bpf, sockmap: Reject sk_msg egress redirects to non-TCP sockets
Subsystems (5)
Jakub Sitnicki
maintainerPATCH 1/1 bpf, sockmap: Reject sk_msg egress redirects to non-TCP sockets
With a SOCKMAP/SOCKHASH map and an sk_msg program user can steer messages sent from one TCP socket (s1) to actually egress from another TCP socket (s2):
tcp_bpf_sendmsg(s1) // = sk_prot->sendmsg
tcp_bpf_send_verdict(s1) // __SK_REDIRECT case
tcp_bpf_sendmsg_redir(s2)
tcp_bpf_push_locked(s2)
tcp_bpf_push(s2)
tcp_rate_check_app_limited(s2) // expects tcp_sock
tcp_sendmsg_locked(s2) // ditto
There is a hard-coded assumption in the call-chain, that the egress socket (s2) is a TCP socket.
However in commit 122e6c79efe1 ("sock_map: Update sock type checks for UDP") we have enabled redirects to non-TCP sockets. This was done for the sake of BPF sk_skb programs. There was no indention to support sk_msg send-to-egress use case.
As a result, attempts to send-to-egress through a non-TCP socket lead to a crash due to invalid downcast from sock to tcp_sock:
BUG: kernel NULL pointer dereference, address: 000000000000002f ... Call Trace: <TASK> ? show_regs+0x60/0x70 ? __die+0x1f/0x70 ? page_fault_oops+0x80/0x160 ? do_user_addr_fault+0x2d7/0x800 ? rcu_is_watching+0x11/0x50 ? exc_page_fault+0x70/0x1c0 ? asm_exc_page_fault+0x27/0x30 ? tcp_tso_segs+0x14/0xa0 tcp_write_xmit+0x67/0xce0 __tcp_push_pending_frames+0x32/0xf0 tcp_push+0x107/0x140 tcp_sendmsg_locked+0x99f/0xbb0 tcp_bpf_push+0x19d/0x3a0 tcp_bpf_sendmsg_redir+0x55/0xd0 tcp_bpf_send_verdict+0x407/0x550 tcp_bpf_sendmsg+0x1a1/0x390 inet_sendmsg+0x6a/0x70 sock_sendmsg+0x9d/0xc0 ? sockfd_lookup_light+0x12/0x80 __sys_sendto+0x10e/0x160 ? syscall_enter_from_user_mode+0x20/0x60 ? __this_cpu_preempt_check+0x13/0x20 ? lockdep_hardirqs_on+0x82/0x110 __x64_sys_sendto+0x1f/0x30 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd
Reject selecting a non-TCP sockets as redirect target from a BPF sk_msg program to prevent the crash. When attempted, user will receive an EACCES error from send/sendto/sendmsg() syscall.
---
FYI, I'm working on revamping the sockmap_listen selftest, which exercises some of redirect combinations, to cover the whole combination matrix so that we can catch these kinds of problems early on.
net/core/sock_map.c | 4 ++++ 1 file changed, 4 insertions(+)
net/core/sock_map.c +4 -0
@@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk =__sock_map_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;
@@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk =__sock_hash_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;
Signature · 1 line
2.41.0
Quoted 15 lines · Jakub Sitnicki
net/core/sock_map.c +2
-0@@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk =__sock_map_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;
net/core/sock_map.c BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, · line 1276
Quoted 8 lines
net/core/sock_map.c +2
-0@@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk =__sock_hash_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;
Just be curious! Can it happen to other socket types?
I mean to redirect a msg from a sk of any type to one of another type.
Jakub Sitnicki
maintainerQuoted 16 lines · Kui-Feng Lee
Quoted 15 lines · Jakub Sitnicki
net/core/sock_map.c +2
-0@@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk =__sock_map_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;@@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk =__sock_hash_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))
Quoted 8 lines
net/core/sock_map.c BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, · line 675
Quoted 5 lines
net/core/sock_map.c +2
-0return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;Just be curious! Can it happen to other socket types?
I mean to redirect a msg from a sk of any type to one of another type.
Today sk_msg redirects are implemented only for tcp4 and tcp6.
Here's a full matrix of what redirects are supported [1].
[1] https://gist.github.com/jsitnicki/578fdd614d181bed2b02922b17972b4e
Quoted 26 lines · Jakub Sitnicki
Quoted 16 lines · Kui-Feng Lee
Quoted 15 lines · Jakub Sitnicki
net/core/sock_map.c +2
-0@@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk =__sock_map_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;@@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk =__sock_hash_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))Quoted 8 lines
net/core/sock_map.c BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, · line 675
Quoted 5 lines
net/core/sock_map.c +2
-0return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;Just be curious! Can it happen to other socket types?
I mean to redirect a msg from a sk of any type to one of another type.
Quoted 5 lines
Today
sk_msgredirects are implemented only for tcp4 and tcp6.Here's a full matrix of what redirects are supported [1].
[1] https://gist.github.com/jsitnicki/578fdd614d181bed2b02922b17972b4e
Thanks!
Quoted 58 lines · Jakub Sitnicki
With a SOCKMAP/SOCKHASH map and an
sk_msgprogram user can steer messages sent from one TCP socket (s1) to actually egress from another TCP socket (s2):
tcp_bpf_sendmsg(s1)// =sk_prot->sendmsg
tcp_bpf_send_verdict(s1)//__SK_REDIRECTcase
tcp_bpf_sendmsg_redir(s2)
tcp_bpf_push_locked(s2)
tcp_bpf_push(s2)
tcp_rate_check_app_limited(s2)// expectstcp_sock
tcp_sendmsg_locked(s2)// dittoThere is a hard-coded assumption in the call-chain, that the egress socket (s2) is a TCP socket.
However in commit
122e6c79efe1("sock_map: Update sock type checks for UDP") we have enabled redirects to non-TCP sockets. This was done for the sake of BPFsk_skbprograms. There was no indention to supportsk_msgsend-to-egress use case.As a result, attempts to send-to-egress through a non-TCP socket lead to a crash due to invalid downcast from sock to
tcp_sock:BUG: kernel NULL pointer dereference, address: 000000000000002f ... Call Trace: <TASK> ? show_regs+0x60/0x70 ? __die+0x1f/0x70 ? page_fault_oops+0x80/0x160 ? do_user_addr_fault+0x2d7/0x800 ? rcu_is_watching+0x11/0x50 ? exc_page_fault+0x70/0x1c0 ? asm_exc_page_fault+0x27/0x30 ? tcp_tso_segs+0x14/0xa0 tcp_write_xmit+0x67/0xce0 __tcp_push_pending_frames+0x32/0xf0 tcp_push+0x107/0x140 tcp_sendmsg_locked+0x99f/0xbb0 tcp_bpf_push+0x19d/0x3a0 tcp_bpf_sendmsg_redir+0x55/0xd0 tcp_bpf_send_verdict+0x407/0x550 tcp_bpf_sendmsg+0x1a1/0x390 inet_sendmsg+0x6a/0x70 sock_sendmsg+0x9d/0xc0 ? sockfd_lookup_light+0x12/0x80 __sys_sendto+0x10e/0x160 ? syscall_enter_from_user_mode+0x20/0x60 ? __this_cpu_preempt_check+0x13/0x20 ? lockdep_hardirqs_on+0x82/0x110 __x64_sys_sendto+0x1f/0x30 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcdReject selecting a non-TCP sockets as redirect target from a BPF
sk_msgprogram to prevent the crash. When attempted, user will receive an EACCES error from send/sendto/sendmsg() syscall.
Quoted 6 lines
Fixes 122e6c79efe1 ("sock_map: Update sock type checks for UDP")Signed-off-by Jakub Sitnicki <[email protected]>---
FYI, I'm working on revamping thesockmap_listenselftest, which exercises some of redirect combinations, to cover the whole combination matrix so that we can catch these kinds of problems early on.
Yes this would be appreciated.
Quoted 18 lines
net/core/sock_map.c | 4 ++++ 1 file changed, 4 insertions(+)net/core/sock_map.c +2
-0@@ -668,6 +668,8 @@ BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg *, msg, sk =__sock_map_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ; msg->flags = flags; msg->sk_redir = sk;
net/core/sock_map.c BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, · line 1273
Quoted 5 lines
net/core/sock_map.c +2
-0@@ -1267,6 +1269,8 @@ BPF_CALL_4(bpf_msg_redirect_hash, struct sk_msg *, msg, sk =__sock_hash_lookup_elem (map, key);if (unlikely (!sk || !sock_map_redirect_allowed (sk)))return SK_DROP ; +if (!(flags &BPF_F_INGRESS ) && !sk_is_tcp (sk)) +return SK_DROP ;
As a stop gap I think this is fine. If anyone wants to add support though I do think as a use case it would make sense to redirect TCP into an AF_UNIX socket and vice versa.
This patch was applied to bpf/bpf.git (master) by Daniel Borkmann <[email protected]>:
Hello:
This patch was applied to bpf/bpf.git (master)
by Daniel Borkmann <[email protected]>:
Quoted 12 lines · On Wed, 20 Sep 2023 12:20:55 +0200 you wrote:
With a SOCKMAP/SOCKHASH map and an
sk_msgprogram user can steer messages sent from one TCP socket (s1) to actually egress from another TCP socket (s2):
tcp_bpf_sendmsg(s1)// =sk_prot->sendmsg
tcp_bpf_send_verdict(s1)//__SK_REDIRECTcase
tcp_bpf_sendmsg_redir(s2)
tcp_bpf_push_locked(s2)
tcp_bpf_push(s2)
tcp_rate_check_app_limited(s2)// expectstcp_sock
tcp_sendmsg_locked(s2)// ditto
Quoted 1 line
[...]
Here is the summary with links:
- [bpf] bpf, sockmap: Reject sk_msg egress redirects to non-TCP sockets
https://git.kernel.org/bpf/bpf/c/b80e31baa436
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html