ugh, sry for missing subject
On Wed, Oct 30, 2019 at 04:43:23PM +0100, Jiri Olsa wrote:
>
> hi,
> I'm getting oops when running the kfree_skb test:
>
> dell-r440-01 login: [ 758.049877] BUG: kernel NULL pointer dereference, address: 0000000000000000^M
> [ 758.056834] #PF: supervisor read access in kernel mode^M
> [ 758.061975] #PF: error_code(0x0000) - not-present page^M
> [ 758.067112] PGD 8000000befba8067 P4D 8000000befba8067 PUD bffe11067 PMD 0 ^M
> [ 758.073987] Oops: 0000 [#1] SMP PTI^M
> [ 758.077478] CPU: 16 PID: 6854 Comm: test_progs Not tainted 5.4.0-rc3+ #96^M
> [ 758.084263] Hardware name: Dell Inc. PowerEdge R440/08CYF7, BIOS 1.7.0 12/14/2018^M
> [ 758.091745] RIP: 0010:0xffffffffc03b672c^M
> [ 758.095669] Code: 4c 8b 6a 00 4c 89 6d c0 8b 77 00 89 75 cc 31 ff 89 75 fc 48 8b 71 00 48 01 fe bf 78 00 00 00 48 89 da 48 01 fa bf 08 00 00 00 <4c> 8b 76 00 4c 89 f6 48 01 fe 4c 8b 7e 00 48 89 ef 48 83 c7 f9 be^M
> [ 758.114414] RSP: 0018:ffffaa3287583d20 EFLAGS: 00010286^M
> [ 758.119640] RAX: ffffffffc03b66ac RBX: ffff9cef028c3900 RCX: ffff9cef0a652018^M
> [ 758.126775] RDX: ffff9cef028c3978 RSI: 0000000000000000 RDI: 0000000000000008^M
> [ 758.133906] RBP: ffffaa3287583d90 R08: 00000000000000b0 R09: 0000000000000000^M
> [ 758.141040] R10: 98ff036c00000000 R11: 0000000000000040 R12: ffffffffba8b5c37^M
> [ 758.148170] R13: ffff9cfb05daf440 R14: 0000000000000000 R15: 000000000000004a^M
> [ 758.155303] FS: 00007f08a18d3740(0000) GS:ffff9cef10c00000(0000) knlGS:0000000000000000^M
> [ 758.163392] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033^M
> [ 758.169136] CR2: 0000000000000000 CR3: 0000000c08e50001 CR4: 00000000007606e0^M
> [ 758.176268] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000^M
> [ 758.183401] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400^M
> [ 758.190534] PKRU: 55555554^M
> [ 758.193248] Call Trace:^M
> [ 758.195704] ? bpf_test_run+0x13d/0x230^M
> [ 758.199539] ? _cond_resched+0x15/0x30^M
> [ 758.203304] bpf_trace_run2+0x37/0x90^M
> [ 758.206967] ? bpf_prog_test_run_skb+0x337/0x450^M
> [ 758.211589] kfree_skb+0x73/0xa0^M
> [ 758.214820] bpf_prog_test_run_skb+0x337/0x450^M
> [ 758.219293] __do_sys_bpf+0x82e/0x1730^M
> [ 758.223043] ? ep_show_fdinfo+0x80/0x80^M
> [ 758.226885] do_syscall_64+0x5b/0x180^M
> [ 758.230550] entry_SYSCALL_64_after_hwframe+0x44/0xa9^M
> [ 758.235620] RIP: 0033:0x7f08a19e91fd^M
> [ 758.239198] Code: 00 c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 5b 8c 0c 00 f7 d8 64 89 01 48^M
>
>
> this seems to be the culprit:
>
> ; ptr = dev->ifalias->rcuhead.next;
> 80: mov 0x0(%rsi),%r14
>
> I used the patch below to bypass the crash, but I guess
> verifier should not let this through
>
> also the net_device struct in the test seems outdated
>
> thanks,
> jirka
>
>
> ---
> tools/testing/selftests/bpf/progs/kfree_skb.c | 15 +++++++--------
> 1 file changed, 7 insertions(+), 8 deletions(-)
>
> diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
> index 89af8a921ee4..64d8c0237186 100644
> --- a/tools/testing/selftests/bpf/progs/kfree_skb.c
> +++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
> @@ -3,6 +3,7 @@
> #include <linux/bpf.h>
> #include "bpf_helpers.h"
> #include "bpf_endian.h"
> +#include "bpf_core_read.h"
>
> char _license[] SEC("license") = "GPL";
> struct {
> @@ -70,14 +71,12 @@ int trace_kfree_skb(struct trace_kfree_skb *ctx)
> unsigned short pkt_data;
> char pkt_type;
>
> - __builtin_preserve_access_index(({
> - users = skb->users.refs.counter;
> - data = skb->data;
> - dev = skb->dev;
> - ifindex = dev->ifindex;
> - ptr = dev->ifalias->rcuhead.next;
> - func = ptr->func;
> - }));
> + users = BPF_CORE_READ(skb, users.refs.counter);
> + data = BPF_CORE_READ(skb, data);
> + dev = BPF_CORE_READ(skb, dev);
> + ifindex = BPF_CORE_READ(dev, ifindex);
> + ptr = BPF_CORE_READ(dev, ifalias, rcuhead.next);
> + func = BPF_CORE_READ(ptr, func);
>
> bpf_probe_read(&pkt_type, sizeof(pkt_type), _(&skb->__pkt_type_offset));
> pkt_type &= 7;
> --
> 2.21.0
>
