From 3046a827316c0e55fc563b4fb78c93b9ca5c7c37 Mon Sep 17 00:00:00 2001 From: Jon Maxwell Date: Wed, 15 Jun 2022 11:15:40 +1000 Subject: bpf: Fix request_sock leak in sk lookup helpers A customer reported a request_socket leak in a Calico cloud environment. We found that a BPF program was doing a socket lookup with takes a refcnt on the socket and that it was finding the request_socket but returning the parent LISTEN socket via sk_to_full_sk() without decrementing the child request socket 1st, resulting in request_sock slab object leak. This patch retains the existing behaviour of returning full socks to the caller but it also decrements the child request_socket if one is present before doing so to prevent the leak. Thanks to Curtis Taylor for all the help in diagnosing and testing this. And thanks to Antoine Tenart for the reproducer and patch input. v2 of this patch contains, refactor as per Daniel Borkmann's suggestions to validate RCU flags on the listen socket so that it balances with bpf_sk_release() and update comments as per Martin KaFai Lau's suggestion. One small change to Daniels suggestion, put "sk = sk2" under "if (sk2 != sk)" to avoid an extra instruction. Fixes: f7355a6c0497 ("bpf: Check sk_fullsock() before returning from bpf_sk_lookup()") Fixes: edbf8c01de5a ("bpf: add skc_lookup_tcp helper") Co-developed-by: Antoine Tenart Signed-off-by: Antoine Tenart Signed-off-by: Jon Maxwell Signed-off-by: Daniel Borkmann Tested-by: Curtis Taylor Cc: Martin KaFai Lau Link: https://lore.kernel.org/bpf/56d6f898-bde0-bb25-3427-12a330b29fb8@iogearbox.net Link: https://lore.kernel.org/bpf/20220615011540.813025-1-jmaxwell37@gmail.com --- net/core/filter.c | 34 ++++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index 5af58eb48587..5d16d66727fc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6516,10 +6516,21 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, ifindex, proto, netns_id, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } @@ -6553,10 +6564,21 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } -- cgit v1.2.3 From cc26c2661fefea215f41edb665193324a5f99021 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 16 Jun 2022 00:34:34 -0700 Subject: net: fix data-race in dev_isalive() dev_isalive() is called under RTNL or dev_base_lock protection. This means that changes to dev->reg_state should be done with both locks held. syzbot reported: BUG: KCSAN: data-race in register_netdevice / type_show write to 0xffff888144ecf518 of 1 bytes by task 20886 on cpu 0: register_netdevice+0xb9f/0xdf0 net/core/dev.c:10050 lapbeth_new_device drivers/net/wan/lapbether.c:414 [inline] lapbeth_device_event+0x4a0/0x6c0 drivers/net/wan/lapbether.c:456 notifier_call_chain kernel/notifier.c:87 [inline] raw_notifier_call_chain+0x53/0xb0 kernel/notifier.c:455 __dev_notify_flags+0x1d6/0x3a0 dev_change_flags+0xa2/0xc0 net/core/dev.c:8607 do_setlink+0x778/0x2230 net/core/rtnetlink.c:2780 __rtnl_newlink net/core/rtnetlink.c:3546 [inline] rtnl_newlink+0x114c/0x16a0 net/core/rtnetlink.c:3593 rtnetlink_rcv_msg+0x811/0x8c0 net/core/rtnetlink.c:6089 netlink_rcv_skb+0x13e/0x240 net/netlink/af_netlink.c:2501 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:6107 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x58a/0x660 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x661/0x750 net/netlink/af_netlink.c:1921 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg net/socket.c:734 [inline] __sys_sendto+0x21e/0x2c0 net/socket.c:2119 __do_sys_sendto net/socket.c:2131 [inline] __se_sys_sendto net/socket.c:2127 [inline] __x64_sys_sendto+0x74/0x90 net/socket.c:2127 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 read to 0xffff888144ecf518 of 1 bytes by task 20423 on cpu 1: dev_isalive net/core/net-sysfs.c:38 [inline] netdev_show net/core/net-sysfs.c:50 [inline] type_show+0x24/0x90 net/core/net-sysfs.c:112 dev_attr_show+0x35/0x90 drivers/base/core.c:2095 sysfs_kf_seq_show+0x175/0x240 fs/sysfs/file.c:59 kernfs_seq_show+0x75/0x80 fs/kernfs/file.c:162 seq_read_iter+0x2c3/0x8e0 fs/seq_file.c:230 kernfs_fop_read_iter+0xd1/0x2f0 fs/kernfs/file.c:235 call_read_iter include/linux/fs.h:2052 [inline] new_sync_read fs/read_write.c:401 [inline] vfs_read+0x5a5/0x6a0 fs/read_write.c:482 ksys_read+0xe8/0x1a0 fs/read_write.c:620 __do_sys_read fs/read_write.c:630 [inline] __se_sys_read fs/read_write.c:628 [inline] __x64_sys_read+0x3e/0x50 fs/read_write.c:628 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 value changed: 0x00 -> 0x01 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 20423 Comm: udevd Tainted: G W 5.19.0-rc2-syzkaller-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/core/dev.c | 25 +++++++++++++++---------- net/core/net-sysfs.c | 1 + 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/net/core/dev.c b/net/core/dev.c index 08ce317fcec8..8e6f22961206 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -397,16 +397,18 @@ static void list_netdevice(struct net_device *dev) /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ -static void unlist_netdevice(struct net_device *dev) +static void unlist_netdevice(struct net_device *dev, bool lock) { ASSERT_RTNL(); /* Unlink dev from the device chain */ - write_lock(&dev_base_lock); + if (lock) + write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - write_unlock(&dev_base_lock); + if (lock) + write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -10043,11 +10045,11 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) { - dev->reg_state = NETREG_UNREGISTERED; + write_lock(&dev_base_lock); + dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; + write_unlock(&dev_base_lock); + if (ret) goto err_uninit; - } - dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); @@ -10329,7 +10331,9 @@ void netdev_run_todo(void) continue; } + write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; + write_unlock(&dev_base_lock); linkwatch_forget_dev(dev); } @@ -10810,9 +10814,10 @@ void unregister_netdevice_many(struct list_head *head) list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ - unlist_netdevice(dev); - + write_lock(&dev_base_lock); + unlist_netdevice(dev, false); dev->reg_state = NETREG_UNREGISTERING; + write_unlock(&dev_base_lock); } flush_all_backlogs(); @@ -10959,7 +10964,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_close(dev); /* And unlink it from device chain */ - unlist_netdevice(dev); + unlist_netdevice(dev, true); synchronize_net(); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e319e242dddf..a3642569fe53 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -33,6 +33,7 @@ static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; +/* Caller holds RTNL or dev_base_lock */ static inline int dev_isalive(const struct net_device *dev) { return dev->reg_state <= NETREG_REGISTERED; -- cgit v1.2.3 From e34a07c0ae3906f97eb18df50902e2a01c1015b6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 20 Jun 2022 12:13:53 -0700 Subject: sock: redo the psock vs ULP protection check Commit 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") has moved the inet_csk_has_ulp(sk) check from sk_psock_init() to the new tcp_bpf_update_proto() function. I'm guessing that this was done to allow creating psocks for non-inet sockets. Unfortunately the destruction path for psock includes the ULP unwind, so we need to fail the sk_psock_init() itself. Otherwise if ULP is already present we'll notice that later, and call tcp_update_ulp() with the sk_proto of the ULP itself, which will most likely result in the ULP looping its callbacks. Fixes: 8a59f9d1e3d4 ("sock: Introduce sk->sk_prot->psock_update_sk_prot()") Signed-off-by: Jakub Kicinski Reviewed-by: John Fastabend Reviewed-by: Jakub Sitnicki Tested-by: Jakub Sitnicki Link: https://lore.kernel.org/r/20220620191353.1184629-2-kuba@kernel.org Signed-off-by: Paolo Abeni --- include/net/inet_sock.h | 5 +++++ net/core/skmsg.c | 5 +++++ net/ipv4/tcp_bpf.c | 3 --- net/tls/tls_main.c | 2 ++ 4 files changed, 12 insertions(+), 3 deletions(-) (limited to 'net/core') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c1b5dcd6597c..daead5fb389a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -253,6 +253,11 @@ struct inet_sock { #define IP_CMSG_CHECKSUM BIT(7) #define IP_CMSG_RECVFRAGSIZE BIT(8) +static inline bool sk_is_inet(struct sock *sk) +{ + return sk->sk_family == AF_INET || sk->sk_family == AF_INET6; +} + /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 22b983ade0e7..b0fcd0200e84 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -699,6 +699,11 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) write_lock_bh(&sk->sk_callback_lock); + if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) { + psock = ERR_PTR(-EINVAL); + goto out; + } + if (sk->sk_user_data) { psock = ERR_PTR(-EBUSY); goto out; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index be3947e70fec..0d3f68bb51c0 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -611,9 +611,6 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) return 0; } - if (inet_csk_has_ulp(sk)) - return -EINVAL; - if (sk->sk_family == AF_INET6) { if (tcp_bpf_assert_proto_ops(psock->sk_proto)) return -EINVAL; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index da176411c1b5..2ffede463e4a 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -921,6 +921,8 @@ static void tls_update(struct sock *sk, struct proto *p, { struct tls_context *ctx; + WARN_ON_ONCE(sk->sk_prot == p); + ctx = tls_get_ctx(sk); if (likely(ctx)) { ctx->sk_write_space = write_space; -- cgit v1.2.3