From 080220b687147fd9376878534aba7194f17f6ef5 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 18 Sep 2018 10:13:59 -0700 Subject: tools: bpf: fix license for a compat header file libc_compat.h is used by libbpf so make sure it's licensed under LGPL or BSD license. The license change should be OK, I'm the only author of the file. Signed-off-by: Jakub Kicinski Reviewed-by: Quentin Monnet Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/include/tools/libc_compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h index 664ced8cb1b0..e907ba6f15e5 100644 --- a/tools/include/tools/libc_compat.h +++ b/tools/include/tools/libc_compat.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: (LGPL-2.0+ OR BSD-2-Clause) /* Copyright (C) 2018 Netronome Systems, Inc. */ #ifndef __TOOLS_LIBC_COMPAT_H -- cgit v1.2.3-59-g8ed1b From 5607fff303636d48b88414c6be353d9fed700af2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 18 Sep 2018 09:01:44 -0700 Subject: bpf: sockmap only allow ESTABLISHED sock state After this patch we only allow socks that are in ESTABLISHED state or are being added via a sock_ops event that is transitioning into an ESTABLISHED state. By allowing sock_ops events we allow users to manage sockmaps directly from sock ops programs. The two supported sock_ops ops are BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB and BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB. Similar to TLS ULP this ensures sk_user_data is correct. Reported-by: Eric Dumazet Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks") Signed-off-by: John Fastabend Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 488ef9663c01..1f97b559892a 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -2097,8 +2097,12 @@ static int sock_map_update_elem(struct bpf_map *map, return -EINVAL; } + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. + */ if (skops.sk->sk_type != SOCK_STREAM || - skops.sk->sk_protocol != IPPROTO_TCP) { + skops.sk->sk_protocol != IPPROTO_TCP || + skops.sk->sk_state != TCP_ESTABLISHED) { fput(socket->file); return -EOPNOTSUPP; } @@ -2453,6 +2457,16 @@ static int sock_hash_update_elem(struct bpf_map *map, return -EINVAL; } + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. + */ + if (skops.sk->sk_type != SOCK_STREAM || + skops.sk->sk_protocol != IPPROTO_TCP || + skops.sk->sk_state != TCP_ESTABLISHED) { + fput(socket->file); + return -EOPNOTSUPP; + } + lock_sock(skops.sk); preempt_disable(); rcu_read_lock(); @@ -2543,10 +2557,22 @@ const struct bpf_map_ops sock_hash_ops = { .map_check_btf = map_check_no_btf, }; +static bool bpf_is_valid_sock_op(struct bpf_sock_ops_kern *ops) +{ + return ops->op == BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB || + ops->op == BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB; +} BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); + + /* ULPs are currently supported only for TCP sockets in ESTABLISHED + * state. This checks that the sock ops triggering the update is + * one indicating we are (or will be soon) in an ESTABLISHED state. + */ + if (!bpf_is_valid_sock_op(bpf_sock)) + return -EOPNOTSUPP; return sock_map_ctx_update_elem(bpf_sock, map, key, flags); } @@ -2565,6 +2591,9 @@ BPF_CALL_4(bpf_sock_hash_update, struct bpf_sock_ops_kern *, bpf_sock, struct bpf_map *, map, void *, key, u64, flags) { WARN_ON_ONCE(!rcu_read_lock_held()); + + if (!bpf_is_valid_sock_op(bpf_sock)) + return -EOPNOTSUPP; return sock_hash_ctx_update_elem(bpf_sock, map, key, flags); } -- cgit v1.2.3-59-g8ed1b From b05545e15e1ff1d6a6a8593971275f9cc3e6b92b Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 18 Sep 2018 09:01:49 -0700 Subject: bpf: sockmap, fix transition through disconnect without close It is possible (via shutdown()) for TCP socks to go trough TCP_CLOSE state via tcp_disconnect() without actually calling tcp_close which would then call our bpf_tcp_close() callback. Because of this a user could disconnect a socket then put it in a LISTEN state which would break our assumptions about sockets always being ESTABLISHED state. To resolve this rely on the unhash hook, which is called in the disconnect case, to remove the sock from the sockmap. Reported-by: Eric Dumazet Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks") Signed-off-by: John Fastabend Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/bpf/sockmap.c | 60 +++++++++++++++++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 19 deletions(-) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 1f97b559892a..0a0f2ec75370 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -132,6 +132,7 @@ struct smap_psock { struct work_struct gc_work; struct proto *sk_proto; + void (*save_unhash)(struct sock *sk); void (*save_close)(struct sock *sk, long timeout); void (*save_data_ready)(struct sock *sk); void (*save_write_space)(struct sock *sk); @@ -143,6 +144,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); static int bpf_tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +static void bpf_tcp_unhash(struct sock *sk); static void bpf_tcp_close(struct sock *sk, long timeout); static inline struct smap_psock *smap_psock_sk(const struct sock *sk) @@ -184,6 +186,7 @@ static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS], struct proto *base) { prot[SOCKMAP_BASE] = *base; + prot[SOCKMAP_BASE].unhash = bpf_tcp_unhash; prot[SOCKMAP_BASE].close = bpf_tcp_close; prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg; prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read; @@ -217,6 +220,7 @@ static int bpf_tcp_init(struct sock *sk) return -EBUSY; } + psock->save_unhash = sk->sk_prot->unhash; psock->save_close = sk->sk_prot->close; psock->sk_proto = sk->sk_prot; @@ -305,30 +309,12 @@ static struct smap_psock_map_entry *psock_map_pop(struct sock *sk, return e; } -static void bpf_tcp_close(struct sock *sk, long timeout) +static void bpf_tcp_remove(struct sock *sk, struct smap_psock *psock) { - void (*close_fun)(struct sock *sk, long timeout); struct smap_psock_map_entry *e; struct sk_msg_buff *md, *mtmp; - struct smap_psock *psock; struct sock *osk; - lock_sock(sk); - rcu_read_lock(); - psock = smap_psock_sk(sk); - if (unlikely(!psock)) { - rcu_read_unlock(); - release_sock(sk); - return sk->sk_prot->close(sk, timeout); - } - - /* The psock may be destroyed anytime after exiting the RCU critial - * section so by the time we use close_fun the psock may no longer - * be valid. However, bpf_tcp_close is called with the sock lock - * held so the close hook and sk are still valid. - */ - close_fun = psock->save_close; - if (psock->cork) { free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); @@ -379,6 +365,42 @@ static void bpf_tcp_close(struct sock *sk, long timeout) kfree(e); e = psock_map_pop(sk, psock); } +} + +static void bpf_tcp_unhash(struct sock *sk) +{ + void (*unhash_fun)(struct sock *sk); + struct smap_psock *psock; + + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + if (sk->sk_prot->unhash) + sk->sk_prot->unhash(sk); + return; + } + unhash_fun = psock->save_unhash; + bpf_tcp_remove(sk, psock); + rcu_read_unlock(); + unhash_fun(sk); +} + +static void bpf_tcp_close(struct sock *sk, long timeout) +{ + void (*close_fun)(struct sock *sk, long timeout); + struct smap_psock *psock; + + lock_sock(sk); + rcu_read_lock(); + psock = smap_psock_sk(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + release_sock(sk); + return sk->sk_prot->close(sk, timeout); + } + close_fun = psock->save_close; + bpf_tcp_remove(sk, psock); rcu_read_unlock(); release_sock(sk); close_fun(sk, timeout); -- cgit v1.2.3-59-g8ed1b From 5028027844cfc6168e39650abecd817ba64c9d98 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 18 Sep 2018 09:01:54 -0700 Subject: bpf: test_maps, only support ESTABLISHED socks Ensure that sockets added to a sock{map|hash} that is not in the ESTABLISHED state is rejected. Fixes: 1aa12bdf1bfb ("bpf: sockmap, add sock close() hook to remove socks") Signed-off-by: John Fastabend Acked-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/test_maps.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 6f54f84144a0..9b552c0fc47d 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -580,7 +580,11 @@ static void test_sockmap(int tasks, void *data) /* Test update without programs */ for (i = 0; i < 6; i++) { err = bpf_map_update_elem(fd, &i, &sfd[i], BPF_ANY); - if (err) { + if (i < 2 && !err) { + printf("Allowed update sockmap '%i:%i' not in ESTABLISHED\n", + i, sfd[i]); + goto out_sockmap; + } else if (i >= 2 && err) { printf("Failed noprog update sockmap '%i:%i'\n", i, sfd[i]); goto out_sockmap; @@ -741,7 +745,7 @@ static void test_sockmap(int tasks, void *data) } /* Test map update elem afterwards fd lives in fd and map_fd */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_update_elem(map_fd_rx, &i, &sfd[i], BPF_ANY); if (err) { printf("Failed map_fd_rx update sockmap %i '%i:%i'\n", @@ -845,7 +849,7 @@ static void test_sockmap(int tasks, void *data) } /* Delete the elems without programs */ - for (i = 0; i < 6; i++) { + for (i = 2; i < 6; i++) { err = bpf_map_delete_elem(fd, &i); if (err) { printf("Failed delete sockmap %i '%i:%i'\n", -- cgit v1.2.3-59-g8ed1b