arena_fork__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/arena_fork.c b/tools/testing/selftests/bpf/progs/arena_fork.c
new file mode 100644
index 000000000000..b1f8435f1834
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/arena_fork.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_arena_common.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARENA);
+	__uint(map_flags, BPF_F_MMAPABLE);
+	__uint(max_entries, 16); /* number of pages */
+#ifdef __TARGET_ARCH_arm64
+	__ulong(map_extra, 0x1ull << 32); /* start of mmap() region */
+#else
+	__ulong(map_extra, 0x1ull << 44); /* start of mmap() region */
+#endif
+} arena SEC(".maps");
+
+void __arena *alloc_addr;
+
+SEC("syscall")
+int arena_alloc(void *ctx)
+{
+	void __arena *p;
+
+	p = bpf_arena_alloc_pages(&arena, NULL, 4, NUMA_NO_NODE, 0);
+	if (!p)
+		return 1;
+	alloc_addr = p;
+	return 0;
+}
+
+SEC("syscall")
+int arena_free(void *ctx)
+{
+	if (!alloc_addr)
+		return 1;
+	bpf_arena_free_pages(&arena, alloc_addr, 4);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.43.0