commit d3fd203f36d46aa29600a72d57a1b61af80e4a25 upstream. We got a syzkaller problem because of aarch64 alignment fault if KFENCE enabled. When the size from user bpf program is an odd number, like 399, 407, etc, it will cause the struct skb_shared_info's unaligned access. As seen below: BUG: KFENCE: use-after-free read in __skb_clone+0x23c/0x2a0 net/core/skbuff.c:1032 Use-after-free read at 0xffff6254fffac077 (in kfence-#213): __lse_atomic_add arch/arm64/include/asm/atomic_lse.h:26 [inline] arch_atomic_add arch/arm64/include/asm/atomic.h:28 [inline] arch_atomic_inc include/linux/atomic-arch-fallback.h:270 [inline] atomic_inc include/asm-generic/atomic-instrumented.h:241 [inline] __skb_clone+0x23c/0x2a0 net/core/skbuff.c:1032 skb_clone+0xf4/0x214 net/core/skbuff.c:1481 ____bpf_clone_redirect net/core/filter.c:2433 [inline] bpf_clone_redirect+0x78/0x1c0 net/core/filter.c:2420 bpf_prog_d3839dd9068ceb51+0x80/0x330 bpf_dispatcher_nop_func include/linux/bpf.h:728 [inline] bpf_test_run+0x3c0/0x6c0 net/bpf/test_run.c:53 bpf_prog_test_run_skb+0x638/0xa7c net/bpf/test_run.c:594 bpf_prog_test_run kernel/bpf/syscall.c:3148 [inline] __do_sys_bpf kernel/bpf/syscall.c:4441 [inline] __se_sys_bpf+0xad0/0x1634 kernel/bpf/syscall.c:4381 kfence-#213: 0xffff6254fffac000-0xffff6254fffac196, size=407, cache=kmalloc-512 allocated by task 15074 on cpu 0 at 1342.585390s: kmalloc include/linux/slab.h:568 [inline] kzalloc include/linux/slab.h:675 [inline] bpf_test_init.isra.0+0xac/0x290 net/bpf/test_run.c:191 bpf_prog_test_run_skb+0x11c/0xa7c net/bpf/test_run.c:512 bpf_prog_test_run kernel/bpf/syscall.c:3148 [inline] __do_sys_bpf kernel/bpf/syscall.c:4441 [inline] __se_sys_bpf+0xad0/0x1634 kernel/bpf/syscall.c:4381 __arm64_sys_bpf+0x50/0x60 kernel/bpf/syscall.c:4381 To fix the problem, we adjust @size so that (@size + @hearoom) is a multiple of SMP_CACHE_BYTES. So we make sure the struct skb_shared_info is aligned to a cache line. Fixes: 1cf1cae963c2 ("bpf: introduce BPF_PROG_TEST_RUN command") Signed-off-by: Baisong Zhong <zhongbaisong@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Eric Dumazet <edumazet@google.com> Link: https://lore.kernel.org/bpf/20221102081620.1465154-1-zhongbaisong@huawei.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
201 lines
5.1 KiB
C
201 lines
5.1 KiB
C
/* Copyright (c) 2017 Facebook
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of version 2 of the GNU General Public
|
|
* License as published by the Free Software Foundation.
|
|
*/
|
|
#include <linux/bpf.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/etherdevice.h>
|
|
#include <linux/filter.h>
|
|
#include <linux/sched/signal.h>
|
|
|
|
static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
|
|
struct bpf_cgroup_storage *storage)
|
|
{
|
|
u32 ret;
|
|
|
|
preempt_disable();
|
|
rcu_read_lock();
|
|
bpf_cgroup_storage_set(storage);
|
|
ret = BPF_PROG_RUN(prog, ctx);
|
|
rcu_read_unlock();
|
|
preempt_enable();
|
|
|
|
return ret;
|
|
}
|
|
|
|
static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
|
|
{
|
|
struct bpf_cgroup_storage *storage = NULL;
|
|
u64 time_start, time_spent = 0;
|
|
u32 ret = 0, i;
|
|
|
|
storage = bpf_cgroup_storage_alloc(prog);
|
|
if (IS_ERR(storage))
|
|
return PTR_ERR(storage);
|
|
|
|
if (!repeat)
|
|
repeat = 1;
|
|
time_start = ktime_get_ns();
|
|
for (i = 0; i < repeat; i++) {
|
|
ret = bpf_test_run_one(prog, ctx, storage);
|
|
if (need_resched()) {
|
|
if (signal_pending(current))
|
|
break;
|
|
time_spent += ktime_get_ns() - time_start;
|
|
cond_resched();
|
|
time_start = ktime_get_ns();
|
|
}
|
|
}
|
|
time_spent += ktime_get_ns() - time_start;
|
|
do_div(time_spent, repeat);
|
|
*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
|
|
|
|
bpf_cgroup_storage_free(storage);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int bpf_test_finish(const union bpf_attr *kattr,
|
|
union bpf_attr __user *uattr, const void *data,
|
|
u32 size, u32 retval, u32 duration)
|
|
{
|
|
void __user *data_out = u64_to_user_ptr(kattr->test.data_out);
|
|
int err = -EFAULT;
|
|
|
|
if (data_out && copy_to_user(data_out, data, size))
|
|
goto out;
|
|
if (copy_to_user(&uattr->test.data_size_out, &size, sizeof(size)))
|
|
goto out;
|
|
if (copy_to_user(&uattr->test.retval, &retval, sizeof(retval)))
|
|
goto out;
|
|
if (copy_to_user(&uattr->test.duration, &duration, sizeof(duration)))
|
|
goto out;
|
|
err = 0;
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
|
|
u32 headroom, u32 tailroom)
|
|
{
|
|
void __user *data_in = u64_to_user_ptr(kattr->test.data_in);
|
|
void *data;
|
|
|
|
if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom)
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
size = SKB_DATA_ALIGN(size);
|
|
data = kzalloc(size + headroom + tailroom, GFP_USER);
|
|
if (!data)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
if (copy_from_user(data + headroom, data_in, size)) {
|
|
kfree(data);
|
|
return ERR_PTR(-EFAULT);
|
|
}
|
|
return data;
|
|
}
|
|
|
|
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
|
|
union bpf_attr __user *uattr)
|
|
{
|
|
bool is_l2 = false, is_direct_pkt_access = false;
|
|
u32 size = kattr->test.data_size_in;
|
|
u32 repeat = kattr->test.repeat;
|
|
u32 retval, duration;
|
|
int hh_len = ETH_HLEN;
|
|
struct sk_buff *skb;
|
|
void *data;
|
|
int ret;
|
|
|
|
data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
|
|
SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
|
|
if (IS_ERR(data))
|
|
return PTR_ERR(data);
|
|
|
|
switch (prog->type) {
|
|
case BPF_PROG_TYPE_SCHED_CLS:
|
|
case BPF_PROG_TYPE_SCHED_ACT:
|
|
is_l2 = true;
|
|
/* fall through */
|
|
case BPF_PROG_TYPE_LWT_IN:
|
|
case BPF_PROG_TYPE_LWT_OUT:
|
|
case BPF_PROG_TYPE_LWT_XMIT:
|
|
is_direct_pkt_access = true;
|
|
break;
|
|
default:
|
|
break;
|
|
}
|
|
|
|
skb = build_skb(data, 0);
|
|
if (!skb) {
|
|
kfree(data);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
|
|
__skb_put(skb, size);
|
|
skb->protocol = eth_type_trans(skb, current->nsproxy->net_ns->loopback_dev);
|
|
skb_reset_network_header(skb);
|
|
|
|
if (is_l2)
|
|
__skb_push(skb, hh_len);
|
|
if (is_direct_pkt_access)
|
|
bpf_compute_data_pointers(skb);
|
|
retval = bpf_test_run(prog, skb, repeat, &duration);
|
|
if (!is_l2) {
|
|
if (skb_headroom(skb) < hh_len) {
|
|
int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
|
|
|
|
if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
|
|
kfree_skb(skb);
|
|
return -ENOMEM;
|
|
}
|
|
}
|
|
memset(__skb_push(skb, hh_len), 0, hh_len);
|
|
}
|
|
|
|
size = skb->len;
|
|
/* bpf program can never convert linear skb to non-linear */
|
|
if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
|
|
size = skb_headlen(skb);
|
|
ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
|
|
kfree_skb(skb);
|
|
return ret;
|
|
}
|
|
|
|
int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
|
|
union bpf_attr __user *uattr)
|
|
{
|
|
u32 size = kattr->test.data_size_in;
|
|
u32 repeat = kattr->test.repeat;
|
|
struct netdev_rx_queue *rxqueue;
|
|
struct xdp_buff xdp = {};
|
|
u32 retval, duration;
|
|
void *data;
|
|
int ret;
|
|
|
|
data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
|
|
if (IS_ERR(data))
|
|
return PTR_ERR(data);
|
|
|
|
xdp.data_hard_start = data;
|
|
xdp.data = data + XDP_PACKET_HEADROOM + NET_IP_ALIGN;
|
|
xdp.data_meta = xdp.data;
|
|
xdp.data_end = xdp.data + size;
|
|
|
|
rxqueue = __netif_get_rx_queue(current->nsproxy->net_ns->loopback_dev, 0);
|
|
xdp.rxq = &rxqueue->xdp_rxq;
|
|
|
|
retval = bpf_test_run(prog, &xdp, repeat, &duration);
|
|
if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN ||
|
|
xdp.data_end != xdp.data + size)
|
|
size = xdp.data_end - xdp.data;
|
|
ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration);
|
|
kfree(data);
|
|
return ret;
|
|
}
|